diff --git a/.mailmap b/.mailmap index e7e639aeb23c..12f3acdebd72 100644 --- a/.mailmap +++ b/.mailmap @@ -642,7 +642,6 @@ Nicholas Piggin Nicholas Piggin Nicholas Piggin Nicholas Piggin -Nick Desaulniers Nicolas Ferre Nicolas Pitre Nicolas Pitre @@ -709,6 +708,10 @@ Qi Zheng Quentin Monnet Quentin Monnet Quentin Perret +Radu Rendec +Radu Rendec +Radu Rendec +Radu Rendec Rae Moar Rafael J. Wysocki Rajeev Nandan diff --git a/Documentation/ABI/testing/sysfs-bus-pci-drivers-xhci_hcd b/Documentation/ABI/testing/sysfs-bus-pci-drivers-xhci_hcd index 98a8376a83d2..991765d84201 100644 --- a/Documentation/ABI/testing/sysfs-bus-pci-drivers-xhci_hcd +++ b/Documentation/ABI/testing/sysfs-bus-pci-drivers-xhci_hcd @@ -22,7 +22,7 @@ Description: Reading this attribute gives the state of the DbC. It can be one of the following states: disabled, enabled, - initialized, connected or configured. + initialized, connected, configured or suspended. What: /sys/bus/pci/drivers/xhci_hcd/.../dbc_idVendor Date: March 2023 diff --git a/Documentation/arch/arm64/cpu-hotplug.rst b/Documentation/arch/arm64/cpu-hotplug.rst index 8fb438bf7781..7c3379b704aa 100644 --- a/Documentation/arch/arm64/cpu-hotplug.rst +++ b/Documentation/arch/arm64/cpu-hotplug.rst @@ -47,11 +47,12 @@ ever have can be described at boot. There are no power-domain considerations as such devices are emulated. CPU Hotplug on virtual systems is supported. It is distinct from physical -CPU Hotplug as all resources are described as ``present``, but CPUs may be -marked as disabled by firmware. Only the CPU's online/offline behaviour is -influenced by firmware. An example is where a virtual machine boots with a -single CPU, and additional CPUs are added once a cloud orchestrator deploys -the workload. +CPU Hotplug as all vCPU resources are statically described in the firmware +configuration tables (e.g. MADT), meaning their maximum possible count is +known at boot. However, vCPUs that are not enabled at boot are not marked +as ``present`` by the kernel until they are hotplugged. An example is where +a virtual machine boots with a single CPU, and additional CPUs are added +once a cloud orchestrator deploys the workload. For a virtual machine, the VMM (e.g. Qemu) plays the part of firmware. @@ -60,16 +61,19 @@ brought online. Firmware can enforce its policy via PSCI's return codes. e.g. ``DENIED``. The ACPI tables must describe all the resources of the virtual machine. CPUs -that firmware wishes to disable either from boot (or later) should not be -``enabled`` in the MADT GICC structures, but should have the ``online capable`` -bit set, to indicate they can be enabled later. The boot CPU must be marked as -``enabled``. The 'always on' GICR structure must be used to describe the -redistributors. +that are hot-pluggable must have the ``online capable`` bit set and the +``enabled`` bit cleared in the MADT GICC structures to indicate they can be +enabled later. The boot CPU must be marked as ``enabled`` with its +``online capable`` bit cleared. The 'always on' GICR structure must be used +to describe the redistributors. CPUs described as ``online capable`` but not ``enabled`` can be set to enabled by the DSDT's Processor object's _STA method. On virtual systems the _STA method -must always report the CPU as ``present``. Changes to the firmware policy can -be notified to the OS via device-check or eject-request. +must always set the ``ACPI_STA_DEVICE_PRESENT`` bit, while toggling the +``ACPI_STA_DEVICE_ENABLED`` bit to reflect its plug status. The kernel will +then dynamically mark the vCPU as ``present`` within the OS when the +``ACPI_STA_DEVICE_ENABLED`` bit becomes set during hot-add. Changes to the +firmware policy can be notified to the OS via device-check or eject-request. CPUs described as ``enabled`` in the static table, should not have their _STA modified dynamically by firmware. Soft-restart features such as kexec will diff --git a/Documentation/arch/riscv/hwprobe.rst b/Documentation/arch/riscv/hwprobe.rst index c420a8349bc6..d9928641deb9 100644 --- a/Documentation/arch/riscv/hwprobe.rst +++ b/Documentation/arch/riscv/hwprobe.rst @@ -82,121 +82,121 @@ The following keys are defined: version 1.0 of the RISC-V Vector extension manual. * :c:macro:`RISCV_HWPROBE_EXT_ZBA`: The Zba address generation extension is - supported, as defined in version 1.0 of the Bit-Manipulation ISA - extensions. + supported, as defined in version 1.0 of the Bit-Manipulation ISA + extensions. * :c:macro:`RISCV_HWPROBE_EXT_ZBB`: The Zbb extension is supported, as defined - in version 1.0 of the Bit-Manipulation ISA extensions. + in version 1.0 of the Bit-Manipulation ISA extensions. * :c:macro:`RISCV_HWPROBE_EXT_ZBS`: The Zbs extension is supported, as defined - in version 1.0 of the Bit-Manipulation ISA extensions. + in version 1.0 of the Bit-Manipulation ISA extensions. * :c:macro:`RISCV_HWPROBE_EXT_ZICBOZ`: The Zicboz extension is supported, as - ratified in commit 3dd606f ("Create cmobase-v1.0.pdf") of riscv-CMOs. + ratified in commit 3dd606f ("Create cmobase-v1.0.pdf") of riscv-CMOs. * :c:macro:`RISCV_HWPROBE_EXT_ZBC` The Zbc extension is supported, as defined - in version 1.0 of the Bit-Manipulation ISA extensions. + in version 1.0 of the Bit-Manipulation ISA extensions. * :c:macro:`RISCV_HWPROBE_EXT_ZBKB` The Zbkb extension is supported, as - defined in version 1.0 of the Scalar Crypto ISA extensions. + defined in version 1.0 of the Scalar Crypto ISA extensions. * :c:macro:`RISCV_HWPROBE_EXT_ZBKC` The Zbkc extension is supported, as - defined in version 1.0 of the Scalar Crypto ISA extensions. + defined in version 1.0 of the Scalar Crypto ISA extensions. * :c:macro:`RISCV_HWPROBE_EXT_ZBKX` The Zbkx extension is supported, as - defined in version 1.0 of the Scalar Crypto ISA extensions. + defined in version 1.0 of the Scalar Crypto ISA extensions. * :c:macro:`RISCV_HWPROBE_EXT_ZKND` The Zknd extension is supported, as - defined in version 1.0 of the Scalar Crypto ISA extensions. + defined in version 1.0 of the Scalar Crypto ISA extensions. * :c:macro:`RISCV_HWPROBE_EXT_ZKNE` The Zkne extension is supported, as - defined in version 1.0 of the Scalar Crypto ISA extensions. + defined in version 1.0 of the Scalar Crypto ISA extensions. * :c:macro:`RISCV_HWPROBE_EXT_ZKNH` The Zknh extension is supported, as - defined in version 1.0 of the Scalar Crypto ISA extensions. + defined in version 1.0 of the Scalar Crypto ISA extensions. * :c:macro:`RISCV_HWPROBE_EXT_ZKSED` The Zksed extension is supported, as - defined in version 1.0 of the Scalar Crypto ISA extensions. + defined in version 1.0 of the Scalar Crypto ISA extensions. * :c:macro:`RISCV_HWPROBE_EXT_ZKSH` The Zksh extension is supported, as - defined in version 1.0 of the Scalar Crypto ISA extensions. + defined in version 1.0 of the Scalar Crypto ISA extensions. * :c:macro:`RISCV_HWPROBE_EXT_ZKT` The Zkt extension is supported, as defined - in version 1.0 of the Scalar Crypto ISA extensions. + in version 1.0 of the Scalar Crypto ISA extensions. * :c:macro:`RISCV_HWPROBE_EXT_ZVBB`: The Zvbb extension is supported as - defined in version 1.0 of the RISC-V Cryptography Extensions Volume II. + defined in version 1.0 of the RISC-V Cryptography Extensions Volume II. * :c:macro:`RISCV_HWPROBE_EXT_ZVBC`: The Zvbc extension is supported as - defined in version 1.0 of the RISC-V Cryptography Extensions Volume II. + defined in version 1.0 of the RISC-V Cryptography Extensions Volume II. * :c:macro:`RISCV_HWPROBE_EXT_ZVKB`: The Zvkb extension is supported as - defined in version 1.0 of the RISC-V Cryptography Extensions Volume II. + defined in version 1.0 of the RISC-V Cryptography Extensions Volume II. * :c:macro:`RISCV_HWPROBE_EXT_ZVKG`: The Zvkg extension is supported as - defined in version 1.0 of the RISC-V Cryptography Extensions Volume II. + defined in version 1.0 of the RISC-V Cryptography Extensions Volume II. * :c:macro:`RISCV_HWPROBE_EXT_ZVKNED`: The Zvkned extension is supported as - defined in version 1.0 of the RISC-V Cryptography Extensions Volume II. + defined in version 1.0 of the RISC-V Cryptography Extensions Volume II. * :c:macro:`RISCV_HWPROBE_EXT_ZVKNHA`: The Zvknha extension is supported as - defined in version 1.0 of the RISC-V Cryptography Extensions Volume II. + defined in version 1.0 of the RISC-V Cryptography Extensions Volume II. * :c:macro:`RISCV_HWPROBE_EXT_ZVKNHB`: The Zvknhb extension is supported as - defined in version 1.0 of the RISC-V Cryptography Extensions Volume II. + defined in version 1.0 of the RISC-V Cryptography Extensions Volume II. * :c:macro:`RISCV_HWPROBE_EXT_ZVKSED`: The Zvksed extension is supported as - defined in version 1.0 of the RISC-V Cryptography Extensions Volume II. + defined in version 1.0 of the RISC-V Cryptography Extensions Volume II. * :c:macro:`RISCV_HWPROBE_EXT_ZVKSH`: The Zvksh extension is supported as - defined in version 1.0 of the RISC-V Cryptography Extensions Volume II. + defined in version 1.0 of the RISC-V Cryptography Extensions Volume II. * :c:macro:`RISCV_HWPROBE_EXT_ZVKT`: The Zvkt extension is supported as - defined in version 1.0 of the RISC-V Cryptography Extensions Volume II. + defined in version 1.0 of the RISC-V Cryptography Extensions Volume II. * :c:macro:`RISCV_HWPROBE_EXT_ZFH`: The Zfh extension version 1.0 is supported - as defined in the RISC-V ISA manual. + as defined in the RISC-V ISA manual. * :c:macro:`RISCV_HWPROBE_EXT_ZFHMIN`: The Zfhmin extension version 1.0 is - supported as defined in the RISC-V ISA manual. + supported as defined in the RISC-V ISA manual. * :c:macro:`RISCV_HWPROBE_EXT_ZIHINTNTL`: The Zihintntl extension version 1.0 - is supported as defined in the RISC-V ISA manual. + is supported as defined in the RISC-V ISA manual. * :c:macro:`RISCV_HWPROBE_EXT_ZVFH`: The Zvfh extension is supported as - defined in the RISC-V Vector manual starting from commit e2ccd0548d6c - ("Remove draft warnings from Zvfh[min]"). + defined in the RISC-V Vector manual starting from commit e2ccd0548d6c + ("Remove draft warnings from Zvfh[min]"). * :c:macro:`RISCV_HWPROBE_EXT_ZVFHMIN`: The Zvfhmin extension is supported as - defined in the RISC-V Vector manual starting from commit e2ccd0548d6c - ("Remove draft warnings from Zvfh[min]"). + defined in the RISC-V Vector manual starting from commit e2ccd0548d6c + ("Remove draft warnings from Zvfh[min]"). * :c:macro:`RISCV_HWPROBE_EXT_ZFA`: The Zfa extension is supported as - defined in the RISC-V ISA manual starting from commit 056b6ff467c7 - ("Zfa is ratified"). + defined in the RISC-V ISA manual starting from commit 056b6ff467c7 + ("Zfa is ratified"). * :c:macro:`RISCV_HWPROBE_EXT_ZTSO`: The Ztso extension is supported as - defined in the RISC-V ISA manual starting from commit 5618fb5a216b - ("Ztso is now ratified.") + defined in the RISC-V ISA manual starting from commit 5618fb5a216b + ("Ztso is now ratified.") * :c:macro:`RISCV_HWPROBE_EXT_ZACAS`: The Zacas extension is supported as - defined in the Atomic Compare-and-Swap (CAS) instructions manual starting - from commit 5059e0ca641c ("update to ratified"). + defined in the Atomic Compare-and-Swap (CAS) instructions manual starting + from commit 5059e0ca641c ("update to ratified"). * :c:macro:`RISCV_HWPROBE_EXT_ZICNTR`: The Zicntr extension version 2.0 - is supported as defined in the RISC-V ISA manual. + is supported as defined in the RISC-V ISA manual. * :c:macro:`RISCV_HWPROBE_EXT_ZICOND`: The Zicond extension is supported as - defined in the RISC-V Integer Conditional (Zicond) operations extension - manual starting from commit 95cf1f9 ("Add changes requested by Ved - during signoff") + defined in the RISC-V Integer Conditional (Zicond) operations extension + manual starting from commit 95cf1f9 ("Add changes requested by Ved + during signoff") * :c:macro:`RISCV_HWPROBE_EXT_ZIHINTPAUSE`: The Zihintpause extension is - supported as defined in the RISC-V ISA manual starting from commit - d8ab5c78c207 ("Zihintpause is ratified"). + supported as defined in the RISC-V ISA manual starting from commit + d8ab5c78c207 ("Zihintpause is ratified"). * :c:macro:`RISCV_HWPROBE_EXT_ZIHPM`: The Zihpm extension version 2.0 - is supported as defined in the RISC-V ISA manual. + is supported as defined in the RISC-V ISA manual. * :c:macro:`RISCV_HWPROBE_EXT_ZVE32X`: The Vector sub-extension Zve32x is supported, as defined by version 1.0 of the RISC-V Vector extension manual. @@ -214,84 +214,89 @@ The following keys are defined: supported, as defined by version 1.0 of the RISC-V Vector extension manual. * :c:macro:`RISCV_HWPROBE_EXT_ZIMOP`: The Zimop May-Be-Operations extension is - supported as defined in the RISC-V ISA manual starting from commit - 58220614a5f ("Zimop is ratified/1.0"). + supported as defined in the RISC-V ISA manual starting from commit + 58220614a5f ("Zimop is ratified/1.0"). * :c:macro:`RISCV_HWPROBE_EXT_ZCA`: The Zca extension part of Zc* standard - extensions for code size reduction, as ratified in commit 8be3419c1c0 - ("Zcf doesn't exist on RV64 as it contains no instructions") of - riscv-code-size-reduction. + extensions for code size reduction, as ratified in commit 8be3419c1c0 + ("Zcf doesn't exist on RV64 as it contains no instructions") of + riscv-code-size-reduction. * :c:macro:`RISCV_HWPROBE_EXT_ZCB`: The Zcb extension part of Zc* standard - extensions for code size reduction, as ratified in commit 8be3419c1c0 - ("Zcf doesn't exist on RV64 as it contains no instructions") of - riscv-code-size-reduction. + extensions for code size reduction, as ratified in commit 8be3419c1c0 + ("Zcf doesn't exist on RV64 as it contains no instructions") of + riscv-code-size-reduction. * :c:macro:`RISCV_HWPROBE_EXT_ZCD`: The Zcd extension part of Zc* standard - extensions for code size reduction, as ratified in commit 8be3419c1c0 - ("Zcf doesn't exist on RV64 as it contains no instructions") of - riscv-code-size-reduction. + extensions for code size reduction, as ratified in commit 8be3419c1c0 + ("Zcf doesn't exist on RV64 as it contains no instructions") of + riscv-code-size-reduction. * :c:macro:`RISCV_HWPROBE_EXT_ZCF`: The Zcf extension part of Zc* standard - extensions for code size reduction, as ratified in commit 8be3419c1c0 - ("Zcf doesn't exist on RV64 as it contains no instructions") of - riscv-code-size-reduction. + extensions for code size reduction, as ratified in commit 8be3419c1c0 + ("Zcf doesn't exist on RV64 as it contains no instructions") of + riscv-code-size-reduction. * :c:macro:`RISCV_HWPROBE_EXT_ZCMOP`: The Zcmop May-Be-Operations extension is - supported as defined in the RISC-V ISA manual starting from commit - c732a4f39a4 ("Zcmop is ratified/1.0"). + supported as defined in the RISC-V ISA manual starting from commit + c732a4f39a4 ("Zcmop is ratified/1.0"). * :c:macro:`RISCV_HWPROBE_EXT_ZAWRS`: The Zawrs extension is supported as - ratified in commit 98918c844281 ("Merge pull request #1217 from - riscv/zawrs") of riscv-isa-manual. + ratified in commit 98918c844281 ("Merge pull request #1217 from + riscv/zawrs") of riscv-isa-manual. * :c:macro:`RISCV_HWPROBE_EXT_ZAAMO`: The Zaamo extension is supported as - defined in the in the RISC-V ISA manual starting from commit e87412e621f1 - ("integrate Zaamo and Zalrsc text (#1304)"). + defined in the in the RISC-V ISA manual starting from commit e87412e621f1 + ("integrate Zaamo and Zalrsc text (#1304)"). * :c:macro:`RISCV_HWPROBE_EXT_ZALASR`: The Zalasr extension is supported as - frozen at commit 194f0094 ("Version 0.9 for freeze") of riscv-zalasr. + frozen at commit 194f0094 ("Version 0.9 for freeze") of riscv-zalasr. * :c:macro:`RISCV_HWPROBE_EXT_ZALRSC`: The Zalrsc extension is supported as - defined in the in the RISC-V ISA manual starting from commit e87412e621f1 - ("integrate Zaamo and Zalrsc text (#1304)"). + defined in the in the RISC-V ISA manual starting from commit e87412e621f1 + ("integrate Zaamo and Zalrsc text (#1304)"). * :c:macro:`RISCV_HWPROBE_EXT_SUPM`: The Supm extension is supported as - defined in version 1.0 of the RISC-V Pointer Masking extensions. + defined in version 1.0 of the RISC-V Pointer Masking extensions. * :c:macro:`RISCV_HWPROBE_EXT_ZFBFMIN`: The Zfbfmin extension is supported as - defined in the RISC-V ISA manual starting from commit 4dc23d6229de - ("Added Chapter title to BF16"). + defined in the RISC-V ISA manual starting from commit 4dc23d6229de + ("Added Chapter title to BF16"). * :c:macro:`RISCV_HWPROBE_EXT_ZVFBFMIN`: The Zvfbfmin extension is supported as - defined in the RISC-V ISA manual starting from commit 4dc23d6229de - ("Added Chapter title to BF16"). + defined in the RISC-V ISA manual starting from commit 4dc23d6229de + ("Added Chapter title to BF16"). * :c:macro:`RISCV_HWPROBE_EXT_ZVFBFWMA`: The Zvfbfwma extension is supported as - defined in the RISC-V ISA manual starting from commit 4dc23d6229de - ("Added Chapter title to BF16"). + defined in the RISC-V ISA manual starting from commit 4dc23d6229de + ("Added Chapter title to BF16"). * :c:macro:`RISCV_HWPROBE_EXT_ZICBOM`: The Zicbom extension is supported, as - ratified in commit 3dd606f ("Create cmobase-v1.0.pdf") of riscv-CMOs. + ratified in commit 3dd606f ("Create cmobase-v1.0.pdf") of riscv-CMOs. * :c:macro:`RISCV_HWPROBE_EXT_ZABHA`: The Zabha extension is supported as - ratified in commit 49f49c842ff9 ("Update to Rafified state") of - riscv-zabha. + ratified in commit 49f49c842ff9 ("Update to Rafified state") of + riscv-zabha. * :c:macro:`RISCV_HWPROBE_EXT_ZICBOP`: The Zicbop extension is supported, as - ratified in commit 3dd606f ("Create cmobase-v1.0.pdf") of riscv-CMOs. + ratified in commit 3dd606f ("Create cmobase-v1.0.pdf") of riscv-CMOs. * :c:macro:`RISCV_HWPROBE_EXT_ZILSD`: The Zilsd extension is supported as - defined in the RISC-V ISA manual starting from commit f88abf1 ("Integrating - load/store pair for RV32 with the main manual") of the riscv-isa-manual. + defined in the RISC-V ISA manual starting from commit f88abf1 ("Integrating + load/store pair for RV32 with the main manual") of the riscv-isa-manual. * :c:macro:`RISCV_HWPROBE_EXT_ZCLSD`: The Zclsd extension is supported as - defined in the RISC-V ISA manual starting from commit f88abf1 ("Integrating - load/store pair for RV32 with the main manual") of the riscv-isa-manual. + defined in the RISC-V ISA manual starting from commit f88abf1 ("Integrating + load/store pair for RV32 with the main manual") of the riscv-isa-manual. + + * :c:macro:`RISCV_HWPROBE_EXT_ZICFILP`: The Zicfilp extension is supported, + as defined in version 1.0 of the RISC-V Control-flow Integrity (CFI) + extensions specification, ratified in commit 302a2d45c243 + ("Update build-pdf.yml") of riscv-cfi. * :c:macro:`RISCV_HWPROBE_KEY_CPUPERF_0`: Deprecated. Returns similar values to - :c:macro:`RISCV_HWPROBE_KEY_MISALIGNED_SCALAR_PERF`, but the key was - mistakenly classified as a bitmask rather than a value. + :c:macro:`RISCV_HWPROBE_KEY_MISALIGNED_SCALAR_PERF`, but the key was + mistakenly classified as a bitmask rather than a value. * :c:macro:`RISCV_HWPROBE_KEY_MISALIGNED_SCALAR_PERF`: An enum value describing the performance of misaligned scalar native word accesses on the selected set @@ -326,7 +331,7 @@ The following keys are defined: * :c:macro:`RISCV_HWPROBE_KEY_TIME_CSR_FREQ`: Frequency (in Hz) of `time CSR`. * :c:macro:`RISCV_HWPROBE_KEY_MISALIGNED_VECTOR_PERF`: An enum value describing the - performance of misaligned vector accesses on the selected set of processors. + performance of misaligned vector accesses on the selected set of processors. * :c:macro:`RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN`: The performance of misaligned vector accesses is unknown. @@ -348,7 +353,7 @@ The following keys are defined: * MIPS * :c:macro:`RISCV_HWPROBE_VENDOR_EXT_XMIPSEXECTL`: The xmipsexectl vendor - extension is supported in the MIPS ISA extensions spec. + extension is supported in the MIPS ISA extensions spec. * :c:macro:`RISCV_HWPROBE_KEY_VENDOR_EXT_THEAD_0`: A bitmask containing the thead vendor extensions that are compatible with the @@ -357,8 +362,8 @@ The following keys are defined: * T-HEAD * :c:macro:`RISCV_HWPROBE_VENDOR_EXT_XTHEADVECTOR`: The xtheadvector vendor - extension is supported in the T-Head ISA extensions spec starting from - commit a18c801634 ("Add T-Head VECTOR vendor extension. "). + extension is supported in the T-Head ISA extensions spec starting from + commit a18c801634 ("Add T-Head VECTOR vendor extension. "). * :c:macro:`RISCV_HWPROBE_KEY_ZICBOM_BLOCK_SIZE`: An unsigned int which represents the size of the Zicbom block in bytes. @@ -370,20 +375,20 @@ The following keys are defined: * SIFIVE * :c:macro:`RISCV_HWPROBE_VENDOR_EXT_XSFVQMACCDOD`: The Xsfqmaccdod vendor - extension is supported in version 1.1 of SiFive Int8 Matrix Multiplication - Extensions Specification. + extension is supported in version 1.1 of SiFive Int8 Matrix Multiplication + Extensions Specification. * :c:macro:`RISCV_HWPROBE_VENDOR_EXT_XSFVQMACCQOQ`: The Xsfqmaccqoq vendor - extension is supported in version 1.1 of SiFive Int8 Matrix Multiplication - Instruction Extensions Specification. + extension is supported in version 1.1 of SiFive Int8 Matrix Multiplication + Instruction Extensions Specification. * :c:macro:`RISCV_HWPROBE_VENDOR_EXT_XSFVFNRCLIPXFQF`: The Xsfvfnrclipxfqf - vendor extension is supported in version 1.0 of SiFive FP32-to-int8 Ranged - Clip Instructions Extensions Specification. + vendor extension is supported in version 1.0 of SiFive FP32-to-int8 Ranged + Clip Instructions Extensions Specification. * :c:macro:`RISCV_HWPROBE_VENDOR_EXT_XSFVFWMACCQQQ`: The Xsfvfwmaccqqq - vendor extension is supported in version 1.0 of Matrix Multiply Accumulate - Instruction Extensions Specification. + vendor extension is supported in version 1.0 of Matrix Multiply Accumulate + Instruction Extensions Specification. * :c:macro:`RISCV_HWPROBE_KEY_ZICBOP_BLOCK_SIZE`: An unsigned int which represents the size of the Zicbop block in bytes. @@ -391,3 +396,8 @@ The following keys are defined: * :c:macro:`RISCV_HWPROBE_KEY_IMA_EXT_1`: A bitmask containing additional extensions that are compatible with the :c:macro:`RISCV_HWPROBE_BASE_BEHAVIOR_IMA`: base system behavior. + + * :c:macro:`RISCV_HWPROBE_EXT_ZICFISS`: The Zicfiss extension is supported, + as defined in version 1.0 of the RISC-V Control-flow Integrity (CFI) + extensions specification, ratified in commit 302a2d45c243 + ("Update build-pdf.yml") of riscv-cfi. diff --git a/Documentation/devicetree/bindings/riscv/extensions.yaml b/Documentation/devicetree/bindings/riscv/extensions.yaml index 2b0a8a93bb21..5ffc40d599c0 100644 --- a/Documentation/devicetree/bindings/riscv/extensions.yaml +++ b/Documentation/devicetree/bindings/riscv/extensions.yaml @@ -457,6 +457,13 @@ properties: merged in the riscv-isa-manual by commit dbc79cf28a2 ("Initial seed of zc.adoc to src tree."). + - const: zclsd + description: + The Zclsd extension implements the compressed (16-bit) version of the + Load/Store Pair for RV32. As with Zilsd, this extension was ratified + in commit f88abf1 ("Integrating load/store pair for RV32 with the + main manual") of riscv-isa-manual. + - const: zcmop description: The standard Zcmop extension version 1.0, as ratified in commit @@ -487,6 +494,22 @@ properties: in commit 64074bc ("Update version numbers for Zfh/Zfinx") of riscv-isa-manual. + - const: zicbom + description: + The standard Zicbom extension for base cache management operations as + ratified in commit 3dd606f ("Create cmobase-v1.0.pdf") of riscv-CMOs. + + - const: zicbop + description: + The standard Zicbop extension for cache-block prefetch instructions + as ratified in commit 3dd606f ("Create cmobase-v1.0.pdf") of + riscv-CMOs. + + - const: zicboz + description: + The standard Zicboz extension for cache-block zeroing as ratified + in commit 3dd606f ("Create cmobase-v1.0.pdf") of riscv-CMOs. + - const: ziccamoa description: The standard Ziccamoa extension for main memory (cacheability and @@ -514,6 +537,66 @@ properties: guarantee on LR/SC sequences, as ratified in commit b1d806605f87 ("Updated to ratified state.") of the riscv profiles specification. + - const: zicfilp + description: | + The standard Zicfilp extension for enforcing forward edge + control-flow integrity as ratified in commit 3f8e450 ("merge + pull request #227 from ved-rivos/0709") of riscv-cfi + github repo. + + - const: zicfiss + description: | + The standard Zicfiss extension for enforcing backward edge + control-flow integrity as ratified in commit 3f8e450 ("merge + pull request #227 from ved-rivos/0709") of riscv-cfi + github repo. + + - const: zicntr + description: + The standard Zicntr extension for base counters and timers, as + ratified in the 20191213 version of the unprivileged ISA + specification. + + - const: zicond + description: + The standard Zicond extension for conditional arithmetic and + conditional-select/move operations as ratified in commit 95cf1f9 + ("Add changes requested by Ved during signoff") of riscv-zicond. + + - const: zicsr + description: | + The standard Zicsr extension for control and status register + instructions, as ratified in the 20191213 version of the + unprivileged ISA specification. + + This does not include Chapter 10, "Counters", which documents + special case read-only CSRs, that were moved into the Zicntr and + Zihpm extensions after the ratification of the 20191213 version of + the unprivileged specification. + + - const: zifencei + description: + The standard Zifencei extension for instruction-fetch fence, as + ratified in the 20191213 version of the unprivileged ISA + specification. + + - const: zihintntl + description: + The standard Zihintntl extension for non-temporal locality hints, as + ratified in commit 0dc91f5 ("Zihintntl is ratified") of the + riscv-isa-manual. + + - const: zihintpause + description: + The standard Zihintpause extension for pause hints, as ratified in + commit d8ab5c7 ("Zihintpause is ratified") of the riscv-isa-manual. + + - const: zihpm + description: + The standard Zihpm extension for hardware performance counters, as + ratified in the 20191213 version of the unprivileged ISA + specification. + - const: zilsd description: The standard Zilsd extension which provides support for aligned @@ -521,12 +604,10 @@ properties: encodings, as ratified in commit f88abf1 ("Integrating load/store pair for RV32 with the main manual") of riscv-isa-manual. - - const: zclsd + - const: zimop description: - The Zclsd extension implements the compressed (16-bit) version of the - Load/Store Pair for RV32. As with Zilsd, this extension was ratified - in commit f88abf1 ("Integrating load/store pair for RV32 with the - main manual") of riscv-isa-manual. + The standard Zimop extension version 1.0, as ratified in commit + 58220614a5f ("Zimop is ratified/1.0") of the riscv-isa-manual. - const: zk description: @@ -590,87 +671,6 @@ properties: in version 1.0 of RISC-V Cryptography Extensions Volume I specification. - - const: zicbom - description: - The standard Zicbom extension for base cache management operations as - ratified in commit 3dd606f ("Create cmobase-v1.0.pdf") of riscv-CMOs. - - - const: zicbop - description: - The standard Zicbop extension for cache-block prefetch instructions - as ratified in commit 3dd606f ("Create cmobase-v1.0.pdf") of - riscv-CMOs. - - - const: zicboz - description: - The standard Zicboz extension for cache-block zeroing as ratified - in commit 3dd606f ("Create cmobase-v1.0.pdf") of riscv-CMOs. - - - const: zicfilp - description: | - The standard Zicfilp extension for enforcing forward edge - control-flow integrity as ratified in commit 3f8e450 ("merge - pull request #227 from ved-rivos/0709") of riscv-cfi - github repo. - - - const: zicfiss - description: | - The standard Zicfiss extension for enforcing backward edge - control-flow integrity as ratified in commit 3f8e450 ("merge - pull request #227 from ved-rivos/0709") of riscv-cfi - github repo. - - - const: zicntr - description: - The standard Zicntr extension for base counters and timers, as - ratified in the 20191213 version of the unprivileged ISA - specification. - - - const: zicond - description: - The standard Zicond extension for conditional arithmetic and - conditional-select/move operations as ratified in commit 95cf1f9 - ("Add changes requested by Ved during signoff") of riscv-zicond. - - - const: zicsr - description: | - The standard Zicsr extension for control and status register - instructions, as ratified in the 20191213 version of the - unprivileged ISA specification. - - This does not include Chapter 10, "Counters", which documents - special case read-only CSRs, that were moved into the Zicntr and - Zihpm extensions after the ratification of the 20191213 version of - the unprivileged specification. - - - const: zifencei - description: - The standard Zifencei extension for instruction-fetch fence, as - ratified in the 20191213 version of the unprivileged ISA - specification. - - - const: zihintpause - description: - The standard Zihintpause extension for pause hints, as ratified in - commit d8ab5c7 ("Zihintpause is ratified") of the riscv-isa-manual. - - - const: zihintntl - description: - The standard Zihintntl extension for non-temporal locality hints, as - ratified in commit 0dc91f5 ("Zihintntl is ratified") of the - riscv-isa-manual. - - - const: zihpm - description: - The standard Zihpm extension for hardware performance counters, as - ratified in the 20191213 version of the unprivileged ISA - specification. - - - const: zimop - description: - The standard Zimop extension version 1.0, as ratified in commit - 58220614a5f ("Zimop is ratified/1.0") of the riscv-isa-manual. - - const: ztso description: The standard Ztso extension for total store ordering, as ratified @@ -809,18 +809,18 @@ properties: instructions, as ratified in commit 56ed795 ("Update riscv-crypto-spec-vector.adoc") of riscv-crypto. - - const: zvksh - description: | - The standard Zvksh extension for ShangMi suite: SM3 secure hash - instructions, as ratified in commit 56ed795 ("Update - riscv-crypto-spec-vector.adoc") of riscv-crypto. - - const: zvksg description: The standard Zvksg extension for ShangMi algorithm suite with GCM instructions, as ratified in commit 56ed795 ("Update riscv-crypto-spec-vector.adoc") of riscv-crypto. + - const: zvksh + description: | + The standard Zvksh extension for ShangMi suite: SM3 secure hash + instructions, as ratified in commit 56ed795 ("Update + riscv-crypto-spec-vector.adoc") of riscv-crypto. + - const: zvkt description: The standard Zvkt extension for vector data-independent execution diff --git a/Documentation/process/embargoed-hardware-issues.rst b/Documentation/process/embargoed-hardware-issues.rst index 34e00848e0da..d07f16c3c7b8 100644 --- a/Documentation/process/embargoed-hardware-issues.rst +++ b/Documentation/process/embargoed-hardware-issues.rst @@ -308,7 +308,7 @@ an involved disclosed party. The current ambassadors list: Google Kees Cook - LLVM Nick Desaulniers + LLVM Nick Desaulniers ============= ======================================================== If you want your organization to be added to the ambassadors list, please diff --git a/Documentation/translations/sp_SP/process/embargoed-hardware-issues.rst b/Documentation/translations/sp_SP/process/embargoed-hardware-issues.rst index 9d444b9c46d3..7d4d694967c7 100644 --- a/Documentation/translations/sp_SP/process/embargoed-hardware-issues.rst +++ b/Documentation/translations/sp_SP/process/embargoed-hardware-issues.rst @@ -287,7 +287,7 @@ revelada involucrada. La lista de embajadores actuales: Google Kees Cook - LLVM Nick Desaulniers + LLVM Nick Desaulniers ============= ======================================================== Si quiere que su organización se añada a la lista de embajadores, por diff --git a/MAINTAINERS b/MAINTAINERS index 4a8b0fd665ce..806bd2d80d15 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6342,7 +6342,7 @@ F: .clang-format CLANG/LLVM BUILD SUPPORT M: Nathan Chancellor -R: Nick Desaulniers +R: Nick Desaulniers R: Bill Wendling R: Justin Stitt L: llvm@lists.linux.dev @@ -17204,6 +17204,7 @@ R: Liam R. Howlett R: Vlastimil Babka R: Harry Yoo R: Jann Horn +R: Lance Yang L: linux-mm@kvack.org S: Maintained F: include/linux/rmap.h @@ -20405,7 +20406,7 @@ F: kernel/padata.c PAGE CACHE M: Matthew Wilcox (Oracle) -R: Jan Kara +M: Jan Kara L: linux-fsdevel@vger.kernel.org L: linux-mm@kvack.org S: Supported @@ -28054,6 +28055,7 @@ F: include/dt-bindings/usb/ F: include/linux/usb.h F: include/linux/usb/ F: include/uapi/linux/usb/ +F: rust/kernel/usb.rs USB TYPEC BUS FOR ALTERNATE MODES M: Heikki Krogerus diff --git a/Makefile b/Makefile index b4035d3cef26..bfb47ad8cb9a 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 7 PATCHLEVEL = 2 SUBLEVEL = 0 -EXTRAVERSION = -rc2 +EXTRAVERSION = -rc3 NAME = Baby Opossum Posse # *DOCUMENTATION* diff --git a/arch/arm64/include/asm/tlbbatch.h b/arch/arm64/include/asm/tlbbatch.h index 6297631532e5..767f35ea62b3 100644 --- a/arch/arm64/include/asm/tlbbatch.h +++ b/arch/arm64/include/asm/tlbbatch.h @@ -2,17 +2,11 @@ #ifndef _ARCH_ARM64_TLBBATCH_H #define _ARCH_ARM64_TLBBATCH_H -#include - struct arch_tlbflush_unmap_batch { -#ifdef CONFIG_ARM64_ERRATUM_4193714 /* - * Track CPUs that need SME DVMSync on completion of this batch. - * Otherwise, the arm64 HW can do tlb shootdown, so we don't need to - * record cpumask for sending IPI + * For arm64, HW can do TLB shootdown, so we don't need to record a + * cpumask for sending IPIs. */ - cpumask_var_t cpumask; -#endif }; #endif /* _ARCH_ARM64_TLBBATCH_H */ diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h index d52ac8c17190..e0e84332f51b 100644 --- a/arch/arm64/include/asm/tlbflush.h +++ b/arch/arm64/include/asm/tlbflush.h @@ -82,6 +82,8 @@ static inline unsigned long get_trans_granule(void) #ifdef CONFIG_ARM64_ERRATUM_4193714 +extern cpumask_t sme_active_cpus; + void sme_do_dvmsync(const struct cpumask *mask); static inline void sme_dvmsync(struct mm_struct *mm) @@ -92,42 +94,12 @@ static inline void sme_dvmsync(struct mm_struct *mm) sme_do_dvmsync(mm_cpumask(mm)); } -static inline void sme_dvmsync_add_pending(struct arch_tlbflush_unmap_batch *batch, - struct mm_struct *mm) +static inline void sme_dvmsync_batch(void) { if (!alternative_has_cap_unlikely(ARM64_WORKAROUND_4193714)) return; - /* - * Order the mm_cpumask() read after the hardware DVMSync. - */ - dsb(ish); - if (cpumask_empty(mm_cpumask(mm))) - return; - - /* - * Allocate the batch cpumask on first use. Fall back to an immediate - * IPI for this mm in case of failure. - */ - if (!cpumask_available(batch->cpumask) && - !zalloc_cpumask_var(&batch->cpumask, GFP_ATOMIC)) { - sme_do_dvmsync(mm_cpumask(mm)); - return; - } - - cpumask_or(batch->cpumask, batch->cpumask, mm_cpumask(mm)); -} - -static inline void sme_dvmsync_batch(struct arch_tlbflush_unmap_batch *batch) -{ - if (!alternative_has_cap_unlikely(ARM64_WORKAROUND_4193714)) - return; - - if (!cpumask_available(batch->cpumask)) - return; - - sme_do_dvmsync(batch->cpumask); - cpumask_clear(batch->cpumask); + sme_do_dvmsync(&sme_active_cpus); } #else @@ -135,11 +107,7 @@ static inline void sme_dvmsync_batch(struct arch_tlbflush_unmap_batch *batch) static inline void sme_dvmsync(struct mm_struct *mm) { } -static inline void sme_dvmsync_add_pending(struct arch_tlbflush_unmap_batch *batch, - struct mm_struct *mm) -{ -} -static inline void sme_dvmsync_batch(struct arch_tlbflush_unmap_batch *batch) +static inline void sme_dvmsync_batch(void) { } @@ -285,11 +253,11 @@ static inline void __tlbi_sync_s1ish(struct mm_struct *mm) sme_dvmsync(mm); } -static inline void __tlbi_sync_s1ish_batch(struct arch_tlbflush_unmap_batch *batch) +static inline void __tlbi_sync_s1ish_batch(void) { dsb(ish); __repeat_tlbi_sync(vale1is, 0); - sme_dvmsync_batch(batch); + sme_dvmsync_batch(); } static inline void __tlbi_sync_s1ish_kernel(void) @@ -434,7 +402,7 @@ static inline bool arch_tlbbatch_should_defer(struct mm_struct *mm) */ static inline void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch) { - __tlbi_sync_s1ish_batch(batch); + __tlbi_sync_s1ish_batch(); } /* @@ -722,7 +690,6 @@ static inline void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *b __flush_tlb_range(&vma, start, end, PAGE_SIZE, 3, TLBF_NOWALKCACHE | TLBF_NOSYNC); - sme_dvmsync_add_pending(batch, mm); } static inline bool __pte_flags_need_flush(ptval_t oldval, ptval_t newval) diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c index 5891f92c2035..681aa2bbc399 100644 --- a/arch/arm64/kernel/acpi.c +++ b/arch/arm64/kernel/acpi.c @@ -448,12 +448,14 @@ int acpi_map_cpu(acpi_handle handle, phys_cpuid_t physid, u32 apci_id, return *pcpu; } + set_cpu_present(*pcpu, true); return 0; } EXPORT_SYMBOL(acpi_map_cpu); int acpi_unmap_cpu(int cpu) { + set_cpu_present(cpu, false); return 0; } EXPORT_SYMBOL(acpi_unmap_cpu); diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 25dc5afe9ba0..e7f1682a3059 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -1355,6 +1355,7 @@ void do_sve_acc(unsigned long esr, struct pt_regs *regs) * SME/CME erratum handling. */ static cpumask_t sme_dvmsync_cpus; +cpumask_t sme_active_cpus; /* * These helpers are only called from non-preemptible contexts, so @@ -1368,13 +1369,15 @@ void sme_set_active(void) return; cpumask_set_cpu(cpu, mm_cpumask(current->mm)); + cpumask_set_cpu(cpu, &sme_active_cpus); /* * A subsequent (post ERET) SME access may use a stale address * translation. On C1-Pro, a TLBI+DSB on a different CPU will wait for - * the completion of cpumask_set_cpu() above as it appears in program - * order before the SME access. The post-TLBI+DSB read of mm_cpumask() - * will lead to the IPI being issued. + * the completion of the cpumask_set_cpu() operations above as they + * appear in program order before the SME access. The post-TLBI+DSB + * read of mm_cpumask() or sme_active_cpus will lead to the IPI being + * issued. * * https://lore.kernel.org/r/ablEXwhfKyJW1i7l@J2N7QTR9R3 */ @@ -1392,6 +1395,7 @@ void sme_clear_active(void) * completed on entering EL1. */ cpumask_clear_cpu(cpu, mm_cpumask(current->mm)); + cpumask_clear_cpu(cpu, &sme_active_cpus); } static void sme_dvmsync_ipi(void *unused) diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 033643cd4e5e..581f80e9b9b7 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -341,41 +341,8 @@ void flush_thread(void) flush_gcs(); } -#ifdef CONFIG_ARM64_ERRATUM_4193714 - -static void arch_dup_tlbbatch_mask(struct task_struct *dst) -{ - /* - * Clear the inherited cpumask with memset() to cover both cases where - * cpumask_var_t is a pointer or an array. It will be allocated lazily - * in sme_dvmsync_add_pending() if CPUMASK_OFFSTACK=y. - */ - if (alternative_has_cap_unlikely(ARM64_WORKAROUND_4193714)) - memset(&dst->tlb_ubc.arch.cpumask, 0, - sizeof(dst->tlb_ubc.arch.cpumask)); -} - -static void arch_release_tlbbatch_mask(struct task_struct *tsk) -{ - if (alternative_has_cap_unlikely(ARM64_WORKAROUND_4193714)) - free_cpumask_var(tsk->tlb_ubc.arch.cpumask); -} - -#else - -static void arch_dup_tlbbatch_mask(struct task_struct *dst) -{ -} - -static void arch_release_tlbbatch_mask(struct task_struct *tsk) -{ -} - -#endif /* CONFIG_ARM64_ERRATUM_4193714 */ - void arch_release_task_struct(struct task_struct *tsk) { - arch_release_tlbbatch_mask(tsk); fpsimd_release_task(tsk); } @@ -391,8 +358,6 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) *dst = *src; - arch_dup_tlbbatch_mask(dst); - /* * Drop stale reference to src's sve_state and convert dst to * non-streaming FPSIMD mode. diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index d46022f72075..cdcdd160e5b6 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -535,23 +535,13 @@ void arch_unregister_cpu(int cpu) { acpi_handle acpi_handle = acpi_get_processor_handle(cpu); struct cpu *c = &per_cpu(cpu_devices, cpu); - acpi_status status; unsigned long long sta; - - if (!acpi_handle) { - pr_err_once("Removing a CPU without associated ACPI handle\n"); - return; - } + acpi_status status; status = acpi_evaluate_integer(acpi_handle, "_STA", NULL, &sta); - if (ACPI_FAILURE(status)) - return; - - /* For now do not allow anything that looks like physical CPU HP */ - if (cpu_present(cpu) && !