diff options
249 files changed, 3034 insertions, 1626 deletions
@@ -223,6 +223,8 @@ Dmitry Safonov <0x7f454c46@gmail.com> <d.safonov@partner.samsung.com> Dmitry Safonov <0x7f454c46@gmail.com> <dsafonov@virtuozzo.com> Domen Puncer <domen@coderock.org> Douglas Gilbert <dougg@torque.net> +Drew Fustini <fustini@kernel.org> <drew@pdp7.com> +<duje@dujemihanovic.xyz> <duje.mihanovic@skole.hr> Ed L. Cashin <ecashin@coraid.com> Elliot Berman <quic_eberman@quicinc.com> <eberman@codeaurora.org> Enric Balletbo i Serra <eballetbo@kernel.org> <enric.balletbo@collabora.com> @@ -830,3 +832,6 @@ Yosry Ahmed <yosry.ahmed@linux.dev> <yosryahmed@google.com> Yusuke Goda <goda.yusuke@renesas.com> Zack Rusin <zack.rusin@broadcom.com> <zackr@vmware.com> Zhu Yanjun <zyjzyj2000@gmail.com> <yanjunz@nvidia.com> +Zijun Hu <zijun.hu@oss.qualcomm.com> <quic_zijuhu@quicinc.com> +Zijun Hu <zijun.hu@oss.qualcomm.com> <zijuhu@codeaurora.org> +Zijun Hu <zijun_hu@htc.com> @@ -2981,6 +2981,11 @@ S: 521 Pleasant Valley Road S: Potsdam, New York 13676 S: USA +N: Shannon Nelson +E: sln@onemain.com +D: Worked on several network drivers including +D: ixgbe, i40e, ionic, pds_core, pds_vdpa, pds_fwctl + N: Dave Neuer E: dave.neuer@pobox.com D: Helped implement support for Compaq's H31xx series iPAQs diff --git a/Documentation/ABI/testing/sysfs-edac-scrub b/Documentation/ABI/testing/sysfs-edac-scrub index c43be90deab4..ab6014743da5 100644 --- a/Documentation/ABI/testing/sysfs-edac-scrub +++ b/Documentation/ABI/testing/sysfs-edac-scrub @@ -49,6 +49,12 @@ Description: (RO) Supported minimum scrub cycle duration in seconds by the memory scrubber. + Device-based scrub: returns the minimum scrub cycle + supported by the memory device. + + Region-based scrub: returns the max of minimum scrub cycles + supported by individual memory devices that back the region. + What: /sys/bus/edac/devices/<dev-name>/scrubX/max_cycle_duration Date: March 2025 KernelVersion: 6.15 @@ -57,6 +63,16 @@ Description: (RO) Supported maximum scrub cycle duration in seconds by the memory scrubber. + Device-based scrub: returns the maximum scrub cycle supported + by the memory device. + + Region-based scrub: returns the min of maximum scrub cycles + supported by individual memory devices that back the region. + + If the memory device does not provide maximum scrub cycle + information, return the maximum supported value of the scrub + cycle field. + What: /sys/bus/edac/devices/<dev-name>/scrubX/current_cycle_duration Date: March 2025 KernelVersion: 6.15 diff --git a/Documentation/bpf/map_hash.rst b/Documentation/bpf/map_hash.rst index d2343952f2cb..8606bf958a8c 100644 --- a/Documentation/bpf/map_hash.rst +++ b/Documentation/bpf/map_hash.rst @@ -233,10 +233,16 @@ attempts in order to enforce the LRU property which have increasing impacts on other CPUs involved in the following operation attempts: - Attempt to use CPU-local state to batch operations -- Attempt to fetch free nodes from global lists +- Attempt to fetch ``target_free`` free nodes from global lists - Attempt to pull any node from a global list and remove it from the hashmap - Attempt to pull any node from any CPU's list and remove it from the hashmap +The number of nodes to borrow from the global list in a batch, ``target_free``, +depends on the size of the map. Larger batch size reduces lock contention, but +may also exhaust the global structure. The value is computed at map init to +avoid exhaustion, by limiting aggregate reservation by all CPUs to half the map +size. With a minimum of a single element and maximum budget of 128 at a time. + This algorithm is described visually in the following diagram. See the description in commit 3a08c2fd7634 ("bpf: LRU List") for a full explanation of the corresponding operations: diff --git a/Documentation/bpf/map_lru_hash_update.dot b/Documentation/bpf/map_lru_hash_update.dot index a0fee349d29c..ab10058f5b79 100644 --- a/Documentation/bpf/map_lru_hash_update.dot +++ b/Documentation/bpf/map_lru_hash_update.dot @@ -35,18 +35,18 @@ digraph { fn_bpf_lru_list_pop_free_to_local [shape=rectangle,fillcolor=2, label="Flush local pending, Rotate Global list, move - LOCAL_FREE_TARGET + target_free from global -> local"] // Also corresponds to: // fn__local_list_flush() // fn_bpf_lru_list_rotate() fn___bpf_lru_node_move_to_free[shape=diamond,fillcolor=2, - label="Able to free\nLOCAL_FREE_TARGET\nnodes?"] + label="Able to free\ntarget_free\nnodes?"] fn___bpf_lru_list_shrink_inactive [shape=rectangle,fillcolor=3, label="Shrink inactive list up to remaining - LOCAL_FREE_TARGET + target_free (global LRU -> local)"] fn___bpf_lru_list_shrink [shape=diamond,fillcolor=2, label="> 0 entries in\nlocal free list?"] diff --git a/Documentation/devicetree/bindings/display/bridge/ti,sn65dsi83.yaml b/Documentation/devicetree/bindings/display/bridge/ti,sn65dsi83.yaml index 9b5f3f3eab19..e69b6343a8eb 100644 --- a/Documentation/devicetree/bindings/display/bridge/ti,sn65dsi83.yaml +++ b/Documentation/devicetree/bindings/display/bridge/ti,sn65dsi83.yaml @@ -118,15 +118,11 @@ $defs: ti,lvds-vod-swing-clock-microvolt: description: LVDS diferential output voltage <min max> for clock lanes in microvolts. - $ref: /schemas/types.yaml#/definitions/uint32-array - minItems: 2 maxItems: 2 ti,lvds-vod-swing-data-microvolt: description: LVDS diferential output voltage <min max> for data lanes in microvolts. - $ref: /schemas/types.yaml#/definitions/uint32-array - minItems: 2 maxItems: 2 allOf: diff --git a/Documentation/devicetree/bindings/serial/altera_jtaguart.txt b/Documentation/devicetree/bindings/serial/altera_jtaguart.txt deleted file mode 100644 index 55a901051e8f..000000000000 --- a/Documentation/devicetree/bindings/serial/altera_jtaguart.txt +++ /dev/null @@ -1,5 +0,0 @@ -Altera JTAG UART - -Required properties: -- compatible : should be "ALTR,juart-1.0" <DEPRECATED> -- compatible : should be "altr,juart-1.0" diff --git a/Documentation/devicetree/bindings/serial/altera_uart.txt b/Documentation/devicetree/bindings/serial/altera_uart.txt deleted file mode 100644 index 81bf7ffb1a81..000000000000 --- a/Documentation/devicetree/bindings/serial/altera_uart.txt +++ /dev/null @@ -1,8 +0,0 @@ -Altera UART - -Required properties: -- compatible : should be "ALTR,uart-1.0" <DEPRECATED> -- compatible : should be "altr,uart-1.0" - -Optional properties: -- clock-frequency : frequency of the clock input to the UART diff --git a/Documentation/devicetree/bindings/serial/altr,juart-1.0.yaml b/Documentation/devicetree/bindings/serial/altr,juart-1.0.yaml new file mode 100644 index 000000000000..02e20fa591da --- /dev/null +++ b/Documentation/devicetree/bindings/serial/altr,juart-1.0.yaml @@ -0,0 +1,19 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/serial/altr,juart-1.0.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Altera JTAG UART + +maintainers: + - Dinh Nguyen <dinguyen@kernel.org> + +properties: + compatible: + const: altr,juart-1.0 + +required: + - compatible + +additionalProperties: false diff --git a/Documentation/devicetree/bindings/serial/altr,uart-1.0.yaml b/Documentation/devicetree/bindings/serial/altr,uart-1.0.yaml new file mode 100644 index 000000000000..72d4972e1e22 --- /dev/null +++ b/Documentation/devicetree/bindings/serial/altr,uart-1.0.yaml @@ -0,0 +1,25 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/serial/altr,uart-1.0.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Altera UART + +maintainers: + - Dinh Nguyen <dinguyen@kernel.org> + +allOf: + - $ref: /schemas/serial/serial.yaml# + +properties: + compatible: + const: altr,uart-1.0 + + clock-frequency: + description: Frequency of the clock input to the UART. + +required: + - compatible + +unevaluatedProperties: false diff --git a/Documentation/devicetree/bindings/soc/fsl/fsl,ls1028a-reset.yaml b/Documentation/devicetree/bindings/soc/fsl/fsl,ls1028a-reset.yaml index 234089b5954d..b43df10c5ef4 100644 --- a/Documentation/devicetree/bindings/soc/fsl/fsl,ls1028a-reset.yaml +++ b/Documentation/devicetree/bindings/soc/fsl/fsl,ls1028a-reset.yaml @@ -1,7 +1,7 @@ # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) %YAML 1.2 --- -$id: http://devicetree.org/schemas//soc/fsl/fsl,ls1028a-reset.yaml# +$id: http://devicetree.org/schemas/soc/fsl/fsl,ls1028a-reset.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# title: Freescale Layerscape Reset Registers Module diff --git a/Documentation/filesystems/porting.rst b/Documentation/filesystems/porting.rst index 3616d7161dab..a5734bdd1cc7 100644 --- a/Documentation/filesystems/porting.rst +++ b/Documentation/filesystems/porting.rst @@ -1249,3 +1249,12 @@ Using try_lookup_noperm() will require linux/namei.h to be included. Calling conventions for ->d_automount() have changed; we should *not* grab an extra reference to new mount - it should be returned with refcount 1. + +--- + +collect_mounts()/drop_collected_mounts()/iterate_mounts() are gone now. +Replacement is collect_paths()/drop_collected_path(), with no special +iterator needed. Instead of a cloned mount tree, the new interface returns +an array of struct path, one for each mount collect_mounts() would've +created. These struct path point to locations in the caller's namespace +that would be roots of the cloned mounts. diff --git a/Documentation/netlink/genetlink-legacy.yaml b/Documentation/netlink/genetlink-legacy.yaml index 4cbfe666e6f5..b29d62eefa16 100644 --- a/Documentation/netlink/genetlink-legacy.yaml +++ b/Documentation/netlink/genetlink-legacy.yaml @@ -6,6 +6,9 @@ $schema: https://json-schema.org/draft-07/schema # Common defines $defs: + name: + type: string + pattern: ^[0-9a-z-]+$ uint: type: integer minimum: 0 @@ -76,7 +79,7 @@ properties: additionalProperties: False properties: name: - type: string + $ref: '#/$defs/name' header: description: For C-compatible languages, header which already defines this value. type: string @@ -103,7 +106,7 @@ properties: additionalProperties: False properties: name: - type: string + $ref: '#/$defs/name' value: type: integer doc: @@ -132,7 +135,7 @@ properties: additionalProperties: False properties: name: - type: string + $ref: '#/$defs/name' type: description: The netlink attribute type enum: [ u8, u16, u32, u64, s8, s16, s32, s64, string, binary ] @@ -169,7 +172,7 @@ properties: name: description: | Name used when referring to this space in other definitions, not used outside of the spec. - type: string + $ref: '#/$defs/name' name-prefix: description: | Prefix for the C enum name of the attributes. Default family[name]-set[name]-a- @@ -206,7 +209,7 @@ properties: additionalProperties: False properties: name: - type: string + $ref: '#/$defs/name' type: &attr-type description: The netlink attribute type enum: [ unused, pad, flag, binary, bitfield32, @@ -348,7 +351,7 @@ properties: properties: name: description: Name of the operation, also defining its C enum value in uAPI. - type: string + $ref: '#/$defs/name' doc: description: Documentation for the command. type: string diff --git a/Documentation/netlink/genetlink.yaml b/Documentation/netlink/genetlink.yaml index 40efbbad76ab..7b1ec153e834 100644 --- a/Documentation/netlink/genetlink.yaml +++ b/Documentation/netlink/genetlink.yaml @@ -6,6 +6,9 @@ $schema: https://json-schema.org/draft-07/schema # Common defines $defs: + name: + type: string + pattern: ^[0-9a-z-]+$ uint: type: integer minimum: 0 @@ -29,7 +32,7 @@ additionalProperties: False properties: name: description: Name of the genetlink family. - type: string + $ref: '#/$defs/name' doc: type: string protocol: @@ -48,7 +51,7 @@ properties: additionalProperties: False properties: name: - type: string + $ref: '#/$defs/name' header: description: For C-compatible languages, header which already defines this value. type: string @@ -75,7 +78,7 @@ properties: additionalProperties: False properties: name: - type: string + $ref: '#/$defs/name' value: type: integer doc: @@ -96,7 +99,7 @@ properties: name: description: | Name used when referring to this space in other definitions, not used outside of the spec. - type: string + $ref: '#/$defs/name' name-prefix: description: | Prefix for the C enum name of the attributes. Default family[name]-set[name]-a- @@ -121,7 +124,7 @@ properties: additionalProperties: False properties: name: - type: string + $ref: '#/$defs/name' type: &attr-type enum: [ unused, pad, flag, binary, uint, sint, u8, u16, u32, u64, s8, s16, s32, s64, @@ -243,7 +246,7 @@ properties: properties: name: description: Name of the operation, also defining its C enum value in uAPI. - type: string + $ref: '#/$defs/name' doc: description: Documentation for the command. type: string @@ -327,7 +330,7 @@ properties: name: description: | The name for the group, used to form the define and the value of the define. - type: string + $ref: '#/$defs/name' flags: *cmd_flags kernel-family: diff --git a/Documentation/netlink/netlink-raw.yaml b/Documentation/netlink/netlink-raw.yaml index e34bf23897fa..246fa07bccf6 100644 --- a/Documentation/netlink/netlink-raw.yaml +++ b/Documentation/netlink/netlink-raw.yaml @@ -6,6 +6,12 @@ $schema: https://json-schema.org/draft-07/schema # Common defines $defs: + name: + type: string + pattern: ^[0-9a-z-]+$ + name-cap: + type: string + pattern: ^[0-9a-zA-Z-]+$ uint: type: integer minimum: 0 @@ -71,7 +77,7 @@ properties: additionalProperties: False properties: name: - type: string + $ref: '#/$defs/name' header: description: For C-compatible languages, header which already defines this value. type: string @@ -98,7 +104,7 @@ properties: additionalProperties: False properties: name: - type: string + $ref: '#/$defs/name' value: type: integer doc: @@ -124,7 +130,7 @@ properties: additionalProperties: False properties: name: - type: string + $ref: '#/$defs/name-cap' type: description: | The netlink attribute type. Members of type 'binary' or 'pad' @@ -183,7 +189,7 @@ properties: name: description: | Name used when referring to this space in other definitions, not used outside of the spec. - type: string + $ref: '#/$defs/name' name-prefix: description: | Prefix for the C enum name of the attributes. Default family[name]-set[name]-a- @@ -220,7 +226,7 @@ properties: additionalProperties: False properties: name: - type: string + $ref: '#/$defs/name' type: &attr-type description: The netlink attribute type enum: [ unused, pad, flag, binary, bitfield32, @@ -408,7 +414,7 @@ properties: properties: name: description: Name of the operation, also defining its C enum value in uAPI. - type: string + $ref: '#/$defs/name' doc: description: Documentation for the command. type: string diff --git a/Documentation/netlink/specs/devlink.yaml b/Documentation/netlink/specs/devlink.yaml index 05fee1b7fe19..38ddc04f9e6d 100644 --- a/Documentation/netlink/specs/devlink.yaml +++ b/Documentation/netlink/specs/devlink.yaml @@ -38,15 +38,15 @@ definitions: - name: dsa - - name: pci_pf + name: pci-pf - - name: pci_vf + name: pci-vf - name: virtual - name: unused - - name: pci_sf + name: pci-sf - type: enum name: port-fn-state @@ -220,7 +220,7 @@ definitions: - name: flag - - name: nul_string + name: nul-string value: 10 - name: binary diff --git a/Documentation/netlink/specs/dpll.yaml b/Documentation/netlink/specs/dpll.yaml index 8feefeae5376..f434140b538e 100644 --- a/Documentation/netlink/specs/dpll.yaml +++ b/Documentation/netlink/specs/dpll.yaml @@ -188,7 +188,7 @@ definitions: value: 10000 - type: const - name: pin-frequency-77_5-khz + name: pin-frequency-77-5-khz value: 77500 - type: const diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml index 72a076b0e1b5..348c6ad548f5 100644 --- a/Documentation/netlink/specs/ethtool.yaml +++ b/Documentation/netlink/specs/ethtool.yaml @@ -48,7 +48,7 @@ definitions: name: started doc: The firmware flashing process has started. - - name: in_progress + name: in-progress doc: The firmware flashing process is in progress. - name: completed @@ -1422,7 +1422,7 @@ attribute-sets: name: hkey type: binary - - name: input_xfrm + name: input-xfrm type: u32 - name: start-context @@ -2238,7 +2238,7 @@ operations: - hfunc - indir - hkey - - input_xfrm + - input-xfrm dump: request: attributes: diff --git a/Documentation/netlink/specs/fou.yaml b/Documentation/netlink/specs/fou.yaml index 0af5ab842c04..b02ab19817d3 100644 --- a/Documentation/netlink/specs/fou.yaml +++ b/Documentation/netlink/specs/fou.yaml @@ -15,7 +15,7 @@ kernel-policy: global definitions: - type: enum - name: encap_type + name: encap-type name-prefix: fou-encap- enum-name: entries: [ unspec, direct, gue ] @@ -43,26 +43,26 @@ attribute-sets: name: type type: u8 - - name: remcsum_nopartial + name: remcsum-nopartial type: flag - - name: local_v4 + name: local-v4 type: u32 - - name: local_v6 + name: local-v6 type: binary checks: min-len: 16 - - name: peer_v4 + name: peer-v4 type: u32 - - name: peer_v6 + name: peer-v6 type: binary checks: min-len: 16 - - name: peer_port + name: peer-port type: u16 byte-order: big-endian - @@ -90,12 +90,12 @@ operations: - port - ipproto - type - - remcsum_nopartial - - local_v4 - - peer_v4 - - local_v6 - - peer_v6 - - peer_port + - remcsum-nopartial + - local-v4 + - peer-v4 + - local-v6 + - peer-v6 + - peer-port - ifindex - @@ -112,11 +112,11 @@ operations: - af - ifindex - port - - peer_port - - local_v4 - - peer_v4 - - local_v6 - - peer_v6 + - peer-port + - local-v4 + - peer-v4 + - local-v6 + - peer-v6 - name: get diff --git a/Documentation/netlink/specs/mptcp_pm.yaml b/Documentation/netlink/specs/mptcp_pm.yaml index dfd017780d2f..fb57860fe778 100644 --- a/Documentation/netlink/specs/mptcp_pm.yaml +++ b/Documentation/netlink/specs/mptcp_pm.yaml @@ -57,21 +57,21 @@ definitions: doc: >- A new subflow has been established. 'error' should not be set. Attributes: token, family, loc_id, rem_id, saddr4 | saddr6, daddr4 | - daddr6, sport, dport, backup, if_idx [, error]. + daddr6, sport, dport, backup, if-idx [, error]. - name: sub-closed doc: >- A subflow has been closed. An error (copy of sk_err) could be set if an error has been detected for this subflow. Attributes: token, family, loc_id, rem_id, saddr4 | saddr6, daddr4 | - daddr6, sport, dport, backup, if_idx [, error]. + daddr6, sport, dport, backup, if-idx [, error]. - name: sub-priority value: 13 doc: >- The priority of a subflow has changed. 'error' should not be set. Attributes: token, family, loc_id, rem_id, saddr4 | saddr6, daddr4 | - daddr6, sport, dport, backup, if_idx [, error]. + daddr6, sport, dport, backup, if-idx [, error]. - name: listener-created value: 15 @@ -255,7 +255,7 @@ attribute-sets: name: timeout type: u32 - - name: if_idx + name: if-idx type: u32 - name: reset-reason diff --git a/Documentation/netlink/specs/nfsd.yaml b/Documentation/netlink/specs/nfsd.yaml index c87658114852..8d1a3c01708f 100644 --- a/Documentation/netlink/specs/nfsd.yaml +++ b/Documentation/netlink/specs/nfsd.yaml @@ -27,7 +27,7 @@ attribute-sets: name: proc type: u32 - - name: service_time + name: service-time type: s64 - name: pad @@ -139,7 +139,7 @@ operations: - prog - version - proc - - service_time + - service-time - saddr4 - daddr4 - saddr6 diff --git a/Documentation/netlink/specs/ovs_flow.yaml b/Documentation/netlink/specs/ovs_flow.yaml index 46f5d1cd8a5f..7974aa7d8905 100644 --- a/Documentation/netlink/specs/ovs_flow.yaml +++ b/Documentation/netlink/specs/ovs_flow.yaml @@ -216,7 +216,7 @@ definitions: type: struct members: - - name: nd_target + name: nd-target type: binary len: 16 byte-order: big-endian @@ -258,12 +258,12 @@ definitions: type: struct members: - - name: vlan_tpid + name: vlan-tpid type: u16 byte-order: big-endian doc: Tag protocol identifier (TPID) to push. - - name: vlan_tci + name: vlan-tci type: u16 byte-order: big-endian doc: Tag control identifier (TCI) to push. diff --git a/Documentation/netlink/specs/rt-link.yaml b/Documentation/netlink/specs/rt-link.yaml index b41b31eebcae..28c4cf66517c 100644 --- a/Documentation/netlink/specs/rt-link.yaml +++ b/Documentation/netlink/specs/rt-link.yaml @@ -603,7 +603,7 @@ definitions: name: optmask type: u32 - - name: if_stats_msg + name: if-stats-msg type: struct members: - @@ -2486,7 +2486,7 @@ operations: name: getstats doc: Get / dump link stats. attribute-set: stats-attrs - fixed-header: if_stats_msg + fixed-header: if-stats-msg do: request: value: 94 diff --git a/Documentation/netlink/specs/tc.yaml b/Documentation/netlink/specs/tc.yaml index cb7ea7d62e56..42d74c9aeb54 100644 --- a/Documentation/netlink/specs/tc.yaml +++ b/Documentation/netlink/specs/tc.yaml @@ -232,7 +232,7 @@ definitions: type: u8 doc: log(P_max / (qth-max - qth-min)) - - name: Scell_log + name: Scell-log type: u8 doc: cell size for idle damping - @@ -253,7 +253,7 @@ definitions: name: DPs type: u32 - - name: def_DP + name: def-DP type: u32 - name: grio diff --git a/Documentation/networking/device_drivers/ethernet/marvell/octeontx2.rst b/Documentation/networking/device_drivers/ethernet/marvell/octeontx2.rst index af7db0e91f6b..a52850602cd8 100644 --- a/Documentation/networking/device_drivers/ethernet/marvell/octeontx2.rst +++ b/Documentation/networking/device_drivers/ethernet/marvell/octeontx2.rst @@ -66,7 +66,7 @@ Admin Function driver As mentioned above RVU PF0 is called the admin function (AF), this driver supports resource provisioning and configuration of functional blocks. Doesn't handle any I/O. It sets up few basic stuff but most of the -funcionality is achieved via configuration requests from PFs and VFs. +functionality is achieved via configuration requests from PFs and VFs. PF/VFs communicates with AF via a shared memory region (mailbox). Upon receiving requests AF does resource provisioning and other HW configuration. diff --git a/MAINTAINERS b/MAINTAINERS index c3f7fbd0d67a..7aff9b0ead32 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -11155,7 +11155,8 @@ F: include/linux/platform_data/huawei-gaokun-ec.h HUGETLB SUBSYSTEM M: Muchun Song <muchun.song@linux.dev> -R: Oscar Salvador <osalvador@suse.de> +M: Oscar Salvador <osalvador@suse.de> +R: David Hildenbrand <david@redhat.com> L: linux-mm@kvack.org S: Maintained F: Documentation/ABI/testing/sysfs-kernel-mm-hugepages @@ -11166,6 +11167,7 @@ F: fs/hugetlbfs/ F: include/linux/hugetlb.h F: include/trace/events/hugetlbfs.h F: mm/hugetlb.c +F: mm/hugetlb_cgroup.c F: mm/hugetlb_cma.c F: mm/hugetlb_cma.h F: mm/hugetlb_vmemmap.c @@ -13345,6 +13347,7 @@ M: Alexander Graf <graf@amazon.com> M: Mike Rapoport <rppt@kernel.org> M: Changyuan Lyu <changyuanl@google.com> L: kexec@lists.infradead.org +L: linux-mm@kvack.org S: Maintained F: Documentation/admin-guide/mm/kho.rst F: Documentation/core-api/kho/* @@ -15673,11 +15676,16 @@ MEMBLOCK AND MEMORY MANAGEMENT INITIALIZATION M: Mike Rapoport <rppt@kernel.org> L: linux-mm@kvack.org S: Maintained +T: git git://git.kernel.org/pub/scm/linux/kernel/git/rppt/memblock.git for-next +T: git git://git.kernel.org/pub/scm/linux/kernel/git/rppt/memblock.git fixes F: Documentation/core-api/boot-time-mm.rst F: Documentation/core-api/kho/bindings/memblock/* F: include/linux/memblock.h +F: mm/bootmem_info.c F: mm/memblock.c +F: mm/memtest.c F: mm/mm_init.c +F: mm/rodata_test.c F: tools/testing/memblock/ MEMORY ALLOCATION PROFILING @@ -15732,7 +15740,6 @@ F: Documentation/admin-guide/mm/ F: Documentation/mm/ F: include/linux/gfp.h F: include/linux/gfp_types.h -F: include/linux/memfd.h F: include/linux/memory_hotplug.h F: include/linux/memory-tiers.h F: include/linux/mempolicy.h @@ -15792,6 +15799,10 @@ S: Maintained W: http://www.linux-mm.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm F: mm/gup.c +F: mm/gup_test.c +F: mm/gup_test.h +F: tools/testing/selftests/mm/gup_longterm.c +F: tools/testing/selftests/mm/gup_test.c MEMORY MANAGEMENT - KSM (Kernel Samepage Merging) M: Andrew Morton <akpm@linux-foundation.org> @@ -15839,6 +15850,17 @@ F: mm/numa.c F: mm/numa_emulation.c F: mm/numa_memblks.c +MEMORY MANAGEMENT - OOM KILLER +M: Michal Hocko <mhocko@suse.com> +R: David Rientjes <rientjes@google.com> +R: Shakeel Butt <shakeel.butt@linux.dev> +L: linux-mm@kvack.org +S: Maintained +F: include/linux/oom.h +F: include/trace/events/oom.h +F: include/uapi/linux/oom.h +F: mm/oom_kill.c + MEMORY MANAGEMENT - PAGE ALLOCATOR M: Andrew Morton <akpm@linux-foundation.org> M: Vlastimil Babka <vbabka@suse.cz> @@ -15853,8 +15875,17 @@ F: include/linux/compaction.h F: include/linux/gfp.h F: include/linux/page-isolation.h F: mm/compaction.c +F: mm/debug_page_alloc.c +F: mm/fail_page_alloc.c F: mm/page_alloc.c +F: mm/page_ext.c +F: mm/page_frag_cache.c F: mm/page_isolation.c +F: mm/page_owner.c +F: mm/page_poison.c +F: mm/page_reporting.c +F: mm/show_mem.c +F: mm/shuffle.c MEMORY MANAGEMENT - RECLAIM M: Andrew Morton <akpm@linux-foundation.org> @@ -15868,6 +15899,7 @@ L: linux-mm@kvack.org S: Maintained F: mm/pt_reclaim.c F: mm/vmscan.c +F: mm/workingset.c MEMORY MANAGEMENT - RMAP (REVERSE MAPPING) M: Andrew Morton <akpm@linux-foundation.org> @@ -15880,6 +15912,7 @@ R: Harry Yoo <harry.yoo@oracle.com> L: linux-mm@kvack.org S: Maintained F: include/linux/rmap.h +F: mm/page_vma_mapped.c F: mm/rmap.c MEMORY MANAGEMENT - SECRETMEM @@ -15912,9 +15945,9 @@ F: mm/swapfile.c MEMORY MANAGEMENT - THP (TRANSPARENT HUGE PAGE) M: Andrew Morton <akpm@linux-foundation.org> M: David Hildenbrand <david@redhat.com> +M: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> R: Zi Yan <ziy@nvidia.com> R: Baolin Wang <baolin.wang@linux.alibaba.com> -R: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> R: Liam R. Howlett <Liam.Howlett@oracle.com> R: Nico Pache <npache@redhat.com> R: Ryan Roberts <ryan.roberts@arm.com> @@ -15972,11 +16005,14 @@ S: Maintained W: http://www.linux-mm.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm F: include/trace/events/mmap.h +F: mm/mincore.c F: mm/mlock.c F: mm/mmap.c F: mm/mprotect.c F: mm/mremap.c F: mm/mseal.c +F: mm/msync.c +F: mm/nommu.c F: mm/vma.c F: mm/vma.h F: mm/vma_exec.c @@ -21374,7 +21410,7 @@ N: spacemit K: spacemit RISC-V THEAD SoC SUPPORT -M: Drew Fustini <drew@pdp7.com> +M: Drew Fustini <fustini@kernel.org> M: Guo Ren <guoren@kernel.org> M: Fu Wei <wefu@redhat.com> L: linux-riscv@lists.infradead.org @@ -25027,8 +25063,11 @@ M: Hugh Dickins <hughd@google.com> R: Baolin Wang <baolin.wang@linux.alibaba.com> L: linux-mm@kvack.org S: Maintained +F: include/linux/memfd.h F: include/linux/shmem_fs.h +F: mm/memfd.c F: mm/shmem.c +F: mm/shmem_quota.c TOMOYO SECURITY MODULE M: Kentaro Takeda <takedakn@nttdata.co.jp> diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 438ce7df24c3..5bd5aae60d53 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -1075,7 +1075,6 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte) */ #ifdef CONFIG_64BIT #define TASK_SIZE_64 (PGDIR_SIZE * PTRS_PER_PGD / 2) -#define TASK_SIZE_MAX LONG_MAX #ifdef CONFIG_COMPAT #define TASK_SIZE_32 (_AC(0x80000000, UL) - PAGE_SIZE) diff --git a/arch/riscv/include/asm/runtime-const.h b/arch/riscv/include/asm/runtime-const.h index 451fd76b8811..d766e2b9e6df 100644 --- a/arch/riscv/include/asm/runtime-const.h +++ b/arch/riscv/include/asm/runtime-const.h @@ -206,7 +206,7 @@ static inline void __runtime_fixup_32(__le16 *lui_parcel, __le16 *addi_parcel, u addi_insn_mask &= 0x07fff; } - if (lower_immediate & 0x00000fff) { + if (lower_immediate & 0x00000fff || lui_insn == RISCV_INSN_NOP4) { /* replace upper 12 bits of addi with lower 12 bits of val */ addi_insn &= addi_insn_mask; addi_insn |= (lower_immediate & 0x00000fff) << 20; diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h index d472da4450e6..525e50db24f7 100644 --- a/arch/riscv/include/asm/uaccess.h +++ b/arch/riscv/include/asm/uaccess.h @@ -127,6 +127,7 @@ do { \ #ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT #define __get_user_8(x, ptr, label) \ +do { \ u32 __user *__ptr = (u32 __user *)(ptr); \ u32 __lo, __hi; \ asm_goto_output( \ @@ -141,7 +142,7 @@ do { \ : : label); \ (x) = (__typeof__(x))((__typeof__((x) - (x)))( \ (((u64)__hi << 32) | __lo))); \ - +} while (0) #else /* !CONFIG_CC_HAS_ASM_GOTO_OUTPUT */ #define __get_user_8(x, ptr, label) \ do { \ diff --git a/arch/riscv/include/asm/vdso/getrandom.h b/arch/riscv/include/asm/vdso/getrandom.h index 8dc92441702a..c6d66895c1f5 100644 --- a/arch/riscv/include/asm/vdso/getrandom.h +++ b/arch/riscv/include/asm/vdso/getrandom.h @@ -18,7 +18,7 @@ static __always_inline ssize_t getrandom_syscall(void *_buffer, size_t _len, uns register unsigned int flags asm("a2") = _flags; asm volatile ("ecall\n" - : "+r" (ret) + : "=r" (ret) : "r" (nr), "r" (buffer), "r" (len), "r" (flags) : "memory"); diff --git a/arch/riscv/include/asm/vector.h b/arch/riscv/include/asm/vector.h index 45c9b426fcc5..b61786d43c20 100644 --- a/arch/riscv/include/asm/vector.h +++ b/arch/riscv/include/asm/vector.h @@ -205,11 +205,11 @@ static inline void __riscv_v_vstate_save(struct __riscv_v_ext_state *save_to, THEAD_VSETVLI_T4X0E8M8D1 THEAD_VSB_V_V0T0 "add t0, t0, t4\n\t" - THEAD_VSB_V_V0T0 + THEAD_VSB_V_V8T0 "add t0, t0, t4\n\t" - THEAD_VSB_V_V0T0 + THEAD_VSB_V_V16T0 "add t0, t0, t4\n\t" - THEAD_VSB_V_V0T0 + THEAD_VSB_V_V24T0 : : "r" (datap) : "memory", "t0", "t4"); } else { asm volatile ( @@ -241,11 +241,11 @@ static inline void __riscv_v_vstate_restore(struct __riscv_v_ext_state *restore_ THEAD_VSETVLI_T4X0E8M8D1 THEAD_VLB_V_V0T0 "add t0, t0, t4\n\t" - THEAD_VLB_V_V0T0 + THEAD_VLB_V_V8T0 "add t0, t0, t4\n\t" - THEAD_VLB_V_V0T0 + THEAD_VLB_V_V16T0 "add t0, t0, t4\n\t" - THEAD_VLB_V_V0T0 + THEAD_VLB_V_V24T0 : : "r" (datap) : "memory", "t0", "t4"); } else { asm volatile ( diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index f7c9a1caa83e..14888e5ea19a 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -50,6 +50,7 @@ atomic_t hart_lottery __section(".sdata") #endif ; unsigned long boot_cpu_hartid; +EXPORT_SYMBOL_GPL(boot_cpu_hartid); /* * Place kernel memory regions on the resource tree so that diff --git a/arch/riscv/kernel/traps_misaligned.c b/arch/riscv/kernel/traps_misaligned.c index dd8e4af6583f..93043924fe6c 100644 --- a/arch/riscv/kernel/traps_misaligned.c +++ b/arch/riscv/kernel/traps_misaligned.c @@ -454,7 +454,7 @@ static int handle_scalar_misaligned_load(struct pt_regs *regs) val.data_u64 = 0; if (user_mode(regs)) { - if (copy_from_user_nofault(&val, (u8 __user *)addr, len)) + if (copy_from_user(&val, (u8 __user *)addr, len)) return -1; } else { memcpy(&val, (u8 *)addr, len); @@ -555,7 +555,7 @@ static int handle_scalar_misaligned_store(struct pt_regs *regs) return -EOPNOTSUPP; if (user_mode(regs)) { - if (copy_to_user_nofault((u8 __user *)addr, &val, len)) + if (copy_to_user((u8 __user *)addr, &val, len)) return -1; } else { memcpy((u8 *)addr, &val, len); diff --git a/arch/riscv/kernel/vdso/vdso.lds.S b/arch/riscv/kernel/vdso/vdso.lds.S index 7c15b0f4ee3b..c29ef12a63bb 100644 --- a/arch/riscv/kernel/vdso/vdso.lds.S +++ b/arch/riscv/kernel/vdso/vdso.lds.S @@ -30,7 +30,7 @@ SECTIONS *(.data .data.* .gnu.linkonce.d.*) *(.dynbss) *(.bss .bss.* .gnu.linkonce.b.*) - } + } :text .note : { *(.note.*) } :text :note diff --git a/arch/riscv/kernel/vendor_extensions/sifive.c b/arch/riscv/kernel/vendor_extensions/sifive.c index 1411337dc1e6..8fcf67e8c07f 100644 --- a/arch/riscv/kernel/vendor_extensions/sifive.c +++ b/arch/riscv/kernel/vendor_extensions/sifive.c @@ -8,7 +8,7 @@ #include <linux/types.h> /* All SiFive vendor extensions supported in Linux */ -const struct riscv_isa_ext_data riscv_isa_vendor_ext_sifive[] = { +static const struct riscv_isa_ext_data riscv_isa_vendor_ext_sifive[] = { __RISCV_ISA_EXT_DATA(xsfvfnrclipxfqf, RISCV_ISA_VENDOR_EXT_XSFVFNRCLIPXFQF), __RISCV_ISA_EXT_DATA(xsfvfwmaccqqq, RISCV_ISA_VENDOR_EXT_XSFVFWMACCQQQ), __RISCV_ISA_EXT_DATA(xsfvqmaccdod, RISCV_ISA_VENDOR_EXT_XSFVQMACCDOD), diff --git a/arch/s390/include/asm/ptrace.h b/arch/s390/include/asm/ptrace.h index 62c0ab4a4b9d..0905fa99a31e 100644 --- a/arch/s390/include/asm/ptrace.h +++ b/arch/s390/include/asm/ptrace.h @@ -265,7 +265,7 @@ static __always_inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *r addr = kernel_stack_pointer(regs) + n * sizeof(long); if (!regs_within_kernel_stack(regs, addr)) return 0; - return READ_ONCE_NOCHECK(addr); + return READ_ONCE_NOCHECK(*(unsigned long *)addr); } /** diff --git a/arch/um/drivers/ubd_user.c b/arch/um/drivers/ubd_user.c index c5e6545f6fcf..8e8a8bf518b6 100644 --- a/arch/um/drivers/ubd_user.c +++ b/arch/um/drivers/ubd_user.c @@ -41,7 +41,7 @@ int start_io_thread(struct os_helper_thread **td_out, int *fd_out) *fd_out = fds[1]; err = os_set_fd_block(*fd_out, 0); - err = os_set_fd_block(kernel_fd, 0); + err |= os_set_fd_block(kernel_fd, 0); if (err) { printk("start_io_thread - failed to set nonblocking I/O.\n"); goto out_close; diff --git a/arch/um/drivers/vector_kern.c b/arch/um/drivers/vector_kern.c index f292e0b4ff8b..9bbbddfe866b 100644 --- a/arch/um/drivers/vector_kern.c +++ b/arch/um/drivers/vector_kern.c @@ -1625,35 +1625,19 @@ static void vector_eth_configure( device->dev = dev; - *vp = ((struct vector_private) - { - .list = LIST_HEAD_INIT(vp->list), - .dev = dev, - .unit = n, - .options = get_transport_options(def), - .rx_irq = 0, - .tx_irq = 0, - .parsed = def, - .max_packet = get_mtu(def) + ETH_HEADER_OTHER, - /* TODO - we need to calculate headroom so that ip header - * is 16 byte aligned all the time - */ - .headroom = get_headroom(def), - .form_header = NULL, - .verify_header = NULL, - .header_rxbuffer = NULL, - .header_txbuffer = NULL, - .header_size = 0, - .rx_header_size = 0, - .rexmit_scheduled = false, - .opened = false, - .transport_data = NULL, - .in_write_poll = false, - .coalesce = 2, - .req_size = get_req_size(def), - .in_error = false, - .bpf = NULL - }); + INIT_LIST_HEAD(&vp->list); + vp->dev = dev; + vp->unit = n; + vp->options = get_transport_options(def); + vp->parsed = def; + vp->max_packet = get_mtu(def) + ETH_HEADER_OTHER; + /* + * TODO - we need to calculate headroom so that ip header + * is 16 byte aligned all the time + */ + vp->headroom = get_headroom(def); + vp->coalesce = 2; + vp->req_size = get_req_size(def); dev->features = dev->hw_features = (NETIF_F_SG | NETIF_F_FRAGLIST); INIT_WORK(&vp->reset_tx, vector_reset_tx); diff --git a/arch/um/drivers/vfio_kern.c b/arch/um/drivers/vfio_kern.c index b51fc9888ae1..13b971a2bd43 100644 --- a/arch/um/drivers/vfio_kern.c +++ b/arch/um/drivers/vfio_kern.c @@ -570,6 +570,17 @@ static void uml_vfio_release_device(struct uml_vfio_device *dev) kfree(dev); } +static struct uml_vfio_device *uml_vfio_find_device(const char *device) +{ + struct uml_vfio_device *dev; + + list_for_each_entry(dev, ¨_vfio_devices, list) { + if (!strcmp(dev->name, device)) + return dev; + } + return NULL; +} + static int uml_vfio_cmdline_set(const char *device, const struct kernel_param *kp) { struct uml_vfio_device *dev; @@ -582,6 +593,9 @@ static int uml_vfio_cmdline_set(const char *device, const struct kernel_param *k uml_vfio_container.fd = fd; } + if (uml_vfio_find_device(device)) + return -EEXIST; + dev = kzalloc(sizeof(*dev), GFP_KERNEL); if (!dev) return -ENOMEM; diff --git a/arch/x86/um/ptrace.c b/arch/x86/um/ptrace.c index 3275870330fe..fae8aabad10f 100644 --- a/arch/x86/um/ptrace.c +++ b/arch/x86/um/ptrace.c @@ -161,7 +161,7 @@ static int fpregs_legacy_set(struct task_struct *target, from = kbuf; } - return um_fxsr_from_i387(fxsave, &buf); + return um_fxsr_from_i387(fxsave, from); } #endif diff --git a/block/genhd.c b/block/genhd.c index 8171a6bc3210..c26733f6324b 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -128,23 +128,27 @@ static void part_stat_read_all(struct block_device *part, static void bdev_count_inflight_rw(struct block_device *part, unsigned int inflight[2], bool mq_driver) { + int write = 0; + int read = 0; int cpu; if (mq_driver) { blk_mq_in_driver_rw(part, inflight); - } else { - for_each_possible_cpu(cpu) { - inflight[READ] += part_stat_local_read_cpu( - part, in_flight[READ], cpu); - inflight[WRITE] += part_stat_local_read_cpu( - part, in_flight[WRITE], cpu); - } + return; + } + + for_each_possible_cpu(cpu) { + read += part_stat_local_read_cpu(part, in_flight[READ], cpu); + write += part_stat_local_read_cpu(part, in_flight[WRITE], cpu); } - if (WARN_ON_ONCE((int)inflight[READ] < 0)) - inflight[READ] = 0; - if (WARN_ON_ONCE((int)inflight[WRITE] < 0)) - inflight[WRITE] = 0; + /* + * While iterating all CPUs, some IOs may be issued from a CPU already + * traversed and complete on a CPU that has not yet been traversed, + * causing the inflight number to be negative. + */ + inflight[READ] = read > 0 ? read : 0; + inflight[WRITE] = write > 0 ? write : 0; } /** diff --git a/crypto/wp512.c b/crypto/wp512.c index 41f13d490333..229b189a7988 100644 --- a/crypto/wp512.c +++ b/crypto/wp512.c @@ -21,10 +21,10 @@ */ #include <crypto/internal/hash.h> #include <linux/init.h> +#include <linux/kernel.h> #include <linux/module.h> -#include <linux/mm.h> -#include <asm/byteorder.h> -#include <linux/types.h> +#include <linux/string.h> +#include <linux/unaligned.h> #define WP512_DIGEST_SIZE 64 #define WP384_DIGEST_SIZE 48 @@ -37,9 +37,6 @@ struct wp512_ctx { u8 bitLength[WP512_LENGTHBYTES]; - u8 buffer[WP512_BLOCK_SIZE]; - int bufferBits; - int bufferPos; u64 hash[WP512_DIGEST_SIZE/8]; }; @@ -779,16 +776,16 @@ static const u64 rc[WHIRLPOOL_ROUNDS] = { * The core Whirlpool transform. */ -static __no_kmsan_checks void wp512_process_buffer(struct wp512_ctx *wctx) { +static __no_kmsan_checks void wp512_process_buffer(struct wp512_ctx *wctx, + const u8 *buffer) { int i, r; u64 K[8]; /* the round key */ u64 block[8]; /* mu(buffer) */ u64 state[8]; /* the cipher state */ u64 L[8]; - const __be64 *buffer = (const __be64 *)wctx->buffer; for (i = 0; i < 8; i++) - block[i] = be64_to_cpu(buffer[i]); + block[i] = get_unaligned_be64(buffer + i * 8); state[0] = block[0] ^ (K[0] = wctx->hash[0]); state[1] = block[1] ^ (K[1] = wctx->hash[1]); @@ -991,8 +988,6 @@ static int wp512_init(struct shash_desc *desc) { int i; memset(wctx->bitLength, 0, 32); - wctx->bufferBits = wctx->bufferPos = 0; - wctx->buffer[0] = 0; for (i = 0; i < 8; i++) { wctx->hash[i] = 0L; } @@ -1000,84 +995,54 @@ static int wp512_init(struct shash_desc *desc) { return 0; } -static int wp512_update(struct shash_desc *desc, const u8 *source, - unsigned int len) +static void wp512_add_length(u8 *bitLength, u64 value) { - struct wp512_ctx *wctx = shash_desc_ctx(desc); - int sourcePos = 0; - unsigned int bits_len = len * 8; // convert to number of bits - int sourceGap = (8 - ((int)bits_len & 7)) & 7; - int bufferRem = wctx->bufferBits & 7; + u32 carry; int i; - u32 b, carry; - u8 *buffer = wctx->buffer; - u8 *bitLength = wctx->bitLength; - int bufferBits = wctx->bufferBits; - int bufferPos = wctx->bufferPos; - u64 value = bits_len; for (i = 31, carry = 0; i >= 0 && (carry != 0 || value != 0ULL); i--) { carry += bitLength[i] + ((u32)value & 0xff); bitLength[i] = (u8)carry; carry >>= 8; value >>= 8; } - while (bits_len > 8) { - b = ((source[sourcePos] << sourceGap) & 0xff) | - ((source[sourcePos + 1] & 0xff) >> (8 - sourceGap)); - buffer[bufferPos++] |= (u8)(b >> bufferRem); - bufferBits += 8 - bufferRem; - if (bufferBits == WP512_BLOCK_SIZE * 8) { - wp512_process_buffer(wctx); - bufferBits = bufferPos = 0; - } - buffer[bufferPos] = b << (8 - bufferRem); - bufferBits += bufferRem; - bits_len -= 8; - sourcePos++; - } - if (bits_len > 0) { - b = (source[sourcePos] << sourceGap) & 0xff; - buffer[bufferPos] |= b >> bufferRem; - } else { - b = 0; - } - if (bufferRem + bits_len < 8) { - bufferBits += bits_len; - } else { - bufferPos++; - bufferBits += 8 - bufferRem; - bits_len -= 8 - bufferRem; - if (bufferBits == WP512_BLOCK_SIZE * 8) { - wp512_process_buffer(wctx); - bufferBits = bufferPos = 0; - } - buffer[bufferPos] = b << (8 - bufferRem); - bufferBits += (int)bits_len; - } +} - wctx->bufferBits = bufferBits; - wctx->bufferPos = bufferPos; +static int wp512_update(struct shash_desc *desc, const u8 *source, + unsigned int len) +{ + struct wp512_ctx *wctx = shash_desc_ctx(desc); + unsigned int remain = len % WP512_BLOCK_SIZE; + u64 bits_len = (len - remain) * 8ull; + u8 *bitLength = wctx->bitLength; - return 0; + wp512_add_length(bitLength, bits_len); + do { + wp512_process_buffer(wctx, source); + source += WP512_BLOCK_SIZE; + bits_len -= WP512_BLOCK_SIZE * 8; + } while (bits_len); + + return remain; } -static int wp512_final(struct shash_desc *desc, u8 *out) +static int wp512_finup(struct shash_desc *desc, const u8 *src, + unsigned int bufferPos, u8 *out) { struct wp512_ctx *wctx = shash_desc_ctx(desc); int i; - u8 *buffer = wctx->buffer; u8 *bitLength = wctx->bitLength; - int bufferBits = wctx->bufferBits; - int bufferPos = wctx->bufferPos; __be64 *digest = (__be64 *)out; + u8 buffer[WP512_BLOCK_SIZE]; - buffer[bufferPos] |= 0x80U >> (bufferBits & 7); + wp512_add_length(bitLength, bufferPos * 8); + memcpy(buffer, src, bufferPos); + buffer[bufferPos] = 0x80U; bufferPos++; if (bufferPos > WP512_BLOCK_SIZE - WP512_LENGTHBYTES) { if (bufferPos < WP512_BLOCK_SIZE) memset(&buffer[bufferPos], 0, WP512_BLOCK_SIZE - bufferPos); - wp512_process_buffer(wctx); + wp512_process_buffer(wctx, buffer); bufferPos = 0; } if (bufferPos < WP512_BLOCK_SIZE - WP512_LENGTHBYTES) @@ -1086,31 +1051,32 @@ static int wp512_final(struct shash_desc *desc, u8 *out) bufferPos = WP512_BLOCK_SIZE - WP512_LENGTHBYTES; memcpy(&buffer[WP512_BLOCK_SIZE - WP512_LENGTHBYTES], bitLength, WP512_LENGTHBYTES); - wp512_process_buffer(wctx); + wp512_process_buffer(wctx, buffer); + memzero_explicit(buffer, sizeof(buffer)); for (i = 0; i < WP512_DIGEST_SIZE/8; i++) digest[i] = cpu_to_be64(wctx->hash[i]); - wctx->bufferBits = bufferBits; - wctx->bufferPos = bufferPos; return 0; } -static int wp384_final(struct shash_desc *desc, u8 *out) +static int wp384_finup(struct shash_desc *desc, const u8 *src, + unsigned int len, u8 *out) { u8 D[64]; - wp512_final(desc, D); + wp512_finup(desc, src, len, D); memcpy(out, D, WP384_DIGEST_SIZE); memzero_explicit(D, WP512_DIGEST_SIZE); return 0; } -static int wp256_final(struct shash_desc *desc, u8 *out) +static int wp256_finup(struct shash_desc *desc, const u8 *src, + unsigned int len, u8 *out) { u8 D[64]; - wp512_final(desc, D); + wp512_finup(desc, src, len, D); memcpy(out, D, WP256_DIGEST_SIZE); memzero_explicit(D, WP512_DIGEST_SIZE); @@ -1121,11 +1087,12 @@ static struct shash_alg wp_algs[3] = { { .digestsize = WP512_DIGEST_SIZE, .init = wp512_init, .update = wp512_update, - .final = wp512_final, + .finup = wp512_finup, .descsize = sizeof(struct wp512_ctx), .base = { .cra_name = "wp512", .cra_driver_name = "wp512-generic", + .cra_flags = CRYPTO_AHASH_ALG_BLOCK_ONLY, .cra_blocksize = WP512_BLOCK_SIZE, .cra_module = THIS_MODULE, } @@ -1133,11 +1100,12 @@ static struct shash_alg wp_algs[3] = { { .digestsize = WP384_DIGEST_SIZE, .init = wp512_init, .update = wp512_update, - .final = wp384_final, + .finup = wp384_finup, .descsize = sizeof(struct wp512_ctx), .base = { .cra_name = "wp384", .cra_driver_name = "wp384-generic", + .cra_flags = CRYPTO_AHASH_ALG_BLOCK_ONLY, .cra_blocksize = WP512_BLOCK_SIZE, .cra_module = THIS_MODULE, } @@ -1145,11 +1113,12 @@ static struct shash_alg wp_algs[3] = { { .digestsize = WP256_DIGEST_SIZE, .init = wp512_init, .update = wp512_update, - .final = wp256_final, + .finup = wp256_finup, .descsize = sizeof(struct wp512_ctx), .base = { .cra_name = "wp256", .cra_driver_name = "wp256-generic", + .cra_flags = CRYPTO_AHASH_ALG_BLOCK_ONLY, .cra_blocksize = WP512_BLOCK_SIZE, .cra_module = THIS_MODULE, } diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index e5e5c2e81d09..aa93b0ecbbc6 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -1450,7 +1450,7 @@ static bool ahci_broken_lpm(struct pci_dev *pdev) { .matches = { DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), - DMI_MATCH(DMI_PRODUCT_VERSION, "ASUSPRO D840MB_M840SA"), + DMI_MATCH(DMI_PRODUCT_NAME, "ASUSPRO D840MB_M840SA"), }, /* 320 is broken, there is no known good version. */ }, diff --git a/drivers/atm/idt77252.c b/drivers/atm/idt77252.c index 1206ab764ba9..f2e91b7d79f0 100644 --- a/drivers/atm/idt77252.c +++ b/drivers/atm/idt77252.c @@ -852,6 +852,8 @@ queue_skb(struct idt77252_dev *card, struct vc_map *vc, IDT77252_PRV_PADDR(skb) = dma_map_single(&card->pcidev->dev, skb->data, skb->len, DMA_TO_DEVICE); + if (dma_mapping_error(&card->pcidev->dev, IDT77252_PRV_PADDR(skb))) + return -ENOMEM; error = -EINVAL; @@ -1857,6 +1859,8 @@ add_rx_skb(struct idt77252_dev *card, int queue, paddr = dma_map_single(&card->pcidev->dev, skb->data, skb_end_pointer(skb) - skb->data, DMA_FROM_DEVICE); + if (dma_mapping_error(&card->pcidev->dev, paddr)) + goto outpoolrm; IDT77252_PRV_PADDR(skb) = paddr; if (push_rx_skb(card, skb, queue)) { @@ -1871,6 +1875,7 @@ outunmap: dma_unmap_single(&card->pcidev->dev, IDT77252_PRV_PADDR(skb), skb_end_pointer(skb) - skb->data, DMA_FROM_DEVICE); +outpoolrm: handle = IDT77252_PRV_POOL(skb); card->sbpool[POOL_QUEUE(handle)].skb[POOL_INDEX(handle)] = NULL; diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index d36f44f5ee80..c3e3c3b65a6d 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -1148,8 +1148,8 @@ exit: blk_mq_end_request(req, res); } -static void ublk_complete_io_cmd(struct ublk_io *io, struct request *req, - int res, unsigned issue_flags) +static struct io_uring_cmd *__ublk_prep_compl_io_cmd(struct ublk_io *io, + struct request *req) { /* read cmd first because req will overwrite it */ struct io_uring_cmd *cmd = io->cmd; @@ -1164,6 +1164,13 @@ static void ublk_complete_io_cmd(struct ublk_io *io, struct request *req, io->flags &= ~UBLK_IO_FLAG_ACTIVE; io->req = req; + return cmd; +} + +static void ublk_complete_io_cmd(struct ublk_io *io, struct request *req, + int res, unsigned issue_flags) +{ + struct io_uring_cmd *cmd = __ublk_prep_compl_io_cmd(io, req); /* tell ublksrv one io request is coming */ io_uring_cmd_done(cmd, res, 0, issue_flags); @@ -1416,6 +1423,14 @@ static blk_status_t ublk_queue_rq(struct blk_mq_hw_ctx *hctx, return BLK_STS_OK; } +static inline bool ublk_belong_to_same_batch(const struct ublk_io *io, + const struct ublk_io *io2) +{ + return (io_uring_cmd_ctx_handle(io->cmd) == + io_uring_cmd_ctx_handle(io2->cmd)) && + (io->task == io2->task); +} + static void ublk_queue_rqs(struct rq_list *rqlist) { struct rq_list requeue_list = { }; @@ -1427,7 +1442,8 @@ static void ublk_queue_rqs(struct rq_list *rqlist) struct ublk_queue *this_q = req->mq_hctx->driver_data; struct ublk_io *this_io = &this_q->ios[req->tag]; - if (io && io->task != this_io->task && !rq_list_empty(&submit_list)) + if (io && !ublk_belong_to_same_batch(io, this_io) && + !rq_list_empty(&submit_list)) ublk_queue_cmd_list(io, &submit_list); io = this_io; @@ -2148,10 +2164,9 @@ static int ublk_commit_and_fetch(const struct ublk_queue *ubq, return 0; } -static bool ublk_get_data(const