diff options
866 files changed, 7000 insertions, 3709 deletions
diff --git a/Documentation/admin-guide/cifs/changes.rst b/Documentation/admin-guide/cifs/changes.rst index 3147bbae9c43..8c42c4de510b 100644 --- a/Documentation/admin-guide/cifs/changes.rst +++ b/Documentation/admin-guide/cifs/changes.rst @@ -5,5 +5,5 @@ Changes See https://wiki.samba.org/index.php/LinuxCIFSKernel for summary information about fixes/improvements to CIFS/SMB2/SMB3 support (changes to cifs.ko module) by kernel version (and cifs internal module version). -This may be easier to read than parsing the output of "git log fs/cifs" -by release. +This may be easier to read than parsing the output of +"git log fs/smb/client" by release. diff --git a/Documentation/admin-guide/cifs/usage.rst b/Documentation/admin-guide/cifs/usage.rst index 2e151cd8c2e4..5f936b4b6018 100644 --- a/Documentation/admin-guide/cifs/usage.rst +++ b/Documentation/admin-guide/cifs/usage.rst @@ -45,7 +45,7 @@ Installation instructions If you have built the CIFS vfs as module (successfully) simply type ``make modules_install`` (or if you prefer, manually copy the file to -the modules directory e.g. /lib/modules/2.4.10-4GB/kernel/fs/cifs/cifs.ko). +the modules directory e.g. /lib/modules/6.3.0-060300-generic/kernel/fs/smb/client/cifs.ko). If you have built the CIFS vfs into the kernel itself, follow the instructions for your distribution on how to install a new kernel (usually you @@ -66,15 +66,15 @@ If cifs is built as a module, then the size and number of network buffers and maximum number of simultaneous requests to one server can be configured. Changing these from their defaults is not recommended. By executing modinfo:: - modinfo kernel/fs/cifs/cifs.ko + modinfo <path to cifs.ko> -on kernel/fs/cifs/cifs.ko the list of configuration changes that can be made +on kernel/fs/smb/client/cifs.ko the list of configuration changes that can be made at module initialization time (by running insmod cifs.ko) can be seen. Recommendations =============== -To improve security the SMB2.1 dialect or later (usually will get SMB3) is now +To improve security the SMB2.1 dialect or later (usually will get SMB3.1.1) is now the new default. To use old dialects (e.g. to mount Windows XP) use "vers=1.0" on mount (or vers=2.0 for Windows Vista). Note that the CIFS (vers=1.0) is much older and less secure than the default dialect SMB3 which includes diff --git a/Documentation/admin-guide/quickly-build-trimmed-linux.rst b/Documentation/admin-guide/quickly-build-trimmed-linux.rst index ff4f4cc8522b..f08149bc53f8 100644 --- a/Documentation/admin-guide/quickly-build-trimmed-linux.rst +++ b/Documentation/admin-guide/quickly-build-trimmed-linux.rst @@ -215,12 +215,14 @@ again. reduce the compile time enormously, especially if you are running an universal kernel from a commodity Linux distribution. - There is a catch: the make target 'localmodconfig' will disable kernel - features you have not directly or indirectly through some program utilized - since you booted the system. You can reduce or nearly eliminate that risk by - using tricks outlined in the reference section; for quick testing purposes - that risk is often negligible, but it is an aspect you want to keep in mind - in case your kernel behaves oddly. + There is a catch: 'localmodconfig' is likely to disable kernel features you + did not use since you booted your Linux -- like drivers for currently + disconnected peripherals or a virtualization software not haven't used yet. + You can reduce or nearly eliminate that risk with tricks the reference + section outlines; but when building a kernel just for quick testing purposes + it is often negligible if such features are missing. But you should keep that + aspect in mind when using a kernel built with this make target, as it might + be the reason why something you only use occasionally stopped working. [:ref:`details<configuration>`] @@ -271,6 +273,9 @@ again. does nothing at all; in that case you have to manually install your kernel, as outlined in the reference section. + If you are running a immutable Linux distribution, check its documentation + and the web to find out how to install your own kernel there. + [:ref:`details<install>`] .. _another_sbs: @@ -291,29 +296,29 @@ again. version you care about, as git otherwise might retrieve the entire commit history:: - git fetch --shallow-exclude=v6.1 origin - - If you modified the sources (for example by applying a patch), you now need - to discard those modifications; that's because git otherwise will not be able - to switch to the sources of another version due to potential conflicting - changes:: - - git reset --hard + git fetch --shallow-exclude=v6.0 origin - Now checkout the version you are interested in, as explained above:: + Now switch to the version you are interested in -- but be aware the command + used here will discard any modifications you performed, as they would + conflict with the sources you want to checkout:: - git checkout --detach origin/master + git checkout --force --detach origin/master At this point you might want to patch the sources again or set/modify a build - tag, as explained earlier; afterwards adjust the build configuration to the - new codebase and build your next kernel:: + tag, as explained earlier. Afterwards adjust the build configuration to the + new codebase using olddefconfig, which will now adjust the configuration file + you prepared earlier using localmodconfig (~/linux/.config) for your next + kernel:: # reminder: if you want to apply patches, do it at this point # reminder: you might want to update your build tag at this point make olddefconfig + + Now build your kernel:: + make -j $(nproc --all) - Install the kernel as outlined above:: + Afterwards install the kernel as outlined above:: command -v installkernel && sudo make modules_install install @@ -584,11 +589,11 @@ versions and individual commits at hand at any time:: curl -L \ https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/clone.bundle \ -o linux-stable.git.bundle - git clone clone.bundle ~/linux/ + git clone linux-stable.git.bundle ~/linux/ rm linux-stable.git.bundle cd ~/linux/ - git remote set-url origin - https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git + git remote set-url origin \ + https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git git fetch origin git checkout --detach origin/master diff --git a/Documentation/cdrom/index.rst b/Documentation/cdrom/index.rst index e87a8785bc1a..e9b022d70939 100644 --- a/Documentation/cdrom/index.rst +++ b/Documentation/cdrom/index.rst @@ -1,8 +1,8 @@ .. SPDX-License-Identifier: GPL-2.0 -===== -cdrom -===== +====== +CD-ROM +====== .. toctree:: :maxdepth: 1 diff --git a/Documentation/devicetree/bindings/ata/ceva,ahci-1v84.yaml b/Documentation/devicetree/bindings/ata/ceva,ahci-1v84.yaml index 9b31f864e071..71364c6081ff 100644 --- a/Documentation/devicetree/bindings/ata/ceva,ahci-1v84.yaml +++ b/Documentation/devicetree/bindings/ata/ceva,ahci-1v84.yaml @@ -32,7 +32,7 @@ properties: maxItems: 1 iommus: - maxItems: 1 + maxItems: 4 power-domains: maxItems: 1 diff --git a/Documentation/devicetree/bindings/display/msm/dsi-controller-main.yaml b/Documentation/devicetree/bindings/display/msm/dsi-controller-main.yaml index e6c1ebfe8a32..130e16d025bc 100644 --- a/Documentation/devicetree/bindings/display/msm/dsi-controller-main.yaml +++ b/Documentation/devicetree/bindings/display/msm/dsi-controller-main.yaml @@ -82,6 +82,18 @@ properties: Indicates if the DSI controller is driving a panel which needs 2 DSI links. + qcom,master-dsi: + type: boolean + description: | + Indicates if the DSI controller is the master DSI controller when + qcom,dual-dsi-mode enabled. + + qcom,sync-dual-dsi: + type: boolean + description: | + Indicates if the DSI controller needs to sync the other DSI controller + with MIPI DCS commands when qcom,dual-dsi-mode enabled. + assigned-clocks: minItems: 2 maxItems: 4 diff --git a/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.yaml b/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.yaml index 92117261e1e1..39e64c7f6360 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.yaml +++ b/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.yaml @@ -166,6 +166,12 @@ properties: resets: maxItems: 1 + mediatek,broken-save-restore-fw: + type: boolean + description: + Asserts that the firmware on this device has issues saving and restoring + GICR registers when the GIC redistributors are powered off. + dependencies: mbi-ranges: [ msi-controller ] msi-controller: [ mbi-ranges ] diff --git a/Documentation/devicetree/bindings/sound/tas2562.yaml b/Documentation/devicetree/bindings/sound/tas2562.yaml index a5bb561bfcfb..31a3024ea789 100644 --- a/Documentation/devicetree/bindings/sound/tas2562.yaml +++ b/Documentation/devicetree/bindings/sound/tas2562.yaml @@ -55,7 +55,9 @@ properties: description: TDM TX current sense time slot. '#sound-dai-cells': - const: 1 + # The codec has a single DAI, the #sound-dai-cells=<1>; case is left in for backward + # compatibility but is deprecated. + enum: [0, 1] required: - compatible @@ -72,7 +74,7 @@ examples: codec: codec@4c { compatible = "ti,tas2562"; reg = <0x4c>; - #sound-dai-cells = <1>; + #sound-dai-cells = <0>; interrupt-parent = <&gpio1>; interrupts = <14>; shutdown-gpios = <&gpio1 15 0>; diff --git a/Documentation/devicetree/bindings/sound/tas2770.yaml b/Documentation/devicetree/bindings/sound/tas2770.yaml index 26088adb9dc2..8908bf1122e9 100644 --- a/Documentation/devicetree/bindings/sound/tas2770.yaml +++ b/Documentation/devicetree/bindings/sound/tas2770.yaml @@ -57,7 +57,9 @@ properties: - 1 # Falling edge '#sound-dai-cells': - const: 1 + # The codec has a single DAI, the #sound-dai-cells=<1>; case is left in for backward + # compatibility but is deprecated. + enum: [0, 1] required: - compatible @@ -74,7 +76,7 @@ examples: codec: codec@41 { compatible = "ti,tas2770"; reg = <0x41>; - #sound-dai-cells = <1>; + #sound-dai-cells = <0>; interrupt-parent = <&gpio1>; interrupts = <14>; reset-gpio = <&gpio1 15 0>; diff --git a/Documentation/devicetree/bindings/sound/tas27xx.yaml b/Documentation/devicetree/bindings/sound/tas27xx.yaml index 8cba01316855..a876545ec87d 100644 --- a/Documentation/devicetree/bindings/sound/tas27xx.yaml +++ b/Documentation/devicetree/bindings/sound/tas27xx.yaml @@ -50,7 +50,9 @@ properties: description: TDM TX voltage sense time slot. '#sound-dai-cells': - const: 1 + # The codec has a single DAI, the #sound-dai-cells=<1>; case is left in for backward + # compatibility but is deprecated. + enum: [0, 1] required: - compatible @@ -67,7 +69,7 @@ examples: codec: codec@38 { compatible = "ti,tas2764"; reg = <0x38>; - #sound-dai-cells = <1>; + #sound-dai-cells = <0>; interrupt-parent = <&gpio1>; interrupts = <14>; reset-gpios = <&gpio1 15 0>; diff --git a/Documentation/devicetree/bindings/sound/tlv320aic32x4.txt b/Documentation/devicetree/bindings/sound/tlv320aic32x4.txt index f59125bc79d1..0b4e21bde5bc 100644 --- a/Documentation/devicetree/bindings/sound/tlv320aic32x4.txt +++ b/Documentation/devicetree/bindings/sound/tlv320aic32x4.txt @@ -8,7 +8,7 @@ Required properties: "ti,tlv320aic32x6" TLV320AIC3206, TLV320AIC3256 "ti,tas2505" TAS2505, TAS2521 - reg: I2C slave address - - supply-*: Required supply regulators are: + - *-supply: Required supply regulators are: "iov" - digital IO power supply "ldoin" - LDO power supply "dv" - Digital core power supply diff --git a/Documentation/devicetree/bindings/usb/cdns,usb3.yaml b/Documentation/devicetree/bindings/usb/cdns,usb3.yaml index cae46c4982ad..69a93a0722f0 100644 --- a/Documentation/devicetree/bindings/usb/cdns,usb3.yaml +++ b/Documentation/devicetree/bindings/usb/cdns,usb3.yaml @@ -64,7 +64,7 @@ properties: description: size of memory intended as internal memory for endpoints buffers expressed in KB - $ref: /schemas/types.yaml#/definitions/uint32 + $ref: /schemas/types.yaml#/definitions/uint16 cdns,phyrst-a-enable: description: Enable resetting of PHY if Rx fail is detected diff --git a/Documentation/filesystems/index.rst b/Documentation/filesystems/index.rst index fbb2b5ada95b..eb252fc972aa 100644 --- a/Documentation/filesystems/index.rst +++ b/Documentation/filesystems/index.rst @@ -72,7 +72,6 @@ Documentation for filesystem implementations. befs bfs btrfs - cifs/index ceph coda configfs @@ -111,6 +110,7 @@ Documentation for filesystem implementations. ramfs-rootfs-initramfs relay romfs + smb/index spufs/index squashfs sysfs diff --git a/Documentation/filesystems/ramfs-rootfs-initramfs.rst b/Documentation/filesystems/ramfs-rootfs-initramfs.rst index 164960631925..447f767c6462 100644 --- a/Documentation/filesystems/ramfs-rootfs-initramfs.rst +++ b/Documentation/filesystems/ramfs-rootfs-initramfs.rst @@ -6,8 +6,7 @@ Ramfs, rootfs and initramfs October 17, 2005 -Rob Landley <[email protected]> -============================= +:Author: Rob Landley <[email protected]> What is ramfs? -------------- diff --git a/Documentation/filesystems/sharedsubtree.rst b/Documentation/filesystems/sharedsubtree.rst index d83395354250..1cf56489ed48 100644 --- a/Documentation/filesystems/sharedsubtree.rst +++ b/Documentation/filesystems/sharedsubtree.rst @@ -147,6 +147,7 @@ replicas continue to be exactly same. 3) Setting mount states +----------------------- The mount command (util-linux package) can be used to set mount states:: @@ -612,6 +613,7 @@ replicas continue to be exactly same. 6) Quiz +------- A. What is the result of the following command sequence? @@ -673,6 +675,7 @@ replicas continue to be exactly same. /mnt/1/test be? 7) FAQ +------ Q1. Why is bind mount needed? How is it different from symbolic links? symbolic links can get stale if the destination mount gets @@ -841,6 +844,7 @@ replicas continue to be exactly same. tmp usr tmp usr tmp usr 8) Implementation +----------------- 8A) Datastructure diff --git a/Documentation/filesystems/cifs/cifsroot.rst b/Documentation/filesystems/smb/cifsroot.rst index 4930bb443134..bf2d9db3acb9 100644 --- a/Documentation/filesystems/cifs/cifsroot.rst +++ b/Documentation/filesystems/smb/cifsroot.rst @@ -59,7 +59,7 @@ the root file system via SMB protocol. Enables the kernel to mount the root file system via SMB that are located in the <server-ip> and <share> specified in this option. -The default mount options are set in fs/cifs/cifsroot.c. +The default mount options are set in fs/smb/client/cifsroot.c. server-ip IPv4 address of the server. diff --git a/Documentation/filesystems/cifs/index.rst b/Documentation/filesystems/smb/index.rst index 1c8597a679ab..1c8597a679ab 100644 --- a/Documentation/filesystems/cifs/index.rst +++ b/Documentation/filesystems/smb/index.rst diff --git a/Documentation/filesystems/cifs/ksmbd.rst b/Documentation/filesystems/smb/ksmbd.rst index 7bed96d794fc..7bed96d794fc 100644 --- a/Documentation/filesystems/cifs/ksmbd.rst +++ b/Documentation/filesystems/smb/ksmbd.rst diff --git a/Documentation/fpga/index.rst b/Documentation/fpga/index.rst index f80f95667ca2..43c968871d99 100644 --- a/Documentation/fpga/index.rst +++ b/Documentation/fpga/index.rst @@ -1,7 +1,7 @@ .. SPDX-License-Identifier: GPL-2.0 ==== -fpga +FPGA ==== .. toctree:: diff --git a/Documentation/locking/index.rst b/Documentation/locking/index.rst index 7003bd5aeff4..6a9ea96c8bcb 100644 --- a/Documentation/locking/index.rst +++ b/Documentation/locking/index.rst @@ -1,7 +1,7 @@ .. SPDX-License-Identifier: GPL-2.0 ======= -locking +Locking ======= .. toctree:: diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml index 129f413ea349..4846345bade4 100644 --- a/Documentation/netlink/specs/ethtool.yaml +++ b/Documentation/netlink/specs/ethtool.yaml @@ -61,22 +61,6 @@ attribute-sets: nested-attributes: bitset-bits - - name: u64-array - attributes: - - - name: u64 - type: nest - multi-attr: true - nested-attributes: u64 - - - name: s32-array - attributes: - - - name: s32 - type: nest - multi-attr: true - nested-attributes: s32 - - name: string attributes: - @@ -239,7 +223,7 @@ attribute-sets: name: tx-min-frag-size type: u32 - - name: tx-min-frag-size + name: rx-min-frag-size type: u32 - name: verify-enabled @@ -310,7 +294,7 @@ attribute-sets: name: master-slave-state type: u8 - - name: master-slave-lanes + name: lanes type: u32 - name: rate-matching @@ -338,7 +322,7 @@ attribute-sets: name: ext-substate type: u8 - - name: down-cnt + name: ext-down-cnt type: u32 - name: debug @@ -593,7 +577,7 @@ attribute-sets: name: phc-index type: u32 - - name: cable-test-nft-nest-result + name: cable-test-ntf-nest-result attributes: - name: pair @@ -602,7 +586,7 @@ attribute-sets: name: code type: u8 - - name: cable-test-nft-nest-fault-length + name: cable-test-ntf-nest-fault-length attributes: - name: pair @@ -611,16 +595,16 @@ attribute-sets: name: cm type: u32 - - name: cable-test-nft-nest + name: cable-test-ntf-nest attributes: - name: result type: nest - nested-attributes: cable-test-nft-nest-result + nested-attributes: cable-test-ntf-nest-result - name: fault-length type: nest - nested-attributes: cable-test-nft-nest-fault-length + nested-attributes: cable-test-ntf-nest-fault-length - name: cable-test attributes: @@ -634,7 +618,7 @@ attribute-sets: - name: nest type: nest - nested-attributes: cable-test-nft-nest + nested-attributes: cable-test-ntf-nest - name: cable-test-tdr-cfg attributes: @@ -705,16 +689,16 @@ attribute-sets: type: u8 - name: corrected - type: nest - nested-attributes: u64-array + type: binary + sub-type: u64 - name: uncorr - type: nest - nested-attributes: u64-array + type: binary + sub-type: u64 - name: corr-bits - type: nest - nested-attributes: u64-array + type: binary + sub-type: u64 - name: fec attributes: @@ -792,7 +776,7 @@ attribute-sets: name: hist-bkt-hi type: u32 - - name: hist-bkt-val + name: hist-val type: u64 - name: stats @@ -827,8 +811,8 @@ attribute-sets: type: u32 - name: index - type: nest - nested-attributes: s32-array + type: binary + sub-type: s32 - name: module attributes: @@ -981,7 +965,7 @@ operations: - duplex - master-slave-cfg - master-slave-state - - master-slave-lanes + - lanes - rate-matching dump: *linkmodes-get-op - @@ -1015,7 +999,7 @@ operations: - sqi-max - ext-state - ext-substate - - down-cnt + - ext-down-cnt dump: *linkstate-get-op - name: debug-get @@ -1367,7 +1351,7 @@ operations: reply: attributes: - header - - cable-test-nft-nest + - cable-test-ntf-nest - name: cable-test-tdr-act doc: Cable test TDR. @@ -1555,7 +1539,7 @@ operations: - hkey dump: *rss-get-op - - name: plca-get + name: plca-get-cfg doc: Get PLCA params. attribute-set: plca @@ -1577,7 +1561,7 @@ operations: - burst-tmr dump: *plca-get-op - - name: plca-set + name: plca-set-cfg doc: Set PLCA params. attribute-set: plca @@ -1601,7 +1585,7 @@ operations: - name: plca-ntf doc: Notification for change in PLCA params. - notify: plca-get + notify: plca-get-cfg - name: mm-get doc: Get MAC Merge configuration and state diff --git a/Documentation/netlink/specs/handshake.yaml b/Documentation/netlink/specs/handshake.yaml index 614f1a585511..6d89e30f5fd5 100644 --- a/Documentation/netlink/specs/handshake.yaml +++ b/Documentation/netlink/specs/handshake.yaml @@ -68,6 +68,9 @@ attribute-sets: type: nest nested-attributes: x509 multi-attr: true + - + name: peername + type: string - name: done attributes: @@ -105,6 +108,7 @@ operations: - auth-mode - peer-identity - certificate + - peername - name: done doc: Handler reports handshake completion diff --git a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/devlink.rst b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/devlink.rst index 3a7a714cc08f..3354ca3608ee 100644 --- a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/devlink.rst +++ b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/devlink.rst @@ -40,6 +40,7 @@ flow_steering_mode: Device flow steering mode --------------------------------------------- The flow steering mode parameter controls the flow steering mode of the driver. Two modes are supported: + 1. 'dmfs' - Device managed flow steering. 2. 'smfs' - Software/Driver managed flow steering. @@ -99,6 +100,7 @@ between representors and stacked devices. By default metadata is enabled on the supported devices in E-switch. Metadata is applicable only for E-switch in switchdev mode and users may disable it when NONE of the below use cases will be in use: + 1. HCA is in Dual/multi-port RoCE mode. 2. VF/SF representor bonding (Usually used for Live migration) 3. Stacked devices @@ -180,7 +182,8 @@ User commands examples: $ devlink health diagnose pci/0000:82:00.0 reporter tx -NOTE: This command has valid output only when interface is up, otherwise the command has empty output. +.. note:: + This command has valid output only when interface is up, otherwise the command has empty output. - Show number of tx errors indicated, number of recover flows ended successfully, is autorecover enabled and graceful period from last recover:: @@ -232,8 +235,9 @@ User commands examples: $ devlink health dump show pci/0000:82:00.0 reporter fw -NOTE: This command can run only on the PF which has fw tracer ownership, -running it on other PF or any VF will return "Operation not permitted". +.. note:: + This command can run only on the PF which has fw tracer ownership, + running it on other PF or any VF will return "Operation not permitted". fw fatal reporter ----------------- @@ -256,7 +260,8 @@ User commands examples: $ devlink health dump show pci/0000:82:00.1 reporter fw_fatal -NOTE: This command can run only on PF. +.. note:: + This command can run only on PF. vnic reporter ------------- @@ -265,28 +270,37 @@ It is responsible for querying the vnic diagnostic counters from fw and displayi them in realtime. Description of the vnic counters: -total_q_under_processor_handle: number of queues in an error state due to -an async error or errored command. -send_queue_priority_update_flow: number of QP/SQ priority/SL update -events. -cq_overrun: number of times CQ entered an error state due to an -overflow. -async_eq_overrun: number of times an EQ mapped to async events was -overrun. -comp_eq_overrun: number of times an EQ mapped to completion events was -overrun. -quota_exceeded_command: number of commands issued and failed due to quota -exceeded. -invalid_command: number of commands issued and failed dues to any reason -other than quota exceeded. -nic_receive_steering_discard: number of packets that completed RX flow -steering but were discarded due to a mismatch in flow table. + +- total_q_under_processor_handle + number of queues in an error state due to + an async error or errored command. +- send_queue_priority_update_flow + number of QP/SQ priority/SL update events. +- cq_overrun + number of times CQ entered an error state due to an overflow. +- async_eq_overrun + number of times an EQ mapped to async events was overrun. + comp_eq_overrun number of times an EQ mapped to completion events was + overrun. +- quota_exceeded_command + number of commands issued and failed due to quota exceeded. +- invalid_command + number of commands issued and failed dues to any reason other than quota + exceeded. +- nic_receive_steering_discard + number of packets that completed RX flow + steering but were discarded due to a mismatch in flow table. User commands examples: -- Diagnose PF/VF vnic counters + +- Diagnose PF/VF vnic counters:: + $ devlink health diagnose pci/0000:82:00.1 reporter vnic + - Diagnose representor vnic counters (performed by supplying devlink port of the - representor, which can be obtained via devlink port command) + representor, which can be obtained via devlink port command):: + $ devlink health diagnose pci/0000:82:00.1/65537 reporter vnic -NOTE: This command can run over all interfaces such as PF/VF and representor ports. +.. note:: + This command can run over all interfaces such as PF/VF and representor ports. diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index 6ec06a33688a..80b8f73a0244 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -1352,8 +1352,8 @@ ping_group_range - 2 INTEGERS Restrict ICMP_PROTO datagram sockets to users in the group range. The default is "1 0", meaning, that nobody (not even root) may create ping sockets. Setting it to "100 100" would grant permissions - to the single group. "0 4294967295" would enable it for the world, "100 - 4294967295" would enable it for the users, but not daemons. + to the single group. "0 4294967294" would enable it for the world, "100 + 4294967294" would enable it for the users, but not daemons. tcp_early_demux - BOOLEAN Enable early demux for established TCP sockets. diff --git a/Documentation/networking/tls-handshake.rst b/Documentation/networking/tls-handshake.rst index a2817a88e905..6f5ea1646a47 100644 --- a/Documentation/networking/tls-handshake.rst +++ b/Documentation/networking/tls-handshake.rst @@ -53,6 +53,7 @@ fills in a structure that contains the parameters of the request: struct socket *ta_sock; tls_done_func_t ta_done; void *ta_data; + const char *ta_peername; unsigned int ta_timeout_ms; key_serial_t ta_keyring; key_serial_t ta_my_cert; @@ -71,6 +72,10 @@ instantiated a struct file in sock->file. has completed. Further explanation of this function is in the "Handshake Completion" sesction below. +The consumer can provide a NUL-terminated hostname in the @ta_peername +field that is sent as part of ClientHello. If no peername is provided, +the DNS hostname associated with the server's IP address is used instead. + The consumer can fill in the @ta_timeout_ms field to force the servicing handshake agent to exit after a number of milliseconds. This enables the socket to be fully closed once both the kernel and the handshake agent diff --git a/Documentation/pcmcia/index.rst b/Documentation/pcmcia/index.rst index 7ae1f62fca14..8067236c51ab 100644 --- a/Documentation/pcmcia/index.rst +++ b/Documentation/pcmcia/index.rst @@ -1,7 +1,7 @@ .. SPDX-License-Identifier: GPL-2.0 ====== -pcmcia +PCMCIA ====== .. toctree:: diff --git a/Documentation/process/maintainer-netdev.rst b/Documentation/process/maintainer-netdev.rst index f73ac9e175a8..83614cec9328 100644 --- a/Documentation/process/maintainer-netdev.rst +++ b/Documentation/process/maintainer-netdev.rst @@ -127,13 +127,32 @@ the value of ``Message-ID`` to the URL above. Updating patch status ~~~~~~~~~~~~~~~~~~~~~ -It may be tempting to help the maintainers and update the state of your -own patches when you post a new version or spot a bug. Please **do not** -do that. -Interfering with the patch status on patchwork will only cause confusion. Leave -it to the maintainer to figure out what is the most recent and current -version that should be applied. If there is any doubt, the maintainer -will reply and ask what should be done. +Contributors and reviewers do not have the permissions to update patch +state directly in patchwork. Patchwork doesn't expose much information +about the history of the state of patches, therefore having multiple +people update the state leads to confusion. + +Instead of delegating patchwork permissions netdev uses a simple mail +bot which looks for special commands/lines within the emails sent to +the mailing list. For example to mark a series as Changes Requested +one needs to send the following line anywhere in the email thread:: + + pw-bot: changes-requested + +As a result the bot will set the entire series to Changes Requested. +This may be useful when author discovers a bug in their own series +and wants to prevent it from getting applied. + +The use of the bot is entirely optional, if in doubt ignore its existence +completely. Maintainers will classify and update the state of the patches +themselves. No email should ever be sent to the list with the main purpose +of communicating with the bot, the bot commands should be seen as metadata. + +The use of the bot is restricted to authors of the patches (the ``From:`` +header on patch submission and command must match!), maintainers themselves +and a handful of senior reviewers. Bot records its activity here: + + https://patchwork.hopto.org/pw-bot.html Review timelines ~~~~~~~~~~~~~~~~ diff --git a/Documentation/s390/vfio-ap.rst b/Documentation/s390/vfio-ap.rst index d46e98c7c1ec..bb3f4c4e2885 100644 --- a/Documentation/s390/vfio-ap.rst +++ b/Documentation/s390/vfio-ap.rst @@ -551,7 +551,6 @@ These are the steps: * IOMMU_SUPPORT * S390 * ZCRYPT - * S390_AP_IOMMU * VFIO * KVM diff --git a/Documentation/staging/crc32.rst b/Documentation/staging/crc32.rst index 8a6860f33b4e..7542220967cb 100644 --- a/Documentation/staging/crc32.rst +++ b/Documentation/staging/crc32.rst @@ -1,5 +1,5 @@ ================================= -brief tutorial on CRC computation +Brief tutorial on CRC computation ================================= A CRC is a long-division remainder. You add the CRC to the message, diff --git a/Documentation/timers/index.rst b/Documentation/timers/index.rst index df510ad0c989..983f91f8f023 100644 --- a/Documentation/timers/index.rst +++ b/Documentation/timers/index.rst @@ -1,7 +1,7 @@ .. SPDX-License-Identifier: GPL-2.0 ====== -timers +Timers ====== .. toctree:: diff --git a/Documentation/trace/histogram.rst b/Documentation/trace/histogram.rst index 479c9eac6335..3c9b263de9c2 100644 --- a/Documentation/trace/histogram.rst +++ b/Documentation/trace/histogram.rst @@ -35,7 +35,7 @@ Documentation written by Tom Zanussi in place of an explicit value field - this is simply a count of event hits. If 'values' isn't specified, an implicit 'hitcount' value will be automatically created and used as the only value. - Keys can be any field, or the special string 'stacktrace', which + Keys can be any field, or the special string 'common_stacktrace', which will use the event's kernel stacktrace as the key. The keywords 'keys' or 'key' can be used to specify keys, and the keywords 'values', 'vals', or 'val' can be used to specify values. Compound @@ -54,7 +54,7 @@ Documentation written by Tom Zanussi 'compatible' if the fields named in the trigger share the same number and type of fields and those fields also have the same names. Note that any two events always share the compatible 'hitcount' and - 'stacktrace' fields and can therefore be combined using those + 'common_stacktrace' fields and can therefore be combined using those fields, however pointless that may be. 'hist' triggers add a 'hist' file to each event's subdirectory. @@ -547,9 +547,9 @@ Extended error information the hist trigger display symbolic call_sites, we can have the hist trigger additionally display the complete set of kernel stack traces that led to each call_site. To do that, we simply use the special - value 'stacktrace' for the key parameter:: + value 'common_stacktrace' for the key parameter:: - # echo 'hist:keys=stacktrace:values=bytes_req,bytes_alloc:sort=bytes_alloc' > \ + # echo 'hist:keys=common_stacktrace:values=bytes_req,bytes_alloc:sort=bytes_alloc' > \ /sys/kernel/tracing/events/kmem/kmalloc/trigger The above trigger will use the kernel stack trace in effect when an @@ -561,9 +561,9 @@ Extended error information every callpath to a kmalloc for a kernel compile):: # cat /sys/kernel/tracing/events/kmem/kmalloc/hist - # trigger info: hist:keys=stacktrace:vals=bytes_req,bytes_alloc:sort=bytes_alloc:size=2048 [active] + # trigger info: hist:keys=common_stacktrace:vals=bytes_req,bytes_alloc:sort=bytes_alloc:size=2048 [active] - { stacktrace: + { common_stacktrace: __kmalloc_track_caller+0x10b/0x1a0 kmemdup+0x20/0x50 hidraw_report_event+0x8a/0x120 [hid] @@ -581,7 +581,7 @@ Extended error information cpu_startup_entry+0x315/0x3e0 rest_init+0x7c/0x80 } hitcount: 3 bytes_req: 21 bytes_alloc: 24 - { stacktrace: + { common_stacktrace: __kmalloc_track_caller+0x10b/0x1a0 kmemdup+0x20/0x50 hidraw_report_event+0x8a/0x120 [hid] @@ -596,7 +596,7 @@ Extended error information do_IRQ+0x5a/0xf0 ret_from_intr+0x0/0x30 } hitcount: 3 bytes_req: 21 bytes_alloc: 24 - { stacktrace: + { common_stacktrace: kmem_cache_alloc_trace+0xeb/0x150 aa_alloc_task_context+0x27/0x40 apparmor_cred_prepare+0x1f/0x50 @@ -608,7 +608,7 @@ Extended error information . . . - { stacktrace: + { common_stacktrace: __kmalloc+0x11b/0x1b0 i915_gem_execbuffer2+0x6c/0x2c0 [i915] drm_ioctl+0x349/0x670 [drm] @@ -616,7 +616,7 @@ Extended error information SyS_ioctl+0x81/0xa0 system_call_fastpath+0x12/0x6a } hitcount: 17726 bytes_req: 13944120 bytes_alloc: 19593808 - { stacktrace: + { common_stacktrace: __kmalloc+0x11b/0x1b0 load_elf_phdrs+0x76/0xa0 load_elf_binary+0x102/0x1650 @@ -625,7 +625,7 @@ Extended error information SyS_execve+0x3a/0x50 return_from_execve+0x0/0x23 } hitcount: 33348 bytes_req: 17152128 bytes_alloc: 20226048 - { stacktrace: + { common_stacktrace: kmem_cache_alloc_trace+0xeb/0x150 apparmor_file_alloc_security+0x27/0x40 security_file_alloc+0x16/0x20 @@ -636,7 +636,7 @@ Extended error information SyS_open+0x1e/0x20 system_call_fastpath+0x12/0x6a } hitcount: 4766422 bytes_req: 9532844 bytes_alloc: 38131376 - { stacktrace: + { common_stacktrace: __kmalloc+0x11b/0x1b0 seq_buf_alloc+0x1b/0x50 seq_read+0x2cc/0x370 @@ -1026,7 +1026,7 @@ Extended error information First we set up an initially paused stacktrace trigger on the netif_receive_skb event:: - # echo 'hist:key=stacktrace:vals=len:pause' > \ + # echo 'hist:key=common_stacktrace:vals=len:pause' > \ /sys/kernel/tracing/events/net/netif_receive_skb/trigger Next, we set up an 'enable_hist' trigger on the sched_process_exec @@ -1060,9 +1060,9 @@ Extended error information $ wget https://www.kernel.org/pub/linux/kernel/v3.x/patch-3.19.xz # cat /sys/kernel/tracing/events/net/netif_receive_skb/hist - # trigger info: hist:keys=stacktrace:vals=len:sort=hitcount:size=2048 [paused] + # trigger info: hist:keys=common_stacktrace:vals=len:sort=hitcount:size=2048 [paused] - { stacktrace: + { common_stacktrace: __netif_receive_skb_core+0x46d/0x990 __netif_receive_skb+0x18/0x60 netif_receive_skb_internal+0x23/0x90 @@ -1079,7 +1079,7 @@ Extended error information kthread+0xd2/0xf0 ret_from_fork+0x42/0x70 } hitcount: 85 len: 28884 - { stacktrace: + { common_stacktrace: __netif_receive_skb_core+0x46d/0x990 __netif_receive_skb+0x18/0x60 netif_receive_skb_internal+0x23/0x90 @@ -1097,7 +1097,7 @@ Extended error information irq_thread+0x11f/0x150 kthread+0xd2/0xf0 } hitcount: 98 len: 664329 - { stacktrace: + { common_stacktrace: __netif_receive_skb_core+0x46d/0x990 __netif_receive_skb+0x18/0x60 process_backlog+0xa8/0x150 @@ -1115,7 +1115,7 @@ Extended error information inet_sendmsg+0x64/0xa0 sock_sendmsg+0x3d/0x50 } hitcount: 115 len: 13030 - { stacktrace: + { common_stacktrace: __netif_receive_skb_core+0x46d/0x990 __netif_receive_skb+0x18/0x60 netif_receive_skb_internal+0x23/0x90 @@ -1142,14 +1142,14 @@ Extended error information into the histogram. In order to avoid having to set everything up again, we can just clear the histogram first:: - # echo 'hist:key=stacktrace:vals=len:clear' >> \ + # echo 'hist:key=common_stacktrace:vals=len:clear' >> \ /sys/kernel/tracing/events/net/netif_receive_skb/trigger Just to verify that it is in fact cleared, here's what we now see in the hist file:: # cat /sys/kernel/tracing/events/net/netif_receive_skb/hist - # trigger info: hist:keys=stacktrace:vals=len:sort=hitcount:size=2048 [paused] + # trigger info: hist:keys=common_stacktrace:vals=len:sort=hitcount:size=2048 [paused] Totals: Hits: 0 @@ -1485,12 +1485,12 @@ Extended error information And here's an example that shows how to combine histogram data from any two events even if they don't share any 'compatible' fields - other than 'hitcount' and 'stacktrace'. These commands create a + other than 'hitcount' and 'common_stacktrace'. These commands create a couple of triggers named 'bar' using those fields:: - # echo 'hist:name=bar:key=stacktrace:val=hitcount' > \ + # echo 'hist:name=bar:key=common_stacktrace:val=hitcount' > \ /sys/kernel/tracing/events/sched/sched_process_fork/trigger - # echo 'hist:name=bar:key=stacktrace:val=hitcount' > \ + # echo 'hist:name=bar:key=common_stacktrace:val=hitcount' > \ /sys/kernel/tracing/events/net/netif_rx/trigger And displaying the output of either shows some interesting if @@ -1501,16 +1501,16 @@ Extended error information # event histogram # - # trigger info: hist:name=bar:keys=stacktrace:vals=hitcount:sort=hitcount:size=2048 [active] + # trigger info: hist:name=bar:keys=common_stacktrace:vals=hitcount:sort=hitcount:size=2048 [active] # - { stacktrace: + { common_stacktrace: kernel_clone+0x18e/0x330 kernel_thread+0x29/0x30 kthreadd+0x154/0x1b0 ret_from_fork+0x3f/0x70 } hitcount: 1 - { stacktrace: + { common_stacktrace: netif_rx_internal+0xb2/0xd0 netif_rx_ni+0x20/0x70 dev_loopback_xmit+0xaa/0xd0 @@ -1528,7 +1528,7 @@ Extended error information call_cpuidle+0x3b/0x60 cpu_startup_entry+0x22d/0x310 } hitcount: 1 - { stacktrace: + { common_stacktrace: netif_rx_internal+0xb2/0xd0 netif_rx_ni+0x20/0x70 dev_loopback_xmit+0xaa/0xd0 @@ -1543,7 +1543,7 @@ Extended error information SyS_sendto+0xe/0x10 entry_SYSCALL_64_fastpath+0x12/0x6a } hitcount: 2 - { stacktrace: + { common_stacktrace: netif_rx_internal+0xb2/0xd0 netif_rx+0x1c/0x60 loopback_xmit+0x6c/0xb0 @@ -1561,7 +1561,7 @@ Extended error information sock_sendmsg+0x38/0x50 ___sys_sendmsg+0x14e/0x270 } hitcount: 76 - { stacktrace: + { common_stacktrace: netif_rx_internal+0xb2/0xd0 netif_rx+0x1c/0x60 loopback_xmit+0x6c/0xb0 @@ -1579,7 +1579,7 @@ Extended error information sock_sendmsg+0x38/0x50 ___sys_sendmsg+0x269/0x270 } hitcount: 77 - { stacktrace: + { common_stacktrace: netif_rx_internal+0xb2/0xd0 netif_rx+0x1c/0x60 loopback_xmit+0x6c/0xb0 @@ -1597,7 +1597,7 @@ Extended error information sock_sendmsg+0x38/0x50 SYSC_sendto+0xef/0x170 } hitcount: 88 - { stacktrace: + { common_stacktrace: kernel_clone+0x18e/0x330 SyS_clone+0x19/0x20 entry_SYSCALL_64_fastpath+0x12/0x6a @@ -1949,7 +1949,7 @@ uninterruptible state:: # cd /sys/kernel/tracing # echo 's:block_lat pid_t pid; u64 delta; unsigned long[] stack;' > dynamic_events - # echo 'hist:keys=next_pid:ts=common_timestamp.usecs,st=stacktrace if prev_state == 2' >> events/sched/sched_switch/trigger + # echo 'hist:keys=next_pid:ts=common_timestamp.usecs,st=common_stacktrace if prev_state == 2' >> events/sched/sched_switch/trigger # echo 'hist:keys=prev_pid:delta=common_timestamp.usecs-$ts,s=$st:onmax($delta).trace(block_lat,prev_pid,$delta,$s)' >> events/sched/sched_switch/trigger # echo 1 > events/synthetic/block_lat/enable # cat trace diff --git a/Documentation/userspace-api/ioctl/ioctl-number.rst b/Documentation/userspace-api/ioctl/ioctl-number.rst index 176e8fc3f31b..4f7b23faebb9 100644 --- a/Documentation/userspace-api/ioctl/ioctl-number.rst +++ b/Documentation/userspace-api/ioctl/ioctl-number.rst @@ -363,7 +363,7 @@ Code Seq# Include File Comments 0xCC 00-0F drivers/misc/ibmvmc.h pseries VMC driver 0xCD 01 linux/reiserfs_fs.h 0xCE 01-02 uapi/linux/cxl_mem.h Compute Express Link Memory Devices -0xCF 02 fs/cifs/ioctl.c +0xCF 02 fs/smb/client/cifs_ioctl.h 0xDB 00-0F drivers/char/mwave/mwavepub.h 0xDD 00-3F ZFCP device driver see drivers/s390/scsi/ <mailto:[email protected]> diff --git a/MAINTAINERS b/MAINTAINERS index 02bfd2c39fe8..a73e5a98503a 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -956,7 +956,8 @@ F: Documentation/networking/device_drivers/ethernet/amazon/ena.rst F: drivers/net/ethernet/amazon/ AMAZON RDMA EFA DRIVER -M: Gal Pressman <[email protected]> +M: Michael Margolin <[email protected]> +R: Gal Pressman <[email protected]> R: Yossi Leybovich <[email protected]> S: Supported @@ -1677,10 +1678,7 @@ F: drivers/power/reset/arm-versatile-reboot.c F: drivers/soc/versatile/ ARM KOMEDA DRM-KMS DRIVER -M: James (Qian) Wang <[email protected]> M: Liviu Dudau <[email protected]> -M: Mihail Atanassov <[email protected]> -L: Mali DP Maintainers <[email protected]> S: Supported T: git git://anongit.freedesktop.org/drm/drm-misc F: Documentation/devicetree/bindings/display/arm,komeda.yaml @@ -1701,8 +1699,6 @@ F: include/uapi/drm/panfrost_drm.h ARM MALI-DP DRM DRIVER M: Liviu Dudau <[email protected]> -M: Brian Starkey <[email protected]> -L: Mali DP Maintainers <[email protected]> S: Supported T: git git://anongit.freedesktop.org/drm/drm-misc F: Documentation/devicetree/bindings/display/arm,malidp.yaml @@ -2434,6 +2430,15 @@ X: drivers/net/wireless/atmel/ N: at91 N: atmel +ARM/MICROCHIP (ARM64) SoC support +M: Conor Dooley <[email protected]> +M: Nicolas Ferre <[email protected]> +M: Claudiu Beznea <[email protected]> +L: [email protected] (moderated for non-subscribers) +S: Supported +T: git https://git.kernel.org/pub/scm/linux/kernel/git/at91/linux.git +F: arch/arm64/boot/dts/microchip/ + ARM/Microchip Sparx5 SoC support M: Lars Povlsen <[email protected]> M: Steen Hegelund <[email protected]> @@ -2441,8 +2446,7 @@ M: Daniel Machon <[email protected]> L: [email protected] (moderated for non-subscribers) S: Supported -T: git git://github.com/microchip-ung/linux-upstream.git -F: arch/arm64/boot/dts/microchip/ +F: arch/arm64/boot/dts/microchip/sparx* F: drivers/net/ethernet/microchip/vcap/ F: drivers/pinctrl/pinctrl-microchip-sgpio.c N: sparx5 @@ -3541,7 +3545,7 @@ F: Documentation/filesystems/befs.rst F: fs/befs/ BFQ I/O SCHEDULER -M: Paolo Valente <[email protected]> +M: Paolo Valente <[email protected]> M: Jens Axboe <[email protected]> S: Maintained @@ -4914,7 +4918,6 @@ F: drivers/media/cec/i2c/ch7322.c CIRRUS LOGIC AUDIO CODEC DRIVERS M: James Schulman <[email protected]> M: David Rhodes <[email protected]> -M: Lucas Tanure <[email protected]> M: Richard Fitzgerald <[email protected]> L: [email protected] (moderated for non-subscribers) @@ -5136,7 +5139,7 @@ X: drivers/clk/clkdev.c COMMON INTERNET FILE SYSTEM CLIENT (CIFS and SMB3) M: Steve French <[email protected]> -R: Paulo Alcantara <[email protected]> (DFS, global name space) +R: Paulo Alcantara <[email protected]> (DFS, global name space) R: Ronnie Sahlberg <[email protected]> (directory leases, sparse files) R: Shyam Prasad N <[email protected]> (multichannel) R: Tom Talpey <[email protected]> (RDMA, smbdirect) @@ -5146,8 +5149,8 @@ S: Supported W: https://wiki.samba.org/index.php/LinuxCIFS T: git git://git.samba.org/sfrench/cifs-2.6.git F: Documentation/admin-guide/cifs/ -F: fs/cifs/ -F: fs/smbfs_common/ +F: fs/smb/client/ +F: fs/smb/common/ F: include/uapi/linux/cifs COMPACTPCI HOTPLUG CORE @@ -6012,7 +6015,7 @@ W: http://www.dialog-semiconductor.com/products F: Documentation/devicetree/bindings/input/da90??-onkey.txt F: Documentation/devicetree/bindings/input/dlg,da72??.txt F: Documentation/devicetree/bindings/mfd/da90*.txt -F: Documentation/devicetree/bindings/mfd/da90*.yaml +F: Documentation/devicetree/bindings/mfd/dlg,da90*.yaml F: Documentation/devicetree/bindings/regulator/da92*.txt F: Documentation/devicetree/bindings/regulator/dlg,da9*.yaml F: Documentation/devicetree/bindings/regulator/slg51000.txt @@ -9341,7 +9344,7 @@ F: include/linux/hisi_acc_qm.h HISILICON ROCE DRIVER M: Haoyue Xu <[email protected]> -M: Wenpeng Liang <[email protected]> +M: Junxian Huang <[email protected]> S: Maintained F: Documentation/devicetree/bindings/infiniband/hisilicon-hns-roce.txt @@ -11307,9 +11310,9 @@ R: Tom Talpey <[email protected]> S: Maintained T: git git://git.samba.org/ksmbd.git -F: Documentation/filesystems/cifs/ksmbd.rst -F: fs/ksmbd/ -F: fs/smbfs_common/ +F: Documentation/filesystems/smb/ksmbd.rst +F: fs/smb/common/ +F: fs/smb/server/ KERNEL UNIT TESTING FRAMEWORK (KUnit) M: Brendan Higgins <[email protected]> @@ -14933,6 +14936,7 @@ F: drivers/ntb/hw/intel/ NTFS FILESYSTEM M: Anton Altaparmakov <[email protected]> +R: Namjae Jeon <[email protected]> S: Supported W: http://www.tuxera.com/ @@ -18580,10 +18584,9 @@ F: Documentation/admin-guide/LSM/SafeSetID.rst F: security/safesetid/ SAMSUNG AUDIO (ASoC) DRIVERS -M: Krzysztof Kozlowski <[email protected]> M: Sylwester Nawrocki <[email protected]> L: [email protected] (moderated for non-subscribers) -S: Supported +S: Maintained B: mailto:[email protected] F: Documentation/devicetree/bindings/sound/samsung* F: sound/soc/samsung/ @@ -18711,7 +18714,6 @@ F: include/dt-bindings/clock/samsung,*.h F: include/linux/clk/samsung.h SAMSUNG SPI DRIVERS -M: Krzysztof Kozlowski <[email protected]> M: Andi Shyti <[email protected]> @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 4 SUBLEVEL = 0 -EXTRAVERSION = -rc2 +EXTRAVERSION = -rc4 NAME = Hurr durr I'ma ninja sloth # *DOCUMENTATION* diff --git a/arch/arm/boot/dts/imx6qdl-mba6.dtsi b/arch/arm/boot/dts/imx6qdl-mba6.dtsi index 78555a618851..7b7e6c2ad190 100644 --- a/arch/arm/boot/dts/imx6qdl-mba6.dtsi +++ b/arch/arm/boot/dts/imx6qdl-mba6.dtsi @@ -209,6 +209,7 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_pcie>; reset-gpio = <&gpio6 7 GPIO_ACTIVE_LOW>; + vpcie-supply = <®_pcie>; status = "okay"; }; diff --git a/arch/arm/boot/dts/imx6ull-dhcor-som.dtsi b/arch/arm/boot/dts/imx6ull-dhcor-som.dtsi index 5882c7565f64..32a6022625d9 100644 --- a/arch/arm/boot/dts/imx6ull-dhcor-som.dtsi +++ b/arch/arm/boot/dts/imx6ull-dhcor-som.dtsi @@ -8,6 +8,7 @@ #include <dt-bindings/input/input.h> #include <dt-bindings/leds/common.h> #include <dt-bindings/pwm/pwm.h> +#include <dt-bindings/regulator/dlg,da9063-regulator.h> #include "imx6ull.dtsi" / { @@ -84,16 +85,20 @@ regulators { vdd_soc_in_1v4: buck1 { + regulator-allowed-modes = <DA9063_BUCK_MODE_SLEEP>; /* PFM */ regulator-always-on; regulator-boot-on; + regulator-initial-mode = <DA9063_BUCK_MODE_SLEEP>; regulator-max-microvolt = <1400000>; regulator-min-microvolt = <1400000>; regulator-name = "vdd_soc_in_1v4"; }; vcc_3v3: buck2 { + regulator-allowed-modes = <DA9063_BUCK_MODE_SYNC>; /* PWM */ regulator-always-on; regulator-boot-on; + regulator-initial-mode = <DA9063_BUCK_MODE_SYNC>; regulator-max-microvolt = <3300000>; regulator-min-microvolt = <3300000>; regulator-name = "vcc_3v3"; @@ -106,8 +111,10 @@ * the voltage is set to 1.5V. */ vcc_ddr_1v35: buck3 { + regulator-allowed-modes = <DA9063_BUCK_MODE_SYNC>; /* PWM */ regulator-always-on; regulator-boot-on; + regulator-initial-mode = <DA9063_BUCK_MODE_SYNC>; regulator-max-microvolt = <1500000>; regulator-min-microvolt = <1500000>; regulator-name = "vcc_ddr_1v35"; diff --git a/arch/arm/boot/dts/vexpress-v2p-ca5s.dts b/arch/arm/boot/dts/vexpress-v2p-ca5s.dts index 3b88209bacea..ff1f9a1bcfcf 100644 --- a/arch/arm/boot/dts/vexpress-v2p-ca5s.dts +++ b/arch/arm/boot/dts/vexpress-v2p-ca5s.dts @@ -132,6 +132,7 @@ reg = <0x2c0f0000 0x1000>; interrupts = <0 84 4>; cache-level = <2>; + cache-unified; }; pmu { diff --git a/arch/arm/include/asm/arm_pmuv3.h b/arch/arm/include/asm/arm_pmuv3.h index 78d3d4b82c6c..f4db3e75d75f 100644 --- a/arch/arm/include/asm/arm_pmuv3.h +++ b/arch/arm/include/asm/arm_pmuv3.h @@ -92,7 +92,7 @@ #define RETURN_READ_PMEVCNTRN(n) \ return read_sysreg(PMEVCNTR##n) -static unsigned long read_pmevcntrn(int n) +static inline unsigned long read_pmevcntrn(int n) { PMEVN_SWITCH(n, RETURN_READ_PMEVCNTRN); return 0; @@ -100,14 +100,14 @@ static unsigned long read_pmevcntrn(int n) #define WRITE_PMEVCNTRN(n) \ write_sysreg(val, PMEVCNTR##n) -static void write_pmevcntrn(int n, unsigned long val) +static inline void write_pmevcntrn(int n, unsigned long val) { PMEVN_SWITCH(n, WRITE_PMEVCNTRN); } #define WRITE_PMEVTYPERN(n) \ write_sysreg(val, PMEVTYPER##n) -static void write_pmevtypern(int n, unsigned long val) +static inline void write_pmevtypern(int n, unsigned long val) { PMEVN_SWITCH(n, WRITE_PMEVTYPERN); } diff --git a/arch/arm64/boot/dts/arm/foundation-v8.dtsi b/arch/arm64/boot/dts/arm/foundation-v8.dtsi index 029578072d8f..7b41537731a6 100644 --- a/arch/arm64/boot/dts/arm/foundation-v8.dtsi +++ b/arch/arm64/boot/dts/arm/foundation-v8.dtsi @@ -59,6 +59,7 @@ L2_0: l2-cache0 { compatible = "cache"; cache-level = <2>; + cache-unified; }; }; diff --git a/arch/arm64/boot/dts/arm/rtsm_ve-aemv8a.dts b/arch/arm64/boot/dts/arm/rtsm_ve-aemv8a.dts index ef68f5aae7dd..afdf954206f1 100644 --- a/arch/arm64/boot/dts/arm/rtsm_ve-aemv8a.dts +++ b/arch/arm64/boot/dts/arm/rtsm_ve-aemv8a.dts @@ -72,6 +72,7 @@ L2_0: l2-cache0 { compatible = "cache"; cache-level = <2>; + cache-unified; }; }; diff --git a/arch/arm64/boot/dts/arm/vexpress-v2f-1xv7-ca53x2.dts b/arch/arm64/boot/dts/arm/vexpress-v2f-1xv7-ca53x2.dts index 796cd7d02eb5..7bdeb965f0a9 100644 --- a/arch/arm64/boot/dts/arm/vexpress-v2f-1xv7-ca53x2.dts +++ b/arch/arm64/boot/dts/arm/vexpress-v2f-1xv7-ca53x2.dts @@ -58,6 +58,7 @@ L2_0: l2-cache0 { compatible = "cache"; cache-level = <2>; + cache-unified; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx8-ss-conn.dtsi b/arch/arm64/boot/dts/freescale/imx8-ss-conn.dtsi index 2209c1ac6e9b..e62a43591361 100644 --- a/arch/arm64/boot/dts/freescale/imx8-ss-conn.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8-ss-conn.dtsi @@ -171,6 +171,7 @@ conn_subsys: bus@5b000000 { interrupt-names = "host", "peripheral", "otg", "wakeup"; phys = <&usb3_phy>; phy-names = "cdns3,usb3-phy"; + cdns,on-chip-buff-size = /bits/ 16 <18>; status = "disabled"; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi index 67072e6c77d5..cbd9d124c80d 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi @@ -98,11 +98,17 @@ #address-cells = <1>; #size-cells = <0>; - ethphy: ethernet-phy@4 { + ethphy: ethernet-phy@4 { /* AR8033 or ADIN1300 */ compatible = "ethernet-phy-ieee802.3-c22"; reg = <4>; reset-gpios = <&gpio1 9 GPIO_ACTIVE_LOW>; reset-assert-us = <10000>; + /* + * Deassert delay: + * ADIN1300 requires 5ms. + * AR8033 requires 1ms. + */ + reset-deassert-us = <20000>; }; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mn.dtsi b/arch/arm64/boot/dts/freescale/imx8mn.dtsi index bd84db550053..8be8f090e8b8 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mn.dtsi @@ -1069,13 +1069,6 @@ <&clk IMX8MN_CLK_DISP_APB_ROOT>, <&clk IMX8MN_CLK_DISP_AXI_ROOT>; clock-names = "pix", "axi", "disp_axi"; - assigned-clocks = <&clk IMX8MN_CLK_DISP_PIXEL_ROOT>, - <&clk IMX8MN_CLK_DISP_AXI>, - <&clk IMX8MN_CLK_DISP_APB>; - assigned-clock-parents = <&clk IMX8MN_CLK_DISP_PIXEL>, - <&clk IMX8MN_SYS_PLL2_1000M>, - <&clk IMX8MN_SYS_PLL1_800M>; - assigned-clock-rates = <594000000>, <500000000>, <200000000>; interrupts = <GIC_SPI 5 IRQ_TYPE_LEVEL_HIGH>; power-domains = <&disp_blk_ctrl IMX8MN_DISPBLK_PD_LCDIF>; status = "disabled"; @@ -1093,12 +1086,6 @@ clocks = <&clk IMX8MN_CLK_DSI_CORE>, <&clk IMX8MN_CLK_DSI_PHY_REF>; clock-names = "bus_clk", "sclk_mipi"; - assigned-clocks = <&clk IMX8MN_CLK_DSI_CORE>, - <&clk IMX8MN_CLK_DSI_PHY_REF>; - assigned-clock-parents = <&clk IMX8MN_SYS_PLL1_266M>, - <&clk IMX8MN_CLK_24M>; - assigned-clock-rates = <266000000>, <24000000>; - samsung,pll-clock-frequency = <24000000>; interrupts = <GIC_SPI 18 IRQ_TYPE_LEVEL_HIGH>; power-domains = <&disp_blk_ctrl IMX8MN_DISPBLK_PD_MIPI_DSI>; status = "disabled"; @@ -1142,6 +1129,21 @@ "lcdif-axi", "lcdif-apb", "lcdif-pix", "dsi-pclk", "dsi-ref", "csi-aclk", "csi-pclk"; + assigned-clocks = <&clk IMX8MN_CLK_DSI_CORE>, + <&clk IMX8MN_CLK_DSI_PHY_REF>, + <&clk IMX8MN_CLK_DISP_PIXEL>, + <&clk IMX8MN_CLK_DISP_AXI>, + <&clk IMX8MN_CLK_DISP_APB>; + assigned-clock-parents = <&clk IMX8MN_SYS_PLL1_266M>, + <&clk IMX8MN_CLK_24M>, + <&clk IMX8MN_VIDEO_PLL1_OUT>, + <&clk IMX8MN_SYS_PLL2_1000M>, + <&clk IMX8MN_SYS_PLL1_800M>; + assigned-clock-rates = <266000000>, + <24000000>, + <594000000>, + <500000000>, + <200000000>; #power-domain-cells = <1>; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mp.dtsi b/arch/arm64/boot/dts/freescale/imx8mp.dtsi index f81391993354..428c60462e3d 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp.dtsi @@ -1211,13 +1211,6 @@ <&clk IMX8MP_CLK_MEDIA_APB_ROOT>, <&clk IMX8MP_CLK_MEDIA_AXI_ROOT>; clock-names = "pix", "axi", "disp_axi"; - assigned-clocks = <&clk IMX8MP_CLK_MEDIA_DISP1_PIX_ROOT>, - <&clk IMX8MP_CLK_MEDIA_AXI>, - <&clk IMX8MP_CLK_MEDIA_APB>; - assigned-clock-parents = <&clk IMX8MP_CLK_MEDIA_DISP1_PIX>, - <&clk IMX8MP_SYS_PLL2_1000M>, - <&clk IMX8MP_SYS_PLL1_800M>; - assigned-clock-rates = <594000000>, <500000000>, <200000000>; interrupts = <GIC_SPI 5 IRQ_TYPE_LEVEL_HIGH>; power-domains = <&media_blk_ctrl IMX8MP_MEDIABLK_PD_LCDIF_1>; status = "disabled"; @@ -1237,11 +1230,6 @@ <&clk IMX8MP_CLK_MEDIA_APB_ROOT>, <&clk IMX8MP_CLK_MEDIA_AXI_ROOT>; clock-names = "pix", "axi", "disp_axi"; - assigned-clocks = <&clk IMX8MP_CLK_MEDIA_DISP2_PIX>, - <&clk IMX8MP_VIDEO_PLL1>; - assigned-clock-parents = <&clk IMX8MP_VIDEO_PLL1_OUT>, - <&clk IMX8MP_VIDEO_PLL1_REF_SEL>; - assigned-clock-rates = <0>, <1039500000>; power-domains = <&media_blk_ctrl IMX8MP_MEDIABLK_PD_LCDIF_2>; status = "disabled"; @@ -1296,11 +1284,16 @@ "disp1", "disp2", "isp", "phy"; assigned-clocks = <&clk IMX8MP_CLK_MEDIA_AXI>, - <&clk IMX8MP_CLK_MEDIA_APB>; + <&clk IMX8MP_CLK_MEDIA_APB>, + <&clk IMX8MP_CLK_MEDIA_DISP1_PIX>, + <&clk IMX8MP_CLK_MEDIA_DISP2_PIX>, + <&clk IMX8MP_VIDEO_PLL1>; assigned-clock-parents = <&clk IMX8MP_SYS_PLL2_1000M>, - <&clk IMX8MP_SYS_PLL1_800M>; - assigned-clock-rates = <500000000>, <200000000>; - + <&clk IMX8MP_SYS_PLL1_800M>, + <&clk IMX8MP_VIDEO_PLL1_OUT>, + <&clk IMX8MP_VIDEO_PLL1_OUT>; + assigned-clock-rates = <500000000>, <200000000>, + <0>, <0>, <1039500000>; #power-domain-cells = <1>; lvds_bridge: bridge@5c { diff --git a/arch/arm64/boot/dts/freescale/imx8x-colibri-eval-v3.dtsi b/arch/arm64/boot/dts/freescale/imx8x-colibri-eval-v3.dtsi index 7264d784ae72..9af769ab8ceb 100644 --- a/arch/arm64/boot/dts/freescale/imx8x-colibri-eval-v3.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8x-colibri-eval-v3.dtsi @@ -33,6 +33,12 @@ }; }; +&iomuxc { + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_ext_io0>, <&pinctrl_hog0>, <&pinctrl_hog1>, + <&pinctrl_lpspi2_cs2>; +}; + /* Colibri SPI */ &lpspi2 { status = "okay"; diff --git a/arch/arm64/boot/dts/freescale/imx8x-colibri-iris.dtsi b/arch/arm64/boot/dts/freescale/imx8x-colibri-iris.dtsi index 5f30c88855e7..f8953067bc3b 100644 --- a/arch/arm64/boot/dts/freescale/imx8x-colibri-iris.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8x-colibri-iris.dtsi @@ -48,8 +48,7 @@ <IMX8QXP_SAI0_TXFS_LSIO_GPIO0_IO28 0x20>, /* SODIMM 101 */ <IMX8QXP_SAI0_RXD_LSIO_GPIO0_IO27 0x20>, /* SODIMM 97 */ <IMX8QXP_ENET0_RGMII_RXC_LSIO_GPIO5_IO03 0x06000020>, /* SODIMM 85 */ - <IMX8QXP_SAI0_TXC_LSIO_GPIO0_IO26 0x20>, /* SODIMM 79 */ - <IMX8QXP_QSPI0A_DATA1_LSIO_GPIO3_IO10 0x06700041>; /* SODIMM 45 */ + <IMX8QXP_SAI0_TXC_LSIO_GPIO0_IO26 0x20>; /* SODIMM 79 */ }; pinctrl_uart1_forceoff: uart1forceoffgrp { diff --git a/arch/arm64/boot/dts/freescale/imx8x-colibri.dtsi b/arch/arm64/boot/dts/freescale/imx8x-colibri.dtsi index 7cad79102e1a..49d105eb4769 100644 --- a/arch/arm64/boot/dts/freescale/imx8x-colibri.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8x-colibri.dtsi @@ -363,10 +363,6 @@ /* TODO VPU Encoder/Decoder */ &iomuxc { - pinctrl-names = "default"; - pinctrl-0 = <&pinctrl_ext_io0>, <&pinctrl_hog0>, <&pinctrl_hog1>, - <&pinctrl_hog2>, <&pinctrl_lpspi2_cs2>; - /* On-module touch pen-down interrupt */ pinctrl_ad7879_int: ad7879intgrp { fsl,pins = <IMX8QXP_MIPI_CSI0_I2C0_SCL_LSIO_GPIO3_IO05 0x21>; @@ -499,8 +495,7 @@ }; pinctrl_hog1: hog1grp { - fsl,pins = <IMX8QXP_CSI_MCLK_LSIO_GPIO3_IO01 0x20>, /* SODIMM 75 */ - <IMX8QXP_QSPI0A_SCLK_LSIO_GPIO3_IO16 0x20>; /* SODIMM 93 */ + fsl,pins = <IMX8QXP_QSPI0A_SCLK_LSIO_GPIO3_IO16 0x20>; /* SODIMM 93 */ }; pinctrl_hog2: hog2grp { @@ -774,3 +769,10 @@ fsl,pins = <IMX8QXP_SCU_BOOT_MODE3_SCU_DSC_RTC_CLOCK_OUTPUT_32K 0x20>; }; }; + +/* Delete peripherals which are not present on SOC, but are defined in imx8-ss-*.dtsi */ + +/delete-node/ &adc1; +/delete-node/ &adc1_lpcg; +/delete-node/ &dsp; +/delete-node/ &dsp_lpcg; diff --git a/arch/arm64/include/asm/arm_pmuv3.h b/arch/arm64/include/asm/arm_pmuv3.h index d6b51deb7bf0..18dc2fb3d7b7 100644 --- a/arch/arm64/include/asm/arm_pmuv3.h +++ b/arch/arm64/include/asm/arm_pmuv3.h @@ -13,7 +13,7 @@ #define RETURN_READ_PMEVCNTRN(n) \ return read_sysreg(pmevcntr##n##_el0) -static unsigned long read_pmevcntrn(int n) +static inline unsigned long read_pmevcntrn(int n) { PMEVN_SWITCH(n, RETURN_READ_PMEVCNTRN); return 0; @@ -21,14 +21,14 @@ static unsigned long read_pmevcntrn(int n) #define WRITE_PMEVCNTRN(n) \ write_sysreg(val, pmevcntr##n##_el0) -static void write_pmevcntrn(int n, unsigned long val) +static inline void write_pmevcntrn(int n, unsigned long val) { PMEVN_SWITCH(n, WRITE_PMEVCNTRN); } #define WRITE_PMEVTYPERN(n) \ write_sysreg(val, pmevtyper##n##_el0) -static void write_pmevtypern(int n, unsigned long val) +static inline void write_pmevtypern(int n, unsigned long val) { PMEVN_SWITCH(n, WRITE_PMEVTYPERN); } diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 683ca3af4084..5f6f84837a49 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -126,6 +126,10 @@ #define APPLE_CPU_PART_M1_FIRESTORM_MAX 0x029 #define APPLE_CPU_PART_M2_BLIZZARD 0x032 #define APPLE_CPU_PART_M2_AVALANCHE 0x033 +#define APPLE_CPU_PART_M2_BLIZZARD_PRO 0x034 +#define APPLE_CPU_PART_M2_AVALANCHE_PRO 0x035 +#define APPLE_CPU_PART_M2_BLIZZARD_MAX 0x038 +#define APPLE_CPU_PART_M2_AVALANCHE_MAX 0x039 #define AMPERE_CPU_PART_AMPERE1 0xAC3 @@ -181,6 +185,10 @@ #define MIDR_APPLE_M1_FIRESTORM_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM_MAX) #define MIDR_APPLE_M2_BLIZZARD MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_BLIZZARD) #define MIDR_APPLE_M2_AVALANCHE MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_AVALANCHE) +#define MIDR_APPLE_M2_BLIZZARD_PRO MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_BLIZZARD_PRO) +#define MIDR_APPLE_M2_AVALANCHE_PRO MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_AVALANCHE_PRO) +#define MIDR_APPLE_M2_BLIZZARD_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_BLIZZARD_MAX) +#define MIDR_APPLE_M2_AVALANCHE_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_AVALANCHE_MAX) #define MIDR_AMPERE1 MIDR_CPU_MODEL(ARM_CPU_IMP_AMPERE, AMPERE_CPU_PART_AMPERE1) /* Fujitsu Erratum 010001 affects A64FX 1.0 and 1.1, (v0r0 and v1r0) */ diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h index 4cd6762bda80..dc3c072e862f 100644 --- a/arch/arm64/include/asm/kvm_pgtable.h +++ b/arch/arm64/include/asm/kvm_pgtable.h @@ -209,6 +209,7 @@ struct kvm_pgtable_visit_ctx { kvm_pte_t old; void *arg; struct kvm_pgtable_mm_ops *mm_ops; + u64 start; u64 addr; u64 end; u32 level; diff --git a/arch/arm64/kernel/mte.c b/arch/arm64/kernel/mte.c index f5bcb0dc6267..7e89968bd282 100644 --- a/arch/arm64/kernel/mte.c +++ b/arch/arm64/kernel/mte.c @@ -66,13 +66,10 @@ void mte_sync_tags(pte_t old_pte, pte_t pte) return; /* if PG_mte_tagged is set, tags have already been initialised */ - for (i = 0; i < nr_pages; i++, page++) { - if (!page_mte_tagged(page)) { + for (i = 0; i < nr_pages; i++, page++) + if (!page_mte_tagged(page)) mte_sync_page_tags(page, old_pte, check_swap, pte_is_tagged); - set_page_mte_tagged(page); - } - } /* ensure the tags are visible before the PTE is set */ smp_wmb(); diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c index 0119dc91abb5..d9e1355730ef 100644 --- a/arch/arm64/kernel/vdso.c +++ b/arch/arm64/kernel/vdso.c @@ -288,7 +288,7 @@ static int aarch32_alloc_kuser_vdso_page(void) memcpy((void *)(vdso_page + 0x1000 - kuser_sz), __kuser_helper_start, kuser_sz); - aarch32_vectors_page = virt_to_page(vdso_page); + aarch32_vectors_page = virt_to_page((void *)vdso_page); return 0; } diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c index 1279949599b5..4c9dcd8fc939 100644 --- a/arch/arm64/kvm/fpsimd.c +++ b/arch/arm64/kvm/fpsimd.c @@ -81,26 +81,34 @@ void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu) fpsimd_kvm_prepare(); + /* + * We will check TIF_FOREIGN_FPSTATE just before entering the + * guest in kvm_arch_vcpu_ctxflush_fp() and override this to + * FP_STATE_FREE if the flag set. + */ vcpu->arch.fp_state = FP_STATE_HOST_OWNED; vcpu_clear_flag(vcpu, HOST_SVE_ENABLED); if (read_sysreg(cpacr_el1) & CPACR_EL1_ZEN_EL0EN) vcpu_set_flag(vcpu, HOST_SVE_ENABLED); - /* - * We don't currently support SME guests but if we leave - * things in streaming mode then when the guest starts running - * FPSIMD or SVE code it may generate SME traps so as a - * special case if we are in streaming mode we force the host - * state to be saved now and exit streaming mode so that we - * don't have to handle any SME traps for valid guest - * operations. Do this for ZA as well for now for simplicity. - */ if (system_supports_sme()) { vcpu_clear_flag(vcpu, HOST_SME_ENABLED); if (read_sysreg(cpacr_el1) & CPACR_EL1_SMEN_EL0EN) vcpu_set_flag(vcpu, HOST_SME_ENABLED); + /* + * If PSTATE.SM is enabled then save any pending FP + * state and disable PSTATE.SM. If we leave PSTATE.SM + * enabled and the guest does not enable SME via + * CPACR_EL1.SMEN then operations that should be valid + * may generate SME traps from EL1 to EL1 which we + * can't intercept and which would confuse the guest. + * + * Do the same for PSTATE.ZA in the case where there + * is state in the registers which has not already + * been saved, this is very unlikely to happen. + */ if (read_sysreg_s(SYS_SVCR) & (SVCR_SM_MASK | SVCR_ZA_MASK)) { vcpu->arch.fp_state = FP_STATE_FREE; fpsimd_save_and_flush_cpu_state(); diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index c41166f1a1dd..e78a08a72a3c 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -177,9 +177,17 @@ static bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code) sve_guest = vcpu_has_sve(vcpu); esr_ec = kvm_vcpu_trap_get_class(vcpu); - /* Don't handle SVE traps for non-SVE vcpus here: */ - if (!sve_guest && esr_ec != ESR_ELx_EC_FP_ASIMD) + /* Only handle traps the vCPU can support here: */ + switch (esr_ec) { + case ESR_ELx_EC_FP_ASIMD: + break; + case ESR_ELx_EC_SVE: + if (!sve_guest) + return false; + break; + default: return false; + } /* Valid trap. Switch the context: */ diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index 3d61bd3e591d..5282cb9ca4cf 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -58,8 +58,9 @@ struct kvm_pgtable_walk_data { struct kvm_pgtable_walker *walker; + const u64 start; u64 addr; - u64 end; + const u64 end; }; static bool kvm_phys_is_valid(u64 phys) @@ -201,6 +202,7 @@ static inline int __kvm_pgtable_visit(struct kvm_pgtable_walk_data *data, .old = READ_ONCE(*ptep), .arg = data->walker->arg, .mm_ops = mm_ops, + .start = data->start, .addr = data->addr, .end = data->end, .level = level, @@ -293,6 +295,7 @@ int kvm_pgtable_walk(struct kvm_pgtable *pgt, u64 addr, u64 size, struct kvm_pgtable_walker *walker) { struct kvm_pgtable_walk_data walk_data = { + .start = ALIGN_DOWN(addr, PAGE_SIZE), .addr = ALIGN_DOWN(addr, PAGE_SIZE), .end = PAGE_ALIGN(walk_data.addr + size), .walker = walker, @@ -349,7 +352,7 @@ int kvm_pgtable_get_leaf(struct kvm_pgtable *pgt, u64 addr, } struct hyp_map_data { - u64 phys; + const u64 phys; kvm_pte_t attr; }; @@ -407,13 +410,12 @@ enum kvm_pgtable_prot kvm_pgtable_hyp_pte_prot(kvm_pte_t pte) static bool hyp_map_walker_try_leaf(const struct kvm_pgtable_visit_ctx *ctx, struct hyp_map_data *data) { + u64 phys = data->phys + (ctx->addr - ctx->start); kvm_pte_t new; - u64 granule = kvm_granule_size(ctx->level), phys = data->phys; if (!kvm_block_mapping_supported(ctx, phys)) return false; - data->phys += granule; new = kvm_init_valid_leaf_pte(phys, data->attr, ctx->level); if (ctx->old == new) return true; @@ -576,7 +578,7 @@ void kvm_pgtable_hyp_destroy(struct kvm_pgtable *pgt) } struct stage2_map_data { - u64 phys; + const u64 phys; kvm_pte_t attr; u8 owner_id; @@ -794,20 +796,43 @@ static bool stage2_pte_executable(kvm_pte_t pte) return !(pte & KVM_PTE_LEAF_ATTR_HI_S2_XN); } +static u64 stage2_map_walker_phys_addr(const struct kvm_pgtable_visit_ctx *ctx, + const struct stage2_map_data *data) +{ + u64 phys = data->phys; + + /* + * Stage-2 walks to update ownership data are communicated to the map + * walker using an invalid PA. Avoid offsetting an already invalid PA, + * which could overflow and make the address valid again. + */ + if (!kvm_phys_is_valid(phys)) + return phys; + + /* + * Otherwise, work out the correct PA based on how far the walk has + * gotten. + */ + return phys + (ctx->addr - ctx->start); +} + static bool stage2_leaf_mapping_allowed(const struct kvm_pgtable_visit_ctx *ctx, struct stage2_map_data *data) { + u64 phys = stage2_map_walker_phys_addr(ctx, data); + if (data->force_pte && (ctx->level < (KVM_PGTABLE_MAX_LEVELS - 1))) return false; - return kvm_block_mapping_supported(ctx, data->phys); + return kvm_block_mapping_supported(ctx, phys); } static int stage2_map_walker_try_leaf(const struct kvm_pgtable_visit_ctx *ctx, struct stage2_map_data *data) { kvm_pte_t new; - u64 granule = kvm_granule_size(ctx->level), phys = data->phys; + u64 phys = stage2_map_walker_phys_addr(ctx, data); + u64 granule = kvm_granule_size(ctx->level); struct kvm_pgtable *pgt = data->mmu->pgt; struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; @@ -841,8 +866,6 @@ static int stage2_map_walker_try_leaf(const struct kvm_pgtable_visit_ctx *ctx, stage2_make_pte(ctx, new); - if (kvm_phys_is_valid(phys)) - data->phys += granule; return 0; } diff --git a/arch/arm64/kvm/inject_fault.c b/arch/arm64/kvm/inject_fault.c index 64c3aec0d937..0bd93a5f21ce 100644 --- a/arch/arm64/kvm/inject_fault.c +++ b/arch/arm64/kvm/inject_fault.c @@ -204,7 +204,7 @@ void kvm_inject_size_fault(struct kvm_vcpu *vcpu) * Size Fault at level 0, as if exceeding PARange. * * Non-LPAE guests will only get the external abort, as there - * is no way to to describe the ASF. + * is no way to describe the ASF. */ if (vcpu_el1_is_32bit(vcpu) && !(vcpu_read_sys_reg(vcpu, TCR_EL1) & TTBCR_EAE)) diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c index 469d816f356f..93a47a515c13 100644 --- a/arch/arm64/kvm/vgic/vgic-v3.c +++ b/arch/arm64/kvm/vgic/vgic-v3.c @@ -616,6 +616,10 @@ static const struct midr_range broken_seis[] = { MIDR_ALL_VERSIONS(MIDR_APPLE_M1_FIRESTORM_MAX), MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD), MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE), + MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD_PRO), + MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE_PRO), + MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD_MAX), + MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE_MAX), {}, }; diff --git a/arch/arm64/kvm/vmid.c b/arch/arm64/kvm/vmid.c index 08978d0672e7..7fe8ba1a2851 100644 --- a/arch/arm64/kvm/vmid.c +++ b/arch/arm64/kvm/vmid.c @@ -47,7 +47,7 @@ static void flush_context(void) int cpu; u64 vmid; - bitmap_clear(vmid_map, 0, NUM_USER_VMIDS); + bitmap_zero(vmid_map, NUM_USER_VMIDS); for_each_possible_cpu(cpu) { vmid = atomic64_xchg_relaxed(&per_cpu(active_vmids, cpu), 0); @@ -182,8 +182,7 @@ int __init kvm_arm_vmid_alloc_init(void) */ WARN_ON(NUM_USER_VMIDS - 1 <= num_possible_cpus()); atomic64_set(&vmid_generation, VMID_FIRST_VERSION); - vmid_map = kcalloc(BITS_TO_LONGS(NUM_USER_VMIDS), - sizeof(*vmid_map), GFP_KERNEL); + vmid_map = bitmap_zalloc(NUM_USER_VMIDS, GFP_KERNEL); if (!vmid_map) return -ENOMEM; @@ -192,5 +191,5 @@ int __init kvm_arm_vmid_alloc_init(void) void __init kvm_arm_vmid_alloc_free(void) { - kfree(vmid_map); + bitmap_free(vmid_map); } diff --git a/arch/arm64/mm/copypage.c b/arch/arm64/mm/copypage.c index 4aadcfb01754..a7bb20055ce0 100644 --- a/arch/arm64/mm/copypage.c +++ b/arch/arm64/mm/copypage.c @@ -21,9 +21,10 @@ void copy_highpage(struct page *to, struct page *from) copy_page(kto, kfrom); + if (kasan_hw_tags_enabled()) + page_kasan_tag_reset(to); + if (system_supports_mte() && page_mte_tagged(from)) { - if (kasan_hw_tags_enabled()) - page_kasan_tag_reset(to); /* It's a new page, shouldn't have been tagged yet */ WARN_ON_ONCE(!try_page_mte_tagging(to)); mte_copy_page_tags(kto, kfrom); diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 9e0db5c387e3..cb21ccd7940d 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -480,8 +480,8 @@ static void do_bad_area(unsigned long far, unsigned long esr, } } -#define VM_FAULT_BADMAP 0x010000 -#define VM_FAULT_BADACCESS 0x020000 +#define VM_FAULT_BADMAP ((__force vm_fault_t)0x010000) +#define VM_FAULT_BADACCESS ((__force vm_fault_t)0x020000) static vm_fault_t __do_page_fault(struct mm_struct *mm, unsigned long addr, unsigned int mm_flags, unsigned long vm_flags, diff --git a/arch/m68k/kernel/signal.c b/arch/m68k/kernel/signal.c index b9f6908a31bc..ba468b5f3f0b 100644 --- a/arch/m68k/kernel/signal.c +++ b/arch/m68k/kernel/signal.c @@ -858,11 +858,17 @@ static inline int rt_setup_ucontext(struct ucontext __user *uc, struct pt_regs * } static inline void __user * -get_sigframe(struct ksignal *ksig, size_t frame_size) +get_sigframe(struct ksignal *ksig, struct pt_regs *tregs, size_t frame_size) { unsigned long usp = sigsp(rdusp(), ksig); + unsigned long gap = 0; - return (void __user *)((usp - frame_size) & -8UL); + if (CPU_IS_020_OR_030 && tregs->format == 0xb) { + /* USP is unreliable so use worst-case value */ + gap = 256; + } + + return (void __user *)((usp - gap - frame_size) & -8UL); } static int setup_frame(struct ksignal *ksig, sigset_t *set, @@ -880,7 +886,7 @@ static int setup_frame(struct ksignal *ksig, sigset_t *set, return -EFAULT; } - frame = get_sigframe(ksig, sizeof(*frame) + fsize); + frame = get_sigframe(ksig, tregs, sizeof(*frame) + fsize); if (fsize) err |= copy_to_user (frame + 1, regs + 1, fsize); @@ -952,7 +958,7 @@ static int setup_rt_frame(struct ksignal *ksig, sigset_t *set, return -EFAULT; } - frame = get_sigframe(ksig, sizeof(*frame)); + frame = get_sigframe(ksig, tregs, sizeof(*frame)); if (fsize) err |= copy_to_user (&frame->uc.uc_extra, regs + 1, fsize); diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index c2f5498d207f..675a8660cb85 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -79,6 +79,7 @@ config MIPS select HAVE_LD_DEAD_CODE_DATA_ELIMINATION select HAVE_MOD_ARCH_SPECIFIC select HAVE_NMI + select HAVE_PATA_PLATFORM select HAVE_PERF_EVENTS select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP diff --git a/arch/mips/alchemy/common/dbdma.c b/arch/mips/alchemy/common/dbdma.c index 5ab043000409..6a3c890f7bbf 100644 --- a/arch/mips/alchemy/common/dbdma.c +++ b/arch/mips/alchemy/common/dbdma.c @@ -30,6 +30,7 @@ * */ +#include <linux/dma-map-ops.h> /* for dma_default_coherent */ #include <linux/init.h> #include <linux/kernel.h> #include <linux/slab.h> @@ -623,17 +624,18 @@ u32 au1xxx_dbdma_put_source(u32 chanid, dma_addr_t buf, int nbytes, u32 flags) dp->dscr_cmd0 &= ~DSCR_CMD0_IE; /* - * There is an errata on the Au1200/Au1550 parts that could result - * in "stale" data being DMA'ed. It has to do with the snoop logic on - * the cache eviction buffer. DMA_NONCOHERENT is on by default for - * these parts. If it is fixed in the future, these dma_cache_inv will - * just be nothing more than empty macros. See io.h. + * There is an erratum on certain Au1200/Au1550 revisions that could + * result in "stale" data being DMA'ed. It has to do with the snoop + * logic on the cache eviction buffer. dma_default_coherent is set + * to false on these parts. */ - dma_cache_wback_inv((unsigned long)buf, nbytes); + if (!dma_default_coherent) + dma_cache_wback_inv(KSEG0ADDR(buf), nbytes); dp->dscr_cmd0 |= DSCR_CMD0_V; /* Let it rip */ wmb(); /* drain writebuffer */ dma_cache_wback_inv((unsigned long)dp, sizeof(*dp)); ctp->chan_ptr->ddma_dbell = 0; + wmb(); /* force doorbell write out to dma engine */ /* Get next descriptor pointer. */ ctp->put_ptr = phys_to_virt(DSCR_GET_NXTPTR(dp->dscr_nxtptr)); @@ -685,17 +687,18 @@ u32 au1xxx_dbdma_put_dest(u32 chanid, dma_addr_t buf, int nbytes, u32 flags) dp->dscr_source1, dp->dscr_dest0, dp->dscr_dest1); #endif /* - * There is an errata on the Au1200/Au1550 parts that could result in - * "stale" data being DMA'ed. It has to do with the snoop logic on the - * cache eviction buffer. DMA_NONCOHERENT is on by default for these - * parts. If it is fixed in the future, these dma_cache_inv will just - * be nothing more than empty macros. See io.h. + * There is an erratum on certain Au1200/Au1550 revisions that could + * result in "stale" data being DMA'ed. It has to do with the snoop + * logic on the cache eviction buffer. dma_default_coherent is set + * to false on these parts. */ - dma_cache_inv((unsigned long)buf, nbytes); + if (!dma_default_coherent) + dma_cache_inv(KSEG0ADDR(buf), nbytes); dp->dscr_cmd0 |= DSCR_CMD0_V; /* Let it rip */ wmb(); /* drain writebuffer */ dma_cache_wback_inv((unsigned long)dp, sizeof(*dp)); ctp->chan_ptr->ddma_dbell = 0; + wmb(); /* force doorbell write out to dma engine */ /* Get next descriptor pointer. */ ctp->put_ptr = phys_to_virt(DSCR_GET_NXTPTR(dp->dscr_nxtptr)); diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c index 6d15a398d389..e79adcb128e6 100644 --- a/arch/mips/kernel/cpu-probe.c +++ b/arch/mips/kernel/cpu-probe.c @@ -1502,6 +1502,10 @@ static inline void cpu_probe_alchemy(struct cpuinfo_mips *c, unsigned int cpu) break; } break; + case PRID_IMP_NETLOGIC_AU13XX: + c->cputype = CPU_ALCHEMY; + __cpu_name[cpu] = "Au1300"; + break; } } @@ -1863,6 +1867,7 @@ void cpu_probe(void) cpu_probe_mips(c, cpu); break; case PRID_COMP_ALCHEMY: + case PRID_COMP_NETLOGIC: cpu_probe_alchemy(c, cpu); break; case PRID_COMP_SIBYTE: diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index febdc5564638..c0e65135481b 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -158,10 +158,6 @@ static unsigned long __init init_initrd(void) pr_err("initrd start must be page aligned\n"); goto disable; } - if (initrd_start < PAGE_OFFSET) { - pr_err("initrd start < PAGE_OFFSET\n"); - goto disable; - } /* * Sanitize initrd addresses. For example firmware @@ -174,6 +170,11 @@ static unsigned long __init init_initrd(void) initrd_end = (unsigned long)__va(end); initrd_start = (unsigned long)__va(__pa(initrd_start)); + if (initrd_start < PAGE_OFFSET) { + pr_err("initrd start < PAGE_OFFSET\n"); + goto disable; + } + ROOT_DEV = Root_RAM0; return PFN_UP(end); disable: diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index 466a25525364..967bde65dd0e 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -130,6 +130,10 @@ config PM config STACKTRACE_SUPPORT def_bool y +config LOCKDEP_SUPPORT + bool + default y + config ISA_DMA_API bool diff --git a/arch/parisc/Kconfig.debug b/arch/parisc/Kconfig.debug index f66554cd5c45..3a059cb5e112 100644 --- a/arch/parisc/Kconfig.debug +++ b/arch/parisc/Kconfig.debug @@ -1 +1,12 @@ # SPDX-License-Identifier: GPL-2.0 +# +config LIGHTWEIGHT_SPINLOCK_CHECK + bool "Enable lightweight spinlock checks" + depends on SMP && !DEBUG_SPINLOCK + default y + help + Add checks with low performance impact to the spinlock functions + to catch memory overwrites at runtime. For more advanced + spinlock debugging you should choose the DEBUG_SPINLOCK option + which will detect unitialized spinlocks too. + If unsure say Y here. diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h index 0bdee6724132..c8b6928cee1e 100644 --- a/arch/parisc/include/asm/cacheflush.h +++ b/arch/parisc/include/asm/cacheflush.h @@ -48,6 +48,10 @@ void flush_dcache_page(struct page *page); #define flush_dcache_mmap_lock(mapping) xa_lock_irq(&mapping->i_pages) #define flush_dcache_mmap_unlock(mapping) xa_unlock_irq(&mapping->i_pages) +#define flush_dcache_mmap_lock_irqsave(mapping, flags) \ + xa_lock_irqsave(&mapping->i_pages, flags) +#define flush_dcache_mmap_unlock_irqrestore(mapping, flags) \ + xa_unlock_irqrestore(&mapping->i_pages, flags) #define flush_icache_page(vma,page) do { \ flush_kernel_dcache_page_addr(page_address(page)); \ diff --git a/arch/parisc/include/asm/spinlock.h b/arch/parisc/include/asm/spinlock.h index a6e5d66a7656..edfcb9858bcb 100644 --- a/arch/parisc/include/asm/spinlock.h +++ b/arch/parisc/include/asm/spinlock.h @@ -7,10 +7,26 @@ #include <asm/processor.h> #include <asm/spinlock_types.h> +#define SPINLOCK_BREAK_INSN 0x0000c006 /* break 6,6 */ + +static inline void arch_spin_val_check(int lock_val) +{ + if (IS_ENABLED(CONFIG_LIGHTWEIGHT_SPINLOCK_CHECK)) + asm volatile( "andcm,= %0,%1,%%r0\n" + ".word %2\n" + : : "r" (lock_val), "r" (__ARCH_SPIN_LOCK_UNLOCKED_VAL), + "i" (SPINLOCK_BREAK_INSN)); +} + static inline int arch_spin_is_locked(arch_spinlock_t *x) { - volatile unsigned int *a = __ldcw_align(x); - return READ_ONCE(*a) == 0; + volatile unsigned int *a; + int lock_val; + + a = __ldcw_align(x); + lock_val = READ_ONCE(*a); + arch_spin_val_check(lock_val); + return (lock_val == 0); } static inline void arch_spin_lock(arch_spinlock_t *x) @@ -18,9 +34,18 @@ static inline void arch_spin_lock(arch_spinlock_t *x) volatile unsigned int *a; a = __ldcw_align(x); - while (__ldcw(a) == 0) + do { + int lock_val_old; + + lock_val_old = __ldcw(a); + arch_spin_val_check(lock_val_old); + if (lock_val_old) + return; /* got lock */ + + /* wait until we should try to get lock again */ while (*a == 0) continue; + } while (1); } static inline void arch_spin_unlock(arch_spinlock_t *x) @@ -29,15 +54,19 @@ static inline void arch_spin_unlock(arch_spinlock_t *x) a = __ldcw_align(x); /* Release with ordered store. */ - __asm__ __volatile__("stw,ma %0,0(%1)" : : "r"(1), "r"(a) : "memory"); + __asm__ __volatile__("stw,ma %0,0(%1)" + : : "r"(__ARCH_SPIN_LOCK_UNLOCKED_VAL), "r"(a) : "memory"); } static inline int arch_spin_trylock(arch_spinlock_t *x) { volatile unsigned int *a; + int lock_val; a = __ldcw_align(x); - return __ldcw(a) != 0; + lock_val = __ldcw(a); + arch_spin_val_check(lock_val); + return lock_val != 0; } /* diff --git a/arch/parisc/include/asm/spinlock_types.h b/arch/parisc/include/asm/spinlock_types.h index ca39ee350c3f..d65934079ebd 100644 --- a/arch/parisc/include/asm/spinlock_types.h +++ b/arch/parisc/include/asm/spinlock_types.h @@ -2,13 +2,17 @@ #ifndef __ASM_SPINLOCK_TYPES_H #define __ASM_SPINLOCK_TYPES_H +#define __ARCH_SPIN_LOCK_UNLOCKED_VAL 0x1a46 + typedef struct { #ifdef CONFIG_PA20 volatile unsigned int slock; -# define __ARCH_SPIN_LOCK_UNLOCKED { 1 } +# define __ARCH_SPIN_LOCK_UNLOCKED { __ARCH_SPIN_LOCK_UNLOCKED_VAL } #else volatile unsigned int lock[4]; -# define __ARCH_SPIN_LOCK_UNLOCKED { { 1, 1, 1, 1 } } +# define __ARCH_SPIN_LOCK_UNLOCKED \ + { { __ARCH_SPIN_LOCK_UNLOCKED_VAL, __ARCH_SPIN_LOCK_UNLOCKED_VAL, \ + __ARCH_SPIN_LOCK_UNLOCKED_VAL, __ARCH_SPIN_LOCK_UNLOCKED_VAL } } #endif } arch_spinlock_t; diff --git a/arch/parisc/kernel/alternative.c b/arch/parisc/kernel/alternative.c index 66f5672c70bd..25c4d6c3375d 100644 --- a/arch/parisc/kernel/alternative.c +++ b/arch/parisc/kernel/alternative.c @@ -25,7 +25,7 @@ void __init_or_module apply_alternatives(struct alt_instr *start, { struct alt_instr *entry; int index = 0, applied = 0; - int num_cpus = num_online_cpus(); + int num_cpus = num_present_cpus(); u16 cond_check; cond_check = ALT_COND_ALWAYS | diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c index 1d3b8bc8a623..ca4a302d4365 100644 --- a/arch/parisc/kernel/cache.c +++ b/arch/parisc/kernel/cache.c @@ -399,6 +399,7 @@ void flush_dcache_page(struct page *page) unsigned long offset; unsigned long addr, old_addr = 0; unsigned long count = 0; + unsigned long flags; pgoff_t pgoff; if (mapping && !mapping_mapped(mapping)) { @@ -420,7 +421,7 @@ void flush_dcache_page(struct page *page) * to flush one address here for them all to become coherent * on machines that support equivalent aliasing */ - flush_dcache_mmap_lock(mapping); + flush_dcache_mmap_lock_irqsave(mapping, flags); vma_interval_tree_foreach(mpnt, &mapping->i_mmap, pgoff, pgoff) { offset = (pgoff - mpnt->vm_pgoff) << PAGE_SHIFT; addr = mpnt->vm_start + offset; @@ -460,7 +461,7 @@ void flush_dcache_page(struct page *page) } WARN_ON(++count == 4096); } - flush_dcache_mmap_unlock(mapping); + flush_dcache_mmap_unlock_irqrestore(mapping, flags); } EXPORT_SYMBOL(flush_dcache_page); diff --git a/arch/parisc/kernel/pci-dma.c b/arch/parisc/kernel/pci-dma.c index ba87f791323b..71ed5391f29d 100644 --- a/arch/parisc/kernel/pci-dma.c +++ b/arch/parisc/kernel/pci-dma.c @@ -446,11 +446,27 @@ void arch_dma_free(struct device *dev, size_t size, void *vaddr, void arch_sync_dma_for_device(phys_addr_t paddr, size_t size, enum dma_data_direction dir) { + /* + * fdc: The data cache line is written back to memory, if and only if + * it is dirty, and then invalidated from the data cache. + */ flush_kernel_dcache_range((unsigned long)phys_to_virt(paddr), size); } void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size, enum dma_data_direction dir) { - flush_kernel_dcache_range((unsigned long)phys_to_virt(paddr), size); + unsigned long addr = (unsigned long) phys_to_virt(paddr); + + switch (dir) { + case DMA_TO_DEVICE: + case DMA_BIDIRECTIONAL: + flush_kernel_dcache_range(addr, size); + return; + case DMA_FROM_DEVICE: + purge_kernel_dcache_range_asm(addr, addr + size); + return; + default: + BUG(); + } } diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c index 97c6f875bd0e..24411ab79c30 100644 --- a/arch/parisc/kernel/process.c +++ b/arch/parisc/kernel/process.c @@ -122,13 +122,18 @@ void machine_power_off(void) /* It seems we have no way to power the system off via * software. The user has to press the button himself. */ - printk(KERN_EMERG "System shut down completed.\n" - "Please power this system off now."); + printk("Power off or press RETURN to reboot.\n"); /* prevent soft lockup/stalled CPU messages for endless loop. */ rcu_sysrq_start(); lockup_detector_soft_poweroff(); - for (;;); + while (1) { + /* reboot if user presses RETURN key */ + if (pdc_iodc_getc() == 13) { + printk("Rebooting...\n"); + machine_restart(NULL); + } + } } void (*pm_power_off)(void); diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c index f9696fbf646c..304eebd1c83e 100644 --- a/arch/parisc/kernel/traps.c +++ b/arch/parisc/kernel/traps.c @@ -47,6 +47,10 @@ #include <linux/kgdb.h> #include <linux/kprobes.h> +#if defined(CONFIG_LIGHTWEIGHT_SPINLOCK_CHECK) +#include <asm/spinlock.h> +#endif + #include "../math-emu/math-emu.h" /* for handle_fpe() */ static void parisc_show_stack(struct task_struct *task, @@ -291,24 +295,30 @@ static void handle_break(struct pt_regs *regs) } #ifdef CONFIG_KPROBES - if (unlikely(iir == PARISC_KPROBES_BREAK_INSN)) { + if (unlikely(iir == PARISC_KPROBES_BREAK_INSN && !user_mode(regs))) { parisc_kprobe_break_handler(regs); return; } - if (unlikely(iir == PARISC_KPROBES_BREAK_INSN2)) { + if (unlikely(iir == PARISC_KPROBES_BREAK_INSN2 && !user_mode(regs))) { parisc_kprobe_ss_handler(regs); return; } #endif #ifdef CONFIG_KGDB - if (unlikely(iir == PARISC_KGDB_COMPILED_BREAK_INSN || - iir == PARISC_KGDB_BREAK_INSN)) { + if (unlikely((iir == PARISC_KGDB_COMPILED_BREAK_INSN || + iir == PARISC_KGDB_BREAK_INSN)) && !user_mode(regs)) { kgdb_handle_exception(9, SIGTRAP, 0, regs); return; } #endif +#ifdef CONFIG_LIGHTWEIGHT_SPINLOCK_CHECK + if ((iir == SPINLOCK_BREAK_INSN) && !user_mode(regs)) { + die_if_kernel("Spinlock was trashed", regs, 1); + } +#endif + if (unlikely(iir != GDB_BREAK_INSN)) parisc_printk_ratelimited(0, regs, KERN_DEBUG "break %d,%d: pid=%d command='%s'\n", diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 539d1f03ff42..bff5820b7cda 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -906,11 +906,17 @@ config DATA_SHIFT config ARCH_FORCE_MAX_ORDER int "Order of maximal physically contiguous allocations" + range 7 8 if PPC64 && PPC_64K_PAGES default "8" if PPC64 && PPC_64K_PAGES + range 12 12 if PPC64 && !PPC_64K_PAGES default "12" if PPC64 && !PPC_64K_PAGES + range 8 10 if PPC32 && PPC_16K_PAGES default "8" if PPC32 && PPC_16K_PAGES + range 6 10 if PPC32 && PPC_64K_PAGES default "6" if PPC32 && PPC_64K_PAGES + range 4 10 if PPC32 && PPC_256K_PAGES default "4" if PPC32 && PPC_256K_PAGES + range 10 10 default "10" help The kernel page allocator limits the size of maximal physically diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index 85cde5bf04b7..771b79423bbc 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -34,8 +34,6 @@ endif BOOTCFLAGS := -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \ -fno-strict-aliasing -O2 -msoft-float -mno-altivec -mno-vsx \ - $(call cc-option,-mno-prefixed) $(call cc-option,-mno-pcrel) \ - $(call cc-option,-mno-mma) \ $(call cc-option,-mno-spe) $(call cc-option,-mspe=no) \ -pipe -fomit-frame-pointer -fno-builtin -fPIC -nostdinc \ $(LINUXINCLUDE) @@ -71,6 +69,10 @@ BOOTAFLAGS := -D__ASSEMBLY__ $(BOOTCFLAGS) -nostdinc BOOTARFLAGS := -crD +BOOTCFLAGS += $(call cc-option,-mno-prefixed) \ + $(call cc-option,-mno-pcrel) \ + $(call cc-option,-mno-mma) + ifdef CONFIG_CC_IS_CLANG BOOTCFLAGS += $(CLANG_FLAGS) BOOTAFLAGS += $(CLANG_FLAGS) diff --git a/arch/powerpc/crypto/Kconfig b/arch/powerpc/crypto/Kconfig index 7113f9355165..ad1872518992 100644 --- a/arch/powerpc/crypto/Kconfig +++ b/arch/powerpc/crypto/Kconfig @@ -96,7 +96,7 @@ config CRYPTO_AES_PPC_SPE config CRYPTO_AES_GCM_P10 tristate "Stitched AES/GCM acceleration support on P10 or later CPU (PPC)" - depends on PPC64 && CPU_LITTLE_ENDIAN + depends on PPC64 && CPU_LITTLE_ENDIAN && VSX select CRYPTO_LIB_AES select CRYPTO_ALGAPI select CRYPTO_AEAD diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h index 678b5bdc79b1..34e14dfd8e04 100644 --- a/arch/powerpc/include/asm/iommu.h +++ b/arch/powerpc/include/asm/iommu.h @@ -205,7 +205,6 @@ extern void iommu_register_group(struct iommu_table_group *table_group, int pci_domain_number, unsigned long pe_num); extern int iommu_add_device(struct iommu_table_group *table_group, struct device *dev); -extern void iommu_del_device(struct device *dev); extern long iommu_tce_xchg(struct mm_struct *mm, struct iommu_table *tbl, unsigned long entry, unsigned long *hpa, enum dma_data_direction *direction); @@ -229,10 +228,6 @@ static inline int iommu_add_device(struct iommu_table_group *table_group, { return 0; } - -static inline void iommu_del_device(struct device *dev) -{ -} #endif /* !CONFIG_IOMMU_API */ u64 dma_iommu_get_required_mask(struct device *dev); diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c index 038ce8d9061d..8920862ffd79 100644 --- a/arch/powerpc/kernel/dma-iommu.c +++ b/arch/powerpc/kernel/dma-iommu.c @@ -144,7 +144,7 @@ static bool dma_iommu_bypass_supported(struct device *dev, u64 mask) /* We support DMA to/from any memory page via the iommu */ int dma_iommu_dma_supported(struct device *dev, u64 mask) { - struct iommu_table *tbl = get_iommu_table_base(dev); + struct iommu_table *tbl; if (dev_is_pci(dev) && dma_iommu_bypass_supported(dev, mask)) { /* @@ -162,6 +162,8 @@ int dma_iommu_dma_supported(struct device *dev, u64 mask) return 1; } + tbl = get_iommu_table_base(dev); + if (!tbl) { dev_err(dev, "Warning: IOMMU dma not supported: mask 0x%08llx, table unavailable\n", mask); return 0; diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index 0089dd49b4cb..67f0b01e6ff5 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -518,7 +518,7 @@ int ppc_iommu_map_sg(struct device *dev, struct iommu_table *tbl, /* Convert entry to a dma_addr_t */ entry += tbl->it_offset; dma_addr = entry << tbl->it_page_shift; - dma_addr |= (s->offset & ~IOMMU_PAGE_MASK(tbl)); + dma_addr |= (vaddr & ~IOMMU_PAGE_MASK(tbl)); DBG(" - %lu pages, entry: %lx, dma_addr: %lx\n", npages, entry, dma_addr); @@ -905,6 +905,7 @@ void *iommu_alloc_coherent(struct device *dev, struct iommu_table *tbl, unsigned int order; unsigned int nio_pages, io_order; struct page *page; + int tcesize = (1 << tbl->it_page_shift); size = PAGE_ALIGN(size); order = get_order(size); @@ -931,7 +932,8 @@ void *iommu_alloc_coherent(struct device *dev, struct iommu_table *tbl, memset(ret, 0, size); /* Set up tces to cover the allocated range */ - nio_pages = size >> tbl->it_page_shift; + nio_pages = IOMMU_PAGE_ALIGN(size, tbl) >> tbl->it_page_shift; + io_order = get_iommu_order(size, tbl); mapping = iommu_alloc(dev, tbl, ret, nio_pages, DMA_BIDIRECTIONAL, mask >> tbl->it_page_shift, io_order, 0); @@ -939,7 +941,8 @@ void *iommu_alloc_coherent(struct device *dev, struct iommu_table *tbl, free_pages((unsigned long)ret, order); return NULL; } - *dma_handle = mapping; + + *dma_handle = mapping | ((u64)ret & (tcesize - 1)); return ret; } @@ -950,7 +953,7 @@ void iommu_free_coherent(struct iommu_table *tbl, size_t size, unsigned int nio_pages; size = PAGE_ALIGN(size); - nio_pages = size >> tbl->it_page_shift; + nio_pages = IOMMU_PAGE_ALIGN(size, tbl) >> tbl->it_page_shift; iommu_free(tbl, dma_handle, nio_pages); size = PAGE_ALIGN(size); free_pages((unsigned long)vaddr, get_order(size)); @@ -1168,23 +1171,6 @@ int iommu_add_device(struct iommu_table_group *table_group, struct device *dev) } EXPORT_SYMBOL_GPL(iommu_add_device); -void iommu_del_device(struct device *dev) -{ - /* - * Some devices might not have IOMMU table and group - * and we needn't detach them from the associated - * IOMMU groups - */ - if (!device_iommu_mapped(dev)) { - pr_debug("iommu_tce: skipping device %s with no tbl\n", - dev_name(dev)); - return; - } - - iommu_group_remove_device(dev); -} -EXPORT_SYMBOL_GPL(iommu_del_device); - /* * A simple iommu_table_group_ops which only allows reusing the existing * iommu_table. This handles VFIO for POWER7 or the nested KVM. diff --git a/arch/powerpc/kernel/isa-bridge.c b/arch/powerpc/kernel/isa-bridge.c index 85bdd7d3652f..48e0eaf1ad61 100644 --- a/arch/powerpc/kernel/isa-bridge.c +++ b/arch/powerpc/kernel/isa-bridge.c @@ -93,11 +93,12 @@ static int process_ISA_OF_ranges(struct device_node *isa_node, } inval_range: - if (!phb_io_base_phys) { + if (phb_io_base_phys) { pr_err("no ISA IO ranges or unexpected isa range, mapping 64k\n"); remap_isa_base(phb_io_base_phys, 0x10000); + return 0; } - return 0; + return -EINVAL; } diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c index 26245aaf12b8..2297aa764ecd 100644 --- a/arch/powerpc/mm/book3s64/radix_pgtable.c +++ b/arch/powerpc/mm/book3s64/radix_pgtable.c @@ -1040,8 +1040,8 @@ void radix__ptep_set_access_flags(struct vm_area_struct *vma, pte_t *ptep, pte_t entry, unsigned long address, int psize) { struct mm_struct *mm = vma->vm_mm; - unsigned long set = pte_val(entry) & (_PAGE_DIRTY | _PAGE_ACCESSED | - _PAGE_RW | _PAGE_EXEC); + unsigned long set = pte_val(entry) & (_PAGE_DIRTY | _PAGE_SOFT_DIRTY | + _PAGE_ACCESSED | _PAGE_RW | _PAGE_EXEC); unsigned long change = pte_val(entry) ^ pte_val(*ptep); /* diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c index e93aefcfb83f..37043dfc1add 100644 --- a/arch/powerpc/net/bpf_jit_comp.c +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -101,6 +101,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp) bpf_hdr = jit_data->header; proglen = jit_data->proglen; extra_pass = true; + /* During extra pass, ensure index is reset before repopulating extable entries */ + cgctx.exentry_idx = 0; goto skip_init_ctx; } diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig index 0d9b7609c7d5..3e2e252016f7 100644 --- a/arch/powerpc/platforms/Kconfig +++ b/arch/powerpc/platforms/Kconfig @@ -265,6 +265,7 @@ config CPM2 config FSL_ULI1575 bool "ULI1575 PCIe south bridge support" depends on FSL_SOC_BOOKE || PPC_86xx + depends on PCI select FSL_PCI select GENERIC_ISA_DMA help diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index 233a50e65fce..7725492097b6 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -865,28 +865,3 @@ void __init pnv_pci_init(void) /* Configure IOMMU DMA hooks */ set_pci_dma_ops(&dma_iommu_ops); } - -static int pnv_tce_iommu_bus_notifier(struct notifier_block *nb, - unsigned long action, void *data) -{ - struct device *dev = data; - - switch (action) { - case BUS_NOTIFY_DEL_DEVICE: - iommu_del_device(dev); - return 0; - default: - return 0; - } -} - -static struct notifier_block pnv_tce_iommu_bus_nb = { - .notifier_call = pnv_tce_iommu_bus_notifier, -}; - -static int __init pnv_tce_iommu_bus_notifier_init(void) -{ - bus_register_notifier(&pci_bus_type, &pnv_tce_iommu_bus_nb); - return 0; -} -machine_subsys_initcall_sync(powernv, pnv_tce_iommu_bus_notifier_init); diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 7464fa6e4145..918f511837db 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -91,19 +91,24 @@ static struct iommu_table_group *iommu_pseries_alloc_group(int node) static void iommu_pseries_free_group(struct iommu_table_group *table_group, const char *node_name) { - struct iommu_table *tbl; - if (!table_group) return; - tbl = table_group->tables[0]; #ifdef CONFIG_IOMMU_API if (table_group->group) { iommu_group_put(table_group->group); BUG_ON(table_group->group); } #endif - iommu_tce_table_put(tbl); + + /* Default DMA window table is at index 0, while DDW at 1. SR-IOV + * adapters only have table on index 1. + */ + if (table_group->tables[0]) + iommu_tce_table_put(table_group->tables[0]); + + if (table_group->tables[1]) + iommu_tce_table_put(table_group->tables[1]); kfree(table_group); } @@ -1695,31 +1700,6 @@ static int __init disable_multitce(char *str) __setup("multitce=", disable_multitce); -static int tce_iommu_bus_notifier(struct notifier_block *nb, - unsigned long action, void *data) -{ - struct device *dev = data; - - switch (action) { - case BUS_NOTIFY_DEL_DEVICE: - iommu_del_device(dev); - return 0; - default: - return 0; - } -} - -static struct notifier_block tce_iommu_bus_nb = { - .notifier_call = tce_iommu_bus_notifier, -}; - -static int __init tce_iommu_bus_notifier_init(void) -{ - bus_register_notifier(&pci_bus_type, &tce_iommu_bus_nb); - return 0; -} -machine_subsys_initcall_sync(pseries, tce_iommu_bus_notifier_init); - #ifdef CONFIG_SPAPR_TCE_IOMMU struct iommu_group *pSeries_pci_device_group(struct pci_controller *hose, struct pci_dev *pdev) diff --git a/arch/riscv/kernel/probes/Makefile b/arch/riscv/kernel/probes/Makefile index c40139e9ca47..8265ff497977 100644 --- a/arch/riscv/kernel/probes/Makefile +++ b/arch/riscv/kernel/probes/Makefile @@ -4,3 +4,5 @@ obj-$(CONFIG_RETHOOK) += rethook.o rethook_trampoline.o obj-$(CONFIG_KPROBES_ON_FTRACE) += ftrace.o obj-$(CONFIG_UPROBES) += uprobes.o decode-insn.o simulate-insn.o CFLAGS_REMOVE_simulate-insn.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_rethook.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_rethook_trampoline.o = $(CC_FLAGS_FTRACE) diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index db20c1589a98..6dab9c1be508 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -469,19 +469,11 @@ config SCHED_SMT config SCHED_MC def_bool n -config SCHED_BOOK - def_bool n - -config SCHED_DRAWER - def_bool n - config SCHED_TOPOLOGY def_bool y prompt "Topology scheduler support" select SCHED_SMT select SCHED_MC - select SCHED_BOOK - select SCHED_DRAWER help Topology scheduler support improves the CPU scheduler's decision making when dealing with machines that have multi-threading, @@ -716,7 +708,6 @@ config EADM_SCH config VFIO_CCW def_tristate n prompt "Support for VFIO-CCW subchannels" - depends on S390_CCW_IOMMU depends on VFIO select VFIO_MDEV help @@ -728,7 +719,7 @@ config VFIO_CCW config VFIO_AP def_tristate n prompt "VFIO support for AP devices" - depends on S390_AP_IOMMU && KVM + depends on KVM depends on VFIO depends on ZCRYPT select VFIO_MDEV diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 4ccf66d29fc2..be3bf03bf361 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -591,8 +591,6 @@ CONFIG_VIRTIO_BALLOON=m CONFIG_VIRTIO_INPUT=y CONFIG_VHOST_NET=m CONFIG_VHOST_VSOCK=m -CONFIG_S390_CCW_IOMMU=y -CONFIG_S390_AP_IOMMU=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y @@ -703,6 +701,7 @@ CONFIG_IMA_DEFAULT_HASH_SHA256=y CONFIG_IMA_WRITE_POLICY=y CONFIG_IMA_APPRAISE=y CONFIG_LSM="yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor" +CONFIG_INIT_STACK_NONE=y CONFIG_CRYPTO_USER=m # CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set CONFIG_CRYPTO_PCRYPT=m diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index 693297a2e897..769c7eed8b6a 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -580,8 +580,6 @@ CONFIG_VIRTIO_BALLOON=m CONFIG_VIRTIO_INPUT=y CONFIG_VHOST_NET=m CONFIG_VHOST_VSOCK=m -CONFIG_S390_CCW_IOMMU=y -CONFIG_S390_AP_IOMMU=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y @@ -686,6 +684,7 @@ CONFIG_IMA_DEFAULT_HASH_SHA256=y CONFIG_IMA_WRITE_POLICY=y CONFIG_IMA_APPRAISE=y CONFIG_LSM="yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor" +CONFIG_INIT_STACK_NONE=y CONFIG_CRYPTO_FIPS=y CONFIG_CRYPTO_USER=m # CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig index 33a232bb68af..6f68b39817ef 100644 --- a/arch/s390/configs/zfcpdump_defconfig +++ b/arch/s390/configs/zfcpdump_defconfig @@ -67,6 +67,7 @@ CONFIG_ZFCP=y # CONFIG_MISC_FILESYSTEMS is not set # CONFIG_NETWORK_FILESYSTEMS is not set CONFIG_LSM="yama,loadpin,safesetid,integrity" +CONFIG_INIT_STACK_NONE=y # CONFIG_ZLIB_DFLTCC is not set CONFIG_XZ_DEC_MICROLZMA=y CONFIG_PRINTK_TIME=y diff --git a/arch/s390/crypto/chacha-glue.c b/arch/s390/crypto/chacha-glue.c index 7752bd314558..5fae187f947a 100644 --- a/arch/s390/crypto/chacha-glue.c +++ b/arch/s390/crypto/chacha-glue.c @@ -82,7 +82,7 @@ void chacha_crypt_arch(u32 *state, u8 *dst, const u8 *src, * it cannot handle a block of data or less, but otherwise * it can handle data of arbitrary size */ - if (bytes <= CHACHA_BLOCK_SIZE || nrounds != 20) + if (bytes <= CHACHA_BLOCK_SIZE || nrounds != 20 || !MACHINE_HAS_VX) chacha_crypt_generic(state, dst, src, bytes, nrounds); else chacha20_crypt_s390(state, dst, src, bytes, diff --git a/arch/s390/include/asm/compat.h b/arch/s390/include/asm/compat.h index a386070f1d56..3cb9d813f022 100644 --- a/arch/s390/include/asm/compat.h +++ b/arch/s390/include/asm/compat.h @@ -112,7 +112,7 @@ struct compat_statfs64 { u32 f_namelen; u32 f_frsize; u32 f_flags; - u32 f_spare[4]; + u32 f_spare[5]; }; /* diff --git a/arch/s390/include/uapi/asm/statfs.h b/arch/s390/include/uapi/asm/statfs.h index 72604f7792c3..f85b50723dd3 100644 --- a/arch/s390/include/uapi/asm/statfs.h +++ b/arch/s390/include/uapi/asm/statfs.h @@ -30,7 +30,7 @@ struct statfs { unsigned int f_namelen; unsigned int f_frsize; unsigned int f_flags; - unsigned int f_spare[4]; + unsigned int f_spare[5]; }; struct statfs64 { @@ -45,7 +45,7 @@ struct statfs64 { unsigned int f_namelen; unsigned int f_frsize; unsigned int f_flags; - unsigned int f_spare[4]; + unsigned int f_spare[5]; }; #endif diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile index 8983837b3565..6b2a051e1f8a 100644 --- a/arch/s390/kernel/Makefile +++ b/arch/s390/kernel/Makefile @@ -10,6 +10,7 @@ CFLAGS_REMOVE_ftrace.o = $(CC_FLAGS_FTRACE) # Do not trace early setup code CFLAGS_REMOVE_early.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_rethook.o = $(CC_FLAGS_FTRACE) endif diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index 43de939b7af1..f44f70de9661 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -1935,14 +1935,13 @@ static struct shutdown_action __refdata dump_action = { static void dump_reipl_run(struct shutdown_trigger *trigger) { - unsigned long ipib = (unsigned long) reipl_block_actual; struct lowcore *abs_lc; unsigned int csum; csum = (__force unsigned int) csum_partial(reipl_block_actual, reipl_block_actual->hdr.len, 0); abs_lc = get_abs_lowcore(); - abs_lc->ipib = ipib; + abs_lc->ipib = __pa(reipl_block_actual); abs_lc->ipib_checksum = csum; put_abs_lowcore(abs_lc); dump_run(trigger); diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c index 9fd19530c9a5..68adf1de8888 100644 --- a/arch/s390/kernel/topology.c +++ b/arch/s390/kernel/topology.c @@ -95,7 +95,7 @@ out: static void cpu_thread_map(cpumask_t *dst, unsigned int cpu) { static cpumask_t mask; - int i; + unsigned int max_cpu; cpumask_clear(&mask); if (!cpumask_test_cpu(cpu, &cpu_setup_mask)) @@ -104,9 +104,10 @@ static void cpu_thread_map(cpumask_t *dst, unsigned int cpu) if (topology_mode != TOPOLOGY_MODE_HW) goto out; cpu -= cpu % (smp_cpu_mtid + 1); - for (i = 0; i <= smp_cpu_mtid; i++) { - if (cpumask_test_cpu(cpu + i, &cpu_setup_mask)) - cpumask_set_cpu(cpu + i, &mask); + max_cpu = min(cpu + smp_cpu_mtid, nr_cpu_ids - 1); + for (; cpu <= max_cpu; cpu++) { + if (cpumask_test_cpu(cpu, &cpu_setup_mask)) + cpumask_set_cpu(cpu, &mask); } out: cpumask_copy(dst, &mask); @@ -123,25 +124,26 @@ static void add_cpus_to_mask(struct topology_core *tl_core, unsigned int core; for_each_set_bit(core, &tl_core->mask, TOPOLOGY_CORE_BITS) { - unsigned int rcore; - int lcpu, i; + unsigned int max_cpu, rcore; + int cpu; rcore = TOPOLOGY_CORE_BITS - 1 - core + tl_core->origin; - lcpu = smp_find_processor_id(rcore << smp_cpu_mt_shift); - if (lcpu < 0) + cpu = smp_find_processor_id(rcore << smp_cpu_mt_shift); + if (cpu < 0) continue; - for (i = 0; i <= smp_cpu_mtid; i++) { - topo = &cpu_topology[lcpu + i]; + max_cpu = min(cpu + smp_cpu_mtid, nr_cpu_ids - 1); + for (; cpu <= max_cpu; cpu++) { + topo = &cpu_topology[cpu]; topo->drawer_id = drawer->id; topo->book_id = book->id; topo->socket_id = socket->id; topo->core_id = rcore; - topo->thread_id = lcpu + i; + topo->thread_id = cpu; topo->dedicated = tl_core->d; - cpumask_set_cpu(lcpu + i, &drawer->mask); - cpumask_set_cpu(lcpu + i, &book->mask); - cpumask_set_cpu(lcpu + i, &socket->mask); - smp_cpu_set_polarization(lcpu + i, tl_core->pp); + cpumask_set_cpu(cpu, &drawer->mask); + cpumask_set_cpu(cpu, &book->mask); + cpumask_set_cpu(cpu, &socket->mask); + smp_cpu_set_polarization(cpu, tl_core->pp); } } } diff --git a/arch/um/drivers/Makefile b/arch/um/drivers/Makefile index dee6f66353b3..a461a950f051 100644 --- a/arch/um/drivers/Makefile +++ b/arch/um/drivers/Makefile @@ -16,7 +16,8 @@ mconsole-objs := mconsole_kern.o mconsole_user.o hostaudio-objs := hostaudio_kern.o ubd-objs := ubd_kern.o ubd_user.o port-objs := port_kern.o port_user.o -harddog-objs := harddog_kern.o harddog_user.o +harddog-objs := harddog_kern.o +harddog-builtin-$(CONFIG_UML_WATCHDOG) := harddog_user.o harddog_user_exp.o rtc-objs := rtc_kern.o rtc_user.o LDFLAGS_pcap.o = $(shell $(CC) $(KBUILD_CFLAGS) -print-file-name=libpcap.a) @@ -60,6 +61,7 @@ obj-$(CONFIG_PTY_CHAN) += pty.o obj-$(CONFIG_TTY_CHAN) += tty.o obj-$(CONFIG_XTERM_CHAN) += xterm.o xterm_kern.o obj-$(CONFIG_UML_WATCHDOG) += harddog.o +obj-y += $(harddog-builtin-y) $(harddog-builtin-m) obj-$(CONFIG_BLK_DEV_COW_COMMON) += cow_user.o obj-$(CONFIG_UML_RANDOM) += random.o obj-$(CONFIG_VIRTIO_UML) += virtio_uml.o diff --git a/arch/um/drivers/harddog.h b/arch/um/drivers/harddog.h new file mode 100644 index 000000000000..6d9ea60e7133 --- /dev/null +++ b/arch/um/drivers/harddog.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef UM_WATCHDOG_H +#define UM_WATCHDOG_H + +int start_watchdog(int *in_fd_ret, int *out_fd_ret, char *sock); +void stop_watchdog(int in_fd, int out_fd); +int ping_watchdog(int fd); + +#endif /* UM_WATCHDOG_H */ diff --git a/arch/um/drivers/harddog_kern.c b/arch/um/drivers/harddog_kern.c index e6d4f43deba8..60d1c6cab8a9 100644 --- a/arch/um/drivers/harddog_kern.c +++ b/arch/um/drivers/harddog_kern.c @@ -47,6 +47,7 @@ #include <linux/spinlock.h> #include <linux/uaccess.h> #include "mconsole.h" +#include "harddog.h" MODULE_LICENSE("GPL"); @@ -60,8 +61,6 @@ static int harddog_out_fd = -1; * Allow only one person to hold it open */ -extern int start_watchdog(int *in_fd_ret, int *out_fd_ret, char *sock); - static int harddog_open(struct inode *inode, struct file *file) { int err = -EBUSY; @@ -92,8 +91,6 @@ err: return err; } -extern void stop_watchdog(int in_fd, int out_fd); - static int harddog_release(struct inode *inode, struct file *file) { /* @@ -112,8 +109,6 @@ static int harddog_release(struct inode *inode, struct file *file) return 0; } -extern int ping_watchdog(int fd); - static ssize_t harddog_write(struct file *file, const char __user *data, size_t len, loff_t *ppos) { diff --git a/arch/um/drivers/harddog_user.c b/arch/um/drivers/harddog_user.c index 070468d22e39..9ed89304975e 100644 --- a/arch/um/drivers/harddog_user.c +++ b/arch/um/drivers/harddog_user.c @@ -7,6 +7,7 @@ #include <unistd.h> #include <errno.h> #include <os.h> +#include "harddog.h" struct dog_data { int stdin_fd; diff --git a/arch/um/drivers/harddog_user_exp.c b/arch/um/drivers/harddog_user_exp.c new file mode 100644 index 000000000000..c74d4b815d14 --- /dev/null +++ b/arch/um/drivers/harddog_user_exp.c @@ -0,0 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/export.h> +#include "harddog.h" + +#if IS_MODULE(CONFIG_UML_WATCHDOG) +EXPORT_SYMBOL(start_watchdog); +EXPORT_SYMBOL(stop_watchdog); +EXPORT_SYMBOL(ping_watchdog); +#endif diff --git a/arch/x86/crypto/aria-aesni-avx-asm_64.S b/arch/x86/crypto/aria-aesni-avx-asm_64.S index 7c1abc513f34..9556dacd9841 100644 --- a/arch/x86/crypto/aria-aesni-avx-asm_64.S +++ b/arch/x86/crypto/aria-aesni-avx-asm_64.S @@ -773,8 +773,6 @@ .octa 0x3F893781E95FE1576CDA64D2BA0CB204 #ifdef CONFIG_AS_GFNI -.section .rodata.cst8, "aM", @progbits, 8 -.align 8 /* AES affine: */ #define tf_aff_const BV8(1, 1, 0, 0, 0, 1, 1, 0) .Ltf_aff_bitmatrix: diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 070cc4ef2672..89b9c1cebb61 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -4074,7 +4074,7 @@ static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr, void *data) if (x86_pmu.intel_cap.pebs_baseline) { arr[(*nr)++] = (struct perf_guest_switch_msr){ .msr = MSR_PEBS_DATA_CFG, - .host = cpuc->pebs_data_cfg, + .host = cpuc->active_pebs_data_cfg, .guest = kvm_pmu->pebs_data_cfg, }; } diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index fa9b209a11fa..d49e90dc04a4 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -6150,6 +6150,7 @@ static struct intel_uncore_type spr_uncore_mdf = { }; #define UNCORE_SPR_NUM_UNCORE_TYPES 12 +#define UNCORE_SPR_CHA 0 #define UNCORE_SPR_IIO 1 #define UNCORE_SPR_IMC 6 #define UNCORE_SPR_UPI 8 @@ -6460,12 +6461,22 @@ static int uncore_type_max_boxes(struct intel_uncore_type **types, return max + 1; } +#define SPR_MSR_UNC_CBO_CONFIG 0x2FFE + void spr_uncore_cpu_init(void) { + struct intel_uncore_type *type; + u64 num_cbo; + uncore_msr_uncores = uncore_get_uncores(UNCORE_ACCESS_MSR, UNCORE_SPR_MSR_EXTRA_UNCORES, spr_msr_uncores); + type = uncore_find_type_by_id(uncore_msr_uncores, UNCORE_SPR_CHA); + if (type) { + rdmsrl(SPR_MSR_UNC_CBO_CONFIG, num_cbo); + type->num_boxes = num_cbo; + } spr_uncore_iio_free_running.num_boxes = uncore_type_max_boxes(uncore_msr_uncores, UNCORE_SPR_IIO); } diff --git a/arch/x86/include/asm/fpu/sched.h b/arch/x86/include/asm/fpu/sched.h index c2d6cd78ed0c..78fcde7b1f07 100644 --- a/arch/x86/include/asm/fpu/sched.h +++ b/arch/x86/include/asm/fpu/sched.h @@ -39,7 +39,7 @@ extern void fpu_flush_thread(void); static inline void switch_fpu_prepare(struct fpu *old_fpu, int cpu) { if (cpu_feature_enabled(X86_FEATURE_FPU) && - !(current->flags & (PF_KTHREAD | PF_IO_WORKER))) { + !(current->flags & (PF_KTHREAD | PF_USER_WORKER))) { save_fpregs_to_fpstate(old_fpu); /* * The save operation preserved register state, so the diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index 498dc600bd5c..0d02c4aafa6f 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -13,7 +13,9 @@ #include <linux/bitops.h> +#include <linux/bug.h> #include <linux/types.h> + #include <uapi/asm/vmx.h> #include <asm/vmxfeatures.h> diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index dd61752f4c96..4070a01c11b7 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -17,6 +17,7 @@ CFLAGS_REMOVE_ftrace.o = -pg CFLAGS_REMOVE_early_printk.o = -pg CFLAGS_REMOVE_head64.o = -pg CFLAGS_REMOVE_sev.o = -pg +CFLAGS_REMOVE_rethook.o = -pg endif KASAN_SANITIZE_head$(BITS).o := n diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c index 5e868b62a7c4..0270925fe013 100644 --- a/arch/x86/kernel/cpu/topology.c +++ b/arch/x86/kernel/cpu/topology.c @@ -79,7 +79,7 @@ int detect_extended_topology_early(struct cpuinfo_x86 *c) * initial apic id, which also represents 32-bit extended x2apic id. */ c->initial_apicid = edx; - smp_num_siblings = LEVEL_MAX_SIBLINGS(ebx); + smp_num_siblings = max_t(int, smp_num_siblings, LEVEL_MAX_SIBLINGS(ebx)); #endif return 0; } @@ -109,7 +109,8 @@ int detect_extended_topology(struct cpuinfo_x86 *c) */ cpuid_count(leaf, SMT_LEVEL, &eax, &ebx, &ecx, &edx); c->initial_apicid = edx; - core_level_siblings = smp_num_siblings = LEVEL_MAX_SIBLINGS(ebx); + core_level_siblings = LEVEL_MAX_SIBLINGS(ebx); + smp_num_siblings = max_t(int, smp_num_siblings, LEVEL_MAX_SIBLINGS(ebx)); core_plus_mask_width = ht_mask_width = BITS_SHIFT_NEXT_LEVEL(eax); die_level_siblings = LEVEL_MAX_SIBLINGS(ebx); pkg_mask_width = die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax); diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 0bf6779187dd..f18ca44c904b 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -195,7 +195,6 @@ static void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, printk("%sCall Trace:\n", log_lvl); unwind_start(&state, task, regs, stack); - stack = stack ? : get_stack_pointer(task, regs); regs = unwind_get_entry_regs(&state, &partial); /* @@ -214,9 +213,13 @@ static void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, * - hardirq stack * - entry stack */ - for ( ; stack; stack = PTR_ALIGN(stack_info.next_sp, sizeof(long))) { + for (stack = stack ?: get_stack_pointer(task, regs); + stack; + stack = stack_info.next_sp) { const char *stack_name; + stack = PTR_ALIGN(stack, sizeof(long)); + if (get_stack_info(stack, task, &stack_info, &visit_mask)) { /* * We weren't on a valid stack. It's possible that diff --git a/arch/x86/kernel/fpu/context.h b/arch/x86/kernel/fpu/context.h index 9fcfa5c4dad7..af5cbdd9bd29 100644 --- a/arch/x86/kernel/fpu/context.h +++ b/arch/x86/kernel/fpu/context.h @@ -57,7 +57,7 @@ static inline void fpregs_restore_userregs(void) struct fpu *fpu = ¤t->thread.fpu; int cpu = smp_processor_id(); - if (WARN_ON_ONCE(current->flags & (PF_KTHREAD | PF_IO_WORKER))) + if (WARN_ON_ONCE(current->flags & (PF_KTHREAD | PF_USER_WORKER))) return; if (!fpregs_state_valid(fpu, cpu)) { diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index caf33486dc5e..1015af1ae562 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -426,7 +426,7 @@ void kernel_fpu_begin_mask(unsigned int kfpu_mask) this_cpu_write(in_kernel_fpu, true); - if (!(current->flags & (PF_KTHREAD | PF_IO_WORKER)) && + if (!(current->flags & (PF_KTHREAD | PF_USER_WORKER)) && !test_thread_flag(TIF_NEED_FPU_LOAD)) { set_thread_flag(TIF_NEED_FPU_LOAD); save_fpregs_to_fpstate(¤t->thread.fpu); diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 123bf8b97a4b..0c9660a07b23 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -253,7 +253,6 @@ static void __kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu, struct kvm_cpuid_e int nent) { struct kvm_cpuid_entry2 *best; - u64 guest_supported_xcr0 = cpuid_get_supported_xcr0(entries, nent); best = cpuid_entry2_find(entries, nent, 1, KVM_CPUID_INDEX_NOT_SIGNIFICANT); if (best) { @@ -292,21 +291,6 @@ static void __kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu, struct kvm_cpuid_e vcpu->arch.ia32_misc_enable_msr & MSR_IA32_MISC_ENABLE_MWAIT); } - - /* - * Bits 127:0 of the allowed SECS.ATTRIBUTES (CPUID.0x12.0x1) enumerate - * the supported XSAVE Feature Request Mask (XFRM), i.e. the enclave's - * requested XCR0 value. The enclave's XFRM must be a subset of XCRO - * at the time of EENTER, thus adjust the allowed XFRM by the guest's - * supported XCR0. Similar to XCR0 handling, FP and SSE are forced to - * '1' even on CPUs that don't support XSAVE. - */ - best = cpuid_entry2_find(entries, nent, 0x12, 0x1); - if (best) { - best->ecx &= guest_supported_xcr0 & 0xffffffff; - best->edx &= guest_supported_xcr0 >> 32; - best->ecx |= XFEATURE_MASK_FPSSE; - } } void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/vmx/sgx.c b/arch/x86/kvm/vmx/sgx.c index 0574030b071f..2261b684a7d4 100644 --- a/arch/x86/kvm/vmx/sgx.c +++ b/arch/x86/kvm/vmx/sgx.c @@ -170,12 +170,19 @@ static int __handle_encls_ecreate(struct kvm_vcpu *vcpu, return 1; } - /* Enforce CPUID restrictions on MISCSELECT, ATTRIBUTES and XFRM. */ + /* + * Enforce CPUID restrictions on MISCSELECT, ATTRIBUTES and XFRM. Note + * that the allowed XFRM (XFeature Request Mask) isn't strictly bound + * by the supported XCR0. FP+SSE *must* be set in XFRM, even if XSAVE + * is unsupported, i.e. even if XCR0 itself is completely unsupported. + */ if ((u32)miscselect & ~sgx_12_0->ebx || (u32)attributes & ~sgx_12_1->eax || (u32)(attributes >> 32) & ~sgx_12_1->ebx || (u32)xfrm & ~sgx_12_1->ecx || - (u32)(xfrm >> 32) & ~sgx_12_1->edx) { + (u32)(xfrm >> 32) & ~sgx_12_1->edx || + xfrm & ~(vcpu->arch.guest_supported_xcr0 | XFEATURE_MASK_FPSSE) || + (xfrm & XFEATURE_MASK_FPSSE) != XFEATURE_MASK_FPSSE) { kvm_inject_gp(vcpu, 0); return 1; } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index ceb7c5e9cf9e..c0778ca39650 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1446,7 +1446,7 @@ static const u32 msrs_to_save_base[] = { #endif MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA, MSR_IA32_FEAT_CTL, MSR_IA32_BNDCFGS, MSR_TSC_AUX, - MSR_IA32_SPEC_CTRL, + MSR_IA32_SPEC_CTRL, MSR_IA32_TSX_CTRL, MSR_IA32_RTIT_CTL, MSR_IA32_RTIT_STATUS, MSR_IA32_RTIT_CR3_MATCH, MSR_IA32_RTIT_OUTPUT_BASE, MSR_IA32_RTIT_OUTPUT_MASK, MSR_IA32_RTIT_ADDR0_A, MSR_IA32_RTIT_ADDR0_B, @@ -7155,6 +7155,10 @@ static void kvm_probe_msr_to_save(u32 msr_index) if (!kvm_cpu_cap_has(X86_FEATURE_XFD)) return; break; + case MSR_IA32_TSX_CTRL: + if (!