(sta & ACPI_STA_DEVICE_PRESENT)) { + if (!ACPI_FAILURE(status) && + cpu_present(cpu) && !(sta & ACPI_STA_DEVICE_PRESENT)) pr_err_once("Changing CPU present bit is not supported\n"); - return; - } unregister_cpu(c); } @@ -566,6 +556,11 @@ struct acpi_madt_generic_interrupt *acpi_cpu_get_madt_gicc(int cpu) } EXPORT_SYMBOL_GPL(acpi_cpu_get_madt_gicc); +static bool acpi_cpu_is_present(int cpu) +{ + return acpi_cpu_get_madt_gicc(cpu)->flags & ACPI_MADT_ENABLED; +} + /* * acpi_map_gic_cpu_interface - parse processor MADT entry * @@ -670,6 +665,10 @@ static void __init acpi_parse_and_init_cpus(void) early_map_cpu_to_node(i, acpi_numa_get_nid(i)); } #else +static bool acpi_cpu_is_present(int cpu) +{ + return false; +} #define acpi_parse_and_init_cpus(...) do { } while (0) #endif @@ -814,7 +813,8 @@ void __init smp_prepare_cpus(unsigned int max_cpus) if (err) continue; - set_cpu_present(cpu, true); + if (acpi_disabled || acpi_cpu_is_present(cpu)) + set_cpu_present(cpu, true); numa_store_cpu_info(cpu); } } diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index f2be501468ce..a25d8beacc83 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -1515,7 +1515,13 @@ static void unmap_hotplug_pmd_range(pud_t *pudp, unsigned long addr, if (free_mapped) { /* CONT blocks are not supported in the vmemmap */ WARN_ON(pmd_cont(pmd)); - flush_tlb_kernel_range(addr, addr + PMD_SIZE); + /* + * Invalidating a block entry requires just + * a single overlapping TLB invalidation, + * so limit the range of the flush to a single + * page. + */ + flush_tlb_kernel_range(addr, addr + PAGE_SIZE); free_hotplug_page_range(pmd_page(pmd), PMD_SIZE, altmap); } @@ -1545,7 +1551,8 @@ static void unmap_hotplug_pud_range(p4d_t *p4dp, unsigned long addr, if (pud_leaf(pud)) { pud_clear(pudp); if (free_mapped) { - flush_tlb_kernel_range(addr, addr + PUD_SIZE); + /* See comment in unmap_hotplug_pmd_range(). */ + flush_tlb_kernel_range(addr, addr + PAGE_SIZE); free_hotplug_page_range(pud_page(pud), PUD_SIZE, altmap); } diff --git a/arch/arm64/tools/sysreg b/arch/arm64/tools/sysreg index bc1788b1662b..7cb61aca3797 100644 --- a/arch/arm64/tools/sysreg +++ b/arch/arm64/tools/sysreg @@ -1806,7 +1806,7 @@ Res0 15:8 UnsignedEnum 7:4 BWE 0b0000 NI 0b0001 FEAT_BWE - 0b0002 FEAT_BWE2 + 0b0010 FEAT_BWE2 EndEnum UnsignedEnum 3:0 STEP 0b0000 NI diff --git a/arch/m68k/coldfire/m523x.c b/arch/m68k/coldfire/m523x.c index 11d7423ef646..ec04c32bb03c 100644 --- a/arch/m68k/coldfire/m523x.c +++ b/arch/m68k/coldfire/m523x.c @@ -79,7 +79,7 @@ static void __init m523x_i2c_init(void) static void __init m523x_fec_init(void) { /* Set multi-function pins to ethernet use */ - mcf_write8(read8(MCFGPIO_PAR_FECI2C) | 0xf0, MCFGPIO_PAR_FECI2C); + mcf_write8(mcf_read8(MCFGPIO_PAR_FECI2C) | 0xf0, MCFGPIO_PAR_FECI2C); } /***************************************************************************/ diff --git a/arch/m68k/coldfire/m528x.c b/arch/m68k/coldfire/m528x.c index b244c9ba40a7..3383b1ba106a 100644 --- a/arch/m68k/coldfire/m528x.c +++ b/arch/m68k/coldfire/m528x.c @@ -113,11 +113,11 @@ void wildfiremod_halt(void) mcf_write16(read16(MCFGPIO_PEPAR) & ~(1 << (5 * 2)), MCFGPIO_PEPAR); /* Make portE.5 an output */ - mcf_write8(read8(MCFGPIO_PDDR_E) | (1 << 5), MCFGPIO_PDDR_E); + mcf_write8(mcf_read8(MCFGPIO_PDDR_E) | (1 << 5), MCFGPIO_PDDR_E); /* Now toggle portE.5 from low to high */ - mcf_write8(read8(MCFGPIO_PODR_E) & ~(1 << 5), MCFGPIO_PODR_E); - mcf_write8(read8(MCFGPIO_PODR_E) | (1 << 5), MCFGPIO_PODR_E); + mcf_write8(mcf_read8(MCFGPIO_PODR_E) & ~(1 << 5), MCFGPIO_PODR_E); + mcf_write8(mcf_read8(MCFGPIO_PODR_E) | (1 << 5), MCFGPIO_PODR_E); printk(KERN_EMERG "Failed to hibernate. Halting!\n"); } diff --git a/arch/riscv/Kconfig.socs b/arch/riscv/Kconfig.socs index c174ac0ec46b..429e07589306 100644 --- a/arch/riscv/Kconfig.socs +++ b/arch/riscv/Kconfig.socs @@ -84,6 +84,12 @@ config ARCH_THEAD help This enables support for the RISC-V based T-HEAD SoCs. +config ARCH_ULTRARISC + bool "UltraRISC RISC-V SoCs" + help + This enables support for UltraRISC SoC platform hardware, + including boards based on the UR-DP1000. + config ARCH_VIRT bool "QEMU Virt Machine" select POWER_RESET diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig index 74ba5acc12a4..ed605b5e3162 100644 --- a/arch/riscv/configs/defconfig +++ b/arch/riscv/configs/defconfig @@ -33,6 +33,7 @@ CONFIG_SOC_STARFIVE=y CONFIG_ARCH_SUNXI=y CONFIG_ARCH_TENSTORRENT=y CONFIG_ARCH_THEAD=y +CONFIG_ARCH_ULTRARISC=y CONFIG_ARCH_VIRT=y CONFIG_ARCH_CANAAN=y CONFIG_SMP=y diff --git a/arch/riscv/kernel/machine_kexec.c b/arch/riscv/kernel/machine_kexec.c index 2306ce3e5f22..738df176ff6f 100644 --- a/arch/riscv/kernel/machine_kexec.c +++ b/arch/riscv/kernel/machine_kexec.c @@ -41,6 +41,9 @@ machine_kexec_prepare(struct kimage *image) if (image->segment[i].memsz <= sizeof(fdt)) continue; + if (!image->segment[i].buf) + continue; + if (image->file_mode) memcpy(&fdt, image->segment[i].buf, sizeof(fdt)); else if (copy_from_user(&fdt, image->segment[i].buf, sizeof(fdt))) diff --git a/arch/s390/kernel/diag/diag310.c b/arch/s390/kernel/diag/diag310.c index f411562aa7f6..c68ec9d28513 100644 --- a/arch/s390/kernel/diag/diag310.c +++ b/arch/s390/kernel/diag/diag310.c @@ -190,17 +190,18 @@ static int memtop_get_stride_len(unsigned long *res) static int memtop_get_page_count(unsigned long *res, unsigned long level) { static unsigned long memtop_pages[DIAG310_LEVELMAX]; - unsigned long pages; + unsigned long pages, idx; int rc; if (level > DIAG310_LEVELMAX || level < DIAG310_LEVELMIN) return -EINVAL; - pages = READ_ONCE(memtop_pages[level - 1]); + idx = array_index_nospec(level - 1, ARRAY_SIZE(memtop_pages)); + pages = READ_ONCE(memtop_pages[idx]); if (!pages) { rc = diag310_get_memtop_size(&pages, level); if (rc) return rc; - WRITE_ONCE(memtop_pages[level - 1], pages); + WRITE_ONCE(memtop_pages[idx], pages); } *res = pages; return 0; diff --git a/arch/s390/kernel/vdso/note.S b/arch/s390/kernel/vdso/note.S index db19d0680a0a..d215781f26b5 100644 --- a/arch/s390/kernel/vdso/note.S +++ b/arch/s390/kernel/vdso/note.S @@ -4,6 +4,7 @@ * Here we can supply some information useful to userland. */ +#include #include #include #include @@ -11,3 +12,5 @@ ELFNOTE_START(Linux, 0, "a") .long LINUX_VERSION_CODE ELFNOTE_END + +BUILD_SALT diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c index 2a222a7e14f4..ef7bfc87758c 100644 --- a/arch/s390/mm/mmap.c +++ b/arch/s390/mm/mmap.c @@ -64,7 +64,7 @@ static inline unsigned long mmap_base(unsigned long rnd, return PAGE_ALIGN(STACK_TOP - gap - rnd); } -static int get_align_mask(struct file *filp, unsigned long flags) +static unsigned long get_align_mask(struct file *filp, unsigned long flags) { if (filp && is_file_hugepages(filp)) return huge_page_mask_align(filp); diff --git a/arch/x86/events/amd/brs.c b/arch/x86/events/amd/brs.c index 06f35a6b58a5..dc564688f3d7 100644 --- a/arch/x86/events/amd/brs.c +++ b/arch/x86/events/amd/brs.c @@ -259,13 +259,13 @@ void amd_brs_disable_all(void) amd_brs_disable(); } -static bool amd_brs_match_plm(struct perf_event *event, u64 to) +static bool amd_brs_match_plm(struct perf_event *event, u64 from, u64 to) { int type = event->attr.branch_sample_type; int plm_k = PERF_SAMPLE_BRANCH_KERNEL | PERF_SAMPLE_BRANCH_HV; int plm_u = PERF_SAMPLE_BRANCH_USER; - if (!(type & plm_k) && kernel_ip(to)) + if (!(type & plm_k) && (kernel_ip(to) || kernel_ip(from))) return 0; if (!(type & plm_u) && !kernel_ip(to)) @@ -338,11 +338,11 @@ void amd_brs_drain(void) */ to = (u64)(((s64)to << shift) >> shift); - if (!amd_brs_match_plm(event, to)) - continue; - rdmsrq(brs_from(brs_idx), from); + if (!amd_brs_match_plm(event, from, to)) + continue; + perf_clear_branch_entry_bitfields(br+nr); br[nr].from = from; diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c index 6569048a8c1c..a787409f5a62 100644 --- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -754,13 +754,11 @@ static void amd_pmu_enable_event(struct perf_event *event) x86_pmu_enable_event(event); } -static void amd_pmu_enable_all(int added) +static void __amd_pmu_enable_all(void) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); int idx; - amd_brs_enable_all(); - for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) { /* only activate events which are marked as active */ if (!test_bit(idx, cpuc->active_mask)) @@ -775,6 +773,12 @@ static void amd_pmu_enable_all(int added) } } +static void amd_pmu_enable_all(int added) +{ + amd_brs_enable_all(); + __amd_pmu_enable_all(); +} + static void amd_pmu_v2_enable_event(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; @@ -1561,7 +1565,7 @@ static inline void amd_pmu_reload_virt(void) * set global enable bits once again */ amd_pmu_v2_disable_all(); - amd_pmu_enable_all(0); + __amd_pmu_enable_all(); amd_pmu_v2_enable_all(0); return; } diff --git a/arch/x86/events/amd/lbr.c b/arch/x86/events/amd/lbr.c index 5b437dc8e4ce..9d9c961989d5 100644 --- a/arch/x86/events/amd/lbr.c +++ b/arch/x86/events/amd/lbr.c @@ -127,7 +127,8 @@ static void amd_pmu_lbr_filter(void) } /* If type does not correspond, then discard */ - if (type == X86_BR_NONE || (br_sel & type) != type) { + if (type == X86_BR_NONE || (br_sel & type) != type || + (!(br_sel & X86_BR_KERNEL) && kernel_ip(cpuc->lbr_entries[i].from))) { cpuc->lbr_entries[i].from = 0; /* mark invalid */ compress = true; } diff --git a/arch/x86/video/video-common.c b/arch/x86/video/video-common.c index 152789f00fcd..8ed82fff7638 100644 --- a/arch/x86/video/video-common.c +++ b/arch/x86/video/video-common.c @@ -43,21 +43,26 @@ bool video_is_primary_device(struct device *dev) if (!pci_is_display(pdev)) return false; - if (pdev == vga_default_device()) - return true; - #ifdef CONFIG_SCREEN_INFO numres = screen_info_resources(si, res, ARRAY_SIZE(res)); - for (i = 0; i < numres; ++i) { - if (!(res[i].flags & IORESOURCE_MEM)) - continue; + if (numres > 0) { + for (i = 0; i < numres; ++i) { + if (!(res[i].flags & IORESOURCE_MEM)) + continue; - if (pci_find_resource(pdev, &res[i])) - return true; + if (pci_find_resource(pdev, &res[i])) + return true; + } + + return false; } #endif - return false; + /* + * No framebuffer was set up by the firmware/bootloader, so fall back + * to the default VGA device. + */ + return pdev == vga_default_device(); } EXPORT_SYMBOL(video_is_primary_device); diff --git a/arch/x86/virt/svm/sev.c b/arch/x86/virt/svm/sev.c index 8bcdce98f6dc..cff285d8ad8e 100644 --- a/arch/x86/virt/svm/sev.c +++ b/arch/x86/virt/svm/sev.c @@ -536,6 +536,8 @@ int snp_prepare(void) goto unlock; } + wbinvd_on_all_cpus(); + /* * MtrrFixDramModEn is not shared between threads on a core, * therefore it must be set on all CPUs prior to enabling SNP. diff --git a/block/blk-mq.c b/block/blk-mq.c index 88cb5acc4f39..2c850330a32b 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -5218,6 +5218,7 @@ static int blk_hctx_poll(struct request_queue *q, struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob, unsigned int flags) { int ret; + unsigned long timeout = jiffies + 2; do { ret = q->mq_ops->poll(hctx, iob); @@ -5228,7 +5229,7 @@ static int blk_hctx_poll(struct request_queue *q, struct blk_mq_hw_ctx *hctx, if (ret < 0 || (flags & BLK_POLL_ONESHOT)) break; cpu_relax(); - } while (!need_resched()); + } while (!need_resched() && time_before(jiffies, timeout)); return 0; } diff --git a/block/blk-wbt.c b/block/blk-wbt.c index dcc2438ca16d..953d400fd013 100644 --- a/block/blk-wbt.c +++ b/block/blk-wbt.c @@ -813,6 +813,21 @@ static void wbt_queue_depth_changed(struct rq_qos *rqos) wbt_update_limits(RQWB(rqos)); } +static bool wbt_set_lat_changed(struct request_queue *q, u64 val) +{ + struct rq_qos *rqos = wbt_rq_qos(q); + struct rq_wb *rwb; + + if (!rqos) + return true; + + rwb = RQWB(rqos); + if (rwb->min_lat_nsec != val) + return true; + + return rwb_enabled(rwb) != !!val; +} + static void wbt_exit(struct rq_qos *rqos) { struct rq_wb *rwb = RQWB(rqos); @@ -1005,8 +1020,12 @@ int wbt_set_lat(struct gendisk *disk, s64 val) else if (val >= 0) val *= 1000ULL; - if (wbt_get_min_lat(q) == val) + mutex_lock(&disk->rqos_state_mutex); + if (!wbt_set_lat_changed(q, val)) { + mutex_unlock(&disk->rqos_state_mutex); goto out; + } + mutex_unlock(&disk->rqos_state_mutex); blk_mq_quiesce_queue(q); diff --git a/block/blk-zoned.c b/block/blk-zoned.c index bea817f3de56..ca30caec838e 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -1923,11 +1923,20 @@ static int disk_alloc_zone_resources(struct gendisk *disk, if (!disk->zone_wplugs_pool) goto free_hash; - disk->zone_wplugs_wq = - alloc_workqueue("%s_zwplugs", WQ_MEM_RECLAIM | WQ_HIGHPRI | WQ_PERCPU, - pool_size, disk->disk_name); - if (!disk->zone_wplugs_wq) - goto destroy_pool; + /* + * We may already have a zone write plug workqueue as this function may + * be called after disk_free_zone_resources(), which does not destroy + * the workqueue (the zone write plugs workqueue is destroyed at + * disk_release() time). + */ + if (!disk->zone_wplugs_wq) { + disk->zone_wplugs_wq = + alloc_workqueue("%s_zwplugs", + WQ_MEM_RECLAIM | WQ_HIGHPRI | WQ_PERCPU, + pool_size, disk->disk_name); + if (!disk->zone_wplugs_wq) + goto destroy_pool; + } disk->zone_wplugs_worker = kthread_create(disk_zone_wplugs_worker, disk, @@ -1935,15 +1944,12 @@ static int disk_alloc_zone_resources(struct gendisk *disk, if (IS_ERR(disk->zone_wplugs_worker)) { ret = PTR_ERR(disk->zone_wplugs_worker); disk->zone_wplugs_worker = NULL; - goto destroy_wq; + goto destroy_pool; } wake_up_process(disk->zone_wplugs_worker); return 0; -destroy_wq: - destroy_workqueue(disk->zone_wplugs_wq); - disk->zone_wplugs_wq = NULL; destroy_pool: mempool_destroy(disk->zone_wplugs_pool); disk->zone_wplugs_pool = NULL; @@ -1999,7 +2005,7 @@ static void disk_set_zones_cond_array(struct gendisk *disk, u8 *zones_cond) kfree_rcu_mightsleep(zones_cond); } -void disk_free_zone_resources(struct gendisk *disk) +static void disk_free_zone_resources(struct gendisk *disk) { if (disk->zone_wplugs_worker) { kthread_stop(disk->zone_wplugs_worker); @@ -2007,10 +2013,8 @@ void disk_free_zone_resources(struct gendisk *disk) } WARN_ON_ONCE(!list_empty(&disk->zone_wplugs_list)); - if (disk->zone_wplugs_wq) { - destroy_workqueue(disk->zone_wplugs_wq); - disk->zone_wplugs_wq = NULL; - } + if (disk->zone_wplugs_wq) + drain_workqueue(disk->zone_wplugs_wq); disk_destroy_zone_wplugs_hash_table(disk); @@ -2020,6 +2024,16 @@ void disk_free_zone_resources(struct gendisk *disk) disk->nr_zones = 0; } +void disk_release_zone_resources(struct gendisk *disk) +{ + if (disk->zone_wplugs_wq) { + destroy_workqueue(disk->zone_wplugs_wq); + disk->zone_wplugs_wq = NULL; + } + + disk_free_zone_resources(disk); +} + struct blk_revalidate_zone_args { struct gendisk *disk; u8 *zones_cond; diff --git a/block/blk.h b/block/blk.h index 25af8ac5ef0f..fb95d3c58950 100644 --- a/block/blk.h +++ b/block/blk.h @@ -528,7 +528,7 @@ static inline void ioc_clear_queue(struct request_queue *q) #ifdef CONFIG_BLK_DEV_ZONED void disk_init_zone_resources(struct gendisk *disk); -void disk_free_zone_resources(struct gendisk *disk); +void disk_release_zone_resources(struct gendisk *disk); static inline bool bio_zone_write_plugging(struct bio *bio) { return bio_flagged(bio, BIO_ZONE_WRITE_PLUGGING); @@ -581,7 +581,7 @@ int blkdev_zone_mgmt_ioctl(struct block_device *bdev, blk_mode_t mode, static inline void disk_init_zone_resources(struct gendisk *disk) { } -static inline void disk_free_zone_resources(struct gendisk *disk) +static inline void disk_release_zone_resources(struct gendisk *disk) { } static inline bool bio_zone_write_plugging(struct bio *bio) diff --git a/block/genhd.c b/block/genhd.c index f84b6a355b57..df2c3c69b467 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -407,10 +407,6 @@ static void add_disk_final(struct gendisk *disk) struct device *ddev = disk_to_dev(disk); if (!(disk->flags & GENHD_FL_HIDDEN)) { - /* Make sure the first partition scan will be proceed */ - if (get_capacity(disk) && disk_has_partscan(disk)) - set_bit(GD_NEED_PART_SCAN, &disk->state); - bdev_add(disk->part0, ddev->devt); if (get_capacity(disk)) disk_scan_partitions(disk, BLK_OPEN_READ); @@ -1300,7 +1296,7 @@ static void disk_release(struct device *dev) disk_release_events(disk); kfree(disk->random); - disk_free_zone_resources(disk); + disk_release_zone_resources(disk); xa_destroy(&disk->part_tbl); kobject_put(&disk->queue_kobj); diff --git a/drivers/accel/amdxdna/aie2_ctx.c b/drivers/accel/amdxdna/aie2_ctx.c index 54486960cbf5..101f324ee178 100644 --- a/drivers/accel/amdxdna/aie2_ctx.c +++ b/drivers/accel/amdxdna/aie2_ctx.c @@ -875,7 +875,7 @@ static int aie2_hwctx_cu_config(struct amdxdna_hwctx *hwctx, void *buf, u32 size if (!hwctx->cus) return -ENOMEM; - ret = amdxdna_pm_resume_get_locked(xdna); + ret = amdxdna_pm_resume_get(xdna); if (ret) goto free_cus; @@ -900,13 +900,16 @@ static int aie2_hwctx_cu_config(struct amdxdna_hwctx *hwctx, void *buf, u32 size static void aie2_cmd_wait(struct amdxdna_hwctx *hwctx, u64 seq) { struct dma_fence *out_fence = aie2_cmd_get_out_fence(hwctx, seq); + struct amdxdna_dev *xdna = hwctx->client->xdna; if (!out_fence) { - XDNA_ERR(hwctx->client->xdna, "Failed to get fence"); + XDNA_ERR(xdna, "Failed to get fence"); return; } + mutex_unlock(&xdna->dev_lock); dma_fence_wait_timeout(out_fence, false, MAX_SCHEDULE_TIMEOUT); + mutex_lock(&xdna->dev_lock); dma_fence_put(out_fence); } @@ -1039,7 +1042,7 @@ static int aie2_populate_range(struct amdxdna_gem_obj *abo) found = false; down_write(&xdna->notifier_lock); list_for_each_entry(mapp, &abo->mem.umap_list, node) { - if (mapp->invalid) { + if (mapp->invalid && kref_get_unless_zero(&mapp->refcnt)) { found = true; break; } @@ -1050,11 +1053,9 @@ static int aie2_populate_range(struct amdxdna_gem_obj *abo) up_write(&xdna->notifier_lock); return 0; } - kref_get(&mapp->refcnt); + up_write(&xdna->notifier_lock); - XDNA_DBG(xdna, "populate memory range %lx %lx", - mapp->vma->vm_start, mapp->vma->vm_end); mm = mapp->notifier.mm; if (!mmget_not_zero(mm)) { amdxdna_umap_put(mapp); @@ -1221,10 +1222,6 @@ int aie2_hwctx_heap_expand(struct amdxdna_hwctx *hwctx, u64 addr; int ret; - ret = amdxdna_pm_resume_get_locked(xdna); - if (ret) - return ret; - addr = amdxdna_obj_dma_addr(heap); ret = aie2_add_host_buf(xdna->dev_handle, hwctx->fw_ctx_id, addr, heap->mem.size); @@ -1233,7 +1230,5 @@ int aie2_hwctx_heap_expand(struct amdxdna_hwctx *hwctx, hwctx->name, heap->mem.size, ret); } - amdxdna_pm_suspend_put(xdna); - return ret; } diff --git a/drivers/accel/amdxdna/aie2_message.c b/drivers/accel/amdxdna/aie2_message.c index c4b364801cc0..dfe0fbdf066d 100644 --- a/drivers/accel/amdxdna/aie2_message.c +++ b/drivers/accel/amdxdna/aie2_message.c @@ -840,7 +840,7 @@ static struct aie2_exec_msg_ops npu_exec_message_ops = { static int aie2_init_exec_req(void *req, struct amdxdna_gem_obj *cmd_abo, size_t *size, u32 *msg_op) { - struct amdxdna_dev *xdna = cmd_abo->client->xdna; + struct amdxdna_dev *xdna = to_xdna_dev(to_gobj(cmd_abo)->dev); int ret; u32 op; @@ -874,7 +874,7 @@ static int aie2_cmdlist_fill_slot(void *slot, struct amdxdna_gem_obj *cmd_abo, size_t *size, u32 *cmd_op) { - struct amdxdna_dev *xdna = cmd_abo->client->xdna; + struct amdxdna_dev *xdna = to_xdna_dev(to_gobj(cmd_abo)->dev); int ret; u32 op; diff --git a/drivers/accel/amdxdna/amdxdna_ctx.c b/drivers/accel/amdxdna/amdxdna_ctx.c index 855da8c79a1c..8f8df9d04ec5 100644 --- a/drivers/accel/amdxdna/amdxdna_ctx.c +++ b/drivers/accel/amdxdna/amdxdna_ctx.c @@ -310,6 +310,7 @@ int amdxdna_drm_destroy_hwctx_ioctl(struct drm_device *dev, void *data, struct d if (!drm_dev_enter(dev, &idx)) return -ENODEV; + mutex_lock(&xdna->client_lock); mutex_lock(&xdna->dev_lock); hwctx = xa_erase(&client->hwctx_xa, args->handle); if (!hwctx) { @@ -328,6 +329,7 @@ int amdxdna_drm_destroy_hwctx_ioctl(struct drm_device *dev, void *data, struct d XDNA_DBG(xdna, "PID %d destroyed HW context %d", client->pid, args->handle); out: mutex_unlock(&xdna->dev_lock); + mutex_unlock(&xdna->client_lock); drm_dev_exit(idx); return ret; } @@ -382,16 +384,27 @@ int amdxdna_drm_config_hwctx_ioctl(struct drm_device *dev, void *data, struct dr return -EINVAL; } - guard(mutex)(&xdna->dev_lock); + ret = amdxdna_pm_resume_get(xdna); + if (ret) { + XDNA_ERR(xdna, "Resume failed, ret %d", ret); + goto free_buf; + } + + mutex_lock(&xdna->client_lock); + mutex_lock(&xdna->dev_lock); hwctx = xa_load(&client->hwctx_xa, args->handle); if (!hwctx) { XDNA_DBG(xdna, "PID %d failed to get hwctx %d", client->pid, args->handle); ret = -EINVAL; - goto free_buf; + goto unlock; } ret = xdna->dev_info->ops->hwctx_config(hwctx, args->param_type, val, buf, buf_size); +unlock: + mutex_unlock(&xdna->dev_lock); + mutex_unlock(&xdna->client_lock); + amdxdna_pm_suspend_put(xdna); free_buf: kfree(buf); return ret; @@ -412,16 +425,27 @@ int amdxdna_hwctx_sync_debug_bo(struct amdxdna_client *client, u32 debug_bo_hdl) if (!gobj) return -EINVAL; + ret = amdxdna_pm_resume_get(xdna); + if (ret) { + XDNA_ERR(xdna, "Resume failed, ret %d", ret); + goto put_obj; + } + abo = to_xdna_obj(gobj); - guard(mutex)(&xdna->dev_lock); + mutex_lock(&xdna->client_lock); + mutex_lock(&xdna->dev_lock); hwctx = xa_load(&client->hwctx_xa, abo->assigned_hwctx); if (!hwctx) { ret = -EINVAL; - goto put_obj; + goto unlock; } ret = xdna->dev_info->ops->hwctx_sync_debug_bo(hwctx, debug_bo_hdl); +unlock: + mutex_unlock(&xdna->dev_lock); + mutex_unlock(&xdna->client_lock); + amdxdna_pm_suspend_put(xdna); put_obj: drm_gem_object_put(gobj); return ret; @@ -448,9 +472,7 @@ static int amdxdna_hwctx_expand_heap(struct amdxdna_hwctx *hwctx) break; } - mutex_unlock(&client->mm_lock); ret = xdna->dev_info->ops->hwctx_heap_expand(hwctx, heap); - mutex_lock(&client->mm_lock); if (ret) { amdxdna_gem_unpin(heap); drm_gem_object_put(to_gobj(heap)); @@ -469,18 +491,26 @@ int amdxdna_update_heap(struct amdxdna_client *client, struct amdxdna_hwctx *hwc unsigned long hwctx_id; int ret; - guard(mutex)(&client->mm_lock); + ret = amdxdna_pm_resume_get_locked(client->xdna); + if (ret) + return ret; - if (hwctx) - return amdxdna_hwctx_expand_heap(hwctx); + mutex_lock(&client->mm_lock); - amdxdna_for_each_hwctx(client, hwctx_id, hwctx) { + if (hwctx) { ret = amdxdna_hwctx_expand_heap(hwctx); - if (ret) - return ret; + } else { + amdxdna_for_each_hwctx(client, hwctx_id, hwctx) { + ret = amdxdna_hwctx_expand_heap(hwctx); + if (ret) + break; + } } + mutex_unlock(&client->mm_lock); - return 0; + amdxdna_pm_suspend_put(client->xdna); + + return ret; } static void diff --git a/drivers/accel/amdxdna/amdxdna_gem.c b/drivers/accel/amdxdna/amdxdna_gem.c index 891112c2cddf..4628a2787265 100644 --- a/drivers/accel/amdxdna/amdxdna_gem.c +++ b/drivers/accel/amdxdna/amdxdna_gem.c @@ -198,6 +198,7 @@ amdxdna_gem_destroy_obj(struct amdxdna_gem_obj *abo) */ void *amdxdna_gem_vmap(struct amdxdna_gem_obj *abo) { + struct amdxdna_dev *xdna = to_xdna_dev(to_gobj(abo)->dev); struct iosys_map map = IOSYS_MAP_INIT_VADDR(NULL); int ret; @@ -210,7 +211,7 @@ void *amdxdna_gem_vmap(struct amdxdna_gem_obj *abo) if (!abo->mem.kva) { ret = drm_gem_vmap(to_gobj(abo), &map); if (ret) - XDNA_ERR(abo->client->xdna, "Vmap bo failed, ret %d", ret); + XDNA_ERR(xdna, "Vmap bo failed, ret %d", ret); else abo->mem.kva = map.vaddr; } @@ -254,7 +255,7 @@ static bool amdxdna_hmm_invalidate(struct mmu_interval_notifier *mni, xdna = to_xdna_dev(to_gobj(abo)->dev); XDNA_DBG(xdna, "Invalidating range 0x%lx, 0x%lx, type %d", - mapp->vma->vm_start, mapp->vma->vm_end, abo->type); + mapp->range.start, mapp->range.end, abo->type); if (!mmu_notifier_range_blockable(range)) return false; @@ -284,15 +285,23 @@ static const struct mmu_interval_notifier_ops amdxdna_hmm_ops = { .invalidate = amdxdna_hmm_invalidate, }; +static inline bool compare_range(struct amdxdna_umap *mapp, + struct mm_struct *mm, + unsigned long start, unsigned long end) +{ + return (!mapp->unmapped && mapp->notifier.mm == mm && + mapp->range.start == start && mapp->range.end == end); +} + static void amdxdna_hmm_unregister(struct amdxdna_gem_obj *abo, struct vm_area_struct *vma) { struct amdxdna_dev *xdna = to_xdna_dev(to_gobj(abo)->dev); struct amdxdna_umap *mapp; - down_read(&xdna->notifier_lock); + down_write(&xdna->notifier_lock); list_for_each_entry(mapp, &abo->mem.umap_list, node) { - if (!vma || mapp->vma == vma) { + if (!vma || compare_range(mapp, vma->vm_mm, vma->vm_start, vma->vm_end)) { if (!mapp->unmapped) { queue_work(xdna->notifier_wq, &mapp->hmm_unreg_work); mapp->unmapped = true; @@ -301,19 +310,16 @@ static void amdxdna_hmm_unregister(struct amdxdna_gem_obj *abo, break; } } - up_read(&xdna->notifier_lock); + up_write(&xdna->notifier_lock); } static void amdxdna_umap_release(struct kref *ref) { struct amdxdna_umap *mapp = container_of(ref, struct amdxdna_umap, refcnt); struct amdxdna_gem_obj *abo = mapp->abo; - struct vm_area_struct *vma = mapp->vma; struct amdxdna_dev *xdna; mmu_interval_notifier_remove(&mapp->notifier); - if (is_import_bo(abo) && vma->vm_file && vma->vm_file->f_mapping) - mapping_clear_unevictable(vma->vm_file->f_mapping); xdna = to_xdna_dev(to_gobj(mapp->abo)->dev); down_write(&xdna->notifier_lock); @@ -346,15 +352,30 @@ static int amdxdna_hmm_register(struct amdxdna_gem_obj *abo, unsigned long len = vma->vm_end - vma->vm_start; unsigned long addr = vma->vm_start; struct amdxdna_umap *mapp; - u32 nr_pages; + unsigned long nr_pages; int ret; - if (!amdxdna_pasid_on(abo->client)) { + /* + * When PASID is off, amdxdna_gem_obj_open() called amdxdna_dma_map_bo() + * and mem.dma_addr is valid; use the DMA address directly and skip HMM. + * Avoid dereferencing abo->client which may be NULL (cleared in close()) + * while internal kernel references are still held. + */ + if (abo->mem.dma_addr != AMDXDNA_INVALID_ADDR) { /* Need to set uva for heap uva validation */ abo->mem.uva = addr; return 0; } + down_read(&xdna->notifier_lock); + list_for_each_entry(mapp, &abo->mem.umap_list, node) { + if (compare_range(mapp, current->mm, addr, addr + len)) { + up_read(&xdna->notifier_lock); + return 0; + } + } + up_read(&xdna->notifier_lock); + mapp = kzalloc_obj(*mapp); if (!mapp) return -ENOMEM; @@ -380,13 +401,10 @@ static int amdxdna_hmm_register(struct amdxdna_gem_obj *abo, mapp->range.start = vma->vm_start; mapp->range.end = vma->vm_end; mapp->range.default_flags = HMM_PFN_REQ_FAULT; - mapp->vma = vma; mapp->abo = abo; kref_init(&mapp->refcnt); INIT_WORK(&mapp->hmm_unreg_work, amdxdna_hmm_unreg_work); - if (is_import_bo(abo) && vma->vm_file && vma->vm_file->f_mapping) - mapping_set_unevictable(vma->vm_file->f_mapping); down_write(&xdna->notifier_lock); if (list_empty(&abo->mem.umap_list)) @@ -527,6 +545,7 @@ static int amdxdna_gem_dmabuf_mmap(struct dma_buf *dma_buf, struct vm_area_struc close_vma: vma->vm_ops->close(vma); + return ret; put_obj: drm_gem_object_put(gobj); return ret; @@ -652,8 +671,11 @@ static int amdxdna_gem_obj_open(struct drm_gem_object *gobj, struct drm_file *fi /* No need to set up dma addr mapping in PASID mode. */ if (!amdxdna_pasid_on(abo->client)) { ret = amdxdna_dma_map_bo(xdna, abo); - if (ret) + if (ret) { + abo->open_ref--; + abo->client = NULL; return ret; + } } amdxdna_gem_add_bo_usage(abo); diff --git a/drivers/accel/amdxdna/amdxdna_gem.h b/drivers/accel/amdxdna/amdxdna_gem.h index a3e44c7a2395..1e90e32bf3cd 100644 --- a/drivers/accel/amdxdna/amdxdna_gem.h +++ b/drivers/accel/amdxdna/amdxdna_gem.h @@ -12,7 +12,6 @@ #include "amdxdna_pci_drv.h" struct amdxdna_umap { - struct vm_area_struct *vma; struct mmu_interval_notifier notifier; struct hmm_range range; struct work_struct hmm_unreg_work; @@ -89,12 +88,19 @@ u64 amdxdna_gem_dev_addr(struct amdxdna_gem_obj *abo); static inline u64 amdxdna_dev_bo_offset(struct amdxdna_gem_obj *abo) { - return amdxdna_gem_dev_addr(abo) - abo->client->xdna->dev_info->dev_mem_base; + return amdxdna_gem_dev_addr(abo) - to_xdna_dev(to_gobj(abo)->dev)->dev_info->dev_mem_base; } static inline u64 amdxdna_obj_dma_addr(struct amdxdna_gem_obj *abo) { - return amdxdna_pasid_on(abo->client) ? amdxdna_gem_uva(abo) : abo->mem.dma_addr; + /* + * amdxdna_gem_obj_open() calls amdxdna_dma_map_bo() only when PASID is + * off, leaving mem.dma_addr at AMDXDNA_INVALID_ADDR when PASID is on. + * Avoid dereferencing abo->client, which is cleared to NULL by + * amdxdna_gem_obj_close() while internal kernel references remain. + */ + return (abo->mem.dma_addr != AMDXDNA_INVALID_ADDR) ? + abo->mem.dma_addr : amdxdna_gem_uva(abo); } void amdxdna_umap_put(struct amdxdna_umap *mapp); diff --git a/drivers/accel/amdxdna/amdxdna_pci_drv.c b/drivers/accel/amdxdna/amdxdna_pci_drv.c index e94d8290a807..bb339e641416 100644 --- a/drivers/accel/amdxdna/amdxdna_pci_drv.c +++ b/drivers/accel/amdxdna/amdxdna_pci_drv.c @@ -109,11 +109,16 @@ static int amdxdna_drm_open(struct drm_device *ddev, struct drm_file *filp) { struct amdxdna_dev *xdna = to_xdna_dev(ddev); struct amdxdna_client *client; + int ret; client = kzalloc_obj(*client); if (!client) return -ENOMEM; + ret = init_srcu_struct(&client->hwctx_srcu); + if (ret) + goto free_client; + client->pid = pid_nr(rcu_access_pointer(filp->pid)); client->xdna = xdna; client->pasid = IOMMU_PASID_INVALID; @@ -125,13 +130,12 @@ static int amdxdna_drm_open(struct drm_device *ddev, struct drm_file *filp) XDNA_WARN(xdna, "PASID not available for pid %d", client->pid); if (!amdxdna_use_carveout(xdna)) { XDNA_ERR(xdna, "PASID unavailable and carveout not configured"); - kfree(client); - return -EINVAL; + ret = -EINVAL; + goto cleanup_srcu; } } } mmgrab(client->mm); - init_srcu_struct(&client->hwctx_srcu); xa_init_flags(&client->hwctx_xa, XA_FLAGS_ALLOC); xa_init_flags(&client->dev_heap_xa, XA_FLAGS_ALLOC); drm_mm_init(&client->dev_heap_mm, xdna->dev_info->dev_mem_base, @@ -149,6 +153,12 @@ static int amdxdna_drm_open(struct drm_device *ddev, struct drm_file *filp) XDNA_DBG(xdna, "pid %d opened", client->pid); return 0; + +cleanup_srcu: + cleanup_srcu_struct(&client->hwctx_srcu); +free_client: + kfree(client); + return ret; } static void amdxdna_client_cleanup(struct amdxdna_client *client) @@ -373,7 +383,10 @@ static int amdxdna_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (ret) return ret; - drmm_mutex_init(ddev, &xdna->dev_lock); + ret = drmm_mutex_init(ddev, &xdna->dev_lock); + if (ret) + return ret; + init_rwsem(&xdna->notifier_lock); INIT_LIST_HEAD(&xdna->client_list); pci_set_drvdata(pdev, xdna); diff --git a/drivers/android/binder.c b/drivers/android/binder.c index ec0ab4f28530..8f2ef1bd539f 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -1658,7 +1658,20 @@ static void binder_txn_latency_free(struct binder_transaction *t) static void binder_free_transaction(struct binder_transaction *t) { - struct binder_proc *target_proc = t->to_proc; + struct binder_thread *target_thread; + struct binder_proc *target_proc; + + spin_lock(&t->lock); + target_proc = t->to_proc; + target_thread = t->to_thread; + /* + * Pin target_thread to keep target_proc alive. Undelivered + * transactions with !target_thread are safe, as target_proc + * can only be the current context there. + */ + if (target_thread) + atomic_inc(&target_thread->tmp_ref); + spin_unlock(&t->lock); if (target_proc) { binder_inner_proc_lock(target_proc); @@ -1672,6 +1685,10 @@ static void binder_free_transaction(struct binder_transaction *t) t->buffer->transaction = NULL; binder_inner_proc_unlock(target_proc); } + + if (target_thread) + binder_thread_dec_tmpref(target_thread); + if (trace_binder_txn_latency_free_enabled()) binder_txn_latency_free(t); /* @@ -3080,6 +3097,7 @@ static void binder_transaction(struct binder_proc *proc, int t_debug_id = atomic_inc_return(&binder_last_id); ktime_t t_start_time = ktime_get(); struct lsm_context lsmctx = { }; + size_t lsmctx_aligned_size = 0; LIST_HEAD(sgc_head); LIST_HEAD(pf_head); const void __user *user_buffer = (const void __user *) @@ -3346,7 +3364,6 @@ static void binder_transaction(struct binder_proc *proc, if (target_node && target_node->txn_security_ctx) { u32 secid; - size_t added_size; security_cred_getsecid(proc->cred, &secid); ret = security_secid_to_secctx(secid, &lsmctx); @@ -3358,9 +3375,9 @@ static void binder_transaction(struct binder_proc *proc, return_error_line = __LINE__; goto err_get_secctx_failed; } - added_size = ALIGN(lsmctx.len, sizeof(u64)); - extra_buffers_size += added_size; - if (extra_buffers_size < added_size) { + lsmctx_aligned_size = ALIGN(lsmctx.len, sizeof(u64)); + extra_buffers_size += lsmctx_aligned_size; + if (extra_buffers_size < lsmctx_aligned_size) { binder_txn_error("%d:%d integer overflow of extra_buffers_size\n", thread->pid, proc->pid); return_error = BR_FAILED_REPLY; @@ -3397,7 +3414,7 @@ static void binder_transaction(struct binder_proc *proc, size_t buf_offset = ALIGN(tr->data_size, sizeof(void *)) + ALIGN(tr->offsets_size, sizeof(void *)) + ALIGN(extra_buffers_size, sizeof(void *)) - - ALIGN(lsmctx.len, sizeof(u64)); + lsmctx_aligned_size; t->security_ctx = t->buffer->user_data + buf_offset; err = binder_alloc_copy_to_buffer(&target_proc->alloc, @@ -3452,7 +3469,7 @@ static void binder_transaction(struct binder_proc *proc, off_end_offset = off_start_offset + tr->offsets_size; sg_buf_offset = ALIGN(off_end_offset, sizeof(void *)); sg_buf_end_offset = sg_buf_offset + extra_buffers_size - - ALIGN(lsmctx.len, sizeof(u64)); + lsmctx_aligned_size; off_min = 0; for (buffer_offset = off_start_offset; buffer_offset < off_end_offset; buffer_offset += sizeof(binder_size_t)) { diff --git a/drivers/android/binder/allocation.rs b/drivers/android/binder/allocation.rs index b7b05e72970a..ea5846e4da16 100644 --- a/drivers/android/binder/allocation.rs +++ b/drivers/android/binder/allocation.rs @@ -259,7 +259,7 @@ fn drop(&mut self) { if let Some(offsets) = info.offsets.clone() { let view = AllocationView::new(self, offsets.start); - for i in offsets.step_by(size_of::()) { + for i in offsets.step_by(size_of::()) { if view.cleanup_object(i).is_err() { pr_warn!("Error cleaning up object at offset {}\n", i) } @@ -420,7 +420,8 @@ pub(crate) fn transfer_binder_object( } fn cleanup_object(&self, index_offset: usize) -> Result { - let offset = self.alloc.read(index_offset)?; + let offset = self.alloc.read::(index_offset)?; + let offset: usize = offset.try_into().map_err(|_| EINVAL)?; let header = self.read::(offset)?; match header.type_ { BINDER_TYPE_WEAK_BINDER | BINDER_TYPE_BINDER => { diff --git a/drivers/android/binder/error.rs b/drivers/android/binder/error.rs index 45d85d4c2815..1296072c35d9 100644 --- a/drivers/android/binder/error.rs +++ b/drivers/android/binder/error.rs @@ -73,20 +73,17 @@ impl fmt::Debug for BinderError { fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { match self.reply { BR_FAILED_REPLY => match self.source.as_ref() { - Some(source) => f - .debug_struct("BR_FAILED_REPLY") - .field("source", source) - .finish(), + Some(source) => source.fmt(f), None => f.pad("BR_FAILED_REPLY"), }, BR_DEAD_REPLY => f.pad("BR_DEAD_REPLY"), BR_FROZEN_REPLY => f.pad("BR_FROZEN_REPLY"), BR_TRANSACTION_PENDING_FROZEN => f.pad("BR_TRANSACTION_PENDING_FROZEN"), BR_TRANSACTION_COMPLETE => f.pad("BR_TRANSACTION_COMPLETE"), - _ => f - .debug_struct("BinderError") - .field("reply", &self.reply) - .finish(), + _ => match self.source.as_ref() { + Some(source) => source.fmt(f), + None => self.reply.fmt(f), + }, } } } diff --git a/drivers/android/binder/freeze.rs b/drivers/android/binder/freeze.rs index 53b60035639a..f4df14568b25 100644 --- a/drivers/android/binder/freeze.rs +++ b/drivers/android/binder/freeze.rs @@ -154,10 +154,17 @@ fn debug_print(&self, m: &SeqFile, prefix: &str, _tprefix: &str) -> Result<()> { } impl FreezeListener { - pub(crate) fn on_process_exit(&self, proc: &Arc) { + /// Called when this freeze listener is cleared abnormally. + /// + /// This occurs either because the process exited or because the process dropped its last + /// refcount on the node ref without explicitly removing the freeze listener first. + /// + /// The returned `KVVec` is just a value that should be dropped outside of the lock. + pub(crate) fn on_process_cleanup(&self, proc: &Process) -> KVVec> { if !self.is_clearing { - self.node.remove_freeze_listener(proc); + return self.node.remove_freeze_listener(proc); } + KVVec::new() } } diff --git a/drivers/android/binder/node.rs b/drivers/android/binder/node.rs index 69f757ff7461..c10148e9069f 100644 --- a/drivers/android/binder/node.rs +++ b/drivers/android/binder/node.rs @@ -682,12 +682,13 @@ pub(crate) fn add_freeze_listener( } } - pub(crate) fn remove_freeze_listener(&self, p: &Arc) { - let _unused_capacity; + pub(crate) fn remove_freeze_listener(&self, p: &Process) -> KVVec> { let mut guard = self.owner.inner.lock(); let inner = self.inner.access_mut(&mut guard); let len = inner.freeze_list.len(); - inner.freeze_list.retain(|proc| !Arc::ptr_eq(proc, p)); + inner + .freeze_list + .retain(|proc| !core::ptr::eq::(&**proc, p)); if len == inner.freeze_list.len() { pr_warn!