struct ublk_queue *ubq, struct ublk_io *io) +static bool ublk_get_data(const struct ublk_queue *ubq, struct ublk_io *io, + struct request *req) { - struct request *req = io->req; - /* * We have handled UBLK_IO_NEED_GET_DATA command, * so clear UBLK_IO_FLAG_NEED_GET_DATA now and just @@ -2178,6 +2193,7 @@ static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd, u32 cmd_op = cmd->cmd_op; unsigned tag = ub_cmd->tag; int ret = -EINVAL; + struct request *req; pr_devel("%s: received: cmd op %d queue %d tag %d result %d\n", __func__, cmd->cmd_op, ub_cmd->q_id, tag, @@ -2236,11 +2252,19 @@ static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd, goto out; break; case UBLK_IO_NEED_GET_DATA: - io->addr = ub_cmd->addr; - if (!ublk_get_data(ubq, io)) - return -EIOCBQUEUED; - - return UBLK_IO_RES_OK; + /* + * ublk_get_data() may fail and fallback to requeue, so keep + * uring_cmd active first and prepare for handling new requeued + * request + */ + req = io->req; + ublk_fill_io_cmd(io, cmd, ub_cmd->addr); + io->flags &= ~UBLK_IO_FLAG_OWNED_BY_SRV; + if (likely(ublk_get_data(ubq, io, req))) { + __ublk_prep_compl_io_cmd(io, req); + return UBLK_IO_RES_OK; + } + break; default: goto out; } @@ -2825,7 +2849,8 @@ static int ublk_ctrl_add_dev(const struct ublksrv_ctrl_cmd *header) if (copy_from_user(&info, argp, sizeof(info))) return -EFAULT; - if (info.queue_depth > UBLK_MAX_QUEUE_DEPTH || info.nr_hw_queues > UBLK_MAX_NR_QUEUES) + if (info.queue_depth > UBLK_MAX_QUEUE_DEPTH || !info.queue_depth || + info.nr_hw_queues > UBLK_MAX_NR_QUEUES || !info.nr_hw_queues) return -EINVAL; if (capable(CAP_SYS_ADMIN)) diff --git a/drivers/bluetooth/btintel_pcie.c b/drivers/bluetooth/btintel_pcie.c index 563165c5efae..e1c688dd2d45 100644 --- a/drivers/bluetooth/btintel_pcie.c +++ b/drivers/bluetooth/btintel_pcie.c @@ -2033,6 +2033,28 @@ static void btintel_pcie_release_hdev(struct btintel_pcie_data *data) data->hdev = NULL; } +static void btintel_pcie_disable_interrupts(struct btintel_pcie_data *data) +{ + spin_lock(&data->irq_lock); + btintel_pcie_wr_reg32(data, BTINTEL_PCIE_CSR_MSIX_FH_INT_MASK, data->fh_init_mask); + btintel_pcie_wr_reg32(data, BTINTEL_PCIE_CSR_MSIX_HW_INT_MASK, data->hw_init_mask); + spin_unlock(&data->irq_lock); +} + +static void btintel_pcie_enable_interrupts(struct btintel_pcie_data *data) +{ + spin_lock(&data->irq_lock); + btintel_pcie_wr_reg32(data, BTINTEL_PCIE_CSR_MSIX_FH_INT_MASK, ~data->fh_init_mask); + btintel_pcie_wr_reg32(data, BTINTEL_PCIE_CSR_MSIX_HW_INT_MASK, ~data->hw_init_mask); + spin_unlock(&data->irq_lock); +} + +static void btintel_pcie_synchronize_irqs(struct btintel_pcie_data *data) +{ + for (int i = 0; i < data->alloc_vecs; i++) + synchronize_irq(data->msix_entries[i].vector); +} + static int btintel_pcie_setup_internal(struct hci_dev *hdev) { struct btintel_pcie_data *data = hci_get_drvdata(hdev); @@ -2152,6 +2174,8 @@ static int btintel_pcie_setup(struct hci_dev *hdev) bt_dev_err(hdev, "Firmware download retry count: %d", fw_dl_retry); btintel_pcie_dump_debug_registers(hdev); + btintel_pcie_disable_interrupts(data); + btintel_pcie_synchronize_irqs(data); err = btintel_pcie_reset_bt(data); if (err) { bt_dev_err(hdev, "Failed to do shr reset: %d", err); @@ -2159,6 +2183,7 @@ static int btintel_pcie_setup(struct hci_dev *hdev) } usleep_range(10000, 12000); btintel_pcie_reset_ia(data); + btintel_pcie_enable_interrupts(data); btintel_pcie_config_msix(data); err = btintel_pcie_enable_bt(data); if (err) { @@ -2291,6 +2316,12 @@ static void btintel_pcie_remove(struct pci_dev *pdev) data = pci_get_drvdata(pdev); + btintel_pcie_disable_interrupts(data); + + btintel_pcie_synchronize_irqs(data); + + flush_work(&data->rx_work); + btintel_pcie_reset_bt(data); for (int i = 0; i < data->alloc_vecs; i++) { struct msix_entry *msix_entry; @@ -2303,8 +2334,6 @@ static void btintel_pcie_remove(struct pci_dev *pdev) btintel_pcie_release_hdev(data); - flush_work(&data->rx_work); - destroy_workqueue(data->workqueue); btintel_pcie_free(data); diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c index 5fe5879881f5..3ec0be496820 100644 --- a/drivers/bluetooth/hci_qca.c +++ b/drivers/bluetooth/hci_qca.c @@ -2392,10 +2392,17 @@ static int qca_serdev_probe(struct serdev_device *serdev) */ qcadev->bt_power->pwrseq = devm_pwrseq_get(&serdev->dev, "bluetooth"); - if (IS_ERR(qcadev->bt_power->pwrseq)) - return PTR_ERR(qcadev->bt_power->pwrseq); - break; + /* + * Some modules have BT_EN enabled via a hardware pull-up, + * meaning it is not defined in the DTS and is not controlled + * through the power sequence. In such cases, fall through + * to follow the legacy flow. + */ + if (IS_ERR(qcadev->bt_power->pwrseq)) + qcadev->bt_power->pwrseq = NULL; + else + break; } fallthrough; case QCA_WCN3950: diff --git a/drivers/cxl/core/edac.c b/drivers/cxl/core/edac.c index 2cbc664e5d62..623aaa4439c4 100644 --- a/drivers/cxl/core/edac.c +++ b/drivers/cxl/core/edac.c @@ -103,10 +103,10 @@ static int cxl_scrub_get_attrbs(struct cxl_patrol_scrub_context *cxl_ps_ctx, u8 *cap, u16 *cycle, u8 *flags, u8 *min_cycle) { struct cxl_mailbox *cxl_mbox; - u8 min_scrub_cycle = U8_MAX; struct cxl_region_params *p; struct cxl_memdev *cxlmd; struct cxl_region *cxlr; + u8 min_scrub_cycle = 0; int i, ret; if (!cxl_ps_ctx->cxlr) { @@ -133,8 +133,12 @@ static int cxl_scrub_get_attrbs(struct cxl_patrol_scrub_context *cxl_ps_ctx, if (ret) return ret; + /* + * The min_scrub_cycle of a region is the max of minimum scrub + * cycles supported by memdevs that back the region. + */ if (min_cycle) - min_scrub_cycle = min(*min_cycle, min_scrub_cycle); + min_scrub_cycle = max(*min_cycle, min_scrub_cycle); } if (min_cycle) @@ -1099,8 +1103,10 @@ int cxl_store_rec_gen_media(struct cxl_memdev *cxlmd, union cxl_event *evt) old_rec = xa_store(&array_rec->rec_gen_media, le64_to_cpu(rec->media_hdr.phys_addr), rec, GFP_KERNEL); - if (xa_is_err(old_rec)) + if (xa_is_err(old_rec)) { + kfree(rec); return xa_err(old_rec); + } kfree(old_rec); @@ -1127,8 +1133,10 @@ int cxl_store_rec_dram(struct cxl_memdev *cxlmd, union cxl_event *evt) old_rec = xa_store(&array_rec->rec_dram, le64_to_cpu(rec->media_hdr.phys_addr), rec, GFP_KERNEL); - if (xa_is_err(old_rec)) + if (xa_is_err(old_rec)) { + kfree(rec); return xa_err(old_rec); + } kfree(old_rec); @@ -1315,7 +1323,7 @@ cxl_mem_get_rec_dram(struct cxl_memdev *cxlmd, attrbs.bank = ctx->bank; break; case EDAC_REPAIR_RANK_SPARING: - attrbs.repair_type = CXL_BANK_SPARING; + attrbs.repair_type = CXL_RANK_SPARING; break; default: return NULL; diff --git a/drivers/cxl/core/features.c b/drivers/cxl/core/features.c index 6f2eae1eb126..7c750599ea69 100644 --- a/drivers/cxl/core/features.c +++ b/drivers/cxl/core/features.c @@ -544,7 +544,7 @@ static bool cxlctl_validate_set_features(struct cxl_features_state *cxlfs, u32 flags; if (rpc_in->op_size < sizeof(uuid_t)) - return ERR_PTR(-EINVAL); + return false; feat = cxl_feature_info(cxlfs, &rpc_in->set_feat_in.uuid); if (IS_ERR(feat)) diff --git a/drivers/cxl/core/ras.c b/drivers/cxl/core/ras.c index 485a831695c7..2731ba3a0799 100644 --- a/drivers/cxl/core/ras.c +++ b/drivers/cxl/core/ras.c @@ -31,40 +31,38 @@ static void cxl_cper_trace_uncorr_port_prot_err(struct pci_dev *pdev, ras_cap.header_log); } -static void cxl_cper_trace_corr_prot_err(struct pci_dev *pdev, - struct cxl_ras_capability_regs ras_cap) +static void cxl_cper_trace_corr_prot_err(struct cxl_memdev *cxlmd, + struct cxl_ras_capability_regs ras_cap) { u32 status = ras_cap.cor_status & ~ras_cap.cor_mask; - struct cxl_dev_state *cxlds; - cxlds = pci_get_drvdata(pdev); - if (!cxlds) - return; - - trace_cxl_aer_correctable_error(cxlds->cxlmd, status); + trace_cxl_aer_correctable_error(cxlmd, status); } -static void cxl_cper_trace_uncorr_prot_err(struct pci_dev *pdev, - struct cxl_ras_capability_regs ras_cap) +static void +cxl_cper_trace_uncorr_prot_err(struct cxl_memdev *cxlmd, + struct cxl_ras_capability_regs ras_cap) { u32 status = ras_cap.uncor_status & ~ras_cap.uncor_mask; - struct cxl_dev_state *cxlds; u32 fe; - cxlds = pci_get_drvdata(pdev); - if (!cxlds) - return; - if (hweight32(status) > 1) fe = BIT(FIELD_GET(CXL_RAS_CAP_CONTROL_FE_MASK, ras_cap.cap_control)); else fe = status; - trace_cxl_aer_uncorrectable_error(cxlds->cxlmd, status, fe, + trace_cxl_aer_uncorrectable_error(cxlmd, status, fe, ras_cap.header_log); } +static int match_memdev_by_parent(struct device *dev, const void *uport) +{ + if (is_cxl_memdev(dev) && dev->parent == uport) + return 1; + return 0; +} + static void cxl_cper_handle_prot_err(struct cxl_cper_prot_err_work_data *data) { unsigned int devfn = PCI_DEVFN(data->prot_err.agent_addr.device, @@ -73,13 +71,12 @@ static void cxl_cper_handle_prot_err(struct cxl_cper_prot_err_work_data *data) pci_get_domain_bus_and_slot(data->prot_err.agent_addr.segment, data->prot_err.agent_addr.bus, devfn); + struct cxl_memdev *cxlmd; int port_type; if (!pdev) return; - guard(device)(&pdev->dev); - port_type = pci_pcie_type(pdev); if (port_type == PCI_EXP_TYPE_ROOT_PORT || port_type == PCI_EXP_TYPE_DOWNSTREAM || @@ -92,10 +89,20 @@ static void cxl_cper_handle_prot_err(struct cxl_cper_prot_err_work_data *data) return; } + guard(device)(&pdev->dev); + if (!pdev->dev.driver) + return; + + struct device *mem_dev __free(put_device) = bus_find_device( + &cxl_bus_type, NULL, pdev, match_memdev_by_parent); + if (!mem_dev) + return; + + cxlmd = to_cxl_memdev(mem_dev); if (data->severity == AER_CORRECTABLE) - cxl_cper_trace_corr_prot_err(pdev, data->ras_cap); + cxl_cper_trace_corr_prot_err(cxlmd, data->ras_cap); else - cxl_cper_trace_uncorr_prot_err(pdev, data->ras_cap); + cxl_cper_trace_uncorr_prot_err(cxlmd, data->ras_cap); } static void cxl_cper_prot_err_work_fn(struct work_struct *work) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c index a0e9bf9b2710..81b3443c8d7f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c @@ -321,10 +321,12 @@ static int amdgpu_discovery_read_binary_from_file(struct amdgpu_device *adev, const struct firmware *fw; int r; - r = request_firmware(&fw, fw_name, adev->dev); + r = firmware_request_nowarn(&fw, fw_name, adev->dev); if (r) { - dev_err(adev->dev, "can't load firmware \"%s\"\n", - fw_name); + if (amdgpu_discovery == 2) + dev_err(adev->dev, "can't load firmware \"%s\"\n", fw_name); + else + drm_info(&adev->ddev, "Optional firmware \"%s\" was not found\n", fw_name); return r; } @@ -459,16 +461,12 @@ static int amdgpu_discovery_init(struct amdgpu_device *adev) /* Read from file if it is the preferred option */ fw_name = amdgpu_discovery_get_fw_name(adev); if (fw_name != NULL) { - dev_info(adev->dev, "use ip discovery information from file"); + drm_dbg(&adev->ddev, "use ip discovery information from file"); r = amdgpu_discovery_read_binary_from_file(adev, adev->mman.discovery_bin, fw_name); - - if (r) { - dev_err(adev->dev, "failed to read ip discovery binary from file\n"); - r = -EINVAL; + if (r) goto out; - } - } else { + drm_dbg(&adev->ddev, "use ip discovery information from memory"); r = amdgpu_discovery_read_binary_from_mem( adev, adev->mman.discovery_bin); if (r) @@ -1338,10 +1336,8 @@ static int amdgpu_discovery_reg_base_init(struct amdgpu_device *adev) int r; r = amdgpu_discovery_init(adev); - if (r) { - DRM_ERROR("amdgpu_discovery_init failed\n"); + if (r) return r; - } wafl_ver = 0; adev->gfx.xcc_mask = 0; @@ -2579,8 +2575,10 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev) break; default: r = amdgpu_discovery_reg_base_init(adev); - if (r) - return -EINVAL; + if (r) { + drm_err(&adev->ddev, "discovery failed: %d\n", r); + return r; + } amdgpu_discovery_harvest_ip(adev); amdgpu_discovery_get_gfx_info(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index d377a7c57d5e..ad9be3656653 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -2235,6 +2235,25 @@ static int gfx_v9_0_sw_init(struct amdgpu_ip_block *ip_block) } switch (amdgpu_ip_version(adev, GC_HWIP, 0)) { + case IP_VERSION(9, 0, 1): + case IP_VERSION(9, 2, 1): + case IP_VERSION(9, 4, 0): + case IP_VERSION(9, 2, 2): + case IP_VERSION(9, 1, 0): + case IP_VERSION(9, 3, 0): + adev->gfx.cleaner_shader_ptr = gfx_9_4_2_cleaner_shader_hex; + adev->gfx.cleaner_shader_size = sizeof(gfx_9_4_2_cleaner_shader_hex); + if (adev->gfx.me_fw_version >= 167 && + adev->gfx.pfp_fw_version >= 196 && + adev->gfx.mec_fw_version >= 474) { + adev->gfx.enable_cleaner_shader = true; + r = amdgpu_gfx_cleaner_shader_sw_init(adev, adev->gfx.cleaner_shader_size); + if (r) { + adev->gfx.enable_cleaner_shader = false; + dev_err(adev->dev, "Failed to initialize cleaner shader\n"); + } + } + break; case IP_VERSION(9, 4, 2): adev->gfx.cleaner_shader_ptr = gfx_9_4_2_cleaner_shader_hex; adev->gfx.cleaner_shader_size = sizeof(gfx_9_4_2_cleaner_shader_hex); diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c index c9eba537de09..28eb846280dd 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c @@ -1630,10 +1630,12 @@ static int mes_v11_0_hw_init(struct amdgpu_ip_block *ip_block) if (r) goto failure; - r = mes_v11_0_set_hw_resources_1(&adev->mes); - if (r) { - DRM_ERROR("failed mes_v11_0_set_hw_resources_1, r=%d\n", r); - goto failure; + if ((adev->mes.sched_version & AMDGPU_MES_VERSION_MASK) >= 0x50) { + r = mes_v11_0_set_hw_resources_1(&adev->mes); + if (r) { + DRM_ERROR("failed mes_v11_0_set_hw_resources_1, r=%d\n", r); + goto failure; + } } r = mes_v11_0_query_sched_status(&adev->mes); diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c index b4f17332d466..6b222630f3fa 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c @@ -1742,7 +1742,8 @@ static int mes_v12_0_hw_init(struct amdgpu_ip_block *ip_block) if (r) goto failure; - mes_v12_0_set_hw_resources_1(&adev->mes, AMDGPU_MES_SCHED_PIPE); + if ((adev->mes.sched_version & AMDGPU_MES_VERSION_MASK) >= 0x4b) + mes_v12_0_set_hw_resources_1(&adev->mes, AMDGPU_MES_SCHED_PIPE); mes_v12_0_init_aggregated_doorbell(&adev->mes); diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c index 5a70ae17be04..a9bdf8d61d6c 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c @@ -1374,9 +1374,22 @@ static int sdma_v6_0_sw_init(struct amdgpu_ip_block *ip_block) else DRM_ERROR("Failed to allocated memory for SDMA IP Dump\n"); - /* add firmware version checks here */ - if (0 && !adev->sdma.disable_uq) - adev->userq_funcs[AMDGPU_HW_IP_DMA] = &userq_mes_funcs; + switch (amdgpu_ip_version(adev, SDMA0_HWIP, 0)) { + case IP_VERSION(6, 0, 0): + if ((adev->sdma.instance[0].fw_version >= 24) && !adev->sdma.disable_uq) + adev->userq_funcs[AMDGPU_HW_IP_DMA] = &userq_mes_funcs; + break; + case IP_VERSION(6, 0, 2): + if ((adev->sdma.instance[0].fw_version >= 21) && !adev->sdma.disable_uq) + adev->userq_funcs[AMDGPU_HW_IP_DMA] = &userq_mes_funcs; + break; + case IP_VERSION(6, 0, 3): + if ((adev->sdma.instance[0].fw_version >= 25) && !adev->sdma.disable_uq) + adev->userq_funcs[AMDGPU_HW_IP_DMA] = &userq_mes_funcs; + break; + default: + break; + } r = amdgpu_sdma_sysfs_reset_mask_init(adev); if (r) diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c index ad47d0bdf777..86903eccbd4e 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c @@ -1349,9 +1349,15 @@ static int sdma_v7_0_sw_init(struct amdgpu_ip_block *ip_block) else DRM_ERROR("Failed to allocated memory for SDMA IP Dump\n"); - /* add firmware version checks here */ - if (0 && !adev->sdma.disable_uq) - adev->userq_funcs[AMDGPU_HW_IP_DMA] = &userq_mes_funcs; + switch (amdgpu_ip_version(adev, SDMA0_HWIP, 0)) { + case IP_VERSION(7, 0, 0): + case IP_VERSION(7, 0, 1): + if ((adev->sdma.instance[0].fw_version >= 7836028) && !adev->sdma.disable_uq) + adev->userq_funcs[AMDGPU_HW_IP_DMA] = &userq_mes_funcs; + break; + default: + break; + } return r; } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index bc4cd11bfc79..0b8ac9edc070 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -4718,16 +4718,16 @@ static int get_brightness_range(const struct amdgpu_dm_backlight_caps *caps, return 1; } -/* Rescale from [min..max] to [0..AMDGPU_MAX_BL_LEVEL] */ +/* Rescale from [min..max] to [0..MAX_BACKLIGHT_LEVEL] */ static inline u32 scale_input_to_fw(int min, int max, u64 input) { - return DIV_ROUND_CLOSEST_ULL(input * AMDGPU_MAX_BL_LEVEL, max - min); + return DIV_ROUND_CLOSEST_ULL(input * MAX_BACKLIGHT_LEVEL, max - min); } -/* Rescale from [0..AMDGPU_MAX_BL_LEVEL] to [min..max] */ +/* Rescale from [0..MAX_BACKLIGHT_LEVEL] to [min..max] */ static inline u32 scale_fw_to_input(int min, int max, u64 input) { - return min + DIV_ROUND_CLOSEST_ULL(input * (max - min), AMDGPU_MAX_BL_LEVEL); + return min + DIV_ROUND_CLOSEST_ULL(input * (max - min), MAX_BACKLIGHT_LEVEL); } static void convert_custom_brightness(const struct amdgpu_dm_backlight_caps *caps, @@ -4947,7 +4947,7 @@ amdgpu_dm_register_backlight_device(struct amdgpu_dm_connector *aconnector) drm_dbg(drm, "Backlight caps: min: %d, max: %d, ac %d, dc %d\n", min, max, caps->ac_level, caps->dc_level); } else - props.brightness = props.max_brightness = AMDGPU_MAX_BL_LEVEL; + props.brightness = props.max_brightness = MAX_BACKLIGHT_LEVEL; if (caps->data_points && !(amdgpu_dc_debug_mask & DC_DISABLE_CUSTOM_BRIGHTNESS_CURVE)) drm_info(drm, "Using custom brightness curve\n"); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c index d4395b92fb85..9e3e51a2dc49 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c @@ -1029,6 +1029,10 @@ enum dc_edid_status dm_helpers_read_local_edid( return EDID_NO_RESPONSE; edid = drm_edid_raw(drm_edid); // FIXME: Get rid of drm_edid_raw() + if (!edid || + edid->extensions >= sizeof(sink->dc_edid.raw_edid) / EDID_LENGTH) + return EDID_BAD_INPUT; + sink->dc_edid.length = EDID_LENGTH * (edid->extensions + 1); memmove(sink->dc_edid.raw_edid, (uint8_t *)edid, sink->dc_edid.length); diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi86.c b/drivers/gpu/drm/bridge/ti-sn65dsi86.c index 60224f476e1d..de9c23537465 100644 --- a/drivers/gpu/drm/bridge/ti-sn65dsi86.c +++ b/drivers/gpu/drm/bridge/ti-sn65dsi86.c @@ -348,12 +348,18 @@ static void ti_sn65dsi86_enable_comms(struct ti_sn65dsi86 *pdata, * 200 ms. We'll assume that the panel driver will have the hardcoded * delay in its prepare and always disable HPD. * - * If HPD somehow makes sense on some future panel we'll have to - * change this to be conditional on someone specifying that HPD should - * be used. + * For DisplayPort bridge type, we need HPD. So we use the bridge type + * to conditionally disable HPD. + * NOTE: The bridge type is set in ti_sn_bridge_probe() but enable_comms() + * can be called before. So for DisplayPort, HPD will be enabled once + * bridge type is set. We are using bridge type instead of "no-hpd" + * property because it is not used properly in devicetree description + * and hence is unreliable. */ - regmap_update_bits(pdata->regmap, SN_HPD_DISABLE_REG, HPD_DISABLE, - HPD_DISABLE); + + if (pdata->bridge.type != DRM_MODE_CONNECTOR_DisplayPort) + regmap_update_bits(pdata->regmap, SN_HPD_DISABLE_REG, HPD_DISABLE, + HPD_DISABLE); pdata->comms_enabled = true; @@ -1195,9 +1201,14 @@ static enum drm_connector_status ti_sn_bridge_detect(struct drm_bridge *bridge) struct ti_sn65dsi86 *pdata = bridge_to_ti_sn65dsi86(bridge); int val = 0; - pm_runtime_get_sync(pdata->dev); + /* + * Runtime reference is grabbed in ti_sn_bridge_hpd_enable() + * as the chip won't report HPD just after being powered on. + * HPD_DEBOUNCED_STATE reflects correct state only after the + * debounce time (~100-400 ms). + */ + regmap_read(pdata->regmap, SN_HPD_DISABLE_REG, &val); - pm_runtime_put_autosuspend(pdata->dev); return val & HPD_DEBOUNCED_STATE ? connector_status_connected : connector_status_disconnected; @@ -1220,6 +1231,26 @@ static void ti_sn65dsi86_debugfs_init(struct drm_bridge *bridge, struct dentry * debugfs_create_file("status", 0600, debugfs, pdata, &status_fops); } +static void ti_sn_bridge_hpd_enable(struct drm_bridge *bridge) +{ + struct ti_sn65dsi86 *pdata = bridge_to_ti_sn65dsi86(bridge); + + /* + * Device needs to be powered on before reading the HPD state + * for reliable hpd detection in ti_sn_bridge_detect() due to + * the high debounce time. + */ + + pm_runtime_get_sync(pdata->dev); +} + +static void ti_sn_bridge_hpd_disable(struct drm_bridge *bridge) +{ + struct ti_sn65dsi86 *pdata = bridge_to_ti_sn65dsi86(bridge); + + pm_runtime_put_autosuspend(pdata->dev); +} + static const struct drm_bridge_funcs ti_sn_bridge_funcs = { .attach = ti_sn_bridge_attach, .detach = ti_sn_bridge_detach, @@ -1234,6 +1265,8 @@ static const struct drm_bridge_funcs ti_sn_bridge_funcs = { .atomic_duplicate_state = drm_atomic_helper_bridge_duplicate_state, .atomic_destroy_state = drm_atomic_helper_bridge_destroy_state, .debugfs_init = ti_sn65dsi86_debugfs_init, + .hpd_enable = ti_sn_bridge_hpd_enable, + .hpd_disable = ti_sn_bridge_hpd_disable, }; static void ti_sn_bridge_parse_lanes(struct ti_sn65dsi86 *pdata, @@ -1321,8 +1354,26 @@ static int ti_sn_bridge_probe(struct auxiliary_device *adev, pdata->bridge.type = pdata->next_bridge->type == DRM_MODE_CONNECTOR_DisplayPort ? DRM_MODE_CONNECTOR_DisplayPort : DRM_MODE_CONNECTOR_eDP; - if (pdata->bridge.type == DRM_MODE_CONNECTOR_DisplayPort) - pdata->bridge.ops = DRM_BRIDGE_OP_EDID | DRM_BRIDGE_OP_DETECT; + if (pdata->bridge.type == DRM_MODE_CONNECTOR_DisplayPort) { + pdata->bridge.ops = DRM_BRIDGE_OP_EDID | DRM_BRIDGE_OP_DETECT | + DRM_BRIDGE_OP_HPD; + /* + * If comms were already enabled they would have been enabled + * with the wrong value of HPD_DISABLE. Update it now. Comms + * could be enabled if anyone is holding a pm_runtime reference + * (like if a GPIO is in use). Note that in most cases nobody + * is doing AUX channel xfers before the bridge is added so + * HPD doesn't _really_ matter then. The only exception is in + * the eDP case where the panel wants to read the EDID before + * the bridge is added. We always consistently have HPD disabled + * for eDP. + */ + mutex_lock(&pdata->comms_mutex); + if (pdata->comms_enabled) + regmap_update_bits(pdata->regmap, SN_HPD_DISABLE_REG, + HPD_DISABLE, 0); + mutex_unlock(&pdata->comms_mutex); + }; drm_bridge_add(&pdata->bridge); diff --git a/drivers/gpu/drm/display/drm_bridge_connector.c b/drivers/gpu/drm/display/drm_bridge_connector.c index 7d2e499ea5de..262e93e07a28 100644 --- a/drivers/gpu/drm/display/drm_bridge_connector.c +++ b/drivers/gpu/drm/display/drm_bridge_connector.c @@ -708,11 +708,14 @@ struct drm_connector *drm_bridge_connector_init(struct drm_device *drm, if (bridge_connector->bridge_hdmi_audio || bridge_connector->bridge_dp_audio) { struct device *dev; + struct drm_bridge *bridge; if (bridge_connector->bridge_hdmi_audio) - dev = bridge_connector->bridge_hdmi_audio->hdmi_audio_dev; + bridge = bridge_connector->bridge_hdmi_audio; else - dev = bridge_connector->bridge_dp_audio->hdmi_audio_dev; + bridge = bridge_connector->bridge_dp_audio; + + dev = bridge->hdmi_audio_dev; ret = drm_connector_hdmi_audio_init(connector, dev, &drm_bridge_connector_hdmi_audio_funcs, diff --git a/drivers/gpu/drm/display/drm_dp_helper.c b/drivers/gpu/drm/display/drm_dp_helper.c index f2a6559a2710..dc622c78db9d 100644 --- a/drivers/gpu/drm/display/drm_dp_helper.c +++ b/drivers/gpu/drm/display/drm_dp_helper.c @@ -725,7 +725,7 @@ ssize_t drm_dp_dpcd_read(struct drm_dp_aux *aux, unsigned int offset, * monitor doesn't power down exactly after the throw away read. */ if (!aux->is_remote) { - ret = drm_dp_dpcd_probe(aux, DP_DPCD_REV); + ret = drm_dp_dpcd_probe(aux, DP_LANE0_1_STATUS); if (ret < 0) return ret; } diff --git a/drivers/gpu/drm/drm_writeback.c b/drivers/gpu/drm/drm_writeback.c index edbeab88ff2b..d983ee85cf13 100644 --- a/drivers/gpu/drm/drm_writeback.c +++ b/drivers/gpu/drm/drm_writeback.c @@ -343,17 +343,18 @@ EXPORT_SYMBOL(drm_writeback_connector_init_with_encoder); /** * drm_writeback_connector_cleanup - Cleanup the writeback connector * @dev: DRM device - * @wb_connector: Pointer to the writeback connector to clean up + * @data: Pointer to the writeback connector to clean up * * This will decrement the reference counter of blobs and destroy properties. It * will also clean the remaining jobs in this writeback connector. Caution: This helper will not * clean up the attached encoder and the drm_connector. */ static void drm_writeback_connector_cleanup(struct drm_device *dev, - struct drm_writeback_connector *wb_connector) + void *data) { unsigned long flags; struct drm_writeback_job *pos, *n; + struct drm_writeback_connector *wb_connector = data; delete_writeback_properties(dev); drm_property_blob_put(wb_connector->pixel_formats_blob_ptr); @@ -405,7 +406,7 @@ int drmm_writeback_connector_init(struct drm_device *dev, if (ret) return ret; - ret = drmm_add_action_or_reset(dev, (void *)drm_writeback_connector_cleanup, + ret = drmm_add_action_or_reset(dev, drm_writeback_connector_cleanup, wb_connector); if (ret) return ret; diff --git a/drivers/gpu/drm/i915/display/intel_snps_hdmi_pll.c b/drivers/gpu/drm/i915/display/intel_snps_hdmi_pll.c index 74bb3bedf30f..5111bdc3075b 100644 --- a/drivers/gpu/drm/i915/display/intel_snps_hdmi_pll.c +++ b/drivers/gpu/drm/i915/display/intel_snps_hdmi_pll.c @@ -103,8 +103,8 @@ static void get_ana_cp_int_prop(u64 vco_clk, DIV_ROUND_DOWN_ULL(curve_1_interpolated, CURVE0_MULTIPLIER))); ana_cp_int_temp = - DIV_ROUND_CLOSEST_ULL(DIV_ROUND_DOWN_ULL(adjusted_vco_clk1, curve_2_scaled1), - CURVE2_MULTIPLIER); + DIV64_U64_ROUND_CLOSEST(DIV_ROUND_DOWN_ULL(adjusted_vco_clk1, curve_2_scaled1), + CURVE2_MULTIPLIER); *ana_cp_int = max(1, min(ana_cp_int_temp, 127)); diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c index 990bfaba3ce4..5bc696bfbb0f 100644 --- a/drivers/gpu/drm/i915/i915_pmu.c +++ b/drivers/gpu/drm/i915/i915_pmu.c @@ -108,7 +108,7 @@ static unsigned int config_bit(const u64 config) return other_bit(config); } -static u32 config_mask(const u64 config) +static __always_inline u32 config_mask(const u64 config) { unsigned int bit = config_bit(config); diff --git a/drivers/gpu/drm/xe/display/xe_display.c b/drivers/gpu/drm/xe/display/xe_display.c index 68f064f33d4b..9f4ade25787a 100644 --- a/drivers/gpu/drm/xe/display/xe_display.c +++ b/drivers/gpu/drm/xe/display/xe_display.c @@ -104,6 +104,8 @@ int xe_display_create(struct xe_device *xe) spin_lock_init(&xe->display.fb_tracking.lock); xe->display.hotplug.dp_wq = alloc_ordered_workqueue("xe-dp", 0); + if (!xe->display.hotplug.dp_wq) + return -ENOMEM; return drmm_add_action_or_reset(&xe->drm, display_destroy, NULL); } diff --git a/drivers/gpu/drm/xe/display/xe_dsb_buffer.c b/drivers/gpu/drm/xe/display/xe_dsb_buffer.c index f95375451e2f..9f941fc2e36b 100644 --- a/drivers/gpu/drm/xe/display/xe_dsb_buffer.c +++ b/drivers/gpu/drm/xe/display/xe_dsb_buffer.c @@ -17,10 +17,7 @@ u32 intel_dsb_buffer_ggtt_offset(struct intel_dsb_buffer *dsb_buf) void intel_dsb_buffer_write(struct intel_dsb_buffer *dsb_buf, u32 idx, u32 val) { - struct xe_device *xe = dsb_buf->vma->bo->tile->xe; - iosys_map_wr(&dsb_buf->vma->bo->vmap, idx * 4, u32, val); - xe_device_l2_flush(xe); } u32 intel_dsb_buffer_read(struct intel_dsb_buffer *dsb_buf, u32 idx) @@ -30,12 +27,9 @@ u32 intel_dsb_buffer_read(struct intel_dsb_buffer *dsb_buf, u32 idx) void intel_dsb_buffer_memset(struct intel_dsb_buffer *dsb_buf, u32 idx, u32 val, size_t size) { - struct xe_device *xe = dsb_buf->vma->bo->tile->xe; - WARN_ON(idx > (dsb_buf->buf_size - size) / sizeof(*dsb_buf->cmd_buf)); iosys_map_memset(&dsb_buf->vma->bo->vmap, idx * 4, val, size); - xe_device_l2_flush(xe); } bool intel_dsb_buffer_create(struct intel_crtc *crtc, struct intel_dsb_buffer *dsb_buf, size_t size) @@ -74,9 +68,12 @@ void intel_dsb_buffer_cleanup(struct intel_dsb_buffer *dsb_buf) void intel_dsb_buffer_flush_map(struct intel_dsb_buffer *dsb_buf) { + struct xe_device *xe = dsb_buf->vma->bo->tile->xe; + /* * The memory barrier here is to ensure coherency of DSB vs MMIO, * both for weak ordering archs and discrete cards. */ - xe_device_wmb(dsb_buf->vma->bo->tile->xe); + xe_device_wmb(xe); + xe_device_l2_flush(xe); } diff --git a/drivers/gpu/drm/xe/display/xe_fb_pin.c b/drivers/gpu/drm/xe/display/xe_fb_pin.c index d918ae1c8061..55259969480b 100644 --- a/drivers/gpu/drm/xe/display/xe_fb_pin.c +++ b/drivers/gpu/drm/xe/display/xe_fb_pin.c @@ -164,6 +164,9 @@ static int __xe_pin_fb_vma_dpt(const struct intel_framebuffer *fb, vma->dpt = dpt; vma->node = dpt->ggtt_node[tile0->id]; + + /* Ensure DPT writes are flushed */ + xe_device_l2_flush(xe); return 0; } @@ -333,8 +336,6 @@ static struct i915_vma *__xe_pin_fb_vma(const struct intel_framebuffer *fb, if (ret) goto err_unpin; - /* Ensure DPT writes are flushed */ - xe_device_l2_flush(xe); return vma; err_unpin: diff --git a/drivers/gpu/drm/xe/regs/xe_mchbar_regs.h b/drivers/gpu/drm/xe/regs/xe_mchbar_regs.h index 5394a1373a6b..ef2bf984723f 100644 --- a/drivers/gpu/drm/xe/regs/xe_mchbar_regs.h +++ b/drivers/gpu/drm/xe/regs/xe_mchbar_regs.h @@ -40,6 +40,7 @@ #define PCU_CR_PACKAGE_RAPL_LIMIT XE_REG(MCHBAR_MIRROR_BASE_SNB + 0x59a0) #define PWR_LIM_VAL REG_GENMASK(14, 0) #define PWR_LIM_EN REG_BIT(15) +#define PWR_LIM REG_GENMASK(15, 0) #define PWR_LIM_TIME REG_GENMASK(23, 17) #define PWR_LIM_TIME_X REG_GENMASK(23, 22) #define PWR_LIM_TIME_Y REG_GENMASK(21, 17) diff --git a/drivers/gpu/drm/xe/xe_ggtt.c b/drivers/gpu/drm/xe/xe_ggtt.c index 7062115909f2..2c799958c1e4 100644 --- a/drivers/gpu/drm/xe/xe_ggtt.c +++ b/drivers/gpu/drm/xe/xe_ggtt.c @@ -201,6 +201,13 @@ static const struct xe_ggtt_pt_ops xelpg_pt_wa_ops = { .ggtt_set_pte = xe_ggtt_set_pte_and_flush, }; +static void dev_fini_ggtt(void *arg) +{ + struct xe_ggtt *ggtt = arg; + + drain_workqueue(ggtt->wq); +} + /** * xe_ggtt_init_early - Early GGTT initialization * @ggtt: the &xe_ggtt to be initialized @@ -257,6 +264,10 @@ int xe_ggtt_init_early(struct xe_ggtt *ggtt) if (err) return err; + err = devm_add_action_or_reset(xe->drm.dev, dev_fini_ggtt, ggtt); + if (err) + return err; + if (IS_SRIOV_VF(xe)) { err = xe_gt_sriov_vf_prepare_ggtt(xe_tile_get_gt(ggtt->tile, 0)); if (err) diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c index d0ac48d8f4f7..bbcbb348256f 100644 --- a/drivers/gpu/drm/xe/xe_guc_ct.c +++ b/drivers/gpu/drm/xe/xe_guc_ct.c @@ -34,6 +34,11 @@ #include "xe_pm.h" #include "xe_trace_guc.h" +static void receive_g2h(struct xe_guc_ct *ct); +static void g2h_worker_func(struct work_struct *w); +static void safe_mode_worker_func(struct work_struct *w); +static void ct_exit_safe_mode(struct xe_guc_ct *ct); + #if IS_ENABLED(CONFIG_DRM_XE_DEBUG) enum { /* Internal states, not error conditions */ @@ -186,14 +191,11 @@ static void guc_ct_fini(struct drm_device *drm, void *arg) { struct xe_guc_ct *ct = arg; + ct_exit_safe_mode(ct); destroy_workqueue(ct->g2h_wq); xa_destroy(&ct->fence_lookup); } -static void receive_g2h(struct xe_guc_ct *ct); -static void g2h_worker_func(struct work_struct *w); -static void safe_mode_worker_func(struct work_struct *w); - static void primelockdep(struct xe_guc_ct *ct) { if (!IS_ENABLED(CONFIG_LOCKDEP)) diff --git a/drivers/gpu/drm/xe/xe_hwmon.c b/drivers/gpu/drm/xe/xe_hwmon.c index 74f31639b37f..f008e8049700 100644 --- a/drivers/gpu/drm/xe/xe_hwmon.c +++ b/drivers/gpu/drm/xe/xe_hwmon.c @@ -159,8 +159,8 @@ static int xe_hwmon_pcode_read_power_limit(const struct xe_hwmon *hwmon, u32 att return ret; } -static int xe_hwmon_pcode_write_power_limit(const struct xe_hwmon *hwmon, u32 attr, u8 channel, - u32 uval) +static int xe_hwmon_pcode_rmw_power_limit(const struct xe_hwmon *hwmon, u32 attr, u8 channel, + u32 clr, u32 set) { struct xe_tile *root_tile = xe_device_get_root_tile(hwmon->xe); u32 val0, val1; @@ -179,7 +179,7 @@ static int xe_hwmon_pcode_write_power_limit(const struct xe_hwmon *hwmon, u32 at channel, val0, val1, ret); if (attr == PL1_HWMON_ATTR) - val0 = uval; + val0 = (val0 & ~clr) | set; else return -EIO; @@ -339,7 +339,7 @@ static int xe_hwmon_power_max_write(struct xe_hwmon *hwmon, u32 attr, int channe if (hwmon->xe->info.has_mbx_power_limits) { drm_dbg(&hwmon->xe->drm, "disabling %s on channel %d\n", PWR_ATTR_TO_STR(attr), channel); - xe_hwmon_pcode_write_power_limit(hwmon, attr, channel, 0); + xe_hwmon_pcode_rmw_power_limit(hwmon, attr, channel, PWR_LIM_EN, 0); xe_hwmon_pcode_read_power_limit(hwmon, attr, channel, ®_val); } else { reg_val = xe_mmio_rmw32(mmio, rapl_limit, PWR_LIM_EN, 0); @@ -370,10 +370,9 @@ static int xe_hwmon_power_max_write(struct xe_hwmon *hwmon, u32 attr, int channe } if (hwmon->xe->info.has_mbx_power_limits) - ret = xe_hwmon_pcode_write_power_limit(hwmon, attr, channel, reg_val); + ret = xe_hwmon_pcode_rmw_power_limit(hwmon, attr, channel, PWR_LIM, reg_val); else - reg_val = xe_mmio_rmw32(mmio, rapl_limit, PWR_LIM_EN | PWR_LIM_VAL, - reg_val); + reg_val = xe_mmio_rmw32(mmio, rapl_limit, PWR_LIM, reg_val); unlock: mutex_unlock(&hwmon->hwmon_lock); return ret; @@ -563,14 +562,11 @@ xe_hwmon_power_max_interval_store(struct device *dev, struct device_attribute *a mutex_lock(&hwmon->hwmon_lock); - if (hwmon->xe->info.has_mbx_power_limits) { - ret = xe_hwmon_pcode_read_power_limit(hwmon, power_attr, channel, (u32 *)&r); - r = (r & ~PWR_LIM_TIME) | rxy; - xe_hwmon_pcode_write_power_limit(hwmon, power_attr, channel, r); - } else { + if (hwmon->xe->info.has_mbx_power_limits) + xe_hwmon_pcode_rmw_power_limit(hwmon, power_attr, channel, PWR_LIM_TIME, rxy); + else r = xe_mmio_rmw32(mmio, xe_hwmon_get_reg(hwmon, REG_PKG_RAPL_LIMIT, channel), PWR_LIM_TIME, rxy); - } mutex_unlock(&hwmon->hwmon_lock); @@ -1138,12 +1134,12 @@ xe_hwmon_get_preregistration_info(struct xe_hwmon *hwmon) } else { drm_info(&hwmon->xe->drm, "Using mailbox commands for power limits\n"); /* Write default limits to read from pcode from now on. */ - xe_hwmon_pcode_write_power_limit(hwmon, PL1_HWMON_ATTR, - CHANNEL_CARD, - hwmon->pl1_on_boot[CHANNEL_CARD]); - xe_hwmon_pcode_write_power_limit(hwmon, PL1_HWMON_ATTR, - CHANNEL_PKG, - hwmon->pl1_on_boot[CHANNEL_PKG]); + xe_hwmon_pcode_rmw_power_limit(hwmon, PL1_HWMON_ATTR, + CHANNEL_CARD, PWR_LIM | PWR_LIM_TIME, + hwmon->pl1_on_boot[CHANNEL_CARD]); + xe_hwmon_pcode_rmw_power_limit(hwmon, PL1_HWMON_ATTR, + CHANNEL_PKG, PWR_LIM | PWR_LIM_TIME, + hwmon->pl1_on_boot[CHANNEL_PKG]); hwmon->scl_shift_power = PWR_UNIT; hwmon->scl_shift_energy = ENERGY_UNIT; hwmon->scl_shift_time = TIME_UNIT; diff --git a/drivers/hid/hid-appletb-kbd.c b/drivers/hid/hid-appletb-kbd.c index 6f251b284018..2e0caf52af13 100644 --- a/drivers/hid/hid-appletb-kbd.c +++ b/drivers/hid/hid-appletb-kbd.c @@ -438,6 +438,8 @@ static int appletb_kbd_probe(struct hid_device *hdev, const struct hid_device_id return 0; close_hw: + if (kbd->backlight_dev) + put_device(&kbd->backlight_dev->dev); hid_hw_close(hdev); stop_hw: hid_hw_stop(hdev); @@ -453,6 +455,9 @@ static void appletb_kbd_remove(struct hid_device *hdev) input_unregister_handler(&kbd->inp_handler); timer_delete_sync(&kbd->inactivity_timer); + if (kbd->backlight_dev) + put_device(&kbd->backlight_dev->dev); + hid_hw_close(hdev); hid_hw_stop(hdev); } diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index e3fb4e2fe911..c6468568aea1 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -312,6 +312,8 @@ #define USB_DEVICE_ID_ASUS_AK1D 0x1125 #define USB_DEVICE_ID_CHICONY_TOSHIBA_WT10A 0x1408 #define USB_DEVICE_ID_CHICONY_ACER_SWITCH12 0x1421 +#define USB_DEVICE_ID_CHICONY_HP_5MP_CAMERA 0xb824 +#define USB_DEVICE_ID_CHICONY_HP_5MP_CAMERA2 0xb82c #define USB_VENDOR_ID_CHUNGHWAT 0x2247 #define USB_DEVICE_ID_CHUNGHWAT_MULTITOUCH 0x0001 @@ -819,6 +821,7 @@ #define USB_DEVICE_ID_LENOVO_TPPRODOCK 0x6067 #define USB_DEVICE_ID_LENOVO_X1_COVER 0x6085 #define USB_DEVICE_ID_LENOVO_X1_TAB 0x60a3 +#define USB_DEVICE_ID_LENOVO_X1_TAB2 0x60a4 #define USB_DEVICE_ID_LENOVO_X1_TAB3 0x60b5 #define USB_DEVICE_ID_LENOVO_X12_TAB 0x60fe #define USB_DEVICE_ID_LENOVO_X12_TAB2 0x61ae @@ -1525,4 +1528,7 @@ #define USB_VENDOR_ID_SIGNOTEC 0x2133 #define USB_DEVICE_ID_SIGNOTEC_VIEWSONIC_PD1011 0x0018 +#define USB_VENDOR_ID_SMARTLINKTECHNOLOGY 0x4c4a +#define USB_DEVICE_ID_SMARTLINKTECHNOLOGY_4155 0x4155 + #endif diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c index 9d80635a91eb..ff1784b5c2a4 100644 --- a/drivers/hid/hid-input.c +++ b/drivers/hid/hid-input.c @@ -2343,7 +2343,7 @@ int hidinput_connect(struct hid_device *hid, unsigned int force) } if (list_empty(&hid->inputs)) { - hid_err(hid, "No inputs registered, leaving\n"); + hid_dbg(hid, "No inputs registered, leaving\n"); goto out_unwind; } diff --git a/drivers/hid/hid-lenovo.c b/drivers/hid/hid-lenovo.c index af29ba840522..b3121fa7a72d 100644 --- a/drivers/hid/hid-lenovo.c +++ b/drivers/hid/hid-lenovo.c @@ -492,6 +492,7 @@ static int lenovo_input_mapping(struct hid_device *hdev, case USB_DEVICE_ID_LENOVO_X12_TAB: case USB_DEVICE_ID_LENOVO_X12_TAB2: case USB_DEVICE_ID_LENOVO_X1_TAB: + case USB_DEVICE_ID_LENOVO_X1_TAB2: case USB_DEVICE_ID_LENOVO_X1_TAB3: return lenovo_input_mapping_x1_tab_kbd(hdev, hi, field, usage, bit, max); default: @@ -548,11 +549,14 @@ static void lenovo_features_set_cptkbd(struct hid_device *hdev) /* * Tell the keyboard a driver understands it, and turn F7, F9, F11 into - * regular keys + * regular keys (Compact only) */ - ret = lenovo_send_cmd_cptkbd(hdev, 0x01, 0x03); - if (ret) - hid_warn(hdev, "Failed to switch F7/9/11 mode: %d\n", ret); + if (hdev->product == USB_DEVICE_ID_LENOVO_CUSBKBD || + hdev->product == USB_DEVICE_ID_LENOVO_CBTKBD) { + ret = lenovo_send_cmd_cptkbd(hdev, 0x01, 0x03); + if (ret) + hid_warn(hdev, "Failed to switch F7/9/11 mode: %d\n", ret); + } /* Switch middle button to native mode */ ret = lenovo_send_cmd_cptkbd(hdev, 0x09, 0x01); @@ -605,6 +609,7 @@ static ssize_t attr_fn_lock_store(struct device *dev, case USB_DEVICE_ID_LENOVO_X12_TAB2: case USB_DEVICE_ID_LENOVO_TP10UBKBD: case USB_DEVICE_ID_LENOVO_X1_TAB: + case USB_DEVICE_ID_LENOVO_X1_TAB2: case USB_DEVICE_ID_LENOVO_X1_TAB3: ret = lenovo_led_set_tp10ubkbd(hdev, TP10UBKBD_FN_LOCK_LED, value); if (ret) @@ -861,6 +866,7 @@ static int lenovo_event(struct hid_device *hdev, struct hid_field *field, case USB_DEVICE_ID_LENOVO_X12_TAB2: case USB_DEVICE_ID_LENOVO_TP10UBKBD: case USB_DEVICE_ID_LENOVO_X1_TAB: + case USB_DEVICE_ID_LENOVO_X1_TAB2: case USB_DEVICE_ID_LENOVO_X1_TAB3: return lenovo_event_tp10ubkbd(hdev, field, usage, value); default: @@ -1144,6 +1150,7 @@ static int lenovo_led_brightness_set(struct led_classdev *led_cdev, case USB_DEVICE_ID_LENOVO_X12_TAB2: case USB_DEVICE_ID_LENOVO_TP10UBKBD: case USB_DEVICE_ID_LENOVO_X1_TAB: + case USB_DEVICE_ID_LENOVO_X1_TAB2: case USB_DEVICE_ID_LENOVO_X1_TAB3: ret = lenovo_led_set_tp10ubkbd(hdev, tp10ubkbd_led[led_nr], value); break; @@ -1384,6 +1391,7 @@ static int lenovo_probe(struct hid_device *hdev, case USB_DEVICE_ID_LENOVO_X12_TAB2: case USB_DEVICE_ID_LENOVO_TP10UBKBD: case USB_DEVICE_ID_LENOVO_X1_TAB: + case USB_DEVICE_ID_LENOVO_X1_TAB2: case USB_DEVICE_ID_LENOVO_X1_TAB3: ret = lenovo_probe_tp10ubkbd(hdev); break; @@ -1473,6 +1481,7 @@ static void lenovo_remove(struct hid_device *hdev) case USB_DEVICE_ID_LENOVO_X12_TAB2: case USB_DEVICE_ID_LENOVO_TP10UBKBD: case USB_DEVICE_ID_LENOVO_X1_TAB: + case USB_DEVICE_ID_LENOVO_X1_TAB2: case USB_DEVICE_ID_LENOVO_X1_TAB3: lenovo_remove_tp10ubkbd(hdev); break; @@ -1524,6 +1533,8 @@ static const struct hid_device_id lenovo_devices[] = { { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_X1_TAB) }, { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, + USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_X1_TAB2) }, + { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_X1_TAB3) }, { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_X12_TAB) }, diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c index b41001e02da7..a1c54ffe02b4 100644 --- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -2132,12 +2132,18 @@ static const struct hid_device_id mt_devices[] = { HID_DEVICE(BUS_I2C, HID_GROUP_GENERIC, USB_VENDOR_ID_LG, I2C_DEVICE_ID_LG_7010) }, - /* Lenovo X1 TAB Gen 2 */ + /* Lenovo X1 TAB Gen 1 */ { .driver_data = MT_CLS_WIN_8_FORCE_MULTI_INPUT, HID_DEVICE(BUS_USB, HID_GROUP_MULTITOUCH_WIN_8, USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_X1_TAB) }, + /* Lenovo X1 TAB Gen 2 */ + { .driver_data = MT_CLS_WIN_8_FORCE_MULTI_INPUT, + HID_DEVICE(BUS_USB, HID_GROUP_MULTITOUCH_WIN_8, + USB_VENDOR_ID_LENOVO, + USB_DEVICE_ID_LENOVO_X1_TAB2) }, + /* Lenovo X1 TAB Gen 3 */ { .driver_data = MT_CLS_WIN_8_FORCE_MULTI_INPUT, HID_DEVICE(BUS_USB, HID_GROUP_MULTITOUCH_WIN_8, diff --git a/drivers/hid/hid-nintendo.c b/drivers/hid/hid-nintendo.c index 839d5bcd72b1..fb4985988615 100644 --- a/drivers/hid/hid-nintendo.c +++ b/drivers/hid/hid-nintendo.c @@ -308,6 +308,7 @@ enum joycon_ctlr_state { JOYCON_CTLR_STATE_INIT, JOYCON_CTLR_STATE_READ, JOYCON_CTLR_STATE_REMOVED, + JOYCON_CTLR_STATE_SUSPENDED, }; /* Controller type received as part of device info */ @@ -2750,14 +2751,46 @@ static void nintendo_hid_remove(struct hid_device *hdev) static int nintendo_hid_resume(struct hid_device *hdev) { - int ret = joycon_init(hdev); + struct joycon_ctlr *ctlr = hid_get_drvdata(hdev); + int ret; + + hid_dbg(hdev, "resume\n"); + if (!joycon_using_usb(ctlr)) { + hid_dbg(hdev, "no-op resume for bt ctlr\n"); + ctlr->ctlr_state = JOYCON_CTLR_STATE_READ; + return 0; + } + ret = joycon_init(hdev); if (ret) - hid_err(hdev, "Failed to restore controller after resume"); + hid_err(hdev, + "Failed to restore controller after resume: %d\n", + ret); + else + ctlr->ctlr_state = JOYCON_CTLR_STATE_READ; return ret; } +static int nintendo_hid_suspend(struct hid_device *hdev, pm_message_t message) +{ + struct joycon_ctlr *ctlr = hid_get_drvdata(hdev); + + hid_dbg(hdev, "suspend: %d\n", message.event); + /* + * Avoid any blocking loops in suspend/resume transitions. + * + * joycon_enforce_subcmd_rate() can result in repeated retries if for + * whatever reason the controller stops providing input reports. + * + * This has been observed with bluetooth controllers which lose + * connectivity prior to suspend (but not long enough to result in + * complete disconnection). + */ + ctlr->ctlr_state = JOYCON_CTLR_STATE_SUSPENDED; + return 0; +} + #endif static const struct hid_device_id nintendo_hid_devices[] = { @@ -2796,6 +2829,7 @@ static struct hid_driver nintendo_hid_driver = { #ifdef CONFIG_PM .resume = nintendo_hid_resume, + .suspend = nintendo_hid_suspend, #endif }; static int __init nintendo_init(void) diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c index 7fefeb413ec3..31508da93ba2 100644 --- a/drivers/hid/hid-quirks.c +++ b/drivers/hid/hid-quirks.c @@ -757,6 +757,8 @@ static const struct hid_device_id hid_ignore_list[] = { { HID_USB_DEVICE(USB_VENDOR_ID_AVERMEDIA, USB_DEVICE_ID_AVER_FM_MR800) }, { HID_USB_DEVICE(USB_VENDOR_ID_AXENTIA, USB_DEVICE_ID_AXENTIA_FM_RADIO) }, { HID_USB_DEVICE(USB_VENDOR_ID_BERKSHIRE, USB_DEVICE_ID_BERKSHIRE_PCWD) }, + { HID_USB_DEVICE(USB_VENDOR_ID_CHICONY, USB_DEVICE_ID_CHICONY_HP_5MP_CAMERA) }, + { HID_USB_DEVICE(USB_VENDOR_ID_CHICONY, USB_DEVICE_ID_CHICONY_HP_5MP_CAMERA2) }, { HID_USB_DEVICE(USB_VENDOR_ID_CIDC, 0x0103) }, { HID_USB_DEVICE(USB_VENDOR_ID_CYGNAL, USB_DEVICE_ID_CYGNAL_RADIO_SI470X) }, { HID_USB_DEVICE(USB_VENDOR_ID_CYGNAL, USB_DEVICE_ID_CYGNAL_RADIO_SI4713) }, @@ -904,6 +906,7 @@ static const struct hid_device_id hid_ignore_list[] = { #endif { HID_USB_DEVICE(USB_VENDOR_ID_YEALINK, USB_DEVICE_ID_YEALINK_P1K_P4K_B2K) }, { HID_USB_DEVICE(USB_VENDOR_ID_QUANTA, USB_DEVICE_ID_QUANTA_HP_5MP_CAMERA_5473) }, + { HID_USB_DEVICE(USB_VENDOR_ID_SMARTLINKTECHNOLOGY, USB_DEVICE_ID_SMARTLINKTECHNOLOGY_4155) }, { } }; diff --git a/drivers/hid/intel-ish-hid/ipc/hw-ish.h b/drivers/hid/intel-ish-hid/ipc/hw-ish.h index 07e90d51f073..fa5d68c36313 100644 --- a/drivers/hid/intel-ish-hid/ipc/hw-ish.h +++ b/drivers/hid/intel-ish-hid/ipc/hw-ish.h @@ -38,6 +38,7 @@ #define PCI_DEVICE_ID_INTEL_ISH_LNL_M 0xA845 #define PCI_DEVICE_ID_INTEL_ISH_PTL_H 0xE345 #define PCI_DEVICE_ID_INTEL_ISH_PTL_P 0xE445 +#define PCI_DEVICE_ID_INTEL_ISH_WCL 0x4D45 #define REVISION_ID_CHT_A0 0x6 #define REVISION_ID_CHT_Ax_SI 0x0 diff --git a/drivers/hid/intel-ish-hid/ipc/pci-ish.c b/drivers/hid/intel-ish-hid/ipc/pci-ish.c index ff0fc8010072..c57483224db6 100644 --- a/drivers/hid/intel-ish-hid/ipc/pci-ish.c +++ b/drivers/hid/intel-ish-hid/ipc/pci-ish.c @@ -27,10 +27,12 @@ enum ishtp_driver_data_index { ISHTP_DRIVER_DATA_NONE, ISHTP_DRIVER_DATA_LNL_M, ISHTP_DRIVER_DATA_PTL, + ISHTP_DRIVER_DATA_WCL, }; #define ISH_FW_GEN_LNL_M "lnlm" #define ISH_FW_GEN_PTL "ptl" +#define ISH_FW_GEN_WCL "wcl" #define ISH_FIRMWARE_PATH(gen) "intel/ish/ish_" gen ".bin" #define ISH_FIRMWARE_PATH_ALL "intel/ish/ish_*.bin" @@ -42,6 +44,9 @@ static struct ishtp_driver_data ishtp_driver_data[] = { [ISHTP_DRIVER_DATA_PTL] = { .fw_generation = ISH_FW_GEN_PTL, }, + [ISHTP_DRIVER_DATA_WCL] = { + .fw_generation = ISH_FW_GEN_WCL, + }, }; static const struct pci_device_id ish_pci_tbl[] = { @@ -67,9 +72,10 @@ static const struct pci_device_id ish_pci_tbl[] = { {PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ISH_MTL_P)}, {PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ISH_ARL_H)}, {PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ISH_ARL_S)}, - {PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ISH_LNL_M), .driver_data = ISHTP_DRIVER_DATA_LNL_M}, - {PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ISH_PTL_H), .driver_data = ISHTP_DRIVER_DATA_PTL}, - {PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ISH_PTL_P), .driver_data = ISHTP_DRIVER_DATA_PTL}, + {PCI_DEVICE_DATA(INTEL, ISH_LNL_M, ISHTP_DRIVER_DATA_LNL_M)}, + {PCI_DEVICE_DATA(INTEL, ISH_PTL_H, ISHTP_DRIVER_DATA_PTL)}, + {PCI_DEVICE_DATA(INTEL, ISH_PTL_P, ISHTP_DRIVER_DATA_PTL)}, + {PCI_DEVICE_DATA(INTEL, ISH_WCL, ISHTP_DRIVER_DATA_WCL)}, {} }; MODULE_DEVICE_TABLE(pci, ish_pci_tbl); diff --git a/drivers/hid/intel-thc-hid/intel-quicki2c/quicki2c-protocol.c b/drivers/hid/intel-thc-hid/intel-quicki2c/quicki2c-protocol.c index f493df0d5dc4..a63f8c833252 100644 --- a/drivers/hid/intel-thc-hid/intel-quicki2c/quicki2c-protocol.c +++ b/drivers/hid/intel-thc-hid/intel-quicki2c/quicki2c-protocol.c @@ -4,6 +4,7 @@ #include <linux/bitfield.h> #include <linux/hid.h> #include <linux/hid-over-i2c.h> +#include <linux/unaligned.h> #include "intel-thc-dev.h" #include "intel-thc-dma.h" @@ -200,6 +201,9 @@ int quicki2c_set_report(struct quicki2c_device *qcdev, u8 report_type, int quicki2c_reset(struct quicki2c_device *qcdev) { + u16 input_reg = le16_to_cpu(qcdev->dev_desc.input_reg); + size_t read_len = HIDI2C_LENGTH_LEN; + u32 prd_len = read_len; int ret; qcdev->reset_ack = false; @@ -213,12 +217,32 @@ int quicki2c_reset(struct quicki2c_device *qcdev) ret = wait_event_interruptible_timeout(qcdev->reset_ack_wq, qcdev->reset_ack, HIDI2C_RESET_TIMEOUT * HZ); - if (ret <= 0 || !qcdev->reset_ack) { + if (qcdev->reset_ack) + return 0; + + /* + * Manually read reset response if it wasn't received, in case reset interrupt + * was missed by touch device or THC hardware. + */ + ret = thc_tic_pio_read(qcdev->thc_hw, input_reg, read_len, &prd_len, + (u32 *)qcdev->input_buf); + if (ret) { + dev_err_once(qcdev->dev, "Read Reset Response failed, ret %d\n", ret); + return ret; + } + + /* + * Check response packet length, it's first 16 bits of packet. + * If response packet length is zero, it's reset response, otherwise not. + */ + if (get_unaligned_le16(qcdev->input_buf)) { dev_err_once(qcdev->dev, "Wait reset response timed out ret:%d timeout:%ds\n", ret, HIDI2C_RESET_TIMEOUT); return -ETIMEDOUT; } + qcdev->reset_ack = true; + return 0; } diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c index eaf099b2efdb..9a57504e51a1 100644 --- a/drivers/hid/wacom_sys.c +++ b/drivers/hid/wacom_sys.c @@ -2048,14 +2048,18 @@ static int wacom_initialize_remotes(struct wacom *wacom) remote->remote_dir = kobject_create_and_add("wacom_remote", &wacom->hdev->dev.kobj); - if (!remote->remote_dir) + if (!remote->remote_dir) { + kfifo_free(&remote->remote_fifo); return -ENOMEM; + } error = sysfs_create_files(remote->remote_dir, remote_unpair_attrs); if (error) { hid_err(wacom->hdev, "cannot create sysfs group err: %d\n", error); + kfifo_free(&remote->remote_fifo); + kobject_put(remote->remote_dir); return error; } @@ -2901,6 +2905,7 @@ static void wacom_remove(struct hid_device *hdev) hid_hw_stop(hdev); cancel_delayed_work_sync(&wacom->init_work); + cancel_delayed_work_sync(&wacom->aes_battery_work); cancel_work_sync(&wacom->wireless_work); cancel_work_sync(&wacom->battery_work); cancel_work_sync(&wacom->remote_work); diff --git a/drivers/md/bcache/Kconfig b/drivers/md/bcache/Kconfig index d4697e79d5a3..b2d10063d35f 100644 --- a/drivers/md/bcache/Kconfig +++ b/drivers/md/bcache/Kconfig @@ -5,7 +5,6 @@ config BCACHE select BLOCK_HOLDER_DEPRECATED if SYSFS select CRC64 select CLOSURES - select MIN_HEAP help Allows a block device to be used as cache for other devices; uses a btree for indexing and the layout is optimized for SSDs. diff --git a/drivers/md/bcache/alloc.c b/drivers/md/bcache/alloc.c index 8998e61efa40..48ce750bf70a 100644 --- a/drivers/md/bcache/alloc.c +++ b/drivers/md/bcache/alloc.c @@ -164,61 +164,40 @@ static void bch_invalidate_one_bucket(struct cache *ca, struct bucket *b) * prio is worth 1/8th of what INITIAL_PRIO is worth. */ -static inline unsigned int new_bucket_prio(struct cache *ca, struct bucket *b) -{ - unsigned int min_prio = (INITIAL_PRIO - ca->set->min_prio) / 8; - - return (b->prio - ca->set->min_prio + min_prio) * GC_SECTORS_USED(b); -} - -static inline bool new_bucket_max_cmp(const void *l, const void *r, void *args) -{ - struct bucket **lhs = (struct bucket **)l; - struct bucket **rhs = (struct bucket **)r; - struct cache *ca = args; - - return new_bucket_prio(ca, *lhs) > new_bucket_prio(ca, *rhs); -} - -static inline bool new_bucket_min_cmp(const void *l, const void *r, void *args) -{ - struct bucket **lhs = (struct bucket **)l; - struct bucket **rhs = (struct bucket **)r; - struct cache *ca = args; +#define bucket_prio(b) \ +({ \ + unsigned int min_prio = (INITIAL_PRIO - ca->set->min_prio) / 8; \ + \ + (b->prio - ca->set->min_prio + min_prio) * GC_SECTORS_USED(b); \ +}) - return new_bucket_prio(ca, *lhs) < new_bucket_prio(ca, *rhs); -} +#define bucket_max_cmp(l, r) (bucket_prio(l) < bucket_prio(r)) +#define bucket_min_cmp(l, r) (bucket_prio(l) > bucket_prio(r)) static void invalidate_buckets_lru(struct cache *ca) { struct bucket *b; - const struct min_heap_callbacks bucket_max_cmp_callback = { - .less = new_bucket_max_cmp, - .swp = NULL, - }; - const struct min_heap_callbacks bucket_min_cmp_callback = { - .less = new_bucket_min_cmp, - .swp = NULL, - }; + ssize_t i; - ca->heap.nr = 0; + ca->heap.used = 0; for_each_bucket(b, ca) { if (!bch_can_invalidate_bucket(ca, b)) continue; - if (!min_heap_full(&ca->heap)) - min_heap_push(&ca->heap, &b, &bucket_max_cmp_callback, ca); - else if (!new_bucket_max_cmp(&b, min_heap_peek(&ca->heap), ca)) { + if (!heap_full(&ca->heap)) + heap_add(&ca->heap, b, bucket_max_cmp); + else if (bucket_max_cmp(b, heap_peek(&ca->heap))) { ca->heap.data[0] = b; - min_heap_sift_down(&ca->heap, 0, &bucket_max_cmp_callback, ca); + heap_sift(&ca->heap, 0, bucket_max_cmp); } } - min_heapify_all(&ca->heap, &bucket_min_cmp_callback, ca); + for (i = ca->heap.used / 2 - 1; i >= 0; --i) + heap_sift(&ca->heap, i, bucket_min_cmp); while (!fifo_full(&ca->free_inc)) { - if (!ca->heap.nr) { + if (!heap_pop(&ca->heap, b, bucket_min_cmp)) { /* * We don't want to be calling invalidate_buckets() * multiple times when it can't do anything @@ -227,8 +206,6 @@ static void invalidate_buckets_lru(struct cache *ca) wake_up_gc(ca->set); return; } - b = min_heap_peek(&ca->heap)[0]; - min_heap_pop(&ca->heap, &bucket_min_cmp_callback, ca); bch_invalidate_one_bucket(ca, b); } diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h index 785b0d9008fa..1d33e40d26ea 100644 --- a/drivers/md/bcache/bcache.h +++ b/drivers/md/bcache/bcache.h @@ -458,7 +458,7 @@ struct cache { /* Allocation stuff: */ struct bucket *buckets; - DEFINE_MIN_HEAP(struct bucket *, cache_heap) heap; + DECLARE_HEAP(struct bucket *, heap); /* * If nonzero, we know we aren't going to find any buckets to invalidate diff --git a/drivers/md/bcache/bset.c b/drivers/md/bcache/bset.c index 68258a16e125..463eb13bd0b2 100644 --- a/drivers/md/bcache/bset.c +++ b/drivers/md/bcache/bset.c @@ -54,11 +54,9 @@ void bch_dump_bucket(struct btree_keys *b) int __bch_count_data(struct btree_keys *b) { unsigned int ret = 0; - struct btree_iter iter; + struct btree_iter_stack iter; struct bkey *k; - min_heap_init(&iter.heap, NULL, MAX_BSETS); - if (b->ops->is_extents) for_each_key(b, k, &iter) ret += KEY_SIZE(k); @@ -69,11 +67,9 @@ void __bch_check_keys(struct btree_keys *b, const char *fmt, ...) { va_list args; struct bkey *k, *p = NULL; - struct btree_iter iter; + struct btree_iter_stack iter; const char *err; - min_heap_init(&iter.heap, NULL, MAX_BSETS); - for_each_key(b, k, &iter) { if (b->ops->is_extents) { err = "Keys out of order"; @@ -114,9 +110,9 @@ bug: static void bch_btree_iter_next_check(struct btree_iter *iter) { - struct bkey *k = iter->heap.data->k, *next = bkey_next(k); + struct bkey *k = iter->data->k, *next = bkey_next(k); - if (next < iter->heap.data->end && + if (next < iter->data->end && bkey_cmp(k, iter->b->ops->is_extents ? &START_KEY(next) : next) > 0) { bch_dump_bucket(iter->b); @@ -883,14 +879,12 @@ unsigned int bch_btree_insert_key(struct btree_keys *b, struct bkey *k, unsigned int status = BTREE_INSERT_STATUS_NO_INSERT; struct bset *i = bset_tree_last(b)->data; struct bkey *m, *prev = NULL; - struct btree_iter iter; + struct btree_iter_stack iter; struct bkey preceding_key_on_stack = ZERO_KEY; struct bkey *preceding_key_p = &preceding_key_on_stack; BUG_ON(b->ops->is_extents && !KEY_SIZE(k)); - min_heap_init(&iter.heap, NULL, MAX_BSETS); - /* * If k has preceding key, preceding_key_p will be set to address * of k's preceding key; otherwise preceding_key_p will be set @@ -901,9 +895,9 @@ unsigned int bch_btree_insert_key(struct btree_keys *b, struct bkey *k, else preceding_key(k, &preceding_key_p); - m = bch_btree_iter_init(b, &iter, preceding_key_p); + m = bch_btree_iter_stack_init(b, &iter, preceding_key_p); - if (b->ops->insert_fixup(b, k, &iter, replace_key)) + if (b->ops->insert_fixup(b, k, &iter.iter, replace_key)) return status; status = BTREE_INSERT_STATUS_INSERT; @@ -1083,94 +1077,79 @@ struct bkey *__bch_bset_search(struct btree_keys *b, struct bset_tree *t, /* Btree iterator */ -typedef bool (new_btree_iter_cmp_fn)(const void *, const void *, void *); +typedef bool (btree_iter_cmp_fn)(struct btree_iter_set, + struct btree_iter_set); -static inline bool new_btree_iter_cmp(const void *l, const void *r, void __always_unused *args) +static inline bool btree_iter_cmp(struct btree_iter_set l, + struct btree_iter_set r) { - const struct btree_iter_set *_l = l; - const struct btree_iter_set *_r = r; - - return bkey_cmp(_l->k, _r->k) <= 0; + return bkey_cmp(l.k, r.k) > 0; } static inline bool btree_iter_end(struct btree_iter *iter) { - return !iter->heap.nr; + return !iter->used; } void bch_btree_iter_push(struct btree_iter *iter, struct bkey *k, struct bkey *end) { - const struct min_heap_callbacks callbacks = { - .less = new_btree_iter_cmp, - .swp = NULL, - }; - if (k != end) - BUG_ON(!min_heap_push(&iter->heap, - &((struct btree_iter_set) { k, end }), - &callbacks, - NULL)); + BUG_ON(!heap_add(iter, + ((struct btree_iter_set) { k, end }), + btree_iter_cmp)); } -static struct bkey *__bch_btree_iter_init(struct btree_keys *b, - struct btree_iter *iter, - struct bkey *search, - struct bset_tree *start) +static struct bkey *__bch_btree_iter_stack_init(struct btree_keys *b, + struct btree_iter_stack *iter, + struct bkey *search, + struct bset_tree *start) { struct bkey *ret = NULL; - iter->heap.size = ARRAY_SIZE(iter->heap.preallocated); - iter->heap.nr = 0; + iter->iter.size = ARRAY_SIZE(iter->stack_data); + iter->iter.used = 0; #ifdef CONFIG_BCACHE_DEBUG - iter->b = b; + iter->iter.b = b; #endif for (; start <= bset_tree_last(b); start++) { ret = bch_bset_search(b, start, search); - bch_btree_iter_push(iter, ret, bset_bkey_last(start->data)); + bch_btree_iter_push(&iter->iter, ret, bset_bkey_last(start->data)); } return ret; } -struct bkey *bch_btree_iter_init(struct btree_keys *b, - struct btree_iter *iter, +struct bkey *bch_btree_iter_stack_init(struct btree_keys *b, + struct btree_iter_stack *iter, struct bkey *search) { - return __bch_btree_iter_init(b, iter, search, b->set); + return __bch_btree_iter_stack_init(b, iter, search, b->set); } static inline struct bkey *__bch_btree_iter_next(struct btree_iter *iter, - new_btree_iter_cmp_fn *cmp) + btree_iter_cmp_fn *cmp) { struct btree_iter_set b __maybe_unused; struct bkey *ret = NULL; - const struct min_heap_callbacks callbacks = { - .less = cmp, - .swp = NULL, - }; if (!btree_iter_end(iter)) { bch_btree_iter_next_check(iter); - ret = iter->heap.data->k; - iter->heap.data->k = bkey_next(iter->heap.data->k); + ret = iter->data->k; + iter->data->k = bkey_next(iter->data->k); - if (iter->heap.data->k > iter->heap.data->end) { + if (iter->data->k > iter->data->end) { WARN_ONCE(1, "bset was corrupt!\n"); - iter->heap.data->k = iter->heap.data->end; + iter->data->k = iter->data->end; } - if (iter->heap.data->k == iter->heap.data->end) { - if (iter->heap.nr) { - b = min_heap_peek(&iter->heap)[0]; - min_heap_pop(&iter->heap, &callbacks, NULL); - } - } + if (iter->data->k == iter->data->end) + heap_pop(iter, b, cmp); else - min_heap_sift_down(&iter->heap, 0, &callbacks, NULL); + heap_sift(iter, 0, cmp); } return ret; @@ -1178,7 +1157,7 @@ static inline struct bkey *__bch_btree_iter_next(struct btree_iter *iter, struct bkey *bch_btree_iter_next(struct btree_iter *iter) { - return __bch_btree_iter_next(iter, new_btree_iter_cmp); + return __bch_btree_iter_next(iter, btree_iter_cmp); } @@ -1216,18 +1195,16 @@ static void btree_mergesort(struct btree_keys *b, struct bset *out, struct btree_iter *iter, bool fixup, bool remove_stale) { + int i; struct bkey *k, *last = NULL; BKEY_PADDED(k) tmp; bool (*bad)(struct btree_keys *, const struct bkey *) = remove_stale ? bch_ptr_bad : bch_ptr_invalid; - const struct min_heap_callbacks callbacks = { - .less = b->ops->sort_cmp, - .swp = NULL, - }; /* Heapify the iterator, using our comparison function */ - min_heapify_all(&iter->heap, &callbacks, NULL); + for (i = iter->used / 2 - 1; i >= 0; --i) + heap_sift(iter, i, b->ops->sort_cmp); while (!btree_iter_end(iter)) { if (b->ops->sort_fixup && fixup) @@ -1316,11 +1293,10 @@ void bch_btree_sort_partial(struct btree_keys *b, unsigned int start, struct bset_sort_state *state) { size_t order = b->page_order, keys = 0; - struct btree_iter iter; + struct btree_iter_stack iter; int oldsize = bch_count_data(b); - min_heap_init(&iter.heap, NULL, MAX_BSETS); - __bch_btree_iter_init(b, &iter, NULL, &b->set[start]); + __bch_btree_iter_stack_init(b, &iter, NULL, &b->set[start]); if (start) { unsigned int i; @@ -1331,7 +1307,7 @@ void bch_btree_sort_partial(struct btree_keys *b, unsigned int start, order = get_order(__set_bytes(b->set->data, keys)); } - __btree_sort(b, &iter, start, order, false, state); + __btree_sort(b, &iter.iter, start, order, false, state); EBUG_ON(oldsize >= 0 && bch_count_data(b) != oldsize); } @@ -1347,13 +1323,11 @@ void bch_btree_sort_into(struct btree_keys *b, struct btree_keys *new, struct bset_sort_state *state) { uint64_t start_time = local_clock(); - struct btree_iter iter; - - min_heap_init(&iter.heap, NULL, MAX_BSETS); + struct btree_iter_stack iter; - bch_btree_iter_init(b, &iter, NULL); + bch_btree_iter_stack_init(b, &iter, NULL); - btree_mergesort(b, new->set->data, &iter, false, true); + btree_mergesort(b, new->set->data, &iter.iter, false, true); bch_time_stats_update(&state->time, start_time); diff --git a/drivers/md/bcache/bset.h b/drivers/md/bcache/bset.h index f79441acd4c1..011f6062c4c0 100644 --- a/drivers/md/bcache/bset.h +++ b/drivers/md/bcache/bset.h @@ -187,9 +187,8 @@ struct bset_tree { }; struct btree_keys_ops { - bool (*sort_cmp)(const void *l, - const void *r, - void *args); + bool (*sort_cmp)(struct btree_iter_set l, + struct btree_iter_set r); struct bkey *(*sort_fixup)(struct btree_iter *iter, struct bkey *tmp); bool (*insert_fixup)(struct btree_keys *b, @@ -313,17 +312,23 @@ enum { BTREE_INSERT_STATUS_FRONT_MERGE, }; -struct btree_iter_set { - struct bkey *k, *end; -}; - /* Btree key iteration */ struct btree_iter { + size_t size, used; #ifdef CONFIG_BCACHE_DEBUG struct btree_keys *b; #endif - MIN_HEAP_PREALLOCATED(struct btree_iter_set, btree_iter_heap, MAX_BSETS) heap; + struct btree_iter_set { + struct bkey *k, *end; + } data[]; +}; + +/* Fixed-size btree_iter that can be allocated on the stack */ + +struct btree_iter_stack { + struct btree_iter iter; + struct btree_iter_set stack_data[MAX_BSETS]; }; typedef bool (*ptr_filter_fn)(struct btree_keys *b, const struct bkey *k); @@ -335,9 +340,9 @@ struct bkey *bch_btree_iter_next_filter(struct btree_iter *iter, void bch_btree_iter_push(struct btree_iter *iter, struct bkey *k, struct bkey *end); -struct bkey *bch_btree_iter_init(struct btree_keys *b, - struct btree_iter *iter, - struct bkey *search); +struct bkey *bch_btree_iter_stack_init(struct btree_keys *b, + struct btree_iter_stack *iter, + struct bkey *search); struct bkey *__bch_bset_search(struct btree_keys *b, struct bset_tree *t, const struct bkey *search); @@ -352,13 +357,14 @@ static inline struct bkey *bch_bset_search(struct btree_keys *b, return search ? __bch_bset_search(b, t, search) : t->data->start; } -#define for_each_key_filter(b, k, iter, filter) \ - for (bch_btree_iter_init((b), (iter), NULL); \ - ((k) = bch_btree_iter_next_filter((iter), (b), filter));) +#define for_each_key_filter(b, k, stack_iter, filter) \ + for (bch_btree_iter_stack_init((b), (stack_iter), NULL); \ + ((k) = bch_btree_iter_next_filter(&((stack_iter)->iter), (b), \ + filter));) -#define for_each_key(b, k, iter) \ - for (bch_btree_iter_init((b), (iter), NULL); \ - ((k) = bch_btree_iter_next(iter));) +#define for_each_key(b, k, stack_iter) \ + for (bch_btree_iter_stack_init((b), (stack_iter), NULL); \ + ((k) = bch_btree_iter_next(&((stack_iter)->iter)));) /* Sorting */ diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c index 1d0100677357..210b59007d98 100644 --- a/drivers/md/bcache/btree.c +++ b/drivers/md/bcache/btree.c @@ -148,19 +148,19 @@ void bch_btree_node_read_done(struct btree *b) { const char *err = "bad btree header"; struct bset *i = btree_bset_first(b); - struct btree_iter iter; + struct btree_iter *iter; /* * c->fill_iter can allocate an iterator with more memory space * than static MAX_BSETS. * See the comment arount cache_set->fill_iter. */ - iter.heap.data = mempool_alloc(&b->c->fill_iter, GFP_NOIO); - iter.heap.size = b->c->cache->sb.bucket_size / b->c->cache->sb.block_size; - iter.heap.nr = 0; + iter = mempool_alloc(&b->c->fill_iter, GFP_NOIO); + iter->size = b->c->cache->sb.bucket_size / b->c->cache->sb.block_size; + iter->used = 0; #ifdef CONFIG_BCACHE_DEBUG - iter.b = &b->keys; + iter->b = &b->keys; #endif if (!i->seq) @@ -198,7 +198,7 @@ void bch_btree_node_read_done(struct btree *b) if (i != b->keys.set[0].data && !i->keys) goto err; - bch_btree_iter_push(&iter, i->start, bset_bkey_last(i)); + bch_btree_iter_push(iter, i->start, bset_bkey_last(i)); b->written += set_blocks(i, block_bytes(b->c->cache)); } @@ -210,7 +210,7 @@ void bch_btree_node_read_done(struct btree *b) if (i->seq == b->keys.set[0].data->seq) goto err; - bch_btree_sort_and_fix_extents(&b->keys, &iter, &b->c->sort); + bch_btree_sort_and_fix_extents(&b->keys, iter, &b->c->sort); i = b->keys.set[0].data; err = "short btree key"; @@ -222,7 +222,7 @@ void bch_btree_node_read_done(struct btree *b) bch_bset_init_next(&b->keys, write_block(b), bset_magic(&b->c->cache->sb)); out: - mempool_free(iter.heap.data, &b->c->fill_iter); + mempool_free(iter, &b->c->fill_iter); return; err: set_btree_node_io_error(b); @@ -1306,11 +1306,9 @@ static bool btree_gc_mark_node(struct btree *b, struct gc_stat *gc) uint8_t stale = 0; unsigned int keys = 0, good_keys = 0; struct bkey *k; - struct btree_iter iter; + struct btree_iter_stack iter; struct bset_tree *t; - min_heap_init(&iter.heap, NULL, MAX_BSETS); - gc->nodes++; for_each_key_filter(&b->keys, k, &iter, bch_ptr_invalid) { @@ -1569,11 +1567,9 @@ static int btree_gc_rewrite_node(struct btree *b, struct btree_op *op, static unsigned int btree_gc_count_keys(struct btree *b) { struct bkey *k; - struct btree_iter iter; + struct btree_iter_stack iter; unsigned int ret = 0; - min_heap_init(&iter.heap, NULL, MAX_BSETS); - for_each_key_filter(&b->keys, k, &iter, bch_ptr_bad) ret += bkey_u64s(k); @@ -1612,18 +1608,18 @@ static int btree_gc_recurse(struct btree *b, struct btree_op *op, int ret = 0; bool should_rewrite; struct bkey *k; - struct btree_iter iter; + struct btree_iter_stack iter; struct gc_merge_info r[GC_MERGE_NODES]; struct gc_merge_info *i, *last = r + ARRAY_SIZE(r) - 1; - min_heap_init(&iter.heap, NULL, MAX_BSETS); - bch_btree_iter_init(&b->keys, &iter, &b->c->gc_done); + bch_btree_iter_stack_init(&b->keys, &iter, &b->c->gc_done); for (i = r; i < r + ARRAY_SIZE(r); i++) i->b = ERR_PTR(-EINTR); while (1) { - k = bch_btree_iter_next_filter(&iter, &b->keys, bch_ptr_bad); + k = bch_btree_iter_next_filter(&iter.iter, &b->keys, + bch_ptr_bad); if (k) { r->b = bch_btree_node_get(b->c, op, k, b->level - 1, true, b); @@ -1918,9 +1914,7 @@ static int bch_btree_check_recurse(struct btree *b, struct btree_op *op) { int ret = 0; struct bkey *k, *p = NULL; - struct btree_iter iter; - - min_heap_init(&iter.heap, NULL, MAX_BSETS); + struct btree_iter_stack iter; for_each_key_filter(&b->keys, k, &iter, bch_ptr_invalid) bch_initial_mark_key(b->c, b->level, k); @@ -1928,10 +1922,10 @@ static int bch_btree_check_recurse(struct btree *b, struct btree_op *op) bch_initial_mark_key(b->c, b->level + 1, &b->key); if (b->level) { - bch_btree_iter_init(&b->keys, &iter, NULL); + bch_btree_iter_stack_init(&b->keys, &iter, NULL); do { - k = bch_btree_iter_next_filter(&iter, &b->keys, + k = bch_btree_iter_next_filter(&iter.iter, &b->keys, bch_ptr_bad); if (k) { btree_node_prefetch(b, k); @@ -1959,7 +1953,7 @@ static int bch_btree_check_thread(void *arg) struct btree_check_info *info = arg; struct btree_check_state *check_state = info->state; struct cache_set *c = check_state->c; - struct btree_iter iter; + struct btree_iter_stack iter; struct bkey *k, *p; int cur_idx, prev_idx, skip_nr; @@ -1967,11 +1961,9 @@ static int bch_btree_check_thread(void *arg) cur_idx = prev_idx = 0; ret = 0; - min_heap_init(&iter.heap, NULL, MAX_BSETS); - /* root node keys are checked before thread created */ - bch_btree_iter_init(&c->root->keys, &iter, NULL); - k = bch_btree_iter_next_filter(&iter, &c->root->keys, bch_ptr_bad); + bch_btree_iter_stack_init(&c->root->keys, &iter, NULL); + k = bch_btree_iter_next_filter(&iter.iter, &c->root->keys, bch_ptr_bad); BUG_ON(!k); p = k; @@ -1989,7 +1981,7 @@ static int bch_btree_check_thread(void *arg) skip_nr = cur_idx - prev_idx; while (skip_nr) { - k = bch_btree_iter_next_filter(&iter, + k = bch_btree_iter_next_filter(&iter.iter, &c->root->keys, bch_ptr_bad); if (k) @@ -2062,11 +2054,9 @@ int bch_btree_check(struct cache_set *c) int ret = 0; int i; struct bkey *k = NULL; - struct btree_iter iter; + struct btree_iter_stack iter; struct btree_check_state check_state; - min_heap_init(&iter.heap, NULL, MAX_BSETS); - /* check and mark root node keys */ for_each_key_filter(&c->root->keys, k, &iter, bch_ptr_invalid) bch_initial_mark_key(c, c->root->level, k); @@ -2560,12 +2550,11 @@ static int bch_btree_map_nodes_recurse(struct btree *b, struct btree_op *op, if (b->level) { struct bkey *k; - struct btree_iter iter; + struct btree_iter_stack iter; - min_heap_init(&iter.heap, NULL, MAX_BSETS); - bch_btree_iter_init(&b->keys, &iter, from); + bch_btree_iter_stack_init(&b->keys, &iter, from); - while ((k = bch_btree_iter_next_filter(&iter, &b->keys, + while ((k = bch_btree_iter_next_filter(&iter.iter, &b->keys, bch_ptr_bad))) { ret = bcache_btree(map_nodes_recurse, k, b, op, from, fn, flags); @@ -2594,12 +2583,12 @@ int bch_btree_map_keys_recurse(struct btree *b, struct btree_op *op, { int ret = MAP_CONTINUE; struct bkey *k; - struct btree_iter iter; + struct btree_iter_stack iter; - min_heap_init(&iter.heap, NULL, MAX_BSETS); - bch_btree_iter_init(&b->keys, &iter, from); + bch_btree_iter_stack_init(&b->keys, &iter, from); - while ((k = bch_btree_iter_next_filter(&iter, &b->keys, bch_ptr_bad))) { + while ((k = bch_btree_iter_next_filter(&iter.iter, &b->keys, + bch_ptr_bad))) { ret = !b->level ? fn(op, b, k) : bcache_btree(map_keys_recurse, k, diff --git a/drivers/md/bcache/extents.c b/drivers/md/bcache/extents.c index 4b84fda1530a..d626ffcbecb9 100644 --- a/drivers/md/bcache/extents.c +++ b/drivers/md/bcache/extents.c @@ -33,16 +33,15 @@ static void sort_key_next(struct btree_iter *iter, i->k = bkey_next(i->k); if (i->k == i->end) - *i = iter->heap.data[--iter->heap.nr]; + *i = iter->data[--iter->used]; } -static bool new_bch_key_sort_cmp(const void *l, const void *r, void *args) +static bool bch_key_sort_cmp(struct btree_iter_set l, + struct btree_iter_set r) { - struct btree_iter_set *_l = (struct btree_iter_set *)l; - struct btree_iter_set *_r = (struct btree_iter_set *)r; - int64_t c = bkey_cmp(_l->k, _r->k); + int64_t c = bkey_cmp(l.k, r.k); - return !(c ? c > 0 : _l->k < _r->k); + return c ? c > 0 : l.k < r.k; } static bool __ptr_invalid(struct cache_set *c, const struct bkey *k) @@ -239,7 +238,7 @@ static bool bch_btree_ptr_insert_fixup(struct btree_keys *bk, } const struct btree_keys_ops bch_btree_keys_ops = { - .sort_cmp = new_bch_key_sort_cmp, + .sort_cmp = bch_key_sort_cmp, .insert_fixup = bch_btree_ptr_insert_fixup, .key_invalid = bch_btree_ptr_invalid, .key_bad = bch_btree_ptr_bad, @@ -256,28 +255,22 @@ const struct btree_keys_ops bch_btree_keys_ops = { * Necessary for btree_sort_fixup() - if there are multiple keys that compare * equal in different sets, we have to process them newest to oldest. */ - -static bool new_bch_extent_sort_cmp(const void *l, const void *r, void __always_unused *args) +static bool bch_extent_sort_cmp(struct btree_iter_set l, + struct btree_iter_set r) { - struct btree_iter_set *_l = (struct btree_iter_set *)l; - struct btree_iter_set *_r = (struct btree_iter_set *)r; - int64_t c = bkey_cmp(&START_KEY(_l->k), &START_KEY(_r->k)); + int64_t c = bkey_cmp(&START_KEY(l.k), &START_KEY(r.k)); - return !(c ? c > 0 : _l->k < _r->k); + return c ? c > 0 : l.k < r.k; } static struct bkey *bch_extent_sort_fixup(struct btree_iter *iter, struct bkey *tmp) { - const struct min_heap_callbacks callbacks = { - .less = new_bch_extent_sort_cmp, - .swp = NULL, - }; - while (iter->heap.nr > 1) { - struct btree_iter_set *top = iter->heap.data, *i = top + 1; - - if (iter->heap.nr > 2 && - !new_bch_extent_sort_cmp(&i[0], &i[1], NULL)) + while (iter->used > 1) { + struct btree_iter_set *top = iter->data, *i = top + 1; + + if (iter->used > 2 && + bch_extent_sort_cmp(i[0], i[1])) i++; if (bkey_cmp(top->k, &START_KEY(i->k)) <= 0) @@ -285,7 +278,7 @@ static struct bkey *bch_extent_sort_fixup(struct btree_iter *iter, if (!KEY_SIZE(i->k)) { sort_key_next(iter, i); - min_heap_sift_down(&iter->heap, i - top, &callbacks, NULL); + heap_sift(iter, i - top, bch_extent_sort_cmp); continue; } @@ -295,7 +288,7 @@ static struct bkey *bch_extent_sort_fixup(struct btree_iter *iter, else bch_cut_front(top->k, i->k); - min_heap_sift_down(&iter->heap, i - top, &callbacks, NULL); + heap_sift(iter, i - top, bch_extent_sort_cmp); } else { /* can't happen because of comparison func */ BUG_ON(!bkey_cmp(&START_KEY(top->k), &START_KEY(i->k))); @@ -305,7 +298,7 @@ static struct bkey *bch_extent_sort_fixup(struct btree_iter *iter, bch_cut_back(&START_KEY(i->k), tmp); bch_cut_front(i->k, top->k); - min_heap_sift_down(&iter->heap, 0, &callbacks, NULL); + heap_sift(iter, 0, bch_extent_sort_cmp); return tmp; } else { @@ -625,7 +618,7 @@ static bool bch_extent_merge(struct btree_keys *bk, } const struct btree_keys_ops bch_extent_keys_ops = { - .sort_cmp = new_bch_extent_sort_cmp, + .sort_cmp = bch_extent_sort_cmp, .sort_fixup = bch_extent_sort_fixup, .insert_fixup = bch_extent_insert_fixup, .key_invalid = bch_extent_invalid, diff --git a/drivers/md/bcache/movinggc.c b/drivers/md/bcache/movinggc.c index 45ca134cbf02..26a6a535ec32 100644 --- a/drivers/md/bcache/movinggc.c +++ b/drivers/md/bcache/movinggc.c @@ -182,19 +182,16 @@ err: if (!IS_ERR_OR_NULL(w->private)) closure_sync(&cl); } -static bool new_bucket_cmp(const void *l, const void *r, void __always_unused *args) +static bool bucket_cmp(struct bucket *l, struct bucket *r) { - struct bucket **_l = (struct bucket **)l; - struct bucket **_r = (struct bucket **)r; - - return GC_SECTORS_USED(*_l) >= GC_SECTORS_USED(*_r); + return GC_SECTORS_USED(l) < GC_SECTORS_USED(r); } static unsigned int bucket_heap_top(struct cache *ca) { struct bucket *b; - return (b = min_heap_peek(&ca->heap)[0]) ? GC_SECTORS_USED(b) : 0; + return (b = heap_peek(&ca->heap)) ? GC_SECTORS_USED(b) : 0; } void bch_moving_gc(struct cache_set *c) @@ -202,10 +199,6 @@ void bch_moving_gc(struct cache_set *c) struct cache *ca = c->cache; struct bucket *b; unsigned long sectors_to_move, reserve_sectors; - const struct min_heap_callbacks callbacks = { - .less = new_bucket_cmp, - .swp = NULL, - }; if (!c->copy_gc_enabled) return; @@ -216,7 +209,7 @@ void bch_moving_gc(struct cache_set *c) reserve_sectors = ca->sb.bucket_size * fifo_used(&ca->free[RESERVE_MOVINGGC]); - ca->heap.nr = 0; + ca->heap.used = 0; for_each_bucket(b, ca) { if (GC_MARK(b) == GC_MARK_METADATA || @@ -225,31 +218,25 @@ void bch_moving_gc(struct cache_set *c) atomic_read(&b->pin)) continue; - if (!min_heap_full(&ca->heap)) { + if (!heap_full(&ca->heap)) { sectors_to_move += GC_SECTORS_USED(b); - min_heap_push(&ca->heap, &b, &callbacks, NULL); - } else if (!new_bucket_cmp(&b, min_heap_peek(&ca->heap), ca)) { + heap_add(&ca->heap, b, bucket_cmp); + } else if (bucket_cmp(b, heap_peek(&ca->heap))) { sectors_to_move -= bucket_heap_top(ca); sectors_to_move += GC_SECTORS_USED(b); ca->heap.data[0] = b; - min_heap_sift_down(&ca->heap, 0, &callbacks, NULL); + heap_sift(&ca->heap, 0, bucket_cmp); } } while (sectors_to_move > reserve_sectors) { - if (ca->heap.nr) { - b = min_heap_peek(&ca->heap)[0]; - min_heap_pop(&ca->heap, &callbacks, NULL); - } + heap_pop(&ca->heap, b, bucket_cmp); sectors_to_move -= GC_SECTORS_USED(b); } - while (ca->heap.nr) { - b = min_heap_peek(&ca->heap)[0]; - min_heap_pop(&ca->heap, &callbacks, NULL); + while (heap_pop(&ca->heap, b, bucket_cmp)) SET_GC_MOVE(b, 1); - } mutex_unlock(&c->bucket_lock); diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 1efb768b2890..2ea490b9d370 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -1912,7 +1912,8 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb) INIT_LIST_HEAD(&c->btree_cache_freed); INIT_LIST_HEAD(&c->data_buckets); - iter_size = ((meta_bucket_pages(sb) * PAGE_SECTORS) / sb->block_size) * + iter_size = sizeof(struct btree_iter) + + ((meta_bucket_pages(sb) * PAGE_SECTORS) / sb->block_size) * sizeof(struct btree_iter_set); c->devices = kcalloc(c->nr_uuids, sizeof(void *), GFP_KERNEL); diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c index e8f696cb58c0..826b14cae4e5 100644 --- a/drivers/md/bcache/sysfs.c +++ b/drivers/md/bcache/sysfs.c @@ -660,9 +660,7 @@ static unsigned int bch_root_usage(struct cache_set *c) unsigned int bytes = 0; struct bkey *k; struct btree *b; - struct btree_iter iter; - - min_heap_init(&iter.heap, NULL, MAX_BSETS); + struct btree_iter_stack iter; goto lock_root; diff --git a/drivers/md/bcache/util.h b/drivers/md/bcache/util.h index 539454d8e2d0..f61ab1bada6c 100644 --- a/drivers/md/bcache/util.h +++ b/drivers/md/bcache/util.h @@ -9,7 +9,6 @@ #include <linux/kernel.h> #include <linux/sched/clock.h> #include <linux/llist.h> -#include <linux/min_heap.h> #include <linux/ratelimit.h> #include <linux/vmalloc.h> #include <linux/workqueue.h> @@ -31,10 +30,16 @@ struct closure; #endif +#define DECLARE_HEAP(type, name) \ + struct { \ + size_t size, used; \ + type *data; \ + } name + #define init_heap(heap, _size, gfp) \ ({ \ size_t _bytes; \ - (heap)->nr = 0; \ + (heap)->used = 0; \ (heap)->size = (_size); \ _bytes = (heap)->size * sizeof(*(heap)->data); \ (heap)->data = kvmalloc(_bytes, (gfp) & GFP_KERNEL); \ @@ -47,6 +52,64 @@ do { \ (heap)->data = NULL; \ } while (0) +#define heap_swap(h, i, j) swap((h)->data[i], (h)->data[j]) + +#define heap_sift(h, i, cmp) \ +do { \ + size_t _r, _j = i; \ + \ + for (; _j * 2 + 1 < (h)->used; _j = _r) { \ + _r = _j * 2 + 1; \ + if (_r + 1 < (h)->used && \ + cmp((h)->data[_r], (h)->data[_r + 1])) \ + _r++; \ + \ + if (cmp((h)->data[_r], (h)->data[_j])) \ + break; \ + heap_swap(h, _r, _j); \ + } \ +} while (0) + +#define heap_sift_down(h, i, cmp) \ +do { \ + while (i) { \ + size_t p = (i - 1) / 2; \ + if (cmp((h)->data[i], (h)->data[p])) \ + break; \ + heap_swap(h, i, p); \ + i = p; \ + } \ +} while (0) + +#define heap_add(h, d, cmp) \ +({ \ + bool _r = !heap_full(h); \ + if (_r) { \ + size_t _i = (h)->used++; \ + (h)->data[_i] = d; \ + \ + heap_sift_down(h, _i, cmp); \ + heap_sift(h, _i, cmp); \ + } \ + _r; \ +}) + +#define heap_pop(h, d, cmp) \ +({ \ + bool _r = (h)->used; \ + if (_r) { \ + (d) = (h)->data[0]; \ + (h)->used--; \ + heap_swap(h, 0, (h)->used); \ + heap_sift(h, 0, cmp); \ + } \ + _r; \ +}) + +#define heap_peek(h) ((h)->used ? (h)->data[0] : NULL) + +#define heap_full(h) ((h)->used == (h)->size) + #define DECLARE_FIFO(type, name) \ struct { \ size_t front, back, size, mask; \ diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c index 453efbbdc8ee..302e75f1fc4b 100644 --- a/drivers/md/bcache/writeback.c +++ b/drivers/md/bcache/writeback.c @@ -908,16 +908,15 @@ static int bch_dirty_init_thread(void *arg) struct dirty_init_thrd_info *info = arg; struct bch_dirty_init_state *state = info->state; struct cache_set *c = state->c; - struct btree_iter iter; + struct btree_iter_stack iter; struct bkey *k, *p; int cur_idx, prev_idx, skip_nr; k = p = NULL; prev_idx = 0; - min_heap_init(&iter.heap, NULL, MAX_BSETS); - bch_btree_iter_init(&c->root->keys, &iter, NULL); - k = bch_btree_iter_next_filter(&iter, &c->root->keys, bch_ptr_bad); + bch_btree_iter_stack_init(&c->root->keys, &iter, NULL); + k = bch_btree_iter_next_filter(&iter.iter, &c->root->keys, bch_ptr_bad); BUG_ON(!k); p = k; @@ -931,7 +930,7 @@ static int bch_dirty_init_thread(void *arg) skip_nr = cur_idx - prev_idx; while (skip_nr) { - k = bch_btree_iter_next_filter(&iter, + k = bch_btree_iter_next_filter(&iter.iter, &c->root->keys, bch_ptr_bad); if (k) @@ -980,13 +979,11 @@ void bch_sectors_dirty_init(struct bcache_device *d) int i; struct btree *b = NULL; struct bkey *k = NULL; - struct btree_iter iter; + struct btree_iter_stack iter; struct sectors_dirty_init op; struct cache_set *c = d->c; struct bch_dirty_init_state state; - min_heap_init(&iter.heap, NULL, MAX_BSETS); - retry_lock: b = c->root; rw_lock(0, b, b->level); diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 9dfdb63220d7..17157c4216a5 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -517,7 +517,10 @@ static int crypt_iv_lmk_one(struct crypt_config *cc, u8 *iv, { struct iv_lmk_private *lmk = &cc->iv_gen_private.lmk; SHASH_DESC_ON_STACK(desc, lmk->hash_tfm); - struct md5_state md5state; + union { + struct md5_state md5state; + u8 state[CRYPTO_MD5_STATESIZE]; + } u; __le32 buf[4]; int i, r; @@ -548,13 +551,13 @@ static int crypt_iv_lmk_one(struct crypt_config *cc, u8 *iv, return r; /* No MD5 padding here */ - r = crypto_shash_export(desc, &md5state); + r = crypto_shash_export(desc, &u.md5state); if (r) return r; for (i = 0; i < MD5_HASH_WORDS; i++) - __cpu_to_le32s(&md5state.hash[i]); - memcpy(iv, &md5state.hash, cc->iv_size); + __cpu_to_le32s(&u.md5state.hash[i]); + memcpy(iv, &u.md5state.hash, cc->iv_size); return 0; } diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index d296770478b2..e8c0a8c6fb51 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -2407,7 +2407,7 @@ static int super_init_validation(struct raid_set *rs, struct md_rdev *rdev) */ sb_retrieve_failed_devices(sb, failed_devices); rdev_for_each(r, mddev) { - if (test_bit(Journal, &rdev->flags) || + if (test_bit(Journal, &r->flags) || !r->sb_page) continue; sb2 = page_address(r->sb_page); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 2cb3185c442c..ae89a981e052 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -2989,6 +2989,7 @@ static int __bnxt_poll_work(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, { struct bnxt_napi *bnapi = cpr->bnapi; u32 raw_cons = cpr->cp_raw_cons; + bool flush_xdp = false; u32 cons; int rx_pkts = 0; u8 event = 0; @@ -3042,6 +3043,8 @@ static int __bnxt_poll_work(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, else rc = bnxt_force_rx_discard(bp, cpr, &raw_cons, &event); + if (event & BNXT_REDIRECT_EVENT) + flush_xdp = true; if (likely(rc >= 0)) rx_pkts += rc; /* Increment rx_pkts when rc is -ENOMEM to count towards @@ -3066,7 +3069,7 @@ static int __bnxt_poll_work(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, } } - if (event & BNXT_REDIRECT_EVENT) { + if (flush_xdp) { xdp_do_flush(); event &= ~BNXT_REDIRECT_EVENT; } diff --git a/drivers/net/ethernet/freescale/enetc/enetc_hw.h b/drivers/net/ethernet/freescale/enetc/enetc_hw.h index 4098f01479bc..53e8d18c7a34 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_hw.h +++ b/drivers/net/ethernet/freescale/enetc/enetc_hw.h @@ -507,7 +507,7 @@ static inline u64 _enetc_rd_reg64(void __iomem *reg) tmp = ioread32(reg + 4); } while (high != tmp); - return le64_to_cpu((__le64)high << 32 | low); + return (u64)high << 32 | low; } #endif diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c index 3504507477c6..52cf7112762c 100644 --- a/drivers/net/ethernet/microsoft/mana/gdma_main.c +++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c @@ -31,6 +31,9 @@ static void mana_gd_init_pf_regs(struct pci_dev *pdev) gc->db_page_base = gc->bar0_va + mana_gd_r64(gc, GDMA_PF_REG_DB_PAGE_OFF); + gc->phys_db_page_base = gc->bar0_pa + + mana_gd_r64(gc, GDMA_PF_REG_DB_PAGE_OFF); + sriov_base_off = mana_gd_r64(gc, GDMA_SRIOV_REG_CFG_BASE_OFF); sriov_base_va = gc->bar0_va + sriov_base_off; diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c index 2ac59564ded1..d10b58ebf603 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c @@ -321,7 +321,7 @@ static int ionic_xdp_post_frame(struct ionic_queue *q, struct xdp_frame *frame, len, DMA_TO_DEVICE); } else /* XDP_REDIRECT */ { dma_addr = ionic_tx_map_single(q, frame->data, len); - if (!dma_addr) + if (dma_addr == DMA_MAPPING_ERROR) return -EIO; } @@ -357,7 +357,7 @@ static int ionic_xdp_post_frame(struct ionic_queue *q, struct xdp_frame *frame, } else { dma_addr = ionic_tx_map_frag(q, frag, 0, skb_frag_size(frag)); - if (dma_mapping_error(q->dev, dma_addr)) { + if (dma_addr == DMA_MAPPING_ERROR) { ionic_tx_desc_unmap_bufs(q, desc_info); return -EIO; } @@ -1083,7 +1083,7 @@ static dma_addr_t ionic_tx_map_single(struct ionic_queue *q, net_warn_ratelimited("%s: DMA single map failed on %s!\n", dev_name(dev), q->name); q_to_tx_stats(q)->dma_map_err++; - return 0; + return DMA_MAPPING_ERROR; } return dma_addr; } @@ -1100,7 +1100,7 @@ static dma_addr_t ionic_tx_map_frag(struct ionic_queue *q, net_warn_ratelimited("%s: DMA frag map failed on %s!\n", dev_name(dev), q->name); q_to_tx_stats(q)->dma_map_err++; - return 0; + return DMA_MAPPING_ERROR; } return dma_addr; } @@ -1116,7 +1116,7 @@ static int ionic_tx_map_skb(struct ionic_queue *q, struct sk_buff *skb, int frag_idx; dma_addr = ionic_tx_map_single(q, skb->data, skb_headlen(skb)); - if (!dma_addr) + if (dma_addr == DMA_MAPPING_ERROR) return -EIO; buf_info->dma_addr = dma_addr; buf_info->len = skb_headlen(skb); @@ -1126,7 +1126,7 @@ static int ionic_tx_map_skb(struct ionic_queue *q, struct sk_buff *skb, nfrags = skb_shinfo(skb)->nr_frags; for (frag_idx = 0; frag_idx < nfrags; frag_idx++, frag++) { dma_addr = ionic_tx_map_frag(q, frag, 0, skb_frag_size(frag)); - if (!dma_addr) + if (dma_addr == DMA_MAPPING_ERROR) goto dma_fail; buf_info->dma_addr = dma_addr; buf_info->len = skb_frag_size(frag); diff --git a/drivers/net/ethernet/qlogic/qed/qed_mng_tlv.c b/drivers/net/ethernet/qlogic/qed/qed_mng_tlv.c index f55eed092f25..7d78f072b0a1 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mng_tlv.c +++ b/drivers/net/ethernet/qlogic/qed/qed_mng_tlv.c @@ -242,7 +242,7 @@ static int qed_mfw_get_tlv_group(u8 tlv_type, u8 *tlv_group) } /* Returns size of the data buffer or, -1 in case TLV data is not available. */ -static int +static noinline_for_stack int qed_mfw_get_gen_tlv_value(struct qed_drv_tlv_hdr *p_tlv, struct qed_mfw_tlv_generic *p_drv_buf, struct qed_tlv_parsed_buf *p_buf) @@ -304,7 +304,7 @@ qed_mfw_get_gen_tlv_value(struct qed_drv_tlv_hdr *p_tlv, return -1; } -static int +static noinline_for_stack int qed_mfw_get_eth_tlv_value(struct qed_drv_tlv_hdr *p_tlv, struct qed_mfw_tlv_eth *p_drv_buf, struct qed_tlv_parsed_buf *p_buf) @@ -438,7 +438,7 @@ qed_mfw_get_tlv_time_value(struct qed_mfw_tlv_time *p_time, return QED_MFW_TLV_TIME_SIZE; } -static int +static noinline_for_stack int qed_mfw_get_fcoe_tlv_value(struct qed_drv_tlv_hdr *p_tlv, struct qed_mfw_tlv_fcoe *p_drv_buf, struct qed_tlv_parsed_buf *p_buf) @@ -1073,7 +1073,7 @@ qed_mfw_get_fcoe_tlv_value(struct qed_drv_tlv_hdr *p_tlv, return -1; } -static int +static noinline_for_stack int qed_mfw_get_iscsi_tlv_value(struct qed_drv_tlv_hdr *p_tlv, struct qed_mfw_tlv_iscsi *p_drv_buf, struct qed_tlv_parsed_buf *p_buf) diff --git a/drivers/net/ethernet/wangxun/libwx/wx_lib.c b/drivers/net/ethernet/wangxun/libwx/wx_lib.c index 7f2e6cddfeb1..c57cc4f27249 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_lib.c +++ b/drivers/net/ethernet/wangxun/libwx/wx_lib.c @@ -2623,7 +2623,7 @@ static int wx_alloc_page_pool(struct wx_ring *rx_ring) struct page_pool_params pp_params = { .flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV, .order = 0, - .pool_size = rx_ring->size, + .pool_size = rx_ring->count, .nid = dev_to_node(rx_ring->dev), .dev = rx_ring->dev, .dma_dir = DMA_FROM_DEVICE, diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index b586b1c13a47..f5647ee0adde 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1426,6 +1426,7 @@ static const struct usb_device_id products[] = { {QMI_QUIRK_SET_DTR(0x22de, 0x9051, 2)}, /* Hucom Wireless HM-211S/K */ {QMI_FIXED_INTF(0x22de, 0x9061, 3)}, /* WeTelecom WPD-600N */ {QMI_QUIRK_SET_DTR(0x1e0e, 0x9001, 5)}, /* SIMCom 7100E, 7230E, 7600E ++ */ + {QMI_QUIRK_SET_DTR(0x1e0e, 0x9071, 3)}, /* SIMCom 8230C ++ */ {QMI_QUIRK_SET_DTR(0x2c7c, 0x0121, 4)}, /* Quectel EC21 Mini PCIe */ {QMI_QUIRK_SET_DTR(0x2c7c, 0x0191, 4)}, /* Quectel EG91 */ {QMI_QUIRK_SET_DTR(0x2c7c, 0x0195, 4)}, /* Quectel EG95 */ diff --git a/drivers/net/wireless/intel/iwlegacy/4965-rs.c b/drivers/net/wireless/intel/iwlegacy/4965-rs.c index 0e5130d1fccd..031d88bf6393 100644 --- a/drivers/net/wireless/intel/iwlegacy/4965-rs.c +++ b/drivers/net/wireless/intel/iwlegacy/4965-rs.c @@ -203,7 +203,8 @@ il4965_rs_extract_rate(u32 rate_n_flags) return (u8) (rate_n_flags & 0xFF); } -static void +/* noinline works around https://github.com/llvm/llvm-project/issues/143908 */ +static noinline_for_stack void il4965_rs_rate_scale_clear_win(struct il_rate_scale_data *win) { win->data = 0; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac.c b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac.c index 3c255ae916c8..3f8b840871d3 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac.c @@ -32,9 +32,9 @@ static void iwl_mvm_mld_mac_ctxt_cmd_common(struct iwl_mvm *mvm, unsigned int link_id; int cmd_ver = iwl_fw_lookup_cmd_ver(mvm->fw, WIDE_ID(MAC_CONF_GROUP, - MAC_CONFIG_CMD), 0); + MAC_CONFIG_CMD), 1); - if (WARN_ON(cmd_ver < 1 || cmd_ver > 3)) + if (WARN_ON(cmd_ver > 3)) return; cmd->id_and_color = cpu_to_le32(mvmvif->id); diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 92697f98c601..e533d791955d 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -2015,21 +2015,41 @@ static void nvme_configure_metadata(struct nvme_ctrl *ctrl, } -static void nvme_update_atomic_write_disk_info(struct nvme_ns *ns, - struct nvme_id_ns *id, struct queue_limits *lim, - u32 bs, u32 atomic_bs) +static u32 nvme_configure_atomic_write(struct nvme_ns *ns, + struct nvme_id_ns *id, struct queue_limits *lim, u32 bs) { - unsigned int boundary = 0; + u32 atomic_bs, boundary = 0; - if (id->nsfeat & NVME_NS_FEAT_ATOMICS && id->nawupf) { - if (le16_to_cpu(id->nabspf)) + /* + * We do not support an offset for the atomic boundaries. + */ + if (id->nabo) + return bs; + + if ((id->nsfeat & NVME_NS_FEAT_ATOMICS) && id->nawupf) { + /* + * Use the per-namespace atomic write unit when available. + */ + atomic_bs = (1 + le16_to_cpu(id->nawupf)) * bs; + if (id->nabspf) boundary = (le16_to_cpu(id->nabspf) + 1) * bs; + } else { + /* + * Use the controller wide atomic write unit. This sucks + * because the limit is defined in terms of logical blocks while + * namespaces can have different formats, and because there is + * no clear language in the specification prohibiting different + * values for different controllers in the subsystem. + */ + atomic_bs = (1 + ns->ctrl->subsys->awupf) * bs; } + lim->atomic_write_hw_max = atomic_bs; lim->atomic_write_hw_boundary = boundary; lim->atomic_write_hw_unit_min = bs; lim->atomic_write_hw_unit_max = rounddown_pow_of_two(atomic_bs); lim->features |= BLK_FEAT_ATOMIC_WRITES; + return atomic_bs; } static u32 nvme_max_drv_segments(struct nvme_ctrl *ctrl) @@ -2067,34 +2087,8 @@ static bool nvme_update_disk_info(struct nvme_ns *ns, struct nvme_id_ns *id, valid = false; } - atomic_bs = phys_bs = bs; - if (id->nabo == 0) { - /* - * Bit 1 indicates whether NAWUPF is defined for this namespace - * and whether it should be used instead of AWUPF. If NAWUPF == - * 0 then AWUPF must be used instead. - */ - if (id->nsfeat & NVME_NS_FEAT_ATOMICS && id->nawupf) - atomic_bs = (1 + le16_to_cpu(id->nawupf)) * bs; - else - atomic_bs = (1 + ns->ctrl->awupf) * bs; - - /* - * Set subsystem atomic bs. - */ - if (ns->ctrl->subsys->atomic_bs) { - if (atomic_bs != ns->ctrl->subsys->atomic_bs) { - dev_err_ratelimited(ns->ctrl->device, - "%s: Inconsistent Atomic Write Size, Namespace will not be added: Subsystem=%d bytes, Controller/Namespace=%d bytes\n", - ns->disk ? ns->disk->disk_name : "?", - ns->ctrl->subsys->atomic_bs, - atomic_bs); - } - } else - ns->ctrl->subsys->atomic_bs = atomic_bs; - - nvme_update_atomic_write_disk_info(ns, id, lim, bs, atomic_bs); - } + phys_bs = bs; + atomic_bs = nvme_configure_atomic_write(ns, id, lim, bs); if (id->nsfeat & NVME_NS_FEAT_IO_OPT) { /* NPWG = Namespace Preferred Write Granularity */ @@ -2382,16 +2376,6 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns, if (!nvme_update_disk_info(ns, id, &lim)) capacity = 0; - /* - * Validate the max atomic write size fits within the subsystem's - * atomic write capabilities. - */ - if (lim.atomic_write_hw_max > ns->ctrl->subsys->atomic_bs) { - blk_mq_unfreeze_queue(ns->disk->queue, memflags); - ret = -ENXIO; - goto out; - } - nvme_config_discard(ns, &lim); if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) && ns->head->ids.csi == NVME_CSI_ZNS) @@ -3215,6 +3199,7 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) memcpy(subsys->model, id->mn, sizeof(subsys->model)); subsys->vendor_id = le16_to_cpu(id->vid); subsys->cmic = id->cmic; + subsys->awupf = le16_to_cpu(id->awupf); /* Versions prior to 1.4 don't necessarily report a valid type */ if (id->cntrltype == NVME_CTRL_DISC || @@ -3552,6 +3537,15 @@ static int nvme_init_identify(struct nvme_ctrl *ctrl) if (ret) goto out_free; } + + if (le16_to_cpu(id->awupf) != ctrl->subsys->awupf) { + dev_err_ratelimited(ctrl->device, + "inconsistent AWUPF, controller not added (%u/%u).