(kvm_get_arch_capabilities() & ARCH_CAP_TSX_CTRL_MSR)) + return; + break; default: break; } diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S index 4fc5c2de2de4..01c5de4c279b 100644 --- a/arch/x86/lib/copy_user_64.S +++ b/arch/x86/lib/copy_user_64.S @@ -7,6 +7,8 @@ */ #include <linux/linkage.h> +#include <asm/cpufeatures.h> +#include <asm/alternative.h> #include <asm/asm.h> #include <asm/export.h> @@ -29,7 +31,7 @@ */ SYM_FUNC_START(rep_movs_alternative) cmpq $64,%rcx - jae .Lunrolled + jae .Llarge cmp $8,%ecx jae .Lword @@ -65,6 +67,12 @@ SYM_FUNC_START(rep_movs_alternative) _ASM_EXTABLE_UA( 2b, .Lcopy_user_tail) _ASM_EXTABLE_UA( 3b, .Lcopy_user_tail) +.Llarge: +0: ALTERNATIVE "jmp .Lunrolled", "rep movsb", X86_FEATURE_ERMS +1: RET + + _ASM_EXTABLE_UA( 0b, 1b) + .p2align 4 .Lunrolled: 10: movq (%rsi),%r8 diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 3cdac0f0055d..8192452d1d2d 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -9,6 +9,7 @@ #include <linux/sched/task.h> #include <asm/set_memory.h> +#include <asm/cpu_device_id.h> #include <asm/e820/api.h> #include <asm/init.h> #include <asm/page.h> @@ -261,6 +262,24 @@ static void __init probe_page_size_mask(void) } } +#define INTEL_MATCH(_model) { .vendor = X86_VENDOR_INTEL, \ + .family = 6, \ + .model = _model, \ + } +/* + * INVLPG may not properly flush Global entries + * on these CPUs when PCIDs are enabled. + */ +static const struct x86_cpu_id invlpg_miss_ids[] = { + INTEL_MATCH(INTEL_FAM6_ALDERLAKE ), + INTEL_MATCH(INTEL_FAM6_ALDERLAKE_L ), + INTEL_MATCH(INTEL_FAM6_ALDERLAKE_N ), + INTEL_MATCH(INTEL_FAM6_RAPTORLAKE ), + INTEL_MATCH(INTEL_FAM6_RAPTORLAKE_P), + INTEL_MATCH(INTEL_FAM6_RAPTORLAKE_S), + {} +}; + static void setup_pcid(void) { if (!IS_ENABLED(CONFIG_X86_64)) @@ -269,6 +288,12 @@ static void setup_pcid(void) if (!boot_cpu_has(X86_FEATURE_PCID)) return; + if (x86_match_cpu(invlpg_miss_ids)) { + pr_info("Incomplete global flushes, disabling PCID"); + setup_clear_cpu_cap(X86_FEATURE_PCID); + return; + } + if (boot_cpu_has(X86_FEATURE_PGE)) { /* * This can't be cr4_set_bits_and_update_boot() -- the diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index 8babce71915f..014c508e914d 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -198,7 +198,7 @@ static int xen_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) i++; } kfree(v); - return 0; + return msi_device_populate_sysfs(&dev->dev); error: if (ret == -ENOSYS) @@ -254,7 +254,7 @@ static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) dev_dbg(&dev->dev, "xen: msi --> pirq=%d --> irq=%d\n", pirq, irq); } - return 0; + return msi_device_populate_sysfs(&dev->dev); error: dev_err(&dev->dev, "Failed to create MSI%s! ret=%d!\n", @@ -346,7 +346,7 @@ static int xen_initdom_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) if (ret < 0) goto out; } - ret = 0; + ret = msi_device_populate_sysfs(&dev->dev); out: return ret; } @@ -394,6 +394,8 @@ static void xen_teardown_msi_irqs(struct pci_dev *dev) xen_destroy_irq(msidesc->irq + i); msidesc->irq = 0; } + + msi_device_destroy_sysfs(&dev->dev); } static void xen_pv_teardown_msi_irqs(struct pci_dev *dev) diff --git a/arch/xtensa/kernel/signal.c b/arch/xtensa/kernel/signal.c index 876d5df157ed..5c01d7e70d90 100644 --- a/arch/xtensa/kernel/signal.c +++ b/arch/xtensa/kernel/signal.c @@ -343,7 +343,19 @@ static int setup_frame(struct ksignal *ksig, sigset_t *set, struct rt_sigframe *frame; int err = 0, sig = ksig->sig; unsigned long sp, ra, tp, ps; + unsigned long handler = (unsigned long)ksig->ka.sa.sa_handler; + unsigned long handler_fdpic_GOT = 0; unsigned int base; + bool fdpic = IS_ENABLED(CONFIG_BINFMT_ELF_FDPIC) && + (current->personality & FDPIC_FUNCPTRS); + + if (fdpic) { + unsigned long __user *fdpic_func_desc = + (unsigned long __user *)handler; + if (__get_user(handler, &fdpic_func_desc[0]) || + __get_user(handler_fdpic_GOT, &fdpic_func_desc[1])) + return -EFAULT; + } sp = regs->areg[1]; @@ -373,20 +385,26 @@ static int setup_frame(struct ksignal *ksig, sigset_t *set, err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); if (ksig->ka.sa.sa_flags & SA_RESTORER) { - ra = (unsigned long)ksig->ka.sa.sa_restorer; + if (fdpic) { + unsigned long __user *fdpic_func_desc = + (unsigned long __user *)ksig->ka.sa.sa_restorer; + + err |= __get_user(ra, fdpic_func_desc); + } else { + ra = (unsigned long)ksig->ka.sa.sa_restorer; + } } else { /* Create sys_rt_sigreturn syscall in stack frame */ err |= gen_return_code(frame->retcode); - - if (err) { - return -EFAULT; - } ra = (unsigned long) frame->retcode; } - /* + if (err) + return -EFAULT; + + /* * Create signal handler execution context. * Return context not modified until this point. */ @@ -394,8 +412,7 @@ static int setup_frame(struct ksignal *ksig, sigset_t *set, /* Set up registers for signal handler; preserve the threadptr */ tp = regs->threadptr; ps = regs->ps; - start_thread(regs, (unsigned long) ksig->ka.sa.sa_handler, - (unsigned long) frame); + start_thread(regs, handler, (unsigned long)frame); /* Set up a stack frame for a call4 if userspace uses windowed ABI */ if (ps & PS_WOE_MASK) { @@ -413,6 +430,8 @@ static int setup_frame(struct ksignal *ksig, sigset_t *set, regs->areg[base + 4] = (unsigned long) &frame->uc; regs->threadptr = tp; regs->ps = ps; + if (fdpic) + regs->areg[base + 11] = handler_fdpic_GOT; pr_debug("SIG rt deliver (%s:%d): signal=%d sp=%p pc=%08lx\n", current->comm, current->pid, sig, frame, regs->pc); diff --git a/arch/xtensa/kernel/xtensa_ksyms.c b/arch/xtensa/kernel/xtensa_ksyms.c index 2a31b1ab0c9f..17a7ef86fd0d 100644 --- a/arch/xtensa/kernel/xtensa_ksyms.c +++ b/arch/xtensa/kernel/xtensa_ksyms.c @@ -56,6 +56,8 @@ EXPORT_SYMBOL(empty_zero_page); */ extern long long __ashrdi3(long long, int); extern long long __ashldi3(long long, int); +extern long long __bswapdi2(long long); +extern int __bswapsi2(int); extern long long __lshrdi3(long long, int); extern int __divsi3(int, int); extern int __modsi3(int, int); @@ -66,6 +68,8 @@ extern unsigned long long __umulsidi3(unsigned int, unsigned int); EXPORT_SYMBOL(__ashldi3); EXPORT_SYMBOL(__ashrdi3); +EXPORT_SYMBOL(__bswapdi2); +EXPORT_SYMBOL(__bswapsi2); EXPORT_SYMBOL(__lshrdi3); EXPORT_SYMBOL(__divsi3); EXPORT_SYMBOL(__modsi3); diff --git a/arch/xtensa/lib/Makefile b/arch/xtensa/lib/Makefile index 7ecef0519a27..c9c2614188f7 100644 --- a/arch/xtensa/lib/Makefile +++ b/arch/xtensa/lib/Makefile @@ -4,7 +4,7 @@ # lib-y += memcopy.o memset.o checksum.o \ - ashldi3.o ashrdi3.o lshrdi3.o \ + ashldi3.o ashrdi3.o bswapdi2.o bswapsi2.o lshrdi3.o \ divsi3.o udivsi3.o modsi3.o umodsi3.o mulsi3.o umulsidi3.o \ usercopy.o strncpy_user.o strnlen_user.o lib-$(CONFIG_PCI) += pci-auto.o diff --git a/arch/xtensa/lib/bswapdi2.S b/arch/xtensa/lib/bswapdi2.S new file mode 100644 index 000000000000..d8e52e05eba6 --- /dev/null +++ b/arch/xtensa/lib/bswapdi2.S @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later WITH GCC-exception-2.0 */ +#include <linux/linkage.h> +#include <asm/asmmacro.h> +#include <asm/core.h> + +ENTRY(__bswapdi2) + + abi_entry_default + ssai 8 + srli a4, a2, 16 + src a4, a4, a2 + src a4, a4, a4 + src a4, a2, a4 + srli a2, a3, 16 + src a2, a2, a3 + src a2, a2, a2 + src a2, a3, a2 + mov a3, a4 + abi_ret_default + +ENDPROC(__bswapdi2) diff --git a/arch/xtensa/lib/bswapsi2.S b/arch/xtensa/lib/bswapsi2.S new file mode 100644 index 000000000000..9c1de1344f79 --- /dev/null +++ b/arch/xtensa/lib/bswapsi2.S @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later WITH GCC-exception-2.0 */ +#include <linux/linkage.h> +#include <asm/asmmacro.h> +#include <asm/core.h> + +ENTRY(__bswapsi2) + + abi_entry_default + ssai 8 + srli a3, a2, 16 + src a3, a3, a2 + src a3, a3, a3 + src a2, a2, a3 + abi_ret_default + +ENDPROC(__bswapsi2) diff --git a/block/blk-core.c b/block/blk-core.c index 00c74330fa92..1da77e7d6289 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -520,7 +520,7 @@ static inline int bio_check_eod(struct bio *bio) sector_t maxsector = bdev_nr_sectors(bio->bi_bdev); unsigned int nr_sectors = bio_sectors(bio); - if (nr_sectors && maxsector && + if (nr_sectors && (nr_sectors > maxsector || bio->bi_iter.bi_sector > maxsector - nr_sectors)) { pr_info_ratelimited("%s: attempt to access beyond end of device\n" diff --git a/block/blk-map.c b/block/blk-map.c index 04c55f1c492e..46eed2e627c3 100644 --- a/block/blk-map.c +++ b/block/blk-map.c @@ -248,7 +248,7 @@ static struct bio *blk_rq_map_bio_alloc(struct request *rq, { struct bio *bio; - if (rq->cmd_flags & REQ_ALLOC_CACHE) { + if (rq->cmd_flags & REQ_ALLOC_CACHE && (nr_vecs <= BIO_INLINE_VECS)) { bio = bio_alloc_bioset(NULL, nr_vecs, rq->cmd_flags, gfp_mask, &fs_bio_set); if (!bio) diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index d6af9d431dc6..dfd81cab5788 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -39,16 +39,20 @@ void __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx) { unsigned int users; + /* + * calling test_bit() prior to test_and_set_bit() is intentional, + * it avoids dirtying the cacheline if the queue is already active. + */ if (blk_mq_is_shared_tags(hctx->flags)) { struct request_queue *q = hctx->queue; - if (test_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags)) + if (test_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags) || + test_and_set_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags)) return; - set_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags); } else { - if (test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state)) + if (test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state) || + test_and_set_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state)) return; - set_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state); } users = atomic_inc_return(&hctx->tags->active_queues); diff --git a/block/blk-wbt.c b/block/blk-wbt.c index e49a48684532..9ec2a2f1eda3 100644 --- a/block/blk-wbt.c +++ b/block/blk-wbt.c @@ -730,14 +730,16 @@ void wbt_enable_default(struct gendisk *disk) { struct request_queue *q = disk->queue; struct rq_qos *rqos; - bool disable_flag = q->elevator && - test_bit(ELEVATOR_FLAG_DISABLE_WBT, &q->elevator->flags); + bool enable = IS_ENABLED(CONFIG_BLK_WBT_MQ); + + if (q->elevator && + test_bit(ELEVATOR_FLAG_DISABLE_WBT, &q->elevator->flags)) + enable = false; /* Throttling already enabled? */ rqos = wbt_rq_qos(q); if (rqos) { - if (!disable_flag && - RQWB(rqos)->enable_state == WBT_STATE_OFF_DEFAULT) + if (enable && RQWB(rqos)->enable_state == WBT_STATE_OFF_DEFAULT) RQWB(rqos)->enable_state = WBT_STATE_ON_DEFAULT; return; } @@ -746,7 +748,7 @@ void wbt_enable_default(struct gendisk *disk) if (!blk_queue_registered(q)) return; - if (queue_is_mq(q) && !disable_flag) + if (queue_is_mq(q) && enable) wbt_init(disk); } EXPORT_SYMBOL_GPL(wbt_enable_default); diff --git a/block/fops.c b/block/fops.c index d2e6be4e3d1c..58d0aebc7313 100644 --- a/block/fops.c +++ b/block/fops.c @@ -678,6 +678,16 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start, return error; } +static int blkdev_mmap(struct file *file, struct vm_area_struct *vma) +{ + struct inode *bd_inode = bdev_file_inode(file); + + if (bdev_read_only(I_BDEV(bd_inode))) + return generic_file_readonly_mmap(file, vma); + + return generic_file_mmap(file, vma); +} + const struct file_operations def_blk_fops = { .open = blkdev_open, .release = blkdev_close, @@ -685,7 +695,7 @@ const struct file_operations def_blk_fops = { .read_iter = blkdev_read_iter, .write_iter = blkdev_write_iter, .iopoll = iocb_bio_iopoll, - .mmap = generic_file_mmap, + .mmap = blkdev_mmap, .fsync = blkdev_fsync, .unlocked_ioctl = blkdev_ioctl, #ifdef CONFIG_COMPAT diff --git a/drivers/accel/qaic/qaic_control.c b/drivers/accel/qaic/qaic_control.c index 9f216eb6f76e..5c57f7b4494e 100644 --- a/drivers/accel/qaic/qaic_control.c +++ b/drivers/accel/qaic/qaic_control.c @@ -997,14 +997,34 @@ static void *msg_xfer(struct qaic_device *qdev, struct wrapper_list *wrappers, u struct xfer_queue_elem elem; struct wire_msg *out_buf; struct wrapper_msg *w; + long ret = -EAGAIN; + int xfer_count = 0; int retry_count; - long ret; if (qdev->in_reset) { mutex_unlock(&qdev->cntl_mutex); return ERR_PTR(-ENODEV); } + /* Attempt to avoid a partial commit of a message */ + list_for_each_entry(w, &wrappers->list, list) + xfer_count++; + + for (retry_count = 0; retry_count < QAIC_MHI_RETRY_MAX; retry_count++) { + if (xfer_count <= mhi_get_free_desc_count(qdev->cntl_ch, DMA_TO_DEVICE)) { + ret = 0; + break; + } + msleep_interruptible(QAIC_MHI_RETRY_WAIT_MS); + if (signal_pending(current)) + break; + } + + if (ret) { + mutex_unlock(&qdev->cntl_mutex); + return ERR_PTR(ret); + } + elem.seq_num = seq_num; elem.buf = NULL; init_completion(&elem.xfer_done); @@ -1038,16 +1058,9 @@ static void *msg_xfer(struct qaic_device *qdev, struct wrapper_list *wrappers, u list_for_each_entry(w, &wrappers->list, list) { kref_get(&w->ref_count); retry_count = 0; -retry: ret = mhi_queue_buf(qdev->cntl_ch, DMA_TO_DEVICE, &w->msg, w->len, list_is_last(&w->list, &wrappers->list) ? MHI_EOT : MHI_CHAIN); if (ret) { - if (ret == -EAGAIN && retry_count++ < QAIC_MHI_RETRY_MAX) { - msleep_interruptible(QAIC_MHI_RETRY_WAIT_MS); - if (!signal_pending(current)) - goto retry; - } - qdev->cntl_lost_buf = true; kref_put(&w->ref_count, free_wrapper); mutex_unlock(&qdev->cntl_mutex); @@ -1249,7 +1262,7 @@ dma_cont_failed: int qaic_manage_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv) { - struct qaic_manage_msg *user_msg; + struct qaic_manage_msg *user_msg = data; struct qaic_device *qdev; struct manage_msg *msg; struct qaic_user *usr; @@ -1258,6 +1271,9 @@ int qaic_manage_ioctl(struct drm_device *dev, void *data, struct drm_file *file_ int usr_rcu_id; int ret; + if (user_msg->len > QAIC_MANAGE_MAX_MSG_LENGTH) + return -EINVAL; + usr = file_priv->driver_priv; usr_rcu_id = srcu_read_lock(&usr->qddev_lock); @@ -1275,13 +1291,6 @@ int qaic_manage_ioctl(struct drm_device *dev, void *data, struct drm_file *file_ return -ENODEV; } - user_msg = data; - - if (user_msg->len > QAIC_MANAGE_MAX_MSG_LENGTH) { - ret = -EINVAL; - goto out; - } - msg = kzalloc(QAIC_MANAGE_MAX_MSG_LENGTH + sizeof(*msg), GFP_KERNEL); if (!msg) { ret = -ENOMEM; diff --git a/drivers/accel/qaic/qaic_data.c b/drivers/accel/qaic/qaic_data.c index c0a574cd1b35..e42c1f9ffff8 100644 --- a/drivers/accel/qaic/qaic_data.c +++ b/drivers/accel/qaic/qaic_data.c @@ -591,7 +591,7 @@ static int qaic_gem_object_mmap(struct drm_gem_object *obj, struct vm_area_struc struct qaic_bo *bo = to_qaic_bo(obj); unsigned long offset = 0; struct scatterlist *sg; - int ret; + int ret = 0; if (obj->import_attach) return -EINVAL; @@ -663,6 +663,10 @@ int qaic_create_bo_ioctl(struct drm_device *dev, void *data, struct drm_file *fi if (args->pad) return -EINVAL; + size = PAGE_ALIGN(args->size); + if (size == 0) + return -EINVAL; + usr = file_priv->driver_priv; usr_rcu_id = srcu_read_lock(&usr->qddev_lock); if (!usr->qddev) { @@ -677,12 +681,6 @@ int qaic_create_bo_ioctl(struct drm_device *dev, void *data, struct drm_file *fi goto unlock_dev_srcu; } - size = PAGE_ALIGN(args->size); - if (size == 0) { - ret = -EINVAL; - goto unlock_dev_srcu; - } - bo = qaic_alloc_init_bo(); if (IS_ERR(bo)) { ret = PTR_ERR(bo); @@ -926,8 +924,8 @@ int qaic_attach_slice_bo_ioctl(struct drm_device *dev, void *data, struct drm_fi { struct qaic_attach_slice_entry *slice_ent; struct qaic_attach_slice *args = data; + int rcu_id, usr_rcu_id, qdev_rcu_id; struct dma_bridge_chan *dbc; - int usr_rcu_id, qdev_rcu_id; struct drm_gem_object *obj; struct qaic_device *qdev; unsigned long arg_size; @@ -936,6 +934,22 @@ int qaic_attach_slice_bo_ioctl(struct drm_device *dev, void *data, struct drm_fi struct qaic_bo *bo; int ret; + if (args->hdr.count == 0) + return -EINVAL; + + arg_size = args->hdr.count * sizeof(*slice_ent); + if (arg_size / args->hdr.count != sizeof(*slice_ent)) + return -EINVAL; + + if (args->hdr.size == 0) + return -EINVAL; + + if (!(args->hdr.dir == DMA_TO_DEVICE || args->hdr.dir == DMA_FROM_DEVICE)) + return -EINVAL; + + if (args->data == 0) + return -EINVAL; + usr = file_priv->driver_priv; usr_rcu_id = srcu_read_lock(&usr->qddev_lock); if (!usr->qddev) { @@ -950,43 +964,11 @@ int qaic_attach_slice_bo_ioctl(struct drm_device *dev, void *data, struct drm_fi goto unlock_dev_srcu; } - if (args->hdr.count == 0) { - ret = -EINVAL; - goto unlock_dev_srcu; - } - - arg_size = args->hdr.count * sizeof(*slice_ent); - if (arg_size / args->hdr.count != sizeof(*slice_ent)) { - ret = -EINVAL; - goto unlock_dev_srcu; - } - if (args->hdr.dbc_id >= qdev->num_dbc) { ret = -EINVAL; goto unlock_dev_srcu; } - if (args->hdr.size == 0) { - ret = -EINVAL; - goto unlock_dev_srcu; - } - - if (!(args->hdr.dir == DMA_TO_DEVICE || args->hdr.dir == DMA_FROM_DEVICE)) { - ret = -EINVAL; - goto unlock_dev_srcu; - } - - dbc = &qdev->dbc[args->hdr.dbc_id]; - if (dbc->usr != usr) { - ret = -EINVAL; - goto unlock_dev_srcu; - } - - if (args->data == 0) { - ret = -EINVAL; - goto unlock_dev_srcu; - } - user_data = u64_to_user_ptr(args->data); slice_ent = kzalloc(arg_size, GFP_KERNEL); @@ -1013,9 +995,21 @@ int qaic_attach_slice_bo_ioctl(struct drm_device *dev, void *data, struct drm_fi bo = to_qaic_bo(obj); + if (bo->sliced) { + ret = -EINVAL; + goto put_bo; + } + + dbc = &qdev->dbc[args->hdr.dbc_id]; + rcu_id = srcu_read_lock(&dbc->ch_lock); + if (dbc->usr != usr) { + ret = -EINVAL; + goto unlock_ch_srcu; + } + ret = qaic_prepare_bo(qdev, bo, &args->hdr); if (ret) - goto put_bo; + goto unlock_ch_srcu; ret = qaic_attach_slicing_bo(qdev, bo, &args->hdr, slice_ent); if (ret) @@ -1025,6 +1019,7 @@ int qaic_attach_slice_bo_ioctl(struct drm_device *dev, void *data, struct drm_fi dma_sync_sgtable_for_cpu(&qdev->pdev->dev, bo->sgt, args->hdr.dir); bo->dbc = dbc; + srcu_read_unlock(&dbc->ch_lock, rcu_id); drm_gem_object_put(obj); srcu_read_unlock(&qdev->dev_lock, qdev_rcu_id); srcu_read_unlock(&usr->qddev_lock, usr_rcu_id); @@ -1033,6 +1028,8 @@ int qaic_attach_slice_bo_ioctl(struct drm_device *dev, void *data, struct drm_fi unprepare_bo: qaic_unprepare_bo(qdev, bo); +unlock_ch_srcu: + srcu_read_unlock(&dbc->ch_lock, rcu_id); put_bo: drm_gem_object_put(obj); free_slice_ent: @@ -1316,7 +1313,6 @@ static int __qaic_execute_bo_ioctl(struct drm_device *dev, void *data, struct dr received_ts = ktime_get_ns(); size = is_partial ? sizeof(*pexec) : sizeof(*exec); - n = (unsigned long)size * args->hdr.count; if (args->hdr.count == 0 || n / args->hdr.count != size) return -EINVAL; @@ -1665,6 +1661,9 @@ int qaic_wait_bo_ioctl(struct drm_device *dev, void *data, struct drm_file *file int rcu_id; int ret; + if (args->pad != 0) + return -EINVAL; + usr = file_priv->driver_priv; usr_rcu_id = srcu_read_lock(&usr->qddev_lock); if (!usr->qddev) { @@ -1679,11 +1678,6 @@ int qaic_wait_bo_ioctl(struct drm_device *dev, void *data, struct drm_file *file goto unlock_dev_srcu; } - if (args->pad != 0) { - ret = -EINVAL; - goto unlock_dev_srcu; - } - if (args->dbc_id >= qdev->num_dbc) { ret = -EINVAL; goto unlock_dev_srcu; @@ -1855,6 +1849,11 @@ void wakeup_dbc(struct qaic_device *qdev, u32 dbc_id) dbc->usr = NULL; empty_xfer_list(qdev, dbc); synchronize_srcu(&dbc->ch_lock); + /* + * Threads holding channel lock, may add more elements in the xfer_list. + * Flush out these elements from xfer_list. + */ + empty_xfer_list(qdev, dbc); } void release_dbc(struct qaic_device *qdev, u32 dbc_id) diff --git a/drivers/accel/qaic/qaic_drv.c b/drivers/accel/qaic/qaic_drv.c index ff80eb571729..2d0828db28d8 100644 --- a/drivers/accel/qaic/qaic_drv.c +++ b/drivers/accel/qaic/qaic_drv.c @@ -262,8 +262,8 @@ static void qaic_destroy_drm_device(struct qaic_device *qdev, s32 partition_id) static int qaic_mhi_probe(struct mhi_device *mhi_dev, const struct mhi_device_id *id) { + u16 major = -1, minor = -1; struct qaic_device *qdev; - u16 major, minor; int ret; /* diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c index e8492b3a393a..0800a9d77558 100644 --- a/drivers/acpi/resource.c +++ b/drivers/acpi/resource.c @@ -516,6 +516,17 @@ static const struct dmi_system_id maingear_laptop[] = { { } }; +static const struct dmi_system_id lg_laptop[] = { + { + .ident = "LG Electronics 17U70P", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LG Electronics"), + DMI_MATCH(DMI_BOARD_NAME, "17U70P"), + }, + }, + { } +}; + struct irq_override_cmp { const struct dmi_system_id *system; unsigned char irq; @@ -532,6 +543,7 @@ static const struct irq_override_cmp override_table[] = { { lenovo_laptop, 10, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW, 0, true }, { tongfang_gm_rg, 1, ACPI_EDGE_SENSITIVE, ACPI_ACTIVE_LOW, 1, true }, { maingear_laptop, 1, ACPI_EDGE_SENSITIVE, ACPI_ACTIVE_LOW, 1, true }, + { lg_laptop, 1, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW, 0, false }, }; static bool acpi_dev_irq_override(u32 gsi, u8 triggering, u8 polarity, diff --git a/drivers/android/binder.c b/drivers/android/binder.c index fb56bfc45096..8fb7672021ee 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -1934,24 +1934,23 @@ static void binder_deferred_fd_close(int fd) static void binder_transaction_buffer_release(struct binder_proc *proc, struct binder_thread *thread, struct binder_buffer *buffer, - binder_size_t failed_at, + binder_size_t off_end_offset, bool is_failure) { int debug_id = buffer->debug_id; - binder_size_t off_start_offset, buffer_offset, off_end_offset; + binder_size_t off_start_offset, buffer_offset; binder_debug(BINDER_DEBUG_TRANSACTION, "%d buffer release %d, size %zd-%zd, failed at %llx\n", proc->pid, buffer->debug_id, buffer->data_size, buffer->offsets_size, - (unsigned long long)failed_at); + (unsigned long long)off_end_offset); if (buffer->target_node) binder_dec_node(buffer->target_node, 1, 0); off_start_offset = ALIGN(buffer->data_size, sizeof(void *)); - off_end_offset = is_failure && failed_at ? failed_at : - off_start_offset + buffer->offsets_size; + for (buffer_offset = off_start_offset; buffer_offset < off_end_offset; buffer_offset += sizeof(binder_size_t)) { struct binder_object_header *hdr; @@ -2111,6 +2110,21 @@ static void binder_transaction_buffer_release(struct binder_proc *proc, } } +/* Clean up all the objects in the buffer */ +static inline void binder_release_entire_buffer(struct binder_proc *proc, + struct binder_thread *thread, + struct binder_buffer *buffer, + bool is_failure) +{ + binder_size_t off_end_offset; + + off_end_offset = ALIGN(buffer->data_size, sizeof(void *)); + off_end_offset += buffer->offsets_size; + + binder_transaction_buffer_release(proc, thread, buffer, + off_end_offset, is_failure); +} + static int binder_translate_binder(struct flat_binder_object *fp, struct binder_transaction *t, struct binder_thread *thread) @@ -2806,7 +2820,7 @@ static int binder_proc_transaction(struct binder_transaction *t, t_outdated->buffer = NULL; buffer->transaction = NULL; trace_binder_transaction_update_buffer_release(buffer); - binder_transaction_buffer_release(proc, NULL, buffer, 0, 0); + binder_release_entire_buffer(proc, NULL, buffer, false); binder_alloc_free_buf(&proc->alloc, buffer); kfree(t_outdated); binder_stats_deleted(BINDER_STAT_TRANSACTION); @@ -3775,7 +3789,7 @@ binder_free_buf(struct binder_proc *proc, binder_node_inner_unlock(buf_node); } trace_binder_transaction_buffer_release(buffer); - binder_transaction_buffer_release(proc, thread, buffer, 0, is_failure); + binder_release_entire_buffer(proc, thread, buffer, is_failure); binder_alloc_free_buf(&proc->alloc, buffer); } diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c index 55a3c3c2409f..662a2a2e2e84 100644 --- a/drivers/android/binder_alloc.c +++ b/drivers/android/binder_alloc.c @@ -212,8 +212,8 @@ static int binder_update_page_range(struct binder_alloc *alloc, int allocate, mm = alloc->mm; if (mm) { - mmap_read_lock(mm); - vma = vma_lookup(mm, alloc->vma_addr); + mmap_write_lock(mm); + vma = alloc->vma; } if (!vma && need_mm) { @@ -270,7 +270,7 @@ static int binder_update_page_range(struct binder_alloc *alloc, int allocate, trace_binder_alloc_page_end(alloc, index); } if (mm) { - mmap_read_unlock(mm); + mmap_write_unlock(mm); mmput(mm); } return 0; @@ -303,21 +303,24 @@ err_page_ptr_cleared: } err_no_vma: if (mm) { - mmap_read_unlock(mm); + mmap_write_unlock(mm); mmput(mm); } return vma ? -ENOMEM : -ESRCH; } +static inline void binder_alloc_set_vma(struct binder_alloc *alloc, + struct vm_area_struct *vma) +{ + /* pairs with smp_load_acquire in binder_alloc_get_vma() */ + smp_store_release(&alloc->vma, vma); +} + static inline struct vm_area_struct *binder_alloc_get_vma( struct binder_alloc *alloc) { - struct vm_area_struct *vma = NULL; - - if (alloc->vma_addr) - vma = vma_lookup(alloc->mm, alloc->vma_addr); - - return vma; + /* pairs with smp_store_release in binder_alloc_set_vma() */ + return smp_load_acquire(&alloc->vma); } static bool debug_low_async_space_locked(struct binder_alloc *alloc, int pid) @@ -380,15 +383,13 @@ static struct binder_buffer *binder_alloc_new_buf_locked( size_t size, data_offsets_size; int ret; - mmap_read_lock(alloc->mm); + /* Check binder_alloc is fully initialized */ if (!binder_alloc_get_vma(alloc)) { - mmap_read_unlock(alloc->mm); binder_alloc_debug(BINDER_DEBUG_USER_ERROR, "%d: binder_alloc_buf, no vma\n", alloc->pid); return ERR_PTR(-ESRCH); } - mmap_read_unlock(alloc->mm); data_offsets_size = ALIGN(data_size, sizeof(void *)) + ALIGN(offsets_size, sizeof(void *)); @@ -778,7 +779,9 @@ int binder_alloc_mmap_handler(struct binder_alloc *alloc, buffer->free = 1; binder_insert_free_buffer(alloc, buffer); alloc->free_async_space = alloc->buffer_size / 2; - alloc->vma_addr = vma->vm_start; + + /* Signal binder_alloc is fully initialized */ + binder_alloc_set_vma(alloc, vma); return 0; @@ -808,8 +811,7 @@ void binder_alloc_deferred_release(struct binder_alloc *alloc) buffers = 0; mutex_lock(&alloc->mutex); - BUG_ON(alloc->vma_addr && - vma_lookup(alloc->mm, alloc->vma_addr)); + BUG_ON(alloc->vma); while ((n = rb_first(&alloc->allocated_buffers))) { buffer = rb_entry(n, struct binder_buffer, rb_node); @@ -916,25 +918,17 @@ void binder_alloc_print_pages(struct seq_file *m, * Make sure the binder_alloc is fully initialized, otherwise we might * read inconsistent state. */ - - mmap_read_lock(alloc->mm); - if (binder_alloc_get_vma(alloc) == NULL) { - mmap_read_unlock(alloc->mm); - goto uninitialized; - } - - mmap_read_unlock(alloc->mm); - for (i = 0; i < alloc->buffer_size / PAGE_SIZE; i++) { - page = &alloc->pages[i]; - if (!page->page_ptr) - free++; - else if (list_empty(&page->lru)) - active++; - else - lru++; + if (binder_alloc_get_vma(alloc) != NULL) { + for (i = 0; i < alloc->buffer_size / PAGE_SIZE; i++) { + page = &alloc->pages[i]; + if (!page->page_ptr) + free++; + else if (list_empty(&page->lru)) + active++; + else + lru++; + } } - -uninitialized: mutex_unlock(&alloc->mutex); seq_printf(m, " pages: %d:%d:%d\n", active, lru, free); seq_printf(m, " pages high watermark: %zu\n", alloc->pages_high); @@ -969,7 +963,7 @@ int binder_alloc_get_allocated_count(struct binder_alloc *alloc) */ void binder_alloc_vma_close(struct binder_alloc *alloc) { - alloc->vma_addr = 0; + binder_alloc_set_vma(alloc, NULL); } /** diff --git a/drivers/android/binder_alloc.h b/drivers/android/binder_alloc.h index 0f811ac4bcff..138d1d5af9ce 100644 --- a/drivers/android/binder_alloc.h +++ b/drivers/android/binder_alloc.h @@ -75,7 +75,7 @@ struct binder_lru_page { /** * struct binder_alloc - per-binder proc state for binder allocator * @mutex: protects binder_alloc fields - * @vma_addr: vm_area_struct->vm_start passed to mmap_handler + * @vma: vm_area_struct passed to mmap_handler * (invariant after mmap) * @mm: copy of task->mm (invariant after open) * @buffer: base of per-proc address space mapped via mmap @@ -99,7 +99,7 @@ struct binder_lru_page { */ struct binder_alloc { struct mutex mutex; - unsigned long vma_addr; + struct vm_area_struct *vma; struct mm_struct *mm; void __user *buffer; struct list_head buffers; diff --git a/drivers/android/binder_alloc_selftest.c b/drivers/android/binder_alloc_selftest.c index 43a881073a42..c2b323bc3b3a 100644 --- a/drivers/android/binder_alloc_selftest.c +++ b/drivers/android/binder_alloc_selftest.c @@ -287,7 +287,7 @@ void binder_selftest_alloc(struct binder_alloc *alloc) if (!binder_selftest_run) return; mutex_lock(&binder_selftest_lock); - if (!binder_selftest_run || !alloc->vma_addr) + if (!binder_selftest_run || !alloc->vma) goto done; pr_info("STARTED\n"); binder_selftest_alloc_offset(alloc, end_offset, 0); diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 7bb12deab70c..8ce90284eb34 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -2694,18 +2694,36 @@ static unsigned int atapi_xlat(struct ata_queued_cmd *qc) return 0; } -static struct ata_device *ata_find_dev(struct ata_port *ap, int devno) +static struct ata_device *ata_find_dev(struct ata_port *ap, unsigned int devno) { - if (!sata_pmp_attached(ap)) { - if (likely(devno >= 0 && - devno < ata_link_max_devices(&ap->link))) + /* + * For the non-PMP case, ata_link_max_devices() returns 1 (SATA case), + * or 2 (IDE master + slave case). However, the former case includes + * libsas hosted devices which are numbered per scsi host, leading + * to devno potentially being larger than 0 but with each struct + * ata_device having its own struct ata_port and struct ata_link. + * To accommodate these, ignore devno and always use device number 0. + */ + if (likely(!sata_pmp_attached(ap))) { + int link_max_devices = ata_link_max_devices(&ap->link); + + if (link_max_devices == 1) + return &ap->link.device[0]; + + if (devno < link_max_devices) return &ap->link.device[devno]; - } else { - if (likely(devno >= 0 && - devno < ap->nr_pmp_links)) - return &ap->pmp_link[devno].device[0]; + + return NULL; } + /* + * For PMP-attached devices, the device number corresponds to C + * (channel) of SCSI [H:C:I:L], indicating the port pmp link + * for the device. + */ + if (devno < ap->nr_pmp_links) + return &ap->pmp_link[devno].device[0]; + return NULL; } diff --git a/drivers/base/class.c b/drivers/base/class.c index ac1808d1a2e8..05d9df90f621 100644 --- a/drivers/base/class.c +++ b/drivers/base/class.c @@ -320,6 +320,7 @@ void class_dev_iter_init(struct class_dev_iter *iter, const struct class *class, start_knode = &start->p->knode_class; klist_iter_init_node(&sp->klist_devices, &iter->ki, start_knode); iter->type = type; + iter->sp = sp; } EXPORT_SYMBOL_GPL(class_dev_iter_init); @@ -361,6 +362,7 @@ EXPORT_SYMBOL_GPL(class_dev_iter_next); void class_dev_iter_exit(struct class_dev_iter *iter) { klist_iter_exit(&iter->ki); + subsys_put(iter->sp); } EXPORT_SYMBOL_GPL(class_dev_iter_exit); diff --git a/drivers/base/regmap/Kconfig b/drivers/base/regmap/Kconfig index 33a8366e22a5..0db2021f7477 100644 --- a/drivers/base/regmap/Kconfig +++ b/drivers/base/regmap/Kconfig @@ -4,16 +4,23 @@ # subsystems should select the appropriate symbols. config REGMAP + bool "Register Map support" if KUNIT_ALL_TESTS default y if (REGMAP_I2C || REGMAP_SPI || REGMAP_SPMI || REGMAP_W1 || REGMAP_AC97 || REGMAP_MMIO || REGMAP_IRQ || REGMAP_SOUNDWIRE || REGMAP_SOUNDWIRE_MBQ || REGMAP_SCCB || REGMAP_I3C || REGMAP_SPI_AVMM || REGMAP_MDIO || REGMAP_FSI) select IRQ_DOMAIN if REGMAP_IRQ select MDIO_BUS if REGMAP_MDIO - bool + help + Enable support for the Register Map (regmap) access API. + + Usually, this option is automatically selected when needed. + However, you may want to enable it manually for running the regmap + KUnit tests. + + If unsure, say N. config REGMAP_KUNIT tristate "KUnit tests for regmap" - depends on KUNIT + depends on KUNIT && REGMAP default KUNIT_ALL_TESTS - select REGMAP select REGMAP_RAM config REGMAP_AC97 diff --git a/drivers/base/regmap/regcache-maple.c b/drivers/base/regmap/regcache-maple.c index 9b1b559107ef..c2e3a0f6c218 100644 --- a/drivers/base/regmap/regcache-maple.c +++ b/drivers/base/regmap/regcache-maple.c @@ -203,15 +203,18 @@ static int regcache_maple_sync(struct regmap *map, unsigned int min, mas_for_each(&mas, entry, max) { for (r = max(mas.index, lmin); r <= min(mas.last, lmax); r++) { + mas_pause(&mas); + rcu_read_unlock(); ret = regcache_sync_val(map, r, entry[r - mas.index]); if (ret != 0) goto out; + rcu_read_lock(); } } -out: rcu_read_unlock(); +out: map->cache_bypass = false; return ret; diff --git a/drivers/base/regmap/regmap-sdw.c b/drivers/base/regmap/regmap-sdw.c index 09899ae99fc1..159c0b740b00 100644 --- a/drivers/base/regmap/regmap-sdw.c +++ b/drivers/base/regmap/regmap-sdw.c @@ -59,6 +59,10 @@ static int regmap_sdw_config_check(const struct regmap_config *config) if (config->pad_bits != 0) return -ENOTSUPP; + /* Only bulk writes are supported not multi-register writes */ + if (config->can_multi_write) + return -ENOTSUPP; + return 0; } diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index db7851f0e3b8..fa2d3fba6ac9 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -2082,6 +2082,8 @@ int _regmap_raw_write(struct regmap *map, unsigned int reg, size_t val_count = val_len / val_bytes; size_t chunk_count, chunk_bytes; size_t chunk_regs = val_count; + size_t max_data = map->max_raw_write - map->format.reg_bytes - + map->format.pad_bytes; int ret, i; if (!val_count) @@ -2089,8 +2091,8 @@ int _regmap_raw_write(struct regmap *map, unsigned int reg, if (map->use_single_write) chunk_regs = 1; - else if (map->max_raw_write && val_len > map->max_raw_write) - chunk_regs = map->max_raw_write / val_bytes; + else if (map->max_raw_write && val_len > max_data) + chunk_regs = max_data / val_bytes; chunk_count = val_count / chunk_regs; chunk_bytes = chunk_regs * val_bytes; diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index c7ed5d69e9ee..33d3298a0da1 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -1120,6 +1120,11 @@ static inline bool ublk_queue_ready(struct ublk_queue *ubq) return ubq->nr_io_ready == ubq->q_depth; } +static void ublk_cmd_cancel_cb(struct io_uring_cmd *cmd, unsigned issue_flags) +{ + io_uring_cmd_done(cmd, UBLK_IO_RES_ABORT, 0, issue_flags); +} + static void ublk_cancel_queue(struct ublk_queue *ubq) { int i; @@ -1131,8 +1136,8 @@ static void ublk_cancel_queue(struct ublk_queue *ubq) struct ublk_io *io = &ubq->ios[i]; if (io->flags & UBLK_IO_FLAG_ACTIVE) - io_uring_cmd_done(io->cmd, UBLK_IO_RES_ABORT, 0, - IO_URING_F_UNLOCKED); + io_uring_cmd_complete_in_task(io->cmd, + ublk_cmd_cancel_cb); } /* all io commands are canceled */ diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 23ed258b57f0..c1890c8a9f6e 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -780,7 +780,8 @@ static int blkif_queue_rw_req(struct request *req, struct blkfront_ring_info *ri ring_req->u.rw.handle = info->handle; ring_req->operation = rq_data_dir(req) ? BLKIF_OP_WRITE : BLKIF_OP_READ; - if (req_op(req) == REQ_OP_FLUSH || req->cmd_flags & REQ_FUA) { + if (req_op(req) == REQ_OP_FLUSH || + (req_op(req) == REQ_OP_WRITE && (req->cmd_flags & REQ_FUA))) { /* * Ideally we can do an unordered flush-to-disk. * In case the backend onlysupports barriers, use that. diff --git a/drivers/bluetooth/btnxpuart.c b/drivers/bluetooth/btnxpuart.c index 3a34d7c1475b..52ef44688d38 100644 --- a/drivers/bluetooth/btnxpuart.c +++ b/drivers/bluetooth/btnxpuart.c @@ -1319,17 +1319,17 @@ static void nxp_serdev_remove(struct serdev_device *serdev) hci_free_dev(hdev); } -static struct btnxpuart_data w8987_data = { +static struct btnxpuart_data w8987_data __maybe_unused = { .helper_fw_name = NULL, .fw_name = FIRMWARE_W8987, }; -static struct btnxpuart_data w8997_data = { +static struct btnxpuart_data w8997_data __maybe_unused = { .helper_fw_name = FIRMWARE_HELPER, .fw_name = FIRMWARE_W8997, }; -static const struct of_device_id nxpuart_of_match_table[] = { +static const struct of_device_id nxpuart_of_match_table[] __maybe_unused = { { .compatible = "nxp,88w8987-bt", .data = &w8987_data }, { .compatible = "nxp,88w8997-bt", .data = &w8997_data }, { } diff --git a/drivers/char/agp/parisc-agp.c b/drivers/char/agp/parisc-agp.c index d68d05d5d383..514f9f287a78 100644 --- a/drivers/char/agp/parisc-agp.c +++ b/drivers/char/agp/parisc-agp.c @@ -90,6 +90,9 @@ parisc_agp_tlbflush(struct agp_memory *mem) { struct _parisc_agp_info *info = &parisc_agp_info; + /* force fdc ops to be visible to IOMMU */ + asm_io_sync(); + writeq(info->gart_base | ilog2(info->gart_size), info->ioc_regs+IOC_PCOM); readq(info->ioc_regs+IOC_PCOM); /* flush */ } @@ -158,6 +161,7 @@ parisc_agp_insert_memory(struct agp_memory *mem, off_t pg_start, int type) info->gatt[j] = parisc_agp_mask_memory(agp_bridge, paddr, type); + asm_io_fdc(&info->gatt[j]); } } @@ -191,7 +195,16 @@ static unsigned long parisc_agp_mask_memory(struct agp_bridge_data *bridge, dma_addr_t addr, int type) { - return SBA_PDIR_VALID_BIT | addr; + unsigned ci; /* coherent index */ + dma_addr_t pa; + + pa = addr & IOVP_MASK; + asm("lci 0(%1), %0" : "=r" (ci) : "r" (phys_to_virt(pa))); + + pa |= (ci >> PAGE_SHIFT) & 0xff;/* move CI (8 bits) into lowest byte */ + pa |= SBA_PDIR_VALID_BIT; /* set "valid" bit */ + + return cpu_to_le64(pa); } static void diff --git a/drivers/char/tpm/tpm_tis.c b/drivers/char/tpm/tpm_tis.c index 709b4e13bd6e..7db3593941ea 100644 --- a/drivers/char/tpm/tpm_tis.c +++ b/drivers/char/tpm/tpm_tis.c @@ -138,6 +138,13 @@ static const struct dmi_system_id tpm_tis_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad L490"), }, }, + { + .callback = tpm_tis_disable_irq, + .ident = "UPX-TGL", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "AAEON"), + }, + }, {} }; diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c index 29904395e95f..b2f05d27167e 100644 --- a/drivers/cpufreq/acpi-cpufreq.c +++ b/drivers/cpufreq/acpi-cpufreq.c @@ -975,7 +975,7 @@ static int __init acpi_cpufreq_probe(struct platform_device *pdev) /* don't keep reloading if cpufreq_driver exists */ if (cpufreq_get_current_driver()) - return -EEXIST; + return -ENODEV; pr_debug("%s\n", __func__); diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c index 5a3d4aa0f45a..ddd346a239e0 100644 --- a/drivers/cpufreq/amd-pstate.c +++ b/drivers/cpufreq/amd-pstate.c @@ -444,9 +444,8 @@ static int amd_pstate_verify(struct cpufreq_policy_data *policy) return 0; } -static int amd_pstate_target(struct cpufreq_policy *policy, - unsigned int target_freq, - unsigned int relation) +static int amd_pstate_update_freq(struct cpufreq_policy *policy, + unsigned int target_freq, bool fast_switch) { struct cpufreq_freqs freqs; struct amd_cpudata *cpudata = policy->driver_data; @@ -465,26 +464,51 @@ static int amd_pstate_target(struct cpufreq_policy *policy, des_perf = DIV_ROUND_CLOSEST(target_freq * cap_perf, cpudata->max_freq); - cpufreq_freq_transition_begin(policy, &freqs); + WARN_ON(fast_switch && !policy->fast_switch_enabled); + /* + * If fast_switch is desired, then there aren't any registered + * transition notifiers. See comment for + * cpufreq_enable_fast_switch(). + */ + if (!fast_switch) + cpufreq_freq_transition_begin(policy, &freqs); + amd_pstate_update(cpudata, min_perf, des_perf, - max_perf, false, policy->governor->flags); - cpufreq_freq_transition_end(policy, &freqs, false); + max_perf, fast_switch, policy->governor->flags); + + if (!fast_switch) + cpufreq_freq_transition_end(policy, &freqs, false); return 0; } +static int amd_pstate_target(struct cpufreq_policy *policy, + unsigned int target_freq, + unsigned int relation) +{ + return amd_pstate_update_freq(policy, target_freq, false); +} + +static unsigned int amd_pstate_fast_switch(struct cpufreq_policy *policy, + unsigned int target_freq) +{ + return amd_pstate_update_freq(policy, target_freq, true); +} + static void amd_pstate_adjust_perf(unsigned int cpu, unsigned long _min_perf, unsigned long target_perf, unsigned long capacity) { unsigned long max_perf, min_perf, des_perf, - cap_perf, lowest_nonlinear_perf; + cap_perf, lowest_nonlinear_perf, max_freq; struct cpufreq_policy *policy = cpufreq_cpu_get(cpu); struct amd_cpudata *cpudata = policy->driver_data; + unsigned int target_freq; cap_perf = READ_ONCE(cpudata->highest_perf); lowest_nonlinear_perf = READ_ONCE(cpudata->lowest_nonlinear_perf); + max_freq = READ_ONCE(cpudata->max_freq); des_perf = cap_perf; if (target_perf < capacity) @@ -501,6 +525,10 @@ static void amd_pstate_adjust_perf(unsigned int cpu, if (max_perf < min_perf) max_perf = min_perf; + des_perf = clamp_t(unsigned long, des_perf, min_perf, max_perf); + target_freq = div_u64(des_perf * max_freq, max_perf); + policy->cur = target_freq; + amd_pstate_update(cpudata, min_perf, des_perf, max_perf, true, policy->governor->flags); cpufreq_cpu_put(policy); @@ -715,6 +743,7 @@ static int amd_pstate_cpu_exit(struct cpufreq_policy *policy) freq_qos_remove_request(&cpudata->req[1]); freq_qos_remove_request(&cpudata->req[0]); + policy->fast_switch_possible = false; kfree(cpudata); return 0; @@ -1079,7 +1108,6 @@ static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy) policy->policy = CPUFREQ_POLICY_POWERSAVE; if (boot_cpu_has(X86_FEATURE_CPPC)) { - policy->fast_switch_possible = true; ret = rdmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, &value); if (ret) return ret; @@ -1102,7 +1130,6 @@ free_cpudata1: static int amd_pstate_epp_cpu_exit(struct cpufreq_policy *policy) { pr_debug("CPU %d exiting\n", policy->cpu); - policy->fast_switch_possible = false; return 0; } @@ -1309,6 +1336,7 @@ static struct cpufreq_driver amd_pstate_driver = { .flags = CPUFREQ_CONST_LOOPS | CPUFREQ_NEED_UPDATE_LIMITS, .verify = amd_pstate_verify, .target = amd_pstate_target, + .fast_switch = amd_pstate_fast_switch, .init = amd_pstate_cpu_init, .exit = amd_pstate_cpu_exit, .suspend = amd_pstate_cpu_suspend, diff --git a/drivers/cpufreq/pcc-cpufreq.c b/drivers/cpufreq/pcc-cpufreq.c index 1d2cfea9858a..73efbcf5513b 100644 --- a/drivers/cpufreq/pcc-cpufreq.c +++ b/drivers/cpufreq/pcc-cpufreq.c @@ -583,7 +583,7 @@ static int __init pcc_cpufreq_probe(struct platform_device *pdev) /* Skip initialization if another cpufreq driver is there. */ if (cpufreq_get_current_driver()) - return -EEXIST; + return -ENODEV; if (acpi_disabled) return -ENODEV; diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c index 23b9ff920d7e..bea9cf31a12d 100644 --- a/drivers/cxl/core/mbox.c +++ b/drivers/cxl/core/mbox.c @@ -1028,7 +1028,7 @@ static int cxl_mem_get_partition_info(struct cxl_dev_state *cxlds) * cxl_dev_state_identify() - Send the IDENTIFY command to the device. * @cxlds: The device data for the operation * - * Return: 0 if identify was executed successfully. + * Return: 0 if identify was executed successfully or media not ready. * * This will dispatch the identify command to the device and on success populate * structures to be exported to sysfs. @@ -1041,6 +1041,9 @@ int cxl_dev_state_identify(struct cxl_dev_state *cxlds) u32 val; int rc; + if (!cxlds->media_ready) + return 0; + mbox_cmd = (struct cxl_mbox_cmd) { .opcode = CXL_MBOX_OP_IDENTIFY, .size_out = sizeof(id), @@ -1102,6 +1105,13 @@ int cxl_mem_create_range_info(struct cxl_dev_state *cxlds) struct device *dev = cxlds->dev; int rc; + if (!cxlds->media_ready) { + cxlds->dpa_res = DEFINE_RES_MEM(0, 0); + cxlds->ram_res = DEFINE_RES_MEM(0, 0); + cxlds->pmem_res = DEFINE_RES_MEM(0, 0); + return 0; + } + cxlds->dpa_res = (struct resource)DEFINE_RES_MEM(0, cxlds->total_bytes); diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c index f332fe7af92b..67f4ab6daa34 100644 --- a/drivers/cxl/core/pci.c +++ b/drivers/cxl/core/pci.c @@ -101,23 +101,57 @@ int devm_cxl_port_enumerate_dports(struct cxl_port *port) } EXPORT_SYMBOL_NS_GPL(devm_cxl_port_enumerate_dports, CXL); -/* - * Wait up to @media_ready_timeout for the device to report memory - * active. - */ -int cxl_await_media_ready(struct cxl_dev_state *cxlds) +static int cxl_dvsec_mem_range_valid(struct cxl_dev_state *cxlds, int id) +{ + struct pci_dev *pdev = to_pci_dev(cxlds->dev); + int d = cxlds->cxl_dvsec; + bool valid = false; + int rc, i; + u32 temp; + + if (id > CXL_DVSEC_RANGE_MAX) + return -EINVAL; + + /* Check MEM INFO VALID bit first, give up after 1s */ + i = 1; + do { + rc = pci_read_config_dword(pdev, + d + CXL_DVSEC_RANGE_SIZE_LOW(id), + &temp); + if (rc) + return rc; + + valid = FIELD_GET(CXL_DVSEC_MEM_INFO_VALID, temp); + if (valid) + break; + msleep(1000); + } while (i--); + + if (!valid) { + dev_err(&pdev->dev, + "Timeout awaiting memory range %d valid after 1s.\n", + id); + return -ETIMEDOUT; + } + + return 0; +} + +static int cxl_dvsec_mem_range_active(struct cxl_dev_state *cxlds, int id) { struct pci_dev *pdev = to_pci_dev(cxlds->dev); int d = cxlds->cxl_dvsec; bool active = false; - u64 md_status; int rc, i; + u32 temp; - for (i = media_ready_timeout; i; i--) { - u32 temp; + if (id > CXL_DVSEC_RANGE_MAX) + return -EINVAL; + /* Check MEM ACTIVE bit, up to 60s timeout by default */ + for (i = media_ready_timeout; i; i--) { rc = pci_read_config_dword( - pdev, d + CXL_DVSEC_RANGE_SIZE_LOW(0), &temp); + pdev, d + CXL_DVSEC_RANGE_SIZE_LOW(id), &temp); if (rc) return rc; @@ -134,6 +168,39 @@ int cxl_await_media_ready(struct cxl_dev_state *cxlds) return -ETIMEDOUT; } + return 0; +} + +/* + * Wait up to @media_ready_timeout for the device to report memory + * active. + */ +int cxl_await_media_ready(struct cxl_dev_state *cxlds) +{ + struct pci_dev *pdev = to_pci_dev(cxlds->dev); + int d = cxlds->cxl_dvsec; + int rc, i, hdm_count; + u64 md_status; + u16 cap; + + rc = pci_read_config_word(pdev, + d + CXL_DVSEC_CAP_OFFSET, &cap); + if (rc) + return rc; + + hdm_count = FIELD_GET(CXL_DVSEC_HDM_COUNT_MASK, cap); + for (i = 0; i < hdm_count; i++) { + rc = cxl_dvsec_mem_range_valid(cxlds, i); + if (rc) + return rc; + } + + for (i = 0; i < hdm_count; i++) { + rc = cxl_dvsec_mem_range_active(cxlds, i); + if (rc) + return rc; + } + md_status = readq(cxlds->regs.memdev + CXLMDEV_STATUS_OFFSET); if (!CXLMDEV_READY(md_status)) return -EIO; @@ -241,17 +308,36 @@ static void disable_hdm(void *_cxlhdm) hdm + CXL_HDM_DECODER_CTRL_OFFSET); } -static int devm_cxl_enable_hdm(struct device *host, struct cxl_hdm *cxlhdm) +int devm_cxl_enable_hdm(struct cxl_port *port, struct cxl_hdm *cxlhdm) { - void __iomem *hdm = cxlhdm->regs.hdm_decoder; + void __iomem *hdm; u32 global_ctrl; + /* + * If the hdm capability was not mapped there is nothing to enable and + * the caller is responsible for what happens next. For example, + * emulate a passthrough decoder. + */ + if (IS_ERR(cxlhdm)) + return 0; + + hdm = cxlhdm->regs.hdm_decoder; global_ctrl = readl(hdm + CXL_HDM_DECODER_CTRL_OFFSET); + + /* + * If the HDM decoder capability was enabled on entry, skip + * registering disable_hdm() since this decode capability may be + * owned by platform firmware. + */ + if (global_ctrl & CXL_HDM_DECODER_ENABLE) + return 0; + writel(global_ctrl | CXL_HDM_DECODER_ENABLE, hdm + CXL_HDM_DECODER_CTRL_OFFSET); - return devm_add_action_or_reset(host, disable_hdm, cxlhdm); + return devm_add_action_or_reset(&port->dev, disable_hdm, cxlhdm); } +EXPORT_SYMBOL_NS_GPL(devm_cxl_enable_hdm, CXL); int cxl_dvsec_rr_decode(struct device *dev, int d, struct cxl_endpoint_dvsec_info *info) @@ -425,7 +511,7 @@ int cxl_hdm_decode_init(struct cxl_dev_state *cxlds, struct cxl_hdm *cxlhdm, if (info->mem_enabled) return 0; - rc = devm_cxl_enable_hdm(&port->dev, cxlhdm); + rc = devm_cxl_enable_hdm(port, cxlhdm); if (rc) return rc; diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c index da2068475fa2..e7c284c890bc 100644 --- a/drivers/cxl/core/port.c +++ b/drivers/cxl/core/port.c @@ -750,11 +750,10 @@ struct cxl_port *devm_cxl_add_port(struct device *host, struct device *uport, parent_port = parent_dport ? parent_dport->port : NULL; if (IS_ERR(port)) { - dev_dbg(uport, "Failed to add %s%s%s%s: %ld\n", - dev_name(&port->dev), - parent_port ? " to " : "", + dev_dbg(uport, "Failed to add%s%s%s: %ld\n", + parent_port ? " port to " : "", parent_port ? dev_name(&parent_port->dev) : "", - parent_port ? "" : " (root port)", + parent_port ? "" : " root port", PTR_ERR(port)); } else { dev_dbg(uport, "%s added%s%s%s\n", diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h index 044a92d9813e..f93a28538962 100644 --- a/drivers/cxl/cxl.h +++ b/drivers/cxl/cxl.h @@ -710,6 +710,7 @@ struct cxl_endpoint_dvsec_info { struct cxl_hdm; struct cxl_hdm *devm_cxl_setup_hdm(struct cxl_port *port, struct cxl_endpoint_dvsec_info *info); +int devm_cxl_enable_hdm(struct cxl_port *port, struct cxl_hdm *cxlhdm); int devm_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm, struct cxl_endpoint_dvsec_info *info); int devm_cxl_add_passthrough_decoder(struct cxl_port *port); diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h index db12b6313afb..a2845a7a69d8 100644 --- a/drivers/cxl/cxlmem.h +++ b/drivers/cxl/cxlmem.h @@ -266,6 +266,7 @@ struct cxl_poison_state { * @regs: Parsed register blocks * @cxl_dvsec: Offset to the PCIe device DVSEC * @rcd: operating in RCD mode (CXL 3.0 9.11.8 CXL Devices Attached to an RCH) + * @media_ready: Indicate whether the device media is usable * @payload_size: Size of space for payload * (CXL 2.0 8.2.8.4.3 Mailbox Capabilities Register) * @lsa_size: Size of Label Storage Area @@ -303,6 +304,7 @@ struct cxl_dev_state { int cxl_dvsec; bool rcd; + bool media_ready; size_t payload_size; size_t lsa_size; struct mutex mbox_mutex; /* Protects device mailbox and firmware */ diff --git a/drivers/cxl/cxlpci.h b/drivers/cxl/cxlpci.h index 0465ef963cd6..7c02e55b8042 100644 --- a/drivers/cxl/cxlpci.h +++ b/drivers/cxl/cxlpci.h @@ -31,6 +31,8 @@ #define CXL_DVSEC_RANGE_BASE_LOW(i) (0x24 + (i * 0x10)) #define CXL_DVSEC_MEM_BASE_LOW_MASK GENMASK(31, 28) +#define CXL_DVSEC_RANGE_MAX 2 + /* CXL 2.0 8.1.4: Non-CXL Function Map DVSEC */ #define CXL_DVSEC_FUNCTION_MAP 2 diff --git a/drivers/cxl/mem.c b/drivers/cxl/mem.c index 10caf180b3fa..519edd0eb196 100644 --- a/drivers/cxl/mem.c +++ b/drivers/cxl/mem.c @@ -124,6 +124,9 @@ static int cxl_mem_probe(struct device *dev) struct dentry *dentry; int rc; + if (!cxlds->media_ready) + return -EBUSY; + /* * Someone is trying to reattach this device after it lost its port * connection (an endpoint port previously registered by this memdev was diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c index f7a5b8e9c102..0872f2233ed0 100644 --- a/drivers/cxl/pci.c +++ b/drivers/cxl/pci.c @@ -708,6 +708,12 @@ static int cxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (rc) dev_dbg(&pdev->dev, "Failed to map RAS capability.\n"); + rc = cxl_await_media_ready(cxlds); + if (rc == 0) + cxlds->media_ready = true; + else + dev_warn(&pdev->dev, "Media not active (%d)\n", rc); + rc = cxl_pci_setup_mailbox(cxlds); if (rc) return rc; diff --git a/drivers/cxl/port.c b/drivers/cxl/port.c index eb57324c4ad4..c23b6164e1c0 100644 --- a/drivers/cxl/port.c +++ b/drivers/cxl/port.c @@ -60,13 +60,17 @@ static int discover_region(struct device *dev, void *root) static int cxl_switch_port_probe(struct cxl_port *port) { struct cxl_hdm *cxlhdm; - int rc; + int rc, nr_dports; - rc = devm_cxl_port_enumerate_dports(port); - if (rc < 0) - return rc; + nr_dports = devm_cxl_port_enumerate_dports(port); + if (nr_dports < 0) + return nr_dports; cxlhdm = devm_cxl_setup_hdm(port, NULL); + rc = devm_cxl_enable_hdm(port, cxlhdm); + if (rc) + return rc; + if (!IS_ERR(cxlhdm)) return devm_cxl_enumerate_decoders(cxlhdm, NULL); @@ -75,7 +79,7 @@ static int cxl_switch_port_probe(struct cxl_port *port) return PTR_ERR(cxlhdm); } - if (rc == 1) { + if (nr_dports == 1) { dev_dbg(&port->dev, "Fallback to passthrough decoder\n"); return devm_cxl_add_passthrough_decoder(port); } @@ -113,12 +117,6 @@ static int cxl_endpoint_port_probe(struct cxl_port *port) if (rc) return rc; - rc = cxl_await_media_ready(cxlds); - if (rc) { - dev_err(&port->dev, "Media not active (%d)\n", rc); - return rc; - } - rc = devm_cxl_enumerate_decoders(cxlhdm, &info); if (rc) return rc; diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c index 8858470246e1..ee3a219e3a89 100644 --- a/drivers/dma/at_hdmac.c +++ b/drivers/dma/at_hdmac.c @@ -132,7 +132,7 @@ #define ATC_DST_PIP BIT(12) /* Destination Picture-in-Picture enabled */ #define ATC_SRC_DSCR_DIS BIT(16) /* Src Descriptor fetch disable */ #define ATC_DST_DSCR_DIS BIT(20) /* Dst Descriptor fetch disable */ -#define ATC_FC GENMASK(22, 21) /* Choose Flow Controller */ +#define ATC_FC GENMASK(23, 21) /* Choose Flow Controller */ #define ATC_FC_MEM2MEM 0x0 /* Mem-to-Mem (DMA) */ #define ATC_FC_MEM2PER 0x1 /* Mem-to-Periph (DMA) */ #define ATC_FC_PER2MEM 0x2 /* Periph-to-Mem (DMA) */ @@ -153,8 +153,6 @@ #define ATC_AUTO BIT(31) /* Auto multiple buffer tx enable */ /* Bitfields in CFG */ -#define ATC_PER_MSB(h) ((0x30U & (h)) >> 4) /* Extract most significant bits of a handshaking identifier */ - #define ATC_SRC_PER GENMASK(3, 0) /* Channel src rq associated with periph handshaking ifc h */ #define ATC_DST_PER GENMASK(7, 4) /* Channel dst rq associated with periph handshaking ifc h */ #define ATC_SRC_REP BIT(8) /* Source Replay Mod */ @@ -181,10 +179,15 @@ #define ATC_DPIP_HOLE GENMASK(15, 0) #define ATC_DPIP_BOUNDARY GENMASK(25, 16) -#define ATC_SRC_PER_ID(id) (FIELD_PREP(ATC_SRC_PER_MSB, (id)) | \ - FIELD_PREP(ATC_SRC_PER, (id))) -#define ATC_DST_PER_ID(id) (FIELD_PREP(ATC_DST_PER_MSB, (id)) | \ - FIELD_PREP(ATC_DST_PER, (id))) +#define ATC_PER_MSB GENMASK(5, 4) /* Extract MSBs of a handshaking identifier */ +#define ATC_SRC_PER_ID(id) \ + ({ typeof(id) _id = (id); \ + FIELD_PREP(ATC_SRC_PER_MSB, FIELD_GET(ATC_PER_MSB, _id)) | \ + FIELD_PREP(ATC_SRC_PER, _id); }) +#define ATC_DST_PER_ID(id) \ + ({ typeof(id) _id = (id); \ + FIELD_PREP(ATC_DST_PER_MSB, FIELD_GET(ATC_PER_MSB, _id)) | \ + FIELD_PREP(ATC_DST_PER, _id); }) diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c index 7da6d9b6098e..c3b37168b21f 100644 --- a/drivers/dma/at_xdmac.c +++ b/drivers/dma/at_xdmac.c @@ -1102,6 +1102,8 @@ at_xdmac_prep_interleaved(struct dma_chan *chan, NULL, src_addr, dst_addr, xt, xt->sgl); + if (!first) + return NULL; /* Length of the block is (BLEN+1) microblocks. */ for (i = 0; i < xt->numf - 1; i++) @@ -1132,8 +1134,9 @@ at_xdmac_prep_interleaved(struct dma_chan *chan, src_addr, dst_addr, xt, chunk); if (!desc) { - list_splice_tail_init(&first->descs_list, - &atchan->free_descs_list); + if (first) + list_splice_tail_init(&first->descs_list, + &atchan->free_descs_list); return NULL; } diff --git a/drivers/dma/idxd/cdev.c b/drivers/dma/idxd/cdev.c index ecbf67c2ad2b..d32deb9b4e3d 100644 --- a/drivers/dma/idxd/cdev.c +++ b/drivers/dma/idxd/cdev.c @@ -277,7 +277,6 @@ static int idxd_cdev_open(struct inode *inode, struct file *filp) if (wq_dedicated(wq)) { rc = idxd_wq_set_pasid(wq, pasid); if (rc < 0) { - iommu_sva_unbind_device(sva); dev_err(dev, "wq set pasid failed: %d\n", rc); goto failed_set_pasid; } diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c index 0d9257fbdfb0..b4731fe6bbc1 100644 --- a/drivers/dma/pl330.c +++ b/drivers/dma/pl330.c @@ -1050,7 +1050,7 @@ static bool _trigger(struct pl330_thread *thrd) return true; } -static bool _start(struct pl330_thread *thrd) +static bool pl330_start_thread(struct pl330_thread *thrd) { switch (_state(thrd)) { case PL330_STATE_FAULT_COMPLETING: @@ -1702,7 +1702,7 @@ static int pl330_update(struct pl330_dmac *pl330) thrd->req_running = -1; /* Get going again ASAP */ - _start(thrd); + pl330_start_thread(thrd); /* For now, just make a list of callbacks to be done */ list_add_tail(&descdone->rqd, &pl330->req_done); @@ -2089,7 +2089,7 @@ static void pl330_tasklet(struct tasklet_struct *t) } else { /* Make sure the PL330 Channel thread is active */ spin_lock(&pch->thread->dmac->lock); - _start(pch->thread); + pl330_start_thread(pch->thread); spin_unlock(&pch->thread->dmac->lock); } @@ -2107,7 +2107,7 @@ static void pl330_tasklet(struct tasklet_struct *t) if (power_down) { pch->active = true; spin_lock(&pch->thread->dmac->lock); - _start(pch->thread); + pl330_start_thread(pch->thread); spin_unlock(&pch->thread->dmac->lock); power_down = false; } diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c index fc3a2a05ab7b..b8329a23728d 100644 --- a/drivers/dma/ti/k3-udma.c +++ b/drivers/dma/ti/k3-udma.c @@ -5527,7 +5527,7 @@ static int udma_probe(struct platform_device *pdev) return ret; } -static int udma_pm_suspend(struct device *dev) +static int __maybe_unused udma_pm_suspend(struct device *dev) { struct udma_dev *ud = dev_get_drvdata(dev); struct dma_device *dma_dev = &ud->ddev; @@ -5549,7 +5549,7 @@ static int udma_pm_suspend(struct device *dev) return 0; } -static int udma_pm_resume(struct device *dev) +static int __maybe_unused udma_pm_resume(struct device *dev) { struct udma_dev *ud = dev_get_drvdata(dev); struct dma_device *dma_dev = &ud->ddev; diff --git a/drivers/firmware/arm_ffa/bus.c b/drivers/firmware/arm_ffa/bus.c index f29d77ecf72d..2b8bfcd010f5 100644 --- a/drivers/firmware/arm_ffa/bus.c +++ b/drivers/firmware/arm_ffa/bus.c @@ -15,6 +15,8 @@ #include "common.h" +static DEFINE_IDA(ffa_bus_id); + static int ffa_device_match(struct device *dev, struct device_driver *drv) { const struct ffa_device_id *id_table; @@ -53,7 +55,8 @@ static void ffa_device_remove(struct device *dev) { struct ffa_driver *ffa_drv = to_ffa_driver(dev->driver); - ffa_drv->remove(to_ffa_dev(dev)); + if (ffa_drv->remove) + ffa_drv->remove(to_ffa_dev(dev)); } static int ffa_device_uevent(const struct device *dev, struct kobj_uevent_env *env) @@ -130,6 +133,7 @@ static void ffa_release_device(struct device *dev) { struct ffa_device *ffa_dev = to_ffa_dev(dev); + ida_free(&ffa_bus_id, ffa_dev->id); kfree(ffa_dev); } @@ -170,18 +174,24 @@ bool ffa_device_is_valid(struct ffa_device *ffa_dev) struct ffa_device *ffa_device_register(const uuid_t *uuid, int vm_id, const struct ffa_ops *ops) { - int ret; + int id, ret; struct device *dev; struct ffa_device *ffa_dev; + id = ida_alloc_min(&ffa_bus_id, 1, GFP_KERNEL); + if (id < 0) + return NULL; + ffa_dev = kzalloc(sizeof(*ffa_dev), GFP_KERNEL); - if (!ffa_dev) + if (!ffa_dev) { + ida_free(&ffa_bus_id, id); return NULL; + } dev = &ffa_dev->dev; dev->bus = &ffa_bus_type; dev->release = ffa_release_device; - dev_set_name(&ffa_dev->dev, "arm-ffa-%04x", vm_id); + dev_set_name(&ffa_dev->dev, "arm-ffa-%d", id); ffa_dev->vm_id = vm_id; ffa_dev->ops = ops; @@ -217,4 +227,5 @@ void arm_ffa_bus_exit(void) { ffa_devices_unregister(); bus_unregister(&ffa_bus_type); + ida_destroy(&ffa_bus_id); } diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c index fa85c64d3ded..e23409138667 100644 --- a/drivers/firmware/arm_ffa/driver.c +++ b/drivers/firmware/arm_ffa/driver.c @@ -193,7 +193,8 @@ __ffa_partition_info_get(u32 uuid0, u32 uuid1, u32 uuid2, u32 uuid3, int idx, count, flags = 0, sz, buf_sz; ffa_value_t partition_info; - if (!buffer || !num_partitions) /* Just get the count for now */ + if (drv_info->version > FFA_VERSION_1_0 && + (!buffer || !num_partitions)) /* Just get the count for now */ flags = PARTITION_INFO_GET_RETURN_COUNT_ONLY; mutex_lock(&drv_info->rx_lock); @@ -420,12 +421,17 @@ ffa_setup_and_transmit(u32 func_id, void *buffer, u32 max_fragsize, ep_mem_access->receiver = args->attrs[idx].receiver; ep_mem_access->attrs = args->attrs[idx].attrs; ep_mem_access->composite_off = COMPOSITE_OFFSET(args->nattrs); + ep_mem_access->flag = 0; + ep_mem_access->reserved = 0; } + mem_region->reserved_0 = 0; + mem_region->reserved_1 = 0; mem_region->ep_count = args->nattrs; composite = buffer + COMPOSITE_OFFSET(args->nattrs); composite->total_pg_cnt = ffa_get_num_pages_sg(args->sg); composite->addr_range_cnt = num_entries; + composite->reserved = 0; length = COMPOSITE_CONSTITUENTS_OFFSET(args->nattrs, num_entries); frag_len = COMPOSITE_CONSTITUENTS_OFFSET(args->nattrs, 0); @@ -460,6 +466,7 @@ ffa_setup_and_transmit(u32 func_id, void *buffer, u32 max_fragsize, constituents->address = sg_phys(args->sg); constituents->pg_cnt = args->sg->length / FFA_PAGE_SIZE; + constituents->reserved = 0; constituents++; frag_len += sizeof(struct ffa_mem_region_addr_range); } while ((args->sg = sg_next(args->sg))); diff --git a/drivers/firmware/arm_scmi/raw_mode.c b/drivers/firmware/arm_scmi/raw_mode.c index d40df099fd51..6971dcf72fb9 100644 --- a/drivers/firmware/arm_scmi/raw_mode.c +++ b/drivers/firmware/arm_scmi/raw_mode.c @@ -1066,7 +1066,7 @@ static int scmi_xfer_raw_worker_init(struct scmi_raw_mode_info *raw) raw->wait_wq = alloc_workqueue("scmi-raw-wait-wq-%d", WQ_UNBOUND | WQ_FREEZABLE | - WQ_HIGHPRI, WQ_SYSFS, raw->id); + WQ_HIGHPRI | WQ_SYSFS, 0, raw->id); if (!raw->wait_wq) return -ENOMEM; diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig index 5521f060d58e..f45c6a36551c 100644 --- a/drivers/gpio/Kconfig +++ b/drivers/gpio/Kconfig @@ -897,7 +897,7 @@ config GPIO_F7188X help This option enables support for GPIOs found on Fintek Super-I/O chips F71869, F71869A, F71882FG, F71889F and F81866. - As well as Nuvoton Super-I/O chip NCT6116D. + As well as Nuvoton Super-I/O chip NCT6126D. To compile this driver as a module, choose M here: the module will be called f7188x-gpio. diff --git a/drivers/gpio/gpio-f7188x.c b/drivers/gpio/gpio-f7188x.c index 9effa7769bef..f54ca5a1775e 100644 --- a/drivers/gpio/gpio-f7188x.c +++ b/drivers/gpio/gpio-f7188x.c @@ -48,7 +48,7 @@ /* * Nuvoton devices. */ -#define SIO_NCT6116D_ID 0xD283 /* NCT6116D chipset ID */ +#define SIO_NCT6126D_ID 0xD283 /* NCT6126D chipset ID */ #define SIO_LD_GPIO_NUVOTON 0x07 /* GPIO logical device */ @@ -62,7 +62,7 @@ enum chips { f81866, f81804, f81865, - nct6116d, + nct6126d, }; static const char * const f7188x_names[] = { @@ -74,7 +74,7 @@ static const char * const f7188x_names[] = { "f81866", "f81804", "f81865", - "nct6116d", + "nct6126d", }; struct f7188x_sio { @@ -187,8 +187,8 @@ static int f7188x_gpio_set_config(struct gpio_chip *chip, unsigned offset, /* Output mode register (0:open drain 1:push-pull). */ #define f7188x_gpio_out_mode(base) ((base) + 3) -#define f7188x_gpio_dir_invert(type) ((type) == nct6116d) -#define f7188x_gpio_data_single(type) ((type) == nct6116d) +#define f7188x_gpio_dir_invert(type) ((type) == nct6126d) +#define f7188x_gpio_data_single(type) ((type) == nct6126d) static struct f7188x_gpio_bank f71869_gpio_bank[] = { F7188X_GPIO_BANK(0, 6, 0xF0, DRVNAME "-0"), @@ -274,7 +274,7 @@ static struct f7188x_gpio_bank f81865_gpio_bank[] = { F7188X_GPIO_BANK(60, 5, 0x90, DRVNAME "-6"), }; -static struct f7188x_gpio_bank nct6116d_gpio_bank[] = { +static struct f7188x_gpio_bank nct6126d_gpio_bank[] = { F7188X_GPIO_BANK(0, 8, 0xE0, DRVNAME "-0"), F7188X_GPIO_BANK(10, 8, 0xE4, DRVNAME "-1"), F7188X_GPIO_BANK(20, 8, 0xE8, DRVNAME "-2"), @@ -282,7 +282,7 @@ static struct f7188x_gpio_bank nct6116d_gpio_bank[] = { F7188X_GPIO_BANK(40, 8, 0xF0, DRVNAME "-4"), F7188X_GPIO_BANK(50, 8, 0xF4, DRVNAME "-5"), F7188X_GPIO_BANK(60, 8, 0xF8, DRVNAME "-6"), - F7188X_GPIO_BANK(70, 1, 0xFC, DRVNAME "-7"), + F7188X_GPIO_BANK(70, 8, 0xFC, DRVNAME "-7"), }; static int f7188x_gpio_get_direction(struct gpio_chip *chip, unsigned offset) @@ -490,9 +490,9 @@ static int f7188x_gpio_probe(struct platform_device *pdev) data->nr_bank = ARRAY_SIZE(f81865_gpio_bank); data->bank = f81865_gpio_bank; break; - case nct6116d: - data->nr_bank = ARRAY_SIZE(nct6116d_gpio_bank); - data->bank = nct6116d_gpio_bank; + case nct6126d: + data->nr_bank = ARRAY_SIZE(nct6126d_gpio_bank); + data->bank = nct6126d_gpio_bank; break; default: return -ENODEV; @@ -559,9 +559,9 @@ static int __init f7188x_find(int addr, struct f7188x_sio *sio) case SIO_F81865_ID: sio->type = f81865; break; - case SIO_NCT6116D_ID: + case SIO_NCT6126D_ID: sio->device = SIO_LD_GPIO_NUVOTON; - sio->type = nct6116d; + sio->type = nct6126d; break; default: pr_info("Unsupported Fintek device 0x%04x\n", devid); @@ -569,7 +569,7 @@ static int __init f7188x_find(int addr, struct f7188x_sio *sio) } /* double check manufacturer where possible */ - if (sio->type != nct6116d) { + if (sio->type != nct6126d) { manid = superio_inw(addr, SIO_FINTEK_MANID); if (manid != SIO_FINTEK_ID) { pr_debug("Not a Fintek device at 0x%08x\n", addr); @@ -581,7 +581,7 @@ static int __init f7188x_find(int addr, struct f7188x_sio *sio) err = 0; pr_info("Found %s at %#x\n", f7188x_names[sio->type], (unsigned int)addr); - if (sio->type != nct6116d) + if (sio->type != nct6126d) pr_info(" revision %d\n", superio_inb(addr, SIO_FINTEK_DEVREV)); err: diff --git a/drivers/gpio/gpio-mockup.c b/drivers/gpio/gpio-mockup.c index e6a7049bef64..b32063ac845a 100644 --- a/drivers/gpio/gpio-mockup.c +++ b/drivers/gpio/gpio-mockup.c @@ -369,7 +369,7 @@ static void gpio_mockup_debugfs_setup(struct device *dev, priv->offset = i; priv->desc = gpiochip_get_desc(gc, i); - debugfs_create_file(name, 0200, chip->dbg_dir, priv, + debugfs_create_file(name, 0600, chip->dbg_dir, priv, &gpio_mockup_debugfs_ops); } } diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 04fb05df805b..a7220e04a93e 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -209,6 +209,8 @@ static int gpiochip_find_base(int ngpio) break; /* nope, check the space right after the chip */ base = gdev->base + gdev->ngpio; + if (base < GPIO_DYNAMIC_BASE) + base = GPIO_DYNAMIC_BASE; } if (gpio_is_valid(base)) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c index f52d0ba91a77..a7d250809da9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c @@ -582,7 +582,8 @@ void amdgpu_fence_driver_hw_fini(struct amdgpu_device *adev) if (r) amdgpu_fence_driver_force_completion(ring); - if (ring->fence_drv.irq_src) + if (!drm_dev_is_unplugged(adev_to_drm(adev)) && + ring->fence_drv.irq_src) amdgpu_irq_put(adev, ring->fence_drv.irq_src, ring->fence_drv.irq_type); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index f5b5ce1051a2..ab44c1391d52 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -6892,8 +6892,10 @@ static int gfx_v10_0_kiq_resume(struct amdgpu_device *adev) return r; r = amdgpu_bo_kmap(ring->mqd_obj, (void **)&ring->mqd_ptr); - if (unlikely(r != 0)) + if (unlikely(r != 0)) { + amdgpu_bo_unreserve(ring->mqd_obj); return r; + } gfx_v10_0_kiq_init_queue(ring); amdgpu_bo_kunmap(ring->mqd_obj); @@ -8152,8 +8154,14 @@ static int gfx_v10_0_set_powergating_state(void *handle, case IP_VERSION(10, 3, 3): case IP_VERSION(10, 3, 6): case IP_VERSION(10, 3, 7): + if (!enable) + amdgpu_gfx_off_ctrl(adev, false); + gfx_v10_cntl_pg(adev, enable); - amdgpu_gfx_off_ctrl(adev, enable); + + if (enable) + amdgpu_gfx_off_ctrl(adev, true); + break; default: break; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c index f5c376276984..c4940b6ea1c4 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c @@ -4667,24 +4667,27 @@ static uint64_t gfx_v11_0_get_gpu_clock_counter(struct amdgpu_device *adev) uint64_t clock; uint64_t clock_counter_lo, clock_counter_hi_pre, clock_counter_hi_after; - amdgpu_gfx_off_ctrl(adev, false); - mutex_lock(&adev->gfx.gpu_clock_mutex); if (amdgpu_sriov_vf(adev)) { + amdgpu_gfx_off_ctrl(adev, false); + mutex_lock(&adev->gfx.gpu_clock_mutex); clock_counter_hi_pre = (uint64_t)RREG32_SOC15(GC, 0, regCP_MES_MTIME_HI); clock_counter_lo = (uint64_t)RREG32_SOC15(GC, 0, regCP_MES_MTIME_LO); clock_counter_hi_after = (uint64_t)RREG32_SOC15(GC, 0, regCP_MES_MTIME_HI); if (clock_counter_hi_pre != clock_counter_hi_after) clock_counter_lo = (uint64_t)RREG32_SOC15(GC, 0, regCP_MES_MTIME_LO); + mutex_unlock(&adev->gfx.gpu_clock_mutex); + amdgpu_gfx_off_ctrl(adev, true); } else { + preempt_disable(); clock_counter_hi_pre = (uint64_t)RREG32_SOC15(SMUIO, 0, regGOLDEN_TSC_COUNT_UPPER); clock_counter_lo = (uint64_t)RREG32_SOC15(SMUIO, 0, regGOLDEN_TSC_COUNT_LOWER); clock_counter_hi_after = (uint64_t)RREG32_SOC15(SMUIO, 0, regGOLDEN_TSC_COUNT_UPPER); if (clock_counter_hi_pre != clock_counter_hi_after) clock_counter_lo = (uint64_t)RREG32_SOC15(SMUIO, 0, regGOLDEN_TSC_COUNT_LOWER); + preempt_enable(); } clock = clock_counter_lo | (clock_counter_hi_after << 32ULL); - mutex_unlock(&adev->gfx.gpu_clock_mutex); - amdgpu_gfx_off_ctrl(adev, true); + return clock; } @@ -5150,8 +5153,14 @@ static int gfx_v11_0_set_powergating_state(void *handle, break; case IP_VERSION(11, 0, 1): case IP_VERSION(11, 0, 4): + if (!enable) + amdgpu_gfx_off_ctrl(adev, false); + gfx_v11_cntl_pg(adev, enable); - amdgpu_gfx_off_ctrl(adev, enable); + + if (enable) + amdgpu_gfx_off_ctrl(adev, true); + break; default: break; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index f46d4b18a3fa..ce22f7b30416 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -3617,8 +3617,10 @@ static int gfx_v9_0_kiq_resume(struct amdgpu_device *adev) return r; r = amdgpu_bo_kmap(ring->mqd_obj, (void **)&ring->mqd_ptr); - if (unlikely(r != 0)) + if (unlikely(r != 0)) { + amdgpu_bo_unreserve(ring->mqd_obj); return r; + } gfx_v9_0_kiq_init_queue(ring); amdgpu_bo_kunmap(ring->mqd_obj); @@ -4003,30 +4005,25 @@ static uint64_t gfx_v9_0_get_gpu_clock_counter(struct amdgpu_device *adev) clock = clock_lo | (clock_hi << 32ULL); break; case IP_VERSION(9, 1, 0): + case IP_VERSION(9, 2, 2): preempt_disable(); - clock_hi = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_UPPER_Raven); - clock_lo = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_LOWER_Raven); - hi_check = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_UPPER_Raven); - /* The PWR TSC clock frequency is 100MHz, which sets 32-bit carry over - * roughly every 42 seconds. - */ - if (hi_check != clock_hi) { + if (adev->rev_id >= 0x8) { + clock_hi = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_UPPER_Raven2); + clock_lo = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_LOWER_Raven2); + hi_check = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_UPPER_Raven2); + } else { + clock_hi = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_UPPER_Raven); clock_lo = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_LOWER_Raven); - clock_hi = hi_check; + hi_check = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_UPPER_Raven); } - preempt_enable(); - clock = clock_lo | (clock_hi << 32ULL); - break; - case IP_VERSION(9, 2, 2): - preempt_disable(); - clock_hi = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_UPPER_Raven2); - clock_lo = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_LOWER_Raven2); - hi_check = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_UPPER_Raven2); /* The PWR TSC clock frequency is 100MHz, which sets 32-bit carry over - * roughly every 42 seconds. - */ + * roughly every 42 seconds. + */ if (hi_check != clock_hi) { - clock_lo = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_LOWER_Raven2); + if (adev->rev_id >= 0x8) + clock_lo = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_LOWER_Raven2); + else + clock_lo = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_LOWER_Raven); clock_hi = hi_check; } preempt_enable(); diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c index d95f9fe8f1c5..4116c112e8a0 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c @@ -31,6 +31,8 @@ #include "umc_v8_10.h" #include "athub/athub_3_0_0_sh_mask.h" #include "athub/athub_3_0_0_offset.h" +#include "dcn/dcn_3_2_0_offset.h" +#include "dcn/dcn_3_2_0_sh_mask.h" #include "oss/osssys_6_0_0_offset.h" #include "ivsrcid/vmc/irqsrcs_vmc_1_0.h" #include "navi10_enum.h" @@ -546,7 +548,24 @@ static void gmc_v11_0_get_vm_pte(struct amdgpu_device *adev, static unsigned gmc_v11_0_get_vbios_fb_size(struct amdgpu_device *adev) { - return 0; + u32 d1vga_control = RREG32_SOC15(DCE, 0, regD1VGA_CONTROL); + unsigned size; + + if (REG_GET_FIELD(d1vga_control, D1VGA_CONTROL, D1VGA_MODE_ENABLE)) { + size = AMDGPU_VBIOS_VGA_ALLOCATION; + } else { + u32 viewport; + u32 pitch; + + viewport = RREG32_SOC15(DCE, 0, regHUBP0_DCSURF_PRI_VIEWPORT_DIMENSION); + pitch = RREG32_SOC15(DCE, 0, regHUBPREQ0_DCSURF_SURFACE_PITCH); + size = (REG_GET_FIELD(viewport, + HUBP0_DCSURF_PRI_VIEWPORT_DIMENSION, PRI_VIEWPORT_HEIGHT) * + REG_GET_FIELD(pitch, HUBPREQ0_DCSURF_SURFACE_PITCH, PITCH) * + 4); + } + + return size; } static const struct amdgpu_gmc_funcs gmc_v11_0_gmc_funcs = { diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v10_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v10_0.c index e1b7fca09666..5f10883da6a2 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v10_0.c @@ -57,7 +57,13 @@ static int psp_v10_0_init_microcode(struct psp_context *psp) if (err) return err; - return psp_init_ta_microcode(psp, ucode_prefix); + err = psp_init_ta_microcode(psp, ucode_prefix); + if ((adev->ip_versions[GC_HWIP][0] == IP_VERSION(9, 1, 0)) && + (adev->pdev->revision == 0xa1) && + (psp->securedisplay_context.context.bin_desc.fw_version >= 0x27000008)) { + adev->psp.securedisplay_context.context.bin_desc.size_bytes = 0; + } + return err; } static int psp_v10_0_ring_create(struct psp_context *psp, 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 8b4b186c57f5..d5cec03eaa8d 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -2479,20 +2479,25 @@ static void dm_gpureset_toggle_interrupts(struct amdgpu_device *adev, if (acrtc && state->stream_status[i].plane_count != 0) { irq_source = IRQ_TYPE_PFLIP + acrtc->otg_inst; rc = dc_interrupt_set(adev->dm.dc, irq_source, enable) ? 0 : -EBUSY; - DRM_DEBUG_VBL("crtc %d - vupdate irq %sabling: r=%d\n", - acrtc->crtc_id, enable ? "en" : "dis", rc); if (rc) DRM_WARN("Failed to %s pflip interrupts\n", enable ? "enable" : "disable"); if (enable) { - rc = amdgpu_dm_crtc_enable_vblank(&acrtc->base); - if (rc) - DRM_WARN("Failed to enable vblank interrupts\n"); - } else { - amdgpu_dm_crtc_disable_vblank(&acrtc->base); - } + if (amdgpu_dm_crtc_vrr_active(to_dm_crtc_state(acrtc->base.state))) + rc = amdgpu_dm_crtc_set_vupdate_irq(&acrtc->base, true); + } else + rc = amdgpu_dm_crtc_set_vupdate_irq(&acrtc->base, false); + if (rc) + DRM_WARN("Failed to %sable vupdate interrupt\n", enable ? "en" : "dis"); + + irq_source = IRQ_TYPE_VBLANK + acrtc->otg_inst; + /* During gpu-reset we disable and then enable vblank irq, so + * don't use amdgpu_irq_get/put() to avoid refcount change. + */ + if (!dc_interrupt_set(adev->dm.dc, irq_source, enable)) + DRM_WARN("Failed to %sable vblank interrupt\n", enable ? "en" : "dis"); } } @@ -2852,7 +2857,7 @@ static int dm_resume(void *handle) * this is the case when traversing through already created * MST connectors, should be skipped */ - if (aconnector->dc_link->type == dc_connection_mst_branch) + if (aconnector && aconnector->mst_root) continue; mutex_lock(&aconnector->hpd_lock); @@ -6737,7 +6742,7 @@ static int dm_encoder_helper_atomic_check(struct drm_encoder *encoder, int clock, bpp = 0; bool is_y420 = false; - if (!aconnector->mst_output_port || !aconnector->dc_sink) + if (!aconnector->mst_output_port) return 0; mst_port = aconnector->mst_output_port; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c index e3762e806617..440fc0869a34 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c @@ -146,7 +146,6 @@ static void vblank_control_worker(struct work_struct *work) static inline int dm_set_vblank(struct drm_crtc *crtc, bool enable) { - enum dc_irq_source irq_source; struct amdgpu_crtc *acrtc = to_amdgpu_crtc(crtc); struct amdgpu_device *adev = drm_to_adev(crtc->dev); struct dm_crtc_state *acrtc_state = to_dm_crtc_state(crtc->state); @@ -169,18 +168,9 @@ static inline int dm_set_vblank(struct drm_crtc *crtc, bool enable) if (rc) return rc; - if (amdgpu_in_reset(adev)) { - irq_source = IRQ_TYPE_VBLANK + acrtc->otg_inst; - /* During gpu-reset we disable and then enable vblank irq, so - * don't use amdgpu_irq_get/put() to avoid refcount change. - */ - if (!dc_interrupt_set(adev->dm.dc, irq_source, enable)) - rc = -EBUSY; - } else { - rc = (enable) - ? amdgpu_irq_get(adev, &adev->crtc_irq, acrtc->crtc_id) - : amdgpu_irq_put(adev, &adev->crtc_irq, acrtc->crtc_id); - } + rc = (enable) + ? amdgpu_irq_get(adev, &adev->crtc_irq, acrtc->crtc_id) + : amdgpu_irq_put(adev, &adev->crtc_irq, acrtc->crtc_id); if (rc) return rc; diff --git a/drivers/gpu/drm/amd/display/dc/link/link_validation.c b/drivers/gpu/drm/amd/display/dc/link/link_validation.c index d4b7da526f0a..e8b2fc4002a5 100644 --- a/drivers/gpu/drm/amd/display/dc/link/link_validation.c +++ b/drivers/gpu/drm/amd/display/dc/link/link_validation.c @@ -359,5 +359,8 @@ bool link_validate_dpia_bandwidth(const struct dc_stream_state *stream, const un link[i] = stream[i].link; bw_needed[i] = dc_bandwidth_in_kbps_from_timing(&stream[i].timing); } + + ret = dpia_validate_usb4_bw(link, bw_needed, num_streams); + return ret; } diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c index 58c2246918fd..f4f40459f22b 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c @@ -871,13 +871,11 @@ static ssize_t amdgpu_get_pp_od_clk_voltage(struct device *dev, } if (ret == -ENOENT) { size = amdgpu_dpm_print_clock_levels(adev, OD_SCLK, buf); - if (size > 0) { - size += amdgpu_dpm_print_clock_levels(adev, OD_MCLK, buf + size); - size += amdgpu_dpm_print_clock_levels(adev, OD_VDDC_CURVE, buf + size); - size += amdgpu_dpm_print_clock_levels(adev, OD_VDDGFX_OFFSET, buf + size); - size += amdgpu_dpm_print_clock_levels(adev, OD_RANGE, buf + size); - size += amdgpu_dpm_print_clock_levels(adev, OD_CCLK, buf + size); - } + size += amdgpu_dpm_print_clock_levels(adev, OD_MCLK, buf + size); + size += amdgpu_dpm_print_clock_levels(adev, OD_VDDC_CURVE, buf + size); + size += amdgpu_dpm_print_clock_levels(adev, OD_VDDGFX_OFFSET, buf + size); + size += amdgpu_dpm_print_clock_levels(adev, OD_RANGE, buf + size); + size += amdgpu_dpm_print_clock_levels(adev, OD_CCLK, buf + size); } if (size == 0) diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c index 5633c5797e85..2ddf5198e5c4 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c @@ -733,6 +733,24 @@ static int smu_late_init(void *handle) return ret; } + /* + * Explicitly notify PMFW the power mode the system in. Since + * the PMFW may boot the ASIC with a different mode. + * For those supporting ACDC switch via gpio, PMFW will + * handle the switch automatically. Driver involvement + * is unnecessary. + */ + if (!smu->dc_controlled_by_gpio) { + ret = smu_set_power_source(smu, + adev->pm.ac_power ? SMU_POWER_SOURCE_AC : + SMU_POWER_SOURCE_DC); + if (ret) { + dev_err(adev->dev, "Failed to switch to %s mode!\n", + adev->pm.ac_power ? "AC" : "DC"); + return ret; + } + } + if ((adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 1)) || (adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 3))) return 0; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c index c4000518dc56..275f708db636 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c @@ -3413,26 +3413,8 @@ static int navi10_post_smu_init(struct smu_context *smu) return 0; ret = navi10_run_umc_cdr_workaround(smu); - if (ret) { + if (ret) dev_err(adev->dev, "Failed to apply umc cdr workaround!\n"); - return ret; - } - - if (!smu->dc_controlled_by_gpio) { - /* - * For Navi1X, manually switch it to AC mode as PMFW - * may boot it with DC mode. - */ - ret = smu_v11_0_set_power_source(smu, - adev->pm.ac_power ? - SMU_POWER_SOURCE_AC : - SMU_POWER_SOURCE_DC); - if (ret) { - dev_err(adev->dev, "Failed to switch to %s mode!\n", - adev->pm.ac_power ? "AC" : "DC"); - return ret; - } - } return ret; } diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c index 3d9ff46706fb..bba621615abf 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c @@ -125,6 +125,7 @@ static struct cmn2asic_msg_mapping smu_v13_0_7_message_map[SMU_MSG_MAX_COUNT] = MSG_MAP(ArmD3, PPSMC_MSG_ArmD3, 0), MSG_MAP(AllowGpo, PPSMC_MSG_SetGpoAllow, 0), MSG_MAP(GetPptLimit, PPSMC_MSG_GetPptLimit, 0), + MSG_MAP(NotifyPowerSource, PPSMC_MSG_NotifyPowerSource, 0), }; static struct cmn2asic_mapping smu_v13_0_7_clk_map[SMU_CLK_COUNT] = { @@ -1770,6 +1771,7 @@ static const struct pptable_funcs smu_v13_0_7_ppt_funcs = { .enable_mgpu_fan_boost = smu_v13_0_7_enable_mgpu_fan_boost, .get_power_limit = smu_v13_0_7_get_power_limit, .set_power_limit = smu_v13_0_set_power_limit, + .set_power_source = smu_v13_0_set_power_source, .get_power_profile_mode = smu_v13_0_7_get_power_profile_mode, .set_power_profile_mode = smu_v13_0_7_set_power_profile_mode, .set_tool_table_location = smu_v13_0_set_tool_table_location, diff --git a/drivers/gpu/drm/drm_managed.c b/drivers/gpu/drm/drm_managed.c index 4cf214de50c4..c21c3f623033 100644 --- a/drivers/gpu/drm/drm_managed.c +++ b/drivers/gpu/drm/drm_managed.c @@ -264,28 +264,10 @@ void drmm_kfree(struct drm_device *dev, void *data) } EXPORT_SYMBOL(drmm_kfree); -static void drmm_mutex_release(struct drm_device *dev, void *res) +void __drmm_mutex_release(struct drm_device *dev, void *res) { struct mutex *lock = res; mutex_destroy(lock); } - -/** - * drmm_mutex_init - &drm_device-managed mutex_init() - * @dev: DRM device - * @lock: lock to be initialized - * - * Returns: - * 0 on success, or a negative errno code otherwise. - * - * This is a &drm_device-managed version of mutex_init(). The initialized - * lock is automatically destroyed on the final drm_dev_put(). - */ -int drmm_mutex_init(struct drm_device *dev, struct mutex *lock) -{ - mutex_init(lock); - - return drmm_add_action_or_reset(dev, drmm_mutex_release, lock); -} -EXPORT_SYMBOL(drmm_mutex_init); +EXPORT_SYMBOL(__drmm_mutex_release); diff --git a/drivers/gpu/drm/drm_panel_orientation_quirks.c b/drivers/gpu/drm/drm_panel_orientation_quirks.c index b1a38e6ce2f8..0cb646cb04ee 100644 --- a/drivers/gpu/drm/drm_panel_orientation_quirks.c +++ b/drivers/gpu/drm/drm_panel_orientation_quirks.c @@ -179,7 +179,7 @@ static const struct dmi_system_id orientation_data[] = { }, { /* AYA NEO AIR */ .matches = { DMI_EXACT_MATCH(DMI_SYS_VENDOR, "AYANEO"), - DMI_MATCH(DMI_BOARD_NAME, "AIR"), + DMI_MATCH(DMI_PRODUCT_NAME, "AIR"), }, .driver_data = (void *)&lcd1080x1920_leftside_up, }, { /* AYA NEO NEXT */ diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.h b/drivers/gpu/drm/exynos/exynos_drm_g2d.h index 74ea3c26dead..1a5ae781b56c 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_g2d.h +++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.h @@ -34,11 +34,11 @@ static inline int exynos_g2d_exec_ioctl(struct drm_device *dev, void *data, return -ENODEV; } -int g2d_open(struct drm_device *drm_dev, struct drm_file *file) +static inline int g2d_open(struct drm_device *drm_dev, struct drm_file *file) { return 0; } -void g2d_close(struct drm_device *drm_dev, struct drm_file *file) +static inline void g2d_close(struct drm_device *drm_dev, struct drm_file *file) { } #endif diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index 3c29792137a5..0aae9a1eb3d5 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -1851,9 +1851,17 @@ static void hsw_crtc_disable(struct intel_atomic_state *state, intel_disable_shared_dpll(old_crtc_state); - intel_encoders_post_pll_disable(state, crtc); + if (!intel_crtc_is_bigjoiner_slave(old_crtc_state)) { + struct intel_crtc *slave_crtc; + + intel_encoders_post_pll_disable(state, crtc); - intel_dmc_disable_pipe(i915, crtc->pipe); + intel_dmc_disable_pipe(i915, crtc->pipe); + + for_each_intel_crtc_in_pipe_mask(&i915->drm, slave_crtc, + intel_crtc_bigjoiner_slave_pipes(old_crtc_state)) + intel_dmc_disable_pipe(i915, slave_crtc->pipe); + } } static void i9xx_pfit_enable(const struct intel_crtc_state *crtc_state) diff --git a/drivers/gpu/drm/i915/display/intel_hdcp.c b/drivers/gpu/drm/i915/display/intel_hdcp.c index 650232c4892b..b183efab04a1 100644 --- a/drivers/gpu/drm/i915/display/intel_hdcp.c +++ b/drivers/gpu/drm/i915/display/intel_hdcp.c @@ -204,8 +204,6 @@ bool intel_hdcp2_capable(struct intel_connector *connector) struct intel_digital_port *dig_port = intel_attached_dig_port(connector); struct drm_i915_private *dev_priv = to_i915(connector->base.dev); struct intel_hdcp *hdcp = &connector->hdcp; - struct intel_gt *gt = dev_priv->media_gt; - struct intel_gsc_uc *gsc = >->uc.gsc; bool capable = false; /* I915 support for HDCP2.2 */ @@ -213,9 +211,13 @@ bool intel_hdcp2_capable(struct intel_connector *connector) return false; /* If MTL+ make sure gsc is loaded and proxy is setup */ - if (intel_hdcp_gsc_cs_required(dev_priv)) - if (!intel_uc_fw_is_running(&gsc->fw)) + if (intel_hdcp_gsc_cs_required(dev_priv)) { + struct intel_gt *gt = dev_priv->media_gt; + struct intel_gsc_uc *gsc = gt ? >->uc.gsc : NULL; + + if (!gsc || !intel_uc_fw_is_running(&gsc->fw)) return false; + } /* MEI/GSC interface is solid depending on which is used */ mutex_lock(&dev_priv->display.hdcp.comp_mutex); diff --git a/drivers/gpu/drm/mgag200/mgag200_mode.c b/drivers/gpu/drm/mgag200/mgag200_mode.c index 0f2dd26755df..af3ce5a6a636 100644 --- a/drivers/gpu/drm/mgag200/mgag200_mode.c +++ b/drivers/gpu/drm/mgag200/mgag200_mode.c @@ -642,6 +642,11 @@ void mgag200_crtc_helper_atomic_enable(struct drm_crtc *crtc, struct drm_atomic_ if (funcs->pixpllc_atomic_update) funcs->pixpllc_atomic_update(crtc, old_state); + if (crtc_state->gamma_lut) + mgag200_crtc_set_gamma(mdev, format, crtc_state->gamma_lut->data); + else + mgag200_crtc_set_gamma_linear(mdev, format); + mgag200_enable_display(mdev); if (funcs->enable_vidrst) diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_0_msm8998.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_0_msm8998.h index 2b3ae84057df..bdcd554fc8a8 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_0_msm8998.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_0_msm8998.h @@ -98,17 +98,17 @@ static const struct dpu_sspp_cfg msm8998_sspp[] = { static const struct dpu_lm_cfg msm8998_lm[] = { LM_BLK("lm_0", LM_0, 0x44000, MIXER_MSM8998_MASK, - &msm8998_lm_sblk, PINGPONG_0, LM_2, DSPP_0), + &msm8998_lm_sblk, PINGPONG_0, LM_1, DSPP_0), LM_BLK("lm_1", LM_1, 0x45000, MIXER_MSM8998_MASK, - &msm8998_lm_sblk, PINGPONG_1, LM_5, DSPP_1), + &msm8998_lm_sblk, PINGPONG_1, LM_0, DSPP_1), LM_BLK("lm_2", LM_2, 0x46000, MIXER_MSM8998_MASK, - &msm8998_lm_sblk, PINGPONG_2, LM_0, 0), + &msm8998_lm_sblk, PINGPONG_2, LM_5, 0), LM_BLK("lm_3", LM_3, 0x47000, MIXER_MSM8998_MASK, &msm8998_lm_sblk, PINGPONG_MAX, 0, 0), LM_BLK("lm_4", LM_4, 0x48000, MIXER_MSM8998_MASK, &msm8998_lm_sblk, PINGPONG_MAX, 0, 0), LM_BLK("lm_5", LM_5, 0x49000, MIXER_MSM8998_MASK, - &msm8998_lm_sblk, PINGPONG_3, LM_1, 0), + &msm8998_lm_sblk, PINGPONG_3, LM_2, 0), }; static const struct dpu_pingpong_cfg msm8998_pp[] = { @@ -134,10 +134,10 @@ static const struct dpu_dspp_cfg msm8998_dspp[] = { }; static const struct dpu_intf_cfg msm8998_intf[] = { - INTF_BLK("intf_0", INTF_0, 0x6a000, 0x280, INTF_DP, 0, 25, INTF_SDM845_MASK, MDP_SSPP_TOP0_INTR, 24, 25), - INTF_BLK("intf_1", INTF_1, 0x6a800, 0x280, INTF_DSI, 0, 25, INTF_SDM845_MASK, MDP_SSPP_TOP0_INTR, 26, 27), - INTF_BLK("intf_2", INTF_2, 0x6b000, 0x280, INTF_DSI, 1, 25, INTF_SDM845_MASK, MDP_SSPP_TOP0_INTR, 28, 29), - INTF_BLK("intf_3", INTF_3, 0x6b800, 0x280, INTF_HDMI, 0, 25, INTF_SDM845_MASK, MDP_SSPP_TOP0_INTR, 30, 31), + INTF_BLK("intf_0", INTF_0, 0x6a000, 0x280, INTF_DP, 0, 21, INTF_SDM845_MASK, MDP_SSPP_TOP0_INTR, 24, 25), + INTF_BLK("intf_1", INTF_1, 0x6a800, 0x280, INTF_DSI, 0, 21, INTF_SDM845_MASK, MDP_SSPP_TOP0_INTR, 26, 27), + INTF_BLK("intf_2", INTF_2, 0x6b000, 0x280, INTF_DSI, 1, 21, INTF_SDM845_MASK, MDP_SSPP_TOP0_INTR, 28, 29), + INTF_BLK("intf_3", INTF_3, 0x6b800, 0x280, INTF_HDMI, 0, 21, INTF_SDM845_MASK, MDP_SSPP_TOP0_INTR, 30, 31), }; static const struct dpu_perf_cfg msm8998_perf_data = { diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_0_sm8150.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_0_sm8150.h index 282d410269ff..42b0e58624d0 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_0_sm8150.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_0_sm8150.h @@ -128,10 +128,10 @@ static const struct dpu_dspp_cfg sm8150_dspp[] = { }; static const struct dpu_pingpong_cfg sm8150_pp[] = { - PP_BLK_TE("pingpong_0", PINGPONG_0, 0x70000, MERGE_3D_0, sdm845_pp_sblk_te, + PP_BLK("pingpong_0", PINGPONG_0, 0x70000, MERGE_3D_0, sdm845_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 12)), - PP_BLK_TE("pingpong_1", PINGPONG_1, 0x70800, MERGE_3D_0, sdm845_pp_sblk_te, + PP_BLK("pingpong_1", PINGPONG_1, 0x70800, MERGE_3D_0, sdm845_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 13)), PP_BLK("pingpong_2", PINGPONG_2, 0x71000, MERGE_3D_1, sdm845_pp_sblk, diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h index c57400265f28..e3bdfe7b30f1 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h @@ -116,10 +116,10 @@ static const struct dpu_lm_cfg sc8180x_lm[] = { }; static const struct dpu_pingpong_cfg sc8180x_pp[] = { - PP_BLK_TE("pingpong_0", PINGPONG_0, 0x70000, MERGE_3D_0, sdm845_pp_sblk_te, + PP_BLK("pingpong_0", PINGPONG_0, 0x70000, MERGE_3D_0, sdm845_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 12)), - PP_BLK_TE("pingpong_1", PINGPONG_1, 0x70800, MERGE_3D_0, sdm845_pp_sblk_te, + PP_BLK("pingpong_1", PINGPONG_1, 0x70800, MERGE_3D_0, sdm845_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 13)), PP_BLK("pingpong_2", PINGPONG_2, 0x71000, MERGE_3D_1, sdm845_pp_sblk, diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_0_sm8250.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_0_sm8250.h index 2c40229ea515..ed130582873c 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_0_sm8250.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_0_sm8250.h @@ -129,10 +129,10 @@ static const struct dpu_dspp_cfg sm8250_dspp[] = { }; static const struct dpu_pingpong_cfg sm8250_pp[] = { - PP_BLK_TE("pingpong_0", PINGPONG_0, 0x70000, MERGE_3D_0, sdm845_pp_sblk_te, + PP_BLK("pingpong_0", PINGPONG_0, 0x70000, MERGE_3D_0, sdm845_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 12)), - PP_BLK_TE("pingpong_1", PINGPONG_1, 0x70800, MERGE_3D_0, sdm845_pp_sblk_te, + PP_BLK("pingpong_1", PINGPONG_1, 0x70800, MERGE_3D_0, sdm845_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 13)), PP_BLK("pingpong_2", PINGPONG_2, 0x71000, MERGE_3D_1, sdm845_pp_sblk, diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_2_sc7180.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_2_sc7180.h index 8799ed757119..a46b11730a4d 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_2_sc7180.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_2_sc7180.h @@ -80,8 +80,8 @@ static const struct dpu_dspp_cfg sc7180_dspp[] = { }; static const struct dpu_pingpong_cfg sc7180_pp[] = { - PP_BLK_TE("pingpong_0", PINGPONG_0, 0x70000, 0, sdm845_pp_sblk_te, -1, -1), - PP_BLK_TE("pingpong_1", PINGPONG_1, 0x70800, 0, sdm845_pp_sblk_te, -1, -1), + PP_BLK("pingpong_0", PINGPONG_0, 0x70000, 0, sdm845_pp_sblk, -1, -1), + PP_BLK("pingpong_1", PINGPONG_1, 0x70800, 0, sdm845_pp_sblk, -1, -1), }; static const struct dpu_intf_cfg sc7180_intf[] = { diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_3_sm6115.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_3_sm6115.h index 6f04d8f85c92..988d820f7ef2 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_3_sm6115.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_3_sm6115.h @@ -122,7 +122,6 @@ const struct dpu_mdss_cfg dpu_sm6115_cfg = { .mdss_irqs = BIT(MDP_SSPP_TOP0_INTR) | \ BIT(MDP_SSPP_TOP0_INTR2) | \ BIT(MDP_SSPP_TOP0_HIST_INTR) | \ - BIT(MDP_INTF0_INTR) | \ BIT(MDP_INTF1_INTR), }; diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_5_qcm2290.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_5_qcm2290.h index 303492d62a5c..c9003dcc1a59 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_5_qcm2290.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_5_qcm2290.h @@ -112,7 +112,6 @@ const struct dpu_mdss_cfg dpu_qcm2290_cfg = { .mdss_irqs = BIT(MDP_SSPP_TOP0_INTR) | \ BIT(MDP_SSPP_TOP0_INTR2) | \ BIT(MDP_SSPP_TOP0_HIST_INTR) | \ - BIT(MDP_INTF0_INTR) | \ BIT(MDP_INTF1_INTR), }; diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h index ca107ca8de46..4f6a965bcd90 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h @@ -127,22 +127,22 @@ static const struct dpu_dspp_cfg sm8350_dspp[] = { }; static const struct dpu_pingpong_cfg sm8350_pp[] = { - PP_BLK_TE("pingpong_0", PINGPONG_0, 0x69000, MERGE_3D_0, sdm845_pp_sblk_te, + PP_BLK_DITHER("pingpong_0", PINGPONG_0, 0x69000, MERGE_3D_0, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 12)), - PP_BLK_TE("pingpong_1", PINGPONG_1, 0x6a000, MERGE_3D_0, sdm845_pp_sblk_te, + PP_BLK_DITHER("pingpong_1", PINGPONG_1, 0x6a000, MERGE_3D_0, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 13)), - PP_BLK("pingpong_2", PINGPONG_2, 0x6b000, MERGE_3D_1, sdm845_pp_sblk, + PP_BLK_DITHER("pingpong_2", PINGPONG_2, 0x6b000, MERGE_3D_1, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 10), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 14)), - PP_BLK("pingpong_3", PINGPONG_3, 0x6c000, MERGE_3D_1, sdm845_pp_sblk, + PP_BLK_DITHER("pingpong_3", PINGPONG_3, 0x6c000, MERGE_3D_1, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 11), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 15)), - PP_BLK("pingpong_4", PINGPONG_4, 0x6d000, MERGE_3D_2, sdm845_pp_sblk, + PP_BLK_DITHER("pingpong_4", PINGPONG_4, 0x6d000, MERGE_3D_2, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 30), -1), - PP_BLK("pingpong_5", PINGPONG_5, 0x6e000, MERGE_3D_2, sdm845_pp_sblk, + PP_BLK_DITHER("pingpong_5", PINGPONG_5, 0x6e000, MERGE_3D_2, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 31), -1), }; diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_2_sc7280.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_2_sc7280.h index 5957de185984..6b2c7eae71d9 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_2_sc7280.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_2_sc7280.h @@ -87,10 +87,10 @@ static const struct dpu_dspp_cfg sc7280_dspp[] = { }; static const struct dpu_pingpong_cfg sc7280_pp[] = { - PP_BLK("pingpong_0", PINGPONG_0, 0x69000, 0, sc7280_pp_sblk, -1, -1), - PP_BLK("pingpong_1", PINGPONG_1, 0x6a000, 0, sc7280_pp_sblk, -1, -1), - PP_BLK("pingpong_2", PINGPONG_2, 0x6b000, 0, sc7280_pp_sblk, -1, -1), - PP_BLK("pingpong_3", PINGPONG_3, 0x6c000, 0, sc7280_pp_sblk, -1, -1), + PP_BLK_DITHER("pingpong_0", PINGPONG_0, 0x69000, 0, sc7280_pp_sblk, -1, -1), + PP_BLK_DITHER("pingpong_1", PINGPONG_1, 0x6a000, 0, sc7280_pp_sblk, -1, -1), + PP_BLK_DITHER("pingpong_2", PINGPONG_2, 0x6b000, 0, sc7280_pp_sblk, -1, -1), + PP_BLK_DITHER("pingpong_3", PINGPONG_3, 0x6c000, 0, sc7280_pp_sblk, -1, -1), }; static const struct dpu_intf_cfg sc7280_intf[] = { diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h index 9aab110b8c44..706d0f13b598 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h @@ -121,18 +121,18 @@ static const struct dpu_dspp_cfg sc8280xp_dspp[] = { }; static const struct dpu_pingpong_cfg sc8280xp_pp[] = { - PP_BLK_TE("pingpong_0", PINGPONG_0, 0x69000, MERGE_3D_0, sdm845_pp_sblk_te, - DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8), -1), - PP_BLK_TE("pingpong_1", PINGPONG_1, 0x6a000, MERGE_3D_0, sdm845_pp_sblk_te, - DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9), -1), - PP_BLK_TE("pingpong_2", PINGPONG_2, 0x6b000, MERGE_3D_1, sdm845_pp_sblk_te, - DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 10), -1), - PP_BLK_TE("pingpong_3", PINGPONG_3, 0x6c000, MERGE_3D_1, sdm845_pp_sblk_te, - DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 11), -1), - PP_BLK_TE("pingpong_4", PINGPONG_4, 0x6d000, MERGE_3D_2, sdm845_pp_sblk_te, - DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 30), -1), - PP_BLK_TE("pingpong_5", PINGPONG_5, 0x6e000, MERGE_3D_2, sdm845_pp_sblk_te, - DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 31), -1), + PP_BLK_DITHER("pingpong_0", PINGPONG_0, 0x69000, MERGE_3D_0, sc7280_pp_sblk, + DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8), -1), + PP_BLK_DITHER("pingpong_1", PINGPONG_1, 0x6a000, MERGE_3D_0, sc7280_pp_sblk, + DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9), -1), + PP_BLK_DITHER("pingpong_2", PINGPONG_2, 0x6b000, MERGE_3D_1, sc7280_pp_sblk, + DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 10), -1), + PP_BLK_DITHER("pingpong_3", PINGPONG_3, 0x6c000, MERGE_3D_1, sc7280_pp_sblk, + DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 11), -1), + PP_BLK_DITHER("pingpong_4", PINGPONG_4, 0x6d000, MERGE_3D_2, sc7280_pp_sblk, + DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 30), -1), + PP_BLK_DITHER("pingpong_5", PINGPONG_5, 0x6e000, MERGE_3D_2, sc7280_pp_sblk, + DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 31), -1), }; static const struct dpu_merge_3d_cfg sc8280xp_merge_3d[] = { diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h index 02a259b6b426..4ecb3df5cbc0 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h @@ -128,28 +128,28 @@ static const struct dpu_dspp_cfg sm8450_dspp[] = { }; /* FIXME: interrupts */ static const struct dpu_pingpong_cfg sm8450_pp[] = { - PP_BLK_TE("pingpong_0", PINGPONG_0, 0x69000, MERGE_3D_0, sdm845_pp_sblk_te, + PP_BLK_DITHER("pingpong_0", PINGPONG_0, 0x69000, MERGE_3D_0, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 12)), - PP_BLK_TE("pingpong_1", PINGPONG_1, 0x6a000, MERGE_3D_0, sdm845_pp_sblk_te, + PP_BLK_DITHER("pingpong_1", PINGPONG_1, 0x6a000, MERGE_3D_0, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 13)), - PP_BLK("pingpong_2", PINGPONG_2, 0x6b000, MERGE_3D_1, sdm845_pp_sblk, + PP_BLK_DITHER("pingpong_2", PINGPONG_2, 0x6b000, MERGE_3D_1, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 10), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 14)), - PP_BLK("pingpong_3", PINGPONG_3, 0x6c000, MERGE_3D_1, sdm845_pp_sblk, + PP_BLK_DITHER("pingpong_3", PINGPONG_3, 0x6c000, MERGE_3D_1, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 11), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 15)), - PP_BLK("pingpong_4", PINGPONG_4, 0x6d000, MERGE_3D_2, sdm845_pp_sblk, + PP_BLK_DITHER("pingpong_4", PINGPONG_4, 0x6d000, MERGE_3D_2, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 30), -1), - PP_BLK("pingpong_5", PINGPONG_5, 0x6e000, MERGE_3D_2, sdm845_pp_sblk, + PP_BLK_DITHER("pingpong_5", PINGPONG_5, 0x6e000, MERGE_3D_2, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 31), -1), - PP_BLK("pingpong_6", PINGPONG_6, 0x65800, MERGE_3D_3, sdm845_pp_sblk, + PP_BLK_DITHER("pingpong_6", PINGPONG_6, 0x65800, MERGE_3D_3, sc7280_pp_sblk, -1, -1), - PP_BLK("pingpong_7", PINGPONG_7, 0x65c00, MERGE_3D_3, sdm845_pp_sblk, + PP_BLK_DITHER("pingpong_7", PINGPONG_7, 0x65c00, MERGE_3D_3, sc7280_pp_sblk, -1, -1), }; diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h index 9e403034093f..d0ab351b6a8b 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h @@ -132,28 +132,28 @@ static const struct dpu_dspp_cfg sm8550_dspp[] = { &sm8150_dspp_sblk), }; static const struct dpu_pingpong_cfg sm8550_pp[] = { - PP_BLK_DIPHER("pingpong_0", PINGPONG_0, 0x69000, MERGE_3D_0, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_0", PINGPONG_0, 0x69000, MERGE_3D_0, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8), -1), - PP_BLK_DIPHER("pingpong_1", PINGPONG_1, 0x6a000, MERGE_3D_0, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_1", PINGPONG_1, 0x6a000, MERGE_3D_0, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9), -1), - PP_BLK_DIPHER("pingpong_2", PINGPONG_2, 0x6b000, MERGE_3D_1, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_2", PINGPONG_2, 0x6b000, MERGE_3D_1, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 10), -1), - PP_BLK_DIPHER("pingpong_3", PINGPONG_3, 0x6c000, MERGE_3D_1, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_3", PINGPONG_3, 0x6c000, MERGE_3D_1, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 11), -1), - PP_BLK_DIPHER("pingpong_4", PINGPONG_4, 0x6d000, MERGE_3D_2, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_4", PINGPONG_4, 0x6d000, MERGE_3D_2, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 30), -1), - PP_BLK_DIPHER("pingpong_5", PINGPONG_5, 0x6e000, MERGE_3D_2, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_5", PINGPONG_5, 0x6e000, MERGE_3D_2, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 31), -1), - PP_BLK_DIPHER("pingpong_6", PINGPONG_6, 0x66000, MERGE_3D_3, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_6", PINGPONG_6, 0x66000, MERGE_3D_3, sc7280_pp_sblk, -1, -1), - PP_BLK_DIPHER("pingpong_7", PINGPONG_7, 0x66400, MERGE_3D_3, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_7", PINGPONG_7, 0x66400, MERGE_3D_3, sc7280_pp_sblk, -1, -1), }; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c index 03f162af1a50..5d994bce696f 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c @@ -491,7 +491,7 @@ static const struct dpu_pingpong_sub_blks sc7280_pp_sblk = { .len = 0x20, .version = 0x20000}, }; -#define PP_BLK_DIPHER(_name, _id, _base, _merge_3d, _sblk, _done, _rdptr) \ +#define PP_BLK_DITHER(_name, _id, _base, _merge_3d, _sblk, _done, _rdptr) \ {\ .name = _name, .id = _id, \ .base = _base, .len = 0, \ @@ -587,12 +587,12 @@ static const u32 sdm845_nrt_pri_lvl[] = {3, 3, 3, 3, 3, 3, 3, 3}; static const struct dpu_vbif_dynamic_ot_cfg msm8998_ot_rdwr_cfg[] = { { - .pps = 1088 * 1920 * 30, + .pps = 1920 * 1080 * 30, .ot_limit = 2, }, { - .pps = 1088 * 1920 * 60, - .ot_limit = 6, + .pps = 1920 * 1080 * 60, + .ot_limit = 4, }, { .pps = 3840 * 2160 * 30, @@ -705,10 +705,7 @@ static const struct dpu_qos_lut_entry msm8998_qos_linear[] = { {.fl = 10, .lut = 0x1555b}, {.fl = 11, .lut = 0x5555b}, {.fl = 12, .lut = 0x15555b}, - {.fl = 13, .lut = 0x55555b}, - {.fl = 14, .lut = 0}, - {.fl = 1, .lut = 0x1b}, - {.fl = 0, .lut = 0} + {.fl = 0, .lut = 0x55555b} }; static const struct dpu_qos_lut_entry sdm845_qos_linear[] = { @@ -730,9 +727,7 @@ static const struct dpu_qos_lut_entry msm8998_qos_macrotile[] = { {.fl = 10, .lut = 0x1aaff}, {.fl = 11, .lut = 0x5aaff}, {.fl = 12, .lut = 0x15aaff}, - {.fl = 13, .lut = 0x55aaff}, - {.fl = 1, .lut = 0x1aaff}, - {.fl = 0, .lut = 0}, + {.fl = 0, .lut = 0x55aaff}, }; static const struct dpu_qos_lut_entry sc7180_qos_linear[] = { diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c index 53326f25e40e..17f3e7e4f194 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c @@ -15,7 +15,7 @@ /* * Register offsets in MDSS register file for the interrupt registers - * w.r.t. to the MDP base + * w.r.t. the MDP base */ #define MDP_SSPP_TOP0_OFF 0x0 #define MDP_INTF_0_OFF 0x6A000 @@ -24,20 +24,23 @@ #define MDP_INTF_3_OFF 0x6B800 #define MDP_INTF_4_OFF 0x6C000 #define MDP_INTF_5_OFF 0x6C800 +#define INTF_INTR_EN 0x1c0 +#define INTF_INTR_STATUS 0x1c4 +#define INTF_INTR_CLEAR 0x1c8 #define MDP_AD4_0_OFF 0x7C000 #define MDP_AD4_1_OFF 0x7D000 #define MDP_AD4_INTR_EN_OFF 0x41c #define MDP_AD4_INTR_CLEAR_OFF 0x424 #define MDP_AD4_INTR_STATUS_OFF 0x420 -#define MDP_INTF_0_OFF_REV_7xxx 0x34000 -#define MDP_INTF_1_OFF_REV_7xxx 0x35000 -#define MDP_INTF_2_OFF_REV_7xxx 0x36000 -#define MDP_INTF_3_OFF_REV_7xxx 0x37000 -#define MDP_INTF_4_OFF_REV_7xxx 0x38000 -#define MDP_INTF_5_OFF_REV_7xxx 0x39000 -#define MDP_INTF_6_OFF_REV_7xxx 0x3a000 -#define MDP_INTF_7_OFF_REV_7xxx 0x3b000 -#define MDP_INTF_8_OFF_REV_7xxx 0x3c000 +#define MDP_INTF_0_OFF_REV_7xxx 0x34000 +#define MDP_INTF_1_OFF_REV_7xxx 0x35000 +#define MDP_INTF_2_OFF_REV_7xxx 0x36000 +#define MDP_INTF_3_OFF_REV_7xxx 0x37000 +#define MDP_INTF_4_OFF_REV_7xxx 0x38000 +#define MDP_INTF_5_OFF_REV_7xxx 0x39000 +#define MDP_INTF_6_OFF_REV_7xxx 0x3a000 +#define MDP_INTF_7_OFF_REV_7xxx 0x3b000 +#define MDP_INTF_8_OFF_REV_7xxx 0x3c000 /** * struct dpu_intr_reg - array of DPU register sets diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c index 84ee2efa9c66..b9dddf576c02 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c @@ -56,11 +56,6 @@ #define INTF_TPG_RGB_MAPPING 0x11C #define INTF_PROG_FETCH_START 0x170 #define INTF_PROG_ROT_START 0x174 - -#define INTF_FRAME_LINE_COUNT_EN 0x0A8 -#define INTF_FRAME_COUNT 0x0AC -#define INTF_LINE_COUNT 0x0B0 - #define INTF_MUX 0x25C #define INTF_STATUS 0x26C diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_wb.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_wb.c index 2d28afdf860e..a3e413d27717 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_wb.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_wb.c @@ -61,6 +61,7 @@ static const struct dpu_wb_cfg *_wb_offset(enum dpu_wb wb, for (i = 0; i < m->wb_count; i++) { if (wb == m->wb[i].id) { b->blk_addr = addr + m->wb[i].base; + b->log_mask = DPU_DBG_MASK_WB; return &m->wb[i]; } } diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hwio.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hwio.h index feb9a729844a..5acd5683d25a 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hwio.