( "Could not remove freeze listener for {}\n", @@ -695,8 +696,9 @@ pub(crate) fn remove_freeze_listener(&self, p: &Arc) { ); } if inner.freeze_list.is_empty() { - _unused_capacity = mem::take(&mut inner.freeze_list); + return mem::take(&mut inner.freeze_list); } + KVVec::new() } pub(crate) fn freeze_list<'a>(&'a self, guard: &'a ProcessInner) -> &'a [Arc] { diff --git a/drivers/android/binder/process.rs b/drivers/android/binder/process.rs index 96b8440ceac6..cdd1a9079726 100644 --- a/drivers/android/binder/process.rs +++ b/drivers/android/binder/process.rs @@ -900,7 +900,11 @@ pub(crate) fn insert_or_update_handle( pub(crate) fn get_transaction_node(&self, handle: u32) -> BinderResult { // When handle is zero, try to get the context manager. if handle == 0 { - Ok(self.ctx.get_manager_node(true)?) + let node_ref = self.ctx.get_manager_node(true)?; + if core::ptr::eq(self, &*node_ref.node.owner) { + return Err(EINVAL.into()); + } + Ok(node_ref) } else { Ok(self.get_node_from_handle(handle, true)?) } @@ -942,6 +946,8 @@ pub(crate) fn update_ref( // To preserve original binder behaviour, we only fail requests where the manager tries to // increment references on itself. + let _to_free_freeze_listener; + let _to_free_freeze_listener_cleanup; let mut refs = self.node_refs.lock(); if let Some(info) = refs.by_handle.get_mut(&handle) { if info.node_ref().update(inc, strong) { @@ -957,6 +963,14 @@ pub(crate) fn update_ref( unsafe { info.node_ref2().node.remove_node_info(info) }; let id = info.node_ref().node.global_id(); + + if let Some(freeze) = *info.freeze() { + if let Some(fl) = refs.freeze_listeners.remove(&freeze) { + _to_free_freeze_listener_cleanup = fl.on_process_cleanup(&self); + _to_free_freeze_listener = fl; + } + } + refs.by_handle.remove(&handle); refs.by_node.remove(&id); refs.handle_is_present.release_id(handle as usize); @@ -1380,7 +1394,7 @@ fn deferred_release(self: Arc) { // Clean up freeze listeners. let freeze_listeners = take(&mut self.node_refs.lock().freeze_listeners); for listener in freeze_listeners.values() { - listener.on_process_exit(&self); + listener.on_process_cleanup(&self); } drop(freeze_listeners); diff --git a/drivers/android/binder/rust_binder_events.c b/drivers/android/binder/rust_binder_events.c index 488b1470060c..5792aa59cc82 100644 --- a/drivers/android/binder/rust_binder_events.c +++ b/drivers/android/binder/rust_binder_events.c @@ -28,6 +28,9 @@ const char * const binder_command_strings[] = { "BC_DEAD_BINDER_DONE", "BC_TRANSACTION_SG", "BC_REPLY_SG", + "BC_REQUEST_FREEZE_NOTIFICATION", + "BC_CLEAR_FREEZE_NOTIFICATION", + "BC_FREEZE_NOTIFICATION_DONE", }; const char * const binder_return_strings[] = { @@ -51,7 +54,9 @@ const char * const binder_return_strings[] = { "BR_FAILED_REPLY", "BR_FROZEN_REPLY", "BR_ONEWAY_SPAM_SUSPECT", - "BR_TRANSACTION_PENDING_FROZEN" + "BR_TRANSACTION_PENDING_FROZEN", + "BR_FROZEN_BINDER", + "BR_CLEAR_FREEZE_NOTIFICATION_DONE", }; #define CREATE_TRACE_POINTS diff --git a/drivers/android/binder/stats.rs b/drivers/android/binder/stats.rs index ab75e9561cbf..ec81dc7747db 100644 --- a/drivers/android/binder/stats.rs +++ b/drivers/android/binder/stats.rs @@ -8,8 +8,8 @@ use kernel::sync::atomic::{ordering::Relaxed, Atomic}; use kernel::{ioctl::_IOC_NR, seq_file::SeqFile, seq_print}; -const BC_COUNT: usize = _IOC_NR(BC_REPLY_SG) as usize + 1; -const BR_COUNT: usize = _IOC_NR(BR_TRANSACTION_PENDING_FROZEN) as usize + 1; +const BC_COUNT: usize = _IOC_NR(BC_FREEZE_NOTIFICATION_DONE) as usize + 1; +const BR_COUNT: usize = _IOC_NR(BR_CLEAR_FREEZE_NOTIFICATION_DONE) as usize + 1; pub(crate) static GLOBAL_STATS: BinderStats = BinderStats::new(); diff --git a/drivers/android/binder/thread.rs b/drivers/android/binder/thread.rs index 97d5f31e8fe3..3b8520813941 100644 --- a/drivers/android/binder/thread.rs +++ b/drivers/android/binder/thread.rs @@ -495,9 +495,16 @@ pub(crate) fn debug_print(self: &Arc, m: &SeqFile, print_all: bool) -> Res Ok(()) } + pub(crate) fn clear_extended_error(&self, debug_id: usize) { + self.inner.lock().extended_error = ExtendedError::new(debug_id as u32, BR_OK, 0); + } + pub(crate) fn get_extended_error(&self, data: UserSlice) -> Result { let mut writer = data.writer(); - let ee = self.inner.lock().extended_error; + let mut inner = self.inner.lock(); + let ee = inner.extended_error; + inner.extended_error = ExtendedError::new(0, BR_OK, 0); + drop(inner); writer.write(&ee)?; Ok(()) } @@ -1109,7 +1116,10 @@ fn unwind_transaction_stack(self: &Arc) { inner.pop_transaction_to_reply(thread.as_ref()) } { let reply = Err(BR_DEAD_REPLY); - if !transaction.from.deliver_single_reply(reply, &transaction) { + if !transaction + .from + .deliver_single_reply(reply, &transaction, None) + { break; } @@ -1121,8 +1131,9 @@ pub(crate) fn deliver_reply( &self, reply: Result, u32>, transaction: &DArc, + extended_error: Option, ) { - if self.deliver_single_reply(reply, transaction) { + if self.deliver_single_reply(reply, transaction, extended_error) { transaction.from.unwind_transaction_stack(); } } @@ -1136,6 +1147,7 @@ fn deliver_single_reply( &self, reply: Result, u32>, transaction: &DArc, + extended_error: Option, ) -> bool { if let Ok(transaction) = &reply { crate::trace::trace_transaction(true, transaction, Some(&self.task)); @@ -1152,6 +1164,12 @@ fn deliver_single_reply( return true; } + if let Some(ee) = extended_error { + if inner.extended_error.command == BR_OK { + inner.extended_error = ee; + } + } + match reply { Ok(work) => { inner.push_work(work); @@ -1222,6 +1240,9 @@ fn read_transaction_info( info.buffers_size = td.buffers_size as usize; // SAFETY: Above `read` call initializes all bytes, so this union read is ok. info.target_handle = unsafe { td.transaction_data.target.handle }; + + info.debug_id = super::next_debug_id(); + Ok(()) } @@ -1230,6 +1251,8 @@ fn transaction(self: &Arc, cmd: u32, reader: &mut UserSliceReader) -> Resu let mut info = TransactionInfo::zeroed(); self.read_transaction_info(cmd, reader, &mut info)?; + self.clear_extended_error(info.debug_id); + let ret = if info.is_reply { self.reply_inner(&mut info) } else if info.is_oneway() { @@ -1239,23 +1262,21 @@ fn transaction(self: &Arc, cmd: u32, reader: &mut UserSliceReader) -> Resu }; if let Err(err) = ret { + self.push_return_work(err.reply); if err.reply != BR_TRANSACTION_COMPLETE { info.reply = err.reply; - } + if let Some(source) = &err.source { + info.errno = source.to_errno(); - self.push_return_work(err.reply); - if let Some(source) = &err.source { - info.errno = source.to_errno(); - info.reply = err.reply; - - { - let mut ee = self.inner.lock().extended_error; - ee.command = err.reply; - ee.param = source.to_errno(); + { + let mut inner = self.inner.lock(); + inner.extended_error = + ExtendedError::new(info.debug_id as u32, err.reply, source.to_errno()); + } } pr_warn!( - "{}:{} transaction to {} failed: {source:?}", + "{}:{} transaction to {} failed: {err:?}", info.from_pid, info.from_tid, info.to_pid @@ -1320,18 +1341,24 @@ fn reply_inner(self: &Arc, info: &mut TransactionInfo) -> BinderResult { let allow_fds = orig.flags & TF_ACCEPT_FDS != 0; let reply = Transaction::new_reply(self, process, info, allow_fds)?; self.inner.lock().push_work(completion); - orig.from.deliver_reply(Ok(reply), &orig); + orig.from.deliver_reply(Ok(reply), &orig, None); Ok(()) })() .map_err(|mut err| { // At this point we only return `BR_TRANSACTION_COMPLETE` to the caller, and we must let // the sender know that the transaction has completed (with an error in this case). + pr_warn!( - "Failure {:?} during reply - delivering BR_FAILED_REPLY to sender.", - err + "{}:{} reply to {} failed: {err:?}", + info.from_pid, + info.from_tid, + info.to_pid ); - let reply = Err(BR_FAILED_REPLY); - orig.from.deliver_reply(reply, &orig); + + let param = err.source.as_ref().map_or(0, |e| e.to_errno()); + let ee = ExtendedError::new(info.debug_id as u32, err.reply, param); + orig.from + .deliver_reply(Err(BR_FAILED_REPLY), &orig, Some(ee)); err.reply = BR_TRANSACTION_COMPLETE; err }); diff --git a/drivers/android/binder/transaction.rs b/drivers/android/binder/transaction.rs index 1d9b66920a21..0e5d07b7e6f0 100644 --- a/drivers/android/binder/transaction.rs +++ b/drivers/android/binder/transaction.rs @@ -42,6 +42,7 @@ pub(crate) struct TransactionInfo { pub(crate) reply: u32, pub(crate) oneway_spam_suspect: bool, pub(crate) is_reply: bool, + pub(crate) debug_id: usize, } impl TransactionInfo { @@ -93,7 +94,6 @@ pub(crate) fn new( from: &Arc, info: &mut TransactionInfo, ) -> BinderResult> { - let debug_id = super::next_debug_id(); let allow_fds = node_ref.node.flags & FLAT_BINDER_FLAG_ACCEPTS_FDS != 0; let txn_security_ctx = node_ref.node.flags & FLAT_BINDER_FLAG_TXN_SECURITY_CTX != 0; let mut txn_security_ctx_off = if txn_security_ctx { Some(0) } else { None }; @@ -101,7 +101,7 @@ pub(crate) fn new( let mut alloc = match from.copy_transaction_data( to.clone(), info, - debug_id, + info.debug_id, allow_fds, txn_security_ctx_off.as_mut(), ) { @@ -128,7 +128,7 @@ pub(crate) fn new( let data_address = alloc.ptr; Ok(DTRWrap::arc_pin_init(pin_init!(Transaction { - debug_id, + debug_id: info.debug_id, target_node: Some(target_node), from_parent, sender_euid: Kuid::current_euid(), @@ -152,9 +152,8 @@ pub(crate) fn new_reply( info: &mut TransactionInfo, allow_fds: bool, ) -> BinderResult> { - let debug_id = super::next_debug_id(); let mut alloc = - match from.copy_transaction_data(to.clone(), info, debug_id, allow_fds, None) { + match from.copy_transaction_data(to.clone(), info, info.debug_id, allow_fds, None) { Ok(alloc) => alloc, Err(err) => { pr_warn!("Failure in copy_transaction_data: {:?}", err); @@ -165,7 +164,7 @@ pub(crate) fn new_reply( alloc.set_info_clear_on_drop(); } Ok(DTRWrap::arc_pin_init(pin_init!(Transaction { - debug_id, + debug_id: info.debug_id, target_node: None, from_parent: None, sender_euid: Kuid::current_euid(), @@ -394,7 +393,7 @@ fn do_work( let send_failed_reply = ScopeGuard::new(|| { if self.target_node.is_some() && self.flags & TF_ONE_WAY == 0 { let reply = Err(BR_FAILED_REPLY); - self.from.deliver_reply(reply, &self); + self.from.deliver_reply(reply, &self, None); } self.drop_outstanding_txn(); }); @@ -478,7 +477,7 @@ fn cancel(self: DArc) { // If this is not a reply or oneway transaction, then send a dead reply. if self.target_node.is_some() && self.flags & TF_ONE_WAY == 0 { let reply = Err(BR_DEAD_REPLY); - self.from.deliver_reply(reply, &self); + self.from.deliver_reply(reply, &self, None); } self.drop_outstanding_txn(); diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index bdc88cf74709..c43bd28b20b1 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -1338,7 +1338,7 @@ static int ata_hpa_resize(struct ata_device *dev) /* do we need to do it? */ if ((dev->class != ATA_DEV_ATA && dev->class != ATA_DEV_ZAC) || !ata_id_has_lba(dev->id) || !ata_id_hpa_enabled(dev->id) || - (dev->quirks & ATA_QUIRK_BROKEN_HPA)) + (dev->quirks & ATA_QUIRK_BROKEN_HPA) || ata_id_is_locked(dev->id)) return 0; /* read native max address */ @@ -3992,7 +3992,7 @@ int ata_dev_revalidate(struct ata_device *dev, unsigned int new_class, /* verify n_sectors hasn't changed */ if (dev->class != ATA_DEV_ATA || !n_sectors || - dev->n_sectors == n_sectors) + dev->n_sectors == n_sectors || ata_id_is_locked(dev->id)) return 0; /* n_sectors has changed */ diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c index 58b95bf4bdca..2135c14354a8 100644 --- a/drivers/block/drbd/drbd_receiver.c +++ b/drivers/block/drbd/drbd_receiver.c @@ -1810,6 +1810,11 @@ static int recv_dless_read(struct drbd_peer_device *peer_device, struct drbd_req data_size -= digest_size; } + if (data_size < 0) { + drbd_err(peer_device, "Invalid data reply size\n"); + return -EIO; + } + /* optimistically update recv_cnt. if receiving fails below, * we disconnect anyways, and counters will be reset. */ peer_device->device->recv_cnt += data_size>>9; diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index 4f6d9e652187..c2c11f2a01e7 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -3584,6 +3584,7 @@ ublk_batch_auto_buf_reg(const struct ublk_batch_io *uc, #define UBLK_CMD_BATCH_TMP_BUF_SZ (48 * 10) struct ublk_batch_io_iter { void __user *uaddr; + const u8 *kaddr; unsigned done, total; unsigned char elem_bytes; /* copy to this buffer from user space */ @@ -3632,7 +3633,10 @@ static int ublk_walk_cmd_buf(struct ublk_batch_io_iter *iter, while (iter->done < iter->total) { unsigned int len = min(sizeof(iter->buf), iter->total - iter->done); - if (copy_from_user(iter->buf, iter->uaddr + iter->done, len)) { + if (iter->kaddr) { + memcpy(iter->buf, iter->kaddr + iter->done, len); + } else if (copy_from_user(iter->buf, iter->uaddr + iter->done, + len)) { pr_warn("ublk%d: read batch cmd buffer failed\n", data->ub->dev_info.dev_id); return -EFAULT; @@ -3723,14 +3727,21 @@ static int ublk_handle_batch_prep_cmd(const struct ublk_batch_io_data *data) .total = uc->nr_elem * uc->elem_bytes, .elem_bytes = uc->elem_bytes, }; + void *cmd_buf; int ret; + cmd_buf = vmemdup_user(iter.uaddr, iter.total); + if (IS_ERR(cmd_buf)) + return PTR_ERR(cmd_buf); + iter.kaddr = cmd_buf; + mutex_lock(&data->ub->mutex); ret = ublk_walk_cmd_buf(&iter, data, ublk_batch_prep_io); if (ret && iter.done) ublk_batch_revert_prep_cmd(&iter, data); mutex_unlock(&data->ub->mutex); + kvfree(cmd_buf); return ret; } diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index f765970578f9..8dad7bf5f664 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -2079,6 +2079,15 @@ static int blkfront_resume(struct xenbus_device *dev) if (!shadow[j].request) continue; + /* + * For requests split across multiple slots, process the + * underlying request only once: skip the linked, sg-less + * secondary slot. + */ + if (shadow[j].associated_id != NO_ASSOCIATED_ID && + shadow[j].num_sg == 0) + continue; + /* * Get the bios in the request so we can re-queue them. */ diff --git a/drivers/bluetooth/bpa10x.c b/drivers/bluetooth/bpa10x.c index 2ae38a321c4b..e63d1af250ec 100644 --- a/drivers/bluetooth/bpa10x.c +++ b/drivers/bluetooth/bpa10x.c @@ -255,9 +255,13 @@ static int bpa10x_setup(struct hci_dev *hdev) if (IS_ERR(skb)) return PTR_ERR(skb); - bt_dev_info(hdev, "%s", (char *)(skb->data + 1)); + /* Bounded print: the device controls skb->len. */ + if (skb->len > 1) { + int len = skb->len - 1; - hci_set_fw_info(hdev, "%s", skb->data + 1); + bt_dev_info(hdev, "%.*s", len, (char *)(skb->data + 1)); + hci_set_fw_info(hdev, "%.*s", len, skb->data + 1); + } kfree_skb(skb); return 0; diff --git a/drivers/bluetooth/btintel_pcie.c b/drivers/bluetooth/btintel_pcie.c index 9e39327dc1fe..2b7231be5973 100644 --- a/drivers/bluetooth/btintel_pcie.c +++ b/drivers/bluetooth/btintel_pcie.c @@ -2127,6 +2127,9 @@ static int btintel_pcie_send_frame(struct hci_dev *hdev, if (test_bit(BTINTEL_PCIE_CORE_HALTED, &data->flags)) return -ENODEV; + if (test_bit(BTINTEL_PCIE_RECOVERY_IN_PROGRESS, &data->flags)) + return -ENODEV; + /* Due to the fw limitation, the type header of the packet should be * 4 bytes unlike 1 byte for UART. In UART, the firmware can read * the first byte to get the packet type and redirect the rest of data @@ -2485,7 +2488,6 @@ static void btintel_pcie_inc_recovery_count(struct pci_dev *pdev, } } -static int btintel_pcie_setup_hdev(struct btintel_pcie_data *data); static void btintel_pcie_reset(struct hci_dev *hdev); static int btintel_pcie_acpi_reset_method(struct btintel_pcie_data *data) @@ -2596,12 +2598,45 @@ static void btintel_pcie_perform_pldr(struct btintel_pcie_data *data) } } +/* + * Issue a Function Level Reset and hand teardown/re-init off to the PCI + * core via device_reprobe(), mirroring the PLDR path's contract. + * + * Caller must hold pci_lock_rescan_remove() and must have already + * disabled interrupts and drained both rx_work and coredump_work. + */ +static int btintel_pcie_perform_flr(struct btintel_pcie_data *data) +{ + struct pci_dev *pdev = data->pdev; + int err; + + /* pci_try_reset_function() avoids the device_lock ABBA against + * btintel_pcie_remove(): .remove() runs with device_lock held and + * then waits for this work via disable_work_sync(); the blocking + * pci_reset_function() would deadlock by trying to re-acquire + * device_lock here. + */ + err = pci_try_reset_function(pdev); + if (err) { + BT_ERR("Failed resetting the pcie device (%d)", err); + return err; + } + + /* device_reprobe() always detaches the driver first (running + * .remove(), which frees 'data'); any re-probe failure leaves the + * device unbound but 'data' is already gone, so just log it. + */ + if (device_reprobe(&pdev->dev)) + BT_ERR("BT reprobe failed for BDF:%s", pci_name(pdev)); + + return 0; +} + static void btintel_pcie_reset_work(struct work_struct *wk) { struct btintel_pcie_data *data = container_of(wk, struct btintel_pcie_data, reset_work); struct pci_dev *pdev = data->pdev; - int err; pci_lock_rescan_remove(); @@ -2621,60 +2656,27 @@ static void btintel_pcie_reset_work(struct work_struct *wk) disable_work_sync(&data->coredump_work); bt_dev_dbg(data->hdev, "Release bluetooth interface"); + + /* Both reset paths follow the same contract: on success they + * destroy 'data' via device_reprobe() (a fresh probe re-INIT_WORKs + * the coredump_work with disable count 0), so enable_work() must + * NOT be called on the success path. Only the FLR path can fail + * with 'data' still alive, in which case we balance the + * disable_work_sync() above so a later successful reset is not + * permanently blocked. + * + * pci_lock_rescan_remove() (held above) serializes against PCI + * device addition/removal (hotplug), so no device can be added to + * or removed from the bus list while this code runs. + */ if (data->reset_type == BTINTEL_PCIE_IOSF_PRR_PLDR) { - /* This function holds pci_lock_rescan_remove(), which acquires - * pci_rescan_remove_lock. This mutex serializes against PCI device - * addition/removal (hotplug), so no device can be added to or - * removed from the bus list while this code runs. - * - * device_reprobe() inside btintel_pcie_perform_pldr() destroys - * 'data' via .remove(); a fresh probe re-INIT_WORKs the - * coredump_work with disable count 0, so we must not call - * enable_work() on this path. - */ btintel_pcie_perform_pldr(data); goto out; } - btintel_pcie_release_hdev(data); - /* Use pci_try_reset_function() rather than pci_reset_function() to - * avoid an ABBA deadlock against btintel_pcie_remove(): the PCI core - * calls .remove() with device_lock held, and remove() then waits for - * this work via cancel_work_sync(); pci_reset_function() would in - * turn try to acquire the same device_lock, deadlocking both paths. - */ - err = pci_try_reset_function(pdev); - if (err) { - BT_ERR("Failed resetting the pcie device (%d)", err); - goto out_enable; - } + if (btintel_pcie_perform_flr(data)) + enable_work(&data->coredump_work); - btintel_pcie_enable_interrupts(data); - btintel_pcie_config_msix(data); - - err = btintel_pcie_enable_bt(data); - if (err) { - BT_ERR("Failed to enable bluetooth hardware after reset (%d)", - err); - goto out_enable; - } - - btintel_pcie_reset_ia(data); - btintel_pcie_start_rx(data); - data->flags = 0; - - err = btintel_pcie_setup_hdev(data); - if (err) { - BT_ERR("Failed registering hdev (%d)", err); - goto out_enable; - } - -out_enable: - /* Balance disable_work_sync() above on every exit. Leaving the - * counter incremented on a failed reset would permanently disable - * coredump_work even after a later successful reset. - */ - enable_work(&data->coredump_work); out: pci_dev_put(pdev); pci_unlock_rescan_remove(); diff --git a/drivers/bluetooth/btnxpuart.c b/drivers/bluetooth/btnxpuart.c index e7036a48ce48..6a1cffe08d5f 100644 --- a/drivers/bluetooth/btnxpuart.c +++ b/drivers/bluetooth/btnxpuart.c @@ -1267,6 +1267,12 @@ static int nxp_recv_fw_req_v3(struct hci_dev *hdev, struct sk_buff *skb) } nxpdev->fw_dnld_v3_offset = offset - nxpdev->fw_v3_offset_correction; + if (nxpdev->fw_dnld_v3_offset >= nxpdev->fw->size || + len > nxpdev->fw->size - nxpdev->fw_dnld_v3_offset) { + bt_dev_err(hdev, "FW download out of bounds, ignoring request"); + len = 0; + goto free_skb; + } serdev_device_write_buf(nxpdev->serdev, nxpdev->fw->data + nxpdev->fw_dnld_v3_offset, len); diff --git a/drivers/bluetooth/hci_ldisc.c b/drivers/bluetooth/hci_ldisc.c index 47f4902b40b4..2ad42c3bbaac 100644 --- a/drivers/bluetooth/hci_ldisc.c +++ b/drivers/bluetooth/hci_ldisc.c @@ -239,6 +239,8 @@ static int hci_uart_flush(struct hci_dev *hdev) BT_DBG("hdev %p tty %p", hdev, tty); + disable_work_sync(&hu->write_work); + if (hu->tx_skb) { kfree_skb(hu->tx_skb); hu->tx_skb = NULL; } @@ -254,6 +256,14 @@ static int hci_uart_flush(struct hci_dev *hdev) percpu_up_read(&hu->proto_lock); + /* Resume TX. Also reschedule in case work was queued concurrently; + * this may schedule write_work although there's nothing to do. + */ + enable_work(&hu->write_work); + clear_bit(HCI_UART_SENDING, &hu->tx_state); + if (test_bit(HCI_UART_TX_WAKEUP, &hu->tx_state)) + hci_uart_tx_wakeup(hu); + return 0; } @@ -271,12 +281,8 @@ static int hci_uart_open(struct hci_dev *hdev) /* Close device */ static int hci_uart_close(struct hci_dev *hdev) { - struct hci_uart *hu = hci_get_drvdata(hdev); - BT_DBG("hdev %p", hdev); - cancel_work_sync(&hu->write_work); - hci_uart_flush(hdev); hdev->flush = NULL; return 0; diff --git a/drivers/char/tpm/tpm-dev.c b/drivers/char/tpm/tpm-dev.c index 2779a8738c59..74488f0a7b78 100644 --- a/drivers/char/tpm/tpm-dev.c +++ b/drivers/char/tpm/tpm-dev.c @@ -36,7 +36,7 @@ static int tpm_open(struct inode *inode, struct file *file) tpm_common_open(file, chip, priv, NULL); - return 0; + return nonseekable_open(inode, file); out: clear_bit(0, &chip->is_open); diff --git a/drivers/char/tpm/tpmrm-dev.c b/drivers/char/tpm/tpmrm-dev.c index f48d4d9e179c..19e8f2779265 100644 --- a/drivers/char/tpm/tpmrm-dev.c +++ b/drivers/char/tpm/tpmrm-dev.c @@ -29,7 +29,7 @@ static int tpmrm_open(struct inode *inode, struct file *file) tpm_common_open(file, chip, &priv->priv, &priv->space); - return 0; + return nonseekable_open(inode, file); } static int tpmrm_release(struct inode *inode, struct file *file) diff --git a/drivers/dibs/dibs_loopback.c b/drivers/dibs/dibs_loopback.c index ec3b48cb0e87..0f2e09311152 100644 --- a/drivers/dibs/dibs_loopback.c +++ b/drivers/dibs/dibs_loopback.c @@ -254,6 +254,11 @@ static int dibs_lo_move_data(struct dibs_dev *dibs, u64 dmb_tok, read_unlock_bh(&ldev->dmb_ht_lock); return -EINVAL; } + if ((u64)offset + size > rmb_node->len) { + read_unlock_bh(&ldev->dmb_ht_lock); + return -EINVAL; + } + memcpy((char *)rmb_node->cpu_addr + offset, data, size); sba_idx = rmb_node->sba_idx; read_unlock_bh(&ldev->dmb_ht_lock); diff --git a/drivers/gpio/gpio-dwapb.c b/drivers/gpio/gpio-dwapb.c index 7b92b233fafe..aa7c08e60707 100644 --- a/drivers/gpio/gpio-dwapb.c +++ b/drivers/gpio/gpio-dwapb.c @@ -117,6 +117,7 @@ struct dwapb_gpio { unsigned int flags; struct reset_control *rst; struct clk_bulk_data clks[DWAPB_NR_CLOCKS]; + bool clocks_on_for_wake; struct dwapb_gpio_port ports[] __counted_by(nr_ports); }; @@ -199,6 +200,22 @@ static void dwapb_toggle_trigger(struct dwapb_gpio *gpio, unsigned int offs) dwapb_write(gpio, GPIO_INT_POLARITY, pol); } +static int dwapb_irq_init_hw(struct gpio_chip *gc) +{ + struct dwapb_gpio *gpio = to_dwapb_gpio(gc); + + /* + * GPIO interrupts may retain stale state across warm reboots when + * peripherals stay powered. Force a known-safe state before the GPIO + * irqchip and irq domain are set up. + */ + dwapb_write(gpio, GPIO_INTEN, 0); + dwapb_write(gpio, GPIO_INTMASK, 0xffffffff); + dwapb_write(gpio, GPIO_PORTA_EOI, 0xffffffff); + + return 0; +} + static u32 dwapb_do_irq(struct dwapb_gpio *gpio) { struct gpio_generic_chip *gen_gc = &gpio->ports[0].chip; @@ -364,11 +381,24 @@ static int dwapb_irq_set_wake(struct irq_data *d, unsigned int enable) struct dwapb_gpio *gpio = to_dwapb_gpio(gc); struct dwapb_context *ctx = gpio->ports[0].ctx; irq_hw_number_t bit = irqd_to_hwirq(d); + u32 wake_en = ctx->wake_en; if (enable) - ctx->wake_en |= BIT(bit); + wake_en |= BIT(bit); else - ctx->wake_en &= ~BIT(bit); + wake_en &= ~BIT(bit); + +#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY + if (d->parent_data && !!ctx->wake_en != !!wake_en) { + int err; + + err = irq_chip_set_wake_parent(d, enable); + if (err) + return err; + } +#endif + + ctx->wake_en = wake_en; return 0; } @@ -457,6 +487,7 @@ static void dwapb_configure_irqs(struct dwapb_gpio *gpio, girq = &gc->irq; girq->handler = handle_bad_irq; girq->default_type = IRQ_TYPE_NONE; + girq->init_hw = dwapb_irq_init_hw; port->pirq = pirq; @@ -749,6 +780,8 @@ static int dwapb_gpio_suspend(struct device *dev) int i; scoped_guard(gpio_generic_lock_irqsave, gen_gc) { + gpio->clocks_on_for_wake = false; + for (i = 0; i < gpio->nr_ports; i++) { unsigned int offset; unsigned int idx = gpio->ports[i].idx; @@ -770,30 +803,66 @@ static int dwapb_gpio_suspend(struct device *dev) ctx->int_pol = dwapb_read(gpio, GPIO_INT_POLARITY); ctx->int_type = dwapb_read(gpio, GPIO_INTTYPE_LEVEL); ctx->int_deb = dwapb_read(gpio, GPIO_PORTA_DEBOUNCE); - - /* Mask out interrupts */ - dwapb_write(gpio, GPIO_INTMASK, ~ctx->wake_en); } } } + return 0; +} + +static int dwapb_gpio_suspend_noirq(struct device *dev) +{ + struct dwapb_gpio *gpio = dev_get_drvdata(dev); + struct gpio_generic_chip *gen_gc = &gpio->ports[0].chip; + bool wake_enabled = false; + int i; + + scoped_guard(gpio_generic_lock_irqsave, gen_gc) { + for (i = 0; i < gpio->nr_ports; i++) { + unsigned int idx = gpio->ports[i].idx; + struct dwapb_context *ctx = gpio->ports[i].ctx; + + if (idx == 0) { + wake_enabled = ctx->wake_en; + dwapb_write(gpio, GPIO_INTMASK, ~ctx->wake_en); + break; + } + } + + gpio->clocks_on_for_wake = wake_enabled; + } + + if (wake_enabled) { + device_set_wakeup_path(dev); + return 0; + } + clk_bulk_disable_unprepare(DWAPB_NR_CLOCKS, gpio->clks); return 0; } +static int dwapb_gpio_resume_noirq(struct device *dev) +{ + struct dwapb_gpio *gpio = dev_get_drvdata(dev); + int err; + + if (gpio->clocks_on_for_wake) + return 0; + + err = clk_bulk_prepare_enable(DWAPB_NR_CLOCKS, gpio->clks); + if (err) + dev_err(gpio->dev, "Cannot reenable APB/Debounce clocks\n"); + + return err; +} + static int dwapb_gpio_resume(struct device *dev) { struct dwapb_gpio *gpio = dev_get_drvdata(dev); struct gpio_chip *gc = &gpio->ports[0].chip.gc; struct gpio_generic_chip *gen_gc = to_gpio_generic_chip(gc); - int i, err; - - err = clk_bulk_prepare_enable(DWAPB_NR_CLOCKS, gpio->clks); - if (err) { - dev_err(gpio->dev, "Cannot reenable APB/Debounce clocks\n"); - return err; - } + int i; guard(gpio_generic_lock_irqsave)(gen_gc); @@ -827,8 +896,11 @@ static int dwapb_gpio_resume(struct device *dev) return 0; } -static DEFINE_SIMPLE_DEV_PM_OPS(dwapb_gpio_pm_ops, - dwapb_gpio_suspend, dwapb_gpio_resume); +static const struct dev_pm_ops dwapb_gpio_pm_ops = { + SYSTEM_SLEEP_PM_OPS(dwapb_gpio_suspend, dwapb_gpio_resume) + NOIRQ_SYSTEM_SLEEP_PM_OPS(dwapb_gpio_suspend_noirq, + dwapb_gpio_resume_noirq) +}; static struct platform_driver dwapb_gpio_driver = { .driver = { diff --git a/drivers/gpio/gpio-mvebu.c b/drivers/gpio/gpio-mvebu.c index 689dc6354c2d..a010604e5ff7 100644 --- a/drivers/gpio/gpio-mvebu.c +++ b/drivers/gpio/gpio-mvebu.c @@ -1110,6 +1110,7 @@ static void mvebu_gpio_remove_irq_domain(void *data) { struct irq_domain *domain = data; + irq_domain_remove_generic_chips(domain); irq_domain_remove(domain); } diff --git a/drivers/gpio/gpio-palmas.c b/drivers/gpio/gpio-palmas.c index e377f6dd4ccf..e64ee0487718 100644 --- a/drivers/gpio/gpio-palmas.c +++ b/drivers/gpio/gpio-palmas.c @@ -116,6 +116,24 @@ static int palmas_gpio_input(struct gpio_chip *gc, unsigned offset) return ret; } +static int palmas_gpio_get_direction(struct gpio_chip *gc, unsigned int offset) +{ + struct palmas_gpio *pg = gpiochip_get_data(gc); + struct palmas *palmas = pg->palmas; + unsigned int val; + unsigned int reg; + int ret; + int gpio16 = (offset/8); + + offset %= 8; + reg = (gpio16) ? PALMAS_GPIO_DATA_DIR2 : PALMAS_GPIO_DATA_DIR; + ret = palmas_read(palmas, PALMAS_GPIO_BASE, reg, &val); + if (ret) + return ret; + + return (val & BIT(offset)) ? GPIO_LINE_DIRECTION_OUT : GPIO_LINE_DIRECTION_IN; +} + static int palmas_gpio_to_irq(struct gpio_chip *gc, unsigned offset) { struct palmas_gpio *pg = gpiochip_get_data(gc); @@ -165,6 +183,7 @@ static int palmas_gpio_probe(struct platform_device *pdev) palmas_gpio->gpio_chip.can_sleep = true; palmas_gpio->gpio_chip.direction_input = palmas_gpio_input; palmas_gpio->gpio_chip.direction_output = palmas_gpio_output; + palmas_gpio->gpio_chip.get_direction = palmas_gpio_get_direction; palmas_gpio->gpio_chip.to_irq = palmas_gpio_to_irq; palmas_gpio->gpio_chip.set = palmas_gpio_set; palmas_gpio->gpio_chip.get = palmas_gpio_get; diff --git a/drivers/gpio/gpio-shared-proxy.c b/drivers/gpio/gpio-shared-proxy.c index 0f39d23ea9cb..bc69b8729d19 100644 --- a/drivers/gpio/gpio-shared-proxy.c +++ b/drivers/gpio/gpio-shared-proxy.c @@ -21,7 +21,7 @@ struct gpio_shared_proxy_data { struct gpio_chip gc; struct gpio_shared_desc *shared_desc; struct device *dev; - bool voted_high; + bool voted_change; }; static int @@ -33,52 +33,54 @@ gpio_shared_proxy_set_unlocked(struct gpio_shared_proxy_data *proxy, int value) lockdep_assert_held(&shared_desc->mutex); - if (value) { - /* User wants to set value to high. */ - if (proxy->voted_high) - /* Already voted for high, nothing to do. */ + if (value != shared_desc->def_val) { + /* User wants to vote for a value change. */ + if (proxy->voted_change) + /* Already voted for a change, nothing to do. */ goto out; - /* Haven't voted for high yet. */ - if (!shared_desc->highcnt) { + /* Haven't voted for a value change yet. */ + if (!shared_desc->votecnt) { /* - * Current value is low, need to actually set value - * to high. + * Current value is default, need to actually set value + * to the opposite. */ - ret = gpiod_set_value_cansleep(desc, 1); + ret = gpiod_set_value_cansleep(desc, value); if (ret) goto out; } - shared_desc->highcnt++; - proxy->voted_high = true; + shared_desc->votecnt++; + proxy->voted_change = true; goto out; } - /* Desired value is low. */ - if (!proxy->voted_high) - /* We didn't vote for high, nothing to do. */ + /* Desired value is the default. */ + if (!proxy->voted_change) + /* We didn't vote for change previously, nothing to do. */ goto out; - /* We previously voted for high. */ - if (shared_desc->highcnt == 1) { - /* This is the last remaining vote for high, set value to low. */ - ret = gpiod_set_value_cansleep(desc, 0); + /* We previously voted for change. */ + if (shared_desc->votecnt == 1) { + /* This is the last remaining vote for change, set value to default. */ + ret = gpiod_set_value_cansleep(desc, shared_desc->def_val); if (ret) goto out; } - shared_desc->highcnt--; - proxy->voted_high = false; + shared_desc->votecnt--; + proxy->voted_change = false; out: - if (shared_desc->highcnt) + if (shared_desc->votecnt) dev_dbg(proxy->dev, - "Voted for value '%s', effective value is 'high', number of votes for 'high': %u\n", - str_high_low(value), shared_desc->highcnt); + "Voted for value '%s', effective value is '%s', number of votes: %u\n", + str_high_low(value), str_high_low(!shared_desc->def_val), + shared_desc->votecnt); else - dev_dbg(proxy->dev, "Voted for value 'low', effective value is 'low'\n"); + dev_dbg(proxy->dev, "Voted for value '%s', effective value is '%s'\n", + str_high_low(value), str_high_low(shared_desc->def_val)); return ret; } @@ -106,8 +108,8 @@ static void gpio_shared_proxy_free(struct gpio_chip *gc, unsigned int offset) guard(mutex)(&shared_desc->mutex); - if (proxy->voted_high) { - ret = gpio_shared_proxy_set_unlocked(proxy, 0); + if (proxy->voted_change) { + ret = gpio_shared_proxy_set_unlocked(proxy, shared_desc->def_val); if (ret) dev_err(proxy->dev, "Failed to unset the shared GPIO value on release: %d\n", ret); @@ -196,13 +198,9 @@ static int gpio_shared_proxy_direction_output(struct gpio_chip *gc, if (ret) return ret; - if (value) { - proxy->voted_high = true; - shared_desc->highcnt = 1; - } else { - proxy->voted_high = false; - shared_desc->highcnt = 0; - } + shared_desc->def_val = value; + shared_desc->votecnt = 0; + proxy->voted_change = false; return 0; } diff --git a/drivers/gpio/gpiolib-shared.h b/drivers/gpio/gpiolib-shared.h index bbdc0ab7b647..618756f6c6aa 100644 --- a/drivers/gpio/gpiolib-shared.h +++ b/drivers/gpio/gpiolib-shared.h @@ -41,7 +41,8 @@ struct gpio_shared_desc { struct gpio_desc *desc; unsigned long cfg; unsigned int usecnt; - unsigned int highcnt; + unsigned int votecnt; + int def_val; struct mutex mutex; /* serializes all proxy operations on this descriptor */ }; diff --git a/drivers/gpu/buddy.c b/drivers/gpu/buddy.c index eb1457376307..b12d3a2ac630 100644 --- a/drivers/gpu/buddy.c +++ b/drivers/gpu/buddy.c @@ -1084,22 +1084,30 @@ static int __gpu_buddy_alloc_range(struct gpu_buddy *mm, blocks, total_allocated_on_err); } +static int __alloc_contig_aligned_retry(struct gpu_buddy *mm, + u64 unaligned_offset, + u64 size, + u64 min_block_size, + struct list_head *blocks) +{ + u64 aligned_offset = round_down(unaligned_offset, min_block_size); + + return __gpu_buddy_alloc_range(mm, aligned_offset, size, NULL, blocks); +} + static int __alloc_contig_try_harder(struct gpu_buddy *mm, u64 size, u64 min_block_size, struct list_head *blocks) { - u64 rhs_offset, lhs_offset, lhs_size, filled; + u64 rhs_offset, lhs_offset, filled; struct gpu_buddy_block *block; unsigned int tree, order; - LIST_HEAD(blocks_lhs); - unsigned long pages; u64 modify_size; int err; modify_size = rounddown_pow_of_two(size); - pages = modify_size >> ilog2(mm->chunk_size); - order = fls(pages) - 1; + order = ilog2(modify_size) - ilog2(mm->chunk_size); if (order == 0) return -ENOSPC; @@ -1115,31 +1123,48 @@ static int __alloc_contig_try_harder(struct gpu_buddy *mm, while (iter) { block = rbtree_get_free_block(iter); - /* Allocate blocks traversing RHS */ rhs_offset = gpu_buddy_block_offset(block); + + /* Allocate blocks traversing RHS */ err = __gpu_buddy_alloc_range(mm, rhs_offset, size, &filled, blocks); - if (!err || err != -ENOSPC) + if (err && err != -ENOSPC) return err; - - lhs_size = max((size - filled), min_block_size); - if (!IS_ALIGNED(lhs_size, min_block_size)) - lhs_size = round_up(lhs_size, min_block_size); - - /* Allocate blocks traversing LHS */ - lhs_offset = gpu_buddy_block_offset(block) - lhs_size; - err = __gpu_buddy_alloc_range(mm, lhs_offset, lhs_size, - NULL, &blocks_lhs); - if (!err) { - list_splice(&blocks_lhs, blocks); + if (!err && IS_ALIGNED(rhs_offset, min_block_size)) return 0; - } else if (err != -ENOSPC) { + if (!err) { + /* Allocate the unaligned RHS offset using round_down */ + gpu_buddy_free_list_internal(mm, blocks); + err = __alloc_contig_aligned_retry(mm, rhs_offset, + size, + min_block_size, + blocks); + if (!err) + return 0; + if (err != -ENOSPC) { + gpu_buddy_free_list_internal(mm, blocks); + return err; + } + goto next; + } + + if (size - filled > rhs_offset) + goto next; + + lhs_offset = rhs_offset - (size - filled); + + /* Allocate the unaligned LHS offset using round_down */ + gpu_buddy_free_list_internal(mm, blocks); + err = __alloc_contig_aligned_retry(mm, lhs_offset, size, + min_block_size, blocks); + if (!err) + return 0; + if (err != -ENOSPC) { gpu_buddy_free_list_internal(mm, blocks); return err; } - /* Free blocks for the next iteration */ +next: gpu_buddy_free_list_internal(mm, blocks); - iter = rb_prev(iter); } } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 8d6502a94306..53335ca96b1d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -1333,7 +1333,8 @@ static bool amdgpu_device_aspm_support_quirk(struct amdgpu_device *adev) * It's unclear if this is a platform-specific or GPU-specific issue. * Disable ASPM on SI for the time being. */ - if (adev->family == AMDGPU_FAMILY_SI) + if (adev->family == AMDGPU_FAMILY_SI || + (!(adev->pm.pp_feature & PP_PCIE_DPM_MASK) && adev->family == AMDGPU_FAMILY_VI)) return true; #if IS_ENABLED(CONFIG_X86) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c index 853365dee2a7..7b9bb998906d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c @@ -2304,6 +2304,7 @@ static int amdgpu_discovery_set_psp_ip_blocks(struct amdgpu_device *adev) amdgpu_device_ip_block_add(adev, &psp_v14_0_ip_block); break; case IP_VERSION(15, 0, 0): + case IP_VERSION(15, 0, 9): amdgpu_device_ip_block_add(adev, &psp_v15_0_ip_block); break; case IP_VERSION(15, 0, 8): @@ -2375,6 +2376,7 @@ static int amdgpu_discovery_set_smu_ip_blocks(struct amdgpu_device *adev) case IP_VERSION(15, 0, 0): case IP_VERSION(15, 0, 5): case IP_VERSION(15, 0, 8): + case IP_VERSION(15, 0, 9): amdgpu_device_ip_block_add(adev, &smu_v15_0_ip_block); break; default: diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index 96e1b72b9e1c..e0c0d7872e45 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -275,6 +275,7 @@ static int psp_early_init(struct amdgpu_ip_block *ip_block) psp->boot_time_tmr = false; break; case IP_VERSION(15, 0, 0): + case IP_VERSION(15, 0, 9): psp_v15_0_0_set_psp_funcs(psp); psp->boot_time_tmr = false; break; @@ -3475,7 +3476,9 @@ static int psp_load_non_psp_fw(struct psp_context *psp) amdgpu_ip_version(adev, MP0_HWIP, 0) == IP_VERSION(15, 0, 0) || amdgpu_ip_version(adev, MP0_HWIP, 0) == - IP_VERSION(15, 0, 8)) && + IP_VERSION(15, 0, 8) || + amdgpu_ip_version(adev, MP0_HWIP, 0) == + IP_VERSION(15, 0, 9)) && (ucode->ucode_id == AMDGPU_UCODE_ID_SDMA1 || ucode->ucode_id == AMDGPU_UCODE_ID_SDMA2 || ucode->ucode_id == AMDGPU_UCODE_ID_SDMA3)) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c index ef3f0213cc46..d854343b3734 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c @@ -523,6 +523,15 @@ amdgpu_userq_destroy(struct amdgpu_userq_mgr *uq_mgr, struct amdgpu_usermode_que amdgpu_userq_cleanup(queue); mutex_unlock(&uq_mgr->userq_mutex); + /* + * A failed unmap means MES could not remove the hung queue and is now + * unresponsive. Recover the GPU here so the wedged MES does not fail + * the next, unrelated queue submission and trigger a reset attributed + * to an innocent workload. + */ + if (r) + queue_work(adev->reset_domain->wq, &uq_mgr->reset_work); + cancel_delayed_work_sync(&queue->hang_detect_work); uq_funcs->mqd_destroy(queue); queue->userq_mgr = NULL; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index f317f888b59f..bb99b7c3a010 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -2460,19 +2460,6 @@ static void amdgpu_vm_destroy_task_info(struct kref *kref) kfree(ti); } -static inline struct amdgpu_vm * -amdgpu_vm_get_vm_from_pasid(struct amdgpu_device *adev, u32 pasid) -{ - struct amdgpu_vm *vm; - unsigned long flags; - - xa_lock_irqsave(&adev->vm_manager.pasids, flags); - vm = xa_load(&adev->vm_manager.pasids, pasid); - xa_unlock_irqrestore(&adev->vm_manager.pasids, flags); - - return vm; -} - /** * amdgpu_vm_put_task_info - reference down the vm task_info ptr * @@ -2519,8 +2506,16 @@ amdgpu_vm_get_task_info_vm(struct amdgpu_vm *vm) struct amdgpu_task_info * amdgpu_vm_get_task_info_pasid(struct amdgpu_device *adev, u32 pasid) { - return amdgpu_vm_get_task_info_vm( - amdgpu_vm_get_vm_from_pasid(adev, pasid)); + struct amdgpu_task_info *ti; + struct amdgpu_vm *vm; + unsigned long flags; + + xa_lock_irqsave(&adev->vm_manager.pasids, flags); + vm = xa_load(&adev->vm_manager.pasids, pasid); + ti = amdgpu_vm_get_task_info_vm(vm); + xa_unlock_irqrestore(&adev->vm_manager.pasids, flags); + + return ti; } static int amdgpu_vm_create_task_info(struct amdgpu_vm *vm) @@ -3015,6 +3010,8 @@ bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, u32 pasid, is_compute_context = vm->is_compute_context; if (is_compute_context) { + __label__ drm_exec_retry; + /* Release the root PD lock since svm_range_restore_pages * might try to take it. * TODO: rework svm_range_restore_pages so that this isn't diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index b4b27e4c495d..a9961d504833 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -5350,6 +5350,15 @@ static void gfx_v10_0_constants_init(struct amdgpu_device *adev) gfx_v10_0_get_tcc_info(adev); adev->gfx.config.pa_sc_tile_steering_override = gfx_v10_0_init_pa_sc_tile_steering_override(adev); + /* Program DB_RING_CONTROL for multiple GFX pipes + * Default power up value is 1. + * Possible values: + * 0 - split occlusion counters between gfx pipes + * 1 - all occlusion counters to pipe 0 + * 2 - all occlusion counters to pipe 1 + */ + WREG32_FIELD15(GC, 0, DB_RING_CONTROL, COUNTER_CONTROL, + (adev->gfx.me.num_pipe_per_me > 1) ? 