\n", + le16_to_cpu(id->awupf), ctrl->subsys->awupf); + ret = -EINVAL; + goto out_free; + } + memcpy(ctrl->subsys->firmware_rev, id->fr, sizeof(ctrl->subsys->firmware_rev)); @@ -3647,7 +3641,6 @@ static int nvme_init_identify(struct nvme_ctrl *ctrl) dev_pm_qos_expose_latency_tolerance(ctrl->device); else if (!ctrl->apst_enabled && prev_apst_enabled) dev_pm_qos_hide_latency_tolerance(ctrl->device); - ctrl->awupf = le16_to_cpu(id->awupf); out_free: kfree(id); return ret; @@ -4036,6 +4029,10 @@ static int nvme_init_ns_head(struct nvme_ns *ns, struct nvme_ns_info *info) list_add_tail_rcu(&ns->siblings, &head->list); ns->head = head; mutex_unlock(&ctrl->subsys->lock); + +#ifdef CONFIG_NVME_MULTIPATH + cancel_delayed_work(&head->remove_work); +#endif return 0; out_put_ns_head: diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index e040e467f9fa..316a269842fa 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -1311,7 +1311,7 @@ void nvme_mpath_remove_disk(struct nvme_ns_head *head) */ if (!try_module_get(THIS_MODULE)) goto out; - queue_delayed_work(nvme_wq, &head->remove_work, + mod_delayed_work(nvme_wq, &head->remove_work, head->delayed_removal_secs * HZ); } else { list_del_init(&head->entry); diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index a468cdc5b5cb..7df2ea21851f 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -410,7 +410,6 @@ struct nvme_ctrl { enum nvme_ctrl_type cntrltype; enum nvme_dctype dctype; - u16 awupf; /* 0's based value. */ }; static inline enum nvme_ctrl_state nvme_ctrl_state(struct nvme_ctrl *ctrl) @@ -443,11 +442,11 @@ struct nvme_subsystem { u8 cmic; enum nvme_subsys_type subtype; u16 vendor_id; + u16 awupf; /* 0's based value. */ struct ida ns_ida; #ifdef CONFIG_NVME_MULTIPATH enum nvme_iopolicy iopolicy; #endif - u32 atomic_bs; }; /* diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c index b78e0e417324..af370628e583 100644 --- a/drivers/pci/pci-acpi.c +++ b/drivers/pci/pci-acpi.c @@ -1676,19 +1676,24 @@ struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root) return NULL; root_ops = kzalloc(sizeof(*root_ops), GFP_KERNEL); - if (!root_ops) - goto free_ri; + if (!root_ops) { + kfree(ri); + return NULL; + } ri->cfg = pci_acpi_setup_ecam_mapping(root); - if (!ri->cfg) - goto free_root_ops; + if (!ri->cfg) { + kfree(ri); + kfree(root_ops); + return NULL; + } root_ops->release_info = pci_acpi_generic_release_info; root_ops->prepare_resources = pci_acpi_root_prepare_resources; root_ops->pci_ops = (struct pci_ops *)&ri->cfg->ops->pci_ops; bus = acpi_pci_root_create(root, root_ops, &ri->common, ri->cfg); if (!bus) - goto free_cfg; + return NULL; /* If we must preserve the resource configuration, claim now */ host = pci_find_host_bridge(bus); @@ -1705,14 +1710,6 @@ struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root) pcie_bus_configure_settings(child); return bus; - -free_cfg: - pci_ecam_free(ri->cfg); -free_root_ops: - kfree(root_ops); -free_ri: - kfree(ri); - return NULL; } void pcibios_add_bus(struct pci_bus *bus) diff --git a/drivers/pci/pcie/ptm.c b/drivers/pci/pcie/ptm.c index ee5f615a9023..4bd73f038ffb 100644 --- a/drivers/pci/pcie/ptm.c +++ b/drivers/pci/pcie/ptm.c @@ -254,6 +254,7 @@ bool pcie_ptm_enabled(struct pci_dev *dev) } EXPORT_SYMBOL(pcie_ptm_enabled); +#if IS_ENABLED(CONFIG_DEBUG_FS) static ssize_t context_update_write(struct file *file, const char __user *ubuf, size_t count, loff_t *ppos) { @@ -552,3 +553,4 @@ void pcie_ptm_destroy_debugfs(struct pci_ptm_debugfs *ptm_debugfs) debugfs_remove_recursive(ptm_debugfs->debugfs); } EXPORT_SYMBOL_GPL(pcie_ptm_destroy_debugfs); +#endif diff --git a/drivers/s390/crypto/pkey_api.c b/drivers/s390/crypto/pkey_api.c index cef60770f68b..b3fcdcae379e 100644 --- a/drivers/s390/crypto/pkey_api.c +++ b/drivers/s390/crypto/pkey_api.c @@ -86,7 +86,7 @@ static void *_copy_apqns_from_user(void __user *uapqns, size_t nr_apqns) if (!uapqns || nr_apqns == 0) return NULL; - return memdup_user(uapqns, nr_apqns * sizeof(struct pkey_apqn)); + return memdup_array_user(uapqns, nr_apqns, sizeof(struct pkey_apqn)); } static int pkey_ioctl_genseck(struct pkey_genseck __user *ugs) diff --git a/drivers/scsi/fnic/fdls_disc.c b/drivers/scsi/fnic/fdls_disc.c index f8ab69c51dab..ae37f85f618b 100644 --- a/drivers/scsi/fnic/fdls_disc.c +++ b/drivers/scsi/fnic/fdls_disc.c @@ -763,50 +763,86 @@ static void fdls_send_fabric_abts(struct fnic_iport_s *iport) iport->fabric.timer_pending = 1; } -static void fdls_send_fdmi_abts(struct fnic_iport_s *iport) +static uint8_t *fdls_alloc_init_fdmi_abts_frame(struct fnic_iport_s *iport, + uint16_t oxid) { - uint8_t *frame; + struct fc_frame_header *pfdmi_abts; uint8_t d_id[3]; + uint8_t *frame; struct fnic *fnic = iport->fnic; - struct fc_frame_header *pfabric_abts; - unsigned long fdmi_tov; - uint16_t oxid; - uint16_t frame_size = FNIC_ETH_FCOE_HDRS_OFFSET + - sizeof(struct fc_frame_header); frame = fdls_alloc_frame(iport); if (frame == NULL) { FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num, "Failed to allocate frame to send FDMI ABTS"); - return; + return NULL; } - pfabric_abts = (struct fc_frame_header *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET); + pfdmi_abts = (struct fc_frame_header *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET); fdls_init_fabric_abts_frame(frame, iport); hton24(d_id, FC_FID_MGMT_SERV); - FNIC_STD_SET_D_ID(*pfabric_abts, d_id); + FNIC_STD_SET_D_ID(*pfdmi_abts, d_id); + FNIC_STD_SET_OX_ID(*pfdmi_abts, oxid); + + return frame; +} + +static void fdls_send_fdmi_abts(struct fnic_iport_s *iport) +{ + uint8_t *frame; + struct fnic *fnic = iport->fnic; + unsigned long fdmi_tov; + uint16_t frame_size = FNIC_ETH_FCOE_HDRS_OFFSET + + sizeof(struct fc_frame_header); if (iport->fabric.fdmi_pending & FDLS_FDMI_PLOGI_PENDING) { - oxid = iport->active_oxid_fdmi_plogi; - FNIC_STD_SET_OX_ID(*pfabric_abts, oxid); + frame = fdls_alloc_init_fdmi_abts_frame(iport, + iport->active_oxid_fdmi_plogi); + if (frame == NULL) + return; + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: FDLS send FDMI PLOGI abts. iport->fabric.state: %d oxid: 0x%x", + iport->fcid, iport->fabric.state, iport->active_oxid_fdmi_plogi); fnic_send_fcoe_frame(iport, frame, frame_size); } else { if (iport->fabric.fdmi_pending & FDLS_FDMI_REG_HBA_PENDING) { - oxid = iport->active_oxid_fdmi_rhba; - FNIC_STD_SET_OX_ID(*pfabric_abts, oxid); + frame = fdls_alloc_init_fdmi_abts_frame(iport, + iport->active_oxid_fdmi_rhba); + if (frame == NULL) + return; + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: FDLS send FDMI RHBA abts. iport->fabric.state: %d oxid: 0x%x", + iport->fcid, iport->fabric.state, iport->active_oxid_fdmi_rhba); fnic_send_fcoe_frame(iport, frame, frame_size); } if (iport->fabric.fdmi_pending & FDLS_FDMI_RPA_PENDING) { - oxid = iport->active_oxid_fdmi_rpa; - FNIC_STD_SET_OX_ID(*pfabric_abts, oxid); + frame = fdls_alloc_init_fdmi_abts_frame(iport, + iport->active_oxid_fdmi_rpa); + if (frame == NULL) { + if (iport->fabric.fdmi_pending & FDLS_FDMI_REG_HBA_PENDING) + goto arm_timer; + else + return; + } + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: FDLS send FDMI RPA abts. iport->fabric.state: %d oxid: 0x%x", + iport->fcid, iport->fabric.state, iport->active_oxid_fdmi_rpa); fnic_send_fcoe_frame(iport, frame, frame_size); } } +arm_timer: fdmi_tov = jiffies + msecs_to_jiffies(2 * iport->e_d_tov); mod_timer(&iport->fabric.fdmi_timer, round_jiffies(fdmi_tov)); iport->fabric.fdmi_pending |= FDLS_FDMI_ABORT_PENDING; + + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: iport->fabric.fdmi_pending: 0x%x", + iport->fcid, iport->fabric.fdmi_pending); } static void fdls_send_fabric_flogi(struct fnic_iport_s *iport) @@ -2245,6 +2281,21 @@ void fdls_fabric_timer_callback(struct timer_list *t) spin_unlock_irqrestore(&fnic->fnic_lock, flags); } +void fdls_fdmi_retry_plogi(struct fnic_iport_s *iport) +{ + struct fnic *fnic = iport->fnic; + + iport->fabric.fdmi_pending = 0; + /* If max retries not exhausted, start over from fdmi plogi */ + if (iport->fabric.fdmi_retry < FDLS_FDMI_MAX_RETRY) { + iport->fabric.fdmi_retry++; + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Retry FDMI PLOGI. FDMI retry: %d", + iport->fabric.fdmi_retry); + fdls_send_fdmi_plogi(iport); + } +} + void fdls_fdmi_timer_callback(struct timer_list *t) { struct fnic_fdls_fabric_s *fabric = timer_container_of(fabric, t, @@ -2257,7 +2308,7 @@ void fdls_fdmi_timer_callback(struct timer_list *t) spin_lock_irqsave(&fnic->fnic_lock, flags); FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, - "fdmi timer callback : 0x%x\n", iport->fabric.fdmi_pending); + "iport->fabric.fdmi_pending: 0x%x\n", iport->fabric.fdmi_pending); if (!iport->fabric.fdmi_pending) { /* timer expired after fdmi responses received. */ @@ -2265,7 +2316,7 @@ void fdls_fdmi_timer_callback(struct timer_list *t) return; } FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, - "fdmi timer callback : 0x%x\n", iport->fabric.fdmi_pending); + "iport->fabric.fdmi_pending: 0x%x\n", iport->fabric.fdmi_pending); /* if not abort pending, send an abort */ if (!(iport->fabric.fdmi_pending & FDLS_FDMI_ABORT_PENDING)) { @@ -2274,33 +2325,37 @@ void fdls_fdmi_timer_callback(struct timer_list *t) return; } FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, - "fdmi timer callback : 0x%x\n", iport->fabric.fdmi_pending); + "iport->fabric.fdmi_pending: 0x%x\n", iport->fabric.fdmi_pending); /* ABTS pending for an active fdmi request that is pending. * That means FDMI ABTS timed out * Schedule to free the OXID after 2*r_a_tov and proceed */ if (iport->fabric.fdmi_pending & FDLS_FDMI_PLOGI_PENDING) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "FDMI PLOGI ABTS timed out. Schedule oxid free: 0x%x\n", + iport->active_oxid_fdmi_plogi); fdls_schedule_oxid_free(iport, &iport->active_oxid_fdmi_plogi); } else { - if (iport->fabric.fdmi_pending & FDLS_FDMI_REG_HBA_PENDING) + if (iport->fabric.fdmi_pending & FDLS_FDMI_REG_HBA_PENDING) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "FDMI RHBA ABTS timed out. Schedule oxid free: 0x%x\n", + iport->active_oxid_fdmi_rhba); fdls_schedule_oxid_free(iport, &iport->active_oxid_fdmi_rhba); - if (iport->fabric.fdmi_pending & FDLS_FDMI_RPA_PENDING) + } + if (iport->fabric.fdmi_pending & FDLS_FDMI_RPA_PENDING) { + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "FDMI RPA ABTS timed out. Schedule oxid free: 0x%x\n", + iport->active_oxid_fdmi_rpa); fdls_schedule_oxid_free(iport, &iport->active_oxid_fdmi_rpa); + } } FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, - "fdmi timer callback : 0x%x\n", iport->fabric.fdmi_pending); + "iport->fabric.fdmi_pending: 0x%x\n", iport->fabric.fdmi_pending); - iport->fabric.fdmi_pending = 0; - /* If max retries not exhaused, start over from fdmi plogi */ - if (iport->fabric.fdmi_retry < FDLS_FDMI_MAX_RETRY) { - iport->fabric.fdmi_retry++; - FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, - "retry fdmi timer %d", iport->fabric.fdmi_retry); - fdls_send_fdmi_plogi(iport); - } + fdls_fdmi_retry_plogi(iport); FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, - "fdmi timer callback : 0x%x\n", iport->fabric.fdmi_pending); + "iport->fabric.fdmi_pending: 0x%x\n", iport->fabric.fdmi_pending); spin_unlock_irqrestore(&fnic->fnic_lock, flags); } @@ -3715,13 +3770,60 @@ static void fdls_process_fdmi_abts_rsp(struct fnic_iport_s *iport, switch (FNIC_FRAME_TYPE(oxid)) { case FNIC_FRAME_TYPE_FDMI_PLOGI: + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Received FDMI PLOGI ABTS rsp with oxid: 0x%x", oxid); + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: iport->fabric.fdmi_pending: 0x%x", + iport->fcid, iport->fabric.fdmi_pending); fdls_free_oxid(iport, oxid, &iport->active_oxid_fdmi_plogi); + + iport->fabric.fdmi_pending &= ~FDLS_FDMI_PLOGI_PENDING; + iport->fabric.fdmi_pending &= ~FDLS_FDMI_ABORT_PENDING; + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: iport->fabric.fdmi_pending: 0x%x", + iport->fcid, iport->fabric.fdmi_pending); break; case FNIC_FRAME_TYPE_FDMI_RHBA: + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Received FDMI RHBA ABTS rsp with oxid: 0x%x", oxid); + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: iport->fabric.fdmi_pending: 0x%x", + iport->fcid, iport->fabric.fdmi_pending); + + iport->fabric.fdmi_pending &= ~FDLS_FDMI_REG_HBA_PENDING; + + /* If RPA is still pending, don't turn off ABORT PENDING. + * We count on the timer to detect the ABTS timeout and take + * corrective action. + */ + if (!(iport->fabric.fdmi_pending & FDLS_FDMI_RPA_PENDING)) + iport->fabric.fdmi_pending &= ~FDLS_FDMI_ABORT_PENDING; + fdls_free_oxid(iport, oxid, &iport->active_oxid_fdmi_rhba); + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: iport->fabric.fdmi_pending: 0x%x", + iport->fcid, iport->fabric.fdmi_pending); break; case FNIC_FRAME_TYPE_FDMI_RPA: + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Received FDMI RPA ABTS rsp with oxid: 0x%x", oxid); + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: iport->fabric.fdmi_pending: 0x%x", + iport->fcid, iport->fabric.fdmi_pending); + + iport->fabric.fdmi_pending &= ~FDLS_FDMI_RPA_PENDING; + + /* If RHBA is still pending, don't turn off ABORT PENDING. + * We count on the timer to detect the ABTS timeout and take + * corrective action. + */ + if (!(iport->fabric.fdmi_pending & FDLS_FDMI_REG_HBA_PENDING)) + iport->fabric.fdmi_pending &= ~FDLS_FDMI_ABORT_PENDING; + fdls_free_oxid(iport, oxid, &iport->active_oxid_fdmi_rpa); + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "0x%x: iport->fabric.fdmi_pending: 0x%x", + iport->fcid, iport->fabric.fdmi_pending); break; default: FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, @@ -3730,10 +3832,16 @@ static void fdls_process_fdmi_abts_rsp(struct fnic_iport_s *iport, break; } - timer_delete_sync(&iport->fabric.fdmi_timer); - iport->fabric.fdmi_pending &= ~FDLS_FDMI_ABORT_PENDING; - - fdls_send_fdmi_plogi(iport); + /* + * Only if ABORT PENDING is off, delete the timer, and if no other + * operations are pending, retry FDMI. + * Otherwise, let the timer pop and take the appropriate action. + */ + if (!(iport->fabric.fdmi_pending & FDLS_FDMI_ABORT_PENDING)) { + timer_delete_sync(&iport->fabric.fdmi_timer); + if (!iport->fabric.fdmi_pending) + fdls_fdmi_retry_plogi(iport); + } } static void @@ -4972,9 +5080,12 @@ void fnic_fdls_link_down(struct fnic_iport_s *iport) fdls_delete_tport(iport, tport); } - if ((fnic_fdmi_support == 1) && (iport->fabric.fdmi_pending > 0)) { - timer_delete_sync(&iport->fabric.fdmi_timer); - iport->fabric.fdmi_pending = 0; + if (fnic_fdmi_support == 1) { + if (iport->fabric.fdmi_pending > 0) { + timer_delete_sync(&iport->fabric.fdmi_timer); + iport->fabric.fdmi_pending = 0; + } + iport->flags &= ~FNIC_FDMI_ACTIVE; } FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, diff --git a/drivers/scsi/fnic/fnic.h b/drivers/scsi/fnic/fnic.h index 6c5f6046b1f5..c2fdc6553e62 100644 --- a/drivers/scsi/fnic/fnic.h +++ b/drivers/scsi/fnic/fnic.h @@ -30,7 +30,7 @@ #define DRV_NAME "fnic" #define DRV_DESCRIPTION "Cisco FCoE HBA Driver" -#define DRV_VERSION "1.8.0.0" +#define DRV_VERSION "1.8.0.2" #define PFX DRV_NAME ": " #define DFX DRV_NAME "%d: " diff --git a/drivers/scsi/fnic/fnic_fcs.c b/drivers/scsi/fnic/fnic_fcs.c index 1e8cd64f9a5c..103ab6f1f7cd 100644 --- a/drivers/scsi/fnic/fnic_fcs.c +++ b/drivers/scsi/fnic/fnic_fcs.c @@ -636,6 +636,8 @@ static int fnic_send_frame(struct fnic *fnic, void *frame, int frame_len) unsigned long flags; pa = dma_map_single(&fnic->pdev->dev, frame, frame_len, DMA_TO_DEVICE); + if (dma_mapping_error(&fnic->pdev->dev, pa)) + return -ENOMEM; if ((fnic_fc_trace_set_data(fnic->fnic_num, FNIC_FC_SEND | 0x80, (char *) frame, diff --git a/drivers/scsi/fnic/fnic_fdls.h b/drivers/scsi/fnic/fnic_fdls.h index 8e610b65ad57..531d0b37e450 100644 --- a/drivers/scsi/fnic/fnic_fdls.h +++ b/drivers/scsi/fnic/fnic_fdls.h @@ -394,6 +394,7 @@ void fdls_send_tport_abts(struct fnic_iport_s *iport, bool fdls_delete_tport(struct fnic_iport_s *iport, struct fnic_tport_s *tport); void fdls_fdmi_timer_callback(struct timer_list *t); +void fdls_fdmi_retry_plogi(struct fnic_iport_s *iport); /* fnic_fcs.c */ void fnic_fdls_init(struct fnic *fnic, int usefip); diff --git a/drivers/scsi/fnic/fnic_scsi.c b/drivers/scsi/fnic/fnic_scsi.c index 7133b254cbe4..75b29a018d1f 100644 --- a/drivers/scsi/fnic/fnic_scsi.c +++ b/drivers/scsi/fnic/fnic_scsi.c @@ -1046,7 +1046,7 @@ static void fnic_fcpio_icmnd_cmpl_handler(struct fnic *fnic, unsigned int cq_ind if (icmnd_cmpl->scsi_status == SAM_STAT_TASK_SET_FULL) atomic64_inc(&fnic_stats->misc_stats.queue_fulls); - FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num, "xfer_len: %llu", xfer_len); break; diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c index 3aac0e17cb00..9179f8aee964 100644 --- a/drivers/scsi/megaraid/megaraid_sas_base.c +++ b/drivers/scsi/megaraid/megaraid_sas_base.c @@ -5910,7 +5910,11 @@ megasas_set_high_iops_queue_affinity_and_hint(struct megasas_instance *instance) const struct cpumask *mask; if (instance->perf_mode == MR_BALANCED_PERF_MODE) { - mask = cpumask_of_node(dev_to_node(&instance->pdev->dev)); + int nid = dev_to_node(&instance->pdev->dev); + + if (nid == NUMA_NO_NODE) + nid = 0; + mask = cpumask_of_node(nid); for (i = 0; i < instance->low_latency_index_start; i++) { irq = pci_irq_vector(instance->pdev, i); diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c index fe0f122f07b0..aa1932ba17cb 100644 --- a/drivers/spi/spi-cadence-quadspi.c +++ b/drivers/spi/spi-cadence-quadspi.c @@ -1958,10 +1958,10 @@ static int cqspi_probe(struct platform_device *pdev) goto probe_setup_failed; } - ret = devm_pm_runtime_enable(dev); - if (ret) { - if (cqspi->rx_chan) - dma_release_channel(cqspi->rx_chan); + pm_runtime_enable(dev); + + if (cqspi->rx_chan) { + dma_release_channel(cqspi->rx_chan); goto probe_setup_failed; } @@ -1981,6 +1981,7 @@ static int cqspi_probe(struct platform_device *pdev) return 0; probe_setup_failed: cqspi_controller_enable(cqspi, 0); + pm_runtime_disable(dev); probe_reset_failed: if (cqspi->is_jh7110) cqspi_jh7110_disable_clk(pdev, cqspi); @@ -1999,7 +2000,8 @@ static void cqspi_remove(struct platform_device *pdev) if (cqspi->rx_chan) dma_release_channel(cqspi->rx_chan); - clk_disable_unprepare(cqspi->clk); + if (pm_runtime_get_sync(&pdev->dev) >= 0) + clk_disable(cqspi->clk); if (cqspi->is_jh7110) cqspi_jh7110_disable_clk(pdev, cqspi); diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index f62d89c8e580..50adfb8b335b 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -7807,7 +7807,8 @@ static int ufshcd_host_reset_and_restore(struct ufs_hba *hba) hba->silence_err_logs = false; /* scale up clocks to max frequency before full reinitialization */ - ufshcd_scale_clks(hba, ULONG_MAX, true); + if (ufshcd_is_clkscaling_supported(hba)) + ufshcd_scale_clks(hba, ULONG_MAX, true); err = ufshcd_hba_enable(hba); diff --git a/fs/bcachefs/alloc_background.c b/fs/bcachefs/alloc_background.c index b228a5a64479..66de46318620 100644 --- a/fs/bcachefs/alloc_background.c +++ b/fs/bcachefs/alloc_background.c @@ -1406,6 +1406,9 @@ int bch2_check_discard_freespace_key(struct btree_trans *trans, struct btree_ite : BCH_DATA_free; struct printbuf buf = PRINTBUF; + unsigned fsck_flags = (async_repair ? FSCK_ERR_NO_LOG : 0)| + FSCK_CAN_FIX|FSCK_CAN_IGNORE; + struct bpos bucket = iter->pos; bucket.offset &= ~(~0ULL << 56); u64 genbits = iter->pos.offset & (~0ULL << 56); @@ -1419,9 +1422,10 @@ int bch2_check_discard_freespace_key(struct btree_trans *trans, struct btree_ite return ret; if (!bch2_dev_bucket_exists(c, bucket)) { - if (fsck_err(trans, need_discard_freespace_key_to_invalid_dev_bucket, - "entry in %s btree for nonexistant dev:bucket %llu:%llu", - bch2_btree_id_str(iter->btree_id), bucket.inode, bucket.offset)) + if (__fsck_err(trans, fsck_flags, + need_discard_freespace_key_to_invalid_dev_bucket, + "entry in %s btree for nonexistant dev:bucket %llu:%llu", + bch2_btree_id_str(iter->btree_id), bucket.inode, bucket.offset)) goto delete; ret = 1; goto out; @@ -1433,7 +1437,8 @@ int bch2_check_discard_freespace_key(struct btree_trans *trans, struct btree_ite if (a->data_type != state || (state == BCH_DATA_free && genbits != alloc_freespace_genbits(*a))) { - if (fsck_err(trans, need_discard_freespace_key_bad, + if (__fsck_err(trans, fsck_flags, + need_discard_freespace_key_bad, "%s\nincorrectly set at %s:%llu:%llu:0 (free %u, genbits %llu should be %llu)", (bch2_bkey_val_to_text(&buf, c, alloc_k), buf.buf), bch2_btree_id_str(iter->btree_id), diff --git a/fs/bcachefs/backpointers.c b/fs/bcachefs/backpointers.c index e76809e71858..77d93beb3c8f 100644 --- a/fs/bcachefs/backpointers.c +++ b/fs/bcachefs/backpointers.c @@ -353,7 +353,7 @@ static struct bkey_s_c __bch2_backpointer_get_key(struct btree_trans *trans, return ret ? bkey_s_c_err(ret) : bkey_s_c_null; } else { struct btree *b = __bch2_backpointer_get_node(trans, bp, iter, last_flushed, commit); - if (b == ERR_PTR(bch_err_throw(c, backpointer_to_overwritten_btree_node))) + if (b == ERR_PTR(-BCH_ERR_backpointer_to_overwritten_btree_node)) return bkey_s_c_null; if (IS_ERR_OR_NULL(b)) return ((struct bkey_s_c) { .k = ERR_CAST(b) }); diff --git a/fs/bcachefs/bcachefs.h b/fs/bcachefs/bcachefs.h index 5a1cede2febf..8043943cdf6a 100644 --- a/fs/bcachefs/bcachefs.h +++ b/fs/bcachefs/bcachefs.h @@ -767,7 +767,8 @@ struct btree_trans_buf { x(sysfs) \ x(btree_write_buffer) \ x(btree_node_scrub) \ - x(async_recovery_passes) + x(async_recovery_passes) \ + x(ioctl_data) enum bch_write_ref { #define x(n) BCH_WRITE_REF_##n, diff --git a/fs/bcachefs/btree_gc.c b/fs/bcachefs/btree_gc.c index e92cf3928c63..bac108e93823 100644 --- a/fs/bcachefs/btree_gc.c +++ b/fs/bcachefs/btree_gc.c @@ -503,8 +503,14 @@ again: prt_newline(&buf); bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&b->key)); + /* + * XXX: we're not passing the trans object here because we're not set up + * to handle a transaction restart - this code needs to be rewritten + * when we start doing online topology repair + */ + bch2_trans_unlock_long(trans); if (mustfix_fsck_err_on(!have_child, - trans, btree_node_topology_interior_node_empty, + c, btree_node_topology_interior_node_empty, "empty interior btree node at %s", buf.buf)) ret = DROP_THIS_NODE; err: @@ -528,32 +534,39 @@ fsck_err: return ret; } -static int bch2_check_root(struct btree_trans *trans, enum btree_id i, +static int bch2_check_root(struct btree_trans *trans, enum btree_id btree, bool *reconstructed_root) { struct bch_fs *c = trans->c; - struct btree_root *r = bch2_btree_id_root(c, i); + struct btree_root *r = bch2_btree_id_root(c, btree); struct printbuf buf = PRINTBUF; int ret = 0; - bch2_btree_id_to_text(&buf, i); + bch2_btree_id_to_text(&buf, btree); if (r->error) { bch_info(c, "btree root %s unreadable, must recover from scan", buf.buf); - r->alive = false; - r->error = 0; + ret = bch2_btree_has_scanned_nodes(c, btree); + if (ret < 0) + goto err; - if (!bch2_btree_has_scanned_nodes(c, i)) { + if (!ret) { __fsck_err(trans, - FSCK_CAN_FIX|(!btree_id_important(i) ? FSCK_AUTOFIX : 0), + FSCK_CAN_FIX|(!btree_id_important(btree) ? FSCK_AUTOFIX : 0), btree_root_unreadable_and_scan_found_nothing, "no nodes found for btree %s, continue?", buf.buf); - bch2_btree_root_alloc_fake_trans(trans, i, 0); + + r->alive = false; + r->error = 0; + bch2_btree_root_alloc_fake_trans(trans, btree, 0); } else { - bch2_btree_root_alloc_fake_trans(trans, i, 1); - bch2_shoot_down_journal_keys(c, i, 1, BTREE_MAX_DEPTH, POS_MIN, SPOS_MAX); - ret = bch2_get_scanned_nodes(c, i, 0, POS_MIN, SPOS_MAX); + r->alive = false; + r->error = 0; + bch2_btree_root_alloc_fake_trans(trans, btree, 1); + + bch2_shoot_down_journal_keys(c, btree, 1, BTREE_MAX_DEPTH, POS_MIN, SPOS_MAX); + ret = bch2_get_scanned_nodes(c, btree, 0, POS_MIN, SPOS_MAX); if (ret) goto err; } diff --git a/fs/bcachefs/btree_io.c b/fs/bcachefs/btree_io.c index d8f3c4c65e90..08b22bddd747 100644 --- a/fs/bcachefs/btree_io.c +++ b/fs/bcachefs/btree_io.c @@ -557,7 +557,9 @@ static int __btree_err(int ret, const char *fmt, ...) { if (c->recovery.curr_pass == BCH_RECOVERY_PASS_scan_for_btree_nodes) - return bch_err_throw(c, fsck_fix); + return ret == -BCH_ERR_btree_node_read_err_fixable + ? bch_err_throw(c, fsck_fix) + : ret; bool have_retry = false; int ret2; @@ -723,12 +725,11 @@ void bch2_btree_node_drop_keys_outside_node(struct btree *b) static int validate_bset(struct bch_fs *c, struct bch_dev *ca, struct btree *b, struct bset *i, - unsigned offset, unsigned sectors, int write, + unsigned offset, int write, struct bch_io_failures *failed, struct printbuf *err_msg) { unsigned version = le16_to_cpu(i->version); - unsigned ptr_written = btree_ptr_sectors_written(bkey_i_to_s_c(&b->key)); struct printbuf buf1 = PRINTBUF; struct printbuf buf2 = PRINTBUF; int ret = 0; @@ -778,15 +779,6 @@ static int validate_bset(struct bch_fs *c, struct bch_dev *ca, btree_node_unsupported_version, "BSET_SEPARATE_WHITEOUTS no longer supported"); - if (!write && - btree_err_on(offset + sectors > (ptr_written ?: btree_sectors(c)), - -BCH_ERR_btree_node_read_err_fixable, - c, ca, b, i, NULL, - bset_past_end_of_btree_node, - "bset past end of btree node (offset %u len %u but written %zu)", - offset, sectors, ptr_written ?: btree_sectors(c))) - i->u64s = 0; - btree_err_on(offset && !i->u64s, -BCH_ERR_btree_node_read_err_fixable, c, ca, b, i, NULL, @@ -1151,6 +1143,14 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca, "unknown checksum type %llu", BSET_CSUM_TYPE(i)); if (first) { + sectors = vstruct_sectors(b->data, c->block_bits); + if (btree_err_on(b->written + sectors > (ptr_written ?: btree_sectors(c)), + -BCH_ERR_btree_node_read_err_fixable, + c, ca, b, i, NULL, + bset_past_end_of_btree_node, + "bset past end of btree node (offset %u len %u but written %zu)", + b->written, sectors, ptr_written ?: btree_sectors(c))) + i->u64s = 0; if (good_csum_type) { struct bch_csum csum = csum_vstruct(c, BSET_CSUM_TYPE(i), nonce, b->data); bool csum_bad = bch2_crc_cmp(b->data->csum, csum); @@ -1178,9 +1178,15 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca, c, NULL, b, NULL, NULL, btree_node_unsupported_version, "btree node does not have NEW_EXTENT_OVERWRITE set"); - - sectors = vstruct_sectors(b->data, c->block_bits); } else { + sectors = vstruct_sectors(bne, c->block_bits); + if (btree_err_on(b->written + sectors > (ptr_written ?: btree_sectors(c)), + -BCH_ERR_btree_node_read_err_fixable, + c, ca, b, i, NULL, + bset_past_end_of_btree_node, + "bset past end of btree node (offset %u len %u but written %zu)", + b->written, sectors, ptr_written ?: btree_sectors(c))) + i->u64s = 0; if (good_csum_type) { struct bch_csum csum = csum_vstruct(c, BSET_CSUM_TYPE(i), nonce, bne); bool csum_bad = bch2_crc_cmp(bne->csum, csum); @@ -1201,14 +1207,12 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca, "decrypting btree node: %s", bch2_err_str(ret))) goto fsck_err; } - - sectors = vstruct_sectors(bne, c->block_bits); } b->version_ondisk = min(b->version_ondisk, le16_to_cpu(i->version)); - ret = validate_bset(c, ca, b, i, b->written, sectors, READ, failed, err_msg); + ret = validate_bset(c, ca, b, i, b->written, READ, failed, err_msg); if (ret) goto fsck_err; @@ -1982,28 +1986,12 @@ static void btree_node_scrub_work(struct work_struct *work) prt_newline(&err); if (!btree_node_scrub_check(c, scrub->buf, scrub->written, &err)) { - struct btree_trans *trans = bch2_trans_get(c); - - struct btree_iter iter; - bch2_trans_node_iter_init(trans, &iter, scrub->btree, - scrub->key.k->k.p, 0, scrub->level - 1, 0); - - struct btree *b; - int ret = lockrestart_do(trans, - PTR_ERR_OR_ZERO(b = bch2_btree_iter_peek_node(trans, &iter))); - if (ret) - goto err; - - if (bkey_i_to_btree_ptr_v2(&b->key)->v.seq == scrub->seq) { - bch_err(c, "error validating btree node during scrub on %s at btree %s", - scrub->ca->name, err.buf); - - ret = bch2_btree_node_rewrite(trans, &iter, b, 0, 0); - } -err: - bch2_trans_iter_exit(trans, &iter); - bch2_trans_begin(trans); - bch2_trans_put(trans); + int ret = bch2_trans_do(c, + bch2_btree_node_rewrite_key(trans, scrub->btree, scrub->level - 1, + scrub->key.k, 0)); + if (!bch2_err_matches(ret, ENOENT) && + !bch2_err_matches(ret, EROFS)) + bch_err_fn_ratelimited(c, ret); } printbuf_exit(&err); @@ -2267,7 +2255,7 @@ static void btree_node_write_endio(struct bio *bio) } static int validate_bset_for_write(struct bch_fs *c, struct btree *b, - struct bset *i, unsigned sectors) + struct bset *i) { int ret = bch2_bkey_validate(c, bkey_i_to_s_c(&b->key), (struct bkey_validate_context) { @@ -2282,7 +2270,7 @@ static int validate_bset_for_write(struct bch_fs *c, struct btree *b, } ret = validate_bset_keys(c, b, i, WRITE, NULL, NULL) ?: - validate_bset(c, NULL, b, i, b->written, sectors, WRITE, NULL, NULL); + validate_bset(c, NULL, b, i, b->written, WRITE, NULL, NULL); if (ret) { bch2_inconsistent_error(c); dump_stack(); @@ -2475,7 +2463,7 @@ do_write: /* if we're going to be encrypting, check metadata validity first: */ if (validate_before_checksum && - validate_bset_for_write(c, b, i, sectors_to_write)) + validate_bset_for_write(c, b, i)) goto err; ret = bset_encrypt(c, i, b->written << 9); @@ -2492,7 +2480,7 @@ do_write: /* if we're not encrypting, check metadata after checksumming: */ if (!validate_before_checksum && - validate_bset_for_write(c, b, i, sectors_to_write)) + validate_bset_for_write(c, b, i)) goto err; /* diff --git a/fs/bcachefs/btree_iter.c b/fs/bcachefs/btree_iter.c index b78403376c07..352f9cd2634f 100644 --- a/fs/bcachefs/btree_iter.c +++ b/fs/bcachefs/btree_iter.c @@ -2076,14 +2076,14 @@ inline bool bch2_btree_iter_rewind(struct btree_trans *trans, struct btree_iter static noinline void bch2_btree_trans_peek_prev_updates(struct btree_trans *trans, struct btree_iter *iter, - struct bkey_s_c *k) + struct bpos search_key, struct bkey_s_c *k) { struct bpos end = path_l(btree_iter_path(trans, iter))->b->data->min_key; trans_for_each_update(trans, i) if (!i->key_cache_already_flushed && i->btree_id == iter->btree_id && - bpos_le(i->k->k.p, iter->pos) && + bpos_le(i->k->k.p, search_key) && bpos_ge(i->k->k.p, k->k ? k->k->p : end)) { iter->k = i->k->k; *k = bkey_i_to_s_c(i->k); @@ -2092,6 +2092,7 @@ void bch2_btree_trans_peek_prev_updates(struct btree_trans *trans, struct btree_ static noinline void bch2_btree_trans_peek_updates(struct btree_trans *trans, struct btree_iter *iter, + struct bpos search_key, struct bkey_s_c *k) { struct btree_path *path = btree_iter_path(trans, iter); @@ -2100,7 +2101,7 @@ void bch2_btree_trans_peek_updates(struct btree_trans *trans, struct btree_iter trans_for_each_update(trans, i) if (!i->key_cache_already_flushed && i->btree_id == iter->btree_id && - bpos_ge(i->k->k.p, path->pos) && + bpos_ge(i->k->k.p, search_key) && bpos_le(i->k->k.p, k->k ? k->k->p : end)) { iter->k = i->k->k; *k = bkey_i_to_s_c(i->k); @@ -2122,13 +2123,14 @@ void bch2_btree_trans_peek_slot_updates(struct btree_trans *trans, struct btree_ static struct bkey_i *bch2_btree_journal_peek(struct btree_trans *trans, struct btree_iter *iter, + struct bpos search_pos, struct bpos end_pos) { struct btree_path *path = btree_iter_path(trans, iter); return bch2_journal_keys_peek_max(trans->c, iter->btree_id, path->level, - path->pos, + search_pos, end_pos, &iter->journal_idx); } @@ -2138,7 +2140,7 @@ struct bkey_s_c btree_trans_peek_slot_journal(struct btree_trans *trans, struct btree_iter *iter) { struct btree_path *path = btree_iter_path(trans, iter); - struct bkey_i *k = bch2_btree_journal_peek(trans, iter, path->pos); + struct bkey_i *k = bch2_btree_journal_peek(trans, iter, path->pos, path->pos); if (k) { iter->k = k->k; @@ -2151,11 +2153,12 @@ struct bkey_s_c btree_trans_peek_slot_journal(struct btree_trans *trans, static noinline void btree_trans_peek_journal(struct btree_trans *trans, struct btree_iter *iter, + struct bpos search_key, struct bkey_s_c *k) { struct btree_path *path = btree_iter_path(trans, iter); struct bkey_i *next_journal = - bch2_btree_journal_peek(trans, iter, + bch2_btree_journal_peek(trans, iter, search_key, k->k ? k->k->p : path_l(path)->b->key.k.p); if (next_journal) { iter->k = next_journal->k; @@ -2165,13 +2168,14 @@ void btree_trans_peek_journal(struct btree_trans *trans, static struct bkey_i *bch2_btree_journal_peek_prev(struct btree_trans *trans, struct btree_iter *iter, + struct bpos search_key, struct bpos end_pos) { struct btree_path *path = btree_iter_path(trans, iter); return bch2_journal_keys_peek_prev_min(trans->c, iter->btree_id, path->level, - path->pos, + search_key, end_pos, &iter->journal_idx); } @@ -2179,11 +2183,12 @@ static struct bkey_i *bch2_btree_journal_peek_prev(struct btree_trans *trans, static noinline void btree_trans_peek_prev_journal(struct btree_trans *trans, struct btree_iter *iter, + struct bpos search_key, struct bkey_s_c *k) { struct btree_path *path = btree_iter_path(trans, iter); struct bkey_i *next_journal = - bch2_btree_journal_peek_prev(trans, iter, + bch2_btree_journal_peek_prev(trans, iter, search_key, k->k ? k->k->p : path_l(path)->b->key.k.p); if (next_journal) { @@ -2292,11 +2297,11 @@ static struct bkey_s_c __bch2_btree_iter_peek(struct btree_trans *trans, struct } if (unlikely(iter->flags & BTREE_ITER_with_journal)) - btree_trans_peek_journal(trans, iter, &k); + btree_trans_peek_journal(trans, iter, search_key, &k); if (unlikely((iter->flags & BTREE_ITER_with_updates) && trans->nr_updates)) - bch2_btree_trans_peek_updates(trans, iter, &k); + bch2_btree_trans_peek_updates(trans, iter, search_key, &k); if (k.k && bkey_deleted(k.k)) { /* @@ -2326,6 +2331,20 @@ static struct bkey_s_c __bch2_btree_iter_peek(struct btree_trans *trans, struct } bch2_btree_iter_verify(trans, iter); + + if (trace___btree_iter_peek_enabled()) { + CLASS(printbuf, buf)(); + + int ret = bkey_err(k); + if (ret) + prt_str(&buf, bch2_err_str(ret)); + else if (k.k) + bch2_bkey_val_to_text(&buf, trans->c, k); + else + prt_str(&buf, "(null)"); + trace___btree_iter_peek(trans->c, buf.buf); + } + return k; } @@ -2484,6 +2503,19 @@ out_no_locked: bch2_btree_iter_verify_entry_exit(iter); + if (trace_btree_iter_peek_max_enabled()) { + CLASS(printbuf, buf)(); + + int ret = bkey_err(k); + if (ret) + prt_str(&buf, bch2_err_str(ret)); + else if (k.k) + bch2_bkey_val_to_text(&buf, trans->c, k); + else + prt_str(&buf, "(null)"); + trace_btree_iter_peek_max(trans->c, buf.buf); + } + return k; end: bch2_btree_iter_set_pos(trans, iter, end); @@ -2557,11 +2589,11 @@ static struct bkey_s_c __bch2_btree_iter_peek_prev(struct btree_trans *trans, st } if (unlikely(iter->flags & BTREE_ITER_with_journal)) - btree_trans_peek_prev_journal(trans, iter, &k); + btree_trans_peek_prev_journal(trans, iter, search_key, &k); if (unlikely((iter->flags & BTREE_ITER_with_updates) && trans->nr_updates)) - bch2_btree_trans_peek_prev_updates(trans, iter, &k); + bch2_btree_trans_peek_prev_updates(trans, iter, search_key, &k); if (likely(k.k && !bkey_deleted(k.k))) { break; @@ -2724,6 +2756,19 @@ out_no_locked: bch2_btree_iter_verify_entry_exit(iter); bch2_btree_iter_verify(trans, iter); + + if (trace_btree_iter_peek_prev_min_enabled()) { + CLASS(printbuf, buf)(); + + int ret = bkey_err(k); + if (ret) + prt_str(&buf, bch2_err_str(ret)); + else if (k.k) + bch2_bkey_val_to_text(&buf, trans->c, k); + else + prt_str(&buf, "(null)"); + trace_btree_iter_peek_prev_min(trans->c, buf.buf); + } return k; end: bch2_btree_iter_set_pos(trans, iter, end); @@ -2767,8 +2812,10 @@ struct bkey_s_c bch2_btree_iter_peek_slot(struct btree_trans *trans, struct btre /* extents can't span inode numbers: */ if ((iter->flags & BTREE_ITER_is_extents) && unlikely(iter->pos.offset == KEY_OFFSET_MAX)) { - if (iter->pos.inode == KEY_INODE_MAX) - return bkey_s_c_null; + if (iter->pos.inode == KEY_INODE_MAX) { + k = bkey_s_c_null; + goto out2; + } bch2_btree_iter_set_pos(trans, iter, bpos_nosnap_successor(iter->pos)); } @@ -2785,8 +2832,10 @@ struct bkey_s_c bch2_btree_iter_peek_slot(struct btree_trans *trans, struct btre } struct btree_path *path = btree_iter_path(trans, iter); - if (unlikely(!btree_path_node(path, path->level))) - return bkey_s_c_null; + if (unlikely(!btree_path_node(path, path->level))) { + k = bkey_s_c_null; + goto out2; + } btree_path_set_should_be_locked(trans, path); @@ -2879,7 +2928,20 @@ out: bch2_btree_iter_verify(trans, iter); ret = bch2_btree_iter_verify_ret(trans, iter, k); if (unlikely(ret)) - return bkey_s_c_err(ret); + k = bkey_s_c_err(ret); +out2: + if (trace_btree_iter_peek_slot_enabled()) { + CLASS(printbuf, buf)(); + + int ret = bkey_err(k); + if (ret) + prt_str(&buf, bch2_err_str(ret)); + else if (k.k) + bch2_bkey_val_to_text(&buf, trans->c, k); + else + prt_str(&buf, "(null)"); + trace_btree_iter_peek_slot(trans->c, buf.buf); + } return k; } @@ -3132,6 +3194,10 @@ void *__bch2_trans_kmalloc(struct btree_trans *trans, size_t size, unsigned long if (WARN_ON_ONCE(new_bytes > BTREE_TRANS_MEM_MAX)) { #ifdef CONFIG_BCACHEFS_TRANS_KMALLOC_TRACE struct printbuf buf = PRINTBUF; + bch2_log_msg_start(c, &buf); + prt_printf(&buf, "bump allocator exceeded BTREE_TRANS_MEM_MAX (%u)\n", + BTREE_TRANS_MEM_MAX); + bch2_trans_kmalloc_trace_to_text(&buf, &trans->trans_kmalloc_trace); bch2_print_str(c, KERN_ERR, buf.buf); printbuf_exit(&buf); @@ -3159,46 +3225,32 @@ void *__bch2_trans_kmalloc(struct btree_trans *trans, size_t size, unsigned long mutex_unlock(&s->lock); } - if (trans->used_mempool) { - if (trans->mem_bytes >= new_bytes) - goto out_change_top; - - /* No more space from mempool item, need malloc new one */ - new_mem = kmalloc(new_bytes, GFP_NOWAIT|__GFP_NOWARN); - if (unlikely(!new_mem)) { - bch2_trans_unlock(trans); - - new_mem = kmalloc(new_bytes, GFP_KERNEL); - if (!new_mem) - return ERR_PTR(-BCH_ERR_ENOMEM_trans_kmalloc); + if (trans->used_mempool || new_bytes > BTREE_TRANS_MEM_MAX) { + EBUG_ON(trans->mem_bytes >= new_bytes); + return ERR_PTR(-BCH_ERR_ENOMEM_trans_kmalloc); + } - ret = bch2_trans_relock(trans); - if (ret) { - kfree(new_mem); - return ERR_PTR(ret); - } - } - memcpy(new_mem, trans->mem, trans->mem_top); - trans->used_mempool = false; - mempool_free(trans->mem, &c->btree_trans_mem_pool); - goto out_new_mem; + if (old_bytes) { + trans->realloc_bytes_required = new_bytes; + trace_and_count(c, trans_restart_mem_realloced, trans, _RET_IP_, new_bytes); + return ERR_PTR(btree_trans_restart_ip(trans, + BCH_ERR_transaction_restart_mem_realloced, _RET_IP_)); } - new_mem = krealloc(trans->mem, new_bytes, GFP_NOWAIT|__GFP_NOWARN); + EBUG_ON(trans->mem); + + new_mem = kmalloc(new_bytes, GFP_NOWAIT|__GFP_NOWARN); if (unlikely(!new_mem)) { bch2_trans_unlock(trans); - new_mem = krealloc(trans->mem, new_bytes, GFP_KERNEL); + new_mem = kmalloc(new_bytes, GFP_KERNEL); if (!new_mem && new_bytes <= BTREE_TRANS_MEM_MAX) { new_mem = mempool_alloc(&c->btree_trans_mem_pool, GFP_KERNEL); new_bytes = BTREE_TRANS_MEM_MAX; - memcpy(new_mem, trans->mem, trans->mem_top); trans->used_mempool = true; - kfree(trans->mem); } - if (!new_mem) - return ERR_PTR(-BCH_ERR_ENOMEM_trans_kmalloc); + EBUG_ON(!new_mem); trans->mem = new_mem; trans->mem_bytes = new_bytes; @@ -3207,18 +3259,10 @@ void *__bch2_trans_kmalloc(struct btree_trans *trans, size_t size, unsigned long if (ret) return ERR_PTR(ret); } -out_new_mem: + trans->mem = new_mem; trans->mem_bytes = new_bytes; - if (old_bytes) { - trace_and_count(c, trans_restart_mem_realloced, trans, _RET_IP_, new_bytes); - return ERR_PTR(btree_trans_restart_ip(trans, - BCH_ERR_transaction_restart_mem_realloced, _RET_IP_)); - } -out_change_top: - bch2_trans_kmalloc_trace(trans, size, ip); - p = trans->mem + trans->mem_top; trans->mem_top += size; memset(p, 0, size); @@ -3279,6 +3323,27 @@ u32 bch2_trans_begin(struct btree_trans *trans) trans->restart_count++; trans->mem_top = 0; + if (trans->restarted == BCH_ERR_transaction_restart_mem_realloced) { + EBUG_ON(!trans->mem || !trans->mem_bytes); + unsigned new_bytes = trans->realloc_bytes_required; + void *new_mem = krealloc(trans->mem, new_bytes, GFP_NOWAIT|__GFP_NOWARN); + if (unlikely(!new_mem)) { + bch2_trans_unlock(trans); + new_mem = krealloc(trans->mem, new_bytes, GFP_KERNEL); + + EBUG_ON(new_bytes > BTREE_TRANS_MEM_MAX); + + if (!new_mem) { + new_mem = mempool_alloc(&trans->c->btree_trans_mem_pool, GFP_KERNEL); + new_bytes = BTREE_TRANS_MEM_MAX; + trans->used_mempool = true; + kfree(trans->mem); + } + } + trans->mem = new_mem; + trans->mem_bytes = new_bytes; + } + trans_for_each_path(trans, path, i) { path->should_be_locked = false; diff --git a/fs/bcachefs/btree_journal_iter.c b/fs/bcachefs/btree_journal_iter.c index cf7398751644..ea839560a136 100644 --- a/fs/bcachefs/btree_journal_iter.c +++ b/fs/bcachefs/btree_journal_iter.c @@ -137,12 +137,15 @@ struct bkey_i *bch2_journal_keys_peek_prev_min(struct bch_fs *c, enum btree_id b struct journal_key *k; BUG_ON(*idx > keys->nr); + + if (!keys->nr) + return NULL; search: if (!*idx) *idx = __bch2_journal_key_search(keys, btree_id, level, pos); - while (*idx && - __journal_key_cmp(btree_id, level, end_pos, idx_to_key(keys, *idx - 1)) <= 0) { + while (*idx < keys->nr && + __journal_key_cmp(btree_id, level, end_pos, idx_to_key(keys, *idx)) >= 0) { (*idx)++; iters++; if (iters == 10) { @@ -151,18 +154,23 @@ search: } } + if (*idx == keys->nr) + --(*idx); + struct bkey_i *ret = NULL; rcu_read_lock(); /* for overwritten_ranges */ - while ((k = *idx < keys->nr ? idx_to_key(keys, *idx) : NULL)) { + while (true) { + k = idx_to_key(keys, *idx); if (__journal_key_cmp(btree_id, level, end_pos, k) > 0) break; if (k->overwritten) { if (k->overwritten_range) - *idx = rcu_dereference(k->overwritten_range)->start - 1; - else - *idx -= 1; + *idx = rcu_dereference(k->overwritten_range)->start; + if (!*idx) + break; + --(*idx); continue; } @@ -171,6 +179,8 @@ search: break; } + if (!*idx) + break; --(*idx); iters++; if (iters == 10) { @@ -641,10 +651,11 @@ static int journal_sort_key_cmp(const void *_l, const void *_r) { const struct journal_key *l = _l; const struct journal_key *r = _r; + int rewind = l->rewind && r->rewind ? -1 : 1; return journal_key_cmp(l, r) ?: - cmp_int(l->journal_seq, r->journal_seq) ?: - cmp_int(l->journal_offset, r->journal_offset); + ((cmp_int(l->journal_seq, r->journal_seq) ?: + cmp_int(l->journal_offset, r->journal_offset)) * rewind); } void bch2_journal_keys_put(struct bch_fs *c) @@ -713,6 +724,8 @@ int bch2_journal_keys_sort(struct bch_fs *c) struct journal_keys *keys = &c->journal_keys; size_t nr_read = 0; + u64 rewind_seq = c->opts.journal_rewind ?: U64_MAX; + genradix_for_each(&c->journal_entries, iter, _i) { i = *_i; @@ -721,28 +734,43 @@ int bch2_journal_keys_sort(struct bch_fs *c) cond_resched(); - for_each_jset_key(k, entry, &i->j) { - struct journal_key n = (struct journal_key) { - .btree_id = entry->btree_id, - .level = entry->level, - .k = k, - .journal_seq = le64_to_cpu(i->j.seq), - .journal_offset = k->_data - i->j._data, - }; - - if (darray_push(keys, n)) { - __journal_keys_sort(keys); - - if (keys->nr * 8 > keys->size * 7) { - bch_err(c, "Too many journal keys for slowpath; have %zu compacted, buf size %zu, processed %zu keys at seq %llu", - keys->nr, keys->size, nr_read, le64_to_cpu(i->j.seq)); - return bch_err_throw(c, ENOMEM_journal_keys_sort); + vstruct_for_each(&i->j, entry) { + bool rewind = !entry->level && + !btree_id_is_alloc(entry->btree_id) && + le64_to_cpu(i->j.seq) >= rewind_seq; + + if (entry->type != (rewind + ? BCH_JSET_ENTRY_overwrite + : BCH_JSET_ENTRY_btree_keys)) + continue; + + if (!rewind && le64_to_cpu(i->j.seq) < c->journal_replay_seq_start) + continue; + + jset_entry_for_each_key(entry, k) { + struct journal_key n = (struct journal_key) { + .btree_id = entry->btree_id, + .level = entry->level, + .rewind = rewind, + .k = k, + .journal_seq = le64_to_cpu(i->j.seq), + .journal_offset = k->_data - i->j._data, + }; + + if (darray_push(keys, n)) { + __journal_keys_sort(keys); + + if (keys->nr * 8 > keys->size * 7) { + bch_err(c, "Too many journal keys for slowpath; have %zu compacted, buf size %zu, processed %zu keys at seq %llu", + keys->nr, keys->size, nr_read, le64_to_cpu(i->j.seq)); + return bch_err_throw(c, ENOMEM_journal_keys_sort); + } + + BUG_ON(darray_push(keys, n)); } - BUG_ON(darray_push(keys, n)); + nr_read++; } - - nr_read++; } } diff --git a/fs/bcachefs/btree_journal_iter_types.h b/fs/bcachefs/btree_journal_iter_types.h index 8b773823704f..86aacb254fb2 100644 --- a/fs/bcachefs/btree_journal_iter_types.h +++ b/fs/bcachefs/btree_journal_iter_types.h @@ -11,8 +11,9 @@ struct journal_key { u32 journal_offset; enum btree_id btree_id:8; unsigned level:8; - bool allocated; - bool overwritten; + bool allocated:1; + bool overwritten:1; + bool rewind:1; struct journal_key_range_overwritten __rcu * overwritten_range; struct bkey_i *k; diff --git a/fs/bcachefs/btree_locking.c b/fs/bcachefs/btree_locking.c index 91a51aef82f1..bed2b4b6ffb9 100644 --- a/fs/bcachefs/btree_locking.c +++ b/fs/bcachefs/btree_locking.c @@ -771,7 +771,7 @@ static inline void __bch2_trans_unlock(struct btree_trans *trans) } static noinline __cold void bch2_trans_relock_fail(struct btree_trans *trans, struct btree_path *path, - struct get_locks_fail *f, bool trace) + struct get_locks_fail *f, bool trace, ulong ip) { if (!trace) goto out; @@ -796,7 +796,7 @@ static noinline __cold void bch2_trans_relock_fail(struct btree_trans *trans, st prt_printf(&buf, " total locked %u.%u.