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hwio.h @@ -21,9 +21,6 @@ #define HIST_INTR_EN 0x01c #define HIST_INTR_STATUS 0x020 #define HIST_INTR_CLEAR 0x024 -#define INTF_INTR_EN 0x1C0 -#define INTF_INTR_STATUS 0x1C4 -#define INTF_INTR_CLEAR 0x1C8 #define SPLIT_DISPLAY_EN 0x2F4 #define SPLIT_DISPLAY_UPPER_PIPE_CTRL 0x2F8 #define DSPP_IGC_COLOR0_RAM_LUTN 0x300 diff --git a/drivers/gpu/drm/msm/dp/dp_audio.c b/drivers/gpu/drm/msm/dp/dp_audio.c index 6666783e1468..1245c7aa49df 100644 --- a/drivers/gpu/drm/msm/dp/dp_audio.c +++ b/drivers/gpu/drm/msm/dp/dp_audio.c @@ -593,6 +593,18 @@ static struct hdmi_codec_pdata codec_data = { .i2s = 1, }; +void dp_unregister_audio_driver(struct device *dev, struct dp_audio *dp_audio) +{ + struct dp_audio_private *audio_priv; + + audio_priv = container_of(dp_audio, struct dp_audio_private, dp_audio); + + if (audio_priv->audio_pdev) { + platform_device_unregister(audio_priv->audio_pdev); + audio_priv->audio_pdev = NULL; + } +} + int dp_register_audio_driver(struct device *dev, struct dp_audio *dp_audio) { diff --git a/drivers/gpu/drm/msm/dp/dp_audio.h b/drivers/gpu/drm/msm/dp/dp_audio.h index 84e5f4a5d26b..4ab78880af82 100644 --- a/drivers/gpu/drm/msm/dp/dp_audio.h +++ b/drivers/gpu/drm/msm/dp/dp_audio.h @@ -53,6 +53,8 @@ struct dp_audio *dp_audio_get(struct platform_device *pdev, int dp_register_audio_driver(struct device *dev, struct dp_audio *dp_audio); +void dp_unregister_audio_driver(struct device *dev, struct dp_audio *dp_audio); + /** * dp_audio_put() * diff --git a/drivers/gpu/drm/msm/dp/dp_display.c b/drivers/gpu/drm/msm/dp/dp_display.c index 3e13acdfa7e5..99a38dbe51c0 100644 --- a/drivers/gpu/drm/msm/dp/dp_display.c +++ b/drivers/gpu/drm/msm/dp/dp_display.c @@ -326,6 +326,7 @@ static void dp_display_unbind(struct device *dev, struct device *master, kthread_stop(dp->ev_tsk); dp_power_client_deinit(dp->power); + dp_unregister_audio_driver(dev, dp->audio); dp_aux_unregister(dp->aux); dp->drm_dev = NULL; dp->aux->drm_dev = NULL; diff --git a/drivers/gpu/drm/msm/msm_atomic.c b/drivers/gpu/drm/msm/msm_atomic.c index d77fa9793c54..9c45d641b521 100644 --- a/drivers/gpu/drm/msm/msm_atomic.c +++ b/drivers/gpu/drm/msm/msm_atomic.c @@ -155,6 +155,8 @@ static bool can_do_async(struct drm_atomic_state *state, for_each_new_crtc_in_state(state, crtc, crtc_state, i) { if (drm_atomic_crtc_needs_modeset(crtc_state)) return false; + if (!crtc_state->active) + return false; if (++num_crtcs > 1) return false; *async_crtc = crtc; diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index db6c4e281d75..cd39b9d8abdb 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -219,7 +219,8 @@ static void put_pages(struct drm_gem_object *obj) } } -static struct page **msm_gem_pin_pages_locked(struct drm_gem_object *obj) +static struct page **msm_gem_pin_pages_locked(struct drm_gem_object *obj, + unsigned madv) { struct msm_drm_private *priv = obj->dev->dev_private; struct msm_gem_object *msm_obj = to_msm_bo(obj); @@ -227,7 +228,9 @@ static struct page **msm_gem_pin_pages_locked(struct drm_gem_object *obj) msm_gem_assert_locked(obj); - if (GEM_WARN_ON(msm_obj->madv != MSM_MADV_WILLNEED)) { + if (GEM_WARN_ON(msm_obj->madv > madv)) { + DRM_DEV_ERROR(obj->dev->dev, "Invalid madv state: %u vs %u\n", + msm_obj->madv, madv); return ERR_PTR(-EBUSY); } @@ -248,7 +251,7 @@ struct page **msm_gem_pin_pages(struct drm_gem_object *obj) struct page **p; msm_gem_lock(obj); - p = msm_gem_pin_pages_locked(obj); + p = msm_gem_pin_pages_locked(obj, MSM_MADV_WILLNEED); msm_gem_unlock(obj); return p; @@ -473,10 +476,7 @@ int msm_gem_pin_vma_locked(struct drm_gem_object *obj, struct msm_gem_vma *vma) msm_gem_assert_locked(obj); - if (GEM_WARN_ON(msm_obj->madv != MSM_MADV_WILLNEED)) - return -EBUSY; - - pages = msm_gem_pin_pages_locked(obj); + pages = msm_gem_pin_pages_locked(obj, MSM_MADV_WILLNEED); if (IS_ERR(pages)) return PTR_ERR(pages); @@ -699,13 +699,7 @@ static void *get_vaddr(struct drm_gem_object *obj, unsigned madv) if (obj->import_attach) return ERR_PTR(-ENODEV); - if (GEM_WARN_ON(msm_obj->madv > madv)) { - DRM_DEV_ERROR(obj->dev->dev, "Invalid madv state: %u vs %u\n", - msm_obj->madv, madv); - return ERR_PTR(-EBUSY); - } - - pages = msm_gem_pin_pages_locked(obj); + pages = msm_gem_pin_pages_locked(obj, madv); if (IS_ERR(pages)) return ERR_CAST(pages); diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c index aff18c2f600a..9f5933c75e3d 100644 --- a/drivers/gpu/drm/msm/msm_gem_submit.c +++ b/drivers/gpu/drm/msm/msm_gem_submit.c @@ -722,7 +722,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, struct msm_drm_private *priv = dev->dev_private; struct drm_msm_gem_submit *args = data; struct msm_file_private *ctx = file->driver_priv; - struct msm_gem_submit *submit; + struct msm_gem_submit *submit = NULL; struct msm_gpu *gpu = priv->gpu; struct msm_gpu_submitqueue *queue; struct msm_ringbuffer *ring; @@ -769,13 +769,15 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, out_fence_fd = get_unused_fd_flags(O_CLOEXEC); if (out_fence_fd < 0) { ret = out_fence_fd; - return ret; + goto out_post_unlock; } } submit = submit_create(dev, gpu, queue, args->nr_bos, args->nr_cmds); - if (IS_ERR(submit)) - return PTR_ERR(submit); + if (IS_ERR(submit)) { + ret = PTR_ERR(submit); + goto out_post_unlock; + } trace_msm_gpu_submit(pid_nr(submit->pid), ring->id, submit->ident, args->nr_bos, args->nr_cmds); @@ -962,11 +964,20 @@ out: if (has_ww_ticket) ww_acquire_fini(&submit->ticket); out_unlock: - if (ret && (out_fence_fd >= 0)) - put_unused_fd(out_fence_fd); mutex_unlock(&queue->lock); out_post_unlock: - msm_gem_submit_put(submit); + if (ret && (out_fence_fd >= 0)) + put_unused_fd(out_fence_fd); + + if (!IS_ERR_OR_NULL(submit)) { + msm_gem_submit_put(submit); + } else { + /* + * If the submit hasn't yet taken ownership of the queue + * then we need to drop the reference ourself: + */ + msm_submitqueue_put(queue); + } if (!IS_ERR_OR_NULL(post_deps)) { for (i = 0; i < args->nr_out_syncobjs; ++i) { kfree(post_deps[i].chain); diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c index 418e1e06cdde..5cc8d358cc97 100644 --- a/drivers/gpu/drm/msm/msm_iommu.c +++ b/drivers/gpu/drm/msm/msm_iommu.c @@ -234,7 +234,12 @@ struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent) /* Get the pagetable configuration from the domain */ if (adreno_smmu->cookie) ttbr1_cfg = adreno_smmu->get_ttbr1_cfg(adreno_smmu->cookie); - if (!ttbr1_cfg) + + /* + * If you hit this WARN_ONCE() you are probably missing an entry in + * qcom_smmu_impl_of_match[] in arm-smmu-qcom.c + */ + if (WARN_ONCE(!ttbr1_cfg, "No per-process page tables")) return ERR_PTR(-ENODEV); pagetable = kzalloc(sizeof(*pagetable), GFP_KERNEL); @@ -410,7 +415,7 @@ struct msm_mmu *msm_iommu_gpu_new(struct device *dev, struct msm_gpu *gpu, unsig struct msm_mmu *mmu; mmu = msm_iommu_new(dev, quirks); - if (IS_ERR(mmu)) + if (IS_ERR_OR_NULL(mmu)) return mmu; iommu = to_msm_iommu(mmu); diff --git a/drivers/gpu/drm/pl111/pl111_display.c b/drivers/gpu/drm/pl111/pl111_display.c index 6afdf260a4e2..b9fe926a49e8 100644 --- a/drivers/gpu/drm/pl111/pl111_display.c +++ b/drivers/gpu/drm/pl111/pl111_display.c @@ -53,7 +53,7 @@ pl111_mode_valid(struct drm_simple_display_pipe *pipe, { struct drm_device *drm = pipe->crtc.dev; struct pl111_drm_dev_private *priv = drm->dev_private; - u32 cpp = priv->variant->fb_bpp / 8; + u32 cpp = DIV_ROUND_UP(priv->variant->fb_depth, 8); u64 bw; /* diff --git a/drivers/gpu/drm/pl111/pl111_drm.h b/drivers/gpu/drm/pl111/pl111_drm.h index 2a46b5bd8576..d1fe756444ee 100644 --- a/drivers/gpu/drm/pl111/pl111_drm.h +++ b/drivers/gpu/drm/pl111/pl111_drm.h @@ -114,7 +114,7 @@ struct drm_minor; * extensions to the control register * @formats: array of supported pixel formats on this variant * @nformats: the length of the array of supported pixel formats - * @fb_bpp: desired bits per pixel on the default framebuffer + * @fb_depth: desired depth per pixel on the default framebuffer */ struct pl111_variant_data { const char *name; @@ -126,7 +126,7 @@ struct pl111_variant_data { bool st_bitmux_control; const u32 *formats; unsigned int nformats; - unsigned int fb_bpp; + unsigned int fb_depth; }; struct pl111_drm_dev_private { diff --git a/drivers/gpu/drm/pl111/pl111_drv.c b/drivers/gpu/drm/pl111/pl111_drv.c index 4b2a9e9753f6..43049c8028b2 100644 --- a/drivers/gpu/drm/pl111/pl111_drv.c +++ b/drivers/gpu/drm/pl111/pl111_drv.c @@ -308,7 +308,7 @@ static int pl111_amba_probe(struct amba_device *amba_dev, if (ret < 0) goto dev_put; - drm_fbdev_dma_setup(drm, priv->variant->fb_bpp); + drm_fbdev_dma_setup(drm, priv->variant->fb_depth); return 0; @@ -351,7 +351,7 @@ static const struct pl111_variant_data pl110_variant = { .is_pl110 = true, .formats = pl110_pixel_formats, .nformats = ARRAY_SIZE(pl110_pixel_formats), - .fb_bpp = 16, + .fb_depth = 16, }; /* RealView, Versatile Express etc use this modern variant */ @@ -376,7 +376,7 @@ static const struct pl111_variant_data pl111_variant = { .name = "PL111", .formats = pl111_pixel_formats, .nformats = ARRAY_SIZE(pl111_pixel_formats), - .fb_bpp = 32, + .fb_depth = 32, }; static const u32 pl110_nomadik_pixel_formats[] = { @@ -405,7 +405,7 @@ static const struct pl111_variant_data pl110_nomadik_variant = { .is_lcdc = true, .st_bitmux_control = true, .broken_vblank = true, - .fb_bpp = 16, + .fb_depth = 16, }; static const struct amba_id pl111_id_table[] = { diff --git a/drivers/gpu/drm/pl111/pl111_versatile.c b/drivers/gpu/drm/pl111/pl111_versatile.c index 1b436b75fd39..00c3ebd32359 100644 --- a/drivers/gpu/drm/pl111/pl111_versatile.c +++ b/drivers/gpu/drm/pl111/pl111_versatile.c @@ -316,7 +316,7 @@ static const struct pl111_variant_data pl110_integrator = { .broken_vblank = true, .formats = pl110_integrator_pixel_formats, .nformats = ARRAY_SIZE(pl110_integrator_pixel_formats), - .fb_bpp = 16, + .fb_depth = 16, }; /* @@ -330,7 +330,7 @@ static const struct pl111_variant_data pl110_impd1 = { .broken_vblank = true, .formats = pl110_integrator_pixel_formats, .nformats = ARRAY_SIZE(pl110_integrator_pixel_formats), - .fb_bpp = 16, + .fb_depth = 15, }; /* @@ -343,7 +343,7 @@ static const struct pl111_variant_data pl110_versatile = { .external_bgr = true, .formats = pl110_versatile_pixel_formats, .nformats = ARRAY_SIZE(pl110_versatile_pixel_formats), - .fb_bpp = 16, + .fb_depth = 16, }; /* @@ -355,7 +355,7 @@ static const struct pl111_variant_data pl111_realview = { .name = "PL111 RealView", .formats = pl111_realview_pixel_formats, .nformats = ARRAY_SIZE(pl111_realview_pixel_formats), - .fb_bpp = 16, + .fb_depth = 16, }; /* @@ -367,7 +367,7 @@ static const struct pl111_variant_data pl111_vexpress = { .name = "PL111 Versatile Express", .formats = pl111_realview_pixel_formats, .nformats = ARRAY_SIZE(pl111_realview_pixel_formats), - .fb_bpp = 16, + .fb_depth = 16, .broken_clockdivider = true, }; diff --git a/drivers/gpu/drm/radeon/radeon_irq_kms.c b/drivers/gpu/drm/radeon/radeon_irq_kms.c index 3377fbc71f65..c4dda908666c 100644 --- a/drivers/gpu/drm/radeon/radeon_irq_kms.c +++ b/drivers/gpu/drm/radeon/radeon_irq_kms.c @@ -99,6 +99,16 @@ static void radeon_hotplug_work_func(struct work_struct *work) static void radeon_dp_work_func(struct work_struct *work) { + struct radeon_device *rdev = container_of(work, struct radeon_device, + dp_work); + struct drm_device *dev = rdev->ddev; + struct drm_mode_config *mode_config = &dev->mode_config; + struct drm_connector *connector; + + mutex_lock(&mode_config->mutex); + list_for_each_entry(connector, &mode_config->connector_list, head) + radeon_connector_hotplug(connector); + mutex_unlock(&mode_config->mutex); } /** diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c index 8c183639603e..aea5a90ff98b 100644 --- a/drivers/gpu/drm/scheduler/sched_main.c +++ b/drivers/gpu/drm/scheduler/sched_main.c @@ -1141,9 +1141,6 @@ void drm_sched_fini(struct drm_gpu_scheduler *sched) for (i = DRM_SCHED_PRIORITY_COUNT - 1; i >= DRM_SCHED_PRIORITY_MIN; i--) { struct drm_sched_rq *rq = &sched->sched_rq[i]; - if (!rq) - continue; - spin_lock(&rq->lock); list_for_each_entry(s_entity, &rq->entities, list) /* diff --git a/drivers/hid/hid-google-hammer.c b/drivers/hid/hid-google-hammer.c index 7ae5f27df54d..c6bdb9c4ef3e 100644 --- a/drivers/hid/hid-google-hammer.c +++ b/drivers/hid/hid-google-hammer.c @@ -587,6 +587,8 @@ static const struct hid_device_id hammer_devices[] = { { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_HAMMER) }, { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, + USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_JEWEL) }, + { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_MAGNEMITE) }, { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_MASTERBALL) }, diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index d79e946acdcb..5d29abac2300 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -529,6 +529,7 @@ #define USB_DEVICE_ID_GOOGLE_MOONBALL 0x5044 #define USB_DEVICE_ID_GOOGLE_DON 0x5050 #define USB_DEVICE_ID_GOOGLE_EEL 0x5057 +#define USB_DEVICE_ID_GOOGLE_JEWEL 0x5061 #define USB_VENDOR_ID_GOTOP 0x08f2 #define USB_DEVICE_ID_SUPER_Q2 0x007f diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c index 0fcfd85fea0f..2246044b1639 100644 --- a/drivers/hid/hid-logitech-hidpp.c +++ b/drivers/hid/hid-logitech-hidpp.c @@ -314,6 +314,7 @@ static int hidpp_send_message_sync(struct hidpp_device *hidpp, dbg_hid("%s:timeout waiting for response\n", __func__); memset(response, 0, sizeof(struct hidpp_report)); ret = -ETIMEDOUT; + goto exit; } if (response->report_id == REPORT_ID_HIDPP_SHORT && diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c index 8214896adada..76e5353aca0c 100644 --- a/drivers/hid/wacom_sys.c +++ b/drivers/hid/wacom_sys.c @@ -2224,7 +2224,9 @@ static void wacom_update_name(struct wacom *wacom, const char *suffix) } else if (strstr(product_name, "Wacom") || strstr(product_name, "wacom") || strstr(product_name, "WACOM")) { - strscpy(name, product_name, sizeof(name)); + if (strscpy(name, product_name, sizeof(name)) < 0) { + hid_warn(wacom->hdev, "String overflow while assembling device name"); + } } else { snprintf(name, sizeof(name), "Wacom %s", product_name); } @@ -2242,7 +2244,9 @@ static void wacom_update_name(struct wacom *wacom, const char *suffix) if (name[strlen(name)-1] == ' ') name[strlen(name)-1] = '\0'; } else { - strscpy(name, features->name, sizeof(name)); + if (strscpy(name, features->name, sizeof(name)) < 0) { + hid_warn(wacom->hdev, "String overflow while assembling device name"); + } } snprintf(wacom_wac->name, sizeof(wacom_wac->name), "%s%s", @@ -2410,8 +2414,13 @@ static int wacom_parse_and_register(struct wacom *wacom, bool wireless) goto fail_quirks; } - if (features->device_type & WACOM_DEVICETYPE_WL_MONITOR) + if (features->device_type & WACOM_DEVICETYPE_WL_MONITOR) { error = hid_hw_open(hdev); + if (error) { + hid_err(hdev, "hw open failed\n"); + goto fail_quirks; + } + } wacom_set_shared_values(wacom_wac); devres_close_group(&hdev->dev, wacom); @@ -2500,8 +2509,10 @@ static void wacom_wireless_work(struct work_struct *work) goto fail; } - strscpy(wacom_wac->name, wacom_wac1->name, - sizeof(wacom_wac->name)); + if (strscpy(wacom_wac->name, wacom_wac1->name, + sizeof(wacom_wac->name)) < 0) { + hid_warn(wacom->hdev, "String overflow while assembling device name"); + } } return; diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index dc0f7d9a992c..2ccf83837134 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -831,7 +831,7 @@ static int wacom_intuos_inout(struct wacom_wac *wacom) /* Enter report */ if ((data[1] & 0xfc) == 0xc0) { /* serial number of the tool */ - wacom->serial[idx] = ((data[3] & 0x0f) << 28) + + wacom->serial[idx] = ((__u64)(data[3] & 0x0f) << 28) + (data[4] << 20) + (data[5] << 12) + (data[6] << 4) + (data[7] >> 4); diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.c b/drivers/hwtracing/coresight/coresight-etm-perf.c index 711f451b6946..89e8ed214ea4 100644 --- a/drivers/hwtracing/coresight/coresight-etm-perf.c +++ b/drivers/hwtracing/coresight/coresight-etm-perf.c @@ -402,6 +402,7 @@ static void *etm_setup_aux(struct perf_event *event, void **pages, trace_id = coresight_trace_id_get_cpu_id(cpu); if (!IS_VALID_CS_TRACE_ID(trace_id)) { cpumask_clear_cpu(cpu, mask); + coresight_release_path(path); continue; } diff --git a/drivers/hwtracing/coresight/coresight-tmc-etr.c b/drivers/hwtracing/coresight/coresight-tmc-etr.c index 918d461fcf4a..eaa296ced167 100644 --- a/drivers/hwtracing/coresight/coresight-tmc-etr.c +++ b/drivers/hwtracing/coresight/coresight-tmc-etr.c @@ -942,7 +942,7 @@ tmc_etr_buf_insert_barrier_packet(struct etr_buf *etr_buf, u64 offset) len = tmc_etr_buf_get_data(etr_buf, offset, CORESIGHT_BARRIER_PKT_SIZE, &bufp); - if (WARN_ON(len < CORESIGHT_BARRIER_PKT_SIZE)) + if (WARN_ON(len < 0 || len < CORESIGHT_BARRIER_PKT_SIZE)) return -EINVAL; coresight_insert_barrier_packet(bufp); return offset + CORESIGHT_BARRIER_PKT_SIZE; diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c index e86afecfbe46..b1c36412025f 100644 --- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c +++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c @@ -3341,9 +3341,7 @@ static int bnxt_re_process_raw_qp_pkt_rx(struct bnxt_re_qp *gsi_qp, udwr.remote_qkey = gsi_sqp->qplib_qp.qkey; /* post data received in the send queue */ - rc = bnxt_re_post_send_shadow_qp(rdev, gsi_sqp, swr); - - return 0; + return bnxt_re_post_send_shadow_qp(rdev, gsi_sqp, swr); } static void bnxt_re_process_res_rawqp1_wc(struct ib_wc *wc, diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c index b9e2f89337e8..e34eccd178d0 100644 --- a/drivers/infiniband/hw/bnxt_re/main.c +++ b/drivers/infiniband/hw/bnxt_re/main.c @@ -1336,6 +1336,10 @@ static void bnxt_re_setup_cc(struct bnxt_re_dev *rdev, bool enable) { struct bnxt_qplib_cc_param cc_param = {}; + /* Do not enable congestion control on VFs */ + if (rdev->is_virtfn) + return; + /* Currently enabling only for GenP5 adapters */ if (!bnxt_qplib_is_chip_gen_p5(rdev->chip_ctx)) return; diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c index f139d4cd1712..8974f6235cfa 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c @@ -2056,6 +2056,12 @@ int bnxt_qplib_create_cq(struct bnxt_qplib_res *res, struct bnxt_qplib_cq *cq) u32 pg_sz_lvl; int rc; + if (!cq->dpi) { + dev_err(&rcfw->pdev->dev, + "FP: CREATE_CQ failed due to NULL DPI\n"); + return -EINVAL; + } + hwq_attr.res = res; hwq_attr.depth = cq->max_wqe; hwq_attr.stride = sizeof(struct cq_base); @@ -2069,11 +2075,6 @@ int bnxt_qplib_create_cq(struct bnxt_qplib_res *res, struct bnxt_qplib_cq *cq) CMDQ_BASE_OPCODE_CREATE_CQ, sizeof(req)); - if (!cq->dpi) { - dev_err(&rcfw->pdev->dev, - "FP: CREATE_CQ failed due to NULL DPI\n"); - return -EINVAL; - } req.dpi = cpu_to_le32(cq->dpi->dpi); req.cq_handle = cpu_to_le64(cq->cq_handle); req.cq_size = cpu_to_le32(cq->hwq.max_elements); diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.c b/drivers/infiniband/hw/bnxt_re/qplib_res.c index 126d4f26f75a..81b0c5e879f9 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_res.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_res.c @@ -215,17 +215,9 @@ int bnxt_qplib_alloc_init_hwq(struct bnxt_qplib_hwq *hwq, return -EINVAL; hwq_attr->sginfo->npages = npages; } else { - unsigned long sginfo_num_pages = ib_umem_num_dma_blocks( - hwq_attr->sginfo->umem, hwq_attr->sginfo->pgsize); - + npages = ib_umem_num_dma_blocks(hwq_attr->sginfo->umem, + hwq_attr->sginfo->pgsize); hwq->is_user = true; - npages = sginfo_num_pages; - npages = (npages * PAGE_SIZE) / - BIT_ULL(hwq_attr->sginfo->pgshft); - if ((sginfo_num_pages * PAGE_SIZE) % - BIT_ULL(hwq_attr->sginfo->pgshft)) - if (!npages) - npages++; } if (npages == MAX_PBL_LVL_0_PGS && !hwq_attr->sginfo->nopte) { diff --git a/drivers/infiniband/hw/bnxt_re/qplib_sp.c b/drivers/infiniband/hw/bnxt_re/qplib_sp.c index 1714a1e23113..b967a17a44be 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_sp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_sp.c @@ -617,16 +617,15 @@ int bnxt_qplib_reg_mr(struct bnxt_qplib_res *res, struct bnxt_qplib_mrw *mr, /* Free the hwq if it already exist, must be a rereg */ if (mr->hwq.max_elements) bnxt_qplib_free_hwq(res, &mr->hwq); - /* Use system PAGE_SIZE */ hwq_attr.res = res; hwq_attr.depth = pages; - hwq_attr.stride = buf_pg_size; + hwq_attr.stride = sizeof(dma_addr_t); hwq_attr.type = HWQ_TYPE_MR; hwq_attr.sginfo = &sginfo; hwq_attr.sginfo->umem = umem; hwq_attr.sginfo->npages = pages; - hwq_attr.sginfo->pgsize = PAGE_SIZE; - hwq_attr.sginfo->pgshft = PAGE_SHIFT; + hwq_attr.sginfo->pgsize = buf_pg_size; + hwq_attr.sginfo->pgshft = ilog2(buf_pg_size); rc = bnxt_qplib_alloc_init_hwq(&mr->hwq, &hwq_attr); if (rc) { dev_err(&res->pdev->dev, diff --git a/drivers/infiniband/hw/efa/efa_verbs.c b/drivers/infiniband/hw/efa/efa_verbs.c index 8eca6c14d0cf..2a195c4b0f17 100644 --- a/drivers/infiniband/hw/efa/efa_verbs.c +++ b/drivers/infiniband/hw/efa/efa_verbs.c @@ -1403,7 +1403,7 @@ static int pbl_continuous_initialize(struct efa_dev *dev, */ static int pbl_indirect_initialize(struct efa_dev *dev, struct pbl_context *pbl) { - u32 size_in_pages = DIV_ROUND_UP(pbl->pbl_buf_size_in_bytes, PAGE_SIZE); + u32 size_in_pages = DIV_ROUND_UP(pbl->pbl_buf_size_in_bytes, EFA_CHUNK_PAYLOAD_SIZE); struct scatterlist *sgl; int sg_dma_cnt, err; diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index 84f1167de1d9..d4c6b9bc0a4e 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -4583,11 +4583,9 @@ static int modify_qp_init_to_rtr(struct ib_qp *ibqp, mtu = ib_mtu_enum_to_int(ib_mtu); if (WARN_ON(mtu <= 0)) return -EINVAL; -#define MAX_LP_MSG_LEN 16384 - /* MTU * (2 ^ LP_PKTN_INI) shouldn't be bigger than 16KB */ - lp_pktn_ini = ilog2(MAX_LP_MSG_LEN / mtu); - if (WARN_ON(lp_pktn_ini >= 0xF)) - return -EINVAL; +#define MIN_LP_MSG_LEN 1024 + /* mtu * (2 ^ lp_pktn_ini) should be in the range of 1024 to mtu */ + lp_pktn_ini = ilog2(max(mtu, MIN_LP_MSG_LEN) / mtu); if (attr_mask & IB_QP_PATH_MTU) { hr_reg_write(context, QPC_MTU, ib_mtu); @@ -5012,7 +5010,6 @@ static int hns_roce_v2_set_abs_fields(struct ib_qp *ibqp, static bool check_qp_timeout_cfg_range(struct hns_roce_dev *hr_dev, u8 *timeout) { #define QP_ACK_TIMEOUT_MAX_HIP08 20 -#define QP_ACK_TIMEOUT_OFFSET 10 #define QP_ACK_TIMEOUT_MAX 31 if (hr_dev->pci_dev->revision == PCI_REVISION_ID_HIP08) { @@ -5021,7 +5018,7 @@ static bool check_qp_timeout_cfg_range(struct hns_roce_dev *hr_dev, u8 *timeout) "local ACK timeout shall be 0 to 20.\n"); return false; } - *timeout += QP_ACK_TIMEOUT_OFFSET; + *timeout += HNS_ROCE_V2_QP_ACK_TIMEOUT_OFS_HIP08; } else if (hr_dev->pci_dev->revision > PCI_REVISION_ID_HIP08) { if (*timeout > QP_ACK_TIMEOUT_MAX) { ibdev_warn(&hr_dev->ib_dev, @@ -5307,6 +5304,18 @@ out: return ret; } +static u8 get_qp_timeout_attr(struct hns_roce_dev *hr_dev, + struct hns_roce_v2_qp_context *context) +{ + u8 timeout; + + timeout = (u8)hr_reg_read(context, QPC_AT); + if (hr_dev->pci_dev->revision == PCI_REVISION_ID_HIP08) + timeout -= HNS_ROCE_V2_QP_ACK_TIMEOUT_OFS_HIP08; + + return timeout; +} + static int hns_roce_v2_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr, int qp_attr_mask, struct ib_qp_init_attr *qp_init_attr) @@ -5384,7 +5393,7 @@ static int hns_roce_v2_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr, qp_attr->max_dest_rd_atomic = 1 << hr_reg_read(&context, QPC_RR_MAX); qp_attr->min_rnr_timer = (u8)hr_reg_read(&context, QPC_MIN_RNR_TIME); - qp_attr->timeout = (u8)hr_reg_read(&context, QPC_AT); + qp_attr->timeout = get_qp_timeout_attr(hr_dev, &context); qp_attr->retry_cnt = hr_reg_read(&context, QPC_RETRY_NUM_INIT); qp_attr->rnr_retry = hr_reg_read(&context, QPC_RNR_NUM_INIT); diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h index 1b44d2434ab4..7033eae2407c 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h @@ -44,6 +44,8 @@ #define HNS_ROCE_V2_MAX_XRCD_NUM 0x1000000 #define HNS_ROCE_V2_RSV_XRCD_NUM 0 +#define HNS_ROCE_V2_QP_ACK_TIMEOUT_OFS_HIP08 10 + #define HNS_ROCE_V3_SCCC_SZ 64 #define HNS_ROCE_V3_GMV_ENTRY_SZ 32 diff --git a/drivers/infiniband/hw/hns/hns_roce_mr.c b/drivers/infiniband/hw/hns/hns_roce_mr.c index 37a5cf62f88b..14376490ac22 100644 --- a/drivers/infiniband/hw/hns/hns_roce_mr.c +++ b/drivers/infiniband/hw/hns/hns_roce_mr.c @@ -33,6 +33,7 @@ #include <linux/vmalloc.h> #include <rdma/ib_umem.h> +#include <linux/math.h> #include "hns_roce_device.h" #include "hns_roce_cmd.h" #include "hns_roce_hem.h" @@ -909,6 +910,44 @@ static int mtr_init_buf_cfg(struct hns_roce_dev *hr_dev, return page_cnt; } +static u64 cal_pages_per_l1ba(unsigned int ba_per_bt, unsigned int hopnum) +{ + return int_pow(ba_per_bt, hopnum - 1); +} + +static unsigned int cal_best_bt_pg_sz(struct hns_roce_dev *hr_dev, + struct hns_roce_mtr *mtr, + unsigned int pg_shift) +{ + unsigned long cap = hr_dev->caps.page_size_cap; + struct hns_roce_buf_region *re; + unsigned int pgs_per_l1ba; + unsigned int ba_per_bt; + unsigned int ba_num; + int i; + + for_each_set_bit_from(pg_shift, &cap, sizeof(cap) * BITS_PER_BYTE) { + if (!(BIT(pg_shift) & cap)) + continue; + + ba_per_bt = BIT(pg_shift) / BA_BYTE_LEN; + ba_num = 0; + for (i = 0; i < mtr->hem_cfg.region_count; i++) { + re = &mtr->hem_cfg.region[i]; + if (re->hopnum == 0) + continue; + + pgs_per_l1ba = cal_pages_per_l1ba(ba_per_bt, re->hopnum); + ba_num += DIV_ROUND_UP(re->count, pgs_per_l1ba); + } + + if (ba_num <= ba_per_bt) + return pg_shift; + } + + return 0; +} + static int mtr_alloc_mtt(struct hns_roce_dev *hr_dev, struct hns_roce_mtr *mtr, unsigned int ba_page_shift) { @@ -917,6 +956,10 @@ static int mtr_alloc_mtt(struct hns_roce_dev *hr_dev, struct hns_roce_mtr *mtr, hns_roce_hem_list_init(&mtr->hem_list); if (!cfg->is_direct) { + ba_page_shift = cal_best_bt_pg_sz(hr_dev, mtr, ba_page_shift); + if (!ba_page_shift) + return -ERANGE; + ret = hns_roce_hem_list_request(hr_dev, &mtr->hem_list, cfg->region, cfg->region_count, ba_page_shift); diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c index ab5cdf782785..eaa12c124598 100644 --- a/drivers/infiniband/hw/irdma/verbs.c +++ b/drivers/infiniband/hw/irdma/verbs.c @@ -522,11 +522,6 @@ static int irdma_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata) if (!iwqp->user_mode) cancel_delayed_work_sync(&iwqp->dwork_flush); - irdma_qp_rem_ref(&iwqp->ibqp); - wait_for_completion(&iwqp->free_qp); - irdma_free_lsmm_rsrc(iwqp); - irdma_cqp_qp_destroy_cmd(&iwdev->rf->sc_dev, &iwqp->sc_qp); - if (!iwqp->user_mode) { if (iwqp->iwscq) { irdma_clean_cqes(iwqp, iwqp->iwscq); @@ -534,6 +529,12 @@ static int irdma_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata) irdma_clean_cqes(iwqp, iwqp->iwrcq); } } + + irdma_qp_rem_ref(&iwqp->ibqp); + wait_for_completion(&iwqp->free_qp); + irdma_free_lsmm_rsrc(iwqp); + irdma_cqp_qp_destroy_cmd(&iwdev->rf->sc_dev, &iwqp->sc_qp); + irdma_remove_push_mmap_entries(iwqp); irdma_free_qp_rsrc(iwqp); @@ -3291,6 +3292,7 @@ static int irdma_post_send(struct ib_qp *ibqp, break; case IB_WR_LOCAL_INV: info.op_type = IRDMA_OP_TYPE_INV_STAG; + info.local_fence = info.read_fence; info.op.inv_local_stag.target_stag = ib_wr->ex.invalidate_rkey; err = irdma_uk_stag_local_invalidate(ukqp, &info, true); break; diff --git a/drivers/infiniband/sw/rxe/rxe_comp.c b/drivers/infiniband/sw/rxe/rxe_comp.c index db18ace74d2b..f46c5a5fd0ae 100644 --- a/drivers/infiniband/sw/rxe/rxe_comp.c +++ b/drivers/infiniband/sw/rxe/rxe_comp.c @@ -115,15 +115,16 @@ static enum ib_wc_opcode wr_to_wc_opcode(enum ib_wr_opcode opcode) void retransmit_timer(struct timer_list *t) { struct rxe_qp *qp = from_timer(qp, t, retrans_timer); + unsigned long flags; rxe_dbg_qp(qp, "retransmit timer fired\n"); - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); if (qp->valid) { qp->comp.timeout = 1; rxe_sched_task(&qp->comp.task); } - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); } void rxe_comp_queue_pkt(struct rxe_qp *qp, struct sk_buff *skb) @@ -481,11 +482,13 @@ static void do_complete(struct rxe_qp *qp, struct rxe_send_wqe *wqe) static void comp_check_sq_drain_done(struct rxe_qp *qp) { - spin_lock_bh(&qp->state_lock); + unsigned long flags; + + spin_lock_irqsave(&qp->state_lock, flags); if (unlikely(qp_state(qp) == IB_QPS_SQD)) { if (qp->attr.sq_draining && qp->comp.psn == qp->req.psn) { qp->attr.sq_draining = 0; - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); if (qp->ibqp.event_handler) { struct ib_event ev; @@ -499,7 +502,7 @@ static void comp_check_sq_drain_done(struct rxe_qp *qp) return; } } - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); } static inline enum comp_state complete_ack(struct rxe_qp *qp, @@ -625,13 +628,15 @@ static void free_pkt(struct rxe_pkt_info *pkt) */ static void reset_retry_timer(struct rxe_qp *qp) { + unsigned long flags; + if (qp_type(qp) == IB_QPT_RC && qp->qp_timeout_jiffies) { - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); if (qp_state(qp) >= IB_QPS_RTS && psn_compare(qp->req.psn, qp->comp.psn) > 0) mod_timer(&qp->retrans_timer, jiffies + qp->qp_timeout_jiffies); - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); } } @@ -643,18 +648,19 @@ int rxe_completer(struct rxe_qp *qp) struct rxe_pkt_info *pkt = NULL; enum comp_state state; int ret; + unsigned long flags; - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); if (!qp->valid || qp_state(qp) == IB_QPS_ERR || qp_state(qp) == IB_QPS_RESET) { bool notify = qp->valid && (qp_state(qp) == IB_QPS_ERR); drain_resp_pkts(qp); flush_send_queue(qp, notify); - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); goto exit; } - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); if (qp->comp.timeout) { qp->comp.timeout_retry = 1; diff --git a/drivers/infiniband/sw/rxe/rxe_net.c b/drivers/infiniband/sw/rxe/rxe_net.c index 2bc7361152ea..a38fab19bed1 100644 --- a/drivers/infiniband/sw/rxe/rxe_net.c +++ b/drivers/infiniband/sw/rxe/rxe_net.c @@ -412,15 +412,16 @@ int rxe_xmit_packet(struct rxe_qp *qp, struct rxe_pkt_info *pkt, int err; int is_request = pkt->mask & RXE_REQ_MASK; struct rxe_dev *rxe = to_rdev(qp->ibqp.device); + unsigned long flags; - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); if ((is_request && (qp_state(qp) < IB_QPS_RTS)) || (!is_request && (qp_state(qp) < IB_QPS_RTR))) { - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); rxe_dbg_qp(qp, "Packet dropped. QP is not in ready state\n"); goto drop; } - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); rxe_icrc_generate(skb, pkt); diff --git a/drivers/infiniband/sw/rxe/rxe_qp.c b/drivers/infiniband/sw/rxe/rxe_qp.c index c5451a4488ca..61a2eb77d999 100644 --- a/drivers/infiniband/sw/rxe/rxe_qp.c +++ b/drivers/infiniband/sw/rxe/rxe_qp.c @@ -300,6 +300,7 @@ int rxe_qp_from_init(struct rxe_dev *rxe, struct rxe_qp *qp, struct rxe_pd *pd, struct rxe_cq *rcq = to_rcq(init->recv_cq); struct rxe_cq *scq = to_rcq(init->send_cq); struct rxe_srq *srq = init->srq ? to_rsrq(init->srq) : NULL; + unsigned long flags; rxe_get(pd); rxe_get(rcq); @@ -325,10 +326,10 @@ int rxe_qp_from_init(struct rxe_dev *rxe, struct rxe_qp *qp, struct rxe_pd *pd, if (err) goto err2; - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); qp->attr.qp_state = IB_QPS_RESET; qp->valid = 1; - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); return 0; @@ -492,24 +493,28 @@ static void rxe_qp_reset(struct rxe_qp *qp) /* move the qp to the error state */ void rxe_qp_error(struct rxe_qp *qp) { - spin_lock_bh(&qp->state_lock); + unsigned long flags; + + spin_lock_irqsave(&qp->state_lock, flags); qp->attr.qp_state = IB_QPS_ERR; /* drain work and packet queues */ rxe_sched_task(&qp->resp.task); rxe_sched_task(&qp->comp.task); rxe_sched_task(&qp->req.task); - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); } static void rxe_qp_sqd(struct rxe_qp *qp, struct ib_qp_attr *attr, int mask) { - spin_lock_bh(&qp->state_lock); + unsigned long flags; + + spin_lock_irqsave(&qp->state_lock, flags); qp->attr.sq_draining = 1; rxe_sched_task(&qp->comp.task); rxe_sched_task(&qp->req.task); - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); } /* caller should hold qp->state_lock */ @@ -555,14 +560,16 @@ int rxe_qp_from_attr(struct rxe_qp *qp, struct ib_qp_attr *attr, int mask, qp->attr.cur_qp_state = attr->qp_state; if (mask & IB_QP_STATE) { - spin_lock_bh(&qp->state_lock); + unsigned long flags; + + spin_lock_irqsave(&qp->state_lock, flags); err = __qp_chk_state(qp, attr, mask); if (!err) { qp->attr.qp_state = attr->qp_state; rxe_dbg_qp(qp, "state -> %s\n", qps2str[attr->qp_state]); } - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); if (err) return err; @@ -688,6 +695,8 @@ int rxe_qp_from_attr(struct rxe_qp *qp, struct ib_qp_attr *attr, int mask, /* called by the query qp verb */ int rxe_qp_to_attr(struct rxe_qp *qp, struct ib_qp_attr *attr, int mask) { + unsigned long flags; + *attr = qp->attr; attr->rq_psn = qp->resp.psn; @@ -708,12 +717,13 @@ int rxe_qp_to_attr(struct rxe_qp *qp, struct ib_qp_attr *attr, int mask) /* Applications that get this state typically spin on it. * Yield the processor */ - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); if (qp->attr.sq_draining) { - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); cond_resched(); + } else { + spin_unlock_irqrestore(&qp->state_lock, flags); } - spin_unlock_bh(&qp->state_lock); return 0; } @@ -736,10 +746,11 @@ int rxe_qp_chk_destroy(struct rxe_qp *qp) static void rxe_qp_do_cleanup(struct work_struct *work) { struct rxe_qp *qp = container_of(work, typeof(*qp), cleanup_work.work); + unsigned long flags; - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); qp->valid = 0; - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); qp->qp_timeout_jiffies = 0; if (qp_type(qp) == IB_QPT_RC) { diff --git a/drivers/infiniband/sw/rxe/rxe_recv.c b/drivers/infiniband/sw/rxe/rxe_recv.c index 2f953cc74256..5861e4244049 100644 --- a/drivers/infiniband/sw/rxe/rxe_recv.c +++ b/drivers/infiniband/sw/rxe/rxe_recv.c @@ -14,6 +14,7 @@ static int check_type_state(struct rxe_dev *rxe, struct rxe_pkt_info *pkt, struct rxe_qp *qp) { unsigned int pkt_type; + unsigned long flags; if (unlikely(!qp->valid)) return -EINVAL; @@ -38,19 +39,19 @@ static int check_type_state(struct rxe_dev *rxe, struct rxe_pkt_info *pkt, return -EINVAL; } - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); if (pkt->mask & RXE_REQ_MASK) { if (unlikely(qp_state(qp) < IB_QPS_RTR)) { - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); return -EINVAL; } } else { if (unlikely(qp_state(qp) < IB_QPS_RTS)) { - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); return -EINVAL; } } - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); return 0; } diff --git a/drivers/infiniband/sw/rxe/rxe_req.c b/drivers/infiniband/sw/rxe/rxe_req.c index 65134a9aefe7..5fe7cbae3031 100644 --- a/drivers/infiniband/sw/rxe/rxe_req.c +++ b/drivers/infiniband/sw/rxe/rxe_req.c @@ -99,17 +99,18 @@ static void req_retry(struct rxe_qp *qp) void rnr_nak_timer(struct timer_list *t) { struct rxe_qp *qp = from_timer(qp, t, rnr_nak_timer); + unsigned long flags; rxe_dbg_qp(qp, "nak timer fired\n"); - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); if (qp->valid) { /* request a send queue retry */ qp->req.need_retry = 1; qp->req.wait_for_rnr_timer = 0; rxe_sched_task(&qp->req.task); } - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); } static void req_check_sq_drain_done(struct rxe_qp *qp) @@ -118,8 +119,9 @@ static void req_check_sq_drain_done(struct rxe_qp *qp) unsigned int index; unsigned int cons; struct rxe_send_wqe *wqe; + unsigned long flags; - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); if (qp_state(qp) == IB_QPS_SQD) { q = qp->sq.queue; index = qp->req.wqe_index; @@ -140,7 +142,7 @@ static void req_check_sq_drain_done(struct rxe_qp *qp) break; qp->attr.sq_draining = 0; - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); if (qp->ibqp.event_handler) { struct ib_event ev; @@ -154,7 +156,7 @@ static void req_check_sq_drain_done(struct rxe_qp *qp) return; } while (0); } - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); } static struct rxe_send_wqe *__req_next_wqe(struct rxe_qp *qp) @@ -173,6 +175,7 @@ static struct rxe_send_wqe *__req_next_wqe(struct rxe_qp *qp) static struct rxe_send_wqe *req_next_wqe(struct rxe_qp *qp) { struct rxe_send_wqe *wqe; + unsigned long flags; req_check_sq_drain_done(qp); @@ -180,13 +183,13 @@ static struct rxe_send_wqe *req_next_wqe(struct rxe_qp *qp) if (wqe == NULL) return NULL; - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); if (unlikely((qp_state(qp) == IB_QPS_SQD) && (wqe->state != wqe_state_processing))) { - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); return NULL; } - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); wqe->mask = wr_opcode_mask(wqe->wr.opcode, qp); return wqe; @@ -676,16 +679,17 @@ int rxe_requester(struct rxe_qp *qp) struct rxe_queue *q = qp->sq.queue; struct rxe_ah *ah; struct rxe_av *av; + unsigned long flags; - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); if (unlikely(!qp->valid)) { - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); goto exit; } if (unlikely(qp_state(qp) == IB_QPS_ERR)) { wqe = __req_next_wqe(qp); - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); if (wqe) goto err; else @@ -700,10 +704,10 @@ int rxe_requester(struct rxe_qp *qp) qp->req.wait_psn = 0; qp->req.need_retry = 0; qp->req.wait_for_rnr_timer = 0; - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); goto exit; } - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); /* we come here if the retransmit timer has fired * or if the rnr timer has fired. If the retransmit diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c index 68f6cd188d8e..1da044f6b7d4 100644 --- a/drivers/infiniband/sw/rxe/rxe_resp.c +++ b/drivers/infiniband/sw/rxe/rxe_resp.c @@ -1047,6 +1047,7 @@ static enum resp_states do_complete(struct rxe_qp *qp, struct ib_uverbs_wc *uwc = &cqe.uibwc; struct rxe_recv_wqe *wqe = qp->resp.wqe; struct rxe_dev *rxe = to_rdev(qp->ibqp.device); + unsigned long flags; if (!wqe) goto finish; @@ -1137,12 +1138,12 @@ static enum resp_states do_complete(struct rxe_qp *qp, return RESPST_ERR_CQ_OVERFLOW; finish: - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); if (unlikely(qp_state(qp) == IB_QPS_ERR)) { - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); return RESPST_CHK_RESOURCE; } - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); if (unlikely(!pkt)) return RESPST_DONE; @@ -1468,18 +1469,19 @@ int rxe_responder(struct rxe_qp *qp) enum resp_states state; struct rxe_pkt_info *pkt = NULL; int ret; + unsigned long flags; - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); if (!qp->valid || qp_state(qp) == IB_QPS_ERR || qp_state(qp) == IB_QPS_RESET) { bool notify = qp->valid && (qp_state(qp) == IB_QPS_ERR); drain_req_pkts(qp); flush_recv_queue(qp, notify); - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); goto exit; } - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); qp->resp.aeth_syndrome = AETH_ACK_UNLIMITED; diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c index dea605b7f683..4d8f6b8051ff 100644 --- a/drivers/infiniband/sw/rxe/rxe_verbs.c +++ b/drivers/infiniband/sw/rxe/rxe_verbs.c @@ -904,10 +904,10 @@ static int rxe_post_send_kernel(struct rxe_qp *qp, if (!err) rxe_sched_task(&qp->req.task); - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); if (qp_state(qp) == IB_QPS_ERR) rxe_sched_task(&qp->comp.task); - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); return err; } @@ -917,22 +917,23 @@ static int rxe_post_send(struct ib_qp *ibqp, const struct ib_send_wr *wr, { struct rxe_qp *qp = to_rqp(ibqp); int err; + unsigned long flags; - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); /* caller has already called destroy_qp */ if (WARN_ON_ONCE(!qp->valid)) { - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); rxe_err_qp(qp, "qp has been destroyed"); return -EINVAL; } if (unlikely(qp_state(qp) < IB_QPS_RTS)) { - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); *bad_wr = wr; rxe_err_qp(qp, "qp not ready to send"); return -EINVAL; } - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); if (qp->is_user) { /* Utilize process context to do protocol processing */ @@ -1008,22 +1009,22 @@ static int rxe_post_recv(struct ib_qp *ibqp, const struct ib_recv_wr *wr, struct rxe_rq *rq = &qp->rq; unsigned long flags; - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); /* caller has already called destroy_qp */ if (WARN_ON_ONCE(!qp->valid)) { - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); rxe_err_qp(qp, "qp has been destroyed"); return -EINVAL; } /* see C10-97.2.1 */ if (unlikely((qp_state(qp) < IB_QPS_INIT))) { - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); *bad_wr = wr; rxe_dbg_qp(qp, "qp not ready to post recv"); return -EINVAL; } - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); if (unlikely(qp->srq)) { *bad_wr = wr; @@ -1044,10 +1045,10 @@ static int rxe_post_recv(struct ib_qp *ibqp, const struct ib_recv_wr *wr, spin_unlock_irqrestore(&rq->producer_lock, flags); - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); if (qp_state(qp) == IB_QPS_ERR) rxe_sched_task(&qp->resp.task); - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); return err; } diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index db98c3f86e8c..6de900776e24 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -417,22 +417,6 @@ config S390_IOMMU help Support for the IOMMU API for s390 PCI devices. -config S390_CCW_IOMMU - bool "S390 CCW IOMMU Support" - depends on S390 && CCW || COMPILE_TEST - select IOMMU_API - help - Enables bits of IOMMU API required by VFIO. The iommu_ops - is not implemented as it is not necessary for VFIO. - -config S390_AP_IOMMU - bool "S390 AP IOMMU Support" - depends on S390 && ZCRYPT || COMPILE_TEST - select IOMMU_API - help - Enables bits of IOMMU API required by VFIO. The iommu_ops - is not implemented as it is not necessary for VFIO. - config MTK_IOMMU tristate "MediaTek IOMMU Support" depends on ARCH_MEDIATEK || COMPILE_TEST diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c index ae09c627bc84..c71afda79d64 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c +++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c @@ -517,6 +517,7 @@ static const struct of_device_id __maybe_unused qcom_smmu_impl_of_match[] = { { .compatible = "qcom,qcm2290-smmu-500", .data = &qcom_smmu_500_impl0_data }, { .compatible = "qcom,qdu1000-smmu-500", .data = &qcom_smmu_500_impl0_data }, { .compatible = "qcom,sc7180-smmu-500", .data = &qcom_smmu_500_impl0_data }, + { .compatible = "qcom,sc7180-smmu-v2", .data = &qcom_smmu_v2_data }, { .compatible = "qcom,sc7280-smmu-500", .data = &qcom_smmu_500_impl0_data }, { .compatible = "qcom,sc8180x-smmu-500", .data = &qcom_smmu_500_impl0_data }, { .compatible = "qcom,sc8280xp-smmu-500", .data = &qcom_smmu_500_impl0_data }, @@ -561,5 +562,14 @@ struct arm_smmu_device *qcom_smmu_impl_init(struct arm_smmu_device *smmu) if (match) return qcom_smmu_create(smmu, match->data); + /* + * If you hit this WARN_ON() you are missing an entry in the + * qcom_smmu_impl_of_match[] table, and GPU per-process page- + * tables will be broken. + */ + WARN(of_device_is_compatible(np, "qcom,adreno-smmu"), + "Missing qcom_smmu_impl_of_match entry for: %s", + dev_name(smmu->dev)); + return smmu; } diff --git a/drivers/irqchip/irq-gic-common.c b/drivers/irqchip/irq-gic-common.c index a610821c8ff2..de47b51cdadb 100644 --- a/drivers/irqchip/irq-gic-common.c +++ b/drivers/irqchip/irq-gic-common.c @@ -16,7 +16,11 @@ void gic_enable_of_quirks(const struct device_node *np, const struct gic_quirk *quirks, void *data) { for (; quirks->desc; quirks++) { - if (!of_device_is_compatible(np, quirks->compatible)) + if (quirks->compatible && + !of_device_is_compatible(np, quirks->compatible)) + continue; + if (quirks->property && + !of_property_read_bool(np, quirks->property)) continue; if (quirks->init(data)) pr_info("GIC: enabling workaround for %s\n", @@ -28,7 +32,7 @@ void gic_enable_quirks(u32 iidr, const struct gic_quirk *quirks, void *data) { for (; quirks->desc; quirks++) { - if (quirks->compatible) + if (quirks->compatible || quirks->property) continue; if (quirks->iidr != (quirks->mask & iidr)) continue; diff --git a/drivers/irqchip/irq-gic-common.h b/drivers/irqchip/irq-gic-common.h index 27e3d4ed4f32..3db4592cda1c 100644 --- a/drivers/irqchip/irq-gic-common.h +++ b/drivers/irqchip/irq-gic-common.h @@ -13,6 +13,7 @@ struct gic_quirk { const char *desc; const char *compatible; + const char *property; bool (*init)(void *data); u32 iidr; u32 mask; diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index 6fcee221f201..a605aa79435a 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -39,6 +39,7 @@ #define FLAGS_WORKAROUND_GICR_WAKER_MSM8996 (1ULL << 0) #define FLAGS_WORKAROUND_CAVIUM_ERRATUM_38539 (1ULL << 1) +#define FLAGS_WORKAROUND_MTK_GICR_SAVE (1ULL << 2) #define GIC_IRQ_TYPE_PARTITION (GIC_IRQ_TYPE_LPI + 1) @@ -1720,6 +1721,15 @@ static bool gic_enable_quirk_msm8996(void *data) return true; } +static bool gic_enable_quirk_mtk_gicr(void *data) +{ + struct gic_chip_data *d = data; + + d->flags |= FLAGS_WORKAROUND_MTK_GICR_SAVE; + + return true; +} + static bool gic_enable_quirk_cavium_38539(void *data) { struct gic_chip_data *d = data; @@ -1793,6 +1803,11 @@ static const struct gic_quirk gic_quirks[] = { .init = gic_enable_quirk_msm8996, }, { + .desc = "GICv3: Mediatek Chromebook GICR save problem", + .property = "mediatek,broken-save-restore-fw", + .init = gic_enable_quirk_mtk_gicr, + }, + { .desc = "GICv3: HIP06 erratum 161010803", .iidr = 0x0204043b, .mask = 0xffffffff, @@ -1834,6 +1849,11 @@ static void gic_enable_nmi_support(void) if (!gic_prio_masking_enabled()) return; + if (gic_data.flags & FLAGS_WORKAROUND_MTK_GICR_SAVE) { + pr_warn("Skipping NMI enable due to firmware issues\n"); + return; + } + ppi_nmi_refs = kcalloc(gic_data.ppi_nr, sizeof(*ppi_nmi_refs), GFP_KERNEL); if (!ppi_nmi_refs) return; diff --git a/drivers/irqchip/irq-mbigen.c b/drivers/irqchip/irq-mbigen.c index eada5e0e3eb9..5101a3fb11df 100644 --- a/drivers/irqchip/irq-mbigen.c +++ b/drivers/irqchip/irq-mbigen.c @@ -240,26 +240,27 @@ static int mbigen_of_create_domain(struct platform_device *pdev, struct irq_domain *domain; struct device_node *np; u32 num_pins; + int ret = 0; + + parent = bus_get_dev_root(&platform_bus_type); + if (!parent) + return -ENODEV; for_each_child_of_node(pdev->dev.of_node, np) { if (!of_property_read_bool(np, "interrupt-controller")) continue; - parent = bus_get_dev_root(&platform_bus_type); - if (parent) { - child = of_platform_device_create(np, NULL, parent); - put_device(parent); - if (!child) { - of_node_put(np); - return -ENOMEM; - } + child = of_platform_device_create(np, NULL, parent); + if (!child) { + ret = -ENOMEM; + break; } if (of_property_read_u32(child->dev.of_node, "num-pins", &num_pins) < 0) { dev_err(&pdev->dev, "No num-pins property\n"); - of_node_put(np); - return -EINVAL; + ret = -EINVAL; + break; } domain = platform_msi_create_device_domain(&child->dev, num_pins, @@ -267,12 +268,16 @@ static int mbigen_of_create_domain(struct platform_device *pdev, &mbigen_domain_ops, mgn_chip); if (!domain) { - of_node_put(np); - return -ENOMEM; + ret = -ENOMEM; + break; } } - return 0; + put_device(parent); + if (ret) + of_node_put(np); + + return ret; } #ifdef CONFIG_ACPI diff --git a/drivers/irqchip/irq-meson-gpio.c b/drivers/irqchip/irq-meson-gpio.c index 2aaa9aad3e87..7da18ef95211 100644 --- a/drivers/irqchip/irq-meson-gpio.c +++ b/drivers/irqchip/irq-meson-gpio.c @@ -150,7 +150,7 @@ static const struct meson_gpio_irq_params s4_params = { INIT_MESON_S4_COMMON_DATA(82) }; -static const struct of_device_id meson_irq_gpio_matches[] = { +static const struct of_device_id meson_irq_gpio_matches[] __maybe_unused = { { .compatible = "amlogic,meson8-gpio-intc", .data = &meson8_params }, { .compatible = "amlogic,meson8b-gpio-intc", .data = &meson8b_params }, { .compatible = "amlogic,meson-gxbb-gpio-intc", .data = &gxbb_params }, diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c index 046c355e120b..6d5ecc10a870 100644 --- a/drivers/irqchip/irq-mips-gic.c +++ b/drivers/irqchip/irq-mips-gic.c @@ -50,7 +50,7 @@ void __iomem *mips_gic_base; static DEFINE_PER_CPU_READ_MOSTLY(unsigned long[GIC_MAX_LONGS], pcpu_masks); -static DEFINE_SPINLOCK(gic_lock); +static DEFINE_RAW_SPINLOCK(gic_lock); static struct irq_domain *gic_irq_domain; static int gic_shared_intrs; static unsigned int gic_cpu_pin; @@ -210,7 +210,7 @@ static int gic_set_type(struct irq_data *d, unsigned int type) irq = GIC_HWIRQ_TO_SHARED(d->hwirq); - spin_lock_irqsave(&gic_lock, flags); + raw_spin_lock_irqsave(&gic_lock, flags); switch (type & IRQ_TYPE_SENSE_MASK) { case IRQ_TYPE_EDGE_FALLING: pol = GIC_POL_FALLING_EDGE; @@ -250,7 +250,7 @@ static int gic_set_type(struct irq_data *d, unsigned int type) else irq_set_chip_handler_name_locked(d, &gic_level_irq_controller, handle_level_irq, NULL); - spin_unlock_irqrestore(&gic_lock, flags); + raw_spin_unlock_irqrestore(&gic_lock, flags); return 0; } @@ -268,7 +268,7 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *cpumask, return -EINVAL; /* Assumption : cpumask refers to a single CPU */ - spin_lock_irqsave(&gic_lock, flags); + raw_spin_lock_irqsave(&gic_lock, flags); /* Re-route this IRQ */ write_gic_map_vp(irq, BIT(mips_cm_vp_id(cpu))); @@ -279,7 +279,7 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *cpumask, set_bit(irq, per_cpu_ptr(pcpu_masks, cpu)); irq_data_update_effective_affinity(d, cpumask_of(cpu)); - spin_unlock_irqrestore(&gic_lock, flags); + raw_spin_unlock_irqrestore(&gic_lock, flags); return IRQ_SET_MASK_OK; } @@ -357,12 +357,12 @@ static void gic_mask_local_irq_all_vpes(struct irq_data *d) cd = irq_data_get_irq_chip_data(d); cd->mask = false; - spin_lock_irqsave(&gic_lock, flags); + raw_spin_lock_irqsave(&gic_lock, flags); for_each_online_cpu(cpu) { write_gic_vl_other(mips_cm_vp_id(cpu)); write_gic_vo_rmask(BIT(intr)); } - spin_unlock_irqrestore(&gic_lock, flags); + raw_spin_unlock_irqrestore(&gic_lock, flags); } static void gic_unmask_local_irq_all_vpes(struct irq_data *d) @@ -375,12 +375,12 @@ static void gic_unmask_local_irq_all_vpes(struct irq_data *d) cd = irq_data_get_irq_chip_data(d); cd->mask = true; - spin_lock_irqsave(&gic_lock, flags); + raw_spin_lock_irqsave(&gic_lock, flags); for_each_online_cpu(cpu) { write_gic_vl_other(mips_cm_vp_id(cpu)); write_gic_vo_smask(BIT(intr)); } - spin_unlock_irqrestore(&gic_lock, flags); + raw_spin_unlock_irqrestore(&gic_lock, flags); } static void gic_all_vpes_irq_cpu_online(void) @@ -393,19 +393,21 @@ static void gic_all_vpes_irq_cpu_online(void) unsigned long flags; int i; - spin_lock_irqsave(&gic_lock, flags); + raw_spin_lock_irqsave(&gic_lock, flags); for (i = 0; i < ARRAY_SIZE(local_intrs); i++) { unsigned int intr = local_intrs[i]; struct gic_all_vpes_chip_data *cd; + if (!gic_local_irq_is_routable(intr)) + continue; cd = &gic_all_vpes_chip_data[intr]; write_gic_vl_map(mips_gic_vx_map_reg(intr), cd->map); if (cd->mask) write_gic_vl_smask(BIT(intr)); } - spin_unlock_irqrestore(&gic_lock, flags); + raw_spin_unlock_irqrestore(&gic_lock, flags); } static struct irq_chip gic_all_vpes_local_irq_controller = { @@ -435,11 +437,11 @@ static int gic_shared_irq_domain_map(struct irq_domain *d, unsigned int virq, data = irq_get_irq_data(virq); - spin_lock_irqsave(&gic_lock, flags); + raw_spin_lock_irqsave(&gic_lock, flags); write_gic_map_pin(intr, GIC_MAP_PIN_MAP_TO_PIN | gic_cpu_pin); write_gic_map_vp(intr, BIT(mips_cm_vp_id(cpu))); irq_data_update_effective_affinity(data, cpumask_of(cpu)); - spin_unlock_irqrestore(&gic_lock, flags); + raw_spin_unlock_irqrestore(&gic_lock, flags); return 0; } @@ -531,12 +533,12 @@ static int gic_irq_domain_map(struct irq_domain *d, unsigned int virq, if (!gic_local_irq_is_routable(intr)) return -EPERM; - spin_lock_irqsave(&gic_lock, flags); + raw_spin_lock_irqsave(&gic_lock, flags); for_each_online_cpu(cpu) { write_gic_vl_other(mips_cm_vp_id(cpu)); write_gic_vo_map(mips_gic_vx_map_reg(intr), map); } - spin_unlock_irqrestore(&gic_lock, flags); + raw_spin_unlock_irqrestore(&gic_lock, flags); return 0; } diff --git a/drivers/mailbox/mailbox-test.c b/drivers/mailbox/mailbox-test.c index c4a705c30331..fc6a12a51b40 100644 --- a/drivers/mailbox/mailbox-test.c +++ b/drivers/mailbox/mailbox-test.c @@ -98,6 +98,7 @@ static ssize_t mbox_test_message_write(struct file *filp, size_t count, loff_t *ppos) { struct mbox_test_device *tdev = filp->private_data; + char *message; void *data; int ret; @@ -113,12 +114,13 @@ static ssize_t mbox_test_message_write(struct file *filp, return -EINVAL; } - mutex_lock(&tdev->mutex); - - tdev->message = kzalloc(MBOX_MAX_MSG_LEN, GFP_KERNEL); - if (!tdev->message) + message = kzalloc(MBOX_MAX_MSG_LEN, GFP_KERNEL); + if (!message) return -ENOMEM; + mutex_lock(&tdev->mutex); + + tdev->message = message; ret = copy_from_user(tdev->message, userbuf, count); if (ret) { ret = -EFAULT; diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index 00c33edb9fb9..d920c4178389 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -264,6 +264,7 @@ static ssize_t power_ro_lock_store(struct device *dev, goto out_put; } req_to_mmc_queue_req(req)->drv_op = MMC_DRV_OP_BOOT_WP; + req_to_mmc_queue_req(req)->drv_op_result = -EIO; blk_execute_rq(req, false); ret = req_to_mmc_queue_req(req)->drv_op_result; blk_mq_free_request(req); @@ -651,6 +652,7 @@ static int mmc_blk_ioctl_cmd(struct mmc_blk_data *md, idatas[0] = idata; req_to_mmc_queue_req(req)->drv_op = rpmb ? MMC_DRV_OP_IOCTL_RPMB : MMC_DRV_OP_IOCTL; + req_to_mmc_queue_req(req)->drv_op_result = -EIO; req_to_mmc_queue_req(req)->drv_op_data = idatas; req_to_mmc_queue_req(req)->ioc_count = 1; blk_execute_rq(req, false); @@ -722,6 +724,7 @@ static int mmc_blk_ioctl_multi_cmd(struct mmc_blk_data *md, } req_to_mmc_queue_req(req)->drv_op = rpmb ? MMC_DRV_OP_IOCTL_RPMB : MMC_DRV_OP_IOCTL; + req_to_mmc_queue_req(req)->drv_op_result = -EIO; req_to_mmc_queue_req(req)->drv_op_data = idata; req_to_mmc_queue_req(req)->ioc_count = n; blk_execute_rq(req, false); @@ -2806,6 +2809,7 @@ static int mmc_dbg_card_status_get(void *data, u64 *val) if (IS_ERR(req)) return PTR_ERR(req); req_to_mmc_queue_req(req)->drv_op = MMC_DRV_OP_GET_CARD_STATUS; + req_to_mmc_queue_req(req)->drv_op_result = -EIO; blk_execute_rq(req, false); ret = req_to_mmc_queue_req(req)->drv_op_result; if (ret >= 0) { @@ -2844,6 +2848,7 @@ static int mmc_ext_csd_open(struct inode *inode, struct file *filp) goto out_free; } req_to_mmc_queue_req(req)->drv_op = MMC_DRV_OP_GET_EXT_CSD; + req_to_mmc_queue_req(req)->drv_op_result = -EIO; req_to_mmc_queue_req(req)->drv_op_data = &ext_csd; blk_execute_rq(req, false); err = req_to_mmc_queue_req(req)->drv_op_result; diff --git a/drivers/mmc/host/sdhci-cadence.c b/drivers/mmc/host/sdhci-cadence.c index b24aa27da50c..d2f625054689 100644 --- a/drivers/mmc/host/sdhci-cadence.c +++ b/drivers/mmc/host/sdhci-cadence.c @@ -540,9 +540,11 @@ static int sdhci_cdns_probe(struct platform_device *pdev) if (host->mmc->caps & MMC_CAP_HW_RESET) { priv->rst_hw = devm_reset_control_get_optional_exclusive(dev, NULL); - if (IS_ERR(priv->rst_hw)) - return dev_err_probe(mmc_dev(host->mmc), PTR_ERR(priv->rst_hw), - "reset controller error\n"); + if (IS_ERR(priv->rst_hw)) { + ret = dev_err_probe(mmc_dev(host->mmc), PTR_ERR(priv->rst_hw), + "reset controller error\n"); + goto free; + } if (priv->rst_hw) host->mmc_host_ops.card_hw_reset = sdhci_cdns_mmc_hw_reset; } diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c index d7c0c0b9e26c..eebf94604a7f 100644 --- a/drivers/mmc/host/sdhci-esdhc-imx.c +++ b/drivers/mmc/host/sdhci-esdhc-imx.c @@ -1634,6 +1634,10 @@ sdhci_esdhc_imx_probe_dt(struct platform_device *pdev, if (ret) return ret; + /* HS400/HS400ES require 8 bit bus */ + if (!(host->mmc->caps & MMC_CAP_8_BIT_DATA)) + host->mmc->caps2 &= ~(MMC_CAP2_HS400 | MMC_CAP2_HS400_ES); + if (mmc_gpio_get_cd(host->mmc) >= 0) host->quirks &= ~SDHCI_QUIRK_BROKEN_CARD_DETECTION; @@ -1724,10 +1728,6 @@ static int sdhci_esdhc_imx_probe(struct platform_device *pdev) host->mmc_host_ops.init_card = usdhc_init_card; } - err = sdhci_esdhc_imx_probe_dt(pdev, host, imx_data); - if (err) - goto disable_ahb_clk; - if (imx_data->socdata->flags & ESDHC_FLAG_MAN_TUNING) sdhci_esdhc_ops.platform_execute_tuning = esdhc_executing_tuning; @@ -1735,15 +1735,13 @@ static int sdhci_esdhc_imx_probe(struct platform_device *pdev) if (imx_data->socdata->flags & ESDHC_FLAG_ERR004536) host->quirks |= SDHCI_QUIRK_BROKEN_ADMA; - if (host->mmc->caps & MMC_CAP_8_BIT_DATA && - imx_data->socdata->flags & ESDHC_FLAG_HS400) + if (imx_data->socdata->flags & ESDHC_FLAG_HS400) host->mmc->caps2 |= MMC_CAP2_HS400; if (imx_data->socdata->flags & ESDHC_FLAG_BROKEN_AUTO_CMD23) host->quirks2 |= SDHCI_QUIRK2_ACMD23_BROKEN; - if (host->mmc->caps & MMC_CAP_8_BIT_DATA && - imx_data->socdata->flags & ESDHC_FLAG_HS400_ES) { + if (imx_data->socdata->flags & ESDHC_FLAG_HS400_ES) { host->mmc->caps2 |= MMC_CAP2_HS400_ES; host->mmc_host_ops.hs400_enhanced_strobe = esdhc_hs400_enhanced_strobe; @@ -1765,6 +1763,10 @@ static int sdhci_esdhc_imx_probe(struct platform_device *pdev) goto disable_ahb_clk; } + err = sdhci_esdhc_imx_probe_dt(pdev, host, imx_data); + if (err) + goto disable_ahb_clk; + sdhci_esdhc_imx_hwinit(host); err = sdhci_add_host(host); diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 3fed888629f7..edbaa1444f8e 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -3947,7 +3947,11 @@ static int bond_slave_netdev_event(unsigned long event, unblock_netpoll_tx(); break; case NETDEV_FEAT_CHANGE: - bond_compute_features(bond); + if (!bond->notifier_ctx) { + bond->notifier_ctx = true; + bond_compute_features(bond); + bond->notifier_ctx = false; + } break; case NETDEV_RESEND_IGMP: /* Propagate to master device */ @@ -6342,6 +6346,8 @@ static int bond_init(struct net_device *bond_dev) if (!bond->wq) return -ENOMEM; + bond->notifier_ctx = false; + spin_lock_init(&bond->stats_lock); netdev_lockdep_set_classes(bond_dev); diff --git a/drivers/net/dsa/lan9303-core.c b/drivers/net/dsa/lan9303-core.c index cbe831875347..c0215a8770f4 100644 --- a/drivers/net/dsa/lan9303-core.c +++ b/drivers/net/dsa/lan9303-core.c @@ -1188,8 +1188,6 @@ static int lan9303_port_fdb_add(struct dsa_switch *ds, int port, struct lan9303 *chip = ds->priv; dev_dbg(chip->dev, "%s(%d, %pM, %d)\n", __func__, port, addr, vid); - if (vid) - return -EOPNOTSUPP; return lan9303_alr_add_port(chip, addr, port, false); } @@ -1201,8 +1199,6 @@ static int lan9303_port_fdb_del(struct dsa_switch *ds, int port, struct lan9303 *chip = ds->priv; dev_dbg(chip->dev, "%s(%d, %pM, %d)\n", __func__, port, addr, vid); - if (vid) - return -EOPNOTSUPP; lan9303_alr_del_port(chip, addr, port); return 0; diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 64a2f2f83735..08a46ffd53af 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -7170,7 +7170,7 @@ static int mv88e6xxx_probe(struct mdio_device *mdiodev) goto out; } if (chip->reset) - usleep_range(1000, 2000); + usleep_range(10000, 20000); /* Detect if the device is configured in single chip addressing mode, * otherwise continue with address specific smi init/detection. diff --git a/drivers/net/dsa/qca/Kconfig b/drivers/net/dsa/qca/Kconfig index 4347b42c50fd..de9da469908b 100644 --- a/drivers/net/dsa/qca/Kconfig +++ b/drivers/net/dsa/qca/Kconfig @@ -20,6 +20,7 @@ config NET_DSA_QCA8K_LEDS_SUPPORT bool "Qualcomm Atheros QCA8K Ethernet switch family LEDs support" depends on NET_DSA_QCA8K depends on LEDS_CLASS=y || LEDS_CLASS=NET_DSA_QCA8K + depends on LEDS_TRIGGERS help This enabled support for LEDs present on the Qualcomm Atheros QCA8K Ethernet switch chips. diff --git a/drivers/net/ethernet/3com/3c589_cs.c b/drivers/net/ethernet/3com/3c589_cs.c index 82f94b1635bf..5267e9dcd87e 100644 --- a/drivers/net/ethernet/3com/3c589_cs.c +++ b/drivers/net/ethernet/3com/3c589_cs.c @@ -195,6 +195,7 @@ static int tc589_probe(struct pcmcia_device *link) { struct el3_private *lp; struct net_device *dev; + int ret; dev_dbg(&link->dev, "3c589_attach()\n"); @@ -218,7 +219,15 @@ static int tc589_probe(struct pcmcia_device *link) dev->ethtool_ops = &netdev_ethtool_ops; - return tc589_config(link); + ret = tc589_config(link); + if (ret) + goto err_free_netdev; + + return 0; + +err_free_netdev: + free_netdev(dev); + return ret; } static void tc589_detach(struct pcmcia_device *link) diff --git a/drivers/net/ethernet/amd/pds_core/dev.c b/drivers/net/ethernet/amd/pds_core/dev.c index f7c597ea5daf..debe5216fe29 100644 --- a/drivers/net/ethernet/amd/pds_core/dev.c +++ b/drivers/net/ethernet/amd/pds_core/dev.c @@ -68,9 +68,15 @@ bool pdsc_is_fw_running(struct pdsc *pdsc) bool pdsc_is_fw_good(struct pdsc *pdsc) { - u8 gen = pdsc->fw_status & PDS_CORE_FW_STS_F_GENERATION; + bool fw_running = pdsc_is_fw_running(pdsc); + u8 gen; - return pdsc_is_fw_running(pdsc) && gen == pdsc->fw_generation; + /* Make sure to update the cached fw_status by calling + * pdsc_is_fw_running() before getting the generation + */ + gen = pdsc->fw_status & PDS_CORE_FW_STS_F_GENERATION; + + return fw_running && gen == pdsc->fw_generation; } static u8 pdsc_devcmd_status(struct pdsc *pdsc) diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c index 33a9574e9e04..32d2c6fac652 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c @@ -1329,7 +1329,7 @@ static enum xgbe_mode xgbe_phy_status_aneg(struct xgbe_prv_data *pdata) return pdata->phy_if.phy_impl.an_outcome(pdata); } -static void xgbe_phy_status_result(struct xgbe_prv_data *pdata) +static bool xgbe_phy_status_result(struct xgbe_prv_data *pdata) { struct ethtool_link_ksettings *lks = &pdata->phy.lks; enum xgbe_mode mode; @@ -1367,8 +1367,13 @@ static void xgbe_phy_status_result(struct xgbe_prv_data *pdata) pdata->phy.duplex = DUPLEX_FULL; - if (xgbe_set_mode(pdata, mode) && pdata->an_again) + if (!xgbe_set_mode(pdata, mode)) + return false; + + if (pdata->an_again) xgbe_phy_reconfig_aneg(pdata); + + return true; } static void xgbe_phy_status(struct xgbe_prv_data *pdata) @@ -1398,7 +1403,8 @@ static void xgbe_phy_status(struct xgbe_prv_data *pdata) return; } - xgbe_phy_status_result(pdata); + if (xgbe_phy_status_result(pdata)) + return; if (test_bit(XGBE_LINK_INIT, &pdata->dev_state)) clear_bit(XGBE_LINK_INIT, &pdata->dev_state); diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index 38d0cdaf22a5..bf1611cce974 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -2531,9 +2531,9 @@ static int bcm_sysport_probe(struct platform_device *pdev) priv->irq0 = platform_get_irq(pdev, 0); if (!priv->is_lite) { priv->irq1 = platform_get_irq(pdev, 1); - priv->wol_irq = platform_get_irq(pdev, 2); + priv->wol_irq = platform_get_irq_optional(pdev, 2); } else { - priv->wol_irq = platform_get_irq(pdev, 1); + priv->wol_irq = platform_get_irq_optional(pdev, 1); } if (priv->irq0 <= 0 || (priv->irq1 <= 0 && !priv->is_lite)) { ret = -EINVAL; diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index 3c4fa26f0f9b..9e1b2536e9a9 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -1229,7 +1229,13 @@ static int enetc_clean_rx_ring(struct enetc_bdr *rx_ring, if (!skb) break; - rx_byte_cnt += skb->len; + /* When set, the outer VLAN header is extracted and reported + * in the receive buffer descriptor. So rx_byte_cnt should + * add the length of the extracted VLAN header. + */ + if (bd_status & ENETC_RXBD_FLAG_VLAN) + rx_byte_cnt += VLAN_HLEN; + rx_byte_cnt += skb->len + ETH_HLEN; rx_frm_cnt++; napi_gro_receive(napi, skb); @@ -1565,6 +1571,14 @@ static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring, enetc_build_xdp_buff(rx_ring, bd_status, &rxbd, &i, &cleaned_cnt, &xdp_buff); + /* When set, the outer VLAN header is extracted and reported + * in the receive buffer descriptor. So rx_byte_cnt should + * add the length of the extracted VLAN header. + */ + if (bd_status & ENETC_RXBD_FLAG_VLAN) + rx_byte_cnt += VLAN_HLEN; + rx_byte_cnt += xdp_get_buff_len(&xdp_buff); + xdp_act = bpf_prog_run_xdp(prog, &xdp_buff); switch (xdp_act) { diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 059bd911c51d..52d0a126eb61 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -1152,11 +1152,11 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) unsigned int total_rx_bytes = 0, total_rx_pkts = 0; unsigned int offset = rx_ring->rx_offset; struct xdp_buff *xdp = &rx_ring->xdp; + u32 cached_ntc = rx_ring->first_desc; struct ice_tx_ring *xdp_ring = NULL; struct bpf_prog *xdp_prog = NULL; u32 ntc = rx_ring->next_to_clean; u32 cnt = rx_ring->count; - u32 cached_ntc = ntc; u32 xdp_xmit = 0; u32 cached_ntu; bool failure; diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index a75fd072082c..834c644b67db 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -3269,18 +3269,14 @@ static int mtk_open(struct net_device *dev) eth->dsa_meta[i] = md_dst; } } else { - /* Hardware special tag parsing needs to be disabled if at least - * one MAC does not use DSA. + /* Hardware DSA untagging and VLAN RX offloading need to be + * disabled if at least one MAC does not use DSA. */ u32 val = mtk_r32(eth, MTK_CDMP_IG_CTRL); val &= ~MTK_CDMP_STAG_EN; mtk_w32(eth, val, MTK_CDMP_IG_CTRL); - val = mtk_r32(eth, MTK_CDMQ_IG_CTRL); - val &= ~MTK_CDMQ_STAG_EN; - mtk_w32(eth, val, MTK_CDMQ_IG_CTRL); - mtk_w32(eth, 0, MTK_CDMP_EG_CTRL); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index d53de39539a8..d532883b42d7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -1920,9 +1920,10 @@ static void mlx5_cmd_err_trace(struct mlx5_core_dev *dev, u16 opcode, u16 op_mod static void cmd_status_log(struct mlx5_core_dev *dev, u16 opcode, u8 status, u32 syndrome, int err) { + const char *namep = mlx5_command_str(opcode); struct mlx5_cmd_stats *stats; - if (!err) + if (!err || !(strcmp(namep, "unknown command opcode"))) return; stats = &dev->cmd.stats[opcode]; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c index f40497823e65..7c0f2adbea00 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c @@ -490,7 +490,7 @@ static void poll_trace(struct mlx5_fw_tracer *tracer, (u64)timestamp_low; break; default: - if (tracer_event->event_id >= tracer->str_db.first_string_trace || + if (tracer_event->event_id >= tracer->str_db.first_string_trace && tracer_event->event_id <= tracer->str_db.first_string_trace + tracer->str_db.num_string_trace) { tracer_event->type = TRACER_EVENT_TYPE_STRING; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index b8987a404d75..8e999f238194 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -327,6 +327,7 @@ struct mlx5e_params { unsigned int sw_mtu; int hard_mtu; bool ptp_rx; + __be32 terminate_lkey_be; }; static inline u8 mlx5e_get_dcb_num_tc(struct mlx5e_params *params) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c index 7ac1ad9c46de..7e8e96cc5cd0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c @@ -51,7 +51,7 @@ int mlx5e_port_query_buffer(struct mlx5e_priv *priv, if (err) goto out; - for (i = 0; i < MLX5E_MAX_BUFFER; i++) { + for (i = 0; i < MLX5E_MAX_NETWORK_BUFFER; i++) { buffer = MLX5_ADDR_OF(pbmc_reg, out, buffer[i]); port_buffer->buffer[i].lossy = MLX5_GET(bufferx_reg, buffer, lossy); @@ -73,14 +73,24 @@ int mlx5e_port_query_buffer(struct mlx5e_priv *priv, port_buffer->buffer[i].lossy); } - port_buffer->headroom_size = total_used; + port_buffer->internal_buffers_size = 0; + for (i = MLX5E_MAX_NETWORK_BUFFER; i < MLX5E_TOTAL_BUFFERS; i++) { + buffer = MLX5_ADDR_OF(pbmc_reg, out, buffer[i]); + port_buffer->internal_buffers_size += + MLX5_GET(bufferx_reg, buffer, size) * port_buff_cell_sz; + } + port_buffer->port_buffer_size = MLX5_GET(pbmc_reg, out, port_buffer_size) * port_buff_cell_sz; - port_buffer->spare_buffer_size = - port_buffer->port_buffer_size - total_used; - - mlx5e_dbg(HW, priv, "total buffer size=%d, spare buffer size=%d\n", - port_buffer->port_buffer_size, + port_buffer->headroom_size = total_used; + port_buffer->spare_buffer_size = port_buffer->port_buffer_size - + port_buffer->internal_buffers_size - + port_buffer->headroom_size; + + mlx5e_dbg(HW, priv, + "total buffer size=%u, headroom buffer size=%u, internal buffers size=%u, spare buffer size=%u\n", + port_buffer->port_buffer_size, port_buffer->headroom_size, + port_buffer->internal_buffers_size, port_buffer->spare_buffer_size); out: kfree(out); @@ -206,11 +216,11 @@ static int port_update_pool_cfg(struct mlx5_core_dev *mdev, if (!MLX5_CAP_GEN(mdev, sbcam_reg)) return 0; - for (i = 0; i < MLX5E_MAX_BUFFER; i++) + for (i = 0; i < MLX5E_MAX_NETWORK_BUFFER; i++) lossless_buff_count += ((port_buffer->buffer[i].size) && (!(port_buffer->buffer[i].lossy))); - for (i = 0; i < MLX5E_MAX_BUFFER; i++) { + for (i = 0; i < MLX5E_MAX_NETWORK_BUFFER; i++) { p = select_sbcm_params(&port_buffer->buffer[i], lossless_buff_count); err = mlx5e_port_set_sbcm(mdev, 0, i, MLX5_INGRESS_DIR, @@ -293,7 +303,7 @@ static int port_set_buffer(struct mlx5e_priv *priv, if (err) goto out; - for (i = 0; i < MLX5E_MAX_BUFFER; i++) { + for (i = 0; i < MLX5E_MAX_NETWORK_BUFFER; i++) { void *buffer = MLX5_ADDR_OF(pbmc_reg, in, buffer[i]); u64 size = port_buffer->buffer[i].size; u64 xoff = port_buffer->buffer[i].xoff; @@ -351,7 +361,7 @@ static int update_xoff_threshold(struct mlx5e_port_buffer *port_buffer, { int i; - for (i = 0; i < MLX5E_MAX_BUFFER; i++) { + for (i = 0; i < MLX5E_MAX_NETWORK_BUFFER; i++) { if (port_buffer->buffer[i].lossy) { port_buffer->buffer[i].xoff = 0; port_buffer->buffer[i].xon = 0; @@ -408,7 +418,7 @@ static int update_buffer_lossy(struct mlx5_core_dev *mdev, int err; int i; - for (i = 0; i < MLX5E_MAX_BUFFER; i++) { + for (i = 0; i < MLX5E_MAX_NETWORK_BUFFER; i++) { prio_count = 0; lossy_count = 0; @@ -432,11 +442,11 @@ static int update_buffer_lossy(struct mlx5_core_dev *mdev, } if (changed) { - err = port_update_pool_cfg(mdev, port_buffer); + err = update_xoff_threshold(port_buffer, xoff, max_mtu, port_buff_cell_sz); if (err) return err; - err = update_xoff_threshold(port_buffer, xoff, max_mtu, port_buff_cell_sz); + err = port_update_pool_cfg(mdev, port_buffer); if (err) return err; @@ -515,7 +525,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv, if (change & MLX5E_PORT_BUFFER_PRIO2BUFFER) { update_prio2buffer = true; - for (i = 0; i < MLX5E_MAX_BUFFER; i++) + for (i = 0; i < MLX5E_MAX_NETWORK_BUFFER; i++) mlx5e_dbg(HW, priv, "%s: requested to map prio[%d] to buffer %d\n", __func__, i, prio2buffer[i]); @@ -530,7 +540,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv, } if (change & MLX5E_PORT_BUFFER_SIZE) { - for (i = 0; i < MLX5E_MAX_BUFFER; i++) { + for (i = 0; i < MLX5E_MAX_NETWORK_BUFFER; i++) { mlx5e_dbg(HW, priv, "%s: buffer[%d]=%d\n", __func__, i, buffer_size[i]); if (!port_buffer.buffer[i].lossy && !buffer_size[i]) { mlx5e_dbg(HW, priv, "%s: lossless buffer[%d] size cannot be zero\n", @@ -544,7 +554,9 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv, mlx5e_dbg(HW, priv, "%s: total buffer requested=%d\n", __func__, total_used); - if (total_used > port_buffer.port_buffer_size) + if (total_used > port_buffer.headroom_size && + (total_used - port_buffer.headroom_size) > + port_buffer.spare_buffer_size) return -EINVAL; update_buffer = true; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.h b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.h index a6ef118de758..f4a19ffbb641 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.h @@ -35,7 +35,8 @@ #include "en.h" #include "port.h" -#define MLX5E_MAX_BUFFER 8 +#define MLX5E_MAX_NETWORK_BUFFER 8 +#define MLX5E_TOTAL_BUFFERS 10 #define MLX5E_DEFAULT_CABLE_LEN 7 /* 7 meters */ #define MLX5_BUFFER_SUPPORTED(mdev) (MLX5_CAP_GEN(mdev, pcam_reg) && \ @@ -60,8 +61,9 @@ struct mlx5e_bufferx_reg { struct mlx5e_port_buffer { u32 port_buffer_size; u32 spare_buffer_size; - u32 headroom_size; - struct mlx5e_bufferx_reg buffer[MLX5E_MAX_BUFFER]; + u32 headroom_size; /* Buffers 0-7 */ + u32 internal_buffers_size; /* Buffers 8-9 */ + struct mlx5e_bufferx_reg buffer[MLX5E_MAX_NETWORK_BUFFER]; }; int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c index eb5abd0e55d9..3cbebfba582b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c @@ -175,6 +175,8 @@ static bool mlx5e_ptp_poll_ts_cq(struct mlx5e_cq *cq, int budget) /* ensure cq space is freed before enabling more cqes */ wmb(); + mlx5e_txqsq_wake(&ptpsq->txqsq); + return work_done == budget; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.c index fc923a99b6a4..0380a04c3691 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.c @@ -84,7 +84,7 @@ mlx5e_tc_act_init_parse_state(struct mlx5e_tc_act_parse_state *parse_state, int mlx5e_tc_act_post_parse(struct mlx5e_tc_act_parse_state *parse_state, - struct flow_action *flow_action, + struct flow_action *flow_action, int from, int to, struct mlx5_flow_attr *attr, enum mlx5_flow_namespace_type ns_type) { @@ -96,6 +96,11 @@ mlx5e_tc_act_post_parse(struct mlx5e_tc_act_parse_state *parse_state, priv = parse_state->flow->priv; flow_action_for_each(i, act, flow_action) { + if (i < from) + continue; + else if (i > to) + break; + tc_act = mlx5e_tc_act_get(act->id, ns_type); if (!tc_act || !tc_act->post_parse) continue; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.h index 0e6e1872ac62..d6c12d0ea55b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.h @@ -112,7 +112,7 @@ mlx5e_tc_act_init_parse_state(struct mlx5e_tc_act_parse_state *parse_state, int mlx5e_tc_act_post_parse(struct mlx5e_tc_act_parse_state *parse_state, - struct flow_action *flow_action, + struct flow_action *flow_action, int from, int to, struct mlx5_flow_attr *attr, enum mlx5_flow_namespace_type ns_type); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c index 20c2d2ecaf93..f0c3464f037f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c @@ -492,6 +492,19 @@ void mlx5e_encap_put(struct mlx5e_priv *priv, struct mlx5e_encap_entry *e) mlx5e_encap_dealloc(priv, e); } +static void mlx5e_encap_put_locked(struct mlx5e_priv *priv, struct mlx5e_encap_entry *e) +{ + struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; + + lockdep_assert_held(&esw->offloads.encap_tbl_lock); + + if (!refcount_dec_and_test(&e->refcnt)) + return; + list_del(&e->route_list); + hash_del_rcu(&e->encap_hlist); + mlx5e_encap_dealloc(priv, e); +} + static void mlx5e_decap_put(struct mlx5e_priv *priv, struct mlx5e_decap_entry *d) { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; @@ -816,6 +829,8 @@ int mlx5e_attach_encap(struct mlx5e_priv *priv, uintptr_t hash_key; int err = 0; + lockdep_assert_held(&esw->offloads.encap_tbl_lock); + parse_attr = attr->parse_attr; tun_info = parse_attr->tun_info[out_index]; mpls_info = &parse_attr->mpls_info[out_index]; @@ -829,7 +844,6 @@ int mlx5e_attach_encap(struct mlx5e_priv *priv, hash_key = hash_encap_info(&key); - mutex_lock(&esw->offloads.encap_tbl_lock); e = mlx5e_encap_get(priv, &key, hash_key); /* must verify if encap is valid or not */ @@ -840,15 +854,6 @@ int mlx5e_attach_encap(struct mlx5e_priv *priv, goto out_err; } - mutex_unlock(&esw->offloads.encap_tbl_lock); - wait_for_completion(&e->res_ready); - - /* Protect against concurrent neigh update. */ - mutex_lock(&esw->offloads.encap_tbl_lock); - if (e->compl_result < 0) { - err = -EREMOTEIO; - goto out_err; - } goto attach_flow; } @@ -877,15 +882,12 @@ int mlx5e_attach_encap(struct mlx5e_priv *priv, INIT_LIST_HEAD(&e->flows); hash_add_rcu(esw->offloads.encap_tbl, &e->encap_hlist, hash_key); tbl_time_before = mlx5e_route_tbl_get_last_update(priv); - mutex_unlock(&esw->offloads.encap_tbl_lock); if (family == AF_INET) err = mlx5e_tc_tun_create_header_ipv4(priv, mirred_dev, e); else if (family == AF_INET6) err = mlx5e_tc_tun_create_header_ipv6(priv, mirred_dev, e); - /* Protect against concurrent neigh update. */ - mutex_lock(&esw->offloads.encap_tbl_lock); complete_all(&e->res_ready); if (err) { e->compl_result = err; @@ -920,18 +922,15 @@ attach_flow: } else { flow_flag_set(flow, SLOW); } - mutex_unlock(&esw->offloads.encap_tbl_lock); return err; out_err: - mutex_unlock(&esw->offloads.encap_tbl_lock); if (e) - mlx5e_encap_put(priv, e); + mlx5e_encap_put_locked(priv, e); return err; out_err_init: - mutex_unlock(&esw->offloads.encap_tbl_lock); kfree(tun_info); kfree(e); return err; @@ -1016,6 +1015,93 @@ out_err: return err; } +int mlx5e_tc_tun_encap_dests_set(struct mlx5e_priv *priv, + struct mlx5e_tc_flow *flow, + struct mlx5_flow_attr *attr, + struct netlink_ext_ack *extack, + bool *vf_tun) +{ + struct mlx5e_tc_flow_parse_attr *parse_attr; + struct mlx5_esw_flow_attr *esw_attr; + struct net_device *encap_dev = NULL; + struct mlx5e_rep_priv *rpriv; + struct mlx5e_priv *out_priv; + struct mlx5_eswitch *esw; + int out_index; + int err = 0; + + if (!mlx5e_is_eswitch_flow(flow)) + return 0; + + parse_attr = attr->parse_attr; + esw_attr = attr->esw_attr; + *vf_tun = false; + + esw = priv->mdev->priv.eswitch; + mutex_lock(&esw->offloads.encap_tbl_lock); + for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) { + struct net_device *out_dev; + int mirred_ifindex; + + if (!(esw_attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP)) + continue; + + mirred_ifindex = parse_attr->mirred_ifindex[out_index]; + out_dev = dev_get_by_index(dev_net(priv->netdev), mirred_ifindex); + if (!out_dev) { + NL_SET_ERR_MSG_MOD(extack, "Requested mirred device not found"); + err = -ENODEV; + goto out; + } + err = mlx5e_attach_encap(priv, flow, attr, out_dev, out_index, + extack, &encap_dev); + dev_put(out_dev); + if (err) + goto out; + + if (esw_attr->dests[out_index].flags & + MLX5_ESW_DEST_CHAIN_WITH_SRC_PORT_CHANGE && + !esw_attr->dest_int_port) + *vf_tun = true; + + out_priv = netdev_priv(encap_dev); + rpriv = out_priv->ppriv; + esw_attr->dests[out_index].rep = rpriv->rep; + esw_attr->dests[out_index].mdev = out_priv->mdev; + } + + if (*vf_tun && esw_attr->out_count > 1) { + NL_SET_ERR_MSG_MOD(extack, "VF tunnel encap with mirroring is not supported"); + err = -EOPNOTSUPP; + goto out; + } + +out: + mutex_unlock(&esw->offloads.encap_tbl_lock); + return err; +} + +void mlx5e_tc_tun_encap_dests_unset(struct mlx5e_priv *priv, + struct mlx5e_tc_flow *flow, + struct mlx5_flow_attr *attr) +{ + struct mlx5_esw_flow_attr *esw_attr; + int out_index; + + if (!mlx5e_is_eswitch_flow(flow)) + return; + + esw_attr = attr->esw_attr; + + for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) { + if (!(esw_attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP)) + continue; + + mlx5e_detach_encap(flow->priv, flow, attr, out_index); + kfree(attr->parse_attr->tun_info[out_index]); + } +} + static int cmp_route_info(struct mlx5e_route_key *a, struct mlx5e_route_key *b) { @@ -1369,11 +1455,13 @@ static void mlx5e_invalidate_encap(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow; list_for_each_entry(flow, encap_flows, tmp_list) { - struct mlx5_flow_attr *attr = flow->attr; struct mlx5_esw_flow_attr *esw_attr; + struct mlx5_flow_attr *attr; if (!mlx5e_is_offloaded_flow(flow)) continue; + + attr = mlx5e_tc_get_encap_attr(flow); esw_attr = attr->esw_attr; if (flow_flag_test(flow, SLOW)) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.h index 8ad273dde40e..5d7d67687cbc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.h @@ -30,6 +30,15 @@ int mlx5e_attach_decap_route(struct mlx5e_priv *priv, void mlx5e_detach_decap_route(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow); +int mlx5e_tc_tun_encap_dests_set(struct mlx5e_priv *priv, + struct mlx5e_tc_flow *flow, + struct mlx5_flow_attr *attr, + struct netlink_ext_ack *extack, + bool *vf_tun); +void mlx5e_tc_tun_encap_dests_unset(struct mlx5e_priv *priv, + struct mlx5e_tc_flow *flow, + struct mlx5_flow_attr *attr); + struct ip_tunnel_info *mlx5e_dup_tun_info(const struct ip_tunnel_info *tun_info); int mlx5e_tc_set_attr_rx_tun(struct mlx5e_tc_flow *flow, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h index 47381e949f1f..879d698b6119 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h @@ -193,6 +193,8 @@ static inline u16 mlx5e_txqsq_get_next_pi(struct mlx5e_txqsq *sq, u16 size) return pi; } +void mlx5e_txqsq_wake(struct mlx5e_txqsq *sq); + static inline u16 mlx5e_shampo_get_cqe_header_index(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) { return be16_to_cpu(cqe->shampo.header_entry_index) & (rq->mpwqe.shampo->hd_per_wq - 1); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c index 1f90594499c6..41c396e76457 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c @@ -150,10 +150,8 @@ int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb, inlen = MLX5_ST_SZ_BYTES(modify_tir_in); in = kvzalloc(inlen, GFP_KERNEL); - if (!in) { - err = -ENOMEM; - goto out; - } + if (!in) + return -ENOMEM; if (enable_uc_lb) lb_flags = MLX5_TIRC_SELF_LB_BLOCK_BLOCK_UNICAST; @@ -171,14 +169,13 @@ int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb, tirn = tir->tirn; err = mlx5_core_modify_tir(mdev, tirn, in); if (err) - goto out; + break; } + mutex_unlock(&mdev->mlx5e_res.hw_objs.td.list_lock); -out: kvfree(in); if (err) netdev_err(priv->netdev, "refresh tir(0x%x) failed, %d\n", tirn, err); - mutex_unlock(&mdev->mlx5e_res.hw_objs.td.list_lock); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c index 89de92d06483..ebee52a8361a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c @@ -926,9 +926,10 @@ static int mlx5e_dcbnl_getbuffer(struct net_device *dev, if (err) return err; - for (i = 0; i < MLX5E_MAX_BUFFER; i++) + for (i = 0; i < MLX5E_MAX_NETWORK_BUFFER; i++) dcb_buffer->buffer_size[i] = port_buffer.buffer[i].size; - dcb_buffer->total_size = port_buffer.port_buffer_size; + dcb_buffer->total_size = port_buffer.port_buffer_size - + port_buffer.internal_buffers_size; return 0; } @@ -970,7 +971,7 @@ static int mlx5e_dcbnl_setbuffer(struct net_device *dev, if (err) return err; - for (i = 0; i < MLX5E_MAX_BUFFER; i++) { + for (i = 0; i < MLX5E_MAX_NETWORK_BUFFER; i++) { if (port_buffer.buffer[i].size != dcb_buffer->buffer_size[i]) { changed |= MLX5E_PORT_BUFFER_SIZE; buffer_size = dcb_buffer->buffer_size; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 2944691f06ad..a7c526ee5024 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -727,26 +727,6 @@ static void mlx5e_rq_free_shampo(struct mlx5e_rq *rq) mlx5e_rq_shampo_hd_free(rq); } -static __be32 mlx5e_get_terminate_scatter_list_mkey(struct mlx5_core_dev *dev) -{ - u32 out[MLX5_ST_SZ_DW(query_special_contexts_out)] = {}; - u32 in[MLX5_ST_SZ_DW(query_special_contexts_in)] = {}; - int res; - - if (!MLX5_CAP_GEN(dev, terminate_scatter_list_mkey)) - return MLX5_TERMINATE_SCATTER_LIST_LKEY; - - MLX5_SET(query_special_contexts_in, in, opcode, - MLX5_CMD_OP_QUERY_SPECIAL_CONTEXTS); - res = mlx5_cmd_exec_inout(dev, query_special_contexts, in, out); - if (res) - return MLX5_TERMINATE_SCATTER_LIST_LKEY; - - res = MLX5_GET(query_special_contexts_out, out, - terminate_scatter_list_mkey); - return cpu_to_be32(res); -} - static int mlx5e_alloc_rq(struct mlx5e_params *params, struct mlx5e_xsk_param *xsk, struct mlx5e_rq_param *rqp, @@ -908,7 +888,7 @@ static int mlx5e_alloc_rq(struct mlx5e_params *params, /* check if num_frags is not a pow of two */ if (rq->wqe.info.num_frags < (1 << rq->wqe.info.log_num_frags)) { wqe->data[f].byte_count = 0; - wqe->data[f].lkey = mlx5e_get_terminate_scatter_list_mkey(mdev); + wqe->data[f].lkey = params->terminate_lkey_be; wqe->data[f].addr = 0; } } @@ -5007,6 +4987,8 @@ void mlx5e_build_nic_params(struct mlx5e_priv *priv, struct mlx5e_xsk *xsk, u16 /* RQ */ mlx5e_build_rq_params(mdev, params); + params->terminate_lkey_be = mlx5_core_get_terminate_scatter_list_mkey(mdev); + params->packet_merge.timeout = mlx5e_choose_lro_timeout(mdev, MLX5E_DEFAULT_LRO_TIMEOUT); /* CQ moderation params */ @@ -5279,12 +5261,16 @@ static int mlx5e_nic_init(struct mlx5_core_dev *mdev, mlx5e_timestamp_init(priv); + priv->dfs_root = debugfs_create_dir("nic", + mlx5_debugfs_get_dev_root(mdev)); + fs = mlx5e_fs_init(priv->profile, mdev, !test_bit(MLX5E_STATE_DESTROYING, &priv->state), priv->dfs_root); if (!fs) { err = -ENOMEM; mlx5_core_err(mdev, "FS initialization failed, %d\n", err); + debugfs_remove_recursive(priv->dfs_root); return err; } priv->fs = fs; @@ -5305,6 +5291,7 @@ static void mlx5e_nic_cleanup(struct mlx5e_priv *priv) mlx5e_health_destroy_reporters(priv); mlx5e_ktls_cleanup(priv); mlx5e_fs_cleanup(priv->fs); + debugfs_remove_recursive(priv->dfs_root); priv->fs = NULL; } @@ -5851,8 +5838,8 @@ void mlx5e_detach_netdev(struct mlx5e_priv *priv) } static int -mlx5e_netdev_attach_profile(struct net_device *netdev, struct mlx5_core_dev *mdev, - const struct mlx5e_profile *new_profile, void *new_ppriv) +mlx5e_netdev_init_profile(struct net_device *netdev, struct mlx5_core_dev *mdev, + const struct mlx5e_profile *new_profile, void *new_ppriv) { struct mlx5e_priv *priv = netdev_priv(netdev); int err; @@ -5868,6 +5855,25 @@ mlx5e_netdev_attach_profile(struct net_device *netdev, struct mlx5_core_dev *mde err = new_profile->init(priv->mdev, priv->netdev); if (err) goto priv_cleanup; + + return 0; + +priv_cleanup: + mlx5e_priv_cleanup(priv); + return err; +} + +static int +mlx5e_netdev_attach_profile(struct net_device *netdev, struct mlx5_core_dev *mdev, + const struct mlx5e_profile *new_profile, void *new_ppriv) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + int err; + + err = mlx5e_netdev_init_profile(netdev, mdev, new_profile, new_ppriv); + if (err) + return err; + err = mlx5e_attach_netdev(priv); if (err) goto profile_cleanup; @@ -5875,7 +5881,6 @@ mlx5e_netdev_attach_profile(struct net_device *netdev, struct mlx5_core_dev *mde profile_cleanup: new_profile->cleanup(priv); -priv_cleanup: mlx5e_priv_cleanup(priv); return err; } @@ -5894,6 +5899,12 @@ int mlx5e_netdev_change_profile(struct mlx5e_priv *priv, priv->profile->cleanup(priv); mlx5e_priv_cleanup(priv); + if (mdev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) { + mlx5e_netdev_init_profile(netdev, mdev, new_profile, new_ppriv); + set_bit(MLX5E_STATE_DESTROYING, &priv->state); + return -EIO; + } + err = mlx5e_netdev_attach_profile(netdev, mdev, new_profile, new_ppriv); if (err) { /* roll back to original profile */ netdev_warn(netdev, "%s: new profile init failed, %d\n", __func__, err); @@ -5955,8 +5966,11 @@ static int mlx5e_suspend(struct auxiliary_device *adev, pm_message_t state) struct net_device *netdev = priv->netdev; struct mlx5_core_dev *mdev = priv->mdev; - if (!netif_device_present(netdev)) + if (!netif_device_present(netdev)) { + if (test_bit(MLX5E_STATE_DESTROYING, &priv->state)) + mlx5e_destroy_mdev_resources(mdev); return -ENODEV; + } mlx5e_detach_netdev(priv); mlx5e_destroy_mdev_resources(mdev); @@ -6002,9 +6016,6 @@ static int mlx5e_probe(struct auxiliary_device *adev, priv->profile = profile; priv->ppriv = NULL; - priv->dfs_root = debugfs_create_dir("nic", - mlx5_debugfs_get_dev_root(priv->mdev)); - err = profile->init(mdev, netdev); if (err) { mlx5_core_err(mdev, "mlx5e_nic_profile init failed, %d\n", err); @@ -6033,7 +6044,6 @@ err_resume: err_profile_cleanup: profile->cleanup(priv); err_destroy_netdev: - debugfs_remove_recursive(priv->dfs_root); mlx5e_destroy_netdev(priv); err_devlink_port_unregister: mlx5e_devlink_port_unregister(mlx5e_dev); @@ -6053,7 +6063,6 @@ static void mlx5e_remove(struct auxiliary_device *adev) unregister_netdev(priv->netdev); mlx5e_suspend(adev, state); priv->profile->cleanup(priv); - debugfs_remove_recursive(priv->dfs_root); mlx5e_destroy_netdev(priv); mlx5e_devlink_port_unregister(mlx5e_dev); mlx5e_destroy_devlink(mlx5e_dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 1fc386eccaf8..3e7041bd5705 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -30,6 +30,7 @@ * SOFTWARE. */ +#include <linux/debugfs.h> #include <linux/mlx5/fs.h> #include <net/switchdev.h> #include <net/pkt_cls.h> @@ -812,11 +813,15 @@ static int mlx5e_init_ul_rep(struct mlx5_core_dev *mdev, { struct mlx5e_priv *priv = netdev_priv(netdev); + priv->dfs_root = debugfs_create_dir("nic", + mlx5_debugfs_get_dev_root(mdev)); + priv->fs = mlx5e_fs_init(priv->profile, mdev, !test_bit(MLX5E_STATE_DESTROYING, &priv->state), priv->dfs_root); if (!priv->fs) { netdev_err(priv->netdev, "FS allocation failed\n"); + debugfs_remove_recursive(priv->dfs_root); return -ENOMEM; } @@ -829,6 +834,7 @@ static int mlx5e_init_ul_rep(struct mlx5_core_dev *mdev, static void mlx5e_cleanup_rep(struct mlx5e_priv *priv) { mlx5e_fs_cleanup(priv->fs); + debugfs_remove_recursive(priv->dfs_root); priv->fs = NULL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 728b82ce4031..8a5a8703f0a3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1665,11 +1665,9 @@ bool mlx5e_tc_is_vf_tunnel(struct net_device *out_dev, struct net_device *route_ int mlx5e_tc_query_route_vport(struct net_device *out_dev, struct net_device *route_dev, u16 *vport) { struct mlx5e_priv *out_priv, *route_priv; - struct mlx5_devcom *devcom = NULL; struct mlx5_core_dev *route_mdev; struct mlx5_eswitch *esw; u16 vhca_id; - int err; out_priv = netdev_priv(out_dev); esw = out_priv->mdev->priv.eswitch; @@ -1678,6 +1676,9 @@ int mlx5e_tc_query_route_vport(struct net_device *out_dev, struct net_device *ro vhca_id = MLX5_CAP_GEN(route_mdev, vhca_id); if (mlx5_lag_is_active(out_priv->mdev)) { + struct mlx5_devcom *devcom; + int err; + /* In lag case we may get devices from different eswitch instances. * If we failed to get vport num, it means, mostly, that we on the wrong * eswitch. @@ -1686,101 +1687,16 @@ int mlx5e_tc_query_route_vport(struct net_device *out_dev, struct net_device *ro if (err != -ENOENT) return err; + rcu_read_lock(); devcom = out_priv->mdev->priv.devcom; - esw = mlx5_devcom_get_peer_data(devcom, MLX5_DEVCOM_ESW_OFFLOADS); - if (!esw) - return -ENODEV; - } - - err = mlx5_eswitch_vhca_id_to_vport(esw, vhca_id, vport); - if (devcom) - mlx5_devcom_release_peer_data(devcom, MLX5_DEVCOM_ESW_OFFLOADS); - return err; -} - -static int -set_encap_dests(struct mlx5e_priv *priv, - struct mlx5e_tc_flow *flow, - struct mlx5_flow_attr *attr, - struct netlink_ext_ack *extack, - bool *vf_tun) -{ - struct mlx5e_tc_flow_parse_attr *parse_attr; - struct mlx5_esw_flow_attr *esw_attr; - struct net_device *encap_dev = NULL; - struct mlx5e_rep_priv *rpriv; - struct mlx5e_priv *out_priv; - int out_index; - int err = 0; - - if (!mlx5e_is_eswitch_flow(flow)) - return 0; - - parse_attr = attr->parse_attr; - esw_attr = attr->esw_attr; - *vf_tun = false; - - for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) { - struct net_device *out_dev; - int mirred_ifindex; - - if (!(esw_attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP)) - continue; - - mirred_ifindex = parse_attr->mirred_ifindex[out_index]; - out_dev = dev_get_by_index(dev_net(priv->netdev), mirred_ifindex); - if (!out_dev) { - NL_SET_ERR_MSG_MOD(extack, "Requested mirred device not found"); - err = -ENODEV; - goto out; - } - err = mlx5e_attach_encap(priv, flow, attr, out_dev, out_index, - extack, &encap_dev); - dev_put(out_dev); - if (err) - goto out; + esw = mlx5_devcom_get_peer_data_rcu(devcom, MLX5_DEVCOM_ESW_OFFLOADS); + err = esw ? mlx5_eswitch_vhca_id_to_vport(esw, vhca_id, vport) : -ENODEV; + rcu_read_unlock(); - if (esw_attr->dests[out_index].flags & - MLX5_ESW_DEST_CHAIN_WITH_SRC_PORT_CHANGE && - !esw_attr->dest_int_port) - *vf_tun = true; - - out_priv = netdev_priv(encap_dev); - rpriv = out_priv->ppriv; - esw_attr->dests[out_index].rep = rpriv->rep; - esw_attr->dests[out_index].mdev = out_priv->mdev; - } - - if (*vf_tun && esw_attr->out_count > 1) { - NL_SET_ERR_MSG_MOD(extack, "VF tunnel encap with mirroring is not supported"); - err = -EOPNOTSUPP; - goto out; + return err; } -out: - return err; -} - -static void -clean_encap_dests(struct mlx5e_priv *priv, - struct mlx5e_tc_flow *flow, - struct mlx5_flow_attr *attr) -{ - struct mlx5_esw_flow_attr *esw_attr; - int out_index; - - if (!mlx5e_is_eswitch_flow(flow)) - return; - - esw_attr = attr->esw_attr; - - for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) { - if (!(esw_attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP)) - continue; - - mlx5e_detach_encap(priv, flow, attr, out_index); - kfree(attr->parse_attr->tun_info[out_index]); - } + return mlx5_eswitch_vhca_id_to_vport(esw, vhca_id, vport); } static int @@ -1819,7 +1735,7 @@ post_process_attr(struct mlx5e_tc_flow *flow, if (err) goto err_out; - err = set_encap_dests(flow->priv, flow, attr, extack, &vf_tun); + err = mlx5e_tc_tun_encap_dests_set(flow->priv, flow, attr, extack, &vf_tun); if (err) goto err_out; @@ -3943,8 +3859,8 @@ parse_tc_actions(struct mlx5e_tc_act_parse_state *parse_state, struct mlx5_flow_attr *prev_attr; struct flow_action_entry *act; struct mlx5e_tc_act *tc_act; + int err, i, i_split = 0; bool is_missable; - int err, i; ns_type = mlx5e_get_flow_namespace(flow); list_add(&attr->list, &flow->attrs); @@ -3985,7 +3901,8 @@ parse_tc_actions(struct mlx5e_tc_act_parse_state *parse_state, i < flow_action->num_entries - 1)) { is_missable = tc_act->is_missable ? tc_act->is_missable(act) : false; - err = mlx5e_tc_act_post_parse(parse_state, flow_action, attr, ns_type); + err = mlx5e_tc_act_post_parse(parse_state, flow_action, i_split, i, attr, + ns_type); if (err) goto out_free_post_acts; @@ -3995,6 +3912,7 @@ parse_tc_actions(struct mlx5e_tc_act_parse_state *parse_state, goto out_free_post_acts; } + i_split = i + 1; list_add(&attr->list, &flow->attrs); } @@ -4009,7 +3927,7 @@ parse_tc_actions(struct mlx5e_tc_act_parse_state *parse_state, } } - err = mlx5e_tc_act_post_parse(parse_state, flow_action, attr, ns_type); + err = mlx5e_tc_act_post_parse(parse_state, flow_action, i_split, i, attr, ns_type); if (err) goto out_free_post_acts; @@ -4323,7 +4241,7 @@ mlx5_free_flow_attr_actions(struct mlx5e_tc_flow *flow, struct mlx5_flow_attr *a if (attr->post_act_handle) mlx5e_tc_post_act_del(get_post_action(flow->priv), attr->post_act_handle); - clean_encap_dests(flow->priv, flow, attr); + mlx5e_tc_tun_encap_dests_unset(flow->priv, flow, attr); if (attr->action & MLX5_FLOW_CONTEXT_ACTION_COUNT) mlx5_fc_destroy(counter_dev, attr->counter); @@ -5301,6 +5219,8 @@ int mlx5e_tc_esw_init(struct mlx5_rep_uplink_priv *uplink_priv) goto err_action_counter; } + mlx5_esw_offloads_devcom_init(esw); + return 0; err_action_counter: @@ -5329,7 +5249,7 @@ void mlx5e_tc_esw_cleanup(struct mlx5_rep_uplink_priv *uplink_priv) priv = netdev_priv(rpriv->netdev); esw = priv->mdev->priv.eswitch; - mlx5e_tc_clean_fdb_peer_flows(esw); + mlx5_esw_offloads_devcom_cleanup(esw); mlx5e_tc_tun_cleanup(uplink_priv->encap); @@ -5643,22 +5563,43 @@ bool mlx5e_tc_update_skb_nic(struct mlx5_cqe64 *cqe, struct sk_buff *skb) 0, NULL); } +static struct mapping_ctx * +mlx5e_get_priv_obj_mapping(struct mlx5e_priv *priv) +{ + struct mlx5e_tc_table *tc; + struct mlx5_eswitch *esw; + struct mapping_ctx *ctx; + + if (is_mdev_switchdev_mode(priv->mdev)) { + esw = priv->mdev->priv.eswitch; + ctx = esw->offloads.reg_c0_obj_pool; + } else { + tc = mlx5e_fs_get_tc(priv->fs); + ctx = tc->mapping; + } + + return ctx; +} + int mlx5e_tc_action_miss_mapping_get(struct mlx5e_priv *priv, struct mlx5_flow_attr *attr, u64 act_miss_cookie, u32 *act_miss_mapping) { - struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct mlx5_mapped_obj mapped_obj = {}; + struct mlx5_eswitch *esw; struct mapping_ctx *ctx; int err; - ctx = esw->offloads.reg_c0_obj_pool; - + ctx = mlx5e_get_priv_obj_mapping(priv); mapped_obj.type = MLX5_MAPPED_OBJ_ACT_MISS; mapped_obj.act_miss_cookie = act_miss_cookie; err = mapping_add(ctx, &mapped_obj, act_miss_mapping); if (err) return err; + if (!is_mdev_switchdev_mode(priv->mdev)) + return 0; + + esw = priv->mdev->priv.eswitch; attr->act_id_restore_rule = esw_add_restore_rule(esw, *act_miss_mapping); if (IS_ERR(attr->act_id_restore_rule)) goto err_rule; @@ -5673,10 +5614,9 @@ err_rule: void mlx5e_tc_action_miss_mapping_put(struct mlx5e_priv *priv, struct mlx5_flow_attr *attr, u32 act_miss_mapping) { - struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; - struct mapping_ctx *ctx; + struct mapping_ctx *ctx = mlx5e_get_priv_obj_mapping(priv); - ctx = esw->offloads.reg_c0_obj_pool; - mlx5_del_flow_rules(attr->act_id_restore_rule); + if (is_mdev_switchdev_mode(priv->mdev)) + mlx5_del_flow_rules(attr->act_id_restore_rule); mapping_remove(ctx, act_miss_mapping); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index df5e780e8e6a..c7eb6b238c2b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -762,6 +762,17 @@ static void mlx5e_tx_wi_consume_fifo_skbs(struct mlx5e_txqsq *sq, struct mlx5e_t } } +void mlx5e_txqsq_wake(struct mlx5e_txqsq *sq) +{ + if (netif_tx_queue_stopped(sq->txq) && + mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, sq->stop_room) && + mlx5e_ptpsq_fifo_has_room(sq) && + !test_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state)) { + netif_tx_wake_queue(sq->txq); + sq->stats->wake++; + } +} + bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget) { struct mlx5e_sq_stats *stats; @@ -861,13 +872,7 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget) netdev_tx_completed_queue(sq->txq, npkts, nbytes); - if (netif_tx_queue_stopped(sq->txq) && - mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, sq->stop_room) && - mlx5e_ptpsq_fifo_has_room(sq) && - !test_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state)) { - netif_tx_wake_queue(sq->txq); - stats->wake++; - } + mlx5e_txqsq_wake(sq); return (i == MLX5E_TX_CQ_POLL_BUDGET); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index 1c35d721a31d..3db4866d7880 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -824,7 +824,7 @@ static int comp_irqs_request_pci(struct mlx5_core_dev *dev) ncomp_eqs = table->num_comp_eqs; cpus = kcalloc(ncomp_eqs, sizeof(*cpus), GFP_KERNEL); if (!cpus) - ret = -ENOMEM; + return -ENOMEM; i = 0; rcu_read_lock(); @@ -1104,7 +1104,7 @@ void mlx5_core_eq_free_irqs(struct mlx5_core_dev *dev) struct mlx5_eq_table *table = dev->priv.eq_table; mutex_lock(&table->lock); /* sync with create/destroy_async_eq */ - mlx5_irq_table_destroy(dev); + mlx5_irq_table_free_irqs(dev); mutex_unlock(&table->lock); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 1a042c981713..add6cfa432a5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -342,6 +342,7 @@ struct mlx5_eswitch { u32 large_group_num; } params; struct blocking_notifier_head n_head; + bool paired[MLX5_MAX_PORTS]; }; void esw_offloads_disable(struct mlx5_eswitch *esw); @@ -369,6 +370,8 @@ int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int num_vfs); void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw, bool clear_vf); void mlx5_eswitch_disable_locked(struct mlx5_eswitch *esw); void mlx5_eswitch_disable(struct mlx5_eswitch *esw); +void mlx5_esw_offloads_devcom_init(struct mlx5_eswitch *esw); +void mlx5_esw_offloads_devcom_cleanup(struct mlx5_eswitch *esw); int mlx5_eswitch_set_vport_mac(struct mlx5_eswitch *esw, u16 vport, const u8 *mac); int mlx5_eswitch_set_vport_state(struct mlx5_eswitch *esw, @@ -767,6 +770,8 @@ static inline void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw) {} static inline int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int num_vfs) { return 0; } static inline void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw, bool clear_vf) {} static inline void mlx5_eswitch_disable(struct mlx5_eswitch *esw) {} +static inline void mlx5_esw_offloads_devcom_init(struct mlx5_eswitch *esw) {} +static inline void mlx5_esw_offloads_devcom_cleanup(struct mlx5_eswitch *esw) {} static inline bool mlx5_eswitch_is_funcs_handler(struct mlx5_core_dev *dev) { return false; } static inline int mlx5_eswitch_set_vport_state(struct mlx5_eswitch *esw, u16 vport, int link_state) { return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 69215ffb9999..8d19c20d3447 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -2742,6 +2742,9 @@ static int mlx5_esw_offloads_devcom_event(int event, mlx5_eswitch_vport_match_metadata_enabled(peer_esw)) break; + if (esw->paired[mlx5_get_dev_index(peer_esw->dev)]) + break; + err = mlx5_esw_offloads_set_ns_peer(esw, peer_esw, true); if (err) goto err_out; @@ -2753,14 +2756,18 @@ static int mlx5_esw_offloads_devcom_event(int event, if (err) goto err_pair; + esw->paired[mlx5_get_dev_index(peer_esw->dev)] = true; + peer_esw->paired[mlx5_get_dev_index(esw->dev)] = true; mlx5_devcom_set_paired(devcom, MLX5_DEVCOM_ESW_OFFLOADS, true); break; case ESW_OFFLOADS_DEVCOM_UNPAIR: - if (!mlx5_devcom_is_paired(devcom, MLX5_DEVCOM_ESW_OFFLOADS)) + if (!esw->paired[mlx5_get_dev_index(peer_esw->dev)]) break; mlx5_devcom_set_paired(devcom, MLX5_DEVCOM_ESW_OFFLOADS, false); + esw->paired[mlx5_get_dev_index(peer_esw->dev)] = false; + peer_esw->paired[mlx5_get_dev_index(esw->dev)] = false; mlx5_esw_offloads_unpair(peer_esw); mlx5_esw_offloads_unpair(esw); mlx5_esw_offloads_set_ns_peer(esw, peer_esw, false); @@ -2779,7 +2786,7 @@ err_out: return err; } -static void esw_offloads_devcom_init(struct mlx5_eswitch *esw) +void mlx5_esw_offloads_devcom_init(struct mlx5_eswitch *esw) { struct mlx5_devcom *devcom = esw->dev->priv.devcom; @@ -2802,7 +2809,7 @@ static void esw_offloads_devcom_init(struct mlx5_eswitch *esw) ESW_OFFLOADS_DEVCOM_PAIR, esw); } -static void esw_offloads_devcom_cleanup(struct mlx5_eswitch *esw) +void mlx5_esw_offloads_devcom_cleanup(struct mlx5_eswitch *esw) { struct mlx5_devcom *devcom = esw->dev->priv.devcom; @@ -3250,8 +3257,6 @@ int esw_offloads_enable(struct mlx5_eswitch *esw) if (err) goto err_vports; - esw_offloads_devcom_init(esw); - return 0; err_vports: @@ -3292,7 +3297,6 @@ static int esw_offloads_stop(struct mlx5_eswitch *esw, void esw_offloads_disable(struct mlx5_eswitch *esw) { - esw_offloads_devcom_cleanup(esw); mlx5_eswitch_disable_pf_vf_vports(esw); esw_offloads_unload_rep(esw, MLX5_VPORT_UPLINK); esw_set_passing_vport_metadata(esw, false); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c index adefde3ea941..b7d779d08d83 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c @@ -3,6 +3,7 @@ #include <linux/mlx5/vport.h> #include "lib/devcom.h" +#include "mlx5_core.h" static LIST_HEAD(devcom_list); @@ -13,7 +14,7 @@ static LIST_HEAD(devcom_list); struct mlx5_devcom_component { struct { - void *data; + void __rcu *data; } device[MLX5_DEVCOM_PORTS_SUPPORTED]; mlx5_devcom_event_handler_t handler; @@ -77,6 +78,7 @@ struct mlx5_devcom *mlx5_devcom_register_device(struct mlx5_core_dev *dev) if (MLX5_CAP_GEN(dev, num_lag_ports) != MLX5_DEVCOM_PORTS_SUPPORTED) return NULL; + mlx5_dev_list_lock(); sguid0 = mlx5_query_nic_system_image_guid(dev); list_for_each_entry(iter, &devcom_list, list) { struct mlx5_core_dev *tmp_dev = NULL; @@ -102,8 +104,10 @@ struct mlx5_devcom *mlx5_devcom_register_device(struct mlx5_core_dev *dev) if (!priv) { priv = mlx5_devcom_list_alloc(); - if (!priv) - return ERR_PTR(-ENOMEM); + if (!priv) { + devcom = ERR_PTR(-ENOMEM); + goto out; + } idx = 0; new_priv = true; @@ -112,13 +116,16 @@ struct mlx5_devcom *mlx5_devcom_register_device(struct mlx5_core_dev *dev) priv->devs[idx] = dev; devcom = mlx5_devcom_alloc(priv, idx); if (!devcom) { - kfree(priv); - return ERR_PTR(-ENOMEM); + if (new_priv) + kfree(priv); + devcom = ERR_PTR(-ENOMEM); + goto out; } if (new_priv) list_add(&priv->list, &devcom_list); - +out: + mlx5_dev_list_unlock(); return devcom; } @@ -131,6 +138,7 @@ void mlx5_devcom_unregister_device(struct mlx5_devcom *devcom) if (IS_ERR_OR_NULL(devcom)) return; + mlx5_dev_list_lock(); priv = devcom->priv; priv->devs[devcom->idx] = NULL; @@ -141,10 +149,12 @@ void mlx5_devcom_unregister_device(struct mlx5_devcom *devcom) break; if (i != MLX5_DEVCOM_PORTS_SUPPORTED) - return; + goto out; list_del(&priv->list); kfree(priv); +out: + mlx5_dev_list_unlock(); } void mlx5_devcom_register_component(struct mlx5_devcom *devcom, @@ -162,7 +172,7 @@ void mlx5_devcom_register_component(struct mlx5_devcom *devcom, comp = &devcom->priv->components[id]; down_write(&comp->sem); comp->handler = handler; - comp->device[devcom->idx].data = data; + rcu_assign_pointer(comp->device[devcom->idx].data, data); up_write(&comp->sem); } @@ -176,8 +186,9 @@ void mlx5_devcom_unregister_component(struct mlx5_devcom *devcom, comp = &devcom->priv->components[id]; down_write(&comp->sem); - comp->device[devcom->idx].data = NULL; + RCU_INIT_POINTER(comp->device[devcom->idx].data, NULL); up_write(&comp->sem); + synchronize_rcu(); } int mlx5_devcom_send_event(struct mlx5_devcom *devcom, @@ -193,12 +204,15 @@ int mlx5_devcom_send_event(struct mlx5_devcom *devcom, comp = &devcom->priv->components[id]; down_write(&comp->sem); - for (i = 0; i < MLX5_DEVCOM_PORTS_SUPPORTED; i++) - if (i != devcom->idx && comp->device[i].data) { - err = comp->handler(event, comp->device[i].data, - event_data); + for (i = 0; i < MLX5_DEVCOM_PORTS_SUPPORTED; i++) { + void *data = rcu_dereference_protected(comp->device[i].data, + lockdep_is_held(&comp->sem)); + + if (i != devcom->idx && data) { + err = comp->handler(event, data, event_data); break; } + } up_write(&comp->sem); return err; @@ -213,7 +227,7 @@ void mlx5_devcom_set_paired(struct mlx5_devcom *devcom, comp = &devcom->priv->components[id]; WARN_ON(!rwsem_is_locked(&comp->sem)); - comp->paired = paired; + WRITE_ONCE(comp->paired, paired); } bool mlx5_devcom_is_paired(struct mlx5_devcom *devcom, @@ -222,7 +236,7 @@ bool mlx5_devcom_is_paired(struct mlx5_devcom *devcom, if (IS_ERR_OR_NULL(devcom)) return false; - return devcom->priv->components[id].paired; + return READ_ONCE(devcom->priv->components[id].paired); } void *mlx5_devcom_get_peer_data(struct mlx5_devcom *devcom, @@ -236,7 +250,7 @@ void *mlx5_devcom_get_peer_data(struct mlx5_devcom *devcom, comp = &devcom->priv->components[id]; down_read(&comp->sem); - if (!comp->paired) { + if (!READ_ONCE(comp->paired)) { up_read(&comp->sem); return NULL; } @@ -245,7 +259,29 @@ void *mlx5_devcom_get_peer_data(struct mlx5_devcom *devcom, if (i != devcom->idx) break; - return comp->device[i].data; + return rcu_dereference_protected(comp->device[i].data, lockdep_is_held(&comp->sem)); +} + +void *mlx5_devcom_get_peer_data_rcu(struct mlx5_devcom *devcom, enum mlx5_devcom_components id) +{ + struct mlx5_devcom_component *comp; + int i; + + if (IS_ERR_OR_NULL(devcom)) + return NULL; + + for (i = 0; i < MLX5_DEVCOM_PORTS_SUPPORTED; i++) + if (i != devcom->idx) + break; + + comp = &devcom->priv->components[id]; + /* This can change concurrently, however 'data' pointer will remain + * valid for the duration of RCU read section. + */ + if (!READ_ONCE(comp->paired)) + return NULL; + + return rcu_dereference(comp->device[i].data); } void mlx5_devcom_release_peer_data(struct mlx5_devcom *devcom, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h index 94313c18bb64..9a496f4722da 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h @@ -41,6 +41,7 @@ bool mlx5_devcom_is_paired(struct mlx5_devcom *devcom, void *mlx5_devcom_get_peer_data(struct mlx5_devcom *devcom, enum mlx5_devcom_components id); +void *mlx5_devcom_get_peer_data_rcu(struct mlx5_devcom *devcom, enum mlx5_devcom_components id); void mlx5_devcom_release_peer_data(struct mlx5_devcom *devcom, enum mlx5_devcom_components id); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 995eb2d5ace0..d6ee016deae1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -923,7 +923,6 @@ static int mlx5_pci_init(struct mlx5_core_dev *dev, struct pci_dev *pdev, } mlx5_pci_vsc_init(dev); - dev->caps.embedded_cpu = mlx5_read_embedded_cpu(dev); return 0; err_clr_master: @@ -1049,7 +1048,7 @@ static int mlx5_init_once(struct mlx5_core_dev *dev) dev->dm = mlx5_dm_create(dev); if (IS_ERR(dev->dm)) - mlx5_core_warn(dev, "Failed to init device memory%d\n", err); + mlx5_core_warn(dev, "Failed to init device memory %ld\n", PTR_ERR(dev->dm)); dev->tracer = mlx5_fw_tracer_create(dev); dev->hv_vhca = mlx5_hv_vhca_create(dev); @@ -1155,6 +1154,7 @@ static int mlx5_function_setup(struct mlx5_core_dev *dev, bool boot, u64 timeout goto err_cmd_cleanup; } + dev->caps.embedded_cpu = mlx5_read_embedded_cpu(dev); mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_UP); mlx5_start_health_poll(dev); @@ -1802,15 +1802,16 @@ static void remove_one(struct pci_dev *pdev) struct devlink *devlink = priv_to_devlink(dev); set_bit(MLX5_BREAK_FW_WAIT, &dev->intf_state); - /* mlx5_drain_fw_reset() is using devlink APIs. Hence, we must drain - * fw_reset before unregistering the devlink. + /* mlx5_drain_fw_reset() and mlx5_drain_health_wq() are using + * devlink notify APIs. + * Hence, we must drain them before unregistering the devlink. */ mlx5_drain_fw_reset(dev); + mlx5_drain_health_wq(dev); devlink_unregister(devlink); mlx5_sriov_disable(pdev); mlx5_thermal_uninit(dev); mlx5_crdump_disable(dev); - mlx5_drain_health_wq(dev); mlx5_uninit_one(dev); mlx5_pci_close(dev); mlx5_mdev_uninit(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h index efd0c299c5c7..aa403a5ea34e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h @@ -15,6 +15,7 @@ int mlx5_irq_table_init(struct mlx5_core_dev *dev); void mlx5_irq_table_cleanup(struct mlx5_core_dev *dev); int mlx5_irq_table_create(struct mlx5_core_dev *dev); void mlx5_irq_table_destroy(struct mlx5_core_dev *dev); +void mlx5_irq_table_free_irqs(struct mlx5_core_dev *dev); int mlx5_irq_table_get_num_comp(struct mlx5_irq_table *table); int mlx5_irq_table_get_sfs_vec(struct mlx5_irq_table *table); struct mlx5_irq_table *mlx5_irq_table_get(struct mlx5_core_dev *dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mr.c b/drivers/net/ethernet/mellanox/mlx5/core/mr.c index 9d735c343a3b..678f0be81375 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mr.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/mr.c @@ -32,6 +32,7 @@ #include <linux/kernel.h> #include <linux/mlx5/driver.h> +#include <linux/mlx5/qp.h> #include "mlx5_core.h" int mlx5_core_create_mkey(struct mlx5_core_dev *dev, u32 *mkey, u32 *in, @@ -122,3 +123,23 @@ int mlx5_core_destroy_psv(struct mlx5_core_dev *dev, int psv_num) return mlx5_cmd_exec_in(dev, destroy_psv, in); } EXPORT_SYMBOL(mlx5_core_destroy_psv); + +__be32 mlx5_core_get_terminate_scatter_list_mkey(struct mlx5_core_dev *dev) +{ + u32 out[MLX5_ST_SZ_DW(query_special_contexts_out)] = {}; + u32 in[MLX5_ST_SZ_DW(query_special_contexts_in)] = {}; + u32 mkey; + + if (!MLX5_CAP_GEN(dev, terminate_scatter_list_mkey)) + return MLX5_TERMINATE_SCATTER_LIST_LKEY; + + MLX5_SET(query_special_contexts_in, in, opcode, + MLX5_CMD_OP_QUERY_SPECIAL_CONTEXTS); + if (mlx5_cmd_exec_inout(dev, query_special_contexts, in, out)) + return MLX5_TERMINATE_SCATTER_LIST_LKEY; + + mkey = MLX5_GET(query_special_contexts_out, out, + terminate_scatter_list_mkey); + return cpu_to_be32(mkey); +} +EXPORT_SYMBOL(mlx5_core_get_terminate_scatter_list_mkey); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c index 2245d3b2f393..843da89a9035 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c @@ -32,6 +32,7 @@ struct mlx5_irq { struct mlx5_irq_pool *pool; int refcount; struct msi_map map; + u32 pool_index; }; struct mlx5_irq_table { @@ -132,7 +133,7 @@ static void irq_release(struct mlx5_irq *irq) struct cpu_rmap *rmap; #endif - xa_erase(&pool->irqs, irq->map.index); + xa_erase(&pool->irqs, irq->pool_index); /* free_irq requires that affinity_hint and rmap will be cleared before * calling it. To satisfy this requirement, we call * irq_cpu_rmap_remove() to remove the notifier @@ -140,7 +141,7 @@ static void irq_release(struct mlx5_irq *irq) irq_update_affinity_hint(irq->map.virq, NULL); #ifdef CONFIG_RFS_ACCEL rmap = mlx5_eq_table_get_rmap(pool->dev); - if (rmap && irq->map.index) + if (rmap) irq_cpu_rmap_remove(rmap, irq->map.virq); #endif @@ -231,12 +232,13 @@ struct mlx5_irq *mlx5_irq_alloc(struct mlx5_irq_pool *pool, int i, if (!irq) return ERR_PTR(-ENOMEM); if (!i || !pci_msix_can_alloc_dyn(dev->pdev)) { - /* The vector at index 0 was already allocated. - * Just get the irq number. If dynamic irq is not supported - * vectors have also been allocated. + /* The vector at index 0 is always statically allocated. If + * dynamic irq is not supported all vectors are statically + * allocated. In both cases just get the irq number and set + * the index. */ irq->map.virq = pci_irq_vector(dev->pdev, i); - irq->map.index = 0; + irq->map.index = i; } else { irq->map = pci_msix_alloc_irq_at(dev->pdev, MSI_ANY_INDEX, af_desc); if (!irq->map.virq) { @@ -276,11 +278,11 @@ struct mlx5_irq *mlx5_irq_alloc(struct mlx5_irq_pool *pool, int i, } irq->pool = pool; irq->refcount = 1; - irq->map.index = i; - err = xa_err(xa_store(&pool->irqs, irq->map.index, irq, GFP_KERNEL)); + irq->pool_index = i; + err = xa_err(xa_store(&pool->irqs, irq->pool_index, irq, GFP_KERNEL)); if (err) { mlx5_core_err(dev, "Failed to alloc xa entry for irq(%u). err = %d\n", - irq->map.index, err); + irq->pool_index, err); goto err_xa; } return irq; @@ -567,13 +569,13 @@ int mlx5_irqs_request_vectors(struct mlx5_core_dev *dev, u16 *cpus, int nirqs, struct mlx5_irq *irq; int i; - af_desc.is_managed = 1; + af_desc.is_managed = false; for (i = 0; i < nirqs; i++) { + cpumask_clear(&af_desc.mask); cpumask_set_cpu(cpus[i], &af_desc.mask); irq = mlx5_irq_request(dev, i + 1, &af_desc, rmap); if (IS_ERR(irq)) break; - cpumask_clear(&af_desc.mask); irqs[i] = irq; } @@ -691,6 +693,24 @@ static void irq_pools_destroy(struct mlx5_irq_table *table) irq_pool_free(table->pcif_pool); } +static void mlx5_irq_pool_free_irqs(struct mlx5_irq_pool *pool) +{ + struct mlx5_irq *irq; + unsigned long index; + + xa_for_each(&pool->irqs, index, irq) + free_irq(irq->map.virq, &irq->nh); +} + +static void mlx5_irq_pools_free_irqs(struct mlx5_irq_table *table) +{ + if (table->sf_ctrl_pool) { + mlx5_irq_pool_free_irqs(table->sf_comp_pool); + mlx5_irq_pool_free_irqs(table->sf_ctrl_pool); + } + mlx5_irq_pool_free_irqs(table->pcif_pool); +} + /* irq_table API */ int mlx5_irq_table_init(struct mlx5_core_dev *dev) @@ -774,6 +794,17 @@ void mlx5_irq_table_destroy(struct mlx5_core_dev *dev) pci_free_irq_vectors(dev->pdev); } +void mlx5_irq_table_free_irqs(struct mlx5_core_dev *dev) +{ + struct mlx5_irq_table *table = dev->priv.irq_table; + + if (mlx5_core_is_sf(dev)) + return; + + mlx5_irq_pools_free_irqs(table); + pci_free_irq_vectors(dev->pdev); +} + int mlx5_irq_table_get_sfs_vec(struct mlx5_irq_table *table) { if (table->sf_comp_pool) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c index e2f26d0bc615..0692363cf80e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c @@ -63,6 +63,7 @@ static void mlx5_sf_dev_remove(struct auxiliary_device *adev) struct mlx5_sf_dev *sf_dev = container_of(adev, struct mlx5_sf_dev, adev); struct devlink *devlink = priv_to_devlink(sf_dev->mdev); + mlx5_drain_health_wq(sf_dev->mdev); devlink_unregister(devlink); mlx5_uninit_one(sf_dev->mdev); iounmap(sf_dev->mdev->iseg); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c index 3835ba3f4dda..1aa525e509f1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c @@ -117,6 +117,8 @@ int mlx5dr_cmd_query_device(struct mlx5_core_dev *mdev, caps->gvmi = MLX5_CAP_GEN(mdev, vhca_id); caps->flex_protocols = MLX5_CAP_GEN(mdev, flex_parser_protocols); caps->sw_format_ver = MLX5_CAP_GEN(mdev, steering_format_version); + caps->roce_caps.fl_rc_qp_when_roce_disabled = + MLX5_CAP_GEN(mdev, fl_rc_qp_when_roce_disabled); if (MLX5_CAP_GEN(mdev, roce)) { err = dr_cmd_query_nic_vport_roce_en(mdev, 0, &roce_en); @@ -124,7 +126,7 @@ int mlx5dr_cmd_query_device(struct mlx5_core_dev *mdev, return err; caps->roce_caps.roce_en = roce_en; - caps->roce_caps.fl_rc_qp_when_roce_disabled = + caps->roce_caps.fl_rc_qp_when_roce_disabled |= MLX5_CAP_ROCE(mdev, fl_rc_qp_when_roce_disabled); caps->roce_caps.fl_rc_qp_when_roce_enabled = MLX5_CAP_ROCE(mdev, fl_rc_qp_when_roce_enabled); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ptrn.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ptrn.c index 13e06a6a6b22..d6947fe13d56 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ptrn.