0 : 1); /* XXX SH_MEM regs */ /* where to put LDS, scratch, GPUVM in FSA64 space */ diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c index 1677e88a4e36..e0b80abcd075 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc21.c +++ b/drivers/gpu/drm/amd/amdgpu/soc21.c @@ -406,6 +406,7 @@ soc21_asic_reset_method(struct amdgpu_device *adev) case IP_VERSION(14, 0, 4): case IP_VERSION(14, 0, 5): case IP_VERSION(15, 0, 0): + case IP_VERSION(15, 0, 9): return AMD_RESET_METHOD_MODE2; default: if (amdgpu_dpm_is_baco_supported(adev)) @@ -861,7 +862,6 @@ static int soc21_common_early_init(struct amdgpu_ip_block *ip_block) AMD_CG_SUPPORT_BIF_LS; adev->pg_flags = AMD_PG_SUPPORT_VCN_DPG | AMD_PG_SUPPORT_VCN | - AMD_PG_SUPPORT_JPEG_DPG | AMD_PG_SUPPORT_JPEG | AMD_PG_SUPPORT_GFX_PG; adev->external_rev_id = adev->rev_id + 0xF; @@ -889,7 +889,6 @@ static int soc21_common_early_init(struct amdgpu_ip_block *ip_block) AMD_CG_SUPPORT_BIF_LS; adev->pg_flags = AMD_PG_SUPPORT_VCN_DPG | AMD_PG_SUPPORT_VCN | - AMD_PG_SUPPORT_JPEG_DPG | AMD_PG_SUPPORT_JPEG | AMD_PG_SUPPORT_GFX_PG; adev->external_rev_id = adev->rev_id + 0x40; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index 2e010c1f8828..678ec611a4f2 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -3818,6 +3818,12 @@ bool kfd_dqm_is_queue_in_process(struct device_queue_manager *dqm, dqm_unlock(dqm); return r; } + +size_t mqd_size_from_queue_type(struct device_queue_manager *dqm, enum kfd_queue_type type) +{ + return dqm->mqd_mgrs[get_mqd_type_from_queue_type(type)]->mqd_size; +} + #if defined(CONFIG_DEBUG_FS) static void seq_reg_dump(struct seq_file *m, diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h index e0b6a47e7722..641b8ada82a0 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h @@ -333,6 +333,8 @@ int debug_refresh_runlist(struct device_queue_manager *dqm); bool kfd_dqm_is_queue_in_process(struct device_queue_manager *dqm, struct qcm_process_device *qpd, int doorbell_off, u32 *queue_format); +size_t mqd_size_from_queue_type(struct device_queue_manager *dqm, + enum kfd_queue_type type); static inline unsigned int get_sh_mem_bases_32(struct kfd_process_device *pdd) { diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c index 81900b49d9d5..2e97da597b3d 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c @@ -107,6 +107,9 @@ static int allocate_event_notification_slot(struct kfd_process *p, } if (restore_id) { + if (*restore_id >= KFD_SIGNAL_EVENT_LIMIT) + return -EINVAL; + id = idr_alloc(&p->event_idr, ev, *restore_id, *restore_id + 1, GFP_KERNEL); } else { @@ -204,7 +207,7 @@ static int create_signal_event(struct file *devkfd, struct kfd_process *p, ret = allocate_event_notification_slot(p, ev, restore_id); if (ret) { - pr_warn("Signal event wasn't created because out of kernel memory\n"); + pr_warn("Failed to create signal event notification slot\n"); return ret; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h index acd0e41e744c..4d65f94da4d8 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -440,7 +440,8 @@ enum kfd_queue_type { KFD_QUEUE_TYPE_SDMA, KFD_QUEUE_TYPE_HIQ, KFD_QUEUE_TYPE_SDMA_XGMI, - KFD_QUEUE_TYPE_SDMA_BY_ENG_ID + KFD_QUEUE_TYPE_SDMA_BY_ENG_ID, + KFD_QUEUE_TYPE_MAX, }; enum kfd_queue_format { diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c index ca71fa726e32..5fb3679e4e85 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c @@ -910,7 +910,7 @@ static void kfd_process_free_id(struct kfd_process *process) { struct kfd_process *primary_process; - if (process->context_id != KFD_CONTEXT_ID_PRIMARY) + if (process->context_id == KFD_CONTEXT_ID_PRIMARY) return; primary_process = kfd_lookup_process_by_mm(process->lead_thread->mm); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c index 0ac35789b239..9ccbc6e5b27b 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c @@ -265,6 +265,11 @@ static int init_user_queue(struct process_queue_manager *pqm, (*q)->process = pqm->process; if (dev->kfd->shared_resources.enable_mes) { + if (!q_properties->wptr_bo) { + pr_debug("Queue initialization with shared MES requires queue buffers to be initialized\n"); + return -EINVAL; + } + retval = amdgpu_amdkfd_alloc_kernel_mem(dev->adev, AMDGPU_MES_GANG_CTX_SIZE, AMDGPU_GEM_DOMAIN_GTT, @@ -1003,6 +1008,23 @@ int kfd_criu_restore_queue(struct kfd_process *p, goto exit; } + pdd = kfd_process_device_data_by_id(p, q_data->gpu_id); + if (!pdd) { + pr_err("Failed to get pdd\n"); + ret = -EINVAL; + goto exit; + } + + if (q_data->type >= KFD_QUEUE_TYPE_MAX) { + ret = -EINVAL; + goto exit; + } + + if (q_data->mqd_size != mqd_size_from_queue_type(pdd->dev->dqm, q_data->type)) { + ret = -EINVAL; + goto exit; + } + *priv_data_offset += sizeof(*q_data); q_extra_data_size = (uint64_t)q_data->ctl_stack_size + q_data->mqd_size; @@ -1025,13 +1047,6 @@ int kfd_criu_restore_queue(struct kfd_process *p, *priv_data_offset += q_extra_data_size; - pdd = kfd_process_device_data_by_id(p, q_data->gpu_id); - if (!pdd) { - pr_err("Failed to get pdd\n"); - ret = -EINVAL; - goto exit; - } - /* * data stored in this order: * mqd[xcc0], mqd[xcc1],..., ctl_stack[xcc0], ctl_stack[xcc1]... @@ -1042,18 +1057,10 @@ int kfd_criu_restore_queue(struct kfd_process *p, memset(&qp, 0, sizeof(qp)); set_queue_properties_from_criu(&qp, q_data, NUM_XCC(pdd->dev->adev->gfx.xcc_mask)); - ret = kfd_queue_acquire_buffers(pdd, &qp); - if (ret) { - pr_debug("failed to acquire user queue buffers for CRIU\n"); - goto exit; - } - print_queue_properties(&qp); ret = pqm_create_queue(&p->pqm, pdd->dev, &qp, &queue_id, q_data, mqd, ctl_stack, NULL); if (ret) { - kfd_queue_unref_bo_vas(pdd, &qp); - kfd_queue_release_buffers(pdd, &qp); pr_err("Failed to create new queue err:%d\n", ret); goto exit; } diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c index 208a2fba6d40..762ec3cede96 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c @@ -802,6 +802,7 @@ static int smu_set_funcs(struct amdgpu_device *adev) break; case IP_VERSION(15, 0, 0): case IP_VERSION(15, 0, 5): + case IP_VERSION(15, 0, 9): smu_v15_0_0_set_ppt_funcs(smu); break; case IP_VERSION(15, 0, 8): diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c index fdc1456b885c..a6a88e7b2668 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c @@ -1621,19 +1621,23 @@ static int smu_v14_0_2_get_power_limit(struct smu_context *smu, table_context->power_play_table; PPTable_t *pptable = table_context->driver_pptable; CustomSkuTable_t *skutable = &pptable->CustomSkuTable; - int16_t od_percent_upper = 0, od_percent_lower = 0; + uint32_t pp_limit = smu->adev->pm.ac_power ? + skutable->SocketPowerLimitAc[PPT_THROTTLER_PPT0] : + skutable->SocketPowerLimitDc[PPT_THROTTLER_PPT0]; uint32_t msg_limit = pptable->SkuTable.MsgLimits.Power[PPT_THROTTLER_PPT0][POWER_SOURCE_AC]; - uint32_t power_limit; + uint32_t min_limit = min_t(uint32_t, pp_limit, msg_limit); + uint32_t max_limit = max_t(uint32_t, pp_limit, msg_limit); + int16_t od_percent_upper = 0, od_percent_lower = 0; + int ret; - if (smu_v14_0_get_current_power_limit(smu, &power_limit)) - power_limit = smu->adev->pm.ac_power ? - skutable->SocketPowerLimitAc[PPT_THROTTLER_PPT0] : - skutable->SocketPowerLimitDc[PPT_THROTTLER_PPT0]; + if (current_power_limit) { + ret = smu_v14_0_get_current_power_limit(smu, current_power_limit); + if (ret) + *current_power_limit = pp_limit; + } - if (current_power_limit) - *current_power_limit = power_limit; if (default_power_limit) - *default_power_limit = power_limit; + *default_power_limit = pp_limit; if (powerplay_table) { if (smu->od_enabled && @@ -1647,15 +1651,15 @@ static int smu_v14_0_2_get_power_limit(struct smu_context *smu, } dev_dbg(smu->adev->dev, "od percent upper:%d, od percent lower:%d (default power: %d)\n", - od_percent_upper, od_percent_lower, power_limit); + od_percent_upper, od_percent_lower, pp_limit); if (max_power_limit) { - *max_power_limit = msg_limit * (100 + od_percent_upper); + *max_power_limit = max_limit * (100 + od_percent_upper); *max_power_limit /= 100; } if (min_power_limit) { - *min_power_limit = power_limit * (100 + od_percent_lower); + *min_power_limit = min_limit * (100 + od_percent_lower); *min_power_limit /= 100; } diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu15/smu_v15_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu15/smu_v15_0.c index a1318409e4b5..8fc99e93ac53 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu15/smu_v15_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu15/smu_v15_0.c @@ -664,6 +664,7 @@ int smu_v15_0_gfx_off_control(struct smu_context *smu, bool enable) switch (amdgpu_ip_version(adev, MP1_HWIP, 0)) { case IP_VERSION(15, 0, 0): + case IP_VERSION(15, 0, 9): if (!(adev->pm.pp_feature & PP_GFXOFF_MASK)) return 0; if (enable) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu15/smu_v15_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu15/smu_v15_0_0_ppt.c index a214ddbd4c86..bb8d09e73c7d 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu15/smu_v15_0_0_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu15/smu_v15_0_0_ppt.c @@ -1177,7 +1177,8 @@ static int smu_v15_0_common_get_dpm_profile_freq(struct smu_context *smu, smu_v15_0_common_get_dpm_ultimate_freq(smu, SMU_SOCCLK, NULL, &clk_limit); break; case SMU_FCLK: - if (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(15, 0, 0)) + if (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(15, 0, 0) || + amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(15, 0, 9)) smu_v15_0_common_get_dpm_ultimate_freq(smu, SMU_FCLK, NULL, &clk_limit); else clk_limit = SMU_15_0_UMD_PSTATE_FCLK; diff --git a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c index 8cf6b73bceac..5006ac181b2d 100644 --- a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c +++ b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c @@ -309,7 +309,9 @@ static void analogix_dp_get_adjust_training_lane(struct analogix_dp_device *dp, lane_count = dp->link_train.lane_count; for (lane = 0; lane < lane_count; lane++) { voltage_swing = drm_dp_get_adjust_request_voltage(link_status, lane); + voltage_swing >>= DP_TRAIN_VOLTAGE_SWING_SHIFT; pre_emphasis = drm_dp_get_adjust_request_pre_emphasis(link_status, lane); + pre_emphasis >>= DP_TRAIN_PRE_EMPHASIS_SHIFT; training_lane = DPCD_VOLTAGE_SWING_SET(voltage_swing) | DPCD_PRE_EMPHASIS_SET(pre_emphasis); @@ -355,7 +357,9 @@ static int analogix_dp_process_clock_recovery(struct analogix_dp_device *dp) for (lane = 0; lane < lane_count; lane++) { training_lane = analogix_dp_get_lane_link_training(dp, lane); voltage_swing = drm_dp_get_adjust_request_voltage(link_status, lane); + voltage_swing >>= DP_TRAIN_VOLTAGE_SWING_SHIFT; pre_emphasis = drm_dp_get_adjust_request_pre_emphasis(link_status, lane); + pre_emphasis >>= DP_TRAIN_PRE_EMPHASIS_SHIFT; if (DPCD_VOLTAGE_SWING_GET(training_lane) == voltage_swing && DPCD_PRE_EMPHASIS_GET(training_lane) == pre_emphasis) diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index 7b11a582f8ec..80ca785bdb26 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -225,16 +225,106 @@ static void drm_fb_helper_resume_worker(struct work_struct *work) console_unlock(); } +static int find_crtc_index_atomic(struct drm_fb_helper *helper) +{ + struct drm_device *dev = helper->dev; + int crtc_index = -EINVAL; + struct drm_modeset_acquire_ctx ctx; + struct drm_plane *plane; + int ret = 0; + + drm_modeset_acquire_init(&ctx, 0); + +retry: + drm_for_each_plane(plane, dev) { + const struct drm_plane_state *plane_state; + + if (plane->type != DRM_PLANE_TYPE_PRIMARY) + continue; + + ret = drm_modeset_lock(&plane->mutex, &ctx); + if (ret) + goto err_drm_modeset_lock; + plane_state = plane->state; + + if (plane_state->fb == helper->fb && plane_state->crtc) { + struct drm_crtc *crtc = plane_state->crtc; + + ret = drm_modeset_lock(&crtc->mutex, &ctx); + if (ret) + goto err_drm_modeset_lock; + if (crtc->state->active) + crtc_index = crtc->index; + drm_modeset_unlock(&crtc->mutex); + } + drm_modeset_unlock(&plane->mutex); + + if (crtc_index >= 0) + break; + } + + drm_modeset_drop_locks(&ctx); + drm_modeset_acquire_fini(&ctx); + + return crtc_index; + +err_drm_modeset_lock: + if (ret == -EDEADLK) { + drm_modeset_backoff(&ctx); + goto retry; + } + return ret; +} + +static int find_crtc_index_legacy(struct drm_fb_helper *helper) +{ + struct drm_device *dev = helper->dev; + struct drm_crtc *crtc; + + drm_for_each_crtc(crtc, dev) { + struct drm_plane *plane = crtc->primary; + + if (!crtc->enabled) + continue; + if (!plane || plane->fb != helper->fb) + continue; /* CRTC doesn't display fbdev emulation */ + + return crtc->index; + } + + return -EINVAL; +} + +static int drm_fb_helper_find_crtc_index(struct drm_fb_helper *helper) +{ + struct drm_device *dev = helper->dev; + int crtc_index; + + mutex_lock(&dev->mode_config.mutex); + + if (drm_drv_uses_atomic_modeset(dev)) + crtc_index = find_crtc_index_atomic(helper); + else + crtc_index = find_crtc_index_legacy(helper); + + mutex_unlock(&dev->mode_config.mutex); + + return crtc_index; +} + static void drm_fb_helper_fb_dirty(struct drm_fb_helper *helper) { struct drm_device *dev = helper->dev; struct drm_clip_rect *clip = &helper->damage_clip; struct drm_clip_rect clip_copy; + int crtc_index; unsigned long flags; int ret; mutex_lock(&helper->lock); - drm_client_modeset_wait_for_vblank(&helper->client, 0); + crtc_index = drm_fb_helper_find_crtc_index(helper); + if (crtc_index >= 0) + drm_client_modeset_wait_for_vblank(&helper->client, crtc_index); mutex_unlock(&helper->lock); if (drm_WARN_ON_ONCE(dev, !helper->funcs->fb_dirty)) diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c index e2df4becce62..9039a39c4324 100644 --- a/drivers/gpu/drm/drm_ioctl.c +++ b/drivers/gpu/drm/drm_ioctl.c @@ -373,13 +373,25 @@ drm_setclientcap(struct drm_device *dev, void *data, struct drm_file *file_priv) return -EINVAL; file_priv->supports_virtualized_cursor_plane = req->value; break; - case DRM_CLIENT_CAP_PLANE_COLOR_PIPELINE: + case DRM_CLIENT_CAP_PLANE_COLOR_PIPELINE: { + struct drm_plane *plane; + bool has_plane_with_color_pipeline = false; + if (!file_priv->atomic) return -EINVAL; if (req->value > 1) return -EINVAL; + drm_for_each_plane(plane, dev) { + if (plane->color_pipeline_property) { + has_plane_with_color_pipeline = true; + break; + } + } + if (!has_plane_with_color_pipeline) + return -EOPNOTSUPP; file_priv->plane_color_pipeline = req->value; break; + } default: return -EINVAL; } diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index 85d3aa3b9894..7ff5712f8b19 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -5737,8 +5737,9 @@ intel_dp_check_mst_status(struct intel_dp *intel_dp) struct intel_display *display = to_intel_display(intel_dp); bool force_retrain = intel_dp->link.force_retrain; bool reprobe_needed = false; + int tries = 33; - for (;;) { + while (--tries) { u8 esi[4] = {}; u8 ack[4] = {}; bool new_irqs; @@ -5781,6 +5782,11 @@ intel_dp_check_mst_status(struct intel_dp *intel_dp) break; } + if (!tries) { + drm_dbg_kms(display->drm, "DPRX ESI not clearing, device may be stuck\n"); + reprobe_needed = true; + } + return !reprobe_needed; } diff --git a/drivers/gpu/drm/i915/display/intel_lt_phy.c b/drivers/gpu/drm/i915/display/intel_lt_phy.c index 615ee980470e..34dbe450cc5b 100644 --- a/drivers/gpu/drm/i915/display/intel_lt_phy.c +++ b/drivers/gpu/drm/i915/display/intel_lt_phy.c @@ -1223,11 +1223,7 @@ intel_lt_phy_program_port_clock_ctl(struct intel_encoder *encoder, else val |= XELPDP_DDI_CLOCK_SELECT_PREP(display, XELPDP_DDI_CLOCK_SELECT_MAXPCLK); - /* DP2.0 10G and 20G rates enable MPLLA*/ - if (port_clock == 1000000 || port_clock == 2000000) - val |= XELPDP_SSC_ENABLE_PLLA; - else - val |= ltpll->ssc_enabled ? XELPDP_SSC_ENABLE_PLLB : 0; + val |= ltpll->ssc_enabled ? XELPDP_SSC_ENABLE_PLLA : 0; intel_de_rmw(display, XELPDP_PORT_CLOCK_CTL(display, encoder->port), XELPDP_LANE1_PHY_CLOCK_SELECT | XELPDP_FORWARD_CLOCK_UNGATE | diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c index e138982dc91f..beaa1d62613d 100644 --- a/drivers/gpu/drm/i915/display/intel_psr.c +++ b/drivers/gpu/drm/i915/display/intel_psr.c @@ -1522,9 +1522,6 @@ int _intel_psr_min_set_context_latency(const struct intel_crtc_state *crtc_state needs_panel_replay) return 0; - if (intel_vrr_always_use_vrr_tg(display)) - return 0; - return 1; } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c index aeafe1742d30..c58ffa5a8fa6 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_context.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c @@ -769,8 +769,8 @@ static int set_proto_ctx_engines(struct drm_i915_file_private *fpriv, struct intel_engine_cs *engine; if (copy_from_user(&ci, &user->engines[n], sizeof(ci))) { - kfree(set.engines); - return -EFAULT; + err = -EFAULT; + goto err; } memset(&set.engines[n], 0, sizeof(set.engines[n])); @@ -786,8 +786,8 @@ static int set_proto_ctx_engines(struct drm_i915_file_private *fpriv, drm_dbg(&i915->drm, "Invalid engine[%d]: { class:%d, instance:%d }\n", n, ci.engine_class, ci.engine_instance); - kfree(set.engines); - return -ENOENT; + err = -ENOENT; + goto err; } set.engines[n].type = I915_GEM_ENGINE_TYPE_PHYSICAL; @@ -800,15 +800,21 @@ static int set_proto_ctx_engines(struct drm_i915_file_private *fpriv, set_proto_ctx_engines_extensions, ARRAY_SIZE(set_proto_ctx_engines_extensions), &set); - if (err) { - kfree(set.engines); - return err; - } + if (err) + goto err_extensions; pc->num_user_engines = set.num_engines; pc->user_engines = set.engines; return 0; + +err_extensions: + for (n = 0; n < set.num_engines; n++) + kfree(set.engines[n].siblings); +err: + kfree(set.engines); + + return err; } static int set_proto_ctx_sseu(struct drm_i915_file_private *fpriv, @@ -850,7 +856,7 @@ static int set_proto_ctx_sseu(struct drm_i915_file_private *fpriv, pe = &pc->user_engines[idx]; /* Only render engine supports RPCS configuration. */ - if (pe->engine->class != RENDER_CLASS) + if (!pe->engine || pe->engine->class != RENDER_CLASS) return -EINVAL; sseu = &pe->sseu; diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c index 1359fc9cb88e..e693b0c9d2a3 100644 --- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c +++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c @@ -3932,11 +3932,11 @@ execlists_create_virtual(struct intel_engine_cs **siblings, unsigned int count, struct drm_i915_private *i915 = siblings[0]->i915; struct virtual_engine *ve; unsigned int n; - int err; + int err = -ENOMEM; ve = kzalloc_flex(*ve, siblings, count); if (!ve) - return ERR_PTR(-ENOMEM); + goto err; ve->base.i915 = i915; ve->base.gt = siblings[0]->gt; @@ -3968,10 +3968,8 @@ execlists_create_virtual(struct intel_engine_cs **siblings, unsigned int count, intel_engine_init_execlists(&ve->base); ve->base.sched_engine = i915_sched_engine_create(ENGINE_VIRTUAL); - if (!ve->base.sched_engine) { - err = -ENOMEM; - goto err_put; - } + if (!ve->base.sched_engine) + goto err_noput; ve->base.sched_engine->private_data = &ve->base; ve->base.cops = &virtual_context_ops; @@ -3987,10 +3985,8 @@ execlists_create_virtual(struct intel_engine_cs **siblings, unsigned int count, intel_context_init(&ve->context, &ve->base); ve->base.breadcrumbs = intel_breadcrumbs_create(NULL); - if (!ve->base.breadcrumbs) { - err = -ENOMEM; + if (!ve->base.breadcrumbs) goto err_put; - } for (n = 0; n < count; n++) { struct intel_engine_cs *sibling = siblings[n]; @@ -4065,8 +4061,13 @@ execlists_create_virtual(struct intel_engine_cs **siblings, unsigned int count, virtual_engine_initial_hint(ve); return &ve->context; +err_noput: + kfree(ve); + goto err; + err_put: intel_context_put(&ve->context); +err: return ERR_PTR(err); } diff --git a/drivers/gpu/drm/imagination/pvr_context.c b/drivers/gpu/drm/imagination/pvr_context.c index 52e16c1e7af0..406e0758e860 100644 --- a/drivers/gpu/drm/imagination/pvr_context.c +++ b/drivers/gpu/drm/imagination/pvr_context.c @@ -309,8 +309,8 @@ int pvr_context_create(struct pvr_file *pvr_file, struct drm_pvr_ioctl_create_co goto err_free_ctx; ctx->vm_ctx = pvr_vm_context_lookup(pvr_file, args->vm_context_handle); - if (IS_ERR(ctx->vm_ctx)) { - err = PTR_ERR(ctx->vm_ctx); + if (!ctx->vm_ctx) { + err = -EINVAL; goto err_free_ctx; } diff --git a/drivers/gpu/drm/imagination/pvr_fw_trace.c b/drivers/gpu/drm/imagination/pvr_fw_trace.c index 6bb5baa6c41b..805d9f9bc1dd 100644 --- a/drivers/gpu/drm/imagination/pvr_fw_trace.c +++ b/drivers/gpu/drm/imagination/pvr_fw_trace.c @@ -71,7 +71,7 @@ pvr_fw_trace_init_mask_set(const char *val, const struct kernel_param *kp) return 0; } -const struct kernel_param_ops pvr_fw_trace_init_mask_ops = { +static const struct kernel_param_ops pvr_fw_trace_init_mask_ops = { .set = pvr_fw_trace_init_mask_set, .get = param_get_hexint, }; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.c index 107bdb642f22..190c082b12c8 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.c @@ -231,29 +231,26 @@ nvkm_vmm_unref_sptes(struct nvkm_vmm_iter *it, struct nvkm_vmm_pt *pgt, * covered by a number of LPTEs, the LPTEs once again take * control over their address range. * - * Determine how many LPTEs need to transition state. + * Transition each LPTE individually as each may have a + * different target state (sparse, invalid, or valid). */ - pgt->pte[ptei].s.spte_valid = false; - for (ptes = 1, ptei++; ptei < lpti; ptes++, ptei++) { + for (ptei++; ptei < lpti; ptei++) { if (pgt->pte[ptei].s.sptes) break; - pgt->pte[ptei].s.spte_valid = false; } - if (pgt->pte[pteb].s.sparse) { - TRA(it, "LPTE %05x: U -> S %d PTEs", pteb, ptes); - pair->func->sparse(vmm, pgt->pt[0], pteb, ptes); - } else if (!pgt->pte[pteb].s.lpte_valid) { - if (pair->func->invalid) { - /* If the MMU supports it, restore the LPTE to the - * INVALID state to tell the MMU there is no point - * trying to fetch the corresponding SPTEs. - */ - TRA(it, "LPTE %05x: U -> I %d PTEs", pteb, ptes); - pair->func->invalid(vmm, pgt->pt[0], pteb, ptes); + while (pteb < ptei) { + pgt->pte[pteb].s.spte_valid = false; + if (pgt->pte[pteb].s.sparse) { + TRA(it, "LPTE %05x: U -> S", pteb); + pair->func->sparse(vmm, pgt->pt[0], pteb, 1); + } else if (!pgt->pte[pteb].s.lpte_valid) { + if (pair->func->invalid) { + TRA(it, "LPTE %05x: U -> I", pteb); + pair->func->invalid(vmm, pgt->pt[0], pteb, 1); + } } - } else { - TRA(it, "LPTE %05x: V %d PTEs", pteb, ptes); + pteb++; } } } diff --git a/drivers/gpu/drm/tests/drm_exec_test.c b/drivers/gpu/drm/tests/drm_exec_test.c index 2fc47f3b463b..7a374e462348 100644 --- a/drivers/gpu/drm/tests/drm_exec_test.c +++ b/drivers/gpu/drm/tests/drm_exec_test.c @@ -180,19 +180,27 @@ static void test_multiple_loops(struct kunit *test) { struct drm_exec exec; - drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT, 0); - drm_exec_until_all_locked(&exec) { - break; - } - drm_exec_fini(&exec); + __label__ drm_exec_retry; - drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT, 0); - drm_exec_until_all_locked(&exec) - { - break; + drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT, 0); + drm_exec_until_all_locked(&exec) + { + break; + } + drm_exec_fini(&exec); + } + + { + __label__ drm_exec_retry; + + drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT, 0); + drm_exec_until_all_locked(&exec) + { + break; + } + drm_exec_fini(&exec); } - drm_exec_fini(&exec); KUNIT_SUCCEED(test); } diff --git a/drivers/gpu/drm/v3d/v3d_submit.c b/drivers/gpu/drm/v3d/v3d_submit.c index 1db43c6a078d..7682b24f13ec 100644 --- a/drivers/gpu/drm/v3d/v3d_submit.c +++ b/drivers/gpu/drm/v3d/v3d_submit.c @@ -495,6 +495,8 @@ v3d_get_cpu_indirect_csd_params(struct drm_file *file_priv, sizeof(indirect_csd.wg_uniform_offsets)); info->indirect = drm_gem_object_lookup(file_priv, indirect_csd.indirect); + if (!info->indirect) + return -ENOENT; return v3d_setup_csd_jobs_and_bos(file_priv, v3d, &indirect_csd.submit, &info->job, &info->clean_job, diff --git a/drivers/gpu/drm/xe/tests/xe_pci.c b/drivers/gpu/drm/xe/tests/xe_pci.c index 9240aff779da..c2c686aed1cb 100644 --- a/drivers/gpu/drm/xe/tests/xe_pci.c +++ b/drivers/gpu/drm/xe/tests/xe_pci.c @@ -9,7 +9,6 @@ #include #include -#include #include #define PLATFORM_CASE(platform__, graphics_step__) \ diff --git a/drivers/gpu/drm/xe/xe_exec.c b/drivers/gpu/drm/xe/xe_exec.c index e05dabfcd43c..d5293bc33a67 100644 --- a/drivers/gpu/drm/xe/xe_exec.c +++ b/drivers/gpu/drm/xe/xe_exec.c @@ -292,13 +292,23 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file) goto err_exec; } - /* Wait behind rebinds */ + /* + * Wait behind rebinds and any kernel operations (evictions, defrag + * moves, ...) on the VM and all external BOs. The VM's private BOs + * carry their kernel ops in the VM dma-resv KERNEL slot, while each + * external BO carries them in its own dma-resv KERNEL slot; both are + * covered by iterating every object locked by the exec, mirroring the + * drm_gpuvm_resv_add_fence() below. + */ if (!xe_vm_in_lr_mode(vm)) { - err = xe_sched_job_add_deps(job, - xe_vm_resv(vm), - DMA_RESV_USAGE_KERNEL); - if (err) - goto err_put_job; + struct drm_gem_object *obj; + + drm_exec_for_each_locked_object(exec, obj) { + err = xe_sched_job_add_deps(job, obj->resv, + DMA_RESV_USAGE_KERNEL); + if (err) + goto err_put_job; + } } for (i = 0; i < num_syncs && !err; i++) diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c index 670bc2206fea..e787c0c27c42 100644 --- a/drivers/gpu/drm/xe/xe_pt.c +++ b/drivers/gpu/drm/xe/xe_pt.c @@ -1026,12 +1026,22 @@ xe_vm_populate_pgtable(struct xe_migrate_pt_update *pt_update, struct xe_tile *t u64 *ptr = data; u32 i; + /* + * @qword_ofs is the absolute entry offset within the page table, while + * @ptes is indexed relative to @update->ofs (its first entry). The GPU + * path (write_pgtable) splits a single update into MAX_PTE_PER_SDI-sized + * chunks, calling this with an advancing @qword_ofs but a fresh @data + * pointer per chunk, so translate back into a @ptes index rather than + * assuming the chunk starts at ptes[0]. + */ for (i = 0; i < num_qwords; i++) { + u32 idx = qword_ofs - update->ofs + i; + if (map) xe_map_wr(tile_to_xe(tile), map, (qword_ofs + i) * - sizeof(u64), u64, ptes[i].pte); + sizeof(u64), u64, ptes[idx].pte); else - ptr[i] = ptes[i].pte; + ptr[i] = ptes[idx].pte; } } @@ -1408,6 +1418,7 @@ static int xe_pt_pre_commit(struct xe_migrate_pt_update *pt_update) pt_update_ops, rftree); } +#if IS_ENABLED(CONFIG_DRM_GPUSVM) /* * Acquire/release the svm notifier_lock around xe_pt_svm_userptr_pre_commit() * and the matching late release in xe_pt_update_ops_run(). Read mode by @@ -1434,6 +1445,10 @@ static void xe_pt_svm_userptr_notifier_unlock(struct xe_vm *vm) xe_svm_notifier_unlock(vm); #endif } +#else +static inline void xe_pt_svm_userptr_notifier_lock(struct xe_vm *vm) { } +static inline void xe_pt_svm_userptr_notifier_unlock(struct xe_vm *vm) { } +#endif #if IS_ENABLED(CONFIG_DRM_GPUSVM) #ifdef CONFIG_DRM_XE_USERPTR_INVAL_INJECT diff --git a/drivers/gpu/drm/xe/xe_vm_madvise.c b/drivers/gpu/drm/xe/xe_vm_madvise.c index c4fb29004195..246fe1843142 100644 --- a/drivers/gpu/drm/xe/xe_vm_madvise.c +++ b/drivers/gpu/drm/xe/xe_vm_madvise.c @@ -643,7 +643,7 @@ int xe_vm_madvise_ioctl(struct drm_device *dev, void *data, struct drm_file *fil xe_device_is_l2_flush_optimized(xe) && (pat_index != 19 && coh_mode != XE_COH_2WAY))) { err = -EINVAL; - goto madv_fini; + goto free_vmas; } } diff --git a/drivers/hid/bpf/hid_bpf_dispatch.c b/drivers/hid/bpf/hid_bpf_dispatch.c index d0130658091b..536f6d01fd14 100644 --- a/drivers/hid/bpf/hid_bpf_dispatch.c +++ b/drivers/hid/bpf/hid_bpf_dispatch.c @@ -17,6 +17,7 @@ #include #include #include +#include #include "hid_bpf_dispatch.h" const struct hid_ops *hid_ops; @@ -296,10 +297,12 @@ __bpf_kfunc __u8 * hid_bpf_get_data(struct hid_bpf_ctx *ctx, unsigned int offset, const size_t rdwr_buf_size) { struct hid_bpf_ctx_kern *ctx_kern; + size_t end; ctx_kern = container_of(ctx, struct hid_bpf_ctx_kern, ctx); - if (rdwr_buf_size + offset > ctx->allocated_size) + if (check_add_overflow(rdwr_buf_size, offset, &end) || + end > ctx->allocated_size) return NULL; return ctx_kern->data + offset; diff --git a/drivers/hid/hid-appleir.c b/drivers/hid/hid-appleir.c index 5e8ced7bc05a..adaa44a858ed 100644 --- a/drivers/hid/hid-appleir.c +++ b/drivers/hid/hid-appleir.c @@ -109,9 +109,10 @@ struct appleir { struct hid_device *hid; unsigned short keymap[ARRAY_SIZE(appleir_key_table)]; struct timer_list key_up_timer; /* timer for key up */ - spinlock_t lock; /* protects .current_key */ + spinlock_t lock; /* protects .current_key, .removing */ int current_key; /* the currently pressed key */ int prev_key_idx; /* key index in a 2 packets message */ + bool removing; /* set during teardown; gates input_dev access */ }; static int get_key(int data) @@ -172,7 +173,7 @@ static void key_up_tick(struct timer_list *t) unsigned long flags; spin_lock_irqsave(&appleir->lock, flags); - if (appleir->current_key) { + if (!appleir->removing && appleir->current_key) { key_up(hid, appleir, appleir->current_key); appleir->current_key = 0; } @@ -195,6 +196,10 @@ static int appleir_raw_event(struct hid_device *hid, struct hid_report *report, int index; spin_lock_irqsave(&appleir->lock, flags); + if (appleir->removing) { + spin_unlock_irqrestore(&appleir->lock, flags); + goto out; + } /* * If we already have a key down, take it up before marking * this one down @@ -229,17 +234,25 @@ static int appleir_raw_event(struct hid_device *hid, struct hid_report *report, appleir->prev_key_idx = 0; if (!memcmp(data, keyrepeat, sizeof(keyrepeat))) { - key_down(hid, appleir, appleir->current_key); - /* - * Remote doesn't do key up, either pull them up, in the test - * above, or here set a timer which pulls them up after 1/8 s - */ - mod_timer(&appleir->key_up_timer, jiffies + HZ / 8); + spin_lock_irqsave(&appleir->lock, flags); + if (!appleir->removing) { + key_down(hid, appleir, appleir->current_key); + /* + * Remote doesn't do key up, either pull them up, in + * the test above, or here set a timer which pulls them + * up after 1/8 s + */ + mod_timer(&appleir->key_up_timer, jiffies + HZ / 8); + } + spin_unlock_irqrestore(&appleir->lock, flags); goto out; } if (!memcmp(data, flatbattery, sizeof(flatbattery))) { - battery_flat(appleir); + spin_lock_irqsave(&appleir->lock, flags); + if (!appleir->removing) + battery_flat(appleir); + spin_unlock_irqrestore(&appleir->lock, flags); /* Fall through */ } @@ -318,8 +331,20 @@ static int appleir_probe(struct hid_device *hid, const struct hid_device_id *id) static void appleir_remove(struct hid_device *hid) { struct appleir *appleir = hid_get_drvdata(hid); + unsigned long flags; + + /* + * Mark the driver as tearing down so that any concurrent raw_event + * (e.g. from a USB URB completion that hid_hw_stop() has not yet + * killed) and the key_up_timer softirq stop touching input_dev + * before hid_hw_stop() frees it via hidinput_disconnect(). + */ + spin_lock_irqsave(&appleir->lock, flags); + appleir->removing = true; + spin_unlock_irqrestore(&appleir->lock, flags); + + timer_shutdown_sync(&appleir->key_up_timer); hid_hw_stop(hid); - timer_delete_sync(&appleir->key_up_timer); } static const struct hid_device_id appleir_devices[] = { diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index 41a79e43c82b..cf123347a2af 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -2045,6 +2045,13 @@ int hid_report_raw_event(struct hid_device *hid, enum hid_report_type type, u8 * u8 *cdata = data; int ret = 0; + if (report_enum->numbered && (size < 1 || bufsize < 1)) { + hid_warn_ratelimited(hid, + "Event data for numbered report is too short (%d vs %zu)\n", + size, bufsize); + return -EINVAL; + } + report = hid_get_report(report_enum, data); if (!report) return 0; diff --git a/drivers/hid/hid-letsketch.c b/drivers/hid/hid-letsketch.c index 11e21f988723..b52e93a91ae5 100644 --- a/drivers/hid/hid-letsketch.c +++ b/drivers/hid/hid-letsketch.c @@ -296,13 +296,42 @@ static int letsketch_probe(struct hid_device *hdev, const struct hid_device_id * ret = letsketch_setup_input_tablet(data); if (ret) - return ret; + goto err_shutdown_timer; ret = letsketch_setup_input_tablet_pad(data); if (ret) - return ret; + goto err_shutdown_timer; - return hid_hw_start(hdev, HID_CONNECT_HIDRAW); + ret = hid_hw_start(hdev, HID_CONNECT_HIDRAW); + if (ret) + goto err_shutdown_timer; + + return 0; + +err_shutdown_timer: + /* + * Drain any pending callback and permanently disable the timer + * before devm releases data: if hid_hw_start() enabled I/O on an + * always-poll-quirk device and then failed, raw_event may have + * armed the timer already. + */ + timer_shutdown_sync(&data->inrange_timer); + return ret; +} + +static void letsketch_remove(struct hid_device *hdev) +{ + struct letsketch_data *data = hid_get_drvdata(hdev); + + /* + * hid_hw_stop() synchronously kills the URBs that deliver + * raw_event(), so once it returns no path can re-arm + * inrange_timer. timer_shutdown_sync() then drains any + * in-flight callback and permanently disables further + * mod_timer() calls before devm releases data. + */ + hid_hw_stop(hdev); + timer_shutdown_sync(&data->inrange_timer); } static const struct hid_device_id letsketch_devices[] = { @@ -315,6 +344,7 @@ static struct hid_driver letsketch_driver = { .name = "letsketch", .id_table = letsketch_devices, .probe = letsketch_probe, + .remove = letsketch_remove, .raw_event = letsketch_raw_event, }; module_hid_driver(letsketch_driver); diff --git a/drivers/hid/hid-lg-g15.c b/drivers/hid/hid-lg-g15.c index 1a88bc44ada4..02ef3e2094b4 100644 --- a/drivers/hid/hid-lg-g15.c +++ b/drivers/hid/hid-lg-g15.c @@ -1374,11 +1374,27 @@ static const struct hid_device_id lg_g15_devices[] = { }; MODULE_DEVICE_TABLE(hid, lg_g15_devices); +static void lg_g15_remove(struct hid_device *hdev) +{ + struct lg_g15_data *g15 = hid_get_drvdata(hdev); + + /* + * g15->work is only initialized for the models that schedule it + * (G15, G15 v2, G510). The G13 and Z-10 leave it zeroed, so only + * cancel it when it was set up. + */ + if (g15 && g15->work.func) + cancel_work_sync(&g15->work); + + hid_hw_stop(hdev); +} + static struct hid_driver lg_g15_driver = { .name = "lg-g15", .id_table = lg_g15_devices, .raw_event = lg_g15_raw_event, .probe = lg_g15_probe, + .remove = lg_g15_remove, }; module_hid_driver(lg_g15_driver); diff --git a/drivers/hid/hid-logitech-dj.c b/drivers/hid/hid-logitech-dj.c index 381e4dc5aba7..9c574ab8b60b 100644 --- a/drivers/hid/hid-logitech-dj.c +++ b/drivers/hid/hid-logitech-dj.c @@ -1907,8 +1907,13 @@ static int logi_dj_probe(struct hid_device *hdev, output_report_enum = &hdev->report_enum[HID_OUTPUT_REPORT]; rep = output_report_enum->report_id_hash[REPORT_ID_DJ_SHORT]; - if (rep && (rep->maxfield < 1 || - rep->field[0]->report_count != DJREPORT_SHORT_LENGTH - 1)) { + if (rep && rep->maxfield < 1) { + hid_err(hdev, "Expected size of DJ short report is %d, but got 0", + DJREPORT_SHORT_LENGTH - 1); + return -EINVAL; + } + + if (rep && rep->field[0]->report_count != DJREPORT_SHORT_LENGTH - 1) { hid_err(hdev, "Expected size of DJ short report is %d, but got %d", DJREPORT_SHORT_LENGTH - 1, rep->field[0]->report_count); return -EINVAL; diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c index 0495152091e3..edb37b4c867e 100644 --- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -31,6 +31,7 @@ * [1] https://gitlab.freedesktop.org/libevdev/hid-tools */ +#include #include #include #include @@ -97,8 +98,7 @@ enum report_mode { TOUCHPAD_REPORT_ALL = TOUCHPAD_REPORT_BUTTONS | TOUCHPAD_REPORT_CONTACTS, }; -#define MT_IO_SLOTS_MASK GENMASK(7, 0) /* reserve first 8 bits for slot tracking */ -#define MT_IO_FLAGS_RUNNING 32 +#define MT_IO_FLAGS_RUNNING 0 static const bool mtrue = true; /* default for true */ static const bool mfalse; /* default for false */ @@ -174,10 +174,9 @@ struct mt_device { struct timer_list release_timer; /* to release sticky fingers */ struct hid_haptic_device *haptic; /* haptic related configuration */ struct hid_device *hdev; /* hid_device we're attached to */ - unsigned long mt_io_flags; /* mt flags (MT_IO_FLAGS_RUNNING) - * first 8 bits are reserved for keeping the slot - * states, this is fine because we only support up - * to 250 slots (MT_MAX_MAXCONTACT) + unsigned long mt_io_flags; /* mt flags (MT_IO_FLAGS_RUNNING) */ + unsigned long *active_slots; /* bitmap of slots with an active + * contact, sized for maxcontacts */ __u8 inputmode_value; /* InputMode HID feature value */ __u8 maxcontacts; @@ -1036,7 +1035,7 @@ static void mt_release_pending_palms(struct mt_device *td, for_each_set_bit(slotnum, app->pending_palm_slots, td->maxcontacts) { clear_bit(slotnum, app->pending_palm_slots); - clear_bit(slotnum, &td->mt_io_flags); + clear_bit(slotnum, td->active_slots); input_mt_slot(input, slotnum); input_mt_report_slot_inactive(input); @@ -1247,9 +1246,9 @@ static int mt_process_slot(struct mt_device *td, struct input_dev *input, input_event(input, EV_ABS, ABS_MT_TOUCH_MAJOR, major); input_event(input, EV_ABS, ABS_MT_TOUCH_MINOR, minor); - set_bit(slotnum, &td->mt_io_flags); + set_bit(slotnum, td->active_slots); } else { - clear_bit(slotnum, &td->mt_io_flags); + clear_bit(slotnum, td->active_slots); } return 0; @@ -1384,7 +1383,7 @@ static void mt_touch_report(struct hid_device *hid, * defect. */ if (app->quirks & MT_QUIRK_STICKY_FINGERS) { - if (td->mt_io_flags & MT_IO_SLOTS_MASK) + if (!bitmap_empty(td->active_slots, td->maxcontacts)) mod_timer(&td->release_timer, jiffies + msecs_to_jiffies(100)); else @@ -1443,6 +1442,15 @@ static int mt_touch_input_configured(struct hid_device *hdev, if (td->is_pressurepad) __set_bit(INPUT_PROP_PRESSUREPAD, input->propbit); + if (!td->active_slots) { + td->active_slots = devm_kcalloc(&td->hdev->dev, + BITS_TO_LONGS(td->maxcontacts), + sizeof(long), + GFP_KERNEL); + if (!td->active_slots) + return -ENOMEM; + } + app->pending_palm_slots = devm_kcalloc(&hi->input->dev, BITS_TO_LONGS(td->maxcontacts), sizeof(long), @@ -2062,7 +2070,7 @@ static void mt_release_contacts(struct hid_device *hid) for (i = 0; i < mt->num_slots; i++) { input_mt_slot(input_dev, i); input_mt_report_slot_inactive(input_dev); - clear_bit(i, &td->mt_io_flags); + clear_bit(i, td->active_slots); } input_mt_sync_frame(input_dev); input_sync(input_dev); @@ -2085,7 +2093,7 @@ static void mt_expired_timeout(struct timer_list *t) */ if (test_and_set_bit_lock(MT_IO_FLAGS_RUNNING, &td->mt_io_flags)) return; - if (td->mt_io_flags & MT_IO_SLOTS_MASK) + if (!bitmap_empty(td->active_slots, td->maxcontacts)) mt_release_contacts(hdev); clear_bit_unlock(MT_IO_FLAGS_RUNNING, &td->mt_io_flags); } diff --git a/drivers/hid/hid-picolcd_core.c b/drivers/hid/hid-picolcd_core.c index 2cc01e1bc1a8..d73e97c8b853 100644 --- a/drivers/hid/hid-picolcd_core.c +++ b/drivers/hid/hid-picolcd_core.c @@ -72,7 +72,8 @@ struct picolcd_pending *picolcd_send_and_wait(struct hid_device *hdev, struct picolcd_pending *work; struct hid_report *report = picolcd_out_report(report_id, hdev); unsigned long flags; - int i, j, k; + int i, j; + unsigned int k; if (!report || !data) return NULL; diff --git a/drivers/hid/hid-sensor-hub.c b/drivers/hid/hid-sensor-hub.c index 90666ff629de..34f710c465b8 100644 --- a/drivers/hid/hid-sensor-hub.c +++ b/drivers/hid/hid-sensor-hub.c @@ -286,6 +286,54 @@ int sensor_hub_get_feature(struct hid_sensor_hub_device *hsdev, u32 report_id, } EXPORT_SYMBOL_GPL(sensor_hub_get_feature); +int sensor_hub_input_attr_read_values(struct hid_sensor_hub_device *hsdev, + u32 usage_id, u32 attr_usage_id, + u32 report_id, + enum sensor_hub_read_flags flag, + u32 buffer_size, u8 *buffer) +{ + struct sensor_hub_data *data = hid_get_drvdata(hsdev->hdev); + struct hid_report *report; + unsigned long flags; + long cycles; + int ret; + + report = sensor_hub_report(report_id, hsdev->hdev, HID_INPUT_REPORT); + if (!report) + return -EINVAL; + + mutex_lock(hsdev->mutex_ptr); + if (flag == SENSOR_HUB_SYNC) { + memset(&hsdev->pending, 0, sizeof(hsdev->pending)); + init_completion(&hsdev->pending.ready); + hsdev->pending.usage_id = usage_id; + hsdev->pending.attr_usage_id = attr_usage_id; + hsdev->pending.max_raw_size = buffer_size; + hsdev->pending.raw_data = buffer; + + spin_lock_irqsave(&data->lock, flags); + hsdev->pending.status = true; + spin_unlock_irqrestore(&data->lock, flags); + } + mutex_lock(&data->mutex); + hid_hw_request(hsdev->hdev, report, HID_REQ_GET_REPORT); + mutex_unlock(&data->mutex); + ret = 0; + if (flag == SENSOR_HUB_SYNC) { + cycles = wait_for_completion_interruptible_timeout(&hsdev->pending.ready, + HZ * 5); + if (cycles == 0) + ret = -ETIMEDOUT; + else if (cycles < 0) + ret = cycles; + + hsdev->pending.status = false; + } + mutex_unlock(hsdev->mutex_ptr); + + return ret; +} +EXPORT_SYMBOL_GPL(sensor_hub_input_attr_read_values); int sensor_hub_input_attr_get_raw_value(struct hid_sensor_hub_device *hsdev, u32 usage_id, @@ -478,6 +526,8 @@ static int sensor_hub_raw_event(struct hid_device *hdev, struct hid_collection *collection = NULL; void *priv = NULL; struct hid_sensor_hub_device *hsdev = NULL; + u32 copy_size; + u32 avail; hid_dbg(hdev, "sensor_hub_raw_event report id:0x%x size:%d type:%d\n", report->id, size, report->type); @@ -518,12 +568,27 @@ static int sensor_hub_raw_event(struct hid_device *hdev, hsdev->pending.attr_usage_id == report->field[i]->logical)) { hid_dbg(hdev, "data was pending ...