%u", c.n[0], c.n[1], c.n[2]); } - trace_trans_restart_relock(trans, _RET_IP_, buf.buf); + trace_trans_restart_relock(trans, ip, buf.buf); printbuf_exit(&buf); } @@ -806,7 +806,7 @@ out: bch2_trans_verify_locks(trans); } -static inline int __bch2_trans_relock(struct btree_trans *trans, bool trace) +static inline int __bch2_trans_relock(struct btree_trans *trans, bool trace, ulong ip) { bch2_trans_verify_locks(trans); @@ -825,7 +825,7 @@ static inline int __bch2_trans_relock(struct btree_trans *trans, bool trace) if (path->should_be_locked && (ret = btree_path_get_locks(trans, path, false, &f, BCH_ERR_transaction_restart_relock))) { - bch2_trans_relock_fail(trans, path, &f, trace); + bch2_trans_relock_fail(trans, path, &f, trace, ip); return ret; } } @@ -838,12 +838,12 @@ out: int bch2_trans_relock(struct btree_trans *trans) { - return __bch2_trans_relock(trans, true); + return __bch2_trans_relock(trans, true, _RET_IP_); } int bch2_trans_relock_notrace(struct btree_trans *trans) { - return __bch2_trans_relock(trans, false); + return __bch2_trans_relock(trans, false, _RET_IP_); } void bch2_trans_unlock(struct btree_trans *trans) diff --git a/fs/bcachefs/btree_node_scan.c b/fs/bcachefs/btree_node_scan.c index a35847734a60..23d8c62ea4b6 100644 --- a/fs/bcachefs/btree_node_scan.c +++ b/fs/bcachefs/btree_node_scan.c @@ -521,8 +521,12 @@ bool bch2_btree_node_is_stale(struct bch_fs *c, struct btree *b) return false; } -bool bch2_btree_has_scanned_nodes(struct bch_fs *c, enum btree_id btree) +int bch2_btree_has_scanned_nodes(struct bch_fs *c, enum btree_id btree) { + int ret = bch2_run_print_explicit_recovery_pass(c, BCH_RECOVERY_PASS_scan_for_btree_nodes); + if (ret) + return ret; + struct found_btree_node search = { .btree_id = btree, .level = 0, diff --git a/fs/bcachefs/btree_node_scan.h b/fs/bcachefs/btree_node_scan.h index 08687b209787..66e6f9ed19d0 100644 --- a/fs/bcachefs/btree_node_scan.h +++ b/fs/bcachefs/btree_node_scan.h @@ -4,7 +4,7 @@ int bch2_scan_for_btree_nodes(struct bch_fs *); bool bch2_btree_node_is_stale(struct bch_fs *, struct btree *); -bool bch2_btree_has_scanned_nodes(struct bch_fs *, enum btree_id); +int bch2_btree_has_scanned_nodes(struct bch_fs *, enum btree_id); int bch2_get_scanned_nodes(struct bch_fs *, enum btree_id, unsigned, struct bpos, struct bpos); void bch2_find_btree_nodes_exit(struct find_btree_nodes *); diff --git a/fs/bcachefs/btree_trans_commit.c b/fs/bcachefs/btree_trans_commit.c index d9710801e3ee..639ef75b3dbd 100644 --- a/fs/bcachefs/btree_trans_commit.c +++ b/fs/bcachefs/btree_trans_commit.c @@ -595,12 +595,13 @@ bch2_trans_commit_write_locked(struct btree_trans *trans, unsigned flags, int ret = 0; bch2_trans_verify_not_unlocked_or_in_restart(trans); - +#if 0 + /* todo: bring back dynamic fault injection */ if (race_fault()) { trace_and_count(c, trans_restart_fault_inject, trans, trace_ip); return btree_trans_restart(trans, BCH_ERR_transaction_restart_fault_inject); } - +#endif /* * Check if the insert will fit in the leaf node with the write lock * held, otherwise another thread could write the node changing the @@ -757,6 +758,8 @@ bch2_trans_commit_write_locked(struct btree_trans *trans, unsigned flags, btree_trans_journal_entries_start(trans), trans->journal_entries.u64s); + EBUG_ON(trans->journal_res.u64s < trans->journal_entries.u64s); + trans->journal_res.offset += trans->journal_entries.u64s; trans->journal_res.u64s -= trans->journal_entries.u64s; @@ -1003,6 +1006,7 @@ int __bch2_trans_commit(struct btree_trans *trans, unsigned flags) { struct btree_insert_entry *errored_at = NULL; struct bch_fs *c = trans->c; + unsigned journal_u64s = 0; int ret = 0; bch2_trans_verify_not_unlocked_or_in_restart(trans); @@ -1031,10 +1035,10 @@ int __bch2_trans_commit(struct btree_trans *trans, unsigned flags) EBUG_ON(test_bit(BCH_FS_clean_shutdown, &c->flags)); - trans->journal_u64s = trans->journal_entries.u64s + jset_u64s(trans->accounting.u64s); + journal_u64s = jset_u64s(trans->accounting.u64s); trans->journal_transaction_names = READ_ONCE(c->opts.journal_transaction_names); if (trans->journal_transaction_names) - trans->journal_u64s += jset_u64s(JSET_ENTRY_LOG_U64s); + journal_u64s += jset_u64s(JSET_ENTRY_LOG_U64s); trans_for_each_update(trans, i) { struct btree_path *path = trans->paths + i->path; @@ -1054,11 +1058,11 @@ int __bch2_trans_commit(struct btree_trans *trans, unsigned flags) continue; /* we're going to journal the key being updated: */ - trans->journal_u64s += jset_u64s(i->k->k.u64s); + journal_u64s += jset_u64s(i->k->k.u64s); /* and we're also going to log the overwrite: */ if (trans->journal_transaction_names) - trans->journal_u64s += jset_u64s(i->old_k.u64s); + journal_u64s += jset_u64s(i->old_k.u64s); } if (trans->extra_disk_res) { @@ -1076,6 +1080,8 @@ retry: memset(&trans->journal_res, 0, sizeof(trans->journal_res)); memset(&trans->fs_usage_delta, 0, sizeof(trans->fs_usage_delta)); + trans->journal_u64s = journal_u64s + trans->journal_entries.u64s; + ret = do_bch2_trans_commit(trans, flags, &errored_at, _RET_IP_); /* make sure we didn't drop or screw up locks: */ diff --git a/fs/bcachefs/btree_types.h b/fs/bcachefs/btree_types.h index 3aa4a602bd02..112170fd9c8f 100644 --- a/fs/bcachefs/btree_types.h +++ b/fs/bcachefs/btree_types.h @@ -497,6 +497,7 @@ struct btree_trans { void *mem; unsigned mem_top; unsigned mem_bytes; + unsigned realloc_bytes_required; #ifdef CONFIG_BCACHEFS_TRANS_KMALLOC_TRACE darray_trans_kmalloc_trace trans_kmalloc_trace; #endif diff --git a/fs/bcachefs/btree_update.c b/fs/bcachefs/btree_update.c index e97e78c10f49..ee657b9f4b96 100644 --- a/fs/bcachefs/btree_update.c +++ b/fs/bcachefs/btree_update.c @@ -549,20 +549,26 @@ void *__bch2_trans_subbuf_alloc(struct btree_trans *trans, unsigned u64s) { unsigned new_top = buf->u64s + u64s; - unsigned old_size = buf->size; + unsigned new_size = buf->size; - if (new_top > buf->size) - buf->size = roundup_pow_of_two(new_top); + BUG_ON(roundup_pow_of_two(new_top) > U16_MAX); - void *n = bch2_trans_kmalloc_nomemzero(trans, buf->size * sizeof(u64)); + if (new_top > new_size) + new_size = roundup_pow_of_two(new_top); + + void *n = bch2_trans_kmalloc_nomemzero(trans, new_size * sizeof(u64)); if (IS_ERR(n)) return n; + unsigned offset = (u64 *) n - (u64 *) trans->mem; + BUG_ON(offset > U16_MAX); + if (buf->u64s) memcpy(n, btree_trans_subbuf_base(trans, buf), - old_size * sizeof(u64)); + buf->size * sizeof(u64)); buf->base = (u64 *) n - (u64 *) trans->mem; + buf->size = new_size; void *p = btree_trans_subbuf_top(trans, buf); buf->u64s = new_top; diff --git a/fs/bcachefs/btree_update.h b/fs/bcachefs/btree_update.h index 9feef1dc4de5..0b98ab959719 100644 --- a/fs/bcachefs/btree_update.h +++ b/fs/bcachefs/btree_update.h @@ -170,8 +170,7 @@ bch2_trans_jset_entry_alloc(struct btree_trans *trans, unsigned u64s) int bch2_btree_insert_clone_trans(struct btree_trans *, enum btree_id, struct bkey_i *); -int bch2_btree_write_buffer_insert_err(struct btree_trans *, - enum btree_id, struct bkey_i *); +int bch2_btree_write_buffer_insert_err(struct bch_fs *, enum btree_id, struct bkey_i *); static inline int __must_check bch2_trans_update_buffered(struct btree_trans *trans, enum btree_id btree, @@ -182,7 +181,7 @@ static inline int __must_check bch2_trans_update_buffered(struct btree_trans *tr EBUG_ON(k->k.u64s > BTREE_WRITE_BUFERED_U64s_MAX); if (unlikely(!btree_type_uses_write_buffer(btree))) { - int ret = bch2_btree_write_buffer_insert_err(trans, btree, k); + int ret = bch2_btree_write_buffer_insert_err(trans->c, btree, k); dump_stack(); return ret; } diff --git a/fs/bcachefs/btree_update_interior.c b/fs/bcachefs/btree_update_interior.c index e77584607f0d..553059b33bfd 100644 --- a/fs/bcachefs/btree_update_interior.c +++ b/fs/bcachefs/btree_update_interior.c @@ -1287,10 +1287,11 @@ bch2_btree_update_start(struct btree_trans *trans, struct btree_path *path, do { ret = bch2_btree_reserve_get(trans, as, nr_nodes, target, flags, &cl); - + if (!bch2_err_matches(ret, BCH_ERR_operation_blocked)) + break; bch2_trans_unlock(trans); bch2_wait_on_allocator(c, &cl); - } while (bch2_err_matches(ret, BCH_ERR_operation_blocked)); + } while (1); } if (ret) { @@ -2293,9 +2294,9 @@ err: goto out; } -static int bch2_btree_node_rewrite_key(struct btree_trans *trans, - enum btree_id btree, unsigned level, - struct bkey_i *k, unsigned flags) +int bch2_btree_node_rewrite_key(struct btree_trans *trans, + enum btree_id btree, unsigned level, + struct bkey_i *k, unsigned flags) { struct btree_iter iter; bch2_trans_node_iter_init(trans, &iter, @@ -2367,9 +2368,8 @@ static void async_btree_node_rewrite_work(struct work_struct *work) int ret = bch2_trans_do(c, bch2_btree_node_rewrite_key(trans, a->btree_id, a->level, a->key.k, 0)); - if (ret != -ENOENT && - !bch2_err_matches(ret, EROFS) && - ret != -BCH_ERR_journal_shutdown) + if (!bch2_err_matches(ret, ENOENT) && + !bch2_err_matches(ret, EROFS)) bch_err_fn_ratelimited(c, ret); spin_lock(&c->btree_node_rewrites_lock); diff --git a/fs/bcachefs/btree_update_interior.h b/fs/bcachefs/btree_update_interior.h index b649c36c3fbb..ac04e45a8515 100644 --- a/fs/bcachefs/btree_update_interior.h +++ b/fs/bcachefs/btree_update_interior.h @@ -176,6 +176,9 @@ static inline int bch2_foreground_maybe_merge(struct btree_trans *trans, int bch2_btree_node_rewrite(struct btree_trans *, struct btree_iter *, struct btree *, unsigned, unsigned); +int bch2_btree_node_rewrite_key(struct btree_trans *, + enum btree_id, unsigned, + struct bkey_i *, unsigned); int bch2_btree_node_rewrite_pos(struct btree_trans *, enum btree_id, unsigned, struct bpos, unsigned, unsigned); diff --git a/fs/bcachefs/btree_write_buffer.c b/fs/bcachefs/btree_write_buffer.c index 90b21e61d2b6..4b095235a0d2 100644 --- a/fs/bcachefs/btree_write_buffer.c +++ b/fs/bcachefs/btree_write_buffer.c @@ -267,10 +267,9 @@ out: BUG_ON(wb->sorted.size < wb->flushing.keys.nr); } -int bch2_btree_write_buffer_insert_err(struct btree_trans *trans, +int bch2_btree_write_buffer_insert_err(struct bch_fs *c, enum btree_id btree, struct bkey_i *k) { - struct bch_fs *c = trans->c; struct printbuf buf = PRINTBUF; prt_printf(&buf, "attempting to do write buffer update on non wb btree="); @@ -332,7 +331,7 @@ static int bch2_btree_write_buffer_flush_locked(struct btree_trans *trans) struct btree_write_buffered_key *k = &wb->flushing.keys.data[i->idx]; if (unlikely(!btree_type_uses_write_buffer(k->btree))) { - ret = bch2_btree_write_buffer_insert_err(trans, k->btree, &k->k); + ret = bch2_btree_write_buffer_insert_err(trans->c, k->btree, &k->k); goto err; } @@ -676,6 +675,9 @@ int bch2_btree_write_buffer_maybe_flush(struct btree_trans *trans, goto err; bch2_bkey_buf_copy(last_flushed, c, tmp.k); + + /* can we avoid the unconditional restart? */ + trace_and_count(c, trans_restart_write_buffer_flush, trans, _RET_IP_); ret = bch_err_throw(c, transaction_restart_write_buffer_flush); } err: diff --git a/fs/bcachefs/btree_write_buffer.h b/fs/bcachefs/btree_write_buffer.h index 05f56fd1eed0..c351d21aca0b 100644 --- a/fs/bcachefs/btree_write_buffer.h +++ b/fs/bcachefs/btree_write_buffer.h @@ -89,6 +89,12 @@ static inline int bch2_journal_key_to_wb(struct bch_fs *c, struct journal_keys_to_wb *dst, enum btree_id btree, struct bkey_i *k) { + if (unlikely(!btree_type_uses_write_buffer(btree))) { + int ret = bch2_btree_write_buffer_insert_err(c, btree, k); + dump_stack(); + return ret; + } + EBUG_ON(!dst->seq); return k->k.type == KEY_TYPE_accounting diff --git a/fs/bcachefs/chardev.c b/fs/bcachefs/chardev.c index fde3c2380e28..5ea89aa2b0c4 100644 --- a/fs/bcachefs/chardev.c +++ b/fs/bcachefs/chardev.c @@ -319,6 +319,7 @@ static int bch2_data_thread(void *arg) ctx->stats.ret = BCH_IOCTL_DATA_EVENT_RET_done; ctx->stats.data_type = (int) DATA_PROGRESS_DATA_TYPE_done; } + enumerated_ref_put(&ctx->c->writes, BCH_WRITE_REF_ioctl_data); return 0; } @@ -378,15 +379,24 @@ static long bch2_ioctl_data(struct bch_fs *c, struct bch_data_ctx *ctx; int ret; - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; + if (!enumerated_ref_tryget(&c->writes, BCH_WRITE_REF_ioctl_data)) + return -EROFS; - if (arg.op >= BCH_DATA_OP_NR || arg.flags) - return -EINVAL; + if (!capable(CAP_SYS_ADMIN)) { + ret = -EPERM; + goto put_ref; + } + + if (arg.op >= BCH_DATA_OP_NR || arg.flags) { + ret = -EINVAL; + goto put_ref; + } ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); - if (!ctx) - return -ENOMEM; + if (!ctx) { + ret = -ENOMEM; + goto put_ref; + } ctx->c = c; ctx->arg = arg; @@ -395,7 +405,12 @@ static long bch2_ioctl_data(struct bch_fs *c, &bcachefs_data_ops, bch2_data_thread); if (ret < 0) - kfree(ctx); + goto cleanup; + return ret; +cleanup: + kfree(ctx); +put_ref: + enumerated_ref_put(&c->writes, BCH_WRITE_REF_ioctl_data); return ret; } diff --git a/fs/bcachefs/data_update.c b/fs/bcachefs/data_update.c index 5f1174348974..e848e210a9bf 100644 --- a/fs/bcachefs/data_update.c +++ b/fs/bcachefs/data_update.c @@ -249,6 +249,7 @@ static int data_update_invalid_bkey(struct data_update *m, bch2_bkey_val_to_text(&buf, c, k); prt_str(&buf, "\nnew: "); bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(insert)); + prt_newline(&buf); bch2_fs_emergency_read_only2(c, &buf); diff --git a/fs/bcachefs/errcode.h b/fs/bcachefs/errcode.h index ac3264134a15..86a842f1e88e 100644 --- a/fs/bcachefs/errcode.h +++ b/fs/bcachefs/errcode.h @@ -137,7 +137,6 @@ x(BCH_ERR_transaction_restart, transaction_restart_relock) \ x(BCH_ERR_transaction_restart, transaction_restart_relock_path) \ x(BCH_ERR_transaction_restart, transaction_restart_relock_path_intent) \ - x(BCH_ERR_transaction_restart, transaction_restart_relock_after_fill) \ x(BCH_ERR_transaction_restart, transaction_restart_too_many_iters) \ x(BCH_ERR_transaction_restart, transaction_restart_lock_node_reused) \ x(BCH_ERR_transaction_restart, transaction_restart_fill_relock) \ @@ -148,11 +147,8 @@ x(BCH_ERR_transaction_restart, transaction_restart_would_deadlock_write)\ x(BCH_ERR_transaction_restart, transaction_restart_deadlock_recursion_limit)\ x(BCH_ERR_transaction_restart, transaction_restart_upgrade) \ - x(BCH_ERR_transaction_restart, transaction_restart_key_cache_upgrade) \ x(BCH_ERR_transaction_restart, transaction_restart_key_cache_fill) \ x(BCH_ERR_transaction_restart, transaction_restart_key_cache_raced) \ - x(BCH_ERR_transaction_restart, transaction_restart_key_cache_realloced)\ - x(BCH_ERR_transaction_restart, transaction_restart_journal_preres_get) \ x(BCH_ERR_transaction_restart, transaction_restart_split_race) \ x(BCH_ERR_transaction_restart, transaction_restart_write_buffer_flush) \ x(BCH_ERR_transaction_restart, transaction_restart_nested) \ @@ -241,7 +237,6 @@ x(BCH_ERR_journal_res_blocked, journal_buf_enomem) \ x(BCH_ERR_journal_res_blocked, journal_stuck) \ x(BCH_ERR_journal_res_blocked, journal_retry_open) \ - x(BCH_ERR_journal_res_blocked, journal_preres_get_blocked) \ x(BCH_ERR_journal_res_blocked, bucket_alloc_blocked) \ x(BCH_ERR_journal_res_blocked, stripe_alloc_blocked) \ x(BCH_ERR_invalid, invalid_sb) \ diff --git a/fs/bcachefs/error.c b/fs/bcachefs/error.c index a8ec6aae5738..b2a6c041e165 100644 --- a/fs/bcachefs/error.c +++ b/fs/bcachefs/error.c @@ -621,7 +621,9 @@ print: if (s) s->ret = ret; - if (trans) + if (trans && + !(flags & FSCK_ERR_NO_LOG) && + ret == -BCH_ERR_fsck_fix) ret = bch2_trans_log_str(trans, bch2_sb_error_strs[err]) ?: ret; err_unlock: mutex_unlock(&c->fsck_error_msgs_lock); diff --git a/fs/bcachefs/extent_update.c b/fs/bcachefs/extent_update.c index b899ee75f5b9..e76e58a568bf 100644 --- a/fs/bcachefs/extent_update.c +++ b/fs/bcachefs/extent_update.c @@ -139,6 +139,17 @@ int bch2_extent_trim_atomic(struct btree_trans *trans, if (ret) return ret; - bch2_cut_back(end, k); + /* tracepoint */ + + if (bpos_lt(end, k->k.p)) { + if (trace_extent_trim_atomic_enabled()) { + CLASS(printbuf, buf)(); + bch2_bpos_to_text(&buf, end); + prt_newline(&buf); + bch2_bkey_val_to_text(&buf, trans->c, bkey_i_to_s_c(k)); + trace_extent_trim_atomic(trans->c, buf.buf); + } + bch2_cut_back(end, k); + } return 0; } diff --git a/fs/bcachefs/fs.c b/fs/bcachefs/fs.c index 3063a8ddc2df..db24a76563f8 100644 --- a/fs/bcachefs/fs.c +++ b/fs/bcachefs/fs.c @@ -1732,7 +1732,8 @@ static int bch2_fileattr_set(struct mnt_idmap *idmap, bch2_write_inode(c, inode, fssetxattr_inode_update_fn, &s, ATTR_CTIME); mutex_unlock(&inode->ei_update_lock); - return ret; + + return bch2_err_class(ret); } static const struct file_operations bch_file_operations = { diff --git a/fs/bcachefs/fsck.c b/fs/bcachefs/fsck.c index 68ed69a255e1..9920f1affc5b 100644 --- a/fs/bcachefs/fsck.c +++ b/fs/bcachefs/fsck.c @@ -327,7 +327,8 @@ static inline bool inode_should_reattach(struct bch_inode_unpacked *inode) (inode->bi_flags & BCH_INODE_has_child_snapshot)) return false; - return !inode->bi_dir && !(inode->bi_flags & BCH_INODE_unlinked); + return !bch2_inode_has_backpointer(inode) && + !(inode->bi_flags & BCH_INODE_unlinked); } static int maybe_delete_dirent(struct btree_trans *trans, struct bpos d_pos, u32 snapshot) @@ -372,6 +373,18 @@ static int reattach_inode(struct btree_trans *trans, struct bch_inode_unpacked * if (inode->bi_subvol) { inode->bi_parent_subvol = BCACHEFS_ROOT_SUBVOL; + struct btree_iter subvol_iter; + struct bkey_i_subvolume *subvol = + bch2_bkey_get_mut_typed(trans, &subvol_iter, + BTREE_ID_subvolumes, POS(0, inode->bi_subvol), + 0, subvolume); + ret = PTR_ERR_OR_ZERO(subvol); + if (ret) + return ret; + + subvol->v.fs_path_parent = BCACHEFS_ROOT_SUBVOL; + bch2_trans_iter_exit(trans, &subvol_iter); + u64 root_inum; ret = subvol_lookup(trans, inode->bi_parent_subvol, &dirent_snapshot, &root_inum); @@ -387,6 +400,8 @@ static int reattach_inode(struct btree_trans *trans, struct bch_inode_unpacked * if (ret) return ret; + bch_verbose(c, "got lostfound inum %llu", lostfound.bi_inum); + lostfound.bi_nlink += S_ISDIR(inode->bi_mode); /* ensure lost+found inode is also present in inode snapshot */ @@ -423,6 +438,16 @@ static int reattach_inode(struct btree_trans *trans, struct bch_inode_unpacked * if (ret) return ret; + { + CLASS(printbuf, buf)(); + ret = bch2_inum_snapshot_to_path(trans, inode->bi_inum, + inode->bi_snapshot, NULL, &buf); + if (ret) + return ret; + + bch_info(c, "reattached at %s", buf.buf); + } + /* * Fix up inodes in child snapshots: if they should also be reattached * update the backpointer field, if they should not be we need to emit @@ -490,13 +515,21 @@ static struct bkey_s_c_dirent dirent_get_by_pos(struct btree_trans *trans, static int remove_backpointer(struct btree_trans *trans, struct bch_inode_unpacked *inode) { - if (!inode->bi_dir) + if (!bch2_inode_has_backpointer(inode)) return 0; + u32 snapshot = inode->bi_snapshot; + + if (inode->bi_parent_subvol) { + int ret = bch2_subvolume_get_snapshot(trans, inode->bi_parent_subvol, &snapshot); + if (ret) + return ret; + } + struct bch_fs *c = trans->c; struct btree_iter iter; struct bkey_s_c_dirent d = dirent_get_by_pos(trans, &iter, - SPOS(inode->bi_dir, inode->bi_dir_offset, inode->bi_snapshot)); + SPOS(inode->bi_dir, inode->bi_dir_offset, snapshot)); int ret = bkey_err(d) ?: dirent_points_to_inode(c, d, inode) ?: bch2_fsck_remove_dirent(trans, d.k->p); @@ -695,14 +728,8 @@ static int snapshots_seen_update(struct bch_fs *c, struct snapshots_seen *s, static bool key_visible_in_snapshot(struct bch_fs *c, struct snapshots_seen *seen, u32 id, u32 ancestor) { - ssize_t i; - EBUG_ON(id > ancestor); - /* @ancestor should be the snapshot most recently added to @seen */ - EBUG_ON(ancestor != seen->pos.snapshot); - EBUG_ON(ancestor != darray_last(seen->ids)); - if (id == ancestor) return true; @@ -718,11 +745,8 @@ static bool key_visible_in_snapshot(struct bch_fs *c, struct snapshots_seen *see * numerically, since snapshot ID lists are kept sorted, so if we find * an id that's an ancestor of @id we're done: */ - - for (i = seen->ids.nr - 2; - i >= 0 && seen->ids.data[i] >= id; - --i) - if (bch2_snapshot_is_ancestor(c, id, seen->ids.data[i])) + darray_for_each_reverse(seen->ids, i) + if (*i != ancestor && bch2_snapshot_is_ancestor(c, id, *i)) return false; return true; @@ -806,7 +830,7 @@ static int add_inode(struct bch_fs *c, struct inode_walker *w, if (!n->whiteout) { return bch2_inode_unpack(inode, &n->inode); } else { - n->inode.bi_inum = inode.k->p.inode; + n->inode.bi_inum = inode.k->p.offset; n->inode.bi_snapshot = inode.k->p.snapshot; return 0; } @@ -903,17 +927,15 @@ lookup_inode_for_snapshot(struct btree_trans *trans, struct inode_walker *w, str w->last_pos.inode, k.k->p.snapshot, i->inode.bi_snapshot, (bch2_bkey_val_to_text(&buf, c, k), buf.buf))) { - struct bch_inode_unpacked new = i->inode; - struct bkey_i whiteout; - - new.bi_snapshot = k.k->p.snapshot; - if (!i->whiteout) { + struct bch_inode_unpacked new = i->inode; + new.bi_snapshot = k.k->p.snapshot; ret = __bch2_fsck_write_inode(trans, &new); } else { + struct bkey_i whiteout; bkey_init(&whiteout.k); whiteout.k.type = KEY_TYPE_whiteout; - whiteout.k.p = SPOS(0, i->inode.bi_inum, i->inode.bi_snapshot); + whiteout.k.p = SPOS(0, i->inode.bi_inum, k.k->p.snapshot); ret = bch2_btree_insert_nonextent(trans, BTREE_ID_inodes, &whiteout, BTREE_UPDATE_internal_snapshot_node); @@ -1135,13 +1157,14 @@ static int check_inode(struct btree_trans *trans, if (ret) goto err; - if (u.bi_dir || u.bi_dir_offset) { + if (bch2_inode_has_backpointer(&u)) { ret = check_inode_dirent_inode(trans, &u, &do_update); if (ret) goto err; } - if (fsck_err_on(u.bi_dir && (u.bi_flags & BCH_INODE_unlinked), + if (fsck_err_on(bch2_inode_has_backpointer(&u) && + (u.bi_flags & BCH_INODE_unlinked), trans, inode_unlinked_but_has_dirent, "inode unlinked but has dirent\n%s", (printbuf_reset(&buf), @@ -1438,6 +1461,7 @@ static int check_key_has_inode(struct btree_trans *trans, { struct bch_fs *c = trans->c; struct printbuf buf = PRINTBUF; + struct btree_iter iter2 = {}; int ret = PTR_ERR_OR_ZERO(i); if (ret) return ret; @@ -1447,40 +1471,105 @@ static int check_key_has_inode(struct btree_trans *trans, bool have_inode = i && !i->whiteout; - if (!have_inode && (c->sb.btrees_lost_data & BIT_ULL(BTREE_ID_inodes))) { - ret = reconstruct_inode(trans, iter->btree_id, k.k->p.snapshot, k.k->p.inode) ?: - bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc); - if (ret) - goto err; + if (!have_inode && (c->sb.btrees_lost_data & BIT_ULL(BTREE_ID_inodes))) + goto reconstruct; - inode->last_pos.inode--; - ret = bch_err_throw(c, transaction_restart_nested); - goto err; + if (have_inode && btree_matches_i_mode(iter->btree_id, i->inode.bi_mode)) + goto out; + + prt_printf(&buf, ", "); + + bool have_old_inode = false; + darray_for_each(inode->inodes, i2) + if (!i2->whiteout && + bch2_snapshot_is_ancestor(c, k.k->p.snapshot, i2->inode.bi_snapshot) && + btree_matches_i_mode(iter->btree_id, i2->inode.bi_mode)) { + prt_printf(&buf, "but found good inode in older snapshot\n"); + bch2_inode_unpacked_to_text(&buf, &i2->inode); + prt_newline(&buf); + have_old_inode = true; + break; + } + + struct bkey_s_c k2; + unsigned nr_keys = 0; + + prt_printf(&buf, "found keys:\n"); + + for_each_btree_key_max_norestart(trans, iter2, iter->btree_id, + SPOS(k.k->p.inode, 0, k.k->p.snapshot), + POS(k.k->p.inode, U64_MAX), + 0, k2, ret) { + nr_keys++; + if (nr_keys <= 10) { + bch2_bkey_val_to_text(&buf, c, k2); + prt_newline(&buf); + } + if (nr_keys >= 100) + break; } - if (fsck_err_on(!have_inode, - trans, key_in_missing_inode, - "key in missing inode:\n%s", - (printbuf_reset(&buf), - bch2_bkey_val_to_text(&buf, c, k), buf.buf))) - goto delete; + if (ret) + goto err; - if (fsck_err_on(have_inode && !btree_matches_i_mode(iter->btree_id, i->inode.bi_mode), - trans, key_in_wrong_inode_type, - "key for wrong inode mode %o:\n%s", - i->inode.bi_mode, - (printbuf_reset(&buf), - bch2_bkey_val_to_text(&buf, c, k), buf.buf))) - goto delete; + if (nr_keys > 100) + prt_printf(&buf, "found > %u keys for this missing inode\n", nr_keys); + else if (nr_keys > 10) + prt_printf(&buf, "found %u keys for this missing inode\n", nr_keys); + + if (!have_inode) { + if (fsck_err_on(!have_inode, + trans, key_in_missing_inode, + "key in missing inode%s", buf.buf)) { + /* + * Maybe a deletion that raced with data move, or something + * weird like that? But if we know the inode was deleted, or + * it's just a few keys, we can safely delete them. + * + * If it's many keys, we should probably recreate the inode + */ + if (have_old_inode || nr_keys <= 2) + goto delete; + else + goto reconstruct; + } + } else { + /* + * not autofix, this one would be a giant wtf - bit error in the + * inode corrupting i_mode? + * + * may want to try repairing inode instead of deleting + */ + if (fsck_err_on(!btree_matches_i_mode(iter->btree_id, i->inode.bi_mode), + trans, key_in_wrong_inode_type, + "key for wrong inode mode %o%s", + i->inode.bi_mode, buf.buf)) + goto delete; + } out: err: fsck_err: + bch2_trans_iter_exit(trans, &iter2); printbuf_exit(&buf); bch_err_fn(c, ret); return ret; delete: + /* + * XXX: print out more info + * count up extents for this inode, check if we have different inode in + * an older snapshot version, perhaps decide if we want to reconstitute + */ ret = bch2_btree_delete_at(trans, iter, BTREE_UPDATE_internal_snapshot_node); goto out; +reconstruct: + ret = reconstruct_inode(trans, iter->btree_id, k.k->p.snapshot, k.k->p.inode) ?: + bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc); + if (ret) + goto err; + + inode->last_pos.inode--; + ret = bch_err_throw(c, transaction_restart_nested); + goto out; } static int check_i_sectors_notnested(struct btree_trans *trans, struct inode_walker *w) @@ -1822,18 +1911,39 @@ static int check_extent(struct btree_trans *trans, struct btree_iter *iter, !key_visible_in_snapshot(c, s, i->inode.bi_snapshot, k.k->p.snapshot)) continue; - if (fsck_err_on(k.k->p.offset > round_up(i->inode.bi_size, block_bytes(c)) >> 9 && + u64 last_block = round_up(i->inode.bi_size, block_bytes(c)) >> 9; + + if (fsck_err_on(k.k->p.offset > last_block && !bkey_extent_is_reservation(k), trans, extent_past_end_of_inode, "extent type past end of inode %llu:%u, i_size %llu\n%s", i->inode.bi_inum, i->inode.bi_snapshot, i->inode.bi_size, (bch2_bkey_val_to_text(&buf, c, k), buf.buf))) { - struct btree_iter iter2; + struct bkey_i *whiteout = bch2_trans_kmalloc(trans, sizeof(*whiteout)); + ret = PTR_ERR_OR_ZERO(whiteout); + if (ret) + goto err; + + bkey_init(&whiteout->k); + whiteout->k.p = SPOS(k.k->p.inode, + last_block, + i->inode.bi_snapshot); + bch2_key_resize(&whiteout->k, + min(KEY_SIZE_MAX & (~0 << c->block_bits), + U64_MAX - whiteout->k.p.offset)); + - bch2_trans_copy_iter(trans, &iter2, iter); - bch2_btree_iter_set_snapshot(trans, &iter2, i->inode.bi_snapshot); + /* + * Need a normal (not BTREE_ITER_all_snapshots) + * iterator, if we're deleting in a different + * snapshot and need to emit a whiteout + */ + struct btree_iter iter2; + bch2_trans_iter_init(trans, &iter2, BTREE_ID_extents, + bkey_start_pos(&whiteout->k), + BTREE_ITER_intent); ret = bch2_btree_iter_traverse(trans, &iter2) ?: - bch2_btree_delete_at(trans, &iter2, + bch2_trans_update(trans, &iter2, whiteout, BTREE_UPDATE_internal_snapshot_node); bch2_trans_iter_exit(trans, &iter2); if (ret) @@ -1949,14 +2059,22 @@ static int check_subdir_count_notnested(struct btree_trans *trans, struct inode_ continue; } - if (fsck_err_on(i->inode.bi_nlink != i->count, - trans, inode_dir_wrong_nlink, - "directory %llu:%u with wrong i_nlink: got %u, should be %llu", - w->last_pos.inode, i->inode.bi_snapshot, i->inode.bi_nlink, i->count)) { - i->inode.bi_nlink = i->count; - ret = bch2_fsck_write_inode(trans, &i->inode); - if (ret) - break; + if (i->inode.bi_nlink != i->count) { + CLASS(printbuf, buf)(); + + lockrestart_do(trans, + bch2_inum_snapshot_to_path(trans, w->last_pos.inode, + i->inode.bi_snapshot, NULL, &buf)); + + if (fsck_err_on(i->inode.bi_nlink != i->count, + trans, inode_dir_wrong_nlink, + "directory with wrong i_nlink: got %u, should be %llu\n%s", + i->inode.bi_nlink, i->count, buf.buf)) { + i->inode.bi_nlink = i->count; + ret = bch2_fsck_write_inode(trans, &i->inode); + if (ret) + break; + } } } fsck_err: @@ -2493,6 +2611,11 @@ static int check_subvol_path(struct btree_trans *trans, struct btree_iter *iter, if (k.k->type != KEY_TYPE_subvolume) return 0; + subvol_inum start = { + .subvol = k.k->p.offset, + .inum = le64_to_cpu(bkey_s_c_to_subvolume(k).v->inode), + }; + while (k.k->p.offset != BCACHEFS_ROOT_SUBVOL) { ret = darray_push(&subvol_path, k.k->p.offset); if (ret) @@ -2511,11 +2634,11 @@ static int check_subvol_path(struct btree_trans *trans, struct btree_iter *iter, if (darray_u32_has(&subvol_path, parent)) { printbuf_reset(&buf); - prt_printf(&buf, "subvolume loop:\n"); + prt_printf(&buf, "subvolume loop: "); - darray_for_each_reverse(subvol_path, i) - prt_printf(&buf, "%u ", *i); - prt_printf(&buf, "%u", parent); + ret = bch2_inum_to_path(trans, start, &buf); + if (ret) + goto err; if (fsck_err(trans, subvol_loop, "%s", buf.buf)) ret = reattach_subvol(trans, s); @@ -2559,19 +2682,13 @@ int bch2_check_subvolume_structure(struct bch_fs *c) return ret; } -struct pathbuf_entry { - u64 inum; - u32 snapshot; -}; - -typedef DARRAY(struct pathbuf_entry) pathbuf; - -static int bch2_bi_depth_renumber_one(struct btree_trans *trans, struct pathbuf_entry *p, +static int bch2_bi_depth_renumber_one(struct btree_trans *trans, + u64 inum, u32 snapshot, u32 new_depth) { struct btree_iter iter; struct bkey_s_c k = bch2_bkey_get_iter(trans, &iter, BTREE_ID_inodes, - SPOS(0, p->inum, p->snapshot), 0); + SPOS(0, inum, snapshot), 0); struct bch_inode_unpacked inode; int ret = bkey_err(k) ?: @@ -2590,14 +2707,15 @@ err: return ret; } -static int bch2_bi_depth_renumber(struct btree_trans *trans, pathbuf *path, u32 new_bi_depth) +static int bch2_bi_depth_renumber(struct btree_trans *trans, darray_u64 *path, + u32 snapshot, u32 new_bi_depth) { u32 restart_count = trans->restart_count; int ret = 0; darray_for_each_reverse(*path, i) { ret = nested_lockrestart_do(trans, - bch2_bi_depth_renumber_one(trans, i, new_bi_depth)); + bch2_bi_depth_renumber_one(trans, *i, snapshot, new_bi_depth)); bch_err_fn(trans->c, ret); if (ret) break; @@ -2608,37 +2726,36 @@ static int bch2_bi_depth_renumber(struct btree_trans *trans, pathbuf *path, u32 return ret ?: trans_was_restarted(trans, restart_count); } -static bool path_is_dup(pathbuf *p, u64 inum, u32 snapshot) -{ - darray_for_each(*p, i) - if (i->inum == inum && - i->snapshot == snapshot) - return true; - return false; -} - static int check_path_loop(struct btree_trans *trans, struct bkey_s_c inode_k) { struct bch_fs *c = trans->c; struct btree_iter inode_iter = {}; - pathbuf path = {}; + darray_u64 path = {}; struct printbuf buf = PRINTBUF; u32 snapshot = inode_k.k->p.snapshot; bool redo_bi_depth = false; u32 min_bi_depth = U32_MAX; int ret = 0; + struct bpos start = inode_k.k->p; + struct bch_inode_unpacked inode; ret = bch2_inode_unpack(inode_k, &inode); if (ret) return ret; - while (!inode.bi_subvol) { + /* + * If we're running full fsck, check_dirents() will have already ran, + * and we shouldn't see any missing backpointers here - otherwise that's + * handled separately, by check_unreachable_inodes + */ + while (!inode.bi_subvol && + bch2_inode_has_backpointer(&inode)) { struct btree_iter dirent_iter; struct bkey_s_c_dirent d; - u32 parent_snapshot = snapshot; - d = inode_get_dirent(trans, &dirent_iter, &inode, &parent_snapshot); + d = dirent_get_by_pos(trans, &dirent_iter, + SPOS(inode.bi_dir, inode.bi_dir_offset, snapshot)); ret = bkey_err(d.s_c); if (ret && !bch2_err_matches(ret, ENOENT)) goto out; @@ -2656,15 +2773,10 @@ static int check_path_loop(struct btree_trans *trans, struct bkey_s_c inode_k) bch2_trans_iter_exit(trans, &dirent_iter); - ret = darray_push(&path, ((struct pathbuf_entry) { - .inum = inode.bi_inum, - .snapshot = snapshot, - })); + ret = darray_push(&path, inode.bi_inum); if (ret) return ret; - snapshot = parent_snapshot; - bch2_trans_iter_exit(trans, &inode_iter); inode_k = bch2_bkey_get_iter(trans, &inode_iter, BTREE_ID_inodes, SPOS(0, inode.bi_dir, snapshot), 0); @@ -2686,15 +2798,22 @@ static int check_path_loop(struct btree_trans *trans, struct bkey_s_c inode_k) break; inode = parent_inode; - snapshot = inode_k.k->p.snapshot; redo_bi_depth = true; - if (path_is_dup(&path, inode.bi_inum, snapshot)) { + if (darray_find(path, inode.bi_inum)) { printbuf_reset(&buf); - prt_printf(&buf, "directory structure loop:\n"); - darray_for_each_reverse(path, i) - prt_printf(&buf, "%llu:%u ", i->inum, i->snapshot); - prt_printf(&buf, "%llu:%u", inode.bi_inum, snapshot); + prt_printf(&buf, "directory structure loop in snapshot %u: ", + snapshot); + + ret = bch2_inum_snapshot_to_path(trans, start.offset, start.snapshot, NULL, &buf); + if (ret) + goto out; + + if (c->opts.verbose) { + prt_newline(&buf); + darray_for_each(path, i) + prt_printf(&buf, "%llu ", *i); + } if (fsck_err(trans, dir_loop, "%s", buf.buf)) { ret = remove_backpointer(trans, &inode); @@ -2714,7 +2833,7 @@ static int check_path_loop(struct btree_trans *trans, struct bkey_s_c inode_k) min_bi_depth = 0; if (redo_bi_depth) - ret = bch2_bi_depth_renumber(trans, &path, min_bi_depth); + ret = bch2_bi_depth_renumber(trans, &path, snapshot, min_bi_depth); out: fsck_err: bch2_trans_iter_exit(trans, &inode_iter); @@ -2731,7 +2850,7 @@ fsck_err: int bch2_check_directory_structure(struct bch_fs *c) { int ret = bch2_trans_run(c, - for_each_btree_key_commit(trans, iter, BTREE_ID_inodes, POS_MIN, + for_each_btree_key_reverse_commit(trans, iter, BTREE_ID_inodes, POS_MIN, BTREE_ITER_intent| BTREE_ITER_prefetch| BTREE_ITER_all_snapshots, k, diff --git a/fs/bcachefs/inode.h b/fs/bcachefs/inode.h index 82cec2836cbd..b8ec3e628d90 100644 --- a/fs/bcachefs/inode.h +++ b/fs/bcachefs/inode.h @@ -254,6 +254,11 @@ static inline bool bch2_inode_casefold(struct bch_fs *c, const struct bch_inode_ : c->opts.casefold; } +static inline bool bch2_inode_has_backpointer(const struct bch_inode_unpacked *bi) +{ + return bi->bi_dir || bi->bi_dir_offset; +} + /* i_nlink: */ static inline unsigned nlink_bias(umode_t mode) diff --git a/fs/bcachefs/io_read.c b/fs/bcachefs/io_read.c index 04bbdcf58e40..cd184b219a65 100644 --- a/fs/bcachefs/io_read.c +++ b/fs/bcachefs/io_read.c @@ -1491,7 +1491,12 @@ void bch2_read_bio_to_text(struct printbuf *out, struct bch_read_bio *rbio) prt_printf(out, "have_ioref:\t%u\n", rbio->have_ioref); prt_printf(out, "narrow_crcs:\t%u\n", rbio->narrow_crcs); prt_printf(out, "context:\t%u\n", rbio->context); - prt_printf(out, "ret:\t%s\n", bch2_err_str(rbio->ret)); + + int ret = READ_ONCE(rbio->ret); + if (ret < 0) + prt_printf(out, "ret:\t%s\n", bch2_err_str(ret)); + else + prt_printf(out, "ret:\t%i\n", ret); prt_printf(out, "flags:\t"); bch2_prt_bitflags(out, bch2_read_bio_flags, rbio->flags); diff --git a/fs/bcachefs/journal.c b/fs/bcachefs/journal.c index dda802a656cf..f22b05e02c1e 100644 --- a/fs/bcachefs/journal.c +++ b/fs/bcachefs/journal.c @@ -1283,7 +1283,7 @@ static int bch2_set_nr_journal_buckets_loop(struct bch_fs *c, struct bch_dev *ca ret = 0; /* wait and retry */ bch2_disk_reservation_put(c, &disk_res); - closure_sync(&cl); + bch2_wait_on_allocator(c, &cl); } return ret; @@ -1474,14 +1474,13 @@ void bch2_fs_journal_stop(struct journal *j) clear_bit(JOURNAL_running, &j->flags); } -int bch2_fs_journal_start(struct journal *j, u64 cur_seq) +int bch2_fs_journal_start(struct journal *j, u64 last_seq, u64 cur_seq) { struct bch_fs *c = container_of(j, struct bch_fs, journal); struct journal_entry_pin_list *p; struct journal_replay *i, **_i; struct genradix_iter iter; bool had_entries = false; - u64 last_seq = cur_seq, nr, seq; /* * @@ -1495,17 +1494,11 @@ int bch2_fs_journal_start(struct journal *j, u64 cur_seq) return -EINVAL; } - genradix_for_each_reverse(&c->journal_entries, iter, _i) { - i = *_i; - - if (journal_replay_ignore(i)) - continue; + /* Clean filesystem? */ + if (!last_seq) + last_seq = cur_seq; - last_seq = le64_to_cpu(i->j.last_seq); - break; - } - - nr = cur_seq - last_seq; + u64 nr = cur_seq - last_seq; /* * Extra fudge factor, in case we crashed when the journal pin fifo was @@ -1532,6 +1525,7 @@ int bch2_fs_journal_start(struct journal *j, u64 cur_seq) j->pin.back = cur_seq; atomic64_set(&j->seq, cur_seq - 1); + u64 seq; fifo_for_each_entry_ptr(p, &j->pin, seq) journal_pin_list_init(p, 1); diff --git a/fs/bcachefs/journal.h b/fs/bcachefs/journal.h index 83734fe4331f..977907038d98 100644 --- a/fs/bcachefs/journal.h +++ b/fs/bcachefs/journal.h @@ -453,7 +453,7 @@ int bch2_fs_journal_alloc(struct bch_fs *); void bch2_dev_journal_stop(struct journal *, struct bch_dev *); void bch2_fs_journal_stop(struct journal *); -int bch2_fs_journal_start(struct journal *, u64); +int bch2_fs_journal_start(struct journal *, u64, u64); void bch2_journal_set_replay_done(struct journal *); void bch2_dev_journal_exit(struct bch_dev *); diff --git a/fs/bcachefs/journal_io.c b/fs/bcachefs/journal_io.c index 0b15d71a8d2d..dd3f3434c1b0 100644 --- a/fs/bcachefs/journal_io.c +++ b/fs/bcachefs/journal_io.c @@ -160,6 +160,9 @@ static int journal_entry_add(struct bch_fs *c, struct bch_dev *ca, struct printbuf buf = PRINTBUF; int ret = JOURNAL_ENTRY_ADD_OK; + if (last_seq && c->opts.journal_rewind) + last_seq = min(last_seq, c->opts.journal_rewind); + if (!c->journal.oldest_seq_found_ondisk || le64_to_cpu(j->seq) < c->journal.oldest_seq_found_ondisk) c->journal.oldest_seq_found_ondisk = le64_to_cpu(j->seq); @@ -1430,11 +1433,21 @@ int bch2_journal_read(struct bch_fs *c, printbuf_reset(&buf); prt_printf(&buf, "journal read done, replaying entries %llu-%llu", *last_seq, *blacklist_seq - 1); + + /* + * Drop blacklisted entries and entries older than last_seq (or start of + * journal rewind: + */ + u64 drop_before = *last_seq; + if (c->opts.journal_rewind) { + drop_before = min(drop_before, c->opts.journal_rewind); + prt_printf(&buf, " (rewinding from %llu)", c->opts.journal_rewind); + } + + *last_seq = drop_before; if (*start_seq != *blacklist_seq) prt_printf(&buf, " (unflushed %llu-%llu)", *blacklist_seq, *start_seq - 1); bch_info(c, "%s", buf.buf); - - /* Drop blacklisted entries and entries older than last_seq: */ genradix_for_each(&c->journal_entries, radix_iter, _i) { i = *_i; @@ -1442,7 +1455,7 @@ int bch2_journal_read(struct bch_fs *c, continue; seq = le64_to_cpu(i->j.seq); - if (seq < *last_seq) { + if (seq < drop_before) { journal_replay_free(c, i, false); continue; } @@ -1455,7 +1468,7 @@ int bch2_journal_read(struct bch_fs *c, } } - ret = bch2_journal_check_for_missing(c, *last_seq, *blacklist_seq - 1); + ret = bch2_journal_check_for_missing(c, drop_before, *blacklist_seq - 1); if (ret) goto err; @@ -1703,9 +1716,10 @@ static CLOSURE_CALLBACK(journal_write_done) bch2_log_msg_start(c, &buf); if (err == -BCH_ERR_journal_write_err) - prt_printf(&buf, "unable to write journal to sufficient devices"); + prt_printf(&buf, "unable to write journal to sufficient devices\n"); else - prt_printf(&buf, "journal write error marking replicas: %s", bch2_err_str(err)); + prt_printf(&buf, "journal write error marking replicas: %s\n", + bch2_err_str(err)); bch2_fs_emergency_read_only2(c, &buf); diff --git a/fs/bcachefs/namei.c b/fs/bcachefs/namei.c index 779c22eb3979..c3f87c59922d 100644 --- a/fs/bcachefs/namei.c +++ b/fs/bcachefs/namei.c @@ -625,14 +625,26 @@ static int __bch2_inum_to_path(struct btree_trans *trans, { unsigned orig_pos = path->pos; int ret = 0; + DARRAY(subvol_inum) inums = {}; + + if (!snapshot) { + ret = bch2_subvolume_get_snapshot(trans, subvol, &snapshot); + if (ret) + goto disconnected; + } while (true) { - if (!snapshot) { - ret = bch2_subvolume_get_snapshot(trans, subvol, &snapshot); - if (ret) - goto disconnected; + subvol_inum n = (subvol_inum) { subvol ?: snapshot, inum }; + + if (darray_find_p(inums, i, i->subvol == n.subvol && i->inum == n.inum)) { + prt_str_reversed(path, "(loop)"); + break; } + ret = darray_push(&inums, n); + if (ret) + goto err; + struct bch_inode_unpacked inode; ret = bch2_inode_find_by_inum_snapshot(trans, inum, snapshot, &inode, 0); if (ret) @@ -650,7 +662,9 @@ static int __bch2_inum_to_path(struct btree_trans *trans, inum = inode.bi_dir; if (inode.bi_parent_subvol) { subvol = inode.bi_parent_subvol; - snapshot = 0; + ret = bch2_subvolume_get_snapshot(trans, inode.bi_parent_subvol, &snapshot); + if (ret) + goto disconnected; } struct btree_iter d_iter; @@ -662,6 +676,7 @@ static int __bch2_inum_to_path(struct btree_trans *trans, goto disconnected; struct qstr dirent_name = bch2_dirent_get_name(d); + prt_bytes_reversed(path, dirent_name.name, dirent_name.len); prt_char(path, '/'); @@ -677,8 +692,10 @@ out: goto err; reverse_bytes(path->buf + orig_pos, path->pos - orig_pos); + darray_exit(&inums); return 0; err: + darray_exit(&inums); return ret; disconnected: if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) @@ -717,8 +734,7 @@ static int bch2_check_dirent_inode_dirent(struct btree_trans *trans, if (inode_points_to_dirent(target, d)) return 0; - if (!target->bi_dir && - !target->bi_dir_offset) { + if (!bch2_inode_has_backpointer(target)) { fsck_err_on(S_ISDIR(target->bi_mode), trans, inode_dir_missing_backpointer, "directory with missing backpointer\n%s", diff --git a/fs/bcachefs/opts.h b/fs/bcachefs/opts.h index 2a02606254b3..b0a76bd6d6f5 100644 --- a/fs/bcachefs/opts.h +++ b/fs/bcachefs/opts.h @@ -379,6 +379,11 @@ enum fsck_err_opts { OPT_BOOL(), \ BCH2_NO_SB_OPT, false, \ NULL, "Exit recovery immediately prior to journal replay")\ + x(journal_rewind, u64, \ + OPT_FS|OPT_MOUNT, \ + OPT_UINT(0, U64_MAX), \ + BCH2_NO_SB_OPT, 0, \ + NULL, "Rewind journal") \ x(recovery_passes, u64, \ OPT_FS|OPT_MOUNT, \ OPT_BITFIELD(bch2_recovery_passes), \ diff --git a/fs/bcachefs/recovery.c b/fs/bcachefs/recovery.c index 0b21fa6ff062..d0b7e3a36a54 100644 --- a/fs/bcachefs/recovery.c +++ b/fs/bcachefs/recovery.c @@ -607,6 +607,7 @@ static int read_btree_roots(struct bch_fs *c) buf.buf, bch2_err_str(ret))) { if (btree_id_is_alloc(i)) r->error = 0; + ret = 0; } } @@ -692,7 +693,7 @@ static bool check_version_upgrade(struct bch_fs *c) ret = true; } - if (new_version > c->sb.version_incompat && + if (new_version > c->sb.version_incompat_allowed && c->opts.version_upgrade == BCH_VERSION_UPGRADE_incompatible) { struct printbuf buf = PRINTBUF; @@ -757,6 +758,21 @@ int bch2_fs_recovery(struct bch_fs *c) if (c->opts.nochanges) c->opts.read_only = true; + if (c->opts.journal_rewind) { + bch_info(c, "rewinding journal, fsck required"); + c->opts.fsck = true; + } + + if (go_rw_in_recovery(c)) { + /* + * start workqueues/kworkers early - kthread creation checks for + * pending signals, which is _very_ annoying + */ + ret = bch2_fs_init_rw(c); + if (ret) + goto err; + } + mutex_lock(&c->sb_lock); struct bch_sb_field_ext *ext = bch2_sb_field_get(c->disk_sb.sb, ext); bool write_sb = false; @@ -965,7 +981,7 @@ use_clean: ret = bch2_journal_log_msg(c, "starting journal at entry %llu, replaying %llu-%llu", journal_seq, last_seq, blacklist_seq - 1) ?: - bch2_fs_journal_start(&c->journal, journal_seq); + bch2_fs_journal_start(&c->journal, last_seq, journal_seq); if (ret) goto err; @@ -1126,7 +1142,7 @@ fsck_err: struct printbuf buf = PRINTBUF; bch2_log_msg_start(c, &buf); - prt_printf(&buf, "error in recovery: %s", bch2_err_str(ret)); + prt_printf(&buf, "error in recovery: %s\n", bch2_err_str(ret)); bch2_fs_emergency_read_only2(c, &buf); bch2_print_str(c, KERN_ERR, buf.buf); @@ -1181,7 +1197,7 @@ int bch2_fs_initialize(struct bch_fs *c) * journal_res_get() will crash if called before this has * set up the journal.pin FIFO and journal.cur pointer: */ - ret = bch2_fs_journal_start(&c->journal, 1); + ret = bch2_fs_journal_start(&c->journal, 1, 1); if (ret) goto err; diff --git a/fs/bcachefs/recovery_passes.c b/fs/bcachefs/recovery_passes.c index 35ac0d64d73a..c09ed2dd4639 100644 --- a/fs/bcachefs/recovery_passes.c +++ b/fs/bcachefs/recovery_passes.c @@ -217,11 +217,7 @@ static int bch2_set_may_go_rw(struct bch_fs *c) set_bit(BCH_FS_may_go_rw, &c->flags); - if (keys->nr || - !c->opts.read_only || - !c->sb.clean || - c->opts.recovery_passes || - (c->opts.fsck && !(c->sb.features & BIT_ULL(BCH_FEATURE_no_alloc_info)))) { + if (go_rw_in_recovery(c)) { if (c->sb.features & BIT_ULL(BCH_FEATURE_no_alloc_info)) { bch_info(c, "mounting a filesystem with no alloc info read-write; will recreate"); bch2_reconstruct_alloc(c); @@ -317,6 +313,9 @@ static bool recovery_pass_needs_set(struct bch_fs *c, */ bool in_recovery = test_bit(BCH_FS_in_recovery, &c->flags); bool persistent = !in_recovery || !(*flags & RUN_RECOVERY_PASS_nopersistent); + bool rewind = in_recovery && + r->curr_pass > pass && + !(r->passes_complete & BIT_ULL(pass)); if (persistent ? !(c->sb.recovery_passes_required & BIT_ULL(pass)) @@ -327,6 +326,9 @@ static bool recovery_pass_needs_set(struct bch_fs *c, (r->passes_ratelimiting & BIT_ULL(pass))) return true; + if (rewind) + return true; + return false; } @@ -341,7 +343,6 @@ int __bch2_run_explicit_recovery_pass(struct bch_fs *c, struct bch_fs_recovery *r = &c->recovery; int ret = 0; - lockdep_assert_held(&c->sb_lock); bch2_printbuf_make_room(out, 1024); @@ -412,10 +413,8 @@ int bch2_run_explicit_recovery_pass(struct bch_fs *c, { int ret = 0; - scoped_guard(mutex, &c->sb_lock) { - if (!recovery_pass_needs_set(c, pass, &flags)) - return 0; - + if (recovery_pass_needs_set(c, pass, &flags)) { + guard(mutex)(&c->sb_lock); ret = __bch2_run_explicit_recovery_pass(c, out, pass, flags); bch2_write_super(c); } diff --git a/fs/bcachefs/recovery_passes.h b/fs/bcachefs/recovery_passes.h index 260571c7105e..2117f0ce1922 100644 --- a/fs/bcachefs/recovery_passes.h +++ b/fs/bcachefs/recovery_passes.h @@ -17,6 +17,15 @@ enum bch_run_recovery_pass_flags { RUN_RECOVERY_PASS_ratelimit = BIT(1), }; +static inline bool go_rw_in_recovery(struct bch_fs *c) +{ + return (c->journal_keys.nr || + !c->opts.read_only || + !c->sb.clean || + c->opts.recovery_passes || + (c->opts.fsck && !