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ptrn.c @@ -213,6 +213,8 @@ struct mlx5dr_ptrn_mgr *mlx5dr_ptrn_mgr_create(struct mlx5dr_domain *dmn) } INIT_LIST_HEAD(&mgr->ptrn_list); + mutex_init(&mgr->modify_hdr_mutex); + return mgr; free_mgr: @@ -237,5 +239,6 @@ void mlx5dr_ptrn_mgr_destroy(struct mlx5dr_ptrn_mgr *mgr) } mlx5dr_icm_pool_destroy(mgr->ptrn_icm_pool); + mutex_destroy(&mgr->modify_hdr_mutex); kfree(mgr); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c index 9413aaf51251..e94fbb015efa 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c @@ -15,7 +15,8 @@ static u32 dr_ste_crc32_calc(const void *input_data, size_t length) { u32 crc = crc32(0, input_data, length); - return (__force u32)htonl(crc); + return (__force u32)((crc >> 24) & 0xff) | ((crc << 8) & 0xff0000) | + ((crc >> 8) & 0xff00) | ((crc << 24) & 0xff000000); } bool mlx5dr_ste_supp_ttl_cs_recalc(struct mlx5dr_cmd_caps *caps) diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c index afa3b92a6905..0d5a41a2ae01 100644 --- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c @@ -245,12 +245,6 @@ static bool mlxbf_gige_rx_packet(struct mlxbf_gige *priv, int *rx_pkts) skb = priv->rx_skb[rx_pi_rem]; - skb_put(skb, datalen); - - skb->ip_summed = CHECKSUM_NONE; /* device did not checksum packet */ - - skb->protocol = eth_type_trans(skb, netdev); - /* Alloc another RX SKB for this same index */ rx_skb = mlxbf_gige_alloc_skb(priv, MLXBF_GIGE_DEFAULT_BUF_SZ, &rx_buf_dma, DMA_FROM_DEVICE); @@ -259,6 +253,13 @@ static bool mlxbf_gige_rx_packet(struct mlxbf_gige *priv, int *rx_pkts) priv->rx_skb[rx_pi_rem] = rx_skb; dma_unmap_single(priv->dev, *rx_wqe_addr, MLXBF_GIGE_DEFAULT_BUF_SZ, DMA_FROM_DEVICE); + + skb_put(skb, datalen); + + skb->ip_summed = CHECKSUM_NONE; /* device did not checksum packet */ + + skb->protocol = eth_type_trans(skb, netdev); + *rx_wqe_addr = rx_buf_dma; } else if (rx_cqe & MLXBF_GIGE_RX_CQE_PKT_STATUS_MAC_ERR) { priv->stats.rx_mac_errors++; diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c index 2b6e046e1d10..ee2698698d71 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c @@ -1039,6 +1039,16 @@ static int lan966x_reset_switch(struct lan966x *lan966x) reset_control_reset(switch_reset); + /* Don't reinitialize the switch core, if it is already initialized. In + * case it is initialized twice, some pointers inside the queue system + * in HW will get corrupted and then after a while the queue system gets + * full and no traffic is passing through the switch. The issue is seen + * when loading and unloading the driver and sending traffic through the + * switch. + */ + if (lan_rd(lan966x, SYS_RESET_CFG) & SYS_RESET_CFG_CORE_ENA) + return 0; + lan_wr(SYS_RESET_CFG_CORE_ENA_SET(0), lan966x, SYS_RESET_CFG); lan_wr(SYS_RAM_INIT_RAM_INIT_SET(1), lan966x, SYS_RAM_INIT); ret = readx_poll_timeout(lan966x_ram_init, lan966x, diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index 06d6292e09b3..d907727c7b7a 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -1279,8 +1279,6 @@ static void mana_poll_tx_cq(struct mana_cq *cq) if (comp_read < 1) return; - apc->eth_stats.tx_cqes = comp_read; - for (i = 0; i < comp_read; i++) { struct mana_tx_comp_oob *cqe_oob; @@ -1363,8 +1361,6 @@ static void mana_poll_tx_cq(struct mana_cq *cq) WARN_ON_ONCE(1); cq->work_done = pkt_transmitted; - - apc->eth_stats.tx_cqes -= pkt_transmitted; } static void mana_post_pkt_rxq(struct mana_rxq *rxq) @@ -1626,15 +1622,11 @@ static void mana_poll_rx_cq(struct mana_cq *cq) { struct gdma_comp *comp = cq->gdma_comp_buf; struct mana_rxq *rxq = cq->rxq; - struct mana_port_context *apc; int comp_read, i; - apc = netdev_priv(rxq->ndev); - comp_read = mana_gd_poll_cq(cq->gdma_cq, comp, CQE_POLLING_BUFFER); WARN_ON_ONCE(comp_read > CQE_POLLING_BUFFER); - apc->eth_stats.rx_cqes = comp_read; rxq->xdp_flush = false; for (i = 0; i < comp_read; i++) { @@ -1646,8 +1638,6 @@ static void mana_poll_rx_cq(struct mana_cq *cq) return; mana_process_rx_cqe(rxq, cq, &comp[i]); - - apc->eth_stats.rx_cqes--; } if (rxq->xdp_flush) diff --git a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c index a64c81410dc1..0dc78679f620 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c +++ b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c @@ -13,11 +13,9 @@ static const struct { } mana_eth_stats[] = { {"stop_queue", offsetof(struct mana_ethtool_stats, stop_queue)}, {"wake_queue", offsetof(struct mana_ethtool_stats, wake_queue)}, - {"tx_cqes", offsetof(struct mana_ethtool_stats, tx_cqes)}, {"tx_cq_err", offsetof(struct mana_ethtool_stats, tx_cqe_err)}, {"tx_cqe_unknown_type", offsetof(struct mana_ethtool_stats, tx_cqe_unknown_type)}, - {"rx_cqes", offsetof(struct mana_ethtool_stats, rx_cqes)}, {"rx_coalesced_err", offsetof(struct mana_ethtool_stats, rx_coalesced_err)}, {"rx_cqe_unknown_type", offsetof(struct mana_ethtool_stats, diff --git a/drivers/net/ethernet/nvidia/forcedeth.c b/drivers/net/ethernet/nvidia/forcedeth.c index 0605d1ee490d..7a549b834e97 100644 --- a/drivers/net/ethernet/nvidia/forcedeth.c +++ b/drivers/net/ethernet/nvidia/forcedeth.c @@ -6138,6 +6138,7 @@ static int nv_probe(struct pci_dev *pci_dev, const struct pci_device_id *id) return 0; out_error: + nv_mgmt_release_sema(dev); if (phystate_orig) writel(phystate|NVREG_ADAPTCTL_RUNNING, base + NvRegAdapterControl); out_freering: diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c index 2edd6bf64a3c..7776d3bdd459 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c @@ -1903,7 +1903,7 @@ void qed_get_vport_stats(struct qed_dev *cdev, struct qed_eth_stats *stats) { u32 i; - if (!cdev) { + if (!cdev || cdev->recov_in_prog) { memset(stats, 0, sizeof(*stats)); return; } diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h index f9931ecb7baa..4d83ceebdc49 100644 --- a/drivers/net/ethernet/qlogic/qede/qede.h +++ b/drivers/net/ethernet/qlogic/qede/qede.h @@ -269,6 +269,10 @@ struct qede_dev { #define QEDE_ERR_WARN 3 struct qede_dump_info dump_info; + struct delayed_work periodic_task; + unsigned long stats_coal_ticks; + u32 stats_coal_usecs; + spinlock_t stats_lock; /* lock for vport stats access */ }; enum QEDE_STATE { diff --git a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c index 374a86b875a3..95820cf1cd6c 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c +++ b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c @@ -429,6 +429,8 @@ static void qede_get_ethtool_stats(struct net_device *dev, } } + spin_lock(&edev->stats_lock); + for (i = 0; i < QEDE_NUM_STATS; i++) { if (qede_is_irrelevant_stat(edev, i)) continue; @@ -438,6 +440,8 @@ static void qede_get_ethtool_stats(struct net_device *dev, buf++; } + spin_unlock(&edev->stats_lock); + __qede_unlock(edev); } @@ -829,6 +833,7 @@ out: coal->rx_coalesce_usecs = rx_coal; coal->tx_coalesce_usecs = tx_coal; + coal->stats_block_coalesce_usecs = edev->stats_coal_usecs; return rc; } @@ -842,6 +847,19 @@ int qede_set_coalesce(struct net_device *dev, struct ethtool_coalesce *coal, int i, rc = 0; u16 rxc, txc; + if (edev->stats_coal_usecs != coal->stats_block_coalesce_usecs) { + edev->stats_coal_usecs = coal->stats_block_coalesce_usecs; + if (edev->stats_coal_usecs) { + edev->stats_coal_ticks = usecs_to_jiffies(edev->stats_coal_usecs); + schedule_delayed_work(&edev->periodic_task, 0); + + DP_INFO(edev, "Configured stats coal ticks=%lu jiffies\n", + edev->stats_coal_ticks); + } else { + cancel_delayed_work_sync(&edev->periodic_task); + } + } + if (!netif_running(dev)) { DP_INFO(edev, "Interface is down\n"); return -EINVAL; @@ -2252,7 +2270,8 @@ out: } static const struct ethtool_ops qede_ethtool_ops = { - .supported_coalesce_params = ETHTOOL_COALESCE_USECS, + .supported_coalesce_params = ETHTOOL_COALESCE_USECS | + ETHTOOL_COALESCE_STATS_BLOCK_USECS, .get_link_ksettings = qede_get_link_ksettings, .set_link_ksettings = qede_set_link_ksettings, .get_drvinfo = qede_get_drvinfo, @@ -2303,7 +2322,8 @@ static const struct ethtool_ops qede_ethtool_ops = { }; static const struct ethtool_ops qede_vf_ethtool_ops = { - .supported_coalesce_params = ETHTOOL_COALESCE_USECS, + .supported_coalesce_params = ETHTOOL_COALESCE_USECS | + ETHTOOL_COALESCE_STATS_BLOCK_USECS, .get_link_ksettings = qede_get_link_ksettings, .get_drvinfo = qede_get_drvinfo, .get_msglevel = qede_get_msglevel, diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index 4c6c685820e3..4b004a728190 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -307,6 +307,8 @@ void qede_fill_by_demand_stats(struct qede_dev *edev) edev->ops->get_vport_stats(edev->cdev, &stats); + spin_lock(&edev->stats_lock); + p_common->no_buff_discards = stats.common.no_buff_discards; p_common->packet_too_big_discard = stats.common.packet_too_big_discard; p_common->ttl0_discard = stats.common.ttl0_discard; @@ -404,6 +406,8 @@ void qede_fill_by_demand_stats(struct qede_dev *edev) p_ah->tx_1519_to_max_byte_packets = stats.ah.tx_1519_to_max_byte_packets; } + + spin_unlock(&edev->stats_lock); } static void qede_get_stats64(struct net_device *dev, @@ -412,9 +416,10 @@ static void qede_get_stats64(struct net_device *dev, struct qede_dev *edev = netdev_priv(dev); struct qede_stats_common *p_common; - qede_fill_by_demand_stats(edev); p_common = &edev->stats.common; + spin_lock(&edev->stats_lock); + stats->rx_packets = p_common->rx_ucast_pkts + p_common->rx_mcast_pkts + p_common->rx_bcast_pkts; stats->tx_packets = p_common->tx_ucast_pkts + p_common->tx_mcast_pkts + @@ -434,6 +439,8 @@ static void qede_get_stats64(struct net_device *dev, stats->collisions = edev->stats.bb.tx_total_collisions; stats->rx_crc_errors = p_common->rx_crc_errors; stats->rx_frame_errors = p_common->rx_align_errors; + + spin_unlock(&edev->stats_lock); } #ifdef CONFIG_QED_SRIOV @@ -1063,6 +1070,23 @@ static void qede_unlock(struct qede_dev *edev) rtnl_unlock(); } +static void qede_periodic_task(struct work_struct *work) +{ + struct qede_dev *edev = container_of(work, struct qede_dev, + periodic_task.work); + + qede_fill_by_demand_stats(edev); + schedule_delayed_work(&edev->periodic_task, edev->stats_coal_ticks); +} + +static void qede_init_periodic_task(struct qede_dev *edev) +{ + INIT_DELAYED_WORK(&edev->periodic_task, qede_periodic_task); + spin_lock_init(&edev->stats_lock); + edev->stats_coal_usecs = USEC_PER_SEC; + edev->stats_coal_ticks = usecs_to_jiffies(USEC_PER_SEC); +} + static void qede_sp_task(struct work_struct *work) { struct qede_dev *edev = container_of(work, struct qede_dev, @@ -1082,6 +1106,7 @@ static void qede_sp_task(struct work_struct *work) */ if (test_and_clear_bit(QEDE_SP_RECOVERY, &edev->sp_flags)) { + cancel_delayed_work_sync(&edev->periodic_task); #ifdef CONFIG_QED_SRIOV /* SRIOV must be disabled outside the lock to avoid a deadlock. * The recovery of the active VFs is currently not supported. @@ -1272,6 +1297,7 @@ static int __qede_probe(struct pci_dev *pdev, u32 dp_module, u8 dp_level, */ INIT_DELAYED_WORK(&edev->sp_task, qede_sp_task); mutex_init(&edev->qede_lock); + qede_init_periodic_task(edev); rc = register_netdev(edev->ndev); if (rc) { @@ -1296,6 +1322,11 @@ static int __qede_probe(struct pci_dev *pdev, u32 dp_module, u8 dp_level, edev->rx_copybreak = QEDE_RX_HDR_SIZE; qede_log_probe(edev); + + /* retain user config (for example - after recovery) */ + if (edev->stats_coal_usecs) + schedule_delayed_work(&edev->periodic_task, 0); + return 0; err4: @@ -1364,6 +1395,7 @@ static void __qede_remove(struct pci_dev *pdev, enum qede_remove_mode mode) unregister_netdev(ndev); cancel_delayed_work_sync(&edev->sp_task); + cancel_delayed_work_sync(&edev->periodic_task); edev->ops->common->set_power_state(cdev, PCI_D0); diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index a7e376e7e689..4b19803a7dd0 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -616,10 +616,10 @@ struct rtl8169_private { struct work_struct work; } wk; - spinlock_t config25_lock; - spinlock_t mac_ocp_lock; + raw_spinlock_t config25_lock; + raw_spinlock_t mac_ocp_lock; - spinlock_t cfg9346_usage_lock; + raw_spinlock_t cfg9346_usage_lock; int cfg9346_usage_count; unsigned supports_gmii:1; @@ -671,20 +671,20 @@ static void rtl_lock_config_regs(struct rtl8169_private *tp) { unsigned long flags; - spin_lock_irqsave(&tp->cfg9346_usage_lock, flags); + raw_spin_lock_irqsave(&tp->cfg9346_usage_lock, flags); if (!--tp->cfg9346_usage_count) RTL_W8(tp, Cfg9346, Cfg9346_Lock); - spin_unlock_irqrestore(&tp->cfg9346_usage_lock, flags); + raw_spin_unlock_irqrestore(&tp->cfg9346_usage_lock, flags); } static void rtl_unlock_config_regs(struct rtl8169_private *tp) { unsigned long flags; - spin_lock_irqsave(&tp->cfg9346_usage_lock, flags); + raw_spin_lock_irqsave(&tp->cfg9346_usage_lock, flags); if (!tp->cfg9346_usage_count++) RTL_W8(tp, Cfg9346, Cfg9346_Unlock); - spin_unlock_irqrestore(&tp->cfg9346_usage_lock, flags); + raw_spin_unlock_irqrestore(&tp->cfg9346_usage_lock, flags); } static void rtl_pci_commit(struct rtl8169_private *tp) @@ -698,10 +698,10 @@ static void rtl_mod_config2(struct rtl8169_private *tp, u8 clear, u8 set) unsigned long flags; u8 val; - spin_lock_irqsave(&tp->config25_lock, flags); + raw_spin_lock_irqsave(&tp->config25_lock, flags); val = RTL_R8(tp, Config2); RTL_W8(tp, Config2, (val & ~clear) | set); - spin_unlock_irqrestore(&tp->config25_lock, flags); + raw_spin_unlock_irqrestore(&tp->config25_lock, flags); } static void rtl_mod_config5(struct rtl8169_private *tp, u8 clear, u8 set) @@ -709,10 +709,10 @@ static void rtl_mod_config5(struct rtl8169_private *tp, u8 clear, u8 set) unsigned long flags; u8 val; - spin_lock_irqsave(&tp->config25_lock, flags); + raw_spin_lock_irqsave(&tp->config25_lock, flags); val = RTL_R8(tp, Config5); RTL_W8(tp, Config5, (val & ~clear) | set); - spin_unlock_irqrestore(&tp->config25_lock, flags); + raw_spin_unlock_irqrestore(&tp->config25_lock, flags); } static bool rtl_is_8125(struct rtl8169_private *tp) @@ -899,9 +899,9 @@ static void r8168_mac_ocp_write(struct rtl8169_private *tp, u32 reg, u32 data) { unsigned long flags; - spin_lock_irqsave(&tp->mac_ocp_lock, flags); + raw_spin_lock_irqsave(&tp->mac_ocp_lock, flags); __r8168_mac_ocp_write(tp, reg, data); - spin_unlock_irqrestore(&tp->mac_ocp_lock, flags); + raw_spin_unlock_irqrestore(&tp->mac_ocp_lock, flags); } static u16 __r8168_mac_ocp_read(struct rtl8169_private *tp, u32 reg) @@ -919,9 +919,9 @@ static u16 r8168_mac_ocp_read(struct rtl8169_private *tp, u32 reg) unsigned long flags; u16 val; - spin_lock_irqsave(&tp->mac_ocp_lock, flags); + raw_spin_lock_irqsave(&tp->mac_ocp_lock, flags); val = __r8168_mac_ocp_read(tp, reg); - spin_unlock_irqrestore(&tp->mac_ocp_lock, flags); + raw_spin_unlock_irqrestore(&tp->mac_ocp_lock, flags); return val; } @@ -932,10 +932,10 @@ static void r8168_mac_ocp_modify(struct rtl8169_private *tp, u32 reg, u16 mask, unsigned long flags; u16 data; - spin_lock_irqsave(&tp->mac_ocp_lock, flags); + raw_spin_lock_irqsave(&tp->mac_ocp_lock, flags); data = __r8168_mac_ocp_read(tp, reg); __r8168_mac_ocp_write(tp, reg, (data & ~mask) | set); - spin_unlock_irqrestore(&tp->mac_ocp_lock, flags); + raw_spin_unlock_irqrestore(&tp->mac_ocp_lock, flags); } /* Work around a hw issue with RTL8168g PHY, the quirk disables @@ -1420,14 +1420,14 @@ static void __rtl8169_set_wol(struct rtl8169_private *tp, u32 wolopts) r8168_mac_ocp_modify(tp, 0xc0b6, BIT(0), 0); } - spin_lock_irqsave(&tp->config25_lock, flags); + raw_spin_lock_irqsave(&tp->config25_lock, flags); for (i = 0; i < tmp; i++) { options = RTL_R8(tp, cfg[i].reg) & ~cfg[i].mask; if (wolopts & cfg[i].opt) options |= cfg[i].mask; RTL_W8(tp, cfg[i].reg, options); } - spin_unlock_irqrestore(&tp->config25_lock, flags); + raw_spin_unlock_irqrestore(&tp->config25_lock, flags); switch (tp->mac_version) { case RTL_GIGA_MAC_VER_02 ... RTL_GIGA_MAC_VER_06: @@ -5179,9 +5179,9 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) tp->eee_adv = -1; tp->ocp_base = OCP_STD_PHY_BASE; - spin_lock_init(&tp->cfg9346_usage_lock); - spin_lock_init(&tp->config25_lock); - spin_lock_init(&tp->mac_ocp_lock); + raw_spin_lock_init(&tp->cfg9346_usage_lock); + raw_spin_lock_init(&tp->config25_lock); + raw_spin_lock_init(&tp->mac_ocp_lock); dev->tstats = devm_netdev_alloc_pcpu_stats(&pdev->dev, struct pcpu_sw_netstats); diff --git a/drivers/net/ethernet/renesas/rswitch.c b/drivers/net/ethernet/renesas/rswitch.c index 29afaddb598d..aace87139cea 100644 --- a/drivers/net/ethernet/renesas/rswitch.c +++ b/drivers/net/ethernet/renesas/rswitch.c @@ -1485,7 +1485,7 @@ static netdev_tx_t rswitch_start_xmit(struct sk_buff *skb, struct net_device *nd if (rswitch_get_num_cur_queues(gq) >= gq->ring_size - 1) { netif_stop_subqueue(ndev, 0); - return ret; + return NETDEV_TX_BUSY; } if (skb_put_padto(skb, ETH_ZLEN)) diff --git a/drivers/net/ethernet/sfc/tc.c b/drivers/net/ethernet/sfc/tc.c index 0327639a628a..c004443c1d58 100644 --- a/drivers/net/ethernet/sfc/tc.c +++ b/drivers/net/ethernet/sfc/tc.c @@ -624,13 +624,12 @@ static int efx_tc_flower_replace_foreign(struct efx_nic *efx, if (!found) { /* We don't care. */ netif_dbg(efx, drv, efx->net_dev, "Ignoring foreign filter that doesn't egdev us\n"); - rc = -EOPNOTSUPP; - goto release; + return -EOPNOTSUPP; } rc = efx_mae_match_check_caps(efx, &match.mask, NULL); if (rc) - goto release; + return rc; if (efx_tc_match_is_encap(&match.mask)) { enum efx_encap_type type; @@ -639,8 +638,7 @@ static int efx_tc_flower_replace_foreign(struct efx_nic *efx, if (type == EFX_ENCAP_TYPE_NONE) { NL_SET_ERR_MSG_MOD(extack, "Egress encap match on unsupported tunnel device"); - rc = -EOPNOTSUPP; - goto release; + return -EOPNOTSUPP; } rc = efx_mae_check_encap_type_supported(efx, type); @@ -648,25 +646,24 @@ static int efx_tc_flower_replace_foreign(struct efx_nic *efx, NL_SET_ERR_MSG_FMT_MOD(extack, "Firmware reports no support for %s encap match", efx_tc_encap_type_name(type)); - goto release; + return rc; } rc = efx_tc_flower_record_encap_match(efx, &match, type, extack); if (rc) - goto release; + return rc; } else { /* This is not a tunnel decap rule, ignore it */ netif_dbg(efx, drv, efx->net_dev, "Ignoring foreign filter without encap match\n"); - rc = -EOPNOTSUPP; - goto release; + return -EOPNOTSUPP; } rule = kzalloc(sizeof(*rule), GFP_USER); if (!rule) { rc = -ENOMEM; - goto release; + goto out_free; } INIT_LIST_HEAD(&rule->acts.list); rule->cookie = tc->cookie; @@ -678,7 +675,7 @@ static int efx_tc_flower_replace_foreign(struct efx_nic *efx, "Ignoring already-offloaded rule (cookie %lx)\n", tc->cookie); rc = -EEXIST; - goto release; + goto out_free; } act = kzalloc(sizeof(*act), GFP_USER); @@ -843,6 +840,7 @@ release: efx_tc_match_action_ht_params); efx_tc_free_action_set_list(efx, &rule->acts, false); } +out_free: kfree(rule); if (match.encap) efx_tc_flower_release_encap_match(efx, match.encap); @@ -899,8 +897,7 @@ static int efx_tc_flower_replace(struct efx_nic *efx, return rc; if (efx_tc_match_is_encap(&match.mask)) { NL_SET_ERR_MSG_MOD(extack, "Ingress enc_key matches not supported"); - rc = -EOPNOTSUPP; - goto release; + return -EOPNOTSUPP; } if (tc->common.chain_index) { @@ -924,9 +921,9 @@ static int efx_tc_flower_replace(struct efx_nic *efx, if (old) { netif_dbg(efx, drv, efx->net_dev, "Already offloaded rule (cookie %lx)\n", tc->cookie); - rc = -EEXIST; NL_SET_ERR_MSG_MOD(extack, "Rule already offloaded"); - goto release; + kfree(rule); + return -EEXIST; } /* Parse actions */ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c index 16a8c361283b..f07905f00f98 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c @@ -644,7 +644,8 @@ static int qcom_ethqos_probe(struct platform_device *pdev) plat_dat->fix_mac_speed = ethqos_fix_mac_speed; plat_dat->dump_debug_regs = rgmii_dump; plat_dat->has_gmac4 = 1; - plat_dat->dwmac4_addrs = &data->dwmac4_addrs; + if (ethqos->has_emac3) + plat_dat->dwmac4_addrs = &data->dwmac4_addrs; plat_dat->pmt = 1; plat_dat->tso_en = of_property_read_bool(np, "snps,tso"); if (of_device_is_compatible(np, "qcom,qcs404-ethqos")) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 0fca81507a77..52cab9de05f2 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -7233,8 +7233,7 @@ int stmmac_dvr_probe(struct device *device, ndev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM; ndev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | - NETDEV_XDP_ACT_XSK_ZEROCOPY | - NETDEV_XDP_ACT_NDO_XMIT; + NETDEV_XDP_ACT_XSK_ZEROCOPY; ret = stmmac_tc_init(priv, priv); if (!ret) { diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_xdp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_xdp.c index 9d4d8c3dad0a..aa6f16d3df64 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_xdp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_xdp.c @@ -117,6 +117,9 @@ int stmmac_xdp_set_prog(struct stmmac_priv *priv, struct bpf_prog *prog, return -EOPNOTSUPP; } + if (!prog) + xdp_features_clear_redirect_target(dev); + need_update = !!priv->xdp_prog != !!prog; if (if_running && need_update) stmmac_xdp_release(dev); @@ -131,5 +134,8 @@ int stmmac_xdp_set_prog(struct stmmac_priv *priv, struct bpf_prog *prog, if (if_running && need_update) stmmac_xdp_open(dev); + if (prog) + xdp_features_set_redirect_target(dev, false); + return 0; } diff --git a/drivers/net/ipa/ipa_endpoint.c b/drivers/net/ipa/ipa_endpoint.c index 2ee80ed140b7..afa1d56d9095 100644 --- a/drivers/net/ipa/ipa_endpoint.c +++ b/drivers/net/ipa/ipa_endpoint.c @@ -119,7 +119,7 @@ enum ipa_status_field_id { }; /* Size in bytes of an IPA packet status structure */ -#define IPA_STATUS_SIZE sizeof(__le32[4]) +#define IPA_STATUS_SIZE sizeof(__le32[8]) /* IPA status structure decoder; looks up field values for a structure */ static u32 ipa_status_extract(struct ipa *ipa, const void *data, diff --git a/drivers/net/phy/mscc/mscc.h b/drivers/net/phy/mscc/mscc.h index a50235fdf7d9..defe5cc6d4fc 100644 --- a/drivers/net/phy/mscc/mscc.h +++ b/drivers/net/phy/mscc/mscc.h @@ -179,6 +179,7 @@ enum rgmii_clock_delay { #define VSC8502_RGMII_CNTL 20 #define VSC8502_RGMII_RX_DELAY_MASK 0x0070 #define VSC8502_RGMII_TX_DELAY_MASK 0x0007 +#define VSC8502_RGMII_RX_CLK_DISABLE 0x0800 #define MSCC_PHY_WOL_LOWER_MAC_ADDR 21 #define MSCC_PHY_WOL_MID_MAC_ADDR 22 @@ -276,6 +277,7 @@ enum rgmii_clock_delay { /* Microsemi PHY ID's * Code assumes lowest nibble is 0 */ +#define PHY_ID_VSC8501 0x00070530 #define PHY_ID_VSC8502 0x00070630 #define PHY_ID_VSC8504 0x000704c0 #define PHY_ID_VSC8514 0x00070670 diff --git a/drivers/net/phy/mscc/mscc_main.c b/drivers/net/phy/mscc/mscc_main.c index 62bf99e45af1..28df8a2e4230 100644 --- a/drivers/net/phy/mscc/mscc_main.c +++ b/drivers/net/phy/mscc/mscc_main.c @@ -519,16 +519,27 @@ out_unlock: * * 2.0 ns (which causes the data to be sampled at exactly half way between * clock transitions at 1000 Mbps) if delays should be enabled */ -static int vsc85xx_rgmii_set_skews(struct phy_device *phydev, u32 rgmii_cntl, - u16 rgmii_rx_delay_mask, - u16 rgmii_tx_delay_mask) +static int vsc85xx_update_rgmii_cntl(struct phy_device *phydev, u32 rgmii_cntl, + u16 rgmii_rx_delay_mask, + u16 rgmii_tx_delay_mask) { u16 rgmii_rx_delay_pos = ffs(rgmii_rx_delay_mask) - 1; u16 rgmii_tx_delay_pos = ffs(rgmii_tx_delay_mask) - 1; u16 reg_val = 0; - int rc; + u16 mask = 0; + int rc = 0; - mutex_lock(&phydev->lock); + /* For traffic to pass, the VSC8502 family needs the RX_CLK disable bit + * to be unset for all PHY modes, so do that as part of the paged + * register modification. + * For some family members (like VSC8530/31/40/41) this bit is reserved + * and read-only, and the RX clock is enabled by default. + */ + if (rgmii_cntl == VSC8502_RGMII_CNTL) + mask |= VSC8502_RGMII_RX_CLK_DISABLE; + + if (phy_interface_is_rgmii(phydev)) + mask |= rgmii_rx_delay_mask | rgmii_tx_delay_mask; if (phydev->interface == PHY_INTERFACE_MODE_RGMII_RXID || phydev->interface == PHY_INTERFACE_MODE_RGMII_ID) @@ -537,31 +548,20 @@ static int vsc85xx_rgmii_set_skews(struct phy_device *phydev, u32 rgmii_cntl, phydev->interface == PHY_INTERFACE_MODE_RGMII_ID) reg_val |= RGMII_CLK_DELAY_2_0_NS << rgmii_tx_delay_pos; - rc = phy_modify_paged(phydev, MSCC_PHY_PAGE_EXTENDED_2, - rgmii_cntl, - rgmii_rx_delay_mask | rgmii_tx_delay_mask, - reg_val); - - mutex_unlock(&phydev->lock); + if (mask) + rc = phy_modify_paged(phydev, MSCC_PHY_PAGE_EXTENDED_2, + rgmii_cntl, mask, reg_val); return rc; } static int vsc85xx_default_config(struct phy_device *phydev) { - int rc; - phydev->mdix_ctrl = ETH_TP_MDI_AUTO; - if (phy_interface_mode_is_rgmii(phydev->interface)) { - rc = vsc85xx_rgmii_set_skews(phydev, VSC8502_RGMII_CNTL, - VSC8502_RGMII_RX_DELAY_MASK, - VSC8502_RGMII_TX_DELAY_MASK); - if (rc) - return rc; - } - - return 0; + return vsc85xx_update_rgmii_cntl(phydev, VSC8502_RGMII_CNTL, + VSC8502_RGMII_RX_DELAY_MASK, + VSC8502_RGMII_TX_DELAY_MASK); } static int vsc85xx_get_tunable(struct phy_device *phydev, @@ -1758,13 +1758,11 @@ static int vsc8584_config_init(struct phy_device *phydev) if (ret) return ret; - if (phy_interface_is_rgmii(phydev)) { - ret = vsc85xx_rgmii_set_skews(phydev, VSC8572_RGMII_CNTL, - VSC8572_RGMII_RX_DELAY_MASK, - VSC8572_RGMII_TX_DELAY_MASK); - if (ret) - return ret; - } + ret = vsc85xx_update_rgmii_cntl(phydev, VSC8572_RGMII_CNTL, + VSC8572_RGMII_RX_DELAY_MASK, + VSC8572_RGMII_TX_DELAY_MASK); + if (ret) + return ret; ret = genphy_soft_reset(phydev); if (ret) @@ -2317,6 +2315,30 @@ static int vsc85xx_probe(struct phy_device *phydev) /* Microsemi VSC85xx PHYs */ static struct phy_driver vsc85xx_driver[] = { { + .phy_id = PHY_ID_VSC8501, + .name = "Microsemi GE VSC8501 SyncE", + .phy_id_mask = 0xfffffff0, + /* PHY_BASIC_FEATURES */ + .soft_reset = &genphy_soft_reset, + .config_init = &vsc85xx_config_init, + .config_aneg = &vsc85xx_config_aneg, + .read_status = &vsc85xx_read_status, + .handle_interrupt = vsc85xx_handle_interrupt, + .config_intr = &vsc85xx_config_intr, + .suspend = &genphy_suspend, + .resume = &genphy_resume, + .probe = &vsc85xx_probe, + .set_wol = &vsc85xx_wol_set, + .get_wol = &vsc85xx_wol_get, + .get_tunable = &vsc85xx_get_tunable, + .set_tunable = &vsc85xx_set_tunable, + .read_page = &vsc85xx_phy_read_page, + .write_page = &vsc85xx_phy_write_page, + .get_sset_count = &vsc85xx_get_sset_count, + .get_strings = &vsc85xx_get_strings, + .get_stats = &vsc85xx_get_stats, +}, +{ .phy_id = PHY_ID_VSC8502, .name = "Microsemi GE VSC8502 SyncE", .phy_id_mask = 0xfffffff0, @@ -2656,6 +2678,8 @@ static struct phy_driver vsc85xx_driver[] = { module_phy_driver(vsc85xx_driver); static struct mdio_device_id __maybe_unused vsc85xx_tbl[] = { + { PHY_ID_VSC8501, 0xfffffff0, }, + { PHY_ID_VSC8502, 0xfffffff0, }, { PHY_ID_VSC8504, 0xfffffff0, }, { PHY_ID_VSC8514, 0xfffffff0, }, { PHY_ID_VSC8530, 0xfffffff0, }, diff --git a/drivers/net/phy/mxl-gpy.c b/drivers/net/phy/mxl-gpy.c index 6301a9abfb95..ea1073adc5a1 100644 --- a/drivers/net/phy/mxl-gpy.c +++ b/drivers/net/phy/mxl-gpy.c @@ -274,13 +274,6 @@ static int gpy_config_init(struct phy_device *phydev) return ret < 0 ? ret : 0; } -static bool gpy_has_broken_mdint(struct phy_device *phydev) -{ - /* At least these PHYs are known to have broken interrupt handling */ - return phydev->drv->phy_id == PHY_ID_GPY215B || - phydev->drv->phy_id == PHY_ID_GPY215C; -} - static int gpy_probe(struct phy_device *phydev) { struct device *dev = &phydev->mdio.dev; @@ -300,8 +293,7 @@ static int gpy_probe(struct phy_device *phydev) phydev->priv = priv; mutex_init(&priv->mbox_lock); - if (gpy_has_broken_mdint(phydev) && - !device_property_present(dev, "maxlinear,use-broken-interrupts")) + if (!device_property_present(dev, "maxlinear,use-broken-interrupts")) phydev->dev_flags |= PHY_F_NO_IRQ; fw_version = phy_read(phydev, PHY_FWV); @@ -659,11 +651,9 @@ static irqreturn_t gpy_handle_interrupt(struct phy_device *phydev) * frame. Therefore, polling is the best we can do and won't do any more * harm. * It was observed that this bug happens on link state and link speed - * changes on a GPY215B and GYP215C independent of the firmware version - * (which doesn't mean that this list is exhaustive). + * changes independent of the firmware version. */ - if (gpy_has_broken_mdint(phydev) && - (reg & (PHY_IMASK_LSTC | PHY_IMASK_LSPC))) { + if (reg & (PHY_IMASK_LSTC | PHY_IMASK_LSPC)) { reg = gpy_mbox_read(phydev, REG_GPIO0_OUT); if (reg < 0) { phy_error(phydev); diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index e237949deee6..b4831110003c 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -2225,11 +2225,13 @@ int phylink_ethtool_ksettings_set(struct phylink *pl, ASSERT_RTNL(); - /* Mask out unsupported advertisements */ - linkmode_and(config.advertising, kset->link_modes.advertising, - pl->supported); - if (pl->phydev) { + struct ethtool_link_ksettings phy_kset = *kset; + + linkmode_and(phy_kset.link_modes.advertising, + phy_kset.link_modes.advertising, + pl->supported); + /* We can rely on phylib for this update; we also do not need * to update the pl->link_config settings: * - the configuration returned via ksettings_get() will come @@ -2248,10 +2250,13 @@ int phylink_ethtool_ksettings_set(struct phylink *pl, * the presence of a PHY, this should not be changed as that * should be determined from the media side advertisement. */ - return phy_ethtool_ksettings_set(pl->phydev, kset); + return phy_ethtool_ksettings_set(pl->phydev, &phy_kset); } config = pl->link_config; + /* Mask out unsupported advertisements */ + linkmode_and(config.advertising, kset->link_modes.advertising, + pl->supported); /* FIXME: should we reject autoneg if phy/mac does not support it? */ switch (kset->base.autoneg) { diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index d10606f257c4..555b0b1e9a78 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -1629,6 +1629,7 @@ static int team_init(struct net_device *dev) team->dev = dev; team_set_no_mode(team); + team->notifier_ctx = false; team->pcpu_stats = netdev_alloc_pcpu_stats(struct team_pcpu_stats); if (!team->pcpu_stats) @@ -3022,7 +3023,11 @@ static int team_device_event(struct notifier_block *unused, team_del_slave(port->team->dev, dev); break; case NETDEV_FEAT_CHANGE: - team_compute_features(port->team); + if (!port->team->notifier_ctx) { + port->team->notifier_ctx = true; + team_compute_features(port->team); + port->team->notifier_ctx = false; + } break; case NETDEV_PRECHANGEMTU: /* Forbid to change mtu of underlaying device */ diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 571e37e67f9c..f1865d047971 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1325,7 +1325,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x2001, 0x7e3d, 4)}, /* D-Link DWM-222 A2 */ {QMI_FIXED_INTF(0x2020, 0x2031, 4)}, /* Olicard 600 */ {QMI_FIXED_INTF(0x2020, 0x2033, 4)}, /* BroadMobi BM806U */ - {QMI_FIXED_INTF(0x2020, 0x2060, 4)}, /* BroadMobi BM818 */ + {QMI_QUIRK_SET_DTR(0x2020, 0x2060, 4)}, /* BroadMobi BM818 */ {QMI_FIXED_INTF(0x0f3d, 0x68a2, 8)}, /* Sierra Wireless MC7700 */ {QMI_FIXED_INTF(0x114f, 0x68a2, 8)}, /* Sierra Wireless MC7750 */ {QMI_FIXED_INTF(0x1199, 0x68a2, 8)}, /* Sierra Wireless MC7710 in QMI mode */ diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 56ca1d270304..486b5849033d 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -205,6 +205,8 @@ struct control_buf { __virtio16 vid; __virtio64 offloads; struct virtio_net_ctrl_rss rss; + struct virtio_net_ctrl_coal_tx coal_tx; + struct virtio_net_ctrl_coal_rx coal_rx; }; struct virtnet_info { @@ -2934,12 +2936,10 @@ static int virtnet_send_notf_coal_cmds(struct virtnet_info *vi, struct ethtool_coalesce *ec) { struct scatterlist sgs_tx, sgs_rx; - struct virtio_net_ctrl_coal_tx coal_tx; - struct virtio_net_ctrl_coal_rx coal_rx; - coal_tx.tx_usecs = cpu_to_le32(ec->tx_coalesce_usecs); - coal_tx.tx_max_packets = cpu_to_le32(ec->tx_max_coalesced_frames); - sg_init_one(&sgs_tx, &coal_tx, sizeof(coal_tx)); + vi->ctrl->coal_tx.tx_usecs = cpu_to_le32(ec->tx_coalesce_usecs); + vi->ctrl->coal_tx.tx_max_packets = cpu_to_le32(ec->tx_max_coalesced_frames); + sg_init_one(&sgs_tx, &vi->ctrl->coal_tx, sizeof(vi->ctrl->coal_tx)); if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_NOTF_COAL, VIRTIO_NET_CTRL_NOTF_COAL_TX_SET, @@ -2950,9 +2950,9 @@ static int virtnet_send_notf_coal_cmds(struct virtnet_info *vi, vi->tx_usecs = ec->tx_coalesce_usecs; vi->tx_max_packets = ec->tx_max_coalesced_frames; - coal_rx.rx_usecs = cpu_to_le32(ec->rx_coalesce_usecs); - coal_rx.rx_max_packets = cpu_to_le32(ec->rx_max_coalesced_frames); - sg_init_one(&sgs_rx, &coal_rx, sizeof(coal_rx)); + vi->ctrl->coal_rx.rx_usecs = cpu_to_le32(ec->rx_coalesce_usecs); + vi->ctrl->coal_rx.rx_max_packets = cpu_to_le32(ec->rx_max_coalesced_frames); + sg_init_one(&sgs_rx, &vi->ctrl->coal_rx, sizeof(vi->ctrl->coal_rx)); if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_NOTF_COAL, VIRTIO_NET_CTRL_NOTF_COAL_RX_SET, diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c index 37aa4676dc94..6d1007f24b4a 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c @@ -2732,17 +2732,13 @@ static bool iwl_mvm_wait_d3_notif(struct iwl_notif_wait_data *notif_wait, if (wowlan_info_ver < 2) { struct iwl_wowlan_info_notif_v1 *notif_v1 = (void *)pkt->data; - notif = kmemdup(notif_v1, - offsetofend(struct iwl_wowlan_info_notif, - received_beacons), - GFP_ATOMIC); - + notif = kmemdup(notif_v1, sizeof(*notif), GFP_ATOMIC); if (!notif) return false; notif->tid_tear_down = notif_v1->tid_tear_down; notif->station_id = notif_v1->station_id; - + memset_after(notif, 0, station_id); } else { notif = (void *)pkt->data; } diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mac.c b/drivers/net/wireless/mediatek/mt76/mt7615/mac.c index da1d17b73a25..64002484ccad 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/mac.c @@ -914,7 +914,10 @@ void mt7615_mac_sta_poll(struct mt7615_dev *dev) msta = list_first_entry(&sta_poll_list, struct mt7615_sta, poll_list); + + spin_lock_bh(&dev->sta_poll_lock); list_del_init(&msta->poll_list); + spin_unlock_bh(&dev->sta_poll_lock); addr = mt7615_mac_wtbl_addr(dev, msta->wcid.idx) + 19 * 4; diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c index 39a4a73ef8e6..9b0f6053e0fa 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c @@ -1004,10 +1004,10 @@ void mt7996_mac_write_txwi(struct mt7996_dev *dev, __le32 *txwi, { struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); struct ieee80211_vif *vif = info->control.vif; - struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv; u8 band_idx = (info->hw_queue & MT_TX_HW_QUEUE_PHY) >> 2; u8 p_fmt, q_idx, omac_idx = 0, wmm_idx = 0; bool is_8023 = info->flags & IEEE80211_TX_CTL_HW_80211_ENCAP; + struct mt7996_vif *mvif; u16 tx_count = 15; u32 val; bool beacon = !!(changed & (BSS_CHANGED_BEACON | @@ -1015,7 +1015,8 @@ void mt7996_mac_write_txwi(struct mt7996_dev *dev, __le32 *txwi, bool inband_disc = !!(changed & (BSS_CHANGED_UNSOL_BCAST_PROBE_RESP | BSS_CHANGED_FILS_DISCOVERY)); - if (vif) { + mvif = vif ? (struct mt7996_vif *)vif->drv_priv : NULL; + if (mvif) { omac_idx = mvif->mt76.omac_idx; wmm_idx = mvif->mt76.wmm_idx; band_idx = mvif->mt76.band_idx; @@ -1081,12 +1082,16 @@ void mt7996_mac_write_txwi(struct mt7996_dev *dev, __le32 *txwi, struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; bool mcast = ieee80211_is_data(hdr->frame_control) && is_multicast_ether_addr(hdr->addr1); - u8 idx = mvif->basic_rates_idx; + u8 idx = MT7996_BASIC_RATES_TBL; - if (mcast && mvif->mcast_rates_idx) - idx = mvif->mcast_rates_idx; - else if (beacon && mvif->beacon_rates_idx) - idx = mvif->beacon_rates_idx; + if (mvif) { + if (mcast && mvif->mcast_rates_idx) + idx = mvif->mcast_rates_idx; + else if (beacon && mvif->beacon_rates_idx) + idx = mvif->beacon_rates_idx; + else + idx = mvif->basic_rates_idx; + } txwi[6] |= cpu_to_le32(FIELD_PREP(MT_TXD6_TX_RATE, idx)); txwi[3] |= cpu_to_le32(MT_TXD3_BA_DISABLE); diff --git a/drivers/net/wireless/realtek/rtw88/mac80211.c b/drivers/net/wireless/realtek/rtw88/mac80211.c index a6c024cab7ee..144618bb94c8 100644 --- a/drivers/net/wireless/realtek/rtw88/mac80211.c +++ b/drivers/net/wireless/realtek/rtw88/mac80211.c @@ -88,15 +88,6 @@ static int rtw_ops_config(struct ieee80211_hw *hw, u32 changed) } } - if (changed & IEEE80211_CONF_CHANGE_PS) { - if (hw->conf.flags & IEEE80211_CONF_PS) { - rtwdev->ps_enabled = true; - } else { - rtwdev->ps_enabled = false; - rtw_leave_lps(rtwdev); - } - } - if (changed & IEEE80211_CONF_CHANGE_CHANNEL) rtw_set_channel(rtwdev); @@ -213,6 +204,7 @@ static int rtw_ops_add_interface(struct ieee80211_hw *hw, config |= PORT_SET_BCN_CTRL; rtw_vif_port_config(rtwdev, rtwvif, config); rtw_core_port_switch(rtwdev, vif); + rtw_recalc_lps(rtwdev, vif); mutex_unlock(&rtwdev->mutex); @@ -244,6 +236,7 @@ static void rtw_ops_remove_interface(struct ieee80211_hw *hw, config |= PORT_SET_BCN_CTRL; rtw_vif_port_config(rtwdev, rtwvif, config); clear_bit(rtwvif->port, rtwdev->hw_port); + rtw_recalc_lps(rtwdev, NULL); mutex_unlock(&rtwdev->mutex); } @@ -438,6 +431,9 @@ static void rtw_ops_bss_info_changed(struct ieee80211_hw *hw, if (changed & BSS_CHANGED_ERP_SLOT) rtw_conf_tx(rtwdev, rtwvif); + if (changed & BSS_CHANGED_PS) + rtw_recalc_lps(rtwdev, NULL); + rtw_vif_port_config(rtwdev, rtwvif, config); mutex_unlock(&rtwdev->mutex); diff --git a/drivers/net/wireless/realtek/rtw88/main.c b/drivers/net/wireless/realtek/rtw88/main.c index d30a191c9291..9447a3aae3b5 100644 --- a/drivers/net/wireless/realtek/rtw88/main.c +++ b/drivers/net/wireless/realtek/rtw88/main.c @@ -271,8 +271,8 @@ static void rtw_watch_dog_work(struct work_struct *work) * more than two stations associated to the AP, then we can not enter * lps, because fw does not handle the overlapped beacon interval * - * mac80211 should iterate vifs and determine if driver can enter - * ps by passing IEEE80211_CONF_PS to us, all we need to do is to + * rtw_recalc_lps() iterate vifs and determine if driver can enter + * ps by vif->type and vif->cfg.ps, all we need to do here is to * get that vif and check if device is having traffic more than the * threshold. */ diff --git a/drivers/net/wireless/realtek/rtw88/ps.c b/drivers/net/wireless/realtek/rtw88/ps.c index 996365575f44..53933fb38a33 100644 --- a/drivers/net/wireless/realtek/rtw88/ps.c +++ b/drivers/net/wireless/realtek/rtw88/ps.c @@ -299,3 +299,46 @@ void rtw_leave_lps_deep(struct rtw_dev *rtwdev) __rtw_leave_lps_deep(rtwdev); } + +struct rtw_vif_recalc_lps_iter_data { + struct rtw_dev *rtwdev; + struct ieee80211_vif *found_vif; + int count; +}; + +static void __rtw_vif_recalc_lps(struct rtw_vif_recalc_lps_iter_data *data, + struct ieee80211_vif *vif) +{ + if (data->count < 0) + return; + + if (vif->type != NL80211_IFTYPE_STATION) { + data->count = -1; + return; + } + + data->count++; + data->found_vif = vif; +} + +static void rtw_vif_recalc_lps_iter(void *data, u8 *mac, + struct ieee80211_vif *vif) +{ + __rtw_vif_recalc_lps(data, vif); +} + +void rtw_recalc_lps(struct rtw_dev *rtwdev, struct ieee80211_vif *new_vif) +{ + struct rtw_vif_recalc_lps_iter_data data = { .rtwdev = rtwdev }; + + if (new_vif) + __rtw_vif_recalc_lps(&data, new_vif); + rtw_iterate_vifs(rtwdev, rtw_vif_recalc_lps_iter, &data); + + if (data.count == 1 && data.found_vif->cfg.ps) { + rtwdev->ps_enabled = true; + } else { + rtwdev->ps_enabled = false; + rtw_leave_lps(rtwdev); + } +} diff --git a/drivers/net/wireless/realtek/rtw88/ps.h b/drivers/net/wireless/realtek/rtw88/ps.h index c194386f6db5..5ae83d2526cf 100644 --- a/drivers/net/wireless/realtek/rtw88/ps.h +++ b/drivers/net/wireless/realtek/rtw88/ps.h @@ -23,4 +23,6 @@ void rtw_enter_lps(struct rtw_dev *rtwdev, u8 port_id); void rtw_leave_lps(struct rtw_dev *rtwdev); void rtw_leave_lps_deep(struct rtw_dev *rtwdev); enum rtw_lps_deep_mode rtw_get_lps_deep_mode(struct rtw_dev *rtwdev); +void rtw_recalc_lps(struct rtw_dev *rtwdev, struct ieee80211_vif *new_vif); + #endif diff --git a/drivers/net/wireless/realtek/rtw89/core.c b/drivers/net/wireless/realtek/rtw89/core.c index 7fc0a26a4d73..bad864d56bd5 100644 --- a/drivers/net/wireless/realtek/rtw89/core.c +++ b/drivers/net/wireless/realtek/rtw89/core.c @@ -2531,9 +2531,6 @@ static void rtw89_vif_enter_lps(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwv rtwvif->tdls_peer) return; - if (rtwdev->total_sta_assoc > 1) - return; - if (rtwvif->offchan) return; diff --git a/drivers/net/wireless/realtek/rtw89/mac80211.c b/drivers/net/wireless/realtek/rtw89/mac80211.c index ee4588b61b8f..c42e31069035 100644 --- a/drivers/net/wireless/realtek/rtw89/mac80211.c +++ b/drivers/net/wireless/realtek/rtw89/mac80211.c @@ -89,15 +89,6 @@ static int rtw89_ops_config(struct ieee80211_hw *hw, u32 changed) !(hw->conf.flags & IEEE80211_CONF_IDLE)) rtw89_leave_ips(rtwdev); - if (changed & IEEE80211_CONF_CHANGE_PS) { - if (hw->conf.flags & IEEE80211_CONF_PS) { - rtwdev->lps_enabled = true; - } else { - rtw89_leave_lps(rtwdev); - rtwdev->lps_enabled = false; - } - } - if (changed & IEEE80211_CONF_CHANGE_CHANNEL) { rtw89_config_entity_chandef(rtwdev, RTW89_SUB_ENTITY_0, &hw->conf.chandef); @@ -168,6 +159,8 @@ static int rtw89_ops_add_interface(struct ieee80211_hw *hw, rtw89_core_txq_init(rtwdev, vif->txq); rtw89_btc_ntfy_role_info(rtwdev, rtwvif, NULL, BTC_ROLE_START); + + rtw89_recalc_lps(rtwdev); out: mutex_unlock(&rtwdev->mutex); @@ -192,6 +185,7 @@ static void rtw89_ops_remove_interface(struct ieee80211_hw *hw, rtw89_mac_remove_vif(rtwdev, rtwvif); rtw89_core_release_bit_map(rtwdev->hw_port, rtwvif->port); list_del_init(&rtwvif->list); + rtw89_recalc_lps(rtwdev); rtw89_enter_ips_by_hwflags(rtwdev); mutex_unlock(&rtwdev->mutex); @@ -451,6 +445,9 @@ static void rtw89_ops_bss_info_changed(struct ieee80211_hw *hw, if (changed & BSS_CHANGED_CQM) rtw89_fw_h2c_set_bcn_fltr_cfg(rtwdev, vif, true); + if (changed & BSS_CHANGED_PS) + rtw89_recalc_lps(rtwdev); + mutex_unlock(&rtwdev->mutex); } diff --git a/drivers/net/wireless/realtek/rtw89/ps.c b/drivers/net/wireless/realtek/rtw89/ps.c index fa94335f699a..84201ef19c17 100644 --- a/drivers/net/wireless/realtek/rtw89/ps.c +++ b/drivers/net/wireless/realtek/rtw89/ps.c @@ -252,3 +252,29 @@ void rtw89_process_p2p_ps(struct rtw89_dev *rtwdev, struct ieee80211_vif *vif) rtw89_p2p_disable_all_noa(rtwdev, vif); rtw89_p2p_update_noa(rtwdev, vif); } + +void rtw89_recalc_lps(struct rtw89_dev *rtwdev) +{ + struct ieee80211_vif *vif, *found_vif = NULL; + struct rtw89_vif *rtwvif; + int count = 0; + + rtw89_for_each_rtwvif(rtwdev, rtwvif) { + vif = rtwvif_to_vif(rtwvif); + + if (vif->type != NL80211_IFTYPE_STATION) { + count = 0; + break; + } + + count++; + found_vif = vif; + } + + if (count == 1 && found_vif->cfg.ps) { + rtwdev->lps_enabled = true; + } else { + rtw89_leave_lps(rtwdev); + rtwdev->lps_enabled = false; + } +} diff --git a/drivers/net/wireless/realtek/rtw89/ps.h b/drivers/net/wireless/realtek/rtw89/ps.h index 73c008db0426..4c18f49204b2 100644 --- a/drivers/net/wireless/realtek/rtw89/ps.h +++ b/drivers/net/wireless/realtek/rtw89/ps.h @@ -15,6 +15,7 @@ void rtw89_enter_ips(struct rtw89_dev *rtwdev); void rtw89_leave_ips(struct rtw89_dev *rtwdev); void rtw89_set_coex_ctrl_lps(struct rtw89_dev *rtwdev, bool btc_ctrl); void rtw89_process_p2p_ps(struct rtw89_dev *rtwdev, struct ieee80211_vif *vif); +void rtw89_recalc_lps(struct rtw89_dev *rtwdev); static inline void rtw89_leave_ips_by_hwflags(struct rtw89_dev *rtwdev) { diff --git a/drivers/nfc/nfcsim.c b/drivers/nfc/nfcsim.c index 44eeb17ae48d..a55381f80cd6 100644 --- a/drivers/nfc/nfcsim.c +++ b/drivers/nfc/nfcsim.c @@ -336,10 +336,6 @@ static struct dentry *nfcsim_debugfs_root; static void nfcsim_debugfs_init(void) { nfcsim_debugfs_root = debugfs_create_dir("nfcsim", NULL); - - if (!nfcsim_debugfs_root) - pr_err("Could not create debugfs entry\n"); - } static void nfcsim_debugfs_remove(void) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index ccb6eb1282f8..1f0cbb77b249 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -3585,6 +3585,9 @@ static ssize_t nvme_sysfs_delete(struct device *dev, { struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + if (!test_bit(NVME_CTRL_STARTED_ONCE, &ctrl->flags)) + return -EBUSY; + if (device_remove_file_self(dev, attr)) nvme_delete_ctrl_sync(ctrl); return count; @@ -5045,7 +5048,7 @@ void nvme_start_ctrl(struct nvme_ctrl *ctrl) * that were missed. We identify persistent discovery controllers by * checking that they started once before, hence are reconnecting back. */ - if (test_and_set_bit(NVME_CTRL_STARTED_ONCE, &ctrl->flags) && + if (test_bit(NVME_CTRL_STARTED_ONCE, &ctrl->flags) && nvme_discovery_ctrl(ctrl)) nvme_change_uevent(ctrl, "NVME_EVENT=rediscover"); @@ -5056,6 +5059,7 @@ void nvme_start_ctrl(struct nvme_ctrl *ctrl) } nvme_change_uevent(ctrl, "NVME_EVENT=connected"); + set_bit(NVME_CTRL_STARTED_ONCE, &ctrl->flags); } EXPORT_SYMBOL_GPL(nvme_start_ctrl); diff --git a/drivers/nvme/host/hwmon.c b/drivers/nvme/host/hwmon.c index 9e6e56c20ec9..316f3e4ca7cc 100644 --- a/drivers/nvme/host/hwmon.c +++ b/drivers/nvme/host/hwmon.c @@ -163,7 +163,9 @@ static umode_t nvme_hwmon_is_visible(const void *_data, case hwmon_temp_max: case hwmon_temp_min: if ((!channel && data->ctrl->wctemp) || - (channel && data->log->temp_sensor[channel - 1])) { + (channel && data->log->temp_sensor[channel - 1] && + !(data->ctrl->quirks & + NVME_QUIRK_NO_SECONDARY_TEMP_THRESH))) { if (data->ctrl->quirks & NVME_QUIRK_NO_TEMP_THRESH_CHANGE) return 0444; diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index 9171452e2f6d..2bc159a318ff 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -884,7 +884,6 @@ void nvme_mpath_remove_disk(struct nvme_ns_head *head) { if (!head->disk) return; - blk_mark_disk_dead(head->disk); /* make sure all pending bios are cleaned up */ kblockd_schedule_work(&head->requeue_work); flush_work(&head->requeue_work); diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index bf46f122e9e1..a2d4f59e0535 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -149,6 +149,11 @@ enum nvme_quirks { * Reports garbage in the namespace identifiers (eui64, nguid, uuid). */ NVME_QUIRK_BOGUS_NID = (1 << 18), + + /* + * No temperature thresholds for channels other than 0 (Composite). + */ + NVME_QUIRK_NO_SECONDARY_TEMP_THRESH = (1 << 19), }; /* diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 7f25c0fe3a0b..492f319ebdf3 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2956,7 +2956,7 @@ static struct nvme_dev *nvme_pci_alloc_dev(struct pci_dev *pdev, * over a single page. */ dev->ctrl.max_hw_sectors = min_t(u32, - NVME_MAX_KB_SZ << 1, dma_max_mapping_size(&pdev->dev) >> 9); + NVME_MAX_KB_SZ << 1, dma_opt_mapping_size(&pdev->dev) >> 9); dev->ctrl.max_segments = NVME_MAX_SEGS; /* @@ -3402,6 +3402,8 @@ static const struct pci_device_id nvme_id_table[] = { .driver_data = NVME_QUIRK_NO_DEEPEST_PS, }, { PCI_DEVICE(0x2646, 0x2263), /* KINGSTON A2000 NVMe SSD */ .driver_data = NVME_QUIRK_NO_DEEPEST_PS, }, + { PCI_DEVICE(0x2646, 0x5013), /* Kingston KC3000, Kingston FURY Renegade */ + .driver_data = NVME_QUIRK_NO_SECONDARY_TEMP_THRESH, }, { PCI_DEVICE(0x2646, 0x5018), /* KINGSTON OM8SFP4xxxxP OS21012 NVMe SSD */ .driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, }, { PCI_DEVICE(0x2646, 0x5016), /* KINGSTON OM3PGP4xxxxP OS21011 NVMe SSD */ @@ -3422,6 +3424,8 @@ static const struct pci_device_id nvme_id_table[] = { .driver_data = NVME_QUIRK_BOGUS_NID, }, { PCI_DEVICE(0x1e4B, 0x1202), /* MAXIO MAP1202 */ .driver_data = NVME_QUIRK_BOGUS_NID, }, + { PCI_DEVICE(0x1e4B, 0x1602), /* MAXIO MAP1602 */ + .driver_data = NVME_QUIRK_BOGUS_NID, }, { PCI_DEVICE(0x1cc1, 0x5350), /* ADATA XPG GAMMIX S50 */ .driver_data = NVME_QUIRK_BOGUS_NID, }, { PCI_DEVICE(0x1dbe, 0x5236), /* ADATA XPG GAMMIX S70 */ @@ -3441,6 +3445,10 @@ static const struct pci_device_id nvme_id_table[] = { NVME_QUIRK_IGNORE_DEV_SUBNQN, }, { PCI_DEVICE(0x10ec, 0x5763), /* TEAMGROUP T-FORCE CARDEA ZERO Z330 SSD */ .driver_data = NVME_QUIRK_BOGUS_NID, }, + { PCI_DEVICE(0x1e4b, 0x1602), /* HS-SSD-FUTURE 2048G */ + .driver_data = NVME_QUIRK_BOGUS_NID, }, + { PCI_DEVICE(0x10ec, 0x5765), /* TEAMGROUP MP33 2TB SSD */ + .driver_data = NVME_QUIRK_BOGUS_NID, }, { PCI_DEVICE(PCI_VENDOR_ID_AMAZON, 0x0061), .driver_data = NVME_QUIRK_DMA_ADDRESS_BITS_48, }, { PCI_DEVICE(PCI_VENDOR_ID_AMAZON, 0x0065), diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index f4e2a88729fd..c525867760bf 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -6003,8 +6003,9 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x56c1, aspm_l1_acceptable_latency #ifdef CONFIG_PCIE_DPC /* - * Intel Tiger Lake and Alder Lake BIOS has a bug that clears the DPC - * RP PIO Log Size of the integrated Thunderbolt PCIe Root Ports. + * Intel Ice Lake, Tiger Lake and Alder Lake BIOS has a bug that clears + * the DPC RP PIO Log Size of the integrated Thunderbolt PCIe Root + * Ports. */ static void dpc_log_size(struct pci_dev *dev) { @@ -6027,6 +6028,10 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x461f, dpc_log_size); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x462f, dpc_log_size); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x463f, dpc_log_size); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x466e, dpc_log_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x8a1d, dpc_log_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x8a1f, dpc_log_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x8a21, dpc_log_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x8a23, dpc_log_size); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x9a23, dpc_log_size); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x9a25, dpc_log_size); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x9a27, dpc_log_size); diff --git a/drivers/phy/amlogic/phy-meson-g12a-mipi-dphy-analog.c b/drivers/phy/amlogic/phy-meson-g12a-mipi-dphy-analog.c index c14089fa7db4..cabdddbbabfd 100644 --- a/drivers/phy/amlogic/phy-meson-g12a-mipi-dphy-analog.c +++ b/drivers/phy/amlogic/phy-meson-g12a-mipi-dphy-analog.c @@ -70,7 +70,7 @@ static int phy_g12a_mipi_dphy_analog_power_on(struct phy *phy) HHI_MIPI_CNTL1_BANDGAP); regmap_write(priv->regmap, HHI_MIPI_CNTL2, - FIELD_PREP(HHI_MIPI_CNTL2_DIF_TX_CTL0, 0x459) | + FIELD_PREP(HHI_MIPI_CNTL2_DIF_TX_CTL0, 0x45a) | FIELD_PREP(HHI_MIPI_CNTL2_DIF_TX_CTL1, 0x2680)); reg = DSI_LANE_CLK; diff --git a/drivers/phy/mediatek/phy-mtk-hdmi-mt8195.c b/drivers/phy/mediatek/phy-mtk-hdmi-mt8195.c index caa953780bee..8aa7251de4a9 100644 --- a/drivers/phy/mediatek/phy-mtk-hdmi-mt8195.c +++ b/drivers/phy/mediatek/phy-mtk-hdmi-mt8195.c @@ -237,11 +237,11 @@ static int mtk_hdmi_pll_calc(struct mtk_hdmi_phy *hdmi_phy, struct clk_hw *hw, */ if (tmds_clk < 54 * MEGA) txposdiv = 8; - else if (tmds_clk >= 54 * MEGA && tmds_clk < 148.35 * MEGA) + else if (tmds_clk >= 54 * MEGA && (tmds_clk * 100) < 14835 * MEGA) txposdiv = 4; - else if (tmds_clk >= 148.35 * MEGA && tmds_clk < 296.7 * MEGA) + else if ((tmds_clk * 100) >= 14835 * MEGA && (tmds_clk * 10) < 2967 * MEGA) txposdiv = 2; - else if (tmds_clk >= 296.7 * MEGA && tmds_clk <= 594 * MEGA) + else if ((tmds_clk * 10) >= 2967 * MEGA && tmds_clk <= 594 * MEGA) txposdiv = 1; else return -EINVAL; @@ -324,12 +324,12 @@ static int mtk_hdmi_pll_drv_setting(struct clk_hw *hw) clk_channel_bias = 0x34; /* 20mA */ impedance_en = 0xf; impedance = 0x36; /* 100ohm */ - } else if (pixel_clk >= 74.175 * MEGA && pixel_clk <= 300 * MEGA) { + } else if (((u64)pixel_clk * 1000) >= 74175 * MEGA && pixel_clk <= 300 * MEGA) { data_channel_bias = 0x34; /* 20mA */ clk_channel_bias = 0x2c; /* 16mA */ impedance_en = 0xf; impedance = 0x36; /* 100ohm */ - } else if (pixel_clk >= 27 * MEGA && pixel_clk < 74.175 * MEGA) { + } else if (pixel_clk >= 27 * MEGA && ((u64)pixel_clk * 1000) < 74175 * MEGA) { data_channel_bias = 0x14; /* 10mA */ clk_channel_bias = 0x14; /* 10mA */ impedance_en = 0x0; diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-combo.c b/drivers/phy/qualcomm/phy-qcom-qmp-combo.c index 6850e04c329b..87b17e5877ab 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-combo.c +++ b/drivers/phy/qualcomm/phy-qcom-qmp-combo.c @@ -2472,7 +2472,7 @@ static int qmp_combo_com_init(struct qmp_combo *qmp) ret = regulator_bulk_enable(cfg->num_vregs, qmp->vregs); if (ret) { dev_err(qmp->dev, "failed to enable regulators, err=%d\n", ret); - goto err_unlock; + goto err_decrement_count; } ret = reset_control_bulk_assert(cfg->num_resets, qmp->resets); @@ -2522,7 +2522,8 @@ err_assert_reset: reset_control_bulk_assert(cfg->num_resets, qmp->resets); err_disable_regulators: regulator_bulk_disable(cfg->num_vregs, qmp->vregs); -err_unlock: +err_decrement_count: + qmp->init_count--; mutex_unlock(&qmp->phy_mutex); return ret; diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcie-msm8996.c b/drivers/phy/qualcomm/phy-qcom-qmp-pcie-msm8996.c index 09824be088c9..0c603bc06e09 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-pcie-msm8996.c +++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcie-msm8996.c @@ -379,7 +379,7 @@ static int qmp_pcie_msm8996_com_init(struct qmp_phy *qphy) ret = regulator_bulk_enable(cfg->num_vregs, qmp->vregs); if (ret) { dev_err(qmp->dev, "failed to enable regulators, err=%d\n", ret); - goto err_unlock; + goto err_decrement_count; } ret = reset_control_bulk_assert(cfg->num_resets, qmp->resets); @@ -409,7 +409,8 @@ err_assert_reset: reset_control_bulk_assert(cfg->num_resets, qmp->resets); err_disable_regulators: regulator_bulk_disable(cfg->num_vregs, qmp->vregs); -err_unlock: +err_decrement_count: + qmp->init_count--; mutex_unlock(&qmp->phy_mutex); return ret; diff --git a/drivers/phy/qualcomm/phy-qcom-snps-femto-v2.c b/drivers/phy/qualcomm/phy-qcom-snps-femto-v2.c index a59063596214..6c237f3cc66d 100644 --- a/drivers/phy/qualcomm/phy-qcom-snps-femto-v2.c +++ b/drivers/phy/qualcomm/phy-qcom-snps-femto-v2.c @@ -115,11 +115,11 @@ struct phy_override_seq { * * @cfg_ahb_clk: AHB2PHY interface clock * @ref_clk: phy reference clock - * @iface_clk: phy interface clock * @phy_reset: phy reset control * @vregs: regulator supplies bulk data * @phy_initialized: if PHY has been initialized correctly * @mode: contains the current mode the PHY is in + * @update_seq_cfg: tuning parameters for phy init */ struct qcom_snps_hsphy { struct phy *phy; diff --git a/drivers/platform/mellanox/mlxbf-pmc.c b/drivers/platform/mellanox/mlxbf-pmc.c index c2c9b0d3244c..be967d797c28 100644 --- a/drivers/platform/mellanox/mlxbf-pmc.c +++ b/drivers/platform/mellanox/mlxbf-pmc.c @@ -1348,9 +1348,8 @@ static int mlxbf_pmc_map_counters(struct device *dev) for (i = 0; i < pmc->total_blocks; ++i) { if (strstr(pmc->block_name[i], "tile")) { - ret = sscanf(pmc->block_name[i], "tile%d", &tile_num); - if (ret < 0) - return ret; + if (sscanf(pmc->block_name[i], "tile%d", &tile_num) != 1) + return -EINVAL; if (tile_num >= pmc->tile_count) continue; diff --git a/drivers/platform/x86/amd/pmf/core.c b/drivers/platform/x86/amd/pmf/core.c index d5bb775dadcf..ee5f124f78b6 100644 --- a/drivers/platform/x86/amd/pmf/core.c +++ b/drivers/platform/x86/amd/pmf/core.c @@ -245,24 +245,29 @@ static const struct pci_device_id pmf_pci_ids[] = { { } }; -int amd_pmf_init_metrics_table(struct amd_pmf_dev *dev) +static void amd_pmf_set_dram_addr(struct amd_pmf_dev *dev) { u64 phys_addr; u32 hi, low; - INIT_DELAYED_WORK(&dev->work_buffer, amd_pmf_get_metrics); + phys_addr = virt_to_phys(dev->buf); + hi = phys_addr >> 32; + low = phys_addr & GENMASK(31, 0); + + amd_pmf_send_cmd(dev, SET_DRAM_ADDR_HIGH, 0, hi, NULL); + amd_pmf_send_cmd(dev, SET_DRAM_ADDR_LOW, 0, low, NULL); +} +int amd_pmf_init_metrics_table(struct amd_pmf_dev *dev) +{ /* Get Metrics Table Address */ dev->buf = kzalloc(sizeof(dev->m_table), GFP_KERNEL); if (!dev->buf) return -ENOMEM; - phys_addr = virt_to_phys(dev->buf); - hi = phys_addr >> 32; - low = phys_addr & GENMASK(31, 0); + INIT_DELAYED_WORK(&dev->work_buffer, amd_pmf_get_metrics); - amd_pmf_send_cmd(dev, SET_DRAM_ADDR_HIGH, 0, hi, NULL); - amd_pmf_send_cmd(dev, SET_DRAM_ADDR_LOW, 0, low, NULL); + amd_pmf_set_dram_addr(dev); /* * Start collecting the metrics data after a small delay @@ -273,6 +278,18 @@ int amd_pmf_init_metrics_table(struct amd_pmf_dev *dev) return 0; } +static int amd_pmf_resume_handler(struct device *dev) +{ + struct amd_pmf_dev *pdev = dev_get_drvdata(dev); + + if (pdev->buf) + amd_pmf_set_dram_addr(pdev); + + return 0; +} + +static DEFINE_SIMPLE_DEV_PM_OPS(amd_pmf_pm, NULL, amd_pmf_resume_handler); + static void amd_pmf_init_features(struct amd_pmf_dev *dev) { int ret; @@ -413,6 +430,7 @@ static struct platform_driver amd_pmf_driver = { .name = "amd-pmf", .acpi_match_table = amd_pmf_acpi_ids, .dev_groups = amd_pmf_driver_groups, + .pm = pm_sleep_ptr(&amd_pmf_pm), }, .probe = amd_pmf_probe, .remove_new = amd_pmf_remove, diff --git a/drivers/platform/x86/asus-nb-wmi.c b/drivers/platform/x86/asus-nb-wmi.c index e2c9a68d12df..fdf7da06af30 100644 --- a/drivers/platform/x86/asus-nb-wmi.c +++ b/drivers/platform/x86/asus-nb-wmi.c @@ -555,6 +555,7 @@ static const struct key_entry asus_nb_wmi_keymap[] = { { KE_KEY, 0x71, { KEY_F13 } }, /* General-purpose button */ { KE_IGNORE, 0x79, }, /* Charger type dectection notification */ { KE_KEY, 0x7a, { KEY_ALS_TOGGLE } }, /* Ambient Light Sensor Toggle */ + { KE_IGNORE, 0x7B, }, /* Charger connect/disconnect notification */ { KE_KEY, 0x7c, { KEY_MICMUTE } }, { KE_KEY, 0x7D, { KEY_BLUETOOTH } }, /* Bluetooth Enable */ { KE_KEY, 0x7E, { KEY_BLUETOOTH } }, /* Bluetooth Disable */ @@ -584,6 +585,7 @@ static const struct key_entry asus_nb_wmi_keymap[] = { { KE_KEY, 0xAE, { KEY_FN_F5 } }, /* Fn+F5 fan mode on 2020+ */ { KE_KEY, 0xB3, { KEY_PROG4 } }, /* AURA */ { KE_KEY, 0xB5, { KEY_CALC } }, + { KE_IGNORE, 0xC0, }, /* External display connect/disconnect notification */ { KE_KEY, 0xC4, { KEY_KBDILLUMUP } }, { KE_KEY, 0xC5, { KEY_KBDILLUMDOWN } }, { KE_IGNORE, 0xC6, }, /* Ambient Light Sensor notification */ diff --git a/drivers/platform/x86/intel/ifs/load.c b/drivers/platform/x86/intel/ifs/load.c index 61dffb4c8a1d..e6ae8265f3a3 100644 --- a/drivers/platform/x86/intel/ifs/load.c +++ b/drivers/platform/x86/intel/ifs/load.c @@ -208,7 +208,7 @@ static int scan_chunks_sanity_check(struct device *dev) continue; reinit_completion(&ifs_done); local_work.dev = dev; - INIT_WORK(&local_work.w, copy_hashes_authenticate_chunks); + INIT_WORK_ONSTACK(&local_work.w, copy_hashes_authenticate_chunks); schedule_work_on(cpu, &local_work.w); wait_for_completion(&ifs_done); if (ifsd->loading_error) { diff --git a/drivers/platform/x86/intel/speed_select_if/isst_if_common.c b/drivers/platform/x86/intel/speed_select_if/isst_if_common.c index e0572a29212e..02fe360a59c7 100644 --- a/drivers/platform/x86/intel/speed_select_if/isst_if_common.c +++ b/drivers/platform/x86/intel/speed_select_if/isst_if_common.c @@ -304,14 +304,13 @@ struct isst_if_pkg_info { static struct isst_if_cpu_info *isst_cpu_info; static struct isst_if_pkg_info *isst_pkg_info; -#define ISST_MAX_PCI_DOMAINS 8 - static struct pci_dev *_isst_if_get_pci_dev(int cpu, int bus_no, int dev, int fn) { struct pci_dev *matched_pci_dev = NULL; struct pci_dev *pci_dev = NULL; + struct pci_dev *_pci_dev = NULL; int no_matches = 0, pkg_id; - int i, bus_number; + int bus_number; if (bus_no < 0 || bus_no >= ISST_MAX_BUS_NUMBER || cpu < 0 || cpu >= nr_cpu_ids || cpu >= num_possible_cpus()) @@ -323,12 +322,11 @@ static struct pci_dev *_isst_if_get_pci_dev(int cpu, int bus_no, int dev, int fn if (bus_number < 0) return NULL; - for (i = 0; i < ISST_MAX_PCI_DOMAINS; ++i) { - struct pci_dev *_pci_dev; + for_each_pci_dev(_pci_dev) { int node; - _pci_dev = pci_get_domain_bus_and_slot(i, bus_number, PCI_DEVFN(dev, fn)); - if (!_pci_dev) + if (_pci_dev->bus->number != bus_number || + _pci_dev->devfn != PCI_DEVFN(dev, fn)) continue; ++no_matches; diff --git a/drivers/power/supply/ab8500_btemp.c b/drivers/power/supply/ab8500_btemp.c index 307ee6f71042..6f83e99d2eb7 100644 --- a/drivers/power/supply/ab8500_btemp.c +++ b/drivers/power/supply/ab8500_btemp.c @@ -624,10 +624,8 @@ static int ab8500_btemp_get_ext_psy_data(struct device *dev, void *data) */ static void ab8500_btemp_external_power_changed(struct power_supply *psy) { - struct ab8500_btemp *di = power_supply_get_drvdata(psy); - - class_for_each_device(power_supply_class, NULL, - di->btemp_psy, ab8500_btemp_get_ext_psy_data); + class_for_each_device(power_supply_class, NULL, psy, + ab8500_btemp_get_ext_psy_data); } /* ab8500 btemp driver interrupts and their respective isr */ diff --git a/drivers/power/supply/ab8500_fg.c b/drivers/power/supply/ab8500_fg.c index 41a7bff9ac37..53560fbb6dcd 100644 --- a/drivers/power/supply/ab8500_fg.c +++ b/drivers/power/supply/ab8500_fg.c @@ -2407,10 +2407,8 @@ out: */ static void ab8500_fg_external_power_changed(struct power_supply *psy) { - struct ab8500_fg *di = power_supply_get_drvdata(psy); - - class_for_each_device(power_supply_class, NULL, - di->fg_psy, ab8500_fg_get_ext_psy_data); + class_for_each_device(power_supply_class, NULL, psy, + ab8500_fg_get_ext_psy_data); } /** diff --git a/drivers/power/supply/axp288_fuel_gauge.c b/drivers/power/supply/axp288_fuel_gauge.c index 05f413178462..3be6f3b10ea4 100644 --- a/drivers/power/supply/axp288_fuel_gauge.c +++ b/drivers/power/supply/axp288_fuel_gauge.c @@ -507,7 +507,7 @@ static void fuel_gauge_external_power_changed(struct power_supply *psy) mutex_lock(&info->lock); info->valid = 0; /* Force updating of the cached registers */ mutex_unlock(&info->lock); - power_supply_changed(info->bat); + power_supply_changed(psy); } static struct power_supply_desc fuel_gauge_desc = { diff --git a/drivers/power/supply/bq24190_charger.c b/drivers/power/supply/bq24190_charger.c index de67b985f0a9..dc33f00fcc06 100644 --- a/drivers/power/supply/bq24190_charger.c +++ b/drivers/power/supply/bq24190_charger.c @@ -1262,6 +1262,7 @@ static void bq24190_input_current_limit_work(struct work_struct *work) bq24190_charger_set_property(bdi->charger, POWER_SUPPLY_PROP_INPUT_CURRENT_LIMIT, &val); + power_supply_changed(bdi->charger); } /* Sync the input-current-limit with our parent supply (if we have one) */ diff --git a/drivers/power/supply/bq25890_charger.c b/drivers/power/supply/bq25890_charger.c index 22cde35eb144..f8636cf86505 100644 --- a/drivers/power/supply/bq25890_charger.c +++ b/drivers/power/supply/bq25890_charger.c @@ -750,7 +750,7 @@ static void bq25890_charger_external_power_changed(struct power_supply *psy) if (bq->chip_version != BQ25892) return; - ret = power_supply_get_property_from_supplier(bq->charger, + ret = power_supply_get_property_from_supplier(psy, POWER_SUPPLY_PROP_USB_TYPE, &val); if (ret) @@ -775,6 +775,7 @@ static void bq25890_charger_external_power_changed(struct power_supply *psy) } bq25890_field_write(bq, F_IINLIM, input_current_limit); + power_supply_changed(psy); } static int bq25890_get_chip_state(struct bq25890_device *bq, @@ -1106,6 +1107,8 @@ static void bq25890_pump_express_work(struct work_struct *data) dev_info(bq->dev, "Hi-voltage charging requested, input voltage is %d mV\n", voltage); + power_supply_changed(bq->charger); + return; error_print: bq25890_field_write(bq, F_PUMPX_EN, 0); diff --git a/drivers/power/supply/bq27xxx_battery.c b/drivers/power/supply/bq27xxx_battery.c index 5ff6f44fd47b..4296600e8912 100644 --- a/drivers/power/supply/bq27xxx_battery.c +++ b/drivers/power/supply/bq27xxx_battery.c @@ -1083,10 +1083,8 @@ static int poll_interval_param_set(const char *val, const struct kernel_param *k return ret; mutex_lock(&bq27xxx_list_lock); - list_for_each_entry(di, &bq27xxx_battery_devices, list) { - cancel_delayed_work_sync(&di->work); - schedule_delayed_work(&di->work, 0); - } + list_for_each_entry(di, &bq27xxx_battery_devices, list) + mod_delayed_work(system_wq, &di->work, 0); mutex_unlock(&bq27xxx_list_lock); return ret; @@ -1761,60 +1759,6 @@ static int bq27xxx_battery_read_health(struct bq27xxx_device_info *di) return POWER_SUPPLY_HEALTH_GOOD; } -void bq27xxx_battery_update(struct bq27xxx_device_info *di) -{ - struct bq27xxx_reg_cache cache = {0, }; - bool has_singe_flag = di->opts & BQ27XXX_O_ZERO; - - cache.flags = bq27xxx_read(di, BQ27XXX_REG_FLAGS, has_singe_flag); - if ((cache.flags & 0xff) == 0xff) - cache.flags = -1; /* read error */ - if (cache.flags >= 0) { - cache.temperature = bq27xxx_battery_read_temperature(di); - if (di->regs[BQ27XXX_REG_TTE] != INVALID_REG_ADDR) - cache.time_to_empty = bq27xxx_battery_read_time(di, BQ27XXX_REG_TTE); - if (di->regs[BQ27XXX_REG_TTECP] != INVALID_REG_ADDR) - cache.time_to_empty_avg = bq27xxx_battery_read_time(di, BQ27XXX_REG_TTECP); - if (di->regs[BQ27XXX_REG_TTF] != INVALID_REG_ADDR) - cache.time_to_full = bq27xxx_battery_read_time(di, BQ27XXX_REG_TTF); - - cache.charge_full = bq27xxx_battery_read_fcc(di); - cache.capacity = bq27xxx_battery_read_soc(di); - if (di->regs[BQ27XXX_REG_AE] != INVALID_REG_ADDR) - cache.energy = bq27xxx_battery_read_energy(di); - di->cache.flags = cache.flags; - cache.health = bq27xxx_battery_read_health(di); - if (di->regs[BQ27XXX_REG_CYCT] != INVALID_REG_ADDR) - cache.cycle_count = bq27xxx_battery_read_cyct(di); - - /* We only have to read charge design full once */ - if (di->charge_design_full <= 0) - di->charge_design_full = bq27xxx_battery_read_dcap(di); - } - - if ((di->cache.capacity != cache.capacity) || - (di->cache.flags != cache.flags)) - power_supply_changed(di->bat); - - if (memcmp(&di->cache, &cache, sizeof(cache)) != 0) - di->cache = cache; - - di->last_update = jiffies; -} -EXPORT_SYMBOL_GPL(bq27xxx_battery_update); - -static void bq27xxx_battery_poll(struct work_struct *work) -{ - struct bq27xxx_device_info *di = - container_of(work, struct bq27xxx_device_info, - work.work); - - bq27xxx_battery_update(di); - - if (poll_interval > 0) - schedule_delayed_work(&di->work, poll_interval * HZ); -} - static bool bq27xxx_battery_is_full(struct bq27xxx_device_info *di, int flags) { if (di->opts & BQ27XXX_O_ZERO) @@ -1833,7 +1777,8 @@ static bool bq27xxx_battery_is_full(struct bq27xxx_device_info *di, int flags) static int bq27xxx_battery_current_and_status( struct bq27xxx_device_info *di, union power_supply_propval *val_curr, - union power_supply_propval *val_status) + union power_supply_propval *val_status, + struct bq27xxx_reg_cache *cache) { bool single_flags = (di->opts & BQ27XXX_O_ZERO); int curr; @@ -1845,10 +1790,14 @@ static int bq27xxx_battery_current_and_status( return curr; } - flags = bq27xxx_read(di, BQ27XXX_REG_FLAGS, single_flags); - if (flags < 0) { - dev_err(di->dev, "error reading flags\n"); - return flags; + if (cache) { + flags = cache->flags; + } else { + flags = bq27xxx_read(di, BQ27XXX_REG_FLAGS, single_flags); + if (flags < 0) { + dev_err(di->dev, "error reading flags\n"); + return flags; + } } if (di->opts & BQ27XXX_O_ZERO) { @@ -1883,6 +1832,78 @@ static int bq27xxx_battery_current_and_status( return 0; } +static void bq27xxx_battery_update_unlocked(struct bq27xxx_device_info *di) +{ + union power_supply_propval status = di->last_status; + struct bq27xxx_reg_cache cache = {0, }; + bool has_singe_flag = di->opts & BQ27XXX_O_ZERO; + + cache.flags = bq27xxx_read(di, BQ27XXX_REG_FLAGS, has_singe_flag); + if ((cache.flags & 0xff) == 0xff) + cache.flags = -1; /* read error */ + if (cache.flags >= 0) { + cache.temperature = bq27xxx_battery_read_temperature(di); + if (di->regs[BQ27XXX_REG_TTE] != INVALID_REG_ADDR) + cache.time_to_empty = bq27xxx_battery_read_time(di, BQ27XXX_REG_TTE); + if (di->regs[BQ27XXX_REG_TTECP] != INVALID_REG_ADDR) + cache.time_to_empty_avg = bq27xxx_battery_read_time(di, BQ27XXX_REG_TTECP); + if (di->regs[BQ27XXX_REG_TTF] != INVALID_REG_ADDR) + cache.time_to_full = bq27xxx_battery_read_time(di, BQ27XXX_REG_TTF); + + cache.charge_full = bq27xxx_battery_read_fcc(di); + cache.capacity = bq27xxx_battery_read_soc(di); + if (di->regs[BQ27XXX_REG_AE] != INVALID_REG_ADDR) + cache.energy = bq27xxx_battery_read_energy(di); + di->cache.flags = cache.flags; + cache.health = bq27xxx_battery_read_health(di); + if (di->regs[BQ27XXX_REG_CYCT] != INVALID_REG_ADDR) + cache.cycle_count = bq27xxx_battery_read_cyct(di); + + /* + * On gauges with signed current reporting the current must be + * checked to detect charging <-> discharging status changes. + */ + if (!(di->opts & BQ27XXX_O_ZERO)) + bq27xxx_battery_current_and_status(di, NULL, &status, &cache); + + /* We only have to read charge design full once */ + if (di->charge_design_full <= 0) + di->charge_design_full = bq27xxx_battery_read_dcap(di); + } + + if ((di->cache.capacity != cache.capacity) || + (di->cache.flags != cache.flags) || + (di->last_status.intval != status.intval)) { + di->last_status.intval = status.intval; + power_supply_changed(di->bat); + } + + if (memcmp(&di->cache, &cache, sizeof(cache)) != 0) + di->cache = cache; + + di->last_update = jiffies; + + if (!di->removed && poll_interval > 0) + mod_delayed_work(system_wq, &di->work, poll_interval * HZ); +} + +void bq27xxx_battery_update(struct bq27xxx_device_info *di) +{ + mutex_lock(&di->lock); + bq27xxx_battery_update_unlocked(di); + mutex_unlock(&di->lock); +} +EXPORT_SYMBOL_GPL(bq27xxx_battery_update); + +static void bq27xxx_battery_poll(struct work_struct *work) +{ + struct bq27xxx_device_info *di = + container_of(work, struct bq27xxx_device_info, + work.work); + + bq27xxx_battery_update(di); +} + /* * Get the average power in µW * Return < 0 if something fails. @@ -1985,10 +2006,8 @@ static int bq27xxx_battery_get_property(struct power_supply *psy, struct bq27xxx_device_info *di = power_supply_get_drvdata(psy); mutex_lock(&di->lock); - if (time_is_before_jiffies(di->last_update + 5 * HZ)) { - cancel_delayed_work_sync(&di->work); - bq27xxx_battery_poll(&di->work.work); - } + if (time_is_before_jiffies(di->last_update + 5 * HZ)) + bq27xxx_battery_update_unlocked(di); mutex_unlock(&di->lock); if (psp != POWER_SUPPLY_PROP_PRESENT && di->cache.flags < 0) @@ -1996,7 +2015,7 @@ static int bq27xxx_battery_get_property(struct power_supply *psy, switch (psp) { case POWER_SUPPLY_PROP_STATUS: - ret = bq27xxx_battery_current_and_status(di, NULL, val); + ret = bq27xxx_battery_current_and_status(di, NULL, val, NULL); break; case POWER_SUPPLY_PROP_VOLTAGE_NOW: ret = bq27xxx_battery_voltage(di, val); @@ -2005,7 +2024,7 @@ static int bq27xxx_battery_get_property(struct power_supply *psy, val->intval = di->cache.flags < 0 ? 0 : 1; break; case POWER_SUPPLY_PROP_CURRENT_NOW: - ret = bq27xxx_battery_current_and_status(di, val, NULL); + ret = bq27xxx_battery_current_and_status(di, val, NULL, NULL); break; case POWER_SUPPLY_PROP_CAPACITY: ret = bq27xxx_simple_value(di->cache.capacity, val); @@ -2078,8 +2097,8 @@ static void bq27xxx_external_power_changed(struct power_supply *psy) { struct bq27xxx_device_info *di = power_supply_get_drvdata(psy); - cancel_delayed_work_sync(&di->work); - schedule_delayed_work(&di->work, 0); + /* After charger plug in/out wait 0.5s for things to stabilize */ + mod_delayed_work(system_wq, &di->work, HZ / 2); } int bq27xxx_battery_setup(struct bq27xxx_device_info *di) @@ -2127,22 +2146,18 @@ EXPORT_SYMBOL_GPL(bq27xxx_battery_setup); void bq27xxx_battery_teardown(struct bq27xxx_device_info *di) { - /* - * power_supply_unregister call bq27xxx_battery_get_property which - * call bq27xxx_battery_poll. - * Make sure that bq27xxx_battery_poll will not call - * schedule_delayed_work again after unregister (which cause OOPS). - */ - poll_interval = 0; - - cancel_delayed_work_sync(&di->work); - - power_supply_unregister(di->bat); - mutex_lock(&bq27xxx_list_lock); list_del(&di->list); mutex_unlock(&bq27xxx_list_lock); + /* Set removed to avoid bq27xxx_battery_update() re-queuing the work */ + mutex_lock(&di->lock); + di->removed = true; + mutex_unlock(&di->lock); + + cancel_delayed_work_sync(&di->work); + + power_supply_unregister(di->bat); mutex_destroy(&di->lock); } EXPORT_SYMBOL_GPL(bq27xxx_battery_teardown); diff --git a/drivers/power/supply/bq27xxx_battery_i2c.c b/drivers/power/supply/bq27xxx_battery_i2c.c index f8768997333b..6d3c74876339 100644 --- a/drivers/power/supply/bq27xxx_battery_i2c.c +++ b/drivers/power/supply/bq27xxx_battery_i2c.c @@ -179,7 +179,7 @@ static int bq27xxx_battery_i2c_probe(struct i2c_client *client) i2c_set_clientdata(client, di); if (client->irq) { - ret = devm_request_threaded_irq(&client->dev, client->irq, + ret = request_threaded_irq(client->irq, NULL, bq27xxx_battery_irq_handler_thread, IRQF_ONESHOT, di->name, di); @@ -209,6 +209,7 @@ static void bq27xxx_battery_i2c_remove(struct i2c_client *client) { struct bq27xxx_device_info *di = i2c_get_clientdata(client); + free_irq(client->irq, di); bq27xxx_battery_teardown(di); mutex_lock(&battery_mutex); diff --git a/drivers/power/supply/mt6360_charger.c b/drivers/power/supply/mt6360_charger.c index 92e48e3a4853..1305cba61edd 100644 --- a/drivers/power/supply/mt6360_charger.c +++ b/drivers/power/supply/mt6360_charger.c @@ -796,7 +796,9 @@ static int mt6360_charger_probe(struct platform_device *pdev) mci->vinovp = 6500000; mutex_init(&mci->chgdet_lock); platform_set_drvdata(pdev, mci); - devm_work_autocancel(&pdev->dev, &mci->chrdet_work, mt6360_chrdet_work); + ret = devm_work_autocancel(&pdev->dev, &mci->chrdet_work, mt6360_chrdet_work); + if (ret) + return dev_err_probe(&pdev->dev, ret, "Failed to set delayed work\n"); ret = device_property_read_u32(&pdev->dev, "richtek,vinovp-microvolt", &mci->vinovp); if (ret) diff --git a/drivers/power/supply/power_supply_core.c b/drivers/power/supply/power_supply_core.c index ab986dbace16..3791aec69ddc 100644 --- a/drivers/power/supply/power_supply_core.c +++ b/drivers/power/supply/power_supply_core.c @@ -348,6 +348,10 @@ static int __power_supply_is_system_supplied(struct device *dev, void *data) struct power_supply *psy = dev_get_drvdata(dev); unsigned int *count = data; + if (!psy->desc->get_property(psy, POWER_SUPPLY_PROP_SCOPE, &ret)) + if (ret.intval == POWER_SUPPLY_SCOPE_DEVICE) + return 0; + (*count)++; if (psy->desc->type != POWER_SUPPLY_TYPE_BATTERY) if (!psy->desc->get_property(psy, POWER_SUPPLY_PROP_ONLINE, @@ -366,8 +370,8 @@ int power_supply_is_system_supplied(void) __power_supply_is_system_supplied); /* - * If no power class device was found at all, most probably we are - * running on a desktop system, so assume we are on mains power. + * If no system scope power class device was found at all, most probably we + * are running on a desktop system, so assume we are on mains power. */ if (count == 0) return 1; @@ -573,7 +577,7 @@ int power_supply_get_battery_info(struct power_supply *psy, struct power_supply_battery_info *info; struct device_node *battery_np = NULL; struct fwnode_reference_args args; - struct fwnode_handle *fwnode; + struct fwnode_handle *fwnode = NULL; const char *value; int err, len, index; const __be32 *list; @@ -585,7 +589,7 @@ int power_supply_get_battery_info(struct power_supply *psy, return -ENODEV; fwnode = fwnode_handle_get(of_fwnode_handle(battery_np)); - } else { + } else if (psy->dev.parent) { err = fwnode_property_get_reference_args( dev_fwnode(psy->dev.parent), "monitored-battery", NULL, 0, 0, &args); @@ -595,6 +599,9 @@ int power_supply_get_battery_info(struct power_supply *psy, fwnode = args.fwnode; } + if (!fwnode) + return -ENOENT; + err = fwnode_property_read_string(fwnode, "compatible", &value); if (err) goto out_put_node; diff --git a/drivers/power/supply/power_supply_leds.c b/drivers/power/supply/power_supply_leds.c index 702bf83f6e6d..0674483279d7 100644 --- a/drivers/power/supply/power_supply_leds.c +++ b/drivers/power/supply/power_supply_leds.c @@ -35,8 +35,9 @@ static void power_supply_update_bat_leds(struct power_supply *psy) led_trigger_event(psy->charging_full_trig, LED_FULL); led_trigger_event(psy->charging_trig, LED_OFF); led_trigger_event(psy->full_trig, LED_FULL); - led_trigger_event(psy->charging_blink_full_solid_trig, - LED_FULL); + /* Going from blink to LED on requires a LED_OFF event to stop blink */ + led_trigger_event(psy->charging_blink_full_solid_trig, LED_OFF); + led_trigger_event(psy->charging_blink_full_solid_trig, LED_FULL); break; case POWER_SUPPLY_STATUS_CHARGING: led_trigger_event(psy->charging_full_trig, LED_FULL); diff --git a/drivers/power/supply/power_supply_sysfs.c b/drivers/power/supply/power_supply_sysfs.c index ba3b125cd66e..06e5b6b0e255 100644 --- a/drivers/power/supply/power_supply_sysfs.c +++ b/drivers/power/supply/power_supply_sysfs.c @@ -286,7 +286,8 @@ static ssize_t power_supply_show_property(struct device *dev, if (ret < 0) { if (ret == -ENODATA) - dev_dbg(dev, "driver has no data for `%s' property\n", + dev_dbg_ratelimited(dev, + "driver has no data for `%s' property\n", attr->attr.name); else if (ret != -ENODEV && ret != -EAGAIN) dev_err_ratelimited(dev, diff --git a/drivers/power/supply/rt9467-charger.c b/drivers/power/supply/rt9467-charger.c index 73f744a3155d..ea33693b6977 100644 --- a/drivers/power/supply/rt9467-charger.c +++ b/drivers/power/supply/rt9467-charger.c @@ -1023,7 +1023,7 @@ static int rt9467_request_interrupt(struct rt9467_chg_data *data) for (i = 0; i < num_chg_irqs; i++) { virq = regmap_irq_get_virq(data->irq_chip_data, chg_irqs[i].hwirq); if (virq <= 0) - return dev_err_probe(dev, virq, "Failed to get (%s) irq\n", + return dev_err_probe(dev, -EINVAL, "Failed to get (%s) irq\n", chg_irqs[i].name); ret = devm_request_threaded_irq(dev, virq, NULL, chg_irqs[i].handler, diff --git a/drivers/power/supply/sbs-charger.c b/drivers/power/supply/sbs-charger.c index 75ebcbf0a788..a14e89ac0369 100644 --- a/drivers/power/supply/sbs-charger.c +++ b/drivers/power/supply/sbs-charger.c @@ -24,7 +24,7 @@ #define SBS_CHARGER_REG_STATUS 0x13 #define SBS_CHARGER_REG_ALARM_WARNING 0x16 -#define SBS_CHARGER_STATUS_CHARGE_INHIBITED BIT(1) +#define SBS_CHARGER_STATUS_CHARGE_INHIBITED BIT(0) #define SBS_CHARGER_STATUS_RES_COLD BIT(9) #define SBS_CHARGER_STATUS_RES_HOT BIT(10) #define SBS_CHARGER_STATUS_BATTERY_PRESENT BIT(14) diff --git a/drivers/power/supply/sc27xx_fuel_gauge.c b/drivers/power/supply/sc27xx_fuel_gauge.c index 632977f84b95..bd23c4d9fed4 100644 --- a/drivers/power/supply/sc27xx_fuel_gauge.c +++ b/drivers/power/supply/sc27xx_fuel_gauge.c @@ -733,13 +733,6 @@ static int sc27xx_fgu_set_property(struct power_supply *psy, return ret; } -static void sc27xx_fgu_external_power_changed(struct power_supply *psy) -{ - struct sc27xx_fgu_data *data = power_supply_get_drvdata(psy); - - power_supply_changed(data->battery); -} - static int sc27xx_fgu_property_is_writeable(struct power_supply *psy, enum power_supply_property psp) { @@ -774,7 +767,7 @@ static const struct power_supply_desc sc27xx_fgu_desc = { .num_properties = ARRAY_SIZE(sc27xx_fgu_props), .get_property = sc27xx_fgu_get_property, .set_property = sc27xx_fgu_set_property, - .external_power_changed = sc27xx_fgu_external_power_changed, + .external_power_changed = power_supply_changed, .property_is_writeable = sc27xx_fgu_property_is_writeable, .no_thermal = true, }; diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index dc741ac156c3..698ab7f5004b 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -5256,7 +5256,7 @@ static void rdev_init_debugfs(struct regulator_dev *rdev) } rdev->debugfs = debugfs_create_dir(rname, debugfs_root); - if (!rdev->debugfs) { + if (IS_ERR(rdev->debugfs)) { rdev_warn(rdev, "Failed to create debugfs directory\n"); return; } @@ -6178,7 +6178,7 @@ static int __init regulator_init(void) ret = class_register(®ulator_class); debugfs_root = debugfs_create_dir("regulator", NULL); - if (!debugfs_root) + if (IS_ERR(debugfs_root)) pr_warn("regulator: Failed to create debugfs directory\n"); #ifdef CONFIG_DEBUG_FS diff --git a/drivers/regulator/mt6359-regulator.c b/drivers/regulator/mt6359-regulator.c index 1849566784ab..3eb86ec21d08 100644 --- a/drivers/regulator/mt6359-regulator.c +++ b/drivers/regulator/mt6359-regulator.c @@ -951,9 +951,12 @@ static int mt6359_regulator_probe(struct platform_device *pdev) struct regulator_config config = {}; struct regulator_dev *rdev; struct mt6359_regulator_info *mt6359_info; - int i, hw_ver; + int i, hw_ver, ret; + + ret = regmap_read(mt6397->regmap, MT6359P_HWCID, &hw_ver); + if (ret) + return ret; - regmap_read(mt6397->regmap, MT6359P_HWCID, &hw_ver); if (hw_ver >= MT6359P_CHIP_VER) mt6359_info = mt6359p_regulators; else diff --git a/drivers/regulator/pca9450-regulator.c b/drivers/regulator/pca9450-regulator.c index 87a746dcb516..e75dd92f86ca 100644 --- a/drivers/regulator/pca9450-regulator.c +++ b/drivers/regulator/pca9450-regulator.c @@ -264,7 +264,7 @@ static const struct pca9450_regulator_desc pca9450a_regulators[] = { .vsel_reg = PCA9450_REG_BUCK2OUT_DVS0, .vsel_mask = BUCK2OUT_DVS0_MASK, .enable_reg = PCA9450_REG_BUCK2CTRL, - .enable_mask = BUCK1_ENMODE_MASK, + .enable_mask = BUCK2_ENMODE_MASK, .ramp_reg = PCA9450_REG_BUCK2CTRL, .ramp_mask = BUCK2_RAMP_MASK, .ramp_delay_table = pca9450_dvs_buck_ramp_table, @@ -502,7 +502,7 @@ static const struct pca9450_regulator_desc pca9450bc_regulators[] = { .vsel_reg = PCA9450_REG_BUCK2OUT_DVS0, .vsel_mask = BUCK2OUT_DVS0_MASK, .enable_reg = PCA9450_REG_BUCK2CTRL, - .enable_mask = BUCK1_ENMODE_MASK, + .enable_mask = BUCK2_ENMODE_MASK, .ramp_reg = PCA9450_REG_BUCK2CTRL, .ramp_mask = BUCK2_RAMP_MASK, .ramp_delay_table = pca9450_dvs_buck_ramp_table, diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c index ade1369fe5ed..113c509bf6d0 100644 --- a/drivers/s390/block/dasd_eckd.c +++ b/drivers/s390/block/dasd_eckd.c @@ -127,6 +127,8 @@ static int prepare_itcw(struct itcw *, unsigned int, unsigned int, int, struct dasd_device *, struct dasd_device *, unsigned int, int, unsigned int, unsigned int, unsigned int, unsigned int); +static int dasd_eckd_query_pprc_status(struct dasd_device *, + struct dasd_pprc_data_sc4 *); /* initial attempt at a probe function. this can be simplified once * the other detection code is gone */ @@ -3733,6 +3735,26 @@ static int count_exts(unsigned int from, unsigned int to, int trks_per_ext) return count; } +static int dasd_in_copy_relation(struct dasd_device *device) +{ + struct dasd_pprc_data_sc4 *temp; + int rc; + + if (!dasd_eckd_pprc_enabled(device)) + return 0; + + temp = kzalloc(sizeof(*temp), GFP_KERNEL); + if (!temp) + return -ENOMEM; + + rc = dasd_eckd_query_pprc_status(device, temp); + if (!rc) + rc = temp->dev_info[0].state; + + kfree(temp); + return rc; +} + /* * Release allocated space for a given range or an entire volume. */ @@ -3749,6 +3771,7 @@ dasd_eckd_dso_ras(struct dasd_device *device, struct dasd_block *block, int cur_to_trk, cur_from_trk; struct dasd_ccw_req *cqr; u32 beg_cyl, end_cyl; + int copy_relation; struct ccw1 *ccw; int trks_per_ext; size_t ras_size; @@ -3760,6 +3783,10 @@ dasd_eckd_dso_ras(struct dasd_device *device, struct dasd_block *block, if (dasd_eckd_ras_sanity_checks(device, first_trk, last_trk)) return ERR_PTR(-EINVAL); + copy_relation = dasd_in_copy_relation(device); + if (copy_relation < 0) + return ERR_PTR(copy_relation); + rq = req ? blk_mq_rq_to_pdu(req) : NULL; features = &private->features; @@ -3788,9 +3815,11 @@ dasd_eckd_dso_ras(struct dasd_device *device, struct dasd_block *block, /* * This bit guarantees initialisation of tracks within an extent that is * not fully specified, but is only supported with a certain feature - * subset. + * subset and for devices not in a copy relation. */ - ras_data->op_flags.guarantee_init = !!(features->feature[56] & 0x01); + if (features->feature[56] & 0x01 && !copy_relation) + ras_data->op_flags.guarantee_init = 1; + ras_data->lss = private->conf.ned->ID; ras_data->dev_addr = private->conf.ned->unit_addr; ras_data->nr_exts = nr_exts; diff --git a/drivers/s390/cio/device.c b/drivers/s390/cio/device.c index 8eb089b99cde..d5c43e9b5128 100644 --- a/drivers/s390/cio/device.c +++ b/drivers/s390/cio/device.c @@ -1111,6 +1111,8 @@ static void io_subchannel_verify(struct subchannel *sch) cdev = sch_get_cdev(sch); if (cdev) dev_fsm_event(cdev, DEV_EVENT_VERIFY); + else + css_schedule_eval(sch->schid); } static void io_subchannel_terminate_path(struct subchannel *sch, u8 mask) diff --git a/drivers/s390/cio/qdio.h b/drivers/s390/cio/qdio.h index 5ea6249d8180..641f0dbb65a9 100644 --- a/drivers/s390/cio/qdio.h +++ b/drivers/s390/cio/qdio.h @@ -95,7 +95,7 @@ static inline int do_sqbs(u64 token, unsigned char state, int queue, " lgr 1,%[token]\n" " .insn rsy,0xeb000000008a,%[qs],%[ccq],0(%[state])" : [ccq] "+&d" (_ccq), [qs] "+&d" (_queuestart) - : [state] "d" ((unsigned long)state), [token] "d" (token) + : [state] "a" ((unsigned long)state), [token] "d" (token) : "memory", "cc", "1"); *count = _ccq & 0xff; *start = _queuestart & 0xff; diff --git a/drivers/s390/crypto/pkey_api.c b/drivers/s390/crypto/pkey_api.c index 5a05d1cdfec2..a8def50c149b 100644 --- a/drivers/s390/crypto/pkey_api.c +++ b/drivers/s390/crypto/pkey_api.c @@ -1293,6 +1293,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, return PTR_ERR(kkey); rc = pkey_keyblob2pkey(kkey, ktp.keylen, &ktp.protkey); DEBUG_DBG("%s pkey_keyblob2pkey()=%d\n", __func__, rc); + memzero_explicit(kkey, ktp.keylen); kfree(kkey); if (rc) break; @@ -1426,6 +1427,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, kkey, ktp.keylen, &ktp.protkey); DEBUG_DBG("%s pkey_keyblob2pkey2()=%d\n", __func__, rc); kfree(apqns); + memzero_explicit(kkey, ktp.keylen); kfree(kkey); if (rc) break; @@ -1552,6 +1554,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, protkey, &protkeylen); DEBUG_DBG("%s pkey_keyblob2pkey3()=%d\n", __func__, rc); kfree(apqns); + memzero_explicit(kkey, ktp.keylen); kfree(kkey); if (rc) { kfree(protkey); diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index b7c569a42aa4..0226c9279cef 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -1463,6 +1463,8 @@ static int scsi_dispatch_cmd(struct scsi_cmnd *cmd) struct Scsi_Host *host = cmd->device->host; int rtn = 0; + atomic_inc(&cmd->device->iorequest_cnt); + /* check if the device is still usable */ if (unlikely(cmd->device->sdev_state == SDEV_DEL)) { /* in SDEV_DEL we error all commands. DID_NO_CONNECT @@ -1483,6 +1485,7 @@ static int scsi_dispatch_cmd(struct scsi_cmnd *cmd) */ SCSI_LOG_MLQUEUE(3, scmd_printk(KERN_INFO, cmd, "queuecommand : device blocked\n")); + atomic_dec(&cmd->device->iorequest_cnt); return SCSI_MLQUEUE_DEVICE_BUSY; } @@ -1515,6 +1518,7 @@ static int scsi_dispatch_cmd(struct scsi_cmnd *cmd) trace_scsi_dispatch_cmd_start(cmd); rtn = host->hostt->queuecommand(host, cmd); if (rtn) { + atomic_dec(&cmd->device->iorequest_cnt); trace_scsi_dispatch_cmd_error(cmd, rtn); if (rtn != SCSI_MLQUEUE_DEVICE_BUSY && rtn != SCSI_MLQUEUE_TARGET_BUSY) @@ -1761,7 +1765,6 @@ static blk_status_t scsi_queue_rq(struct blk_mq_hw_ctx *hctx, goto out_dec_host_busy; } - atomic_inc(&cmd->device->iorequest_cnt); return BLK_STS_OK; out_dec_host_busy: diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index d9ce379c4d2e..e6bc622954cf 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -1780,7 +1780,7 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd) length = scsi_bufflen(scmnd); payload = (struct vmbus_packet_mpb_array *)&cmd_request->mpb; - payload_sz = sizeof(cmd_request->mpb); + payload_sz = 0; if (scsi_sg_count(scmnd)) { unsigned long offset_in_hvpg = offset_in_hvpage(sgl->offset); @@ -1789,10 +1789,10 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd) unsigned long hvpfn, hvpfns_to_add; int j, i = 0, sg_count; - if (hvpg_count > MAX_PAGE_BUFFER_COUNT) { + payload_sz = (hvpg_count * sizeof(u64) + + sizeof(struct vmbus_packet_mpb_array)); - payload_sz = (hvpg_count * sizeof(u64) + - sizeof(struct vmbus_packet_mpb_array)); + if (hvpg_count > MAX_PAGE_BUFFER_COUNT) { payload = kzalloc(payload_sz, GFP_ATOMIC); if (!payload) return SCSI_MLQUEUE_DEVICE_BUSY; diff --git a/drivers/spi/spi-cadence.c b/drivers/spi/spi-cadence.c index ac85d5562212..26e663369319 100644 --- a/drivers/spi/spi-cadence.c +++ b/drivers/spi/spi-cadence.c @@ -12,6 +12,7 @@ #include <linux/gpio/consumer.h> #include <linux/interrupt.h> #include <linux/io.h> +#include <linux/kernel.h> #include <linux/module.h> #include <linux/of_irq.h> #include <linux/of_address.h> @@ -301,49 +302,43 @@ static int cdns_spi_setup_transfer(struct spi_device *spi, } /** - * cdns_spi_fill_tx_fifo - Fills the TX FIFO with as many bytes as possible + * cdns_spi_process_fifo - Fills the TX FIFO, and drain the RX FIFO * @xspi: Pointer to the cdns_spi structure + * @ntx: Number of bytes to pack into the TX FIFO + * @nrx: Number of bytes to drain from the RX FIFO */ -static void cdns_spi_fill_tx_fifo(struct cdns_spi *xspi) +static void cdns_spi_process_fifo(struct cdns_spi *xspi, int ntx, int nrx) { - unsigned long trans_cnt = 0; + ntx = clamp(ntx, 0, xspi->tx_bytes); + nrx = clamp(nrx, 0, xspi->rx_bytes); - while ((trans_cnt < xspi->tx_fifo_depth) && - (xspi->tx_bytes > 0)) { + xspi->tx_bytes -= ntx; + xspi->rx_bytes -= nrx; + while (ntx || nrx) { /* When xspi in busy condition, bytes may send failed, * then spi control did't work thoroughly, add one byte delay */ - if (cdns_spi_read(xspi, CDNS_SPI_ISR) & - CDNS_SPI_IXR_TXFULL) + if (cdns_spi_read(xspi, CDNS_SPI_ISR) & CDNS_SPI_IXR_TXFULL) udelay(10); - if (xspi->txbuf) - cdns_spi_write(xspi, CDNS_SPI_TXD, *xspi->txbuf++); - else - cdns_spi_write(xspi, CDNS_SPI_TXD, 0); + if (ntx) { + if (xspi->txbuf) + cdns_spi_write(xspi, CDNS_SPI_TXD, *xspi->txbuf++); + else + cdns_spi_write(xspi, CDNS_SPI_TXD, 0); - xspi->tx_bytes--; - trans_cnt++; - } -} + ntx--; + } -/** - * cdns_spi_read_rx_fifo - Reads the RX FIFO with as many bytes as possible - * @xspi: Pointer to the cdns_spi structure - * @count: Read byte count - */ -static void cdns_spi_read_rx_fifo(struct cdns_spi *xspi, unsigned long count) -{ - u8 data; - - /* Read out the data from the RX FIFO */ - while (count > 0) { - data = cdns_spi_read(xspi, CDNS_SPI_RXD); - if (xspi->rxbuf) - *xspi->rxbuf++ = data; - xspi->rx_bytes--; - count--; + if (nrx) { + u8 data = cdns_spi_read(xspi, CDNS_SPI_RXD); + + if (xspi->rxbuf) + *xspi->rxbuf++ = data; + + nrx--; + } } } @@ -381,33 +376,22 @@ static irqreturn_t cdns_spi_irq(int irq, void *dev_id) spi_finalize_current_transfer(ctlr); status = IRQ_HANDLED; } else if (intr_status & CDNS_SPI_IXR_TXOW) { - int trans_cnt = cdns_spi_read(xspi, CDNS_SPI_THLD); + int threshold = cdns_spi_read(xspi, CDNS_SPI_THLD); + int trans_cnt = xspi->rx_bytes - xspi->tx_bytes; + + if (threshold > 1) + trans_cnt -= threshold; + /* Set threshold to one if number of pending are * less than half fifo */ if (xspi->tx_bytes < xspi->tx_fifo_depth >> 1) cdns_spi_write(xspi, CDNS_SPI_THLD, 1); - while (trans_cnt) { - cdns_spi_read_rx_fifo(xspi, 1); - - if (xspi->tx_bytes) { - if (xspi->txbuf) - cdns_spi_write(xspi, CDNS_SPI_TXD, - *xspi->txbuf++); - else - cdns_spi_write(xspi, CDNS_SPI_TXD, 0); - xspi->tx_bytes--; - } - trans_cnt--; - } - if (!xspi->tx_bytes) { - /* Fixed delay due to controller limitation with - * RX_NEMPTY incorrect status - * Xilinx AR:65885 contains more details - */ - udelay(10); - cdns_spi_read_rx_fifo(xspi, xspi->rx_bytes); + if (xspi->tx_bytes) { + cdns_spi_process_fifo(xspi, trans_cnt, trans_cnt); + } else { + cdns_spi_process_fifo(xspi, 0, trans_cnt); cdns_spi_write(xspi, CDNS_SPI_IDR, CDNS_SPI_IXR_DEFAULT); spi_finalize_current_transfer(ctlr); @@ -450,16 +434,17 @@ static int cdns_transfer_one(struct spi_controller *ctlr, xspi->tx_bytes = transfer->len; xspi->rx_bytes = transfer->len; - if (!spi_controller_is_slave(ctlr)) + if (!spi_controller_is_slave(ctlr)) { cdns_spi_setup_transfer(spi, transfer); + } else { + /* Set TX empty threshold to half of FIFO depth + * only if TX bytes are more than half FIFO depth. + */ + if (xspi->tx_bytes > xspi->tx_fifo_depth) + cdns_spi_write(xspi, CDNS_SPI_THLD, xspi->tx_fifo_depth >> 1); + } - /* Set TX empty threshold to half of FIFO depth - * only if TX bytes are more than half FIFO depth. - */ - if (xspi->tx_bytes > (xspi->tx_fifo_depth >> 1)) - cdns_spi_write(xspi, CDNS_SPI_THLD, xspi->tx_fifo_depth >> 1); - - cdns_spi_fill_tx_fifo(xspi); + cdns_spi_process_fifo(xspi, xspi->tx_fifo_depth, 0); spi_transfer_delay_exec(transfer); cdns_spi_write(xspi, CDNS_SPI_IER, CDNS_SPI_IXR_DEFAULT); diff --git a/drivers/spi/spi-dw-mmio.c b/drivers/spi/spi-dw-mmio.c index 5e6faa98aa85..5f2aee69c1c1 100644 --- a/drivers/spi/spi-dw-mmio.c +++ b/drivers/spi/spi-dw-mmio.c @@ -264,17 +264,17 @@ static void dw_spi_elba_set_cs(struct spi_device *spi, bool enable) struct regmap *syscon = dwsmmio->priv; u8 cs; - cs = spi->chip_select; + cs = spi_get_chipselect(spi, 0); if (cs < 2) - dw_spi_elba_override_cs(syscon, spi->chip_select, enable); + dw_spi_elba_override_cs(syscon, spi_get_chipselect(spi, 0), enable); /* * The DW SPI controller needs a native CS bit selected to start * the serial engine. */ - spi->chip_select = 0; + spi_set_chipselect(spi, 0, 0); dw_spi_set_cs(spi, enable); - spi->chip_select = cs; + spi_get_chipselect(spi, cs); } static int dw_spi_elba_init(struct platform_device *pdev, diff --git a/drivers/spi/spi-geni-qcom.c b/drivers/spi/spi-geni-qcom.c index ba7be505ec4e..a98b781b103a 100644 --- a/drivers/spi/spi-geni-qcom.c +++ b/drivers/spi/spi-geni-qcom.c @@ -294,6 +294,8 @@ static void spi_geni_set_cs(struct spi_device *slv, bool set_flag) mas->cs_flag = set_flag; /* set xfer_mode to FIFO to complete cs_done in isr */ mas->cur_xfer_mode = GENI_SE_FIFO; + geni_se_select_mode(se, mas->cur_xfer_mode); + reinit_completion(&mas->cs_done); if (set_flag) geni_se_setup_m_cmd(se, SPI_CS_ASSERT, 0); diff --git a/drivers/tee/optee/smc_abi.c b/drivers/tee/optee/smc_abi.c index 49702cb08f4f..3861ae06d902 100644 --- a/drivers/tee/optee/smc_abi.c +++ b/drivers/tee/optee/smc_abi.c @@ -1004,8 +1004,10 @@ static u32 get_async_notif_value(optee_invoke_fn *invoke_fn, bool *value_valid, invoke_fn(OPTEE_SMC_GET_ASYNC_NOTIF_VALUE, 0, 0, 0, 0, 0, 0, 0, &res); - if (res.a0) + if (res.a0) { + *value_valid = false; return 0; + } *value_valid = (res.a2 & OPTEE_SMC_ASYNC_NOTIF_VALUE_VALID); *value_pending = (res.a2 & OPTEE_SMC_ASYNC_NOTIF_VALUE_PENDING); return res.a1; diff --git a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c index 810231b59dcd..5e1164226ada 100644 --- a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c +++ b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c @@ -131,7 +131,7 @@ static ssize_t available_uuids_show(struct device *dev, for (i = 0; i < INT3400_THERMAL_MAXIMUM_UUID; i++) { if (priv->uuid_bitmap & (1 << i)) - length += sysfs_emit_at(buf, length, int3400_thermal_uuids[i]); + length += sysfs_emit_at(buf, length, "%s\n", int3400_thermal_uuids[i]); } return length; @@ -149,7 +149,7 @@ static ssize_t current_uuid_show(struct device *dev, for (i = 0; i <= INT3400_THERMAL_CRITICAL; i++) { if (priv->os_uuid_mask & BIT(i)) - length += sysfs_emit_at(buf, length, int3400_thermal_uuids[i]); + length += sysfs_emit_at(buf, length, "%s\n", int3400_thermal_uuids[i]); } if (length) diff --git a/drivers/thunderbolt/nhi.c b/drivers/thunderbolt/nhi.c index d76e923fbc6a..c0aee5dc5237 100644 --- a/drivers/thunderbolt/nhi.c +++ b/drivers/thunderbolt/nhi.c @@ -54,6 +54,21 @@ static int ring_interrupt_index(const struct tb_ring *ring) return bit; } +static void nhi_mask_interrupt(struct tb_nhi *nhi, int mask, int ring) +{ + if (nhi->quirks & QUIRK_AUTO_CLEAR_INT) + return; + iowrite32(mask, nhi->iobase + REG_RING_INTERRUPT_MASK_CLEAR_BASE + ring); +} + +static void nhi_clear_interrupt(struct tb_nhi *nhi, int ring) +{ + if (nhi->quirks & QUIRK_AUTO_CLEAR_INT) + ioread32(nhi->iobase + REG_RING_NOTIFY_BASE + ring); + else + iowrite32(~0, nhi->iobase + REG_RING_INT_CLEAR + ring); +} + /* * ring_interrupt_active() - activate/deactivate interrupts for a single ring * @@ -61,8 +76,8 @@ static int ring_interrupt_index(const struct tb_ring *ring) */ static void ring_interrupt_active(struct tb_ring *ring, bool active) { - int reg = REG_RING_INTERRUPT_BASE + - ring_interrupt_index(ring) / 32 * 4; + int index = ring_interrupt_index(ring) / 32 * 4; + int reg = REG_RING_INTERRUPT_BASE + index; int interrupt_bit = ring_interrupt_index(ring) & 31; int mask = 1 << interrupt_bit; u32 old, new; @@ -123,7 +138,11 @@ static void ring_interrupt_active(struct tb_ring *ring, bool active) "interrupt for %s %d is already %s\n", RING_TYPE(ring), ring->hop, active ? "enabled" : "disabled"); - iowrite32(new, ring->nhi->iobase + reg); + + if (active) + iowrite32(new, ring->nhi->iobase + reg); + else + nhi_mask_interrupt(ring->nhi, mask, index); } /* @@ -136,11 +155,11 @@ static void nhi_disable_interrupts(struct tb_nhi *nhi) int i = 0; /* disable interrupts */ for (i = 0; i < RING_INTERRUPT_REG_COUNT(nhi); i++) - iowrite32(0, nhi->iobase + REG_RING_INTERRUPT_BASE + 4 * i); + nhi_mask_interrupt(nhi, ~0, 4 * i); /* clear interrupt status bits */ for (i = 0; i < RING_NOTIFY_REG_COUNT(nhi); i++) - ioread32(nhi->iobase + REG_RING_NOTIFY_BASE + 4 * i); + nhi_clear_interrupt(nhi, 4 * i); } /* ring helper methods */ diff --git a/drivers/thunderbolt/nhi_regs.h b/drivers/thunderbolt/nhi_regs.h index faef165a919c..6ba295815477 100644 --- a/drivers/thunderbolt/nhi_regs.h +++ b/drivers/thunderbolt/nhi_regs.h @@ -93,6 +93,8 @@ struct ring_desc { #define REG_RING_INTERRUPT_BASE 0x38200 #define RING_INTERRUPT_REG_COUNT(nhi) ((31 + 2 * nhi->hop_count) / 32) +#define REG_RING_INTERRUPT_MASK_CLEAR_BASE 0x38208 + #define REG_INT_THROTTLING_RATE 0x38c00 /* Interrupt Vector Allocation */ diff --git a/drivers/tty/serial/8250/8250_bcm7271.c b/drivers/tty/serial/8250/8250_bcm7271.c index f801b1f5b46c..af0e1c070187 100644 --- a/drivers/tty/serial/8250/8250_bcm7271.c +++ b/drivers/tty/serial/8250/8250_bcm7271.c @@ -1012,7 +1012,7 @@ static int brcmuart_probe(struct platform_device *pdev) of_property_read_u32(np, "clock-frequency", &clk_rate); /* See if a Baud clock has been specified */ - baud_mux_clk = of_clk_get_by_name(np, "sw_baud"); + baud_mux_clk = devm_clk_get(dev, "sw_baud"); if (IS_ERR(baud_mux_clk)) { if (PTR_ERR(baud_mux_clk) == -EPROBE_DEFER) { ret = -EPROBE_DEFER; @@ -1032,7 +1032,7 @@ static int brcmuart_probe(struct platform_device *pdev) if (clk_rate == 0) { dev_err(dev, "clock-frequency or clk not defined\n"); ret = -EINVAL; - goto release_dma; + goto err_clk_disable; } dev_dbg(dev, "DMA is %senabled\n", priv->dma_enabled ? "" : "not "); @@ -1119,6 +1119,8 @@ err1: serial8250_unregister_port(priv->line); err: brcmuart_free_bufs(dev, priv); +err_clk_disable: + clk_disable_unprepare(baud_mux_clk); release_dma: if (priv->dma_enabled) brcmuart_arbitration(priv, 0); @@ -1133,6 +1135,7 @@ static int brcmuart_remove(struct platform_device *pdev) hrtimer_cancel(&priv->hrt); serial8250_unregister_port(priv->line); brcmuart_free_bufs(&pdev->dev, priv); + clk_disable_unprepare(priv->baud_mux_clk); if (priv->dma_enabled) brcmuart_arbitration(priv, 0); return 0; diff --git a/drivers/tty/serial/8250/8250_exar.c b/drivers/tty/serial/8250/8250_exar.c index 64770c62bbec..b406cba10b0e 100644 --- a/drivers/tty/serial/8250/8250_exar.c +++ b/drivers/tty/serial/8250/8250_exar.c @@ -40,9 +40,13 @@ #define PCI_DEVICE_ID_COMMTECH_4224PCIE 0x0020 #define PCI_DEVICE_ID_COMMTECH_4228PCIE 0x0021 #define PCI_DEVICE_ID_COMMTECH_4222PCIE 0x0022 + #define PCI_DEVICE_ID_EXAR_XR17V4358 0x4358 #define PCI_DEVICE_ID_EXAR_XR17V8358 0x8358 +#define PCI_SUBDEVICE_ID_USR_2980 0x0128 +#define PCI_SUBDEVICE_ID_USR_2981 0x0129 + #define PCI_DEVICE_ID_SEALEVEL_710xC 0x1001 #define PCI_DEVICE_ID_SEALEVEL_720xC 0x1002 #define PCI_DEVICE_ID_SEALEVEL_740xC 0x1004 @@ -829,6 +833,15 @@ static const struct exar8250_board pbn_exar_XR17V8358 = { (kernel_ulong_t)&bd \ } +#define USR_DEVICE(devid, sdevid, bd) { \ + PCI_DEVICE_SUB( \ + PCI_VENDOR_ID_USR, \ + PCI_DEVICE_ID_EXAR_##devid, \ + PCI_VENDOR_ID_EXAR, \ + PCI_SUBDEVICE_ID_USR_##sdevid), 0, 0, \ + (kernel_ulong_t)&bd \ + } + static const struct pci_device_id exar_pci_tbl[] = { EXAR_DEVICE(ACCESSIO, COM_2S, pbn_exar_XR17C15x), EXAR_DEVICE(ACCESSIO, COM_4S, pbn_exar_XR17C15x), @@ -853,6 +866,10 @@ static const struct pci_device_id exar_pci_tbl[] = { IBM_DEVICE(XR17C152, SATURN_SERIAL_ONE_PORT, pbn_exar_ibm_saturn), + /* USRobotics USR298x-OEM PCI Modems */ + USR_DEVICE(XR17C152, 2980, pbn_exar_XR17C15x), + USR_DEVICE(XR17C152, 2981, pbn_exar_XR17C15x), + /* Exar Corp. XR17C15[248] Dual/Quad/Octal UART */ EXAR_DEVICE(EXAR, XR17C152, pbn_exar_XR17C15x), EXAR_DEVICE(EXAR, XR17C154, pbn_exar_XR17C15x), diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c index c55be6fda0ca..e80c4f6551a1 100644 --- a/drivers/tty/serial/8250/8250_pci.c +++ b/drivers/tty/serial/8250/8250_pci.c @@ -1920,6 +1920,8 @@ pci_moxa_setup(struct serial_private *priv, #define PCI_SUBDEVICE_ID_SIIG_DUAL_30 0x2530 #define PCI_VENDOR_ID_ADVANTECH 0x13fe #define PCI_DEVICE_ID_INTEL_CE4100_UART 0x2e66 +#define PCI_DEVICE_ID_ADVANTECH_PCI1600 0x1600 +#define PCI_DEVICE_ID_ADVANTECH_PCI1600_1611 0x1611 #define PCI_DEVICE_ID_ADVANTECH_PCI3620 0x3620 #define PCI_DEVICE_ID_ADVANTECH_PCI3618 0x3618 #define PCI_DEVICE_ID_ADVANTECH_PCIf618 0xf618 @@ -4085,6 +4087,9 @@ static SIMPLE_DEV_PM_OPS(pciserial_pm_ops, pciserial_suspend_one, pciserial_resume_one); static const struct pci_device_id serial_pci_tbl[] = { + { PCI_VENDOR_ID_ADVANTECH, PCI_DEVICE_ID_ADVANTECH_PCI1600, + PCI_DEVICE_ID_ADVANTECH_PCI1600_1611, PCI_ANY_ID, 0, 0, + pbn_b0_4_921600 }, /* Advantech use PCI_DEVICE_ID_ADVANTECH_PCI3620 (0x3620) as 'PCI_SUBVENDOR_ID' */ { PCI_VENDOR_ID_ADVANTECH, PCI_DEVICE_ID_ADVANTECH_PCI3620, PCI_DEVICE_ID_ADVANTECH_PCI3620, 0x0001, 0, 0, diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index fe8d79c4ae95..c153ba3a018a 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -669,6 +669,7 @@ EXPORT_SYMBOL_GPL(serial8250_em485_supported); /** * serial8250_em485_config() - generic ->rs485_config() callback * @port: uart port + * @termios: termios structure * @rs485: rs485 settings * * Generic callback usable by 8250 uart drivers to activate rs485 settings diff --git a/drivers/tty/serial/arc_uart.c b/drivers/tty/serial/arc_uart.c index 59e25f2b6632..4b2512eef577 100644 --- a/drivers/tty/serial/arc_uart.c +++ b/drivers/tty/serial/arc_uart.c @@ -606,10 +606,11 @@ static int arc_serial_probe(struct platform_device *pdev) } uart->baud = val; - port->membase = of_iomap(np, 0); - if (!port->membase) + port->membase = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(port->membase)) { /* No point of dev_err since UART itself is hosed here */ - return -ENXIO; + return PTR_ERR(port->membase); + } port->irq = irq_of_parse_and_map(np, 0); diff --git a/drivers/tty/serial/qcom_geni_serial.c b/drivers/tty/serial/qcom_geni_serial.c index 08dc3e2a729c..8582479f0211 100644 --- a/drivers/tty/serial/qcom_geni_serial.c +++ b/drivers/tty/serial/qcom_geni_serial.c @@ -1664,19 +1664,18 @@ static int qcom_geni_serial_probe(struct platform_device *pdev) uport->private_data = &port->private_data; platform_set_drvdata(pdev, port); - ret = uart_add_one_port(drv, uport); - if (ret) - return ret; - irq_set_status_flags(uport->irq, IRQ_NOAUTOEN); ret = devm_request_irq(uport->dev, uport->irq, qcom_geni_serial_isr, IRQF_TRIGGER_HIGH, port->name, uport); if (ret) { dev_err(uport->dev, "Failed to get IRQ ret %d\n", ret); - uart_remove_one_port(drv, uport); return ret; } + ret = uart_add_one_port(drv, uport); + if (ret) + return ret; + /* * Set pm_runtime status as ACTIVE so that wakeup_irq gets * enabled/disabled from dev_pm_arm_wake_irq during system diff --git a/drivers/tty/vt/vc_screen.c b/drivers/tty/vt/vc_screen.c index 498ba9c0ee93..829c4be66f3b 100644 --- a/drivers/tty/vt/vc_screen.c +++ b/drivers/tty/vt/vc_screen.c @@ -656,10 +656,17 @@ vcs_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) } } - /* The vcs_size might have changed while we slept to grab - * the user buffer, so recheck. + /* The vc might have been freed or vcs_size might have changed + * while we slept to grab the user buffer, so recheck. * Return data written up to now on failure. */ + vc = vcs_vc(inode, &viewed); + if (!vc) { + if (written) + break; + ret = -ENXIO; + goto unlock_out; + } size = vcs_size(vc, attr, false); if (size < 0) { if (written) diff --git a/drivers/ufs/core/ufs-mcq.c b/drivers/ufs/core/ufs-mcq.c index 202ff71e1b58..51b3c6ae781d 100644 --- a/drivers/ufs/core/ufs-mcq.c +++ b/drivers/ufs/core/ufs-mcq.c @@ -150,7 +150,8 @@ static int ufshcd_mcq_config_nr_queues(struct ufs_hba *hba) u32 hba_maxq, rem, tot_queues; struct Scsi_Host *host = hba->host; - hba_maxq = FIELD_GET(MAX_QUEUE_SUP, hba->mcq_capabilities); + /* maxq is 0 based value */ + hba_maxq = FIELD_GET(MAX_QUEUE_SUP, hba->mcq_capabilities) + 1; tot_queues = UFS_MCQ_NUM_DEV_CMD_QUEUES + read_queues + poll_queues + rw_queues; @@ -265,7 +266,7 @@ static int ufshcd_mcq_get_tag(struct ufs_hba *hba, addr = (le64_to_cpu(cqe->command_desc_base_addr) & CQE_UCD_BA) - hba->ucdl_dma_addr; - return div_u64(addr, sizeof(struct utp_transfer_cmd_desc)); + return div_u64(addr, ufshcd_get_ucd_size(hba)); } static void ufshcd_mcq_process_cqe(struct ufs_hba *hba, diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index 45fd374fe56c..e7e79f515e14 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -2849,10 +2849,10 @@ static void ufshcd_map_queues(struct Scsi_Host *shost) static void ufshcd_init_lrb(struct ufs_hba *hba, struct ufshcd_lrb *lrb, int i) { struct utp_transfer_cmd_desc *cmd_descp = (void *)hba->ucdl_base_addr + - i * sizeof_utp_transfer_cmd_desc(hba); + i * ufshcd_get_ucd_size(hba); struct utp_transfer_req_desc *utrdlp = hba->utrdl_base_addr; dma_addr_t cmd_desc_element_addr = hba->ucdl_dma_addr + - i * sizeof_utp_transfer_cmd_desc(hba); + i * ufshcd_get_ucd_size(hba); u16 response_offset = offsetof(struct utp_transfer_cmd_desc, response_upiu); u16 prdt_offset = offsetof(struct utp_transfer_cmd_desc, prd_table); @@ -3761,7 +3761,7 @@ static int ufshcd_memory_alloc(struct ufs_hba *hba) size_t utmrdl_size, utrdl_size, ucdl_size; /* Allocate memory for UTP command descriptors */ - ucdl_size = sizeof_utp_transfer_cmd_desc(hba) * hba->nutrs; + ucdl_size = ufshcd_get_ucd_size(hba) * hba->nutrs; hba->ucdl_base_addr = dmam_alloc_coherent(hba->dev, ucdl_size, &hba->ucdl_dma_addr, @@ -3861,7 +3861,7 @@ static void ufshcd_host_memory_configure(struct ufs_hba *hba) prdt_offset = offsetof(struct utp_transfer_cmd_desc, prd_table); - cmd_desc_size = sizeof_utp_transfer_cmd_desc(hba); + cmd_desc_size = ufshcd_get_ucd_size(hba); cmd_desc_dma_addr = hba->ucdl_dma_addr; for (i = 0; i < hba->nutrs; i++) { @@ -8452,7 +8452,7 @@ static void ufshcd_release_sdb_queue(struct ufs_hba *hba, int nutrs) { size_t ucdl_size, utrdl_size; - ucdl_size = sizeof(struct utp_transfer_cmd_desc) * nutrs; + ucdl_size = ufshcd_get_ucd_size(hba) * nutrs; dmam_free_coherent(hba->dev, ucdl_size, hba->ucdl_base_addr, hba->ucdl_dma_addr); diff --git a/drivers/usb/class/usbtmc.c b/drivers/usb/class/usbtmc.c index 4bb6d304eb4b..311007b1d904 100644 --- a/drivers/usb/class/usbtmc.c +++ b/drivers/usb/class/usbtmc.c @@ -1928,6 +1928,8 @@ static int usbtmc_ioctl_request(struct usbtmc_device_data *data, if (request.req.wLength > USBTMC_BUFSIZE) return -EMSGSIZE; + if (request.req.wLength == 0) /* Length-0 requests are never IN */ + request.req.bRequestType &= ~USB_DIR_IN; is_in = request.req.bRequestType & USB_DIR_IN; diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index 0beaab932e7d..7b2ce013cc5b 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -1137,7 +1137,7 @@ static int dwc3_core_init(struct dwc3 *dwc) dwc3_set_incr_burst_type(dwc); - dwc3_phy_power_on(dwc); + ret = dwc3_phy_power_on(dwc); if (ret) goto err_exit_phy; diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h index d56457c02996..1f043c31a096 100644 --- a/drivers/usb/dwc3/core.h +++ b/drivers/usb/dwc3/core.h @@ -1116,6 +1116,7 @@ struct dwc3_scratchpad_array { * @dis_metastability_quirk: set to disable metastability quirk. * @dis_split_quirk: set to disable split boundary. * @wakeup_configured: set if the device is configured for remote wakeup. + * @suspended: set to track suspend event due to U3/L2. * @imod_interval: set the interrupt moderation interval in 250ns * increments or 0 to disable. * @max_cfg_eps: current max number of IN eps used across all USB configs. @@ -1332,6 +1333,7 @@ struct dwc3 { unsigned dis_split_quirk:1; unsigned async_callbacks:1; unsigned wakeup_configured:1; + unsigned suspended:1; u16 imod_interval; diff --git a/drivers/usb/dwc3/debugfs.c b/drivers/usb/dwc3/debugfs.c index e4a2560b9dc0..ebf03468fac4 100644 --- a/drivers/usb/dwc3/debugfs.c +++ b/drivers/usb/dwc3/debugfs.c @@ -332,6 +332,11 @@ static int dwc3_lsp_show(struct seq_file *s, void *unused) unsigned int current_mode; unsigned long flags; u32 reg; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); reg = dwc3_readl(dwc->regs, DWC3_GSTS); @@ -350,6 +355,8 @@ static int dwc3_lsp_show(struct seq_file *s, void *unused) } spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -395,6 +402,11 @@ static int dwc3_mode_show(struct seq_file *s, void *unused) struct dwc3 *dwc = s->private; unsigned long flags; u32 reg; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); reg = dwc3_readl(dwc->regs, DWC3_GCTL); @@ -414,6 +426,8 @@ static int dwc3_mode_show(struct seq_file *s, void *unused) seq_printf(s, "UNKNOWN %08x\n", DWC3_GCTL_PRTCAP(reg)); } + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -463,6 +477,11 @@ static int dwc3_testmode_show(struct seq_file *s, void *unused) struct dwc3 *dwc = s->private; unsigned long flags; u32 reg; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); reg = dwc3_readl(dwc->regs, DWC3_DCTL); @@ -493,6 +512,8 @@ static int dwc3_testmode_show(struct seq_file *s, void *unused) seq_printf(s, "UNKNOWN %d\n", reg); } + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -509,6 +530,7 @@ static ssize_t dwc3_testmode_write(struct file *file, unsigned long flags; u32 testmode = 0; char buf[32]; + int ret; if (copy_from_user(&buf, ubuf, min_t(size_t, sizeof(buf) - 1, count))) return -EFAULT; @@ -526,10 +548,16 @@ static ssize_t dwc3_testmode_write(struct file *file, else testmode = 0; + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; + spin_lock_irqsave(&dwc->lock, flags); dwc3_gadget_set_test_mode(dwc, testmode); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return count; } @@ -548,12 +576,18 @@ static int dwc3_link_state_show(struct seq_file *s, void *unused) enum dwc3_link_state state; u32 reg; u8 speed; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); reg = dwc3_readl(dwc->regs, DWC3_GSTS); if (DWC3_GSTS_CURMOD(reg) != DWC3_GSTS_CURMOD_DEVICE) { seq_puts(s, "Not available\n"); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); return 0; } @@ -566,6 +600,8 @@ static int dwc3_link_state_show(struct seq_file *s, void *unused) dwc3_gadget_hs_link_string(state)); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -584,6 +620,7 @@ static ssize_t dwc3_link_state_write(struct file *file, char buf[32]; u32 reg; u8 speed; + int ret; if (copy_from_user(&buf, ubuf, min_t(size_t, sizeof(buf) - 1, count))) return -EFAULT; @@ -603,10 +640,15 @@ static ssize_t dwc3_link_state_write(struct file *file, else return -EINVAL; + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; + spin_lock_irqsave(&dwc->lock, flags); reg = dwc3_readl(dwc->regs, DWC3_GSTS); if (DWC3_GSTS_CURMOD(reg) != DWC3_GSTS_CURMOD_DEVICE) { spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); return -EINVAL; } @@ -616,12 +658,15 @@ static ssize_t dwc3_link_state_write(struct file *file, if (speed < DWC3_DSTS_SUPERSPEED && state != DWC3_LINK_STATE_RECOV) { spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); return -EINVAL; } dwc3_gadget_set_link_state(dwc, state); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return count; } @@ -645,6 +690,11 @@ static int dwc3_tx_fifo_size_show(struct seq_file *s, void *unused) unsigned long flags; u32 mdwidth; u32 val; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); val = dwc3_core_fifo_space(dep, DWC3_TXFIFO); @@ -657,6 +707,8 @@ static int dwc3_tx_fifo_size_show(struct seq_file *s, void *unused) seq_printf(s, "%u\n", val); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -667,6 +719,11 @@ static int dwc3_rx_fifo_size_show(struct seq_file *s, void *unused) unsigned long flags; u32 mdwidth; u32 val; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); val = dwc3_core_fifo_space(dep, DWC3_RXFIFO); @@ -679,6 +736,8 @@ static int dwc3_rx_fifo_size_show(struct seq_file *s, void *unused) seq_printf(s, "%u\n", val); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -688,12 +747,19 @@ static int dwc3_tx_request_queue_show(struct seq_file *s, void *unused) struct dwc3 *dwc = dep->dwc; unsigned long flags; u32 val; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); val = dwc3_core_fifo_space(dep, DWC3_TXREQQ); seq_printf(s, "%u\n", val); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -703,12 +769,19 @@ static int dwc3_rx_request_queue_show(struct seq_file *s, void *unused) struct dwc3 *dwc = dep->dwc; unsigned long flags; u32 val; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); val = dwc3_core_fifo_space(dep, DWC3_RXREQQ); seq_printf(s, "%u\n", val); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -718,12 +791,19 @@ static int dwc3_rx_info_queue_show(struct seq_file *s, void *unused) struct dwc3 *dwc = dep->dwc; unsigned long flags; u32 val; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); val = dwc3_core_fifo_space(dep, DWC3_RXINFOQ); seq_printf(s, "%u\n", val); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -733,12 +813,19 @@ static int dwc3_descriptor_fetch_queue_show(struct seq_file *s, void *unused) struct dwc3 *dwc = dep->dwc; unsigned long flags; u32 val; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); val = dwc3_core_fifo_space(dep, DWC3_DESCFETCHQ); seq_printf(s, "%u\n", val); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -748,12 +835,19 @@ static int dwc3_event_queue_show(struct seq_file *s, void *unused) struct dwc3 *dwc = dep->dwc; unsigned long flags; u32 val; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); val = dwc3_core_fifo_space(dep, DWC3_EVENTQ); seq_printf(s, "%u\n", val); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -798,6 +892,11 @@ static int dwc3_trb_ring_show(struct seq_file *s, void *unused) struct dwc3 *dwc = dep->dwc; unsigned long flags; int i; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); if (dep->number <= 1) { @@ -827,6 +926,8 @@ static int dwc3_trb_ring_show(struct seq_file *s, void *unused) out: spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -839,6 +940,11 @@ static int dwc3_ep_info_register_show(struct seq_file *s, void *unused) u32 lower_32_bits; u32 upper_32_bits; u32 reg; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); reg = DWC3_GDBGLSPMUX_EPSELECT(dep->number); @@ -851,6 +957,8 @@ static int dwc3_ep_info_register_show(struct seq_file *s, void *unused) seq_printf(s, "0x%016llx\n", ep_info); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -910,6 +1018,7 @@ void dwc3_debugfs_init(struct dwc3 *dwc) dwc->regset->regs = dwc3_regs; dwc->regset->nregs = ARRAY_SIZE(dwc3_regs); dwc->regset->base = dwc->regs - DWC3_GLOBALS_REGS_START; + dwc->regset->dev = dwc->dev; root = debugfs_create_dir(dev_name(dwc->dev), usb_debug_root); dwc->debug_root = root; diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index c0ca4d12f95d..d831f5acf7b5 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -2440,6 +2440,7 @@ static int dwc3_gadget_func_wakeup(struct usb_gadget *g, int intf_id) return -EINVAL; } dwc3_resume_gadget(dwc); + dwc->suspended = false; dwc->link_state = DWC3_LINK_STATE_U0; } @@ -2699,6 +2700,21 @@ static int dwc3_gadget_soft_disconnect(struct dwc3 *dwc) return ret; } +static int dwc3_gadget_soft_connect(struct dwc3 *dwc) +{ + /* + * In the Synopsys DWC_usb31 1.90a programming guide section + * 4.1.9, it specifies that for a reconnect after a + * device-initiated disconnect requires a core soft reset + * (DCTL.CSftRst) before enabling the run/stop bit. + */ + dwc3_core_soft_reset(dwc); + + dwc3_event_buffers_setup(dwc); + __dwc3_gadget_start(dwc); + return dwc3_gadget_run_stop(dwc, true); +} + static int dwc3_gadget_pullup(struct usb_gadget *g, int is_on) { struct dwc3 *dwc = gadget_to_dwc(g); @@ -2737,21 +2753,10 @@ static int dwc3_gadget_pullup(struct usb_gadget *g, int is_on) synchronize_irq(dwc->irq_gadget); - if (!is_on) { + if (!is_on) ret = dwc3_gadget_soft_disconnect(dwc); - } else { - /* - * In the Synopsys DWC_usb31 1.90a programming guide section - * 4.1.9, it specifies that for a reconnect after a - * device-initiated disconnect requires a core soft reset - * (DCTL.CSftRst) before enabling the run/stop bit. - */ - dwc3_core_soft_reset(dwc); - - dwc3_event_buffers_setup(dwc); - __dwc3_gadget_start(dwc); - ret = dwc3_gadget_run_stop(dwc, true); - } + else + ret = dwc3_gadget_soft_connect(dwc); pm_runtime_put(dwc->dev); @@ -3938,6 +3943,8 @@ static void dwc3_gadget_disconnect_interrupt(struct dwc3 *dwc) { int reg; + dwc->suspended = false; + dwc3_gadget_set_link_state(dwc, DWC3_LINK_STATE_RX_DET); reg = dwc3_readl(dwc->regs, DWC3_DCTL); @@ -3962,6 +3969,8 @@ static void dwc3_gadget_reset_interrupt(struct dwc3 *dwc) { u32 reg; + dwc->suspended = false; + /* * Ideally, dwc3_reset_gadget() would trigger the function * drivers to stop any active transfers through ep disable. @@ -4180,6 +4189,8 @@ static void dwc3_gadget_conndone_interrupt(struct dwc3 *dwc) static void dwc3_gadget_wakeup_interrupt(struct dwc3 *dwc, unsigned int evtinfo) { + dwc->suspended = false; + /* * TODO take core out of low power mode when that's * implemented. @@ -4277,6 +4288,7 @@ static void dwc3_gadget_linksts_change_interrupt(struct dwc3 *dwc, if (dwc->gadget->wakeup_armed) { dwc3_gadget_enable_linksts_evts(dwc, false); dwc3_resume_gadget(dwc); + dwc->suspended = false; } break; case DWC3_LINK_STATE_U1: @@ -4303,8 +4315,10 @@ static void dwc3_gadget_suspend_interrupt(struct dwc3 *dwc, { enum dwc3_link_state next = evtinfo & DWC3_LINK_STATE_MASK; - if (dwc->link_state != next && next == DWC3_LINK_STATE_U3) + if (!dwc->suspended && next == DWC3_LINK_STATE_U3) { + dwc->suspended = true; dwc3_suspend_gadget(dwc); + } dwc->link_state = next; } @@ -4655,42 +4669,39 @@ void dwc3_gadget_exit(struct dwc3 *dwc) int dwc3_gadget_suspend(struct dwc3 *dwc) { unsigned long flags; + int ret; if (!dwc->gadget_driver) return 0; - dwc3_gadget_run_stop(dwc, false); + ret = dwc3_gadget_soft_disconnect(dwc); + if (ret) + goto err; spin_lock_irqsave(&dwc->lock, flags); dwc3_disconnect_gadget(dwc); - __dwc3_gadget_stop(dwc); spin_unlock_irqrestore(&dwc->lock, flags); return 0; + +err: + /* + * Attempt to reset the controller's state. Likely no + * communication can be established until the host + * performs a port reset. + */ + if (dwc->softconnect) + dwc3_gadget_soft_connect(dwc); + + return ret; } int dwc3_gadget_resume(struct dwc3 *dwc) { - int ret; - if (!dwc->gadget_driver || !dwc->softconnect) return 0; - ret = __dwc3_gadget_start(dwc); - if (ret < 0) - goto err0; - - ret = dwc3_gadget_run_stop(dwc, true); - if (ret < 0) - goto err1; - - return 0; - -err1: - __dwc3_gadget_stop(dwc); - -err0: - return ret; + return dwc3_gadget_soft_connect(dwc); } void dwc3_gadget_process_pending_events(struct dwc3 *dwc) diff --git a/drivers/usb/gadget/function/u_ether.c b/drivers/usb/gadget/function/u_ether.c index 6956ad8ba8dd..a366abb45623 100644 --- a/drivers/usb/gadget/function/u_ether.c +++ b/drivers/usb/gadget/function/u_ether.c @@ -17,6 +17,7 @@ #include <linux/etherdevice.h> #include <linux/ethtool.h> #include <linux/if_vlan.h> +#include <linux/string_helpers.h> #include <linux/usb/composite.h> #include "u_ether.h" @@ -965,6 +966,8 @@ int gether_get_host_addr_cdc(struct net_device *net, char *host_addr, int len) dev = netdev_priv(net); snprintf(host_addr, len, "%pm", dev->host_mac); + string_upper(host_addr, host_addr); + return strlen(host_addr); } EXPORT_SYMBOL_GPL(gether_get_host_addr_cdc); diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c index 4641153e9706..52e6d2e84e35 100644 --- a/drivers/usb/gadget/udc/core.c +++ b/drivers/usb/gadget/udc/core.c @@ -37,10 +37,6 @@ static const struct bus_type gadget_bus_type; * @vbus: for udcs who care about vbus status, this value is real vbus status; * for udcs who do not care about vbus status, this value is always true * @started: the UDC's started state. True if the UDC had started. - * @connect_lock: protects udc->vbus, udc->started, gadget->connect, gadget->deactivate related - * functions. usb_gadget_connect_locked, usb_gadget_disconnect_locked, - * usb_udc_connect_control_locked, usb_gadget_udc_start_locked, usb_gadget_udc_stop_locked are - * called with this lock held. * * This represents the internal data structure which is used by the UDC-class * to hold information about udc driver and gadget together. @@ -52,7 +48,6 @@ struct usb_udc { struct list_head list; bool vbus; bool started; - struct mutex connect_lock; }; static struct class *udc_class; @@ -692,9 +687,17 @@ out: } EXPORT_SYMBOL_GPL(usb_gadget_vbus_disconnect); -/* Internal version of usb_gadget_connect needs to be called with connect_lock held. */ -static int usb_gadget_connect_locked(struct usb_gadget *gadget) - __must_hold(&gadget->udc->connect_lock) +/** + * usb_gadget_connect - software-controlled connect to USB host + * @gadget:the peripheral being connected + * + * Enables the D+ (or potentially D-) pullup. The host will start + * enumerating this gadget when the pullup is active and a VBUS session + * is active (the link is powered). + * + * Returns zero on success, else negative errno. + */ +int usb_gadget_connect(struct usb_gadget *gadget) { int ret = 0; @@ -703,15 +706,10 @@ static int usb_gadget_connect_locked(struct usb_gadget *gadget) goto out; } - if (gadget->connected) - goto out; - - if (gadget->deactivated || !gadget->udc->started) { + if (gadget->deactivated) { /* * If gadget is deactivated we only save new state. * Gadget will be connected automatically after activation. - * - * udc first needs to be started before gadget can be pulled up. */ gadget->connected = true; goto out; @@ -726,32 +724,22 @@ out: return ret; } +EXPORT_SYMBOL_GPL(usb_gadget_connect); /** - * usb_gadget_connect - software-controlled connect to USB host - * @gadget:the peripheral being connected + * usb_gadget_disconnect - software-controlled disconnect from USB host + * @gadget:the peripheral being disconnected * - * Enables the D+ (or potentially D-) pullup. The host will start - * enumerating this gadget when the pullup is active and a VBUS session - * is active (the link is powered). + * Disables the D+ (or potentially D-) pullup, which the host may see + * as a disconnect (when a VBUS session is active). Not all systems + * support software pullup controls. + * + * Following a successful disconnect, invoke the ->disconnect() callback + * for the current gadget driver so that UDC drivers don't need to. * * Returns zero on success, else negative errno. */ -int usb_gadget_connect(struct usb_gadget *gadget) -{ - int ret; - - mutex_lock(&gadget->udc->connect_lock); - ret = usb_gadget_connect_locked(gadget); - mutex_unlock(&gadget->udc->connect_lock); - - return ret; -} -EXPORT_SYMBOL_GPL(usb_gadget_connect); - -/* Internal version of usb_gadget_disconnect needs to be called with connect_lock held. */ -static int usb_gadget_disconnect_locked(struct usb_gadget *gadget) - __must_hold(&gadget->udc->connect_lock) +int usb_gadget_disconnect(struct usb_gadget *gadget) { int ret = 0; @@ -763,12 +751,10 @@ static int usb_gadget_disconnect_locked(struct usb_gadget *gadget) if (!gadget->connected) goto out; - if (gadget->deactivated || !gadget->udc->started) { + if (gadget->deactivated) { /* * If gadget is deactivated we only save new state. * Gadget will stay disconnected after activation. - * - * udc should have been started before gadget being pulled down. */ gadget->connected = false; goto out; @@ -788,30 +774,6 @@ out: return ret; } - -/** - * usb_gadget_disconnect - software-controlled disconnect from USB host - * @gadget:the peripheral being disconnected - * - * Disables the D+ (or potentially D-) pullup, which the host may see - * as a disconnect (when a VBUS session is active). Not all systems - * support software pullup controls. - * - * Following a successful disconnect, invoke the ->disconnect() callback - * for the current gadget driver so that UDC drivers don't need to. - * - * Returns zero on success, else negative errno. - */ -int usb_gadget_disconnect(struct usb_gadget *gadget) -{ - int ret; - - mutex_lock(&gadget->udc->connect_lock); - ret = usb_gadget_disconnect_locked(gadget); - mutex_unlock(&gadget->udc->connect_lock); - - return ret; -} EXPORT_SYMBOL_GPL(usb_gadget_disconnect); /** @@ -832,11 +794,10 @@ int usb_gadget_deactivate(struct usb_gadget *gadget) if (gadget->deactivated) goto out; - mutex_lock(&gadget->udc->connect_lock); if (gadget->connected) { - ret = usb_gadget_disconnect_locked(gadget); + ret = usb_gadget_disconnect(gadget); if (ret) - goto unlock; + goto out; /* * If gadget was being connected before deactivation, we want @@ -846,8 +807,6 @@ int usb_gadget_deactivate(struct usb_gadget *gadget) } gadget->deactivated = true; -unlock: - mutex_unlock(&gadget->udc->connect_lock); out: trace_usb_gadget_deactivate(gadget, ret); @@ -871,7 +830,6 @@ int usb_gadget_activate(struct usb_gadget *gadget) if (!gadget->deactivated) goto out; - mutex_lock(&gadget->udc->connect_lock); gadget->deactivated = false; /* @@ -879,8 +837,7 @@ int usb_gadget_activate(struct usb_gadget *gadget) * while it was being deactivated, we call usb_gadget_connect(). */ if (gadget->connected) - ret = usb_gadget_connect_locked(gadget); - mutex_unlock(&gadget->udc->connect_lock); + ret = usb_gadget_connect(gadget); out: trace_usb_gadget_activate(gadget, ret); @@ -1121,13 +1078,12 @@ EXPORT_SYMBOL_GPL(usb_gadget_set_state); /* ------------------------------------------------------------------------- */ -/* Acquire connect_lock before calling this function. */ -static void usb_udc_connect_control_locked(struct usb_udc *udc) __must_hold(&udc->connect_lock) +static void usb_udc_connect_control(struct usb_udc *udc) { - if (udc->vbus && udc->started) - usb_gadget_connect_locked(udc->gadget); + if (udc->vbus) + usb_gadget_connect(udc->gadget); else - usb_gadget_disconnect_locked(udc->gadget); + usb_gadget_disconnect(udc->gadget); } /** @@ -1143,12 +1099,10 @@ void usb_udc_vbus_handler(struct usb_gadget *gadget, bool status) { struct usb_udc *udc = gadget->udc; - mutex_lock(&udc->connect_lock); if (udc) { udc->vbus = status; - usb_udc_connect_control_locked(udc); + usb_udc_connect_control(udc); } - mutex_unlock(&udc->connect_lock); } EXPORT_SYMBOL_GPL(usb_udc_vbus_handler); @@ -1170,7 +1124,7 @@ void usb_gadget_udc_reset(struct usb_gadget *gadget, EXPORT_SYMBOL_GPL(usb_gadget_udc_reset); /** - * usb_gadget_udc_start_locked - tells usb device controller to start up + * usb_gadget_udc_start - tells usb device controller to start up * @udc: The UDC to be started * * This call is issued by the UDC Class driver when it's about @@ -1181,11 +1135,8 @@ EXPORT_SYMBOL_GPL(usb_gadget_udc_reset); * necessary to have it powered on. * * Returns zero on success, else negative errno. - * - * Caller should acquire connect_lock before invoking this function. */ -static inline int usb_gadget_udc_start_locked(struct usb_udc *udc) - __must_hold(&udc->connect_lock) +static inline int usb_gadget_udc_start(struct usb_udc *udc) { int ret; @@ -1202,7 +1153,7 @@ static inline int usb_gadget_udc_start_locked(struct usb_udc *udc) } /** - * usb_gadget_udc_stop_locked - tells usb device controller we don't need it anymore + * usb_gadget_udc_stop - tells usb device controller we don't need it anymore * @udc: The UDC to be stopped * * This call is issued by the UDC Class driver after calling @@ -1211,11 +1162,8 @@ static inline int usb_gadget_udc_start_locked(struct usb_udc *udc) * The details are implementation specific, but it can go as * far as powering off UDC completely and disable its data * line pullups. - * - * Caller should acquire connect lock before invoking this function. */ -static inline void usb_gadget_udc_stop_locked(struct usb_udc *udc) - __must_hold(&udc->connect_lock) +static inline void usb_gadget_udc_stop(struct usb_udc *udc) { if (!udc->started) { dev_err(&udc->dev, "UDC had already stopped\n"); @@ -1374,7 +1322,6 @@ int usb_add_gadget(struct usb_gadget *gadget) udc->gadget = gadget; gadget->udc = udc; - mutex_init(&udc->connect_lock); udc->started = false; @@ -1576,15 +1523,11 @@ static int gadget_bind_driver(struct device *dev) if (ret) goto err_bind; - mutex_lock(&udc->connect_lock); - ret = usb_gadget_udc_start_locked(udc); - if (ret) { - mutex_unlock(&udc->connect_lock); + ret = usb_gadget_udc_start(udc); + if (ret) goto err_start; - } usb_gadget_enable_async_callbacks(udc); - usb_udc_connect_control_locked(udc); - mutex_unlock(&udc->connect_lock); + usb_udc_connect_control(udc); kobject_uevent(&udc->dev.kobj, KOBJ_CHANGE); return 0; @@ -1615,14 +1558,12 @@ static void gadget_unbind_driver(struct device *dev) kobject_uevent(&udc->dev.kobj, KOBJ_CHANGE); - mutex_lock(&udc->connect_lock); - usb_gadget_disconnect_locked(gadget); + usb_gadget_disconnect(gadget); usb_gadget_disable_async_callbacks(udc); if (gadget->irq) synchronize_irq(gadget->irq); udc->driver->unbind(gadget); - usb_gadget_udc_stop_locked(udc); - mutex_unlock(&udc->connect_lock); + usb_gadget_udc_stop(udc); mutex_lock(&udc_lock); driver->is_bound = false; @@ -1708,15 +1649,11 @@ static ssize_t soft_connect_store(struct device *dev, } if (sysfs_streq(buf, "connect")) { - mutex_lock(&udc->connect_lock); - usb_gadget_udc_start_locked(udc); - usb_gadget_connect_locked(udc->gadget); - mutex_unlock(&udc->connect_lock); + usb_gadget_udc_start(udc); + usb_gadget_connect(udc->gadget); } else if (sysfs_streq(buf, "disconnect")) { - mutex_lock(&udc->connect_lock); - usb_gadget_disconnect_locked(udc->gadget); - usb_gadget_udc_stop_locked(udc); - mutex_unlock(&udc->connect_lock); + usb_gadget_disconnect(udc->gadget); + usb_gadget_udc_stop(udc); } else { dev_err(dev, "unsupported command '%s'\n", buf); ret = -EINVAL; diff --git a/drivers/usb/host/uhci-pci.c b/drivers/usb/host/uhci-pci.c index 3592f757fe05..7bd2fddde770 100644 --- a/drivers/usb/host/uhci-pci.c +++ b/drivers/usb/host/uhci-pci.c @@ -119,11 +119,13 @@ static int uhci_pci_init(struct usb_hcd *hcd) uhci->rh_numports = uhci_count_ports(hcd); - /* Intel controllers report the OverCurrent bit active on. - * VIA controllers report it active off, so we'll adjust the - * bit value. (It's not standardized in the UHCI spec.) + /* + * Intel controllers report the OverCurrent bit active on. VIA + * and ZHAOXIN controllers report it active off, so we'll adjust + * the bit value. (It's not standardized in the UHCI spec.) */ - if (to_pci_dev(uhci_dev(uhci))->vendor == PCI_VENDOR_ID_VIA) + if (to_pci_dev(uhci_dev(uhci))->vendor == PCI_VENDOR_ID_VIA || + to_pci_dev(uhci_dev(uhci))->vendor == PCI_VENDOR_ID_ZHAOXIN) uhci->oc_low = 1; /* HP's server management chip requires a longer port reset delay. */ diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index ddb79f23fb3b..79b3691f373f 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -13,6 +13,7 @@ #include <linux/module.h> #include <linux/acpi.h> #include <linux/reset.h> +#include <linux/suspend.h> #include "xhci.h" #include "xhci-trace.h" @@ -387,7 +388,7 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) if (pdev->vendor == PCI_VENDOR_ID_AMD && pdev->device == PCI_DEVICE_ID_AMD_RENOIR_XHCI) - xhci->quirks |= XHCI_BROKEN_D3COLD; + xhci->quirks |= XHCI_BROKEN_D3COLD_S2I; if (pdev->vendor == PCI_VENDOR_ID_INTEL) { xhci->quirks |= XHCI_LPM_SUPPORT; @@ -801,9 +802,16 @@ static int xhci_pci_suspend(struct usb_hcd *hcd, bool do_wakeup) * Systems with the TI redriver that loses port status change events * need to have the registers polled during D3, so avoid D3cold. */ - if (xhci->quirks & (XHCI_COMP_MODE_QUIRK | XHCI_BROKEN_D3COLD)) + if (xhci->quirks & XHCI_COMP_MODE_QUIRK) pci_d3cold_disable(pdev); +#ifdef CONFIG_SUSPEND + /* d3cold is broken, but only when s2idle is used */ + if (pm_suspend_target_state == PM_SUSPEND_TO_IDLE && + xhci->quirks & (XHCI_BROKEN_D3COLD_S2I)) + pci_d3cold_disable(pdev); +#endif + if (xhci->quirks & XHCI_PME_STUCK_QUIRK) xhci_pme_quirk(hcd); diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index 1ad12d5a4857..2bc82b3a2f98 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -276,6 +276,26 @@ static void inc_enq(struct xhci_hcd *xhci, struct xhci_ring *ring, trace_xhci_inc_enq(ring); } +static int xhci_num_trbs_to(struct xhci_segment *start_seg, union xhci_trb *start, + struct xhci_segment *end_seg, union xhci_trb *end, + unsigned int num_segs) +{ + union xhci_trb *last_on_seg; + int num = 0; + int i = 0; + + do { + if (start_seg == end_seg && end >= start) + return num + (end - start); + last_on_seg = &start_seg->trbs[TRBS_PER_SEGMENT - 1]; + num += last_on_seg - start; + start_seg = start_seg->next; + start = start_seg->trbs; + } while (i++ <= num_segs); + + return -EINVAL; +} + /* * Check to see if there's room to enqueue num_trbs on the ring and make sure * enqueue pointer will not advance into dequeue segment. See rules above. @@ -2140,6 +2160,7 @@ static int finish_td(struct xhci_hcd *xhci, struct xhci_virt_ep *ep, u32 trb_comp_code) { struct xhci_ep_ctx *ep_ctx; + int trbs_freed; ep_ctx = xhci_get_ep_ctx(xhci, ep->vdev->out_ctx, ep->ep_index); @@ -2209,9 +2230,15 @@ static int finish_td(struct xhci_hcd *xhci, struct xhci_virt_ep *ep, } /* Update ring dequeue pointer */ + trbs_freed = xhci_num_trbs_to(ep_ring->deq_seg, ep_ring->dequeue, + td->last_trb_seg, td->last_trb, + ep_ring->num_segs); + if (trbs_freed < 0) + xhci_dbg(xhci, "Failed to count freed trbs at TD finish\n"); + else + ep_ring->num_trbs_free += trbs_freed; ep_ring->dequeue = td->last_trb; ep_ring->deq_seg = td->last_trb_seg; - ep_ring->num_trbs_free += td->num_trbs - 1; inc_deq(xhci, ep_ring); return xhci_td_cleanup(xhci, td, ep_ring, td->status); diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index 08d721921b7b..6b690ec91ff3 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -1901,7 +1901,7 @@ struct xhci_hcd { #define XHCI_DISABLE_SPARSE BIT_ULL(38) #define XHCI_SG_TRB_CACHE_SIZE_QUIRK BIT_ULL(39) #define XHCI_NO_SOFT_RETRY BIT_ULL(40) -#define XHCI_BROKEN_D3COLD BIT_ULL(41) +#define XHCI_BROKEN_D3COLD_S2I BIT_ULL(41) #define XHCI_EP_CTX_BROKEN_DCS BIT_ULL(42) #define XHCI_SUSPEND_RESUME_CLKS BIT_ULL(43) #define XHCI_RESET_TO_DEFAULT BIT_ULL(44) diff --git a/drivers/usb/storage/scsiglue.c b/drivers/usb/storage/scsiglue.c index 8931df5a85fd..c54e9805da53 100644 --- a/drivers/usb/storage/scsiglue.c +++ b/drivers/usb/storage/scsiglue.c @@ -406,22 +406,25 @@ static DEF_SCSI_QCMD(queuecommand) ***********************************************************************/ /* Command timeout and abort */ -static int command_abort(struct scsi_cmnd *srb) +static int command_abort_matching(struct us_data *us, struct scsi_cmnd *srb_match) { - struct us_data *us = host_to_us(srb->device->host); - - usb_stor_dbg(us, "%s called\n", __func__); - /* * us->srb together with the TIMED_OUT, RESETTING, and ABORTING * bits are protected by the host lock. */ scsi_lock(us_to_host(us)); - /* Is this command still active? */ - if (us->srb != srb) { + /* is there any active pending command to abort ? */ + if (!us->srb) { scsi_unlock(us_to_host(us)); usb_stor_dbg(us, "-- nothing to abort\n"); + return SUCCESS; + } + + /* Does the command match the passed srb if any ? */ + if (srb_match && us->srb != srb_match) { + scsi_unlock(us_to_host(us)); + usb_stor_dbg(us, "-- pending command mismatch\n"); return FAILED; } @@ -444,6 +447,14 @@ static int command_abort(struct scsi_cmnd *srb) return SUCCESS; } +static int command_abort(struct scsi_cmnd *srb) +{ + struct us_data *us = host_to_us(srb->device->host); + + usb_stor_dbg(us, "%s called\n", __func__); + return command_abort_matching(us, srb); +} + /* * This invokes the transport reset mechanism to reset the state of the * device @@ -455,6 +466,9 @@ static int device_reset(struct scsi_cmnd *srb) usb_stor_dbg(us, "%s called\n", __func__); + /* abort any pending command before reset */ + command_abort_matching(us, NULL); + /* lock the device pointers and do the reset */ mutex_lock(&(us->dev_mutex)); result = us->transport_reset(us); diff --git a/drivers/usb/typec/altmodes/displayport.c b/drivers/usb/typec/altmodes/displayport.c index 8f3e884222ad..66de880b28d0 100644 --- a/drivers/usb/typec/altmodes/displayport.c +++ b/drivers/usb/typec/altmodes/displayport.c @@ -516,6 +516,10 @@ static ssize_t pin_assignment_show(struct device *dev, mutex_unlock(&dp->lock); + /* get_current_pin_assignments can return 0 when no matching pin assignments are found */ + if (len == 0) + len++; + buf[len - 1] = '\n'; return len; } diff --git a/drivers/usb/typec/tipd/core.c b/drivers/usb/typec/tipd/core.c index 8b075ca82ef6..438cc40660a1 100644 --- a/drivers/usb/typec/tipd/core.c +++ b/drivers/usb/typec/tipd/core.c @@ -886,6 +886,9 @@ static void tps6598x_remove(struct i2c_client *client) { struct tps6598x *tps = i2c_get_clientdata(client); + if (!client->irq) + cancel_delayed_work_sync(&tps->wq_poll); + tps6598x_disconnect(tps, 0); typec_unregister_port(tps->port); usb_role_switch_put(tps->role_sw); diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index 3d4dd9420c30..0d2f805468e1 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -860,6 +860,11 @@ static int vfio_iommu_type1_pin_pages(void *iommu_data, if (ret) goto pin_unwind; + if (!pfn_valid(phys_pfn)) { + ret = -EINVAL; + goto pin_unwind; + } + ret = vfio_add_to_pfn_list(dma, iova, phys_pfn); if (ret) { if (put_pfn(phys_pfn, dma->prot) && do_accounting) diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index a92af08e7864..074273020849 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -256,7 +256,7 @@ void vhost_work_queue(struct vhost_dev *dev, struct vhost_work *work) * test_and_set_bit() implies a memory barrier. */ llist_add(&work->node, &dev->worker->work_list); - wake_up_process(dev->worker->vtsk->task); + vhost_task_wake(dev->worker->vtsk); } } EXPORT_SYMBOL_GPL(vhost_work_queue); @@ -333,31 +333,19 @@ static void vhost_vq_reset(struct vhost_dev *dev, __vhost_vq_meta_reset(vq); } -static int vhost_worker(void *data) +static bool vhost_worker(void *data) { struct vhost_worker *worker = data; struct vhost_work *work, *work_next; struct llist_node *node; - for (;;) { - /* mb paired w/ kthread_stop */ - set_current_state(TASK_INTERRUPTIBLE); - - if (vhost_task_should_stop(worker->vtsk)) { - __set_current_state(TASK_RUNNING); - break; - } - - node = llist_del_all(&worker->work_list); - if (!node) - schedule(); - + node = llist_del_all(&worker->work_list); + if (node) { node = llist_reverse_order(node); /* make sure flag is seen after deletion */ smp_wmb(); llist_for_each_entry_safe(work, work_next, node, node) { clear_bit(VHOST_WORK_QUEUED, &work->flags); - __set_current_state(TASK_RUNNING); kcov_remote_start_common(worker->kcov_handle); work->fn(work); kcov_remote_stop(); @@ -365,7 +353,7 @@ static int vhost_worker(void *data) } } - return 0; + return !!node; } static void vhost_vq_free_iovecs(struct vhost_virtqueue *vq) diff --git a/drivers/video/fbdev/Kconfig b/drivers/video/fbdev/Kconfig index 96e91570cdd3..0fdf5f46802c 100644 --- a/drivers/video/fbdev/Kconfig +++ b/drivers/video/fbdev/Kconfig @@ -124,7 +124,7 @@ config FB_PROVIDE_GET_FB_UNMAPPED_AREA depends on FB help Allow generic frame-buffer to provide get_fb_unmapped_area - function. + function to provide shareable character device support on nommu. menuconfig FB_FOREIGN_ENDIAN bool "Framebuffer foreign endianness support" diff --git a/drivers/video/fbdev/aty/atyfb_base.c b/drivers/video/fbdev/aty/atyfb_base.c index b02e4e645035..cba2b113b28b 100644 --- a/drivers/video/fbdev/aty/atyfb_base.c +++ b/drivers/video/fbdev/aty/atyfb_base.c @@ -3498,11 +3498,6 @@ static int atyfb_setup_generic(struct pci_dev *pdev, struct fb_info *info, if (ret) goto atyfb_setup_generic_fail; #endif - if (!(aty_ld_le32(CRTC_GEN_CNTL, par) & CRTC_EXT_DISP_EN)) - par->clk_wr_offset = (inb(R_GENMO) & 0x0CU) >> 2; - else - par->clk_wr_offset = aty_ld_8(CLOCK_CNTL, par) & 0x03U; - /* according to ATI, we should use clock 3 for acelerated mode */ par->clk_wr_offset = 3; diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c index e808dc86001c..28739f1cb5e7 100644 --- a/drivers/video/fbdev/core/fbmem.c +++ b/drivers/video/fbdev/core/fbmem.c @@ -1468,7 +1468,7 @@ __releases(&info->lock) } #if defined(CONFIG_FB_PROVIDE_GET_FB_UNMAPPED_AREA) && !defined(CONFIG_MMU) -unsigned long get_fb_unmapped_area(struct file *filp, +static unsigned long get_fb_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { diff --git a/drivers/video/fbdev/i810/i810_dvt.c b/drivers/video/fbdev/i810/i810_dvt.c index b4b3670667ab..2082b5c92e8f 100644 --- a/drivers/video/fbdev/i810/i810_dvt.c +++ b/drivers/video/fbdev/i810/i810_dvt.c @@ -14,6 +14,7 @@ #include "i810_regs.h" #include "i810.h" +#include "i810_main.h" struct mode_registers std_modes[] = { /* 640x480 @ 60Hz */ @@ -276,7 +277,7 @@ void i810fb_fill_var_timings(struct fb_var_screeninfo *var) var->upper_margin = total - (yres + var->lower_margin + var->vsync_len); } -u32 i810_get_watermark(struct fb_var_screeninfo *var, +u32 i810_get_watermark(const struct fb_var_screeninfo *var, struct i810fb_par *par) { struct mode_registers *params = &par->regs; diff --git a/drivers/video/fbdev/omap2/omapfb/displays/panel-tpo-td043mtea1.c b/drivers/video/fbdev/omap2/omapfb/displays/panel-tpo-td043mtea1.c index 1eaa35c27835..477789cff8e0 100644 --- a/drivers/video/fbdev/omap2/omapfb/displays/panel-tpo-td043mtea1.c +++ b/drivers/video/fbdev/omap2/omapfb/displays/panel-tpo-td043mtea1.c @@ -491,7 +491,8 @@ static int tpo_td043_probe(struct spi_device *spi) ddata->vcc_reg = devm_regulator_get(&spi->dev, "vcc"); if (IS_ERR(ddata->vcc_reg)) { - r = dev_err_probe(&spi->dev, r, "failed to get LCD VCC regulator\n"); + r = dev_err_probe(&spi->dev, PTR_ERR(ddata->vcc_reg), + "failed to get LCD VCC regulator\n"); goto err_regulator; } diff --git a/drivers/video/fbdev/stifb.c b/drivers/video/fbdev/stifb.c index 14c9215284c5..686a234f3899 100644 --- a/drivers/video/fbdev/stifb.c +++ b/drivers/video/fbdev/stifb.c @@ -741,7 +741,7 @@ ngleClearOverlayPlanes(struct stifb_info *fb, int mask, int data) packed_len = (fb->info.var.xres << 16) | fb->info.var.yres; NGLE_SET_DSTXY(fb, packed_dst); - /* Write zeroes to overlay planes */ + /* Write zeroes to overlay planes */ NGLE_QUICK_SET_IMAGE_BITMAP_OP(fb, IBOvals(RopSrc, MaskAddrOffset(0), BitmapExtent08, StaticReg(0), @@ -1297,14 +1297,14 @@ static int __init stifb_init_fb(struct sti_struct *sti, int bpp_pref) break; default: #ifdef FALLBACK_TO_1BPP - printk(KERN_WARNING + printk(KERN_WARNING "stifb: Unsupported graphics card (id=0x%08x) " "- now trying 1bpp mode instead\n", fb->id); bpp = 1; /* default to 1 bpp */ break; #else - printk(KERN_WARNING + printk(KERN_WARNING "stifb: Unsupported graphics card (id=0x%08x) " "- skipping.\n", fb->id); diff --git a/drivers/video/fbdev/udlfb.c b/drivers/video/fbdev/udlfb.c index 216d49c9d47e..dabc30a09f96 100644 --- a/drivers/video/fbdev/udlfb.c +++ b/drivers/video/fbdev/udlfb.c @@ -27,6 +27,8 @@ #include <video/udlfb.h> #include "edid.h" +#define OUT_EP_NUM 1 /* The endpoint number we will use */ + static const struct fb_fix_screeninfo dlfb_fix = { .id = "udlfb", .type = FB_TYPE_PACKED_PIXELS, @@ -1541,24 +1543,16 @@ static const struct device_attribute fb_device_attrs[] = { static int dlfb_select_std_channel(struct dlfb_data *dlfb) { int ret; - void *buf; static const u8 set_def_chn[] = { 0x57, 0xCD, 0xDC, 0xA7, 0x1C, 0x88, 0x5E, 0x15, 0x60, 0xFE, 0xC6, 0x97, 0x16, 0x3D, 0x47, 0xF2 }; - buf = kmemdup(set_def_chn, sizeof(set_def_chn), GFP_KERNEL); - - if (!buf) - return -ENOMEM; - - ret = usb_control_msg(dlfb->udev, usb_sndctrlpipe(dlfb->udev, 0), - NR_USB_REQUEST_CHANNEL, + ret = usb_control_msg_send(dlfb->udev, 0, NR_USB_REQUEST_CHANNEL, (USB_DIR_OUT | USB_TYPE_VENDOR), 0, 0, - buf, sizeof(set_def_chn), USB_CTRL_SET_TIMEOUT); - - kfree(buf); + &set_def_chn, sizeof(set_def_chn), USB_CTRL_SET_TIMEOUT, + GFP_KERNEL); return ret; } @@ -1652,7 +1646,7 @@ static int dlfb_usb_probe(struct usb_interface *intf, struct fb_info *info; int retval; struct usb_device *usbdev = interface_to_usbdev(intf); - struct usb_endpoint_descriptor *out; + static u8 out_ep[] = {OUT_EP_NUM + USB_DIR_OUT, 0}; /* usb initialization */ dlfb = kzalloc(sizeof(*dlfb), GFP_KERNEL); @@ -1666,9 +1660,9 @@ static int dlfb_usb_probe(struct usb_interface *intf, dlfb->udev = usb_get_dev(usbdev); usb_set_intfdata(intf, dlfb); - retval = usb_find_common_endpoints(intf->cur_altsetting, NULL, &out, NULL, NULL); - if (retval) { - dev_err(&intf->dev, "Device should have at lease 1 bulk endpoint!\n"); + if (!usb_check_bulk_endpoints(intf, out_ep)) { + dev_err(&intf->dev, "Invalid DisplayLink device!\n"); + retval = -EINVAL; goto error; } @@ -1927,7 +1921,8 @@ retry: } /* urb->transfer_buffer_length set to actual before submit */ - usb_fill_bulk_urb(urb, dlfb->udev, usb_sndbulkpipe(dlfb->udev, 1), + usb_fill_bulk_urb(urb, dlfb->udev, + usb_sndbulkpipe(dlfb->udev, OUT_EP_NUM), buf, size, dlfb_urb_completion, unode); urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP; diff --git a/drivers/xen/pvcalls-back.c b/drivers/xen/pvcalls-back.c index 1f5219e12cc3..7beaf2c41fbb 100644 --- a/drivers/xen/pvcalls-back.c +++ b/drivers/xen/pvcalls-back.c @@ -325,8 +325,10 @@ static struct sock_mapping *pvcalls_new_active_socket( void *page; map = kzalloc(sizeof(*map), GFP_KERNEL); - if (map == NULL) + if (map == NULL) { + sock_release(sock); return NULL; + } map->fedata = fedata; map->sock = sock; @@ -418,10 +420,8 @@ static int pvcalls_back_connect(struct xenbus_device *dev, req->u.connect.ref, req->u.connect.evtchn, sock); - if (!map) { + if (!map) ret = -EFAULT; - sock_release(sock); - } out: rsp = RING_GET_RESPONSE(&fedata->ring, fedata->ring.rsp_prod_pvt++); @@ -561,7 +561,6 @@ static void __pvcalls_back_accept(struct work_struct *work) sock); if (!map) { ret = -EFAULT; - sock_release(sock); goto out_error; } diff --git a/fs/Kconfig b/fs/Kconfig index cc07a0cd3172..18d034ec7953 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -368,14 +368,7 @@ config NFS_V4_2_SSC_HELPER source "net/sunrpc/Kconfig" source "fs/ceph/Kconfig" -source "fs/cifs/Kconfig" -source "fs/ksmbd/Kconfig" - -config SMBFS_COMMON - tristate - default y if CIFS=y || SMB_SERVER=y - default m if CIFS=m || SMB_SERVER=m - +source "fs/smb/Kconfig" source "fs/coda/Kconfig" source "fs/afs/Kconfig" source "fs/9p/Kconfig" diff --git a/fs/Makefile b/fs/Makefile index 834f1c3dba46..5bfdbf0d7037 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -95,9 +95,7 @@ obj-$(CONFIG_LOCKD) += lockd/ obj-$(CONFIG_NLS) += nls/ obj-y += unicode/ obj-$(CONFIG_SYSV_FS) += sysv/ -obj-$(CONFIG_SMBFS_COMMON) += smbfs_common/ -obj-$(CONFIG_CIFS) += cifs/ -obj-$(CONFIG_SMB_SERVER) += ksmbd/ +obj-$(CONFIG_SMBFS) += smb/ obj-$(CONFIG_HPFS_FS) += hpfs/ obj-$(CONFIG_NTFS_FS) += ntfs/ obj-$(CONFIG_NTFS3_FS) += ntfs3/ diff --git a/fs/btrfs/bio.c b/fs/btrfs/bio.c index 5379c4714905..35d34c731d72 100644 --- a/fs/btrfs/bio.c +++ b/fs/btrfs/bio.c @@ -330,7 +330,7 @@ static void btrfs_end_bio_work(struct work_struct *work) if (bbio->inode && !(bbio->bio.bi_opf & REQ_META)) btrfs_check_read_bio(bbio, bbio->bio.bi_private); else - bbio->end_io(bbio); + btrfs_orig_bbio_end_io(bbio); } static void btrfs_simple_end_io(struct bio *bio) diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 957ad1c31c4f..590b03560265 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -2818,10 +2818,20 @@ int btrfs_inc_block_group_ro(struct btrfs_block_group *cache, } ret = inc_block_group_ro(cache, 0); - if (!do_chunk_alloc || ret == -ETXTBSY) - goto unlock_out; if (!ret) goto out; + if (ret == -ETXTBSY) + goto unlock_out; + + /* + * Skip chunk alloction if the bg is SYSTEM, this is to avoid system + * chunk allocation storm to exhaust the system chunk array. Otherwise + * we still want to try our best to mark the block group read-only. + */ + if (!do_chunk_alloc && ret == -ENOSPC && + (cache->flags & BTRFS_BLOCK_GROUP_SYSTEM)) + goto unlock_out; + alloc_flags = btrfs_get_alloc_profile(fs_info, cache->space_info->flags); ret = btrfs_chunk_alloc(trans, alloc_flags, CHUNK_ALLOC_FORCE); if (ret < 0) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index fbf9006c6234..2b1b227505f3 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -96,7 +96,7 @@ static void csum_tree_block(struct extent_buffer *buf, u8 *result) crypto_shash_update(shash, kaddr + BTRFS_CSUM_SIZE, first_page_part - BTRFS_CSUM_SIZE); - for (i = 1; i < num_pages; i++) { + for (i = 1; i < num_pages && INLINE_EXTENT_BUFFER_PAGES > 1; i++) { kaddr = page_address(buf->pages[i]); crypto_shash_update(shash, kaddr, PAGE_SIZE); } @@ -4936,7 +4936,11 @@ static void btrfs_destroy_delalloc_inodes(struct btrfs_root *root) */ inode = igrab(&btrfs_inode->vfs_inode); if (inode) { + unsigned int nofs_flag; + + nofs_flag = memalloc_nofs_save(); invalidate_inode_pages2(inode->i_mapping); + memalloc_nofs_restore(nofs_flag); iput(inode); } spin_lock(&root->delalloc_lock); @@ -5042,7 +5046,12 @@ static void btrfs_cleanup_bg_io(struct btrfs_block_group *cache) inode = cache->io_ctl.inode; if (inode) { + unsigned int nofs_flag; + + nofs_flag = memalloc_nofs_save(); invalidate_inode_pages2(inode->i_mapping); + memalloc_nofs_restore(nofs_flag); + BTRFS_I(inode)->generation = 0; cache->io_ctl.inode = NULL; iput(inode); diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c index cd4cce9ba443..d1cd0a692f8e 100644 --- a/fs/btrfs/file-item.c +++ b/fs/btrfs/file-item.c @@ -792,7 +792,9 @@ blk_status_t btrfs_csum_one_bio(struct btrfs_bio *bbio) sums = kvzalloc(btrfs_ordered_sum_size(fs_info, bytes_left), GFP_KERNEL); memalloc_nofs_restore(nofs_flag); - BUG_ON(!sums); /* -ENOMEM */ + if (!sums) + return BLK_STS_RESOURCE; + sums->len = bytes_left; ordered = btrfs_lookup_ordered_extent(inode, offset); diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 836725a19661..dd37cba58022 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -2518,13 +2518,20 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx, if (ret == 0) { ro_set = 1; - } else if (ret == -ENOSPC && !sctx->is_dev_replace) { + } else if (ret == -ENOSPC && !sctx->is_dev_replace && + !(cache->flags & BTRFS_BLOCK_GROUP_RAID56_MASK)) { /* * btrfs_inc_block_group_ro return -ENOSPC when it * failed in creating new chunk for metadata. * It is not a problem for scrub, because * metadata are always cowed, and our scrub paused * commit_transactions. + * + * For RAID56 chunks, we have to mark them read-only + * for scrub, as later we would use our own cache + * out of RAID56 realm. + * Thus we want the RAID56 bg to be marked RO to + * prevent RMW from screwing up out cache. */ ro_set = 0; } else if (ret == -ETXTBSY) { diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 9b212e8c70cc..d2755d5e338b 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -6158,7 +6158,7 @@ static int log_delayed_deletions_incremental(struct btrfs_trans_handle *trans, { struct btrfs_root *log = inode->root->log_root; const struct btrfs_delayed_item *curr; - u64 last_range_start; + u64 last_range_start = 0; u64 last_range_end = 0; struct btrfs_key key; diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 29cf00220b09..4c0f22acf53d 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -3942,7 +3942,7 @@ static int reconnect_caps_cb(struct inode *inode, int mds, void *arg) struct dentry *dentry; struct ceph_cap *cap; char *path; - int pathlen = 0, err = 0; + int pathlen = 0, err; u64 pathbase; u64 snap_follows; @@ -3965,6 +3965,7 @@ static int reconnect_caps_cb(struct inode *inode, int mds, void *arg) cap = __get_cap_for_mds(ci, mds); if (!cap) { spin_unlock(&ci->i_ceph_lock); + err = 0; goto out_err; } dout(" adding %p ino %llx.%llx cap %p %lld %s\n", diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c index 87007203f130..0b236ebd989f 100644 --- a/fs/ceph/snap.c +++ b/fs/ceph/snap.c @@ -1111,6 +1111,19 @@ skip_inode: continue; adjust_snap_realm_parent(mdsc, child, realm->ino); } + } else { + /* + * In the non-split case both 'num_split_inos' and + * 'num_split_realms' should be 0, making this a no-op. + * However the MDS happens to populate 'split_realms' list + * in one of the UPDATE op cases by mistake. + * + * Skip both lists just in case to ensure that 'p' is + * positioned at the start of realm info, as expected by + * ceph_update_snap_trace(). + */ + p += sizeof(u64) * num_split_inos; + p += sizeof(u64) * num_split_realms; } /* diff --git a/fs/coredump.c b/fs/coredump.c index ece7badf701b..88740c51b942 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -371,7 +371,9 @@ static int zap_process(struct task_struct *start, int exit_code) if (t != current && !(t->flags & PF_POSTCOREDUMP)) { sigaddset(&t->pending.signal, SIGKILL); signal_wake_up(t, 1); - nr++; + /* The vhost_worker does not particpate in coredumps */ + if ((t->flags & (PF_USER_WORKER | PF_IO_WORKER)) != PF_USER_WORKER) + nr++; } } diff --git a/fs/erofs/Kconfig b/fs/erofs/Kconfig index 704fb59577e0..f259d92c9720 100644 --- a/fs/erofs/Kconfig +++ b/fs/erofs/Kconfig @@ -121,6 +121,7 @@ config EROFS_FS_PCPU_KTHREAD config EROFS_FS_PCPU_KTHREAD_HIPRI bool "EROFS high priority per-CPU kthread workers" depends on EROFS_FS_ZIP && EROFS_FS_PCPU_KTHREAD + default y help This permits EROFS to configure per-CPU kthread workers to run at higher priority. diff --git a/fs/erofs/Makefile b/fs/erofs/Makefile index 99bbc597a3e9..a3a98fc3e481 100644 --- a/fs/erofs/Makefile +++ b/fs/erofs/Makefile @@ -1,8 +1,8 @@ # SPDX-License-Identifier: GPL-2.0-only obj-$(CONFIG_EROFS_FS) += erofs.o -erofs-objs := super.o inode.o data.o namei.o dir.o utils.o pcpubuf.o sysfs.o +erofs-objs := super.o inode.o data.o namei.o dir.o utils.o sysfs.o erofs-$(CONFIG_EROFS_FS_XATTR) += xattr.o -erofs-$(CONFIG_EROFS_FS_ZIP) += decompressor.o zmap.o zdata.o +erofs-$(CONFIG_EROFS_FS_ZIP) += decompressor.o zmap.o zdata.o pcpubuf.o erofs-$(CONFIG_EROFS_FS_ZIP_LZMA) += decompressor_lzma.o erofs-$(CONFIG_EROFS_FS_ONDEMAND) += fscache.o diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h index af0431a40647..1e39c03357d1 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -472,12 +472,6 @@ static inline void *erofs_vm_map_ram(struct page **pages, unsigned int count) return NULL; } -void *erofs_get_pcpubuf(unsigned int requiredpages); -void erofs_put_pcpubuf(void *ptr); -int erofs_pcpubuf_growsize(unsigned int nrpages); -void __init erofs_pcpubuf_init(void); -void erofs_pcpubuf_exit(void); - int erofs_register_sysfs(struct super_block *sb); void erofs_unregister_sysfs(struct super_block *sb); int __init erofs_init_sysfs(void); @@ -512,6 +506,11 @@ int z_erofs_load_lz4_config(struct super_block *sb, struct z_erofs_lz4_cfgs *lz4, int len); int z_erofs_map_blocks_iter(struct inode *inode, struct erofs_map_blocks *map, int flags); +void *erofs_get_pcpubuf(unsigned int requiredpages); +void erofs_put_pcpubuf(void *ptr); +int erofs_pcpubuf_growsize(unsigned int nrpages); +void __init erofs_pcpubuf_init(void); +void erofs_pcpubuf_exit(void); #else static inline void erofs_shrinker_register(struct super_block *sb) {} static inline void erofs_shrinker_unregister(struct super_block *sb) {} @@ -529,6 +528,8 @@ static inline int z_erofs_load_lz4_config(struct super_block *sb, } return 0; } +static inline void erofs_pcpubuf_init(void) {} +static inline void erofs_pcpubuf_exit(void) {} #endif /* !CONFIG_EROFS_FS_ZIP */ #ifdef CONFIG_EROFS_FS_ZIP_LZMA diff --git a/fs/erofs/xattr.c b/fs/erofs/xattr.c index cd80499351e0..bbfe7ce170d2 100644 --- a/fs/erofs/xattr.c +++ b/fs/erofs/xattr.c @@ -675,7 +675,7 @@ int erofs_xattr_prefixes_init(struct super_block *sb) if (!pfs) return -ENOMEM; - if (erofs_sb_has_fragments(sbi)) + if (sbi->packed_inode) buf.inode = sbi->packed_inode; else erofs_init_metabuf(&buf, sb); diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index 45f21db2303a..160b3da43aec 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -369,8 +369,6 @@ static struct kthread_worker *erofs_init_percpu_worker(int cpu) return worker; if (IS_ENABLED(CONFIG_EROFS_FS_PCPU_KTHREAD_HIPRI)) sched_set_fifo_low(worker->task); - else - sched_set_normal(worker->task, 0); return worker; } diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 6948d673bba2..8104a21b001a 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -918,11 +918,13 @@ do { \ * where the second inode has larger inode number * than the first * I_DATA_SEM_QUOTA - Used for quota inodes only + * I_DATA_SEM_EA - Used for ea_inodes only */ enum { I_DATA_SEM_NORMAL = 0, I_DATA_SEM_OTHER, I_DATA_SEM_QUOTA, + I_DATA_SEM_EA }; @@ -2901,7 +2903,8 @@ typedef enum { EXT4_IGET_NORMAL = 0, EXT4_IGET_SPECIAL = 0x0001, /* OK to iget a system inode */ EXT4_IGET_HANDLE = 0x0002, /* Inode # is from a handle */ - EXT4_IGET_BAD = 0x0004 /* Allow to iget a bad inode */ + EXT4_IGET_BAD = 0x0004, /* Allow to iget a bad inode */ + EXT4_IGET_EA_INODE = 0x0008 /* Inode should contain an EA value */ } ext4_iget_flags; extern struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c index f65fdb27ce14..2a143209aa0c 100644 --- a/fs/ext4/fsync.c +++ b/fs/ext4/fsync.c @@ -108,6 +108,13 @@ static int ext4_fsync_journal(struct inode *inode, bool datasync, journal_t *journal = EXT4_SB(inode->i_sb)->s_journal; tid_t commit_tid = datasync ? ei->i_datasync_tid : ei->i_sync_tid; + /* + * Fastcommit does not really support fsync on directories or other + * special files. Force a full commit. + */ + if (!S_ISREG(inode->i_mode)) + return ext4_force_commit(inode->i_sb); + if (journal->j_flags & JBD2_BARRIER && !jbd2_trans_will_send_data_barrier(journal, commit_tid)) *needs_barrier = true; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index ce5f21b6c2b3..02de439bf1f0 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -4641,6 +4641,24 @@ static inline void ext4_inode_set_iversion_queried(struct inode *inode, u64 val) inode_set_iversion_queried(inode, val); } +static const char *check_igot_inode(struct inode *inode, ext4_iget_flags flags) + +{ + if (flags & EXT4_IGET_EA_INODE) { + if (!(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)) + return "missing EA_INODE flag"; + if (ext4_test_inode_state(inode, EXT4_STATE_XATTR) || + EXT4_I(inode)->i_file_acl) + return "ea_inode with extended attributes"; + } else { + if ((EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)) + return "unexpected EA_INODE flag"; + } + if (is_bad_inode(inode) && !(flags & EXT4_IGET_BAD)) + return "unexpected bad inode w/o EXT4_IGET_BAD"; + return NULL; +} + struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, ext4_iget_flags flags, const char *function, unsigned int line) @@ -4650,6 +4668,7 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, struct ext4_inode_info *ei; struct ext4_super_block *es = EXT4_SB(sb)->s_es; struct inode *inode; + const char *err_str; journal_t *journal = EXT4_SB(sb)->s_journal; long ret; loff_t size; @@ -4677,8 +4696,14 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, inode = iget_locked(sb, ino); if (!inode) return ERR_PTR(-ENOMEM); - if (!(inode->i_state & I_NEW)) + if (!(inode->i_state & I_NEW)) { + if ((err_str = check_igot_inode(inode, flags)) != NULL) { + ext4_error_inode(inode, function, line, 0, err_str); + iput(inode); + return ERR_PTR(-EFSCORRUPTED); + } return inode; + } ei = EXT4_I(inode); iloc.bh = NULL; @@ -4944,10 +4969,9 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, if (IS_CASEFOLDED(inode) && !ext4_has_feature_casefold(inode->i_sb)) ext4_error_inode(inode, function, line, 0, "casefold flag without casefold feature"); - if (is_bad_inode(inode) && !(flags & EXT4_IGET_BAD)) { - ext4_error_inode(inode, function, line, 0, - "bad inode without EXT4_IGET_BAD flag"); - ret = -EUCLEAN; + if ((err_str = check_igot_inode(inode, flags)) != NULL) { + ext4_error_inode(inode, function, line, 0, err_str); + ret = -EFSCORRUPTED; goto bad_inode; } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 9680fe753e59..56a5d1c469fc 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -6589,18 +6589,6 @@ static int __ext4_remount(struct fs_context *fc, struct super_block *sb) } /* - * Reinitialize lazy itable initialization thread based on - * current settings - */ - if (sb_rdonly(sb) || !test_opt(sb, INIT_INODE_TABLE)) - ext4_unregister_li_request(sb); - else { - ext4_group_t first_not_zeroed; - first_not_zeroed = ext4_has_uninit_itable(sb); - ext4_register_li_request(sb, first_not_zeroed); - } - - /* * Handle creation of system zone data early because it can fail. * Releasing of existing data is done when we are sure remount will * succeed. @@ -6637,6 +6625,18 @@ static int __ext4_remount(struct fs_context *fc, struct super_block *sb) if (enable_rw) sb->s_flags &= ~SB_RDONLY; + /* + * Reinitialize lazy itable initialization thread based on + * current settings + */ + if (sb_rdonly(sb) || !test_opt(sb, INIT_INODE_TABLE)) + ext4_unregister_li_request(sb); + else { + ext4_group_t first_not_zeroed; + first_not_zeroed = ext4_has_uninit_itable(sb); + ext4_register_li_request(sb, first_not_zeroed); + } + if (!ext4_has_feature_mmp(sb) || sb_rdonly(sb)) ext4_stop_mmpd(sbi); diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index dfc2e223bd10..13d7f17a9c8c 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -121,7 +121,11 @@ ext4_expand_inode_array(struct ext4_xattr_inode_array **ea_inode_array, #ifdef CONFIG_LOCKDEP void ext4_xattr_inode_set_class(struct inode *ea_inode) { + struct ext4_inode_info *ei = EXT4_I(ea_inode); + lockdep_set_subclass(&ea_inode->i_rwsem, 1); + (void) ei; /* shut up clang warning if !CONFIG_LOCKDEP */ + lockdep_set_subclass(&ei->i_data_sem, I_DATA_SEM_EA); } #endif @@ -433,7 +437,7 @@ static int ext4_xattr_inode_iget(struct inode *parent, unsigned long ea_ino, return -EFSCORRUPTED; } - inode = ext4_iget(parent->i_sb, ea_ino, EXT4_IGET_NORMAL); + inode = ext4_iget(parent->i_sb, ea_ino, EXT4_IGET_EA_INODE); if (IS_ERR(inode)) { err = PTR_ERR(inode); ext4_error(parent->i_sb, @@ -441,23 +445,6 @@ static int ext4_xattr_inode_iget(struct inode *parent, unsigned long ea_ino, err); return err; } - - if (is_bad_inode(inode)) { - ext4_error(parent->i_sb, - "error while reading EA inode %lu is_bad_inode", - ea_ino); - err = -EIO; - goto error; - } - - if (!(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)) { - ext4_error(parent->i_sb, - "EA inode %lu does not have EXT4_EA_INODE_FL flag", - ea_ino); - err = -EINVAL; - goto error; - } - ext4_xattr_inode_set_class(inode); /* @@ -478,9 +465,6 @@ static int ext4_xattr_inode_iget(struct inode *parent, unsigned long ea_ino, *ea_inode = inode; return 0; -error: - iput(inode); - return err; } /* Remove entry from mbcache when EA inode is getting evicted */ @@ -1556,11 +1540,11 @@ ext4_xattr_inode_cache_find(struct inode *inode, const void *value, while (ce) { ea_inode = ext4_iget(inode->i_sb, ce->e_value, - EXT4_IGET_NORMAL); - if (!IS_ERR(ea_inode) && - !is_bad_inode(ea_inode) && - (EXT4_I(ea_inode)->i_flags & EXT4_EA_INODE_FL) && - i_size_read(ea_inode) == value_len && + EXT4_IGET_EA_INODE); + if (IS_ERR(ea_inode)) + goto next_entry; + ext4_xattr_inode_set_class(ea_inode); + if (i_size_read(ea_inode) == value_len && !ext4_xattr_inode_read(ea_inode, ea_data, value_len) && !ext4_xattr_inode_verify_hashes(ea_inode, NULL, ea_data, value_len) && @@ -1570,9 +1554,8 @@ ext4_xattr_inode_cache_find(struct inode *inode, const void *value, kvfree(ea_data); return ea_inode; } - - if (!IS_ERR(ea_inode)) - iput(ea_inode); + iput(ea_inode); + next_entry: ce = mb_cache_entry_find_next(ea_inode_cache, ce); } kvfree(ea_data); diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index e63c1d46f189..8f3112e71a6a 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -317,7 +317,7 @@ static int nfs_readdir_folio_array_append(struct folio *folio, name = nfs_readdir_copy_name(entry->name, entry->len); - array = kmap_atomic(folio_page(folio, 0)); + array = kmap_local_folio(folio, 0); if (!name) goto out; ret = nfs_readdir_array_can_expand(array); @@ -340,7 +340,7 @@ static int nfs_readdir_folio_array_append(struct folio *folio, nfs_readdir_array_set_eof(array); out: *cookie = array->last_cookie; - kunmap_atomic(array); + kunmap_local(array); return ret; } diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 18f25ff4bff7..d3665390c4cb 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -5437,10 +5437,18 @@ static bool nfs4_read_plus_not_supported(struct rpc_task *task, return false; } -static int nfs4_read_done(struct rpc_task *task, struct nfs_pgio_header *hdr) +static inline void nfs4_read_plus_scratch_free(struct nfs_pgio_header *hdr) { - if (hdr->res.scratch) + if (hdr->res.scratch) { kfree(hdr->res.scratch); + hdr->res.scratch = NULL; + } +} + +static int nfs4_read_done(struct rpc_task *task, struct nfs_pgio_header *hdr) +{ + nfs4_read_plus_scratch_free(hdr); + if (!nfs4_sequence_done(task, &hdr->res.seq_res)) return -EAGAIN; if (nfs4_read_stateid_changed(task, &hdr->args)) diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index 1310d2d5feb3..a8ce522ac747 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -917,6 +917,7 @@ void nilfs_evict_inode(struct inode *inode) struct nilfs_transaction_info ti; struct super_block *sb = inode->i_sb; struct nilfs_inode_info *ii = NILFS_I(inode); + struct the_nilfs *nilfs; int ret; if (inode->i_nlink || !ii->i_root || unlikely(is_bad_inode(inode))) { @@ -929,6 +930,23 @@ void nilfs_evict_inode(struct inode *inode) truncate_inode_pages_final(&inode->i_data); + nilfs = sb->s_fs_info; + if (unlikely(sb_rdonly(sb) || !nilfs->ns_writer)) { + /* + * If this inode is about to be disposed after the file system + * has been degraded to read-only due to file system corruption + * or after the writer has been detached, do not make any + * changes that cause writes, just clear it. + * Do this check after read-locking ns_segctor_sem by + * nilfs_transaction_begin() in order to avoid a race with + * the writer detach operation. + */ + clear_inode(inode); + nilfs_clear_inode(inode); + nilfs_transaction_abort(sb); + return; + } + /* TODO: some of the following operations may fail. */ nilfs_truncate_bmap(ii, 0); nilfs_mark_inode_dirty(inode); diff --git a/fs/smb/Kconfig b/fs/smb/Kconfig new file mode 100644 index 000000000000..ef425789fa6a --- /dev/null +++ b/fs/smb/Kconfig @@ -0,0 +1,11 @@ +# SPDX-License-Identifier: GPL-2.0-only +# +# smbfs configuration + +source "fs/smb/client/Kconfig" +source "fs/smb/server/Kconfig" + +config SMBFS + tristate + default y if CIFS=y || SMB_SERVER=y + default m if CIFS=m || SMB_SERVER=m diff --git a/fs/smb/Makefile b/fs/smb/Makefile new file mode 100644 index 000000000000..9a1bf59a1a65 --- /dev/null +++ b/fs/smb/Makefile @@ -0,0 +1,5 @@ +# SPDX-License-Identifier: GPL-2.0 + +obj-$(CONFIG_SMBFS) += common/ +obj-$(CONFIG_CIFS) += client/ +obj-$(CONFIG_SMB_SERVER) += server/ diff --git a/fs/cifs/Kconfig b/fs/smb/client/Kconfig index 4c0d53bf931a..4c0d53bf931a 100644 --- a/fs/cifs/Kconfig +++ b/fs/smb/client/Kconfig diff --git a/fs/cifs/Makefile b/fs/smb/client/Makefile index 304a7f6cc13a..304a7f6cc13a 100644 --- a/fs/cifs/Makefile +++ b/fs/smb/client/Makefile diff --git a/fs/cifs/asn1.c b/fs/smb/client/asn1.c index b5724ef9f182..b5724ef9f182 100644 --- a/fs/cifs/asn1.c +++ b/fs/smb/client/asn1.c diff --git a/fs/cifs/cached_dir.c b/fs/smb/client/cached_dir.c index bfc964b36c72..bfc964b36c72 100644 --- a/fs/cifs/cached_dir.c +++ b/fs/smb/client/cached_dir.c diff --git a/fs/cifs/cached_dir.h b/fs/smb/client/cached_dir.h index 2f4e764c9ca9..2f4e764c9ca9 100644 --- a/fs/cifs/cached_dir.h +++ b/fs/smb/client/cached_dir.h diff --git a/fs/cifs/cifs_debug.c b/fs/smb/client/cifs_debug.c index d4ed200a9471..5034b862cec2 100644 --- a/fs/cifs/cifs_debug.c +++ b/fs/smb/client/cifs_debug.c @@ -108,7 +108,7 @@ static void cifs_debug_tcon(struct seq_file *m, struct cifs_tcon *tcon) if ((tcon->seal) || (tcon->ses->session_flags & SMB2_SESSION_FLAG_ENCRYPT_DATA) || (tcon->share_flags & SHI1005_FLAGS_ENCRYPT_DATA)) - seq_printf(m, " Encrypted"); + seq_puts(m, " encrypted"); if (tcon->nocase) seq_printf(m, " nocase"); if (tcon->unix_ext) @@ -415,8 +415,12 @@ skip_rdma: /* dump session id helpful for use with network trace */ seq_printf(m, " SessionId: 0x%llx", ses->Suid); - if (ses->session_flags & SMB2_SESSION_FLAG_ENCRYPT_DATA) + if (ses->session_flags & SMB2_SESSION_FLAG_ENCRYPT_DATA) { seq_puts(m, " encrypted"); + /* can help in debugging to show encryption type */ + if (server->cipher_type == SMB2_ENCRYPTION_AES256_GCM) + seq_puts(m, "(gcm256)"); + } if (ses->sign) seq_puts(m, " signed"); diff --git a/fs/cifs/cifs_debug.h b/fs/smb/client/cifs_debug.h index ce5cfd236fdb..ce5cfd236fdb 100644 --- a/fs/cifs/cifs_debug.h +++ b/fs/smb/client/cifs_debug.h diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/smb/client/cifs_dfs_ref.c index 0329a907bdfe..0329a907bdfe 100644 --- a/fs/cifs/cifs_dfs_ref.c +++ b/fs/smb/client/cifs_dfs_ref.c diff --git a/fs/cifs/cifs_fs_sb.h b/fs/smb/client/cifs_fs_sb.h index 651759192280..651759192280 100644 --- a/fs/cifs/cifs_fs_sb.h +++ b/fs/smb/client/cifs_fs_sb.h diff --git a/fs/cifs/cifs_ioctl.h b/fs/smb/client/cifs_ioctl.h index 332588e77c31..332588e77c31 100644 --- a/fs/cifs/cifs_ioctl.h +++ b/fs/smb/client/cifs_ioctl.h diff --git a/fs/cifs/cifs_spnego.c b/fs/smb/client/cifs_spnego.c index 6f3285f1dfee..6f3285f1dfee 100644 --- a/fs/cifs/cifs_spnego.c +++ b/fs/smb/client/cifs_spnego.c diff --git a/fs/cifs/cifs_spnego.h b/fs/smb/client/cifs_spnego.h index e4d751b0c812..e4d751b0c812 100644 --- a/fs/cifs/cifs_spnego.h +++ b/fs/smb/client/cifs_spnego.h diff --git a/fs/cifs/cifs_spnego_negtokeninit.asn1 b/fs/smb/client/cifs_spnego_negtokeninit.asn1 index 181c083887d5..181c083887d5 100644 --- a/fs/cifs/cifs_spnego_negtokeninit.asn1 +++ b/fs/smb/client/cifs_spnego_negtokeninit.asn1 diff --git a/fs/cifs/cifs_swn.c b/fs/smb/client/cifs_swn.c index 7233c6a7e6d7..7233c6a7e6d7 100644 --- a/fs/cifs/cifs_swn.c +++ b/fs/smb/client/cifs_swn.c diff --git a/fs/cifs/cifs_swn.h b/fs/smb/client/cifs_swn.h index 8a9d2a5c9077..8a9d2a5c9077 100644 --- a/fs/cifs/cifs_swn.h +++ b/fs/smb/client/cifs_swn.h diff --git a/fs/cifs/cifs_unicode.c b/fs/smb/client/cifs_unicode.c index e7582dd79179..e7582dd79179 100644 --- a/fs/cifs/cifs_unicode.c +++ b/fs/smb/client/cifs_unicode.c diff --git a/fs/cifs/cifs_unicode.h b/fs/smb/client/cifs_unicode.h index 80b3d845419f..80b3d845419f 100644 --- a/fs/cifs/cifs_unicode.h +++ b/fs/smb/client/cifs_unicode.h diff --git a/fs/cifs/cifs_uniupr.h b/fs/smb/client/cifs_uniupr.h index 7b272fcdf0d3..7b272fcdf0d3 100644 --- a/fs/cifs/cifs_uniupr.h +++ b/fs/smb/client/cifs_uniupr.h diff --git a/fs/cifs/cifsacl.c b/fs/smb/client/cifsacl.c index f5b6df82e857..f5b6df82e857 100644 --- a/fs/cifs/cifsacl.c +++ b/fs/smb/client/cifsacl.c diff --git a/fs/cifs/cifsacl.h b/fs/smb/client/cifsacl.h index ccbfc754bd3c..ccbfc754bd3c 100644 --- a/fs/cifs/cifsacl.h +++ b/fs/smb/client/cifsacl.h diff --git a/fs/cifs/cifsencrypt.c b/fs/smb/client/cifsencrypt.c index 357bd27a7fd1..ef4c2e3c9fa6 100644 --- a/fs/cifs/cifsencrypt.c +++ b/fs/smb/client/cifsencrypt.c @@ -21,7 +21,7 @@ #include <linux/random.h> #include <linux/highmem.h> #include <linux/fips.h> -#include "../smbfs_common/arc4.h" +#include "../common/arc4.h" #include <crypto/aead.h> /* diff --git a/fs/cifs/cifsfs.c b/fs/smb/client/cifsfs.c index 43a4d8603db3..43a4d8603db3 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/smb/client/cifsfs.c diff --git a/fs/cifs/cifsfs.h b/fs/smb/client/cifsfs.h index 74cd6fafb33e..74cd6fafb33e 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/smb/client/cifsfs.h diff --git a/fs/cifs/cifsglob.h b/fs/smb/client/cifsglob.h index 414685c5d530..0d84bb1a8cd9 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -24,7 +24,7 @@ #include "cifsacl.h" #include <crypto/internal/hash.h> #include <uapi/linux/cifs/cifs_mount.h> -#include "../smbfs_common/smb2pdu.h" +#include "../common/smb2pdu.h" #include "smb2pdu.h" #include <linux/filelock.h> @@ -424,8 +424,8 @@ struct smb_version_operations { /* check for STATUS_NETWORK_SESSION_EXPIRED */ bool (*is_session_expired)(char *); /* send oplock break response */ - int (*oplock_response)(struct cifs_tcon *, struct cifs_fid *, - struct cifsInodeInfo *); + int (*oplock_response)(struct cifs_tcon *tcon, __u64 persistent_fid, __u64 volatile_fid, + __u16 net_fid, struct cifsInodeInfo *cifs_inode); /* query remote filesystem */ int (*queryfs)(const unsigned int, struct cifs_tcon *, struct cifs_sb_info *, struct kstatfs *); diff --git a/fs/cifs/cifspdu.h b/fs/smb/client/cifspdu.h index 445e3eaebcc1..e17222fec9d2 100644 --- a/fs/cifs/cifspdu.h +++ b/fs/smb/client/cifspdu.h @@ -11,7 +11,7 @@ #include <net/sock.h> #include <asm/unaligned.h> -#include "../smbfs_common/smbfsctl.h" +#include "../common/smbfsctl.h" #define CIFS_PROT 0 #define POSIX_PROT (CIFS_PROT+1) diff --git a/fs/cifs/cifsproto.h b/fs/smb/client/cifsproto.h index c1c704990b98..c1c704990b98 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/smb/client/cifsproto.h diff --git a/fs/cifs/cifsroot.c b/fs/smb/client/cifsroot.c index 56ec1b233f52..56ec1b233f52 100644 --- a/fs/cifs/cifsroot.c +++ b/fs/smb/client/cifsroot.c diff --git a/fs/cifs/cifssmb.c b/fs/smb/client/cifssmb.c index 9d963caec35c..9d963caec35c 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/smb/client/cifssmb.c diff --git a/fs/cifs/connect.c b/fs/smb/client/connect.c index 8e9a672320ab..8e9a672320ab 100644 --- a/fs/cifs/connect.c +++ b/fs/smb/client/connect.c diff --git a/fs/cifs/dfs.c b/fs/smb/client/dfs.c index a93dbca1411b..2f93bf8c3325 100644 --- a/fs/cifs/dfs.c +++ b/fs/smb/client/dfs.c @@ -303,7 +303,7 @@ int dfs_mount_share(struct cifs_mount_ctx *mnt_ctx, bool *isdfs) if (!nodfs) { rc = dfs_get_referral(mnt_ctx, ctx->UNC + 1, NULL, NULL); if (rc) { - if (rc != -ENOENT && rc != -EOPNOTSUPP) + if (rc != -ENOENT && rc != -EOPNOTSUPP && rc != -EIO) goto out; nodfs = true; } diff --git a/fs/cifs/dfs.h b/fs/smb/client/dfs.h index 1c90df5ecfbd..1c90df5ecfbd 100644 --- a/fs/cifs/dfs.h +++ b/fs/smb/client/dfs.h diff --git a/fs/cifs/dfs_cache.c b/fs/smb/client/dfs_cache.c index 1513b2709889..1513b2709889 100644 --- a/fs/cifs/dfs_cache.c +++ b/fs/smb/client/dfs_cache.c diff --git a/fs/cifs/dfs_cache.h b/fs/smb/client/dfs_cache.h index c6d89cd6d4fd..c6d89cd6d4fd 100644 --- a/fs/cifs/dfs_cache.h +++ b/fs/smb/client/dfs_cache.h diff --git a/fs/cifs/dir.c b/fs/smb/client/dir.c index 30b1e1bfd204..30b1e1bfd204 100644 --- a/fs/cifs/dir.c +++ b/fs/smb/client/dir.c diff --git a/fs/cifs/dns_resolve.c b/fs/smb/client/dns_resolve.c index 8bf8978bc5d6..8bf8978bc5d6 100644 --- a/fs/cifs/dns_resolve.c +++ b/fs/smb/client/dns_resolve.c diff --git a/fs/cifs/dns_resolve.h b/fs/smb/client/dns_resolve.h index 6eb0c15a2440..6eb0c15a2440 100644 --- a/fs/cifs/dns_resolve.h +++ b/fs/smb/client/dns_resolve.h diff --git a/fs/cifs/export.c b/fs/smb/client/export.c index 37c28415df1e..37c28415df1e 100644 --- a/fs/cifs/export.c +++ b/fs/smb/client/export.c diff --git a/fs/cifs/file.c b/fs/smb/client/file.c index c5fcefdfd797..df88b8c04d03 100644 --- a/fs/cifs/file.c +++ b/fs/smb/client/file.c @@ -3353,9 +3353,10 @@ static size_t cifs_limit_bvec_subset(const struct iov_iter *iter, size_t max_siz while (n && ix < nbv) { len = min3(n, bvecs[ix].bv_len - skip, max_size); span += len; + max_size -= len; nsegs++; ix++; - if (span >= max_size || nsegs >= max_segs) + if (max_size == 0 || nsegs >= max_segs) break; skip = 0; n -= len; @@ -4881,9 +4882,9 @@ void cifs_oplock_break(struct work_struct *work) struct cifs_tcon *tcon = tlink_tcon(cfile->tlink); struct TCP_Server_Info *server = tcon->ses->server; int rc = 0; - bool purge_cache = false; - struct cifs_deferred_close *dclose; - bool is_deferred = false; + bool purge_cache = false, oplock_break_cancelled; + __u64 persistent_fid, volatile_fid; + __u16 net_fid; wait_on_bit(&cinode->flags, CIFS_INODE_PENDING_WRITERS, TASK_UNINTERRUPTIBLE); @@ -4924,28 +4925,28 @@ oplock_break_ack: * file handles but cached, then schedule deferred close immediately. * So, new open will not use cached handle. */ - spin_lock(&CIFS_I(inode)->deferred_lock); - is_deferred = cifs_is_deferred_close(cfile, &dclose); - spin_unlock(&CIFS_I(inode)->deferred_lock); - if (!CIFS_CACHE_HANDLE(cinode) && is_deferred && - cfile->deferred_close_scheduled && delayed_work_pending(&cfile->deferred)) { + if (!CIFS_CACHE_HANDLE(cinode) && !list_empty(&cinode->deferred_closes)) cifs_close_deferred_file(cinode); - } + persistent_fid = cfile->fid.persistent_fid; + volatile_fid = cfile->fid.volatile_fid; + net_fid = cfile->fid.netfid; + oplock_break_cancelled = cfile->oplock_break_cancelled; + + _cifsFileInfo_put(cfile, false /* do not wait for ourself */, false); /* * releasing stale oplock after recent reconnect of smb session using * a now incorrect file handle is not a data integrity issue but do * not bother sending an oplock release if session to server still is * disconnected since oplock already released by the server */ - if (!cfile->oplock_break_cancelled) { - rc = tcon->ses->server->ops->oplock_response(tcon, &cfile->fid, - cinode); + if (!oplock_break_cancelled) { + rc = tcon->ses->server->ops->oplock_response(tcon, persistent_fid, + volatile_fid, net_fid, cinode); cifs_dbg(FYI, "Oplock release rc = %d\n", rc); } - _cifsFileInfo_put(cfile, false /* do not wait for ourself */, false); cifs_done_oplock_break(cinode); } diff --git a/fs/cifs/fs_context.c b/fs/smb/client/fs_context.c index ace11a1a7c8a..1bda75609b64 100644 --- a/fs/cifs/fs_context.c +++ b/fs/smb/client/fs_context.c @@ -904,6 +904,14 @@ static int smb3_fs_context_parse_param(struct fs_context *fc, ctx->sfu_remap = false; /* disable SFU mapping */ } break; + case Opt_mapchars: + if (result.negated) + ctx->sfu_remap = false; + else { + ctx->sfu_remap = true; + ctx->remap = false; /* disable SFM (mapposix) mapping */ + } + break; case Opt_user_xattr: if (result.negated) ctx->no_xattr = 1; diff --git a/fs/cifs/fs_context.h b/fs/smb/client/fs_context.h index f4eaf8558902..f4eaf8558902 100644 --- a/fs/cifs/fs_context.h +++ b/fs/smb/client/fs_context.h diff --git a/fs/cifs/fscache.c b/fs/smb/client/fscache.c index 8f6909d633da..8f6909d633da 100644 --- a/fs/cifs/fscache.c +++ b/fs/smb/client/fscache.c diff --git a/fs/cifs/fscache.h b/fs/smb/client/fscache.h index 173999610997..173999610997 100644 --- a/fs/cifs/fscache.h +++ b/fs/smb/client/fscache.h diff --git a/fs/cifs/inode.c b/fs/smb/client/inode.c index 1087ac6104a9..1087ac6104a9 100644 --- a/fs/cifs/inode.c +++ b/fs/smb/client/inode.c diff --git a/fs/cifs/ioctl.c b/fs/smb/client/ioctl.c index cb3be58cd55e..fff092bbc7a3 100644 --- a/fs/cifs/ioctl.c +++ b/fs/smb/client/ioctl.c @@ -321,7 +321,11 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg) struct tcon_link *tlink; struct cifs_sb_info *cifs_sb; __u64 ExtAttrBits = 0; +#ifdef CONFIG_CIFS_POSIX +#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY __u64 caps; +#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ +#endif /* CONFIG_CIFS_POSIX */ xid = get_xid(); @@ -331,9 +335,9 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg) if (pSMBFile == NULL) break; tcon = tlink_tcon(pSMBFile->tlink); - caps = le64_to_cpu(tcon->fsUnixInfo.Capability); #ifdef CONFIG_CIFS_POSIX #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY + caps = le64_to_cpu(tcon->fsUnixInfo.Capability); if (CIFS_UNIX_EXTATTR_CAP & caps) { __u64 ExtAttrMask = 0; rc = CIFSGetExtAttr(xid, tcon, diff --git a/fs/cifs/link.c b/fs/smb/client/link.c index c66be4904e1f..c66be4904e1f 100644 --- a/fs/cifs/link.c +++ b/fs/smb/client/link.c diff --git a/fs/cifs/misc.c b/fs/smb/client/misc.c index cd914be905b2..cd914be905b2 100644 --- a/fs/cifs/misc.c +++ b/fs/smb/client/misc.c diff --git a/fs/cifs/netlink.c b/fs/smb/client/netlink.c index 147d9409252c..147d9409252c 100644 --- a/fs/cifs/netlink.c +++ b/fs/smb/client/netlink.c diff --git a/fs/cifs/netlink.h b/fs/smb/client/netlink.h index e2fa8ed24c54..e2fa8ed24c54 100644 --- a/fs/cifs/netlink.h +++ b/fs/smb/client/netlink.h diff --git a/fs/cifs/netmisc.c b/fs/smb/client/netmisc.c index 1b52e6ac431c..1b52e6ac431c 100644 --- a/fs/cifs/netmisc.c +++ b/fs/smb/client/netmisc.c diff --git a/fs/cifs/nterr.c b/fs/smb/client/nterr.c index 358a766375b4..358a766375b4 100644 --- a/fs/cifs/nterr.c +++ b/fs/smb/client/nterr.c diff --git a/fs/cifs/nterr.h b/fs/smb/client/nterr.h index edd4741cab0a..edd4741cab0a 100644 --- a/fs/cifs/nterr.h +++ b/fs/smb/client/nterr.h diff --git a/fs/cifs/ntlmssp.h b/fs/smb/client/ntlmssp.h index 2c5dde2ece58..2c5dde2ece58 100644 --- a/fs/cifs/ntlmssp.h +++ b/fs/smb/client/ntlmssp.h diff --git a/fs/cifs/readdir.c b/fs/smb/client/readdir.c index ef638086d734..ef638086d734 100644 --- a/fs/cifs/readdir.c +++ b/fs/smb/client/readdir.c diff --git a/fs/cifs/rfc1002pdu.h b/fs/smb/client/rfc1002pdu.h index ae1d025da294..ae1d025da294 100644 --- a/fs/cifs/rfc1002pdu.h +++ b/fs/smb/client/rfc1002pdu.h diff --git a/fs/cifs/sess.c b/fs/smb/client/sess.c index 335c078c42fb..335c078c42fb 100644 --- a/fs/cifs/sess.c +++ b/fs/smb/client/sess.c diff --git a/fs/cifs/smb1ops.c b/fs/smb/client/smb1ops.c index abda6148be10..7d1b3fc014d9 100644 --- a/fs/cifs/smb1ops.c +++ b/fs/smb/client/smb1ops.c @@ -897,12 +897,11 @@ cifs_close_dir(const unsigned int xid, struct cifs_tcon *tcon, } static int -cifs_oplock_response(struct cifs_tcon *tcon, struct cifs_fid *fid, - struct cifsInodeInfo *cinode) +cifs_oplock_response(struct cifs_tcon *tcon, __u64 persistent_fid, + __u64 volatile_fid, __u16 net_fid, struct cifsInodeInfo *cinode) { - return CIFSSMBLock(0, tcon, fid->netfid, current->tgid, 0, 0, 0, 0, - LOCKING_ANDX_OPLOCK_RELEASE, false, - CIFS_CACHE_READ(cinode) ? 1 : 0); + return CIFSSMBLock(0, tcon, net_fid, current->tgid, 0, 0, 0, 0, + LOCKING_ANDX_OPLOCK_RELEASE, false, CIFS_CACHE_READ(cinode) ? 1 : 0); } static int diff --git a/fs/cifs/smb2file.c b/fs/smb/client/smb2file.c index e0ee96d69d49..e0ee96d69d49 100644 --- a/fs/cifs/smb2file.c +++ b/fs/smb/client/smb2file.c diff --git a/fs/cifs/smb2glob.h b/fs/smb/client/smb2glob.h index 82e916ad167c..82e916ad167c 100644 --- a/fs/cifs/smb2glob.h +++ b/fs/smb/client/smb2glob.h diff --git a/fs/cifs/smb2inode.c b/fs/smb/client/smb2inode.c index 163a03298430..163a03298430 100644 --- a/fs/cifs/smb2inode.c +++ b/fs/smb/client/smb2inode.c diff --git a/fs/cifs/smb2maperror.c b/fs/smb/client/smb2maperror.c index 194799ddd382..194799ddd382 100644 --- a/fs/cifs/smb2maperror.c +++ b/fs/smb/client/smb2maperror.c diff --git a/fs/cifs/smb2misc.c b/fs/smb/client/smb2misc.c index 3935a60db5c3..3935a60db5c3 100644 --- a/fs/cifs/smb2misc.c +++ b/fs/smb/client/smb2misc.c diff --git a/fs/cifs/smb2ops.c b/fs/smb/client/smb2ops.c index a295e4c2d54e..6e3be58cfe49 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -618,7 +618,6 @@ parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf, * Add a new one instead */ spin_lock(&ses->iface_lock); - iface = niface = NULL; list_for_each_entry_safe(iface, niface, &ses->iface_list, iface_head) { ret = iface_cmp(iface, &tmp_iface); @@ -2383,15 +2382,14 @@ smb2_is_network_name_deleted(char *buf, struct TCP_Server_Info *server) } static int -smb2_oplock_response(struct cifs_tcon *tcon, struct cifs_fid *fid, - struct cifsInodeInfo *cinode) +smb2_oplock_response(struct cifs_tcon *tcon, __u64 persistent_fid, + __u64 volatile_fid, __u16 net_fid, struct cifsInodeInfo *cinode) { if (tcon->ses->server->capabilities & SMB2_GLOBAL_CAP_LEASING) return SMB2_lease_break(0, tcon, cinode->lease_key, smb2_get_lease_state(cinode)); - return SMB2_oplock_break(0, tcon, fid->persistent_fid, - fid->volatile_fid, + return SMB2_oplock_break(0, tcon, persistent_fid, volatile_fid, CIFS_CACHE_READ(cinode) ? 1 : 0); } diff --git a/fs/cifs/smb2pdu.c b/fs/smb/client/smb2pdu.c index 9ed61b6f9b21..7063b395d22f 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -3725,7 +3725,7 @@ SMB2_change_notify(const unsigned int xid, struct cifs_tcon *tcon, if (*out_data == NULL) { rc = -ENOMEM; goto cnotify_exit; - } else + } else if (plen) *plen = le32_to_cpu(smb_rsp->OutputBufferLength); } diff --git a/fs/cifs/smb2pdu.h b/fs/smb/client/smb2pdu.h index 220994d0a0f7..220994d0a0f7 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/smb/client/smb2pdu.h diff --git a/fs/cifs/smb2proto.h b/fs/smb/client/smb2proto.h index d5d7ffb7711c..d5d7ffb7711c 100644 --- a/fs/cifs/smb2proto.h +++ b/fs/smb/client/smb2proto.h diff --git a/fs/cifs/smb2status.h b/fs/smb/client/smb2status.h index a9e958166fc5..a9e958166fc5 100644 --- a/fs/cifs/smb2status.h +++ b/fs/smb/client/smb2status.h diff --git a/fs/cifs/smb2transport.c b/fs/smb/client/smb2transport.c index 790acf65a092..790acf65a092 100644 --- a/fs/cifs/smb2transport.c +++ b/fs/smb/client/smb2transport.c diff --git a/fs/cifs/smbdirect.c b/fs/smb/client/smbdirect.c index 0362ebd4fa0f..0362ebd4fa0f 100644 --- a/fs/cifs/smbdirect.c +++ b/fs/smb/client/smbdirect.c diff --git a/fs/cifs/smbdirect.h b/fs/smb/client/smbdirect.h index 83f239f376f0..83f239f376f0 100644 --- a/fs/cifs/smbdirect.h +++ b/fs/smb/client/smbdirect.h diff --git a/fs/cifs/smbencrypt.c b/fs/smb/client/smbencrypt.c index 4a0487753869..f0ce26414f17 100644 --- a/fs/cifs/smbencrypt.c +++ b/fs/smb/client/smbencrypt.c @@ -24,7 +24,7 @@ #include "cifsglob.h" #include "cifs_debug.h" #include "cifsproto.h" -#include "../smbfs_common/md4.h" +#include "../common/md4.h" #ifndef false #define false 0 diff --git a/fs/cifs/smberr.h b/fs/smb/client/smberr.h index aeffdad829e2..aeffdad829e2 100644 --- a/fs/cifs/smberr.h +++ b/fs/smb/client/smberr.h diff --git a/fs/cifs/trace.c b/fs/smb/client/trace.c index 465483787193..465483787193 100644 --- a/fs/cifs/trace.c +++ b/fs/smb/client/trace.c diff --git a/fs/cifs/trace.h b/fs/smb/client/trace.h index d3053bd8ae73..d3053bd8ae73 100644 --- a/fs/cifs/trace.h +++ b/fs/smb/client/trace.h diff --git a/fs/cifs/transport.c b/fs/smb/client/transport.c index 24bdd5f4d3bc..24bdd5f4d3bc 100644 --- a/fs/cifs/transport.c +++ b/fs/smb/client/transport.c diff --git a/fs/cifs/unc.c b/fs/smb/client/unc.c index f6fc5e343ea4..f6fc5e343ea4 100644 --- a/fs/cifs/unc.c +++ b/fs/smb/client/unc.c diff --git a/fs/cifs/winucase.c b/fs/smb/client/winucase.c index 2f075b5b50df..2f075b5b50df 100644 --- a/fs/cifs/winucase.c +++ b/fs/smb/client/winucase.c diff --git a/fs/cifs/xattr.c b/fs/smb/client/xattr.c index 4ad5531686d8..4ad5531686d8 100644 --- a/fs/cifs/xattr.c +++ b/fs/smb/client/xattr.c diff --git a/fs/smbfs_common/Makefile b/fs/smb/common/Makefile index cafc61a3bfc3..c66dbbc1469c 100644 --- a/fs/smbfs_common/Makefile +++ b/fs/smb/common/Makefile @@ -3,5 +3,5 @@ # Makefile for Linux filesystem routines that are shared by client and server. # -obj-$(CONFIG_SMBFS_COMMON) += cifs_arc4.o -obj-$(CONFIG_SMBFS_COMMON) += cifs_md4.o +obj-$(CONFIG_SMBFS) += cifs_arc4.o +obj-$(CONFIG_SMBFS) += cifs_md4.o diff --git a/fs/smbfs_common/arc4.h b/fs/smb/common/arc4.h index 12e71ec033a1..12e71ec033a1 100644 --- a/fs/smbfs_common/arc4.h +++ b/fs/smb/common/arc4.h diff --git a/fs/smbfs_common/cifs_arc4.c b/fs/smb/common/cifs_arc4.c index 043e4cb839fa..043e4cb839fa 100644 --- a/fs/smbfs_common/cifs_arc4.c +++ b/fs/smb/common/cifs_arc4.c diff --git a/fs/smbfs_common/cifs_md4.c b/fs/smb/common/cifs_md4.c index 50f78cfc6ce9..50f78cfc6ce9 100644 --- a/fs/smbfs_common/cifs_md4.c +++ b/fs/smb/common/cifs_md4.c diff --git a/fs/smbfs_common/md4.h b/fs/smb/common/md4.h index 5337becc699a..5337becc699a 100644 --- a/fs/smbfs_common/md4.h +++ b/fs/smb/common/md4.h diff --git a/fs/smbfs_common/smb2pdu.h b/fs/smb/common/smb2pdu.h index bae590eec871..bae590eec871 100644 --- a/fs/smbfs_common/smb2pdu.h +++ b/fs/smb/common/smb2pdu.h diff --git a/fs/smbfs_common/smbfsctl.h b/fs/smb/common/smbfsctl.h index edd7fc2a7921..edd7fc2a7921 100644 --- a/fs/smbfs_common/smbfsctl.h +++ b/fs/smb/common/smbfsctl.h diff --git a/fs/ksmbd/Kconfig b/fs/smb/server/Kconfig index 7055cb5d2880..7055cb5d2880 100644 --- a/fs/ksmbd/Kconfig +++ b/fs/smb/server/Kconfig diff --git a/fs/ksmbd/Makefile b/fs/smb/server/Makefile index 7d6337a7dee4..7d6337a7dee4 100644 --- a/fs/ksmbd/Makefile +++ b/fs/smb/server/Makefile diff --git a/fs/ksmbd/asn1.c b/fs/smb/server/asn1.c index cc6384f79675..cc6384f79675 100644 --- a/fs/ksmbd/asn1.c +++ b/fs/smb/server/asn1.c diff --git a/fs/ksmbd/asn1.h b/fs/smb/server/asn1.h index ce105f4ce305..ce105f4ce305 100644 --- a/fs/ksmbd/asn1.h +++ b/fs/smb/server/asn1.h diff --git a/fs/ksmbd/auth.c b/fs/smb/server/auth.c index df8fb076f6f1..5e5e120edcc2 100644 --- a/fs/ksmbd/auth.c +++ b/fs/smb/server/auth.c @@ -29,7 +29,7 @@ #include "mgmt/user_config.h" #include "crypto_ctx.h" #include "transport_ipc.h" -#include "../smbfs_common/arc4.h" +#include "../common/arc4.h" /* * Fixed format data defining GSS header and fixed string diff --git a/fs/ksmbd/auth.h b/fs/smb/server/auth.h index 362b6159a6cf..362b6159a6cf 100644 --- a/fs/ksmbd/auth.h +++ b/fs/smb/server/auth.h diff --git a/fs/ksmbd/connection.c b/fs/smb/server/connection.c index 4ed379f9b1aa..4882a812ea86 100644 --- a/fs/ksmbd/connection.c +++ b/fs/smb/server/connection.c @@ -351,7 +351,8 @@ int ksmbd_conn_handler_loop(void *p) break; /* 4 for rfc1002 length field */ - size = pdu_size + 4; + /* 1 for implied bcc[0] */ + size = pdu_size + 4 + 1; conn->request_buf = kvmalloc(size, GFP_KERNEL); if (!conn->request_buf) break; diff --git a/fs/ksmbd/connection.h b/fs/smb/server/connection.h index ad8dfaa48ffb..ad8dfaa48ffb 100644 --- a/fs/ksmbd/connection.h +++ b/fs/smb/server/connection.h diff --git a/fs/ksmbd/crypto_ctx.c b/fs/smb/server/crypto_ctx.c index 81488d04199d..81488d04199d 100644 --- a/fs/ksmbd/crypto_ctx.c +++ b/fs/smb/server/crypto_ctx.c diff --git a/fs/ksmbd/crypto_ctx.h b/fs/smb/server/crypto_ctx.h index 4a367c62f653..4a367c62f653 100644 --- a/fs/ksmbd/crypto_ctx.h +++ b/fs/smb/server/crypto_ctx.h diff --git a/fs/ksmbd/glob.h b/fs/smb/server/glob.h index 5b8f3e0ebdb3..5b8f3e0ebdb3 100644 --- a/fs/ksmbd/glob.h +++ b/fs/smb/server/glob.h diff --git a/fs/ksmbd/ksmbd_netlink.h b/fs/smb/server/ksmbd_netlink.h index fb8b2d566efb..fb8b2d566efb 100644 --- a/fs/ksmbd/ksmbd_netlink.h +++ b/fs/smb/server/ksmbd_netlink.h diff --git a/fs/ksmbd/ksmbd_spnego_negtokeninit.asn1 b/fs/smb/server/ksmbd_spnego_negtokeninit.asn1 index 0065f191b54b..0065f191b54b 100644 --- a/fs/ksmbd/ksmbd_spnego_negtokeninit.asn1 +++ b/fs/smb/server/ksmbd_spnego_negtokeninit.asn1 diff --git a/fs/ksmbd/ksmbd_spnego_negtokentarg.asn1 b/fs/smb/server/ksmbd_spnego_negtokentarg.asn1 index 1151933e7b9c..1151933e7b9c 100644 --- a/fs/ksmbd/ksmbd_spnego_negtokentarg.asn1 +++ b/fs/smb/server/ksmbd_spnego_negtokentarg.asn1 diff --git a/fs/ksmbd/ksmbd_work.c b/fs/smb/server/ksmbd_work.c index 14b9caebf7a4..14b9caebf7a4 100644 --- a/fs/ksmbd/ksmbd_work.c +++ b/fs/smb/server/ksmbd_work.c diff --git a/fs/ksmbd/ksmbd_work.h b/fs/smb/server/ksmbd_work.h index f8ae6144c0ae..f8ae6144c0ae 100644 --- a/fs/ksmbd/ksmbd_work.h +++ b/fs/smb/server/ksmbd_work.h diff --git a/fs/ksmbd/mgmt/ksmbd_ida.c b/fs/smb/server/mgmt/ksmbd_ida.c index 54194d959a5e..54194d959a5e 100644 --- a/fs/ksmbd/mgmt/ksmbd_ida.c +++ b/fs/smb/server/mgmt/ksmbd_ida.c diff --git a/fs/ksmbd/mgmt/ksmbd_ida.h b/fs/smb/server/mgmt/ksmbd_ida.h index 2bc07b16cfde..2bc07b16cfde 100644 --- a/fs/ksmbd/mgmt/ksmbd_ida.h +++ b/fs/smb/server/mgmt/ksmbd_ida.h diff --git a/fs/ksmbd/mgmt/share_config.c b/fs/smb/server/mgmt/share_config.c index 328a412259dc..328a412259dc 100644 --- a/fs/ksmbd/mgmt/share_config.c +++ b/fs/smb/server/mgmt/share_config.c diff --git a/fs/ksmbd/mgmt/share_config.h b/fs/smb/server/mgmt/share_config.h index 3fd338293942..3fd338293942 100644 --- a/fs/ksmbd/mgmt/share_config.h +++ b/fs/smb/server/mgmt/share_config.h diff --git a/fs/ksmbd/mgmt/tree_connect.c b/fs/smb/server/mgmt/tree_connect.c index f07a05f37651..f07a05f37651 100644 --- a/fs/ksmbd/mgmt/tree_connect.c +++ b/fs/smb/server/mgmt/tree_connect.c diff --git a/fs/ksmbd/mgmt/tree_connect.h b/fs/smb/server/mgmt/tree_connect.h index 700df36cf3e3..700df36cf3e3 100644 --- a/fs/ksmbd/mgmt/tree_connect.h +++ b/fs/smb/server/mgmt/tree_connect.h diff --git a/fs/ksmbd/mgmt/user_config.c b/fs/smb/server/mgmt/user_config.c index 279d00feff21..279d00feff21 100644 --- a/fs/ksmbd/mgmt/user_config.c +++ b/fs/smb/server/mgmt/user_config.c diff --git a/fs/ksmbd/mgmt/user_config.h b/fs/smb/server/mgmt/user_config.h index 6a44109617f1..6a44109617f1 100644 --- a/fs/ksmbd/mgmt/user_config.h +++ b/fs/smb/server/mgmt/user_config.h diff --git a/fs/ksmbd/mgmt/user_session.c b/fs/smb/server/mgmt/user_session.c index 8a5dcab05614..8a5dcab05614 100644 --- a/fs/ksmbd/mgmt/user_session.c +++ b/fs/smb/server/mgmt/user_session.c diff --git a/fs/ksmbd/mgmt/user_session.h b/fs/smb/server/mgmt/user_session.h index f99d475b28db..f99d475b28db 100644 --- a/fs/ksmbd/mgmt/user_session.h +++ b/fs/smb/server/mgmt/user_session.h diff --git a/fs/ksmbd/misc.c b/fs/smb/server/misc.c index 9e8afaa686e3..9e8afaa686e3 100644 --- a/fs/ksmbd/misc.c +++ b/fs/smb/server/misc.c diff --git a/fs/ksmbd/misc.h b/fs/smb/server/misc.h index 1facfcd21200..1facfcd21200 100644 --- a/fs/ksmbd/misc.h +++ b/fs/smb/server/misc.h diff --git a/fs/ksmbd/ndr.c b/fs/smb/server/ndr.c index 3507d8f89074..3507d8f89074 100644 --- a/fs/ksmbd/ndr.c +++ b/fs/smb/server/ndr.c diff --git a/fs/ksmbd/ndr.h b/fs/smb/server/ndr.h index f3c108c8cf4d..f3c108c8cf4d 100644 --- a/fs/ksmbd/ndr.h +++ b/fs/smb/server/ndr.h diff --git a/fs/ksmbd/nterr.h b/fs/smb/server/nterr.h index 2f358f88a018..2f358f88a018 100644 --- a/fs/ksmbd/nterr.h +++ b/fs/smb/server/nterr.h diff --git a/fs/ksmbd/ntlmssp.h b/fs/smb/server/ntlmssp.h index f13153c18b4e..f13153c18b4e 100644 --- a/fs/ksmbd/ntlmssp.h +++ b/fs/smb/server/ntlmssp.h diff --git a/fs/ksmbd/oplock.c b/fs/smb/server/oplock.c index 2e54ded4d92c..db181bdad73a 100644 --- a/fs/ksmbd/oplock.c +++ b/fs/smb/server/oplock.c @@ -157,13 +157,42 @@ static struct oplock_info *opinfo_get_list(struct ksmbd_inode *ci) rcu_read_lock(); opinfo = list_first_or_null_rcu(&ci->m_op_list, struct oplock_info, op_entry); - if (opinfo && !atomic_inc_not_zero(&opinfo->refcount)) - opinfo = NULL; + if (opinfo) { + if (!atomic_inc_not_zero(&opinfo->refcount)) + opinfo = NULL; + else { + atomic_inc(&opinfo->conn->r_count); + if (ksmbd_conn_releasing(opinfo->conn)) { + atomic_dec(&opinfo->conn->r_count); + atomic_dec(&opinfo->refcount); + opinfo = NULL; + } + } + } + rcu_read_unlock(); return opinfo; } +static void opinfo_conn_put(struct oplock_info *opinfo) +{ + struct ksmbd_conn *conn; + + if (!opinfo) + return; + + conn = opinfo->conn; + /* + * Checking waitqueue to dropping pending requests on + * disconnection. waitqueue_active is safe because it + * uses atomic operation for condition. + */ + if (!atomic_dec_return(&conn->r_count) && waitqueue_active(&conn->r_count_q)) + wake_up(&conn->r_count_q); + opinfo_put(opinfo); +} + void opinfo_put(struct oplock_info *opinfo) { if (!atomic_dec_and_test(&opinfo->refcount)) @@ -666,13 +695,6 @@ static void __smb2_oplock_break_noti(struct work_struct *wk) out: ksmbd_free_work_struct(work); - /* - * Checking waitqueue to dropping pending requests on - * disconnection. waitqueue_active is safe because it - * uses atomic operation for condition. - */ - if (!atomic_dec_return(&conn->r_count) && waitqueue_active(&conn->r_count_q)) - wake_up(&conn->r_count_q); } /** @@ -706,7 +728,6 @@ static int smb2_oplock_break_noti(struct oplock_info *opinfo) work->conn = conn; work->sess = opinfo->sess; - atomic_inc(&conn->r_count); if (opinfo->op_state == OPLOCK_ACK_WAIT) { INIT_WORK(&work->work, __smb2_oplock_break_noti); ksmbd_queue_work(work); @@ -776,13 +797,6 @@ static void __smb2_lease_break_noti(struct work_struct *wk) out: ksmbd_free_work_struct(work); - /* - * Checking waitqueue to dropping pending requests on - * disconnection. waitqueue_active is safe because it - * uses atomic operation for condition. - */ - if (!atomic_dec_return(&conn->r_count) && waitqueue_active(&conn->r_count_q)) - wake_up(&conn->r_count_q); } /** @@ -822,7 +836,6 @@ static int smb2_lease_break_noti(struct oplock_info *opinfo) work->conn = conn; work->sess = opinfo->sess; - atomic_inc(&conn->r_count); if (opinfo->op_state == OPLOCK_ACK_WAIT) { list_for_each_safe(tmp, t, &opinfo->interim_list) { struct ksmbd_work *in_work; @@ -1144,8 +1157,10 @@ int smb_grant_oplock(struct ksmbd_work *work, int req_op_level, u64 pid, } prev_opinfo = opinfo_get_list(ci); if (!prev_opinfo || - (prev_opinfo->level == SMB2_OPLOCK_LEVEL_NONE && lctx)) + (prev_opinfo->level == SMB2_OPLOCK_LEVEL_NONE && lctx)) { + opinfo_conn_put(prev_opinfo); goto set_lev; + } prev_op_has_lease = prev_opinfo->is_lease; if (prev_op_has_lease) prev_op_state = prev_opinfo->o_lease->state; @@ -1153,19 +1168,19 @@ int smb_grant_oplock(struct ksmbd_work *work, int req_op_level, u64 pid, if (share_ret < 0 && prev_opinfo->level == SMB2_OPLOCK_LEVEL_EXCLUSIVE) { err = share_ret; - opinfo_put(prev_opinfo); + opinfo_conn_put(prev_opinfo); goto err_out; } if (prev_opinfo->level != SMB2_OPLOCK_LEVEL_BATCH && prev_opinfo->level != SMB2_OPLOCK_LEVEL_EXCLUSIVE) { - opinfo_put(prev_opinfo); + opinfo_conn_put(prev_opinfo); goto op_break_not_needed; } list_add(&work->interim_entry, &prev_opinfo->interim_list); err = oplock_break(prev_opinfo, SMB2_OPLOCK_LEVEL_II); - opinfo_put(prev_opinfo); + opinfo_conn_put(prev_opinfo); if (err == -ENOENT) goto set_lev; /* Check all oplock was freed by close */ @@ -1228,14 +1243,14 @@ static void smb_break_all_write_oplock(struct ksmbd_work *work, return; if (brk_opinfo->level != SMB2_OPLOCK_LEVEL_BATCH && brk_opinfo->level != SMB2_OPLOCK_LEVEL_EXCLUSIVE) { - opinfo_put(brk_opinfo); + opinfo_conn_put(brk_opinfo); return; } brk_opinfo->open_trunc = is_trunc; list_add(&work->interim_entry, &brk_opinfo->interim_list); oplock_break(brk_opinfo, SMB2_OPLOCK_LEVEL_II); - opinfo_put(brk_opinfo); + opinfo_conn_put(brk_opinfo); } /** @@ -1263,6 +1278,13 @@ void smb_break_all_levII_oplock(struct ksmbd_work *work, struct ksmbd_file *fp, list_for_each_entry_rcu(brk_op, &ci->m_op_list, op_entry) { if (!atomic_inc_not_zero(&brk_op->refcount)) continue; + + atomic_inc(&brk_op->conn->r_count); + if (ksmbd_conn_releasing(brk_op->conn)) { + atomic_dec(&brk_op->conn->r_count); + continue; + } + rcu_read_unlock(); if (brk_op->is_lease && (brk_op->o_lease->state & (~(SMB2_LEASE_READ_CACHING_LE | @@ -1292,7 +1314,7 @@ void smb_break_all_levII_oplock(struct ksmbd_work *work, struct ksmbd_file *fp, brk_op->open_trunc = is_trunc; oplock_break(brk_op, SMB2_OPLOCK_LEVEL_NONE); next: - opinfo_put(brk_op); + opinfo_conn_put(brk_op); rcu_read_lock(); } rcu_read_unlock(); @@ -1449,11 +1471,12 @@ struct lease_ctx_info *parse_lease_state(void *open_req) * smb2_find_context_vals() - find a particular context info in open request * @open_req: buffer containing smb2 file open(create) request * @tag: context name to search for + * @tag_len: the length of tag * * Return: pointer to requested context, NULL if @str context not found * or error pointer if name length is invalid. */ -struct create_context *smb2_find_context_vals(void *open_req, const char *tag) +struct create_context *smb2_find_context_vals(void *open_req, const char *tag, int tag_len) { struct create_context *cc; unsigned int next = 0; @@ -1492,7 +1515,7 @@ struct create_context *smb2_find_context_vals(void *open_req, const char *tag) return ERR_PTR(-EINVAL); name = (char *)cc + name_off; - if (memcmp(name, tag, name_len) == 0) + if (name_len == tag_len && !memcmp(name, tag, name_len)) return cc; remain_len -= next; diff --git a/fs/ksmbd/oplock.h b/fs/smb/server/oplock.h index 09753448f779..4b0fe6da7694 100644 --- a/fs/ksmbd/oplock.h +++ b/fs/smb/server/oplock.h @@ -118,7 +118,7 @@ void create_durable_v2_rsp_buf(char *cc, struct ksmbd_file *fp); void create_mxac_rsp_buf(char *cc, int maximal_access); void create_disk_id_rsp_buf(char *cc, __u64 file_id, __u64 vol_id); void create_posix_rsp_buf(char *cc, struct ksmbd_file *fp); -struct create_context *smb2_find_context_vals(void *open_req, const char *str); +struct create_context *smb2_find_context_vals(void *open_req, const char *tag, int tag_len); struct oplock_info *lookup_lease_in_table(struct ksmbd_conn *conn, char *lease_key); int find_same_lease_key(struct ksmbd_session *sess, struct ksmbd_inode *ci, diff --git a/fs/ksmbd/server.c b/fs/smb/server/server.c index f9b2e0f19b03..f9b2e0f19b03 100644 --- a/fs/ksmbd/server.c +++ b/fs/smb/server/server.c diff --git a/fs/ksmbd/server.h b/fs/smb/server/server.h index db7278181760..db7278181760 100644 --- a/fs/ksmbd/server.h +++ b/fs/smb/server/server.h diff --git a/fs/ksmbd/smb2misc.c b/fs/smb/server/smb2misc.c index fbdde426dd01..0ffe663b7590 100644 --- a/fs/ksmbd/smb2misc.c +++ b/fs/smb/server/smb2misc.c @@ -416,8 +416,11 @@ int ksmbd_smb2_check_message(struct ksmbd_work *work) /* * Allow a message that padded to 8byte boundary. + * Linux 4.19.217 with smb 3.0.2 are sometimes + * sending messages where the cls_len is exactly + * 8 bytes less than len. */ - if (clc_len < len && (len - clc_len) < 8) + if (clc_len < len && (len - clc_len) <= 8) goto validate_credit; pr_err_ratelimited( diff --git a/fs/ksmbd/smb2ops.c b/fs/smb/server/smb2ops.c index aed7704a0672..aed7704a0672 100644 --- a/fs/ksmbd/smb2ops.c +++ b/fs/smb/server/smb2ops.c diff --git a/fs/ksmbd/smb2pdu.c b/fs/smb/server/smb2pdu.c index cb93fd231f4e..7a81541de602 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -326,13 +326,9 @@ int smb2_set_rsp_credits(struct ksmbd_work *work) if (hdr->Command == SMB2_NEGOTIATE) aux_max = 1; else - aux_max = conn->vals->max_credits - credit_charge; + aux_max = conn->vals->max_credits - conn->total_credits; credits_granted = min_t(unsigned short, credits_requested, aux_max); - if (conn->vals->max_credits - conn->total_credits < credits_granted) - credits_granted = conn->vals->max_credits - - conn->total_credits; - conn->total_credits += credits_granted; work->credits_granted += credits_granted; @@ -849,13 +845,14 @@ static void assemble_neg_contexts(struct ksmbd_conn *conn, static __le32 decode_preauth_ctxt(struct ksmbd_conn *conn, struct smb2_preauth_neg_context *pneg_ctxt, - int len_of_ctxts) + int ctxt_len) { /* * sizeof(smb2_preauth_neg_context) assumes SMB311_SALT_SIZE Salt, * which may not be present. Only check for used HashAlgorithms[1]. */ - if (len_of_ctxts < MIN_PREAUTH_CTXT_DATA_LEN) + if (ctxt_len < + sizeof(struct smb2_neg_context) + MIN_PREAUTH_CTXT_DATA_LEN) return STATUS_INVALID_PARAMETER; if (pneg_ctxt->HashAlgorithms != SMB2_PREAUTH_INTEGRITY_SHA512) @@ -867,15 +864,23 @@ static __le32 decode_preauth_ctxt(struct ksmbd_conn *conn, static void decode_encrypt_ctxt(struct ksmbd_conn *conn, struct smb2_encryption_neg_context *pneg_ctxt, - int len_of_ctxts) + int ctxt_len) { - int cph_cnt = le16_to_cpu(pneg_ctxt->CipherCount); - int i, cphs_size = cph_cnt * sizeof(__le16); + int cph_cnt; + int i, cphs_size; + + if (sizeof(struct smb2_encryption_neg_context) > ctxt_len) { + pr_err("Invalid SMB2_ENCRYPTION_CAPABILITIES context size\n"); + return; + } conn->cipher_type = 0; + cph_cnt = le16_to_cpu(pneg_ctxt->CipherCount); + cphs_size = cph_cnt * sizeof(__le16); + if (sizeof(struct smb2_encryption_neg_context) + cphs_size > - len_of_ctxts) { + ctxt_len) { pr_err("Invalid cipher count(%d)\n", cph_cnt); return; } @@ -923,15 +928,22 @@ static void decode_compress_ctxt(struct ksmbd_conn *conn, static void decode_sign_cap_ctxt(struct ksmbd_conn *conn, struct smb2_signing_capabilities *pneg_ctxt, - int len_of_ctxts) + int ctxt_len) { - int sign_algo_cnt = le16_to_cpu(pneg_ctxt->SigningAlgorithmCount); - int i, sign_alos_size = sign_algo_cnt * sizeof(__le16); + int sign_algo_cnt; + int i, sign_alos_size; + + if (sizeof(struct smb2_signing_capabilities) > ctxt_len) { + pr_err("Invalid SMB2_SIGNING_CAPABILITIES context length\n"); + return; + } conn->signing_negotiated = false; + sign_algo_cnt = le16_to_cpu(pneg_ctxt->SigningAlgorithmCount); + sign_alos_size = sign_algo_cnt * sizeof(__le16); if (sizeof(struct smb2_signing_capabilities) + sign_alos_size > - len_of_ctxts) { + ctxt_len) { pr_err("Invalid signing algorithm count(%d)\n", sign_algo_cnt); return; } @@ -969,18 +981,16 @@ static __le32 deassemble_neg_contexts(struct ksmbd_conn *conn, len_of_ctxts = len_of_smb - offset; while (i++ < neg_ctxt_cnt) { - int clen; - - /* check that offset is not beyond end of SMB */ - if (len_of_ctxts == 0) - break; + int clen, ctxt_len; if (len_of_ctxts < sizeof(struct smb2_neg_context)) break; pctx = (struct smb2_neg_context *)((char *)pctx + offset); clen = le16_to_cpu(pctx->DataLength); - if (clen + sizeof(struct smb2_neg_context) > len_of_ctxts) + ctxt_len = clen + sizeof(struct smb2_neg_context); + + if (ctxt_len > len_of_ctxts) break; if (pctx->ContextType == SMB2_PREAUTH_INTEGRITY_CAPABILITIES) { @@ -991,7 +1001,7 @@ static __le32 deassemble_neg_contexts(struct ksmbd_conn *conn, status = decode_preauth_ctxt(conn, (struct smb2_preauth_neg_context *)pctx, - len_of_ctxts); + ctxt_len); if (status != STATUS_SUCCESS) break; } else if (pctx->ContextType == SMB2_ENCRYPTION_CAPABILITIES) { @@ -1002,7 +1012,7 @@ static __le32 deassemble_neg_contexts(struct ksmbd_conn *conn, decode_encrypt_ctxt(conn, (struct smb2_encryption_neg_context *)pctx, - len_of_ctxts); + ctxt_len); } else if (pctx->ContextType == SMB2_COMPRESSION_CAPABILITIES) { ksmbd_debug(SMB, "deassemble SMB2_COMPRESSION_CAPABILITIES context\n"); @@ -1021,9 +1031,10 @@ static __le32 deassemble_neg_contexts(struct ksmbd_conn *conn, } else if (pctx->ContextType == SMB2_SIGNING_CAPABILITIES) { ksmbd_debug(SMB, "deassemble SMB2_SIGNING_CAPABILITIES context\n"); + decode_sign_cap_ctxt(conn, (struct smb2_signing_capabilities *)pctx, - len_of_ctxts); + ctxt_len); } /* offsets must be 8 byte aligned */ @@ -1057,16 +1068,16 @@ int smb2_handle_negotiate(struct ksmbd_work *work) return rc; } - if (req->DialectCount == 0) { - pr_err("malformed packet\n"); + smb2_buf_len = get_rfc1002_len(work->request_buf); + smb2_neg_size = offsetof(struct smb2_negotiate_req, Dialects); + if (smb2_neg_size > smb2_buf_len) { rsp->hdr.Status = STATUS_INVALID_PARAMETER; rc = -EINVAL; goto err_out; } - smb2_buf_len = get_rfc1002_len(work->request_buf); - smb2_neg_size = offsetof(struct smb2_negotiate_req, Dialects); - if (smb2_neg_size > smb2_buf_len) { + if (req->DialectCount == 0) { + pr_err("malformed packet\n"); rsp->hdr.Status = STATUS_INVALID_PARAMETER; rc = -EINVAL; goto err_out; @@ -1356,7 +1367,7 @@ static struct ksmbd_user *session_user(struct ksmbd_conn *conn, struct authenticate_message *authblob; struct ksmbd_user *user; char *name; - unsigned int auth_msg_len, name_off, name_len, secbuf_len; + unsigned int name_off, name_len, secbuf_len; secbuf_len = le16_to_cpu(req->SecurityBufferLength); if (secbuf_len < sizeof(struct authenticate_message)) { @@ -1366,9 +1377,8 @@ static struct ksmbd_user *session_user(struct ksmbd_conn *conn, authblob = user_authblob(conn, req); name_off = le32_to_cpu(authblob->UserName.BufferOffset); name_len = le16_to_cpu(authblob->UserName.Length); - auth_msg_len = le16_to_cpu(req->SecurityBufferOffset) + secbuf_len; - if (auth_msg_len < (u64)name_off + name_len) + if (secbuf_len < (u64)name_off + name_len) return NULL; name = smb_strndup_from_utf16((const char *)authblob + name_off, @@ -2464,7 +2474,7 @@ static int smb2_create_sd_buffer(struct ksmbd_work *work, return -ENOENT; /* Parse SD BUFFER create contexts */ - context = smb2_find_context_vals(req, SMB2_CREATE_SD_BUFFER); + context = smb2_find_context_vals(req, SMB2_CREATE_SD_BUFFER, 4); if (!context) return -ENOENT; else if (IS_ERR(context)) @@ -2666,7 +2676,7 @@ int smb2_open(struct ksmbd_work *work) if (req->CreateContextsOffset) { /* Parse non-durable handle create contexts */ - context = smb2_find_context_vals(req, SMB2_CREATE_EA_BUFFER); + context = smb2_find_context_vals(req, SMB2_CREATE_EA_BUFFER, 4); if (IS_ERR(context)) { rc = PTR_ERR(context); goto err_out1; @@ -2686,7 +2696,7 @@ int smb2_open(struct ksmbd_work *work) } context = smb2_find_context_vals(req, - SMB2_CREATE_QUERY_MAXIMAL_ACCESS_REQUEST); + SMB2_CREATE_QUERY_MAXIMAL_ACCESS_REQUEST, 4); if (IS_ERR(context)) { rc = PTR_ERR(context); goto err_out1; @@ -2697,7 +2707,7 @@ int smb2_open(struct ksmbd_work *work) } context = smb2_find_context_vals(req, - SMB2_CREATE_TIMEWARP_REQUEST); + SMB2_CREATE_TIMEWARP_REQUEST, 4); if (IS_ERR(context)) { rc = PTR_ERR(context); goto err_out1; @@ -2709,7 +2719,7 @@ int smb2_open(struct ksmbd_work *work) if (tcon->posix_extensions) { context = smb2_find_context_vals(req, - SMB2_CREATE_TAG_POSIX); + SMB2_CREATE_TAG_POSIX, 16); if (IS_ERR(context)) { rc = PTR_ERR(context); goto err_out1; @@ -3107,7 +3117,7 @@ int smb2_open(struct ksmbd_work *work) struct create_alloc_size_req *az_req; az_req = (struct create_alloc_size_req *)smb2_find_context_vals(req, - SMB2_CREATE_ALLOCATION_SIZE); + SMB2_CREATE_ALLOCATION_SIZE, 4); if (IS_ERR(az_req)) { rc = PTR_ERR(az_req); goto err_out; @@ -3134,7 +3144,7 @@ int smb2_open(struct ksmbd_work *work) err); } - context = smb2_find_context_vals(req, SMB2_CREATE_QUERY_ON_DISK_ID); + context = smb2_find_context_vals(req, SMB2_CREATE_QUERY_ON_DISK_ID, 4); if (IS_ERR(context)) { rc = PTR_ERR(context); goto err_out; @@ -4359,21 +4369,6 @@ static int get_file_basic_info(struct smb2_query_info_rsp *rsp, return 0; } -static unsigned long long get_allocation_size(struct inode *inode, - struct kstat *stat) -{ - unsigned long long alloc_size = 0; - - if (!S_ISDIR(stat->mode)) { - if ((inode->i_blocks << 9) <= stat->size) - alloc_size = stat->size; - else - alloc_size = inode->i_blocks << 9; - } - - return alloc_size; -} - static void get_file_standard_info(struct smb2_query_info_rsp *rsp, struct ksmbd_file *fp, void *rsp_org) { @@ -4388,7 +4383,7 @@ static void get_file_standard_info(struct smb2_query_info_rsp *rsp, sinfo = (struct smb2_file_standard_info *)rsp->Buffer; delete_pending = ksmbd_inode_pending_delete(fp); - sinfo->AllocationSize = cpu_to_le64(get_allocation_size(inode, &stat)); + sinfo->AllocationSize = cpu_to_le64(inode->i_blocks << 9); sinfo->EndOfFile = S_ISDIR(stat.mode) ? 0 : cpu_to_le64(stat.size); sinfo->NumberOfLinks = cpu_to_le32(get_nlink(&stat) - delete_pending); sinfo->DeletePending = delete_pending; @@ -4453,7 +4448,7 @@ static int get_file_all_info(struct ksmbd_work *work, file_info->Attributes = fp->f_ci->m_fattr; file_info->Pad1 = 0; file_info->AllocationSize = - cpu_to_le64(get_allocation_size(inode, &stat)); + cpu_to_le64(inode->i_blocks << 9); file_info->EndOfFile = S_ISDIR(stat.mode) ? 0 : cpu_to_le64(stat.size); file_info->NumberOfLinks = cpu_to_le32(get_nlink(&stat) - delete_pending); @@ -4642,7 +4637,7 @@ static int get_file_network_open_info(struct smb2_query_info_rsp *rsp, file_info->ChangeTime = cpu_to_le64(time); file_info->Attributes = fp->f_ci->m_fattr; file_info->AllocationSize = - cpu_to_le64(get_allocation_size(inode, &stat)); + cpu_to_le64(inode->i_blocks << 9); file_info->EndOfFile = S_ISDIR(stat.mode) ? 0 : cpu_to_le64(stat.size); file_info->Reserved = cpu_to_le32(0); rsp->OutputBufferLength = @@ -5507,7 +5502,7 @@ static int smb2_create_link(struct ksmbd_work *work, { char *link_name = NULL, *target_name = NULL, *pathname = NULL; struct path path; - bool file_present = true; + bool file_present = false; int rc; if (buf_len < (u64)sizeof(struct smb2_file_link_info) + @@ -5540,8 +5535,8 @@ static int smb2_create_link(struct ksmbd_work *work, if (rc) { if (rc != -ENOENT) goto out; - file_present = false; - } + } else + file_present = true; if (file_info->ReplaceIfExists) { if (file_present) { diff --git a/fs/ksmbd/smb2pdu.h b/fs/smb/server/smb2pdu.h index 2767c08a534a..2767c08a534a 100644 --- a/fs/ksmbd/smb2pdu.h +++ b/fs/smb/server/smb2pdu.h diff --git a/fs/ksmbd/smb_common.c b/fs/smb/server/smb_common.c index af0c2a9b8529..af0c2a9b8529 100644 --- a/fs/ksmbd/smb_common.c +++ b/fs/smb/server/smb_common.c diff --git a/fs/ksmbd/smb_common.h b/fs/smb/server/smb_common.h index 9130d2e3cd78..6b0d5f1fe85c 100644 --- a/fs/ksmbd/smb_common.h +++ b/fs/smb/server/smb_common.h @@ -10,7 +10,7 @@ #include "glob.h" #include "nterr.h" -#include "../smbfs_common/smb2pdu.h" +#include "../common/smb2pdu.h" #include "smb2pdu.h" /* ksmbd's Specific ERRNO */ diff --git a/fs/ksmbd/smbacl.c b/fs/smb/server/smbacl.c index 6d6cfb6957a9..6d6cfb6957a9 100644 --- a/fs/ksmbd/smbacl.c +++ b/fs/smb/server/smbacl.c diff --git a/fs/ksmbd/smbacl.h b/fs/smb/server/smbacl.h index 49a8c292bd2e..49a8c292bd2e 100644 --- a/fs/ksmbd/smbacl.h +++ b/fs/smb/server/smbacl.h diff --git a/fs/ksmbd/smbfsctl.h b/fs/smb/server/smbfsctl.h index b98418aae20c..ecdf8f6e0df4 100644 --- a/fs/ksmbd/smbfsctl.h +++ b/fs/smb/server/smbfsctl.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: LGPL-2.1+ */ /* - * fs/cifs/smbfsctl.h: SMB, CIFS, SMB2 FSCTL definitions + * fs/smb/server/smbfsctl.h: SMB, CIFS, SMB2 FSCTL definitions * * Copyright (c) International Business Machines Corp., 2002,2009 * Author(s): Steve French ([email protected]) diff --git a/fs/ksmbd/smbstatus.h b/fs/smb/server/smbstatus.h index 108a8b6ed24a..8963deb42404 100644 --- a/fs/ksmbd/smbstatus.h +++ b/fs/smb/server/smbstatus.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: LGPL-2.1+ */ /* - * fs/cifs/smb2status.h + * fs/server/smb2status.h * * SMB2 Status code (network error) definitions * Definitions are from MS-ERREF diff --git a/fs/ksmbd/transport_ipc.c b/fs/smb/server/transport_ipc.c index 40c721f9227e..40c721f9227e 100644 --- a/fs/ksmbd/transport_ipc.c +++ b/fs/smb/server/transport_ipc.c diff --git a/fs/ksmbd/transport_ipc.h b/fs/smb/server/transport_ipc.h index 5e5b90a0c187..5e5b90a0c187 100644 --- a/fs/ksmbd/transport_ipc.h +++ b/fs/smb/server/transport_ipc.h diff --git a/fs/ksmbd/transport_rdma.c b/fs/smb/server/transport_rdma.c index c06efc020bd9..c06efc020bd9 100644 --- a/fs/ksmbd/transport_rdma.c +++ b/fs/smb/server/transport_rdma.c diff --git a/fs/ksmbd/transport_rdma.h b/fs/smb/server/transport_rdma.h index 77aee4e5c9dc..77aee4e5c9dc 100644 --- a/fs/ksmbd/transport_rdma.h +++ b/fs/smb/server/transport_rdma.h diff --git a/fs/ksmbd/transport_tcp.c b/fs/smb/server/transport_tcp.c index eff7a1d793f0..eff7a1d793f0 100644 --- a/fs/ksmbd/transport_tcp.c +++ b/fs/smb/server/transport_tcp.c diff --git a/fs/ksmbd/transport_tcp.h b/fs/smb/server/transport_tcp.h index e338bebe322f..e338bebe322f 100644 --- a/fs/ksmbd/transport_tcp.h +++ b/fs/smb/server/transport_tcp.h diff --git a/fs/ksmbd/unicode.c b/fs/smb/server/unicode.c index 9ae676906ed3..9ae676906ed3 100644 --- a/fs/ksmbd/unicode.c +++ b/fs/smb/server/unicode.c diff --git a/fs/ksmbd/unicode.h b/fs/smb/server/unicode.h index 076f6034a789..076f6034a789 100644 --- a/fs/ksmbd/unicode.h +++ b/fs/smb/server/unicode.h diff --git a/fs/ksmbd/uniupr.h b/fs/smb/server/uniupr.h index 26583b776897..26583b776897 100644 --- a/fs/ksmbd/uniupr.h +++ b/fs/smb/server/uniupr.h diff --git a/fs/ksmbd/vfs.c b/fs/smb/server/vfs.c index 778c152708e4..6f302919e9f7 100644 --- a/fs/ksmbd/vfs.c +++ b/fs/smb/server/vfs.c @@ -86,12 +86,14 @@ static int ksmbd_vfs_path_lookup_locked(struct ksmbd_share_config *share_conf, err = vfs_path_parent_lookup(filename, flags, &parent_path, &last, &type, root_share_path); - putname(filename); - if (err) + if (err) { + putname(filename); return err; + } if (unlikely(type != LAST_NORM)) { path_put(&parent_path); + putname(filename); return -ENOENT; } @@ -108,12 +110,14 @@ static int ksmbd_vfs_path_lookup_locked(struct ksmbd_share_config *share_conf, path->dentry = d; path->mnt = share_conf->vfs_path.mnt; path_put(&parent_path); + putname(filename); return 0; err_out: inode_unlock(parent_path.dentry->d_inode); path_put(&parent_path); + putname(filename); return -ENOENT; } @@ -743,6 +747,7 @@ retry: rd.new_dir = new_path.dentry->d_inode, rd.new_dentry = new_dentry, rd.flags = flags, + rd.delegated_inode = NULL, err = vfs_rename(&rd); if (err) ksmbd_debug(VFS, "vfs_rename failed err %d\n", err); diff --git a/fs/ksmbd/vfs.h b/fs/smb/server/vfs.h index a4ae89f3230d..a4ae89f3230d 100644 --- a/fs/ksmbd/vfs.h +++ b/fs/smb/server/vfs.h diff --git a/fs/ksmbd/vfs_cache.c b/fs/smb/server/vfs_cache.c index 2d0138e72d78..2d0138e72d78 100644 --- a/fs/ksmbd/vfs_cache.c +++ b/fs/smb/server/vfs_cache.c diff --git a/fs/ksmbd/vfs_cache.h b/fs/smb/server/vfs_cache.h index fcb13413fa8d..fcb13413fa8d 100644 --- a/fs/ksmbd/vfs_cache.h +++ b/fs/smb/server/vfs_cache.h diff --git a/fs/ksmbd/xattr.h b/fs/smb/server/xattr.h index 16499ca5c82d..16499ca5c82d 100644 --- a/fs/ksmbd/xattr.h +++ b/fs/smb/server/xattr.h diff --git a/fs/statfs.c b/fs/statfs.c index 0ba34c135593..96d1c3edf289 100644 --- a/fs/statfs.c +++ b/fs/statfs.c @@ -130,6 +130,7 @@ static int do_statfs_native(struct kstatfs *st, struct statfs __user *p) if (sizeof(buf) == sizeof(*st)) memcpy(&buf, st, sizeof(*st)); else { + memset(&buf, 0, sizeof(buf)); if (sizeof buf.f_blocks == 4) { if ((st->f_blocks | st->f_bfree | st->f_bavail | st->f_bsize | st->f_frsize) & @@ -158,7 +159,6 @@ static int do_statfs_native(struct kstatfs *st, struct statfs __user *p) buf.f_namelen = st->f_namelen; buf.f_frsize = st->f_frsize; buf.f_flags = st->f_flags; - memset(buf.f_spare, 0, sizeof(buf.f_spare)); } if (copy_to_user(p, &buf, sizeof(buf))) return -EFAULT; @@ -171,6 +171,7 @@ static int do_statfs64(struct kstatfs *st, struct statfs64 __user *p) if (sizeof(buf) == sizeof(*st)) memcpy(&buf, st, sizeof(*st)); else { + memset(&buf, 0, sizeof(buf)); buf.f_type = st->f_type; buf.f_bsize = st->f_bsize; buf.f_blocks = st->f_blocks; @@ -182,7 +183,6 @@ static int do_statfs64(struct kstatfs *st, struct statfs64 __user *p) buf.f_namelen = st->f_namelen; buf.f_frsize = st->f_frsize; buf.f_flags = st->f_flags; - memset(buf.f_spare, 0, sizeof(buf.f_spare)); } if (copy_to_user(p, &buf, sizeof(buf))) return -EFAULT; diff --git a/fs/xattr.c b/fs/xattr.c index fcf67d80d7f9..e7bbb7f57557 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -985,9 +985,16 @@ int xattr_list_one(char **buffer, ssize_t *remaining_size, const char *name) return 0; } -/* +/** + * generic_listxattr - run through a dentry's xattr list() operations + * @dentry: dentry to list the xattrs + * @buffer: result buffer + * @buffer_size: size of @buffer + * * Combine the results of the list() operation from every xattr_handler in the - * list. + * xattr_handler stack. + * + * Note that this will not include the entries for POSIX ACLs. */ ssize_t generic_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size) @@ -996,10 +1003,6 @@ generic_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size) ssize_t remaining_size = buffer_size; int err = 0; - err = posix_acl_listxattr(d_inode(dentry), &buffer, &remaining_size); - if (err) - return err; - for_each_xattr_handler(handlers, handler) { if (!handler->name || (handler->list && !handler->list(dentry))) continue; diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index d1f57e4868ed..cebdf1ca415d 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -891,9 +891,16 @@ /* * Discard .note.GNU-stack, which is emitted as PROGBITS by the compiler. * Otherwise, the type of .notes section would become PROGBITS instead of NOTES. + * + * Also, discard .note.gnu.property, otherwise it forces the notes section to + * be 8-byte aligned which causes alignment mismatches with the kernel's custom + * 4-byte aligned notes. */ #define NOTES \ - /DISCARD/ : { *(.note.GNU-stack) } \ + /DISCARD/ : { \ + *(.note.GNU-stack) \ + *(.note.gnu.property) \ + } \ .notes : AT(ADDR(.notes) - LOAD_OFFSET) { \ BOUNDED_SECTION_BY(.note.