\n"); - hsdev->pending.raw_data = kmemdup(ptr, sz, GFP_ATOMIC); - if (hsdev->pending.raw_data) - hsdev->pending.raw_size = sz; - else - hsdev->pending.raw_size = 0; - complete(&hsdev->pending.ready); + if (hsdev->pending.max_raw_size) { + if (hsdev->pending.index < hsdev->pending.max_raw_size) { + avail = hsdev->pending.max_raw_size - hsdev->pending.index; + copy_size = clamp(sz, 0U, avail); + + memcpy(hsdev->pending.raw_data + hsdev->pending.index, + ptr, copy_size); + hsdev->pending.index += copy_size; + if (hsdev->pending.index >= hsdev->pending.max_raw_size) { + hsdev->pending.raw_size = hsdev->pending.index; + complete(&hsdev->pending.ready); + } + } + } else { + hsdev->pending.raw_data = kmemdup(ptr, sz, GFP_ATOMIC); + if (hsdev->pending.raw_data) + hsdev->pending.raw_size = sz; + else + hsdev->pending.raw_size = 0; + complete(&hsdev->pending.ready); + } } if (callback->capture_sample) { if (report->field[i]->logical) diff --git a/drivers/iio/accel/bmc150-accel-core.c b/drivers/iio/accel/bmc150-accel-core.c index 2398eb7e12cd..dc8a6285cf3d 100644 --- a/drivers/iio/accel/bmc150-accel-core.c +++ b/drivers/iio/accel/bmc150-accel-core.c @@ -991,6 +991,8 @@ static int __bmc150_accel_fifo_flush(struct iio_dev *indio_dev, if (samples && count > samples) count = samples; + count = min_t(u8, count, BMC150_ACCEL_FIFO_LENGTH); + ret = bmc150_accel_fifo_transfer(data, (u8 *)buffer, count); if (ret) return ret; diff --git a/drivers/iio/accel/kxsd9.c b/drivers/iio/accel/kxsd9.c index 4717d80fc24a..7ac885d94d7f 100644 --- a/drivers/iio/accel/kxsd9.c +++ b/drivers/iio/accel/kxsd9.c @@ -147,8 +147,9 @@ static int kxsd9_write_raw(struct iio_dev *indio_dev, if (mask == IIO_CHAN_INFO_SCALE) { /* Check no integer component */ if (val) - return -EINVAL; - ret = kxsd9_write_scale(indio_dev, val2); + ret = -EINVAL; + else + ret = kxsd9_write_scale(indio_dev, val2); } pm_runtime_put_autosuspend(st->dev); diff --git a/drivers/iio/adc/Kconfig b/drivers/iio/adc/Kconfig index 1c663c98c6c9..3755a81c1efd 100644 --- a/drivers/iio/adc/Kconfig +++ b/drivers/iio/adc/Kconfig @@ -108,6 +108,7 @@ config AD4130 depends on SPI depends on GPIOLIB select IIO_BUFFER + select IIO_TRIGGERED_BUFFER select IIO_KFIFO_BUF select REGMAP_SPI depends on COMMON_CLK @@ -328,6 +329,7 @@ config AD7298 config AD7380 tristate "Analog Devices AD7380 ADC driver" depends on SPI_MASTER + select REGMAP select SPI_OFFLOAD select IIO_BUFFER select IIO_BUFFER_DMAENGINE @@ -452,6 +454,7 @@ config AD7779 depends on SPI select CRC8 select IIO_BUFFER + select IIO_TRIGGERED_BUFFER select IIO_BACKEND help Say yes here to build support for Analog Devices AD777X family diff --git a/drivers/iio/adc/lpc32xx_adc.c b/drivers/iio/adc/lpc32xx_adc.c index 0128d003f960..32a15d193d97 100644 --- a/drivers/iio/adc/lpc32xx_adc.c +++ b/drivers/iio/adc/lpc32xx_adc.c @@ -178,6 +178,8 @@ static int lpc32xx_adc_probe(struct platform_device *pdev) if (irq < 0) return irq; + init_completion(&st->completion); + retval = devm_request_irq(&pdev->dev, irq, lpc32xx_adc_isr, 0, LPC32XXAD_NAME, st); if (retval < 0) { @@ -196,8 +198,6 @@ static int lpc32xx_adc_probe(struct platform_device *pdev) platform_set_drvdata(pdev, iodev); - init_completion(&st->completion); - iodev->name = LPC32XXAD_NAME; iodev->info = &lpc32xx_adc_iio_info; iodev->modes = INDIO_DIRECT_MODE; diff --git a/drivers/iio/adc/nxp-sar-adc.c b/drivers/iio/adc/nxp-sar-adc.c index 35b81331fdee..894d3211b283 100644 --- a/drivers/iio/adc/nxp-sar-adc.c +++ b/drivers/iio/adc/nxp-sar-adc.c @@ -197,13 +197,13 @@ static void nxp_sar_adc_irq_cfg(struct nxp_sar_adc *info, bool enable) writel(0, NXP_SAR_ADC_IMR(info->regs)); } -static void nxp_sar_adc_wait_for(struct nxp_sar_adc *info, unsigned int cycles) +static void nxp_sar_adc_wait_for(struct nxp_sar_adc *info, u64 cycles) { u64 rate; rate = clk_get_rate(info->clk); if (rate) - ndelay(div64_u64(NSEC_PER_SEC, rate * cycles)); + ndelay(div64_u64(NSEC_PER_SEC * cycles, rate)); } static bool nxp_sar_adc_set_enabled(struct nxp_sar_adc *info, bool enable) diff --git a/drivers/iio/adc/spear_adc.c b/drivers/iio/adc/spear_adc.c index bdb3ca8f229a..91c0fb1f4da7 100644 --- a/drivers/iio/adc/spear_adc.c +++ b/drivers/iio/adc/spear_adc.c @@ -282,6 +282,7 @@ static int spear_adc_probe(struct platform_device *pdev) st = iio_priv(indio_dev); st->dev = dev; + init_completion(&st->completion); mutex_init(&st->lock); /* @@ -328,8 +329,6 @@ static int spear_adc_probe(struct platform_device *pdev) spear_adc_configure(st); - init_completion(&st->completion); - indio_dev->name = SPEAR_ADC_MOD_NAME; indio_dev->info = &spear_adc_info; indio_dev->modes = INDIO_DIRECT_MODE; diff --git a/drivers/iio/adc/ti-ads1119.c b/drivers/iio/adc/ti-ads1119.c index d31f3d6eb781..b0f04741ddc6 100644 --- a/drivers/iio/adc/ti-ads1119.c +++ b/drivers/iio/adc/ti-ads1119.c @@ -459,7 +459,11 @@ static int ads1119_triggered_buffer_preenable(struct iio_dev *indio_dev) if (ret) return ret; - return i2c_smbus_write_byte(st->client, ADS1119_CMD_START_SYNC); + ret = i2c_smbus_write_byte(st->client, ADS1119_CMD_START_SYNC); + if (ret) + pm_runtime_put_autosuspend(dev); + + return ret; } static int ads1119_triggered_buffer_postdisable(struct iio_dev *indio_dev) diff --git a/drivers/iio/adc/ti-ads124s08.c b/drivers/iio/adc/ti-ads124s08.c index 522b43118af6..45de47778809 100644 --- a/drivers/iio/adc/ti-ads124s08.c +++ b/drivers/iio/adc/ti-ads124s08.c @@ -320,7 +320,8 @@ static int ads124s_probe(struct spi_device *spi) ads124s_priv->reset_gpio = devm_gpiod_get_optional(&spi->dev, "reset", GPIOD_OUT_LOW); if (IS_ERR(ads124s_priv->reset_gpio)) - dev_info(&spi->dev, "Reset GPIO not defined\n"); + return dev_err_probe(&spi->dev, PTR_ERR(ads124s_priv->reset_gpio), + "Failed to get reset GPIO\n"); ads124s_priv->chip_info = &ads124s_chip_info_tbl[spi_id->driver_data]; diff --git a/drivers/iio/common/st_sensors/st_sensors_core.c b/drivers/iio/common/st_sensors/st_sensors_core.c index dbc5e16fbde4..76f91696f66a 100644 --- a/drivers/iio/common/st_sensors/st_sensors_core.c +++ b/drivers/iio/common/st_sensors/st_sensors_core.c @@ -498,6 +498,7 @@ static int st_sensors_read_axis_data(struct iio_dev *indio_dev, u8 *outdata; struct st_sensor_data *sdata = iio_priv(indio_dev); unsigned int byte_for_channel; + u32 tmp; byte_for_channel = DIV_ROUND_UP(ch->scan_type.realbits + ch->scan_type.shift, 8); @@ -508,12 +509,22 @@ static int st_sensors_read_axis_data(struct iio_dev *indio_dev, if (err < 0) return err; - if (byte_for_channel == 1) - *data = (s8)*outdata; - else if (byte_for_channel == 2) - *data = (s16)get_unaligned_le16(outdata); - else if (byte_for_channel == 3) - *data = (s32)sign_extend32(get_unaligned_le24(outdata), 23); + if (byte_for_channel == 1) { + tmp = *outdata; + } else if (byte_for_channel == 2) { + if (ch->scan_type.endianness == IIO_BE) + tmp = get_unaligned_be16(outdata); + else + tmp = get_unaligned_le16(outdata); + } else if (byte_for_channel == 3) { + if (ch->scan_type.endianness == IIO_BE) + tmp = get_unaligned_be24(outdata); + else + tmp = get_unaligned_le24(outdata); + } else { + return -EINVAL; + } + *data = sign_extend32(tmp, BYTES_TO_BITS(byte_for_channel) - 1); return 0; } diff --git a/drivers/iio/dac/mcp47feb02.c b/drivers/iio/dac/mcp47feb02.c index 5c0f3064df7a..8640b0ef4433 100644 --- a/drivers/iio/dac/mcp47feb02.c +++ b/drivers/iio/dac/mcp47feb02.c @@ -1135,26 +1135,33 @@ static int mcp47feb02_probe(struct i2c_client *client) vdd_uV = ret; - ret = devm_regulator_get_enable_read_voltage(dev, "vref"); - if (ret > 0) { - vref_uV = ret; + if (device_property_present(dev, "vref-supply")) { + vref_uV = devm_regulator_get_enable_read_voltage(dev, "vref"); + if (vref_uV < 0) + return vref_uV; + + if (vref_uV == 0) + return dev_err_probe(dev, -EINVAL, "Vref is 0 uV.\n"); + data->use_vref = true; } else { vref_uV = 0; - dev_dbg(dev, "using internal band gap as voltage reference.\n"); - dev_dbg(dev, "Vref is unavailable.\n"); + dev_dbg(dev, "Using internal band gap as voltage reference.\n"); } - if (chip_features->have_ext_vref1) { - ret = devm_regulator_get_enable_read_voltage(dev, "vref1"); - if (ret > 0) { - vref1_uV = ret; - data->use_vref1 = true; - } else { - vref1_uV = 0; - dev_dbg(dev, "using internal band gap as voltage reference 1.\n"); - dev_dbg(dev, "Vref1 is unavailable.\n"); - } + if (chip_features->have_ext_vref1 && + device_property_present(dev, "vref1-supply")) { + vref1_uV = devm_regulator_get_enable_read_voltage(dev, "vref1"); + if (vref1_uV < 0) + return vref1_uV; + + if (vref1_uV == 0) + return dev_err_probe(dev, -EINVAL, "Vref1 is 0 uV.\n"); + + data->use_vref1 = true; + } else { + vref1_uV = 0; + dev_dbg(dev, "Using internal band gap as voltage reference 1.\n"); } ret = mcp47feb02_init_ctrl_regs(data); diff --git a/drivers/iio/imu/adis_trigger.c b/drivers/iio/imu/adis_trigger.c index d76e13cbac68..3e6a7af6ab01 100644 --- a/drivers/iio/imu/adis_trigger.c +++ b/drivers/iio/imu/adis_trigger.c @@ -94,7 +94,7 @@ int devm_adis_probe_trigger(struct adis *adis, struct iio_dev *indio_dev) else ret = devm_request_irq(&adis->spi->dev, adis->spi->irq, &iio_trigger_generic_data_rdy_poll, - adis->irq_flag, + adis->irq_flag | IRQF_NO_THREAD, indio_dev->name, adis->trig); if (ret) diff --git a/drivers/iio/imu/bmi160/bmi160_core.c b/drivers/iio/imu/bmi160/bmi160_core.c index 4abb83b75e2e..86f6ecfd64aa 100644 --- a/drivers/iio/imu/bmi160/bmi160_core.c +++ b/drivers/iio/imu/bmi160/bmi160_core.c @@ -788,7 +788,8 @@ int bmi160_probe_trigger(struct iio_dev *indio_dev, int irq, u32 irq_type) ret = devm_request_irq(&indio_dev->dev, irq, &iio_trigger_generic_data_rdy_poll, - irq_type, "bmi160", data->trig); + irq_type | IRQF_NO_THREAD, + "bmi160", data->trig); if (ret) return ret; diff --git a/drivers/iio/imu/inv_icm42600/inv_icm42600_accel.c b/drivers/iio/imu/inv_icm42600/inv_icm42600_accel.c index 532d5fdffaf8..7df920ef3cf0 100644 --- a/drivers/iio/imu/inv_icm42600/inv_icm42600_accel.c +++ b/drivers/iio/imu/inv_icm42600/inv_icm42600_accel.c @@ -1170,10 +1170,10 @@ struct iio_dev *inv_icm42600_accel_init(struct inv_icm42600_state *st) accel_st->filter = INV_ICM42600_FILTER_AVG_16X; /* - * clock period is 32kHz (31250ns) + * clock period is 8kHz (125000ns) * jitter is +/- 2% (20 per mille) */ - ts_chip.clock_period = 31250; + ts_chip.clock_period = 125000; ts_chip.jitter = 20; ts_chip.init_period = inv_icm42600_odr_to_period(st->conf.accel.odr); inv_sensors_timestamp_init(&accel_st->ts, &ts_chip); diff --git a/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.c b/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.c index 68a395758031..5c3840acf085 100644 --- a/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.c +++ b/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.c @@ -248,6 +248,7 @@ int inv_icm42600_buffer_update_watermark(struct inv_icm42600_state *st) /* compute watermark value in bytes */ wm_size = watermark * packet_size; + st->fifo.watermark.value = watermark; /* changing FIFO watermark requires to turn off watermark interrupt */ ret = regmap_update_bits_check(st->map, INV_ICM42600_REG_INT_SOURCE0, @@ -454,11 +455,10 @@ int inv_icm42600_buffer_fifo_read(struct inv_icm42600_state *st, st->fifo.nb.accel = 0; st->fifo.nb.total = 0; - /* compute maximum FIFO read size */ + /* compute maximum FIFO read size (watermark for max = 0 interrupt case) */ if (max == 0) - max_count = sizeof(st->fifo.data); - else - max_count = max * inv_icm42600_get_packet_size(st->fifo.en); + max = st->fifo.watermark.value; + max_count = max * inv_icm42600_get_packet_size(st->fifo.en); /* read FIFO count value */ raw_fifo_count = (__be16 *)st->buffer; @@ -574,6 +574,7 @@ int inv_icm42600_buffer_init(struct inv_icm42600_state *st) st->fifo.watermark.eff_gyro = 1; st->fifo.watermark.eff_accel = 1; + st->fifo.watermark.value = 1; /* * Default FIFO configuration (bits 7 to 5) diff --git a/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.h b/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.h index ffca4da1e249..88b8b9f780af 100644 --- a/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.h +++ b/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.h @@ -34,6 +34,7 @@ struct inv_icm42600_fifo { unsigned int accel; unsigned int eff_gyro; unsigned int eff_accel; + unsigned int value; } watermark; size_t count; struct { diff --git a/drivers/iio/imu/inv_icm42600/inv_icm42600_gyro.c b/drivers/iio/imu/inv_icm42600/inv_icm42600_gyro.c index 11339ddf1da3..a18dcac93929 100644 --- a/drivers/iio/imu/inv_icm42600/inv_icm42600_gyro.c +++ b/drivers/iio/imu/inv_icm42600/inv_icm42600_gyro.c @@ -755,10 +755,10 @@ struct iio_dev *inv_icm42600_gyro_init(struct inv_icm42600_state *st) } /* - * clock period is 32kHz (31250ns) + * clock period is 8kHz (125000ns) * jitter is +/- 2% (20 per mille) */ - ts_chip.clock_period = 31250; + ts_chip.clock_period = 125000; ts_chip.jitter = 20; ts_chip.init_period = inv_icm42600_odr_to_period(st->conf.accel.odr); inv_sensors_timestamp_init(&gyro_st->ts, &ts_chip); diff --git a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c index 630e2cae6f19..f4edcb73ec8c 100644 --- a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c +++ b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c @@ -1712,6 +1712,26 @@ static int st_lsm6dsx_check_whoami(struct st_lsm6dsx_hw *hw, int id, return -ENODEV; } + hw->settings = &st_lsm6dsx_sensor_settings[i]; + + if (hw->settings->shub_settings.page_mux.addr) { + /* + * If the IMU has the shub page selected on init, for example + * after a CPU watchdog reset while the page is selected, the + * regular register space is shadowed. While the regular + * register space is shadowed, the registers needed for + * initializing the IMU are not available. + * + * Unconditionally clear the shub page selection to ensure + * normal register access. + */ + err = st_lsm6dsx_set_page(hw, false); + if (err < 0) { + dev_err(hw->dev, "failed to clear shub page\n"); + return err; + } + } + err = regmap_read(hw->regmap, ST_LSM6DSX_REG_WHOAMI_ADDR, &data); if (err < 0) { dev_err(hw->dev, "failed to read whoami register\n"); @@ -1724,7 +1744,6 @@ static int st_lsm6dsx_check_whoami(struct st_lsm6dsx_hw *hw, int id, } *name = st_lsm6dsx_sensor_settings[i].id[j].name; - hw->settings = &st_lsm6dsx_sensor_settings[i]; return 0; } diff --git a/drivers/iio/industrialio-event.c b/drivers/iio/industrialio-event.c index a0d6fcf2a9c9..e6730f52262a 100644 --- a/drivers/iio/industrialio-event.c +++ b/drivers/iio/industrialio-event.c @@ -207,6 +207,8 @@ static int iio_event_getfd(struct iio_dev *indio_dev) goto unlock; } + kfifo_reset_out(&ev_int->det_events); + iio_device_get(indio_dev); fd = anon_inode_getfd("iio:event", &iio_event_chrdev_fileops, @@ -214,10 +216,7 @@ static int iio_event_getfd(struct iio_dev *indio_dev) if (fd < 0) { clear_bit(IIO_BUSY_BIT_POS, &ev_int->flags); iio_device_put(indio_dev); - } else { - kfifo_reset_out(&ev_int->det_events); } - unlock: mutex_unlock(&iio_dev_opaque->mlock); return fd; diff --git a/drivers/iio/light/Kconfig b/drivers/iio/light/Kconfig index ef36824f312f..f23bbce12c72 100644 --- a/drivers/iio/light/Kconfig +++ b/drivers/iio/light/Kconfig @@ -45,6 +45,7 @@ config ADUX1020 config AL3000A tristate "AL3000a ambient light sensor" + select REGMAP_I2C depends on I2C help Say Y here if you want to build a driver for the Dyna Image AL3000a @@ -55,6 +56,7 @@ config AL3000A config AL3010 tristate "AL3010 ambient light sensor" + select REGMAP_I2C depends on I2C help Say Y here if you want to build a driver for the Dyna Image AL3010 @@ -65,6 +67,7 @@ config AL3010 config AL3320A tristate "AL3320A ambient light sensor" + select REGMAP_I2C depends on I2C help Say Y here if you want to build a driver for the Dyna Image AL3320A diff --git a/drivers/iio/light/al3010.c b/drivers/iio/light/al3010.c index 62a77acfd075..49f6d8336dbe 100644 --- a/drivers/iio/light/al3010.c +++ b/drivers/iio/light/al3010.c @@ -41,7 +41,7 @@ enum al3xxxx_range { }; static const int al3010_scales[][2] = { - {0, 1187200}, {0, 296800}, {0, 74200}, {0, 18600} + { 1, 187200 }, { 0, 296800 }, { 0, 74200 }, { 0, 18600 }, }; static const struct regmap_config al3010_regmap_config = { diff --git a/drivers/iio/light/gp2ap002.c b/drivers/iio/light/gp2ap002.c index c83f67ff2464..a8db514cca5e 100644 --- a/drivers/iio/light/gp2ap002.c +++ b/drivers/iio/light/gp2ap002.c @@ -258,7 +258,7 @@ static int gp2ap002_read_raw(struct iio_dev *indio_dev, case IIO_LIGHT: ret = gp2ap002_get_lux(gp2ap002); if (ret < 0) - return ret; + goto out; *val = ret; ret = IIO_VAL_INT; goto out; diff --git a/drivers/iio/light/tsl2591.c b/drivers/iio/light/tsl2591.c index f3ffa9721ad5..ef3ed9635a1e 100644 --- a/drivers/iio/light/tsl2591.c +++ b/drivers/iio/light/tsl2591.c @@ -1070,10 +1070,8 @@ static int tsl2591_probe(struct i2c_client *client) NULL, tsl2591_event_handler, IRQF_TRIGGER_FALLING | IRQF_ONESHOT, "tsl2591_irq", indio_dev); - if (ret) { - dev_err_probe(&client->dev, ret, "IRQ request error\n"); - return -EINVAL; - } + if (ret) + return ret; indio_dev->info = &tsl2591_info; } else { indio_dev->info = &tsl2591_info_no_irq; diff --git a/drivers/iio/orientation/hid-sensor-rotation.c b/drivers/iio/orientation/hid-sensor-rotation.c index 52d39c104560..cc3e66dbb90f 100644 --- a/drivers/iio/orientation/hid-sensor-rotation.c +++ b/drivers/iio/orientation/hid-sensor-rotation.c @@ -85,6 +85,13 @@ static int dev_rot_read_raw(struct iio_dev *indio_dev, long mask) { struct dev_rot_state *rot_state = iio_priv(indio_dev); + struct hid_sensor_hub_device *hsdev = rot_state->common_attributes.hsdev; + struct hid_sensor_hub_attribute_info *info = &rot_state->quaternion; + u32 usage_id = HID_USAGE_SENSOR_ORIENT_QUATERNION; + union { + s16 val16[4]; + s32 val32[4]; + } raw_buf; int ret_type; int i; @@ -94,8 +101,37 @@ static int dev_rot_read_raw(struct iio_dev *indio_dev, switch (mask) { case IIO_CHAN_INFO_RAW: if (size >= 4) { - for (i = 0; i < 4; ++i) - vals[i] = rot_state->scan.sampled_vals[i]; + if (info->size <= 0 || info->size > sizeof(raw_buf)) + return -EINVAL; + + hid_sensor_power_state(&rot_state->common_attributes, true); + + ret_type = sensor_hub_input_attr_read_values(hsdev, + hsdev->usage, + usage_id, + info->report_id, + SENSOR_HUB_SYNC, + info->size, + (u8 *)&raw_buf); + + hid_sensor_power_state(&rot_state->common_attributes, false); + + if (ret_type < 0) + return ret_type; + + switch (info->size) { + case sizeof(raw_buf.val16): + for (i = 0; i < ARRAY_SIZE(raw_buf.val16); i++) + vals[i] = raw_buf.val16[i]; + break; + case sizeof(raw_buf.val32): + for (i = 0; i < ARRAY_SIZE(raw_buf.val32); i++) + vals[i] = raw_buf.val32[i]; + break; + default: + return -EINVAL; + } + ret_type = IIO_VAL_INT_MULTIPLE; *val_len = 4; } else diff --git a/drivers/iio/pressure/mpl115.c b/drivers/iio/pressure/mpl115.c index 830a5065c008..16e112b796ba 100644 --- a/drivers/iio/pressure/mpl115.c +++ b/drivers/iio/pressure/mpl115.c @@ -106,18 +106,18 @@ static int mpl115_read_raw(struct iio_dev *indio_dev, case IIO_CHAN_INFO_PROCESSED: pm_runtime_get_sync(data->dev); ret = mpl115_comp_pressure(data, val, val2); + pm_runtime_put_autosuspend(data->dev); if (ret < 0) return ret; - pm_runtime_put_autosuspend(data->dev); return IIO_VAL_INT_PLUS_MICRO; case IIO_CHAN_INFO_RAW: pm_runtime_get_sync(data->dev); /* temperature -5.35 C / LSB, 472 LSB is 25 C */ ret = mpl115_read_temp(data); + pm_runtime_put_autosuspend(data->dev); if (ret < 0) return ret; - pm_runtime_put_autosuspend(data->dev); *val = ret >> 6; return IIO_VAL_INT; diff --git a/drivers/iio/temperature/Makefile b/drivers/iio/temperature/Makefile index 07d6e65709f7..0850bf691820 100644 --- a/drivers/iio/temperature/Makefile +++ b/drivers/iio/temperature/Makefile @@ -13,7 +13,7 @@ obj-$(CONFIG_MAX31865) += max31865.o obj-$(CONFIG_MCP9600) += mcp9600.o obj-$(CONFIG_MLX90614) += mlx90614.o obj-$(CONFIG_MLX90632) += mlx90632.o -obj-$(CONFIG_MLX90632) += mlx90635.o +obj-$(CONFIG_MLX90635) += mlx90635.o obj-$(CONFIG_TMP006) += tmp006.o obj-$(CONFIG_TMP007) += tmp007.o obj-$(CONFIG_TMP117) += tmp117.o diff --git a/drivers/input/joystick/maplecontrol.c b/drivers/input/joystick/maplecontrol.c index 7f36f73844a9..6293b6e8148b 100644 --- a/drivers/input/joystick/maplecontrol.c +++ b/drivers/input/joystick/maplecontrol.c @@ -112,6 +112,8 @@ static int probe_maple_controller(struct device *dev) pad->dev = idev; pad->mdev = mdev; + maple_set_drvdata(mdev, pad); + idev->open = dc_pad_open; idev->close = dc_pad_close; @@ -146,7 +148,6 @@ static int probe_maple_controller(struct device *dev) goto fail; mdev->driver = mdrv; - maple_set_drvdata(mdev, pad); return 0; diff --git a/drivers/input/keyboard/maple_keyb.c b/drivers/input/keyboard/maple_keyb.c index 80a5181313e1..3d5538dd4f23 100644 --- a/drivers/input/keyboard/maple_keyb.c +++ b/drivers/input/keyboard/maple_keyb.c @@ -166,6 +166,8 @@ static int probe_maple_kbd(struct device *dev) kbd->dev = idev; memcpy(kbd->keycode, dc_kbd_keycode, sizeof(kbd->keycode)); + maple_set_drvdata(mdev, kbd); + idev->name = mdev->product_name; idev->evbit[0] = BIT(EV_KEY) | BIT(EV_REP); idev->keycode = kbd->keycode; @@ -190,8 +192,6 @@ static int probe_maple_kbd(struct device *dev) mdev->driver = mdrv; - maple_set_drvdata(mdev, kbd); - return error; fail_register: diff --git a/drivers/input/mouse/maplemouse.c b/drivers/input/mouse/maplemouse.c index c99f7e234219..0c8f7d1b02aa 100644 --- a/drivers/input/mouse/maplemouse.c +++ b/drivers/input/mouse/maplemouse.c @@ -48,7 +48,7 @@ static void dc_mouse_callback(struct mapleq *mq) static int dc_mouse_open(struct input_dev *dev) { - struct dc_mouse *mse = maple_get_drvdata(to_maple_dev(&dev->dev)); + struct dc_mouse *mse = input_get_drvdata(dev); maple_getcond_callback(mse->mdev, dc_mouse_callback, HZ/50, MAPLE_FUNC_MOUSE); @@ -58,7 +58,7 @@ static int dc_mouse_open(struct input_dev *dev) static void dc_mouse_close(struct input_dev *dev) { - struct dc_mouse *mse = maple_get_drvdata(to_maple_dev(&dev->dev)); + struct dc_mouse *mse = input_get_drvdata(dev); maple_getcond_callback(mse->mdev, dc_mouse_callback, 0, MAPLE_FUNC_MOUSE); @@ -88,6 +88,9 @@ static int probe_maple_mouse(struct device *dev) mse->dev = input_dev; mse->mdev = mdev; + maple_set_drvdata(mdev, mse); + + input_set_drvdata(input_dev, mse); input_dev->evbit[0] = BIT_MASK(EV_KEY) | BIT_MASK(EV_REL); input_dev->keybit[BIT_WORD(BTN_MOUSE)] = BIT_MASK(BTN_LEFT) | BIT_MASK(BTN_RIGHT) | BIT_MASK(BTN_MIDDLE); @@ -102,12 +105,12 @@ static int probe_maple_mouse(struct device *dev) goto fail_register; mdev->driver = mdrv; - maple_set_drvdata(mdev, mse); return error; fail_register: input_free_device(input_dev); + maple_set_drvdata(mdev, NULL); fail_nomem: kfree(mse); fail: diff --git a/drivers/input/touchscreen/mms114.c b/drivers/input/touchscreen/mms114.c index 53ad35d61d47..5cef97246a15 100644 --- a/drivers/input/touchscreen/mms114.c +++ b/drivers/input/touchscreen/mms114.c @@ -165,7 +165,7 @@ static void mms114_process_mt(struct mms114_data *data, struct mms114_touch *tou unsigned int x; unsigned int y; - if (touch->id > MMS114_MAX_TOUCH) { + if (touch->id == 0 || touch->id > MMS114_MAX_TOUCH) { dev_err(&client->dev, "Wrong touch id (%d)\n", touch->id); return; } diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index 26fedf5883ef..a458b9fd2fcd 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -2238,7 +2238,9 @@ int dm_bufio_issue_discard(struct dm_bufio_client *c, sector_t block, sector_t c struct dm_io_region io_reg = { .bdev = c->bdev, .sector = block_to_sector(c, block), - .count = block_to_sector(c, count), + .count = likely(c->sectors_per_block_bits >= 0) ? + count << c->sectors_per_block_bits : + count * (c->block_size >> SECTOR_SHIFT), }; if (WARN_ON_ONCE(dm_bufio_in_request())) diff --git a/drivers/md/dm-era-target.c b/drivers/md/dm-era-target.c index 05285c04ff2c..7fe4d19ade4f 100644 --- a/drivers/md/dm-era-target.c +++ b/drivers/md/dm-era-target.c @@ -810,8 +810,10 @@ static struct era_metadata *metadata_open(struct block_device *bdev, int r; struct era_metadata *md = kzalloc_obj(*md); - if (!md) - return NULL; + if (!md) { + DMERR("could not allocate metadata struct"); + return ERR_PTR(-ENOMEM); + } md->bdev = bdev; md->block_size = block_size; @@ -1229,6 +1231,7 @@ static dm_block_t get_block(struct era *era, struct bio *bio) static void remap_to_origin(struct era *era, struct bio *bio) { bio_set_dev(bio, era->origin_dev->bdev); + bio->bi_iter.bi_sector = dm_target_offset(era->ti, bio->bi_iter.bi_sector); } /* @@ -1486,7 +1489,7 @@ static int era_ctr(struct dm_target *ti, unsigned int argc, char **argv) if (r) { ti->error = "Error opening metadata device"; era_destroy(era); - return -EINVAL; + return r; } r = dm_get_device(ti, argv[1], BLK_OPEN_READ | BLK_OPEN_WRITE, @@ -1494,7 +1497,7 @@ static int era_ctr(struct dm_target *ti, unsigned int argc, char **argv) if (r) { ti->error = "Error opening data device"; era_destroy(era); - return -EINVAL; + return r; } r = sscanf(argv[2], "%u%c", &era->sectors_per_block, &dummy); @@ -1508,7 +1511,7 @@ static int era_ctr(struct dm_target *ti, unsigned int argc, char **argv) if (r) { ti->error = "could not set max io len"; era_destroy(era); - return -EINVAL; + return r; } if (!valid_block_size(era->sectors_per_block)) { @@ -1560,7 +1563,7 @@ static void era_dtr(struct dm_target *ti) static int era_map(struct dm_target *ti, struct bio *bio) { struct era *era = ti->private; - dm_block_t block = get_block(era, bio); + dm_block_t block; /* * All bios get remapped to the origin device. We do this now, but @@ -1568,6 +1571,7 @@ static int era_map(struct dm_target *ti, struct bio *bio) * block is marked in this era. */ remap_to_origin(era, bio); + block = get_block(era, bio); /* * REQ_PREFLUSH bios carry no data, so we're not interested in them. diff --git a/drivers/md/dm-inlinecrypt.c b/drivers/md/dm-inlinecrypt.c index be1b4aa8f28b..41293c18d10f 100644 --- a/drivers/md/dm-inlinecrypt.c +++ b/drivers/md/dm-inlinecrypt.c @@ -347,7 +347,8 @@ static int inlinecrypt_ctr(struct dm_target *ti, unsigned int argc, char **argv) err = get_key_size(&argv[1]); if (err < 0) { ti->error = "Cannot parse key size"; - return -EINVAL; + err = -EINVAL; + goto bad; } ctx->key_size = err; @@ -398,6 +399,7 @@ static int inlinecrypt_ctr(struct dm_target *ti, unsigned int argc, char **argv) if (ctx->iv_offset & ((ctx->sector_size >> SECTOR_SHIFT) - 1)) { ti->error = "Wrong alignment of iv_offset sector"; err = -EINVAL; + goto bad; } ctx->max_dun = (ctx->iv_offset + ti->len - 1) >> diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index 65c30dec8222..1f2593f113f6 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -1480,9 +1480,6 @@ static int dm_integrity_rw_tag(struct dm_integrity_c *ic, unsigned char *tag, se *metadata_offset = 0; } - if (unlikely(!is_power_of_2(ic->tag_size))) - hash_offset = (hash_offset + to_copy) % ic->tag_size; - total_size -= to_copy; } while (unlikely(total_size)); @@ -2523,6 +2520,9 @@ static int dm_integrity_map_inline(struct dm_integrity_io *dio, bool from_map) if (unlikely((bio->bi_opf & REQ_PREFLUSH) != 0)) return DM_MAPIO_REMAPPED; + if (unlikely(!dm_integrity_check_limits(ic, bio->bi_iter.bi_sector, bio))) + return DM_MAPIO_KILL; + retry: if (!dio->integrity_payload) { unsigned digest_size, extra_size; @@ -2587,10 +2587,6 @@ static int dm_integrity_map_inline(struct dm_integrity_io *dio, bool from_map) dio->bio_details.bi_iter = bio->bi_iter; - if (unlikely(!dm_integrity_check_limits(ic, bio->bi_iter.bi_sector, bio))) { - return DM_MAPIO_KILL; - } - bio->bi_iter.bi_sector += ic->start + SB_SECTORS; bip = bio_integrity_alloc(bio, GFP_NOIO, 1); @@ -2606,7 +2602,7 @@ static int dm_integrity_map_inline(struct dm_integrity_io *dio, bool from_map) struct bio_vec bv = bio_iter_iovec(bio, dio->bio_details.bi_iter); const char *mem = integrity_kmap(ic, bv.bv_page); if (ic->tag_size < ic->tuple_size) - memset(dio->integrity_payload + pos + ic->tag_size, 0, ic->tuple_size - ic->tuple_size); + memset(dio->integrity_payload + pos + ic->tag_size, 0, ic->tuple_size - ic->tag_size); integrity_sector_checksum(ic, &dio->ahash_req, dio->bio_details.bi_iter.bi_sector, mem, bv.bv_offset, dio->integrity_payload + pos); integrity_kunmap(ic, mem); pos += ic->tuple_size; @@ -5130,6 +5126,20 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned int argc, char **argv ti->error = "Journal mac mismatch"; goto bad; } + if (ic->fix_hmac && !(ic->sb->flags & cpu_to_le32(SB_FLAG_FIXED_HMAC)) && ic->journal_mac_alg.key_string) { + /* + * If this happens, it may be either because someone tampered + * with the device or it may be due to a bug in the + * integritysetup tool. + * + * In the latter case, upgrade to integritysetup 2.8.7 and use + * the argument --integrity-legacy-hmac when using the open + * command. + */ + r = -EINVAL; + ti->error = "fix_hmac is on the command line but not in the superblock"; + goto bad; + } get_provided_data_sectors(ic); if (!ic->provided_data_sectors) { diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c index ac77dc0ca225..61af2a437a05 100644 --- a/drivers/md/dm-ioctl.c +++ b/drivers/md/dm-ioctl.c @@ -785,7 +785,7 @@ static void list_version_get_info(struct target_type *tt, void *param) struct vers_iter *info = param; /* Check space - it might have changed since the first iteration */ - if ((char *)info->vers + sizeof(tt->version) + strlen(tt->name) + 1 > info->end) { + if ((char *)info->vers + sizeof(struct dm_target_versions) + strlen(tt->name) + 1 > info->end) { info->flags = DM_BUFFER_FULL_FLAG; return; } @@ -2473,7 +2473,7 @@ int __init dm_early_create(struct dm_ioctl *dmi, /* resume device */ r = dm_resume(md); if (r) - goto err_destroy_table; + goto err_hash_remove; DMINFO("%s (%s) is ready", md->disk->disk_name, dmi->name); dm_put(md); diff --git a/drivers/md/dm-log.c b/drivers/md/dm-log.c index d316757a328b..2ddeb4250c59 100644 --- a/drivers/md/dm-log.c +++ b/drivers/md/dm-log.c @@ -425,6 +425,9 @@ static int create_log_context(struct dm_dirty_log *log, struct dm_target *ti, */ bitset_size = dm_round_up(region_count, BITS_PER_LONG); bitset_size >>= BYTE_SHIFT; + /* Handle dm_round_up rollover on 32-bit systems */ + if (!bitset_size) + bitset_size = 1UL << (BITS_PER_LONG - BYTE_SHIFT); lc->bitset_uint32_count = bitset_size / sizeof(*lc->clean_bits); diff --git a/drivers/md/dm-pcache/dm_pcache.c b/drivers/md/dm-pcache/dm_pcache.c index 81c795c0400e..d5cfd162c063 100644 --- a/drivers/md/dm-pcache/dm_pcache.c +++ b/drivers/md/dm-pcache/dm_pcache.c @@ -168,6 +168,10 @@ static int parse_cache_opts(struct dm_pcache *pcache, struct dm_arg_set *as, argc--; if (!strcmp(arg, "cache_mode")) { + if (!argc) { + *error = "Missing value for cache_mode"; + return -EINVAL; + } arg = dm_shift_arg(as); if (!strcmp(arg, "writeback")) { opts->cache_mode = PCACHE_CACHE_MODE_WRITEBACK; @@ -177,6 +181,10 @@ static int parse_cache_opts(struct dm_pcache *pcache, struct dm_arg_set *as, } argc--; } else if (!strcmp(arg, "data_crc")) { + if (!argc) { + *error = "Missing value for data_crc"; + return -EINVAL; + } arg = dm_shift_arg(as); if (!strcmp(arg, "true")) { opts->data_crc = true; diff --git a/drivers/md/dm-stats.c b/drivers/md/dm-stats.c index c53cf07ab7b0..5df710061a11 100644 --- a/drivers/md/dm-stats.c +++ b/drivers/md/dm-stats.c @@ -692,10 +692,8 @@ void dm_stats_account_io(struct dm_stats *stats, unsigned long bi_rw, */ last = raw_cpu_ptr(stats->last); stats_aux->merged = - (bi_sector == (READ_ONCE(last->last_sector) && - ((bi_rw == WRITE) == - (READ_ONCE(last->last_rw) == WRITE)) - )); + bi_sector == READ_ONCE(last->last_sector) && + (bi_rw == WRITE) == (READ_ONCE(last->last_rw) == WRITE); WRITE_ONCE(last->last_sector, end_sector); WRITE_ONCE(last->last_rw, bi_rw); } else @@ -842,10 +840,10 @@ static unsigned long long dm_jiffies_to_msec64(struct dm_stat *s, unsigned long result = jiffies_to_msecs(j & 0x3fffff); if (j >= 1 << 22) { mult = jiffies_to_msecs(1 << 22); - result += (unsigned long long)mult * (unsigned long long)jiffies_to_msecs((j >> 22) & 0x3fffff); + result += (unsigned long long)mult * ((j >> 22) & 0x3fffff); } if (j >= 1ULL << 44) - result += (unsigned long long)mult * (unsigned long long)mult * (unsigned long long)jiffies_to_msecs(j >> 44); + result += (unsigned long long)mult * (unsigned long long)(1 << 22) * (j >> 44); return result; } diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c index b6a2d2081a24..e60e1326376a 100644 --- a/drivers/md/dm-thin-metadata.c +++ b/drivers/md/dm-thin-metadata.c @@ -186,6 +186,7 @@ struct dm_pool_metadata { uint32_t time; dm_block_t root; dm_block_t details_root; + dm_block_t held_root; struct list_head thin_devices; uint64_t trans_id; unsigned long flags; @@ -748,6 +749,7 @@ static int __open_metadata(struct dm_pool_metadata *pmd) */ pmd->root = le64_to_cpu(disk_super->data_mapping_root); pmd->details_root = le64_to_cpu(disk_super->device_details_root); + pmd->held_root = le64_to_cpu(disk_super->held_root); __setup_btree_details(pmd); dm_bm_unlock(sblock); @@ -838,6 +840,7 @@ static int __begin_transaction(struct dm_pool_metadata *pmd) pmd->time = le32_to_cpu(disk_super->time); pmd->root = le64_to_cpu(disk_super->data_mapping_root); pmd->details_root = le64_to_cpu(disk_super->device_details_root); + pmd->held_root = le64_to_cpu(disk_super->held_root); pmd->trans_id = le64_to_cpu(disk_super->trans_id); pmd->flags = le32_to_cpu(disk_super->flags); pmd->data_block_size = le32_to_cpu(disk_super->data_block_size); @@ -928,6 +931,7 @@ static int __commit_transaction(struct dm_pool_metadata *pmd) disk_super->time = cpu_to_le32(pmd->time); disk_super->data_mapping_root = cpu_to_le64(pmd->root); disk_super->device_details_root = cpu_to_le64(pmd->details_root); + disk_super->held_root = cpu_to_le64(pmd->held_root); disk_super->trans_id = cpu_to_le64(pmd->trans_id); disk_super->flags = cpu_to_le32(pmd->flags); @@ -1333,9 +1337,14 @@ static int __reserve_metadata_snap(struct dm_pool_metadata *pmd) { int r, inc; struct thin_disk_superblock *disk_super; - struct dm_block *copy, *sblock; + struct dm_block *copy; dm_block_t held_root; + if (pmd->held_root) { + DMWARN("Pool metadata snapshot already exists: release this before taking another."); + return -EBUSY; + } + /* * We commit to ensure the btree roots which we increment in a * moment are up to date. @@ -1353,22 +1362,16 @@ static int __reserve_metadata_snap(struct dm_pool_metadata *pmd) dm_sm_inc_block(pmd->metadata_sm, THIN_SUPERBLOCK_LOCATION); r = dm_tm_shadow_block(pmd->tm, THIN_SUPERBLOCK_LOCATION, &sb_validator, ©, &inc); - if (r) + if (r) { + dm_sm_dec_block(pmd->metadata_sm, THIN_SUPERBLOCK_LOCATION); return r; + } BUG_ON(!inc); held_root = dm_block_location(copy); disk_super = dm_block_data(copy); - if (le64_to_cpu(disk_super->held_root)) { - DMWARN("Pool metadata snapshot already exists: release this before taking another."); - - dm_tm_dec(pmd->tm, held_root); - dm_tm_unlock(pmd->tm, copy); - return -EBUSY; - } - /* * Wipe the spacemap since we're not publishing this. */ @@ -1384,18 +1387,8 @@ static int __reserve_metadata_snap(struct dm_pool_metadata *pmd) dm_tm_inc(pmd->tm, le64_to_cpu(disk_super->device_details_root)); dm_tm_unlock(pmd->tm, copy); - /* - * Write the held root into the superblock. - */ - r = superblock_lock(pmd, &sblock); - if (r) { - dm_tm_dec(pmd->tm, held_root); - return r; - } + pmd->held_root = held_root; - disk_super = dm_block_data(sblock); - disk_super->held_root = cpu_to_le64(held_root); - dm_bm_unlock(sblock); return 0; } @@ -1415,18 +1408,10 @@ static int __release_metadata_snap(struct dm_pool_metadata *pmd) { int r; struct thin_disk_superblock *disk_super; - struct dm_block *sblock, *copy; + struct dm_block *copy; dm_block_t held_root; - r = superblock_lock(pmd, &sblock); - if (r) - return r; - - disk_super = dm_block_data(sblock); - held_root = le64_to_cpu(disk_super->held_root); - disk_super->held_root = cpu_to_le64(0); - - dm_bm_unlock(sblock); + held_root = pmd->held_root; if (!held_root) { DMWARN("No pool metadata snapshot found: nothing to release."); @@ -1437,13 +1422,15 @@ static int __release_metadata_snap(struct dm_pool_metadata *pmd) if (r) return r; + pmd->held_root = 0; + disk_super = dm_block_data(copy); dm_btree_del(&pmd->info, le64_to_cpu(disk_super->data_mapping_root)); dm_btree_del(&pmd->details_info, le64_to_cpu(disk_super->device_details_root)); - dm_sm_dec_block(pmd->metadata_sm, held_root); - dm_tm_unlock(pmd->tm, copy); + dm_sm_dec_block(pmd->metadata_sm, held_root); + return 0; } @@ -1462,19 +1449,7 @@ int dm_pool_release_metadata_snap(struct dm_pool_metadata *pmd) static int __get_metadata_snap(struct dm_pool_metadata *pmd, dm_block_t *result) { - int r; - struct thin_disk_superblock *disk_super; - struct dm_block *sblock; - - r = dm_bm_read_lock(pmd->bm, THIN_SUPERBLOCK_LOCATION, - &sb_validator, &sblock); - if (r) - return r; - - disk_super = dm_block_data(sblock); - *result = le64_to_cpu(disk_super->held_root); - - dm_bm_unlock(sblock); + *result = pmd->held_root; return 0; } diff --git a/drivers/md/dm-verity-fec.c b/drivers/md/dm-verity-fec.c index 85ad9dc210ff..c79f60df3a90 100644 --- a/drivers/md/dm-verity-fec.c +++ b/drivers/md/dm-verity-fec.c @@ -220,7 +220,7 @@ static int fec_read_bufs(struct dm_verity *v, struct dm_verity_io *io, PTR_ERR(bbuf)); /* assume the block is corrupted */ - if (neras && *neras <= v->fec->roots) + if (neras && *neras < v->fec->roots) fio->erasures[(*neras)++] = i; continue; @@ -238,7 +238,7 @@ static int fec_read_bufs(struct dm_verity *v, struct dm_verity_io *io, * skip if we have already found the theoretical * maximum number (i.e. fec->roots) of erasures */ - if (neras && *neras <= v->fec->roots && + if (neras && *neras < v->fec->roots && fec_is_erasure(v, io, want_digest, bbuf)) fio->erasures[(*neras)++] = i; } diff --git a/drivers/md/dm-verity-fec.h b/drivers/md/dm-verity-fec.h index 50b5e187d5cc..3885b514fc23 100644 --- a/drivers/md/dm-verity-fec.h +++ b/drivers/md/dm-verity-fec.h @@ -47,7 +47,7 @@ struct dm_verity_fec { /* per-bio data */ struct dm_verity_fec_io { struct rs_control *rs; /* Reed-Solomon state */ - int erasures[DM_VERITY_FEC_MAX_ROOTS + 1]; /* erasures for decode_rs8 */ + int erasures[DM_VERITY_FEC_MAX_ROOTS]; /* erasures for decode_rs8 */ u8 *output; /* buffer for corrected output */ unsigned int level; /* recursion level */ unsigned int nbufs; /* number of buffers allocated */ diff --git a/drivers/md/dm-verity-loadpin.c b/drivers/md/dm-verity-loadpin.c index 0666699b6858..9a64f575ae5f 100644 --- a/drivers/md/dm-verity-loadpin.c +++ b/drivers/md/dm-verity-loadpin.c @@ -70,7 +70,7 @@ bool dm_verity_loadpin_is_bdev_trusted(struct block_device *bdev) table = dm_get_live_table(md, &srcu_idx); - if (table->num_targets != 1) + if (!table || table->num_targets != 1) goto out; ti = dm_table_get_target(table, 0); diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c index 9a9847f94c46..1b0763091254 100644 --- a/drivers/md/dm-verity-target.c +++ b/drivers/md/dm-verity-target.c @@ -26,7 +26,7 @@ #define DM_MSG_PREFIX "verity" -#define DM_VERITY_ENV_LENGTH 42 +#define DM_VERITY_ENV_LENGTH 46 #define DM_VERITY_ENV_VAR_NAME "DM_VERITY_ERR_BLOCK_NR" #define DM_VERITY_DEFAULT_PREFETCH_SIZE 262144 @@ -180,14 +180,16 @@ static int verity_handle_err(struct dm_verity *v, enum verity_block_type type, char *envp[] = { verity_env, NULL }; const char *type_str = ""; struct mapped_device *md = dm_table_get_md(v->ti->table); + int ce; /* Corruption should be visible in device status in all modes */ v->hash_failed = true; - if (v->corrupted_errs >= DM_VERITY_MAX_CORRUPTED_ERRS) - goto out; - - v->corrupted_errs++; + ce = atomic_read(&v->corrupted_errs); + do { + if (ce >= DM_VERITY_MAX_CORRUPTED_ERRS) + goto out; + } while (!atomic_try_cmpxchg(&v->corrupted_errs, &ce, ce + 1)); switch (type) { case DM_VERITY_BLOCK_TYPE_DATA: @@ -203,7 +205,7 @@ static int verity_handle_err(struct dm_verity *v, enum verity_block_type type, DMERR_LIMIT("%s: %s block %llu is corrupted", v->data_dev->name, type_str, block); - if (v->corrupted_errs == DM_VERITY_MAX_CORRUPTED_ERRS) { + if (ce + 1 == DM_VERITY_MAX_CORRUPTED_ERRS) { DMERR("%s: reached maximum errors", v->data_dev->name); dm_audit_log_target(DM_MSG_PREFIX, "max-corrupted-errors", v->ti, 0); } @@ -1262,6 +1264,8 @@ static int verity_parse_opt_args(struct dm_arg_set *as, struct dm_verity *v, continue; } else if (!strcasecmp(arg_name, DM_VERITY_OPT_TASKLET_VERIFY)) { + if (v->use_bh_wq) + continue; v->use_bh_wq = true; static_branch_inc(&use_bh_wq_enabled); continue; diff --git a/drivers/md/dm-verity.h b/drivers/md/dm-verity.h index 2922263501f6..e104a651c657 100644 --- a/drivers/md/dm-verity.h +++ b/drivers/md/dm-verity.h @@ -68,7 +68,7 @@ struct dm_verity { unsigned int digest_size; /* digest size for the current hash algorithm */ enum verity_mode mode; /* mode for handling verification errors */ enum verity_mode error_mode;/* mode for handling I/O errors */ - unsigned int corrupted_errs;/* Number of errors for corrupted blocks */ + atomic_t corrupted_errs;/* Number of errors for corrupted blocks */ struct workqueue_struct *verify_wq; diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 7287bed6eb64..d413bfaf3527 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -735,7 +735,16 @@ static struct table_device *open_table_device(struct mapped_device *md, return ERR_PTR(-ENOMEM); refcount_set(&td->count, 1); - bdev_file = bdev_file_open_by_dev(dev, mode, _dm_claim_ptr, NULL); + /* + * Open the backing device with kernel rather than caller + * credentials. Otherwise the caller's credentials would be + * pinned in bdev_file->f_cred until the table device is closed. + * That would keep the caller's thread keyring alive long beyond the + * lifetime of the caller, breaking userspace expectation (e.g. + * cryptsetup(8) leaking the LUKS volume key). + */ + scoped_with_kernel_creds() + bdev_file = bdev_file_open_by_dev(dev, mode, _dm_claim_ptr, NULL); if (IS_ERR(bdev_file)) { r = PTR_ERR(bdev_file); goto out_free_td; diff --git a/drivers/net/amt.c b/drivers/net/amt.c index 724a8163a514..951dd10e192b 100644 --- a/drivers/net/amt.c +++ b/drivers/net/amt.c @@ -3301,9 +3301,9 @@ static size_t amt_get_size(const struct net_device *dev) nla_total_size(sizeof(__u16)) + /* IFLA_AMT_GATEWAY_PORT */ nla_total_size(sizeof(__u32)) + /* IFLA_AMT_LINK */ nla_total_size(sizeof(__u32)) + /* IFLA_MAX_TUNNELS */ - nla_total_size(sizeof(struct iphdr)) + /* IFLA_AMT_DISCOVERY_IP */ - nla_total_size(sizeof(struct iphdr)) + /* IFLA_AMT_REMOTE_IP */ - nla_total_size(sizeof(struct iphdr)); /* IFLA_AMT_LOCAL_IP */ + nla_total_size(sizeof(__be32)) + /* IFLA_AMT_DISCOVERY_IP */ + nla_total_size(sizeof(__be32)) + /* IFLA_AMT_REMOTE_IP */ + nla_total_size(sizeof(__be32)); /* IFLA_AMT_LOCAL_IP */ } static int amt_fill_info(struct sk_buff *skb, const struct net_device *dev) diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index fd282a1700fb..d394f1f43b68 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -2668,8 +2668,25 @@ static void macb_free_consistent(struct macb *bp) dma_free_coherent(dev, size, bp->queues[0].rx_ring, bp->queues[0].rx_ring_dma); for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) { - kfree(queue->tx_skb); - queue->tx_skb = NULL; + if (queue->tx_skb) { + unsigned int dropped = 0, tail; + + for (tail = queue->tx_tail; tail != queue->tx_head; + tail++) { + if (macb_tx_skb(queue, tail)->skb) + dropped++; + macb_tx_unmap(bp, macb_tx_skb(queue, tail), 0); + } + + queue->stats.tx_dropped += dropped; + bp->dev->stats.tx_dropped += dropped; + + kfree(queue->tx_skb); + queue->tx_skb = NULL; + } + + queue->tx_head = 0; + queue->tx_tail = 0; queue->tx_ring = NULL; queue->rx_ring = NULL; } diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c index 0db08ac3d098..e303956b4bf1 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c @@ -3779,9 +3779,7 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) static int octeon_enable_sriov(struct octeon_device *oct) { unsigned int num_vfs_alloced = oct->sriov_info.num_vfs_alloced; - struct pci_dev *vfdev; int err; - u32 u; if (OCTEON_CN23XX_PF(oct) && num_vfs_alloced) { err = pci_enable_sriov(oct->pci_dev, @@ -3794,23 +3792,6 @@ static int octeon_enable_sriov(struct octeon_device *oct) return err; } oct->sriov_info.sriov_enabled = 1; - - /* init lookup table that maps DPI ring number to VF pci_dev - * struct pointer - */ - u = 0; - vfdev = pci_get_device(PCI_VENDOR_ID_CAVIUM, - OCTEON_CN23XX_VF_VID, NULL); - while (vfdev) { - if (vfdev->is_virtfn && - (vfdev->physfn == oct->pci_dev)) { - oct->sriov_info.dpiring_to_vfpcidev_lut[u] = - vfdev; - u += oct->sriov_info.rings_per_vf; - } - vfdev = pci_get_device(PCI_VENDOR_ID_CAVIUM, - OCTEON_CN23XX_VF_VID, vfdev); - } } return num_vfs_alloced; @@ -3818,8 +3799,6 @@ static int octeon_enable_sriov(struct octeon_device *oct) static int lio_pci_sriov_disable(struct octeon_device *oct) { - int u; - if (pci_vfs_assigned(oct->pci_dev)) { dev_err(&oct->pci_dev->dev, "VFs are still assigned to VMs.\n"); return -EPERM; @@ -3827,12 +3806,6 @@ static int lio_pci_sriov_disable(struct octeon_device *oct) pci_disable_sriov(oct->pci_dev); - u = 0; - while (u < MAX_POSSIBLE_VFS) { - oct->sriov_info.dpiring_to_vfpcidev_lut[u] = NULL; - u += oct->sriov_info.rings_per_vf; - } - oct->sriov_info.num_vfs_alloced = 0; dev_info(&oct->pci_dev->dev, "oct->pf_num:%d disabled VFs\n", oct->pf_num); diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_device.h b/drivers/net/ethernet/cavium/liquidio/octeon_device.h index 19344b21f8fb..858a0fff2cc0 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_device.h +++ b/drivers/net/ethernet/cavium/liquidio/octeon_device.h @@ -390,9 +390,6 @@ struct octeon_sriov_info { struct lio_trusted_vf trusted_vf; - /*lookup table that maps DPI ring number to VF pci_dev struct pointer*/ - struct pci_dev *dpiring_to_vfpcidev_lut[MAX_POSSIBLE_VFS]; - u64 vf_macaddr[MAX_POSSIBLE_VFS]; u16 vf_vlantci[MAX_POSSIBLE_VFS]; diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_mailbox.c b/drivers/net/ethernet/cavium/liquidio/octeon_mailbox.c index ad685f5d0a13..697fcdc41e3c 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_mailbox.c +++ b/drivers/net/ethernet/cavium/liquidio/octeon_mailbox.c @@ -26,6 +26,31 @@ #include "octeon_mailbox.h" #include "cn23xx_pf_device.h" +static struct pci_dev *lio_vf_pci_dev_by_qno(struct octeon_device *oct, u32 q_no) +{ + struct pci_dev *vfdev = NULL; + int vfidx; + + if (!oct->sriov_info.rings_per_vf) + return NULL; + + if (q_no % oct->sriov_info.rings_per_vf) + return NULL; + + vfidx = q_no / oct->sriov_info.rings_per_vf; + if (vfidx >= oct->sriov_info.num_vfs_alloced) + return NULL; + + while ((vfdev = pci_get_device(PCI_VENDOR_ID_CAVIUM, + OCTEON_CN23XX_VF_VID, vfdev))) { + if (pci_physfn(vfdev) && pci_physfn(vfdev) == oct->pci_dev && + pci_iov_vf_id(vfdev) == vfidx) + return vfdev; + } + + return NULL; +} + /** * octeon_mbox_read: * @mbox: Pointer mailbox @@ -237,6 +262,7 @@ static int octeon_mbox_process_cmd(struct octeon_mbox *mbox, struct octeon_mbox_cmd *mbox_cmd) { struct octeon_device *oct = mbox->oct_dev; + struct pci_dev *vfdev; switch (mbox_cmd->msg.s.cmd) { case OCTEON_VF_ACTIVE: @@ -260,7 +286,12 @@ static int octeon_mbox_process_cmd(struct octeon_mbox *mbox, dev_info(&oct->pci_dev->dev, "got a request for FLR from VF that owns DPI ring %u\n", mbox->q_no); - pcie_flr(oct->sriov_info.dpiring_to_vfpcidev_lut[mbox->q_no]); + vfdev = lio_vf_pci_dev_by_qno(oct, mbox->q_no); + if (!vfdev) + break; + + pcie_flr(vfdev); + pci_dev_put(vfdev); break; case OCTEON_PF_CHANGED_VF_MACADDR: diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index 0297c7ab0614..6a0ce2665031 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -4580,7 +4580,7 @@ int rvu_mbox_handler_nix_set_rx_mode(struct rvu *rvu, struct nix_rx_mode *req, rvu_npc_install_allmulti_entry(rvu, pcifunc, nixlf, pfvf->rx_chan_base); } else { - if (!nix_rx_multicast) + if (!nix_rx_multicast && !is_vf(pcifunc)) rvu_npc_enable_allmulti_entry(rvu, pcifunc, nixlf, false); } @@ -4590,7 +4590,7 @@ int rvu_mbox_handler_nix_set_rx_mode(struct rvu *rvu, struct nix_rx_mode *req, pfvf->rx_chan_base, pfvf->rx_chan_cnt); else - if (!nix_rx_multicast) + if (!nix_rx_multicast && !is_vf(pcifunc)) rvu_npc_enable_promisc_entry(rvu, pcifunc, nixlf, false); return 0; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index b63df5737ff2..2e33b33ec993 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -1568,15 +1568,15 @@ static void otx2_free_sq_res(struct otx2_nic *pf) otx2_sq_free_sqbs(pf); for (qidx = 0; qidx < otx2_get_total_tx_queues(pf); qidx++) { sq = &qset->sq[qidx]; - /* Skip freeing Qos queues if they are not initialized */ - if (!sq->sqe) - continue; - qmem_free(pf->dev, sq->sqe); - qmem_free(pf->dev, sq->sqe_ring); - qmem_free(pf->dev, sq->cpt_resp); - qmem_free(pf->dev, sq->tso_hdrs); - qmem_free(pf->dev, sq->timestamps); - kfree(sq->sg); + /* sq->sqe is not initialized for unused QoS queues */ + if (sq->sqe) { + qmem_free(pf->dev, sq->sqe); + qmem_free(pf->dev, sq->sqe_ring); + qmem_free(pf->dev, sq->cpt_resp); + qmem_free(pf->dev, sq->tso_hdrs); + qmem_free(pf->dev, sq->timestamps); + kfree(sq->sg); + } kfree(sq->sqb_ptrs); } } @@ -1711,13 +1711,12 @@ int otx2_init_hw_resources(struct otx2_nic *pf) return err; err_free_nix_queues: - otx2_free_sq_res(pf); otx2_free_cq_res(pf); otx2_ctx_disable(mbox, NIX_AQ_CTYPE_RQ, false); err_free_txsch: otx2_txschq_stop(pf); err_free_sq_ptrs: - otx2_sq_free_sqbs(pf); + otx2_free_sq_res(pf); err_free_rq_ptrs: otx2_free_aura_ptr(pf, AURA_NIX_RQ); otx2_ctx_disable(mbox, NPA_AQ_CTYPE_POOL, true); @@ -2517,10 +2516,42 @@ EXPORT_SYMBOL(otx2_config_hwtstamp_set); static int otx2_do_set_vf_mac(struct otx2_nic *pf, int vf, const u8 *mac) { + struct npc_get_field_status_req *freq; + struct npc_get_field_status_rsp *frsp; struct npc_install_flow_req *req; int err; mutex_lock(&pf->mbox.lock); + + /* Skip installing the DMAC filter if the hardware parser profile + * does not support DMAC extraction. + */ + freq = otx2_mbox_alloc_msg_npc_get_field_status(&pf->mbox); + if (!freq) { + err = -ENOMEM; + goto out; + } + + freq->field = NPC_DMAC; + err = otx2_sync_mbox_msg(&pf->mbox); + if (err) + goto out; + + frsp = (struct npc_get_field_status_rsp *)otx2_mbox_get_rsp + (&pf->mbox.mbox, 0, &freq->hdr); + if (IS_ERR(frsp)) { + err = PTR_ERR(frsp); + goto out; + } + + if (!frsp->enable) { + netdev_warn(pf->netdev, + "VF %d MAC filter not installed: DMAC extraction not supported by parser profile\n", + vf); + err = -EOPNOTSUPP; + goto out; + } + req = otx2_mbox_alloc_msg_npc_install_flow(&pf->mbox); if (!req) { err = -ENOMEM; @@ -2559,13 +2590,12 @@ static int otx2_set_vf_mac(struct net_device *netdev, int vf, u8 *mac) if (!is_valid_ether_addr(mac)) return -EINVAL; - config = &pf->vf_configs[vf]; - ether_addr_copy(config->mac, mac); - ret = otx2_do_set_vf_mac(pf, vf, mac); - if (ret == 0) - dev_info(&pdev->dev, - "Load/Reload VF driver\n"); + if (ret == 0) { + config = &pf->vf_configs[vf]; + ether_addr_copy(config->mac, mac); + dev_info(&pdev->dev, "Load/Reload VF driver\n"); + } return ret; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 2270e2e550dd..d507289096c2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -987,6 +987,18 @@ struct mlx5e_priv { struct ethtool_fec_hist_range *fec_ranges; }; +static inline u16 mlx5e_stats_nch_read(const struct mlx5e_priv *priv) +{ + /* Pairs with smp_store_release in mlx5e_stats_nch_write(). */ + return smp_load_acquire(&priv->stats_nch); +} + +static inline void mlx5e_stats_nch_write(struct mlx5e_priv *priv, u16 n) +{ + /* Pairs with smp_load_acquire in mlx5e_stats_nch_read(). */ + smp_store_release(&priv->stats_nch, n); +} + struct mlx5e_dev { struct net_device *netdev; struct devlink_port dl_port; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/hv_vhca_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en/hv_vhca_stats.c index 195863b2c013..631f802105d5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/hv_vhca_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/hv_vhca_stats.c @@ -33,9 +33,10 @@ mlx5e_hv_vhca_fill_ring_stats(struct mlx5e_priv *priv, int ch, static void mlx5e_hv_vhca_fill_stats(struct mlx5e_priv *priv, void *data, int buf_len) { + u16 nch = mlx5e_stats_nch_read(priv); int ch, i = 0; - for (ch = 0; ch < priv->stats_nch; ch++) { + for (ch = 0; ch < nch; ch++) { void *buf = data + i; if (WARN_ON_ONCE(buf + @@ -49,9 +50,16 @@ static void mlx5e_hv_vhca_fill_stats(struct mlx5e_priv *priv, void *data, } static int mlx5e_hv_vhca_stats_buf_size(struct mlx5e_priv *priv) +{ + u16 nch = mlx5e_stats_nch_read(priv); + + return sizeof(struct mlx5e_hv_vhca_per_ring_stats) * nch; +} + +static int mlx5e_hv_vhca_stats_buf_max_size(struct mlx5e_priv *priv) { return (sizeof(struct mlx5e_hv_vhca_per_ring_stats) * - priv->stats_nch); + max(priv->max_nch, priv->stats_nch)); } static void mlx5e_hv_vhca_stats_work(struct work_struct *work) @@ -67,7 +75,7 @@ static void mlx5e_hv_vhca_stats_work(struct work_struct *work) sagent = container_of(dwork, struct mlx5e_hv_vhca_stats_agent, work); priv = container_of(sagent, struct mlx5e_priv, stats_agent); buf_len = mlx5e_hv_vhca_stats_buf_size(priv); - agent = sagent->agent; + agent = READ_ONCE(sagent->agent); buf = sagent->buf; memset(buf, 0, buf_len); @@ -100,7 +108,7 @@ static void mlx5e_hv_vhca_stats_control(struct mlx5_hv_vhca_agent *agent, sagent = &priv->stats_agent; block->version = MLX5_HV_VHCA_STATS_VERSION; - block->rings = priv->stats_nch; + block->rings = mlx5e_stats_nch_read(priv); if (!block->command) { cancel_delayed_work_sync(&priv->stats_agent.work); @@ -122,18 +130,21 @@ static void mlx5e_hv_vhca_stats_cleanup(struct mlx5_hv_vhca_agent *agent) void mlx5e_hv_vhca_stats_create(struct mlx5e_priv *priv) { - int buf_len = mlx5e_hv_vhca_stats_buf_size(priv); + int buf_len = mlx5e_hv_vhca_stats_buf_max_size(priv); struct mlx5_hv_vhca_agent *agent; priv->stats_agent.buf = kvzalloc(buf_len, GFP_KERNEL); if (!priv->stats_agent.buf) return; + INIT_DELAYED_WORK(&priv->stats_agent.work, mlx5e_hv_vhca_stats_work); + agent = mlx5_hv_vhca_agent_create(priv->mdev->hv_vhca, MLX5_HV_VHCA_AGENT_STATS, mlx5e_hv_vhca_stats_control, NULL, mlx5e_hv_vhca_stats_cleanup, - priv); + priv, + &priv->stats_agent.agent); if (IS_ERR_OR_NULL(agent)) { if (IS_ERR(agent)) @@ -142,18 +153,20 @@ void mlx5e_hv_vhca_stats_create(struct mlx5e_priv *priv) agent); kvfree(priv->stats_agent.buf); - return; + priv->stats_agent.buf = NULL; } - - priv->stats_agent.agent = agent; - INIT_DELAYED_WORK(&priv->stats_agent.work, mlx5e_hv_vhca_stats_work); } void mlx5e_hv_vhca_stats_destroy(struct mlx5e_priv *priv) { - if (IS_ERR_OR_NULL(priv->stats_agent.agent)) + struct mlx5_hv_vhca_agent *agent; + + agent = READ_ONCE(priv->stats_agent.agent); + if (IS_ERR_OR_NULL(agent)) return; - mlx5_hv_vhca_agent_destroy(priv->stats_agent.agent); + mlx5_hv_vhca_agent_destroy(agent); + WRITE_ONCE(priv->stats_agent.agent, NULL); kvfree(priv->stats_agent.buf); + priv->stats_agent.buf = NULL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 775f0c6e55c9..aa8610cedaa8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -2773,7 +2773,7 @@ static int mlx5e_channel_stats_alloc(struct mlx5e_priv *priv, int ix, int cpu) GFP_KERNEL, cpu_to_node(cpu)); if (!priv->channel_stats[ix]) return -ENOMEM; - priv->stats_nch++; + mlx5e_stats_nch_write(priv, priv->stats_nch + 1); return 0; } @@ -4040,9 +4040,10 @@ static int mlx5e_setup_tc(struct net_device *dev, enum tc_setup_type type, void mlx5e_fold_sw_stats64(struct mlx5e_priv *priv, struct rtnl_link_stats64 *s) { + u16 nch = mlx5e_stats_nch_read(priv); int i; - for (i = 0; i < priv->stats_nch; i++) { + for (i = 0; i < nch; i++) { struct mlx5e_channel_stats *channel_stats = priv->channel_stats[i]; struct mlx5e_rq_stats *xskrq_stats = &channel_stats->xskrq; struct mlx5e_rq_stats *rq_stats = &channel_stats->rq; @@ -5488,7 +5489,7 @@ static void mlx5e_get_queue_stats_rx(struct net_device *dev, int i, struct mlx5e_rq_stats *xskrq_stats; struct mlx5e_rq_stats *rq_stats; - if (mlx5e_is_uplink_rep(priv) || !priv->stats_nch) + if (mlx5e_is_uplink_rep(priv) || !mlx5e_stats_nch_read(priv)) return; channel_stats = priv->channel_stats[i]; @@ -5512,7 +5513,7 @@ static void mlx5e_get_queue_stats_tx(struct net_device *dev, int i, struct mlx5e_priv *priv = netdev_priv(dev); struct mlx5e_sq_stats *sq_stats; - if (!priv->stats_nch) + if (!mlx5e_stats_nch_read(priv)) return; /* no special case needed for ptp htb etc since txq2sq_stats is kept up @@ -5538,6 +5539,7 @@ static void mlx5e_get_base_stats(struct net_device *dev, struct netdev_queue_stats_tx *tx) { struct mlx5e_priv *priv = netdev_priv(dev); + u16 nch = mlx5e_stats_nch_read(priv); struct mlx5e_ptp *ptp_channel; int i, tc; @@ -5549,7 +5551,7 @@ static void mlx5e_get_base_stats(struct net_device *dev, rx->hw_gro_wire_packets = 0; rx->hw_gro_wire_bytes = 0; - for (i = priv->channels.params.num_channels; i < priv->stats_nch; i++) { + for (i = priv->channels.params.num_channels; i < nch; i++) { struct netdev_queue_stats_rx rx_i = {0}; mlx5e_get_queue_stats_rx(dev, i, &rx_i); @@ -5585,7 +5587,7 @@ static void mlx5e_get_base_stats(struct net_device *dev, tx->stop = 0; tx->wake = 0; - for (i = 0; i < priv->stats_nch; i++) { + for (i = 0; i < nch; i++) { struct mlx5e_channel_stats *channel_stats = priv->channel_stats[i]; /* handle two cases: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c index 7f33261ba655..de38b60806c2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c @@ -515,6 +515,7 @@ static void mlx5e_stats_update_stats_rq_page_pool(struct mlx5e_channel *c) static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(sw) { struct mlx5e_sw_stats *s = &priv->stats.sw; + u16 nch = mlx5e_stats_nch_read(priv); int i; memset(s, 0, sizeof(*s)); @@ -522,7 +523,7 @@ static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(sw) for (i = 0; i < priv->channels.num; i++) /* for active channels only */ mlx5e_stats_update_stats_rq_page_pool(priv->channels.c[i]); - for (i = 0; i < priv->stats_nch; i++) { + for (i = 0; i < nch; i++) { struct mlx5e_channel_stats *channel_stats = priv->channel_stats[i]; @@ -2614,7 +2615,7 @@ static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(ptp) { return; } static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(channels) { - int max_nch = priv->stats_nch; + int max_nch = mlx5e_stats_nch_read(priv); return (NUM_RQ_STATS * max_nch) + (NUM_CH_STATS * max_nch) + @@ -2627,8 +2628,8 @@ static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(channels) static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(channels) { + int max_nch = mlx5e_stats_nch_read(priv); bool is_xsk = priv->xsk.ever_used; - int max_nch = priv->stats_nch; int i, j, tc; for (i = 0; i < max_nch; i++) @@ -2660,8 +2661,8 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(channels) static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(channels) { + int max_nch = mlx5e_stats_nch_read(priv); bool is_xsk = priv->xsk.ever_used; - int max_nch = priv->stats_nch; int i, j, tc; for (i = 0; i < max_nch; i++) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 910492eb51f2..1bc7b9019124 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -5547,6 +5547,9 @@ void mlx5e_tc_clean_fdb_peer_flows(struct mlx5_eswitch *esw) mlx5_devcom_for_each_peer_entry(devcom, peer_esw, pos) { i = mlx5_lag_get_dev_seq(peer_esw->dev); + if (i < 0) + continue; + list_for_each_entry_safe(flow, tmp, &esw->offloads.peer_flows[i], peer[i]) mlx5e_tc_del_fdb_peers_flow(flow); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c index 0a6003fe60e9..674bed721e63 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c @@ -135,10 +135,11 @@ void mlx5i_cleanup(struct mlx5e_priv *priv) static void mlx5i_grp_sw_update_stats(struct mlx5e_priv *priv) { + u16 nch = mlx5e_stats_nch_read(priv); struct rtnl_link_stats64 s = {}; int i, j; - for (i = 0; i < priv->stats_nch; i++) { + for (i = 0; i < nch; i++) { struct mlx5e_channel_stats *channel_stats; struct mlx5e_rq_stats *rq_stats; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c index 50bfb450c71e..abf72026c751 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c @@ -194,8 +194,10 @@ static void mlx5_mpesw_work(struct work_struct *work) struct mlx5_lag *ldev = mpesww->lag; devcom = mlx5_lag_get_devcom_comp(ldev); - if (!devcom) - return; + if (!devcom) { + mpesww->result = -ENODEV; + goto complete; + } mlx5_devcom_comp_lock(devcom); mlx5_mpesw_sd_devcoms_lock(ldev); @@ -213,6 +215,7 @@ static void mlx5_mpesw_work(struct work_struct *work) mutex_unlock(&ldev->lock); mlx5_mpesw_sd_devcoms_unlock(ldev); mlx5_devcom_comp_unlock(devcom); +complete: complete(&mpesww->comp); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/shared_fdb.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/shared_fdb.c index 113866494d16..6b4ad3c53f2f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/shared_fdb.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/shared_fdb.c @@ -78,7 +78,7 @@ static int mlx5_lag_create_single_fdb_filter(struct mlx5_lag *ldev, u32 filter) } return 0; err: - mlx5_lag_for_each_reverse(j, i, 0, ldev, filter) { + mlx5_lag_for_each_reverse(j, i - 1, 0, ldev, filter) { struct mlx5_eswitch *slave_esw; if (j == master_idx) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/hv_vhca.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/hv_vhca.c index d6dc7bce855e..305752dab7bd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/hv_vhca.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/hv_vhca.c @@ -190,7 +190,7 @@ mlx5_hv_vhca_control_agent_create(struct mlx5_hv_vhca *hv_vhca) return mlx5_hv_vhca_agent_create(hv_vhca, MLX5_HV_VHCA_AGENT_CONTROL, NULL, mlx5_hv_vhca_control_agent_invalidate, - NULL, NULL); + NULL, NULL, NULL); } static void mlx5_hv_vhca_control_agent_destroy(struct mlx5_hv_vhca_agent *agent) @@ -256,7 +256,8 @@ mlx5_hv_vhca_agent_create(struct mlx5_hv_vhca *hv_vhca, void (*invalidate)(struct mlx5_hv_vhca_agent*, u64 block_mask), void (*cleaup)(struct mlx5_hv_vhca_agent *agent), - void *priv) + void *priv, + struct mlx5_hv_vhca_agent **ctx_update) { struct mlx5_hv_vhca_agent *agent; @@ -284,6 +285,9 @@ mlx5_hv_vhca_agent_create(struct mlx5_hv_vhca *hv_vhca, agent->invalidate = invalidate; agent->cleanup = cleaup; + if (ctx_update) + WRITE_ONCE(*ctx_update, agent); + mutex_lock(&hv_vhca->agents_lock); hv_vhca->agents[type] = agent; mutex_unlock(&hv_vhca->agents_lock); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/hv_vhca.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/hv_vhca.h index f240ffe5116c..8b3974cf0ee4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/hv_vhca.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/hv_vhca.h @@ -43,7 +43,8 @@ mlx5_hv_vhca_agent_create(struct mlx5_hv_vhca *hv_vhca, void (*invalidate)(struct mlx5_hv_vhca_agent*, u64 block_mask), void (*cleanup)(struct mlx5_hv_vhca_agent *agent), - void *context); + void *context, + struct mlx5_hv_vhca_agent **ctx_update); void mlx5_hv_vhca_agent_destroy(struct mlx5_hv_vhca_agent *agent); int mlx5_hv_vhca_agent_write(struct mlx5_hv_vhca_agent *agent, @@ -84,7 +85,8 @@ mlx5_hv_vhca_agent_create(struct mlx5_hv_vhca *hv_vhca, void (*invalidate)(struct mlx5_hv_vhca_agent*, u64 block_mask), void (*cleanup)(struct mlx5_hv_vhca_agent *agent), - void *context) + void *context, + struct mlx5_hv_vhca_agent **ctx_update) { return NULL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/port_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/port_tun.c index 4571c56ec3c9..97f6097d4c70 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/port_tun.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/port_tun.c @@ -176,7 +176,8 @@ void mlx5_tun_entropy_refcount_dec(struct mlx5_tun_entropy *tun_entropy, int reformat_type) { mutex_lock(&tun_entropy->lock); - if (reformat_type == MLX5_REFORMAT_TYPE_L2_TO_VXLAN) + if (reformat_type == MLX5_REFORMAT_TYPE_L2_TO_VXLAN || + reformat_type == MLX5_REFORMAT_TYPE_L2_TO_L3_TUNNEL) tun_entropy->num_enabling_entries--; else if (reformat_type == MLX5_REFORMAT_TYPE_L2_TO_NVGRE && --tun_entropy->num_disabling_entries == 0) diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_vcap_impl.c b/drivers/net/ethernet/microchip/lan966x/lan966x_vcap_impl.c index 72e3b189bac5..eb28df80b281 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_vcap_impl.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_vcap_impl.c @@ -601,7 +601,6 @@ static void lan966x_vcap_admin_free(struct vcap_admin *admin) kfree(admin->cache.keystream); kfree(admin->cache.maskstream); kfree(admin->cache.actionstream); - mutex_destroy(&admin->lock); kfree(admin); } @@ -615,7 +614,7 @@ lan966x_vcap_admin_alloc(struct lan966x *lan966x, struct vcap_control *ctrl, if (!admin) return ERR_PTR(-ENOMEM); - mutex_init(&admin->lock); + admin->vctrl = ctrl; INIT_LIST_HEAD(&admin->list); INIT_LIST_HEAD(&admin->rules); INIT_LIST_HEAD(&admin->enabled); @@ -721,6 +720,7 @@ int lan966x_vcap_init(struct lan966x *lan966x) ctrl->ops = &lan966x_vcap_ops; INIT_LIST_HEAD(&ctrl->list); + mutex_init(&ctrl->lock); for (int i = 0; i < ARRAY_SIZE(lan966x_vcap_inst_cfg); ++i) { cfg = &lan966x_vcap_inst_cfg[i]; @@ -780,5 +780,6 @@ void lan966x_vcap_deinit(struct lan966x *lan966x) lan966x_vcap_admin_free(admin); } + mutex_destroy(&ctrl->lock); kfree(ctrl); } diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_impl.c b/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_impl.c index 95b93e46a41d..cf332de6bf73 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_impl.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_impl.c @@ -1930,7 +1930,6 @@ static void sparx5_vcap_admin_free(struct vcap_admin *admin) { if (!admin) return; - mutex_destroy(&admin->lock); kfree(admin->cache.keystream); kfree(admin->cache.maskstream); kfree(admin->cache.actionstream); @@ -1950,7 +1949,7 @@ sparx5_vcap_admin_alloc(struct sparx5 *sparx5, struct vcap_control *ctrl, INIT_LIST_HEAD(&admin->list); INIT_LIST_HEAD(&admin->rules); INIT_LIST_HEAD(&admin->enabled); - mutex_init(&admin->lock); + admin->vctrl = ctrl; admin->vtype = cfg->vtype; admin->vinst = cfg->vinst; admin->ingress = cfg->ingress; @@ -2059,6 +2058,7 @@ int sparx5_vcap_init(struct sparx5 *sparx5) ctrl->ops = &sparx5_vcap_ops; INIT_LIST_HEAD(&ctrl->list); + mutex_init(&ctrl->lock); for (idx = 0; idx < ARRAY_SIZE(sparx5_vcap_inst_cfg); ++idx) { cfg = &consts->vcaps_cfg[idx]; admin = sparx5_vcap_admin_alloc(sparx5, ctrl, cfg); @@ -2097,5 +2097,6 @@ void sparx5_vcap_deinit(struct sparx5 *sparx5) list_del(&admin->list); sparx5_vcap_admin_free(admin); } + mutex_destroy(&ctrl->lock); kfree(ctrl); } diff --git a/drivers/net/ethernet/microchip/vcap/vcap_api.c b/drivers/net/ethernet/microchip/vcap/vcap_api.c index 0fdb5e363bad..ff86cde11a32 100644 --- a/drivers/net/ethernet/microchip/vcap/vcap_api.c +++ b/drivers/net/ethernet/microchip/vcap/vcap_api.c @@ -934,6 +934,16 @@ static bool vcap_rule_exists(struct vcap_control *vctrl, u32 id) return false; } +void vcap_lock(struct vcap_admin *admin) +{ + mutex_lock(&admin->vctrl->lock); +} + +void vcap_unlock(struct vcap_admin *admin) +{ + mutex_unlock(&admin->vctrl->lock); +} + /* Find a rule with a provided rule id return a locked vcap */ static struct vcap_rule_internal * vcap_get_locked_rule(struct vcap_control *vctrl, u32 id) @@ -943,11 +953,11 @@ vcap_get_locked_rule(struct vcap_control *vctrl, u32 id) /* Look for the rule id in all vcaps */ list_for_each_entry(admin, &vctrl->list, list) { - mutex_lock(&admin->lock); + vcap_lock(admin); list_for_each_entry(ri, &admin->rules, list) if (ri->data.id == id) return ri; - mutex_unlock(&admin->lock); + vcap_unlock(admin); } return NULL; } @@ -961,14 +971,14 @@ int vcap_lookup_rule_by_cookie(struct vcap_control *vctrl, u64 cookie) /* Look for the rule id in all vcaps */ list_for_each_entry(admin, &vctrl->list, list) { - mutex_lock(&admin->lock); + vcap_lock(admin); list_for_each_entry(ri, &admin->rules, list) { if (ri->data.cookie == cookie) { id = ri->data.id; break; } } - mutex_unlock(&admin->lock); + vcap_unlock(admin); if (id) return id; } @@ -985,11 +995,11 @@ int vcap_admin_rule_count(struct vcap_admin *admin, int cid) int count = 0; list_for_each_entry(elem, &admin->rules, list) { - mutex_lock(&admin->lock); + vcap_lock(admin); if (elem->data.vcap_chain_id >= min_cid && elem->data.vcap_chain_id < max_cid) ++count; - mutex_unlock(&admin->lock); + vcap_unlock(admin); } return count; } @@ -2266,7 +2276,7 @@ int vcap_add_rule(struct vcap_rule *rule) if (ret) return ret; /* Insert the new rule in the list of vcap rules */ - mutex_lock(&ri->admin->lock); + vcap_lock(ri->admin); vcap_rule_set_state(ri); ret = vcap_insert_rule(ri, &move); @@ -2302,7 +2312,7 @@ int vcap_add_rule(struct vcap_rule *rule) goto out; } out: - mutex_unlock(&ri->admin->lock); + vcap_unlock(ri->admin); return ret; } EXPORT_SYMBOL_GPL(vcap_add_rule); @@ -2330,7 +2340,7 @@ struct vcap_rule *vcap_alloc_rule(struct vcap_control *vctrl, if (vctrl->vcaps[admin->vtype].rows == 0) return ERR_PTR(-EINVAL); - mutex_lock(&admin->lock); + vcap_lock(admin); /* Check if a rule with this id already exists */ if (vcap_rule_exists(vctrl, id)) { err = -EINVAL; @@ -2369,13 +2379,13 @@ struct vcap_rule *vcap_alloc_rule(struct vcap_control *vctrl, goto out_free; } - mutex_unlock(&admin->lock); + vcap_unlock(admin); return (struct vcap_rule *)ri; out_free: kfree(ri); out_unlock: - mutex_unlock(&admin->lock); + vcap_unlock(admin); return ERR_PTR(err); } @@ -2446,7 +2456,7 @@ struct vcap_rule *vcap_get_rule(struct vcap_control *vctrl, u32 id) return ERR_PTR(-ENOENT); rule = vcap_decode_rule(elem); - mutex_unlock(&elem->admin->lock); + vcap_unlock(elem->admin); return rule; } EXPORT_SYMBOL_GPL(vcap_get_rule); @@ -2483,7 +2493,7 @@ int vcap_mod_rule(struct vcap_rule *rule) err = vcap_write_counter(ri, &ctr); out: - mutex_unlock(&ri->admin->lock); + vcap_unlock(ri->admin); return err; } EXPORT_SYMBOL_GPL(vcap_mod_rule); @@ -2570,7 +2580,7 @@ int vcap_del_rule(struct vcap_control *vctrl, struct net_device *ndev, u32 id) admin->last_used_addr = elem->addr; } - mutex_unlock(&admin->lock); + vcap_unlock(admin); return err; } EXPORT_SYMBOL_GPL(vcap_del_rule); @@ -2585,7 +2595,7 @@ int vcap_del_rules(struct vcap_control *vctrl, struct vcap_admin *admin) if (ret) return ret; - mutex_lock(&admin->lock); + vcap_lock(admin); list_for_each_entry_safe(ri, next_ri, &admin->rules, list) { vctrl->ops->init(ri->ndev, admin, ri->addr, ri->size); list_del(&ri->list); @@ -2598,7 +2608,7 @@ int vcap_del_rules(struct vcap_control *vctrl, struct vcap_admin *admin) list_del(&eport->list); kfree(eport); } - mutex_unlock(&admin->lock); + vcap_unlock(admin); return 0; } @@ -3016,7 +3026,7 @@ static int vcap_enable_rules(struct vcap_control *vctrl, continue; /* Found the admin, now find the offloadable rules */ - mutex_lock(&admin->lock); + vcap_lock(admin); list_for_each_entry(ri, &admin->rules, list) { /* Is the rule in the lookup defined by the chain */ if (!