(c->sb.features & BIT_ULL(BCH_FEATURE_no_alloc_info)))); +} + int bch2_run_print_explicit_recovery_pass(struct bch_fs *, enum bch_recovery_pass); int __bch2_run_explicit_recovery_pass(struct bch_fs *, struct printbuf *, diff --git a/fs/bcachefs/reflink.c b/fs/bcachefs/reflink.c index a535abd44df3..92b90cfe622b 100644 --- a/fs/bcachefs/reflink.c +++ b/fs/bcachefs/reflink.c @@ -64,6 +64,9 @@ void bch2_reflink_p_to_text(struct printbuf *out, struct bch_fs *c, REFLINK_P_IDX(p.v), le32_to_cpu(p.v->front_pad), le32_to_cpu(p.v->back_pad)); + + if (REFLINK_P_ERROR(p.v)) + prt_str(out, " error"); } bool bch2_reflink_p_merge(struct bch_fs *c, struct bkey_s _l, struct bkey_s_c _r) @@ -269,13 +272,12 @@ struct bkey_s_c bch2_lookup_indirect_extent(struct btree_trans *trans, return k; if (unlikely(!bkey_extent_is_reflink_data(k.k))) { - unsigned size = min((u64) k.k->size, - REFLINK_P_IDX(p.v) + p.k->size + le32_to_cpu(p.v->back_pad) - - reflink_offset); - bch2_key_resize(&iter->k, size); + u64 missing_end = min(k.k->p.offset, + REFLINK_P_IDX(p.v) + p.k->size + le32_to_cpu(p.v->back_pad)); + BUG_ON(reflink_offset == missing_end); int ret = bch2_indirect_extent_missing_error(trans, p, reflink_offset, - k.k->p.offset, should_commit); + missing_end, should_commit); if (ret) { bch2_trans_iter_exit(trans, iter); return bkey_s_c_err(ret); diff --git a/fs/bcachefs/sb-errors_format.h b/fs/bcachefs/sb-errors_format.h index d06e73884871..0641fb634bd4 100644 --- a/fs/bcachefs/sb-errors_format.h +++ b/fs/bcachefs/sb-errors_format.h @@ -3,9 +3,10 @@ #define _BCACHEFS_SB_ERRORS_FORMAT_H enum bch_fsck_flags { - FSCK_CAN_FIX = 1 << 0, - FSCK_CAN_IGNORE = 1 << 1, - FSCK_AUTOFIX = 1 << 2, + FSCK_CAN_FIX = BIT(0), + FSCK_CAN_IGNORE = BIT(1), + FSCK_AUTOFIX = BIT(2), + FSCK_ERR_NO_LOG = BIT(3), }; #define BCH_SB_ERRS() \ @@ -217,7 +218,7 @@ enum bch_fsck_flags { x(inode_str_hash_invalid, 194, 0) \ x(inode_v3_fields_start_bad, 195, 0) \ x(inode_snapshot_mismatch, 196, 0) \ - x(snapshot_key_missing_inode_snapshot, 314, 0) \ + x(snapshot_key_missing_inode_snapshot, 314, FSCK_AUTOFIX) \ x(inode_unlinked_but_clean, 197, 0) \ x(inode_unlinked_but_nlink_nonzero, 198, 0) \ x(inode_unlinked_and_not_open, 281, 0) \ @@ -251,20 +252,20 @@ enum bch_fsck_flags { x(deleted_inode_not_unlinked, 214, FSCK_AUTOFIX) \ x(deleted_inode_has_child_snapshots, 288, FSCK_AUTOFIX) \ x(extent_overlapping, 215, 0) \ - x(key_in_missing_inode, 216, 0) \ + x(key_in_missing_inode, 216, FSCK_AUTOFIX) \ x(key_in_wrong_inode_type, 217, 0) \ - x(extent_past_end_of_inode, 218, 0) \ + x(extent_past_end_of_inode, 218, FSCK_AUTOFIX) \ x(dirent_empty_name, 219, 0) \ x(dirent_val_too_big, 220, 0) \ x(dirent_name_too_long, 221, 0) \ x(dirent_name_embedded_nul, 222, 0) \ x(dirent_name_dot_or_dotdot, 223, 0) \ x(dirent_name_has_slash, 224, 0) \ - x(dirent_d_type_wrong, 225, 0) \ + x(dirent_d_type_wrong, 225, FSCK_AUTOFIX) \ x(inode_bi_parent_wrong, 226, 0) \ x(dirent_in_missing_dir_inode, 227, 0) \ x(dirent_in_non_dir_inode, 228, 0) \ - x(dirent_to_missing_inode, 229, 0) \ + x(dirent_to_missing_inode, 229, FSCK_AUTOFIX) \ x(dirent_to_overwritten_inode, 302, 0) \ x(dirent_to_missing_subvol, 230, 0) \ x(dirent_to_itself, 231, 0) \ @@ -300,7 +301,7 @@ enum bch_fsck_flags { x(btree_node_bkey_bad_u64s, 260, 0) \ x(btree_node_topology_empty_interior_node, 261, 0) \ x(btree_ptr_v2_min_key_bad, 262, 0) \ - x(btree_root_unreadable_and_scan_found_nothing, 263, FSCK_AUTOFIX) \ + x(btree_root_unreadable_and_scan_found_nothing, 263, 0) \ x(snapshot_node_missing, 264, FSCK_AUTOFIX) \ x(dup_backpointer_to_bad_csum_extent, 265, 0) \ x(btree_bitmap_not_marked, 266, FSCK_AUTOFIX) \ diff --git a/fs/bcachefs/snapshot.c b/fs/bcachefs/snapshot.c index 23a332d76b32..4c43d2a2c1f5 100644 --- a/fs/bcachefs/snapshot.c +++ b/fs/bcachefs/snapshot.c @@ -135,7 +135,9 @@ static bool test_ancestor_bitmap(struct snapshot_table *t, u32 id, u32 ancestor) bool __bch2_snapshot_is_ancestor(struct bch_fs *c, u32 id, u32 ancestor) { - bool ret; +#ifdef CONFIG_BCACHEFS_DEBUG + u32 orig_id = id; +#endif guard(rcu)(); struct snapshot_table *t = rcu_dereference(c->snapshots); @@ -147,11 +149,11 @@ bool __bch2_snapshot_is_ancestor(struct bch_fs *c, u32 id, u32 ancestor) while (id && id < ancestor - IS_ANCESTOR_BITMAP) id = get_ancestor_below(t, id, ancestor); - ret = id && id < ancestor + bool ret = id && id < ancestor ? test_ancestor_bitmap(t, id, ancestor) : id == ancestor; - EBUG_ON(ret != __bch2_snapshot_is_ancestor_early(t, id, ancestor)); + EBUG_ON(ret != __bch2_snapshot_is_ancestor_early(t, orig_id, ancestor)); return ret; } @@ -869,7 +871,8 @@ static int check_snapshot_exists(struct btree_trans *trans, u32 id) for_each_btree_key_norestart(trans, iter, BTREE_ID_snapshot_trees, POS_MIN, 0, k, ret) { - if (le32_to_cpu(bkey_s_c_to_snapshot_tree(k).v->root_snapshot) == id) { + if (k.k->type == KEY_TYPE_snapshot_tree && + le32_to_cpu(bkey_s_c_to_snapshot_tree(k).v->root_snapshot) == id) { tree_id = k.k->p.offset; break; } @@ -897,7 +900,8 @@ static int check_snapshot_exists(struct btree_trans *trans, u32 id) for_each_btree_key_norestart(trans, iter, BTREE_ID_subvolumes, POS_MIN, 0, k, ret) { - if (le32_to_cpu(bkey_s_c_to_subvolume(k).v->snapshot) == id) { + if (k.k->type == KEY_TYPE_subvolume && + le32_to_cpu(bkey_s_c_to_subvolume(k).v->snapshot) == id) { snapshot->v.subvol = cpu_to_le32(k.k->p.offset); SET_BCH_SNAPSHOT_SUBVOL(&snapshot->v, true); break; diff --git a/fs/bcachefs/super.c b/fs/bcachefs/super.c index a5b97c9c5163..69c097ff54e7 100644 --- a/fs/bcachefs/super.c +++ b/fs/bcachefs/super.c @@ -210,7 +210,6 @@ static int bch2_dev_alloc(struct bch_fs *, unsigned); static int bch2_dev_sysfs_online(struct bch_fs *, struct bch_dev *); static void bch2_dev_io_ref_stop(struct bch_dev *, int); static void __bch2_dev_read_only(struct bch_fs *, struct bch_dev *); -static int bch2_fs_init_rw(struct bch_fs *); struct bch_fs *bch2_dev_to_fs(dev_t dev) { @@ -794,7 +793,7 @@ err: return ret; } -static int bch2_fs_init_rw(struct bch_fs *c) +int bch2_fs_init_rw(struct bch_fs *c) { if (test_bit(BCH_FS_rw_init_done, &c->flags)) return 0; @@ -1015,6 +1014,16 @@ static struct bch_fs *bch2_fs_alloc(struct bch_sb *sb, struct bch_opts *opts, if (ret) goto err; + if (go_rw_in_recovery(c)) { + /* + * start workqueues/kworkers early - kthread creation checks for + * pending signals, which is _very_ annoying + */ + ret = bch2_fs_init_rw(c); + if (ret) + goto err; + } + #ifdef CONFIG_UNICODE /* Default encoding until we can potentially have more as an option. */ c->cf_encoding = utf8_load(BCH_FS_DEFAULT_UTF8_ENCODING); diff --git a/fs/bcachefs/super.h b/fs/bcachefs/super.h index dc52f06cb2b9..e90bab9afe78 100644 --- a/fs/bcachefs/super.h +++ b/fs/bcachefs/super.h @@ -46,6 +46,7 @@ void __bch2_fs_stop(struct bch_fs *); void bch2_fs_free(struct bch_fs *); void bch2_fs_stop(struct bch_fs *); +int bch2_fs_init_rw(struct bch_fs *); int bch2_fs_start(struct bch_fs *); struct bch_fs *bch2_fs_open(darray_const_str *, struct bch_opts *); diff --git a/fs/bcachefs/trace.h b/fs/bcachefs/trace.h index dc09532796af..9c5a9c551f03 100644 --- a/fs/bcachefs/trace.h +++ b/fs/bcachefs/trace.h @@ -1080,34 +1080,14 @@ TRACE_EVENT(trans_blocked_journal_reclaim, __entry->must_wait) ); -TRACE_EVENT(trans_restart_journal_preres_get, - TP_PROTO(struct btree_trans *trans, - unsigned long caller_ip, - unsigned flags), - TP_ARGS(trans, caller_ip, flags), - - TP_STRUCT__entry( - __array(char, trans_fn, 32 ) - __field(unsigned long, caller_ip ) - __field(unsigned, flags ) - ), - - TP_fast_assign( - strscpy(__entry->trans_fn, trans->fn, sizeof(__entry->trans_fn)); - __entry->caller_ip = caller_ip; - __entry->flags = flags; - ), - - TP_printk("%s %pS %x", __entry->trans_fn, - (void *) __entry->caller_ip, - __entry->flags) -); - +#if 0 +/* todo: bring back dynamic fault injection */ DEFINE_EVENT(transaction_event, trans_restart_fault_inject, TP_PROTO(struct btree_trans *trans, unsigned long caller_ip), TP_ARGS(trans, caller_ip) ); +#endif DEFINE_EVENT(transaction_event, trans_traverse_all, TP_PROTO(struct btree_trans *trans, @@ -1195,19 +1175,6 @@ DEFINE_EVENT(transaction_restart_iter, trans_restart_relock_parent_for_fill, TP_ARGS(trans, caller_ip, path) ); -DEFINE_EVENT(transaction_restart_iter, trans_restart_relock_after_fill, - TP_PROTO(struct btree_trans *trans, - unsigned long caller_ip, - struct btree_path *path), - TP_ARGS(trans, caller_ip, path) -); - -DEFINE_EVENT(transaction_event, trans_restart_key_cache_upgrade, - TP_PROTO(struct btree_trans *trans, - unsigned long caller_ip), - TP_ARGS(trans, caller_ip) -); - DEFINE_EVENT(transaction_restart_iter, trans_restart_relock_key_cache_fill, TP_PROTO(struct btree_trans *trans, unsigned long caller_ip, @@ -1229,13 +1196,6 @@ DEFINE_EVENT(transaction_restart_iter, trans_restart_relock_path_intent, TP_ARGS(trans, caller_ip, path) ); -DEFINE_EVENT(transaction_restart_iter, trans_restart_traverse, - TP_PROTO(struct btree_trans *trans, - unsigned long caller_ip, - struct btree_path *path), - TP_ARGS(trans, caller_ip, path) -); - DEFINE_EVENT(transaction_restart_iter, trans_restart_memory_allocation_failure, TP_PROTO(struct btree_trans *trans, unsigned long caller_ip, @@ -1294,44 +1254,6 @@ TRACE_EVENT(trans_restart_mem_realloced, __entry->bytes) ); -TRACE_EVENT(trans_restart_key_cache_key_realloced, - TP_PROTO(struct btree_trans *trans, - unsigned long caller_ip, - struct btree_path *path, - unsigned old_u64s, - unsigned new_u64s), - TP_ARGS(trans, caller_ip, path, old_u64s, new_u64s), - - TP_STRUCT__entry( - __array(char, trans_fn, 32 ) - __field(unsigned long, caller_ip ) - __field(enum btree_id, btree_id ) - TRACE_BPOS_entries(pos) - __field(u32, old_u64s ) - __field(u32, new_u64s ) - ), - - TP_fast_assign( - strscpy(__entry->trans_fn, trans->fn, sizeof(__entry->trans_fn)); - __entry->caller_ip = caller_ip; - - __entry->btree_id = path->btree_id; - TRACE_BPOS_assign(pos, path->pos); - __entry->old_u64s = old_u64s; - __entry->new_u64s = new_u64s; - ), - - TP_printk("%s %pS btree %s pos %llu:%llu:%u old_u64s %u new_u64s %u", - __entry->trans_fn, - (void *) __entry->caller_ip, - bch2_btree_id_str(__entry->btree_id), - __entry->pos_inode, - __entry->pos_offset, - __entry->pos_snapshot, - __entry->old_u64s, - __entry->new_u64s) -); - DEFINE_EVENT(transaction_event, trans_restart_write_buffer_flush, TP_PROTO(struct btree_trans *trans, unsigned long caller_ip), @@ -1490,6 +1412,31 @@ DEFINE_EVENT(fs_str, io_move_evacuate_bucket, TP_ARGS(c, str) ); +DEFINE_EVENT(fs_str, extent_trim_atomic, + TP_PROTO(struct bch_fs *c, const char *str), + TP_ARGS(c, str) +); + +DEFINE_EVENT(fs_str, btree_iter_peek_slot, + TP_PROTO(struct bch_fs *c, const char *str), + TP_ARGS(c, str) +); + +DEFINE_EVENT(fs_str, __btree_iter_peek, + TP_PROTO(struct bch_fs *c, const char *str), + TP_ARGS(c, str) +); + +DEFINE_EVENT(fs_str, btree_iter_peek_max, + TP_PROTO(struct bch_fs *c, const char *str), + TP_ARGS(c, str) +); + +DEFINE_EVENT(fs_str, btree_iter_peek_prev_min, + TP_PROTO(struct bch_fs *c, const char *str), + TP_ARGS(c, str) +); + #ifdef CONFIG_BCACHEFS_PATH_TRACEPOINTS TRACE_EVENT(update_by_path, @@ -1902,21 +1849,6 @@ TRACE_EVENT(btree_path_free, __entry->dup_locked) ); -TRACE_EVENT(btree_path_free_trans_begin, - TP_PROTO(btree_path_idx_t path), - TP_ARGS(path), - - TP_STRUCT__entry( - __field(btree_path_idx_t, idx ) - ), - - TP_fast_assign( - __entry->idx = path; - ), - - TP_printk(" path %3u", __entry->idx) -); - #else /* CONFIG_BCACHEFS_PATH_TRACEPOINTS */ #ifndef _TRACE_BCACHEFS_H @@ -1934,7 +1866,6 @@ static inline void trace_btree_path_traverse_start(struct btree_trans *trans, st static inline void trace_btree_path_traverse_end(struct btree_trans *trans, struct btree_path *path) {} static inline void trace_btree_path_set_pos(struct btree_trans *trans, struct btree_path *path, struct bpos *new_pos) {} static inline void trace_btree_path_free(struct btree_trans *trans, btree_path_idx_t path, struct btree_path *dup) {} -static inline void trace_btree_path_free_trans_begin(btree_path_idx_t path) {} #endif #endif /* CONFIG_BCACHEFS_PATH_TRACEPOINTS */ diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index c7cc24a5dd5e..8c597fa60523 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -1377,7 +1377,10 @@ static int btrfs_wq_run_delayed_node(struct btrfs_delayed_root *delayed_root, void btrfs_assert_delayed_root_empty(struct btrfs_fs_info *fs_info) { - WARN_ON(btrfs_first_delayed_node(fs_info->delayed_root)); + struct btrfs_delayed_node *node = btrfs_first_delayed_node(fs_info->delayed_root); + + if (WARN_ON(node)) + refcount_dec(&node->refs); } static bool could_end_wait(struct btrfs_delayed_root *delayed_root, int seq) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 1beb9458f622..0d6ad7512f21 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1835,6 +1835,8 @@ void btrfs_put_root(struct btrfs_root *root) if (refcount_dec_and_test(&root->refs)) { if (WARN_ON(!xa_empty(&root->inodes))) xa_destroy(&root->inodes); + if (WARN_ON(!xa_empty(&root->delayed_nodes))) + xa_destroy(&root->delayed_nodes); WARN_ON(test_bit(BTRFS_ROOT_DEAD_RELOC_TREE, &root->state)); if (root->anon_dev) free_anon_bdev(root->anon_dev); @@ -2156,8 +2158,7 @@ static int load_global_roots_objectid(struct btrfs_root *tree_root, found = true; root = read_tree_root_path(tree_root, path, &key); if (IS_ERR(root)) { - if (!btrfs_test_opt(fs_info, IGNOREBADROOTS)) - ret = PTR_ERR(root); + ret = PTR_ERR(root); break; } set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state); @@ -4310,8 +4311,8 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info) * * So wait for all ongoing ordered extents to complete and then run * delayed iputs. This works because once we reach this point no one - * can either create new ordered extents nor create delayed iputs - * through some other means. + * can create new ordered extents, but delayed iputs can still be added + * by a reclaim worker (see comments further below). * * Also note that btrfs_wait_ordered_roots() is not safe here, because * it waits for BTRFS_ORDERED_COMPLETE to be set on an ordered extent, @@ -4322,15 +4323,29 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info) btrfs_flush_workqueue(fs_info->endio_write_workers); /* Ordered extents for free space inodes. */ btrfs_flush_workqueue(fs_info->endio_freespace_worker); + /* + * Run delayed iputs in case an async reclaim worker is waiting for them + * to be run as mentioned above. + */ btrfs_run_delayed_iputs(fs_info); - /* There should be no more workload to generate new delayed iputs. */ - set_bit(BTRFS_FS_STATE_NO_DELAYED_IPUT, &fs_info->fs_state); cancel_work_sync(&fs_info->async_reclaim_work); cancel_work_sync(&fs_info->async_data_reclaim_work); cancel_work_sync(&fs_info->preempt_reclaim_work); cancel_work_sync(&fs_info->em_shrinker_work); + /* + * Run delayed iputs again because an async reclaim worker may have + * added new ones if it was flushing delalloc: + * + * shrink_delalloc() -> btrfs_start_delalloc_roots() -> + * start_delalloc_inodes() -> btrfs_add_delayed_iput() + */ + btrfs_run_delayed_iputs(fs_info); + + /* There should be no more workload to generate new delayed iputs. */ + set_bit(BTRFS_FS_STATE_NO_DELAYED_IPUT, &fs_info->fs_state); + /* Cancel or finish ongoing discard work */ btrfs_discard_cleanup(fs_info); diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 849199768664..1dc931c4937f 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -4312,7 +4312,6 @@ static int try_release_subpage_extent_buffer(struct folio *folio) spin_unlock(&eb->refs_lock); continue; } - xa_unlock_irq(&fs_info->buffer_tree); /* * If tree ref isn't set then we know the ref on this eb is a @@ -4329,6 +4328,7 @@ static int try_release_subpage_extent_buffer(struct folio *folio) * check the folio private at the end. And * release_extent_buffer() will release the refs_lock. */ + xa_unlock_irq(&fs_info->buffer_tree); release_extent_buffer(eb); xa_lock_irq(&fs_info->buffer_tree); } diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c index 0c573d46639a..a3e2a2a81461 100644 --- a/fs/btrfs/free-space-tree.c +++ b/fs/btrfs/free-space-tree.c @@ -1115,11 +1115,21 @@ static int populate_free_space_tree(struct btrfs_trans_handle *trans, ret = btrfs_search_slot_for_read(extent_root, &key, path, 1, 0); if (ret < 0) goto out_locked; - ASSERT(ret == 0); + /* + * If ret is 1 (no key found), it means this is an empty block group, + * without any extents allocated from it and there's no block group + * item (key BTRFS_BLOCK_GROUP_ITEM_KEY) located in the extent tree + * because we are using the block group tree feature, so block group + * items are stored in the block group tree. It also means there are no + * extents allocated for block groups with a start offset beyond this + * block group's end offset (this is the last, highest, block group). + */ + if (!btrfs_fs_compat_ro(trans->fs_info, BLOCK_GROUP_TREE)) + ASSERT(ret == 0); start = block_group->start; end = block_group->start + block_group->length; - while (1) { + while (ret == 0) { btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); if (key.type == BTRFS_EXTENT_ITEM_KEY || @@ -1149,8 +1159,6 @@ static int populate_free_space_tree(struct btrfs_trans_handle *trans, ret = btrfs_next_item(extent_root, path); if (ret < 0) goto out_locked; - if (ret) - break; } if (start < end) { ret = __add_to_free_space_tree(trans, block_group, path2, diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index c0c778243bf1..26d6ed170a19 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -4250,9 +4250,9 @@ static int __btrfs_unlink_inode(struct btrfs_trans_handle *trans, ret = btrfs_del_inode_ref(trans, root, name, ino, dir_ino, &index); if (ret) { - btrfs_info(fs_info, - "failed to delete reference to %.*s, inode %llu parent %llu", - name->len, name->name, ino, dir_ino); + btrfs_crit(fs_info, + "failed to delete reference to %.*s, root %llu inode %llu parent %llu", + name->len, name->name, btrfs_root_id(root), ino, dir_ino); btrfs_abort_transaction(trans, ret); goto err; } @@ -8059,6 +8059,7 @@ static int btrfs_rename_exchange(struct inode *old_dir, int ret; int ret2; bool need_abort = false; + bool logs_pinned = false; struct fscrypt_name old_fname, new_fname; struct fscrypt_str *old_name, *new_name; @@ -8182,6 +8183,31 @@ static int btrfs_rename_exchange(struct inode *old_dir, inode_inc_iversion(new_inode); simple_rename_timestamp(old_dir, old_dentry, new_dir, new_dentry); + if (old_ino != BTRFS_FIRST_FREE_OBJECTID && + new_ino != BTRFS_FIRST_FREE_OBJECTID) { + /* + * If we are renaming in the same directory (and it's not for + * root entries) pin the log early to prevent any concurrent + * task from logging the directory after we removed the old + * entries and before we add the new entries, otherwise that + * task can sync a log without any entry for the inodes we are + * renaming and therefore replaying that log, if a power failure + * happens after syncing the log, would result in deleting the + * inodes. + * + * If the rename affects two different directories, we want to + * make sure the that there's no log commit that contains + * updates for only one of the directories but not for the + * other. + * + * If we are renaming an entry for a root, we don't care about + * log updates since we called btrfs_set_log_full_commit(). + */ + btrfs_pin_log_trans(root); + btrfs_pin_log_trans(dest); + logs_pinned = true; + } + if (old_dentry->d_parent != new_dentry->d_parent) { btrfs_record_unlink_dir(trans, BTRFS_I(old_dir), BTRFS_I(old_inode), true); @@ -8253,30 +8279,23 @@ static int btrfs_rename_exchange(struct inode *old_dir, BTRFS_I(new_inode)->dir_index = new_idx; /* - * Now pin the logs of the roots. We do it to ensure that no other task - * can sync the logs while we are in progress with the rename, because - * that could result in an inconsistency in case any of the inodes that - * are part of this rename operation were logged before. + * Do the log updates for all inodes. + * + * If either entry is for a root we don't need to update the logs since + * we've called btrfs_set_log_full_commit() before. */ - if (old_ino != BTRFS_FIRST_FREE_OBJECTID) - btrfs_pin_log_trans(root); - if (new_ino != BTRFS_FIRST_FREE_OBJECTID) - btrfs_pin_log_trans(dest); - - /* Do the log updates for all inodes. */ - if (old_ino != BTRFS_FIRST_FREE_OBJECTID) + if (logs_pinned) { btrfs_log_new_name(trans, old_dentry, BTRFS_I(old_dir), old_rename_ctx.index, new_dentry->d_parent); - if (new_ino != BTRFS_FIRST_FREE_OBJECTID) btrfs_log_new_name(trans, new_dentry, BTRFS_I(new_dir), new_rename_ctx.index, old_dentry->d_parent); + } - /* Now unpin the logs. */ - if (old_ino != BTRFS_FIRST_FREE_OBJECTID) +out_fail: + if (logs_pinned) { btrfs_end_log_trans(root); - if (new_ino != BTRFS_FIRST_FREE_OBJECTID) btrfs_end_log_trans(dest); -out_fail: + } ret2 = btrfs_end_transaction(trans); ret = ret ? ret : ret2; out_notrans: @@ -8326,6 +8345,7 @@ static int btrfs_rename(struct mnt_idmap *idmap, int ret2; u64 old_ino = btrfs_ino(BTRFS_I(old_inode)); struct fscrypt_name old_fname, new_fname; + bool logs_pinned = false; if (btrfs_ino(BTRFS_I(new_dir)) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID) return -EPERM; @@ -8460,6 +8480,29 @@ static int btrfs_rename(struct mnt_idmap *idmap, inode_inc_iversion(old_inode); simple_rename_timestamp(old_dir, old_dentry, new_dir, new_dentry); + if (old_ino != BTRFS_FIRST_FREE_OBJECTID) { + /* + * If we are renaming in the same directory (and it's not a + * root entry) pin the log to prevent any concurrent task from + * logging the directory after we removed the old entry and + * before we add the new entry, otherwise that task can sync + * a log without any entry for the inode we are renaming and + * therefore replaying that log, if a power failure happens + * after syncing the log, would result in deleting the inode. + * + * If the rename affects two different directories, we want to + * make sure the that there's no log commit that contains + * updates for only one of the directories but not for the + * other. + * + * If we are renaming an entry for a root, we don't care about + * log updates since we called btrfs_set_log_full_commit(). + */ + btrfs_pin_log_trans(root); + btrfs_pin_log_trans(dest); + logs_pinned = true; + } + if (old_dentry->d_parent != new_dentry->d_parent) btrfs_record_unlink_dir(trans, BTRFS_I(old_dir), BTRFS_I(old_inode), true); @@ -8524,7 +8567,7 @@ static int btrfs_rename(struct mnt_idmap *idmap, if (old_inode->i_nlink == 1) BTRFS_I(old_inode)->dir_index = index; - if (old_ino != BTRFS_FIRST_FREE_OBJECTID) + if (logs_pinned) btrfs_log_new_name(trans, old_dentry, BTRFS_I(old_dir), rename_ctx.index, new_dentry->d_parent); @@ -8540,6 +8583,10 @@ static int btrfs_rename(struct mnt_idmap *idmap, } } out_fail: + if (logs_pinned) { + btrfs_end_log_trans(root); + btrfs_end_log_trans(dest); + } ret2 = btrfs_end_transaction(trans); ret = ret ? ret : ret2; out_notrans: diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 913acef3f0a9..4eda35bdba71 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -3139,7 +3139,7 @@ static long btrfs_ioctl_scrub(struct file *file, void __user *arg) return -EPERM; if (btrfs_fs_incompat(fs_info, EXTENT_TREE_V2)) { - btrfs_err(fs_info, "scrub is not supported on extent tree v2 yet"); + btrfs_err(fs_info, "scrub: extent tree v2 not yet supported"); return -EINVAL; } diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index ce36fafc771e..7cd5e76a783c 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -557,7 +557,7 @@ static int scrub_print_warning_inode(u64 inum, u64 offset, u64 num_bytes, */ for (i = 0; i < ipath->fspath->elem_cnt; ++i) btrfs_warn_in_rcu(fs_info, -"%s at logical %llu on dev %s, physical %llu, root %llu, inode %llu, offset %llu, length %u, links %u (path: %s)", +"scrub: %s at logical %llu on dev %s, physical %llu root %llu inode %llu offset %llu length %u links %u (path: %s)", swarn->errstr, swarn->logical, btrfs_dev_name(swarn->dev), swarn->physical, @@ -571,7 +571,7 @@ static int scrub_print_warning_inode(u64 inum, u64 offset, u64 num_bytes, err: btrfs_warn_in_rcu(fs_info, - "%s at logical %llu on dev %s, physical %llu, root %llu, inode %llu, offset %llu: path resolving failed with ret=%d", + "scrub: %s at logical %llu on dev %s, physical %llu root %llu inode %llu offset %llu: path resolving failed with ret=%d", swarn->errstr, swarn->logical, btrfs_dev_name(swarn->dev), swarn->physical, @@ -596,7 +596,7 @@ static void scrub_print_common_warning(const char *errstr, struct btrfs_device * /* Super block error, no need to search extent tree. */ if (is_super) { - btrfs_warn_in_rcu(fs_info, "%s on device %s, physical %llu", + btrfs_warn_in_rcu(fs_info, "scrub: %s on device %s, physical %llu", errstr, btrfs_dev_name(dev), physical); return; } @@ -631,14 +631,14 @@ static void scrub_print_common_warning(const char *errstr, struct btrfs_device * &ref_level); if (ret < 0) { btrfs_warn(fs_info, - "failed to resolve tree backref for logical %llu: %d", - swarn.logical, ret); + "scrub: failed to resolve tree backref for logical %llu: %d", + swarn.logical, ret); break; } if (ret > 0) break; btrfs_warn_in_rcu(fs_info, -"%s at logical %llu on dev %s, physical %llu: metadata %s (level %d) in tree %llu", +"scrub: %s at logical %llu on dev %s, physical %llu: metadata %s (level %d) in tree %llu", errstr, swarn.logical, btrfs_dev_name(dev), swarn.physical, (ref_level ? "node" : "leaf"), ref_level, ref_root); @@ -718,7 +718,7 @@ static void scrub_verify_one_metadata(struct scrub_stripe *stripe, int sector_nr scrub_bitmap_set_meta_error(stripe, sector_nr, sectors_per_tree); scrub_bitmap_set_error(stripe, sector_nr, sectors_per_tree); btrfs_warn_rl(fs_info, - "tree block %llu mirror %u has bad bytenr, has %llu want %llu", + "scrub: tree block %llu mirror %u has bad bytenr, has %llu want %llu", logical, stripe->mirror_num, btrfs_stack_header_bytenr(header), logical); return; @@ -728,7 +728,7 @@ static void scrub_verify_one_metadata(struct scrub_stripe *stripe, int sector_nr scrub_bitmap_set_meta_error(stripe, sector_nr, sectors_per_tree); scrub_bitmap_set_error(stripe, sector_nr, sectors_per_tree); btrfs_warn_rl(fs_info, - "tree block %llu mirror %u has bad fsid, has %pU want %pU", + "scrub: tree block %llu mirror %u has bad fsid, has %pU want %pU", logical, stripe->mirror_num, header->fsid, fs_info->fs_devices->fsid); return; @@ -738,7 +738,7 @@ static void scrub_verify_one_metadata(struct scrub_stripe *stripe, int sector_nr scrub_bitmap_set_meta_error(stripe, sector_nr, sectors_per_tree); scrub_bitmap_set_error(stripe, sector_nr, sectors_per_tree); btrfs_warn_rl(fs_info, - "tree block %llu mirror %u has bad chunk tree uuid, has %pU want %pU", + "scrub: tree block %llu mirror %u has bad chunk tree uuid, has %pU want %pU", logical, stripe->mirror_num, header->chunk_tree_uuid, fs_info->chunk_tree_uuid); return; @@ -760,7 +760,7 @@ static void scrub_verify_one_metadata(struct scrub_stripe *stripe, int sector_nr scrub_bitmap_set_meta_error(stripe, sector_nr, sectors_per_tree); scrub_bitmap_set_error(stripe, sector_nr, sectors_per_tree); btrfs_warn_rl(fs_info, - "tree block %llu mirror %u has bad csum, has " CSUM_FMT " want " CSUM_FMT, +"scrub: tree block %llu mirror %u has bad csum, has " CSUM_FMT " want " CSUM_FMT, logical, stripe->mirror_num, CSUM_FMT_VALUE(fs_info->csum_size, on_disk_csum), CSUM_FMT_VALUE(fs_info->csum_size, calculated_csum)); @@ -771,7 +771,7 @@ static void scrub_verify_one_metadata(struct scrub_stripe *stripe, int sector_nr scrub_bitmap_set_meta_gen_error(stripe, sector_nr, sectors_per_tree); scrub_bitmap_set_error(stripe, sector_nr, sectors_per_tree); btrfs_warn_rl(fs_info, - "tree block %llu mirror %u has bad generation, has %llu want %llu", + "scrub: tree block %llu mirror %u has bad generation, has %llu want %llu", logical, stripe->mirror_num, btrfs_stack_header_generation(header), stripe->sectors[sector_nr].generation); @@ -814,7 +814,7 @@ static void scrub_verify_one_sector(struct scrub_stripe *stripe, int sector_nr) */ if (unlikely(sector_nr + sectors_per_tree > stripe->nr_sectors)) { btrfs_warn_rl(fs_info, - "tree block at %llu crosses stripe boundary %llu", + "scrub: tree block at %llu crosses stripe boundary %llu", stripe->logical + (sector_nr << fs_info->sectorsize_bits), stripe->logical); @@ -1046,12 +1046,12 @@ skip: if (repaired) { if (dev) { btrfs_err_rl_in_rcu(fs_info, - "fixed up error at logical %llu on dev %s physical %llu", + "scrub: fixed up error at logical %llu on dev %s physical %llu", stripe->logical, btrfs_dev_name(dev), physical); } else { btrfs_err_rl_in_rcu(fs_info, - "fixed up error at logical %llu on mirror %u", + "scrub: fixed up error at logical %llu on mirror %u", stripe->logical, stripe->mirror_num); } continue; @@ -1060,12 +1060,12 @@ skip: /* The remaining are all for unrepaired. */ if (dev) { btrfs_err_rl_in_rcu(fs_info, - "unable to fixup (regular) error at logical %llu on dev %s physical %llu", +"scrub: unable to fixup (regular) error at logical %llu on dev %s physical %llu", stripe->logical, btrfs_dev_name(dev), physical); } else { btrfs_err_rl_in_rcu(fs_info, - "unable to fixup (regular) error at logical %llu on mirror %u", + "scrub: unable to fixup (regular) error at logical %llu on mirror %u", stripe->logical, stripe->mirror_num); } @@ -1593,8 +1593,7 @@ static int sync_write_pointer_for_zoned(struct scrub_ctx *sctx, u64 logical, physical, sctx->write_pointer); if (ret) - btrfs_err(fs_info, - "zoned: failed to recover write pointer"); + btrfs_err(fs_info, "scrub: zoned: failed to recover write pointer"); } mutex_unlock(&sctx->wr_lock); btrfs_dev_clear_zone_empty(sctx->wr_tgtdev, physical); @@ -1658,7 +1657,7 @@ static int scrub_find_fill_first_stripe(struct btrfs_block_group *bg, int ret; if (unlikely(!extent_root || !csum_root)) { - btrfs_err(fs_info, "no valid extent or csum root for scrub"); + btrfs_err(fs_info, "scrub: no valid extent or csum root found"); return -EUCLEAN; } memset(stripe->sectors, 0, sizeof(struct scrub_sector_verification) * @@ -1907,7 +1906,7 @@ static bool stripe_has_metadata_error(struct scrub_stripe *stripe) struct btrfs_fs_info *fs_info = stripe->bg->fs_info; btrfs_err(fs_info, - "stripe %llu has unrepaired metadata sector at %llu", + "scrub: stripe %llu has unrepaired metadata sector at logical %llu", stripe->logical, stripe->logical + (i << fs_info->sectorsize_bits)); return true; @@ -2167,7 +2166,7 @@ static int scrub_raid56_parity_stripe(struct scrub_ctx *sctx, bitmap_and(&error, &error, &has_extent, stripe->nr_sectors); if (!bitmap_empty(&error, stripe->nr_sectors)) { btrfs_err(fs_info, -"unrepaired sectors detected, full stripe %llu data stripe %u errors %*pbl", +"scrub: unrepaired sectors detected, full stripe %llu data stripe %u errors %*pbl", full_stripe_start, i, stripe->nr_sectors, &error); ret = -EIO; @@ -2789,14 +2788,14 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx, ro_set = 0; } else if (ret == -ETXTBSY) { btrfs_warn(fs_info, - "skipping scrub of block group %llu due to active swapfile", + "scrub: skipping scrub of block group %llu due to active swapfile", cache->start); scrub_pause_off(fs_info); ret = 0; goto skip_unfreeze; } else { - btrfs_warn(fs_info, - "failed setting block group ro: %d", ret); + btrfs_warn(fs_info, "scrub: failed setting block group ro: %d", + ret); btrfs_unfreeze_block_group(cache); btrfs_put_block_group(cache); scrub_pause_off(fs_info); @@ -2892,13 +2891,13 @@ static int scrub_one_super(struct scrub_ctx *sctx, struct btrfs_device *dev, ret = btrfs_check_super_csum(fs_info, sb); if (ret != 0) { btrfs_err_rl(fs_info, - "super block at physical %llu devid %llu has bad csum", + "scrub: super block at physical %llu devid %llu has bad csum", physical, dev->devid); return -EIO; } if (btrfs_super_generation(sb) != generation) { btrfs_err_rl(fs_info, -"super block at physical %llu devid %llu has bad generation %llu expect %llu", +"scrub: super block at physical %llu devid %llu has bad generation %llu expect %llu", physical, dev->devid, btrfs_super_generation(sb), generation); return -EUCLEAN; @@ -3059,7 +3058,7 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start, !test_bit(BTRFS_DEV_STATE_WRITEABLE, &dev->dev_state)) { mutex_unlock(&fs_info->fs_devices->device_list_mutex); btrfs_err_in_rcu(fs_info, - "scrub on devid %llu: filesystem on %s is not writable", + "scrub: devid %llu: filesystem on %s is not writable", devid, btrfs_dev_name(dev)); ret = -EROFS; goto out; diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 97e933113b82..858b609e292c 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -668,15 +668,15 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans, extent_end = ALIGN(start + size, fs_info->sectorsize); } else { - ret = 0; - goto out; + btrfs_err(fs_info, + "unexpected extent type=%d root=%llu inode=%llu offset=%llu", + found_type, btrfs_root_id(root), key->objectid, key->offset); + return -EUCLEAN; } inode = read_one_inode(root, key->objectid); - if (!inode) { - ret = -EIO; - goto out; - } + if (!inode) + return -EIO; /* * first check to see if we already have this extent in the @@ -961,7 +961,8 @@ static noinline int drop_one_dir_item(struct btrfs_trans_handle *trans, ret = unlink_inode_for_log_replay(trans, dir, inode, &name); out: kfree(name.name); - iput(&inode->vfs_inode); + if (inode) + iput(&inode->vfs_inode); return ret; } @@ -1176,8 +1177,8 @@ again: ret = unlink_inode_for_log_replay(trans, victim_parent, inode, &victim_name); + iput(&victim_parent->vfs_inode); } - iput(&victim_parent->vfs_inode); kfree(victim_name.name); if (ret) return ret; diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 89835071cfea..f475b4b7c457 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -3282,6 +3282,12 @@ int btrfs_remove_chunk(struct btrfs_trans_handle *trans, u64 chunk_offset) device->bytes_used - dev_extent_len); atomic64_add(dev_extent_len, &fs_info->free_chunk_space); btrfs_clear_space_info_full(fs_info); + + if (list_empty(&device->post_commit_list)) { + list_add_tail(&device->post_commit_list, + &trans->transaction->dev_update_list); + } + mutex_unlock(&fs_info->chunk_mutex); } } diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index b5b0156d5b95..9430b34d3cbb 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -1403,7 +1403,8 @@ static int btrfs_load_block_group_single(struct btrfs_block_group *bg, static int btrfs_load_block_group_dup(struct btrfs_block_group *bg, struct btrfs_chunk_map *map, struct zone_info *zone_info, - unsigned long *active) + unsigned long *active, + u64 last_alloc) { struct btrfs_fs_info *fs_info = bg->fs_info; @@ -1426,6 +1427,13 @@ static int btrfs_load_block_group_dup(struct btrfs_block_group *bg, zone_info[1].physical); return -EIO; } + + if (zone_info[0].alloc_offset == WP_CONVENTIONAL) + zone_info[0].alloc_offset = last_alloc; + + if (zone_info[1].alloc_offset == WP_CONVENTIONAL) + zone_info[1].alloc_offset = last_alloc; + if (zone_info[0].alloc_offset != zone_info[1].alloc_offset) { btrfs_err(bg->fs_info, "zoned: write pointer offset mismatch of zones in DUP profile"); @@ -1446,7 +1454,8 @@ static int btrfs_load_block_group_dup(struct btrfs_block_group *bg, static int btrfs_load_block_group_raid1(struct btrfs_block_group *bg, struct btrfs_chunk_map *map, struct zone_info *zone_info, - unsigned long *active) + unsigned long *active, + u64 last_alloc) { struct btrfs_fs_info *fs_info = bg->fs_info; int i; @@ -1461,10 +1470,12 @@ static int btrfs_load_block_group_raid1(struct btrfs_block_group *bg, bg->zone_capacity = min_not_zero(zone_info[0].capacity, zone_info[1].capacity); for (i = 0; i < map->num_stripes; i++) { - if (zone_info[i].alloc_offset == WP_MISSING_DEV || - zone_info[i].alloc_offset == WP_CONVENTIONAL) + if (zone_info[i].alloc_offset == WP_MISSING_DEV) continue; + if (zone_info[i].alloc_offset == WP_CONVENTIONAL) + zone_info[i].alloc_offset = last_alloc; + if ((zone_info[0].alloc_offset != zone_info[i].alloc_offset) && !btrfs_test_opt(fs_info, DEGRADED)) { btrfs_err(fs_info, @@ -1494,7 +1505,8 @@ static int btrfs_load_block_group_raid1(struct btrfs_block_group *bg, static int btrfs_load_block_group_raid0(struct btrfs_block_group *bg, struct btrfs_chunk_map *map, struct zone_info *zone_info, - unsigned long *active) + unsigned long *active, + u64 last_alloc) { struct btrfs_fs_info *fs_info = bg->fs_info; @@ -1505,10 +1517,29 @@ static int btrfs_load_block_group_raid0(struct btrfs_block_group *bg, } for (int i = 0; i < map->num_stripes; i++) { - if (zone_info[i].alloc_offset == WP_MISSING_DEV || - zone_info[i].alloc_offset == WP_CONVENTIONAL) + if (zone_info[i].alloc_offset == WP_MISSING_DEV) continue; + if (zone_info[i].alloc_offset == WP_CONVENTIONAL) { + u64 stripe_nr, full_stripe_nr; + u64 stripe_offset; + int stripe_index; + + stripe_nr = div64_u64(last_alloc, map->stripe_size); + stripe_offset = stripe_nr * map->stripe_size; + full_stripe_nr = div_u64(stripe_nr, map->num_stripes); + div_u64_rem(stripe_nr, map->num_stripes, &stripe_index); + + zone_info[i].alloc_offset = + full_stripe_nr * map->stripe_size; + + if (stripe_index > i) + zone_info[i].alloc_offset += map->stripe_size; + else if (stripe_index == i) + zone_info[i].alloc_offset += + (last_alloc - stripe_offset); + } + if (test_bit(0, active) != test_bit(i, active)) { if (!btrfs_zone_activate(bg)) return -EIO; @@ -1526,7 +1557,8 @@ static int btrfs_load_block_group_raid0(struct btrfs_block_group *bg, static int btrfs_load_block_group_raid10(struct btrfs_block_group *bg, struct btrfs_chunk_map *map, struct zone_info *zone_info, - unsigned long *active) + unsigned long *active, + u64 last_alloc) { struct btrfs_fs_info *fs_info = bg->fs_info; @@ -1537,8 +1569,7 @@ static int btrfs_load_block_group_raid10(struct btrfs_block_group *bg, } for (int i = 0; i < map->num_stripes; i++) { - if (zone_info[i].alloc_offset == WP_MISSING_DEV || - zone_info[i].alloc_offset == WP_CONVENTIONAL) + if (zone_info[i].alloc_offset == WP_MISSING_DEV) continue; if (test_bit(0, active) != test_bit(i, active)) { @@ -1549,6 +1580,29 @@ static int btrfs_load_block_group_raid10(struct btrfs_block_group *bg, set_bit(BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE, &bg->runtime_flags); } + if (zone_info[i].alloc_offset == WP_CONVENTIONAL) { + u64 stripe_nr, full_stripe_nr; + u64 stripe_offset; + int stripe_index; + + stripe_nr = div64_u64(last_alloc, map->stripe_size); + stripe_offset = stripe_nr * map->stripe_size; + full_stripe_nr = div_u64(stripe_nr, + map->num_stripes / map->sub_stripes); + div_u64_rem(stripe_nr, + (map->num_stripes / map->sub_stripes), + &stripe_index); + + zone_info[i].alloc_offset = + full_stripe_nr * map->stripe_size; + + if (stripe_index > (i / map->sub_stripes)) + zone_info[i].alloc_offset += map->stripe_size; + else if (stripe_index == (i / map->sub_stripes)) + zone_info[i].alloc_offset += + (last_alloc - stripe_offset); + } + if ((i % map->sub_stripes) == 0) { bg->zone_capacity += zone_info[i].capacity; bg->alloc_offset += zone_info[i].alloc_offset; @@ -1637,18 +1691,22 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new) ret = btrfs_load_block_group_single(cache, &zone_info[0], active); break; case BTRFS_BLOCK_GROUP_DUP: - ret = btrfs_load_block_group_dup(cache, map, zone_info, active); + ret = btrfs_load_block_group_dup(cache, map, zone_info, active, + last_alloc); break; case BTRFS_BLOCK_GROUP_RAID1: case BTRFS_BLOCK_GROUP_RAID1C3: case BTRFS_BLOCK_GROUP_RAID1C4: - ret = btrfs_load_block_group_raid1(cache, map, zone_info, active); + ret = btrfs_load_block_group_raid1(cache, map, zone_info, + active, last_alloc); break; case BTRFS_BLOCK_GROUP_RAID0: - ret = btrfs_load_block_group_raid0(cache, map, zone_info, active); + ret = btrfs_load_block_group_raid0(cache, map, zone_info, + active, last_alloc); break; case BTRFS_BLOCK_GROUP_RAID10: - ret = btrfs_load_block_group_raid10(cache, map, zone_info, active); + ret = btrfs_load_block_group_raid10(cache, map, zone_info, + active, last_alloc); break; case BTRFS_BLOCK_GROUP_RAID5: case BTRFS_BLOCK_GROUP_RAID6: diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 6bd3de64f2a8..696131e655ed 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -35,6 +35,17 @@ #include <trace/events/f2fs.h> #include <uapi/linux/f2fs.h> +static void f2fs_zero_post_eof_page(struct inode *inode, loff_t new_size) +{ + loff_t old_size = i_size_read(inode); + + if (old_size >= new_size) + return; + + /* zero or drop pages only in range of [old_size, new_size] */ + truncate_pagecache(inode, old_size); +} + static vm_fault_t f2fs_filemap_fault(struct vm_fault *vmf) { struct inode *inode = file_inode(vmf->vma->vm_file); @@ -103,8 +114,13 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf) f2fs_bug_on(sbi, f2fs_has_inline_data(inode)); + filemap_invalidate_lock(inode->i_mapping); + f2fs_zero_post_eof_page(inode, (folio->index + 1) << PAGE_SHIFT); + filemap_invalidate_unlock(inode->i_mapping); + file_update_time(vmf->vma->vm_file); filemap_invalidate_lock_shared(inode->i_mapping); + folio_lock(folio); if (unlikely(folio->mapping != inode->i_mapping || folio_pos(folio) > i_size_read(inode) || @@ -1109,6 +1125,8 @@ int f2fs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, f2fs_down_write(&fi->i_gc_rwsem[WRITE]); filemap_invalidate_lock(inode->i_mapping); + if (attr->ia_size > old_size) + f2fs_zero_post_eof_page(inode, attr->ia_size); truncate_setsize(inode, attr->ia_size); if (attr->ia_size <= old_size) @@ -1227,6 +1245,10 @@ static int f2fs_punch_hole(struct inode *inode, loff_t offset, loff_t len) if (ret) return ret; + filemap_invalidate_lock(inode->i_mapping); + f2fs_zero_post_eof_page(inode, offset + len); + filemap_invalidate_unlock(inode->i_mapping); + pg_start = ((unsigned long long) offset) >> PAGE_SHIFT; pg_end = ((unsigned long long) offset + len) >> PAGE_SHIFT; @@ -1510,6 +1532,8 @@ static int f2fs_do_collapse(struct inode *inode, loff_t offset, loff_t len) f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); filemap_invalidate_lock(inode->i_mapping); + f2fs_zero_post_eof_page(inode, offset + len); + f2fs_lock_op(sbi); f2fs_drop_extent_tree(inode); truncate_pagecache(inode, offset); @@ -1631,6 +1655,10 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len, if (ret) return ret; + filemap_invalidate_lock(mapping); + f2fs_zero_post_eof_page(inode, offset + len); + filemap_invalidate_unlock(mapping); + pg_start = ((unsigned long long) offset) >> PAGE_SHIFT; pg_end = ((unsigned long long) offset + len) >> PAGE_SHIFT; @@ -1762,6 +1790,8 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len) /* avoid gc operation during block exchange */ f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); filemap_invalidate_lock(mapping); + + f2fs_zero_post_eof_page(inode, offset + len); truncate_pagecache(inode, offset); while (!ret && idx > pg_start) { @@ -1819,6 +1849,10 @@ static int f2fs_expand_inode_data(struct inode *inode, loff_t offset, if (err) return err; + filemap_invalidate_lock(inode->i_mapping); + f2fs_zero_post_eof_page(inode, offset + len); + filemap_invalidate_unlock(inode->i_mapping); + f2fs_balance_fs(sbi, true); pg_start = ((unsigned long long)offset) >> PAGE_SHIFT; @@ -4860,6 +4894,10 @@ static ssize_t f2fs_write_checks(struct kiocb *iocb, struct iov_iter *from) err = file_modified(file); if (err) return err; + + filemap_invalidate_lock(inode->i_mapping); + f2fs_zero_post_eof_page(inode, iocb->ki_pos + iov_iter_count(from)); + filemap_invalidate_unlock(inode->i_mapping); return count; } diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 1cb4cba7f961..bfe104db284e 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -2078,7 +2078,6 @@ write_node: if (!__write_node_folio(folio, false, &submitted, wbc, do_balance, io_type, NULL)) { - folio_unlock(folio); folio_batch_release(&fbatch); ret = -EIO; goto out; diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index bfe8d8af46f3..9572bdef49ee 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -9,6 +9,7 @@ #include "fuse_i.h" #include "dev_uring_i.h" +#include <linux/dax.h> #include <linux/pagemap.h> #include <linux/slab.h> #include <linux/file.h> @@ -162,6 +163,9 @@ static void fuse_evict_inode(struct inode *inode) /* Will write inode on close/munmap and in all other dirtiers */ WARN_ON(inode->i_state & I_DIRTY_INODE); + if (FUSE_IS_DAX(inode)) + dax_break_layout_final(inode); + truncate_inode_pages_final(&inode->i_data); clear_inode(inode); if (inode->i_sb->s_flags & SB_ACTIVE) { diff --git a/fs/namespace.c b/fs/namespace.c index e13d9ab4f564..54c59e091919 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -2310,21 +2310,62 @@ out: return dst_mnt; } -/* Caller should check returned pointer for errors */ +static inline bool extend_array(struct path **res, struct path **to_free, + unsigned n, unsigned *count, unsigned new_count) +{ + struct path *p; -struct vfsmount *collect_mounts(const struct path *path) + if (likely(n < *count)) + return true; + p = kmalloc_array(new_count, sizeof(struct path), GFP_KERNEL); + if (p && *count) + memcpy(p, *res, *count * sizeof(struct path)); + *count = new_count; + kfree(*to_free); + *to_free = *res = p; + return p; +} + +struct path *collect_paths(const struct path *path, + struct path *prealloc, unsigned count) { - struct mount *tree; - namespace_lock(); - if (!check_mnt(real_mount(path->mnt))) - tree = ERR_PTR(-EINVAL); - else - tree = copy_tree(real_mount(path->mnt), path->dentry, - CL_COPY_ALL | CL_PRIVATE); - namespace_unlock(); - if (IS_ERR(tree)) - return ERR_CAST(tree); - return &tree->mnt; + struct mount *root = real_mount(path->mnt); + struct mount *child; + struct path *res = prealloc, *to_free = NULL; + unsigned n = 0; + + guard(rwsem_read)(&namespace_sem); + + if (!check_mnt(root)) + return ERR_PTR(-EINVAL); + if (!extend_array(&res, &to_free, 0, &count, 32)) + return ERR_PTR(-ENOMEM); + res[n++] = *path; + list_for_each_entry(child, &root->mnt_mounts, mnt_child) { + if (!is_subdir(child->mnt_mountpoint, path->dentry)) + continue; + for (struct mount *m = child; m; m = next_mnt(m, child)) { + if (!extend_array(&res, &to_free, n, &count, 2 * count)) + return ERR_PTR(-ENOMEM); + res[n].mnt = &m->mnt; + res[n].dentry = m->mnt.mnt_root; + n++; + } + } + if (!extend_array(&res, &to_free, n, &count, count + 1)) + return ERR_PTR(-ENOMEM); + memset(res + n, 0, (count - n) * sizeof(struct path)); + for (struct path *p = res; p->mnt; p++) + path_get(p); + return res; +} + +void drop_collected_paths(struct path *paths, struct path *prealloc) +{ + for (struct path *p = paths; p->mnt; p++) + path_put(p); + if (paths != prealloc) + kfree(paths); } static void free_mnt_ns(struct mnt_namespace *); @@ -2401,15 +2442,6 @@ void dissolve_on_fput(struct vfsmount *mnt) free_mnt_ns(ns); } -void drop_collected_mounts(struct vfsmount *mnt) -{ - namespace_lock(); - lock_mount_hash(); - umount_tree(real_mount(mnt), 0); - unlock_mount_hash(); - namespace_unlock(); -} - static bool __has_locked_children(struct mount *mnt, struct dentry *dentry) { struct mount *child; @@ -2511,21 +2543,6 @@ struct vfsmount *clone_private_mount(const struct path *path) } EXPORT_SYMBOL_GPL(clone_private_mount); -int iterate_mounts(int (*f)(struct vfsmount *, void *), void *arg, - struct vfsmount *root) -{ - struct mount *mnt; - int res = f(root, arg); - if (res) - return res; - list_for_each_entry(mnt, &real_mount(root)->mnt_list, mnt_list) { - res = f(&mnt->mnt, arg); - if (res) - return res; - } - return 0; -} - static void lock_mnt_tree(struct mount *mnt) { struct mount *p; @@ -2751,14 +2768,14 @@ static int attach_recursive_mnt(struct mount *source_mnt, hlist_for_each_entry_safe(child, n, &tree_list, mnt_hash) { struct mount *q; hlist_del_init(&child->mnt_hash); - q = __lookup_mnt(&child->mnt_parent->mnt, - child->mnt_mountpoint); - if (q) - mnt_change_mountpoint(child, smp, q); /* Notice when we are propagating across user namespaces */ if (child->mnt_parent->mnt_ns->user_ns != user_ns) lock_mnt_tree(child); child->mnt.mnt_flags &= ~MNT_LOCKED; + q = __lookup_mnt(&child->mnt_parent->mnt, + child->mnt_mountpoint); + if (q) + mnt_change_mountpoint(child, smp, q); commit_tree(child); } put_mountpoint(smp); @@ -5290,16 +5307,12 @@ SYSCALL_DEFINE5(open_tree_attr, int, dfd, const char __user *, filename, kattr.kflags |= MOUNT_KATTR_RECURSE; ret = wants_mount_setattr(uattr, usize, &kattr); - if (ret < 0) - return ret; - - if (ret) { + if (ret > 0) { ret = do_mount_setattr(&file->f_path, &kattr); - if (ret) - return ret; - finish_mount_kattr(&kattr); } + if (ret) + return ret; } fd = get_unused_fd_flags(flags & O_CLOEXEC); @@ -6262,7 +6275,11 @@ void put_mnt_ns(struct mnt_namespace *ns) { if (!refcount_dec_and_test(&ns->ns.count)) return; - drop_collected_mounts(&ns->root->mnt); + namespace_lock(); + lock_mount_hash(); + umount_tree(ns->root, 0); + unlock_mount_hash(); + namespace_unlock(); free_mnt_ns(ns); } diff --git a/fs/pnode.h b/fs/pnode.h index 34b6247af01d..2d026fb98b18 100644 --- a/fs/pnode.h +++ b/fs/pnode.h @@ -28,8 +28,6 @@ #define CL_SHARED_TO_SLAVE 0x20 #define CL_COPY_MNT_NS_FILE 0x40 -#define CL_COPY_ALL (CL_COPY_UNBINDABLE | CL_COPY_MNT_NS_FILE) - static inline void set_mnt_shared(struct mount *mnt) { mnt->mnt.mnt_flags &= ~MNT_SHARED_MASK; diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 27972c0749e7..4be91eb6ea5c 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -2182,7 +2182,7 @@ static unsigned long pagemap_thp_category(struct pagemap_scan_private *p, categories |= PAGE_IS_FILE; } - if (is_zero_pfn(pmd_pfn(pmd))) + if (is_huge_zero_pmd(pmd)) categories |= PAGE_IS_PFNZERO; if (pmd_soft_dirty(pmd)) categories |= PAGE_IS_SOFT_DIRTY; diff --git a/include/crypto/hash.h b/include/crypto/hash.h index 6f6b9de12cd3..db294d452e8c 100644 --- a/include/crypto/hash.h +++ b/include/crypto/hash.h @@ -202,6 +202,8 @@ struct shash_desc { #define HASH_REQUEST_CLONE(name, gfp) \ hash_request_clone(name, sizeof(__##name##_req), gfp) +#define CRYPTO_HASH_STATESIZE(coresize, blocksize) (coresize + blocksize + 1) + /** * struct shash_alg - synchronous message digest definition * @init: see struct ahash_alg diff --git a/include/crypto/internal/sha2.h b/include/crypto/internal/sha2.h index b9bccd3ff57f..21a27fd5e198 100644 --- a/include/crypto/internal/sha2.h +++ b/include/crypto/internal/sha2.h @@ -25,7 +25,7 @@ void sha256_blocks_arch(u32 state[SHA256_STATE_WORDS], void sha256_blocks_simd(u32 state[SHA256_STATE_WORDS], const u8 *data, size_t nblocks); -static inline void sha256_choose_blocks( +static __always_inline void sha256_choose_blocks( u32 state[SHA256_STATE_WORDS], const u8 *data, size_t nblocks, bool force_generic, bool force_simd) { diff --git a/include/crypto/md5.h b/include/crypto/md5.h index 198b5d69b92f..28ee533a0507 100644 --- a/include/crypto/md5.h +++ b/include/crypto/md5.h @@ -2,6 +2,7 @@ #ifndef _CRYPTO_MD5_H #define _CRYPTO_MD5_H +#include <crypto/hash.h> #include <linux/types.h> #define MD5_DIGEST_SIZE 16 @@ -15,6 +16,9 @@ #define MD5_H2 0x98badcfeUL #define MD5_H3 0x10325476UL +#define CRYPTO_MD5_STATESIZE \ + CRYPTO_HASH_STATESIZE(MD5_STATE_SIZE, MD5_HMAC_BLOCK_SIZE) + extern const u8 md5_zero_message_hash[MD5_DIGEST_SIZE]; struct md5_state { diff --git a/include/linux/kmemleak.h b/include/linux/kmemleak.h index 93a73c076d16..fbd424b2abb1 100644 --- a/include/linux/kmemleak.h +++ b/include/linux/kmemleak.h @@ -28,6 +28,7 @@ extern void kmemleak_update_trace(const void *ptr) __ref; extern void kmemleak_not_leak(const void *ptr) __ref; extern void kmemleak_transient_leak(const void *ptr) __ref; extern void kmemleak_ignore(const void *ptr) __ref; +extern void kmemleak_ignore_percpu(const void __percpu *ptr) __ref; extern void kmemleak_scan_area(const void *ptr, size_t size, gfp_t gfp) __ref; extern void kmemleak_no_scan(const void *ptr) __ref; extern void kmemleak_alloc_phys(phys_addr_t phys, size_t size, @@ -97,6 +98,9 @@ static inline void kmemleak_not_leak(const void *ptr) static inline void kmemleak_transient_leak(const void *ptr) { } +static inline void kmemleak_ignore_percpu(const void __percpu *ptr) +{ +} static inline void kmemleak_ignore(const void *ptr) { } diff --git a/include/linux/mount.h b/include/linux/mount.h index 4880f434c021..1a508beba446 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -116,10 +116,8 @@ extern int may_umount_tree(struct vfsmount *); extern int may_umount(struct vfsmount *); int do_mount(const char *, const char __user *, const char *, unsigned long, void *); -extern struct vfsmount *collect_mounts(const struct path *); -extern void drop_collected_mounts(struct vfsmount *); -extern int iterate_mounts(int (*)(struct vfsmount *, void *), void *, - struct vfsmount *); +extern struct path *collect_paths(const struct path *, struct path *, unsigned); +extern void drop_collected_paths(struct path *, struct path *); extern void kern_unmount_array(struct vfsmount *mnt[], unsigned int num); extern int cifs_root_data(char **dev, char **opts); diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index a760f05fa3fb..9fc8f544e20e 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -29,6 +29,7 @@ #include <linux/idr.h> #include <linux/leds.h> #include <linux/rculist.h> +#include <linux/srcu.h> #include <net/bluetooth/hci.h> #include <net/bluetooth/hci_drv.h> @@ -347,6 +348,7 @@ struct adv_monitor { struct hci_dev { struct list_head list; + struct srcu_struct srcu; struct mutex lock; struct ida unset_handle_ida; diff --git a/include/uapi/linux/mptcp_pm.h b/include/uapi/linux/mptcp_pm.h index 84fa8a21dfd0..6ac84b2f636c 100644 --- a/include/uapi/linux/mptcp_pm.h +++ b/include/uapi/linux/mptcp_pm.h @@ -27,14 +27,14 @@ * token, rem_id. * @MPTCP_EVENT_SUB_ESTABLISHED: A new subflow has been established. 