*, _notes) \ } NOTES_HEADERS \ diff --git a/include/drm/drm_managed.h b/include/drm/drm_managed.h index 359883942612..ad08f834af40 100644 --- a/include/drm/drm_managed.h +++ b/include/drm/drm_managed.h @@ -105,6 +105,22 @@ char *drmm_kstrdup(struct drm_device *dev, const char *s, gfp_t gfp); void drmm_kfree(struct drm_device *dev, void *data); -int drmm_mutex_init(struct drm_device *dev, struct mutex *lock); +void __drmm_mutex_release(struct drm_device *dev, void *res); + +/** + * drmm_mutex_init - &drm_device-managed mutex_init() + * @dev: DRM device + * @lock: lock to be initialized + * + * Returns: + * 0 on success, or a negative errno code otherwise. + * + * This is a &drm_device-managed version of mutex_init(). The initialized + * lock is automatically destroyed on the final drm_dev_put(). + */ +#define drmm_mutex_init(dev, lock) ({ \ + mutex_init(lock); \ + drmm_add_action_or_reset(dev, __drmm_mutex_release, lock); \ +}) \ #endif diff --git a/include/linux/arm_ffa.h b/include/linux/arm_ffa.h index c87aeecaa9b2..583fe3b49a49 100644 --- a/include/linux/arm_ffa.h +++ b/include/linux/arm_ffa.h @@ -96,6 +96,7 @@ /* FFA Bus/Device/Driver related */ struct ffa_device { + u32 id; int vm_id; bool mode_32bit; uuid_t uuid; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index b441e633f4dd..c0ffe203a602 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1376,8 +1376,6 @@ enum blk_unique_id { BLK_UID_NAA = 3, }; -#define NFL4_UFLG_MASK 0x0000003F - struct block_device_operations { void (*submit_bio)(struct bio *bio); int (*poll_bio)(struct bio *bio, struct io_comp_batch *iob, diff --git a/include/linux/device/class.h b/include/linux/device/class.h index 9deeaeb457bb..abf3d3bfb6fe 100644 --- a/include/linux/device/class.h +++ b/include/linux/device/class.h @@ -74,6 +74,7 @@ struct class { struct class_dev_iter { struct klist_iter ki; const struct device_type *type; + struct subsys_private *sp; }; int __must_check class_register(const struct class *class); diff --git a/include/linux/firewire.h b/include/linux/firewire.h index 1716c01c4e54..efb6e2cf2034 100644 --- a/include/linux/firewire.h +++ b/include/linux/firewire.h @@ -391,7 +391,7 @@ struct fw_iso_packet { u32 tag:2; /* tx: Tag in packet header */ u32 sy:4; /* tx: Sy in packet header */ u32 header_length:8; /* Length of immediate header */ - u32 header[0]; /* tx: Top of 1394 isoch. data_block */ + u32 header[]; /* tx: Top of 1394 isoch. data_block */ }; #define FW_ISO_CONTEXT_TRANSMIT 0 diff --git a/include/linux/fs.h b/include/linux/fs.h index 21a981680856..133f0640fb24 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1076,29 +1076,29 @@ extern int send_sigurg(struct fown_struct *fown); * sb->s_flags. Note that these mirror the equivalent MS_* flags where * represented in both. */ -#define SB_RDONLY 1 /* Mount read-only */ -#define SB_NOSUID 2 /* Ignore suid and sgid bits */ -#define SB_NODEV 4 /* Disallow access to device special files */ -#define SB_NOEXEC 8 /* Disallow program execution */ -#define SB_SYNCHRONOUS 16 /* Writes are synced at once */ -#define SB_MANDLOCK 64 /* Allow mandatory locks on an FS */ -#define SB_DIRSYNC 128 /* Directory modifications are synchronous */ -#define SB_NOATIME 1024 /* Do not update access times. */ -#define SB_NODIRATIME 2048 /* Do not update directory access times */ -#define SB_SILENT 32768 -#define SB_POSIXACL (1<<16) /* VFS does not apply the umask */ -#define SB_INLINECRYPT (1<<17) /* Use blk-crypto for encrypted files */ -#define SB_KERNMOUNT (1<<22) /* this is a kern_mount call */ -#define SB_I_VERSION (1<<23) /* Update inode I_version field */ -#define SB_LAZYTIME (1<<25) /* Update the on-disk [acm]times lazily */ +#define SB_RDONLY BIT(0) /* Mount read-only */ +#define SB_NOSUID BIT(1) /* Ignore suid and sgid bits */ +#define SB_NODEV BIT(2) /* Disallow access to device special files */ +#define SB_NOEXEC BIT(3) /* Disallow program execution */ +#define SB_SYNCHRONOUS BIT(4) /* Writes are synced at once */ +#define SB_MANDLOCK BIT(6) /* Allow mandatory locks on an FS */ +#define SB_DIRSYNC BIT(7) /* Directory modifications are synchronous */ +#define SB_NOATIME BIT(10) /* Do not update access times. */ +#define SB_NODIRATIME BIT(11) /* Do not update directory access times */ +#define SB_SILENT BIT(15) +#define SB_POSIXACL BIT(16) /* VFS does not apply the umask */ +#define SB_INLINECRYPT BIT(17) /* Use blk-crypto for encrypted files */ +#define SB_KERNMOUNT BIT(22) /* this is a kern_mount call */ +#define SB_I_VERSION BIT(23) /* Update inode I_version field */ +#define SB_LAZYTIME BIT(25) /* Update the on-disk [acm]times lazily */ /* These sb flags are internal to the kernel */ -#define SB_SUBMOUNT (1<<26) -#define SB_FORCE (1<<27) -#define SB_NOSEC (1<<28) -#define SB_BORN (1<<29) -#define SB_ACTIVE (1<<30) -#define SB_NOUSER (1<<31) +#define SB_SUBMOUNT BIT(26) +#define SB_FORCE BIT(27) +#define SB_NOSEC BIT(28) +#define SB_BORN BIT(29) +#define SB_ACTIVE BIT(30) +#define SB_NOUSER BIT(31) /* These flags relate to encoding and casefolding */ #define SB_ENC_STRICT_MODE_FL (1 << 0) diff --git a/include/linux/if_team.h b/include/linux/if_team.h index fc985e5c739d..8de6b6e67829 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -208,6 +208,7 @@ struct team { bool queue_override_enabled; struct list_head *qom_lists; /* array of queue override mapping lists */ bool port_mtu_change_allowed; + bool notifier_ctx; struct { unsigned int count; unsigned int interval; /* in ms */ diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index b32256e9e944..74bd269a80a2 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -344,6 +344,16 @@ extern void lock_unpin_lock(struct lockdep_map *lock, struct pin_cookie); #define lockdep_repin_lock(l,c) lock_repin_lock(&(l)->dep_map, (c)) #define lockdep_unpin_lock(l,c) lock_unpin_lock(&(l)->dep_map, (c)) +/* + * Must use lock_map_aquire_try() with override maps to avoid + * lockdep thinking they participate in the block chain. + */ +#define DEFINE_WAIT_OVERRIDE_MAP(_name, _wait_type) \ + struct lockdep_map _name = { \ + .name = #_name "-wait-type-override", \ + .wait_type_inner = _wait_type, \ + .lock_type = LD_LOCK_WAIT_OVERRIDE, } + #else /* !CONFIG_LOCKDEP */ static inline void lockdep_init_task(struct task_struct *task) @@ -432,6 +442,9 @@ extern int lockdep_is_held(const void *); #define lockdep_repin_lock(l, c) do { (void)(l); (void)(c); } while (0) #define lockdep_unpin_lock(l, c) do { (void)(l); (void)(c); } while (0) +#define DEFINE_WAIT_OVERRIDE_MAP(_name, _wait_type) \ + struct lockdep_map __maybe_unused _name = {} + #endif /* !LOCKDEP */ enum xhlock_context_t { @@ -556,6 +569,7 @@ do { \ #define rwsem_release(l, i) lock_release(l, i) #define lock_map_acquire(l) lock_acquire_exclusive(l, 0, 0, NULL, _THIS_IP_) +#define lock_map_acquire_try(l) lock_acquire_exclusive(l, 0, 1, NULL, _THIS_IP_) #define lock_map_acquire_read(l) lock_acquire_shared_recursive(l, 0, 0, NULL, _THIS_IP_) #define lock_map_acquire_tryread(l) lock_acquire_shared_recursive(l, 0, 1, NULL, _THIS_IP_) #define lock_map_release(l) lock_release(l, _THIS_IP_) diff --git a/include/linux/lockdep_types.h b/include/linux/lockdep_types.h index d22430840b53..59f4fb1626ea 100644 --- a/include/linux/lockdep_types.h +++ b/include/linux/lockdep_types.h @@ -33,6 +33,7 @@ enum lockdep_wait_type { enum lockdep_lock_type { LD_LOCK_NORMAL = 0, /* normal, catch all */ LD_LOCK_PERCPU, /* percpu */ + LD_LOCK_WAIT_OVERRIDE, /* annotation */ LD_LOCK_MAX, }; diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index a4c4f737f9c1..94d2be5848ae 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1093,6 +1093,7 @@ void mlx5_cmdif_debugfs_cleanup(struct mlx5_core_dev *dev); int mlx5_core_create_psv(struct mlx5_core_dev *dev, u32 pdn, int npsvs, u32 *sig_index); int mlx5_core_destroy_psv(struct mlx5_core_dev *dev, int psv_num); +__be32 mlx5_core_get_terminate_scatter_list_mkey(struct mlx5_core_dev *dev); void mlx5_core_put_rsc(struct mlx5_core_rsc_common *common); int mlx5_query_odp_caps(struct mlx5_core_dev *dev, struct mlx5_odp_caps *odp_caps); diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index dc5e2cb302a5..b89778d0d326 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1705,7 +1705,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 rc[0x1]; u8 uar_4k[0x1]; - u8 reserved_at_241[0x9]; + u8 reserved_at_241[0x7]; + u8 fl_rc_qp_when_roce_disabled[0x1]; + u8 regexp_params[0x1]; u8 uar_sz[0x6]; u8 port_selection_cap[0x1]; u8 reserved_at_248[0x1]; diff --git a/include/linux/msi.h b/include/linux/msi.h index cdb14a1ef268..a50ea79522f8 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -383,6 +383,13 @@ int arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc); void arch_teardown_msi_irq(unsigned int irq); int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type); void arch_teardown_msi_irqs(struct pci_dev *dev); +#endif /* CONFIG_PCI_MSI_ARCH_FALLBACKS */ + +/* + * Xen uses non-default msi_domain_ops and hence needs a way to populate sysfs + * entries of MSI IRQs. + */ +#if defined(CONFIG_PCI_XEN) || defined(CONFIG_PCI_MSI_ARCH_FALLBACKS) #ifdef CONFIG_SYSFS int msi_device_populate_sysfs(struct device *dev); void msi_device_destroy_sysfs(struct device *dev); @@ -390,7 +397,7 @@ void msi_device_destroy_sysfs(struct device *dev); static inline int msi_device_populate_sysfs(struct device *dev) { return 0; } static inline void msi_device_destroy_sysfs(struct device *dev) { } #endif /* !CONFIG_SYSFS */ -#endif /* CONFIG_PCI_MSI_ARCH_FALLBACKS */ +#endif /* CONFIG_PCI_XEN || CONFIG_PCI_MSI_ARCH_FALLBACKS */ /* * The restore hook is still available even for fully irq domain based diff --git a/include/linux/power/bq27xxx_battery.h b/include/linux/power/bq27xxx_battery.h index a1aa68141d0b..7c8d65414a70 100644 --- a/include/linux/power/bq27xxx_battery.h +++ b/include/linux/power/bq27xxx_battery.h @@ -2,6 +2,8 @@ #ifndef __LINUX_BQ27X00_BATTERY_H__ #define __LINUX_BQ27X00_BATTERY_H__ +#include <linux/power_supply.h> + enum bq27xxx_chip { BQ27000 = 1, /* bq27000, bq27200 */ BQ27010, /* bq27010, bq27210 */ @@ -68,7 +70,9 @@ struct bq27xxx_device_info { struct bq27xxx_access_methods bus; struct bq27xxx_reg_cache cache; int charge_design_full; + bool removed; unsigned long last_update; + union power_supply_propval last_status; struct delayed_work work; struct power_supply *bat; struct list_head list; diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 537cbf9a2ade..e0f5ac90a228 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -29,7 +29,6 @@ struct kernel_clone_args { u32 io_thread:1; u32 user_worker:1; u32 no_files:1; - u32 ignore_signals:1; unsigned long stack; unsigned long stack_size; unsigned long tls; diff --git a/include/linux/sched/vhost_task.h b/include/linux/sched/vhost_task.h index 6123c10b99cf..837a23624a66 100644 --- a/include/linux/sched/vhost_task.h +++ b/include/linux/sched/vhost_task.h @@ -2,22 +2,13 @@ #ifndef _LINUX_VHOST_TASK_H #define _LINUX_VHOST_TASK_H -#include <linux/completion.h> -struct task_struct; +struct vhost_task; -struct vhost_task { - int (*fn)(void *data); - void *data; - struct completion exited; - unsigned long flags; - struct task_struct *task; -}; - -struct vhost_task *vhost_task_create(int (*fn)(void *), void *arg, +struct vhost_task *vhost_task_create(bool (*fn)(void *), void *arg, const char *name); void vhost_task_start(struct vhost_task *vtsk); void vhost_task_stop(struct vhost_task *vtsk); -bool vhost_task_should_stop(struct vhost_task *vtsk); +void vhost_task_wake(struct vhost_task *vtsk); #endif diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h index 7bde8e1c228a..224293b2dd06 100644 --- a/include/linux/shrinker.h +++ b/include/linux/shrinker.h @@ -107,7 +107,10 @@ extern void synchronize_shrinkers(void); #ifdef CONFIG_SHRINKER_DEBUG extern int shrinker_debugfs_add(struct shrinker *shrinker); -extern struct dentry *shrinker_debugfs_remove(struct shrinker *shrinker); +extern struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker, + int *debugfs_id); +extern void shrinker_debugfs_remove(struct dentry *debugfs_entry, + int debugfs_id); extern int __printf(2, 3) shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...); #else /* CONFIG_SHRINKER_DEBUG */ @@ -115,10 +118,16 @@ static inline int shrinker_debugfs_add(struct shrinker *shrinker) { return 0; } -static inline struct dentry *shrinker_debugfs_remove(struct shrinker *shrinker) +static inline struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker, + int *debugfs_id) { + *debugfs_id = -1; return NULL; } +static inline void shrinker_debugfs_remove(struct dentry *debugfs_entry, + int debugfs_id) +{ +} static inline __printf(2, 3) int shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...) { diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 84f787416a54..054d7911bfc9 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -71,7 +71,6 @@ struct sk_psock_link { }; struct sk_psock_work_state { - struct sk_buff *skb; u32 len; u32 off; }; @@ -105,7 +104,7 @@ struct sk_psock { struct proto *sk_proto; struct mutex work_mutex; struct sk_psock_work_state work_state; - struct work_struct work; + struct delayed_work work; struct rcu_work rwork; }; diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 0e373222a6df..7c4a0b72334e 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -806,6 +806,7 @@ enum { FILTER_TRACE_FN, FILTER_COMM, FILTER_CPU, + FILTER_STACKTRACE, }; extern int trace_event_raw_init(struct trace_event_call *call); diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h index a2448e98854f..07531c4f4350 100644 --- a/include/linux/usb/composite.h +++ b/include/linux/usb/composite.h @@ -443,7 +443,7 @@ static inline struct usb_composite_driver *to_cdriver( * @bcd_webusb_version: 0x0100 by default, WebUSB specification version * @b_webusb_vendor_code: 0x0 by default, vendor code for WebUSB * @landing_page: empty by default, landing page to announce in WebUSB - * @use_webusb:: false by default, interested gadgets set it + * @use_webusb: false by default, interested gadgets set it * @os_desc_config: the configuration to be used with OS descriptors * @setup_pending: true when setup request is queued but not completed * @os_desc_pending: true when os_desc request is queued but not completed diff --git a/include/linux/user_events.h b/include/linux/user_events.h index 2847f5a18a86..8afa8c3a0973 100644 --- a/include/linux/user_events.h +++ b/include/linux/user_events.h @@ -17,9 +17,10 @@ #ifdef CONFIG_USER_EVENTS struct user_event_mm { - struct list_head link; + struct list_head mms_link; struct list_head enablers; struct mm_struct *mm; + /* Used for one-shot lists, protected by event_mutex */ struct user_event_mm *next; refcount_t refcnt; refcount_t tasks; diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index a6c8aee2f256..8baf34639939 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1327,7 +1327,7 @@ int hci_le_create_cis(struct hci_conn *conn); struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst, u8 role); -int hci_conn_del(struct hci_conn *conn); +void hci_conn_del(struct hci_conn *conn); void hci_conn_hash_flush(struct hci_dev *hdev); void hci_conn_check_pending(struct hci_dev *hdev); diff --git a/include/net/bonding.h b/include/net/bonding.h index 0efef2a952b7..59955ac33157 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -221,6 +221,7 @@ struct bonding { struct bond_up_slave __rcu *usable_slaves; struct bond_up_slave __rcu *all_slaves; bool force_primary; + bool notifier_ctx; s32 slave_cnt; /* never change this value outside the attach/detach wrappers */ int (*recv_probe)(const struct sk_buff *, struct bonding *, struct slave *); diff --git a/include/net/handshake.h b/include/net/handshake.h index 3352b1ab43b3..2e26e436e85f 100644 --- a/include/net/handshake.h +++ b/include/net/handshake.h @@ -24,6 +24,7 @@ struct tls_handshake_args { struct socket *ta_sock; tls_done_func_t ta_done; void *ta_data; + const char *ta_peername; unsigned int ta_timeout_ms; key_serial_t ta_keyring; key_serial_t ta_my_cert; diff --git a/include/net/ip.h b/include/net/ip.h index c3fffaa92d6e..acec504c469a 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -76,6 +76,7 @@ struct ipcm_cookie { __be32 addr; int oif; struct ip_options_rcu *opt; + __u8 protocol; __u8 ttl; __s16 tos; char priority; @@ -96,6 +97,7 @@ static inline void ipcm_init_sk(struct ipcm_cookie *ipcm, ipcm->sockc.tsflags = inet->sk.sk_tsflags; ipcm->oif = READ_ONCE(inet->sk.sk_bound_dev_if); ipcm->addr = inet->inet_saddr; + ipcm->protocol = inet->inet_num; } #define IPCB(skb) ((struct inet_skb_parm*)((skb)->cb)) diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h index cd386aa7c7cc..9eef19972845 100644 --- a/include/net/mana/mana.h +++ b/include/net/mana/mana.h @@ -347,10 +347,8 @@ struct mana_tx_qp { struct mana_ethtool_stats { u64 stop_queue; u64 wake_queue; - u64 tx_cqes; u64 tx_cqe_err; u64 tx_cqe_unknown_type; - u64 rx_cqes; u64 rx_coalesced_err; u64 rx_cqe_unknown_type; }; diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 3fa5774bddac..f6a8ecc6b1fa 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -180,7 +180,7 @@ struct pneigh_entry { netdevice_tracker dev_tracker; u32 flags; u8 protocol; - u8 key[]; + u32 key[]; }; /* diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index 3cceb3e9320b..5f2cfd84570a 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -53,7 +53,7 @@ struct netns_sysctl_ipv6 { int seg6_flowlabel; u32 ioam6_id; u64 ioam6_id_wide; - bool skip_notify_on_dev_down; + u8 skip_notify_on_dev_down; u8 fib_notify_on_flag_change; u8 icmpv6_error_anycast_as_unicast; }; diff --git a/include/net/page_pool.h b/include/net/page_pool.h index c8ec2f34722b..126f9e294389 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -399,22 +399,4 @@ static inline void page_pool_nid_changed(struct page_pool *pool, int new_nid) page_pool_update_nid(pool, new_nid); } -static inline void page_pool_ring_lock(struct page_pool *pool) - __acquires(&pool->ring.producer_lock) -{ - if (in_softirq()) - spin_lock(&pool->ring.producer_lock); - else - spin_lock_bh(&pool->ring.producer_lock); -} - -static inline void page_pool_ring_unlock(struct page_pool *pool) - __releases(&pool->ring.producer_lock) -{ - if (in_softirq()) - spin_unlock(&pool->ring.producer_lock); - else - spin_unlock_bh(&pool->ring.producer_lock); -} - #endif /* _NET_PAGE_POOL_H */ diff --git a/include/net/ping.h b/include/net/ping.h index 9233ad3de0ad..bc7779262e60 100644 --- a/include/net/ping.h +++ b/include/net/ping.h @@ -16,11 +16,7 @@ #define PING_HTABLE_SIZE 64 #define PING_HTABLE_MASK (PING_HTABLE_SIZE-1) -/* - * gid_t is either uint or ushort. We want to pass it to - * proc_dointvec_minmax(), so it must not be larger than MAX_INT - */ -#define GID_T_MAX (((gid_t)~0U) >> 1) +#define GID_T_MAX (((gid_t)~0U) - 1) /* Compatibility glue so we can support IPv6 when it's compiled as a module */ struct pingv6_ops { diff --git a/include/net/rpl.h b/include/net/rpl.h index 308ef0a05cae..30fe780d1e7c 100644 --- a/include/net/rpl.h +++ b/include/net/rpl.h @@ -23,9 +23,6 @@ static inline int rpl_init(void) static inline void rpl_exit(void) {} #endif -/* Worst decompression memory usage ipv6 address (16) + pad 7 */ -#define IPV6_RPL_SRH_WORST_SWAP_SIZE (sizeof(struct in6_addr) + 7) - size_t ipv6_rpl_srh_size(unsigned char n, unsigned char cmpri, unsigned char cmpre); diff --git a/include/net/sock.h b/include/net/sock.h index 656ea89f60ff..b418425d7230 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -336,6 +336,7 @@ struct sk_filter; * @sk_cgrp_data: cgroup data for this cgroup * @sk_memcg: this socket's memory cgroup association * @sk_write_pending: a write to stream socket waits to start + * @sk_wait_pending: number of threads blocked on this socket * @sk_state_change: callback to indicate change in the state of the sock * @sk_data_ready: callback to indicate there is data to be processed * @sk_write_space: callback to indicate there is bf sending space available @@ -428,6 +429,7 @@ struct sock { unsigned int sk_napi_id; #endif int sk_rcvbuf; + int sk_wait_pending; struct sk_filter __rcu *sk_filter; union { @@ -1174,6 +1176,7 @@ static inline void sock_rps_reset_rxhash(struct sock *sk) #define sk_wait_event(__sk, __timeo, __condition, __wait) \ ({ int __rc; \ + __sk->sk_wait_pending++; \ release_sock(__sk); \ __rc = __condition; \ if (!__rc) { \ @@ -1183,6 +1186,7 @@ static inline void sock_rps_reset_rxhash(struct sock *sk) } \ sched_annotate_sleep(); \ lock_sock(__sk); \ + __sk->sk_wait_pending--; \ __rc = __condition; \ __rc; \ }) diff --git a/include/net/tcp.h b/include/net/tcp.h index 04a31643cda3..5066e4586cf0 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -632,6 +632,7 @@ void tcp_reset(struct sock *sk, struct sk_buff *skb); void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp, struct sk_buff *skb); void tcp_fin(struct sock *sk); void tcp_check_space(struct sock *sk); +void tcp_sack_compress_send_ack(struct sock *sk); /* tcp_timer.c */ void tcp_init_xmit_timers(struct sock *); @@ -1470,6 +1471,8 @@ static inline void tcp_adjust_rcv_ssthresh(struct sock *sk) } void tcp_cleanup_rbuf(struct sock *sk, int copied); +void __tcp_cleanup_rbuf(struct sock *sk, int copied); + /* We provision sk_rcvbuf around 200% of sk_rcvlowat. * If 87.5 % (7/8) of the space has been consumed, we want to override @@ -2326,6 +2329,14 @@ int tcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore); void tcp_bpf_clone(const struct sock *sk, struct sock *newsk); #endif /* CONFIG_BPF_SYSCALL */ +#ifdef CONFIG_INET +void tcp_eat_skb(struct sock *sk, struct sk_buff *skb); +#else +static inline void tcp_eat_skb(struct sock *sk, struct sk_buff *skb) +{ +} +#endif + int tcp_bpf_sendmsg_redir(struct sock *sk, bool ingress, struct sk_msg *msg, u32 bytes, int flags); #endif /* CONFIG_NET_SOCK_MSG */ diff --git a/include/sound/hda-mlink.h b/include/sound/hda-mlink.h index dbc47af08135..4f44f0bd5388 100644 --- a/include/sound/hda-mlink.h +++ b/include/sound/hda-mlink.h @@ -44,6 +44,9 @@ int hdac_bus_eml_sdw_power_down_unlocked(struct hdac_bus *bus, int sublink); int hdac_bus_eml_sdw_set_lsdiid(struct hdac_bus *bus, int sublink, int dev_num); +int hdac_bus_eml_sdw_map_stream_ch(struct hdac_bus *bus, int sublink, int y, + int channel_mask, int stream_id, int dir); + void hda_bus_ml_put_all(struct hdac_bus *bus); void hda_bus_ml_reset_losidv(struct hdac_bus *bus); int hda_bus_ml_resume(struct hdac_bus *bus); @@ -51,6 +54,7 @@ int hda_bus_ml_suspend(struct hdac_bus *bus); struct hdac_ext_link *hdac_bus_eml_ssp_get_hlink(struct hdac_bus *bus); struct hdac_ext_link *hdac_bus_eml_dmic_get_hlink(struct hdac_bus *bus); +struct hdac_ext_link *hdac_bus_eml_sdw_get_hlink(struct hdac_bus *bus); struct mutex *hdac_bus_eml_get_mutex(struct hdac_bus *bus, bool alt, int elid); @@ -144,6 +148,13 @@ hdac_bus_eml_sdw_power_down_unlocked(struct hdac_bus *bus, int sublink) { return static inline int hdac_bus_eml_sdw_set_lsdiid(struct hdac_bus *bus, int sublink, int dev_num) { return 0; } +static inline int +hdac_bus_eml_sdw_map_stream_ch(struct hdac_bus *bus, int sublink, int y, + int channel_mask, int stream_id, int dir) +{ + return 0; +} + static inline void hda_bus_ml_put_all(struct hdac_bus *bus) { } static inline void hda_bus_ml_reset_losidv(struct hdac_bus *bus) { } static inline int hda_bus_ml_resume(struct hdac_bus *bus) { return 0; } @@ -155,6 +166,9 @@ hdac_bus_eml_ssp_get_hlink(struct hdac_bus *bus) { return NULL; } static inline struct hdac_ext_link * hdac_bus_eml_dmic_get_hlink(struct hdac_bus *bus) { return NULL; } +static inline struct hdac_ext_link * +hdac_bus_eml_sdw_get_hlink(struct hdac_bus *bus) { return NULL; } + static inline struct mutex * hdac_bus_eml_get_mutex(struct hdac_bus *bus, bool alt, int elid) { return NULL; } diff --git a/include/sound/soc-acpi.h b/include/sound/soc-acpi.h index b38fd25c5729..528279056b3a 100644 --- a/include/sound/soc-acpi.h +++ b/include/sound/soc-acpi.h @@ -170,6 +170,7 @@ struct snd_soc_acpi_link_adr { /* Descriptor for SST ASoC machine driver */ struct snd_soc_acpi_mach { u8 id[ACPI_ID_LEN]; + const char *uid; const struct snd_soc_acpi_codecs *comp_ids; const u32 link_mask; const struct snd_soc_acpi_link_adr *links; diff --git a/include/sound/soc-dpcm.h b/include/sound/soc-dpcm.h index 4d6ac7699833..ebd24753dd00 100644 --- a/include/sound/soc-dpcm.h +++ b/include/sound/soc-dpcm.h @@ -122,6 +122,10 @@ int snd_soc_dpcm_can_be_free_stop(struct snd_soc_pcm_runtime *fe, int snd_soc_dpcm_can_be_params(struct snd_soc_pcm_runtime *fe, struct snd_soc_pcm_runtime *be, int stream); +/* can this BE perform prepare */ +int snd_soc_dpcm_can_be_prepared(struct snd_soc_pcm_runtime *fe, + struct snd_soc_pcm_runtime *be, int stream); + /* is the current PCM operation for this FE ? */ int snd_soc_dpcm_fe_can_update(struct snd_soc_pcm_runtime *fe, int stream); diff --git a/include/uapi/linux/handshake.h b/include/uapi/linux/handshake.h index 1de4d0b95325..3d7ea58778c9 100644 --- a/include/uapi/linux/handshake.h +++ b/include/uapi/linux/handshake.h @@ -44,6 +44,7 @@ enum { HANDSHAKE_A_ACCEPT_AUTH_MODE, HANDSHAKE_A_ACCEPT_PEER_IDENTITY, HANDSHAKE_A_ACCEPT_CERTIFICATE, + HANDSHAKE_A_ACCEPT_PEERNAME, __HANDSHAKE_A_ACCEPT_MAX, HANDSHAKE_A_ACCEPT_MAX = (__HANDSHAKE_A_ACCEPT_MAX - 1) diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h index 4b7f2df66b99..e682ab628dfa 100644 --- a/include/uapi/linux/in.h +++ b/include/uapi/linux/in.h @@ -163,6 +163,7 @@ struct in_addr { #define IP_MULTICAST_ALL 49 #define IP_UNICAST_IF 50 #define IP_LOCAL_PORT_RANGE 51 +#define IP_PROTOCOL 52 #define MCAST_EXCLUDE 0 #define MCAST_INCLUDE 1 diff --git a/include/uapi/sound/skl-tplg-interface.h b/include/uapi/sound/skl-tplg-interface.h index f29899b179a6..4bf9c4f9add8 100644 --- a/include/uapi/sound/skl-tplg-interface.h +++ b/include/uapi/sound/skl-tplg-interface.h @@ -66,7 +66,8 @@ enum skl_ch_cfg { SKL_CH_CFG_DUAL_MONO = 9, SKL_CH_CFG_I2S_DUAL_STEREO_0 = 10, SKL_CH_CFG_I2S_DUAL_STEREO_1 = 11, - SKL_CH_CFG_4_CHANNEL = 12, + SKL_CH_CFG_7_1 = 12, + SKL_CH_CFG_4_CHANNEL = SKL_CH_CFG_7_1, SKL_CH_CFG_INVALID }; diff --git a/include/uapi/sound/sof/tokens.h b/include/uapi/sound/sof/tokens.h index bbc37877aaff..e9ec7e4eb982 100644 --- a/include/uapi/sound/sof/tokens.h +++ b/include/uapi/sound/sof/tokens.h @@ -183,7 +183,7 @@ #define SOF_TKN_CAVS_AUDIO_FORMAT_IN_INTERLEAVING_STYLE 1906 #define SOF_TKN_CAVS_AUDIO_FORMAT_IN_FMT_CFG 1907 #define SOF_TKN_CAVS_AUDIO_FORMAT_IN_SAMPLE_TYPE 1908 -#define SOF_TKN_CAVS_AUDIO_FORMAT_PIN_INDEX 1909 +#define SOF_TKN_CAVS_AUDIO_FORMAT_INPUT_PIN_INDEX 1909 /* intentional token numbering discontinuity, reserved for future use */ #define SOF_TKN_CAVS_AUDIO_FORMAT_OUT_RATE 1930 #define SOF_TKN_CAVS_AUDIO_FORMAT_OUT_BIT_DEPTH 1931 @@ -194,6 +194,7 @@ #define SOF_TKN_CAVS_AUDIO_FORMAT_OUT_INTERLEAVING_STYLE 1936 #define SOF_TKN_CAVS_AUDIO_FORMAT_OUT_FMT_CFG 1937 #define SOF_TKN_CAVS_AUDIO_FORMAT_OUT_SAMPLE_TYPE 1938 +#define SOF_TKN_CAVS_AUDIO_FORMAT_OUTPUT_PIN_INDEX 1939 /* intentional token numbering discontinuity, reserved for future use */ #define SOF_TKN_CAVS_AUDIO_FORMAT_IBS 1970 #define SOF_TKN_CAVS_AUDIO_FORMAT_OBS 1971 diff --git a/include/ufs/ufshcd.h b/include/ufs/ufshcd.h index f7553293ba98..df1d04f7a542 100644 --- a/include/ufs/ufshcd.h +++ b/include/ufs/ufshcd.h @@ -1133,7 +1133,7 @@ static inline size_t ufshcd_sg_entry_size(const struct ufs_hba *hba) ({ (void)(hba); BUILD_BUG_ON(sg_entry_size != sizeof(struct ufshcd_sg_entry)); }) #endif -static inline size_t sizeof_utp_transfer_cmd_desc(const struct ufs_hba *hba) +static inline size_t ufshcd_get_ucd_size(const struct ufs_hba *hba) { return sizeof(struct utp_transfer_cmd_desc) + SG_ALL * ufshcd_sg_entry_size(hba); } diff --git a/io_uring/sqpoll.c b/io_uring/sqpoll.c index 9db4bc1f521a..5e329e3cd470 100644 --- a/io_uring/sqpoll.c +++ b/io_uring/sqpoll.c @@ -255,9 +255,13 @@ static int io_sq_thread(void *data) sqt_spin = true; if (sqt_spin || !time_after(jiffies, timeout)) { - cond_resched(); if (sqt_spin) timeout = jiffies + sqd->sq_thread_idle; + if (unlikely(need_resched())) { + mutex_unlock(&sqd->lock); + cond_resched(); + mutex_lock(&sqd->lock); + } continue; } diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 00c253b84bf5..9901efee4339 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -1215,7 +1215,7 @@ static long htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value ret = htab_lock_bucket(htab, b, hash, &flags); if (ret) - return ret; + goto err_lock_bucket; l_old = lookup_elem_raw(head, hash, key, key_size); @@ -1236,6 +1236,7 @@ static long htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value err: htab_unlock_bucket(htab, b, hash, flags); +err_lock_bucket: if (ret) htab_lru_push_free(htab, l_new); else if (l_old) @@ -1338,7 +1339,7 @@ static long __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key, ret = htab_lock_bucket(htab, b, hash, &flags); if (ret) - return ret; + goto err_lock_bucket; l_old = lookup_elem_raw(head, hash, key, key_size); @@ -1361,6 +1362,7 @@ static long __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key, ret = 0; err: htab_unlock_bucket(htab, b, hash, flags); +err_lock_bucket: if (l_new) bpf_lru_push_free(&htab->lru, &l_new->lru_node); return ret; diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c index d9c9f45e3529..8a26cd8814c1 100644 --- a/kernel/bpf/offload.c +++ b/kernel/bpf/offload.c @@ -859,4 +859,4 @@ static int __init bpf_offload_init(void) return rhashtable_init(&offdevs, &offdevs_params); } -late_initcall(bpf_offload_init); +core_initcall(bpf_offload_init); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index fbcf5a4e2fcd..5871aa78d01a 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -17033,7 +17033,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) insn_buf[cnt++] = BPF_ALU64_IMM(BPF_RSH, insn->dst_reg, shift); - insn_buf[cnt++] = BPF_ALU64_IMM(BPF_AND, insn->dst_reg, + insn_buf[cnt++] = BPF_ALU32_IMM(BPF_AND, insn->dst_reg, (1ULL << size * 8) - 1); } } diff --git a/kernel/exit.c b/kernel/exit.c index 34b90e2e7cf7..edb50b4c9972 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -411,7 +411,10 @@ static void coredump_task_exit(struct task_struct *tsk) tsk->flags |= PF_POSTCOREDUMP; core_state = tsk->signal->core_state; spin_unlock_irq(&tsk->sighand->siglock); - if (core_state) { + + /* The vhost_worker does not particpate in coredumps */ + if (core_state && + ((tsk->flags & (PF_IO_WORKER | PF_USER_WORKER)) != PF_USER_WORKER)) { struct core_thread self; self.task = current; diff --git a/kernel/fork.c b/kernel/fork.c index ed4e01daccaa..81cba91f30bb 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2336,16 +2336,16 @@ __latent_entropy struct task_struct *copy_process( p->flags &= ~PF_KTHREAD; if (args->kthread) p->flags |= PF_KTHREAD; - if (args->user_worker) - p->flags |= PF_USER_WORKER; - if (args->io_thread) { + if (args->user_worker) { /* - * Mark us an IO worker, and block any signal that isn't + * Mark us a user worker, and block any signal that isn't * fatal or STOP */ - p->flags |= PF_IO_WORKER; + p->flags |= PF_USER_WORKER; siginitsetinv(&p->blocked, sigmask(SIGKILL)|sigmask(SIGSTOP)); } + if (args->io_thread) + p->flags |= PF_IO_WORKER; if (args->name) strscpy_pad(p->comm, args->name, sizeof(p->comm)); @@ -2517,9 +2517,6 @@ __latent_entropy struct task_struct *copy_process( if (retval) goto bad_fork_cleanup_io; - if (args->ignore_signals) - ignore_signals(p); - stackleak_task_init(p); if (pid != &init_struct_pid) { diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index 7a97bcb086bf..b4c31a5c1147 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -542,7 +542,7 @@ fail: return ret; } -#ifdef CONFIG_PCI_MSI_ARCH_FALLBACKS +#if defined(CONFIG_PCI_MSI_ARCH_FALLBACKS) || defined(CONFIG_PCI_XEN) /** * msi_device_populate_sysfs - Populate msi_irqs sysfs entries for a device * @dev: The device (PCI, platform etc) which will get sysfs entries @@ -574,7 +574,7 @@ void msi_device_destroy_sysfs(struct device *dev) msi_for_each_desc(desc, dev, MSI_DESC_ALL) msi_sysfs_remove_desc(dev, desc); } -#endif /* CONFIG_PCI_MSI_ARCH_FALLBACK */ +#endif /* CONFIG_PCI_MSI_ARCH_FALLBACK || CONFIG_PCI_XEN */ #else /* CONFIG_SYSFS */ static inline int msi_sysfs_create_group(struct device *dev) { return 0; } static inline int msi_sysfs_populate_desc(struct device *dev, struct msi_desc *desc) { return 0; } diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index dcd1d5bfc1e0..4dfd2f3e09b2 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -2263,6 +2263,9 @@ static inline bool usage_match(struct lock_list *entry, void *mask) static inline bool usage_skip(struct lock_list *entry, void *mask) { + if (entry->class->lock_type == LD_LOCK_NORMAL) + return false; + /* * Skip local_lock() for irq inversion detection. * @@ -2289,14 +2292,16 @@ static inline bool usage_skip(struct lock_list *entry, void *mask) * As a result, we will skip local_lock(), when we search for irq * inversion bugs. */ - if (entry->class->lock_type == LD_LOCK_PERCPU) { - if (DEBUG_LOCKS_WARN_ON(entry->class->wait_type_inner < LD_WAIT_CONFIG)) - return false; + if (entry->class->lock_type == LD_LOCK_PERCPU && + DEBUG_LOCKS_WARN_ON(entry->class->wait_type_inner < LD_WAIT_CONFIG)) + return false; - return true; - } + /* + * Skip WAIT_OVERRIDE for irq inversion detection -- it's not actually + * a lock and only used to override the wait_type. + */ - return false; + return true; } /* @@ -4768,7 +4773,8 @@ static int check_wait_context(struct task_struct *curr, struct held_lock *next) for (; depth < curr->lockdep_depth; depth++) { struct held_lock *prev = curr->held_locks + depth; - u8 prev_inner = hlock_class(prev)->wait_type_inner; + struct lock_class *class = hlock_class(prev); + u8 prev_inner = class->wait_type_inner; if (prev_inner) { /* @@ -4778,6 +4784,14 @@ static int check_wait_context(struct task_struct *curr, struct held_lock *next) * Also due to trylocks. */ curr_inner = min(curr_inner, prev_inner); + + /* + * Allow override for annotations -- this is typically + * only valid/needed for code that only exists when + * CONFIG_PREEMPT_RT=n. + */ + if (unlikely(class->lock_type == LD_LOCK_WAIT_OVERRIDE)) + curr_inner = prev_inner; } } diff --git a/kernel/module/main.c b/kernel/module/main.c index 044aa2c9e3cb..4e2cf784cf8c 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -1521,14 +1521,14 @@ static void __layout_sections(struct module *mod, struct load_info *info, bool i MOD_RODATA, MOD_RO_AFTER_INIT, MOD_DATA, - MOD_INVALID, /* This is needed to match the masks array */ + MOD_DATA, }; static const int init_m_to_mem_type[] = { MOD_INIT_TEXT, MOD_INIT_RODATA, MOD_INVALID, MOD_INIT_DATA, - MOD_INVALID, /* This is needed to match the masks array */ + MOD_INIT_DATA, }; for (m = 0; m < ARRAY_SIZE(masks); ++m) { diff --git a/kernel/module/stats.c b/kernel/module/stats.c index ad7b6ada29f2..6ab2c94d6bc3 100644 --- a/kernel/module/stats.c +++ b/kernel/module/stats.c @@ -276,6 +276,7 @@ static ssize_t read_file_mod_stats(struct file *file, char __user *user_buf, struct mod_fail_load *mod_fail; unsigned int len, size, count_failed = 0; char *buf; + int ret; u32 live_mod_count, fkreads, fdecompress, fbecoming, floads; unsigned long total_size, text_size, ikread_bytes, ibecoming_bytes, idecompress_bytes, imod_bytes, total_virtual_lost; @@ -390,8 +391,9 @@ static ssize_t read_file_mod_stats(struct file *file, char __user *user_buf, out_unlock: mutex_unlock(&module_mutex); out: + ret = simple_read_from_buffer(user_buf, count, ppos, buf, len); kfree(buf); - return simple_read_from_buffer(user_buf, count, ppos, buf, len); + return ret; } #undef MAX_PREAMBLE #undef MAX_FAILED_MOD_PRINT diff --git a/kernel/signal.c b/kernel/signal.c index 8f6330f0e9ca..2547fa73bde5 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1368,7 +1368,9 @@ int zap_other_threads(struct task_struct *p) while_each_thread(p, t) { task_clear_jobctl_pending(t, JOBCTL_PENDING_MASK); - count++; + /* Don't require de_thread to wait for the vhost_worker */ + if ((t->flags & (PF_IO_WORKER | PF_USER_WORKER)) != PF_USER_WORKER) + count++; /* Don't bother with already dead threads */ if (t->exit_state) @@ -2861,11 +2863,11 @@ relock: } /* - * PF_IO_WORKER threads will catch and exit on fatal signals + * PF_USER_WORKER threads will catch and exit on fatal signals * themselves. They have cleanup that must be performed, so * we cannot call do_exit() on their behalf. */ - if (current->flags & PF_IO_WORKER) + if (current->flags & PF_USER_WORKER) goto out; /* diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index 9abb3905bc8e..18d36842faf5 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -17,36 +17,30 @@ struct fprobe_rethook_node { struct rethook_node node; unsigned long entry_ip; + unsigned long entry_parent_ip; char data[]; }; -static void fprobe_handler(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *ops, struct ftrace_regs *fregs) +static inline void __fprobe_handler(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *ops, struct ftrace_regs *fregs) { struct fprobe_rethook_node *fpr; struct rethook_node *rh = NULL; struct fprobe *fp; void *entry_data = NULL; - int bit, ret; + int ret = 0; fp = container_of(ops, struct fprobe, ops); - if (fprobe_disabled(fp)) - return; - - bit = ftrace_test_recursion_trylock(ip, parent_ip); - if (bit < 0) { - fp->nmissed++; - return; - } if (fp->exit_handler) { rh = rethook_try_get(fp->rethook); if (!rh) { fp->nmissed++; - goto out; + return; } fpr = container_of(rh, struct fprobe_rethook_node, node); fpr->entry_ip = ip; + fpr->entry_parent_ip = parent_ip; if (fp->entry_data_size) entry_data = fpr->data; } @@ -61,23 +55,60 @@ static void fprobe_handler(unsigned long ip, unsigned long parent_ip, else rethook_hook(rh, ftrace_get_regs(fregs), true); } -out: +} + +static void fprobe_handler(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *ops, struct ftrace_regs *fregs) +{ + struct fprobe *fp; + int bit; + + fp = container_of(ops, struct fprobe, ops); + if (fprobe_disabled(fp)) + return; + + /* recursion detection has to go before any traceable function and + * all functions before this point should be marked as notrace + */ + bit = ftrace_test_recursion_trylock(ip, parent_ip); + if (bit < 0) { + fp->nmissed++; + return; + } + __fprobe_handler(ip, parent_ip, ops, fregs); ftrace_test_recursion_unlock(bit); + } NOKPROBE_SYMBOL(fprobe_handler); static void fprobe_kprobe_handler(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *ops, struct ftrace_regs *fregs) { - struct fprobe *fp = container_of(ops, struct fprobe, ops); + struct fprobe *fp; + int bit; + + fp = container_of(ops, struct fprobe, ops); + if (fprobe_disabled(fp)) + return; + + /* recursion detection has to go before any traceable function and + * all functions called before this point should be marked as notrace + */ + bit = ftrace_test_recursion_trylock(ip, parent_ip); + if (bit < 0) { + fp->nmissed++; + return; + } if (unlikely(kprobe_running())) { fp->nmissed++; return; } + kprobe_busy_begin(); - fprobe_handler(ip, parent_ip, ops, fregs); + __fprobe_handler(ip, parent_ip, ops, fregs); kprobe_busy_end(); + ftrace_test_recursion_unlock(bit); } static void fprobe_exit_handler(struct rethook_node *rh, void *data, @@ -85,14 +116,26 @@ static void fprobe_exit_handler(struct rethook_node *rh, void *data, { struct fprobe *fp = (struct fprobe *)data; struct fprobe_rethook_node *fpr; + int bit; if (!fp || fprobe_disabled(fp)) return; fpr = container_of(rh, struct fprobe_rethook_node, node); + /* + * we need to assure no calls to traceable functions in-between the + * end of fprobe_handler and the beginning of fprobe_exit_handler. + */ + bit = ftrace_test_recursion_trylock(fpr->entry_ip, fpr->entry_parent_ip); + if (bit < 0) { + fp->nmissed++; + return; + } + fp->exit_handler(fp, fpr->entry_ip, regs, fp->entry_data_size ? (void *)fpr->data : NULL); + ftrace_test_recursion_unlock(bit); } NOKPROBE_SYMBOL(fprobe_exit_handler); diff --git a/kernel/trace/rethook.c b/kernel/trace/rethook.c index 32c3dfdb4d6a..60f6cb2b486b 100644 --- a/kernel/trace/rethook.c +++ b/kernel/trace/rethook.c @@ -288,7 +288,7 @@ unsigned long rethook_trampoline_handler(struct pt_regs *regs, * These loops must be protected from rethook_free_rcu() because those * are accessing 'rhn->rethook'. */ - preempt_disable(); + preempt_disable_notrace(); /* * Run the handler on the shadow stack. Do not unlink the list here because @@ -321,7 +321,7 @@ unsigned long rethook_trampoline_handler(struct pt_regs *regs, first = first->next; rethook_recycle(rhn); } - preempt_enable(); + preempt_enable_notrace(); return correct_ret_addr; } diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index ebc59781456a..64a4dde073ef 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -60,6 +60,7 @@ */ bool ring_buffer_expanded; +#ifdef CONFIG_FTRACE_STARTUP_TEST /* * We need to change this state when a selftest is running. * A selftest will lurk into the ring-buffer to count the @@ -75,7 +76,6 @@ static bool __read_mostly tracing_selftest_running; */ bool __read_mostly tracing_selftest_disabled; -#ifdef CONFIG_FTRACE_STARTUP_TEST void __init disable_tracing_selftest(const char *reason) { if (!tracing_selftest_disabled) { @@ -83,6 +83,9 @@ void __init disable_tracing_selftest(const char *reason) pr_info("Ftrace startup test is disabled due to %s\n", reason); } } +#else +#define tracing_selftest_running 0 +#define tracing_selftest_disabled 0 #endif /* Pipe tracepoints to printk */ @@ -1051,7 +1054,10 @@ int __trace_array_puts(struct trace_array *tr, unsigned long ip, if (!(tr->trace_flags & TRACE_ITER_PRINTK)) return 0; - if (unlikely(tracing_selftest_running || tracing_disabled)) + if (unlikely(tracing_selftest_running && tr == &global_trace)) + return 0; + + if (unlikely(tracing_disabled)) return 0; alloc = sizeof(*entry) + size + 2; /* possible \n added */ @@ -2041,6 +2047,24 @@ static int run_tracer_selftest(struct tracer *type) return 0; } +static int do_run_tracer_selftest(struct tracer *type) +{ + int ret; + + /* + * Tests can take a long time, especially if they are run one after the + * other, as does happen during bootup when all the tracers are + * registered. This could cause the soft lockup watchdog to trigger. + */ + cond_resched(); + + tracing_selftest_running = true; + ret = run_tracer_selftest(type); + tracing_selftest_running = false; + + return ret; +} + static __init int init_trace_selftests(void) { struct trace_selftests *p, *n; @@ -2092,6 +2116,10 @@ static inline int run_tracer_selftest(struct tracer *type) { return 0; } +static inline int do_run_tracer_selftest(struct tracer *type) +{ + return 0; +} #endif /* CONFIG_FTRACE_STARTUP_TEST */ static void add_tracer_options(struct trace_array *tr, struct tracer *t); @@ -2127,8 +2155,6 @@ int __init register_tracer(struct tracer *type) mutex_lock(&trace_types_lock); - tracing_selftest_running = true; - for (t = trace_types; t; t = t->next) { if (strcmp(type->name, t->name) == 0) { /* already found */ @@ -2157,7 +2183,7 @@ int __init register_tracer(struct tracer *type) /* store the tracer for __set_tracer_option */ type->flags->trace = type; - ret = run_tracer_selftest(type); + ret = do_run_tracer_selftest(type); if (ret < 0) goto out; @@ -2166,7 +2192,6 @@ int __init register_tracer(struct tracer *type) add_tracer_options(&global_trace, type); out: - tracing_selftest_running = false; mutex_unlock(&trace_types_lock); if (ret || !default_bootup_tracer) @@ -3490,7 +3515,7 @@ __trace_array_vprintk(struct trace_buffer *buffer, unsigned int trace_ctx; char *tbuffer; - if (tracing_disabled || tracing_selftest_running) + if (tracing_disabled) return 0; /* Don't pollute graph traces with trace_vprintk internals */ @@ -3538,6 +3563,9 @@ __printf(3, 0) int trace_array_vprintk(struct trace_array *tr, unsigned long ip, const char *fmt, va_list args) { + if (tracing_selftest_running && tr == &global_trace) + return 0; + return __trace_array_vprintk(tr->array_buffer.buffer, ip, fmt, args); } @@ -5752,7 +5780,7 @@ static const char readme_msg[] = "\t table using the key(s) and value(s) named, and the value of a\n" "\t sum called 'hitcount' is incremented. Keys and values\n" "\t correspond to fields in the event's format description. Keys\n" - "\t can be any field, or the special string 'stacktrace'.\n" + "\t can be any field, or the special string 'common_stacktrace'.\n" "\t Compound keys consisting of up to two fields can be specified\n" "\t by the 'keys' keyword. Values must correspond to numeric\n" "\t fields. Sort keys consisting of up to two fields can be\n" diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 654ffa40457a..57e539d47989 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -194,6 +194,8 @@ static int trace_define_generic_fields(void) __generic_field(int, common_cpu, FILTER_CPU); __generic_field(char *, COMM, FILTER_COMM); __generic_field(char *, comm, FILTER_COMM); + __generic_field(char *, stacktrace, FILTER_STACKTRACE); + __generic_field(char *, STACKTRACE, FILTER_STACKTRACE); return ret; } diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 486cca3c2b75..b97d3ad832f1 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -1364,7 +1364,7 @@ static const char *hist_field_name(struct hist_field *field, if (field->field) field_name = field->field->name; else - field_name = "stacktrace"; + field_name = "common_stacktrace"; } else if (field->flags & HIST_FIELD_FL_HITCOUNT) field_name = "hitcount"; @@ -2367,7 +2367,7 @@ parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file, hist_data->enable_timestamps = true; if (*flags & HIST_FIELD_FL_TIMESTAMP_USECS) hist_data->attrs->ts_in_usecs = true; - } else if (strcmp(field_name, "stacktrace") == 0) { + } else if (strcmp(field_name, "common_stacktrace") == 0) { *flags |= HIST_FIELD_FL_STACKTRACE; } else if (strcmp(field_name, "common_cpu") == 0) *flags |= HIST_FIELD_FL_CPU; @@ -2378,11 +2378,15 @@ parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file, if (!field || !field->size) { /* * For backward compatibility, if field_name - * was "cpu", then we treat this the same as - * common_cpu. This also works for "CPU". + * was "cpu" or "stacktrace", then we treat this + * the same as common_cpu and common_stacktrace + * respectively. This also works for "CPU", and + * "STACKTRACE". */ if (field && field->filter_type == FILTER_CPU) { *flags |= HIST_FIELD_FL_CPU; + } else if (field && field->filter_type == FILTER_STACKTRACE) { + *flags |= HIST_FIELD_FL_STACKTRACE; } else { hist_err(tr, HIST_ERR_FIELD_NOT_FOUND, errpos(field_name)); @@ -4238,13 +4242,19 @@ static int __create_val_field(struct hist_trigger_data *hist_data, goto out; } - /* Some types cannot be a value */ - if (hist_field->flags & (HIST_FIELD_FL_GRAPH | HIST_FIELD_FL_PERCENT | - HIST_FIELD_FL_BUCKET | HIST_FIELD_FL_LOG2 | - HIST_FIELD_FL_SYM | HIST_FIELD_FL_SYM_OFFSET | - HIST_FIELD_FL_SYSCALL | HIST_FIELD_FL_STACKTRACE)) { - hist_err(file->tr, HIST_ERR_BAD_FIELD_MODIFIER, errpos(field_str)); - ret = -EINVAL; + /* values and variables should not have some modifiers */ + if (hist_field->flags & HIST_FIELD_FL_VAR) { + /* Variable */ + if (hist_field->flags & (HIST_FIELD_FL_GRAPH | HIST_FIELD_FL_PERCENT | + HIST_FIELD_FL_BUCKET | HIST_FIELD_FL_LOG2)) + goto err; + } else { + /* Value */ + if (hist_field->flags & (HIST_FIELD_FL_GRAPH | HIST_FIELD_FL_PERCENT | + HIST_FIELD_FL_BUCKET | HIST_FIELD_FL_LOG2 | + HIST_FIELD_FL_SYM | HIST_FIELD_FL_SYM_OFFSET | + HIST_FIELD_FL_SYSCALL | HIST_FIELD_FL_STACKTRACE)) + goto err; } hist_data->fields[val_idx] = hist_field; @@ -4256,6 +4266,9 @@ static int __create_val_field(struct hist_trigger_data *hist_data, ret = -EINVAL; out: return ret; + err: + hist_err(file->tr, HIST_ERR_BAD_FIELD_MODIFIER, errpos(field_str)); + return -EINVAL; } static int create_val_field(struct hist_trigger_data *hist_data, @@ -5385,7 +5398,7 @@ static void hist_trigger_print_key(struct seq_file *m, if (key_field->field) seq_printf(m, "%s.stacktrace", key_field->field->name); else - seq_puts(m, "stacktrace:\n"); + seq_puts(m, "common_stacktrace:\n"); hist_trigger_stacktrace_print(m, key + key_field->offset, HIST_STACKTRACE_DEPTH); @@ -5968,7 +5981,7 @@ static int event_hist_trigger_print(struct seq_file *m, if (field->field) seq_printf(m, "%s.stacktrace", field->field->name); else - seq_puts(m, "stacktrace"); + seq_puts(m, "common_stacktrace"); } else hist_field_print(m, field); } diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c index b1ecd7677642..dbb14705d0d3 100644 --- a/kernel/trace/trace_events_user.c +++ b/kernel/trace/trace_events_user.c @@ -96,12 +96,12 @@ struct user_event { * these to track enablement sites that are tied to an event. */ struct user_event_enabler { - struct list_head link; + struct list_head mm_enablers_link; struct user_event *event; unsigned long addr; /* Track enable bit, flags, etc. Aligned for bitops. */ - unsigned int values; + unsigned long values; }; /* Bits 0-5 are for the bit to update upon enable/disable (0-63 allowed) */ @@ -116,7 +116,9 @@ struct user_event_enabler { /* Only duplicate the bit value */ #define ENABLE_VAL_DUP_MASK ENABLE_VAL_BIT_MASK -#define ENABLE_BITOPS(e) ((unsigned long *)&(e)->values) +#define ENABLE_BITOPS(e) (&(e)->values) + +#define ENABLE_BIT(e) ((int)((e)->values & ENABLE_VAL_BIT_MASK)) /* Used for asynchronous faulting in of pages */ struct user_event_enabler_fault { @@ -153,7 +155,7 @@ struct user_event_file_info { #define VALIDATOR_REL (1 << 1) struct user_event_validator { - struct list_head link; + struct list_head user_event_link; int offset; int flags; }; @@ -259,7 +261,7 @@ error: static void user_event_enabler_destroy(struct user_event_enabler *enabler) { - list_del_rcu(&enabler->link); + list_del_rcu(&enabler->mm_enablers_link); /* No longer tracking the event via the enabler */ refcount_dec(&enabler->event->refcnt); @@ -423,9 +425,9 @@ static int user_event_enabler_write(struct user_event_mm *mm, /* Update bit atomically, user tracers must be atomic as well */ if (enabler->event && enabler->event->status) - set_bit(enabler->values & ENABLE_VAL_BIT_MASK, ptr); + set_bit(ENABLE_BIT(enabler), ptr); else - clear_bit(enabler->values & ENABLE_VAL_BIT_MASK, ptr); + clear_bit(ENABLE_BIT(enabler), ptr); kunmap_local(kaddr); unpin_user_pages_dirty_lock(&page, 1, true); @@ -437,11 +439,9 @@ static bool user_event_enabler_exists(struct user_event_mm *mm, unsigned long uaddr, unsigned char bit) { struct user_event_enabler *enabler; - struct user_event_enabler *next; - list_for_each_entry_safe(enabler, next, &mm->enablers, link) { - if (enabler->addr == uaddr && - (enabler->values & ENABLE_VAL_BIT_MASK) == bit) + list_for_each_entry(enabler, &mm->enablers, mm_enablers_link) { + if (enabler->addr == uaddr && ENABLE_BIT(enabler) == bit) return true; } @@ -451,23 +451,36 @@ static bool user_event_enabler_exists(struct user_event_mm *mm, static void user_event_enabler_update(struct user_event *user) { struct user_event_enabler *enabler; - struct user_event_mm *mm = user_event_mm_get_all(user); struct user_event_mm *next; + struct user_event_mm *mm; int attempt; + lockdep_assert_held(&event_mutex); + + /* + * We need to build a one-shot list of all the mms that have an + * enabler for the user_event passed in. This list is only valid + * while holding the event_mutex. The only reason for this is due + * to the global mm list being RCU protected and we use methods + * which can wait (mmap_read_lock and pin_user_pages_remote). + * + * NOTE: user_event_mm_get_all() increments the ref count of each + * mm that is added to the list to prevent removal timing windows. + * We must always put each mm after they are used, which may wait. + */ + mm = user_event_mm_get_all(user); + while (mm) { next = mm->next; mmap_read_lock(mm->mm); - rcu_read_lock(); - list_for_each_entry_rcu(enabler, &mm->enablers, link) { + list_for_each_entry(enabler, &mm->enablers, mm_enablers_link) { if (enabler->event == user) { attempt = 0; user_event_enabler_write(mm, enabler, true, &attempt); } } - rcu_read_unlock(); mmap_read_unlock(mm->mm); user_event_mm_put(mm); mm = next; @@ -495,7 +508,9 @@ static bool user_event_enabler_dup(struct user_event_enabler *orig, enabler->values = orig->values & ENABLE_VAL_DUP_MASK; refcount_inc(&enabler->event->refcnt); - list_add_rcu(&enabler->link, &mm->enablers); + + /* Enablers not exposed yet, RCU not required */ + list_add(&enabler->mm_enablers_link, &mm->enablers); return true; } @@ -514,6 +529,14 @@ static struct user_event_mm *user_event_mm_get_all(struct user_event *user) struct user_event_mm *mm; /* + * We use the mm->next field to build a one-shot list from the global + * RCU protected list. To build this list the event_mutex must be held. + * This lets us build a list without requiring allocs that could fail + * when user based events are most wanted for diagnostics. + */ + lockdep_assert_held(&event_mutex); + + /* * We do not want to block fork/exec while enablements are being * updated, so we use RCU to walk the current tasks that have used * user_events ABI for 1 or more events. Each enabler found in each @@ -525,23 +548,24 @@ static struct user_event_mm *user_event_mm_get_all(struct user_event *user) */ rcu_read_lock(); - list_for_each_entry_rcu(mm, &user_event_mms, link) - list_for_each_entry_rcu(enabler, &mm->enablers, link) + list_for_each_entry_rcu(mm, &user_event_mms, mms_link) { + list_for_each_entry_rcu(enabler, &mm->enablers, mm_enablers_link) { if (enabler->event == user) { mm->next = found; found = user_event_mm_get(mm); break; } + } + } rcu_read_unlock(); return found; } -static struct user_event_mm *user_event_mm_create(struct task_struct *t) +static struct user_event_mm *user_event_mm_alloc(struct task_struct *t) { struct user_event_mm *user_mm; - unsigned long flags; user_mm = kzalloc(sizeof(*user_mm), GFP_KERNEL_ACCOUNT); @@ -553,12 +577,6 @@ static struct user_event_mm *user_event_mm_create(struct task_struct *t) refcount_set(&user_mm->refcnt, 1); refcount_set(&user_mm->tasks, 1); - spin_lock_irqsave(&user_event_mms_lock, flags); - list_add_rcu(&user_mm->link, &user_event_mms); - spin_unlock_irqrestore(&user_event_mms_lock, flags); - - t->user_event_mm = user_mm; - /* * The lifetime of the memory descriptor can slightly outlast * the task lifetime if a ref to the user_event_mm is taken @@ -572,6 +590,17 @@ static struct user_event_mm *user_event_mm_create(struct task_struct *t) return user_mm; } +static void user_event_mm_attach(struct user_event_mm *user_mm, struct task_struct *t) +{ + unsigned long flags; + + spin_lock_irqsave(&user_event_mms_lock, flags); + list_add_rcu(&user_mm->mms_link, &user_event_mms); + spin_unlock_irqrestore(&user_event_mms_lock, flags); + + t->user_event_mm = user_mm; +} + static struct user_event_mm *current_user_event_mm(void) { struct user_event_mm *user_mm = current->user_event_mm; @@ -579,10 +608,12 @@ static struct user_event_mm *current_user_event_mm(void) if (user_mm) goto inc; - user_mm = user_event_mm_create(current); + user_mm = user_event_mm_alloc(current); if (!user_mm) goto error; + + user_event_mm_attach(user_mm, current); inc: refcount_inc(&user_mm->refcnt); error: @@ -593,7 +624,7 @@ static void user_event_mm_destroy(struct user_event_mm *mm) { struct user_event_enabler *enabler, *next; - list_for_each_entry_safe(enabler, next, &mm->enablers, link) + list_for_each_entry_safe(enabler, next, &mm->enablers, mm_enablers_link) user_event_enabler_destroy(enabler); mmdrop(mm->mm); @@ -630,7 +661,7 @@ void user_event_mm_remove(struct task_struct *t) /* Remove the mm from the list, so it can no longer be enabled */ spin_lock_irqsave(&user_event_mms_lock, flags); - list_del_rcu(&mm->link); + list_del_rcu(&mm->mms_link); spin_unlock_irqrestore(&user_event_mms_lock, flags); /* @@ -670,7 +701,7 @@ void user_event_mm_remove(struct task_struct *t) void user_event_mm_dup(struct task_struct *t, struct user_event_mm *old_mm) { - struct user_event_mm *mm = user_event_mm_create(t); + struct user_event_mm *mm = user_event_mm_alloc(t); struct user_event_enabler *enabler; if (!mm) @@ -678,16 +709,18 @@ void user_event_mm_dup(struct task_struct *t, struct user_event_mm *old_mm) rcu_read_lock(); - list_for_each_entry_rcu(enabler, &old_mm->enablers, link) + list_for_each_entry_rcu(enabler, &old_mm->enablers, mm_enablers_link) { if (!user_event_enabler_dup(enabler, mm)) goto error; + } rcu_read_unlock(); + user_event_mm_attach(mm, t); return; error: rcu_read_unlock(); - user_event_mm_remove(t); + user_event_mm_destroy(mm); } static bool current_user_event_enabler_exists(unsigned long uaddr, @@ -748,7 +781,7 @@ retry: */ if (!*write_result) { refcount_inc(&enabler->event->refcnt); - list_add_rcu(&enabler->link, &user_mm->enablers); + list_add_rcu(&enabler->mm_enablers_link, &user_mm->enablers); } mutex_unlock(&event_mutex); @@ -904,8 +937,8 @@ static void user_event_destroy_validators(struct user_event *user) struct user_event_validator *validator, *next; struct list_head *head = &user->validators; - list_for_each_entry_safe(validator, next, head, link) { - list_del(&validator->link); + list_for_each_entry_safe(validator, next, head, user_event_link) { + list_del(&validator->user_event_link); kfree(validator); } } @@ -959,7 +992,7 @@ add_validator: validator->offset = offset; /* Want sequential access when validating */ - list_add_tail(&validator->link, &user->validators); + list_add_tail(&validator->user_event_link, &user->validators); add_field: field->type = type; @@ -1349,7 +1382,7 @@ static int user_event_validate(struct user_event *user, void *data, int len) void *pos, *end = data + len; u32 loc, offset, size; - list_for_each_entry(validator, head, link) { + list_for_each_entry(validator, head, user_event_link) { pos = data + validator->offset; /* Already done min_size check, no bounds check here */ @@ -2270,9 +2303,9 @@ static long user_events_ioctl_unreg(unsigned long uarg) */ mutex_lock(&event_mutex); - list_for_each_entry_safe(enabler, next, &mm->enablers, link) + list_for_each_entry_safe(enabler, next, &mm->enablers, mm_enablers_link) { if (enabler->addr == reg.disable_addr && - (enabler->values & ENABLE_VAL_BIT_MASK) == reg.disable_bit) { + ENABLE_BIT(enabler) == reg.disable_bit) { set_bit(ENABLE_VAL_FREEING_BIT, ENABLE_BITOPS(enabler)); if (!test_bit(ENABLE_VAL_FAULTING_BIT, ENABLE_BITOPS(enabler))) @@ -2281,6 +2314,7 @@ static long user_events_ioctl_unreg(unsigned long uarg) /* Removed at least one */ ret = 0; } + } mutex_unlock(&event_mutex); diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c index efbbec2caff8..e97e3fa5cbed 100644 --- a/kernel/trace/trace_osnoise.c +++ b/kernel/trace/trace_osnoise.c @@ -1652,6 +1652,8 @@ static enum hrtimer_restart timerlat_irq(struct hrtimer *timer) osnoise_stop_tracing(); notify_new_max_latency(diff); + wake_up_process(tlat->kthread); + return HRTIMER_NORESTART; } } diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index a931d9aaea26..529590499b1f 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -848,6 +848,12 @@ trace_selftest_startup_function_graph(struct tracer *trace, } #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS + /* + * These tests can take some time to run. Make sure on non PREEMPT + * kernels, we do not trigger the softlockup detector. + */ + cond_resched(); + tracing_reset_online_cpus(&tr->array_buffer); set_graph_array(tr); @@ -869,6 +875,8 @@ trace_selftest_startup_function_graph(struct tracer *trace, if (ret) goto out; + cond_resched(); + ret = register_ftrace_graph(&fgraph_ops); if (ret) { warn_failed_init_tracer(trace, ret); @@ -891,6 +899,8 @@ trace_selftest_startup_function_graph(struct tracer *trace, if (ret) goto out; + cond_resched(); + tracing_start(); if (!ret && !count) { diff --git a/kernel/vhost_task.c b/kernel/vhost_task.c index b7cbd66f889e..f80d5c51ae67 100644 --- a/kernel/vhost_task.c +++ b/kernel/vhost_task.c @@ -12,58 +12,88 @@ enum vhost_task_flags { VHOST_TASK_FLAGS_STOP, }; +struct vhost_task { + bool (*fn)(void *data); + void *data; + struct completion exited; + unsigned long flags; + struct task_struct *task; +}; + static int vhost_task_fn(void *data) { struct vhost_task *vtsk = data; - int ret; + bool dead = false; + + for (;;) { + bool did_work; + + /* mb paired w/ vhost_task_stop */ + if (test_bit(VHOST_TASK_FLAGS_STOP, &vtsk->flags)) + break; + + if (!dead && signal_pending(current)) { + struct ksignal ksig; + /* + * Calling get_signal will block in SIGSTOP, + * or clear fatal_signal_pending, but remember + * what was set. + * + * This thread won't actually exit until all + * of the file descriptors are closed, and + * the release function is called. + */ + dead = get_signal(&ksig); + if (dead) + clear_thread_flag(TIF_SIGPENDING); + } + + did_work = vtsk->fn(vtsk->data); + if (!did_work) { + set_current_state(TASK_INTERRUPTIBLE); + schedule(); + } + } - ret = vtsk->fn(vtsk->data); complete(&vtsk->exited); - do_exit(ret); + do_exit(0); +} + +/** + * vhost_task_wake - wakeup the vhost_task + * @vtsk: vhost_task to wake + * + * wake up the vhost_task worker thread + */ +void vhost_task_wake(struct vhost_task *vtsk) +{ + wake_up_process(vtsk->task); } +EXPORT_SYMBOL_GPL(vhost_task_wake); /** * vhost_task_stop - stop a vhost_task * @vtsk: vhost_task to stop * - * Callers must call vhost_task_should_stop and return from their worker - * function when it returns true; + * vhost_task_fn ensures the worker thread exits after + * VHOST_TASK_FLAGS_SOP becomes true. */ void vhost_task_stop(struct vhost_task *vtsk) { - pid_t pid = vtsk->task->pid; - set_bit(VHOST_TASK_FLAGS_STOP, &vtsk->flags); - wake_up_process(vtsk->task); + vhost_task_wake(vtsk); /* * Make sure vhost_task_fn is no longer accessing the vhost_task before - * freeing it below. If userspace crashed or exited without closing, - * then the vhost_task->task could already be marked dead so - * kernel_wait will return early. + * freeing it below. */ wait_for_completion(&vtsk->exited); - /* - * If we are just closing/removing a device and the parent process is - * not exiting then reap the task. - */ - kernel_wait4(pid, NULL, __WCLONE, NULL); kfree(vtsk); } EXPORT_SYMBOL_GPL(vhost_task_stop); /** - * vhost_task_should_stop - should the vhost task return from the work function - * @vtsk: vhost_task to stop - */ -bool vhost_task_should_stop(struct vhost_task *vtsk) -{ - return test_bit(VHOST_TASK_FLAGS_STOP, &vtsk->flags); -} -EXPORT_SYMBOL_GPL(vhost_task_should_stop); - -/** - * vhost_task_create - create a copy of a process to be used by the kernel - * @fn: thread stack + * vhost_task_create - create a copy of a task to be used by the kernel + * @fn: vhost worker function * @arg: data to be passed to fn * @name: the thread's name * @@ -71,17 +101,17 @@ EXPORT_SYMBOL_GPL(vhost_task_should_stop); * failure. The returned task is inactive, and the caller must fire it up * through vhost_task_start(). */ -struct vhost_task *vhost_task_create(int (*fn)(void *), void *arg, +struct vhost_task *vhost_task_create(bool (*fn)(void *), void *arg, const char *name) { struct kernel_clone_args args = { - .flags = CLONE_FS | CLONE_UNTRACED | CLONE_VM, + .flags = CLONE_FS | CLONE_UNTRACED | CLONE_VM | + CLONE_THREAD | CLONE_SIGHAND, .exit_signal = 0, .fn = vhost_task_fn, .name = name, .user_worker = 1, .no_files = 1, - .ignore_signals = 1, }; struct vhost_task *vtsk; struct task_struct *tsk; diff --git a/lib/debugobjects.c b/lib/debugobjects.c index 003edc5ebd67..984985c39c9b 100644 --- a/lib/debugobjects.c +++ b/lib/debugobjects.c @@ -126,7 +126,7 @@ static const char *obj_states[ODEBUG_STATE_MAX] = { static void fill_pool(void) { - gfp_t gfp = GFP_ATOMIC | __GFP_NORETRY | __GFP_NOWARN; + gfp_t gfp = __GFP_HIGH | __GFP_NOWARN; struct debug_obj *obj; unsigned long flags; @@ -591,10 +591,21 @@ static void debug_objects_fill_pool(void) { /* * On RT enabled kernels the pool refill must happen in preemptible - * context: + * context -- for !RT kernels we rely on the fact that spinlock_t and + * raw_spinlock_t are basically the same type and this lock-type + * inversion works just fine. */ - if (!IS_ENABLED(CONFIG_PREEMPT_RT) || preemptible()) + if (!IS_ENABLED(CONFIG_PREEMPT_RT) || preemptible()) { + /* + * Annotate away the spinlock_t inside raw_spinlock_t warning + * by temporarily raising the wait-type to WAIT_SLEEP, matching + * the preemptible() condition above. + */ + static DEFINE_WAIT_OVERRIDE_MAP(fill_pool_map, LD_WAIT_SLEEP); + lock_map_acquire_try(&fill_pool_map); fill_pool(); + lock_map_release(&fill_pool_map); + } } static void diff --git a/lib/maple_tree.c b/lib/maple_tree.c index 110a36479dce..8ebc43d4cc8c 100644 --- a/lib/maple_tree.c +++ b/lib/maple_tree.c @@ -5317,15 +5317,9 @@ int mas_empty_area(struct ma_state *mas, unsigned long min, mt = mte_node_type(mas->node); pivots = ma_pivots(mas_mn(mas), mt); - if (offset) - mas->min = pivots[offset - 1] + 1; - - if (offset < mt_pivots[mt]) - mas->max = pivots[offset]; - - if (mas->index < mas->min) - mas->index = mas->min; - + min = mas_safe_min(mas, pivots, offset); + if (mas->index < min) + mas->index = min; mas->last = mas->index + size - 1; return 0; } diff --git a/mm/kfence/kfence.h b/mm/kfence/kfence.h index 2aafc46a4aaf..392fb273e7bd 100644 --- a/mm/kfence/kfence.h +++ b/mm/kfence/kfence.h @@ -29,7 +29,7 @@ * canary of every 8 bytes is the same. 64-bit memory can be filled and checked * at a time instead of byte by byte to improve performance. */ -#define KFENCE_CANARY_PATTERN_U64 ((u64)0xaaaaaaaaaaaaaaaa ^ (u64)(0x0706050403020100)) +#define KFENCE_CANARY_PATTERN_U64 ((u64)0xaaaaaaaaaaaaaaaa ^ (u64)(le64_to_cpu(0x0706050403020100))) /* Maximum stack depth for reports. */ #define KFENCE_STACK_DEPTH 64 diff --git a/mm/shrinker_debug.c b/mm/shrinker_debug.c index 3f83b10c5031..fe10436d9911 100644 --- a/mm/shrinker_debug.c +++ b/mm/shrinker_debug.c @@ -237,7 +237,8 @@ int shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...) } EXPORT_SYMBOL(shrinker_debugfs_rename); -struct dentry *shrinker_debugfs_remove(struct shrinker *shrinker) +struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker, + int *debugfs_id) { struct dentry *entry = shrinker->debugfs_entry; @@ -246,14 +247,18 @@ struct dentry *shrinker_debugfs_remove(struct shrinker *shrinker) kfree_const(shrinker->name); shrinker->name = NULL; - if (entry) { - ida_free(&shrinker_debugfs_ida, shrinker->debugfs_id); - shrinker->debugfs_entry = NULL; - } + *debugfs_id = entry ? shrinker->debugfs_id : -1; + shrinker->debugfs_entry = NULL; return entry; } +void shrinker_debugfs_remove(struct dentry *debugfs_entry, int debugfs_id) +{ + debugfs_remove_recursive(debugfs_entry); + ida_free(&shrinker_debugfs_ida, debugfs_id); +} + static int __init shrinker_debugfs_init(void) { struct shrinker *shrinker; diff --git a/mm/vmscan.c b/mm/vmscan.c index d257916f39e5..6d0cd2840cf0 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -805,6 +805,7 @@ EXPORT_SYMBOL(register_shrinker); void unregister_shrinker(struct shrinker *shrinker) { struct dentry *debugfs_entry; + int debugfs_id; if (!(shrinker->flags & SHRINKER_REGISTERED)) return; @@ -814,13 +815,13 @@ void unregister_shrinker(struct shrinker *shrinker) shrinker->flags &= ~SHRINKER_REGISTERED; if (shrinker->flags & SHRINKER_MEMCG_AWARE) unregister_memcg_shrinker(shrinker); - debugfs_entry = shrinker_debugfs_remove(shrinker); + debugfs_entry = shrinker_debugfs_detach(shrinker, &debugfs_id); mutex_unlock(&shrinker_mutex); atomic_inc(&shrinker_srcu_generation); synchronize_srcu(&shrinker_srcu); - debugfs_remove_recursive(debugfs_entry); + shrinker_debugfs_remove(debugfs_entry, debugfs_id); kfree(shrinker->nr_deferred); shrinker->nr_deferred = NULL; diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 44ddaf5d601e..02f7f414aade 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -1331,31 +1331,6 @@ void *zs_map_object(struct zs_pool *pool, unsigned long handle, obj_to_location(obj, &page, &obj_idx); zspage = get_zspage(page); -#ifdef CONFIG_ZPOOL - /* - * Move the zspage to front of pool's LRU. - * - * Note that this is swap-specific, so by definition there are no ongoing - * accesses to the memory while the page is swapped out that would make - * it "hot". A new entry is hot, then ages to the tail until it gets either - * written back or swaps back in. - * - * Furthermore, map is also called during writeback. We must not put an - * isolated page on the LRU mid-reclaim. - * - * As a result, only update the LRU when the page is mapped for write - * when it's first instantiated. - * - * This is a deviation from the other backends, which perform this update - * in the allocation function (zbud_alloc, z3fold_alloc). - */ - if (mm == ZS_MM_WO) { - if (!list_empty(&zspage->lru)) - list_del(&zspage->lru); - list_add(&zspage->lru, &pool->lru); - } -#endif - /* * migration cannot move any zpages in this zspage. Here, pool->lock * is too heavy since callers would take some time until they calls @@ -1525,9 +1500,8 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size, gfp_t gfp) fix_fullness_group(class, zspage); record_obj(handle, obj); class_stat_inc(class, ZS_OBJS_INUSE, 1); - spin_unlock(&pool->lock); - return handle; + goto out; } spin_unlock(&pool->lock); @@ -1550,6 +1524,14 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size, gfp_t gfp) /* We completely set up zspage so mark them as movable */ SetZsPageMovable(pool, zspage); +out: +#ifdef CONFIG_ZPOOL + /* Add/move zspage to beginning of LRU */ + if (!list_empty(&zspage->lru)) + list_del(&zspage->lru); + list_add(&zspage->lru, &pool->lru); +#endif + spin_unlock(&pool->lock); return handle; diff --git a/mm/zswap.c b/mm/zswap.c index e1e621d0b6a0..59da2a415fbb 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -1020,6 +1020,22 @@ static int zswap_writeback_entry(struct zpool *pool, unsigned long handle) goto fail; case ZSWAP_SWAPCACHE_NEW: /* page is locked */ + /* + * Having a local reference to the zswap entry doesn't exclude + * swapping from invalidating and recycling the swap slot. Once + * the swapcache is secured against concurrent swapping to and + * from the slot, recheck that the entry is still current before + * writing. + */ + spin_lock(&tree->lock); + if (zswap_rb_search(&tree->rbroot, entry->offset) != entry) { + spin_unlock(&tree->lock); + delete_from_swap_cache(page_folio(page)); + ret = -ENOMEM; + goto fail; + } + spin_unlock(&tree->lock); + /* decompress */ acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx); dlen = PAGE_SIZE; diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 640b951bf40a..f75ef12f18f7 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -1083,8 +1083,28 @@ static void hci_conn_unlink(struct hci_conn *conn) if (!conn->parent) { struct hci_link *link, *t; - list_for_each_entry_safe(link, t, &conn->link_list, list) - hci_conn_unlink(link->conn); + list_for_each_entry_safe(link, t, &conn->link_list, list) { + struct hci_conn *child = link->conn; + + hci_conn_unlink(child); + + /* If hdev is down it means + * hci_dev_close_sync/hci_conn_hash_flush is in progress + * and links don't need to be cleanup as all connections + * would be cleanup. + */ + if (!test_bit(HCI_UP, &hdev->flags)) + continue; + + /* Due to race, SCO connection might be not established + * yet at this point. Delete it now, otherwise it is + * possible for it to be stuck and can't be deleted. + */ + if ((child->type == SCO_LINK || + child->type == ESCO_LINK) && + child->handle == HCI_CONN_HANDLE_UNSET) + hci_conn_del(child); + } return; } @@ -1092,35 +1112,30 @@ static void hci_conn_unlink(struct hci_conn *conn) if (!conn->link) return; - hci_conn_put(conn->parent); - conn->parent = NULL; - list_del_rcu(&conn->link->list); synchronize_rcu(); + hci_conn_drop(conn->parent); + hci_conn_put(conn->parent); + conn->parent = NULL; + kfree(conn->link); conn->link = NULL; - - /* Due to race, SCO connection might be not established - * yet at this point. Delete it now, otherwise it is - * possible for it to be stuck and can't be deleted. - */ - if (conn->handle == HCI_CONN_HANDLE_UNSET) - hci_conn_del(conn); } -int hci_conn_del(struct hci_conn *conn) +void hci_conn_del(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; BT_DBG("%s hcon %p handle %d", hdev->name, conn, conn->handle); + hci_conn_unlink(conn); + cancel_delayed_work_sync(&conn->disc_work); cancel_delayed_work_sync(&conn->auto_accept_work); cancel_delayed_work_sync(&conn->idle_work); if (conn->type == ACL_LINK) { - hci_conn_unlink(conn); /* Unacked frames */ hdev->acl_cnt += conn->sent; } else if (conn->type == LE_LINK) { @@ -1131,13 +1146,6 @@ int hci_conn_del(struct hci_conn *conn) else hdev->acl_cnt += conn->sent; } else { - struct hci_conn *acl = conn->parent; - - if (acl) { - hci_conn_unlink(conn); - hci_conn_drop(acl); - } - /* Unacked ISO frames */ if (conn->type == ISO_LINK) { if (hdev->iso_pkts) @@ -1160,8 +1168,6 @@ int hci_conn_del(struct hci_conn *conn) * rest of hci_conn_del. */ hci_conn_cleanup(conn); - - return 0; } struct hci_dev *hci_get_route(bdaddr_t *dst, bdaddr_t *src, uint8_t src_type) @@ -2462,22 +2468,21 @@ timer: /* Drop all connection on the device */ void hci_conn_hash_flush(struct hci_dev *hdev) { - struct hci_conn_hash *h = &hdev->conn_hash; - struct hci_conn *c, *n; + struct list_head *head = &hdev->conn_hash.list; + struct hci_conn *conn; BT_DBG("hdev %s", hdev->name); - list_for_each_entry_safe(c, n, &h->list, list) { - c->state = BT_CLOSED; - - hci_disconn_cfm(c, HCI_ERROR_LOCAL_HOST_TERM); - - /* Unlink before deleting otherwise it is possible that - * hci_conn_del removes the link which may cause the list to - * contain items already freed. - */ - hci_conn_unlink(c); - hci_conn_del(c); + /* We should not traverse the list here, because hci_conn_del + * can remove extra links, which may cause the list traversal + * to hit items that have already been released. + */ + while ((conn = list_first_entry_or_null(head, + struct hci_conn, + list)) != NULL) { + conn->state = BT_CLOSED; + hci_disconn_cfm(conn, HCI_ERROR_LOCAL_HOST_TERM); + hci_conn_del(conn); } } diff --git a/net/can/j1939/main.c b/net/can/j1939/main.c index 821d4ff303b3..ecff1c947d68 100644 --- a/net/can/j1939/main.c +++ b/net/can/j1939/main.c @@ -126,7 +126,7 @@ static void j1939_can_recv(struct sk_buff *iskb, void *data) #define J1939_CAN_ID CAN_EFF_FLAG #define J1939_CAN_MASK (CAN_EFF_FLAG | CAN_RTR_FLAG) -static DEFINE_SPINLOCK(j1939_netdev_lock); +static DEFINE_MUTEX(j1939_netdev_lock); static struct j1939_priv *j1939_priv_create(struct net_device *ndev) { @@ -220,7 +220,7 @@ static void __j1939_rx_release(struct kref *kref) j1939_can_rx_unregister(priv); j1939_ecu_unmap_all(priv); j1939_priv_set(priv->ndev, NULL); - spin_unlock(&j1939_netdev_lock); + mutex_unlock(&j1939_netdev_lock); } /* get pointer to priv without increasing ref counter */ @@ -248,9 +248,9 @@ static struct j1939_priv *j1939_priv_get_by_ndev(struct net_device *ndev) { struct j1939_priv *priv; - spin_lock(&j1939_netdev_lock); + mutex_lock(&j1939_netdev_lock); priv = j1939_priv_get_by_ndev_locked(ndev); - spin_unlock(&j1939_netdev_lock); + mutex_unlock(&j1939_netdev_lock); return priv; } @@ -260,14 +260,14 @@ struct j1939_priv *j1939_netdev_start(struct net_device *ndev) struct j1939_priv *priv, *priv_new; int ret; - spin_lock(&j1939_netdev_lock); + mutex_lock(&j1939_netdev_lock); priv = j1939_priv_get_by_ndev_locked(ndev); if (priv) { kref_get(&priv->rx_kref); - spin_unlock(&j1939_netdev_lock); + mutex_unlock(&j1939_netdev_lock); return priv; } - spin_unlock(&j1939_netdev_lock); + mutex_unlock(&j1939_netdev_lock); priv = j1939_priv_create(ndev); if (!priv) @@ -277,29 +277,31 @@ struct j1939_priv *j1939_netdev_start(struct net_device *ndev) spin_lock_init(&priv->j1939_socks_lock); INIT_LIST_HEAD(&priv->j1939_socks); - spin_lock(&j1939_netdev_lock); + mutex_lock(&j1939_netdev_lock); priv_new = j1939_priv_get_by_ndev_locked(ndev); if (priv_new) { /* Someone was faster than us, use their priv and roll * back our's. */ kref_get(&priv_new->rx_kref); - spin_unlock(&j1939_netdev_lock); + mutex_unlock(&j1939_netdev_lock); dev_put(ndev); kfree(priv); return priv_new; } j1939_priv_set(ndev, priv); - spin_unlock(&j1939_netdev_lock); ret = j1939_can_rx_register(priv); if (ret < 0) goto out_priv_put; + mutex_unlock(&j1939_netdev_lock); return priv; out_priv_put: j1939_priv_set(ndev, NULL); + mutex_unlock(&j1939_netdev_lock); + dev_put(ndev); kfree(priv); @@ -308,7 +310,7 @@ struct j1939_priv *j1939_netdev_start(struct net_device *ndev) void j1939_netdev_stop(struct j1939_priv *priv) { - kref_put_lock(&priv->rx_kref, __j1939_rx_release, &j1939_netdev_lock); + kref_put_mutex(&priv->rx_kref, __j1939_rx_release, &j1939_netdev_lock); j1939_priv_put(priv); } diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c index 1790469b2580..35970c25496a 100644 --- a/net/can/j1939/socket.c +++ b/net/can/j1939/socket.c @@ -1088,6 +1088,11 @@ void j1939_sk_errqueue(struct j1939_session *session, void j1939_sk_send_loop_abort(struct sock *sk, int err) { + struct j1939_sock *jsk = j1939_sk(sk); + + if (jsk->state & J1939_SOCK_ERRQUEUE) + return; + sk->sk_err = err; sk_error_report(sk); diff --git a/net/core/page_pool.c b/net/core/page_pool.c index e212e9d7edcb..a3e12a61d456 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -134,6 +134,29 @@ EXPORT_SYMBOL(page_pool_ethtool_stats_get); #define recycle_stat_add(pool, __stat, val) #endif +static bool page_pool_producer_lock(struct page_pool *pool) + __acquires(&pool->ring.producer_lock) +{ + bool in_softirq = in_softirq(); + + if (in_softirq) + spin_lock(&pool->ring.producer_lock); + else + spin_lock_bh(&pool->ring.producer_lock); + + return in_softirq; +} + +static void page_pool_producer_unlock(struct page_pool *pool, + bool in_softirq) + __releases(&pool->ring.producer_lock) +{ + if (in_softirq) + spin_unlock(&pool->ring.producer_lock); + else + spin_unlock_bh(&pool->ring.producer_lock); +} + static int page_pool_init(struct page_pool *pool, const struct page_pool_params *params) { @@ -617,6 +640,7 @@ void page_pool_put_page_bulk(struct page_pool *pool, void **data, int count) { int i, bulk_len = 0; + bool in_softirq; for (i = 0; i < count; i++) { struct page *page = virt_to_head_page(data[i]); @@ -635,7 +659,7 @@ void page_pool_put_page_bulk(struct page_pool *pool, void **data, return; /* Bulk producer into ptr_ring page_pool cache */ - page_pool_ring_lock(pool); + in_softirq = page_pool_producer_lock(pool); for (i = 0; i < bulk_len; i++) { if (__ptr_ring_produce(&pool->ring, data[i])) { /* ring full */ @@ -644,7 +668,7 @@ void page_pool_put_page_bulk(struct page_pool *pool, void **data, } } recycle_stat_add(pool, ring, i); - page_pool_ring_unlock(pool); + page_pool_producer_unlock(pool, in_softirq); /* Hopefully all pages was return into ptr_ring */ if (likely(i == bulk_len)) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 653901a1bf75..41de3a2f29e1 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2385,6 +2385,37 @@ static int validate_linkmsg(struct net_device *dev, struct nlattr *tb[], if (tb[IFLA_BROADCAST] && nla_len(tb[IFLA_BROADCAST]) < dev->addr_len) return -EINVAL; + + if (tb[IFLA_GSO_MAX_SIZE] && + nla_get_u32(tb[IFLA_GSO_MAX_SIZE]) > dev->tso_max_size) { + NL_SET_ERR_MSG(extack, "too big gso_max_size"); + return -EINVAL; + } + + if (tb[IFLA_GSO_MAX_SEGS] && + (nla_get_u32(tb[IFLA_GSO_MAX_SEGS]) > GSO_MAX_SEGS || + nla_get_u32(tb[IFLA_GSO_MAX_SEGS]) > dev->tso_max_segs)) { + NL_SET_ERR_MSG(extack, "too big gso_max_segs"); + return -EINVAL; + } + + if (tb[IFLA_GRO_MAX_SIZE] && + nla_get_u32(tb[IFLA_GRO_MAX_SIZE]) > GRO_MAX_SIZE) { + NL_SET_ERR_MSG(extack, "too big gro_max_size"); + return -EINVAL; + } + + if (tb[IFLA_GSO_IPV4_MAX_SIZE] && + nla_get_u32(tb[IFLA_GSO_IPV4_MAX_SIZE]) > dev->tso_max_size) { + NL_SET_ERR_MSG(extack, "too big gso_ipv4_max_size"); + return -EINVAL; + } + + if (tb[IFLA_GRO_IPV4_MAX_SIZE] && + nla_get_u32(tb[IFLA_GRO_IPV4_MAX_SIZE]) > GRO_MAX_SIZE) { + NL_SET_ERR_MSG(extack, "too big gro_ipv4_max_size"); + return -EINVAL; + } } if (tb[IFLA_AF_SPEC]) { @@ -2858,11 +2889,6 @@ static int do_setlink(const struct sk_buff *skb, if (tb[IFLA_GSO_MAX_SIZE]) { u32 max_size = nla_get_u32(tb[IFLA_GSO_MAX_SIZE]); - if (max_size > dev->tso_max_size) { - err = -EINVAL; - goto errout; - } - if (dev->gso_max_size ^ max_size) { netif_set_gso_max_size(dev, max_size); status |= DO_SETLINK_MODIFIED; @@ -2872,11 +2898,6 @@ static int do_setlink(const struct sk_buff *skb, if (tb[IFLA_GSO_MAX_SEGS]) { u32 max_segs = nla_get_u32(tb[IFLA_GSO_MAX_SEGS]); - if (max_segs > GSO_MAX_SEGS || max_segs > dev->tso_max_segs) { - err = -EINVAL; - goto errout; - } - if (dev->gso_max_segs ^ max_segs) { netif_set_gso_max_segs(dev, max_segs); status |= DO_SETLINK_MODIFIED; @@ -2895,11 +2916,6 @@ static int do_setlink(const struct sk_buff *skb, if (tb[IFLA_GSO_IPV4_MAX_SIZE]) { u32 max_size = nla_get_u32(tb[IFLA_GSO_IPV4_MAX_SIZE]); - if (max_size > dev->tso_max_size) { - err = -EINVAL; - goto errout; - } - if (dev->gso_ipv4_max_size ^ max_size) { netif_set_gso_ipv4_max_size(dev, max_size); status |= DO_SETLINK_MODIFIED; @@ -3285,6 +3301,7 @@ struct net_device *rtnl_create_link(struct net *net, const char *ifname, struct net_device *dev; unsigned int num_tx_queues = 1; unsigned int num_rx_queues = 1; + int err; if (tb[IFLA_NUM_TX_QUEUES]) num_tx_queues = nla_get_u32(tb[IFLA_NUM_TX_QUEUES]); @@ -3320,13 +3337,18 @@ struct net_device *rtnl_create_link(struct net *net, const char *ifname, if (!dev) return ERR_PTR(-ENOMEM); + err = validate_linkmsg(dev, tb, extack); + if (err < 0) { + free_netdev(dev); + return ERR_PTR(err); + } + dev_net_set(dev, net); dev->rtnl_link_ops = ops; dev->rtnl_link_state = RTNL_LINK_INITIALIZING; if (tb[IFLA_MTU]) { u32 mtu = nla_get_u32(tb[IFLA_MTU]); - int err; err = dev_validate_mtu(dev, mtu, extack); if (err) { diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 515ec5cdc79c..cea28d30abb5 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -5224,8 +5224,10 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb, } else { skb = skb_clone(orig_skb, GFP_ATOMIC); - if (skb_orphan_frags_rx(skb, GFP_ATOMIC)) + if (skb_orphan_frags_rx(skb, GFP_ATOMIC)) { + kfree_skb(skb); return; + } } if (!skb) return; diff --git a/net/core/skmsg.c b/net/core/skmsg.c index f81883759d38..a9060e1f0e43 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -481,8 +481,6 @@ int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, msg_rx = sk_psock_peek_msg(psock); } out: - if (psock->work_state.skb && copied > 0) - schedule_work(&psock->work); return copied; } EXPORT_SYMBOL_GPL(sk_msg_recvmsg); @@ -624,42 +622,33 @@ static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb, static void sk_psock_skb_state(struct sk_psock *psock, struct sk_psock_work_state *state, - struct sk_buff *skb, int len, int off) { spin_lock_bh(&psock->ingress_lock); if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) { - state->skb = skb; state->len = len; state->off = off; - } else { - sock_drop(psock->sk, skb); } spin_unlock_bh(&psock->ingress_lock); } static void sk_psock_backlog(struct work_struct *work) { - struct sk_psock *psock = container_of(work, struct sk_psock, work); + struct delayed_work *dwork = to_delayed_work(work); + struct sk_psock *psock = container_of(dwork, struct sk_psock, work); struct sk_psock_work_state *state = &psock->work_state; struct sk_buff *skb = NULL; + u32 len = 0, off = 0; bool ingress; - u32 len, off; int ret; mutex_lock(&psock->work_mutex); - if (unlikely(state->skb)) { - spin_lock_bh(&psock->ingress_lock); - skb = state->skb; + if (unlikely(state->len)) { len = state->len; off = state->off; - state->skb = NULL; - spin_unlock_bh(&psock->ingress_lock); } - if (skb) - goto start; - while ((skb = skb_dequeue(&psock->ingress_skb))) { + while ((skb = skb_peek(&psock->ingress_skb))) { len = skb->len; off = 0; if (skb_bpf_strparser(skb)) { @@ -668,7 +657,6 @@ static void sk_psock_backlog(struct work_struct *work) off = stm->offset; len = stm->full_len; } -start: ingress = skb_bpf_ingress(skb); skb_bpf_redirect_clear(skb); do { @@ -678,22 +666,28 @@ start: len, ingress); if (ret <= 0) { if (ret == -EAGAIN) { - sk_psock_skb_state(psock, state, skb, - len, off); + sk_psock_skb_state(psock, state, len, off); + + /* Delay slightly to prioritize any + * other work that might be here. + */ + if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) + schedule_delayed_work(&psock->work, 1); goto end; } /* Hard errors break pipe and stop xmit. */ sk_psock_report_error(psock, ret ? -ret : EPIPE); sk_psock_clear_state(psock, SK_PSOCK_TX_ENABLED); - sock_drop(psock->sk, skb); goto end; } off += ret; len -= ret; } while (len); - if (!ingress) + skb = skb_dequeue(&psock->ingress_skb); + if (!ingress) { kfree_skb(skb); + } } end: mutex_unlock(&psock->work_mutex); @@ -734,7 +728,7 @@ struct sk_psock *sk_psock_init(struct sock *sk, int node) INIT_LIST_HEAD(&psock->link); spin_lock_init(&psock->link_lock); - INIT_WORK(&psock->work, sk_psock_backlog); + INIT_DELAYED_WORK(&psock->work, sk_psock_backlog); mutex_init(&psock->work_mutex); INIT_LIST_HEAD(&psock->ingress_msg); spin_lock_init(&psock->ingress_lock); @@ -786,11 +780,6 @@ static void __sk_psock_zap_ingress(struct sk_psock *psock) skb_bpf_redirect_clear(skb); sock_drop(psock->sk, skb); } - kfree_skb(psock->work_state.skb); - /* We null the skb here to ensure that calls to sk_psock_backlog - * do not pick up the free'd skb. - */ - psock->work_state.skb = NULL; __sk_psock_purge_ingress_msg(psock); } @@ -809,7 +798,6 @@ void sk_psock_stop(struct sk_psock *psock) spin_lock_bh(&psock->ingress_lock); sk_psock_clear_state(psock, SK_PSOCK_TX_ENABLED); sk_psock_cork_free(psock); - __sk_psock_zap_ingress(psock); spin_unlock_bh(&psock->ingress_lock); } @@ -823,7 +811,8 @@ static void sk_psock_destroy(struct work_struct *work) sk_psock_done_strp(psock); - cancel_work_sync(&psock->work); + cancel_delayed_work_sync(&psock->work); + __sk_psock_zap_ingress(psock); mutex_destroy(&psock->work_mutex); psock_progs_drop(&psock->progs); @@ -938,7 +927,7 @@ static int sk_psock_skb_redirect(struct sk_psock *from, struct sk_buff *skb) } skb_queue_tail(&psock_other->ingress_skb, skb); - schedule_work(&psock_other->work); + schedule_delayed_work(&psock_other->work, 0); spin_unlock_bh(&psock_other->ingress_lock); return 0; } @@ -990,10 +979,8 @@ static int sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb, err = -EIO; sk_other = psock->sk; if (sock_flag(sk_other, SOCK_DEAD) || - !sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) { - skb_bpf_redirect_clear(skb); + !sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) goto out_free; - } skb_bpf_set_ingress(skb); @@ -1018,22 +1005,23 @@ static int sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb, spin_lock_bh(&psock->ingress_lock); if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) { skb_queue_tail(&psock->ingress_skb, skb); - schedule_work(&psock->work); + schedule_delayed_work(&psock->work, 0); err = 0; } spin_unlock_bh(&psock->ingress_lock); - if (err < 0) { - skb_bpf_redirect_clear(skb); + if (err < 0) goto out_free; - } } break; case __SK_REDIRECT: + tcp_eat_skb(psock->sk, skb); err = sk_psock_skb_redirect(psock, skb); break; case __SK_DROP: default: out_free: + skb_bpf_redirect_clear(skb); + tcp_eat_skb(psock->sk, skb); sock_drop(psock->sk, skb); } @@ -1049,7 +1037,7 @@ static void sk_psock_write_space(struct sock *sk) psock = sk_psock(sk); if (likely(psock)) { if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) - schedule_work(&psock->work); + schedule_delayed_work(&psock->work, 0); write_space = psock->saved_write_space; } rcu_read_unlock(); @@ -1078,8 +1066,7 @@ static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb) skb_dst_drop(skb); skb_bpf_redirect_clear(skb); ret = bpf_prog_run_pin_on_cpu(prog, skb); - if (ret == SK_PASS) - skb_bpf_set_strparser(skb); + skb_bpf_set_strparser(skb); ret = sk_psock_map_verd(ret, skb_bpf_redirect_fetch(skb)); skb->sk = NULL; } @@ -1183,12 +1170,11 @@ static int sk_psock_verdict_recv(struct sock *sk, struct sk_buff *skb) int ret = __SK_DROP; int len = skb->len; - skb_get(skb); - rcu_read_lock(); psock = sk_psock(sk); if (unlikely(!psock)) { len = 0; + tcp_eat_skb(sk, skb); sock_drop(sk, skb); goto out; } @@ -1212,12 +1198,21 @@ out: static void sk_psock_verdict_data_ready(struct sock *sk) { struct socket *sock = sk->sk_socket; + int copied; trace_sk_data_ready(sk); if (unlikely(!sock || !sock->ops || !sock->ops->read_skb)) return; - sock->ops->read_skb(sk, sk_psock_verdict_recv); + copied = sock->ops->read_skb(sk, sk_psock_verdict_recv); + if (copied >= 0) { + struct sk_psock *psock; + + rcu_read_lock(); + psock = sk_psock(sk); + psock->saved_data_ready(sk); + rcu_read_unlock(); + } } void sk_psock_start_verdict(struct sock *sk, struct sk_psock *psock) diff --git a/net/core/sock.c b/net/core/sock.c index 5440e67bcfe3..24f2761bdb1d 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2381,7 +2381,6 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst) { u32 max_segs = 1; - sk_dst_set(sk, dst); sk->sk_route_caps = dst->dev->features; if (sk_is_tcp(sk)) sk->sk_route_caps |= NETIF_F_GSO; @@ -2400,6 +2399,7 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst) } } sk->sk_gso_max_segs = max_segs; + sk_dst_set(sk, dst); } EXPORT_SYMBOL_GPL(sk_setup_caps); diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 7c189c2e2fbf..00afb66cd095 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -1644,9 +1644,10 @@ void sock_map_close(struct sock *sk, long timeout) rcu_read_unlock(); sk_psock_stop(psock); release_sock(sk); - cancel_work_sync(&psock->work); + cancel_delayed_work_sync(&psock->work); sk_psock_put(sk, psock); } + /* Make sure we do not recurse. This is a bug. * Leak the socket instead of crashing on a stack overflow. */ diff --git a/net/handshake/handshake-test.c b/net/handshake/handshake-test.c index e6adc5dec11a..6d37bab35c8f 100644 --- a/net/handshake/handshake-test.c +++ b/net/handshake/handshake-test.c @@ -102,7 +102,7 @@ struct handshake_req_alloc_test_param handshake_req_alloc_params[] = { { .desc = "handshake_req_alloc excessive privsize", .proto = &handshake_req_alloc_proto_6, - .gfp = GFP_KERNEL, + .gfp = GFP_KERNEL | __GFP_NOWARN, .expect_success = false, }, { @@ -209,6 +209,7 @@ static void handshake_req_submit_test4(struct kunit *test) { struct handshake_req *req, *result; struct socket *sock; + struct file *filp; int err; /* Arrange */ @@ -218,9 +219,10 @@ static void handshake_req_submit_test4(struct kunit *test) err = __sock_create(&init_net, PF_INET, SOCK_STREAM, IPPROTO_TCP, &sock, 1); KUNIT_ASSERT_EQ(test, err, 0); - sock->file = sock_alloc_file(sock, O_NONBLOCK, NULL); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, sock->file); + filp = sock_alloc_file(sock, O_NONBLOCK, NULL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, filp); KUNIT_ASSERT_NOT_NULL(test, sock->sk); + sock->file = filp; err = handshake_req_submit(sock, req, GFP_KERNEL); KUNIT_ASSERT_EQ(test, err, 0); @@ -241,6 +243,7 @@ static void handshake_req_submit_test5(struct kunit *test) struct handshake_req *req; struct handshake_net *hn; struct socket *sock; + struct file *filp; struct net *net; int saved, err; @@ -251,9 +254,10 @@ static void handshake_req_submit_test5(struct kunit *test) err = __sock_create(&init_net, PF_INET, SOCK_STREAM, IPPROTO_TCP, &sock, 1); KUNIT_ASSERT_EQ(test, err, 0); - sock->file = sock_alloc_file(sock, O_NONBLOCK, NULL); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, sock->file); + filp = sock_alloc_file(sock, O_NONBLOCK, NULL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, filp); KUNIT_ASSERT_NOT_NULL(test, sock->sk); + sock->file = filp; net = sock_net(sock->sk); hn = handshake_pernet(net); @@ -276,6 +280,7 @@ static void handshake_req_submit_test6(struct kunit *test) { struct handshake_req *req1, *req2; struct socket *sock; + struct file *filp; int err; /* Arrange */ @@ -287,9 +292,10 @@ static void handshake_req_submit_test6(struct kunit *test) err = __sock_create(&init_net, PF_INET, SOCK_STREAM, IPPROTO_TCP, &sock, 1); KUNIT_ASSERT_EQ(test, err, 0); - sock->file = sock_alloc_file(sock, O_NONBLOCK, NULL); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, sock->file); + filp = sock_alloc_file(sock, O_NONBLOCK, NULL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, filp); KUNIT_ASSERT_NOT_NULL(test, sock->sk); + sock->file = filp; /* Act */ err = handshake_req_submit(sock, req1, GFP_KERNEL); @@ -307,6 +313,7 @@ static void handshake_req_cancel_test1(struct kunit *test) { struct handshake_req *req; struct socket *sock; + struct file *filp; bool result; int err; @@ -318,8 +325,9 @@ static void handshake_req_cancel_test1(struct kunit *test) &sock, 1); KUNIT_ASSERT_EQ(test, err, 0); - sock->file = sock_alloc_file(sock, O_NONBLOCK, NULL); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, sock->file); + filp = sock_alloc_file(sock, O_NONBLOCK, NULL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, filp); + sock->file = filp; err = handshake_req_submit(sock, req, GFP_KERNEL); KUNIT_ASSERT_EQ(test, err, 0); @@ -340,6 +348,7 @@ static void handshake_req_cancel_test2(struct kunit *test) struct handshake_req *req, *next; struct handshake_net *hn; struct socket *sock; + struct file *filp; struct net *net; bool result; int err; @@ -352,8 +361,9 @@ static void handshake_req_cancel_test2(struct kunit *test) &sock, 1); KUNIT_ASSERT_EQ(test, err, 0); - sock->file = sock_alloc_file(sock, O_NONBLOCK, NULL); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, sock->file); + filp = sock_alloc_file(sock, O_NONBLOCK, NULL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, filp); + sock->file = filp; err = handshake_req_submit(sock, req, GFP_KERNEL); KUNIT_ASSERT_EQ(test, err, 0); @@ -380,6 +390,7 @@ static void handshake_req_cancel_test3(struct kunit *test) struct handshake_req *req, *next; struct handshake_net *hn; struct socket *sock; + struct file *filp; struct net *net; bool result; int err; @@ -392,8 +403,9 @@ static void handshake_req_cancel_test3(struct kunit *test) &sock, 1); KUNIT_ASSERT_EQ(test, err, 0); - sock->file = sock_alloc_file(sock, O_NONBLOCK, NULL); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, sock->file); + filp = sock_alloc_file(sock, O_NONBLOCK, NULL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, filp); + sock->file = filp; err = handshake_req_submit(sock, req, GFP_KERNEL); KUNIT_ASSERT_EQ(test, err, 0); @@ -436,6 +448,7 @@ static void handshake_req_destroy_test1(struct kunit *test) { struct handshake_req *req; struct socket *sock; + struct file *filp; int err; /* Arrange */ @@ -448,8 +461,9 @@ static void handshake_req_destroy_test1(struct kunit *test) &sock, 1); KUNIT_ASSERT_EQ(test, err, 0); - sock->file = sock_alloc_file(sock, O_NONBLOCK, NULL); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, sock->file); + filp = sock_alloc_file(sock, O_NONBLOCK, NULL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, filp); + sock->file = filp; err = handshake_req_submit(sock, req, GFP_KERNEL); KUNIT_ASSERT_EQ(test, err, 0); diff --git a/net/handshake/handshake.h b/net/handshake/handshake.h index 4dac965c99df..8aeaadca844f 100644 --- a/net/handshake/handshake.h +++ b/net/handshake/handshake.h @@ -31,6 +31,7 @@ struct handshake_req { struct list_head hr_list; struct rhash_head hr_rhash; unsigned long hr_flags; + struct file *hr_file; const struct handshake_proto *hr_proto; struct sock *hr_sk; void (*hr_odestruct)(struct sock *sk); diff --git a/net/handshake/netlink.c b/net/handshake/netlink.c index 35c9c445e0b8..1086653e1fad 100644 --- a/net/handshake/netlink.c +++ b/net/handshake/netlink.c @@ -48,7 +48,7 @@ int handshake_genl_notify(struct net *net, const struct handshake_proto *proto, proto->hp_handler_class)) return -ESRCH; - msg = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); + msg = genlmsg_new(GENLMSG_DEFAULT_SIZE, flags); if (!msg) return -ENOMEM; @@ -99,9 +99,6 @@ static int handshake_dup(struct socket *sock) struct file *file; int newfd; - if (!sock->file) - return -EBADF; - file = get_file(sock->file); newfd = get_unused_fd_flags(O_CLOEXEC); if (newfd < 0) { @@ -142,15 +139,16 @@ int handshake_nl_accept_doit(struct sk_buff *skb, struct genl_info *info) goto out_complete; } err = req->hr_proto->hp_accept(req, info, fd); - if (err) + if (err) { + fput(sock->file); goto out_complete; + } trace_handshake_cmd_accept(net, req, req->hr_sk, fd); return 0; out_complete: handshake_complete(req, -EIO, NULL); - fput(sock->file); out_status: trace_handshake_cmd_accept_err(net, req, NULL, err); return err; @@ -159,8 +157,8 @@ out_status: int handshake_nl_done_doit(struct sk_buff *skb, struct genl_info *info) { struct net *net = sock_net(skb->sk); + struct handshake_req *req = NULL; struct socket *sock = NULL; - struct handshake_req *req; int fd, status, err; if (GENL_REQ_ATTR_CHECK(info, HANDSHAKE_A_DONE_SOCKFD)) diff --git a/net/handshake/request.c b/net/handshake/request.c index 94d5cef3e048..d78d41abb3d9 100644 --- a/net/handshake/request.c +++ b/net/handshake/request.c @@ -239,6 +239,7 @@ int handshake_req_submit(struct socket *sock, struct handshake_req *req, } req->hr_odestruct = req->hr_sk->sk_destruct; req->hr_sk->sk_destruct = handshake_sk_destruct; + req->hr_file = sock->file; ret = -EOPNOTSUPP; net = sock_net(req->hr_sk); @@ -334,6 +335,9 @@ bool handshake_req_cancel(struct sock *sk) return false; } + /* Request accepted and waiting for DONE */ + fput(req->hr_file); + out_true: trace_handshake_cancel(net, req, sk); diff --git a/net/handshake/tlshd.c b/net/handshake/tlshd.c index fcbeb63b4eb1..b735f5cced2f 100644 --- a/net/handshake/tlshd.c +++ b/net/handshake/tlshd.c @@ -31,6 +31,7 @@ struct tls_handshake_req { int th_type; unsigned int th_timeout_ms; int th_auth_mode; + const char *th_peername; key_serial_t th_keyring; key_serial_t th_certificate; key_serial_t th_privkey; @@ -48,6 +49,7 @@ tls_handshake_req_init(struct handshake_req *req, treq->th_timeout_ms = args->ta_timeout_ms; treq->th_consumer_done = args->ta_done; treq->th_consumer_data = args->ta_data; + treq->th_peername = args->ta_peername; treq->th_keyring = args->ta_keyring; treq->th_num_peerids = 0; treq->th_certificate = TLS_NO_CERT; @@ -214,6 +216,12 @@ static int tls_handshake_accept(struct handshake_req *req, ret = nla_put_u32(msg, HANDSHAKE_A_ACCEPT_MESSAGE_TYPE, treq->th_type); if (ret < 0) goto out_cancel; + if (treq->th_peername) { + ret = nla_put_string(msg, HANDSHAKE_A_ACCEPT_PEERNAME, + treq->th_peername); + if (ret < 0) + goto out_cancel; + } if (treq->th_timeout_ms) { ret = nla_put_u32(msg, HANDSHAKE_A_ACCEPT_TIMEOUT, treq->th_timeout_ms); if (ret < 0) diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index c4aab3aacbd8..4a76ebf793b8 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -586,6 +586,7 @@ static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias) add_wait_queue(sk_sleep(sk), &wait); sk->sk_write_pending += writebias; + sk->sk_wait_pending++; /* Basic assumption: if someone sets sk->sk_err, he _must_ * change state of the socket from TCP_SYN_*. @@ -601,6 +602,7 @@ static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias) } remove_wait_queue(sk_sleep(sk), &wait); sk->sk_write_pending -= writebias; + sk->sk_wait_pending--; return timeo; } diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 65ad4251f6fd..1386787eaf1a 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -1142,6 +1142,7 @@ struct sock *inet_csk_clone_lock(const struct sock *sk, if (newsk) { struct inet_connection_sock *newicsk = inet_csk(newsk); + newsk->sk_wait_pending = 0; inet_sk_set_state(newsk, TCP_SYN_RECV); newicsk->icsk_bind_hash = NULL; newicsk->icsk_bind2_hash = NULL; diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index b511ff0adc0a..8e97d8d4cc9d 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -317,7 +317,14 @@ int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc, ipc->tos = val; ipc->priority = rt_tos2priority(ipc->tos); break; - + case IP_PROTOCOL: + if (cmsg->cmsg_len != CMSG_LEN(sizeof(int))) + return -EINVAL; + val = *(int *)CMSG_DATA(cmsg); + if (val < 1 || val > 255) + return -EINVAL; + ipc->protocol = val; + break; default: return -EINVAL; } @@ -1761,6 +1768,9 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname, case IP_LOCAL_PORT_RANGE: val = inet->local_port_range.hi << 16 | inet->local_port_range.lo; break; + case IP_PROTOCOL: + val = inet_sk(sk)->inet_num; + break; default: sockopt_release_sock(sk); return -ENOPROTOOPT; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index ff712bf2a98d..eadf1c9ef7e4 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -532,6 +532,9 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) } ipcm_init_sk(&ipc, inet); + /* Keep backward compat */ + if (hdrincl) + ipc.protocol = IPPROTO_RAW; if (msg->msg_controllen) { err = ip_cmsg_send(sk, msg, &ipc, false); @@ -599,7 +602,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) flowi4_init_output(&fl4, ipc.oif, ipc.sockc.mark, tos, RT_SCOPE_UNIVERSE, - hdrincl ? IPPROTO_RAW : sk->sk_protocol, + hdrincl ? ipc.protocol : sk->sk_protocol, inet_sk_flowi_flags(sk) | (hdrincl ? FLOWI_FLAG_KNOWN_NH : 0), daddr, saddr, 0, 0, sk->sk_uid); diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 40fe70fc2015..88dfe51e68f3 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -34,8 +34,8 @@ static int ip_ttl_min = 1; static int ip_ttl_max = 255; static int tcp_syn_retries_min = 1; static int tcp_syn_retries_max = MAX_TCP_SYNCNT; -static int ip_ping_group_range_min[] = { 0, 0 }; -static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX }; +static unsigned long ip_ping_group_range_min[] = { 0, 0 }; +static unsigned long ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX }; static u32 u32_max_div_HZ = UINT_MAX / HZ; static int one_day_secs = 24 * 3600; static u32 fib_multipath_hash_fields_all_mask __maybe_unused = @@ -165,7 +165,7 @@ static int ipv4_ping_group_range(struct ctl_table *table, int write, { struct user_namespace *user_ns = current_user_ns(); int ret; - gid_t urange[2]; + unsigned long urange[2]; kgid_t low, high; struct ctl_table tmp = { .data = &urange, @@ -178,7 +178,7 @@ static int ipv4_ping_group_range(struct ctl_table *table, int write, inet_get_ping_group_range_table(table, &low, &high); urange[0] = from_kgid_munged(user_ns, low); urange[1] = from_kgid_munged(user_ns, high); - ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); + ret = proc_doulongvec_minmax(&tmp, write, buffer, lenp, ppos); if (write && ret == 0) { low = make_kgid(user_ns, urange[0]); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 4d6392c16b7a..8d20d9221238 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1571,7 +1571,7 @@ static int tcp_peek_sndq(struct sock *sk, struct msghdr *msg, int len) * calculation of whether or not we must ACK for the sake of * a window update. */ -static void __tcp_cleanup_rbuf(struct sock *sk, int copied) +void __tcp_cleanup_rbuf(struct sock *sk, int copied) { struct tcp_sock *tp = tcp_sk(sk); bool time_to_ack = false; @@ -1773,7 +1773,6 @@ int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor) WARN_ON_ONCE(!skb_set_owner_sk_safe(skb, sk)); tcp_flags = TCP_SKB_CB(skb)->tcp_flags; used = recv_actor(sk, skb); - consume_skb(skb); if (used < 0) { if (!copied) copied = used; @@ -1787,14 +1786,6 @@ int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor) break; } } - WRITE_ONCE(tp->copied_seq, seq); - - tcp_rcv_space_adjust(sk); - - /* Clean up data we have read: This will do ACK frames. */ - if (copied > 0) - __tcp_cleanup_rbuf(sk, copied); - return copied; } EXPORT_SYMBOL(tcp_read_skb); @@ -3090,6 +3081,12 @@ int tcp_disconnect(struct sock *sk, int flags) int old_state = sk->sk_state; u32 seq; + /* Deny disconnect if other threads are blocked in sk_wait_event() + * or inet_wait_for_connect(). + */ + if (sk->sk_wait_pending) + return -EBUSY; + if (old_state != TCP_CLOSE) tcp_set_state(sk, TCP_CLOSE); @@ -4081,7 +4078,8 @@ int do_tcp_getsockopt(struct sock *sk, int level, switch (optname) { case TCP_MAXSEG: val = tp->mss_cache; - if (!val && ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) + if (tp->rx_opt.user_mss && + ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) val = tp->rx_opt.user_mss; if (tp->repair) val = tp->rx_opt.mss_clamp; diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 2e9547467edb..5f93918c063c 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -11,6 +11,24 @@ #include <net/inet_common.h> #include <net/tls.h> +void tcp_eat_skb(struct sock *sk, struct sk_buff *skb) +{ + struct tcp_sock *tcp; + int copied; + + if (!skb || !skb->len || !sk_is_tcp(sk)) + return; + + if (skb_bpf_strparser(skb)) + return; + + tcp = tcp_sk(sk); + copied = tcp->copied_seq + skb->len; + WRITE_ONCE(tcp->copied_seq, copied); + tcp_rcv_space_adjust(sk); + __tcp_cleanup_rbuf(sk, skb->len); +} + static int bpf_tcp_ingress(struct sock *sk, struct sk_psock *psock, struct sk_msg *msg, u32 apply_bytes, int flags) { @@ -174,14 +192,34 @@ static int tcp_msg_wait_data(struct sock *sk, struct sk_psock *psock, return ret; } +static bool is_next_msg_fin(struct sk_psock *psock) +{ + struct scatterlist *sge; + struct sk_msg *msg_rx; + int i; + + msg_rx = sk_psock_peek_msg(psock); + i = msg_rx->sg.start; + sge = sk_msg_elem(msg_rx, i); + if (!sge->length) { + struct sk_buff *skb = msg_rx->skb; + + if (skb && TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) + return true; + } + return false; +} + static int tcp_bpf_recvmsg_parser(struct sock *sk, struct msghdr *msg, size_t len, int flags, int *addr_len) { + struct tcp_sock *tcp = tcp_sk(sk); + u32 seq = tcp->copied_seq; struct sk_psock *psock; - int copied; + int copied = 0; if (unlikely(flags & MSG_ERRQUEUE)) return inet_recv_error(sk, msg, len, addr_len); @@ -194,8 +232,43 @@ static int tcp_bpf_recvmsg_parser(struct sock *sk, return tcp_recvmsg(sk, msg, len, flags, addr_len); lock_sock(sk); + + /* We may have received data on the sk_receive_queue pre-accept and + * then we can not use read_skb in this context because we haven't + * assigned a sk_socket yet so have no link to the ops. The work-around + * is to check the sk_receive_queue and in these cases read skbs off + * queue again. The read_skb hook is not running at this point because + * of lock_sock so we avoid having multiple runners in read_skb. + */ + if (unlikely(!skb_queue_empty(&sk->sk_receive_queue))) { + tcp_data_ready(sk); + /* This handles the ENOMEM errors if we both receive data + * pre accept and are already under memory pressure. At least + * let user know to retry. + */ + if (unlikely(!skb_queue_empty(&sk->sk_receive_queue))) { + copied = -EAGAIN; + goto out; + } + } + msg_bytes_ready: copied = sk_msg_recvmsg(sk, psock, msg, len, flags); + /* The typical case for EFAULT is the socket was gracefully + * shutdown with a FIN pkt. So check here the other case is + * some error on copy_page_to_iter which would be unexpected. + * On fin return correct return code to zero. + */ + if (copied == -EFAULT) { + bool is_fin = is_next_msg_fin(psock); + + if (is_fin) { + copied = 0; + seq++; + goto out; + } + } + seq += copied; if (!copied) { long timeo; int data; @@ -233,6 +306,10 @@ msg_bytes_ready: copied = -EAGAIN; } out: + WRITE_ONCE(tcp->copied_seq, seq); + tcp_rcv_space_adjust(sk); + if (copied > 0) + __tcp_cleanup_rbuf(sk, copied); release_sock(sk); sk_psock_put(sk, psock); return copied; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 61b6710f337a..bf8b22218dd4 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4530,7 +4530,7 @@ static void tcp_sack_maybe_coalesce(struct tcp_sock *tp) } } -static void tcp_sack_compress_send_ack(struct sock *sk) +void tcp_sack_compress_send_ack(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index 45dda7889387..4851211aa60d 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -60,12 +60,12 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb, struct tcphdr *th; unsigned int thlen; unsigned int seq; - __be32 delta; unsigned int oldlen; unsigned int mss; struct sk_buff *gso_skb = skb; __sum16 newcheck; bool ooo_okay, copy_destructor; + __wsum delta; th = tcp_hdr(skb); thlen = th->doff * 4; @@ -75,7 +75,7 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb, if (!pskb_may_pull(skb, thlen)) goto out; - oldlen = (u16)~skb->len; + oldlen = ~skb->len; __skb_pull(skb, thlen); mss = skb_shinfo(skb)->gso_size; @@ -110,7 +110,7 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb, if (skb_is_gso(segs)) mss *= skb_shinfo(segs)->gso_segs; - delta = htonl(oldlen + (thlen + mss)); + delta = (__force __wsum)htonl(oldlen + thlen + mss); skb = segs; th = tcp_hdr(skb); @@ -119,8 +119,7 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb, if (unlikely(skb_shinfo(gso_skb)->tx_flags & SKBTX_SW_TSTAMP)) tcp_gso_tstamp(segs, skb_shinfo(gso_skb)->tskey, seq, mss); - newcheck = ~csum_fold((__force __wsum)((__force u32)th->check + - (__force u32)delta)); + newcheck = ~csum_fold(csum_add(csum_unfold(th->check), delta)); while (skb->next) { th->fin = th->psh = 0; @@ -165,11 +164,11 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb, WARN_ON_ONCE(refcount_sub_and_test(-delta, &skb->sk->sk_wmem_alloc)); } - delta = htonl(oldlen + (skb_tail_pointer(skb) - - skb_transport_header(skb)) + - skb->data_len); - th->check = ~csum_fold((__force __wsum)((__force u32)th->check + - (__force u32)delta)); + delta = (__force __wsum)htonl(oldlen + + (skb_tail_pointer(skb) - + skb_transport_header(skb)) + + skb->data_len); + th->check = ~csum_fold(csum_add(csum_unfold(th->check), delta)); if (skb->ip_summed == CHECKSUM_PARTIAL) gso_reset_checksum(skb, ~th->check); else diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index b839c2f91292..39eb947fe392 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -290,9 +290,19 @@ static int tcp_write_timeout(struct sock *sk) void tcp_delack_timer_handler(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); + struct tcp_sock *tp = tcp_sk(sk); - if (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) || - !(icsk->icsk_ack.pending & ICSK_ACK_TIMER)) + if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) + return; + + /* Handling the sack compression case */ + if (tp->compressed_ack) { + tcp_mstamp_refresh(tp); + tcp_sack_compress_send_ack(sk); + return; + } + + if (!(icsk->icsk_ack.pending & ICSK_ACK_TIMER)) return; if (time_after(icsk->icsk_ack.timeout, jiffies)) { @@ -312,7 +322,7 @@ void tcp_delack_timer_handler(struct sock *sk) inet_csk_exit_pingpong_mode(sk); icsk->icsk_ack.ato = TCP_ATO_MIN; } - tcp_mstamp_refresh(tcp_sk(sk)); + tcp_mstamp_refresh(tp); tcp_send_ack(sk); __NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKS); } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index aa32afd871ee..9482def1f310 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1818,7 +1818,7 @@ EXPORT_SYMBOL(__skb_recv_udp); int udp_read_skb(struct sock *sk, skb_read_actor_t recv_actor) { struct sk_buff *skb; - int err, copied; + int err; try_again: skb = skb_recv_udp(sk, MSG_DONTWAIT, &err); @@ -1837,10 +1837,7 @@ try_again: } WARN_ON_ONCE(!skb_set_owner_sk_safe(skb, sk)); - copied = recv_actor(sk, skb); - kfree_skb(skb); - - return copied; + return recv_actor(sk, skb); } EXPORT_SYMBOL(udp_read_skb); diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c index e0c9cc39b81e..56d94d23b9e0 100644 --- a/net/ipv4/udplite.c +++ b/net/ipv4/udplite.c @@ -64,6 +64,8 @@ struct proto udplite_prot = { .per_cpu_fw_alloc = &udp_memory_per_cpu_fw_alloc, .sysctl_mem = sysctl_udp_mem, + .sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_udp_wmem_min), + .sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_udp_rmem_min), .obj_size = sizeof(struct udp_sock), .h.udp_table = &udplite_table, }; diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index a8d961d3a477..5fa0e37305d9 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -569,24 +569,6 @@ looped_back: return -1; } - if (skb_cloned(skb)) { - if (pskb_expand_head(skb, IPV6_RPL_SRH_WORST_SWAP_SIZE, 0, - GFP_ATOMIC)) { - __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), - IPSTATS_MIB_OUTDISCARDS); - kfree_skb(skb); - return -1; - } - } else { - err = skb_cow_head(skb, IPV6_RPL_SRH_WORST_SWAP_SIZE); - if (unlikely(err)) { - kfree_skb(skb); - return -1; - } - } - - hdr = (struct ipv6_rpl_sr_hdr *)skb_transport_header(skb); - if (!pskb_may_pull(skb, ipv6_rpl_srh_size(n, hdr->cmpri, hdr->cmpre))) { kfree_skb(skb); @@ -630,6 +612,17 @@ looped_back: skb_pull(skb, ((hdr->hdrlen + 1) << 3)); skb_postpull_rcsum(skb, oldhdr, sizeof(struct ipv6hdr) + ((hdr->hdrlen + 1) << 3)); + if (unlikely(!hdr->segments_left)) { + if (pskb_expand_head(skb, sizeof(struct ipv6hdr) + ((chdr->hdrlen + 1) << 3), 0, + GFP_ATOMIC)) { + __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_OUTDISCARDS); + kfree_skb(skb); + kfree(buf); + return -1; + } + + oldhdr = ipv6_hdr(skb); + } skb_push(skb, ((chdr->hdrlen + 1) << 3) + sizeof(struct ipv6hdr)); skb_reset_network_header(skb); skb_mac_header_rebuild(skb); diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c index da46c4284676..49e31e4ae7b7 100644 --- a/net/ipv6/exthdrs_core.c +++ b/net/ipv6/exthdrs_core.c @@ -143,6 +143,8 @@ int ipv6_find_tlv(const struct sk_buff *skb, int offset, int type) optlen = 1; break; default: + if (len < 2) + goto bad; optlen = nh[offset + 1] + 2; if (optlen > len) goto bad; diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 7d0adb612bdd..44ee7a2e72ac 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -793,7 +793,8 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (!proto) proto = inet->inet_num; - else if (proto != inet->inet_num) + else if (proto != inet->inet_num && + inet->inet_num != IPPROTO_RAW) return -EINVAL; if (proto > 255) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index e3aec46bd466..392aaa373b66 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -6412,9 +6412,9 @@ static struct ctl_table ipv6_route_table_template[] = { { .procname = "skip_notify_on_dev_down", .data = &init_net.ipv6.sysctl.skip_notify_on_dev_down, - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec_minmax, + .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c index 67eaf3ca14ce..3bab0cc13697 100644 --- a/net/ipv6/udplite.c +++ b/net/ipv6/udplite.c @@ -60,6 +60,8 @@ struct proto udplitev6_prot = { .per_cpu_fw_alloc = &udp_memory_per_cpu_fw_alloc, .sysctl_mem = sysctl_udp_mem, + .sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_udp_wmem_min), + .sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_udp_rmem_min), .obj_size = sizeof(struct udp6_sock), .h.udp_table = &udplite_table, }; diff --git a/net/mac80211/he.c b/net/mac80211/he.c index 729f261520c7..0322abae0825 100644 --- a/net/mac80211/he.c +++ b/net/mac80211/he.c @@ -3,7 +3,7 @@ * HE handling * * Copyright(c) 2017 Intel Deutschland GmbH - * Copyright(c) 2019 - 2022 Intel Corporation + * Copyright(c) 2019 - 2023 Intel Corporation */ #include "ieee80211_i.h" @@ -114,6 +114,7 @@ ieee80211_he_cap_ie_to_sta_he_cap(struct ieee80211_sub_if_data *sdata, struct link_sta_info *link_sta) { struct ieee80211_sta_he_cap *he_cap = &link_sta->pub->he_cap; + const struct ieee80211_sta_he_cap *own_he_cap_ptr; struct ieee80211_sta_he_cap own_he_cap; struct ieee80211_he_cap_elem *he_cap_ie_elem = (void *)he_cap_ie; u8 he_ppe_size; @@ -123,12 +124,16 @@ ieee80211_he_cap_ie_to_sta_he_cap(struct ieee80211_sub_if_data *sdata, memset(he_cap, 0, sizeof(*he_cap)); - if (!he_cap_ie || - !ieee80211_get_he_iftype_cap(sband, - ieee80211_vif_type_p2p(&sdata->vif))) + if (!he_cap_ie) return; - own_he_cap = sband->iftype_data->he_cap; + own_he_cap_ptr = + ieee80211_get_he_iftype_cap(sband, + ieee80211_vif_type_p2p(&sdata->vif)); + if (!own_he_cap_ptr) + return; + + own_he_cap = *own_he_cap_ptr; /* Make sure size is OK */ mcs_nss_size = ieee80211_he_mcs_nss_size(he_cap_ie_elem); diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index e13a0354c397..bd8d6f9545f5 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -1217,6 +1217,7 @@ static void ieee80211_add_non_inheritance_elem(struct sk_buff *skb, const u16 *inner) { unsigned int skb_len = skb->len; + bool at_extension = false; bool added = false; int i, j; u8 *len, *list_len = NULL; @@ -1228,7 +1229,6 @@ static void ieee80211_add_non_inheritance_elem(struct sk_buff *skb, for (i = 0; i < PRESENT_ELEMS_MAX && outer[i]; i++) { u16 elem = outer[i]; bool have_inner = false; - bool at_extension = false; /* should at least be sorted in the sense of normal -> ext */ WARN_ON(at_extension && elem < PRESENT_ELEM_EXT_OFFS); @@ -1257,8 +1257,14 @@ static void ieee80211_add_non_inheritance_elem(struct sk_buff *skb, } *list_len += 1; skb_put_u8(skb, (u8)elem); + added = true; } + /* if we added a list but no extension list, make a zero-len one */ + if (added && (!at_extension || !list_len)) + skb_put_u8(skb, 0); + + /* if nothing added remove extension element completely */ if (!added) skb_trim(skb, skb_len); else diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 58222c077898..d996aa2579df 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -4965,7 +4965,9 @@ static bool ieee80211_prepare_and_rx_handle(struct ieee80211_rx_data *rx, } if (unlikely(rx->sta && rx->sta->sta.mlo) && - is_unicast_ether_addr(hdr->addr1)) { + is_unicast_ether_addr(hdr->addr1) && + !ieee80211_is_probe_resp(hdr->frame_control) && + !ieee80211_is_beacon(hdr->frame_control)) { /* translate to MLD addresses */ if (ether_addr_equal(link->conf->addr, hdr->addr1)) ether_addr_copy(hdr->addr1, rx->sdata->vif.addr); diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 0d9fbc8458fd..7f1c7f67014b 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -5528,7 +5528,7 @@ ieee80211_beacon_get_template_ema_list(struct ieee80211_hw *hw, { struct ieee80211_ema_beacons *ema_beacons = NULL; - WARN_ON(__ieee80211_beacon_get(hw, vif, NULL, false, link_id, 0, + WARN_ON(__ieee80211_beacon_get(hw, vif, NULL, true, link_id, 0, &ema_beacons)); return ema_beacons; diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index 78c924506e83..76612bca275a 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -87,8 +87,15 @@ bool mptcp_pm_allow_new_subflow(struct mptcp_sock *msk) unsigned int subflows_max; int ret = 0; - if (mptcp_pm_is_userspace(msk)) - return mptcp_userspace_pm_active(msk); + if (mptcp_pm_is_userspace(msk)) { + if (mptcp_userspace_pm_active(msk)) { + spin_lock_bh(&pm->lock); + pm->subflows++; + spin_unlock_bh(&pm->lock); + return true; + } + return false; + } subflows_max = mptcp_pm_get_subflows_max(msk); @@ -181,8 +188,16 @@ void mptcp_pm_subflow_check_next(struct mptcp_sock *msk, const struct sock *ssk, struct mptcp_pm_data *pm = &msk->pm; bool update_subflows; - update_subflows = (subflow->request_join || subflow->mp_join) && - mptcp_pm_is_kernel(msk); + update_subflows = subflow->request_join || subflow->mp_join; + if (mptcp_pm_is_userspace(msk)) { + if (update_subflows) { + spin_lock_bh(&pm->lock); + pm->subflows--; + spin_unlock_bh(&pm->lock); + } + return; + } + if (!READ_ONCE(pm->work_pending) && !update_subflows) return; diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index bc343dab5e3f..59f8f3124855 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -1558,6 +1558,24 @@ static int mptcp_nl_cmd_del_addr(struct sk_buff *skb, struct genl_info *info) return ret; } +void mptcp_pm_remove_addrs(struct mptcp_sock *msk, struct list_head *rm_list) +{ + struct mptcp_rm_list alist = { .nr = 0 }; + struct mptcp_pm_addr_entry *entry; + + list_for_each_entry(entry, rm_list, list) { + remove_anno_list_by_saddr(msk, &entry->addr); + if (alist.nr < MPTCP_RM_IDS_MAX) + alist.ids[alist.nr++] = entry->addr.id; + } + + if (alist.nr) { + spin_lock_bh(&msk->pm.lock); + mptcp_pm_remove_addr(msk, &alist); + spin_unlock_bh(&msk->pm.lock); + } +} + void mptcp_pm_remove_addrs_and_subflows(struct mptcp_sock *msk, struct list_head *rm_list) { diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c index 27a275805c06..b06aa58dfcf2 100644 --- a/net/mptcp/pm_userspace.c +++ b/net/mptcp/pm_userspace.c @@ -69,6 +69,7 @@ static int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk, MPTCP_PM_MAX_ADDR_ID + 1, 1); list_add_tail_rcu(&e->list, &msk->pm.userspace_pm_local_addr_list); + msk->pm.local_addr_used++; ret = e->addr.id; } else if (match) { ret = entry->addr.id; @@ -79,6 +80,31 @@ append_err: return ret; } +/* If the subflow is closed from the other peer (not via a + * subflow destroy command then), we want to keep the entry + * not to assign the same ID to another address and to be + * able to send RM_ADDR after the removal of the subflow. + */ +static int mptcp_userspace_pm_delete_local_addr(struct mptcp_sock *msk, + struct mptcp_pm_addr_entry *addr) +{ + struct mptcp_pm_addr_entry *entry, *tmp; + + list_for_each_entry_safe(entry, tmp, &msk->pm.userspace_pm_local_addr_list, list) { + if (mptcp_addresses_equal(&entry->addr, &addr->addr, false)) { + /* TODO: a refcount is needed because the entry can + * be used multiple times (e.g. fullmesh mode). + */ + list_del_rcu(&entry->list); + kfree(entry); + msk->pm.local_addr_used--; + return 0; + } + } + + return -EINVAL; +} + int mptcp_userspace_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int id, u8 *flags, int *ifindex) @@ -171,6 +197,7 @@ int mptcp_nl_cmd_announce(struct sk_buff *skb, struct genl_info *info) spin_lock_bh(&msk->pm.lock); if (mptcp_pm_alloc_anno_list(msk, &addr_val)) { + msk->pm.add_addr_signaled++; mptcp_pm_announce_addr(msk, &addr_val.addr, false); mptcp_pm_nl_addr_send_ack(msk); } @@ -232,7 +259,7 @@ int mptcp_nl_cmd_remove(struct sk_buff *skb, struct genl_info *info) list_move(&match->list, &free_list); - mptcp_pm_remove_addrs_and_subflows(msk, &free_list); + mptcp_pm_remove_addrs(msk, &free_list); release_sock((struct sock *)msk); @@ -251,6 +278,7 @@ int mptcp_nl_cmd_sf_create(struct sk_buff *skb, struct genl_info *info) struct nlattr *raddr = info->attrs[MPTCP_PM_ATTR_ADDR_REMOTE]; struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN]; struct nlattr *laddr = info->attrs[MPTCP_PM_ATTR_ADDR]; + struct mptcp_pm_addr_entry local = { 0 }; struct mptcp_addr_info addr_r; struct mptcp_addr_info addr_l; struct mptcp_sock *msk; @@ -302,12 +330,26 @@ int mptcp_nl_cmd_sf_create(struct sk_buff *skb, struct genl_info *info) goto create_err; } + local.addr = addr_l; + err = mptcp_userspace_pm_append_new_local_addr(msk, &local); + if (err < 0) { + GENL_SET_ERR_MSG(info, "did not match address and id"); + goto create_err; + } + lock_sock(sk); err = __mptcp_subflow_connect(sk, &addr_l, &addr_r); release_sock(sk); + spin_lock_bh(&msk->pm.lock); + if (err) + mptcp_userspace_pm_delete_local_addr(msk, &local); + else + msk->pm.subflows++; + spin_unlock_bh(&msk->pm.lock); + create_err: sock_put((struct sock *)msk); return err; @@ -420,7 +462,11 @@ int mptcp_nl_cmd_sf_destroy(struct sk_buff *skb, struct genl_info *info) ssk = mptcp_nl_find_ssk(msk, &addr_l, &addr_r); if (ssk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); + struct mptcp_pm_addr_entry entry = { .addr = addr_l }; + spin_lock_bh(&msk->pm.lock); + mptcp_userspace_pm_delete_local_addr(msk, &entry); + spin_unlock_bh(&msk->pm.lock); mptcp_subflow_shutdown(sk, ssk, RCV_SHUTDOWN | SEND_SHUTDOWN); mptcp_close_ssk(sk, ssk, subflow); MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RMSUBFLOW); diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 08dc53f56bc2..67311e7d5b21 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -90,8 +90,8 @@ static int __mptcp_socket_create(struct mptcp_sock *msk) if (err) return err; - msk->first = ssock->sk; - msk->subflow = ssock; + WRITE_ONCE(msk->first, ssock->sk); + WRITE_ONCE(msk->subflow, ssock); subflow = mptcp_subflow_ctx(ssock->sk); list_add(&subflow->node, &msk->conn_list); sock_hold(ssock->sk); @@ -603,7 +603,7 @@ static bool mptcp_check_data_fin(struct sock *sk) WRITE_ONCE(msk->ack_seq, msk->ack_seq + 1); WRITE_ONCE(msk->rcv_data_fin, 0); - sk->sk_shutdown |= RCV_SHUTDOWN; + WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | RCV_SHUTDOWN); smp_mb__before_atomic(); /* SHUTDOWN must be visible first */ switch (sk->sk_state) { @@ -825,6 +825,13 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk) mptcp_data_unlock(sk); } +static void mptcp_subflow_joined(struct mptcp_sock *msk, struct sock *ssk) +{ + mptcp_subflow_ctx(ssk)->map_seq = READ_ONCE(msk->ack_seq); + WRITE_ONCE(msk->allow_infinite_fallback, false); + mptcp_event(MPTCP_EVENT_SUB_ESTABLISHED, msk, ssk, GFP_ATOMIC); +} + static bool __mptcp_finish_join(struct mptcp_sock *msk, struct sock *ssk) { struct sock *sk = (struct sock *)msk; @@ -839,6 +846,7 @@ static bool __mptcp_finish_join(struct mptcp_sock *msk, struct sock *ssk) mptcp_sock_graft(ssk, sk->sk_socket); mptcp_sockopt_sync_locked(msk, ssk); + mptcp_subflow_joined(msk, ssk); return true; } @@ -910,7 +918,7 @@ static void mptcp_check_for_eof(struct mptcp_sock *msk) /* hopefully temporary hack: propagate shutdown status * to msk, when all subflows agree on it */ - sk->sk_shutdown |= RCV_SHUTDOWN; + WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | RCV_SHUTDOWN); smp_mb__before_atomic(); /* SHUTDOWN must be visible first */ sk->sk_data_ready(sk); @@ -1702,7 +1710,6 @@ static int mptcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, lock_sock(ssk); msg->msg_flags |= MSG_DONTWAIT; - msk->connect_flags = O_NONBLOCK; msk->fastopening = 1; ret = tcp_sendmsg_fastopen(ssk, msg, copied_syn, len, NULL); msk->fastopening = 0; @@ -2283,7 +2290,7 @@ static void mptcp_dispose_initial_subflow(struct mptcp_sock *msk) { if (msk->subflow) { iput(SOCK_INODE(msk->subflow)); - msk->subflow = NULL; + WRITE_ONCE(msk->subflow, NULL); } } @@ -2420,7 +2427,7 @@ out_release: sock_put(ssk); if (ssk == msk->first) - msk->first = NULL; + WRITE_ONCE(msk->first, NULL); out: if (ssk == msk->last_snd) @@ -2527,7 +2534,7 @@ static void mptcp_check_fastclose(struct mptcp_sock *msk) } inet_sk_state_store(sk, TCP_CLOSE); - sk->sk_shutdown = SHUTDOWN_MASK; + WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK); smp_mb__before_atomic(); /* SHUTDOWN must be visible first */ set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags); @@ -2721,7 +2728,7 @@ static int __mptcp_init_sock(struct sock *sk) WRITE_ONCE(msk->rmem_released, 0); msk->timer_ival = TCP_RTO_MIN; - msk->first = NULL; + WRITE_ONCE(msk->first, NULL); inet_csk(sk)->icsk_sync_mss = mptcp_sync_mss; WRITE_ONCE(msk->csum_enabled, mptcp_is_checksum_enabled(sock_net(sk))); WRITE_ONCE(msk->allow_infinite_fallback, true); @@ -2959,7 +2966,7 @@ bool __mptcp_close(struct sock *sk, long timeout) bool do_cancel_work = false; int subflows_alive = 0; - sk->sk_shutdown = SHUTDOWN_MASK; + WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK); if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) { mptcp_listen_inuse_dec(sk); @@ -3039,7 +3046,7 @@ static void mptcp_close(struct sock *sk, long timeout) sock_put(sk); } -void mptcp_copy_inaddrs(struct sock *msk, const struct sock *ssk) +static void mptcp_copy_inaddrs(struct sock *msk, const struct sock *ssk) { #if IS_ENABLED(CONFIG_MPTCP_IPV6) const struct ipv6_pinfo *ssk6 = inet6_sk(ssk); @@ -3102,7 +3109,7 @@ static int mptcp_disconnect(struct sock *sk, int flags) mptcp_pm_data_reset(msk); mptcp_ca_reset(sk); - sk->sk_shutdown = 0; + WRITE_ONCE(sk->sk_shutdown, 0); sk_error_report(sk); return 0; } @@ -3116,9 +3123,10 @@ static struct ipv6_pinfo *mptcp_inet6_sk(const struct sock *sk) } #endif -struct sock *mptcp_sk_clone(const struct sock *sk, - const struct mptcp_options_received *mp_opt, - struct request_sock *req) +struct sock *mptcp_sk_clone_init(const struct sock *sk, + const struct mptcp_options_received *mp_opt, + struct sock *ssk, + struct request_sock *req) { struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req); struct sock *nsk = sk_clone_lock(sk, GFP_ATOMIC); @@ -3137,7 +3145,7 @@ struct sock *mptcp_sk_clone(const struct sock *sk, msk = mptcp_sk(nsk); msk->local_key = subflow_req->local_key; msk->token = subflow_req->token; - msk->subflow = NULL; + WRITE_ONCE(msk->subflow, NULL); msk->in_accept_queue = 1; WRITE_ONCE(msk->fully_established, false); if (mp_opt->suboptions & OPTION_MPTCP_CSUMREQD) @@ -3150,10 +3158,30 @@ struct sock *mptcp_sk_clone(const struct sock *sk, msk->setsockopt_seq = mptcp_sk(sk)->setsockopt_seq; sock_reset_flag(nsk, SOCK_RCU_FREE); - /* will be fully established after successful MPC subflow creation */ - inet_sk_state_store(nsk, TCP_SYN_RECV); - security_inet_csk_clone(nsk, req); + + /* this can't race with mptcp_close(), as the msk is + * not yet exposted to user-space + */ + inet_sk_state_store(nsk, TCP_ESTABLISHED); + + /* The msk maintain a ref to each subflow in the connections list */ + WRITE_ONCE(msk->first, ssk); + list_add(&mptcp_subflow_ctx(ssk)->node, &msk->conn_list); + sock_hold(ssk); + + /* new mpc subflow takes ownership of the newly + * created mptcp socket + */ + mptcp_token_accept(subflow_req, msk); + + /* set msk addresses early to ensure mptcp_pm_get_local_id() + * uses the correct data + */ + mptcp_copy_inaddrs(nsk, ssk); + mptcp_propagate_sndbuf(nsk, ssk); + + mptcp_rcv_space_init(msk, ssk); bh_unlock_sock(nsk); /* note: the newly allocated socket refcount is 2 now */ @@ -3185,7 +3213,7 @@ static struct sock *mptcp_accept(struct sock *sk, int flags, int *err, struct socket *listener; struct sock *newsk; - listener = msk->subflow; + listener = READ_ONCE(msk->subflow); if (WARN_ON_ONCE(!listener)) { *err = -EINVAL; return NULL; @@ -3465,14 +3493,16 @@ bool mptcp_finish_join(struct sock *ssk) return false; } - if (!list_empty(&subflow->node)) - goto out; + /* active subflow, already present inside the conn_list */ + if (!list_empty(&subflow->node)) { + mptcp_subflow_joined(msk, ssk); + return true; + } if (!mptcp_pm_allow_new_subflow(msk)) goto err_prohibited; - /* active connections are already on conn_list. - * If we can't acquire msk socket lock here, let the release callback + /* If we can't acquire msk socket lock here, let the release callback * handle it */ mptcp_data_lock(parent); @@ -3495,11 +3525,6 @@ err_prohibited: return false; } - subflow->map_seq = READ_ONCE(msk->ack_seq); - WRITE_ONCE(msk->allow_infinite_fallback, false); - -out: - mptcp_event(MPTCP_EVENT_SUB_ESTABLISHED, msk, ssk, GFP_ATOMIC); return true; } @@ -3617,9 +3642,9 @@ static int mptcp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) * acquired the subflow socket lock, too. */ if (msk->fastopening) - err = __inet_stream_connect(ssock, uaddr, addr_len, msk->connect_flags, 1); + err = __inet_stream_connect(ssock, uaddr, addr_len, O_NONBLOCK, 1); else - err = inet_stream_connect(ssock, uaddr, addr_len, msk->connect_flags); + err = inet_stream_connect(ssock, uaddr, addr_len, O_NONBLOCK); inet_sk(sk)->defer_connect = inet_sk(ssock->sk)->defer_connect; /* on successful connect, the msk state will be moved to established by @@ -3632,12 +3657,10 @@ static int mptcp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) mptcp_copy_inaddrs(sk, ssock->sk); - /* unblocking connect, mptcp-level inet_stream_connect will error out - * without changing the socket state, update it here. + /* silence EINPROGRESS and let the caller inet_stream_connect + * handle the connection in progress */ - if (err == -EINPROGRESS) - sk->sk_socket->state = ssock->state; - return err; + return 0; } static struct proto mptcp_prot = { @@ -3696,18 +3719,6 @@ unlock: return err; } -static int mptcp_stream_connect(struct socket *sock, struct sockaddr *uaddr, - int addr_len, int flags) -{ - int ret; - - lock_sock(sock->sk); - mptcp_sk(sock->sk)->connect_flags = flags; - ret = __inet_stream_connect(sock, uaddr, addr_len, flags, 0); - release_sock(sock->sk); - return ret; -} - static int mptcp_listen(struct socket *sock, int backlog) { struct mptcp_sock *msk = mptcp_sk(sock->sk); @@ -3751,10 +3762,10 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock, pr_debug("msk=%p", msk); - /* buggy applications can call accept on socket states other then LISTEN + /* Buggy applications can call accept on socket states other then LISTEN * but no need to allocate the first subflow just to error out. */ - ssock = msk->subflow; + ssock = READ_ONCE(msk->subflow); if (!ssock) return -EINVAL; @@ -3800,9 +3811,6 @@ static __poll_t mptcp_check_writeable(struct mptcp_sock *msk) { struct sock *sk = (struct sock *)msk; - if (unlikely(sk->sk_shutdown & SEND_SHUTDOWN)) - return EPOLLOUT | EPOLLWRNORM; - if (sk_stream_is_writeable(sk)) return EPOLLOUT | EPOLLWRNORM; @@ -3820,6 +3828,7 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock, struct sock *sk = sock->sk; struct mptcp_sock *msk; __poll_t mask = 0; + u8 shutdown; int state; msk = mptcp_sk(sk); @@ -3828,23 +3837,30 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock, state = inet_sk_state_load(sk); pr_debug("msk=%p state=%d flags=%lx", msk, state, msk->flags); if (state == TCP_LISTEN) { - if (WARN_ON_ONCE(!msk->subflow || !msk->subflow->sk)) + struct socket *ssock = READ_ONCE(msk->subflow); + + if (WARN_ON_ONCE(!ssock || !ssock->sk)) return 0; - return inet_csk_listen_poll(msk->subflow->sk); + return inet_csk_listen_poll(ssock->sk); } + shutdown = READ_ONCE(sk->sk_shutdown); + if (shutdown == SHUTDOWN_MASK || state == TCP_CLOSE) + mask |= EPOLLHUP; + if (shutdown & RCV_SHUTDOWN) + mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP; + if (state != TCP_SYN_SENT && state != TCP_SYN_RECV) { mask |= mptcp_check_readable(msk); - mask |= mptcp_check_writeable(msk); + if (shutdown & SEND_SHUTDOWN) + mask |= EPOLLOUT | EPOLLWRNORM; + else + mask |= mptcp_check_writeable(msk); } else if (state == TCP_SYN_SENT && inet_sk(sk)->defer_connect) { /* cf tcp_poll() note about TFO */ mask |= EPOLLOUT | EPOLLWRNORM; } - if (sk->sk_shutdown == SHUTDOWN_MASK || state == TCP_CLOSE) - mask |= EPOLLHUP; - if (sk->sk_shutdown & RCV_SHUTDOWN) - mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP; /* This barrier is coupled with smp_wmb() in __mptcp_error_report() */ smp_rmb(); @@ -3859,7 +3875,7 @@ static const struct proto_ops mptcp_stream_ops = { .owner = THIS_MODULE, .release = inet_release, .bind = mptcp_bind, - .connect = mptcp_stream_connect, + .connect = inet_stream_connect, .socketpair = sock_no_socketpair, .accept = mptcp_stream_accept, .getname = inet_getname, @@ -3954,7 +3970,7 @@ static const struct proto_ops mptcp_v6_stream_ops = { .owner = THIS_MODULE, .release = inet6_release, .bind = mptcp_bind, - .connect = mptcp_stream_connect, + .connect = inet_stream_connect, .socketpair = sock_no_socketpair, .accept = mptcp_stream_accept, .getname = inet6_getname, diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 2d7b2c80a164..70c957bc56a8 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -297,7 +297,6 @@ struct mptcp_sock { nodelay:1, fastopening:1, in_accept_queue:1; - int connect_flags; struct work_struct work; struct sk_buff *ooo_last_skb; struct rb_root out_of_order_queue; @@ -306,7 +305,11 @@ struct mptcp_sock { struct list_head rtx_queue; struct mptcp_data_frag *first_pending; struct list_head join_list; - struct socket *subflow; /* outgoing connect/listener/!mp_capable */ + struct socket *subflow; /* outgoing connect/listener/!mp_capable + * The mptcp ops can safely dereference, using suitable + * ONCE annotation, the subflow outside the socket + * lock as such sock is freed after close(). + */ struct sock *first; struct mptcp_pm_data pm; struct { @@ -613,7 +616,6 @@ int mptcp_is_checksum_enabled(const struct net *net); int mptcp_allow_join_id0(const struct net *net); unsigned int mptcp_stale_loss_cnt(const struct net *net); int mptcp_get_pm_type(const struct net *net); -void mptcp_copy_inaddrs(struct sock *msk, const struct sock *ssk); void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow, const struct mptcp_options_received *mp_opt); bool __mptcp_retransmit_pending_data(struct sock *sk); @@ -683,9 +685,10 @@ void __init mptcp_proto_init(void); int __init mptcp_proto_v6_init(void); #endif -struct sock *mptcp_sk_clone(const struct sock *sk, - const struct mptcp_options_received *mp_opt, - struct request_sock *req); +struct sock *mptcp_sk_clone_init(const struct sock *sk, + const struct mptcp_options_received *mp_opt, + struct sock *ssk, + struct request_sock *req); void mptcp_get_options(const struct sk_buff *skb, struct mptcp_options_received *mp_opt); @@ -829,6 +832,7 @@ int mptcp_pm_announce_addr(struct mptcp_sock *msk, bool echo); int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list); int mptcp_pm_remove_subflow(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list); +void mptcp_pm_remove_addrs(struct mptcp_sock *msk, struct list_head *rm_list); void mptcp_pm_remove_addrs_and_subflows(struct mptcp_sock *msk, struct list_head *rm_list); diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index ba065b66551a..4688daa6b38b 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -815,38 +815,12 @@ create_child: ctx->setsockopt_seq = listener->setsockopt_seq; if (ctx->mp_capable) { - ctx->conn = mptcp_sk_clone(listener->conn, &mp_opt, req); + ctx->conn = mptcp_sk_clone_init(listener->conn, &mp_opt, child, req); if (!ctx->conn) goto fallback; owner = mptcp_sk(ctx->conn); - - /* this can't race with mptcp_close(), as the msk is - * not yet exposted to user-space - */ - inet_sk_state_store(ctx->conn, TCP_ESTABLISHED); - - /* record the newly created socket as the first msk - * subflow, but don't link it yet into conn_list - */ - WRITE_ONCE(owner->first, child); - - /* new mpc subflow takes ownership of the newly - * created mptcp socket - */ - owner->setsockopt_seq = ctx->setsockopt_seq; mptcp_pm_new_connection(owner, child, 1); - mptcp_token_accept(subflow_req, owner); - - /* set msk addresses early to ensure mptcp_pm_get_local_id() - * uses the correct data - */ - mptcp_copy_inaddrs(ctx->conn, child); - mptcp_propagate_sndbuf(ctx->conn, child); - - mptcp_rcv_space_init(owner, child); - list_add(&ctx->node, &owner->conn_list); - sock_hold(child); /* with OoO packets we can reach here without ingress * mpc option diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index c87804112d0c..3a1e0fd5bf14 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1779,7 +1779,7 @@ static int netlink_getsockopt(struct socket *sock, int level, int optname, break; } } - if (put_user(ALIGN(nlk->ngroups / 8, sizeof(u32)), optlen)) + if (put_user(ALIGN(BITS_TO_BYTES(nlk->ngroups), sizeof(u32)), optlen)) err = -EFAULT; netlink_unlock_table(); return err; diff --git a/net/netrom/nr_subr.c b/net/netrom/nr_subr.c index 3f99b432ea70..e2d2af924cff 100644 --- a/net/netrom/nr_subr.c +++ b/net/netrom/nr_subr.c @@ -123,7 +123,7 @@ void nr_write_internal(struct sock *sk, int frametype) unsigned char *dptr; int len, timeout; - len = NR_NETWORK_LEN + NR_TRANSPORT_LEN; + len = NR_TRANSPORT_LEN; switch (frametype & 0x0F) { case NR_CONNREQ: @@ -141,7 +141,8 @@ void nr_write_internal(struct sock *sk, int frametype) return; } - if ((skb = alloc_skb(len, GFP_ATOMIC)) == NULL) + skb = alloc_skb(NR_NETWORK_LEN + len, GFP_ATOMIC); + if (!skb) return; /* @@ -149,7 +150,7 @@ void nr_write_internal(struct sock *sk, int frametype) */ skb_reserve(skb, NR_NETWORK_LEN); - dptr = skb_put(skb, skb_tailroom(skb)); + dptr = skb_put(skb, len); switch (frametype & 0x0F) { case NR_CONNREQ: diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 94c6a1ffa459..a2dbeb264f26 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -3201,6 +3201,9 @@ static int packet_do_bind(struct sock *sk, const char *name, int ifindex, lock_sock(sk); spin_lock(&po->bind_lock); + if (!proto) + proto = po->num; + rcu_read_lock(); if (po->fanout) { @@ -3299,7 +3302,7 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr, memcpy(name, uaddr->sa_data, sizeof(uaddr->sa_data_min)); name[sizeof(uaddr->sa_data_min)] = 0; - return packet_do_bind(sk, name, 0, pkt_sk(sk)->num); + return packet_do_bind(sk, name, 0, 0); } static int packet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) @@ -3316,8 +3319,7 @@ static int packet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len if (sll->sll_family != AF_PACKET) return -EINVAL; - return packet_do_bind(sk, NULL, sll->sll_ifindex, - sll->sll_protocol ? : pkt_sk(sk)->num); + return packet_do_bind(sk, NULL, sll->sll_ifindex, sll->sll_protocol); } static struct proto packet_proto = { diff --git a/net/packet/diag.c b/net/packet/diag.c index d0c4eda4cdc6..f6b200cb3c06 100644 --- a/net/packet/diag.c +++ b/net/packet/diag.c @@ -143,7 +143,7 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, rp = nlmsg_data(nlh); rp->pdiag_family = AF_PACKET; rp->pdiag_type = sk->sk_type; - rp->pdiag_num = ntohs(po->num); + rp->pdiag_num = ntohs(READ_ONCE(po->num)); rp->pdiag_ino = sk_ino; sock_diag_save_cookie(sk, rp->pdiag_cookie); diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index 31f738d65f1c..da0b3b5157d5 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -980,6 +980,7 @@ static int __init af_rxrpc_init(void) BUILD_BUG_ON(sizeof(struct rxrpc_skb_priv) > sizeof_field(struct sk_buff, cb)); ret = -ENOMEM; + rxrpc_gen_version_string(); rxrpc_call_jar = kmem_cache_create( "rxrpc_call_jar", sizeof(struct rxrpc_call), 0, SLAB_HWCACHE_ALIGN, NULL); diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 5d44dc08f66d..e8e14c6f904d 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -1068,6 +1068,7 @@ int rxrpc_get_server_data_key(struct rxrpc_connection *, const void *, time64_t, /* * local_event.c */ +void rxrpc_gen_version_string(void); void rxrpc_send_version_request(struct rxrpc_local *local, struct rxrpc_host_header *hdr, struct sk_buff *skb); diff --git a/net/rxrpc/local_event.c b/net/rxrpc/local_event.c index 5e69ea6b233d..993c69f97488 100644 --- a/net/rxrpc/local_event.c +++ b/net/rxrpc/local_event.c @@ -16,7 +16,16 @@ #include <generated/utsrelease.h> #include "ar-internal.h" -static const char rxrpc_version_string[65] = "linux-" UTS_RELEASE " AF_RXRPC"; +static char rxrpc_version_string[65]; // "linux-" UTS_RELEASE " AF_RXRPC"; + +/* + * Generate the VERSION packet string. + */ +void rxrpc_gen_version_string(void) +{ + snprintf(rxrpc_version_string, sizeof(rxrpc_version_string), + "linux-%.49s AF_RXRPC", UTS_RELEASE); +} /* * Reply to a version request diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 9dbc43388e57..815c3e416bc5 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -1153,6 +1153,9 @@ static int fl_set_geneve_opt(const struct nlattr *nla, struct fl_flow_key *key, if (option_len > sizeof(struct geneve_opt)) data_len = option_len - sizeof(struct geneve_opt); + if (key->enc_opts.len > FLOW_DIS_TUN_OPTS_MAX - 4) + return -ERANGE; + opt = (struct geneve_opt *)&key->enc_opts.data[key->enc_opts.len]; memset(opt, 0xff, option_len); opt->length = data_len / 4; diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index fdb8f429333d..9ea51812b9cf 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1252,7 +1252,12 @@ static struct Qdisc *qdisc_create(struct net_device *dev, sch->parent = parent; if (handle == TC_H_INGRESS) { - sch->flags |= TCQ_F_INGRESS; + if (!(sch->flags & TCQ_F_INGRESS)) { + NL_SET_ERR_MSG(extack, + "Specified parent ID is reserved for ingress and clsact Qdiscs"); + err = -EINVAL; + goto err_out3; + } handle = TC_H_MAKE(TC_H_INGRESS, 0); } else { if (handle == 0) { @@ -1591,11 +1596,20 @@ replay: NL_SET_ERR_MSG(extack, "Invalid qdisc name"); return -EINVAL; } + if (q->flags & TCQ_F_INGRESS) { + NL_SET_ERR_MSG(extack, + "Cannot regraft ingress or clsact Qdiscs"); + return -EINVAL; + } if (q == p || (p && check_loop(q, p, 0))) { NL_SET_ERR_MSG(extack, "Qdisc parent/child loop detected"); return -ELOOP; } + if (clid == TC_H_INGRESS) { + NL_SET_ERR_MSG(extack, "Ingress cannot graft directly"); + return -EINVAL; + } qdisc_refcount_inc(q); goto graft; } else { @@ -2288,7 +2302,9 @@ static struct pernet_operations psched_net_ops = { .exit = psched_net_exit, }; +#if IS_ENABLED(CONFIG_RETPOLINE) DEFINE_STATIC_KEY_FALSE(tc_skip_wrapper); +#endif static int __init pktsched_init(void) { diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c index 6980796d435d..c699e5095607 100644 --- a/net/sched/sch_fq_pie.c +++ b/net/sched/sch_fq_pie.c @@ -201,6 +201,11 @@ out: return NET_XMIT_CN; } +static struct netlink_range_validation fq_pie_q_range = { + .min = 1, + .max = 1 << 20, +}; + static const struct nla_policy fq_pie_policy[TCA_FQ_PIE_MAX + 1] = { [TCA_FQ_PIE_LIMIT] = {.type = NLA_U32}, [TCA_FQ_PIE_FLOWS] = {.type = NLA_U32}, @@ -208,7 +213,8 @@ static const struct nla_policy fq_pie_policy[TCA_FQ_PIE_MAX + 1] = { [TCA_FQ_PIE_TUPDATE] = {.type = NLA_U32}, [TCA_FQ_PIE_ALPHA] = {.type = NLA_U32}, [TCA_FQ_PIE_BETA] = {.type = NLA_U32}, - [TCA_FQ_PIE_QUANTUM] = {.type = NLA_U32}, + [TCA_FQ_PIE_QUANTUM] = + NLA_POLICY_FULL_RANGE(NLA_U32, &fq_pie_q_range), [TCA_FQ_PIE_MEMORY_LIMIT] = {.type = NLA_U32}, [TCA_FQ_PIE_ECN_PROB] = {.type = NLA_U32}, [TCA_FQ_PIE_ECN] = {.type = NLA_U32}, diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c index 84838128b9c5..e43a45499372 100644 --- a/net/sched/sch_ingress.c +++ b/net/sched/sch_ingress.c @@ -80,6 +80,9 @@ static int ingress_init(struct Qdisc *sch, struct nlattr *opt, struct net_device *dev = qdisc_dev(sch); int err; + if (sch->parent != TC_H_INGRESS) + return -EOPNOTSUPP; + net_inc_ingress_queue(); mini_qdisc_pair_init(&q->miniqp, sch, &dev->miniq_ingress); @@ -101,6 +104,9 @@ static void ingress_destroy(struct Qdisc *sch) { struct ingress_sched_data *q = qdisc_priv(sch); + if (sch->parent != TC_H_INGRESS) + return; + tcf_block_put_ext(q->block, sch, &q->block_info); net_dec_ingress_queue(); } @@ -134,7 +140,7 @@ static struct Qdisc_ops ingress_qdisc_ops __read_mostly = { .cl_ops = &ingress_class_ops, .id = "ingress", .priv_size = sizeof(struct ingress_sched_data), - .static_flags = TCQ_F_CPUSTATS, + .static_flags = TCQ_F_INGRESS | TCQ_F_CPUSTATS, .init = ingress_init, .destroy = ingress_destroy, .dump = ingress_dump, @@ -219,6 +225,9 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt, struct net_device *dev = qdisc_dev(sch); int err; + if (sch->parent != TC_H_CLSACT) + return -EOPNOTSUPP; + net_inc_ingress_queue(); net_inc_egress_queue(); @@ -248,6 +257,9 @@ static void clsact_destroy(struct Qdisc *sch) { struct clsact_sched_data *q = qdisc_priv(sch); + if (sch->parent != TC_H_CLSACT) + return; + tcf_block_put_ext(q->egress_block, sch, &q->egress_block_info); tcf_block_put_ext(q->ingress_block, sch, &q->ingress_block_info); @@ -269,7 +281,7 @@ static struct Qdisc_ops clsact_qdisc_ops __read_mostly = { .cl_ops = &clsact_class_ops, .id = "clsact", .priv_size = sizeof(struct clsact_sched_data), - .static_flags = TCQ_F_CPUSTATS, + .static_flags = TCQ_F_INGRESS | TCQ_F_CPUSTATS, .init = clsact_init, .destroy = clsact_destroy, .dump = ingress_dump, diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 2f66a2006517..2abe45af98e7 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -324,9 +324,12 @@ bool sctp_transport_pl_recv(struct sctp_transport *t) t->pl.probe_size += SCTP_PL_BIG_STEP; } else if (t->pl.state == SCTP_PL_SEARCH) { if (!t->pl.probe_high) { - t->pl.probe_size = min(t->pl.probe_size + SCTP_PL_BIG_STEP, - SCTP_MAX_PLPMTU); - return false; + if (t->pl.probe_size < SCTP_MAX_PLPMTU) { + t->pl.probe_size = min(t->pl.probe_size + SCTP_PL_BIG_STEP, + SCTP_MAX_PLPMTU); + return false; + } + t->pl.probe_high = SCTP_MAX_PLPMTU; } t->pl.probe_size += SCTP_PL_MIN_STEP; if (t->pl.probe_size >= t->pl.probe_high) { @@ -341,7 +344,7 @@ bool sctp_transport_pl_recv(struct sctp_transport *t) } else if (t->pl.state == SCTP_PL_COMPLETE) { /* Raise probe_size again after 30 * interval in Search Complete */ t->pl.state = SCTP_PL_SEARCH; /* Search Complete -> Search */ - t->pl.probe_size += SCTP_PL_MIN_STEP; + t->pl.probe_size = min(t->pl.probe_size + SCTP_PL_MIN_STEP, SCTP_MAX_PLPMTU); } return t->pl.state == SCTP_PL_COMPLETE; diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c index a0840b8c935b..90f0b60b196a 100644 --- a/net/smc/smc_llc.c +++ b/net/smc/smc_llc.c @@ -578,7 +578,10 @@ static struct smc_buf_desc *smc_llc_get_next_rmb(struct smc_link_group *lgr, { struct smc_buf_desc *buf_next; - if (!buf_pos || list_is_last(&buf_pos->list, &lgr->rmbs[*buf_lst])) { + if (!buf_pos) + return _smc_llc_get_next_rmb(lgr, buf_lst); + + if (list_is_last(&buf_pos->list, &lgr->rmbs[*buf_lst])) { (*buf_lst)++; return _smc_llc_get_next_rmb(lgr, buf_lst); } @@ -614,6 +617,8 @@ static int smc_llc_fill_ext_v2(struct smc_llc_msg_add_link_v2_ext *ext, goto out; buf_pos = smc_llc_get_first_rmb(lgr, &buf_lst); for (i = 0; i < ext->num_rkeys; i++) { + while (buf_pos && !(buf_pos)->used) + buf_pos = smc_llc_get_next_rmb(lgr, &buf_lst, buf_pos); if (!buf_pos) break; rmb = buf_pos; @@ -623,8 +628,6 @@ static int smc_llc_fill_ext_v2(struct smc_llc_msg_add_link_v2_ext *ext, cpu_to_be64((uintptr_t)rmb->cpu_addr) : cpu_to_be64((u64)sg_dma_address(rmb->sgt[lnk_idx].sgl)); buf_pos = smc_llc_get_next_rmb(lgr, &buf_lst, buf_pos); - while (buf_pos && !(buf_pos)->used) - buf_pos = smc_llc_get_next_rmb(lgr, &buf_lst, buf_pos); } len += i * sizeof(ext->rt[0]); out: @@ -848,6 +851,8 @@ static int smc_llc_add_link_cont(struct smc_link *link, addc_llc->num_rkeys = *num_rkeys_todo; n = *num_rkeys_todo; for (i = 0; i < min_t(u8, n, SMC_LLC_RKEYS_PER_CONT_MSG); i++) { + while (*buf_pos && !(*buf_pos)->used) + *buf_pos = smc_llc_get_next_rmb(lgr, buf_lst, *buf_pos); if (!*buf_pos) { addc_llc->num_rkeys = addc_llc->num_rkeys - *num_rkeys_todo; @@ -864,8 +869,6 @@ static int smc_llc_add_link_cont(struct smc_link *link, (*num_rkeys_todo)--; *buf_pos = smc_llc_get_next_rmb(lgr, buf_lst, *buf_pos); - while (*buf_pos && !(*buf_pos)->used) - *buf_pos = smc_llc_get_next_rmb(lgr, buf_lst, *buf_pos); } addc_llc->hd.common.llc_type = SMC_LLC_ADD_LINK_CONT; addc_llc->hd.length = sizeof(struct smc_llc_msg_add_link_cont); diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index c8321de341ee..6debf4fd42d4 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -927,11 +927,10 @@ static void __rpc_execute(struct rpc_task *task) */ do_action = task->tk_action; /* Tasks with an RPC error status should exit */ - if (do_action != rpc_exit_task && + if (do_action && do_action != rpc_exit_task && (status = READ_ONCE(task->tk_rpc_status)) != 0) { task->tk_status = status; - if (do_action != NULL) - do_action = rpc_exit_task; + do_action = rpc_exit_task; } /* Callbacks override all actions */ if (task->tk_callback) { diff --git a/net/tls/tls_strp.c b/net/tls/tls_strp.c index da95abbb7ea3..f37f4a0fcd3c 100644 --- a/net/tls/tls_strp.c +++ b/net/tls/tls_strp.c @@ -20,7 +20,9 @@ static void tls_strp_abort_strp(struct tls_strparser *strp, int err) strp->stopped = 1; /* Report an error on the lower socket */ - strp->sk->sk_err = -err; + WRITE_ONCE(strp->sk->sk_err, -err); + /* Paired with smp_rmb() in tcp_poll() */ + smp_wmb(); sk_error_report(strp->sk); } diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 6e6a7c37d685..1a53c8f481e9 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -70,7 +70,9 @@ noinline void tls_err_abort(struct sock *sk, int err) { WARN_ON_ONCE(err >= 0); /* sk->sk_err should contain a positive error code. */ - sk->sk_err = -err; + WRITE_ONCE(sk->sk_err, -err); + /* Paired with smp_rmb() in tcp_poll() */ + smp_wmb(); sk_error_report(sk); } diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index cc695c9f09ec..e7728b57a8c7 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2553,7 +2553,7 @@ static int unix_read_skb(struct sock *sk, skb_read_actor_t recv_actor) { struct unix_sock *u = unix_sk(sk); struct sk_buff *skb; - int err, copied; + int err; mutex_lock(&u->iolock); skb = skb_recv_datagram(sk, MSG_DONTWAIT, &err); @@ -2561,10 +2561,7 @@ static int unix_read_skb(struct sock *sk, skb_read_actor_t recv_actor) if (!skb) return err; - copied = recv_actor(sk, skb); - kfree_skb(skb); - - return copied; + return recv_actor(sk, skb); } /* diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index e4878551f140..b769fc258931 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -1441,7 +1441,6 @@ int virtio_transport_read_skb(struct vsock_sock *vsk, skb_read_actor_t recv_acto struct sock *sk = sk_vsock(vsk); struct sk_buff *skb; int off = 0; - int copied; int err; spin_lock_bh(&vvs->rx_lock); @@ -1454,9 +1453,7 @@ int virtio_transport_read_skb(struct vsock_sock *vsk, skb_read_actor_t recv_acto if (!skb) return err; - copied = recv_actor(sk, skb); - kfree_skb(skb); - return copied; + return recv_actor(sk, skb); } EXPORT_SYMBOL_GPL(virtio_transport_read_skb); diff --git a/net/wireless/core.c b/net/wireless/core.c index 5b0c4d5b80cf..b3ec9eaec36b 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -368,12 +368,12 @@ static void cfg80211_sched_scan_stop_wk(struct work_struct *work) rdev = container_of(work, struct cfg80211_registered_device, sched_scan_stop_wk); - rtnl_lock(); + wiphy_lock(&rdev->wiphy); list_for_each_entry_safe(req, tmp, &rdev->sched_scan_req_list, list) { if (req->nl_owner_dead) cfg80211_stop_sched_scan_req(rdev, req, false); } - rtnl_unlock(); + wiphy_unlock(&rdev->wiphy); } static void cfg80211_propagate_radar_detect_wk(struct work_struct *work) diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index d95f8053020d..087d60c0f6e4 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -10723,6 +10723,8 @@ static int nl80211_authenticate(struct sk_buff *skb, struct genl_info *info) if (!info->attrs[NL80211_ATTR_MLD_ADDR]) return -EINVAL; req.ap_mld_addr = nla_data(info->attrs[NL80211_ATTR_MLD_ADDR]); + if (!is_valid_ether_addr(req.ap_mld_addr)) + return -EINVAL; } req.bss = cfg80211_get_bss(&rdev->wiphy, chan, bssid, ssid, ssid_len, diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 0d40d6af7e10..949e1fb3bec6 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -2440,11 +2440,11 @@ static void reg_leave_invalid_chans(struct wiphy *wiphy) struct wireless_dev *wdev; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); - ASSERT_RTNL(); - + wiphy_lock(wiphy); list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) if (!reg_wdev_chan_valid(wiphy, wdev)) cfg80211_leave(rdev, wdev); + wiphy_unlock(wiphy); } static void reg_check_chans_work(struct work_struct *work) diff --git a/samples/bpf/hbm.c b/samples/bpf/hbm.c index 6448b7826107..bf66277115e2 100644 --- a/samples/bpf/hbm.c +++ b/samples/bpf/hbm.c @@ -498,7 +498,6 @@ int main(int argc, char **argv) "Option -%c requires an argument.\n\n", optopt); case 'h': - __fallthrough; default: Usage(); return 0; diff --git a/sound/core/oss/pcm_plugin.h b/sound/core/oss/pcm_plugin.h index 46e273bd4a78..50a6b50f5db4 100644 --- a/sound/core/oss/pcm_plugin.h +++ b/sound/core/oss/pcm_plugin.h @@ -141,6 +141,14 @@ int snd_pcm_area_copy(const struct snd_pcm_channel_area *src_channel, void *snd_pcm_plug_buf_alloc(struct snd_pcm_substream *plug, snd_pcm_uframes_t size); void snd_pcm_plug_buf_unlock(struct snd_pcm_substream *plug, void *ptr); +#else + +static inline snd_pcm_sframes_t snd_pcm_plug_client_size(struct snd_pcm_substream *handle, snd_pcm_uframes_t drv_size) { return drv_size; } +static inline snd_pcm_sframes_t snd_pcm_plug_slave_size(struct snd_pcm_substream *handle, snd_pcm_uframes_t clt_size) { return clt_size; } +static inline int snd_pcm_plug_slave_format(int format, const struct snd_mask *format_mask) { return format; } + +#endif + snd_pcm_sframes_t snd_pcm_oss_write3(struct snd_pcm_substream *substream, const char *ptr, snd_pcm_uframes_t size, int in_kernel); @@ -151,14 +159,6 @@ snd_pcm_sframes_t snd_pcm_oss_writev3(struct snd_pcm_substream *substream, snd_pcm_sframes_t snd_pcm_oss_readv3(struct snd_pcm_substream *substream, void **bufs, snd_pcm_uframes_t frames); -#else - -static inline snd_pcm_sframes_t snd_pcm_plug_client_size(struct snd_pcm_substream *handle, snd_pcm_uframes_t drv_size) { return drv_size; } -static inline snd_pcm_sframes_t snd_pcm_plug_slave_size(struct snd_pcm_substream *handle, snd_pcm_uframes_t clt_size) { return clt_size; } -static inline int snd_pcm_plug_slave_format(int format, const struct snd_mask *format_mask) { return format; } - -#endif - #ifdef PLUGIN_DEBUG #define pdprintf(fmt, args...) printk(KERN_DEBUG "plugin: " fmt, ##args) #else diff --git a/sound/firewire/digi00x/digi00x-stream.c b/sound/firewire/digi00x/digi00x-stream.c index a15f55b0dce3..295163bb8abb 100644 --- a/sound/firewire/digi00x/digi00x-stream.c +++ b/sound/firewire/digi00x/digi00x-stream.c @@ -259,8 +259,10 @@ int snd_dg00x_stream_init_duplex(struct snd_dg00x *dg00x) return err; err = init_stream(dg00x, &dg00x->tx_stream); - if (err < 0) + if (err < 0) { destroy_stream(dg00x, &dg00x->rx_stream); + return err; + } err = amdtp_domain_init(&dg00x->domain); if (err < 0) { diff --git a/sound/hda/hdac_device.c b/sound/hda/hdac_device.c index accc9d279ce5..6c043fbd606f 100644 --- a/sound/hda/hdac_device.c +++ b/sound/hda/hdac_device.c @@ -611,7 +611,7 @@ EXPORT_SYMBOL_GPL(snd_hdac_power_up_pm); int snd_hdac_keep_power_up(struct hdac_device *codec) { if (!atomic_inc_not_zero(&codec->in_pm)) { - int ret = pm_runtime_get_if_in_use(&codec->dev); + int ret = pm_runtime_get_if_active(&codec->dev, true); if (!ret) return -1; if (ret < 0) diff --git a/sound/pci/cs46xx/cs46xx_lib.c b/sound/pci/cs46xx/cs46xx_lib.c index 62f45847b351..7d882b33d45e 100644 --- a/sound/pci/cs46xx/cs46xx_lib.c +++ b/sound/pci/cs46xx/cs46xx_lib.c @@ -531,7 +531,7 @@ static int load_firmware(struct snd_cs46xx *chip) return err; } -int snd_cs46xx_download_image(struct snd_cs46xx *chip) +static __maybe_unused int snd_cs46xx_download_image(struct snd_cs46xx *chip) { int idx, err; unsigned int offset = 0; diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c index fc114e522480..dbf7aa88e0e3 100644 --- a/sound/pci/hda/hda_generic.c +++ b/sound/pci/hda/hda_generic.c @@ -1155,8 +1155,8 @@ static bool path_has_mixer(struct hda_codec *codec, int path_idx, int ctl_type) return path && path->ctls[ctl_type]; } -static const char * const channel_name[4] = { - "Front", "Surround", "CLFE", "Side" +static const char * const channel_name[] = { + "Front", "Surround", "CLFE", "Side", "Back", }; /* give some appropriate ctl name prefix for the given line out channel */ @@ -1182,7 +1182,7 @@ static const char *get_line_out_pfx(struct hda_codec *codec, int ch, /* multi-io channels */ if (ch >= cfg->line_outs) - return channel_name[ch]; + goto fixed_name; switch (cfg->line_out_type) { case AUTO_PIN_SPEAKER_OUT: @@ -1234,6 +1234,7 @@ static const char *get_line_out_pfx(struct hda_codec *codec, int ch, if (cfg->line_outs == 1 && !spec->multi_ios) return "Line Out"; + fixed_name: if (ch >= ARRAY_SIZE(channel_name)) { snd_BUG(); return "PCM"; diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c index 099722ebaed8..748a3c40966e 100644 --- a/sound/pci/hda/patch_ca0132.c +++ b/sound/pci/hda/patch_ca0132.c @@ -1306,6 +1306,7 @@ static const struct snd_pci_quirk ca0132_quirks[] = { SND_PCI_QUIRK(0x1458, 0xA026, "Gigabyte G1.Sniper Z97", QUIRK_R3DI), SND_PCI_QUIRK(0x1458, 0xA036, "Gigabyte GA-Z170X-Gaming 7", QUIRK_R3DI), SND_PCI_QUIRK(0x3842, 0x1038, "EVGA X99 Classified", QUIRK_R3DI), + SND_PCI_QUIRK(0x3842, 0x104b, "EVGA X299 Dark", QUIRK_R3DI), SND_PCI_QUIRK(0x3842, 0x1055, "EVGA Z390 DARK", QUIRK_R3DI), SND_PCI_QUIRK(0x1102, 0x0013, "Recon3D", QUIRK_R3D), SND_PCI_QUIRK(0x1102, 0x0018, "Recon3D", QUIRK_R3D), diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 64a944016c78..5c0b1a09fd57 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -4589,6 +4589,11 @@ HDA_CODEC_ENTRY(0x10de009d, "GPU 9d HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de009e, "GPU 9e HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de009f, "GPU 9f HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de00a0, "GPU a0 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00a3, "GPU a3 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00a4, "GPU a4 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00a5, "GPU a5 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00a6, "GPU a6 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00a7, "GPU a7 HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de8001, "MCP73 HDMI", patch_nvhdmi_2ch), HDA_CODEC_ENTRY(0x10de8067, "MCP67/68 HDMI", patch_nvhdmi_2ch), HDA_CODEC_ENTRY(0x67663d82, "Arise 82 HDMI/DP", patch_gf_hdmi), diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 172ffc2c332b..7b5f194513c7 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -7063,6 +7063,8 @@ enum { ALC225_FIXUP_DELL1_MIC_NO_PRESENCE, ALC295_FIXUP_DISABLE_DAC3, ALC285_FIXUP_SPEAKER2_TO_DAC1, + ALC285_FIXUP_ASUS_SPEAKER2_TO_DAC1, + ALC285_FIXUP_ASUS_HEADSET_MIC, ALC280_FIXUP_HP_HEADSET_MIC, ALC221_FIXUP_HP_FRONT_MIC, ALC292_FIXUP_TPT460, @@ -8033,6 +8035,22 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC269_FIXUP_THINKPAD_ACPI }, + [ALC285_FIXUP_ASUS_SPEAKER2_TO_DAC1] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc285_fixup_speaker2_to_dac1, + .chained = true, + .chain_id = ALC245_FIXUP_CS35L41_SPI_2 + }, + [ALC285_FIXUP_ASUS_HEADSET_MIC] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x19, 0x03a11050 }, + { 0x1b, 0x03a11c30 }, + { } + }, + .chained = true, + .chain_id = ALC285_FIXUP_ASUS_SPEAKER2_TO_DAC1 + }, [ALC256_FIXUP_DELL_INSPIRON_7559_SUBWOOFER] = { .type = HDA_FIXUP_PINS, .v.pins = (const struct hda_pintbl[]) { @@ -9363,7 +9381,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x802f, "HP Z240", ALC221_FIXUP_HP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x8077, "HP", ALC256_FIXUP_HP_HEADSET_MIC), SND_PCI_QUIRK(0x103c, 0x8158, "HP", ALC256_FIXUP_HP_HEADSET_MIC), - SND_PCI_QUIRK(0x103c, 0x820d, "HP Pavilion 15", ALC269_FIXUP_HP_MUTE_LED_MIC3), + SND_PCI_QUIRK(0x103c, 0x820d, "HP Pavilion 15", ALC295_FIXUP_HP_X360), SND_PCI_QUIRK(0x103c, 0x8256, "HP", ALC221_FIXUP_HP_FRONT_MIC), SND_PCI_QUIRK(0x103c, 0x827e, "HP x360", ALC295_FIXUP_HP_X360), SND_PCI_QUIRK(0x103c, 0x827f, "HP x360", ALC269_FIXUP_HP_MUTE_LED_MIC3), @@ -9458,7 +9476,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8aa3, "HP ProBook 450 G9 (MB 8AA1)", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8aa8, "HP EliteBook 640 G9 (MB 8AA6)", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8aab, "HP EliteBook 650 G9 (MB 8AA9)", ALC236_FIXUP_HP_GPIO_LED), - SND_PCI_QUIRK(0x103c, 0x8abb, "HP ZBook Firefly 14 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8abb, "HP ZBook Firefly 14 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8ad1, "HP EliteBook 840 14 inch G9 Notebook PC", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8ad2, "HP EliteBook 860 16 inch G9 Notebook PC", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b42, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), @@ -9469,8 +9487,13 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8b47, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b5d, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8b5e, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), + SND_PCI_QUIRK(0x103c, 0x8b63, "HP Elite Dragonfly 13.5 inch G4", ALC245_FIXUP_CS35L41_SPI_4_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b65, "HP ProBook 455 15.6 inch G10 Notebook PC", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8b66, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), + SND_PCI_QUIRK(0x103c, 0x8b70, "HP EliteBook 835 G10", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x103c, 0x8b72, "HP EliteBook 845 G10", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x103c, 0x8b74, "HP EliteBook 845W G10", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x103c, 0x8b77, "HP ElieBook 865 G10", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x8b7a, "HP", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b7d, "HP", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b87, "HP", ALC236_FIXUP_HP_GPIO_LED), @@ -9480,7 +9503,9 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8b8f, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b92, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b96, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), + SND_PCI_QUIRK(0x103c, 0x8b97, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8bf0, "HP", ALC236_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8c26, "HP HP EliteBook 800G11", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x1043, 0x103e, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC), SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300), SND_PCI_QUIRK(0x1043, 0x106d, "Asus K53BE", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), @@ -9500,6 +9525,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1313, "Asus K42JZ", ALC269VB_FIXUP_ASUS_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1043, 0x13b0, "ASUS Z550SA", ALC256_FIXUP_ASUS_MIC), SND_PCI_QUIRK(0x1043, 0x1427, "Asus Zenbook UX31E", ALC269VB_FIXUP_ASUS_ZENBOOK), + SND_PCI_QUIRK(0x1043, 0x1473, "ASUS GU604V", ALC285_FIXUP_ASUS_HEADSET_MIC), + SND_PCI_QUIRK(0x1043, 0x1483, "ASUS GU603V", ALC285_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x1517, "Asus Zenbook UX31A", ALC269VB_FIXUP_ASUS_ZENBOOK_UX31A), SND_PCI_QUIRK(0x1043, 0x1662, "ASUS GV301QH", ALC294_FIXUP_ASUS_DUAL_SPK), SND_PCI_QUIRK(0x1043, 0x1683, "ASUS UM3402YAR", ALC287_FIXUP_CS35L41_I2C_2), @@ -9522,6 +9549,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1b13, "Asus U41SV", ALC269_FIXUP_INV_DMIC), SND_PCI_QUIRK(0x1043, 0x1bbd, "ASUS Z550MA", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1043, 0x1c23, "Asus X55U", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), + SND_PCI_QUIRK(0x1043, 0x1c62, "ASUS GU603", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x1c92, "ASUS ROG Strix G15", ALC285_FIXUP_ASUS_G533Z_PINS), SND_PCI_QUIRK(0x1043, 0x1ccd, "ASUS X555UB", ALC256_FIXUP_ASUS_MIC), SND_PCI_QUIRK(0x1043, 0x1d42, "ASUS Zephyrus G14 2022", ALC289_FIXUP_ASUS_GA401), @@ -9618,6 +9646,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1558, 0x7716, "Clevo NS50PU", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x7717, "Clevo NS70PU", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x7718, "Clevo L140PU", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x7724, "Clevo L140AU", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x8228, "Clevo NR40BU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x8520, "Clevo NH50D[CD]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x8521, "Clevo NH77D[CD]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), @@ -11663,6 +11692,7 @@ static const struct snd_pci_quirk alc662_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x1632, "HP RP5800", ALC662_FIXUP_HP_RP5800), SND_PCI_QUIRK(0x103c, 0x870c, "HP", ALC897_FIXUP_HP_HSMIC_VERB), SND_PCI_QUIRK(0x103c, 0x8719, "HP", ALC897_FIXUP_HP_HSMIC_VERB), + SND_PCI_QUIRK(0x103c, 0x872b, "HP", ALC897_FIXUP_HP_HSMIC_VERB), SND_PCI_QUIRK(0x103c, 0x873e, "HP", ALC671_FIXUP_HP_HEADSET_MIC2), SND_PCI_QUIRK(0x103c, 0x877e, "HP 288 Pro G6", ALC671_FIXUP_HP_HEADSET_MIC2), SND_PCI_QUIRK(0x103c, 0x885f, "HP 288 Pro G8", ALC671_FIXUP_HP_HEADSET_MIC2), @@ -11689,6 +11719,8 @@ static const struct snd_pci_quirk alc662_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x32cb, "Lenovo ThinkCentre M70", ALC897_FIXUP_HEADSET_MIC_PIN), SND_PCI_QUIRK(0x17aa, 0x32cf, "Lenovo ThinkCentre M950", ALC897_FIXUP_HEADSET_MIC_PIN), SND_PCI_QUIRK(0x17aa, 0x32f7, "Lenovo ThinkCentre M90", ALC897_FIXUP_HEADSET_MIC_PIN), + SND_PCI_QUIRK(0x17aa, 0x3321, "Lenovo ThinkCentre M70 Gen4", ALC897_FIXUP_HEADSET_MIC_PIN), + SND_PCI_QUIRK(0x17aa, 0x331b, "Lenovo ThinkCentre M90 Gen4", ALC897_FIXUP_HEADSET_MIC_PIN), SND_PCI_QUIRK(0x17aa, 0x3742, "Lenovo TianYi510Pro-14IOB", ALC897_FIXUP_HEADSET_MIC_PIN2), SND_PCI_QUIRK(0x17aa, 0x38af, "Lenovo Ideapad Y550P", ALC662_FIXUP_IDEAPAD), SND_PCI_QUIRK(0x17aa, 0x3a0d, "Lenovo Ideapad Y550", ALC662_FIXUP_IDEAPAD), diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c index 0bc6e4066d0f..4406a5def076 100644 --- a/sound/soc/amd/yc/acp6x-mach.c +++ b/sound/soc/amd/yc/acp6x-mach.c @@ -311,6 +311,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { DMI_MATCH(DMI_BOARD_NAME, "8A22"), } }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "System76"), + DMI_MATCH(DMI_PRODUCT_VERSION, "pang12"), + } + }, {} }; diff --git a/sound/soc/codecs/cs35l41-lib.c b/sound/soc/codecs/cs35l41-lib.c index 8538e2871c5f..1e4205295a0d 100644 --- a/sound/soc/codecs/cs35l41-lib.c +++ b/sound/soc/codecs/cs35l41-lib.c @@ -46,7 +46,7 @@ static const struct reg_default cs35l41_reg[] = { { CS35L41_DSP1_RX5_SRC, 0x00000020 }, { CS35L41_DSP1_RX6_SRC, 0x00000021 }, { CS35L41_DSP1_RX7_SRC, 0x0000003A }, - { CS35L41_DSP1_RX8_SRC, 0x00000001 }, + { CS35L41_DSP1_RX8_SRC, 0x0000003B }, { CS35L41_NGATE1_SRC, 0x00000008 }, { CS35L41_NGATE2_SRC, 0x00000009 }, { CS35L41_AMP_DIG_VOL_CTRL, 0x00008000 }, @@ -58,8 +58,8 @@ static const struct reg_default cs35l41_reg[] = { { CS35L41_IRQ1_MASK2, 0xFFFFFFFF }, { CS35L41_IRQ1_MASK3, 0xFFFF87FF }, { CS35L41_IRQ1_MASK4, 0xFEFFFFFF }, - { CS35L41_GPIO1_CTRL1, 0xE1000001 }, - { CS35L41_GPIO2_CTRL1, 0xE1000001 }, + { CS35L41_GPIO1_CTRL1, 0x81000001 }, + { CS35L41_GPIO2_CTRL1, 0x81000001 }, { CS35L41_MIXER_NGATE_CFG, 0x00000000 }, { CS35L41_MIXER_NGATE_CH1_CFG, 0x00000303 }, { CS35L41_MIXER_NGATE_CH2_CFG, 0x00000303 }, diff --git a/sound/soc/codecs/cs35l56.c b/sound/soc/codecs/cs35l56.c index 46762f7f1449..d1677d76d018 100644 --- a/sound/soc/codecs/cs35l56.c +++ b/sound/soc/codecs/cs35l56.c @@ -852,10 +852,11 @@ static void cs35l56_dsp_work(struct work_struct *work) */ if (cs35l56->sdw_peripheral) { cs35l56->sdw_irq_no_unmask = true; - cancel_work_sync(&cs35l56->sdw_irq_work); + flush_work(&cs35l56->sdw_irq_work); sdw_write_no_pm(cs35l56->sdw_peripheral, CS35L56_SDW_GEN_INT_MASK_1, 0); sdw_read_no_pm(cs35l56->sdw_peripheral, CS35L56_SDW_GEN_INT_STAT_1); sdw_write_no_pm(cs35l56->sdw_peripheral, CS35L56_SDW_GEN_INT_STAT_1, 0xFF); + flush_work(&cs35l56->sdw_irq_work); } ret = cs35l56_mbox_send(cs35l56, CS35L56_MBOX_CMD_SHUTDOWN); diff --git a/sound/soc/codecs/lpass-tx-macro.c b/sound/soc/codecs/lpass-tx-macro.c index da6fcf7f0991..de978c3d70b7 100644 --- a/sound/soc/codecs/lpass-tx-macro.c +++ b/sound/soc/codecs/lpass-tx-macro.c @@ -746,6 +746,8 @@ static int tx_macro_put_dec_enum(struct snd_kcontrol *kcontrol, struct tx_macro *tx = snd_soc_component_get_drvdata(component); val = ucontrol->value.enumerated.item[0]; + if (val >= e->items) + return -EINVAL; switch (e->reg) { case CDC_TX_INP_MUX_ADC_MUX0_CFG0: @@ -772,6 +774,9 @@ static int tx_macro_put_dec_enum(struct snd_kcontrol *kcontrol, case CDC_TX_INP_MUX_ADC_MUX7_CFG0: mic_sel_reg = CDC_TX7_TX_PATH_CFG0; break; + default: + dev_err(component->dev, "Error in configuration!!\n"); + return -EINVAL; } if (val != 0) { diff --git a/sound/soc/codecs/rt5682-i2c.c b/sound/soc/codecs/rt5682-i2c.c index 2935c1bb81f3..5bc46b041786 100644 --- a/sound/soc/codecs/rt5682-i2c.c +++ b/sound/soc/codecs/rt5682-i2c.c @@ -267,7 +267,9 @@ static int rt5682_i2c_probe(struct i2c_client *i2c) ret = devm_request_threaded_irq(&i2c->dev, i2c->irq, NULL, rt5682_irq, IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING | IRQF_ONESHOT, "rt5682", rt5682); - if (ret) + if (!ret) + rt5682->irq = i2c->irq; + else dev_err(&i2c->dev, "Failed to reguest IRQ: %d\n", ret); } diff --git a/sound/soc/codecs/rt5682.c b/sound/soc/codecs/rt5682.c index f6c798b65c08..5d992543b791 100644 --- a/sound/soc/codecs/rt5682.c +++ b/sound/soc/codecs/rt5682.c @@ -2959,6 +2959,9 @@ static int rt5682_suspend(struct snd_soc_component *component) if (rt5682->is_sdw) return 0; + if (rt5682->irq) + disable_irq(rt5682->irq); + cancel_delayed_work_sync(&rt5682->jack_detect_work); cancel_delayed_work_sync(&rt5682->jd_check_work); if (rt5682->hs_jack && (rt5682->jack_type & SND_JACK_HEADSET) == SND_JACK_HEADSET) { @@ -3027,6 +3030,9 @@ static int rt5682_resume(struct snd_soc_component *component) mod_delayed_work(system_power_efficient_wq, &rt5682->jack_detect_work, msecs_to_jiffies(0)); + if (rt5682->irq) + enable_irq(rt5682->irq); + return 0; } #else diff --git a/sound/soc/codecs/rt5682.h b/sound/soc/codecs/rt5682.h index d568c6993c33..e8efd8a84a6c 100644 --- a/sound/soc/codecs/rt5682.h +++ b/sound/soc/codecs/rt5682.h @@ -1462,6 +1462,7 @@ struct rt5682_priv { int pll_out[RT5682_PLLS]; int jack_type; + int irq; int irq_work_delay_time; }; diff --git a/sound/soc/codecs/ssm2602.c b/sound/soc/codecs/ssm2602.c index 00b60369b029..c29324403e9d 100644 --- a/sound/soc/codecs/ssm2602.c +++ b/sound/soc/codecs/ssm2602.c @@ -53,6 +53,18 @@ static const struct reg_default ssm2602_reg[SSM2602_CACHEREGNUM] = { { .reg = 0x09, .def = 0x0000 } }; +/* + * ssm2602 register patch + * Workaround for playback distortions after power up: activates digital + * core, and then powers on output, DAC, and whole chip at the same time + */ + +static const struct reg_sequence ssm2602_patch[] = { + { SSM2602_ACTIVE, 0x01 }, + { SSM2602_PWR, 0x07 }, + { SSM2602_RESET, 0x00 }, +}; + /*Appending several "None"s just for OSS mixer use*/ static const char *ssm2602_input_select[] = { @@ -598,6 +610,9 @@ static int ssm260x_component_probe(struct snd_soc_component *component) return ret; } + regmap_register_patch(ssm2602->regmap, ssm2602_patch, + ARRAY_SIZE(ssm2602_patch)); + /* set the update bits */ regmap_update_bits(ssm2602->regmap, SSM2602_LINVOL, LINVOL_LRIN_BOTH, LINVOL_LRIN_BOTH); diff --git a/sound/soc/dwc/dwc-i2s.c b/sound/soc/dwc/dwc-i2s.c index acdf98b2ee9c..399a489f24f2 100644 --- a/sound/soc/dwc/dwc-i2s.c +++ b/sound/soc/dwc/dwc-i2s.c @@ -132,13 +132,13 @@ static irqreturn_t i2s_irq_handler(int irq, void *dev_id) /* Error Handling: TX */ if (isr[i] & ISR_TXFO) { - dev_err(dev->dev, "TX overrun (ch_id=%d)\n", i); + dev_err_ratelimited(dev->dev, "TX overrun (ch_id=%d)\n", i); irq_valid = true; } /* Error Handling: TX */ if (isr[i] & ISR_RXFO) { - dev_err(dev->dev, "RX overrun (ch_id=%d)\n", i); + dev_err_ratelimited(dev->dev, "RX overrun (ch_id=%d)\n", i); irq_valid = true; } } @@ -183,30 +183,6 @@ static void i2s_stop(struct dw_i2s_dev *dev, } } -static int dw_i2s_startup(struct snd_pcm_substream *substream, - struct snd_soc_dai *cpu_dai) -{ - struct dw_i2s_dev *dev = snd_soc_dai_get_drvdata(cpu_dai); - union dw_i2s_snd_dma_data *dma_data = NULL; - - if (!(dev->capability & DWC_I2S_RECORD) && - (substream->stream == SNDRV_PCM_STREAM_CAPTURE)) - return -EINVAL; - - if (!(dev->capability & DWC_I2S_PLAY) && - (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)) - return -EINVAL; - - if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) - dma_data = &dev->play_dma_data; - else if (substream->stream == SNDRV_PCM_STREAM_CAPTURE) - dma_data = &dev->capture_dma_data; - - snd_soc_dai_set_dma_data(cpu_dai, substream, (void *)dma_data); - - return 0; -} - static void dw_i2s_config(struct dw_i2s_dev *dev, int stream) { u32 ch_reg; @@ -305,12 +281,6 @@ static int dw_i2s_hw_params(struct snd_pcm_substream *substream, return 0; } -static void dw_i2s_shutdown(struct snd_pcm_substream *substream, - struct snd_soc_dai *dai) -{ - snd_soc_dai_set_dma_data(dai, substream, NULL); -} - static int dw_i2s_prepare(struct snd_pcm_substream *substream, struct snd_soc_dai *dai) { @@ -382,8 +352,6 @@ static int dw_i2s_set_fmt(struct snd_soc_dai *cpu_dai, unsigned int fmt) } static const struct snd_soc_dai_ops dw_i2s_dai_ops = { - .startup = dw_i2s_startup, - .shutdown = dw_i2s_shutdown, .hw_params = dw_i2s_hw_params, .prepare = dw_i2s_prepare, .trigger = dw_i2s_trigger, @@ -625,6 +593,14 @@ static int dw_configure_dai_by_dt(struct dw_i2s_dev *dev, } +static int dw_i2s_dai_probe(struct snd_soc_dai *dai) +{ + struct dw_i2s_dev *dev = snd_soc_dai_get_drvdata(dai); + + snd_soc_dai_init_dma_data(dai, &dev->play_dma_data, &dev->capture_dma_data); + return 0; +} + static int dw_i2s_probe(struct platform_device *pdev) { const struct i2s_platform_data *pdata = pdev->dev.platform_data; @@ -643,6 +619,7 @@ static int dw_i2s_probe(struct platform_device *pdev) return -ENOMEM; dw_i2s_dai->ops = &dw_i2s_dai_ops; + dw_i2s_dai->probe = dw_i2s_dai_probe; dev->i2s_base = devm_platform_get_and_ioremap_resource(pdev, 0, &res); if (IS_ERR(dev->i2s_base)) diff --git a/sound/soc/fsl/fsl_micfil.c b/sound/soc/fsl/fsl_micfil.c index 94341e4352b3..3f08082a55be 100644 --- a/sound/soc/fsl/fsl_micfil.c +++ b/sound/soc/fsl/fsl_micfil.c @@ -1159,7 +1159,7 @@ static int fsl_micfil_probe(struct platform_device *pdev) ret = devm_snd_dmaengine_pcm_register(&pdev->dev, NULL, 0); if (ret) { dev_err(&pdev->dev, "failed to pcm register\n"); - return ret; + goto err_pm_disable; } fsl_micfil_dai.capture.formats = micfil->soc->formats; @@ -1169,9 +1169,20 @@ static int fsl_micfil_probe(struct platform_device *pdev) if (ret) { dev_err(&pdev->dev, "failed to register component %s\n", fsl_micfil_component.name); + goto err_pm_disable; } return ret; + +err_pm_disable: + pm_runtime_disable(&pdev->dev); + + return ret; +} + +static void fsl_micfil_remove(struct platform_device *pdev) +{ + pm_runtime_disable(&pdev->dev); } static int __maybe_unused fsl_micfil_runtime_suspend(struct device *dev) @@ -1232,6 +1243,7 @@ static const struct dev_pm_ops fsl_micfil_pm_ops = { static struct platform_driver fsl_micfil_driver = { .probe = fsl_micfil_probe, + .remove_new = fsl_micfil_remove, .driver = { .name = "fsl-micfil-dai", .pm = &fsl_micfil_pm_ops, diff --git a/sound/soc/intel/avs/apl.c b/sound/soc/intel/avs/apl.c index 02683dce277a..1860099c782a 100644 --- a/sound/soc/intel/avs/apl.c +++ b/sound/soc/intel/avs/apl.c @@ -169,6 +169,7 @@ static bool apl_lp_streaming(struct avs_dev *adev) { struct avs_path *path; + spin_lock(&adev->path_list_lock); /* Any gateway without buffer allocated in LP area disqualifies D0IX. */ list_for_each_entry(path, &adev->path_list, node) { struct avs_path_pipeline *ppl; @@ -188,11 +189,14 @@ static bool apl_lp_streaming(struct avs_dev *adev) if (cfg->copier.dma_type == INVALID_OBJECT_ID) continue; - if (!mod->gtw_attrs.lp_buffer_alloc) + if (!mod->gtw_attrs.lp_buffer_alloc) { + spin_unlock(&adev->path_list_lock); return false; + } } } } + spin_unlock(&adev->path_list_lock); return true; } diff --git a/sound/soc/intel/avs/avs.h b/sound/soc/intel/avs/avs.h index d7fccdcb9c16..0cf38c9e768e 100644 --- a/sound/soc/intel/avs/avs.h +++ b/sound/soc/intel/avs/avs.h @@ -283,8 +283,8 @@ void avs_release_firmwares(struct avs_dev *adev); int avs_dsp_init_module(struct avs_dev *adev, u16 module_id, u8 ppl_instance_id, u8 core_id, u8 domain, void *param, u32 param_size, - u16 *instance_id); -void avs_dsp_delete_module(struct avs_dev *adev, u16 module_id, u16 instance_id, + u8 *instance_id); +void avs_dsp_delete_module(struct avs_dev *adev, u16 module_id, u8 instance_id, u8 ppl_instance_id, u8 core_id); int avs_dsp_create_pipeline(struct avs_dev *adev, u16 req_size, u8 priority, bool lp, u16 attributes, u8 *instance_id); diff --git a/sound/soc/intel/avs/board_selection.c b/sound/soc/intel/avs/board_selection.c index b2823c2107f7..60f8fb0bff95 100644 --- a/sound/soc/intel/avs/board_selection.c +++ b/sound/soc/intel/avs/board_selection.c @@ -443,7 +443,7 @@ static int avs_register_i2s_boards(struct avs_dev *adev) } for (mach = boards->machs; mach->id[0]; mach++) { - if (!acpi_dev_present(mach->id, NULL, -1)) + if (!acpi_dev_present(mach->id, mach->uid, -1)) continue; if (mach->machine_quirk) diff --git a/sound/soc/intel/avs/control.c b/sound/soc/intel/avs/control.c index a8b14b784f8a..3dfa2e9816db 100644 --- a/sound/soc/intel/avs/control.c +++ b/sound/soc/intel/avs/control.c @@ -21,17 +21,25 @@ static struct avs_dev *avs_get_kcontrol_adev(struct snd_kcontrol *kcontrol) return to_avs_dev(w->dapm->component->dev); } -static struct avs_path_module *avs_get_kcontrol_module(struct avs_dev *adev, u32 id) +static struct avs_path_module *avs_get_volume_module(struct avs_dev *adev, u32 id) { struct avs_path *path; struct avs_path_pipeline *ppl; struct avs_path_module *mod; - list_for_each_entry(path, &adev->path_list, node) - list_for_each_entry(ppl, &path->ppl_list, node) - list_for_each_entry(mod, &ppl->mod_list, node) - if (mod->template->ctl_id && mod->template->ctl_id == id) + spin_lock(&adev->path_list_lock); + list_for_each_entry(path, &adev->path_list, node) { + list_for_each_entry(ppl, &path->ppl_list, node) { + list_for_each_entry(mod, &ppl->mod_list, node) { + if (guid_equal(&mod->template->cfg_ext->type, &AVS_PEAKVOL_MOD_UUID) + && mod->template->ctl_id == id) { + spin_unlock(&adev->path_list_lock); return mod; + } + } + } + } + spin_unlock(&adev->path_list_lock); return NULL; } @@ -49,7 +57,7 @@ int avs_control_volume_get(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_va /* prevent access to modules while path is being constructed */ mutex_lock(&adev->path_mutex); - active_module = avs_get_kcontrol_module(adev, ctl_data->id); + active_module = avs_get_volume_module(adev, ctl_data->id); if (active_module) { ret = avs_ipc_peakvol_get_volume(adev, active_module->module_id, active_module->instance_id, &dspvols, @@ -89,7 +97,7 @@ int avs_control_volume_put(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_va changed = 1; } - active_module = avs_get_kcontrol_module(adev, ctl_data->id); + active_module = avs_get_volume_module(adev, ctl_data->id); if (active_module) { dspvol.channel_id = AVS_ALL_CHANNELS_MASK; dspvol.target_volume = *volume; diff --git a/sound/soc/intel/avs/dsp.c b/sound/soc/intel/avs/dsp.c index b881100d3e02..aa03af4473e9 100644 --- a/sound/soc/intel/avs/dsp.c +++ b/sound/soc/intel/avs/dsp.c @@ -225,7 +225,7 @@ err: int avs_dsp_init_module(struct avs_dev *adev, u16 module_id, u8 ppl_instance_id, u8 core_id, u8 domain, void *param, u32 param_size, - u16 *instance_id) + u8 *instance_id) { struct avs_module_entry mentry; bool was_loaded = false; @@ -272,7 +272,7 @@ err_mod_entry: return ret; } -void avs_dsp_delete_module(struct avs_dev *adev, u16 module_id, u16 instance_id, +void avs_dsp_delete_module(struct avs_dev *adev, u16 module_id, u8 instance_id, u8 ppl_instance_id, u8 core_id) { struct avs_module_entry mentry; diff --git a/sound/soc/intel/avs/messages.h b/sound/soc/intel/avs/messages.h index d3b60ae7d743..7f23a304b4a9 100644 --- a/sound/soc/intel/avs/messages.h +++ b/sound/soc/intel/avs/messages.h @@ -619,7 +619,7 @@ enum avs_channel_config { AVS_CHANNEL_CONFIG_DUAL_MONO = 9, AVS_CHANNEL_CONFIG_I2S_DUAL_STEREO_0 = 10, AVS_CHANNEL_CONFIG_I2S_DUAL_STEREO_1 = 11, - AVS_CHANNEL_CONFIG_4_CHANNEL = 12, + AVS_CHANNEL_CONFIG_7_1 = 12, AVS_CHANNEL_CONFIG_INVALID }; diff --git a/sound/soc/intel/avs/path.h b/sound/soc/intel/avs/path.h index 197222c5e008..657f7b093e80 100644 --- a/sound/soc/intel/avs/path.h +++ b/sound/soc/intel/avs/path.h @@ -37,7 +37,7 @@ struct avs_path_pipeline { struct avs_path_module { u16 module_id; - u16 instance_id; + u8 instance_id; union avs_gtw_attributes gtw_attrs; struct avs_tplg_module *template; diff --git a/sound/soc/intel/avs/pcm.c b/sound/soc/intel/avs/pcm.c index 31c032a0f7e4..1fbb2c2fadb5 100644 --- a/sound/soc/intel/avs/pcm.c +++ b/sound/soc/intel/avs/pcm.c @@ -468,21 +468,34 @@ static int avs_dai_fe_startup(struct snd_pcm_substream *substream, struct snd_so host_stream = snd_hdac_ext_stream_assign(bus, substream, HDAC_EXT_STREAM_TYPE_HOST); if (!host_stream) { - kfree(data); - return -EBUSY; + ret = -EBUSY; + goto err; } data->host_stream = host_stream; - snd_pcm_hw_constraint_integer(runtime, SNDRV_PCM_HW_PARAM_PERIODS); + ret = snd_pcm_hw_constraint_integer(runtime, SNDRV_PCM_HW_PARAM_PERIODS); + if (ret < 0) + goto err; + /* avoid wrap-around with wall-clock */ - snd_pcm_hw_constraint_minmax(runtime, SNDRV_PCM_HW_PARAM_BUFFER_TIME, 20, 178000000); - snd_pcm_hw_constraint_list(runtime, 0, SNDRV_PCM_HW_PARAM_RATE, &hw_rates); + ret = snd_pcm_hw_constraint_minmax(runtime, SNDRV_PCM_HW_PARAM_BUFFER_TIME, 20, 178000000); + if (ret < 0) + goto err; + + ret = snd_pcm_hw_constraint_list(runtime, 0, SNDRV_PCM_HW_PARAM_RATE, &hw_rates); + if (ret < 0) + goto err; + snd_pcm_set_sync(substream); dev_dbg(dai->dev, "%s fe STARTUP tag %d str %p", __func__, hdac_stream(host_stream)->stream_tag, substream); return 0; + +err: + kfree(data); + return ret; } static void avs_dai_fe_shutdown(struct snd_pcm_substream *substream, struct snd_soc_dai *dai) diff --git a/sound/soc/intel/avs/probes.c b/sound/soc/intel/avs/probes.c index 70a94201d6a5..275928281c6c 100644 --- a/sound/soc/intel/avs/probes.c +++ b/sound/soc/intel/avs/probes.c @@ -18,7 +18,7 @@ static int avs_dsp_init_probe(struct avs_dev *adev, union avs_connector_node_id { struct avs_probe_cfg cfg = {{0}}; struct avs_module_entry mentry; - u16 dummy; + u8 dummy; avs_get_module_entry(adev, &AVS_PROBE_MOD_UUID, &mentry); diff --git a/sound/soc/jz4740/jz4740-i2s.c b/sound/soc/jz4740/jz4740-i2s.c index 6d9cfe0a5041..d0f6c945d9ae 100644 --- a/sound/soc/jz4740/jz4740-i2s.c +++ b/sound/soc/jz4740/jz4740-i2s.c @@ -218,18 +218,48 @@ static int jz4740_i2s_set_fmt(struct snd_soc_dai *dai, unsigned int fmt) return 0; } +static int jz4740_i2s_get_i2sdiv(unsigned long mclk, unsigned long rate, + unsigned long i2sdiv_max) +{ + unsigned long div, rate1, rate2, err1, err2; + + div = mclk / (64 * rate); + if (div == 0) + div = 1; + + rate1 = mclk / (64 * div); + rate2 = mclk / (64 * (div + 1)); + + err1 = abs(rate1 - rate); + err2 = abs(rate2 - rate); + + /* + * Choose the divider that produces the smallest error in the + * output rate and reject dividers with a 5% or higher error. + * In the event that both dividers are outside the acceptable + * error margin, reject the rate to prevent distorted audio. + * (The number 5% is arbitrary.) + */ + if (div <= i2sdiv_max && err1 <= err2 && err1 < rate/20) + return div; + if (div < i2sdiv_max && err2 < rate/20) + return div + 1; + + return -EINVAL; +} + static int jz4740_i2s_hw_params(struct snd_pcm_substream *substream, struct snd_pcm_hw_params *params, struct snd_soc_dai *dai) { struct jz4740_i2s *i2s = snd_soc_dai_get_drvdata(dai); struct regmap_field *div_field; + unsigned long i2sdiv_max; unsigned int sample_size; - uint32_t ctrl; - int div; + uint32_t ctrl, conf; + int div = 1; regmap_read(i2s->regmap, JZ_REG_AIC_CTRL, &ctrl); - - div = clk_get_rate(i2s->clk_i2s) / (64 * params_rate(params)); + regmap_read(i2s->regmap, JZ_REG_AIC_CONF, &conf); switch (params_format(params)) { case SNDRV_PCM_FORMAT_S8: @@ -258,11 +288,27 @@ static int jz4740_i2s_hw_params(struct snd_pcm_substream *substream, ctrl &= ~JZ_AIC_CTRL_MONO_TO_STEREO; div_field = i2s->field_i2sdiv_playback; + i2sdiv_max = GENMASK(i2s->soc_info->field_i2sdiv_playback.msb, + i2s->soc_info->field_i2sdiv_playback.lsb); } else { ctrl &= ~JZ_AIC_CTRL_INPUT_SAMPLE_SIZE; ctrl |= FIELD_PREP(JZ_AIC_CTRL_INPUT_SAMPLE_SIZE, sample_size); div_field = i2s->field_i2sdiv_capture; + i2sdiv_max = GENMASK(i2s->soc_info->field_i2sdiv_capture.msb, + i2s->soc_info->field_i2sdiv_capture.lsb); + } + + /* + * Only calculate I2SDIV if we're supplying the bit or frame clock. + * If the codec is supplying both clocks then the divider output is + * unused, and we don't want it to limit the allowed sample rates. + */ + if (conf & (JZ_AIC_CONF_BIT_CLK_MASTER | JZ_AIC_CONF_SYNC_CLK_MASTER)) { + div = jz4740_i2s_get_i2sdiv(clk_get_rate(i2s->clk_i2s), + params_rate(params), i2sdiv_max); + if (div < 0) + return div; } regmap_write(i2s->regmap, JZ_REG_AIC_CTRL, ctrl); diff --git a/sound/soc/mediatek/mt8186/mt8186-afe-clk.c b/sound/soc/mediatek/mt8186/mt8186-afe-clk.c index a6b4f29049bb..539e3a023bc4 100644 --- a/sound/soc/mediatek/mt8186/mt8186-afe-clk.c +++ b/sound/soc/mediatek/mt8186/mt8186-afe-clk.c @@ -644,9 +644,3 @@ int mt8186_init_clock(struct mtk_base_afe *afe) return 0; } - -void mt8186_deinit_clock(void *priv) -{ - struct mtk_base_afe *afe = priv; - mt8186_audsys_clk_unregister(afe); -} diff --git a/sound/soc/mediatek/mt8186/mt8186-afe-clk.h b/sound/soc/mediatek/mt8186/mt8186-afe-clk.h index d5988717d8f2..a9d59e506d9a 100644 --- a/sound/soc/mediatek/mt8186/mt8186-afe-clk.h +++ b/sound/soc/mediatek/mt8186/mt8186-afe-clk.h @@ -81,7 +81,6 @@ enum { struct mtk_base_afe; int mt8186_set_audio_int_bus_parent(struct mtk_base_afe *afe, int clk_id); int mt8186_init_clock(struct mtk_base_afe *afe); -void mt8186_deinit_clock(void *priv); int mt8186_afe_enable_cgs(struct mtk_base_afe *afe); void mt8186_afe_disable_cgs(struct mtk_base_afe *afe); int mt8186_afe_enable_clock(struct mtk_base_afe *afe); diff --git a/sound/soc/mediatek/mt8186/mt8186-afe-pcm.c b/sound/soc/mediatek/mt8186/mt8186-afe-pcm.c index 41172a82103e..a868a04ed4e7 100644 --- a/sound/soc/mediatek/mt8186/mt8186-afe-pcm.c +++ b/sound/soc/mediatek/mt8186/mt8186-afe-pcm.c @@ -2848,10 +2848,6 @@ static int mt8186_afe_pcm_dev_probe(struct platform_device *pdev) return ret; } - ret = devm_add_action_or_reset(dev, mt8186_deinit_clock, (void *)afe); - if (ret) - return ret; - /* init memif */ afe->memif_32bit_supported = 0; afe->memif_size = MT8186_MEMIF_NUM; diff --git a/sound/soc/mediatek/mt8186/mt8186-audsys-clk.c b/sound/soc/mediatek/mt8186/mt8186-audsys-clk.c index 578969ca91c8..5666be6b1bd2 100644 --- a/sound/soc/mediatek/mt8186/mt8186-audsys-clk.c +++ b/sound/soc/mediatek/mt8186/mt8186-audsys-clk.c @@ -84,6 +84,29 @@ static const struct afe_gate aud_clks[CLK_AUD_NR_CLK] = { GATE_AUD2(CLK_AUD_ETDM_OUT1_BCLK, "aud_etdm_out1_bclk", "top_audio", 24), }; +static void mt8186_audsys_clk_unregister(void *data) +{ + struct mtk_base_afe *afe = data; + struct mt8186_afe_private *afe_priv = afe->platform_priv; + struct clk *clk; + struct clk_lookup *cl; + int i; + + if (!afe_priv) + return; + + for (i = 0; i < CLK_AUD_NR_CLK; i++) { + cl = afe_priv->lookup[i]; + if (!cl) + continue; + + clk = cl->clk; + clk_unregister_gate(clk); + + clkdev_drop(cl); + } +} + int mt8186_audsys_clk_register(struct mtk_base_afe *afe) { struct mt8186_afe_private *afe_priv = afe->platform_priv; @@ -124,27 +147,6 @@ int mt8186_audsys_clk_register(struct mtk_base_afe *afe) afe_priv->lookup[i] = cl; } - return 0; + return devm_add_action_or_reset(afe->dev, mt8186_audsys_clk_unregister, afe); } -void mt8186_audsys_clk_unregister(struct mtk_base_afe *afe) -{ - struct mt8186_afe_private *afe_priv = afe->platform_priv; - struct clk *clk; - struct clk_lookup *cl; - int i; - - if (!afe_priv) - return; - - for (i = 0; i < CLK_AUD_NR_CLK; i++) { - cl = afe_priv->lookup[i]; - if (!cl) - continue; - - clk = cl->clk; - clk_unregister_gate(clk); - - clkdev_drop(cl); - } -} diff --git a/sound/soc/mediatek/mt8186/mt8186-audsys-clk.h b/sound/soc/mediatek/mt8186/mt8186-audsys-clk.h index b8d6a06e11e8..897a2914dc19 100644 --- a/sound/soc/mediatek/mt8186/mt8186-audsys-clk.h +++ b/sound/soc/mediatek/mt8186/mt8186-audsys-clk.h @@ -10,6 +10,5 @@ #define _MT8186_AUDSYS_CLK_H_ int mt8186_audsys_clk_register(struct mtk_base_afe *afe); -void mt8186_audsys_clk_unregister(struct mtk_base_afe *afe); #endif diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c index adb69d7820a8..4fb1ac8e1c4a 100644 --- a/sound/soc/soc-pcm.c +++ b/sound/soc/soc-pcm.c @@ -2405,6 +2405,9 @@ int dpcm_be_dai_prepare(struct snd_soc_pcm_runtime *fe, int stream) if (!snd_soc_dpcm_be_can_update(fe, be, stream)) continue; + if (!snd_soc_dpcm_can_be_prepared(fe, be, stream)) + continue; + if ((be->dpcm[stream].state != SND_SOC_DPCM_STATE_HW_PARAMS) && (be->dpcm[stream].state != SND_SOC_DPCM_STATE_STOP) && (be->dpcm[stream].state != SND_SOC_DPCM_STATE_SUSPEND) && @@ -3042,3 +3045,20 @@ int snd_soc_dpcm_can_be_params(struct snd_soc_pcm_runtime *fe, return snd_soc_dpcm_check_state(fe, be, stream, state, ARRAY_SIZE(state)); } EXPORT_SYMBOL_GPL(snd_soc_dpcm_can_be_params); + +/* + * We can only prepare a BE DAI if any of it's FE are not prepared, + * running or paused for the specified stream direction. + */ +int snd_soc_dpcm_can_be_prepared(struct snd_soc_pcm_runtime *fe, + struct snd_soc_pcm_runtime *be, int stream) +{ + const enum snd_soc_dpcm_state state[] = { + SND_SOC_DPCM_STATE_START, + SND_SOC_DPCM_STATE_PAUSED, + SND_SOC_DPCM_STATE_PREPARE, + }; + + return snd_soc_dpcm_check_state(fe, be, stream, state, ARRAY_SIZE(state)); +} +EXPORT_SYMBOL_GPL(snd_soc_dpcm_can_be_prepared); diff --git a/sound/soc/sof/amd/acp-ipc.c b/sound/soc/sof/amd/acp-ipc.c index 4e0c48a36159..749e856dc601 100644 --- a/sound/soc/sof/amd/acp-ipc.c +++ b/sound/soc/sof/amd/acp-ipc.c @@ -209,7 +209,12 @@ int acp_sof_ipc_msg_data(struct snd_sof_dev *sdev, struct snd_sof_pcm_stream *sp acp_mailbox_read(sdev, offset, p, sz); } else { struct snd_pcm_substream *substream = sps->substream; - struct acp_dsp_stream *stream = substream->runtime->private_data; + struct acp_dsp_stream *stream; + + if (!substream || !substream->runtime) + return -ESTRPIPE; + + stream = substream->runtime->private_data; if (!stream) return -ESTRPIPE; diff --git a/sound/soc/sof/debug.c b/sound/soc/sof/debug.c index b42b5982cbbc..d547318e0d32 100644 --- a/sound/soc/sof/debug.c +++ b/sound/soc/sof/debug.c @@ -438,8 +438,8 @@ void snd_sof_handle_fw_exception(struct snd_sof_dev *sdev, const char *msg) /* should we prevent DSP entering D3 ? */ if (!sdev->ipc_dump_printed) dev_info(sdev->dev, - "preventing DSP entering D3 state to preserve context\n"); - pm_runtime_get_noresume(sdev->dev); + "Attempting to prevent DSP from entering D3 state to preserve context\n"); + pm_runtime_get_if_in_use(sdev->dev); } /* dump vital information to the logs */ diff --git a/sound/soc/sof/intel/hda-mlink.c b/sound/soc/sof/intel/hda-mlink.c index 775582ab7494..b7cbf66badf5 100644 --- a/sound/soc/sof/intel/hda-mlink.c +++ b/sound/soc/sof/intel/hda-mlink.c @@ -19,6 +19,9 @@ #if IS_ENABLED(CONFIG_SND_SOC_SOF_HDA_MLINK) +/* worst-case number of sublinks is used for sublink refcount array allocation only */ +#define HDAML_MAX_SUBLINKS (AZX_ML_LCTL_CPA_SHIFT - AZX_ML_LCTL_SPA_SHIFT) + /** * struct hdac_ext2_link - HDAudio extended+alternate link * @@ -33,6 +36,7 @@ * @leptr: extended link pointer * @eml_lock: mutual exclusion to access shared registers e.g. CPA/SPA bits * in LCTL register + * @sublink_ref_count: array of refcounts, required to power-manage sublinks independently * @base_ptr: pointer to shim/ip/shim_vs space * @instance_offset: offset between each of @slcount instances managed by link * @shim_offset: offset to SHIM register base @@ -53,6 +57,7 @@ struct hdac_ext2_link { u32 leptr; struct mutex eml_lock; /* prevent concurrent access to e.g. CPA/SPA */ + int sublink_ref_count[HDAML_MAX_SUBLINKS]; /* internal values computed from LCAP contents */ void __iomem *base_ptr; @@ -68,6 +73,7 @@ struct hdac_ext2_link { #define AZX_REG_SDW_SHIM_OFFSET 0x0 #define AZX_REG_SDW_IP_OFFSET 0x100 #define AZX_REG_SDW_VS_SHIM_OFFSET 0x6000 +#define AZX_REG_SDW_SHIM_PCMSyCM(y) (0x16 + 0x4 * (y)) /* only one instance supported */ #define AZX_REG_INTEL_DMIC_SHIM_OFFSET 0x0 @@ -91,7 +97,7 @@ struct hdac_ext2_link { */ static int hdaml_lnk_enum(struct device *dev, struct hdac_ext2_link *h2link, - void __iomem *ml_addr, int link_idx) + void __iomem *remap_addr, void __iomem *ml_addr, int link_idx) { struct hdac_ext_link *hlink = &h2link->hext_link; u32 base_offset; @@ -126,15 +132,16 @@ static int hdaml_lnk_enum(struct device *dev, struct hdac_ext2_link *h2link, link_idx, h2link->slcount); /* find IP ID and offsets */ - h2link->leptr = readl(hlink->ml_addr + AZX_REG_ML_LEPTR); + h2link->leptr = readl(ml_addr + AZX_REG_ML_LEPTR); h2link->elid = FIELD_GET(AZX_REG_ML_LEPTR_ID, h2link->leptr); base_offset = FIELD_GET(AZX_REG_ML_LEPTR_PTR, h2link->leptr); - h2link->base_ptr = hlink->ml_addr + base_offset; + h2link->base_ptr = remap_addr + base_offset; switch (h2link->elid) { case AZX_REG_ML_LEPTR_ID_SDW: + h2link->instance_offset = AZX_REG_SDW_INSTANCE_OFFSET; h2link->shim_offset = AZX_REG_SDW_SHIM_OFFSET; h2link->ip_offset = AZX_REG_SDW_IP_OFFSET; h2link->shim_vs_offset = AZX_REG_SDW_VS_SHIM_OFFSET; @@ -149,6 +156,7 @@ static int hdaml_lnk_enum(struct device *dev, struct hdac_ext2_link *h2link, link_idx, base_offset); break; case AZX_REG_ML_LEPTR_ID_INTEL_SSP: + h2link->instance_offset = AZX_REG_INTEL_SSP_INSTANCE_OFFSET; h2link->shim_offset = AZX_REG_INTEL_SSP_SHIM_OFFSET; h2link->ip_offset = AZX_REG_INTEL_SSP_IP_OFFSET; h2link->shim_vs_offset = AZX_REG_INTEL_SSP_VS_SHIM_OFFSET; @@ -333,6 +341,21 @@ static void hdaml_link_set_lsdiid(u32 __iomem *lsdiid, int dev_num) writel(val, lsdiid); } +static void hdaml_shim_map_stream_ch(u16 __iomem *pcmsycm, int lchan, int hchan, + int stream_id, int dir) +{ + u16 val; + + val = readw(pcmsycm); + + u16p_replace_bits(&val, lchan, GENMASK(3, 0)); + u16p_replace_bits(&val, hchan, GENMASK(7, 4)); + u16p_replace_bits(&val, stream_id, GENMASK(13, 8)); + u16p_replace_bits(&val, dir, BIT(15)); + + writew(val, pcmsycm); +} + static void hdaml_lctl_offload_enable(u32 __iomem *lctl, bool enable) { u32 val = readl(lctl); @@ -364,7 +387,7 @@ static int hda_ml_alloc_h2link(struct hdac_bus *bus, int index) hlink->bus = bus; hlink->ml_addr = bus->mlcap + AZX_ML_BASE + (AZX_ML_INTERVAL * index); - ret = hdaml_lnk_enum(bus->dev, h2link, hlink->ml_addr, index); + ret = hdaml_lnk_enum(bus->dev, h2link, bus->remap_addr, hlink->ml_addr, index); if (ret < 0) { kfree(h2link); return ret; @@ -641,8 +664,13 @@ static int hdac_bus_eml_power_up_base(struct hdac_bus *bus, bool alt, int elid, if (eml_lock) mutex_lock(&h2link->eml_lock); - if (++hlink->ref_count > 1) - goto skip_init; + if (!alt) { + if (++hlink->ref_count > 1) + goto skip_init; + } else { + if (++h2link->sublink_ref_count[sublink] > 1) + goto skip_init; + } ret = hdaml_link_init(hlink->ml_addr + AZX_REG_ML_LCTL, sublink); @@ -684,9 +712,13 @@ static int hdac_bus_eml_power_down_base(struct hdac_bus *bus, bool alt, int elid if (eml_lock) mutex_lock(&h2link->eml_lock); - if (--hlink->ref_count > 0) - goto skip_shutdown; - + if (!alt) { + if (--hlink->ref_count > 0) + goto skip_shutdown; + } else { + if (--h2link->sublink_ref_count[sublink] > 0) + goto skip_shutdown; + } ret = hdaml_link_shutdown(hlink->ml_addr + AZX_REG_ML_LCTL, sublink); skip_shutdown: @@ -740,6 +772,40 @@ int hdac_bus_eml_sdw_set_lsdiid(struct hdac_bus *bus, int sublink, int dev_num) return 0; } EXPORT_SYMBOL_NS(hdac_bus_eml_sdw_set_lsdiid, SND_SOC_SOF_HDA_MLINK); +/* + * the 'y' parameter comes from the PCMSyCM hardware register naming. 'y' refers to the + * PDI index, i.e. the FIFO used for RX or TX + */ +int hdac_bus_eml_sdw_map_stream_ch(struct hdac_bus *bus, int sublink, int y, + int channel_mask, int stream_id, int dir) +{ + struct hdac_ext2_link *h2link; + u16 __iomem *pcmsycm; + u16 val; + + h2link = find_ext2_link(bus, true, AZX_REG_ML_LEPTR_ID_SDW); + if (!h2link) + return -ENODEV; + + pcmsycm = h2link->base_ptr + h2link->shim_offset + + h2link->instance_offset * sublink + + AZX_REG_SDW_SHIM_PCMSyCM(y); + + mutex_lock(&h2link->eml_lock); + + hdaml_shim_map_stream_ch(pcmsycm, 0, hweight32(channel_mask), + stream_id, dir); + + mutex_unlock(&h2link->eml_lock); + + val = readw(pcmsycm); + + dev_dbg(bus->dev, "channel_mask %#x stream_id %d dir %d pcmscm %#x\n", + channel_mask, stream_id, dir, val); + + return 0; +} EXPORT_SYMBOL_NS(hdac_bus_eml_sdw_map_stream_ch, SND_SOC_SOF_HDA_MLINK); + void hda_bus_ml_put_all(struct hdac_bus *bus) { struct hdac_ext_link *hlink; @@ -836,6 +902,18 @@ struct hdac_ext_link *hdac_bus_eml_dmic_get_hlink(struct hdac_bus *bus) } EXPORT_SYMBOL_NS(hdac_bus_eml_dmic_get_hlink, SND_SOC_SOF_HDA_MLINK); +struct hdac_ext_link *hdac_bus_eml_sdw_get_hlink(struct hdac_bus *bus) +{ + struct hdac_ext2_link *h2link; + + h2link = find_ext2_link(bus, true, AZX_REG_ML_LEPTR_ID_SDW); + if (!h2link) + return NULL; + + return &h2link->hext_link; +} +EXPORT_SYMBOL_NS(hdac_bus_eml_sdw_get_hlink, SND_SOC_SOF_HDA_MLINK); + int hdac_bus_eml_enable_offload(struct hdac_bus *bus, bool alt, int elid, bool enable) { struct hdac_ext2_link *h2link; diff --git a/sound/soc/sof/ipc3-topology.c b/sound/soc/sof/ipc3-topology.c index fc1eb8e2de2c..ba4ef290b634 100644 --- a/sound/soc/sof/ipc3-topology.c +++ b/sound/soc/sof/ipc3-topology.c @@ -2103,10 +2103,13 @@ static int sof_ipc3_dai_config(struct snd_sof_dev *sdev, struct snd_sof_widget * * For the case of PAUSE/HW_FREE, since there are no quirks, flags can be used as is. */ - if (flags & SOF_DAI_CONFIG_FLAGS_HW_PARAMS) + if (flags & SOF_DAI_CONFIG_FLAGS_HW_PARAMS) { + /* Clear stale command */ + config->flags &= ~SOF_DAI_CONFIG_FLAGS_CMD_MASK; config->flags |= flags; - else + } else { config->flags = flags; + } /* only send the IPC if the widget is set up in the DSP */ if (swidget->use_count > 0) { diff --git a/sound/soc/sof/ipc4-topology.c b/sound/soc/sof/ipc4-topology.c index 059eebf0a687..5abe616a2054 100644 --- a/sound/soc/sof/ipc4-topology.c +++ b/sound/soc/sof/ipc4-topology.c @@ -59,7 +59,7 @@ static const struct sof_topology_token ipc4_in_audio_format_tokens[] = { audio_fmt.interleaving_style)}, {SOF_TKN_CAVS_AUDIO_FORMAT_IN_FMT_CFG, SND_SOC_TPLG_TUPLE_TYPE_WORD, get_token_u32, offsetof(struct sof_ipc4_pin_format, audio_fmt.fmt_cfg)}, - {SOF_TKN_CAVS_AUDIO_FORMAT_PIN_INDEX, SND_SOC_TPLG_TUPLE_TYPE_WORD, get_token_u32, + {SOF_TKN_CAVS_AUDIO_FORMAT_INPUT_PIN_INDEX, SND_SOC_TPLG_TUPLE_TYPE_WORD, get_token_u32, offsetof(struct sof_ipc4_pin_format, pin_index)}, {SOF_TKN_CAVS_AUDIO_FORMAT_IBS, SND_SOC_TPLG_TUPLE_TYPE_WORD, get_token_u32, offsetof(struct sof_ipc4_pin_format, buffer_size)}, @@ -79,7 +79,7 @@ static const struct sof_topology_token ipc4_out_audio_format_tokens[] = { audio_fmt.interleaving_style)}, {SOF_TKN_CAVS_AUDIO_FORMAT_OUT_FMT_CFG, SND_SOC_TPLG_TUPLE_TYPE_WORD, get_token_u32, offsetof(struct sof_ipc4_pin_format, audio_fmt.fmt_cfg)}, - {SOF_TKN_CAVS_AUDIO_FORMAT_PIN_INDEX, SND_SOC_TPLG_TUPLE_TYPE_WORD, get_token_u32, + {SOF_TKN_CAVS_AUDIO_FORMAT_OUTPUT_PIN_INDEX, SND_SOC_TPLG_TUPLE_TYPE_WORD, get_token_u32, offsetof(struct sof_ipc4_pin_format, pin_index)}, {SOF_TKN_CAVS_AUDIO_FORMAT_OBS, SND_SOC_TPLG_TUPLE_TYPE_WORD, get_token_u32, offsetof(struct sof_ipc4_pin_format, buffer_size)}, diff --git a/sound/soc/sof/pcm.c b/sound/soc/sof/pcm.c index 567db32173a8..d0ab6f390734 100644 --- a/sound/soc/sof/pcm.c +++ b/sound/soc/sof/pcm.c @@ -643,16 +643,17 @@ static int sof_pcm_probe(struct snd_soc_component *component) "%s/%s", plat_data->tplg_filename_prefix, plat_data->tplg_filename); - if (!tplg_filename) - return -ENOMEM; + if (!tplg_filename) { + ret = -ENOMEM; + goto pm_error; + } ret = snd_sof_load_topology(component, tplg_filename); - if (ret < 0) { + if (ret < 0) dev_err(component->dev, "error: failed to load DSP topology %d\n", ret); - return ret; - } +pm_error: pm_runtime_mark_last_busy(component->dev); pm_runtime_put_autosuspend(component->dev); diff --git a/sound/soc/sof/pm.c b/sound/soc/sof/pm.c index 2fdbc53ca715..2b232442e84b 100644 --- a/sound/soc/sof/pm.c +++ b/sound/soc/sof/pm.c @@ -164,7 +164,7 @@ static int sof_resume(struct device *dev, bool runtime_resume) ret = tplg_ops->set_up_all_pipelines(sdev, false); if (ret < 0) { dev_err(sdev->dev, "Failed to restore pipeline after resume %d\n", ret); - return ret; + goto setup_fail; } } @@ -178,6 +178,18 @@ static int sof_resume(struct device *dev, bool runtime_resume) dev_err(sdev->dev, "ctx_restore IPC error during resume: %d\n", ret); } +setup_fail: +#if IS_ENABLED(CONFIG_SND_SOC_SOF_DEBUG_ENABLE_DEBUGFS_CACHE) + if (ret < 0) { + /* + * Debugfs cannot be read in runtime suspend, so cache + * the contents upon failure. This allows to capture + * possible DSP coredump information. + */ + sof_cache_debugfs(sdev); + } +#endif + return ret; } diff --git a/sound/soc/sof/sof-client-probes.c b/sound/soc/sof/sof-client-probes.c index fff126808bc0..8d9e9d5f40e4 100644 --- a/sound/soc/sof/sof-client-probes.c +++ b/sound/soc/sof/sof-client-probes.c @@ -218,12 +218,7 @@ static ssize_t sof_probes_dfs_points_read(struct file *file, char __user *to, ret = ipc->points_info(cdev, &desc, &num_desc); if (ret < 0) - goto exit; - - pm_runtime_mark_last_busy(dev); - err = pm_runtime_put_autosuspend(dev); - if (err < 0) - dev_err_ratelimited(dev, "debugfs read failed to idle %d\n", err); + goto pm_error; for (i = 0; i < num_desc; i++) { offset = strlen(buf); @@ -241,6 +236,13 @@ static ssize_t sof_probes_dfs_points_read(struct file *file, char __user *to, ret = simple_read_from_buffer(to, count, ppos, buf, strlen(buf)); kfree(desc); + +pm_error: + pm_runtime_mark_last_busy(dev); + err = pm_runtime_put_autosuspend(dev); + if (err < 0) + dev_err_ratelimited(dev, "debugfs read failed to idle %d\n", err); + exit: kfree(buf); return ret; diff --git a/sound/soc/sof/topology.c b/sound/soc/sof/topology.c index d3d536b0a8f5..f160dc454b44 100644 --- a/sound/soc/sof/topology.c +++ b/sound/soc/sof/topology.c @@ -586,6 +586,10 @@ static int sof_copy_tuples(struct snd_sof_dev *sdev, struct snd_soc_tplg_vendor_ if (*num_copied_tuples == tuples_size) return 0; } + + /* stop when we've found the required token instances */ + if (found == num_tokens * token_instance_num) + return 0; } /* next array */ @@ -1261,7 +1265,7 @@ static int sof_widget_parse_tokens(struct snd_soc_component *scomp, struct snd_s if (num_sets > 1) { struct snd_sof_tuple *new_tuples; - num_tuples += token_list[object_token_list[i]].count * num_sets; + num_tuples += token_list[object_token_list[i]].count * (num_sets - 1); new_tuples = krealloc(swidget->tuples, sizeof(*new_tuples) * num_tuples, GFP_KERNEL); if (!new_tuples) { diff --git a/sound/usb/format.c b/sound/usb/format.c index 4b1c5ba121f3..ab5fed9f55b6 100644 --- a/sound/usb/format.c +++ b/sound/usb/format.c @@ -423,6 +423,7 @@ static int line6_parse_audio_format_rates_quirk(struct snd_usb_audio *chip, case USB_ID(0x0e41, 0x4248): /* Line6 Helix >= fw 2.82 */ case USB_ID(0x0e41, 0x4249): /* Line6 Helix Rack >= fw 2.82 */ case USB_ID(0x0e41, 0x424a): /* Line6 Helix LT >= fw 2.82 */ + case USB_ID(0x0e41, 0x424b): /* Line6 Pod Go */ case USB_ID(0x19f7, 0x0011): /* Rode Rodecaster Pro */ return set_fixed_rate(fp, 48000, SNDRV_PCM_RATE_48000); } diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h index f8129c624b07..f7ddd73a8c0f 100644 --- a/tools/arch/arm64/include/uapi/asm/kvm.h +++ b/tools/arch/arm64/include/uapi/asm/kvm.h @@ -198,6 +198,15 @@ struct kvm_arm_copy_mte_tags { __u64 reserved[2]; }; +/* + * Counter/Timer offset structure. Describe the virtual/physical offset. + * To be used with KVM_ARM_SET_COUNTER_OFFSET. + */ +struct kvm_arm_counter_offset { + __u64 counter_offset; + __u64 reserved; +}; + #define KVM_ARM_TAGS_TO_GUEST 0 #define KVM_ARM_TAGS_FROM_GUEST 1 @@ -372,6 +381,10 @@ enum { #endif }; +/* Device Control API on vm fd */ +#define KVM_ARM_VM_SMCCC_CTRL 0 +#define KVM_ARM_VM_SMCCC_FILTER 0 + /* Device Control API: ARM VGIC */ #define KVM_DEV_ARM_VGIC_GRP_ADDR 0 #define KVM_DEV_ARM_VGIC_GRP_DIST_REGS 1 @@ -411,6 +424,8 @@ enum { #define KVM_ARM_VCPU_TIMER_CTRL 1 #define KVM_ARM_VCPU_TIMER_IRQ_VTIMER 0 #define KVM_ARM_VCPU_TIMER_IRQ_PTIMER 1 +#define KVM_ARM_VCPU_TIMER_IRQ_HVTIMER 2 +#define KVM_ARM_VCPU_TIMER_IRQ_HPTIMER 3 #define KVM_ARM_VCPU_PVTIME_CTRL 2 #define KVM_ARM_VCPU_PVTIME_IPA 0 @@ -469,6 +484,27 @@ enum { /* run->fail_entry.hardware_entry_failure_reason codes. */ #define KVM_EXIT_FAIL_ENTRY_CPU_UNSUPPORTED (1ULL << 0) +enum kvm_smccc_filter_action { + KVM_SMCCC_FILTER_HANDLE = 0, + KVM_SMCCC_FILTER_DENY, + KVM_SMCCC_FILTER_FWD_TO_USER, + +#ifdef __KERNEL__ + NR_SMCCC_FILTER_ACTIONS +#endif +}; + +struct kvm_smccc_filter { + __u32 base; + __u32 nr_functions; + __u8 action; + __u8 pad[15]; +}; + +/* arm64-specific KVM_EXIT_HYPERCALL flags */ +#define KVM_HYPERCALL_EXIT_SMC (1U << 0) +#define KVM_HYPERCALL_EXIT_16BIT (1U << 1) + #endif #endif /* __ARM_KVM_H__ */ diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index b89005819cd5..cb8ca46213be 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -97,7 +97,7 @@ #define X86_FEATURE_SYSENTER32 ( 3*32+15) /* "" sysenter in IA32 userspace */ #define X86_FEATURE_REP_GOOD ( 3*32+16) /* REP microcode works well */ #define X86_FEATURE_AMD_LBR_V2 ( 3*32+17) /* AMD Last Branch Record Extension Version 2 */ -#define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) /* "" LFENCE synchronizes RDTSC */ +/* FREE, was #define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) "" LFENCE synchronizes RDTSC */ #define X86_FEATURE_ACC_POWER ( 3*32+19) /* AMD Accumulated Power Mechanism */ #define X86_FEATURE_NOPL ( 3*32+20) /* The NOPL (0F 1F) instructions */ #define X86_FEATURE_ALWAYS ( 3*32+21) /* "" Always-present feature */ @@ -226,10 +226,9 @@ /* Virtualization flags: Linux defined, word 8 */ #define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ -#define X86_FEATURE_VNMI ( 8*32+ 1) /* Intel Virtual NMI */ -#define X86_FEATURE_FLEXPRIORITY ( 8*32+ 2) /* Intel FlexPriority */ -#define X86_FEATURE_EPT ( 8*32+ 3) /* Intel Extended Page Table */ -#define X86_FEATURE_VPID ( 8*32+ 4) /* Intel Virtual Processor ID */ +#define X86_FEATURE_FLEXPRIORITY ( 8*32+ 1) /* Intel FlexPriority */ +#define X86_FEATURE_EPT ( 8*32+ 2) /* Intel Extended Page Table */ +#define X86_FEATURE_VPID ( 8*32+ 3) /* Intel Virtual Processor ID */ #define X86_FEATURE_VMMCALL ( 8*32+15) /* Prefer VMMCALL to VMCALL */ #define X86_FEATURE_XENPV ( 8*32+16) /* "" Xen paravirtual guest */ @@ -307,14 +306,21 @@ #define X86_FEATURE_SGX_EDECCSSA (11*32+18) /* "" SGX EDECCSSA user leaf function */ #define X86_FEATURE_CALL_DEPTH (11*32+19) /* "" Call depth tracking for RSB stuffing */ #define X86_FEATURE_MSR_TSX_CTRL (11*32+20) /* "" MSR IA32_TSX_CTRL (Intel) implemented */ +#define X86_FEATURE_SMBA (11*32+21) /* "" Slow Memory Bandwidth Allocation */ +#define X86_FEATURE_BMEC (11*32+22) /* "" Bandwidth Monitoring Event Configuration */ /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ #define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI instructions */ #define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */ #define X86_FEATURE_CMPCCXADD (12*32+ 7) /* "" CMPccXADD instructions */ +#define X86_FEATURE_ARCH_PERFMON_EXT (12*32+ 8) /* "" Intel Architectural PerfMon Extension */ +#define X86_FEATURE_FZRM (12*32+10) /* "" Fast zero-length REP MOVSB */ +#define X86_FEATURE_FSRS (12*32+11) /* "" Fast short REP STOSB */ +#define X86_FEATURE_FSRC (12*32+12) /* "" Fast short REP {CMPSB,SCASB} */ #define X86_FEATURE_LKGS (12*32+18) /* "" Load "kernel" (userspace) GS */ #define X86_FEATURE_AMX_FP16 (12*32+21) /* "" AMX fp16 Support */ #define X86_FEATURE_AVX_IFMA (12*32+23) /* "" Support for VPMADD52[H,L]UQ */ +#define X86_FEATURE_LAM (12*32+26) /* Linear Address Masking */ /* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */ #define X86_FEATURE_CLZERO (13*32+ 0) /* CLZERO instruction */ @@ -331,6 +337,7 @@ #define X86_FEATURE_VIRT_SSBD (13*32+25) /* Virtualized Speculative Store Bypass Disable */ #define X86_FEATURE_AMD_SSB_NO (13*32+26) /* "" Speculative Store Bypass is fixed in hardware. */ #define X86_FEATURE_CPPC (13*32+27) /* Collaborative Processor Performance Control */ +#define X86_FEATURE_AMD_PSFD (13*32+28) /* "" Predictive Store Forwarding Disable */ #define X86_FEATURE_BTC_NO (13*32+29) /* "" Not vulnerable to Branch Type Confusion */ #define X86_FEATURE_BRS (13*32+31) /* Branch Sampling available */ @@ -363,6 +370,7 @@ #define X86_FEATURE_VGIF (15*32+16) /* Virtual GIF */ #define X86_FEATURE_X2AVIC (15*32+18) /* Virtual x2apic */ #define X86_FEATURE_V_SPEC_CTRL (15*32+20) /* Virtual SPEC_CTRL */ +#define X86_FEATURE_VNMI (15*32+25) /* Virtual NMI */ #define X86_FEATURE_SVME_ADDR_CHK (15*32+28) /* "" SVME addr check */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (ECX), word 16 */ @@ -427,6 +435,13 @@ #define X86_FEATURE_V_TSC_AUX (19*32+ 9) /* "" Virtual TSC_AUX */ #define X86_FEATURE_SME_COHERENT (19*32+10) /* "" AMD hardware-enforced cache coherency */ +/* AMD-defined Extended Feature 2 EAX, CPUID level 0x80000021 (EAX), word 20 */ +#define X86_FEATURE_NO_NESTED_DATA_BP (20*32+ 0) /* "" No Nested Data Breakpoints */ +#define X86_FEATURE_LFENCE_RDTSC (20*32+ 2) /* "" LFENCE always serializing / synchronizes RDTSC */ +#define X86_FEATURE_NULL_SEL_CLR_BASE (20*32+ 6) /* "" Null Selector Clears Base */ +#define X86_FEATURE_AUTOIBRS (20*32+ 8) /* "" Automatic IBRS */ +#define X86_FEATURE_NO_SMM_CTL_MSR (20*32+ 9) /* "" SMM_CTL MSR is not present */ + /* * BUG word(s) */ @@ -467,5 +482,6 @@ #define X86_BUG_MMIO_UNKNOWN X86_BUG(26) /* CPU is too old and its MMIO Stale Data status is unknown */ #define X86_BUG_RETBLEED X86_BUG(27) /* CPU is affected by RETBleed */ #define X86_BUG_EIBRS_PBRSB X86_BUG(28) /* EIBRS is vulnerable to Post Barrier RSB Predictions */ +#define X86_BUG_SMT_RSB X86_BUG(29) /* CPU is vulnerable to Cross-Thread Return Address Predictions */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h index 5dfa4fb76f4b..fafe9be7a6f4 100644 --- a/tools/arch/x86/include/asm/disabled-features.h +++ b/tools/arch/x86/include/asm/disabled-features.h @@ -75,6 +75,12 @@ # define DISABLE_CALL_DEPTH_TRACKING (1 << (X86_FEATURE_CALL_DEPTH & 31)) #endif +#ifdef CONFIG_ADDRESS_MASKING +# define DISABLE_LAM 0 +#else +# define DISABLE_LAM (1 << (X86_FEATURE_LAM & 31)) +#endif + #ifdef CONFIG_INTEL_IOMMU_SVM # define DISABLE_ENQCMD 0 #else @@ -115,7 +121,7 @@ #define DISABLED_MASK10 0 #define DISABLED_MASK11 (DISABLE_RETPOLINE|DISABLE_RETHUNK|DISABLE_UNRET| \ DISABLE_CALL_DEPTH_TRACKING) -#define DISABLED_MASK12 0 +#define DISABLED_MASK12 (DISABLE_LAM) #define DISABLED_MASK13 0 #define DISABLED_MASK14 0 #define DISABLED_MASK15 0 diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index ad35355ee43e..3aedae61af4f 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -206,6 +206,8 @@ /* Abbreviated from Intel SDM name IA32_INTEGRITY_CAPABILITIES */ #define MSR_INTEGRITY_CAPS 0x000002d9 +#define MSR_INTEGRITY_CAPS_ARRAY_BIST_BIT 2 +#define MSR_INTEGRITY_CAPS_ARRAY_BIST BIT(MSR_INTEGRITY_CAPS_ARRAY_BIST_BIT) #define MSR_INTEGRITY_CAPS_PERIODIC_BIST_BIT 4 #define MSR_INTEGRITY_CAPS_PERIODIC_BIST BIT(MSR_INTEGRITY_CAPS_PERIODIC_BIST_BIT) diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h index 7f467fe05d42..1a6a1f987949 100644 --- a/tools/arch/x86/include/uapi/asm/kvm.h +++ b/tools/arch/x86/include/uapi/asm/kvm.h @@ -559,4 +559,7 @@ struct kvm_pmu_event_filter { #define KVM_VCPU_TSC_CTRL 0 /* control group for the timestamp counter (TSC) */ #define KVM_VCPU_TSC_OFFSET 0 /* attribute for the TSC offset */ +/* x86-specific KVM_EXIT_HYPERCALL flags. */ +#define KVM_EXIT_HYPERCALL_LONG_MODE BIT(0) + #endif /* _ASM_X86_KVM_H */ diff --git a/tools/arch/x86/include/uapi/asm/prctl.h b/tools/arch/x86/include/uapi/asm/prctl.h index 500b96e71f18..e8d7ebbca1a4 100644 --- a/tools/arch/x86/include/uapi/asm/prctl.h +++ b/tools/arch/x86/include/uapi/asm/prctl.h @@ -16,8 +16,16 @@ #define ARCH_GET_XCOMP_GUEST_PERM 0x1024 #define ARCH_REQ_XCOMP_GUEST_PERM 0x1025 +#define ARCH_XCOMP_TILECFG 17 +#define ARCH_XCOMP_TILEDATA 18 + #define ARCH_MAP_VDSO_X32 0x2001 #define ARCH_MAP_VDSO_32 0x2002 #define ARCH_MAP_VDSO_64 0x2003 +#define ARCH_GET_UNTAG_MASK 0x4001 +#define ARCH_ENABLE_TAGGED_ADDR 0x4002 +#define ARCH_GET_MAX_TAG_BITS 0x4003 +#define ARCH_FORCE_TAGGED_SVA 0x4004 + #endif /* _ASM_X86_PRCTL_H */ diff --git a/tools/arch/x86/include/uapi/asm/unistd_32.h b/tools/arch/x86/include/uapi/asm/unistd_32.h index b8ddfc4c4ab0..bc48a4dabe5d 100644 --- a/tools/arch/x86/include/uapi/asm/unistd_32.h +++ b/tools/arch/x86/include/uapi/asm/unistd_32.h @@ -2,6 +2,9 @@ #ifndef __NR_fork #define __NR_fork 2 #endif +#ifndef __NR_execve +#define __NR_execve 11 +#endif #ifndef __NR_getppid #define __NR_getppid 64 #endif diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S index a91ac666f758..d055b82d22cc 100644 --- a/tools/arch/x86/lib/memcpy_64.S +++ b/tools/arch/x86/lib/memcpy_64.S @@ -10,13 +10,6 @@ .section .noinstr.text, "ax" /* - * We build a jump to memcpy_orig by default which gets NOPped out on - * the majority of x86 CPUs which set REP_GOOD. In addition, CPUs which - * have the enhanced REP MOVSB/STOSB feature (ERMS), change those NOPs - * to a jmp to memcpy_erms which does the REP; MOVSB mem copy. - */ - -/* * memcpy - Copy a memory block. * * Input: @@ -26,17 +19,21 @@ * * Output: * rax original destination + * + * The FSRM alternative should be done inline (avoiding the call and + * the disgusting return handling), but that would require some help + * from the compiler for better calling conventions. + * + * The 'rep movsb' itself is small enough to replace the call, but the + * two register moves blow up the code. And one of them is "needed" + * only for the return value that is the same as the source input, + * which the compiler could/should do much better anyway. */ SYM_TYPED_FUNC_START(__memcpy) - ALTERNATIVE_2 "jmp memcpy_orig", "", X86_FEATURE_REP_GOOD, \ - "jmp memcpy_erms", X86_FEATURE_ERMS + ALTERNATIVE "jmp memcpy_orig", "", X86_FEATURE_FSRM movq %rdi, %rax movq %rdx, %rcx - shrq $3, %rcx - andl $7, %edx - rep movsq - movl %edx, %ecx rep movsb RET SYM_FUNC_END(__memcpy) @@ -45,17 +42,6 @@ EXPORT_SYMBOL(__memcpy) SYM_FUNC_ALIAS(memcpy, __memcpy) EXPORT_SYMBOL(memcpy) -/* - * memcpy_erms() - enhanced fast string memcpy. This is faster and - * simpler than memcpy. Use memcpy_erms when possible. - */ -SYM_FUNC_START_LOCAL(memcpy_erms) - movq %rdi, %rax - movq %rdx, %rcx - rep movsb - RET -SYM_FUNC_END(memcpy_erms) - SYM_FUNC_START_LOCAL(memcpy_orig) movq %rdi, %rax diff --git a/tools/arch/x86/lib/memset_64.S b/tools/arch/x86/lib/memset_64.S index 6143b1a6fa2c..7c59a704c458 100644 --- a/tools/arch/x86/lib/memset_64.S +++ b/tools/arch/x86/lib/memset_64.S @@ -18,27 +18,22 @@ * rdx count (bytes) * * rax original destination + * + * The FSRS alternative should be done inline (avoiding the call and + * the disgusting return handling), but that would require some help + * from the compiler for better calling conventions. + * + * The 'rep stosb' itself is small enough to replace the call, but all + * the register moves blow up the code. And two of them are "needed" + * only for the return value that is the same as the source input, + * which the compiler could/should do much better anyway. */ SYM_FUNC_START(__memset) - /* - * Some CPUs support enhanced REP MOVSB/STOSB feature. It is recommended - * to use it when possible. If not available, use fast string instructions. - * - * Otherwise, use original memset function. - */ - ALTERNATIVE_2 "jmp memset_orig", "", X86_FEATURE_REP_GOOD, \ - "jmp memset_erms", X86_FEATURE_ERMS + ALTERNATIVE "jmp memset_orig", "", X86_FEATURE_FSRS movq %rdi,%r9 + movb %sil,%al movq %rdx,%rcx - andl $7,%edx - shrq $3,%rcx - /* expand byte value */ - movzbl %sil,%esi - movabs $0x0101010101010101,%rax - imulq %rsi,%rax - rep stosq - movl %edx,%ecx rep stosb movq %r9,%rax RET @@ -48,26 +43,6 @@ EXPORT_SYMBOL(__memset) SYM_FUNC_ALIAS(memset, __memset) EXPORT_SYMBOL(memset) -/* - * ISO C memset - set a memory block to a byte value. This function uses - * enhanced rep stosb to override the fast string function. - * The code is simpler and shorter than the fast string function as well. - * - * rdi destination - * rsi value (char) - * rdx count (bytes) - * - * rax original destination - */ -SYM_FUNC_START_LOCAL(memset_erms) - movq %rdi,%r9 - movb %sil,%al - movq %rdx,%rcx - rep stosb - movq %r9,%rax - RET -SYM_FUNC_END(memset_erms) - SYM_FUNC_START_LOCAL(memset_orig) movq %rdi,%r10 diff --git a/tools/gpio/lsgpio.c b/tools/gpio/lsgpio.c index c61d061247e1..52a0be45410c 100644 --- a/tools/gpio/lsgpio.c +++ b/tools/gpio/lsgpio.c @@ -94,7 +94,7 @@ static void print_attributes(struct gpio_v2_line_info *info) for (i = 0; i < info->num_attrs; i++) { if (info->attrs[i].id == GPIO_V2_LINE_ATTR_ID_DEBOUNCE) fprintf(stdout, ", debounce_period=%dusec", - info->attrs[0].debounce_period_us); + info->attrs[i].debounce_period_us); } } diff --git a/tools/include/asm/alternative.h b/tools/include/asm/alternative.h index b54bd860dff6..7ce02a223732 100644 --- a/tools/include/asm/alternative.h +++ b/tools/include/asm/alternative.h @@ -4,7 +4,6 @@ /* Just disable it so we can build arch/x86/lib/memcpy_64.S for perf bench: */ -#define altinstruction_entry # -#define ALTERNATIVE_2 # +#define ALTERNATIVE # #endif diff --git a/tools/include/linux/coresight-pmu.h b/tools/include/linux/coresight-pmu.h index cef3b1c25335..51ac441a37c3 100644 --- a/tools/include/linux/coresight-pmu.h +++ b/tools/include/linux/coresight-pmu.h @@ -21,19 +21,6 @@ */ #define CORESIGHT_LEGACY_CPU_TRACE_ID(cpu) (0x10 + (cpu * 2)) -/* CoreSight trace ID is currently the bottom 7 bits of the value */ -#define CORESIGHT_TRACE_ID_VAL_MASK GENMASK(6, 0) - -/* - * perf record will set the legacy meta data values as unused initially. - * This allows perf report to manage the decoders created when dynamic - * allocation in operation. - */ -#define CORESIGHT_TRACE_ID_UNUSED_FLAG BIT(31) - -/* Value to set for unused trace ID values */ -#define CORESIGHT_TRACE_ID_UNUSED_VAL 0x7F - /* * Below are the definition of bit offsets for perf option, and works as * arbitrary values for all ETM versions. diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h index 642808520d92..a87bbbbca2d4 100644 --- a/tools/include/uapi/drm/drm.h +++ b/tools/include/uapi/drm/drm.h @@ -972,6 +972,19 @@ extern "C" { #define DRM_IOCTL_GET_STATS DRM_IOR( 0x06, struct drm_stats) #define DRM_IOCTL_SET_VERSION DRM_IOWR(0x07, struct drm_set_version) #define DRM_IOCTL_MODESET_CTL DRM_IOW(0x08, struct drm_modeset_ctl) +/** + * DRM_IOCTL_GEM_CLOSE - Close a GEM handle. + * + * GEM handles are not reference-counted by the kernel. User-space is + * responsible for managing their lifetime. For example, if user-space imports + * the same memory object twice on the same DRM file description, the same GEM + * handle is returned by both imports, and user-space needs to ensure + * &DRM_IOCTL_GEM_CLOSE is performed once only. The same situation can happen + * when a memory object is allocated, then exported and imported again on the + * same DRM file description. The &DRM_IOCTL_MODE_GETFB2 IOCTL is an exception + * and always returns fresh new GEM handles even if an existing GEM handle + * already refers to the same memory object before the IOCTL is performed. + */ #define DRM_IOCTL_GEM_CLOSE DRM_IOW (0x09, struct drm_gem_close) #define DRM_IOCTL_GEM_FLINK DRM_IOWR(0x0a, struct drm_gem_flink) #define DRM_IOCTL_GEM_OPEN DRM_IOWR(0x0b, struct drm_gem_open) @@ -1012,7 +1025,37 @@ extern "C" { #define DRM_IOCTL_UNLOCK DRM_IOW( 0x2b, struct drm_lock) #define DRM_IOCTL_FINISH DRM_IOW( 0x2c, struct drm_lock) +/** + * DRM_IOCTL_PRIME_HANDLE_TO_FD - Convert a GEM handle to a DMA-BUF FD. + * + * User-space sets &drm_prime_handle.handle with the GEM handle to export and + * &drm_prime_handle.flags, and gets back a DMA-BUF file descriptor in + * &drm_prime_handle.fd. + * + * The export can fail for any driver-specific reason, e.g. because export is + * not supported for this specific GEM handle (but might be for others). + * + * Support for exporting DMA-BUFs is advertised via &DRM_PRIME_CAP_EXPORT. + */ #define DRM_IOCTL_PRIME_HANDLE_TO_FD DRM_IOWR(0x2d, struct drm_prime_handle) +/** + * DRM_IOCTL_PRIME_FD_TO_HANDLE - Convert a DMA-BUF FD to a GEM handle. + * + * User-space sets &drm_prime_handle.fd with a DMA-BUF file descriptor to + * import, and gets back a GEM handle in &drm_prime_handle.handle. + * &drm_prime_handle.flags is unused. + * + * If an existing GEM handle refers to the memory object backing the DMA-BUF, + * that GEM handle is returned. Therefore user-space which needs to handle + * arbitrary DMA-BUFs must have a user-space lookup data structure to manually + * reference-count duplicated GEM handles. For more information see + * &DRM_IOCTL_GEM_CLOSE. + * + * The import can fail for any driver-specific reason, e.g. because import is + * only supported for DMA-BUFs allocated on this DRM device. + * + * Support for importing DMA-BUFs is advertised via &DRM_PRIME_CAP_IMPORT. + */ #define DRM_IOCTL_PRIME_FD_TO_HANDLE DRM_IOWR(0x2e, struct drm_prime_handle) #define DRM_IOCTL_AGP_ACQUIRE DRM_IO( 0x30) @@ -1104,8 +1147,13 @@ extern "C" { * struct as the output. * * If the client is DRM master or has &CAP_SYS_ADMIN, &drm_mode_fb_cmd2.handles - * will be filled with GEM buffer handles. Planes are valid until one has a - * zero handle -- this can be used to compute the number of planes. + * will be filled with GEM buffer handles. Fresh new GEM handles are always + * returned, even if another GEM handle referring to the same memory object + * already exists on the DRM file description. The caller is responsible for + * removing the new handles, e.g. via the &DRM_IOCTL_GEM_CLOSE IOCTL. The same + * new handle will be returned for multiple planes in case they use the same + * memory object. Planes are valid until one has a zero handle -- this can be + * used to compute the number of planes. * * Otherwise, &drm_mode_fb_cmd2.handles will be zeroed and planes are valid * until one has a zero &drm_mode_fb_cmd2.pitches. @@ -1113,6 +1161,11 @@ extern "C" { * If the framebuffer has a format modifier, &DRM_MODE_FB_MODIFIERS will be set * in &drm_mode_fb_cmd2.flags and &drm_mode_fb_cmd2.modifier will contain the * modifier. Otherwise, user-space must ignore &drm_mode_fb_cmd2.modifier. + * + * To obtain DMA-BUF FDs for each plane without leaking GEM handles, user-space + * can export each handle via &DRM_IOCTL_PRIME_HANDLE_TO_FD, then immediately + * close each unique handle via &DRM_IOCTL_GEM_CLOSE, making sure to not + * double-close handles which are specified multiple times in the array. */ #define DRM_IOCTL_MODE_GETFB2 DRM_IOWR(0xCE, struct drm_mode_fb_cmd2) diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h index 8df261c5ab9b..dba7c5a5b25e 100644 --- a/tools/include/uapi/drm/i915_drm.h +++ b/tools/include/uapi/drm/i915_drm.h @@ -2491,7 +2491,7 @@ struct i915_context_param_engines { #define I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE 0 /* see i915_context_engines_load_balance */ #define I915_CONTEXT_ENGINES_EXT_BOND 1 /* see i915_context_engines_bond */ #define I915_CONTEXT_ENGINES_EXT_PARALLEL_SUBMIT 2 /* see i915_context_engines_parallel_submit */ - struct i915_engine_class_instance engines[0]; + struct i915_engine_class_instance engines[]; } __attribute__((packed)); #define I915_DEFINE_CONTEXT_PARAM_ENGINES(name__, N__) struct { \ @@ -2676,6 +2676,10 @@ enum drm_i915_oa_format { I915_OAR_FORMAT_A32u40_A4u32_B8_C8, I915_OA_FORMAT_A24u40_A14u32_B8_C8, + /* MTL OAM */ + I915_OAM_FORMAT_MPEC8u64_B8_C8, + I915_OAM_FORMAT_MPEC8u32_B8_C8, + I915_OA_FORMAT_MAX /* non-ABI */ }; @@ -2758,6 +2762,25 @@ enum drm_i915_perf_property_id { */ DRM_I915_PERF_PROP_POLL_OA_PERIOD, + /** + * Multiple engines may be mapped to the same OA unit. The OA unit is + * identified by class:instance of any engine mapped to it. + * + * This parameter specifies the engine class and must be passed along + * with DRM_I915_PERF_PROP_OA_ENGINE_INSTANCE. + * + * This property is available in perf revision 6. + */ + DRM_I915_PERF_PROP_OA_ENGINE_CLASS, + + /** + * This parameter specifies the engine instance and must be passed along + * with DRM_I915_PERF_PROP_OA_ENGINE_CLASS. + * + * This property is available in perf revision 6. + */ + DRM_I915_PERF_PROP_OA_ENGINE_INSTANCE, + DRM_I915_PERF_PROP_MAX /* non-ABI */ }; diff --git a/tools/include/uapi/linux/const.h b/tools/include/uapi/linux/const.h index af2a44c08683..a429381e7ca5 100644 --- a/tools/include/uapi/linux/const.h +++ b/tools/include/uapi/linux/const.h @@ -28,7 +28,7 @@ #define _BITUL(x) (_UL(1) << (x)) #define _BITULL(x) (_ULL(1) << (x)) -#define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (typeof(x))(a) - 1) +#define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (__typeof__(x))(a) - 1) #define __ALIGN_KERNEL_MASK(x, mask) (((x) + (mask)) & ~(mask)) #define __KERNEL_DIV_ROUND_UP(n, d) (((n) + (d) - 1) / (d)) diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h index 07a4cb149305..e682ab628dfa 100644 --- a/tools/include/uapi/linux/in.h +++ b/tools/include/uapi/linux/in.h @@ -162,6 +162,8 @@ struct in_addr { #define MCAST_MSFILTER 48 #define IP_MULTICAST_ALL 49 #define IP_UNICAST_IF 50 +#define IP_LOCAL_PORT_RANGE 51 +#define IP_PROTOCOL 52 #define MCAST_EXCLUDE 0 #define MCAST_INCLUDE 1 diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 4003a166328c..737318b1c1d9 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -341,8 +341,13 @@ struct kvm_run { __u64 nr; __u64 args[6]; __u64 ret; - __u32 longmode; - __u32 pad; + + union { +#ifndef __KERNEL__ + __u32 longmode; +#endif + __u64 flags; + }; } hypercall; /* KVM_EXIT_TPR_ACCESS */ struct { @@ -1184,6 +1189,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_S390_PROTECTED_ASYNC_DISABLE 224 #define KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP 225 #define KVM_CAP_PMU_EVENT_MASKED_EVENTS 226 +#define KVM_CAP_COUNTER_OFFSET 227 #ifdef KVM_CAP_IRQ_ROUTING @@ -1543,6 +1549,8 @@ struct kvm_s390_ucas_mapping { #define KVM_SET_PMU_EVENT_FILTER _IOW(KVMIO, 0xb2, struct kvm_pmu_event_filter) #define KVM_PPC_SVM_OFF _IO(KVMIO, 0xb3) #define KVM_ARM_MTE_COPY_TAGS _IOR(KVMIO, 0xb4, struct kvm_arm_copy_mte_tags) +/* Available with KVM_CAP_COUNTER_OFFSET */ +#define KVM_ARM_SET_COUNTER_OFFSET _IOW(KVMIO, 0xb5, struct kvm_arm_counter_offset) /* ioctl for vm fd */ #define KVM_CREATE_DEVICE _IOWR(KVMIO, 0xe0, struct kvm_create_device) diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h index 759b3f53e53f..f23d9a16507f 100644 --- a/tools/include/uapi/linux/prctl.h +++ b/tools/include/uapi/linux/prctl.h @@ -290,6 +290,8 @@ struct prctl_mm_map { #define PR_SET_VMA 0x53564d41 # define PR_SET_VMA_ANON_NAME 0 +#define PR_GET_AUXV 0x41555856 + #define PR_SET_MEMORY_MERGE 67 #define PR_GET_MEMORY_MERGE 68 #endif /* _LINUX_PRCTL_H */ diff --git a/tools/include/uapi/sound/asound.h b/tools/include/uapi/sound/asound.h index de6810e94abe..0aa955aa8246 100644 --- a/tools/include/uapi/sound/asound.h +++ b/tools/include/uapi/sound/asound.h @@ -429,9 +429,14 @@ struct snd_pcm_sw_params { snd_pcm_uframes_t avail_min; /* min avail frames for wakeup */ snd_pcm_uframes_t xfer_align; /* obsolete: xfer size need to be a multiple */ snd_pcm_uframes_t start_threshold; /* min hw_avail frames for automatic start */ - snd_pcm_uframes_t stop_threshold; /* min avail frames for automatic stop */ - snd_pcm_uframes_t silence_threshold; /* min distance from noise for silence filling */ - snd_pcm_uframes_t silence_size; /* silence block size */ + /* + * The following two thresholds alleviate playback buffer underruns; when + * hw_avail drops below the threshold, the respective action is triggered: + */ + snd_pcm_uframes_t stop_threshold; /* - stop playback */ + snd_pcm_uframes_t silence_threshold; /* - pre-fill buffer with silence */ + snd_pcm_uframes_t silence_size; /* max size of silence pre-fill; when >= boundary, + * fill played area with silence immediately */ snd_pcm_uframes_t boundary; /* pointers wrap point */ unsigned int proto; /* protocol version */ unsigned int tstamp_type; /* timestamp type (req. proto >= 2.0.12) */ @@ -570,7 +575,8 @@ struct __snd_pcm_mmap_status64 { struct __snd_pcm_mmap_control64 { __pad_before_uframe __pad1; snd_pcm_uframes_t appl_ptr; /* RW: appl ptr (0...boundary-1) */ - __pad_before_uframe __pad2; + __pad_before_uframe __pad2; // This should be __pad_after_uframe, but binary + // backwards compatibility constraints prevent a fix. __pad_before_uframe __pad3; snd_pcm_uframes_t avail_min; /* RW: min available frames for wakeup */ diff --git a/tools/net/ynl/lib/ynl.py b/tools/net/ynl/lib/ynl.py index aa77bcae4807..3144f33196be 100644 --- a/tools/net/ynl/lib/ynl.py +++ b/tools/net/ynl/lib/ynl.py @@ -591,8 +591,9 @@ class YnlFamily(SpecFamily): print('Unexpected message: ' + repr(gm)) continue - rsp.append(self._decode(gm.raw_attrs, op.attr_set.name) - | gm.fixed_header_attrs) + rsp_msg = self._decode(gm.raw_attrs, op.attr_set.name) + rsp_msg.update(gm.fixed_header_attrs) + rsp.append(rsp_msg) if not rsp: return None diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 4884520f954f..a794d9eca93d 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -216,6 +216,12 @@ ifeq ($(call get-executable,$(BISON)),) dummy := $(error Error: $(BISON) is missing on this system, please install it) endif +ifeq ($(BUILD_BPF_SKEL),1) + ifeq ($(call get-executable,$(CLANG)),) + dummy := $(error $(CLANG) is missing on this system, please install it to be able to build with BUILD_BPF_SKEL=1) + endif +endif + ifneq ($(OUTPUT),) ifeq ($(shell expr $(shell $(BISON) --version | grep bison | sed -e 's/.\+ \([0-9]\+\).\([0-9]\+\).\([0-9]\+\)/\1\2\3/g') \>\= 371), 1) BISON_FILE_PREFIX_MAP := --file-prefix-map=$(OUTPUT)= @@ -921,6 +927,7 @@ ifndef NO_DEMANGLE EXTLIBS += -lstdc++ CFLAGS += -DHAVE_CXA_DEMANGLE_SUPPORT CXXFLAGS += -DHAVE_CXA_DEMANGLE_SUPPORT + $(call detected,CONFIG_CXX_DEMANGLE) endif ifdef BUILD_NONDISTRO ifeq ($(filter -liberty,$(EXTLIBS)),) diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index a42a6a99c2bc..f48794816d82 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -181,7 +181,6 @@ HOSTCC ?= gcc HOSTLD ?= ld HOSTAR ?= ar CLANG ?= clang -LLVM_STRIP ?= llvm-strip PKG_CONFIG = $(CROSS_COMPILE)pkg-config @@ -1057,15 +1056,33 @@ $(SKEL_TMP_OUT) $(LIBAPI_OUTPUT) $(LIBBPF_OUTPUT) $(LIBPERF_OUTPUT) $(LIBSUBCMD_ ifdef BUILD_BPF_SKEL BPFTOOL := $(SKEL_TMP_OUT)/bootstrap/bpftool -BPF_INCLUDE := -I$(SKEL_TMP_OUT)/.. -I$(LIBBPF_INCLUDE) +# Get Clang's default includes on this system, as opposed to those seen by +# '-target bpf'. This fixes "missing" files on some architectures/distros, +# such as asm/byteorder.h, asm/socket.h, asm/sockios.h, sys/cdefs.h etc. +# +# Use '-idirafter': Don't interfere with include mechanics except where the +# build would have failed anyways. +define get_sys_includes +$(shell $(1) $(2) -v -E - </dev/null 2>&1 \ + | sed -n '/<...> search starts here:/,/End of search list./{ s| \(/.