'error' * should not be set. Attributes: token, family, loc_id, rem_id, saddr4 | - * saddr6, daddr4 | daddr6, sport, dport, backup, if_idx [, error]. + * saddr6, daddr4 | daddr6, sport, dport, backup, if-idx [, error]. * @MPTCP_EVENT_SUB_CLOSED: A subflow has been closed. An error (copy of * sk_err) could be set if an error has been detected for this subflow. * Attributes: token, family, loc_id, rem_id, saddr4 | saddr6, daddr4 | - * daddr6, sport, dport, backup, if_idx [, error]. + * daddr6, sport, dport, backup, if-idx [, error]. * @MPTCP_EVENT_SUB_PRIORITY: The priority of a subflow has changed. 'error' * should not be set. Attributes: token, family, loc_id, rem_id, saddr4 | - * saddr6, daddr4 | daddr6, sport, dport, backup, if_idx [, error]. + * saddr6, daddr4 | daddr6, sport, dport, backup, if-idx [, error]. * @MPTCP_EVENT_LISTENER_CREATED: A new PM listener is created. Attributes: * family, sport, saddr4 | saddr6. * @MPTCP_EVENT_LISTENER_CLOSED: A PM listener is closed. Attributes: family, diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h index 77d9d6af46da..c9751bdfd937 100644 --- a/include/uapi/linux/ublk_cmd.h +++ b/include/uapi/linux/ublk_cmd.h @@ -135,8 +135,28 @@ #define UBLKSRV_IO_BUF_TOTAL_SIZE (1ULL << UBLKSRV_IO_BUF_TOTAL_BITS) /* - * zero copy requires 4k block size, and can remap ublk driver's io - * request into ublksrv's vm space + * ublk server can register data buffers for incoming I/O requests with a sparse + * io_uring buffer table. The request buffer can then be used as the data buffer + * for io_uring operations via the fixed buffer index. + * Note that the ublk server can never directly access the request data memory. + * + * To use this feature, the ublk server must first register a sparse buffer + * table on an io_uring instance. + * When an incoming ublk request is received, the ublk server submits a + * UBLK_U_IO_REGISTER_IO_BUF command to that io_uring instance. The + * ublksrv_io_cmd's q_id and tag specify the request whose buffer to register + * and addr is the index in the io_uring's buffer table to install the buffer. + * SQEs can now be submitted to the io_uring to read/write the request's buffer + * by enabling fixed buffers (e.g. using IORING_OP_{READ,WRITE}_FIXED or + * IORING_URING_CMD_FIXED) and passing the registered buffer index in buf_index. + * Once the last io_uring operation using the request's buffer has completed, + * the ublk server submits a UBLK_U_IO_UNREGISTER_IO_BUF command with q_id, tag, + * and addr again specifying the request buffer to unregister. + * The ublk request is completed when its buffer is unregistered from all + * io_uring instances and the ublk server issues UBLK_U_IO_COMMIT_AND_FETCH_REQ. + * + * Not available for UBLK_F_UNPRIVILEGED_DEV, as a ublk server can leak + * uninitialized kernel memory by not reading into the full request buffer. */ #define UBLK_F_SUPPORT_ZERO_COPY (1ULL << 0) @@ -450,10 +470,10 @@ static inline struct ublk_auto_buf_reg ublk_sqe_addr_to_auto_buf_reg( __u64 sqe_addr) { struct ublk_auto_buf_reg reg = { - .index = sqe_addr & 0xffff, - .flags = (sqe_addr >> 16) & 0xff, - .reserved0 = (sqe_addr >> 24) & 0xff, - .reserved1 = sqe_addr >> 32, + .index = (__u16)sqe_addr, + .flags = (__u8)(sqe_addr >> 16), + .reserved0 = (__u8)(sqe_addr >> 24), + .reserved1 = (__u32)(sqe_addr >> 32), }; return reg; diff --git a/include/uapi/linux/vm_sockets.h b/include/uapi/linux/vm_sockets.h index ed07181d4eff..e05280e41522 100644 --- a/include/uapi/linux/vm_sockets.h +++ b/include/uapi/linux/vm_sockets.h @@ -17,6 +17,10 @@ #ifndef _UAPI_VM_SOCKETS_H #define _UAPI_VM_SOCKETS_H +#ifndef __KERNEL__ +#include <sys/socket.h> /* for struct sockaddr and sa_family_t */ +#endif + #include <linux/socket.h> #include <linux/types.h> diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c index ce95e3af44a9..f2d2cc319faa 100644 --- a/io_uring/kbuf.c +++ b/io_uring/kbuf.c @@ -271,6 +271,7 @@ static int io_ring_buffers_peek(struct io_kiocb *req, struct buf_sel_arg *arg, if (len > arg->max_len) { len = arg->max_len; if (!(bl->flags & IOBL_INC)) { + arg->partial_map = 1; if (iov != arg->iovs) break; buf->len = len; diff --git a/io_uring/kbuf.h b/io_uring/kbuf.h index 5d83c7adc739..723d0361898e 100644 --- a/io_uring/kbuf.h +++ b/io_uring/kbuf.h @@ -58,7 +58,8 @@ struct buf_sel_arg { size_t max_len; unsigned short nr_iovs; unsigned short mode; - unsigned buf_group; + unsigned short buf_group; + unsigned short partial_map; }; void __user *io_buffer_select(struct io_kiocb *req, size_t *len, diff --git a/io_uring/net.c b/io_uring/net.c index 9550d4c8f866..43a43522f406 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -75,12 +75,17 @@ struct io_sr_msg { u16 flags; /* initialised and used only by !msg send variants */ u16 buf_group; - bool retry; + unsigned short retry_flags; void __user *msg_control; /* used only for send zerocopy */ struct io_kiocb *notif; }; +enum sr_retry_flags { + IO_SR_MSG_RETRY = 1, + IO_SR_MSG_PARTIAL_MAP = 2, +}; + /* * Number of times we'll try and do receives if there's more data. If we * exceed this limit, then add us to the back of the queue and retry from @@ -187,7 +192,7 @@ static inline void io_mshot_prep_retry(struct io_kiocb *req, req->flags &= ~REQ_F_BL_EMPTY; sr->done_io = 0; - sr->retry = false; + sr->retry_flags = 0; sr->len = 0; /* get from the provided buffer */ } @@ -397,7 +402,7 @@ int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg); sr->done_io = 0; - sr->retry = false; + sr->retry_flags = 0; sr->len = READ_ONCE(sqe->len); sr->flags = READ_ONCE(sqe->ioprio); if (sr->flags & ~SENDMSG_FLAGS) @@ -751,7 +756,7 @@ int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg); sr->done_io = 0; - sr->retry = false; + sr->retry_flags = 0; if (unlikely(sqe->file_index || sqe->addr2)) return -EINVAL; @@ -823,7 +828,7 @@ static inline bool io_recv_finish(struct io_kiocb *req, int *ret, cflags |= io_put_kbufs(req, this_ret, io_bundle_nbufs(kmsg, this_ret), issue_flags); - if (sr->retry) + if (sr->retry_flags & IO_SR_MSG_RETRY) cflags = req->cqe.flags | (cflags & CQE_F_MASK); /* bundle with no more immediate buffers, we're done */ if (req->flags & REQ_F_BL_EMPTY) @@ -832,12 +837,12 @@ static inline bool io_recv_finish(struct io_kiocb *req, int *ret, * If more is available AND it was a full transfer, retry and * append to this one */ - if (!sr->retry && kmsg->msg.msg_inq > 1 && this_ret > 0 && + if (!sr->retry_flags && kmsg->msg.msg_inq > 1 && this_ret > 0 && !iov_iter_count(&kmsg->msg.msg_iter)) { req->cqe.flags = cflags & ~CQE_F_MASK; sr->len = kmsg->msg.msg_inq; sr->done_io += this_ret; - sr->retry = true; + sr->retry_flags |= IO_SR_MSG_RETRY; return false; } } else { @@ -1077,6 +1082,14 @@ static int io_recv_buf_select(struct io_kiocb *req, struct io_async_msghdr *kmsg if (unlikely(ret < 0)) return ret; + if (arg.iovs != &kmsg->fast_iov && arg.iovs != kmsg->vec.iovec) { + kmsg->vec.nr = ret; + kmsg->vec.iovec = arg.iovs; + req->flags |= REQ_F_NEED_CLEANUP; + } + if (arg.partial_map) + sr->retry_flags |= IO_SR_MSG_PARTIAL_MAP; + /* special case 1 vec, can be a fast path */ if (ret == 1) { sr->buf = arg.iovs[0].iov_base; @@ -1085,11 +1098,6 @@ static int io_recv_buf_select(struct io_kiocb *req, struct io_async_msghdr *kmsg } iov_iter_init(&kmsg->msg.msg_iter, ITER_DEST, arg.iovs, ret, arg.out_len); - if (arg.iovs != &kmsg->fast_iov && arg.iovs != kmsg->vec.iovec) { - kmsg->vec.nr = ret; - kmsg->vec.iovec = arg.iovs; - req->flags |= REQ_F_NEED_CLEANUP; - } } else { void __user *buf; @@ -1275,7 +1283,7 @@ int io_send_zc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) int ret; zc->done_io = 0; - zc->retry = false; + zc->retry_flags = 0; if (unlikely(READ_ONCE(sqe->__pad2[0]) || READ_ONCE(sqe->addr3))) return -EINVAL; diff --git a/io_uring/opdef.c b/io_uring/opdef.c index 6e0882b051f9..6de6229207a8 100644 --- a/io_uring/opdef.c +++ b/io_uring/opdef.c @@ -216,6 +216,7 @@ const struct io_issue_def io_issue_defs[] = { }, [IORING_OP_FALLOCATE] = { .needs_file = 1, + .hash_reg_file = 1, .prep = io_fallocate_prep, .issue = io_fallocate, }, diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c index d724602697e7..f2b31fb68992 100644 --- a/io_uring/rsrc.c +++ b/io_uring/rsrc.c @@ -112,8 +112,11 @@ static void io_release_ubuf(void *priv) struct io_mapped_ubuf *imu = priv; unsigned int i; - for (i = 0; i < imu->nr_bvecs; i++) - unpin_user_page(imu->bvec[i].bv_page); + for (i = 0; i < imu->nr_bvecs; i++) { + struct folio *folio = page_folio(imu->bvec[i].bv_page); + + unpin_user_folio(folio, 1); + } } static struct io_mapped_ubuf *io_alloc_imu(struct io_ring_ctx *ctx, @@ -731,6 +734,7 @@ bool io_check_coalesce_buffer(struct page **page_array, int nr_pages, data->nr_pages_mid = folio_nr_pages(folio); data->folio_shift = folio_shift(folio); + data->first_folio_page_idx = folio_page_idx(folio, page_array[0]); /* * Check if pages are contiguous inside a folio, and all folios have @@ -824,7 +828,11 @@ static struct io_rsrc_node *io_sqe_buffer_register(struct io_ring_ctx *ctx, if (coalesced) imu->folio_shift = data.folio_shift; refcount_set(&imu->refs, 1); - off = (unsigned long) iov->iov_base & ((1UL << imu->folio_shift) - 1); + + off = (unsigned long)iov->iov_base & ~PAGE_MASK; + if (coalesced) + off += data.first_folio_page_idx << PAGE_SHIFT; + node->buf = imu; ret = 0; @@ -840,8 +848,10 @@ done: if (ret) { if (imu) io_free_imu(ctx, imu); - if (pages) - unpin_user_pages(pages, nr_pages); + if (pages) { + for (i = 0; i < nr_pages; i++) + unpin_user_folio(page_folio(pages[i]), 1); + } io_cache_free(&ctx->node_cache, node); node = ERR_PTR(ret); } @@ -1329,7 +1339,6 @@ static int io_vec_fill_bvec(int ddir, struct iov_iter *iter, { unsigned long folio_size = 1 << imu->folio_shift; unsigned long folio_mask = folio_size - 1; - u64 folio_addr = imu->ubuf & ~folio_mask; struct bio_vec *res_bvec = vec->bvec; size_t total_len = 0; unsigned bvec_idx = 0; @@ -1351,8 +1360,13 @@ static int io_vec_fill_bvec(int ddir, struct iov_iter *iter, if (unlikely(check_add_overflow(total_len, iov_len, &total_len))) return -EOVERFLOW; - /* by using folio address it also accounts for bvec offset */ - offset = buf_addr - folio_addr; + offset = buf_addr - imu->ubuf; + /* + * Only the first bvec can have non zero bv_offset, account it + * here and work with full folios below. + */ + offset += imu->bvec[0].bv_offset; + src_bvec = imu->bvec + (offset >> imu->folio_shift); offset &= folio_mask; diff --git a/io_uring/rsrc.h b/io_uring/rsrc.h index 0d2138f16322..25e7e998dcfd 100644 --- a/io_uring/rsrc.h +++ b/io_uring/rsrc.h @@ -49,6 +49,7 @@ struct io_imu_folio_data { unsigned int nr_pages_mid; unsigned int folio_shift; unsigned int nr_folios; + unsigned long first_folio_page_idx; }; bool io_rsrc_cache_init(struct io_ring_ctx *ctx); diff --git a/io_uring/zcrx.c b/io_uring/zcrx.c index 797247a34cb7..085eeed8cd50 100644 --- a/io_uring/zcrx.c +++ b/io_uring/zcrx.c @@ -106,8 +106,10 @@ static int io_import_dmabuf(struct io_zcrx_ifq *ifq, for_each_sgtable_dma_sg(mem->sgt, sg, i) total_size += sg_dma_len(sg); - if (total_size < off + len) - return -EINVAL; + if (total_size < off + len) { + ret = -EINVAL; + goto err; + } mem->dmabuf_offset = off; mem->size = len; diff --git a/kernel/Kconfig.kexec b/kernel/Kconfig.kexec index e64ce21f9a80..2ee603a98813 100644 --- a/kernel/Kconfig.kexec +++ b/kernel/Kconfig.kexec @@ -134,6 +134,7 @@ config CRASH_DM_CRYPT depends on KEXEC_FILE depends on CRASH_DUMP depends on DM_CRYPT + depends on KEYS help With this option enabled, user space can intereact with /sys/kernel/config/crash_dm_crypt_keys to make the dm crypt keys diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c index f2f38903b2fe..b0eae2a3c895 100644 --- a/kernel/audit_tree.c +++ b/kernel/audit_tree.c @@ -668,12 +668,6 @@ int audit_remove_tree_rule(struct audit_krule *rule) return 0; } -static int compare_root(struct vfsmount *mnt, void *arg) -{ - return inode_to_key(d_backing_inode(mnt->mnt_root)) == - (unsigned long)arg; -} - void audit_trim_trees(void) { struct list_head cursor; @@ -683,8 +677,9 @@ void audit_trim_trees(void) while (cursor.next != &tree_list) { struct audit_tree *tree; struct path path; - struct vfsmount *root_mnt; struct audit_node *node; + struct path *paths; + struct path array[16]; int err; tree = container_of(cursor.next, struct audit_tree, list); @@ -696,9 +691,9 @@ void audit_trim_trees(void) if (err) goto skip_it; - root_mnt = collect_mounts(&path); + paths = collect_paths(&path, array, 16); path_put(&path); - if (IS_ERR(root_mnt)) + if (IS_ERR(paths)) goto skip_it; spin_lock(&hash_lock); @@ -706,14 +701,17 @@ void audit_trim_trees(void) struct audit_chunk *chunk = find_chunk(node); /* this could be NULL if the watch is dying else where... */ node->index |= 1U<<31; - if (iterate_mounts(compare_root, - (void *)(chunk->key), - root_mnt)) - node->index &= ~(1U<<31); + for (struct path *p = paths; p->dentry; p++) { + struct inode *inode = p->dentry->d_inode; + if (inode_to_key(inode) == chunk->key) { + node->index &= ~(1U<<31); + break; + } + } } spin_unlock(&hash_lock); trim_marked(tree); - drop_collected_mounts(root_mnt); + drop_collected_paths(paths, array); skip_it: put_tree(tree); mutex_lock(&audit_filter_mutex); @@ -742,9 +740,14 @@ void audit_put_tree(struct audit_tree *tree) put_tree(tree); } -static int tag_mount(struct vfsmount *mnt, void *arg) +static int tag_mounts(struct path *paths, struct audit_tree *tree) { - return tag_chunk(d_backing_inode(mnt->mnt_root), arg); + for (struct path *p = paths; p->dentry; p++) { + int err = tag_chunk(p->dentry->d_inode, tree); + if (err) + return err; + } + return 0; } /* @@ -801,7 +804,8 @@ int audit_add_tree_rule(struct audit_krule *rule) { struct audit_tree *seed = rule->tree, *tree; struct path path; - struct vfsmount *mnt; + struct path array[16]; + struct path *paths; int err; rule->tree = NULL; @@ -828,16 +832,16 @@ int audit_add_tree_rule(struct audit_krule *rule) err = kern_path(tree->pathname, 0, &path); if (err) goto Err; - mnt = collect_mounts(&path); + paths = collect_paths(&path, array, 16); path_put(&path); - if (IS_ERR(mnt)) { - err = PTR_ERR(mnt); + if (IS_ERR(paths)) { + err = PTR_ERR(paths); goto Err; } get_tree(tree); - err = iterate_mounts(tag_mount, tree, mnt); - drop_collected_mounts(mnt); + err = tag_mounts(paths, tree); + drop_collected_paths(paths, array); if (!err) { struct audit_node *node; @@ -872,20 +876,21 @@ int audit_tag_tree(char *old, char *new) struct list_head cursor, barrier; int failed = 0; struct path path1, path2; - struct vfsmount *tagged; + struct path array[16]; + struct path *paths; int err; err = kern_path(new, 0, &path2); if (err) return err; - tagged = collect_mounts(&path2); + paths = collect_paths(&path2, array, 16); path_put(&path2); - if (IS_ERR(tagged)) - return PTR_ERR(tagged); + if (IS_ERR(paths)) + return PTR_ERR(paths); err = kern_path(old, 0, &path1); if (err) { - drop_collected_mounts(tagged); + drop_collected_paths(paths, array); return err; } @@ -914,7 +919,7 @@ int audit_tag_tree(char *old, char *new) continue; } - failed = iterate_mounts(tag_mount, tree, tagged); + failed = tag_mounts(paths, tree); if (failed) { put_tree(tree); mutex_lock(&audit_filter_mutex); @@ -955,7 +960,7 @@ int audit_tag_tree(char *old, char *new) list_del(&cursor); mutex_unlock(&audit_filter_mutex); path_put(&path1); - drop_collected_mounts(tagged); + drop_collected_paths(paths, array); return failed; } diff --git a/kernel/bpf/bpf_lru_list.c b/kernel/bpf/bpf_lru_list.c index 3dabdd137d10..2d6e1c98d8ad 100644 --- a/kernel/bpf/bpf_lru_list.c +++ b/kernel/bpf/bpf_lru_list.c @@ -337,12 +337,12 @@ static void bpf_lru_list_pop_free_to_local(struct bpf_lru *lru, list) { __bpf_lru_node_move_to_free(l, node, local_free_list(loc_l), BPF_LRU_LOCAL_LIST_T_FREE); - if (++nfree == LOCAL_FREE_TARGET) + if (++nfree == lru->target_free) break; } - if (nfree < LOCAL_FREE_TARGET) - __bpf_lru_list_shrink(lru, l, LOCAL_FREE_TARGET - nfree, + if (nfree < lru->target_free) + __bpf_lru_list_shrink(lru, l, lru->target_free - nfree, local_free_list(loc_l), BPF_LRU_LOCAL_LIST_T_FREE); @@ -577,6 +577,9 @@ static void bpf_common_lru_populate(struct bpf_lru *lru, void *buf, list_add(&node->list, &l->lists[BPF_LRU_LIST_T_FREE]); buf += elem_size; } + + lru->target_free = clamp((nr_elems / num_possible_cpus()) / 2, + 1, LOCAL_FREE_TARGET); } static void bpf_percpu_lru_populate(struct bpf_lru *lru, void *buf, diff --git a/kernel/bpf/bpf_lru_list.h b/kernel/bpf/bpf_lru_list.h index cbd8d3720c2b..fe2661a58ea9 100644 --- a/kernel/bpf/bpf_lru_list.h +++ b/kernel/bpf/bpf_lru_list.h @@ -58,6 +58,7 @@ struct bpf_lru { del_from_htab_func del_from_htab; void *del_arg; unsigned int hash_offset; + unsigned int target_free; unsigned int nr_scans; bool percpu; }; diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 9122c39870bf..f4885514f007 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -2134,7 +2134,7 @@ static const struct bpf_func_proto bpf_sysctl_get_name_proto = { .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_WRITE, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, }; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index a7d6e0c5928b..169845710c7e 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -7027,8 +7027,7 @@ BTF_TYPE_SAFE_TRUSTED(struct file) { struct inode *f_inode; }; -BTF_TYPE_SAFE_TRUSTED(struct dentry) { - /* no negative dentry-s in places where bpf can see it */ +BTF_TYPE_SAFE_TRUSTED_OR_NULL(struct dentry) { struct inode *d_inode; }; @@ -7066,7 +7065,6 @@ static bool type_is_trusted(struct bpf_verifier_env *env, BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct bpf_iter__task)); BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct linux_binprm)); BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct file)); - BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct dentry)); return btf_nested_type_is_trusted(&env->log, reg, field_name, btf_id, "__safe_trusted"); } @@ -7076,6 +7074,7 @@ static bool type_is_trusted_or_null(struct bpf_verifier_env *env, const char *field_name, u32 btf_id) { BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED_OR_NULL(struct socket)); + BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED_OR_NULL(struct dentry)); return btf_nested_type_is_trusted(&env->log, reg, field_name, btf_id, "__safe_trusted_or_null"); diff --git a/kernel/kexec_handover.c b/kernel/kexec_handover.c index 69b953551677..5a21dbe17950 100644 --- a/kernel/kexec_handover.c +++ b/kernel/kexec_handover.c @@ -164,11 +164,21 @@ static int __kho_preserve_order(struct kho_mem_track *track, unsigned long pfn, } /* almost as free_reserved_page(), just don't free the page */ -static void kho_restore_page(struct page *page) +static void kho_restore_page(struct page *page, unsigned int order) { - ClearPageReserved(page); - init_page_count(page); - adjust_managed_page_count(page, 1); + unsigned int nr_pages = (1 << order); + + /* Head page gets refcount of 1. */ + set_page_count(page, 1); + + /* For higher order folios, tail pages get a page count of zero. */ + for (unsigned int i = 1; i < nr_pages; i++) + set_page_count(page + i, 0); + + if (order > 0) + prep_compound_page(page, order); + + adjust_managed_page_count(page, nr_pages); } /** @@ -186,15 +196,10 @@ struct folio *kho_restore_folio(phys_addr_t phys) return NULL; order = page->private; - if (order) { - if (order > MAX_PAGE_ORDER) - return NULL; - - prep_compound_page(page, order); - } else { - kho_restore_page(page); - } + if (order > MAX_PAGE_ORDER) + return NULL; + kho_restore_page(page, order); return page_folio(page); } EXPORT_SYMBOL_GPL(kho_restore_folio); diff --git a/lib/alloc_tag.c b/lib/alloc_tag.c index d48b80f3f007..3a74d63a959e 100644 --- a/lib/alloc_tag.c +++ b/lib/alloc_tag.c @@ -10,6 +10,7 @@ #include <linux/seq_buf.h> #include <linux/seq_file.h> #include <linux/vmalloc.h> +#include <linux/kmemleak.h> #define ALLOCINFO_FILE_NAME "allocinfo" #define MODULE_ALLOC_TAG_VMAP_SIZE (100000UL * sizeof(struct alloc_tag)) @@ -632,8 +633,13 @@ static int load_module(struct module *mod, struct codetag *start, struct codetag mod->name); return -ENOMEM; } - } + /* + * Avoid a kmemleak false positive. The pointer to the counters is stored + * in the alloc_tag section of the module and cannot be directly accessed. + */ + kmemleak_ignore_percpu(tag->counters); + } return 0; } diff --git a/lib/group_cpus.c b/lib/group_cpus.c index ee272c4cefcc..18d43a406114 100644 --- a/lib/group_cpus.c +++ b/lib/group_cpus.c @@ -352,6 +352,9 @@ struct cpumask *group_cpus_evenly(unsigned int numgrps) int ret = -ENOMEM; struct cpumask *masks = NULL; + if (numgrps == 0) + return NULL; + if (!zalloc_cpumask_var(&nmsk, GFP_KERNEL)) return NULL; @@ -426,8 +429,12 @@ struct cpumask *group_cpus_evenly(unsigned int numgrps) #else /* CONFIG_SMP */ struct cpumask *group_cpus_evenly(unsigned int numgrps) { - struct cpumask *masks = kcalloc(numgrps, sizeof(*masks), GFP_KERNEL); + struct cpumask *masks; + if (numgrps == 0) + return NULL; + + masks = kcalloc(numgrps, sizeof(*masks), GFP_KERNEL); if (!masks) return NULL; diff --git a/lib/maple_tree.c b/lib/maple_tree.c index affe979bd14d..00524e55a21e 100644 --- a/lib/maple_tree.c +++ b/lib/maple_tree.c @@ -5527,8 +5527,9 @@ int mas_preallocate(struct ma_state *mas, void *entry, gfp_t gfp) mas->store_type = mas_wr_store_type(&wr_mas); request = mas_prealloc_calc(&wr_mas, entry); if (!request) - return ret; + goto set_flag; + mas->mas_flags &= ~MA_STATE_PREALLOC; mas_node_count_gfp(mas, request, gfp); if (mas_is_err(mas)) { mas_set_alloc_req(mas, 0); @@ -5538,6 +5539,7 @@ int mas_preallocate(struct ma_state *mas, void *entry, gfp_t gfp) return ret; } +set_flag: mas->mas_flags |= MA_STATE_PREALLOC; return ret; } diff --git a/lib/raid6/rvv.c b/lib/raid6/rvv.c index f0887344b274..7d82efa5b14f 100644 --- a/lib/raid6/rvv.c +++ b/lib/raid6/rvv.c @@ -26,9 +26,9 @@ static int rvv_has_vector(void) static void raid6_rvv1_gen_syndrome_real(int disks, unsigned long bytes, void **ptrs) { u8 **dptr = (u8 **)ptrs; - unsigned long d; - int z, z0; u8 *p, *q; + unsigned long vl, d; + int z, z0; z0 = disks - 3; /* Highest data disk */ p = dptr[z0 + 1]; /* XOR parity */ @@ -36,8 +36,9 @@ static void raid6_rvv1_gen_syndrome_real(int disks, unsigned long bytes, void ** asm volatile (".option push\n" ".option arch,+v\n" - "vsetvli t0, x0, e8, m1, ta, ma\n" + "vsetvli %0, x0, e8, m1, ta, ma\n" ".option pop\n" + : "=&r" (vl) ); /* v0:wp0, v1:wq0, v2:wd0/w20, v3:w10 */ @@ -99,7 +100,7 @@ static void raid6_rvv1_xor_syndrome_real(int disks, int start, int stop, { u8 **dptr = (u8 **)ptrs; u8 *p, *q; - unsigned long d; + unsigned long vl, d; int z, z0; z0 = stop; /* P/Q right side optimization */ @@ -108,8 +109,9 @@ static void raid6_rvv1_xor_syndrome_real(int disks, int start, int stop, asm volatile (".option push\n" ".option arch,+v\n" - "vsetvli t0, x0, e8, m1, ta, ma\n" + "vsetvli %0, x0, e8, m1, ta, ma\n" ".option pop\n" + : "=&r" (vl) ); /* v0:wp0, v1:wq0, v2:wd0/w20, v3:w10 */ @@ -195,9 +197,9 @@ static void raid6_rvv1_xor_syndrome_real(int disks, int start, int stop, static void raid6_rvv2_gen_syndrome_real(int disks, unsigned long bytes, void **ptrs) { u8 **dptr = (u8 **)ptrs; - unsigned long d; - int z, z0; u8 *p, *q; + unsigned long vl, d; + int z, z0; z0 = disks - 3; /* Highest data disk */ p = dptr[z0 + 1]; /* XOR parity */ @@ -205,8 +207,9 @@ static void raid6_rvv2_gen_syndrome_real(int disks, unsigned long bytes, void ** asm volatile (".option push\n" ".option arch,+v\n" - "vsetvli t0, x0, e8, m1, ta, ma\n" + "vsetvli %0, x0, e8, m1, ta, ma\n" ".option pop\n" + : "=&r" (vl) ); /* @@ -287,7 +290,7 @@ static void raid6_rvv2_xor_syndrome_real(int disks, int start, int stop, { u8 **dptr = (u8 **)ptrs; u8 *p, *q; - unsigned long d; + unsigned long vl, d; int z, z0; z0 = stop; /* P/Q right side optimization */ @@ -296,8 +299,9 @@ static void raid6_rvv2_xor_syndrome_real(int disks, int start, int stop, asm volatile (".option push\n" ".option arch,+v\n" - "vsetvli t0, x0, e8, m1, ta, ma\n" + "vsetvli %0, x0, e8, m1, ta, ma\n" ".option pop\n" + : "=&r" (vl) ); /* @@ -413,9 +417,9 @@ static void raid6_rvv2_xor_syndrome_real(int disks, int start, int stop, static void raid6_rvv4_gen_syndrome_real(int disks, unsigned long bytes, void **ptrs) { u8 **dptr = (u8 **)ptrs; - unsigned long d; - int z, z0; u8 *p, *q; + unsigned long vl, d; + int z, z0; z0 = disks - 3; /* Highest data disk */ p = dptr[z0 + 1]; /* XOR parity */ @@ -423,8 +427,9 @@ static void raid6_rvv4_gen_syndrome_real(int disks, unsigned long bytes, void ** asm volatile (".option push\n" ".option arch,+v\n" - "vsetvli t0, x0, e8, m1, ta, ma\n" + "vsetvli %0, x0, e8, m1, ta, ma\n" ".option pop\n" + : "=&r" (vl) ); /* @@ -539,7 +544,7 @@ static void raid6_rvv4_xor_syndrome_real(int disks, int start, int stop, { u8 **dptr = (u8 **)ptrs; u8 *p, *q; - unsigned long d; + unsigned long vl, d; int z, z0; z0 = stop; /* P/Q right side optimization */ @@ -548,8 +553,9 @@ static void raid6_rvv4_xor_syndrome_real(int disks, int start, int stop, asm volatile (".option push\n" ".option arch,+v\n" - "vsetvli t0, x0, e8, m1, ta, ma\n" + "vsetvli %0, x0, e8, m1, ta, ma\n" ".option pop\n" + : "=&r" (vl) ); /* @@ -721,9 +727,9 @@ static void raid6_rvv4_xor_syndrome_real(int disks, int start, int stop, static void raid6_rvv8_gen_syndrome_real(int disks, unsigned long bytes, void **ptrs) { u8 **dptr = (u8 **)ptrs; - unsigned long d; - int z, z0; u8 *p, *q; + unsigned long vl, d; + int z, z0; z0 = disks - 3; /* Highest data disk */ p = dptr[z0 + 1]; /* XOR parity */ @@ -731,8 +737,9 @@ static void raid6_rvv8_gen_syndrome_real(int disks, unsigned long bytes, void ** asm volatile (".option push\n" ".option arch,+v\n" - "vsetvli t0, x0, e8, m1, ta, ma\n" + "vsetvli %0, x0, e8, m1, ta, ma\n" ".option pop\n" + : "=&r" (vl) ); /* @@ -915,7 +922,7 @@ static void raid6_rvv8_xor_syndrome_real(int disks, int start, int stop, { u8 **dptr = (u8 **)ptrs; u8 *p, *q; - unsigned long d; + unsigned long vl, d; int z, z0; z0 = stop; /* P/Q right side optimization */ @@ -924,8 +931,9 @@ static void raid6_rvv8_xor_syndrome_real(int disks, int start, int stop, asm volatile (".option push\n" ".option arch,+v\n" - "vsetvli t0, x0, e8, m1, ta, ma\n" + "vsetvli %0, x0, e8, m1, ta, ma\n" ".option pop\n" + : "=&r" (vl) ); /* diff --git a/mm/damon/sysfs-schemes.c b/mm/damon/sysfs-schemes.c index 0f6c9e1fec0b..30ae7518ffbf 100644 --- a/mm/damon/sysfs-schemes.c +++ b/mm/damon/sysfs-schemes.c @@ -472,6 +472,7 @@ static ssize_t memcg_path_store(struct kobject *kobj, return -ENOMEM; strscpy(path, buf, count + 1); + kfree(filter->memcg_path); filter->memcg_path = path; return count; } @@ -2303,13 +2303,13 @@ static void pofs_unpin(struct pages_or_folios *pofs) /* * Returns the number of collected folios. Return value is always >= 0. */ -static void collect_longterm_unpinnable_folios( +static unsigned long collect_longterm_unpinnable_folios( struct list_head *movable_folio_list, struct pages_or_folios *pofs) { + unsigned long i, collected = 0; struct folio *prev_folio = NULL; bool drain_allow = true; - unsigned long i; for (i = 0; i < pofs->nr_entries; i++) { struct folio *folio = pofs_get_folio(pofs, i); @@ -2321,6 +2321,8 @@ static void collect_longterm_unpinnable_folios( if (folio_is_longterm_pinnable(folio)) continue; + collected++; + if (folio_is_device_coherent(folio)) continue; @@ -2342,6 +2344,8 @@ static void collect_longterm_unpinnable_folios( NR_ISOLATED_ANON + folio_is_file_lru(folio), folio_nr_pages(folio)); } + + return collected; } /* @@ -2418,9 +2422,11 @@ static long check_and_migrate_movable_pages_or_folios(struct pages_or_folios *pofs) { LIST_HEAD(movable_folio_list); + unsigned long collected; - collect_longterm_unpinnable_folios(&movable_folio_list, pofs); - if (list_empty(&movable_folio_list)) + collected = collect_longterm_unpinnable_folios(&movable_folio_list, + pofs); + if (!collected) return 0; return migrate_longterm_unpinnable_folios(&movable_folio_list, pofs); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 8746ed2fec13..9dc95eac558c 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2787,20 +2787,24 @@ void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma, /* * alloc_and_dissolve_hugetlb_folio - Allocate a new folio and dissolve * the old one - * @h: struct hstate old page belongs to * @old_folio: Old folio to dissolve * @list: List to isolate the page in case we need to * Returns 0 on success, otherwise negated error. */ -static int alloc_and_dissolve_hugetlb_folio(struct hstate *h, - struct folio *old_folio, struct list_head *list) +static int alloc_and_dissolve_hugetlb_folio(struct folio *old_folio, + struct list_head *list) { - gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE; + gfp_t gfp_mask; + struct hstate *h; int nid = folio_nid(old_folio); struct folio *new_folio = NULL; int ret = 0; retry: + /* + * The old_folio might have been dissolved from under our feet, so make sure + * to carefully check the state under the lock. + */ spin_lock_irq(&hugetlb_lock); if (!folio_test_hugetlb(old_folio)) { /* @@ -2829,8 +2833,10 @@ retry: cond_resched(); goto retry; } else { + h = folio_hstate(old_folio); if (!new_folio) { spin_unlock_irq(&hugetlb_lock); + gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE; new_folio = alloc_buddy_hugetlb_folio(h, gfp_mask, nid, NULL, NULL); if (!new_folio) @@ -2874,35 +2880,24 @@ free_new: int isolate_or_dissolve_huge_folio(struct folio *folio, struct list_head *list) { - struct hstate *h; int ret = -EBUSY; - /* - * The page might have been dissolved from under our feet, so make sure - * to carefully check the state under the lock. - * Return success when racing as if we dissolved the page ourselves. - */ - spin_lock_irq(&hugetlb_lock); - if (folio_test_hugetlb(folio)) { - h = folio_hstate(folio); - } else { - spin_unlock_irq(&hugetlb_lock); + /* Not to disrupt normal path by vainly holding hugetlb_lock */ + if (!folio_test_hugetlb(folio)) return 0; - } - spin_unlock_irq(&hugetlb_lock); /* * Fence off gigantic pages as there is a cyclic dependency between * alloc_contig_range and them. Return -ENOMEM as this has the effect * of bailing out right away without further retrying. */ - if (hstate_is_gigantic(h)) + if (folio_order(folio) > MAX_PAGE_ORDER) return -ENOMEM; if (folio_ref_count(folio) && folio_isolate_hugetlb(folio, list)) ret = 0; else if (!folio_ref_count(folio)) - ret = alloc_and_dissolve_hugetlb_folio(h, folio, list); + ret = alloc_and_dissolve_hugetlb_folio(folio, list); return ret; } @@ -2916,7 +2911,6 @@ int isolate_or_dissolve_huge_folio(struct folio *folio, struct list_head *list) */ int replace_free_hugepage_folios(unsigned long start_pfn, unsigned long end_pfn) { - struct hstate *h; struct folio *folio; int ret = 0; @@ -2925,23 +2919,9 @@ int replace_free_hugepage_folios(unsigned long start_pfn, unsigned long end_pfn) while (start_pfn < end_pfn) { folio = pfn_folio(start_pfn); - /* - * The folio might have been dissolved from under our feet, so make sure - * to carefully check the state under the lock. - */ - spin_lock_irq(&hugetlb_lock); - if (folio_test_hugetlb(folio)) { - h = folio_hstate(folio); - } else { - spin_unlock_irq(&hugetlb_lock); - start_pfn++; - continue; - } - spin_unlock_irq(&hugetlb_lock); - - if (!folio_ref_count(folio)) { - ret = alloc_and_dissolve_hugetlb_folio(h, folio, - &isolate_list); + /* Not to disrupt normal path by vainly holding hugetlb_lock */ + if (folio_test_hugetlb(folio) && !folio_ref_count(folio)) { + ret = alloc_and_dissolve_hugetlb_folio(folio, &isolate_list); if (ret) break; diff --git a/mm/kmemleak.c b/mm/kmemleak.c index da9cee34ee1b..8d588e685311 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -1247,6 +1247,20 @@ void __ref kmemleak_transient_leak(const void *ptr) EXPORT_SYMBOL(kmemleak_transient_leak); /** + * kmemleak_ignore_percpu - similar to kmemleak_ignore but taking a percpu + * address argument + * @ptr: percpu address of the object + */ +void __ref kmemleak_ignore_percpu(const void __percpu *ptr) +{ + pr_debug("%s(0x%px)\n", __func__, ptr); + + if (kmemleak_enabled && ptr && !IS_ERR_PCPU(ptr)) + make_black_object((unsigned long)ptr, OBJECT_PERCPU); +} +EXPORT_SYMBOL_GPL(kmemleak_ignore_percpu); + +/** * kmemleak_ignore - ignore an allocated object * @ptr: pointer to beginning of the object * diff --git a/mm/memory.c b/mm/memory.c index 8eba595056fe..b0cda5aab398 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -4315,26 +4315,6 @@ static struct folio *__alloc_swap_folio(struct vm_fault *vmf) } #ifdef CONFIG_TRANSPARENT_HUGEPAGE -static inline int non_swapcache_batch(swp_entry_t entry, int max_nr) -{ - struct swap_info_struct *si = swp_swap_info(entry); - pgoff_t offset = swp_offset(entry); - int i; - - /* - * While allocating a large folio and doing swap_read_folio, which is - * the case the being faulted pte doesn't have swapcache. We need to - * ensure all PTEs have no cache as well, otherwise, we might go to - * swap devices while the content is in swapcache. - */ - for (i = 0; i < max_nr; i++) { - if ((si->swap_map[offset + i] & SWAP_HAS_CACHE)) - return i; - } - - return i; -} - /* * Check if the PTEs within a range are contiguous swap entries * and have consistent swapcache, zeromap. diff --git a/mm/shmem.c b/mm/shmem.c index 0c5fb4ffa03a..3a5a65b1f41a 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2259,6 +2259,7 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index, folio = swap_cache_get_folio(swap, NULL, 0); order = xa_get_order(&mapping->i_pages, index); if (!folio) { + int nr_pages = 1 << order; bool fallback_order0 = false; /* Or update major stats only when swapin succeeds?? */ @@ -2272,9 +2273,12 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index, * If uffd is active for the vma, we need per-page fault * fidelity to maintain the uffd semantics, then fallback * to swapin order-0 folio, as well as for zswap case. + * Any existing sub folio in the swap cache also blocks + * mTHP swapin. */ if (order > 0 && ((vma && unlikely(userfaultfd_armed(vma))) || - !zswap_never_enabled())) + !zswap_never_enabled() || + non_swapcache_batch(swap, nr_pages) != nr_pages)) fallback_order0 = true; /* Skip swapcache for synchronous device. */ diff --git a/mm/swap.h b/mm/swap.h index 2269eb9df0af..9096082a915e 100644 --- a/mm/swap.h +++ b/mm/swap.h @@ -106,6 +106,25 @@ static inline int swap_zeromap_batch(swp_entry_t entry, int max_nr, return find_next_bit(sis->zeromap, end, start) - start; } +static inline int non_swapcache_batch(swp_entry_t entry, int max_nr) +{ + struct swap_info_struct *si = swp_swap_info(entry); + pgoff_t offset = swp_offset(entry); + int i; + + /* + * While allocating a large folio and doing mTHP swapin, we need to + * ensure all entries are not cached, otherwise, the mTHP folio will + * be in conflict with the folio in swap cache. + */ + for (i = 0; i < max_nr; i++) { + if ((si->swap_map[offset + i] & SWAP_HAS_CACHE)) + return i; + } + + return i; +} + #else /* CONFIG_SWAP */ struct swap_iocb; static inline void swap_read_folio(struct folio *folio, struct swap_iocb **plug) @@ -199,6 +218,10 @@ static inline int swap_zeromap_batch(swp_entry_t entry, int max_nr, return 0; } +static inline int non_swapcache_batch(swp_entry_t entry, int max_nr) +{ + return 0; +} #endif /* CONFIG_SWAP */ /** diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index bc473ad21202..8253978ee0fb 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -1084,8 +1084,18 @@ static int move_swap_pte(struct mm_struct *mm, struct vm_area_struct *dst_vma, pte_t orig_dst_pte, pte_t orig_src_pte, pmd_t *dst_pmd, pmd_t dst_pmdval, spinlock_t *dst_ptl, spinlock_t *src_ptl, - struct folio *src_folio) + struct folio *src_folio, + struct swap_info_struct *si, swp_entry_t entry) { + /* + * Check if the folio still belongs to the target swap entry after + * acquiring the lock. Folio can be freed in the swap cache while + * not locked. + */ + if (src_folio && unlikely(!folio_test_swapcache(src_folio) || + entry.val != src_folio->swap.val)) + return -EAGAIN; + double_pt_lock(dst_ptl, src_ptl); if (!is_pte_pages_stable(dst_pte, src_pte, orig_dst_pte, orig_src_pte, @@ -1102,6 +1112,25 @@ static int move_swap_pte(struct mm_struct *mm, struct vm_area_struct *dst_vma, if (src_folio) { folio_move_anon_rmap(src_folio, dst_vma); src_folio->index = linear_page_index(dst_vma, dst_addr); + } else { + /* + * Check if the swap entry is cached after acquiring the src_pte + * lock. Otherwise, we might miss a newly loaded swap cache folio. + * + * Check swap_map directly to minimize overhead, READ_ONCE is sufficient. + * We are trying to catch newly added swap cache, the only possible case is + * when a folio is swapped in and out again staying in swap cache, using the + * same entry before the PTE check above. The PTL is acquired and released + * twice, each time after updating the swap_map's flag. So holding + * the PTL here ensures we see the updated value. False positive is possible, + * e.g. SWP_SYNCHRONOUS_IO swapin may set the flag without touching the + * cache, or during the tiny synchronization window between swap cache and + * swap_map, but it will be gone very quickly, worst result is retry jitters. + */ + if (READ_ONCE(si->swap_map[swp_offset(entry)]) & SWAP_HAS_CACHE) { + double_pt_unlock(dst_ptl, src_ptl); + return -EAGAIN; + } } orig_src_pte = ptep_get_and_clear(mm, src_addr, src_pte); @@ -1412,7 +1441,7 @@ retry: } err = move_swap_pte(mm, dst_vma, dst_addr, src_addr, dst_pte, src_pte, orig_dst_pte, orig_src_pte, dst_pmd, dst_pmdval, - dst_ptl, src_ptl, src_folio); + dst_ptl, src_ptl, src_folio, si, entry); } out: diff --git a/net/atm/clip.c b/net/atm/clip.c index 61b5b700817d..b234dc3bcb0d 100644 --- a/net/atm/clip.c +++ b/net/atm/clip.c @@ -193,12 +193,6 @@ static void clip_push(struct atm_vcc *vcc, struct sk_buff *skb) pr_debug("\n"); - if (!clip_devs) { - atm_return(vcc, skb->truesize); - kfree_skb(skb); - return; - } - if (!skb) { pr_debug("removing VCC %p\n", clip_vcc); if (clip_vcc->entry) @@ -208,6 +202,11 @@ static void clip_push(struct atm_vcc *vcc, struct sk_buff *skb) return; } atm_return(vcc, skb->truesize); + if (!clip_devs) { + kfree_skb(skb); + return; + } + skb->dev = clip_vcc->entry ? clip_vcc->entry->neigh->dev : clip_devs; /* clip_vcc->entry == NULL if we don't have an IP address yet */ if (!skb->dev) { diff --git a/net/atm/resources.c b/net/atm/resources.c index 995d29e7fb13..b19d851e1f44 100644 --- a/net/atm/resources.c +++ b/net/atm/resources.c @@ -146,11 +146,10 @@ void atm_dev_deregister(struct atm_dev *dev) */ mutex_lock(&atm_dev_mutex); list_del(&dev->dev_list); - mutex_unlock(&atm_dev_mutex); - atm_dev_release_vccs(dev); atm_unregister_sysfs(dev); atm_proc_dev_deregister(dev); + mutex_unlock(&atm_dev_mutex); atm_dev_put(dev); } diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 07a8b4281a39..14d7221b8ac0 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -64,7 +64,7 @@ static DEFINE_IDA(hci_index_ida); /* Get HCI device by index. * Device is held on return. */ -struct hci_dev *hci_dev_get(int index) +static struct hci_dev *__hci_dev_get(int index, int *srcu_index) { struct hci_dev *hdev = NULL, *d; @@ -77,6 +77,8 @@ struct hci_dev *hci_dev_get(int index) list_for_each_entry(d, &hci_dev_list, list) { if (d->id == index) { hdev = hci_dev_hold(d); + if (srcu_index) + *srcu_index = srcu_read_lock(&d->srcu); break; } } @@ -84,6 +86,22 @@ struct hci_dev *hci_dev_get(int index) return hdev; } +struct hci_dev *hci_dev_get(int index) +{ + return __hci_dev_get(index, NULL); +} + +static struct hci_dev *hci_dev_get_srcu(int index, int *srcu_index) +{ + return __hci_dev_get(index, srcu_index); +} + +static void hci_dev_put_srcu(struct hci_dev *hdev, int srcu_index) +{ + srcu_read_unlock(&hdev->srcu, srcu_index); + hci_dev_put(hdev); +} + /* ---- Inquiry support ---- */ bool hci_discovery_active(struct hci_dev *hdev) @@ -568,9 +586,9 @@ static int hci_dev_do_reset(struct hci_dev *hdev) int hci_dev_reset(__u16 dev) { struct hci_dev *hdev; - int err; + int err, srcu_index; - hdev = hci_dev_get(dev); + hdev = hci_dev_get_srcu(dev, &srcu_index); if (!hdev) return -ENODEV; @@ -592,7 +610,7 @@ int hci_dev_reset(__u16 dev) err = hci_dev_do_reset(hdev); done: - hci_dev_put(hdev); + hci_dev_put_srcu(hdev, srcu_index); return err; } @@ -2433,6 +2451,11 @@ struct hci_dev *hci_alloc_dev_priv(int sizeof_priv) if (!hdev) return NULL; + if (init_srcu_struct(&hdev->srcu)) { + kfree(hdev); + return NULL; + } + hdev->pkt_type = (HCI_DM1 | HCI_DH1 | HCI_HV1); hdev->esco_type = (ESCO_HV1); hdev->link_mode = (HCI_LM_ACCEPT); @@ -2678,6 +2701,9 @@ void hci_unregister_dev(struct hci_dev *hdev) list_del(&hdev->list); write_unlock(&hci_dev_list_lock); + synchronize_srcu(&hdev->srcu); + cleanup_srcu_struct(&hdev->srcu); + disable_work_sync(&hdev->rx_work); disable_work_sync(&hdev->cmd_work); disable_work_sync(&hdev->tx_work); diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index a5bde5db58ef..40daa38276f3 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -3415,7 +3415,7 @@ static int l2cap_parse_conf_req(struct l2cap_chan *chan, void *data, size_t data struct l2cap_conf_rfc rfc = { .mode = L2CAP_MODE_BASIC }; struct l2cap_conf_efs efs; u8 remote_efs = 0; - u16 mtu = L2CAP_DEFAULT_MTU; + u16 mtu = 0; u16 result = L2CAP_CONF_SUCCESS; u16 size; @@ -3520,6 +3520,13 @@ done: /* Configure output options and let the other side know * which ones we don't like. */ + /* If MTU is not provided in configure request, use the most recently + * explicitly or implicitly accepted value for the other direction, + * or the default value. + */ + if (mtu == 0) + mtu = chan->imtu ? chan->imtu : L2CAP_DEFAULT_MTU; + if (mtu < L2CAP_DEFAULT_MIN_MTU) result = L2CAP_CONF_UNACCEPT; else { diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 0224ef3dfec0..1377f31b719c 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -2015,10 +2015,19 @@ void br_multicast_port_ctx_init(struct net_bridge_port *port, void br_multicast_port_ctx_deinit(struct net_bridge_mcast_port *pmctx) { + struct net_bridge *br = pmctx->port->br; + bool del = false; + #if IS_ENABLED(CONFIG_IPV6) timer_delete_sync(&pmctx->ip6_mc_router_timer); #endif timer_delete_sync(&pmctx->ip4_mc_router_timer); + + spin_lock_bh(&br->multicast_lock); + del |= br_ip6_multicast_rport_del(pmctx); + del |= br_ip4_multicast_rport_del(pmctx); + br_multicast_rport_del_notify(pmctx, del); + spin_unlock_bh(&br->multicast_lock); } int br_multicast_add_port(struct net_bridge_port *port) diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 4ddb7490df4b..6ad84d4a2b46 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -432,6 +432,7 @@ int netpoll_send_udp(struct netpoll *np, const char *msg, int len) udph->dest = htons(np->remote_port); udph->len = htons(udp_len); + udph->check = 0; if (np->ipv6) { udph->check = csum_ipv6_magic(&np->local_ip.in6, &np->remote_ip.in6, @@ -460,7 +461,6 @@ int netpoll_send_udp(struct netpoll *np, const char *msg, int len) skb_reset_mac_header(skb); skb->protocol = eth->h_proto = htons(ETH_P_IPV6); } else { - udph->check = 0; udph->check = csum_tcpudp_magic(np->local_ip.ip, np->remote_ip.ip, udp_len, IPPROTO_UDP, diff --git a/net/core/selftests.c b/net/core/selftests.c index 35f807ea9952..406faf8e5f3f 100644 --- a/net/core/selftests.c +++ b/net/core/selftests.c @@ -160,8 +160,9 @@ static struct sk_buff *net_test_get_skb(struct net_device *ndev, skb->csum = 0; skb->ip_summed = CHECKSUM_PARTIAL; if (attr->tcp) { - thdr->check = ~tcp_v4_check(skb->len, ihdr->saddr, - ihdr->daddr, 0); + int l4len = skb->len - skb_transport_offset(skb); + + thdr->check = ~tcp_v4_check(l4len, ihdr->saddr, ihdr->daddr, 0); skb->csum_start = skb_transport_header(skb) - skb->head; skb->csum_offset = offsetof(struct tcphdr, check); } else { diff --git a/net/mac80211/link.c b/net/mac80211/link.c index d40c2bd3b50b..4f7b7d0f64f2 100644 --- a/net/mac80211/link.c +++ b/net/mac80211/link.c @@ -93,9 +93,6 @@ void ieee80211_link_init(struct ieee80211_sub_if_data *sdata, if (link_id < 0) link_id = 0; - rcu_assign_pointer(sdata->vif.link_conf[link_id], link_conf); - rcu_assign_pointer(sdata->link[link_id], link); - if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) { struct ieee80211_sub_if_data *ap_bss; struct ieee80211_bss_conf *ap_bss_conf; @@ -145,6 +142,9 @@ void ieee80211_link_init(struct ieee80211_sub_if_data *sdata, ieee80211_link_debugfs_add(link); } + + rcu_assign_pointer(sdata->vif.link_conf[link_id], link_conf); + rcu_assign_pointer(sdata->link[link_id], link); } void ieee80211_link_stop(struct ieee80211_link_data *link) diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 27d414efa3fd..a125995ed252 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -3884,7 +3884,7 @@ void ieee80211_recalc_dtim(struct ieee80211_local *local, { u64 tsf = drv_get_tsf(local, sdata); u64 dtim_count = 0; - u16 beacon_int = sdata->vif.bss_conf.beacon_int * 1024; + u32 beacon_int = sdata->vif.bss_conf.beacon_int * 1024; u8 dtim_period = sdata->vif.bss_conf.dtim_period; struct ps_data *ps; u8 bcns_from_dtim; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 22e170fb5dda..52b155123985 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -660,6 +660,11 @@ static void unix_sock_destructor(struct sock *sk) #endif } +static unsigned int unix_skb_len(const struct sk_buff *skb) +{ + return skb->len - UNIXCB(skb).consumed; +} + static void unix_release_sock(struct sock *sk, int embrion) { struct unix_sock *u = unix_sk(sk); @@ -694,10 +699,16 @@ static void unix_release_sock(struct sock *sk, int embrion) if (skpair != NULL) { if (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) { + struct sk_buff *skb = skb_peek(&sk->sk_receive_queue); + +#if IS_ENABLED(CONFIG_AF_UNIX_OOB) + if (skb && !unix_skb_len(skb)) + skb = skb_peek_next(skb, &sk->sk_receive_queue); +#endif unix_state_lock(skpair); /* No more writes */ WRITE_ONCE(skpair->sk_shutdown, SHUTDOWN_MASK); - if (!skb_queue_empty_lockless(&sk->sk_receive_queue) || embrion) + if (skb || embrion) WRITE_ONCE(skpair->sk_err, ECONNRESET); unix_state_unlock(skpair); skpair->sk_state_change(skpair); @@ -2661,11 +2672,6 @@ static long unix_stream_data_wait(struct sock *sk, long timeo, return timeo; } -static unsigned int unix_skb_len(const struct sk_buff *skb) -{ - return skb->len - UNIXCB(skb).consumed; -} - struct unix_stream_read_state { int (*recv_actor)(struct sk_buff *, int, int, struct unix_stream_read_state *); @@ -2680,11 +2686,11 @@ struct unix_stream_read_state { #if IS_ENABLED(CONFIG_AF_UNIX_OOB) static int unix_stream_recv_urg(struct unix_stream_read_state *state) { + struct sk_buff *oob_skb, *read_skb = NULL; struct socket *sock = state->socket; struct sock *sk = sock->sk; struct unix_sock *u = unix_sk(sk); int chunk = 1; - struct sk_buff *oob_skb; mutex_lock(&u->iolock); unix_state_lock(sk); @@ -2699,9 +2705,16 @@ static int unix_stream_recv_urg(struct unix_stream_read_state *state) oob_skb = u->oob_skb; - if (!