*\)|-idirafter \1|p }') \ +$(shell $(1) $(2) -dM -E - </dev/null | grep '__riscv_xlen ' | awk '{printf("-D__riscv_xlen=%d -D__BITS_PER_LONG=%d", $$3, $$3)}') +endef + +ifneq ($(CROSS_COMPILE),) +CLANG_TARGET_ARCH = --target=$(notdir $(CROSS_COMPILE:%-=%)) +endif + +CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG),$(CLANG_TARGET_ARCH)) +BPF_INCLUDE := -I$(SKEL_TMP_OUT)/.. -I$(LIBBPF_INCLUDE) $(CLANG_SYS_INCLUDES) +TOOLS_UAPI_INCLUDE := -I$(srctree)/tools/include/uapi $(BPFTOOL): | $(SKEL_TMP_OUT) $(Q)CFLAGS= $(MAKE) -C ../bpf/bpftool \ OUTPUT=$(SKEL_TMP_OUT)/ bootstrap $(SKEL_TMP_OUT)/%.bpf.o: util/bpf_skel/%.bpf.c $(LIBBPF) | $(SKEL_TMP_OUT) - $(QUIET_CLANG)$(CLANG) -g -O2 -target bpf -Wall -Werror $(BPF_INCLUDE) \ - -c $(filter util/bpf_skel/%.bpf.c,$^) -o $@ && $(LLVM_STRIP) -g $@ + $(QUIET_CLANG)$(CLANG) -g -O2 -target bpf -Wall -Werror $(BPF_INCLUDE) $(TOOLS_UAPI_INCLUDE) \ + -c $(filter util/bpf_skel/%.bpf.c,$^) -o $@ $(SKEL_OUT)/%.skel.h: $(SKEL_TMP_OUT)/%.bpf.o | $(BPFTOOL) $(QUIET_GENSKEL)$(BPFTOOL) gen skeleton $< > $@ diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c index 77cb03e6ff87..9ca040bfb1aa 100644 --- a/tools/perf/arch/arm/util/cs-etm.c +++ b/tools/perf/arch/arm/util/cs-etm.c @@ -78,9 +78,9 @@ static int cs_etm_validate_context_id(struct auxtrace_record *itr, char path[PATH_MAX]; int err; u32 val; - u64 contextid = - evsel->core.attr.config & - (perf_pmu__format_bits(&cs_etm_pmu->format, "contextid1") | + u64 contextid = evsel->core.attr.config & + (perf_pmu__format_bits(&cs_etm_pmu->format, "contextid") | + perf_pmu__format_bits(&cs_etm_pmu->format, "contextid1") | perf_pmu__format_bits(&cs_etm_pmu->format, "contextid2")); if (!contextid) @@ -114,8 +114,7 @@ static int cs_etm_validate_context_id(struct auxtrace_record *itr, * 0b00100 Maximum of 32-bit Context ID size. * All other values are reserved. */ - val = BMVAL(val, 5, 9); - if (!val || val != 0x4) { + if (BMVAL(val, 5, 9) != 0x4) { pr_err("%s: CONTEXTIDR_EL1 isn't supported, disable with %s/contextid1=0/\n", CORESIGHT_ETM_PMU_NAME, CORESIGHT_ETM_PMU_NAME); return -EINVAL; diff --git a/tools/perf/arch/arm/util/pmu.c b/tools/perf/arch/arm/util/pmu.c index 860a8b42b4b5..a9623b128ece 100644 --- a/tools/perf/arch/arm/util/pmu.c +++ b/tools/perf/arch/arm/util/pmu.c @@ -12,7 +12,7 @@ #include "arm-spe.h" #include "hisi-ptt.h" #include "../../../util/pmu.h" -#include "../cs-etm.h" +#include "../../../util/cs-etm.h" struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused) diff --git a/tools/perf/arch/arm64/util/header.c b/tools/perf/arch/arm64/util/header.c index d730666ab95d..80b9f6287fe2 100644 --- a/tools/perf/arch/arm64/util/header.c +++ b/tools/perf/arch/arm64/util/header.c @@ -29,8 +29,8 @@ static int _get_cpuid(char *buf, size_t sz, struct perf_cpu_map *cpus) char path[PATH_MAX]; FILE *file; - scnprintf(path, PATH_MAX, "%s/devices/system/cpu/cpu%d"MIDR, - sysfs, cpus->map[cpu]); + scnprintf(path, PATH_MAX, "%s/devices/system/cpu/cpu%d" MIDR, + sysfs, RC_CHK_ACCESS(cpus)->map[cpu].cpu); file = fopen(path, "r"); if (!file) { diff --git a/tools/perf/arch/arm64/util/pmu.c b/tools/perf/arch/arm64/util/pmu.c index fa143acb4c8d..ef1ed645097c 100644 --- a/tools/perf/arch/arm64/util/pmu.c +++ b/tools/perf/arch/arm64/util/pmu.c @@ -18,7 +18,7 @@ static struct perf_pmu *pmu__find_core_pmu(void) * The cpumap should cover all CPUs. Otherwise, some CPUs may * not support some events or have different event IDs. */ - if (pmu->cpus->nr != cpu__max_cpu().cpu) + if (RC_CHK_ACCESS(pmu->cpus)->nr != cpu__max_cpu().cpu) return NULL; return pmu; diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl index 799147658dee..b68f47541169 100644 --- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl @@ -449,7 +449,7 @@ 444 common landlock_create_ruleset sys_landlock_create_ruleset sys_landlock_create_ruleset 445 common landlock_add_rule sys_landlock_add_rule sys_landlock_add_rule 446 common landlock_restrict_self sys_landlock_restrict_self sys_landlock_restrict_self -# 447 reserved for memfd_secret +447 common memfd_secret sys_memfd_secret sys_memfd_secret 448 common process_mrelease sys_process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv sys_futex_waitv 450 common set_mempolicy_home_node sys_set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm-def.h b/tools/perf/bench/mem-memcpy-x86-64-asm-def.h index 50ae8bd58296..6188e19d3129 100644 --- a/tools/perf/bench/mem-memcpy-x86-64-asm-def.h +++ b/tools/perf/bench/mem-memcpy-x86-64-asm-def.h @@ -7,7 +7,3 @@ MEMCPY_FN(memcpy_orig, MEMCPY_FN(__memcpy, "x86-64-movsq", "movsq-based memcpy() in arch/x86/lib/memcpy_64.S") - -MEMCPY_FN(memcpy_erms, - "x86-64-movsb", - "movsb-based memcpy() in arch/x86/lib/memcpy_64.S") diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm.S b/tools/perf/bench/mem-memcpy-x86-64-asm.S index 6eb45a2aa8db..1b9fef7efcdc 100644 --- a/tools/perf/bench/mem-memcpy-x86-64-asm.S +++ b/tools/perf/bench/mem-memcpy-x86-64-asm.S @@ -2,7 +2,7 @@ /* Various wrappers to make the kernel .S file build in user-space: */ -// memcpy_orig and memcpy_erms are being defined as SYM_L_LOCAL but we need it +// memcpy_orig is being defined as SYM_L_LOCAL but we need it #define SYM_FUNC_START_LOCAL(name) \ SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) #define memcpy MEMCPY /* don't hide glibc's memcpy() */ diff --git a/tools/perf/bench/mem-memset-x86-64-asm-def.h b/tools/perf/bench/mem-memset-x86-64-asm-def.h index dac6d2b7c39b..247c72fdfb9d 100644 --- a/tools/perf/bench/mem-memset-x86-64-asm-def.h +++ b/tools/perf/bench/mem-memset-x86-64-asm-def.h @@ -7,7 +7,3 @@ MEMSET_FN(memset_orig, MEMSET_FN(__memset, "x86-64-stosq", "movsq-based memset() in arch/x86/lib/memset_64.S") - -MEMSET_FN(memset_erms, - "x86-64-stosb", - "movsb-based memset() in arch/x86/lib/memset_64.S") diff --git a/tools/perf/bench/mem-memset-x86-64-asm.S b/tools/perf/bench/mem-memset-x86-64-asm.S index 6f093c483842..abd26c95f1aa 100644 --- a/tools/perf/bench/mem-memset-x86-64-asm.S +++ b/tools/perf/bench/mem-memset-x86-64-asm.S @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -// memset_orig and memset_erms are being defined as SYM_L_LOCAL but we need it +// memset_orig is being defined as SYM_L_LOCAL but we need it #define SYM_FUNC_START_LOCAL(name) \ SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) #define memset MEMSET /* don't hide glibc's memset() */ diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c index 810e3376c7d6..f9906f52e4fa 100644 --- a/tools/perf/builtin-ftrace.c +++ b/tools/perf/builtin-ftrace.c @@ -1175,7 +1175,7 @@ int cmd_ftrace(int argc, const char **argv) OPT_BOOLEAN('b', "use-bpf", &ftrace.target.use_bpf, "Use BPF to measure function latency"), #endif - OPT_BOOLEAN('n', "--use-nsec", &ftrace.use_nsec, + OPT_BOOLEAN('n', "use-nsec", &ftrace.use_nsec, "Use nano-second histogram"), OPT_PARENT(common_options), }; diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 006f522d0e7f..c57be48d65bb 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -3647,6 +3647,13 @@ static int process_stat_config_event(struct perf_session *session __maybe_unused union perf_event *event) { perf_event__read_stat_config(&stat_config, &event->stat_config); + + /* + * Aggregation modes are not used since post-processing scripts are + * supposed to take care of such requirements + */ + stat_config.aggr_mode = AGGR_NONE; + return 0; } diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index cc9fa48d636f..b9ad32f21e57 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -667,6 +667,13 @@ static enum counter_recovery stat_handle_error(struct evsel *counter) evsel_list->core.threads->err_thread = -1; return COUNTER_RETRY; } + } else if (counter->skippable) { + if (verbose > 0) + ui__warning("skipping event %s that kernel failed to open .\n", + evsel__name(counter)); + counter->supported = false; + counter->errored = true; + return COUNTER_SKIP; } evsel__open_strerror(counter, &target, errno, msg, sizeof(msg)); @@ -1890,15 +1897,28 @@ static int add_default_attributes(void) * caused by exposing latent bugs. This is fixed properly in: * https://lore.kernel.org/lkml/[email protected]/ */ - if (metricgroup__has_metric("TopdownL1") && !perf_pmu__has_hybrid() && - metricgroup__parse_groups(evsel_list, "TopdownL1", - /*metric_no_group=*/false, - /*metric_no_merge=*/false, - /*metric_no_threshold=*/true, - stat_config.user_requested_cpu_list, - stat_config.system_wide, - &stat_config.metric_events) < 0) - return -1; + if (metricgroup__has_metric("TopdownL1") && !perf_pmu__has_hybrid()) { + struct evlist *metric_evlist = evlist__new(); + struct evsel *metric_evsel; + + if (!metric_evlist) + return -1; + + if (metricgroup__parse_groups(metric_evlist, "TopdownL1", + /*metric_no_group=*/false, + /*metric_no_merge=*/false, + /*metric_no_threshold=*/true, + stat_config.user_requested_cpu_list, + stat_config.system_wide, + &stat_config.metric_events) < 0) + return -1; + + evlist__for_each_entry(metric_evlist, metric_evsel) { + metric_evsel->skippable = true; + } + evlist__splice_list_tail(evsel_list, &metric_evlist->core.entries); + evlist__delete(metric_evlist); + } /* Platform specific attrs */ if (evlist__add_default_attrs(evsel_list, default_null_attrs) < 0) diff --git a/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json b/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json index 75d80e70e5cd..1f9047553942 100644 --- a/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json @@ -133,6 +133,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count. The rest of these subevents count backend stalls, in cycles, due to an outstanding request which is memory bound vs core bound. The subevents are not slot based events and therefore can not be precisely added or subtracted from the Backend_Bound_Aux subevents which are slot based.", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -143,6 +144,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound_aux", "MetricThreshold": "tma_backend_bound_aux > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that UOPS must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count. All of these subevents count backend stalls, in slots, due to a resource limitation. These are not cycle based events and therefore can not be precisely added or subtracted from the Backend_Bound subevents which are cycle based. These subevents are supplementary to Backend_Bound and can be used to analyze results from a resource perspective at allocation.", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -153,6 +155,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the instruction queue (IQ). Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -163,6 +166,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_base", "MetricThreshold": "tma_base > 0.6", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -182,6 +186,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.05", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -209,6 +214,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -255,6 +261,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -264,6 +271,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.15", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -291,6 +299,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -593,6 +602,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.05", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -611,6 +621,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -629,6 +640,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_ms_uops", "MetricThreshold": "tma_ms_uops > 0.05", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "Counts the number of uops that are from the complex flows issued by the micro-sequencer (MS). This includes uops from flows due to complex instructions, faults, assists, and inserted flows.", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -729,6 +741,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_aux_group", "MetricName": "tma_resource_bound", "MetricThreshold": "tma_resource_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count.", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -739,6 +752,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.75", + "MetricgroupNoGroup": "TopdownL1", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -848,6 +862,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -858,6 +873,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -868,6 +884,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: TOPDOWN.BR_MISPREDICT_SLOTS. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -919,6 +936,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -1031,6 +1049,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 6 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -1041,6 +1060,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -1121,6 +1141,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -1141,6 +1162,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences. Sample with: UOPS_RETIRED.HEAVY", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2023,6 +2045,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2082,6 +2105,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2112,6 +2136,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2310,6 +2335,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS", "ScaleUnit": "100%", "Unit": "cpu_core" diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json b/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json index 1a85d935c733..0402adbf7d92 100644 --- a/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json +++ b/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json @@ -98,6 +98,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count. The rest of these subevents count backend stalls, in cycles, due to an outstanding request which is memory bound vs core bound. The subevents are not slot based events and therefore can not be precisely added or subtracted from the Backend_Bound_Aux subevents which are slot based.", "ScaleUnit": "100%" }, @@ -107,6 +108,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound_aux", "MetricThreshold": "tma_backend_bound_aux > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that UOPS must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count. All of these subevents count backend stalls, in slots, due to a resource limitation. These are not cycle based events and therefore can not be precisely added or subtracted from the Backend_Bound subevents which are cycle based. These subevents are supplementary to Backend_Bound and can be used to analyze results from a resource perspective at allocation.", "ScaleUnit": "100%" }, @@ -116,6 +118,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the instruction queue (IQ). Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.", "ScaleUnit": "100%" }, @@ -125,6 +128,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_base", "MetricThreshold": "tma_base > 0.6", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { @@ -142,6 +146,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.05", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { @@ -166,6 +171,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { @@ -207,6 +213,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { @@ -215,6 +222,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.15", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { @@ -239,6 +247,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "ScaleUnit": "100%" }, { @@ -499,6 +508,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.05", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { @@ -515,6 +525,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { @@ -531,6 +542,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_ms_uops", "MetricThreshold": "tma_ms_uops > 0.05", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "Counts the number of uops that are from the complex flows issued by the micro-sequencer (MS). This includes uops from flows due to complex instructions, faults, assists, and inserted flows.", "ScaleUnit": "100%" }, @@ -620,6 +632,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_aux_group", "MetricName": "tma_resource_bound", "MetricThreshold": "tma_resource_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count.", "ScaleUnit": "100%" }, @@ -629,6 +642,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.75", + "MetricgroupNoGroup": "TopdownL1", "ScaleUnit": "100%" }, { diff --git a/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json b/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json index 51cf8560a8d3..f9e2316601e1 100644 --- a/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json +++ b/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json @@ -103,6 +103,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -112,6 +113,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -122,6 +124,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -170,6 +173,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -263,6 +267,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -272,6 +277,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, @@ -326,6 +332,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, @@ -335,6 +342,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -828,6 +836,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -858,6 +867,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -886,6 +896,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1048,6 +1059,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json b/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json index fb57c7382408..e9c46d336a8e 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json +++ b/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json @@ -97,6 +97,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS", "ScaleUnit": "100%" }, @@ -106,6 +107,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -116,6 +118,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: TOPDOWN.BR_MISPREDICT_SLOTS. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -164,6 +167,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -248,6 +252,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -257,6 +262,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, @@ -311,6 +317,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, @@ -320,6 +327,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -795,6 +803,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -825,6 +834,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -853,6 +863,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1013,6 +1024,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json b/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json index 65ec0c9e55d1..437b9867acb9 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json @@ -103,6 +103,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -112,6 +113,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -122,6 +124,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -170,6 +173,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -263,6 +267,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -272,6 +277,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, @@ -326,6 +332,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, @@ -335,6 +342,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -829,6 +837,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -869,6 +878,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -897,6 +907,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1079,6 +1090,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json index 8f7dc72accd0..875c766222e3 100644 --- a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json @@ -101,6 +101,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -110,6 +111,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -120,6 +122,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -167,6 +170,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -271,6 +275,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -280,6 +285,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, @@ -354,6 +360,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, @@ -372,6 +379,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -1142,6 +1150,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -1196,6 +1205,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -1224,6 +1234,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1458,6 +1469,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json b/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json index 2528418200bb..9570a88d6d1c 100644 --- a/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json +++ b/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json @@ -103,6 +103,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -112,6 +113,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -122,6 +124,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -161,6 +164,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -254,6 +258,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -263,6 +268,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, @@ -272,6 +278,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, @@ -281,6 +288,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -663,6 +671,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -693,6 +702,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -721,6 +731,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -874,6 +885,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json b/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json index 11f152c346eb..a522202cf684 100644 --- a/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json @@ -103,6 +103,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -112,6 +113,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -122,6 +124,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -161,6 +164,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -254,6 +258,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -263,6 +268,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, @@ -272,6 +278,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, @@ -281,6 +288,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -664,6 +672,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -704,6 +713,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -732,6 +742,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -905,6 +916,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json b/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json index f45ae3483df4..1a2154f28b7b 100644 --- a/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json @@ -115,6 +115,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS", "ScaleUnit": "100%" }, @@ -124,6 +125,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -141,6 +143,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -187,6 +190,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -288,6 +292,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -297,6 +302,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, @@ -369,6 +375,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, @@ -378,6 +385,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -1111,6 +1119,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -1164,6 +1173,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -1191,6 +1201,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1360,6 +1371,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json b/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json index 0f9b174dfc22..1ef772b40e04 100644 --- a/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json @@ -80,6 +80,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS", "ScaleUnit": "100%" }, @@ -89,6 +90,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -106,6 +108,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -152,6 +155,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -253,6 +257,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -262,6 +267,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, @@ -334,6 +340,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, @@ -343,6 +350,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -1134,6 +1142,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -1187,6 +1196,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -1214,6 +1224,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1410,6 +1421,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json b/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json index 5247f69c13b6..11080ccffd51 100644 --- a/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json +++ b/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json @@ -103,6 +103,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -112,6 +113,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -122,6 +124,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -161,6 +164,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -254,6 +258,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -263,6 +268,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, @@ -299,6 +305,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, @@ -308,6 +315,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -724,6 +732,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -754,6 +763,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -782,6 +792,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -917,6 +928,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json b/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json index 89469b10fa30..65a46d659c0a 100644 --- a/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json +++ b/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json @@ -103,6 +103,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -112,6 +113,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -122,6 +124,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -161,6 +164,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -254,6 +258,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -263,6 +268,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, @@ -299,6 +305,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, @@ -308,6 +315,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -725,6 +733,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -765,6 +774,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -793,6 +803,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -948,6 +959,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json b/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json index e8f4e5c01c9f..66a6f657bd6f 100644 --- a/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json +++ b/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json @@ -76,6 +76,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -85,6 +86,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -95,6 +97,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -114,6 +117,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -160,6 +164,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_lcp", "ScaleUnit": "100%" }, @@ -169,6 +174,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, @@ -205,6 +211,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, @@ -214,6 +221,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -412,6 +420,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -422,6 +431,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -450,6 +460,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -487,6 +498,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json b/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json index 4a99fe515f4b..4b8bc19392a4 100644 --- a/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json +++ b/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json @@ -76,6 +76,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -85,6 +86,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -95,6 +97,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -114,6 +117,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -160,6 +164,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_lcp", "ScaleUnit": "100%" }, @@ -169,6 +174,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, @@ -205,6 +211,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, @@ -214,6 +221,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -411,6 +419,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -421,6 +430,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -449,6 +459,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -486,6 +497,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json index 126300b7ae77..620fc5bd2217 100644 --- a/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json @@ -87,6 +87,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS", "ScaleUnit": "100%" }, @@ -96,6 +97,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -105,6 +107,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: TOPDOWN.BR_MISPREDICT_SLOTS. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -151,6 +154,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -252,6 +256,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 6 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -261,6 +266,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, @@ -351,6 +357,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, @@ -369,6 +376,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences. Sample with: UOPS_RETIRED.HEAVY", "ScaleUnit": "100%" }, @@ -1216,6 +1224,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -1269,6 +1278,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -1304,6 +1314,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1509,6 +1520,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json index a6d212b349f5..21ef6c9be816 100644 --- a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json @@ -101,6 +101,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -110,6 +111,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -120,6 +122,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -167,6 +170,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -271,6 +275,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -280,6 +285,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, @@ -345,6 +351,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, @@ -363,6 +370,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -1065,6 +1073,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -1110,6 +1119,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -1138,6 +1148,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1343,6 +1354,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json index fa2f7f126a30..eb6f12c0343d 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json @@ -101,6 +101,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -110,6 +111,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -120,6 +122,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -167,6 +170,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -271,6 +275,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -280,6 +285,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, @@ -354,6 +360,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, @@ -372,6 +379,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -1123,6 +1131,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -1177,6 +1186,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -1205,6 +1215,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1429,6 +1440,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json b/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json index 4c80d6be6cf1..b442ed4acfbb 100644 --- a/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json @@ -109,6 +109,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS", "ScaleUnit": "100%" }, @@ -118,6 +119,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -135,6 +137,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -181,6 +184,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -282,6 +286,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -291,6 +296,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, @@ -363,6 +369,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, @@ -372,6 +379,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -1125,6 +1133,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -1178,6 +1187,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -1205,6 +1215,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1374,6 +1385,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py index ca99b9cfe4ad..f57a8f274025 100755 --- a/tools/perf/pmu-events/jevents.py +++ b/tools/perf/pmu-events/jevents.py @@ -52,7 +52,8 @@ _json_event_attributes = [ # Attributes that are in pmu_metric rather than pmu_event. _json_metric_attributes = [ 'metric_name', 'metric_group', 'metric_expr', 'metric_threshold', 'desc', - 'long_desc', 'unit', 'compat', 'aggr_mode', 'event_grouping' + 'long_desc', 'unit', 'compat', 'metricgroup_no_group', 'aggr_mode', + 'event_grouping' ] # Attributes that are bools or enum int values, encoded as '0', '1',... _json_enum_attributes = ['aggr_mode', 'deprecated', 'event_grouping', 'perpkg'] @@ -303,6 +304,7 @@ class JsonEvent: self.deprecated = jd.get('Deprecated') self.metric_name = jd.get('MetricName') self.metric_group = jd.get('MetricGroup') + self.metricgroup_no_group = jd.get('MetricgroupNoGroup') self.event_grouping = convert_metric_constraint(jd.get('MetricConstraint')) self.metric_expr = None if 'MetricExpr' in jd: diff --git a/tools/perf/pmu-events/pmu-events.h b/tools/perf/pmu-events/pmu-events.h index b7dff8f1021f..80349685cf4d 100644 --- a/tools/perf/pmu-events/pmu-events.h +++ b/tools/perf/pmu-events/pmu-events.h @@ -59,6 +59,7 @@ struct pmu_metric { const char *compat; const char *desc; const char *long_desc; + const char *metricgroup_no_group; enum aggr_mode_class aggr_mode; enum metric_event_groups event_grouping; }; diff --git a/tools/perf/tests/attr.py b/tools/perf/tests/attr.py index ccfef861e931..e890c261ad26 100644 --- a/tools/perf/tests/attr.py +++ b/tools/perf/tests/attr.py @@ -152,7 +152,7 @@ def parse_version(version): # - expected values assignments class Test(object): def __init__(self, path, options): - parser = configparser.SafeConfigParser() + parser = configparser.ConfigParser() parser.read(path) log.warning("running '%s'" % path) @@ -247,7 +247,7 @@ class Test(object): return True def load_events(self, path, events): - parser_event = configparser.SafeConfigParser() + parser_event = configparser.ConfigParser() parser_event.read(path) # The event record section header contains 'event' word, @@ -261,7 +261,7 @@ class Test(object): # Read parent event if there's any if (':' in section): base = section[section.index(':') + 1:] - parser_base = configparser.SafeConfigParser() + parser_base = configparser.ConfigParser() parser_base.read(self.test_dir + '/' + base) base_items = parser_base.items('event') diff --git a/tools/perf/tests/attr/base-stat b/tools/perf/tests/attr/base-stat index a21fb65bc012..fccd8ec4d1b0 100644 --- a/tools/perf/tests/attr/base-stat +++ b/tools/perf/tests/attr/base-stat @@ -16,7 +16,7 @@ pinned=0 exclusive=0 exclude_user=0 exclude_kernel=0|1 -exclude_hv=0 +exclude_hv=0|1 exclude_idle=0 mmap=0 comm=0 diff --git a/tools/perf/tests/attr/test-stat-default b/tools/perf/tests/attr/test-stat-default index d8ea6a88163f..a1e2da0a9a6d 100644 --- a/tools/perf/tests/attr/test-stat-default +++ b/tools/perf/tests/attr/test-stat-default @@ -40,7 +40,6 @@ fd=6 type=0 config=7 optional=1 - # PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_BACKEND [event7:base-stat] fd=7 @@ -89,79 +88,98 @@ enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-bad-spec (0x8100) +# PERF_TYPE_RAW / topdown-fe-bound (0x8200) [event13:base-stat] fd=13 group_fd=11 type=4 -config=33024 +config=33280 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-fe-bound (0x8200) +# PERF_TYPE_RAW / topdown-be-bound (0x8300) [event14:base-stat] fd=14 group_fd=11 type=4 -config=33280 +config=33536 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-be-bound (0x8300) +# PERF_TYPE_RAW / topdown-bad-spec (0x8100) [event15:base-stat] fd=15 group_fd=11 type=4 -config=33536 +config=33024 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-heavy-ops (0x8400) +# PERF_TYPE_RAW / INT_MISC.UOP_DROPPING [event16:base-stat] fd=16 -group_fd=11 type=4 -config=33792 -disabled=0 -enable_on_exec=0 -read_format=15 +config=4109 optional=1 -# PERF_TYPE_RAW / topdown-br-mispredict (0x8500) +# PERF_TYPE_RAW / cpu/INT_MISC.RECOVERY_CYCLES,cmask=1,edge/ [event17:base-stat] fd=17 -group_fd=11 type=4 -config=34048 -disabled=0 -enable_on_exec=0 -read_format=15 +config=17039629 optional=1 -# PERF_TYPE_RAW / topdown-fetch-lat (0x8600) +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.THREAD [event18:base-stat] fd=18 -group_fd=11 type=4 -config=34304 -disabled=0 -enable_on_exec=0 -read_format=15 +config=60 optional=1 -# PERF_TYPE_RAW / topdown-mem-bound (0x8700) +# PERF_TYPE_RAW / INT_MISC.RECOVERY_CYCLES_ANY [event19:base-stat] fd=19 -group_fd=11 type=4 -config=34560 -disabled=0 -enable_on_exec=0 -read_format=15 +config=2097421 +optional=1 + +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.REF_XCLK +[event20:base-stat] +fd=20 +type=4 +config=316 +optional=1 + +# PERF_TYPE_RAW / IDQ_UOPS_NOT_DELIVERED.CORE +[event21:base-stat] +fd=21 +type=4 +config=412 +optional=1 + +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE +[event22:base-stat] +fd=22 +type=4 +config=572 +optional=1 + +# PERF_TYPE_RAW / UOPS_RETIRED.RETIRE_SLOTS +[event23:base-stat] +fd=23 +type=4 +config=706 +optional=1 + +# PERF_TYPE_RAW / UOPS_ISSUED.ANY +[event24:base-stat] +fd=24 +type=4 +config=270 optional=1 diff --git a/tools/perf/tests/attr/test-stat-detailed-1 b/tools/perf/tests/attr/test-stat-detailed-1 index b656ab93c5bf..1c52cb05c900 100644 --- a/tools/perf/tests/attr/test-stat-detailed-1 +++ b/tools/perf/tests/attr/test-stat-detailed-1 @@ -90,89 +90,108 @@ enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-bad-spec (0x8100) +# PERF_TYPE_RAW / topdown-fe-bound (0x8200) [event13:base-stat] fd=13 group_fd=11 type=4 -config=33024 +config=33280 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-fe-bound (0x8200) +# PERF_TYPE_RAW / topdown-be-bound (0x8300) [event14:base-stat] fd=14 group_fd=11 type=4 -config=33280 +config=33536 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-be-bound (0x8300) +# PERF_TYPE_RAW / topdown-bad-spec (0x8100) [event15:base-stat] fd=15 group_fd=11 type=4 -config=33536 +config=33024 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-heavy-ops (0x8400) +# PERF_TYPE_RAW / INT_MISC.UOP_DROPPING [event16:base-stat] fd=16 -group_fd=11 type=4 -config=33792 -disabled=0 -enable_on_exec=0 -read_format=15 +config=4109 optional=1 -# PERF_TYPE_RAW / topdown-br-mispredict (0x8500) +# PERF_TYPE_RAW / cpu/INT_MISC.RECOVERY_CYCLES,cmask=1,edge/ [event17:base-stat] fd=17 -group_fd=11 type=4 -config=34048 -disabled=0 -enable_on_exec=0 -read_format=15 +config=17039629 optional=1 -# PERF_TYPE_RAW / topdown-fetch-lat (0x8600) +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.THREAD [event18:base-stat] fd=18 -group_fd=11 type=4 -config=34304 -disabled=0 -enable_on_exec=0 -read_format=15 +config=60 optional=1 -# PERF_TYPE_RAW / topdown-mem-bound (0x8700) +# PERF_TYPE_RAW / INT_MISC.RECOVERY_CYCLES_ANY [event19:base-stat] fd=19 -group_fd=11 type=4 -config=34560 -disabled=0 -enable_on_exec=0 -read_format=15 +config=2097421 +optional=1 + +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.REF_XCLK +[event20:base-stat] +fd=20 +type=4 +config=316 +optional=1 + +# PERF_TYPE_RAW / IDQ_UOPS_NOT_DELIVERED.CORE +[event21:base-stat] +fd=21 +type=4 +config=412 +optional=1 + +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE +[event22:base-stat] +fd=22 +type=4 +config=572 +optional=1 + +# PERF_TYPE_RAW / UOPS_RETIRED.RETIRE_SLOTS +[event23:base-stat] +fd=23 +type=4 +config=706 +optional=1 + +# PERF_TYPE_RAW / UOPS_ISSUED.ANY +[event24:base-stat] +fd=24 +type=4 +config=270 optional=1 # PERF_TYPE_HW_CACHE / # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event20:base-stat] -fd=20 +[event25:base-stat] +fd=25 type=3 config=0 optional=1 @@ -181,8 +200,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event21:base-stat] -fd=21 +[event26:base-stat] +fd=26 type=3 config=65536 optional=1 @@ -191,8 +210,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event22:base-stat] -fd=22 +[event27:base-stat] +fd=27 type=3 config=2 optional=1 @@ -201,8 +220,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event23:base-stat] -fd=23 +[event28:base-stat] +fd=28 type=3 config=65538 optional=1 diff --git a/tools/perf/tests/attr/test-stat-detailed-2 b/tools/perf/tests/attr/test-stat-detailed-2 index 97625090a1c4..7e961d24a885 100644 --- a/tools/perf/tests/attr/test-stat-detailed-2 +++ b/tools/perf/tests/attr/test-stat-detailed-2 @@ -90,89 +90,108 @@ enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-bad-spec (0x8100) +# PERF_TYPE_RAW / topdown-fe-bound (0x8200) [event13:base-stat] fd=13 group_fd=11 type=4 -config=33024 +config=33280 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-fe-bound (0x8200) +# PERF_TYPE_RAW / topdown-be-bound (0x8300) [event14:base-stat] fd=14 group_fd=11 type=4 -config=33280 +config=33536 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-be-bound (0x8300) +# PERF_TYPE_RAW / topdown-bad-spec (0x8100) [event15:base-stat] fd=15 group_fd=11 type=4 -config=33536 +config=33024 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-heavy-ops (0x8400) +# PERF_TYPE_RAW / INT_MISC.UOP_DROPPING [event16:base-stat] fd=16 -group_fd=11 type=4 -config=33792 -disabled=0 -enable_on_exec=0 -read_format=15 +config=4109 optional=1 -# PERF_TYPE_RAW / topdown-br-mispredict (0x8500) +# PERF_TYPE_RAW / cpu/INT_MISC.RECOVERY_CYCLES,cmask=1,edge/ [event17:base-stat] fd=17 -group_fd=11 type=4 -config=34048 -disabled=0 -enable_on_exec=0 -read_format=15 +config=17039629 optional=1 -# PERF_TYPE_RAW / topdown-fetch-lat (0x8600) +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.THREAD [event18:base-stat] fd=18 -group_fd=11 type=4 -config=34304 -disabled=0 -enable_on_exec=0 -read_format=15 +config=60 optional=1 -# PERF_TYPE_RAW / topdown-mem-bound (0x8700) +# PERF_TYPE_RAW / INT_MISC.RECOVERY_CYCLES_ANY [event19:base-stat] fd=19 -group_fd=11 type=4 -config=34560 -disabled=0 -enable_on_exec=0 -read_format=15 +config=2097421 +optional=1 + +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.REF_XCLK +[event20:base-stat] +fd=20 +type=4 +config=316 +optional=1 + +# PERF_TYPE_RAW / IDQ_UOPS_NOT_DELIVERED.CORE +[event21:base-stat] +fd=21 +type=4 +config=412 +optional=1 + +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE +[event22:base-stat] +fd=22 +type=4 +config=572 +optional=1 + +# PERF_TYPE_RAW / UOPS_RETIRED.RETIRE_SLOTS +[event23:base-stat] +fd=23 +type=4 +config=706 +optional=1 + +# PERF_TYPE_RAW / UOPS_ISSUED.ANY +[event24:base-stat] +fd=24 +type=4 +config=270 optional=1 # PERF_TYPE_HW_CACHE / # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event20:base-stat] -fd=20 +[event25:base-stat] +fd=25 type=3 config=0 optional=1 @@ -181,8 +200,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event21:base-stat] -fd=21 +[event26:base-stat] +fd=26 type=3 config=65536 optional=1 @@ -191,8 +210,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event22:base-stat] -fd=22 +[event27:base-stat] +fd=27 type=3 config=2 optional=1 @@ -201,8 +220,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event23:base-stat] -fd=23 +[event28:base-stat] +fd=28 type=3 config=65538 optional=1 @@ -211,8 +230,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1I << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event24:base-stat] -fd=24 +[event29:base-stat] +fd=29 type=3 config=1 optional=1 @@ -221,8 +240,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1I << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event25:base-stat] -fd=25 +[event30:base-stat] +fd=30 type=3 config=65537 optional=1 @@ -231,8 +250,8 @@ optional=1 # PERF_COUNT_HW_CACHE_DTLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event26:base-stat] -fd=26 +[event31:base-stat] +fd=31 type=3 config=3 optional=1 @@ -241,8 +260,8 @@ optional=1 # PERF_COUNT_HW_CACHE_DTLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event27:base-stat] -fd=27 +[event32:base-stat] +fd=32 type=3 config=65539 optional=1 @@ -251,8 +270,8 @@ optional=1 # PERF_COUNT_HW_CACHE_ITLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event28:base-stat] -fd=28 +[event33:base-stat] +fd=33 type=3 config=4 optional=1 @@ -261,8 +280,8 @@ optional=1 # PERF_COUNT_HW_CACHE_ITLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event29:base-stat] -fd=29 +[event34:base-stat] +fd=34 type=3 config=65540 optional=1 diff --git a/tools/perf/tests/attr/test-stat-detailed-3 b/tools/perf/tests/attr/test-stat-detailed-3 index d555042e3fbf..e50535f45977 100644 --- a/tools/perf/tests/attr/test-stat-detailed-3 +++ b/tools/perf/tests/attr/test-stat-detailed-3 @@ -90,89 +90,108 @@ enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-bad-spec (0x8100) +# PERF_TYPE_RAW / topdown-fe-bound (0x8200) [event13:base-stat] fd=13 group_fd=11 type=4 -config=33024 +config=33280 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-fe-bound (0x8200) +# PERF_TYPE_RAW / topdown-be-bound (0x8300) [event14:base-stat] fd=14 group_fd=11 type=4 -config=33280 +config=33536 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-be-bound (0x8300) +# PERF_TYPE_RAW / topdown-bad-spec (0x8100) [event15:base-stat] fd=15 group_fd=11 type=4 -config=33536 +config=33024 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-heavy-ops (0x8400) +# PERF_TYPE_RAW / INT_MISC.UOP_DROPPING [event16:base-stat] fd=16 -group_fd=11 type=4 -config=33792 -disabled=0 -enable_on_exec=0 -read_format=15 +config=4109 optional=1 -# PERF_TYPE_RAW / topdown-br-mispredict (0x8500) +# PERF_TYPE_RAW / cpu/INT_MISC.RECOVERY_CYCLES,cmask=1,edge/ [event17:base-stat] fd=17 -group_fd=11 type=4 -config=34048 -disabled=0 -enable_on_exec=0 -read_format=15 +config=17039629 optional=1 -# PERF_TYPE_RAW / topdown-fetch-lat (0x8600) +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.THREAD [event18:base-stat] fd=18 -group_fd=11 type=4 -config=34304 -disabled=0 -enable_on_exec=0 -read_format=15 +config=60 optional=1 -# PERF_TYPE_RAW / topdown-mem-bound (0x8700) +# PERF_TYPE_RAW / INT_MISC.RECOVERY_CYCLES_ANY [event19:base-stat] fd=19 -group_fd=11 type=4 -config=34560 -disabled=0 -enable_on_exec=0 -read_format=15 +config=2097421 +optional=1 + +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.REF_XCLK +[event20:base-stat] +fd=20 +type=4 +config=316 +optional=1 + +# PERF_TYPE_RAW / IDQ_UOPS_NOT_DELIVERED.CORE +[event21:base-stat] +fd=21 +type=4 +config=412 +optional=1 + +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE +[event22:base-stat] +fd=22 +type=4 +config=572 +optional=1 + +# PERF_TYPE_RAW / UOPS_RETIRED.RETIRE_SLOTS +[event23:base-stat] +fd=23 +type=4 +config=706 +optional=1 + +# PERF_TYPE_RAW / UOPS_ISSUED.ANY +[event24:base-stat] +fd=24 +type=4 +config=270 optional=1 # PERF_TYPE_HW_CACHE / # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event20:base-stat] -fd=20 +[event25:base-stat] +fd=25 type=3 config=0 optional=1 @@ -181,8 +200,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event21:base-stat] -fd=21 +[event26:base-stat] +fd=26 type=3 config=65536 optional=1 @@ -191,8 +210,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event22:base-stat] -fd=22 +[event27:base-stat] +fd=27 type=3 config=2 optional=1 @@ -201,8 +220,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event23:base-stat] -fd=23 +[event28:base-stat] +fd=28 type=3 config=65538 optional=1 @@ -211,8 +230,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1I << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event24:base-stat] -fd=24 +[event29:base-stat] +fd=29 type=3 config=1 optional=1 @@ -221,8 +240,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1I << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event25:base-stat] -fd=25 +[event30:base-stat] +fd=30 type=3 config=65537 optional=1 @@ -231,8 +250,8 @@ optional=1 # PERF_COUNT_HW_CACHE_DTLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event26:base-stat] -fd=26 +[event31:base-stat] +fd=31 type=3 config=3 optional=1 @@ -241,8 +260,8 @@ optional=1 # PERF_COUNT_HW_CACHE_DTLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event27:base-stat] -fd=27 +[event32:base-stat] +fd=32 type=3 config=65539 optional=1 @@ -251,8 +270,8 @@ optional=1 # PERF_COUNT_HW_CACHE_ITLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event28:base-stat] -fd=28 +[event33:base-stat] +fd=33 type=3 config=4 optional=1 @@ -261,8 +280,8 @@ optional=1 # PERF_COUNT_HW_CACHE_ITLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event29:base-stat] -fd=29 +[event34:base-stat] +fd=34 type=3 config=65540 optional=1 @@ -271,8 +290,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_PREFETCH << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event30:base-stat] -fd=30 +[event35:base-stat] +fd=35 type=3 config=512 optional=1 @@ -281,8 +300,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_PREFETCH << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event31:base-stat] -fd=31 +[event36:base-stat] +fd=36 type=3 config=66048 optional=1 diff --git a/tools/perf/tests/expr.c b/tools/perf/tests/expr.c index cbf0e0c74906..733ead151c63 100644 --- a/tools/perf/tests/expr.c +++ b/tools/perf/tests/expr.c @@ -120,7 +120,8 @@ static int test__expr(struct test_suite *t __maybe_unused, int subtest __maybe_u p = "FOO/0"; ret = expr__parse(&val, ctx, p); - TEST_ASSERT_VAL("division by zero", ret == -1); + TEST_ASSERT_VAL("division by zero", ret == 0); + TEST_ASSERT_VAL("division by zero", isnan(val)); p = "BAR/"; ret = expr__parse(&val, ctx, p); diff --git a/tools/perf/tests/parse-metric.c b/tools/perf/tests/parse-metric.c index 1185b79e6274..c05148ea400c 100644 --- a/tools/perf/tests/parse-metric.c +++ b/tools/perf/tests/parse-metric.c @@ -38,6 +38,7 @@ static void load_runtime_stat(struct evlist *evlist, struct value *vals) evlist__alloc_aggr_stats(evlist, 1); evlist__for_each_entry(evlist, evsel) { count = find_value(evsel->name, vals); + evsel->supported = true; evsel->stats->aggr->counts.val = count; if (evsel__name_is(evsel, "duration_time")) update_stats(&walltime_nsecs_stats, count); diff --git a/tools/perf/tests/shell/stat.sh b/tools/perf/tests/shell/stat.sh index 2c1d3f704995..b154fbb15d54 100755 --- a/tools/perf/tests/shell/stat.sh +++ b/tools/perf/tests/shell/stat.sh @@ -28,6 +28,18 @@ test_stat_record_report() { echo "stat record and report test [Success]" } +test_stat_record_script() { + echo "stat record and script test" + if ! perf stat record -o - true | perf script -i - 2>&1 | \ + grep -E -q "CPU[[:space:]]+THREAD[[:space:]]+VAL[[:space:]]+ENA[[:space:]]+RUN[[:space:]]+TIME[[:space:]]+EVENT" + then + echo "stat record and script test [Failed]" + err=1 + return + fi + echo "stat record and script test [Success]" +} + test_stat_repeat_weak_groups() { echo "stat repeat weak groups test" if ! perf stat -e '{cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles}' \ @@ -93,6 +105,7 @@ test_topdown_weak_groups() { test_default_stat test_stat_record_report +test_stat_record_script test_stat_repeat_weak_groups test_topdown_groups test_topdown_weak_groups diff --git a/tools/perf/tests/shell/test_intel_pt.sh b/tools/perf/tests/shell/test_intel_pt.sh index 4ddb17cb83c5..3a8b9bffa022 100755 --- a/tools/perf/tests/shell/test_intel_pt.sh +++ b/tools/perf/tests/shell/test_intel_pt.sh @@ -506,6 +506,13 @@ test_sample() echo "perf record failed with --aux-sample" return 1 fi + # Check with event with PMU name + if perf_record_no_decode -o "${perfdatafile}" -e br_misp_retired.all_branches:u uname ; then + if ! perf_record_no_decode -o "${perfdatafile}" -e '{intel_pt//,br_misp_retired.all_branches/aux-sample-size=8192/}:u' uname ; then + echo "perf record failed with --aux-sample-size" + return 1 + fi + fi echo OK return 0 } diff --git a/tools/perf/tests/shell/test_java_symbol.sh b/tools/perf/tests/shell/test_java_symbol.sh index 90cea8811926..499539d1c479 100755 --- a/tools/perf/tests/shell/test_java_symbol.sh +++ b/tools/perf/tests/shell/test_java_symbol.sh @@ -56,7 +56,7 @@ if [ $? -ne 0 ]; then exit 1 fi -if ! perf inject -i $PERF_DATA -o $PERF_INJ_DATA -j; then +if ! DEBUGINFOD_URLS='' perf inject -i $PERF_DATA -o $PERF_INJ_DATA -j; then echo "Fail to inject samples" exit 1 fi diff --git a/tools/perf/trace/beauty/arch_prctl.c b/tools/perf/trace/beauty/arch_prctl.c index fe022ca67e60..a211348d3204 100644 --- a/tools/perf/trace/beauty/arch_prctl.c +++ b/tools/perf/trace/beauty/arch_prctl.c @@ -12,10 +12,12 @@ static DEFINE_STRARRAY_OFFSET(x86_arch_prctl_codes_1, "ARCH_", x86_arch_prctl_codes_1_offset); static DEFINE_STRARRAY_OFFSET(x86_arch_prctl_codes_2, "ARCH_", x86_arch_prctl_codes_2_offset); +static DEFINE_STRARRAY_OFFSET(x86_arch_prctl_codes_3, "ARCH_", x86_arch_prctl_codes_3_offset); static struct strarray *x86_arch_prctl_codes[] = { &strarray__x86_arch_prctl_codes_1, &strarray__x86_arch_prctl_codes_2, + &strarray__x86_arch_prctl_codes_3, }; static DEFINE_STRARRAYS(x86_arch_prctl_codes); diff --git a/tools/perf/trace/beauty/x86_arch_prctl.sh b/tools/perf/trace/beauty/x86_arch_prctl.sh index 57fa6aaffe70..fd5c740512c5 100755 --- a/tools/perf/trace/beauty/x86_arch_prctl.sh +++ b/tools/perf/trace/beauty/x86_arch_prctl.sh @@ -24,3 +24,4 @@ print_range () { print_range 1 0x1 0x1001 print_range 2 0x2 0x2001 +print_range 3 0x4 0x4001 diff --git a/tools/perf/util/Build b/tools/perf/util/Build index bd18fe5f2719..f9df1df1eec0 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -214,7 +214,7 @@ perf-$(CONFIG_ZSTD) += zstd.o perf-$(CONFIG_LIBCAP) += cap.o -perf-y += demangle-cxx.o +perf-$(CONFIG_CXX_DEMANGLE) += demangle-cxx.o perf-y += demangle-ocaml.o perf-y += demangle-java.o perf-y += demangle-rust.o diff --git a/tools/perf/util/bpf_skel/lock_contention.bpf.c b/tools/perf/util/bpf_skel/lock_contention.bpf.c index 8d3cfbb3cc65..1d48226ae75d 100644 --- a/tools/perf/util/bpf_skel/lock_contention.bpf.c +++ b/tools/perf/util/bpf_skel/lock_contention.bpf.c @@ -416,6 +416,8 @@ int contention_end(u64 *ctx) return 0; } +struct rq {}; + extern struct rq runqueues __ksym; struct rq___old { diff --git a/tools/perf/util/bpf_skel/sample_filter.bpf.c b/tools/perf/util/bpf_skel/sample_filter.bpf.c index cffe493af1ed..fb94f5280626 100644 --- a/tools/perf/util/bpf_skel/sample_filter.bpf.c +++ b/tools/perf/util/bpf_skel/sample_filter.bpf.c @@ -25,7 +25,7 @@ struct perf_sample_data___new { } __attribute__((preserve_access_index)); /* new kernel perf_mem_data_src definition */ -union perf_mem_data_src__new { +union perf_mem_data_src___new { __u64 val; struct { __u64 mem_op:5, /* type of opcode */ @@ -108,7 +108,7 @@ static inline __u64 perf_get_sample(struct bpf_perf_event_data_kern *kctx, if (entry->part == 7) return kctx->data->data_src.mem_blk; if (entry->part == 8) { - union perf_mem_data_src__new *data = (void *)&kctx->data->data_src; + union perf_mem_data_src___new *data = (void *)&kctx->data->data_src; if (bpf_core_field_exists(data->mem_hops)) return data->mem_hops; diff --git a/tools/perf/util/bpf_skel/vmlinux.h b/tools/perf/util/bpf_skel/vmlinux.h index 449b1ea91fc4..c7ed51b0c1ef 100644 --- a/tools/perf/util/bpf_skel/vmlinux.h +++ b/tools/perf/util/bpf_skel/vmlinux.h @@ -1,6 +1,7 @@ #ifndef __VMLINUX_H #define __VMLINUX_H +#include <linux/stddef.h> // for define __always_inline #include <linux/bpf.h> #include <linux/types.h> #include <linux/perf_event.h> diff --git a/tools/perf/util/cs-etm.h b/tools/perf/util/cs-etm.h index 70cac0375b34..ecca40787ac9 100644 --- a/tools/perf/util/cs-etm.h +++ b/tools/perf/util/cs-etm.h @@ -227,6 +227,19 @@ struct cs_etm_packet_queue { #define INFO_HEADER_SIZE (sizeof(((struct perf_record_auxtrace_info *)0)->type) + \ sizeof(((struct perf_record_auxtrace_info *)0)->reserved__)) +/* CoreSight trace ID is currently the bottom 7 bits of the value */ +#define CORESIGHT_TRACE_ID_VAL_MASK GENMASK(6, 0) + +/* + * perf record will set the legacy meta data values as unused initially. + * This allows perf report to manage the decoders created when dynamic + * allocation in operation. + */ +#define CORESIGHT_TRACE_ID_UNUSED_FLAG BIT(31) + +/* Value to set for unused trace ID values */ +#define CORESIGHT_TRACE_ID_UNUSED_VAL 0x7F + int cs_etm__process_auxtrace_info(union perf_event *event, struct perf_session *session); struct perf_event_attr *cs_etm_get_default_config(struct perf_pmu *pmu); diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 356c07f03be6..c2dbb5647e75 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -282,6 +282,7 @@ void evsel__init(struct evsel *evsel, evsel->bpf_fd = -1; INIT_LIST_HEAD(&evsel->config_terms); INIT_LIST_HEAD(&evsel->bpf_counter_list); + INIT_LIST_HEAD(&evsel->bpf_filters); perf_evsel__object.init(evsel); evsel->sample_size = __evsel__sample_size(attr->sample_type); evsel__calc_id_pos(evsel); @@ -290,6 +291,7 @@ void evsel__init(struct evsel *evsel, evsel->per_pkg_mask = NULL; evsel->collect_stat = false; evsel->pmu_name = NULL; + evsel->skippable = false; } struct evsel *evsel__new_idx(struct perf_event_attr *attr, int idx) @@ -828,26 +830,26 @@ bool evsel__name_is(struct evsel *evsel, const char *name) const char *evsel__group_pmu_name(const struct evsel *evsel) { - const struct evsel *leader; + struct evsel *leader = evsel__leader(evsel); + struct evsel *pos; - /* If the pmu_name is set use it. pmu_name isn't set for CPU and software events. */ - if (evsel->pmu_name) - return evsel->pmu_name; /* * Software events may be in a group with other uncore PMU events. Use - * the pmu_name of the group leader to avoid breaking the software event - * out of the group. + * the pmu_name of the first non-software event to avoid breaking the + * software event out of the group. * * Aux event leaders, like intel_pt, expect a group with events from * other PMUs, so substitute the AUX event's PMU in this case. */ - leader = evsel__leader(evsel); - if ((evsel->core.attr.type == PERF_TYPE_SOFTWARE || evsel__is_aux_event(leader)) && - leader->pmu_name) { - return leader->pmu_name; + if (evsel->core.attr.type == PERF_TYPE_SOFTWARE || evsel__is_aux_event(leader)) { + /* Starting with the leader, find the first event with a named PMU. */ + for_each_group_evsel(pos, leader) { + if (pos->pmu_name) + return pos->pmu_name; + } } - return "cpu"; + return evsel->pmu_name ?: "cpu"; } const char *evsel__metric_id(const struct evsel *evsel) @@ -1725,9 +1727,13 @@ static int get_group_fd(struct evsel *evsel, int cpu_map_idx, int thread) return -1; fd = FD(leader, cpu_map_idx, thread); - BUG_ON(fd == -1); + BUG_ON(fd == -1 && !leader->skippable); - return fd; + /* + * When the leader has been skipped, return -2 to distinguish from no + * group leader case. + */ + return fd == -1 ? -2 : fd; } static void evsel__remove_fd(struct evsel *pos, int nr_cpus, int nr_threads, int thread_idx) @@ -2109,6 +2115,12 @@ retry_open: group_fd = get_group_fd(evsel, idx, thread); + if (group_fd == -2) { + pr_debug("broken group leader for %s\n", evsel->name); + err = -EINVAL; + goto out_close; + } + test_attr__ready(); /* Debug message used by test scripts */ diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index d575390d80bc..0f54f28a69c2 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -95,6 +95,7 @@ struct evsel { bool weak_group; bool bpf_counter; bool use_config_name; + bool skippable; int bpf_fd; struct bpf_object *bpf_obj; struct list_head config_terms; @@ -150,10 +151,8 @@ struct evsel { */ struct bpf_counter_ops *bpf_counter_ops; - union { - struct list_head bpf_counter_list; /* for perf-stat -b */ - struct list_head bpf_filters; /* for perf-record --filter */ - }; + struct list_head bpf_counter_list; /* for perf-stat -b */ + struct list_head bpf_filters; /* for perf-record --filter */ /* for perf-stat --use-bpf */ int bperf_leader_prog_fd; diff --git a/tools/perf/util/expr.y b/tools/perf/util/expr.y index 250e444bf032..4ce931cccb63 100644 --- a/tools/perf/util/expr.y +++ b/tools/perf/util/expr.y @@ -225,7 +225,11 @@ expr: NUMBER { if (fpclassify($3.val) == FP_ZERO) { pr_debug("division by zero\n"); - YYABORT; + assert($3.ids == NULL); + if (compute_ids) + ids__free($1.ids); + $$.val = NAN; + $$.ids = NULL; } else if (!compute_ids || (is_const($1.val) && is_const($3.val))) { assert($1.ids == NULL); assert($3.ids == NULL); diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index c566c6859302..5e9c657dd3f7 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -1144,12 +1144,12 @@ static int metricgroup__add_metric_callback(const struct pmu_metric *pm, struct metricgroup__add_metric_data *data = vdata; int ret = 0; - if (pm->metric_expr && - (match_metric(pm->metric_group, data->metric_name) || - match_metric(pm->metric_name, data->metric_name))) { + if (pm->metric_expr && match_pm_metric(pm, data->metric_name)) { + bool metric_no_group = data->metric_no_group || + match_metric(data->metric_name, pm->metricgroup_no_group); data->has_match = true; - ret = add_metric(data->list, pm, data->modifier, data->metric_no_group, + ret = add_metric(data->list, pm, data->modifier, metric_no_group, data->metric_no_threshold, data->user_requested_cpu_list, data->system_wide, /*root_metric=*/NULL, /*visited_metrics=*/NULL, table); @@ -1672,7 +1672,7 @@ static int metricgroup__topdown_max_level_callback(const struct pmu_metric *pm, { unsigned int *max_level = data; unsigned int level; - const char *p = strstr(pm->metric_group, "TopdownL"); + const char *p = strstr(pm->metric_group ?: "", "TopdownL"); if (!p || p[8] == '\0') return 0; diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index d71019dcd614..34ba840ae19a 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -2140,25 +2140,32 @@ static int evlist__cmp(void *state, const struct list_head *l, const struct list int *leader_idx = state; int lhs_leader_idx = *leader_idx, rhs_leader_idx = *leader_idx, ret; const char *lhs_pmu_name, *rhs_pmu_name; + bool lhs_has_group = false, rhs_has_group = false; /* * First sort by grouping/leader. Read the leader idx only if the evsel * is part of a group, as -1 indicates no group. */ - if (lhs_core->leader != lhs_core || lhs_core->nr_members > 1) + if (lhs_core->leader != lhs_core || lhs_core->nr_members > 1) { + lhs_has_group = true; lhs_leader_idx = lhs_core->leader->idx; - if (rhs_core->leader != rhs_core || rhs_core->nr_members > 1) + } + if (rhs_core->leader != rhs_core || rhs_core->nr_members > 1) { + rhs_has_group = true; rhs_leader_idx = rhs_core->leader->idx; + } if (lhs_leader_idx != rhs_leader_idx) return lhs_leader_idx - rhs_leader_idx; - /* Group by PMU. Groups can't span PMUs. */ - lhs_pmu_name = evsel__group_pmu_name(lhs); - rhs_pmu_name = evsel__group_pmu_name(rhs); - ret = strcmp(lhs_pmu_name, rhs_pmu_name); - if (ret) - return ret; + /* Group by PMU if there is a group. Groups can't span PMUs. */ + if (lhs_has_group && rhs_has_group) { + lhs_pmu_name = evsel__group_pmu_name(lhs); + rhs_pmu_name = evsel__group_pmu_name(rhs); + ret = strcmp(lhs_pmu_name, rhs_pmu_name); + if (ret) + return ret; + } /* Architecture specific sorting. */ return arch_evlist__cmp(lhs, rhs); diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index 73b2ff2ddf29..bf5a6c14dfcd 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -431,7 +431,7 @@ static void print_metric_json(struct perf_stat_config *config __maybe_unused, struct outstate *os = ctx; FILE *out = os->fh; - fprintf(out, "\"metric-value\" : %f, ", val); + fprintf(out, "\"metric-value\" : \"%f\", ", val); fprintf(out, "\"metric-unit\" : \"%s\"", unit); if (!config->metric_only) fprintf(out, "}"); diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index eeccab6751d7..1566a206ba42 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -403,12 +403,25 @@ static int prepare_metric(struct evsel **metric_events, if (!aggr) break; - /* - * If an event was scaled during stat gathering, reverse - * the scale before computing the metric. - */ - val = aggr->counts.val * (1.0 / metric_events[i]->scale); - source_count = evsel__source_count(metric_events[i]); + if (!metric_events[i]->supported) { + /* + * Not supported events will have a count of 0, + * which can be confusing in a + * metric. Explicitly set the value to NAN. Not + * counted events (enable time of 0) are read as + * 0. + */ + val = NAN; + source_count = 0; + } else { + /* + * If an event was scaled during stat gathering, + * reverse the scale before computing the + * metric. + */ + val = aggr->counts.val * (1.0 / metric_events[i]->scale); + source_count = evsel__source_count(metric_events[i]); + } } n = strdup(evsel__metric_id(metric_events[i])); if (!n) diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index b2ed9cc52265..63882a4db5c7 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -31,6 +31,13 @@ #include <bfd.h> #endif +#if defined(HAVE_LIBBFD_SUPPORT) || defined(HAVE_CPLUS_DEMANGLE_SUPPORT) +#ifndef DMGL_PARAMS +#define DMGL_PARAMS (1 << 0) /* Include function args */ +#define DMGL_ANSI (1 << 1) /* Include const, volatile, etc */ +#endif +#endif + #ifndef EM_AARCH64 #define EM_AARCH64 183 /* ARM 64 bit */ #endif @@ -271,6 +278,26 @@ static bool want_demangle(bool is_kernel_sym) return is_kernel_sym ? symbol_conf.demangle_kernel : symbol_conf.demangle; } +/* + * Demangle C++ function signature, typically replaced by demangle-cxx.cpp + * version. + */ +__weak char *cxx_demangle_sym(const char *str __maybe_unused, bool params __maybe_unused, + bool modifiers __maybe_unused) +{ +#ifdef HAVE_LIBBFD_SUPPORT + int flags = (params ? DMGL_PARAMS : 0) | (modifiers ? DMGL_ANSI : 0); + + return bfd_demangle(NULL, str, flags); +#elif defined(HAVE_CPLUS_DEMANGLE_SUPPORT) + int flags = (params ? DMGL_PARAMS : 0) | (modifiers ? DMGL_ANSI : 0); + + return cplus_demangle(str, flags); +#else + return NULL; +#endif +} + static char *demangle_sym(struct dso *dso, int kmodule, const char *elf_name) { char *demangled = NULL; diff --git a/tools/power/cpupower/lib/powercap.c b/tools/power/cpupower/lib/powercap.c index 0ce29ee4c2e4..a7a59c6bacda 100644 --- a/tools/power/cpupower/lib/powercap.c +++ b/tools/power/cpupower/lib/powercap.c @@ -40,25 +40,34 @@ static int sysfs_get_enabled(char *path, int *mode) { int fd; char yes_no; + int ret = 0; *mode = 0; fd = open(path, O_RDONLY); - if (fd == -1) - return -1; + if (fd == -1) { + ret = -1; + goto out; + } if (read(fd, &yes_no, 1) != 1) { - close(fd); - return -1; + ret = -1; + goto out_close; } if (yes_no == '1') { *mode = 1; - return 0; + goto out_close; } else if (yes_no == '0') { - return 0; + goto out_close; + } else { + ret = -1; + goto out_close; } - return -1; +out_close: + close(fd); +out: + return ret; } int powercap_get_enabled(int *mode) diff --git a/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c b/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c index e7d48cb563c0..ae6af354a81d 100644 --- a/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c +++ b/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c @@ -70,8 +70,8 @@ static int max_freq_mode; */ static unsigned long max_frequency; -static unsigned long long tsc_at_measure_start; -static unsigned long long tsc_at_measure_end; +static unsigned long long *tsc_at_measure_start; +static unsigned long long *tsc_at_measure_end; static unsigned long long *mperf_previous_count; static unsigned long long *aperf_previous_count; static unsigned long long *mperf_current_count; @@ -169,7 +169,7 @@ static int mperf_get_count_percent(unsigned int id, double *percent, aperf_diff = aperf_current_count[cpu] - aperf_previous_count[cpu]; if (max_freq_mode == MAX_FREQ_TSC_REF) { - tsc_diff = tsc_at_measure_end - tsc_at_measure_start; + tsc_diff = tsc_at_measure_end[cpu] - tsc_at_measure_start[cpu]; *percent = 100.0 * mperf_diff / tsc_diff; dprint("%s: TSC Ref - mperf_diff: %llu, tsc_diff: %llu\n", mperf_cstates[id].name, mperf_diff, tsc_diff); @@ -206,7 +206,7 @@ static int mperf_get_count_freq(unsigned int id, unsigned long long *count, if (max_freq_mode == MAX_FREQ_TSC_REF) { /* Calculate max_freq from TSC count */ - tsc_diff = tsc_at_measure_end - tsc_at_measure_start; + tsc_diff = tsc_at_measure_end[cpu] - tsc_at_measure_start[cpu]; time_diff = timespec_diff_us(time_start, time_end); max_frequency = tsc_diff / time_diff; } @@ -225,33 +225,27 @@ static int mperf_get_count_freq(unsigned int id, unsigned long long *count, static int mperf_start(void) { int cpu; - unsigned long long dbg; clock_gettime(CLOCK_REALTIME, &time_start); - mperf_get_tsc(&tsc_at_measure_start); - for (cpu = 0; cpu < cpu_count; cpu++) + for (cpu = 0; cpu < cpu_count; cpu++) { + mperf_get_tsc(&tsc_at_measure_start[cpu]); mperf_init_stats(cpu); + } - mperf_get_tsc(&dbg); - dprint("TSC diff: %llu\n", dbg - tsc_at_measure_start); return 0; } static int mperf_stop(void) { - unsigned long long dbg; int cpu; - for (cpu = 0; cpu < cpu_count; cpu++) + for (cpu = 0; cpu < cpu_count; cpu++) { mperf_measure_stats(cpu); + mperf_get_tsc(&tsc_at_measure_end[cpu]); + } - mperf_get_tsc(&tsc_at_measure_end); clock_gettime(CLOCK_REALTIME, &time_end); - - mperf_get_tsc(&dbg); - dprint("TSC diff: %llu\n", dbg - tsc_at_measure_end); - return 0; } @@ -353,7 +347,8 @@ struct cpuidle_monitor *mperf_register(void) aperf_previous_count = calloc(cpu_count, sizeof(unsigned long long)); mperf_current_count = calloc(cpu_count, sizeof(unsigned long long)); aperf_current_count = calloc(cpu_count, sizeof(unsigned long long)); - + tsc_at_measure_start = calloc(cpu_count, sizeof(unsigned long long)); + tsc_at_measure_end = calloc(cpu_count, sizeof(unsigned long long)); mperf_monitor.name_len = strlen(mperf_monitor.name); return &mperf_monitor; } @@ -364,6 +359,8 @@ void mperf_unregister(void) free(aperf_previous_count); free(mperf_current_count); free(aperf_current_count); + free(tsc_at_measure_start); + free(tsc_at_measure_end); free(is_valid); } diff --git a/tools/testing/cxl/Kbuild b/tools/testing/cxl/Kbuild index fba7bec96acd..6f9347ade82c 100644 --- a/tools/testing/cxl/Kbuild +++ b/tools/testing/cxl/Kbuild @@ -6,6 +6,7 @@ ldflags-y += --wrap=acpi_pci_find_root ldflags-y += --wrap=nvdimm_bus_register ldflags-y += --wrap=devm_cxl_port_enumerate_dports ldflags-y += --wrap=devm_cxl_setup_hdm +ldflags-y += --wrap=devm_cxl_enable_hdm ldflags-y += --wrap=devm_cxl_add_passthrough_decoder ldflags-y += --wrap=devm_cxl_enumerate_decoders ldflags-y += --wrap=cxl_await_media_ready diff --git a/tools/testing/cxl/test/mem.c b/tools/testing/cxl/test/mem.c index ba572d03c687..34b48027b3de 100644 --- a/tools/testing/cxl/test/mem.c +++ b/tools/testing/cxl/test/mem.c @@ -1256,6 +1256,7 @@ static int cxl_mock_mem_probe(struct platform_device *pdev) if (rc) return rc; + cxlds->media_ready = true; rc = cxl_dev_state_identify(cxlds); if (rc) return rc; diff --git a/tools/testing/cxl/test/mock.c b/tools/testing/cxl/test/mock.c index de3933a776fd..284416527644 100644 --- a/tools/testing/cxl/test/mock.c +++ b/tools/testing/cxl/test/mock.c @@ -149,6 +149,21 @@ struct cxl_hdm *__wrap_devm_cxl_setup_hdm(struct cxl_port *port, } EXPORT_SYMBOL_NS_GPL(__wrap_devm_cxl_setup_hdm, CXL); +int __wrap_devm_cxl_enable_hdm(struct cxl_port *port, struct cxl_hdm *cxlhdm) +{ + int index, rc; + struct cxl_mock_ops *ops = get_cxl_mock_ops(&index); + + if (ops && ops->is_mock_port(port->uport)) + rc = 0; + else + rc = devm_cxl_enable_hdm(port, cxlhdm); + put_cxl_mock_ops(index); + + return rc; +} +EXPORT_SYMBOL_NS_GPL(__wrap_devm_cxl_enable_hdm, CXL); + int __wrap_devm_cxl_add_passthrough_decoder(struct cxl_port *port) { int rc, index; diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index c49e5403ad0e..28d2c77262be 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -197,7 +197,7 @@ $(OUTPUT)/urandom_read: urandom_read.c urandom_read_aux.c $(OUTPUT)/liburandom_r $(OUTPUT)/sign-file: ../../../../scripts/sign-file.c $(call msg,SIGN-FILE,,$@) - $(Q)$(CC) $(shell $(HOSTPKG_CONFIG)--cflags libcrypto 2> /dev/null) \ + $(Q)$(CC) $(shell $(HOSTPKG_CONFIG) --cflags libcrypto 2> /dev/null) \ $< -o $@ \ $(shell $(HOSTPKG_CONFIG) --libs libcrypto 2> /dev/null || echo -lcrypto) diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c index 0ce25a967481..064cc5e8d9ad 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c @@ -2,6 +2,7 @@ // Copyright (c) 2020 Cloudflare #include <error.h> #include <netinet/tcp.h> +#include <sys/epoll.h> #include "test_progs.h" #include "test_skmsg_load_helpers.skel.h" @@ -9,8 +10,12 @@ #include "test_sockmap_invalid_update.skel.h" #include "test_sockmap_skb_verdict_attach.skel.h" #include "test_sockmap_progs_query.skel.h" +#include "test_sockmap_pass_prog.skel.h" +#include "test_sockmap_drop_prog.skel.h" #include "bpf_iter_sockmap.skel.h" +#include "sockmap_helpers.h" + #define TCP_REPAIR 19 /* TCP sock is under repair right now */ #define TCP_REPAIR_ON 1 @@ -350,6 +355,126 @@ out: test_sockmap_progs_query__destroy(skel); } +#define MAX_EVENTS 10 +static void test_sockmap_skb_verdict_shutdown(void) +{ + struct epoll_event ev, events[MAX_EVENTS]; + int n, err, map, verdict, s, c1, p1; + struct test_sockmap_pass_prog *skel; + int epollfd; + int zero = 0; + char b; + + skel = test_sockmap_pass_prog__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open_and_load")) + return; + + verdict = bpf_program__fd(skel->progs.prog_skb_verdict); + map = bpf_map__fd(skel->maps.sock_map_rx); + + err = bpf_prog_attach(verdict, map, BPF_SK_SKB_STREAM_VERDICT, 0); + if (!ASSERT_OK(err, "bpf_prog_attach")) + goto out; + + s = socket_loopback(AF_INET, SOCK_STREAM); + if (s < 0) + goto out; + err = create_pair(s, AF_INET, SOCK_STREAM, &c1, &p1); + if (err < 0) + goto out; + + err = bpf_map_update_elem(map, &zero, &c1, BPF_NOEXIST); + if (err < 0) + goto out_close; + + shutdown(p1, SHUT_WR); + + ev.events = EPOLLIN; + ev.data.fd = c1; + + epollfd = epoll_create1(0); + if (!ASSERT_GT(epollfd, -1, "epoll_create(0)")) + goto out_close; + err = epoll_ctl(epollfd, EPOLL_CTL_ADD, c1, &ev); + if (!ASSERT_OK(err, "epoll_ctl(EPOLL_CTL_ADD)")) + goto out_close; + err = epoll_wait(epollfd, events, MAX_EVENTS, -1); + if (!ASSERT_EQ(err, 1, "epoll_wait(fd)")) + goto out_close; + + n = recv(c1, &b, 1, SOCK_NONBLOCK); + ASSERT_EQ(n, 0, "recv_timeout(fin)"); +out_close: + close(c1); + close(p1); +out: + test_sockmap_pass_prog__destroy(skel); +} + +static void test_sockmap_skb_verdict_fionread(bool pass_prog) +{ + int expected, zero = 0, sent, recvd, avail; + int err, map, verdict, s, c0, c1, p0, p1; + struct test_sockmap_pass_prog *pass; + struct test_sockmap_drop_prog *drop; + char buf[256] = "0123456789"; + + if (pass_prog) { + pass = test_sockmap_pass_prog__open_and_load(); + if (!ASSERT_OK_PTR(pass, "open_and_load")) + return; + verdict = bpf_program__fd(pass->progs.prog_skb_verdict); + map = bpf_map__fd(pass->maps.sock_map_rx); + expected = sizeof(buf); + } else { + drop = test_sockmap_drop_prog__open_and_load(); + if (!ASSERT_OK_PTR(drop, "open_and_load")) + return; + verdict = bpf_program__fd(drop->progs.prog_skb_verdict); + map = bpf_map__fd(drop->maps.sock_map_rx); + /* On drop data is consumed immediately and copied_seq inc'd */ + expected = 0; + } + + + err = bpf_prog_attach(verdict, map, BPF_SK_SKB_STREAM_VERDICT, 0); + if (!ASSERT_OK(err, "bpf_prog_attach")) + goto out; + + s = socket_loopback(AF_INET, SOCK_STREAM); + if (!ASSERT_GT(s, -1, "socket_loopback(s)")) + goto out; + err = create_socket_pairs(s, AF_INET, SOCK_STREAM, &c0, &c1, &p0, &p1); + if (!ASSERT_OK(err, "create_socket_pairs(s)")) + goto out; + + err = bpf_map_update_elem(map, &zero, &c1, BPF_NOEXIST); + if (!ASSERT_OK(err, "bpf_map_update_elem(c1)")) + goto out_close; + + sent = xsend(p1, &buf, sizeof(buf), 0); + ASSERT_EQ(sent, sizeof(buf), "xsend(p0)"); + err = ioctl(c1, FIONREAD, &avail); + ASSERT_OK(err, "ioctl(FIONREAD) error"); + ASSERT_EQ(avail, expected, "ioctl(FIONREAD)"); + /* On DROP test there will be no data to read */ + if (pass_prog) { + recvd = recv_timeout(c1, &buf, sizeof(buf), SOCK_NONBLOCK, IO_TIMEOUT_SEC); + ASSERT_EQ(recvd, sizeof(buf), "recv_timeout(c0)"); + } + +out_close: + close(c0); + close(p0); + close(c1); + close(p1); +out: + if (pass_prog) + test_sockmap_pass_prog__destroy(pass); + else + test_sockmap_drop_prog__destroy(drop); +} + void test_sockmap_basic(void) { if (test__start_subtest("sockmap create_update_free")) @@ -384,4 +509,10 @@ void test_sockmap_basic(void) test_sockmap_progs_query(BPF_SK_SKB_STREAM_VERDICT); if (test__start_subtest("sockmap skb_verdict progs query")) test_sockmap_progs_query(BPF_SK_SKB_VERDICT); + if (test__start_subtest("sockmap skb_verdict shutdown")) + test_sockmap_skb_verdict_shutdown(); + if (test__start_subtest("sockmap skb_verdict fionread")) + test_sockmap_skb_verdict_fionread(true); + if (test__start_subtest("sockmap skb_verdict fionread on drop")) + test_sockmap_skb_verdict_fionread(false); } diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h b/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h new file mode 100644 index 000000000000..d12665490a90 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h @@ -0,0 +1,390 @@ +#ifndef __SOCKMAP_HELPERS__ +#define __SOCKMAP_HELPERS__ + +#include <linux/vm_sockets.h> + +#define IO_TIMEOUT_SEC 30 +#define MAX_STRERR_LEN 256 +#define MAX_TEST_NAME 80 + +/* workaround for older vm_sockets.h */ +#ifndef VMADDR_CID_LOCAL +#define VMADDR_CID_LOCAL 1 +#endif + +#define __always_unused __attribute__((__unused__)) + +#define _FAIL(errnum, fmt...) \ + ({ \ + error_at_line(0, (errnum), __func__, __LINE__, fmt); \ + CHECK_FAIL(true); \ + }) +#define FAIL(fmt...) _FAIL(0, fmt) +#define FAIL_ERRNO(fmt...) _FAIL(errno, fmt) +#define FAIL_LIBBPF(err, msg) \ + ({ \ + char __buf[MAX_STRERR_LEN]; \ + libbpf_strerror((err), __buf, sizeof(__buf)); \ + FAIL("%s: %s", (msg), __buf); \ + }) + +/* Wrappers that fail the test on error and report it. */ + +#define xaccept_nonblock(fd, addr, len) \ + ({ \ + int __ret = \ + accept_timeout((fd), (addr), (len), IO_TIMEOUT_SEC); \ + if (__ret == -1) \ + FAIL_ERRNO("accept"); \ + __ret; \ + }) + +#define xbind(fd, addr, len) \ + ({ \ + int __ret = bind((fd), (addr), (len)); \ + if (__ret == -1) \ + FAIL_ERRNO("bind"); \ + __ret; \ + }) + +#define xclose(fd) \ + ({ \ + int __ret = close((fd)); \ + if (__ret == -1) \ + FAIL_ERRNO("close"); \ + __ret; \ + }) + +#define xconnect(fd, addr, len) \ + ({ \ + int __ret = connect((fd), (addr), (len)); \ + if (__ret == -1) \ + FAIL_ERRNO("connect"); \ + __ret; \ + }) + +#define xgetsockname(fd, addr, len) \ + ({ \ + int __ret = getsockname((fd), (addr), (len)); \ + if (__ret == -1) \ + FAIL_ERRNO("getsockname"); \ + __ret; \ + }) + +#define xgetsockopt(fd, level, name, val, len) \ + ({ \ + int __ret = getsockopt((fd), (level), (name), (val), (len)); \ + if (__ret == -1) \ + FAIL_ERRNO("getsockopt(" #name ")"); \ + __ret; \ + }) + +#define xlisten(fd, backlog) \ + ({ \ + int __ret = listen((fd), (backlog)); \ + if (__ret == -1) \ + FAIL_ERRNO("listen"); \ + __ret; \ + }) + +#define xsetsockopt(fd, level, name, val, len) \ + ({ \ + int __ret = setsockopt((fd), (level), (name), (val), (len)); \ + if (__ret == -1) \ + FAIL_ERRNO("setsockopt(" #name ")"); \ + __ret; \ + }) + +#define xsend(fd, buf, len, flags) \ + ({ \ + ssize_t __ret = send((fd), (buf), (len), (flags)); \ + if (__ret == -1) \ + FAIL_ERRNO("send"); \ + __ret; \ + }) + +#define xrecv_nonblock(fd, buf, len, flags) \ + ({ \ + ssize_t __ret = recv_timeout((fd), (buf), (len), (flags), \ + IO_TIMEOUT_SEC); \ + if (__ret == -1) \ + FAIL_ERRNO("recv"); \ + __ret; \ + }) + +#define xsocket(family, sotype, flags) \ + ({ \ + int __ret = socket(family, sotype, flags); \ + if (__ret == -1) \ + FAIL_ERRNO("socket"); \ + __ret; \ + }) + +#define xbpf_map_delete_elem(fd, key) \ + ({ \ + int __ret = bpf_map_delete_elem((fd), (key)); \ + if (__ret < 0) \ + FAIL_ERRNO("map_delete"); \ + __ret; \ + }) + +#define xbpf_map_lookup_elem(fd, key, val) \ + ({ \ + int __ret = bpf_map_lookup_elem((fd), (key), (val)); \ + if (__ret < 0) \ + FAIL_ERRNO("map_lookup"); \ + __ret; \ + }) + +#define xbpf_map_update_elem(fd, key, val, flags) \ + ({ \ + int __ret = bpf_map_update_elem((fd), (key), (val), (flags)); \ + if (__ret < 0) \ + FAIL_ERRNO("map_update"); \ + __ret; \ + }) + +#define xbpf_prog_attach(prog, target, type, flags) \ + ({ \ + int __ret = \ + bpf_prog_attach((prog), (target), (type), (flags)); \ + if (__ret < 0) \ + FAIL_ERRNO("prog_attach(" #type ")"); \ + __ret; \ + }) + +#define xbpf_prog_detach2(prog, target, type) \ + ({ \ + int __ret = bpf_prog_detach2((prog), (target), (type)); \ + if (__ret < 0) \ + FAIL_ERRNO("prog_detach2(" #type ")"); \ + __ret; \ + }) + +#define xpthread_create(thread, attr, func, arg) \ + ({ \ + int __ret = pthread_create((thread), (attr), (func), (arg)); \ + errno = __ret; \ + if (__ret) \ + FAIL_ERRNO("pthread_create"); \ + __ret; \ + }) + +#define xpthread_join(thread, retval) \ + ({ \ + int __ret = pthread_join((thread), (retval)); \ + errno = __ret; \ + if (__ret) \ + FAIL_ERRNO("pthread_join"); \ + __ret; \ + }) + +static inline int poll_read(int fd, unsigned int timeout_sec) +{ + struct timeval timeout = { .tv_sec = timeout_sec }; + fd_set rfds; + int r; + + FD_ZERO(&rfds); + FD_SET(fd, &rfds); + + r = select(fd + 1, &rfds, NULL, NULL, &timeout); + if (r == 0) + errno = ETIME; + + return r == 1 ? 0 : -1; +} + +static inline int accept_timeout(int fd, struct sockaddr *addr, socklen_t *len, + unsigned int timeout_sec) +{ + if (poll_read(fd, timeout_sec)) + return -1; + + return accept(fd, addr, len); +} + +static inline int recv_timeout(int fd, void *buf, size_t len, int flags, + unsigned int timeout_sec) +{ + if (poll_read(fd, timeout_sec)) + return -1; + + return recv(fd, buf, len, flags); +} + +static inline void init_addr_loopback4(struct sockaddr_storage *ss, + socklen_t *len) +{ + struct sockaddr_in *addr4 = memset(ss, 0, sizeof(*ss)); + + addr4->sin_family = AF_INET; + addr4->sin_port = 0; + addr4->sin_addr.s_addr = htonl(INADDR_LOOPBACK); + *len = sizeof(*addr4); +} + +static inline void init_addr_loopback6(struct sockaddr_storage *ss, + socklen_t *len) +{ + struct sockaddr_in6 *addr6 = memset(ss, 0, sizeof(*ss)); + + addr6->sin6_family = AF_INET6; + addr6->sin6_port = 0; + addr6->sin6_addr = in6addr_loopback; + *len = sizeof(*addr6); +} + +static inline void init_addr_loopback_vsock(struct sockaddr_storage *ss, + socklen_t *len) +{ + struct sockaddr_vm *addr = memset(ss, 0, sizeof(*ss)); + + addr->svm_family = AF_VSOCK; + addr->svm_port = VMADDR_PORT_ANY; + addr->svm_cid = VMADDR_CID_LOCAL; + *len = sizeof(*addr); +} + +static inline void init_addr_loopback(int family, struct sockaddr_storage *ss, + socklen_t *len) +{ + switch (family) { + case AF_INET: + init_addr_loopback4(ss, len); + return; + case AF_INET6: + init_addr_loopback6(ss, len); + return; + case AF_VSOCK: + init_addr_loopback_vsock(ss, len); + return; + default: + FAIL("unsupported address family %d", family); + } +} + +static inline struct sockaddr *sockaddr(struct sockaddr_storage *ss) +{ + return (struct sockaddr *)ss; +} + +static inline int add_to_sockmap(int sock_mapfd, int fd1, int fd2) +{ + u64 value; + u32 key; + int err; + + key = 0; + value = fd1; + err = xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST); + if (err) + return err; + + key = 1; + value = fd2; + return xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST); +} + +static inline int create_pair(int s, int family, int sotype, int *c, int *p) +{ + struct sockaddr_storage addr; + socklen_t len; + int err = 0; + + len = sizeof(addr); + err = xgetsockname(s, sockaddr(&addr), &len); + if (err) + return err; + + *c = xsocket(family, sotype, 0); + if (*c < 0) + return errno; + err = xconnect(*c, sockaddr(&addr), len); + if (err) { + err = errno; + goto close_cli0; + } + + *p = xaccept_nonblock(s, NULL, NULL); + if (*p < 0) { + err = errno; + goto close_cli0; + } + return err; +close_cli0: + close(*c); + return err; +} + +static inline int create_socket_pairs(int s, int family, int sotype, + int *c0, int *c1, int *p0, int *p1) +{ + int err; + + err = create_pair(s, family, sotype, c0, p0); + if (err) + return err; + + err = create_pair(s, family, sotype, c1, p1); + if (err) { + close(*c0); + close(*p0); + } + return err; +} + +static inline int enable_reuseport(int s, int progfd) +{ + int err, one = 1; + + err = xsetsockopt(s, SOL_SOCKET, SO_REUSEPORT, &one, sizeof(one)); + if (err) + return -1; + err = xsetsockopt(s, SOL_SOCKET, SO_ATTACH_REUSEPORT_EBPF, &progfd, + sizeof(progfd)); + if (err) + return -1; + + return 0; +} + +static inline int socket_loopback_reuseport(int family, int sotype, int progfd) +{ + struct sockaddr_storage addr; + socklen_t len; + int err, s; + + init_addr_loopback(family, &addr, &len); + + s = xsocket(family, sotype, 0); + if (s == -1) + return -1; + + if (progfd >= 0) + enable_reuseport(s, progfd); + + err = xbind(s, sockaddr(&addr), len); + if (err) + goto close; + + if (sotype & SOCK_DGRAM) + return s; + + err = xlisten(s, SOMAXCONN); + if (err) + goto close; + + return s; +close: + xclose(s); + return -1; +} + +static inline int socket_loopback(int family, int sotype) +{ + return socket_loopback_reuseport(family, sotype, -1); +} + + +#endif // __SOCKMAP_HELPERS__ diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c index 141c1e5944ee..b4f6f3a50ae5 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c @@ -20,11 +20,6 @@ #include <unistd.h> #include <linux/vm_sockets.h> -/* workaround for older vm_sockets.h */ -#ifndef VMADDR_CID_LOCAL -#define VMADDR_CID_LOCAL 1 -#endif - #include <bpf/bpf.h> #include <bpf/libbpf.h> @@ -32,315 +27,7 @@ #include "test_progs.h" #include "test_sockmap_listen.skel.h" -#define IO_TIMEOUT_SEC 30 -#define MAX_STRERR_LEN 256 -#define MAX_TEST_NAME 80 - -#define __always_unused __attribute__((__unused__)) - -#define _FAIL(errnum, fmt...) \ - ({ \ - error_at_line(0, (errnum), __func__, __LINE__, fmt); \ - CHECK_FAIL(true); \ - }) -#define FAIL(fmt...) _FAIL(0, fmt) -#define FAIL_ERRNO(fmt...) _FAIL(errno, fmt) -#define FAIL_LIBBPF(err, msg) \ - ({ \ - char __buf[MAX_STRERR_LEN]; \ - libbpf_strerror((err), __buf, sizeof(__buf)); \ - FAIL("%s: %s", (msg), __buf); \ - }) - -/* Wrappers that fail the test on error and report it. */ - -#define xaccept_nonblock(fd, addr, len) \ - ({ \ - int __ret = \ - accept_timeout((fd), (addr), (len), IO_TIMEOUT_SEC); \ - if (__ret == -1) \ - FAIL_ERRNO("accept"); \ - __ret; \ - }) - -#define xbind(fd, addr, len) \ - ({ \ - int __ret = bind((fd), (addr), (len)); \ - if (__ret == -1) \ - FAIL_ERRNO("bind"); \ - __ret; \ - }) - -#define xclose(fd) \ - ({ \ - int __ret = close((fd)); \ - if (__ret == -1) \ - FAIL_ERRNO("close"); \ - __ret; \ - }) - -#define xconnect(fd, addr, len) \ - ({ \ - int __ret = connect((fd), (addr), (len)); \ - if (__ret == -1) \ - FAIL_ERRNO("connect"); \ - __ret; \ - }) - -#define xgetsockname(fd, addr, len) \ - ({ \ - int __ret = getsockname((fd), (addr), (len)); \ - if (__ret == -1) \ - FAIL_ERRNO("getsockname"); \ - __ret; \ - }) - -#define xgetsockopt(fd, level, name, val, len) \ - ({ \ - int __ret = getsockopt((fd), (level), (name), (val), (len)); \ - if (__ret == -1) \ - FAIL_ERRNO("getsockopt(" #name ")"); \ - __ret; \ - }) - -#define xlisten(fd, backlog) \ - ({ \ - int __ret = listen((fd), (backlog)); \ - if (__ret == -1) \ - FAIL_ERRNO("listen"); \ - __ret; \ - }) - -#define xsetsockopt(fd, level, name, val, len) \ - ({ \ - int __ret = setsockopt((fd), (level), (name), (val), (len)); \ - if (__ret == -1) \ - FAIL_ERRNO("setsockopt(" #name ")"); \ - __ret; \ - }) - -#define xsend(fd, buf, len, flags) \ - ({ \ - ssize_t __ret = send((fd), (buf), (len), (flags)); \ - if (__ret == -1) \ - FAIL_ERRNO("send"); \ - __ret; \ - }) - -#define xrecv_nonblock(fd, buf, len, flags) \ - ({ \ - ssize_t __ret = recv_timeout((fd), (buf), (len), (flags), \ - IO_TIMEOUT_SEC); \ - if (__ret == -1) \ - FAIL_ERRNO("recv"); \ - __ret; \ - }) - -#define xsocket(family, sotype, flags) \ - ({ \ - int __ret = socket(family, sotype, flags); \ - if (__ret == -1) \ - FAIL_ERRNO("socket"); \ - __ret; \ - }) - -#define xbpf_map_delete_elem(fd, key) \ - ({ \ - int __ret = bpf_map_delete_elem((fd), (key)); \ - if (__ret < 0) \ - FAIL_ERRNO("map_delete"); \ - __ret; \ - }) - -#define xbpf_map_lookup_elem(fd, key, val) \ - ({ \ - int __ret = bpf_map_lookup_elem((fd), (key), (val)); \ - if (__ret < 0) \ - FAIL_ERRNO("map_lookup"); \ - __ret; \ - }) - -#define xbpf_map_update_elem(fd, key, val, flags) \ - ({ \ - int __ret = bpf_map_update_elem((fd), (key), (val), (flags)); \ - if (__ret < 0) \ - FAIL_ERRNO("map_update"); \ - __ret; \ - }) - -#define xbpf_prog_attach(prog, target, type, flags) \ - ({ \ - int __ret = \ - bpf_prog_attach((prog), (target), (type), (flags)); \ - if (__ret < 0) \ - FAIL_ERRNO("prog_attach(" #type ")"); \ - __ret; \ - }) - -#define xbpf_prog_detach2(prog, target, type) \ - ({ \ - int __ret = bpf_prog_detach2((prog), (target), (type)); \ - if (__ret < 0) \ - FAIL_ERRNO("prog_detach2(" #type ")"); \ - __ret; \ - }) - -#define xpthread_create(thread, attr, func, arg) \ - ({ \ - int __ret = pthread_create((thread), (attr), (func), (arg)); \ - errno = __ret; \ - if (__ret) \ - FAIL_ERRNO("pthread_create"); \ - __ret; \ - }) - -#define xpthread_join(thread, retval) \ - ({ \ - int __ret = pthread_join((thread), (retval)); \ - errno = __ret; \ - if (__ret) \ - FAIL_ERRNO("pthread_join"); \ - __ret; \ - }) - -static int poll_read(int fd, unsigned int timeout_sec) -{ - struct timeval timeout = { .tv_sec = timeout_sec }; - fd_set rfds; - int r; - - FD_ZERO(&rfds); - FD_SET(fd, &rfds); - - r = select(fd + 1, &rfds, NULL, NULL, &timeout); - if (r == 0) - errno = ETIME; - - return r == 1 ? 0 : -1; -} - -static int accept_timeout(int fd, struct sockaddr *addr, socklen_t *len, - unsigned int timeout_sec) -{ - if (poll_read(fd, timeout_sec)) - return -1; - - return accept(fd, addr, len); -} - -static int recv_timeout(int fd, void *buf, size_t len, int flags, - unsigned int timeout_sec) -{ - if (poll_read(fd, timeout_sec)) - return -1; - - return recv(fd, buf, len, flags); -} - -static void init_addr_loopback4(struct sockaddr_storage *ss, socklen_t *len) -{ - struct sockaddr_in *addr4 = memset(ss, 0, sizeof(*ss)); - - addr4->sin_family = AF_INET; - addr4->sin_port = 0; - addr4->sin_addr.s_addr = htonl(INADDR_LOOPBACK); - *len = sizeof(*addr4); -} - -static void init_addr_loopback6(struct sockaddr_storage *ss, socklen_t *len) -{ - struct sockaddr_in6 *addr6 = memset(ss, 0, sizeof(*ss)); - - addr6->sin6_family = AF_INET6; - addr6->sin6_port = 0; - addr6->sin6_addr = in6addr_loopback; - *len = sizeof(*addr6); -} - -static void init_addr_loopback_vsock(struct sockaddr_storage *ss, socklen_t *len) -{ - struct sockaddr_vm *addr = memset(ss, 0, sizeof(*ss)); - - addr->svm_family = AF_VSOCK; - addr->svm_port = VMADDR_PORT_ANY; - addr->svm_cid = VMADDR_CID_LOCAL; - *len = sizeof(*addr); -} - -static void init_addr_loopback(int family, struct sockaddr_storage *ss, - socklen_t *len) -{ - switch (family) { - case AF_INET: - init_addr_loopback4(ss, len); - return; - case AF_INET6: - init_addr_loopback6(ss, len); - return; - case AF_VSOCK: - init_addr_loopback_vsock(ss, len); - return; - default: - FAIL("unsupported address family %d", family); - } -} - -static inline struct sockaddr *sockaddr(struct sockaddr_storage *ss) -{ - return (struct sockaddr *)ss; -} - -static int enable_reuseport(int s, int progfd) -{ - int err, one = 1; - - err = xsetsockopt(s, SOL_SOCKET, SO_REUSEPORT, &one, sizeof(one)); - if (err) - return -1; - err = xsetsockopt(s, SOL_SOCKET, SO_ATTACH_REUSEPORT_EBPF, &progfd, - sizeof(progfd)); - if (err) - return -1; - - return 0; -} - -static int socket_loopback_reuseport(int family, int sotype, int progfd) -{ - struct sockaddr_storage addr; - socklen_t len; - int err, s; - - init_addr_loopback(family, &addr, &len); - - s = xsocket(family, sotype, 0); - if (s == -1) - return -1; - - if (progfd >= 0) - enable_reuseport(s, progfd); - - err = xbind(s, sockaddr(&addr), len); - if (err) - goto close; - - if (sotype & SOCK_DGRAM) - return s; - - err = xlisten(s, SOMAXCONN); - if (err) - goto close; - - return s; -close: - xclose(s); - return -1; -} - -static int socket_loopback(int family, int sotype) -{ - return socket_loopback_reuseport(family, sotype, -1); -} +#include "sockmap_helpers.h" static void test_insert_invalid(struct test_sockmap_listen *skel __always_unused, int family, int sotype, int mapfd) @@ -984,31 +671,12 @@ static const char *redir_mode_str(enum redir_mode mode) } } -static int add_to_sockmap(int sock_mapfd, int fd1, int fd2) -{ - u64 value; - u32 key; - int err; - - key = 0; - value = fd1; - err = xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST); - if (err) - return err; - - key = 1; - value = fd2; - return xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST); -} - static void redir_to_connected(int family, int sotype, int sock_mapfd, int verd_mapfd, enum redir_mode mode) { const char *log_prefix = redir_mode_str(mode); - struct sockaddr_storage addr; int s, c0, c1, p0, p1; unsigned int pass; - socklen_t len; int err, n; u32 key; char b; @@ -1019,36 +687,13 @@ static void redir_to_connected(int family, int sotype, int sock_mapfd, if (s < 0) return; - len = sizeof(addr); - err = xgetsockname(s, sockaddr(&addr), &len); + err = create_socket_pairs(s, family, sotype, &c0, &c1, &p0, &p1); if (err) goto close_srv; - c0 = xsocket(family, sotype, 0); - if (c0 < 0) - goto close_srv; - err = xconnect(c0, sockaddr(&addr), len); - if (err) - goto close_cli0; - - p0 = xaccept_nonblock(s, NULL, NULL); - if (p0 < 0) - goto close_cli0; - - c1 = xsocket(family, sotype, 0); - if (c1 < 0) - goto close_peer0; - err = xconnect(c1, sockaddr(&addr), len); - if (err) - goto close_cli1; - - p1 = xaccept_nonblock(s, NULL, NULL); - if (p1 < 0) - goto close_cli1; - err = add_to_sockmap(sock_mapfd, p0, p1); if (err) - goto close_peer1; + goto close; n = write(mode == REDIR_INGRESS ? c1 : p1, "a", 1); if (n < 0) @@ -1056,12 +701,12 @@ static void redir_to_connected(int family, int sotype, int sock_mapfd, if (n == 0) FAIL("%s: incomplete write", log_prefix); if (n < 1) - goto close_peer1; + goto close; key = SK_PASS; err = xbpf_map_lookup_elem(verd_mapfd, &key, &pass); if (err) - goto close_peer1; + goto close; if (pass != 1) FAIL("%s: want pass count 1, have %d", log_prefix, pass); n = recv_timeout(c0, &b, 1, 0, IO_TIMEOUT_SEC); @@ -1070,13 +715,10 @@ static void redir_to_connected(int family, int sotype, int sock_mapfd, if (n == 0) FAIL("%s: incomplete recv", log_prefix); -close_peer1: +close: xclose(p1); -close_cli1: xclose(c1); -close_peer0: xclose(p0); -close_cli0: xclose(c0); close_srv: xclose(s); diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_drop_prog.c b/tools/testing/selftests/bpf/progs/test_sockmap_drop_prog.c new file mode 100644 index 000000000000..29314805ce42 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sockmap_drop_prog.c @@ -0,0 +1,32 @@ +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 20); + __type(key, int); + __type(value, int); +} sock_map_rx SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 20); + __type(key, int); + __type(value, int); +} sock_map_tx SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 20); + __type(key, int); + __type(value, int); +} sock_map_msg SEC(".maps"); + +SEC("sk_skb") +int prog_skb_verdict(struct __sk_buff *skb) +{ + return SK_DROP; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_kern.h b/tools/testing/selftests/bpf/progs/test_sockmap_kern.h index baf9ebc6d903..99d2ea9fb658 100644 --- a/tools/testing/selftests/bpf/progs/test_sockmap_kern.h +++ b/tools/testing/selftests/bpf/progs/test_sockmap_kern.h @@ -191,7 +191,7 @@ SEC("sockops") int bpf_sockmap(struct bpf_sock_ops *skops) { __u32 lport, rport; - int op, err, ret; + int op, ret; op = (int) skops->op; @@ -203,10 +203,10 @@ int bpf_sockmap(struct bpf_sock_ops *skops) if (lport == 10000) { ret = 1; #ifdef SOCKMAP - err = bpf_sock_map_update(skops, &sock_map, &ret, + bpf_sock_map_update(skops, &sock_map, &ret, BPF_NOEXIST); #else - err = bpf_sock_hash_update(skops, &sock_map, &ret, + bpf_sock_hash_update(skops, &sock_map, &ret, BPF_NOEXIST); #endif } @@ -218,10 +218,10 @@ int bpf_sockmap(struct bpf_sock_ops *skops) if (bpf_ntohl(rport) == 10001) { ret = 10; #ifdef SOCKMAP - err = bpf_sock_map_update(skops, &sock_map, &ret, + bpf_sock_map_update(skops, &sock_map, &ret, BPF_NOEXIST); #else - err = bpf_sock_hash_update(skops, &sock_map, &ret, + bpf_sock_hash_update(skops, &sock_map, &ret, BPF_NOEXIST); #endif } @@ -230,8 +230,6 @@ int bpf_sockmap(struct bpf_sock_ops *skops) break; } - __sink(err); - return 0; } diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_pass_prog.c b/tools/testing/selftests/bpf/progs/test_sockmap_pass_prog.c new file mode 100644 index 000000000000..1d86a717a290 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sockmap_pass_prog.c @@ -0,0 +1,32 @@ +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 20); + __type(key, int); + __type(value, int); +} sock_map_rx SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 20); + __type(key, int); + __type(value, int); +} sock_map_tx SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 20); + __type(key, int); + __type(value, int); +} sock_map_msg SEC(".maps"); + +SEC("sk_skb") +int prog_skb_verdict(struct __sk_buff *skb) +{ + return SK_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-stack-legacy.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-stack-legacy.tc new file mode 100644 index 000000000000..d0cd91a93069 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-stack-legacy.tc @@ -0,0 +1,24 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# description: event trigger - test inter-event histogram trigger trace action with dynamic string param (legacy stack) +# requires: set_event synthetic_events events/sched/sched_process_exec/hist "long[] stack' >> synthetic_events":README + +fail() { #msg + echo $1 + exit_fail +} + +echo "Test create synthetic event with stack" + +# Test the old stacktrace keyword (for backward compatibility) +echo 's:wake_lat pid_t pid; u64 delta; unsigned long[] stack;' > dynamic_events +echo 'hist:keys=next_pid:ts=common_timestamp.usecs,st=stacktrace if prev_state == 1||prev_state == 2' >> events/sched/sched_switch/trigger +echo 'hist:keys=prev_pid:delta=common_timestamp.usecs-$ts,s=$st:onmax($delta).trace(wake_lat,prev_pid,$delta,$s)' >> events/sched/sched_switch/trigger +echo 1 > events/synthetic/wake_lat/enable +sleep 1 + +if ! grep -q "=>.*sched" trace; then + fail "Failed to create synthetic event with stack" +fi + +exit 0 diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-stack.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-stack.tc index 755dbe94ccf4..8f1cc9a86a06 100644 --- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-stack.tc +++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-stack.tc @@ -1,7 +1,7 @@ #!/bin/sh # SPDX-License-Identifier: GPL-2.0 # description: event trigger - test inter-event histogram trigger trace action with dynamic string param -# requires: set_event synthetic_events events/sched/sched_process_exec/hist "long[]' >> synthetic_events":README +# requires: set_event synthetic_events events/sched/sched_process_exec/hist "can be any field, or the special string 'common_stacktrace'":README fail() { #msg echo $1 @@ -10,9 +10,8 @@ fail() { #msg echo "Test create synthetic event with stack" - echo 's:wake_lat pid_t pid; u64 delta; unsigned long[] stack;' > dynamic_events -echo 'hist:keys=next_pid:ts=common_timestamp.usecs,st=stacktrace if prev_state == 1||prev_state == 2' >> events/sched/sched_switch/trigger +echo 'hist:keys=next_pid:ts=common_timestamp.usecs,st=common_stacktrace if prev_state == 1||prev_state == 2' >> events/sched/sched_switch/trigger echo 'hist:keys=prev_pid:delta=common_timestamp.usecs-$ts,s=$st:onmax($delta).trace(wake_lat,prev_pid,$delta,$s)' >> events/sched/sched_switch/trigger echo 1 > events/synthetic/wake_lat/enable sleep 1 diff --git a/tools/testing/selftests/gpio/gpio-sim.sh b/tools/testing/selftests/gpio/gpio-sim.sh index 9f539d454ee4..fa2ce2b9dd5f 100755 --- a/tools/testing/selftests/gpio/gpio-sim.sh +++ b/tools/testing/selftests/gpio/gpio-sim.sh @@ -389,6 +389,9 @@ create_chip chip create_bank chip bank set_num_lines chip bank 8 enable_chip chip +DEVNAME=`configfs_dev_name chip` +CHIPNAME=`configfs_chip_name chip bank` +SYSFS_PATH="/sys/devices/platform/$DEVNAME/$CHIPNAME/sim_gpio0/value" $BASE_DIR/gpio-mockup-cdev -b pull-up /dev/`configfs_chip_name chip bank` 0 test `cat $SYSFS_PATH` = "1" || fail "bias setting does not work" remove_chip chip diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index 80f06aa62034..f27a7338b60e 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -8,8 +8,10 @@ diag_uid fin_ack_lat gro hwtstamp_config +io_uring_zerocopy_tx ioam6_parser ip_defrag +ip_local_port_range ipsec ipv6_flowlabel ipv6_flowlabel_mgr @@ -26,6 +28,7 @@ reuseport_bpf_cpu reuseport_bpf_numa reuseport_dualstack rxtimestamp +sctp_hello sk_bind_sendto_listen sk_connect_zero_addr socket diff --git a/tools/testing/selftests/net/mptcp/Makefile b/tools/testing/selftests/net/mptcp/Makefile index 43a723626126..7b936a926859 100644 --- a/tools/testing/selftests/net/mptcp/Makefile +++ b/tools/testing/selftests/net/mptcp/Makefile @@ -9,7 +9,7 @@ TEST_PROGS := mptcp_connect.sh pm_netlink.sh mptcp_join.sh diag.sh \ TEST_GEN_FILES = mptcp_connect pm_nl_ctl mptcp_sockopt mptcp_inq -TEST_FILES := settings +TEST_FILES := mptcp_lib.sh settings EXTRA_CLEAN := *.pcap diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh index ef628b16fe9b..4eacdb1ab962 100755 --- a/tools/testing/selftests/net/mptcp/diag.sh +++ b/tools/testing/selftests/net/mptcp/diag.sh @@ -1,6 +1,8 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +. "$(dirname "${0}")/mptcp_lib.sh" + sec=$(date +%s) rndh=$(printf %x $sec)-$(mktemp -u XXXXXX) ns="ns1-$rndh" @@ -31,6 +33,8 @@ cleanup() ip netns del $ns } +mptcp_lib_check_mptcp + ip -Version > /dev/null 2>&1 if [ $? -ne 0 ];then echo "SKIP: Could not run test without ip tool" diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh index a43d3e2f59bb..c1f7bac19942 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh @@ -1,6 +1,8 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +. "$(dirname "${0}")/mptcp_lib.sh" + time_start=$(date +%s) optstring="S:R:d:e:l:r:h4cm:f:tC" @@ -141,6 +143,8 @@ cleanup() done } +mptcp_lib_check_mptcp + ip -Version > /dev/null 2>&1 if [ $? -ne 0 ];then echo "SKIP: Could not run test without ip tool" diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 26310c17b4c6..29f0c99d9a46 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -10,6 +10,8 @@ # because it's invoked by variable name, see how the "tests" array is used #shellcheck disable=SC2317 +. "$(dirname "${0}")/mptcp_lib.sh" + ret=0 sin="" sinfail="" @@ -17,6 +19,7 @@ sout="" cin="" cinfail="" cinsent="" +tmpfile="" cout="" capout="" ns1="" @@ -136,6 +139,8 @@ cleanup_partial() check_tools() { + mptcp_lib_check_mptcp + if ! ip -Version &> /dev/null; then echo "SKIP: Could not run test without ip tool" exit $ksft_skip @@ -175,6 +180,7 @@ cleanup() { rm -f "$cin" "$cout" "$sinfail" rm -f "$sin" "$sout" "$cinsent" "$cinfail" + rm -f "$tmpfile" rm -rf $evts_ns1 $evts_ns2 cleanup_partial } @@ -383,9 +389,16 @@ check_transfer() fail_test return 1 fi - bytes="--bytes=${bytes}" + + # note: BusyBox's "cmp" command doesn't support --bytes + tmpfile=$(mktemp) + head --bytes="$bytes" "$in" > "$tmpfile" + mv "$tmpfile" "$in" + head --bytes="$bytes" "$out" > "$tmpfile" + mv "$tmpfile" "$out" + tmpfile="" fi - cmp -l "$in" "$out" ${bytes} | while read -r i a b; do + cmp -l "$in" "$out" | while read -r i a b; do local sum=$((0${a} + 0${b})) if [ $check_invert -eq 0 ] || [ $sum -ne $((0xff)) ]; then echo "[ FAIL ] $what does not match (in, out):" @@ -849,7 +862,15 @@ do_transfer() sed -n 's/.*\(token:\)\([[:digit:]]*\).*$/\2/p;q') ip netns exec ${listener_ns} ./pm_nl_ctl ann $addr token $tk id $id sleep 1 + sp=$(grep "type:10" "$evts_ns1" | + sed -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q') + da=$(grep "type:10" "$evts_ns1" | + sed -n 's/.*\(daddr6:\)\([0-9a-f:.]*\).*$/\2/p;q') + dp=$(grep "type:10" "$evts_ns1" | + sed -n 's/.*\(dport:\)\([[:digit:]]*\).*$/\2/p;q') ip netns exec ${listener_ns} ./pm_nl_ctl rem token $tk id $id + ip netns exec ${listener_ns} ./pm_nl_ctl dsf lip "::ffff:$addr" \ + lport $sp rip $da rport $dp token $tk fi counter=$((counter + 1)) @@ -915,6 +936,7 @@ do_transfer() sleep 1 sp=$(grep "type:10" "$evts_ns2" | sed -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q') + ip netns exec ${connector_ns} ./pm_nl_ctl rem token $tk id $id ip netns exec ${connector_ns} ./pm_nl_ctl dsf lip $addr lport $sp \ rip $da rport $dp token $tk fi @@ -3129,7 +3151,7 @@ userspace_tests() pm_nl_set_limits $ns1 0 1 run_tests $ns1 $ns2 10.0.1.1 0 0 userspace_1 slow chk_join_nr 1 1 1 - chk_rm_nr 0 1 + chk_rm_nr 1 1 kill_events_pids fi } diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh new file mode 100644 index 000000000000..3286536b79d5 --- /dev/null +++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh @@ -0,0 +1,40 @@ +#! /bin/bash +# SPDX-License-Identifier: GPL-2.0 + +readonly KSFT_FAIL=1 +readonly KSFT_SKIP=4 + +# SELFTESTS_MPTCP_LIB_EXPECT_ALL_FEATURES env var can be set when validating all +# features using the last version of the kernel and the selftests to make sure +# a test is not being skipped by mistake. +mptcp_lib_expect_all_features() { + [ "${SELFTESTS_MPTCP_LIB_EXPECT_ALL_FEATURES:-}" = "1" ] +} + +# $1: msg +mptcp_lib_fail_if_expected_feature() { + if mptcp_lib_expect_all_features; then + echo "ERROR: missing feature: ${*}" + exit ${KSFT_FAIL} + fi + + return 1 +} + +# $1: file +mptcp_lib_has_file() { + local f="${1}" + + if [ -f "${f}" ]; then + return 0 + fi + + mptcp_lib_fail_if_expected_feature "${f} file not found" +} + +mptcp_lib_check_mptcp() { + if ! mptcp_lib_has_file "/proc/sys/net/mptcp/enabled"; then + echo "SKIP: MPTCP support is not available" + exit ${KSFT_SKIP} + fi +} diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh index 1b70c0a304ce..ff5adbb9c7f2 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh @@ -1,6 +1,8 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +. "$(dirname "${0}")/mptcp_lib.sh" + ret=0 sin="" sout="" @@ -84,6 +86,8 @@ cleanup() rm -f "$sin" "$sout" } +mptcp_lib_check_mptcp + ip -Version > /dev/null 2>&1 if [ $? -ne 0 ];then echo "SKIP: Could not run test without ip tool" diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh index 89839d1ff9d8..32f7533e0919 100755 --- a/tools/testing/selftests/net/mptcp/pm_netlink.sh +++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh @@ -1,6 +1,8 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +. "$(dirname "${0}")/mptcp_lib.sh" + ksft_skip=4 ret=0 @@ -34,6 +36,8 @@ cleanup() ip netns del $ns1 } +mptcp_lib_check_mptcp + ip -Version > /dev/null 2>&1 if [ $? -ne 0 ];then echo "SKIP: Could not run test without ip tool" diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh index 9f22f7e5027d..36a3c9d92e20 100755 --- a/tools/testing/selftests/net/mptcp/simult_flows.sh +++ b/tools/testing/selftests/net/mptcp/simult_flows.sh @@ -1,6 +1,8 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +. "$(dirname "${0}")/mptcp_lib.sh" + sec=$(date +%s) rndh=$(printf %x $sec)-$(mktemp -u XXXXXX) ns1="ns1-$rndh" @@ -34,6 +36,8 @@ cleanup() done } +mptcp_lib_check_mptcp + ip -Version > /dev/null 2>&1 if [ $? -ne 0 ];then echo "SKIP: Could not run test without ip tool" diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh index b1eb7bce599d..8092399d911f 100755 --- a/tools/testing/selftests/net/mptcp/userspace_pm.sh +++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh @@ -1,6 +1,10 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +. "$(dirname "${0}")/mptcp_lib.sh" + +mptcp_lib_check_mptcp + ip -Version > /dev/null 2>&1 if [ $? -ne 0 ];then echo "SKIP: Cannot not run test without ip tool" diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index cb5c13eee193..479802a892d4 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -3962,18 +3962,19 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id) } vcpu->vcpu_idx = atomic_read(&kvm->online_vcpus); - r = xa_insert(&kvm->vcpu_array, vcpu->vcpu_idx, vcpu, GFP_KERNEL_ACCOUNT); - BUG_ON(r == -EBUSY); + r = xa_reserve(&kvm->vcpu_array, vcpu->vcpu_idx, GFP_KERNEL_ACCOUNT); if (r) goto unlock_vcpu_destroy; /* Now it's all set up, let userspace reach it */ kvm_get_kvm(kvm); r = create_vcpu_fd(vcpu); - if (r < 0) { - xa_erase(&kvm->vcpu_array, vcpu->vcpu_idx); - kvm_put_kvm_no_destroy(kvm); - goto unlock_vcpu_destroy; + if (r < 0) + goto kvm_put_xa_release; + + if (KVM_BUG_ON(!!xa_store(&kvm->vcpu_array, vcpu->vcpu_idx, vcpu, 0), kvm)) { + r = -EINVAL; + goto kvm_put_xa_release; } /* @@ -3988,6 +3989,9 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id) kvm_create_vcpu_debugfs(vcpu); return r; +kvm_put_xa_release: + kvm_put_kvm_no_destroy(kvm); + xa_release(&kvm->vcpu_array, vcpu->vcpu_idx); unlock_vcpu_destroy: mutex_unlock(&kvm->lock); kvm_dirty_ring_free(&vcpu->dirty_ring); @@ -5184,7 +5188,20 @@ static void hardware_disable_all(void) static int hardware_enable_all(void) { atomic_t failed = ATOMIC_INIT(0); - int r = 0; + int r; + + /* + * Do not enable hardware virtualization if the system is going down. + * If userspace initiated a forced reboot, e.g. reboot -f, then it's + * possible for an in-flight KVM_CREATE_VM to trigger hardware enabling + * after kvm_reboot() is called. Note, this relies on system_state + * being set _before_ kvm_reboot(), which is why KVM uses a syscore ops + * hook instead of registering a dedicated reboot notifier (the latter + * runs before system_state is updated). + */ + if (system_state == SYSTEM_HALT || system_state == SYSTEM_POWER_OFF || + system_state == SYSTEM_RESTART) + return -EBUSY; /* * When onlining a CPU, cpu_online_mask is set before kvm_online_cpu() @@ -5197,6 +5214,8 @@ static int hardware_enable_all(void) cpus_read_lock(); mutex_lock(&kvm_lock); + r = 0; + kvm_usage_count++; if (kvm_usage_count == 1) { on_each_cpu(hardware_enable_nolock, &failed, 1); @@ -5213,26 +5232,24 @@ static int hardware_enable_all(void) return r; } -static int kvm_reboot(struct notifier_block *notifier, unsigned long val, - void *v) +static void kvm_shutdown(void) { /* - * Some (well, at least mine) BIOSes hang on reboot if - * in vmx root mode. - * - * And Intel TXT required VMX off for all cpu when system shutdown. + * Disable hardware virtualization and set kvm_rebooting to indicate + * that KVM has asynchronously disabled hardware virtualization, i.e. + * that relevant errors and exceptions aren't entirely unexpected. + * Some flavors of hardware virtualization need to be disabled before + * transferring control to firmware (to perform shutdown/reboot), e.g. + * on x86, virtualization can block INIT interrupts, which are used by + * firmware to pull APs back under firmware control. Note, this path + * is used for both shutdown and reboot scenarios, i.e. neither name is + * 100% comprehensive. */ pr_info("kvm: exiting hardware virtualization\n"); kvm_rebooting = true; on_each_cpu(hardware_disable_nolock, NULL, 1); - return NOTIFY_OK; } -static struct notifier_block kvm_reboot_notifier = { - .notifier_call = kvm_reboot, - .priority = 0, -}; - static int kvm_suspend(void) { /* @@ -5263,6 +5280,7 @@ static void kvm_resume(void) static struct syscore_ops kvm_syscore_ops = { .suspend = kvm_suspend, .resume = kvm_resume, + .shutdown = kvm_shutdown, }; #else /* CONFIG_KVM_GENERIC_HARDWARE_ENABLING */ static int hardware_enable_all(void) @@ -5967,7 +5985,6 @@ int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module) if (r) return r; - register_reboot_notifier(&kvm_reboot_notifier); register_syscore_ops(&kvm_syscore_ops); #endif @@ -6039,7 +6056,6 @@ err_cpu_kick_mask: err_vcpu_cache: #ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING unregister_syscore_ops(&kvm_syscore_ops); - unregister_reboot_notifier(&kvm_reboot_notifier); cpuhp_remove_state_nocalls(CPUHP_AP_KVM_ONLINE); #endif return r; @@ -6065,7 +6081,6 @@ void kvm_exit(void) kvm_async_pf_deinit(); #ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING unregister_syscore_ops(&kvm_syscore_ops); - unregister_reboot_notifier(&kvm_reboot_notifier); cpuhp_remove_state_nocalls(CPUHP_AP_KVM_ONLINE); #endif kvm_irqfd_exit(); |