(state->flags & MSG_PEEK)) + if (!(state->flags & MSG_PEEK)) { WRITE_ONCE(u->oob_skb, NULL); + if (oob_skb->prev != (struct sk_buff *)&sk->sk_receive_queue && + !unix_skb_len(oob_skb->prev)) { + read_skb = oob_skb->prev; + __skb_unlink(read_skb, &sk->sk_receive_queue); + } + } + spin_unlock(&sk->sk_receive_queue.lock); unix_state_unlock(sk); @@ -2712,6 +2725,8 @@ static int unix_stream_recv_urg(struct unix_stream_read_state *state) mutex_unlock(&u->iolock); + consume_skb(read_skb); + if (chunk < 0) return -EFAULT; diff --git a/scripts/gdb/linux/vfs.py b/scripts/gdb/linux/vfs.py index c77b9ce75f6d..b5fbb18ccb77 100644 --- a/scripts/gdb/linux/vfs.py +++ b/scripts/gdb/linux/vfs.py @@ -22,7 +22,7 @@ def dentry_name(d): if parent == d or parent == 0: return "" p = dentry_name(d['d_parent']) + "/" - return p + d['d_iname'].string() + return p + d['d_shortname']['string'].string() class DentryName(gdb.Function): """Return string of the full path of a dentry. diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c index 7becf3808818..d185754c2786 100644 --- a/security/selinux/ss/services.c +++ b/security/selinux/ss/services.c @@ -1909,11 +1909,17 @@ retry: goto out_unlock; } /* Obtain the sid for the context. */ - rc = sidtab_context_to_sid(sidtab, &newcontext, out_sid); - if (rc == -ESTALE) { - rcu_read_unlock(); - context_destroy(&newcontext); - goto retry; + if (context_equal(scontext, &newcontext)) + *out_sid = ssid; + else if (context_equal(tcontext, &newcontext)) + *out_sid = tsid; + else { + rc = sidtab_context_to_sid(sidtab, &newcontext, out_sid); + if (rc == -ESTALE) { + rcu_read_unlock(); + context_destroy(&newcontext); + goto retry; + } } out_unlock: rcu_read_unlock(); diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 2e1618494c20..5d6d01ecfee2 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -2656,6 +2656,7 @@ static const struct hda_quirk alc882_fixup_tbl[] = { SND_PCI_QUIRK(0x147b, 0x107a, "Abit AW9D-MAX", ALC882_FIXUP_ABIT_AW9D_MAX), SND_PCI_QUIRK(0x1558, 0x3702, "Clevo X370SN[VW]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK(0x1558, 0x50d3, "Clevo PC50[ER][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), + SND_PCI_QUIRK(0x1558, 0x5802, "Clevo X58[05]WN[RST]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK(0x1558, 0x65d1, "Clevo PB51[ER][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK(0x1558, 0x65d2, "Clevo PB51R[CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK(0x1558, 0x65e1, "Clevo PB51[ED][DF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), @@ -6609,6 +6610,7 @@ static void alc294_fixup_bass_speaker_15(struct hda_codec *codec, if (action == HDA_FIXUP_ACT_PRE_PROBE) { static const hda_nid_t conn[] = { 0x02, 0x03 }; snd_hda_override_conn_list(codec, 0x15, ARRAY_SIZE(conn), conn); + snd_hda_gen_add_micmute_led_cdev(codec, NULL); } } @@ -10737,6 +10739,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8975, "HP EliteBook x360 840 Aero G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x897d, "HP mt440 Mobile Thin Client U74", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8981, "HP Elite Dragonfly G3", ALC245_FIXUP_CS35L41_SPI_4), + SND_PCI_QUIRK(0x103c, 0x898a, "HP Pavilion 15-eg100", ALC287_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x898e, "HP EliteBook 835 G9", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x898f, "HP EliteBook 835 G9", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x8991, "HP EliteBook 845 G9", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED), @@ -10907,7 +10910,9 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8def, "HP EliteBook 660 G12", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8df0, "HP EliteBook 630 G12", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8df1, "HP EliteBook 630 G12", ALC236_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8dfb, "HP EliteBook 6 G1a 14", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8dfc, "HP EliteBook 645 G12", ALC236_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8dfd, "HP EliteBook 6 G1a 16", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8dfe, "HP EliteBook 665 G12", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8e11, "HP Trekker", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x8e12, "HP Trekker", ALC287_FIXUP_CS35L41_I2C_2), @@ -11026,6 +11031,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1df3, "ASUS UM5606WA", ALC294_FIXUP_BASS_SPEAKER_15), SND_PCI_QUIRK(0x1043, 0x1264, "ASUS UM5606KA", ALC294_FIXUP_BASS_SPEAKER_15), SND_PCI_QUIRK(0x1043, 0x1e02, "ASUS UX3402ZA", ALC245_FIXUP_CS35L41_SPI_2), + SND_PCI_QUIRK(0x1043, 0x1e10, "ASUS VivoBook X507UAR", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1043, 0x1e11, "ASUS Zephyrus G15", ALC289_FIXUP_ASUS_GA502), SND_PCI_QUIRK(0x1043, 0x1e12, "ASUS UM3402", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x1043, 0x1e1f, "ASUS Vivobook 15 X1504VAP", ALC2XX_FIXUP_HEADSET_MIC), @@ -11135,6 +11141,8 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1558, 0x14a1, "Clevo L141MU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x2624, "Clevo L240TU", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x28c1, "Clevo V370VND", ALC2XX_FIXUP_HEADSET_MIC), + SND_PCI_QUIRK(0x1558, 0x35a1, "Clevo V3[56]0EN[CDE]", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x35b1, "Clevo V3[57]0WN[MNP]Q", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x4018, "Clevo NV40M[BE]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x4019, "Clevo NV40MZ", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x4020, "Clevo NV40MB", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), @@ -11162,6 +11170,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1558, 0x51b1, "Clevo NS50AU", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x51b3, "Clevo NS70AU", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x5630, "Clevo NP50RNJS", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x5700, "Clevo X560WN[RST]", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x70a1, "Clevo NB70T[HJK]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x70b3, "Clevo NK70SB", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x70f2, "Clevo NH79EPY", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), @@ -11201,6 +11210,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1558, 0xa650, "Clevo NP[567]0SN[CD]", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0xa671, "Clevo NP70SN[CDE]", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0xa741, "Clevo V54x_6x_TNE", ALC245_FIXUP_CLEVO_NOISY_MIC), + SND_PCI_QUIRK(0x1558, 0xa743, "Clevo V54x_6x_TU", ALC245_FIXUP_CLEVO_NOISY_MIC), SND_PCI_QUIRK(0x1558, 0xa763, "Clevo V54x_6x_TU", ALC245_FIXUP_CLEVO_NOISY_MIC), SND_PCI_QUIRK(0x1558, 0xb018, "Clevo NP50D[BE]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0xb019, "Clevo NH77D[BE]Q", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), diff --git a/sound/soc/amd/ps/acp63.h b/sound/soc/amd/ps/acp63.h index 85feae45c44c..d7c994e26e4d 100644 --- a/sound/soc/amd/ps/acp63.h +++ b/sound/soc/amd/ps/acp63.h @@ -334,6 +334,8 @@ struct acp_hw_ops { * @addr: pci ioremap address * @reg_range: ACP reigister range * @acp_rev: ACP PCI revision id + * @acp_sw_pad_keeper_en: store acp SoundWire pad keeper enable register value + * @acp_pad_pulldown_ctrl: store acp pad pulldown control register value * @acp63_sdw0-dma_intr_stat: DMA interrupt status array for ACP6.3 platform SoundWire * manager-SW0 instance * @acp63_sdw_dma_intr_stat: DMA interrupt status array for ACP6.3 platform SoundWire @@ -367,6 +369,8 @@ struct acp63_dev_data { u32 addr; u32 reg_range; u32 acp_rev; + u32 acp_sw_pad_keeper_en; + u32 acp_pad_pulldown_ctrl; u16 acp63_sdw0_dma_intr_stat[ACP63_SDW0_DMA_MAX_STREAMS]; u16 acp63_sdw1_dma_intr_stat[ACP63_SDW1_DMA_MAX_STREAMS]; u16 acp70_sdw0_dma_intr_stat[ACP70_SDW0_DMA_MAX_STREAMS]; diff --git a/sound/soc/amd/ps/ps-common.c b/sound/soc/amd/ps/ps-common.c index 1c89fb5fe1da..7b4966b75dc6 100644 --- a/sound/soc/amd/ps/ps-common.c +++ b/sound/soc/amd/ps/ps-common.c @@ -160,6 +160,8 @@ static int __maybe_unused snd_acp63_suspend(struct device *dev) adata = dev_get_drvdata(dev); if (adata->is_sdw_dev) { + adata->acp_sw_pad_keeper_en = readl(adata->acp63_base + ACP_SW0_PAD_KEEPER_EN); + adata->acp_pad_pulldown_ctrl = readl(adata->acp63_base + ACP_PAD_PULLDOWN_CTRL); adata->sdw_en_stat = check_acp_sdw_enable_status(adata); if (adata->sdw_en_stat) { writel(1, adata->acp63_base + ACP_ZSC_DSP_CTRL); @@ -197,6 +199,7 @@ static int __maybe_unused snd_acp63_runtime_resume(struct device *dev) static int __maybe_unused snd_acp63_resume(struct device *dev) { struct acp63_dev_data *adata; + u32 acp_sw_pad_keeper_en; int ret; adata = dev_get_drvdata(dev); @@ -209,6 +212,12 @@ static int __maybe_unused snd_acp63_resume(struct device *dev) if (ret) dev_err(dev, "ACP init failed\n"); + acp_sw_pad_keeper_en = readl(adata->acp63_base + ACP_SW0_PAD_KEEPER_EN); + dev_dbg(dev, "ACP_SW0_PAD_KEEPER_EN:0x%x\n", acp_sw_pad_keeper_en); + if (!acp_sw_pad_keeper_en) { + writel(adata->acp_sw_pad_keeper_en, adata->acp63_base + ACP_SW0_PAD_KEEPER_EN); + writel(adata->acp_pad_pulldown_ctrl, adata->acp63_base + ACP_PAD_PULLDOWN_CTRL); + } return ret; } @@ -408,6 +417,8 @@ static int __maybe_unused snd_acp70_suspend(struct device *dev) adata = dev_get_drvdata(dev); if (adata->is_sdw_dev) { + adata->acp_sw_pad_keeper_en = readl(adata->acp63_base + ACP_SW0_PAD_KEEPER_EN); + adata->acp_pad_pulldown_ctrl = readl(adata->acp63_base + ACP_PAD_PULLDOWN_CTRL); adata->sdw_en_stat = check_acp_sdw_enable_status(adata); if (adata->sdw_en_stat) { writel(1, adata->acp63_base + ACP_ZSC_DSP_CTRL); @@ -445,6 +456,7 @@ static int __maybe_unused snd_acp70_runtime_resume(struct device *dev) static int __maybe_unused snd_acp70_resume(struct device *dev) { struct acp63_dev_data *adata; + u32 acp_sw_pad_keeper_en; int ret; adata = dev_get_drvdata(dev); @@ -459,6 +471,12 @@ static int __maybe_unused snd_acp70_resume(struct device *dev) if (ret) dev_err(dev, "ACP init failed\n"); + acp_sw_pad_keeper_en = readl(adata->acp63_base + ACP_SW0_PAD_KEEPER_EN); + dev_dbg(dev, "ACP_SW0_PAD_KEEPER_EN:0x%x\n", acp_sw_pad_keeper_en); + if (!acp_sw_pad_keeper_en) { + writel(adata->acp_sw_pad_keeper_en, adata->acp63_base + ACP_SW0_PAD_KEEPER_EN); + writel(adata->acp_pad_pulldown_ctrl, adata->acp63_base + ACP_PAD_PULLDOWN_CTRL); + } return ret; } diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c index 98022e5fd428..97e340140d0c 100644 --- a/sound/soc/amd/yc/acp6x-mach.c +++ b/sound/soc/amd/yc/acp6x-mach.c @@ -356,6 +356,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { { .driver_data = &acp6x_card, .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "RB"), + DMI_MATCH(DMI_PRODUCT_NAME, "Nitro ANV15-41"), + } + }, + { + .driver_data = &acp6x_card, + .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), DMI_MATCH(DMI_PRODUCT_NAME, "83J2"), } @@ -363,6 +370,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { { .driver_data = &acp6x_card, .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "83J3"), + } + }, + { + .driver_data = &acp6x_card, + .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC."), DMI_MATCH(DMI_PRODUCT_NAME, "UM5302TA"), } diff --git a/sound/soc/codecs/rt721-sdca.c b/sound/soc/codecs/rt721-sdca.c index 1c9f32e405cf..ba080957e933 100644 --- a/sound/soc/codecs/rt721-sdca.c +++ b/sound/soc/codecs/rt721-sdca.c @@ -430,6 +430,7 @@ static int rt721_sdca_set_gain_get(struct snd_kcontrol *kcontrol, unsigned int read_l, read_r, ctl_l = 0, ctl_r = 0; unsigned int adc_vol_flag = 0; const unsigned int interval_offset = 0xc0; + const unsigned int tendA = 0x200; const unsigned int tendB = 0xa00; if (strstr(ucontrol->id.name, "FU1E Capture Volume") || @@ -439,9 +440,16 @@ static int rt721_sdca_set_gain_get(struct snd_kcontrol *kcontrol, regmap_read(rt721->mbq_regmap, mc->reg, &read_l); regmap_read(rt721->mbq_regmap, mc->rreg, &read_r); - if (mc->shift == 8) /* boost gain */ + if (mc->shift == 8) { + /* boost gain */ ctl_l = read_l / tendB; - else { + } else if (mc->shift == 1) { + /* FU33 boost gain */ + if (read_l == 0x8000 || read_l == 0xfe00) + ctl_l = 0; + else + ctl_l = read_l / tendA + 1; + } else { if (adc_vol_flag) ctl_l = mc->max - (((0x1e00 - read_l) & 0xffff) / interval_offset); else @@ -449,9 +457,16 @@ static int rt721_sdca_set_gain_get(struct snd_kcontrol *kcontrol, } if (read_l != read_r) { - if (mc->shift == 8) /* boost gain */ + if (mc->shift == 8) { + /* boost gain */ ctl_r = read_r / tendB; - else { /* ADC/DAC gain */ + } else if (mc->shift == 1) { + /* FU33 boost gain */ + if (read_r == 0x8000 || read_r == 0xfe00) + ctl_r = 0; + else + ctl_r = read_r / tendA + 1; + } else { /* ADC/DAC gain */ if (adc_vol_flag) ctl_r = mc->max - (((0x1e00 - read_r) & 0xffff) / interval_offset); else diff --git a/sound/soc/qcom/Kconfig b/sound/soc/qcom/Kconfig index e86b4a03dd61..3d9ba13ee1e5 100644 --- a/sound/soc/qcom/Kconfig +++ b/sound/soc/qcom/Kconfig @@ -186,6 +186,7 @@ config SND_SOC_SM8250 tristate "SoC Machine driver for SM8250 boards" depends on QCOM_APR && SOUNDWIRE depends on COMMON_CLK + depends on SND_SOC_QCOM_OFFLOAD_UTILS || !SND_SOC_QCOM_OFFLOAD_UTILS select SND_SOC_QDSP6 select SND_SOC_QCOM_COMMON select SND_SOC_QCOM_SDW diff --git a/sound/soc/sof/intel/hda.c b/sound/soc/sof/intel/hda.c index bdfe388da198..3b47191ea7a5 100644 --- a/sound/soc/sof/intel/hda.c +++ b/sound/soc/sof/intel/hda.c @@ -1257,11 +1257,11 @@ static int check_tplg_quirk_mask(struct snd_soc_acpi_mach *mach) return 0; } -static char *remove_file_ext(const char *tplg_filename) +static char *remove_file_ext(struct device *dev, const char *tplg_filename) { char *filename, *tmp; - filename = kstrdup(tplg_filename, GFP_KERNEL); + filename = devm_kstrdup(dev, tplg_filename, GFP_KERNEL); if (!filename) return NULL; @@ -1345,7 +1345,7 @@ struct snd_soc_acpi_mach *hda_machine_select(struct snd_sof_dev *sdev) */ if (!sof_pdata->tplg_filename) { /* remove file extension if it exists */ - tplg_filename = remove_file_ext(mach->sof_tplg_filename); + tplg_filename = remove_file_ext(sdev->dev, mach->sof_tplg_filename); if (!tplg_filename) return NULL; diff --git a/sound/usb/qcom/qc_audio_offload.c b/sound/usb/qcom/qc_audio_offload.c index 5bc27c82e0af..3543b5a53592 100644 --- a/sound/usb/qcom/qc_audio_offload.c +++ b/sound/usb/qcom/qc_audio_offload.c @@ -759,7 +759,7 @@ static void qmi_stop_session(void) subs = find_substream(pcm_card_num, info->pcm_dev_num, info->direction); if (!subs || !chip || atomic_read(&chip->shutdown)) { - dev_err(&subs->dev->dev, + dev_err(&uadev[idx].udev->dev, "no sub for c#%u dev#%u dir%u\n", info->pcm_card_num, info->pcm_dev_num, @@ -1360,20 +1360,21 @@ static int prepare_qmi_response(struct snd_usb_substream *subs, if (!uadev[card_num].ctrl_intf) { dev_err(&subs->dev->dev, "audio ctrl intf info not cached\n"); - ret = -ENODEV; - goto err; + return -ENODEV; } ret = uaudio_populate_uac_desc(subs, resp); if (ret < 0) - goto err; + return ret; resp->slot_id = subs->dev->slot_id; resp->slot_id_valid = 1; data = snd_soc_usb_find_priv_data(uaudio_qdev->auxdev->dev.parent); - if (!data) - goto err; + if (!data) { + dev_err(&subs->dev->dev, "No private data found\n"); + return -ENODEV; + } uaudio_qdev->data = data; @@ -1382,7 +1383,7 @@ static int prepare_qmi_response(struct snd_usb_substream *subs, &resp->xhci_mem_info.tr_data, &resp->std_as_data_ep_desc); if (ret < 0) - goto err; + return ret; resp->std_as_data_ep_desc_valid = 1; @@ -1500,7 +1501,6 @@ drop_data_ep: xhci_sideband_remove_endpoint(uadev[card_num].sb, usb_pipe_endpoint(subs->dev, subs->data_endpoint->pipe)); -err: return ret; } diff --git a/sound/usb/stream.c b/sound/usb/stream.c index c1ea8844a46f..aa91d63749f2 100644 --- a/sound/usb/stream.c +++ b/sound/usb/stream.c @@ -987,6 +987,8 @@ snd_usb_get_audioformat_uac3(struct snd_usb_audio *chip, * and request Cluster Descriptor */ wLength = le16_to_cpu(hc_header.wLength); + if (wLength < sizeof(cluster)) + return NULL; cluster = kzalloc(wLength, GFP_KERNEL); if (!cluster) return ERR_PTR(-ENOMEM); diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c index 460c3e57fadb..0381f209920a 100644 --- a/tools/lib/bpf/btf_dump.c +++ b/tools/lib/bpf/btf_dump.c @@ -226,6 +226,9 @@ static void btf_dump_free_names(struct hashmap *map) size_t bkt; struct hashmap_entry *cur; + if (!map) + return; + hashmap__for_each_entry(map, cur, bkt) free((void *)cur->pkey); diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index e9c641a2fb20..52e353368f58 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -597,7 +597,7 @@ struct extern_desc { int sym_idx; int btf_id; int sec_btf_id; - const char *name; + char *name; char *essent_name; bool is_set; bool is_weak; @@ -4259,7 +4259,9 @@ static int bpf_object__collect_externs(struct bpf_object *obj) return ext->btf_id; } t = btf__type_by_id(obj->btf, ext->btf_id); - ext->name = btf__name_by_offset(obj->btf, t->name_off); + ext->name = strdup(btf__name_by_offset(obj->btf, t->name_off)); + if (!ext->name) + return -ENOMEM; ext->sym_idx = i; ext->is_weak = ELF64_ST_BIND(sym->st_info) == STB_WEAK; @@ -9138,8 +9140,10 @@ void bpf_object__close(struct bpf_object *obj) zfree(&obj->btf_custom_path); zfree(&obj->kconfig); - for (i = 0; i < obj->nr_extern; i++) + for (i = 0; i < obj->nr_extern; i++) { + zfree(&obj->externs[i].name); zfree(&obj->externs[i].essent_name); + } zfree(&obj->externs); obj->nr_extern = 0; diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore index e2a2c46c008b..3d8378972d26 100644 --- a/tools/testing/selftests/bpf/.gitignore +++ b/tools/testing/selftests/bpf/.gitignore @@ -21,7 +21,6 @@ test_lirc_mode2_user flow_dissector_load test_tcpnotify_user test_libbpf -test_sysctl xdping test_cpp *.d diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index cf5ed3bee573..910d8d6402ef 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -73,7 +73,7 @@ endif # Order correspond to 'make run_tests' order TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_progs \ test_sockmap \ - test_tcpnotify_user test_sysctl \ + test_tcpnotify_user \ test_progs-no_alu32 TEST_INST_SUBDIRS := no_alu32 @@ -220,7 +220,7 @@ ifeq ($(VMLINUX_BTF),) $(error Cannot find a vmlinux for VMLINUX_BTF at any of "$(VMLINUX_BTF_PATHS)") endif -# Define simple and short `make test_progs`, `make test_sysctl`, etc targets +# Define simple and short `make test_progs`, `make test_maps`, etc targets # to build individual tests. # NOTE: Semicolon at the end is critical to override lib.mk's default static # rule for binaries. @@ -329,7 +329,6 @@ NETWORK_HELPERS := $(OUTPUT)/network_helpers.o $(OUTPUT)/test_sockmap: $(CGROUP_HELPERS) $(TESTING_HELPERS) $(OUTPUT)/test_tcpnotify_user: $(CGROUP_HELPERS) $(TESTING_HELPERS) $(TRACE_HELPERS) $(OUTPUT)/test_sock_fields: $(CGROUP_HELPERS) $(TESTING_HELPERS) -$(OUTPUT)/test_sysctl: $(CGROUP_HELPERS) $(TESTING_HELPERS) $(OUTPUT)/test_tag: $(TESTING_HELPERS) $(OUTPUT)/test_lirc_mode2_user: $(TESTING_HELPERS) $(OUTPUT)/xdping: $(TESTING_HELPERS) diff --git a/tools/testing/selftests/bpf/test_sysctl.c b/tools/testing/selftests/bpf/prog_tests/test_sysctl.c index bcdbd27f22f0..273dd41ca09e 100644 --- a/tools/testing/selftests/bpf/test_sysctl.c +++ b/tools/testing/selftests/bpf/prog_tests/test_sysctl.c @@ -1,22 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2019 Facebook -#include <fcntl.h> -#include <stdint.h> -#include <stdio.h> -#include <stdlib.h> -#include <string.h> -#include <unistd.h> - -#include <linux/filter.h> - -#include <bpf/bpf.h> -#include <bpf/libbpf.h> - -#include <bpf/bpf_endian.h> -#include "bpf_util.h" +#include "test_progs.h" #include "cgroup_helpers.h" -#include "testing_helpers.h" #define CG_PATH "/foo" #define MAX_INSNS 512 @@ -1608,26 +1594,19 @@ static int run_tests(int cgfd) return fails ? -1 : 0; } -int main(int argc, char **argv) +void test_sysctl(void) { - int cgfd = -1; - int err = 0; + int cgfd; cgfd = cgroup_setup_and_join(CG_PATH); - if (cgfd < 0) - goto err; + if (!ASSERT_OK_FD(cgfd < 0, "create_cgroup")) + goto out; - /* Use libbpf 1.0 API mode */ - libbpf_set_strict_mode(LIBBPF_STRICT_ALL); + if (!ASSERT_OK(run_tests(cgfd), "run_tests")) + goto out; - if (run_tests(cgfd)) - goto err; - - goto out; -err: - err = -1; out: close(cgfd); cleanup_cgroup_environment(); - return err; + return; } diff --git a/tools/testing/selftests/bpf/progs/test_global_map_resize.c b/tools/testing/selftests/bpf/progs/test_global_map_resize.c index a3f220ba7025..ee65bad0436d 100644 --- a/tools/testing/selftests/bpf/progs/test_global_map_resize.c +++ b/tools/testing/selftests/bpf/progs/test_global_map_resize.c @@ -32,6 +32,16 @@ int my_int_last SEC(".data.array_not_last"); int percpu_arr[1] SEC(".data.percpu_arr"); +/* at least one extern is included, to ensure that a specific + * regression is tested whereby resizing resulted in a free-after-use + * bug after type information is invalidated by the resize operation. + * + * There isn't a particularly good API to test for this specific condition, + * but by having externs for the resizing tests it will cover this path. + */ +extern int LINUX_KERNEL_VERSION __kconfig; +long version_sink; + SEC("tp/syscalls/sys_enter_getpid") int bss_array_sum(void *ctx) { @@ -44,6 +54,9 @@ int bss_array_sum(void *ctx) for (size_t i = 0; i < bss_array_len; ++i) sum += array[i]; + /* see above; ensure this is not optimized out */ + version_sink = LINUX_KERNEL_VERSION; + return 0; } @@ -59,6 +72,9 @@ int data_array_sum(void *ctx) for (size_t i = 0; i < data_array_len; ++i) sum += my_array[i]; + /* see above; ensure this is not optimized out */ + version_sink = LINUX_KERNEL_VERSION; + return 0; } diff --git a/tools/testing/selftests/bpf/progs/verifier_vfs_accept.c b/tools/testing/selftests/bpf/progs/verifier_vfs_accept.c index a7c0a553aa50..3e2d76ee8050 100644 --- a/tools/testing/selftests/bpf/progs/verifier_vfs_accept.c +++ b/tools/testing/selftests/bpf/progs/verifier_vfs_accept.c @@ -2,6 +2,7 @@ /* Copyright (c) 2024 Google LLC. */ #include <vmlinux.h> +#include <errno.h> #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> @@ -82,4 +83,21 @@ int BPF_PROG(path_d_path_from_file_argument, struct file *file) return 0; } +SEC("lsm.s/inode_rename") +__success +int BPF_PROG(inode_rename, struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry, + unsigned int flags) +{ + struct inode *inode = new_dentry->d_inode; + ino_t ino; + + if (!inode) + return 0; + ino = inode->i_ino; + if (ino == 0) + return -EACCES; + return 0; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_vfs_reject.c b/tools/testing/selftests/bpf/progs/verifier_vfs_reject.c index d6d3f4fcb24c..4b392c6c8fc4 100644 --- a/tools/testing/selftests/bpf/progs/verifier_vfs_reject.c +++ b/tools/testing/selftests/bpf/progs/verifier_vfs_reject.c @@ -2,6 +2,7 @@ /* Copyright (c) 2024 Google LLC. */ #include <vmlinux.h> +#include <errno.h> #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> #include <linux/limits.h> @@ -158,4 +159,18 @@ int BPF_PROG(path_d_path_kfunc_non_lsm, struct path *path, struct file *f) return 0; } +SEC("lsm.s/inode_rename") +__failure __msg("invalid mem access 'trusted_ptr_or_null_'") +int BPF_PROG(inode_rename, struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry, + unsigned int flags) +{ + struct inode *inode = new_dentry->d_inode; + ino_t ino; + + ino = inode->i_ino; + if (ino == 0) + return -EACCES; + return 0; +} char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_lru_map.c b/tools/testing/selftests/bpf/test_lru_map.c index fda7589c5023..0921939532c6 100644 --- a/tools/testing/selftests/bpf/test_lru_map.c +++ b/tools/testing/selftests/bpf/test_lru_map.c @@ -138,6 +138,18 @@ static int sched_next_online(int pid, int *next_to_try) return ret; } +/* Derive target_free from map_size, same as bpf_common_lru_populate */ +static unsigned int __tgt_size(unsigned int map_size) +{ + return (map_size / nr_cpus) / 2; +} + +/* Inverse of how bpf_common_lru_populate derives target_free from map_size. */ +static unsigned int __map_size(unsigned int tgt_free) +{ + return tgt_free * nr_cpus * 2; +} + /* Size of the LRU map is 2 * Add key=1 (+1 key) * Add key=2 (+1 key) @@ -231,11 +243,11 @@ static void test_lru_sanity0(int map_type, int map_flags) printf("Pass\n"); } -/* Size of the LRU map is 1.5*tgt_free - * Insert 1 to tgt_free (+tgt_free keys) - * Lookup 1 to tgt_free/2 - * Insert 1+tgt_free to 2*tgt_free (+tgt_free keys) - * => 1+tgt_free/2 to LOCALFREE_TARGET will be removed by LRU +/* Verify that unreferenced elements are recycled before referenced ones. + * Insert elements. + * Reference a subset of these. + * Insert more, enough to trigger recycling. + * Verify that unreferenced are recycled. */ static void test_lru_sanity1(int map_type, int map_flags, unsigned int tgt_free) { @@ -257,7 +269,7 @@ static void test_lru_sanity1(int map_type, int map_flags, unsigned int tgt_free) batch_size = tgt_free / 2; assert(batch_size * 2 == tgt_free); - map_size = tgt_free + batch_size; + map_size = __map_size(tgt_free) + batch_size; lru_map_fd = create_map(map_type, map_flags, map_size); assert(lru_map_fd != -1); @@ -266,13 +278,13 @@ static void test_lru_sanity1(int map_type, int map_flags, unsigned int tgt_free) value[0] = 1234; - /* Insert 1 to tgt_free (+tgt_free keys) */ - end_key = 1 + tgt_free; + /* Insert map_size - batch_size keys */ + end_key = 1 + __map_size(tgt_free); for (key = 1; key < end_key; key++) assert(!bpf_map_update_elem(lru_map_fd, &key, value, BPF_NOEXIST)); - /* Lookup 1 to tgt_free/2 */ + /* Lookup 1 to batch_size */ end_key = 1 + batch_size; for (key = 1; key < end_key; key++) { assert(!bpf_map_lookup_elem_with_ref_bit(lru_map_fd, key, value)); @@ -280,12 +292,13 @@ static void test_lru_sanity1(int map_type, int map_flags, unsigned int tgt_free) BPF_NOEXIST)); } - /* Insert 1+tgt_free to 2*tgt_free - * => 1+tgt_free/2 to LOCALFREE_TARGET will be + /* Insert another map_size - batch_size keys + * Map will contain 1 to batch_size plus these latest, i.e., + * => previous 1+batch_size to map_size - batch_size will have been * removed by LRU */ - key = 1 + tgt_free; - end_key = key + tgt_free; + key = 1 + __map_size(tgt_free); + end_key = key + __map_size(tgt_free); for (; key < end_key; key++) { assert(!bpf_map_update_elem(lru_map_fd, &key, value, BPF_NOEXIST)); @@ -301,17 +314,8 @@ static void test_lru_sanity1(int map_type, int map_flags, unsigned int tgt_free) printf("Pass\n"); } -/* Size of the LRU map 1.5 * tgt_free - * Insert 1 to tgt_free (+tgt_free keys) - * Update 1 to tgt_free/2 - * => The original 1 to tgt_free/2 will be removed due to - * the LRU shrink process - * Re-insert 1 to tgt_free/2 again and do a lookup immeidately - * Insert 1+tgt_free to tgt_free*3/2 - * Insert 1+tgt_free*3/2 to tgt_free*5/2 - * => Key 1+tgt_free to tgt_free*3/2 - * will be removed from LRU because it has never - * been lookup and ref bit is not set +/* Verify that insertions exceeding map size will recycle the oldest. + * Verify that unreferenced elements are recycled before referenced. */ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free) { @@ -334,7 +338,7 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free) batch_size = tgt_free / 2; assert(batch_size * 2 == tgt_free); - map_size = tgt_free + batch_size; + map_size = __map_size(tgt_free) + batch_size; lru_map_fd = create_map(map_type, map_flags, map_size); assert(lru_map_fd != -1); @@ -343,8 +347,8 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free) value[0] = 1234; - /* Insert 1 to tgt_free (+tgt_free keys) */ - end_key = 1 + tgt_free; + /* Insert map_size - batch_size keys */ + end_key = 1 + __map_size(tgt_free); for (key = 1; key < end_key; key++) assert(!bpf_map_update_elem(lru_map_fd, &key, value, BPF_NOEXIST)); @@ -357,8 +361,7 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free) * shrink the inactive list to get tgt_free * number of free nodes. * - * Hence, the oldest key 1 to tgt_free/2 - * are removed from the LRU list. + * Hence, the oldest key is removed from the LRU list. */ key = 1; if (map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) { @@ -370,8 +373,7 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free) BPF_EXIST)); } - /* Re-insert 1 to tgt_free/2 again and do a lookup - * immeidately. + /* Re-insert 1 to batch_size again and do a lookup immediately. */ end_key = 1 + batch_size; value[0] = 4321; @@ -387,17 +389,18 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free) value[0] = 1234; - /* Insert 1+tgt_free to tgt_free*3/2 */ - end_key = 1 + tgt_free + batch_size; - for (key = 1 + tgt_free; key < end_key; key++) + /* Insert batch_size new elements */ + key = 1 + __map_size(tgt_free); + end_key = key + batch_size; + for (; key < end_key; key++) /* These newly added but not referenced keys will be * gone during the next LRU shrink. */ assert(!bpf_map_update_elem(lru_map_fd, &key, value, BPF_NOEXIST)); - /* Insert 1+tgt_free*3/2 to tgt_free*5/2 */ - end_key = key + tgt_free; + /* Insert map_size - batch_size elements */ + end_key += __map_size(tgt_free); for (; key < end_key; key++) { assert(!bpf_map_update_elem(lru_map_fd, &key, value, BPF_NOEXIST)); @@ -413,12 +416,12 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free) printf("Pass\n"); } -/* Size of the LRU map is 2*tgt_free - * It is to test the active/inactive list rotation - * Insert 1 to 2*tgt_free (+2*tgt_free keys) - * Lookup key 1 to tgt_free*3/2 - * Add 1+2*tgt_free to tgt_free*5/2 (+tgt_free/2 keys) - * => key 1+tgt_free*3/2 to 2*tgt_free are removed from LRU +/* Test the active/inactive list rotation + * + * Fill the whole map, deplete the free list. + * Reference all except the last lru->target_free elements. + * Insert lru->target_free new elements. This triggers one shrink. + * Verify that the non-referenced elements are replaced. */ static void test_lru_sanity3(int map_type, int map_flags, unsigned int tgt_free) { @@ -437,8 +440,7 @@ static void test_lru_sanity3(int map_type, int map_flags, unsigned int tgt_free) assert(sched_next_online(0, &next_cpu) != -1); - batch_size = tgt_free / 2; - assert(batch_size * 2 == tgt_free); + batch_size = __tgt_size(tgt_free); map_size = tgt_free * 2; lru_map_fd = create_map(map_type, map_flags, map_size); @@ -449,23 +451,21 @@ static void test_lru_sanity3(int map_type, int map_flags, unsigned int tgt_free) value[0] = 1234; - /* Insert 1 to 2*tgt_free (+2*tgt_free keys) */ - end_key = 1 + (2 * tgt_free); + /* Fill the map */ + end_key = 1 + map_size; for (key = 1; key < end_key; key++) assert(!bpf_map_update_elem(lru_map_fd, &key, value, BPF_NOEXIST)); - /* Lookup key 1 to tgt_free*3/2 */ - end_key = tgt_free + batch_size; + /* Reference all but the last batch_size */ + end_key = 1 + map_size - batch_size; for (key = 1; key < end_key; key++) { assert(!bpf_map_lookup_elem_with_ref_bit(lru_map_fd, key, value)); assert(!bpf_map_update_elem(expected_map_fd, &key, value, BPF_NOEXIST)); } - /* Add 1+2*tgt_free to tgt_free*5/2 - * (+tgt_free/2 keys) - */ + /* Insert new batch_size: replaces the non-referenced elements */ key = 2 * tgt_free + 1; end_key = key + batch_size; for (; key < end_key; key++) { @@ -500,7 +500,8 @@ static void test_lru_sanity4(int map_type, int map_flags, unsigned int tgt_free) lru_map_fd = create_map(map_type, map_flags, 3 * tgt_free * nr_cpus); else - lru_map_fd = create_map(map_type, map_flags, 3 * tgt_free); + lru_map_fd = create_map(map_type, map_flags, + 3 * __map_size(tgt_free)); assert(lru_map_fd != -1); expected_map_fd = create_map(BPF_MAP_TYPE_HASH, 0, diff --git a/tools/testing/selftests/drivers/net/hw/rss_input_xfrm.py b/tools/testing/selftests/drivers/net/hw/rss_input_xfrm.py index f439c434ba36..648ff50bc1c3 100755 --- a/tools/testing/selftests/drivers/net/hw/rss_input_xfrm.py +++ b/tools/testing/selftests/drivers/net/hw/rss_input_xfrm.py @@ -38,7 +38,7 @@ def test_rss_input_xfrm(cfg, ipver): raise KsftSkipEx("socket.SO_INCOMING_CPU was added in Python 3.11") input_xfrm = cfg.ethnl.rss_get( - {'header': {'dev-name': cfg.ifname}}).get('input_xfrm') + {'header': {'dev-name': cfg.ifname}}).get('input-xfrm') # Check for symmetric xor/or-xor if not input_xfrm or (input_xfrm != 1 and input_xfrm != 2): diff --git a/tools/testing/selftests/mm/config b/tools/testing/selftests/mm/config index a28baa536332..deba93379c80 100644 --- a/tools/testing/selftests/mm/config +++ b/tools/testing/selftests/mm/config @@ -8,3 +8,6 @@ CONFIG_GUP_TEST=y CONFIG_TRANSPARENT_HUGEPAGE=y CONFIG_MEM_SOFT_DIRTY=y CONFIG_ANON_VMA_NAME=y +CONFIG_FTRACE=y +CONFIG_PROFILING=y +CONFIG_UPROBES=y diff --git a/tools/testing/selftests/mm/merge.c b/tools/testing/selftests/mm/merge.c index bbae66fc5038..cc26480098ae 100644 --- a/tools/testing/selftests/mm/merge.c +++ b/tools/testing/selftests/mm/merge.c @@ -470,7 +470,9 @@ TEST_F(merge, handle_uprobe_upon_merged_vma) ASSERT_GE(fd, 0); ASSERT_EQ(ftruncate(fd, page_size), 0); - ASSERT_EQ(read_sysfs("/sys/bus/event_source/devices/uprobe/type", &type), 0); + if (read_sysfs("/sys/bus/event_source/devices/uprobe/type", &type) != 0) { + SKIP(goto out, "Failed to read uprobe sysfs file, skipping"); + } memset(&attr, 0, attr_sz); attr.size = attr_sz; @@ -491,6 +493,7 @@ TEST_F(merge, handle_uprobe_upon_merged_vma) ASSERT_NE(mremap(ptr2, page_size, page_size, MREMAP_MAYMOVE | MREMAP_FIXED, ptr1), MAP_FAILED); +out: close(fd); remove(probe_file); } diff --git a/tools/testing/selftests/mm/settings b/tools/testing/selftests/mm/settings index a953c96aa16e..e2206265f67c 100644 --- a/tools/testing/selftests/mm/settings +++ b/tools/testing/selftests/mm/settings @@ -1 +1 @@ -timeout=180 +timeout=900 diff --git a/tools/testing/selftests/mm/virtual_address_range.c b/tools/testing/selftests/mm/virtual_address_range.c index b380e102b22f..169dbd692bf5 100644 --- a/tools/testing/selftests/mm/virtual_address_range.c +++ b/tools/testing/selftests/mm/virtual_address_range.c @@ -77,8 +77,11 @@ static void validate_addr(char *ptr, int high_addr) { unsigned long addr = (unsigned long) ptr; - if (high_addr && addr < HIGH_ADDR_MARK) - ksft_exit_fail_msg("Bad address %lx\n", addr); + if (high_addr) { + if (addr < HIGH_ADDR_MARK) + ksft_exit_fail_msg("Bad address %lx\n", addr); + return; + } if (addr > HIGH_ADDR_MARK) ksft_exit_fail_msg("Bad address %lx\n", addr); diff --git a/tools/testing/selftests/net/af_unix/msg_oob.c b/tools/testing/selftests/net/af_unix/msg_oob.c index 3ed3882a93b8..b5f474969917 100644 --- a/tools/testing/selftests/net/af_unix/msg_oob.c +++ b/tools/testing/selftests/net/af_unix/msg_oob.c @@ -210,7 +210,7 @@ static void __sendpair(struct __test_metadata *_metadata, static void __recvpair(struct __test_metadata *_metadata, FIXTURE_DATA(msg_oob) *self, const char *expected_buf, int expected_len, - int buf_len, int flags) + int buf_len, int flags, bool is_sender) { int i, ret[2], recv_errno[2], expected_errno = 0; char recv_buf[2][BUF_SZ] = {}; @@ -221,7 +221,9 @@ static void __recvpair(struct __test_metadata *_metadata, errno = 0; for (i = 0; i < 2; i++) { - ret[i] = recv(self->fd[i * 2 + 1], recv_buf[i], buf_len, flags); + int index = is_sender ? i * 2 : i * 2 + 1; + + ret[i] = recv(self->fd[index], recv_buf[i], buf_len, flags); recv_errno[i] = errno; } @@ -308,6 +310,20 @@ static void __siocatmarkpair(struct __test_metadata *_metadata, ASSERT_EQ(answ[0], answ[1]); } +static void __resetpair(struct __test_metadata *_metadata, + FIXTURE_DATA(msg_oob) *self, + const FIXTURE_VARIANT(msg_oob) *variant, + bool reset) +{ + int i; + + for (i = 0; i < 2; i++) + close(self->fd[i * 2 + 1]); + + __recvpair(_metadata, self, "", reset ? -ECONNRESET : 0, 1, + variant->peek ? MSG_PEEK : 0, true); +} + #define sendpair(buf, len, flags) \ __sendpair(_metadata, self, buf, len, flags) @@ -316,9 +332,10 @@ static void __siocatmarkpair(struct __test_metadata *_metadata, if (variant->peek) \ __recvpair(_metadata, self, \ expected_buf, expected_len, \ - buf_len, (flags) | MSG_PEEK); \ + buf_len, (flags) | MSG_PEEK, false); \ __recvpair(_metadata, self, \ - expected_buf, expected_len, buf_len, flags); \ + expected_buf, expected_len, \ + buf_len, flags, false); \ } while (0) #define epollpair(oob_remaining) \ @@ -330,6 +347,9 @@ static void __siocatmarkpair(struct __test_metadata *_metadata, #define setinlinepair() \ __setinlinepair(_metadata, self) +#define resetpair(reset) \ + __resetpair(_metadata, self, variant, reset) + #define tcp_incompliant \ for (self->tcp_compliant = false; \ self->tcp_compliant == false; \ @@ -344,6 +364,21 @@ TEST_F(msg_oob, non_oob) recvpair("", -EINVAL, 1, MSG_OOB); epollpair(false); siocatmarkpair(false); + + resetpair(true); +} + +TEST_F(msg_oob, non_oob_no_reset) +{ + sendpair("x", 1, 0); + epollpair(false); + siocatmarkpair(false); + + recvpair("x", 1, 1, 0); + epollpair(false); + siocatmarkpair(false); + + resetpair(false); } TEST_F(msg_oob, oob) @@ -355,6 +390,19 @@ TEST_F(msg_oob, oob) recvpair("x", 1, 1, MSG_OOB); epollpair(false); siocatmarkpair(true); + + tcp_incompliant { + resetpair(false); /* TCP sets -ECONNRESET for ex-OOB. */ + } +} + +TEST_F(msg_oob, oob_reset) +{ + sendpair("x", 1, MSG_OOB); + epollpair(true); + siocatmarkpair(true); + + resetpair(true); } TEST_F(msg_oob, oob_drop) @@ -370,6 +418,8 @@ TEST_F(msg_oob, oob_drop) recvpair("", -EINVAL, 1, MSG_OOB); epollpair(false); siocatmarkpair(false); + + resetpair(false); } TEST_F(msg_oob, oob_ahead) @@ -385,6 +435,10 @@ TEST_F(msg_oob, oob_ahead) recvpair("hell", 4, 4, 0); epollpair(false); siocatmarkpair(true); + + tcp_incompliant { + resetpair(false); /* TCP sets -ECONNRESET for ex-OOB. */ + } } TEST_F(msg_oob, oob_break) @@ -403,6 +457,8 @@ TEST_F(msg_oob, oob_break) recvpair("", -EAGAIN, 1, 0); siocatmarkpair(false); + + resetpair(false); } TEST_F(msg_oob, oob_ahead_break) @@ -426,6 +482,8 @@ TEST_F(msg_oob, oob_ahead_break) recvpair("world", 5, 5, 0); epollpair(false); siocatmarkpair(false); + + resetpair(false); } TEST_F(msg_oob, oob_break_drop) @@ -449,6 +507,8 @@ TEST_F(msg_oob, oob_break_drop) recvpair("", -EINVAL, 1, MSG_OOB); epollpair(false); siocatmarkpair(false); + + resetpair(false); } TEST_F(msg_oob, ex_oob_break) @@ -476,6 +536,8 @@ TEST_F(msg_oob, ex_oob_break) recvpair("ld", 2, 2, 0); epollpair(false); siocatmarkpair(false); + + resetpair(false); } TEST_F(msg_oob, ex_oob_drop) @@ -498,6 +560,8 @@ TEST_F(msg_oob, ex_oob_drop) epollpair(false); siocatmarkpair(true); } + + resetpair(false); } TEST_F(msg_oob, ex_oob_drop_2) @@ -523,6 +587,8 @@ TEST_F(msg_oob, ex_oob_drop_2) epollpair(false); siocatmarkpair(true); } + + resetpair(false); } TEST_F(msg_oob, ex_oob_oob) @@ -546,6 +612,54 @@ TEST_F(msg_oob, ex_oob_oob) recvpair("", -EINVAL, 1, MSG_OOB); epollpair(false); siocatmarkpair(false); + + resetpair(false); +} + +TEST_F(msg_oob, ex_oob_ex_oob) +{ + sendpair("x", 1, MSG_OOB); + epollpair(true); + siocatmarkpair(true); + + recvpair("x", 1, 1, MSG_OOB); + epollpair(false); + siocatmarkpair(true); + + sendpair("y", 1, MSG_OOB); + epollpair(true); + siocatmarkpair(true); + + recvpair("y", 1, 1, MSG_OOB); + epollpair(false); + siocatmarkpair(true); + + tcp_incompliant { + resetpair(false); /* TCP sets -ECONNRESET for ex-OOB. */ + } +} + +TEST_F(msg_oob, ex_oob_ex_oob_oob) +{ + sendpair("x", 1, MSG_OOB); + epollpair(true); + siocatmarkpair(true); + + recvpair("x", 1, 1, MSG_OOB); + epollpair(false); + siocatmarkpair(true); + + sendpair("y", 1, MSG_OOB); + epollpair(true); + siocatmarkpair(true); + + recvpair("y", 1, 1, MSG_OOB); + epollpair(false); + siocatmarkpair(true); + + sendpair("z", 1, MSG_OOB); + epollpair(true); + siocatmarkpair(true); } TEST_F(msg_oob, ex_oob_ahead_break) @@ -576,6 +690,10 @@ TEST_F(msg_oob, ex_oob_ahead_break) recvpair("d", 1, 1, MSG_OOB); epollpair(false); siocatmarkpair(true); + + tcp_incompliant { + resetpair(false); /* TCP sets -ECONNRESET for ex-OOB. */ + } } TEST_F(msg_oob, ex_oob_siocatmark) @@ -595,6 +713,8 @@ TEST_F(msg_oob, ex_oob_siocatmark) recvpair("hell", 4, 4, 0); /* Intentionally stop at ex-OOB. */ epollpair(true); siocatmarkpair(false); + + resetpair(true); } TEST_F(msg_oob, inline_oob) @@ -612,6 +732,8 @@ TEST_F(msg_oob, inline_oob) recvpair("x", 1, 1, 0); epollpair(false); siocatmarkpair(false); + + resetpair(false); } TEST_F(msg_oob, inline_oob_break) @@ -633,6 +755,8 @@ TEST_F(msg_oob, inline_oob_break) recvpair("o", 1, 1, 0); epollpair(false); siocatmarkpair(false); + + resetpair(false); } TEST_F(msg_oob, inline_oob_ahead_break) @@ -661,6 +785,8 @@ TEST_F(msg_oob, inline_oob_ahead_break) epollpair(false); siocatmarkpair(false); + + resetpair(false); } TEST_F(msg_oob, inline_ex_oob_break) @@ -686,6 +812,8 @@ TEST_F(msg_oob, inline_ex_oob_break) recvpair("rld", 3, 3, 0); epollpair(false); siocatmarkpair(false); + + resetpair(false); } TEST_F(msg_oob, inline_ex_oob_no_drop) @@ -707,6 +835,8 @@ TEST_F(msg_oob, inline_ex_oob_no_drop) recvpair("y", 1, 1, 0); epollpair(false); siocatmarkpair(false); + + resetpair(false); } TEST_F(msg_oob, inline_ex_oob_drop) @@ -731,6 +861,8 @@ TEST_F(msg_oob, inline_ex_oob_drop) epollpair(false); siocatmarkpair(false); } + + resetpair(false); } TEST_F(msg_oob, inline_ex_oob_siocatmark) @@ -752,6 +884,8 @@ TEST_F(msg_oob, inline_ex_oob_siocatmark) recvpair("hell", 4, 4, 0); /* Intentionally stop at ex-OOB. */ epollpair(true); siocatmarkpair(false); + + resetpair(true); } TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/ublk/test_stress_03.sh b/tools/testing/selftests/ublk/test_stress_03.sh index 6eef282d569f..3ed4c9b2d8c0 100755 --- a/tools/testing/selftests/ublk/test_stress_03.sh +++ b/tools/testing/selftests/ublk/test_stress_03.sh @@ -32,22 +32,23 @@ _create_backfile 2 128M ublk_io_and_remove 8G -t null -q 4 -z & ublk_io_and_remove 256M -t loop -q 4 -z "${UBLK_BACKFILES[0]}" & ublk_io_and_remove 256M -t stripe -q 4 -z "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" & +wait if _have_feature "AUTO_BUF_REG"; then ublk_io_and_remove 8G -t null -q 4 --auto_zc & ublk_io_and_remove 256M -t loop -q 4 --auto_zc "${UBLK_BACKFILES[0]}" & ublk_io_and_remove 256M -t stripe -q 4 --auto_zc "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" & ublk_io_and_remove 8G -t null -q 4 -z --auto_zc --auto_zc_fallback & + wait fi -wait if _have_feature "PER_IO_DAEMON"; then ublk_io_and_remove 8G -t null -q 4 --auto_zc --nthreads 8 --per_io_tasks & ublk_io_and_remove 256M -t loop -q 4 --auto_zc --nthreads 8 --per_io_tasks "${UBLK_BACKFILES[0]}" & ublk_io_and_remove 256M -t stripe -q 4 --auto_zc --nthreads 8 --per_io_tasks "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" & ublk_io_and_remove 8G -t null -q 4 -z --auto_zc --auto_zc_fallback --nthreads 8 --per_io_tasks & + wait fi -wait _cleanup_test "stress" _show_result $TID $ERR_CODE |