(ri->data.vcap_chain_id >= chain && @@ -3034,7 +3044,7 @@ static int vcap_enable_rules(struct vcap_control *vctrl, if (err) break; } - mutex_unlock(&admin->lock); + vcap_unlock(admin); if (err) break; } @@ -3074,7 +3084,7 @@ static int vcap_disable_rules(struct vcap_control *vctrl, continue; /* Found the admin, now find the rules on the chain */ - mutex_lock(&admin->lock); + vcap_lock(admin); list_for_each_entry(ri, &admin->rules, list) { if (ri->data.vcap_chain_id != chain) continue; @@ -3089,7 +3099,7 @@ static int vcap_disable_rules(struct vcap_control *vctrl, if (err) break; } - mutex_unlock(&admin->lock); + vcap_unlock(admin); if (err) break; } @@ -3133,9 +3143,9 @@ static int vcap_enable(struct vcap_control *vctrl, struct net_device *ndev, eport->cookie = cookie; eport->src_cid = src_cid; eport->dst_cid = dst_cid; - mutex_lock(&admin->lock); + vcap_lock(admin); list_add_tail(&eport->list, &admin->enabled); - mutex_unlock(&admin->lock); + vcap_unlock(admin); if (vcap_path_exist(vctrl, ndev, src_cid)) { /* Enable chained lookups */ @@ -3185,9 +3195,9 @@ static int vcap_disable(struct vcap_control *vctrl, struct net_device *ndev, dst_cid = vcap_get_next_chain(vctrl, ndev, dst_cid); } - mutex_lock(&found->lock); + vcap_lock(found); list_del(&eport->list); - mutex_unlock(&found->lock); + vcap_unlock(found); kfree(eport); return 0; } @@ -3270,9 +3280,9 @@ int vcap_rule_set_counter(struct vcap_rule *rule, struct vcap_counter *ctr) return -EINVAL; } - mutex_lock(&ri->admin->lock); + vcap_lock(ri->admin); err = vcap_write_counter(ri, ctr); - mutex_unlock(&ri->admin->lock); + vcap_unlock(ri->admin); return err; } @@ -3291,9 +3301,9 @@ int vcap_rule_get_counter(struct vcap_rule *rule, struct vcap_counter *ctr) return -EINVAL; } - mutex_lock(&ri->admin->lock); + vcap_lock(ri->admin); err = vcap_read_counter(ri, ctr); - mutex_unlock(&ri->admin->lock); + vcap_unlock(ri->admin); return err; } @@ -3395,7 +3405,7 @@ int vcap_get_rule_count_by_cookie(struct vcap_control *vctrl, /* Iterate all rules in each VCAP instance */ list_for_each_entry(admin, &vctrl->list, list) { - mutex_lock(&admin->lock); + vcap_lock(admin); list_for_each_entry(ri, &admin->rules, list) { if (ri->data.cookie != cookie) continue; @@ -3412,12 +3422,12 @@ int vcap_get_rule_count_by_cookie(struct vcap_control *vctrl, if (err) goto unlock; } - mutex_unlock(&admin->lock); + vcap_unlock(admin); } return err; unlock: - mutex_unlock(&admin->lock); + vcap_unlock(admin); return err; } EXPORT_SYMBOL_GPL(vcap_get_rule_count_by_cookie); diff --git a/drivers/net/ethernet/microchip/vcap/vcap_api.h b/drivers/net/ethernet/microchip/vcap/vcap_api.h index 6069ad95c27e..05b4b02e59ef 100644 --- a/drivers/net/ethernet/microchip/vcap/vcap_api.h +++ b/drivers/net/ethernet/microchip/vcap/vcap_api.h @@ -164,7 +164,7 @@ struct vcap_admin { struct list_head list; /* for insertion in vcap_control */ struct list_head rules; /* list of rules */ struct list_head enabled; /* list of enabled ports */ - struct mutex lock; /* control access to rules */ + struct vcap_control *vctrl; /* the control instance owning this vcap */ enum vcap_type vtype; /* type of vcap */ int vinst; /* instance number within the same type */ int first_cid; /* first chain id in this vcap */ @@ -275,6 +275,7 @@ struct vcap_control { const struct vcap_info *vcaps; /* client supplied vcap models */ const struct vcap_statistics *stats; /* client supplied vcap stats */ struct list_head list; /* list of vcap instances */ + struct mutex lock; /* serialize access to all vcap instances */ }; #endif /* __VCAP_API__ */ diff --git a/drivers/net/ethernet/microchip/vcap/vcap_api_debugfs.c b/drivers/net/ethernet/microchip/vcap/vcap_api_debugfs.c index 59bfbda29bb3..e0c65c7ab23e 100644 --- a/drivers/net/ethernet/microchip/vcap/vcap_api_debugfs.c +++ b/drivers/net/ethernet/microchip/vcap/vcap_api_debugfs.c @@ -410,9 +410,9 @@ static int vcap_debugfs_show(struct seq_file *m, void *unused) }; int ret; - mutex_lock(&info->admin->lock); + vcap_lock(info->admin); ret = vcap_show_admin(info->vctrl, info->admin, &out); - mutex_unlock(&info->admin->lock); + vcap_unlock(info->admin); return ret; } DEFINE_SHOW_ATTRIBUTE(vcap_debugfs); @@ -427,9 +427,9 @@ static int vcap_raw_debugfs_show(struct seq_file *m, void *unused) }; int ret; - mutex_lock(&info->admin->lock); + vcap_lock(info->admin); ret = vcap_show_admin_raw(info->vctrl, info->admin, &out); - mutex_unlock(&info->admin->lock); + vcap_unlock(info->admin); return ret; } DEFINE_SHOW_ATTRIBUTE(vcap_raw_debugfs); diff --git a/drivers/net/ethernet/microchip/vcap/vcap_api_debugfs_kunit.c b/drivers/net/ethernet/microchip/vcap/vcap_api_debugfs_kunit.c index 9c9d38042125..ac2a3b8c4f32 100644 --- a/drivers/net/ethernet/microchip/vcap/vcap_api_debugfs_kunit.c +++ b/drivers/net/ethernet/microchip/vcap/vcap_api_debugfs_kunit.c @@ -243,10 +243,11 @@ static void vcap_test_api_init(struct vcap_admin *admin) { /* Initialize the shared objects */ INIT_LIST_HEAD(&test_vctrl.list); + mutex_init(&test_vctrl.lock); INIT_LIST_HEAD(&admin->list); INIT_LIST_HEAD(&admin->rules); INIT_LIST_HEAD(&admin->enabled); - mutex_init(&admin->lock); + admin->vctrl = &test_vctrl; list_add_tail(&admin->list, &test_vctrl.list); memset(test_updateaddr, 0, sizeof(test_updateaddr)); test_updateaddridx = 0; diff --git a/drivers/net/ethernet/microchip/vcap/vcap_api_kunit.c b/drivers/net/ethernet/microchip/vcap/vcap_api_kunit.c index ce26ccbdccdf..83de384d3e3b 100644 --- a/drivers/net/ethernet/microchip/vcap/vcap_api_kunit.c +++ b/drivers/net/ethernet/microchip/vcap/vcap_api_kunit.c @@ -233,10 +233,11 @@ static void vcap_test_api_init(struct vcap_admin *admin) { /* Initialize the shared objects */ INIT_LIST_HEAD(&test_vctrl.list); + mutex_init(&test_vctrl.lock); INIT_LIST_HEAD(&admin->list); INIT_LIST_HEAD(&admin->rules); INIT_LIST_HEAD(&admin->enabled); - mutex_init(&admin->lock); + admin->vctrl = &test_vctrl; list_add_tail(&admin->list, &test_vctrl.list); memset(test_updateaddr, 0, sizeof(test_updateaddr)); test_updateaddridx = 0; diff --git a/drivers/net/ethernet/microchip/vcap/vcap_api_private.h b/drivers/net/ethernet/microchip/vcap/vcap_api_private.h index 844bdf6b5f45..b4057fbe3d18 100644 --- a/drivers/net/ethernet/microchip/vcap/vcap_api_private.h +++ b/drivers/net/ethernet/microchip/vcap/vcap_api_private.h @@ -50,6 +50,9 @@ struct vcap_stream_iter { /* Check that the control has a valid set of callbacks */ int vcap_api_check(struct vcap_control *ctrl); +/* Serialize access to the vcap instances of a control */ +void vcap_lock(struct vcap_admin *admin); +void vcap_unlock(struct vcap_admin *admin); /* Erase the VCAP cache area used or encoding and decoding */ void vcap_erase_cache(struct vcap_rule_internal *ri); diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index 7438ea6b3f26..9d9bfd116dab 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -2120,12 +2120,16 @@ static void mana_rx_skb(void *buf_va, bool from_pool, } static void *mana_get_rxfrag(struct mana_rxq *rxq, struct device *dev, - dma_addr_t *da, bool *from_pool) + dma_addr_t *da, bool *from_pool, + struct page **pp_page, u32 *dma_sync_offset) { struct page *page; u32 offset; void *va; + *from_pool = false; + *pp_page = NULL; + *dma_sync_offset = 0; /* Don't use fragments for jumbo frames or XDP where it's 1 fragment * per page. @@ -2163,31 +2167,47 @@ static void *mana_get_rxfrag(struct mana_rxq *rxq, struct device *dev, va = page_to_virt(page) + offset; *da = page_pool_get_dma_addr(page) + offset + rxq->headroom; *from_pool = true; + *pp_page = page; + *dma_sync_offset = offset + rxq->headroom; return va; } /* Allocate frag for rx buffer, and save the old buf */ static void mana_refill_rx_oob(struct device *dev, struct mana_rxq *rxq, - struct mana_recv_buf_oob *rxoob, void **old_buf, - bool *old_fp) + struct mana_recv_buf_oob *rxoob, u32 pktlen, + void **old_buf, bool *old_fp) { + struct page *pp_page; + u32 dma_sync_offset; bool from_pool; dma_addr_t da; void *va; - va = mana_get_rxfrag(rxq, dev, &da, &from_pool); + va = mana_get_rxfrag(rxq, dev, &da, &from_pool, &pp_page, + &dma_sync_offset); if (!va) return; - if (!rxoob->from_pool || rxq->frag_count == 1) + if (!rxoob->from_pool || rxq->frag_count == 1) { dma_unmap_single(dev, rxoob->sgl[0].address, rxq->datasize, DMA_FROM_DEVICE); + } else { + /* The page pool maps the whole page and only syncs for device + * automatically (PP_FLAG_DMA_SYNC_DEV). Sync the received bytes + * for the CPU before they are read: this is required if DMA + * is incoherent or bounce buffers are used. + */ + page_pool_dma_sync_for_cpu(rxq->page_pool, rxoob->pp_page, + rxoob->dma_sync_offset, pktlen); + } *old_buf = rxoob->buf_va; *old_fp = rxoob->from_pool; rxoob->buf_va = va; rxoob->sgl[0].address = da; rxoob->from_pool = from_pool; + rxoob->pp_page = pp_page; + rxoob->dma_sync_offset = dma_sync_offset; } static void mana_process_rx_cqe(struct mana_rxq *rxq, struct mana_cq *cq, @@ -2246,12 +2266,26 @@ static void mana_process_rx_cqe(struct mana_rxq *rxq, struct mana_cq *cq, rxbuf_oob = &rxq->rx_oobs[curr]; WARN_ON_ONCE(rxbuf_oob->wqe_inf.wqe_size_in_bu != 1); - mana_refill_rx_oob(dev, rxq, rxbuf_oob, &old_buf, &old_fp); + if (unlikely(pktlen > rxq->datasize)) { + /* Increase it even if mana_rx_skb() isn't called. */ + rxq->rx_cq.work_done++; - /* Unsuccessful refill will have old_buf == NULL. - * In this case, mana_rx_skb() will drop the packet. - */ - mana_rx_skb(old_buf, old_fp, oob, rxq, i); + ++ndev->stats.rx_dropped; + netdev_warn_once(ndev, + "Dropped oversized RX packet: len=%u, datasize=%u\n", + pktlen, rxq->datasize); + + /* Reuse the RX buffer since rxbuf_oob is unchanged. */ + } else { + + mana_refill_rx_oob(dev, rxq, rxbuf_oob, pktlen, + &old_buf, &old_fp); + + /* Unsuccessful refill will have old_buf == NULL. + * In this case, mana_rx_skb() will drop the packet. + */ + mana_rx_skb(old_buf, old_fp, oob, rxq, i); + } mana_move_wq_tail(rxq->gdma_rq, rxbuf_oob->wqe_inf.wqe_size_in_bu); @@ -2655,6 +2689,8 @@ static int mana_fill_rx_oob(struct mana_recv_buf_oob *rx_oob, u32 mem_key, struct mana_rxq *rxq, struct device *dev) { struct mana_port_context *mpc = netdev_priv(rxq->ndev); + struct page *pp_page = NULL; + u32 dma_sync_offset = 0; bool from_pool = false; dma_addr_t da; void *va; @@ -2662,13 +2698,16 @@ static int mana_fill_rx_oob(struct mana_recv_buf_oob *rx_oob, u32 mem_key, if (mpc->rxbufs_pre) va = mana_get_rxbuf_pre(rxq, &da); else - va = mana_get_rxfrag(rxq, dev, &da, &from_pool); + va = mana_get_rxfrag(rxq, dev, &da, &from_pool, &pp_page, + &dma_sync_offset); if (!va) return -ENOMEM; rx_oob->buf_va = va; rx_oob->from_pool = from_pool; + rx_oob->pp_page = pp_page; + rx_oob->dma_sync_offset = dma_sync_offset; rx_oob->sgl[0].address = da; rx_oob->sgl[0].size = rxq->datasize; diff --git a/drivers/net/ethernet/mucse/rnpgbe/rnpgbe_mbx.c b/drivers/net/ethernet/mucse/rnpgbe/rnpgbe_mbx.c index de5e29230b3c..c46408698263 100644 --- a/drivers/net/ethernet/mucse/rnpgbe/rnpgbe_mbx.c +++ b/drivers/net/ethernet/mucse/rnpgbe/rnpgbe_mbx.c @@ -166,18 +166,23 @@ static void mucse_mbx_inc_pf_ack(struct mucse_hw *hw) * * Return: 0 on success, negative errno on failure **/ -static int mucse_read_mbx_pf(struct mucse_hw *hw, u32 *msg, u16 size) +static int mucse_read_mbx_pf(struct mucse_hw *hw, __le32 *msg, u16 size) { - const int size_in_words = size / sizeof(u32); + const int size_in_words = size / sizeof(__le32); struct mucse_mbx_info *mbx = &hw->mbx; + int off = MUCSE_MBX_FWPF_SHM; int err; err = mucse_obtain_mbx_lock_pf(hw); if (err) return err; + /* memcpy_fromio() is unsuitable: the mailbox uses 32-bit MMIO + * registers, not byte-addressable RAM. readl() guarantees + * the required 32-bit access width. + */ for (int i = 0; i < size_in_words; i++) - msg[i] = mbx_data_rd32(mbx, MUCSE_MBX_FWPF_SHM + 4 * i); + msg[i] = cpu_to_le32(mbx_data_rd32(mbx, off + 4 * i)); /* Hw needs write data_reg at last */ mbx_data_wr32(mbx, MUCSE_MBX_FWPF_SHM, 0); /* flush reqs as we have read this request data */ @@ -236,7 +241,7 @@ static int mucse_poll_for_msg(struct mucse_hw *hw) * Return: 0 if it successfully received a message notification and * copied it into the receive buffer, negative errno on failure **/ -int mucse_poll_and_read_mbx(struct mucse_hw *hw, u32 *msg, u16 size) +int mucse_poll_and_read_mbx(struct mucse_hw *hw, __le32 *msg, u16 size) { int err; @@ -290,9 +295,9 @@ static void mucse_mbx_inc_pf_req(struct mucse_hw *hw) * Return: 0 if it successfully copied message into the buffer, * negative errno on failure **/ -static int mucse_write_mbx_pf(struct mucse_hw *hw, u32 *msg, u16 size) +static int mucse_write_mbx_pf(struct mucse_hw *hw, const __le32 *msg, u16 size) { - const int size_in_words = size / sizeof(u32); + const int size_in_words = size / sizeof(__le32); struct mucse_mbx_info *mbx = &hw->mbx; int err; @@ -300,8 +305,12 @@ static int mucse_write_mbx_pf(struct mucse_hw *hw, u32 *msg, u16 size) if (err) return err; + /* memcpy_toio() would decompose into arbitrary-width accesses; + * the mailbox requires 32-bit MMIO writes via writel(). + */ for (int i = 0; i < size_in_words; i++) - mbx_data_wr32(mbx, MUCSE_MBX_FWPF_SHM + i * 4, msg[i]); + mbx_data_wr32(mbx, MUCSE_MBX_FWPF_SHM + i * 4, + le32_to_cpu(msg[i])); /* flush acks as we are overwriting the message buffer */ hw->mbx.fw_ack = mucse_mbx_get_fwack(mbx); @@ -360,7 +369,8 @@ static int mucse_poll_for_ack(struct mucse_hw *hw) * Return: 0 if it successfully copied message into the buffer and * received an ack to that message within delay * timeout_cnt period **/ -int mucse_write_and_wait_ack_mbx(struct mucse_hw *hw, u32 *msg, u16 size) +int mucse_write_and_wait_ack_mbx(struct mucse_hw *hw, const __le32 *msg, + u16 size) { int err; diff --git a/drivers/net/ethernet/mucse/rnpgbe/rnpgbe_mbx.h b/drivers/net/ethernet/mucse/rnpgbe/rnpgbe_mbx.h index e6fcc8d1d3ca..75b88b18b04d 100644 --- a/drivers/net/ethernet/mucse/rnpgbe/rnpgbe_mbx.h +++ b/drivers/net/ethernet/mucse/rnpgbe/rnpgbe_mbx.h @@ -14,7 +14,8 @@ #define MUCSE_MBX_REQ BIT(0) /* Request a req to mailbox */ #define MUCSE_MBX_PFU BIT(3) /* PF owns the mailbox buffer */ -int mucse_write_and_wait_ack_mbx(struct mucse_hw *hw, u32 *msg, u16 size); +int mucse_write_and_wait_ack_mbx(struct mucse_hw *hw, + const __le32 *msg, u16 size); void mucse_init_mbx_params_pf(struct mucse_hw *hw); -int mucse_poll_and_read_mbx(struct mucse_hw *hw, u32 *msg, u16 size); +int mucse_poll_and_read_mbx(struct mucse_hw *hw, __le32 *msg, u16 size); #endif /* _RNPGBE_MBX_H */ diff --git a/drivers/net/ethernet/mucse/rnpgbe/rnpgbe_mbx_fw.c b/drivers/net/ethernet/mucse/rnpgbe/rnpgbe_mbx_fw.c index 8c8bd5e8e1db..5ba74997beac 100644 --- a/drivers/net/ethernet/mucse/rnpgbe/rnpgbe_mbx_fw.c +++ b/drivers/net/ethernet/mucse/rnpgbe/rnpgbe_mbx_fw.c @@ -20,32 +20,32 @@ * Return: 0 on success, negative errno on failure **/ static int mucse_fw_send_cmd_wait_resp(struct mucse_hw *hw, - struct mbx_fw_cmd_req *req, - struct mbx_fw_cmd_reply *reply) + union mbx_fw_cmd_req_u *req, + union mbx_fw_cmd_reply_u *reply) { - int len = le16_to_cpu(req->datalen); + int len = le16_to_cpu(req->r.datalen); int retry_cnt = 3; int err; mutex_lock(&hw->mbx.lock); - err = mucse_write_and_wait_ack_mbx(hw, (u32 *)req, len); + err = mucse_write_and_wait_ack_mbx(hw, req->dwords, len); if (err) goto out; do { - err = mucse_poll_and_read_mbx(hw, (u32 *)reply, - sizeof(*reply)); + err = mucse_poll_and_read_mbx(hw, reply->dwords, + sizeof(reply->r)); if (err) goto out; /* mucse_write_and_wait_ack_mbx return 0 means fw has * received request, wait for the expect opcode * reply with 'retry_cnt' times. */ - } while (--retry_cnt >= 0 && reply->opcode != req->opcode); + } while (--retry_cnt >= 0 && reply->r.opcode != req->r.opcode); out: mutex_unlock(&hw->mbx.lock); if (!err && retry_cnt < 0) return -ETIMEDOUT; - if (!err && reply->error_code) + if (!err && reply->r.error_code) return -EIO; return err; @@ -61,17 +61,19 @@ static int mucse_fw_send_cmd_wait_resp(struct mucse_hw *hw, **/ static int mucse_mbx_get_info(struct mucse_hw *hw) { - struct mbx_fw_cmd_req req = { - .datalen = cpu_to_le16(MUCSE_MBX_REQ_HDR_LEN), - .opcode = cpu_to_le16(GET_HW_INFO), + union mbx_fw_cmd_req_u req = { + .r = { + .datalen = cpu_to_le16(MUCSE_MBX_REQ_HDR_LEN), + .opcode = cpu_to_le16(GET_HW_INFO), + }, }; - struct mbx_fw_cmd_reply reply = {}; + union mbx_fw_cmd_reply_u reply = {}; int err; err = mucse_fw_send_cmd_wait_resp(hw, &req, &reply); if (!err) hw->pfvfnum = FIELD_GET(GENMASK_U16(7, 0), - le16_to_cpu(reply.hw_info.pfnum)); + le16_to_cpu(reply.r.hw_info.pfnum)); return err; } @@ -111,21 +113,23 @@ int mucse_mbx_sync_fw(struct mucse_hw *hw) **/ int mucse_mbx_powerup(struct mucse_hw *hw, bool is_powerup) { - struct mbx_fw_cmd_req req = { - .datalen = cpu_to_le16(sizeof(req.powerup) + - MUCSE_MBX_REQ_HDR_LEN), - .opcode = cpu_to_le16(POWER_UP), - .powerup = { - /* fw needs this to reply correct cmd */ - .version = cpu_to_le32(GENMASK_U32(31, 0)), - .status = cpu_to_le32(is_powerup ? 1 : 0), + union mbx_fw_cmd_req_u req = { + .r = { + .datalen = cpu_to_le16(sizeof(req.r.powerup) + + MUCSE_MBX_REQ_HDR_LEN), + .opcode = cpu_to_le16(POWER_UP), + .powerup = { + /* fw needs this to reply correct cmd */ + .version = cpu_to_le32(GENMASK_U32(31, 0)), + .status = cpu_to_le32(is_powerup ? 1 : 0), + }, }, }; int len, err; - len = le16_to_cpu(req.datalen); + len = le16_to_cpu(req.r.datalen); mutex_lock(&hw->mbx.lock); - err = mucse_write_and_wait_ack_mbx(hw, (u32 *)&req, len); + err = mucse_write_and_wait_ack_mbx(hw, req.dwords, len); mutex_unlock(&hw->mbx.lock); return err; @@ -142,11 +146,13 @@ int mucse_mbx_powerup(struct mucse_hw *hw, bool is_powerup) **/ int mucse_mbx_reset_hw(struct mucse_hw *hw) { - struct mbx_fw_cmd_req req = { - .datalen = cpu_to_le16(MUCSE_MBX_REQ_HDR_LEN), - .opcode = cpu_to_le16(RESET_HW), + union mbx_fw_cmd_req_u req = { + .r = { + .datalen = cpu_to_le16(MUCSE_MBX_REQ_HDR_LEN), + .opcode = cpu_to_le16(RESET_HW), + }, }; - struct mbx_fw_cmd_reply reply = {}; + union mbx_fw_cmd_reply_u reply = {}; return mucse_fw_send_cmd_wait_resp(hw, &req, &reply); } @@ -166,24 +172,26 @@ int mucse_mbx_get_macaddr(struct mucse_hw *hw, int pfvfnum, u8 *mac_addr, int port) { - struct mbx_fw_cmd_req req = { - .datalen = cpu_to_le16(sizeof(req.get_mac_addr) + - MUCSE_MBX_REQ_HDR_LEN), - .opcode = cpu_to_le16(GET_MAC_ADDRESS), - .get_mac_addr = { - .port_mask = cpu_to_le32(BIT(port)), - .pfvf_num = cpu_to_le32(pfvfnum), + union mbx_fw_cmd_req_u req = { + .r = { + .datalen = cpu_to_le16(sizeof(req.r.get_mac_addr) + + MUCSE_MBX_REQ_HDR_LEN), + .opcode = cpu_to_le16(GET_MAC_ADDRESS), + .get_mac_addr = { + .port_mask = cpu_to_le32(BIT(port)), + .pfvf_num = cpu_to_le32(pfvfnum), + }, }, }; - struct mbx_fw_cmd_reply reply = {}; + union mbx_fw_cmd_reply_u reply = {}; int err; err = mucse_fw_send_cmd_wait_resp(hw, &req, &reply); if (err) return err; - if (le32_to_cpu(reply.mac_addr.ports) & BIT(port)) - memcpy(mac_addr, reply.mac_addr.addrs[port].mac, ETH_ALEN); + if (le32_to_cpu(reply.r.mac_addr.ports) & BIT(port)) + memcpy(mac_addr, reply.r.mac_addr.addrs[port].mac, ETH_ALEN); else return -ENODATA; diff --git a/drivers/net/ethernet/mucse/rnpgbe/rnpgbe_mbx_fw.h b/drivers/net/ethernet/mucse/rnpgbe/rnpgbe_mbx_fw.h index fb24fc12b613..fe996aeffc4d 100644 --- a/drivers/net/ethernet/mucse/rnpgbe/rnpgbe_mbx_fw.h +++ b/drivers/net/ethernet/mucse/rnpgbe/rnpgbe_mbx_fw.h @@ -80,6 +80,20 @@ struct mbx_fw_cmd_reply { }; } __packed; +/* Union wrappers to expose struct as __le32 dword array for mailbox + * transport, eliminating the need for pointer casts. The __packed + * structs have no padding, so dwords[] overlays the fields exactly. + */ +union mbx_fw_cmd_req_u { + struct mbx_fw_cmd_req r; + __le32 dwords[sizeof(struct mbx_fw_cmd_req) / sizeof(__le32)]; +}; + +union mbx_fw_cmd_reply_u { + struct mbx_fw_cmd_reply r; + __le32 dwords[sizeof(struct mbx_fw_cmd_reply) / sizeof(__le32)]; +}; + int mucse_mbx_sync_fw(struct mucse_hw *hw); int mucse_mbx_powerup(struct mucse_hw *hw, bool is_powerup); int mucse_mbx_reset_hw(struct mucse_hw *hw); diff --git a/drivers/net/ethernet/qlogic/qede/qede_fp.c b/drivers/net/ethernet/qlogic/qede/qede_fp.c index 33e18bb69774..c11e0d8f98aa 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_fp.c +++ b/drivers/net/ethernet/qlogic/qede/qede_fp.c @@ -765,6 +765,9 @@ qede_tpa_rx_build_skb(struct qede_dev *edev, struct sk_buff *skb; skb = qede_build_skb(rxq, bd, len, pad); + if (unlikely(!skb)) + return NULL; + bd->page_offset += rxq->rx_buf_seg_size; if (bd->page_offset == PAGE_SIZE) { @@ -812,6 +815,8 @@ qede_rx_build_skb(struct qede_dev *edev, } skb = qede_build_skb(rxq, bd, len, pad); + if (unlikely(!skb)) + return NULL; if (unlikely(qede_realloc_rx_buffer(rxq, bd))) { /* Incr page ref count to reuse on allocation failure so diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c index 9f3479500f85..d055a2628d8c 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c @@ -126,7 +126,10 @@ rmnet_map_ingress_handler(struct sk_buff *skb, consume_skb(skb); } else { - __rmnet_map_ingress_handler(skb, port); + if (rmnet_map_validate_packet_len(skb, port)) + __rmnet_map_ingress_handler(skb, port); + else + kfree_skb(skb); } } diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map.h b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map.h index b70284095568..60ca8b780c88 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map.h +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map.h @@ -59,5 +59,6 @@ void rmnet_map_tx_aggregate_init(struct rmnet_port *port); void rmnet_map_tx_aggregate_exit(struct rmnet_port *port); void rmnet_map_update_ul_agg_config(struct rmnet_port *port, u32 size, u32 count, u32 time); +u32 rmnet_map_validate_packet_len(struct sk_buff *skb, struct rmnet_port *port); #endif /* _RMNET_MAP_H_ */ diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c index 8b4640c5d61e..305ae15ae8f3 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c @@ -333,6 +333,47 @@ struct rmnet_map_header *rmnet_map_add_map_header(struct sk_buff *skb, return map_header; } +u32 rmnet_map_validate_packet_len(struct sk_buff *skb, struct rmnet_port *port) +{ + struct rmnet_map_v5_csum_header *next_hdr = NULL; + struct rmnet_map_header *maph; + void *data = skb->data; + u32 packet_len; + + if (skb->len < sizeof(*maph)) + return 0; + + maph = (struct rmnet_map_header *)skb->data; + + /* Some hardware can send us empty frames. Catch them */ + if (!maph->pkt_len) + return 0; + + packet_len = ntohs(maph->pkt_len) + sizeof(*maph); + + if (port->data_format & RMNET_FLAGS_INGRESS_MAP_CKSUMV4) { + packet_len += sizeof(struct rmnet_map_dl_csum_trailer); + } else if ((port->data_format & RMNET_FLAGS_INGRESS_MAP_CKSUMV5) && + !(maph->flags & MAP_CMD_FLAG)) { + /* Mapv5 data pkt without csum hdr is invalid */ + if (!(maph->flags & MAP_NEXT_HEADER_FLAG)) + return 0; + + packet_len += sizeof(*next_hdr); + next_hdr = data + sizeof(*maph); + } + + if (skb->len < packet_len) + return 0; + + if (next_hdr && + u8_get_bits(next_hdr->header_info, MAPV5_HDRINFO_HDR_TYPE_FMASK) != + RMNET_MAP_HEADER_TYPE_CSUM_OFFLOAD) + return 0; + + return packet_len; +} + /* Deaggregates a single packet * A whole new buffer is allocated for each portion of an aggregated frame. * Caller should keep calling deaggregate() on the source skb until 0 is @@ -342,46 +383,13 @@ struct rmnet_map_header *rmnet_map_add_map_header(struct sk_buff *skb, struct sk_buff *rmnet_map_deaggregate(struct sk_buff *skb, struct rmnet_port *port) { - struct rmnet_map_v5_csum_header *next_hdr = NULL; - struct rmnet_map_header *maph; - void *data = skb->data; struct sk_buff *skbn; - u8 nexthdr_type; u32 packet_len; - if (skb->len == 0) + packet_len = rmnet_map_validate_packet_len(skb, port); + if (!packet_len) return NULL; - maph = (struct rmnet_map_header *)skb->data; - packet_len = ntohs(maph->pkt_len) + sizeof(*maph); - - if (port->data_format & RMNET_FLAGS_INGRESS_MAP_CKSUMV4) { - packet_len += sizeof(struct rmnet_map_dl_csum_trailer); - } else if (port->data_format & RMNET_FLAGS_INGRESS_MAP_CKSUMV5) { - if (!(maph->flags & MAP_CMD_FLAG)) { - packet_len += sizeof(*next_hdr); - if (maph->flags & MAP_NEXT_HEADER_FLAG) - next_hdr = data + sizeof(*maph); - else - /* Mapv5 data pkt without csum hdr is invalid */ - return NULL; - } - } - - if (((int)skb->len - (int)packet_len) < 0) - return NULL; - - /* Some hardware can send us empty frames. Catch them */ - if (!maph->pkt_len) - return NULL; - - if (next_hdr) { - nexthdr_type = u8_get_bits(next_hdr->header_info, - MAPV5_HDRINFO_HDR_TYPE_FMASK); - if (nexthdr_type != RMNET_MAP_HEADER_TYPE_CSUM_OFFLOAD) - return NULL; - } - skbn = alloc_skb(packet_len + RMNET_MAP_DEAGGR_SPACING, GFP_ATOMIC); if (!skbn) return NULL; diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index fb009120a924..dd89282f0179 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -646,7 +646,7 @@ static struct sk_buff *macsec_encrypt(struct sk_buff *skb, } unprotected_len = skb->len; - eth = eth_hdr(skb); + eth = skb_eth_hdr(skb); sci_present = macsec_send_sci(secy); hh = skb_push(skb, macsec_extra_len(sci_present)); memmove(hh, eth, 2 * ETH_ALEN); diff --git a/drivers/net/mdio/Kconfig b/drivers/net/mdio/Kconfig index c591eec8e97a..e57121019153 100644 --- a/drivers/net/mdio/Kconfig +++ b/drivers/net/mdio/Kconfig @@ -122,7 +122,8 @@ config MDIO_MVUSB config MDIO_MSCC_MIIM tristate "Microsemi MIIM interface support" - depends on HAS_IOMEM && REGMAP_MMIO + depends on HAS_IOMEM + select REGMAP_MMIO help This driver supports the MIIM (MDIO) interface found in the network switches of the Microsemi SoCs; it is recommended to switch on diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index c4cebacabcb5..cb782d81d84f 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -1499,6 +1499,17 @@ static void lan78xx_deferred_multicast_write(struct work_struct *param) return; } +static void lan78xx_update_vlan_filter(struct lan78xx_priv *pdata, + struct net_device *netdev, + netdev_features_t features) +{ + if ((features & NETIF_F_HW_VLAN_CTAG_FILTER) && + !(netdev->flags & IFF_PROMISC)) + pdata->rfe_ctl |= RFE_CTL_VLAN_FILTER_; + else + pdata->rfe_ctl &= ~RFE_CTL_VLAN_FILTER_; +} + static void lan78xx_set_multicast(struct net_device *netdev) { struct lan78xx_net *dev = netdev_priv(netdev); @@ -1533,6 +1544,8 @@ static void lan78xx_set_multicast(struct net_device *netdev) } } + lan78xx_update_vlan_filter(pdata, dev->net, dev->net->features); + if (netdev_mc_count(dev->net)) { struct netdev_hw_addr *ha; int i; @@ -3074,10 +3087,7 @@ static int lan78xx_set_features(struct net_device *netdev, else pdata->rfe_ctl &= ~RFE_CTL_VLAN_STRIP_; - if (features & NETIF_F_HW_VLAN_CTAG_FILTER) - pdata->rfe_ctl |= RFE_CTL_VLAN_FILTER_; - else - pdata->rfe_ctl &= ~RFE_CTL_VLAN_FILTER_; + lan78xx_update_vlan_filter(pdata, netdev, features); spin_unlock_irqrestore(&pdata->rfe_ctl_lock, flags); diff --git a/drivers/net/usb/net1080.c b/drivers/net/usb/net1080.c index 5d4a1fd2b524..19f6e1222d93 100644 --- a/drivers/net/usb/net1080.c +++ b/drivers/net/usb/net1080.c @@ -381,7 +381,7 @@ static int net1080_rx_fixup(struct usbnet *dev, struct sk_buff *skb) skb_trim(skb, skb->len - sizeof *trailer); if ((packet_len & 0x01) == 0) { - if (skb->data [packet_len] != PAD_BYTE) { + if (packet_len >= skb->len || skb->data[packet_len] != PAD_BYTE) { dev->net->stats.rx_frame_errors++; netdev_dbg(dev->net, "bad pad\n"); return 0; diff --git a/drivers/platform/x86/amd/pmc/pmc.c b/drivers/platform/x86/amd/pmc/pmc.c index d50ea62fa2f3..a37083cdb908 100644 --- a/drivers/platform/x86/amd/pmc/pmc.c +++ b/drivers/platform/x86/amd/pmc/pmc.c @@ -33,6 +33,28 @@ #include "pmc.h" +static const struct amd_pmc_bit_map soc15_ip_blk_v3[] = { + {"VDDCR", BIT(0)}, + {"VDDCR_LP", BIT(1)}, + {"LSOCV", BIT(2)}, + {"DISPLAY", BIT(3)}, + {"VCN", BIT(4)}, + {"JPEG", BIT(5)}, + {"UMSCH", BIT(6)}, + {"VPE", BIT(7)}, + {"MPM", BIT(8)}, + {"NPU", BIT(9)}, + {"USB_HC0", BIT(10)}, + {"eUSB_HC0", BIT(11)}, + {"RT0_ADP_HC1", BIT(12)}, + {"RT1_ADP_HC1", BIT(13)}, + {"RT2_ADP_HC2", BIT(14)}, + {"USB4_RT0", BIT(15)}, + {"USB4_RT1", BIT(16)}, + {"USB4-RT2", BIT(17)}, + {"LAPIC", BIT(18)}, +}; + static const struct amd_pmc_bit_map soc15_ip_blk_v2[] = { {"DISPLAY", BIT(0)}, {"CPU", BIT(1)}, @@ -159,9 +181,9 @@ static const struct amd_pmc_cpu_info amd_1ah_m80_cpu_info = { .smu_msg = AMD_PMC_REGISTER_MSG_1AH_80H, .smu_arg = AMD_PMC_REGISTER_ARG_1AH_80H, .smu_rsp = AMD_PMC_REGISTER_RSP_1AH_80H, - .num_ips = ARRAY_SIZE(soc15_ip_blk), + .num_ips = ARRAY_SIZE(soc15_ip_blk_v3), .scratch_reg = AMD_PMC_SCRATCH_REG_1AH, - .ips_ptr = soc15_ip_blk, + .ips_ptr = soc15_ip_blk_v3, .os_hint = MSG_OS_HINT_RN, }; @@ -735,11 +757,11 @@ static bool amd_pmc_want_suspend_delay(struct amd_pmc_dev *pdev) } else if (delay_suspend == 1) { if (!intermediate_wakeup) dev_info(pdev->dev, "Delaying suspend by 2.5s because delay_suspend=1. If this solves problems on your machine, please report this whole line to: platform-driver-x86@vger.kernel.org so it can be automatically detected as affected in the future. System Vendor: \"%s\" Product Name: \"%s\" Product Family: \"%s\" Board Vendor: \"%s\" Board Name: \"%s\"\n", - dmi_get_system_info(DMI_SYS_VENDOR), - dmi_get_system_info(DMI_PRODUCT_NAME), - dmi_get_system_info(DMI_PRODUCT_FAMILY), - dmi_get_system_info(DMI_BOARD_VENDOR), - dmi_get_system_info(DMI_BOARD_NAME)); + dmi_get_system_info(DMI_SYS_VENDOR) ?: "(Unknown)", + dmi_get_system_info(DMI_PRODUCT_NAME) ?: "(Unknown)", + dmi_get_system_info(DMI_PRODUCT_FAMILY) ?: "(Unknown)", + dmi_get_system_info(DMI_BOARD_VENDOR) ?: "(Unknown)", + dmi_get_system_info(DMI_BOARD_NAME) ?: "(Unknown)"); return true; } return false; diff --git a/drivers/platform/x86/asus-armoury.h b/drivers/platform/x86/asus-armoury.h index 65166b50a2c3..322bfa647c2d 100644 --- a/drivers/platform/x86/asus-armoury.h +++ b/drivers/platform/x86/asus-armoury.h @@ -1997,13 +1997,13 @@ static const struct dmi_system_id power_limits[] = { .driver_data = &(struct power_data) { .ac_data = &(struct power_limits) { .ppt_pl1_spl_min = 30, - .ppt_pl1_spl_max = 90, + .ppt_pl1_spl_max = 120, .ppt_pl2_sppt_min = 65, - .ppt_pl2_sppt_def = 110, - .ppt_pl2_sppt_max = 125, + .ppt_pl2_sppt_def = 140, + .ppt_pl2_sppt_max = 145, .ppt_pl3_fppt_min = 65, - .ppt_pl3_fppt_def = 110, - .ppt_pl3_fppt_max = 125, + .ppt_pl3_fppt_def = 140, + .ppt_pl3_fppt_max = 145, .nv_temp_target_min = 75, .nv_temp_target_max = 87, .nv_dynamic_boost_min = 5, diff --git a/drivers/platform/x86/bitland-mifs-wmi.c b/drivers/platform/x86/bitland-mifs-wmi.c index b0d06a80e89e..3a373184519d 100644 --- a/drivers/platform/x86/bitland-mifs-wmi.c +++ b/drivers/platform/x86/bitland-mifs-wmi.c @@ -300,6 +300,10 @@ static int bitland_mifs_wmi_suspend(struct device *dev) enum platform_profile_option profile; int ret; + /* Skip event device */ + if (!data->pp_dev) + return 0; + ret = laptop_profile_get(data->pp_dev, &profile); if (ret == 0) data->saved_profile = profile; @@ -311,6 +315,10 @@ static int bitland_mifs_wmi_resume(struct device *dev) { struct bitland_mifs_wmi_data *data = dev_get_drvdata(dev); + /* Skip event device */ + if (!data->pp_dev) + return 0; + dev_dbg(dev, "Resuming, restoring profile %d\n", data->saved_profile); return laptop_profile_set(dev, data->saved_profile); } diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index dc5d67767336..1797929dfe56 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -248,7 +248,7 @@ static void regulator_lock_two(struct regulator_dev *rdev1, ret = regulator_lock_nested(rdev1, ww_ctx); WARN_ON(ret); ret = regulator_lock_nested(rdev2, ww_ctx); - if (ret != -EDEADLOCK) { + if (ret != -EDEADLK) { WARN_ON(ret); goto exit; } @@ -264,7 +264,7 @@ static void regulator_lock_two(struct regulator_dev *rdev1, swap(held, contended); ret = regulator_lock_nested(contended, ww_ctx); - if (ret != -EDEADLOCK) { + if (ret != -EDEADLK) { WARN_ON(ret); break; } diff --git a/drivers/regulator/mt6316-regulator.c b/drivers/regulator/mt6316-regulator.c index 952852bbe923..b170506eec57 100644 --- a/drivers/regulator/mt6316-regulator.c +++ b/drivers/regulator/mt6316-regulator.c @@ -329,6 +329,7 @@ static const struct of_device_id mt6316_regulator_match[] = { { .compatible = "mediatek,mt6316d-regulator", .data = (void *)MT6316_TYPE_4PHASE }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, mt6316_regulator_match); static struct spmi_driver mt6316_regulator_driver = { .driver = { diff --git a/drivers/regulator/mt6363-regulator.c b/drivers/regulator/mt6363-regulator.c index 0aebcbda0a19..aa6a8eb7ac4b 100644 --- a/drivers/regulator/mt6363-regulator.c +++ b/drivers/regulator/mt6363-regulator.c @@ -927,6 +927,7 @@ static const struct of_device_id mt6363_regulator_match[] = { { .compatible = "mediatek,mt6363-regulator" }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, mt6363_regulator_match); static struct platform_driver mt6363_regulator_driver = { .driver = { diff --git a/drivers/s390/crypto/zcrypt_cex2a.c b/drivers/s390/crypto/zcrypt_cex2a.c deleted file mode 100644 index e69de29bb2d1..000000000000 diff --git a/drivers/s390/crypto/zcrypt_cex2a.h b/drivers/s390/crypto/zcrypt_cex2a.h deleted file mode 100644 index e69de29bb2d1..000000000000 diff --git a/drivers/s390/crypto/zcrypt_cex2c.c b/drivers/s390/crypto/zcrypt_cex2c.c deleted file mode 100644 index e69de29bb2d1..000000000000 diff --git a/drivers/s390/crypto/zcrypt_cex2c.h b/drivers/s390/crypto/zcrypt_cex2c.h deleted file mode 100644 index e69de29bb2d1..000000000000 diff --git a/drivers/staging/rtl8723bs/core/rtw_ieee80211.c b/drivers/staging/rtl8723bs/core/rtw_ieee80211.c index 8d4bcf7ebeaf..d670540d5809 100644 --- a/drivers/staging/rtl8723bs/core/rtw_ieee80211.c +++ b/drivers/staging/rtl8723bs/core/rtw_ieee80211.c @@ -587,9 +587,14 @@ int rtw_get_wapi_ie(u8 *in_ie, uint in_len, u8 *wapi_ie, u16 *wapi_len) cnt = (_TIMESTAMP_ + _BEACON_ITERVAL_ + _CAPABILITY_); while (cnt < in_len) { + if (cnt + 2 > in_len) + break; + if (cnt + 2 + in_ie[cnt + 1] > in_len) + break; authmode = in_ie[cnt]; if (authmode == WLAN_EID_BSS_AC_ACCESS_DELAY && + in_ie[cnt + 1] >= 8 && (!memcmp(&in_ie[cnt + 6], wapi_oui1, 4) || !memcmp(&in_ie[cnt + 6], wapi_oui2, 4))) { if (wapi_ie) @@ -619,9 +624,14 @@ void rtw_get_sec_ie(u8 *in_ie, uint in_len, u8 *rsn_ie, u16 *rsn_len, u8 *wpa_ie cnt = (_TIMESTAMP_ + _BEACON_ITERVAL_ + _CAPABILITY_); while (cnt < in_len) { + if (cnt + 2 > in_len) + break; + if (cnt + 2 + in_ie[cnt + 1] > in_len) + break; authmode = in_ie[cnt]; if ((authmode == WLAN_EID_VENDOR_SPECIFIC) && + in_ie[cnt + 1] >= 4 && (!memcmp(&in_ie[cnt + 2], &wpa_oui[0], 4))) { if (wpa_ie) memcpy(wpa_ie, &in_ie[cnt], in_ie[cnt + 1] + 2); @@ -702,6 +712,9 @@ u8 *rtw_get_wps_attr(u8 *wps_ie, uint wps_ielen, u16 target_attr_id, u8 *buf_att if (len_attr) *len_attr = 0; + if (wps_ielen < 6) + return attr_ptr; + if ((wps_ie[0] != WLAN_EID_VENDOR_SPECIFIC) || (memcmp(wps_ie + 2, wps_oui, 4))) { return attr_ptr; @@ -712,6 +725,8 @@ u8 *rtw_get_wps_attr(u8 *wps_ie, uint wps_ielen, u16 target_attr_id, u8 *buf_att while (attr_ptr - wps_ie < wps_ielen) { /* 4 = 2(Attribute ID) + 2(Length) */ + if (attr_ptr + 4 > wps_ie + wps_ielen) + break; u16 attr_id = get_unaligned_be16(attr_ptr); u16 attr_data_len = get_unaligned_be16(attr_ptr + 2); u16 attr_len = attr_data_len + 4; diff --git a/drivers/staging/rtl8723bs/core/rtw_mlme_ext.c b/drivers/staging/rtl8723bs/core/rtw_mlme_ext.c index 833132a12be2..8cf3c14a0dd7 100644 --- a/drivers/staging/rtl8723bs/core/rtw_mlme_ext.c +++ b/drivers/staging/rtl8723bs/core/rtw_mlme_ext.c @@ -683,6 +683,9 @@ unsigned int OnAuth(struct adapter *padapter, union recv_frame *precv_frame) if ((pmlmeinfo->state & 0x03) != WIFI_FW_AP_STATE) return _FAIL; + if (len < WLAN_HDR_A3_LEN) + return _FAIL; + sa = GetAddr2Ptr(pframe); auth_mode = psecuritypriv->dot11_auth_algrthm; @@ -694,6 +697,9 @@ unsigned int OnAuth(struct adapter *padapter, union recv_frame *precv_frame) prxattrib->hdrlen = WLAN_HDR_A3_LEN; prxattrib->encrypt = _WEP40_; + if (len < WLAN_HDR_A3_LEN + 8) + return _FAIL; + iv = pframe + prxattrib->hdrlen; prxattrib->key_index = ((iv[3] >> 6) & 0x3); @@ -793,7 +799,7 @@ unsigned int OnAuth(struct adapter *padapter, union recv_frame *precv_frame) p = rtw_get_ie(pframe + WLAN_HDR_A3_LEN + 4 + _AUTH_IE_OFFSET_, WLAN_EID_CHALLENGE, (int *)&ie_len, len - WLAN_HDR_A3_LEN - _AUTH_IE_OFFSET_ - 4); - if (!p || ie_len <= 0) { + if (!p || ie_len != 128) { status = WLAN_STATUS_CHALLENGE_FAIL; goto auth_fail; } @@ -1376,7 +1382,11 @@ unsigned int OnAssocRsp(struct adapter *padapter, union recv_frame *precv_frame) /* to handle HT, WMM, rate adaptive, update MAC reg */ /* for not to handle the synchronous IO in the tasklet */ for (i = (6 + WLAN_HDR_A3_LEN); i < pkt_len;) { + if (i + sizeof(*pIE) > pkt_len) + break; pIE = (struct ndis_80211_var_ie *)(pframe + i); + if (i + sizeof(*pIE) + pIE->length > pkt_len) + break; switch (pIE->element_id) { case WLAN_EID_VENDOR_SPECIFIC: @@ -2875,7 +2885,11 @@ void issue_assocreq(struct adapter *padapter) /* vendor specific IE, such as WPA, WMM, WPS */ for (i = sizeof(struct ndis_802_11_fix_ie); i < pmlmeinfo->network.ie_length;) { + if (i + sizeof(*pIE) > pmlmeinfo->network.ie_length) + break; pIE = (struct ndis_80211_var_ie *)(pmlmeinfo->network.ies + i); + if (i + sizeof(*pIE) + pIE->length > pmlmeinfo->network.ie_length) + break; switch (pIE->element_id) { case WLAN_EID_VENDOR_SPECIFIC: @@ -5208,7 +5222,11 @@ u8 join_cmd_hdl(struct adapter *padapter, u8 *pbuf) /* sizeof(struct ndis_802_11_fix_ie) */ for (i = _FIXED_IE_LENGTH_; i < pnetwork->ie_length;) { + if (i + sizeof(*pIE) > pnetwork->ie_length) + break; pIE = (struct ndis_80211_var_ie *)(pnetwork->ies + i); + if (i + sizeof(*pIE) + pIE->length > pnetwork->ie_length) + break; switch (pIE->element_id) { case WLAN_EID_VENDOR_SPECIFIC:/* Get WMM IE. */ diff --git a/drivers/staging/rtl8723bs/core/rtw_wlan_util.c b/drivers/staging/rtl8723bs/core/rtw_wlan_util.c index 3682048b29be..fb9bc9507ce5 100644 --- a/drivers/staging/rtl8723bs/core/rtw_wlan_util.c +++ b/drivers/staging/rtl8723bs/core/rtw_wlan_util.c @@ -908,7 +908,8 @@ void HT_caps_handler(struct adapter *padapter, struct ndis_80211_var_ie *pIE) pmlmeinfo->HT_caps_enable = 1; - for (i = 0; i < (pIE->length); i++) { + for (i = 0; i < umin(pIE->length, + sizeof(pmlmeinfo->HT_caps.u.HT_cap)); i++) { if (i != 2) { /* Commented by Albert 2010/07/12 */ /* Got the endian issue here. */ @@ -1261,7 +1262,11 @@ void update_beacon_info(struct adapter *padapter, u8 *pframe, uint pkt_len, stru len = pkt_len - (_BEACON_IE_OFFSET_ + WLAN_HDR_A3_LEN); for (i = 0; i < len;) { + if (i + sizeof(*pIE) > len) + break; pIE = (struct ndis_80211_var_ie *)(pframe + (_BEACON_IE_OFFSET_ + WLAN_HDR_A3_LEN) + i); + if (i + sizeof(*pIE) + pIE->length > len) + break; switch (pIE->element_id) { case WLAN_EID_VENDOR_SPECIFIC: @@ -1286,7 +1291,7 @@ void update_beacon_info(struct adapter *padapter, u8 *pframe, uint pkt_len, stru break; } - i += (pIE->length + 2); + i += sizeof(*pIE) + pIE->length; } } @@ -1302,15 +1307,23 @@ unsigned int is_ap_in_tkip(struct adapter *padapter) for (i = sizeof(struct ndis_802_11_fix_ie); i < pmlmeinfo->network.ie_length;) { pIE = (struct ndis_80211_var_ie *)(pmlmeinfo->network.ies + i); + if (i + sizeof(*pIE) > pmlmeinfo->network.ie_length) + break; + if (i + sizeof(*pIE) + pIE->length > pmlmeinfo->network.ie_length) + break; + switch (pIE->element_id) { case WLAN_EID_VENDOR_SPECIFIC: - if ((!memcmp(pIE->data, RTW_WPA_OUI, 4)) && (!memcmp((pIE->data + 12), WPA_TKIP_CIPHER, 4))) + if (pIE->length >= 16 && + !memcmp(pIE->data, RTW_WPA_OUI, 4) && + !memcmp((pIE->data + 12), WPA_TKIP_CIPHER, 4)) return true; break; case WLAN_EID_RSN: - if (!memcmp((pIE->data + 8), RSN_TKIP_CIPHER, 4)) + if (pIE->length >= 12 && + !memcmp((pIE->data + 8), RSN_TKIP_CIPHER, 4)) return true; break; @@ -1318,7 +1331,7 @@ unsigned int is_ap_in_tkip(struct adapter *padapter) break; } - i += (pIE->length + 2); + i += sizeof(*pIE) + pIE->length; } return false; diff --git a/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c b/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c index ed1b936215b9..f022931e4af9 100644 --- a/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c +++ b/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c @@ -1430,6 +1430,10 @@ static int rtw_cfg80211_set_wpa_ie(struct adapter *padapter, u8 *pie, size_t iel pwpa = rtw_get_wpa_ie(buf, &wpa_ielen, ielen); if (pwpa && wpa_ielen > 0) { + if (wpa_ielen + 2 > sizeof(padapter->securitypriv.supplicant_ie)) { + ret = -EINVAL; + goto exit; + } if (rtw_parse_wpa_ie(pwpa, wpa_ielen + 2, &group_cipher, &pairwise_cipher, NULL) == _SUCCESS) { padapter->securitypriv.dot11_auth_algrthm = dot11AuthAlgrthm_8021X; padapter->securitypriv.ndisauthtype = Ndis802_11AuthModeWPAPSK; @@ -1439,6 +1443,10 @@ static int rtw_cfg80211_set_wpa_ie(struct adapter *padapter, u8 *pie, size_t iel pwpa2 = rtw_get_wpa2_ie(buf, &wpa2_ielen, ielen); if (pwpa2 && wpa2_ielen > 0) { + if (wpa2_ielen + 2 > sizeof(padapter->securitypriv.supplicant_ie)) { + ret = -EINVAL; + goto exit; + } if (rtw_parse_wpa2_ie(pwpa2, wpa2_ielen + 2, &group_cipher, &pairwise_cipher, NULL) == _SUCCESS) { padapter->securitypriv.dot11_auth_algrthm = dot11AuthAlgrthm_8021X; padapter->securitypriv.ndisauthtype = Ndis802_11AuthModeWPA2PSK; diff --git a/drivers/staging/rtl8723bs/os_dep/xmit_linux.c b/drivers/staging/rtl8723bs/os_dep/xmit_linux.c index 9723b25998c7..e4b069f5cfa3 100644 --- a/drivers/staging/rtl8723bs/os_dep/xmit_linux.c +++ b/drivers/staging/rtl8723bs/os_dep/xmit_linux.c @@ -24,9 +24,11 @@ void _rtw_open_pktfile(struct sk_buff *pktptr, struct pkt_file *pfile) int _rtw_pktfile_read(struct pkt_file *pfile, u8 *rmem, unsigned int rlen) { int ret; + unsigned int remain = rtw_remainder_len(pfile); - if (rtw_remainder_len(pfile) < rlen) - return -EINVAL; + /* clamp to bytes remaining; the coalesce loop relies on short reads */ + if (rlen > remain) + rlen = remain; if (rmem) { ret = skb_copy_bits(pfile->pkt, pfile->buf_len - pfile->pkt_len, rmem, rlen); diff --git a/drivers/staging/vme_user/vme_fake.c b/drivers/staging/vme_user/vme_fake.c index 8abaa3165fbb..434cf760ade6 100644 --- a/drivers/staging/vme_user/vme_fake.c +++ b/drivers/staging/vme_user/vme_fake.c @@ -1239,6 +1239,7 @@ static void __exit fake_exit(void) { struct list_head *pos = NULL; struct list_head *tmplist; + struct vme_lm_resource *lm; struct vme_master_resource *master_image; struct vme_slave_resource *slave_image; int i; @@ -1268,6 +1269,13 @@ static void __exit fake_exit(void) vme_unregister_bridge(fake_bridge); fake_crcsr_exit(fake_bridge); + /* resources are stored in link list */ + list_for_each_safe(pos, tmplist, &fake_bridge->lm_resources) { + lm = list_entry(pos, struct vme_lm_resource, list); + list_del(pos); + kfree(lm); + } + /* resources are stored in link list */ list_for_each_safe(pos, tmplist, &fake_bridge->slave_resources) { slave_image = list_entry(pos, struct vme_slave_resource, list); diff --git a/drivers/staging/vme_user/vme_tsi148.c b/drivers/staging/vme_user/vme_tsi148.c index 4cf3486646ce..c695ad9b4ca2 100644 --- a/drivers/staging/vme_user/vme_tsi148.c +++ b/drivers/staging/vme_user/vme_tsi148.c @@ -2534,6 +2534,7 @@ static void tsi148_remove(struct pci_dev *pdev) { struct list_head *pos = NULL; struct list_head *tmplist; + struct vme_lm_resource *lm; struct vme_master_resource *master_image; struct vme_slave_resource *slave_image; struct vme_dma_resource *dma_ctrlr; @@ -2590,6 +2591,13 @@ static void tsi148_remove(struct pci_dev *pdev) tsi148_crcsr_exit(tsi148_bridge, pdev); + /* resources are stored in link list */ + list_for_each_safe(pos, tmplist, &tsi148_bridge->lm_resources) { + lm = list_entry(pos, struct vme_lm_resource, list); + list_del(pos); + kfree(lm); + } + /* resources are stored in link list */ list_for_each_safe(pos, tmplist, &tsi148_bridge->dma_resources) { dma_ctrlr = list_entry(pos, struct vme_dma_resource, list); diff --git a/drivers/staging/vme_user/vme_user.c b/drivers/staging/vme_user/vme_user.c index 11e25c2f6b0a..a472a38ef613 100644 --- a/drivers/staging/vme_user/vme_user.c +++ b/drivers/staging/vme_user/vme_user.c @@ -156,6 +156,17 @@ static ssize_t buffer_to_user(unsigned int minor, char __user *buf, { void *image_ptr; + /* + * The slave window (image_size) can exceed the fixed kern_buf + * (size_buf == PCI_BUF_SIZE), so bound the copy to kern_buf. + * *ppos is >= 0 here (checked by the caller), so the + * subtraction below cannot wrap. + */ + if (*ppos >= image[minor].size_buf) + return 0; + if (count > image[minor].size_buf - *ppos) + count = image[minor].size_buf - *ppos; + image_ptr = image[minor].kern_buf + *ppos; if (copy_to_user(buf, image_ptr, (unsigned long)count)) return -EFAULT; @@ -168,6 +179,17 @@ static ssize_t buffer_from_user(unsigned int minor, const char __user *buf, { void *image_ptr; + /* + * The slave window (image_size) can exceed the fixed kern_buf + * (size_buf == PCI_BUF_SIZE), so bound the copy to kern_buf. + * *ppos is >= 0 here (checked by the caller), so the + * subtraction below cannot wrap. + */ + if (*ppos >= image[minor].size_buf) + return 0; + if (count > image[minor].size_buf - *ppos) + count = image[minor].size_buf - *ppos; + image_ptr = image[minor].kern_buf + *ppos; if (copy_from_user(image_ptr, buf, (unsigned long)count)) return -EFAULT; diff --git a/drivers/tty/serial/8250/8250_mid.c b/drivers/tty/serial/8250/8250_mid.c index 8ec03863606e..f88809ff370b 100644 --- a/drivers/tty/serial/8250/8250_mid.c +++ b/drivers/tty/serial/8250/8250_mid.c @@ -10,6 +10,7 @@ #include #include #include +#include #include @@ -368,8 +369,16 @@ static const struct mid8250_board dnv_board = { .freq = 133333333, .base_baud = 115200, .bar = 1, - .setup = dnv_setup, - .exit = dnv_exit, + /* + * Errata: + * HSUART May Stop Functioning when DMA is Active. + * + * - Denverton document #572409, rev 3.4, DNV60 + * - Ice Lake Xeon D document #714070, ICXD65 + * - Snowridge document #731931, SNR44 + */ + .setup = PTR_IF(false, dnv_setup), + .exit = PTR_IF(false, dnv_exit), }; static const struct pci_device_id pci_ids[] = { diff --git a/drivers/tty/serial/8250/8250_omap.c b/drivers/tty/serial/8250/8250_omap.c index c552c6b9a037..3c7775df27ef 100644 --- a/drivers/tty/serial/8250/8250_omap.c +++ b/drivers/tty/serial/8250/8250_omap.c @@ -944,11 +944,12 @@ static void __dma_rx_do_complete(struct uart_8250_port *p) dev_err(p->port.dev, "teardown incomplete\n"); } } + + dma->rx_running = 0; if (!count) goto out; ret = tty_insert_flip_string(tty_port, dma->rx_buf, count); - dma->rx_running = 0; p->port.icount.rx += ret; p->port.icount.buf_overrun += count - ret; out: diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index 630deb7dd344..e94a0802cbdd 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -2000,8 +2000,14 @@ static void wait_for_xmitr(struct uart_8250_port *up, int bits) tx_ready = wait_for_lsr(up, bits); - /* Wait up to 1s for flow control if necessary */ - if (uart_console_hwflow_active(&up->port)) { + /* + * Wait up to 1s for flow control if necessary. + * When 'no_console_suspend' is active (in the window between + * suspend() and resume()), flow control is temporarily ignored + * because the canary workaround is not reliable in all situations, + * leading to flow control timeouts for every character. + */ + if (uart_console_hwflow_active(&up->port) && !up->canary) { for (tmout = 1000000; tmout; tmout--) { unsigned int msr = serial_in(up, UART_MSR); up->msr_saved_flags |= msr & MSR_SAVE_FLAGS; diff --git a/drivers/tty/serial/max310x.c b/drivers/tty/serial/max310x.c index 59e71306a5d4..5fe12577ce8b 100644 --- a/drivers/tty/serial/max310x.c +++ b/drivers/tty/serial/max310x.c @@ -1243,6 +1243,17 @@ static int max310x_gpio_set(struct gpio_chip *chip, unsigned int offset, return 0; } +static int max310x_gpio_get_direction(struct gpio_chip *chip, unsigned int offset) +{ + struct max310x_port *s = gpiochip_get_data(chip); + struct uart_port *port = &s->p[offset / 4].port; + unsigned int val; + + val = max310x_port_read(port, MAX310X_GPIOCFG_REG); + + return val & BIT(offset % 4) ? GPIO_LINE_DIRECTION_OUT : GPIO_LINE_DIRECTION_IN; +} + static int max310x_gpio_direction_input(struct gpio_chip *chip, unsigned int offset) { struct max310x_port *s = gpiochip_get_data(chip); @@ -1446,6 +1457,7 @@ static int max310x_probe(struct device *dev, const struct max310x_devtype *devty s->gpio.owner = THIS_MODULE; s->gpio.parent = dev; s->gpio.label = devtype->name; + s->gpio.get_direction = max310x_gpio_get_direction; s->gpio.direction_input = max310x_gpio_direction_input; s->gpio.get = max310x_gpio_get; s->gpio.direction_output= max310x_gpio_direction_output; diff --git a/drivers/tty/serial/msm_serial.c b/drivers/tty/serial/msm_serial.c index 2e999cb9c974..bfa44b01c3e9 100644 --- a/drivers/tty/serial/msm_serial.c +++ b/drivers/tty/serial/msm_serial.c @@ -1228,7 +1228,8 @@ static int msm_startup(struct uart_port *port) data |= MSM_UART_MR1_AUTO_RFR_LEVEL0 & rfr_level; msm_write(port, data, MSM_UART_MR1); - if (msm_port->is_uartdm) { + /* Disable DMA for console to prevent PIO/DMA collisions */ + if (msm_port->is_uartdm && !uart_console(port)) { msm_request_tx_dma(msm_port, msm_port->uart.mapbase); msm_request_rx_dma(msm_port, msm_port->uart.mapbase); } diff --git a/drivers/tty/vt/keyboard.c b/drivers/tty/vt/keyboard.c index dfdea0842149..763a3f1b7be0 100644 --- a/drivers/tty/vt/keyboard.c +++ b/drivers/tty/vt/keyboard.c @@ -765,16 +765,22 @@ static void k_fn(struct vc_data *vc, unsigned char value, char up_flag) /* * Compute xterm-style modifier parameter for CSI sequences. * Returns 1 + (shift ? 1 : 0) + (alt ? 2 : 0) + (ctrl ? 4 : 0) + * + * Only the canonical modifier weights are counted. The left/right variants + * (KG_SHIFTL, KG_SHIFTR, KG_CTRLL, KG_CTRLR) and KG_ALTGR are commonly + * repurposed as keymap layout-group or level selectors rather than as plain + * modifiers (for instance XKB-derived keymaps select the layout group with + * KG_SHIFTL/KG_SHIFTR), so counting them would encode a spurious modifier. */ static int csi_modifier_param(void) { int mod = 1; - if (shift_state & (BIT(KG_SHIFT) | BIT(KG_SHIFTL) | BIT(KG_SHIFTR))) + if (shift_state & BIT(KG_SHIFT)) mod += 1; - if (shift_state & (BIT(KG_ALT) | BIT(KG_ALTGR))) + if (shift_state & BIT(KG_ALT)) mod += 2; - if (shift_state & (BIT(KG_CTRL) | BIT(KG_CTRLL) | BIT(KG_CTRLR))) + if (shift_state & BIT(KG_CTRL)) mod += 4; return mod; } diff --git a/drivers/ufs/core/ufs_trace.h b/drivers/ufs/core/ufs_trace.h index 309ae51b4906..377a3c54b9f5 100644 --- a/drivers/ufs/core/ufs_trace.h +++ b/drivers/ufs/core/ufs_trace.h @@ -89,16 +89,18 @@ TRACE_EVENT(ufshcd_clk_gating, TP_STRUCT__entry( __field(struct ufs_hba *, hba) + __string(dev_name, dev_name(hba->dev)) __field(int, state) ), TP_fast_assign( + __assign_str(dev_name); __entry->hba = hba; __entry->state = state; ), TP_printk("%s: gating state changed to %s", - dev_name(__entry->hba->dev), + __get_str(dev_name), __print_symbolic(__entry->state, UFSCHD_CLK_GATING_STATES)) ); @@ -111,6 +113,7 @@ TRACE_EVENT(ufshcd_clk_scaling, TP_STRUCT__entry( __field(struct ufs_hba *, hba) + __string(dev_name, dev_name(hba->dev)) __string(state, state) __string(clk, clk) __field(u32, prev_state) @@ -119,6 +122,7 @@ TRACE_EVENT(ufshcd_clk_scaling, TP_fast_assign( __entry->hba = hba; + __assign_str(dev_name); __assign_str(state); __assign_str(clk); __entry->prev_state = prev_state; @@ -126,7 +130,7 @@ TRACE_EVENT(ufshcd_clk_scaling, ), TP_printk("%s: %s %s from %u to %u Hz", - dev_name(__entry->hba->dev), __get_str(state), __get_str(clk), + __get_str(dev_name), __get_str(state), __get_str(clk), __entry->prev_state, __entry->curr_state) ); @@ -138,16 +142,18 @@ TRACE_EVENT(ufshcd_auto_bkops_state, TP_STRUCT__entry( __field(struct ufs_hba *, hba) + __string(dev_name, dev_name(hba->dev)) __string(state, state) ), TP_fast_assign( __entry->hba = hba; + __assign_str(dev_name); __assign_str(state); ), TP_printk("%s: auto bkops - %s", - dev_name(__entry->hba->dev), __get_str(state)) + __get_str(dev_name), __get_str(state)) ); DECLARE_EVENT_CLASS(ufshcd_profiling_template, @@ -158,6 +164,7 @@ DECLARE_EVENT_CLASS(ufshcd_profiling_template, TP_STRUCT__entry( __field(struct ufs_hba *, hba) + __string(dev_name, dev_name(hba->dev)) __string(profile_info, profile_info) __field(s64, time_us) __field(int, err) @@ -165,13 +172,14 @@ DECLARE_EVENT_CLASS(ufshcd_profiling_template, TP_fast_assign( __entry->hba = hba; + __assign_str(dev_name); __assign_str(profile_info); __entry->time_us = time_us; __entry->err = err; ), TP_printk("%s: %s: took %lld usecs, err %d", - dev_name(__entry->hba->dev), __get_str(profile_info), + __get_str(dev_name), __get_str(profile_info), __entry->time_us, __entry->err) ); @@ -200,6 +208,7 @@ DECLARE_EVENT_CLASS(ufshcd_template, __field(s64, usecs) __field(int, err) __field(struct ufs_hba *, hba) + __string(dev_name, dev_name(hba->dev)) __field(int, dev_state) __field(int, link_state) ), @@ -208,13 +217,14 @@ DECLARE_EVENT_CLASS(ufshcd_template, __entry->usecs = usecs; __entry->err = err; __entry->hba = hba; + __assign_str(dev_name); __entry->dev_state = dev_state; __entry->link_state = link_state; ), TP_printk( "%s: took %lld usecs, dev_state: %s, link_state: %s, err %d", - dev_name(__entry->hba->dev), + __get_str(dev_name), __entry->usecs, __print_symbolic(__entry->dev_state, UFS_PWR_MODES), __print_symbolic(__entry->link_state, UFS_LINK_STATES), @@ -279,6 +289,7 @@ TRACE_EVENT(ufshcd_command, TP_STRUCT__entry( __field(struct scsi_device *, sdev) __field(struct ufs_hba *, hba) + __string(dev_name, dev_name(&sdev->sdev_dev)) __field(enum ufs_trace_str_t, str_t) __field(unsigned int, tag) __field(u32, doorbell) @@ -291,6 +302,7 @@ TRACE_EVENT(ufshcd_command, ), TP_fast_assign( + __assign_str(dev_name); __entry->sdev = sdev; __entry->hba = hba; __entry->str_t = str_t; @@ -307,7 +319,7 @@ TRACE_EVENT(ufshcd_command, TP_printk( "%s: %s: tag: %u, DB: 0x%x, size: %d, IS: %u, LBA: %llu, opcode: 0x%x (%s), group_id: 0x%x, hwq_id: %d", show_ufs_cmd_trace_str(__entry->str_t), - dev_name(&__entry->sdev->sdev_dev), __entry->tag, + __get_str(dev_name), __entry->tag, __entry->doorbell, __entry->transfer_len, __entry->intr, __entry->lba, (u32)__entry->opcode, str_opcode(__entry->opcode), (u32)__entry->group_id, __entry->hwq_id @@ -322,6 +334,7 @@ TRACE_EVENT(ufshcd_uic_command, TP_STRUCT__entry( __field(struct ufs_hba *, hba) + __string(dev_name, dev_name(hba->dev)) __field(enum ufs_trace_str_t, str_t) __field(u32, cmd) __field(u32, arg1) @@ -331,6 +344,7 @@ TRACE_EVENT(ufshcd_uic_command, TP_fast_assign( __entry->hba = hba; + __assign_str(dev_name); __entry->str_t = str_t; __entry->cmd = cmd; __entry->arg1 = arg1; @@ -340,7 +354,7 @@ TRACE_EVENT(ufshcd_uic_command, TP_printk( "%s: %s: cmd: 0x%x, arg1: 0x%x, arg2: 0x%x, arg3: 0x%x", - show_ufs_cmd_trace_str(__entry->str_t), dev_name(__entry->hba->dev), + show_ufs_cmd_trace_str(__entry->str_t), __get_str(dev_name), __entry->cmd, __entry->arg1, __entry->arg2, __entry->arg3 ) ); @@ -353,6 +367,7 @@ TRACE_EVENT(ufshcd_upiu, TP_STRUCT__entry( __field(struct ufs_hba *, hba) + __string(dev_name, dev_name(hba->dev)) __field(enum ufs_trace_str_t, str_t) __array(unsigned char, hdr, 12) __array(unsigned char, tsf, 16) @@ -361,6 +376,7 @@ TRACE_EVENT(ufshcd_upiu, TP_fast_assign( __entry->hba = hba; + __assign_str(dev_name); __entry->str_t = str_t; memcpy(__entry->hdr, hdr, sizeof(__entry->hdr)); memcpy(__entry->tsf, tsf, sizeof(__entry->tsf)); @@ -369,7 +385,7 @@ TRACE_EVENT(ufshcd_upiu, TP_printk( "%s: %s: HDR:%s, %s:%s", - show_ufs_cmd_trace_str(__entry->str_t), dev_name(__entry->hba->dev), + show_ufs_cmd_trace_str(__entry->str_t), __get_str(dev_name), __print_hex(__entry->hdr, sizeof(__entry->hdr)), show_ufs_cmd_trace_tsf(__entry->tsf_t), __print_hex(__entry->tsf, sizeof(__entry->tsf)) @@ -384,16 +400,18 @@ TRACE_EVENT(ufshcd_exception_event, TP_STRUCT__entry( __field(struct ufs_hba *, hba) + __string(dev_name, dev_name(hba->dev)) __field(u16, status) ), TP_fast_assign( __entry->hba = hba; + __assign_str(dev_name); __entry->status = status; ), TP_printk("%s: status 0x%x", - dev_name(__entry->hba->dev), __entry->status + __get_str(dev_name), __entry->status ) ); diff --git a/drivers/usb/atm/ueagle-atm.c b/drivers/usb/atm/ueagle-atm.c index d610cdcef7d0..4e71ed679a76 100644 --- a/drivers/usb/atm/ueagle-atm.c +++ b/drivers/usb/atm/ueagle-atm.c @@ -594,7 +594,9 @@ static int uea_send_modem_cmd(struct usb_device *usb, static void uea_upload_pre_firmware(const struct firmware *fw_entry, void *context) { - struct usb_device *usb = context; + struct usb_interface *intf = context; + struct usb_device *usb = interface_to_usbdev(intf); + struct completion *fw_done = usb_get_intfdata(intf); const u8 *pfw; u8 value; u32 crc = 0; @@ -663,15 +665,17 @@ static void uea_upload_pre_firmware(const struct firmware *fw_entry, uea_err(usb, "firmware is corrupted\n"); err: release_firmware(fw_entry); + complete(fw_done); } /* * uea_load_firmware - Load usb firmware for pre-firmware devices. */ -static int uea_load_firmware(struct usb_device *usb, unsigned int ver) +static int uea_load_firmware(struct usb_interface *intf, unsigned int ver) { int ret; char *fw_name = EAGLE_FIRMWARE; + struct usb_device *usb = interface_to_usbdev(intf); uea_info(usb, "pre-firmware device, uploading firmware\n"); @@ -694,7 +698,7 @@ static int uea_load_firmware(struct usb_device *usb, unsigned int ver) } ret = request_firmware_nowait(THIS_MODULE, 1, fw_name, &usb->dev, - GFP_KERNEL, usb, + GFP_KERNEL, intf, uea_upload_pre_firmware); if (ret) uea_err(usb, "firmware %s is not available\n", fw_name); @@ -2555,8 +2559,23 @@ static int uea_probe(struct usb_interface *intf, const struct usb_device_id *id) usb_reset_device(usb); - if (UEA_IS_PREFIRM(id)) - return uea_load_firmware(usb, UEA_CHIP_VERSION(id)); + if (UEA_IS_PREFIRM(id)) { + struct completion *fw_done; + + /* Wait for the firmware load to be done, in .disconnect() */ + fw_done = kzalloc_obj(*fw_done); + if (!fw_done) + return -ENOMEM; + + init_completion(fw_done); + usb_set_intfdata(intf, fw_done); + + ret = uea_load_firmware(intf, UEA_CHIP_VERSION(id)); + if (ret) + kfree(fw_done); + + return ret; + } ret = usbatm_usb_probe(intf, id, &uea_usbatm_driver); if (ret == 0) { @@ -2586,6 +2605,13 @@ static void uea_disconnect(struct usb_interface *intf) usbatm_usb_disconnect(intf); mutex_unlock(&uea_mutex); uea_info(usb, "ADSL device removed\n"); + } else if (usb->config->desc.bNumInterfaces == 1) { + struct completion *fw_done = usb_get_intfdata(intf); + + uea_dbg(usb, "pre-firmware device, waiting firmware upload\n"); + wait_for_completion(fw_done); + uea_dbg(usb, "pre-firmware device, finished waiting\n"); + kfree(fw_done); } } diff --git a/drivers/usb/cdns3/cdnsp-mem.c b/drivers/usb/cdns3/cdnsp-mem.c index 5d8cdc91927d..83f3384b735d 100644 --- a/drivers/usb/cdns3/cdnsp-mem.c +++ b/drivers/usb/cdns3/cdnsp-mem.c @@ -631,6 +631,8 @@ int cdnsp_alloc_stream_info(struct cdnsp_device *pdev, } } + cdnsp_free_stream_ctx(pdev, pep); + cleanup_stream_rings: kfree(pep->stream_info.stream_rings); diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index 49ab02f25872..7bc5329fa3ed 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -1816,6 +1816,9 @@ static const struct usb_device_id acm_ids[] = { { USB_DEVICE(0x1901, 0x0006), /* GE Healthcare Patient Monitor UI Controller */ .driver_info = DISABLE_ECHO, /* DISABLE ECHO in termios flag */ }, + { USB_DEVICE(0x1965, 0x0017), /* Uniden BC125AT */ + .driver_info = NO_UNION_NORMAL, /* has no union descriptor */ + }, { USB_DEVICE(0x1965, 0x0018), /* Uniden UBC125XLT */ .driver_info = NO_UNION_NORMAL, /* has no union descriptor */ }, diff --git a/drivers/usb/common/ulpi.c b/drivers/usb/common/ulpi.c index 9b69148128e5..7e43429e996e 100644 --- a/drivers/usb/common/ulpi.c +++ b/drivers/usb/common/ulpi.c @@ -281,28 +281,24 @@ static int ulpi_register(struct device *dev, struct ulpi *ulpi) ulpi->dev.parent = dev; /* needed early for ops */ ulpi->dev.bus = &ulpi_bus; ulpi->dev.type = &ulpi_dev_type; + + device_initialize(&ulpi->dev); + dev_set_name(&ulpi->dev, "%s.ulpi", dev_name(dev)); ACPI_COMPANION_SET(&ulpi->dev, ACPI_COMPANION(dev)); ret = ulpi_of_register(ulpi); - if (ret) { - kfree(ulpi); + if (ret) return ret; - } ret = ulpi_read_id(ulpi); - if (ret) { - of_node_put(ulpi->dev.of_node); - kfree(ulpi); + if (ret) return ret; - } - ret = device_register(&ulpi->dev); - if (ret) { - put_device(&ulpi->dev); + ret = device_add(&ulpi->dev); + if (ret) return ret; - } root = debugfs_create_dir(dev_name(&ulpi->dev), ulpi_root); debugfs_create_file("regs", 0444, root, ulpi, &ulpi_regs_fops); @@ -334,9 +330,10 @@ struct ulpi *ulpi_register_interface(struct device *dev, ulpi->ops = ops; ret = ulpi_register(dev, ulpi); - if (ret) + if (ret) { + put_device(&ulpi->dev); return ERR_PTR(ret); - + } return ulpi; } diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 24960ba9caa9..5262e11c12cd 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -3148,7 +3148,7 @@ static int hub_port_reset(struct usb_hub *hub, int port1, delay = HUB_LONG_RESET_TIME; } - dev_err(&port_dev->dev, "Cannot enable. Maybe the USB cable is bad?\n"); + dev_err_ratelimited(&port_dev->dev, "Cannot enable. Maybe the USB cable is bad?\n"); done: if (status == 0) { diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index 87810eff974e..87ee2d938bc0 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -296,6 +296,9 @@ static const struct usb_device_id usb_quirk_list[] = { /* CarrolTouch 4500U */ { USB_DEVICE(0x04e7, 0x0030), .driver_info = USB_QUIRK_RESET_RESUME }, + /* Samsung T5 EVO Portable SSD */ + { USB_DEVICE(0x04e8, 0x6200), .driver_info = USB_QUIRK_NO_LPM }, + /* Samsung Android phone modem - ID conflict with SPH-I500 */ { USB_DEVICE(0x04e8, 0x6601), .driver_info = USB_QUIRK_CONFIG_INTF_STRINGS }, @@ -576,6 +579,9 @@ static const struct usb_device_id usb_quirk_list[] = { /* VLI disk */ { USB_DEVICE(0x2109, 0x0711), .driver_info = USB_QUIRK_NO_LPM }, + /* VIA Labs, Inc. USB2.0 Hub */ + { USB_DEVICE(0x2109, 0x2817), .driver_info = USB_QUIRK_NO_LPM }, + /* Raydium Touchscreen */ { USB_DEVICE(0x2386, 0x3114), .driver_info = USB_QUIRK_NO_LPM }, diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index 517aa7f1486d..ceb49f2f8004 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -789,9 +789,9 @@ static void dwc3_ulpi_setup(struct dwc3 *dwc) if (dwc->enable_usb2_transceiver_delay) { for (index = 0; index < dwc->num_usb2_ports; index++) { - reg = dwc3_readl(dwc->regs, DWC3_GUSB2PHYCFG(index)); + reg = dwc3_readl(dwc, DWC3_GUSB2PHYCFG(index)); reg |= DWC3_GUSB2PHYCFG_XCVRDLY; - dwc3_writel(dwc->regs, DWC3_GUSB2PHYCFG(index), reg); + dwc3_writel(dwc, DWC3_GUSB2PHYCFG(index), reg); } } } diff --git a/drivers/usb/dwc3/dwc3-meson-g12a.c b/drivers/usb/dwc3/dwc3-meson-g12a.c index 55e144ba8cfc..4d611c08e8a4 100644 --- a/drivers/usb/dwc3/dwc3-meson-g12a.c +++ b/drivers/usb/dwc3/dwc3-meson-g12a.c @@ -907,35 +907,39 @@ static int __maybe_unused dwc3_meson_g12a_resume(struct device *dev) ret = priv->drvdata->usb_init(priv); if (ret) - return ret; + goto err_rearm; /* Init PHYs */ for (i = 0 ; i < PHY_COUNT ; ++i) { ret = phy_init(priv->phys[i]); if (ret) - return ret; + goto err_rearm; } /* Set PHY Power */ for (i = 0 ; i < PHY_COUNT ; ++i) { ret = phy_power_on(priv->phys[i]); if (ret) - return ret; + goto err_rearm; } if (priv->vbus && priv->otg_phy_mode == PHY_MODE_USB_HOST) { ret = regulator_enable(priv->vbus); if (ret) - return ret; + goto err_rearm; } if (priv->drvdata->usb_post_init) { ret = priv->drvdata->usb_post_init(priv); if (ret) - return ret; + goto err_rearm; } return 0; + +err_rearm: + reset_control_rearm(priv->reset); + return ret; } static const struct dev_pm_ops dwc3_meson_g12a_dev_pm_ops = { diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 3d4ca68e584c..1082e9c9afaa 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -3934,15 +3934,48 @@ static void dwc3_endpoint_interrupt(struct dwc3 *dwc, } } +static bool dwc3_prepare_disconnect_gadget(struct dwc3 *dwc, + struct usb_gadget_driver **driver, + struct usb_gadget **gadget) +{ + if (!dwc->async_callbacks || !dwc->gadget_driver || + !dwc->gadget_driver->disconnect) + return false; + + *driver = dwc->gadget_driver; + *gadget = dwc->gadget; + + return true; +} + static void dwc3_disconnect_gadget(struct dwc3 *dwc) { - if (dwc->async_callbacks && dwc->gadget_driver->disconnect) { + struct usb_gadget_driver *driver; + struct usb_gadget *gadget; + + if (dwc3_prepare_disconnect_gadget(dwc, &driver, &gadget)) { spin_unlock(&dwc->lock); - dwc->gadget_driver->disconnect(dwc->gadget); + driver->disconnect(gadget); spin_lock(&dwc->lock); } } +static void dwc3_disconnect_gadget_sleepable(struct dwc3 *dwc) +{ + struct usb_gadget_driver *driver; + struct usb_gadget *gadget; + unsigned long flags; + + spin_lock_irqsave(&dwc->lock, flags); + if (!dwc3_prepare_disconnect_gadget(dwc, &driver, &gadget)) { + spin_unlock_irqrestore(&dwc->lock, flags); + return; + } + + spin_unlock_irqrestore(&dwc->lock, flags); + driver->disconnect(gadget); +} + static void dwc3_suspend_gadget(struct dwc3 *dwc) { if (dwc->async_callbacks && dwc->gadget_driver->suspend) { @@ -4838,7 +4871,6 @@ EXPORT_SYMBOL_GPL(dwc3_gadget_exit); int dwc3_gadget_suspend(struct dwc3 *dwc) { - unsigned long flags; int ret; ret = dwc3_gadget_soft_disconnect(dwc); @@ -4852,10 +4884,7 @@ int dwc3_gadget_suspend(struct dwc3 *dwc) return -EAGAIN; } - spin_lock_irqsave(&dwc->lock, flags); - if (dwc->gadget_driver) - dwc3_disconnect_gadget(dwc); - spin_unlock_irqrestore(&dwc->lock, flags); + dwc3_disconnect_gadget_sleepable(dwc); return 0; } diff --git a/drivers/usb/fotg210/fotg210-hcd.c b/drivers/usb/fotg210/fotg210-hcd.c index 1a48329a4e08..956be5b56510 100644 --- a/drivers/usb/fotg210/fotg210-hcd.c +++ b/drivers/usb/fotg210/fotg210-hcd.c @@ -4267,8 +4267,6 @@ static int iso_stream_schedule(struct fotg210_hcd *fotg210, struct urb *urb, return 0; fail: - iso_sched_free(stream, sched); - urb->hcpriv = NULL; return status; } @@ -4562,6 +4560,10 @@ static int itd_submit(struct fotg210_hcd *fotg210, struct urb *urb, else usb_hcd_unlink_urb_from_ep(fotg210_to_hcd(fotg210), urb); done_not_linked: + if (status < 0) { + iso_sched_free(stream, urb->hcpriv); + urb->hcpriv = NULL; + } spin_unlock_irqrestore(&fotg210->lock, flags); done: return status; diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c index dc3664374596..df39e3487c1f 100644 --- a/drivers/usb/gadget/composite.c +++ b/drivers/usb/gadget/composite.c @@ -1863,9 +1863,10 @@ composite_setup(struct usb_gadget *gadget, const struct usb_ctrlrequest *ctrl) if (cdev->config) config = cdev->config; else - config = list_first_entry( + config = list_first_entry_or_null( &cdev->configs, - struct usb_configuration, list); + struct usb_configuration, + list); if (!config) goto done; diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index 75912ce6ab55..44218be1e676 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -288,6 +288,7 @@ static int ffs_acquire_dev(const char *dev_name, struct ffs_data *ffs_data); static void ffs_release_dev(struct ffs_dev *ffs_dev); static int ffs_ready(struct ffs_data *ffs); static void ffs_closed(struct ffs_data *ffs); +static void ffs_reset_work(struct work_struct *work); /* Misc helper functions ****************************************************/ @@ -1374,7 +1375,6 @@ ffs_epfile_release(struct inode *inode, struct file *file) mutex_unlock(&epfile->dmabufs_mutex); - __ffs_epfile_read_buffer_free(epfile); ffs_data_closed(epfile->ffs); return 0; @@ -1704,6 +1704,7 @@ static int ffs_dmabuf_transfer(struct file *file, resv_dir = epfile->in ? DMA_RESV_USAGE_READ : DMA_RESV_USAGE_WRITE; dma_resv_add_fence(dmabuf->resv, &fence->base, resv_dir); + dma_fence_put(&fence->base); dma_resv_unlock(dmabuf->resv); /* Now that the dma_fence is in place, queue the transfer. */ @@ -2221,6 +2222,7 @@ static struct ffs_data *ffs_data_new(const char *dev_name) init_waitqueue_head(&ffs->ev.waitq); init_waitqueue_head(&ffs->wait); init_completion(&ffs->ep0req_completion); + INIT_WORK(&ffs->reset_work, ffs_reset_work); /* XXX REVISIT need to update it in some places, or do we? */ ffs->ev.can_stall = 1; @@ -2364,6 +2366,7 @@ static int ffs_epfiles_create(struct ffs_data *ffs) sprintf(epfile->name, "ep%02x", ffs->eps_addrmap[i]); else sprintf(epfile->name, "ep%u", i); + epfile->in = (ffs->eps_addrmap[i] & USB_ENDPOINT_DIR_MASK) ? 1 : 0; err = ffs_sb_create_file(ffs->sb, epfile->name, epfile, &ffs_epfile_operations); if (err) { @@ -2389,6 +2392,7 @@ static void ffs_epfiles_destroy(struct super_block *sb, for (; count; --count, ++epfile) { BUG_ON(mutex_is_locked(&epfile->mutex)); + __ffs_epfile_read_buffer_free(epfile); simple_remove_by_name(root, epfile->name, clear_one); } @@ -2453,7 +2457,6 @@ static int ffs_func_eps_enable(struct ffs_function *func) ret = usb_ep_enable(ep->ep); if (!ret) { epfile->ep = ep; - epfile->in = usb_endpoint_dir_in(ep->ep->desc); epfile->isoc = usb_endpoint_xfer_isoc(ep->ep->desc); } else { break; @@ -3775,7 +3778,6 @@ static int ffs_func_set_alt(struct usb_function *f, if (ffs->state == FFS_DEACTIVATED) { ffs->state = FFS_CLOSING; spin_unlock_irqrestore(&ffs->eps_lock, flags); - INIT_WORK(&ffs->reset_work, ffs_reset_work); schedule_work(&ffs->reset_work); return -ENODEV; } @@ -3806,7 +3808,6 @@ static void ffs_func_disable(struct usb_function *f) if (ffs->state == FFS_DEACTIVATED) { ffs->state = FFS_CLOSING; spin_unlock_irqrestore(&ffs->eps_lock, flags); - INIT_WORK(&ffs->reset_work, ffs_reset_work); schedule_work(&ffs->reset_work); return; } diff --git a/drivers/usb/gadget/function/f_printer.c b/drivers/usb/gadget/function/f_printer.c index e4f7828ae75d..837f753d0cae 100644 --- a/drivers/usb/gadget/function/f_printer.c +++ b/drivers/usb/gadget/function/f_printer.c @@ -363,12 +363,11 @@ printer_open(struct inode *inode, struct file *fd) ret = 0; /* Change the printer status to show that it's on-line. */ dev->printer_status |= PRINTER_SELECTED; + kref_get(&dev->kref); } spin_unlock_irqrestore(&dev->lock, flags); - kref_get(&dev->kref); - return ret; } diff --git a/drivers/usb/gadget/function/rndis.c b/drivers/usb/gadget/function/rndis.c index 3da54a7d7aba..a2fd239b7ad3 100644 --- a/drivers/usb/gadget/function/rndis.c +++ b/drivers/usb/gadget/function/rndis.c @@ -591,6 +591,7 @@ static int rndis_init_response(struct rndis_params *params, static int rndis_query_response(struct rndis_params *params, rndis_query_msg_type *buf) { + u32 BufLength, BufOffset; rndis_query_cmplt_type *resp; rndis_resp_t *r; @@ -598,6 +599,13 @@ static int rndis_query_response(struct rndis_params *params, if (!params->dev) return -ENOTSUPP; + BufLength = le32_to_cpu(buf->InformationBufferLength); + BufOffset = le32_to_cpu(buf->InformationBufferOffset); + if ((BufLength > RNDIS_MAX_TOTAL_SIZE) || + (BufOffset > RNDIS_MAX_TOTAL_SIZE) || + (BufOffset + 8 >= RNDIS_MAX_TOTAL_SIZE)) + return -EINVAL; + /* * we need more memory: * gen_ndis_query_resp expects enough space for @@ -614,10 +622,8 @@ static int rndis_query_response(struct rndis_params *params, resp->RequestID = buf->RequestID; /* Still LE in msg buffer */ if (gen_ndis_query_resp(params, le32_to_cpu(buf->OID), - le32_to_cpu(buf->InformationBufferOffset) - + 8 + (u8 *)buf, - le32_to_cpu(buf->InformationBufferLength), - r)) { + BufOffset + 8 + (u8 *)buf, + BufLength, r)) { /* OID not supported */ resp->Status = cpu_to_le32(RNDIS_STATUS_NOT_SUPPORTED); resp->MessageLength = cpu_to_le32(sizeof *resp); @@ -1074,6 +1080,12 @@ int rndis_rm_hdr(struct gether *port, /* tmp points to a struct rndis_packet_msg_type */ __le32 *tmp = (void *)skb->data; + /* Need at least MessageType, MessageLength, DataOffset, DataLength */ + if (skb->len < 16) { + dev_kfree_skb_any(skb); + return -EINVAL; + } + /* MessageType, MessageLength */ if (cpu_to_le32(RNDIS_MSG_PACKET) != get_unaligned(tmp++)) { diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c index 60340ff9edbf..f6da12b553a0 100644 --- a/drivers/usb/gadget/udc/core.c +++ b/drivers/usb/gadget/udc/core.c @@ -31,8 +31,9 @@ static const struct bus_type gadget_bus_type; /** * struct usb_udc - describes one usb device controller * @driver: the gadget driver pointer. For use by the class code - * @dev: the child device to the actual controller * @gadget: the gadget. For use by the class code + * @gadget_release: the gadget's release routine + * @dev: the child device to the actual controller * @list: for use by the udc class driver * @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 @@ -53,6 +54,7 @@ static const struct bus_type gadget_bus_type; struct usb_udc { struct usb_gadget_driver *driver; struct usb_gadget *gadget; + void (*gadget_release)(struct device *dev); struct device dev; struct list_head list; bool vbus; @@ -1362,6 +1364,17 @@ static void usb_udc_nop_release(struct device *dev) dev_vdbg(dev, "%s\n", __func__); } +static void usb_gadget_release(struct device *dev) +{ + struct usb_gadget *gadget = dev_to_usb_gadget(dev); + struct usb_udc *udc = gadget->udc; + /* Cache the gadget's release routine to prevent UAF */ + void (*release)(struct device *dev) = udc->gadget_release; + + put_device(&udc->dev); + release(dev); +} + /** * usb_initialize_gadget - initialize a gadget and its embedded struct device * @parent: the parent device to this udc. Usually the controller driver's @@ -1418,6 +1431,14 @@ int usb_add_gadget(struct usb_gadget *gadget) mutex_init(&udc->connect_lock); udc->started = false; + /* + * Align decoupled lifecycles: take a UDC reference to ensure it + * remains allocated until the gadget is released, requiring an + * override of the gadget's release routine to drop it. + */ + udc->gadget_release = gadget->dev.release; + gadget->dev.release = usb_gadget_release; + get_device(&udc->dev); mutex_lock(&udc_lock); list_add_tail(&udc->list, &udc_list); @@ -1462,6 +1483,12 @@ int usb_add_gadget(struct usb_gadget *gadget) mutex_lock(&udc_lock); list_del(&udc->list); mutex_unlock(&udc_lock); + /* + * Revert the override and drop the UDC reference to prevent + * leaking the UDC if the gadget was statically allocated. + */ + gadget->dev.release = udc->gadget_release; + put_device(&udc->dev); err_put_udc: put_device(&udc->dev); diff --git a/drivers/usb/host/ehci-sched.c b/drivers/usb/host/ehci-sched.c index a241337c9af8..57d07d1c2dfa 100644 --- a/drivers/usb/host/ehci-sched.c +++ b/drivers/usb/host/ehci-sched.c @@ -1623,6 +1623,7 @@ iso_stream_schedule( status = 1; /* and give it back immediately */ iso_sched_free(stream, sched); sched = NULL; + urb->hcpriv = NULL; } } urb->error_count = skip / period; @@ -1653,8 +1654,6 @@ iso_stream_schedule( return status; fail: - iso_sched_free(stream, sched); - urb->hcpriv = NULL; return status; } @@ -1966,6 +1965,10 @@ static int itd_submit(struct ehci_hcd *ehci, struct urb *urb, usb_hcd_unlink_urb_from_ep(ehci_to_hcd(ehci), urb); } done_not_linked: + if (status < 0) { + iso_sched_free(stream, urb->hcpriv); + urb->hcpriv = NULL; + } spin_unlock_irqrestore(&ehci->lock, flags); done: return status; @@ -2343,6 +2346,10 @@ static int sitd_submit(struct ehci_hcd *ehci, struct urb *urb, usb_hcd_unlink_urb_from_ep(ehci_to_hcd(ehci), urb); } done_not_linked: + if (status < 0) { + iso_sched_free(stream, urb->hcpriv); + urb->hcpriv = NULL; + } spin_unlock_irqrestore(&ehci->lock, flags); done: return status; diff --git a/drivers/usb/host/sl811-hcd.c b/drivers/usb/host/sl811-hcd.c index 4ae47edd4b8b..b044977f6f56 100644 --- a/drivers/usb/host/sl811-hcd.c +++ b/drivers/usb/host/sl811-hcd.c @@ -1591,6 +1591,7 @@ sl811h_remove(struct platform_device *dev) remove_debug_file(sl811); usb_remove_hcd(hcd); + device_wakeup_disable(hcd->self.controller); /* some platforms may use IORESOURCE_IO */ res = platform_get_resource(dev, IORESOURCE_MEM, 1); diff --git a/drivers/usb/host/xhci-dbgcap.c b/drivers/usb/host/xhci-dbgcap.c index b1cabf5582fa..48ee6a4f9e1c 100644 --- a/drivers/usb/host/xhci-dbgcap.c +++ b/drivers/usb/host/xhci-dbgcap.c @@ -646,6 +646,31 @@ static int xhci_dbc_enable_dce(struct xhci_dbc *dbc, bool enable) static void xhci_dbc_set_state(struct xhci_dbc *dbc, enum dbc_state new_state) { + if (dbc->state == new_state) + return; + + switch (new_state) { + case DS_ENABLED: + /* + * DbC pm usage is 1 here, both when moved from disconnect or + * configured states, or when setting initial DbC enable state. + * Just enable pending put + */ + dev_dbg(dbc->dev, "DbC set pending_rpm_put = 1\n"); + dbc->pending_rpm_put = 1; + break; + case DS_CONNECTED: + if (dbc->pending_rpm_put) + /* DbC pm usage still 1, just remove pending put */ + dbc->pending_rpm_put = 0; + else + /* DbC pm usage was put to 0, call get */ + pm_runtime_get(dbc->dev); + break; + default: + break; + } + dbc->state_timestamp = jiffies; dbc->state = new_state; } @@ -681,7 +706,7 @@ static int xhci_dbc_start(struct xhci_dbc *dbc) WARN_ON(!dbc); - pm_runtime_get_sync(dbc->dev); /* note this was self.controller */ + pm_runtime_get(dbc->dev); spin_lock_irqsave(&dbc->lock, flags); ret = xhci_do_dbc_start(dbc); @@ -706,6 +731,7 @@ static int xhci_dbc_start(struct xhci_dbc *dbc) static void xhci_dbc_stop(struct xhci_dbc *dbc) { unsigned long flags; + bool need_rpm_put = false; WARN_ON(!dbc); @@ -731,12 +757,20 @@ static void xhci_dbc_stop(struct xhci_dbc *dbc) spin_lock_irqsave(&dbc->lock, flags); writel(0, &dbc->regs->control); + + if (dbc->state == DS_CONNECTED || dbc->state == DS_CONFIGURED || + dbc->pending_rpm_put) + need_rpm_put = true; + + dbc->pending_rpm_put = 0; + xhci_dbc_set_state(dbc, DS_DISABLED); spin_unlock_irqrestore(&dbc->lock, flags); xhci_dbc_mem_cleanup(dbc); - pm_runtime_put(dbc->dev); /* note, was self.controller */ + if (need_rpm_put) + pm_runtime_put(dbc->dev); } static void @@ -908,6 +942,12 @@ static enum evtreturn xhci_dbc_do_handle_events(struct xhci_dbc *dbc) dev_info(dbc->dev, "DbC connected\n"); } else if (!(ctrl & DBC_CTRL_DBC_ENABLE)) { dev_err(dbc->dev, "unexpected DbC disable, xHC reset?\n"); + } else if (dbc->pending_rpm_put && + time_is_before_jiffies(dbc->state_timestamp + + msecs_to_jiffies(DBC_AUTOSUSPEND_DELAY))) { + dbc->pending_rpm_put = 0; + dev_dbg(dbc->dev, "DbC Enabled state for 15 seconds, allow rpm suspend\n"); + pm_runtime_put(dbc->dev); } return EVT_DONE; @@ -1096,6 +1136,9 @@ static ssize_t dbc_show(struct device *dev, if (dbc->state >= ARRAY_SIZE(dbc_state_strings)) return sysfs_emit(buf, "unknown\n"); + if (dbc->resume_required) + return sysfs_emit(buf, "suspended\n"); + return sysfs_emit(buf, "%s\n", dbc_state_strings[dbc->state]); } @@ -1110,12 +1153,25 @@ static ssize_t dbc_store(struct device *dev, dbc = xhci->dbc; if (sysfs_streq(buf, "enable")) { + pm_runtime_get_sync(dbc->dev); + mutex_lock(&dbc->enable_mutex); + /* + * DbC may already be enabled here if xhci was suspended with + * dbc->resume_required set, and resumed by pm_runtime_get_sync() + * above. In this case we end up calling xhci_dbc_start() twice, + * second time returns an error but is harmless + */ xhci_dbc_start(dbc); + mutex_unlock(&dbc->enable_mutex); + pm_runtime_put(dbc->dev); } else if (sysfs_streq(buf, "disable")) { mutex_lock(&dbc->enable_mutex); + + dbc->resume_required = 0; xhci_dbc_stop(dbc); + mutex_unlock(&dbc->enable_mutex); } else { return -EINVAL; diff --git a/drivers/usb/host/xhci-dbgcap.h b/drivers/usb/host/xhci-dbgcap.h index df7aca8bfe99..5b18efb2c1ea 100644 --- a/drivers/usb/host/xhci-dbgcap.h +++ b/drivers/usb/host/xhci-dbgcap.h @@ -114,6 +114,8 @@ struct dbc_ep { #define DBC_POLL_INTERVAL_MAX 5000 /* milliseconds */ #define DBC_XFER_INACTIVITY_TIMEOUT 10 /* milliseconds */ #define DBC_ENUMERATION_TIMEOUT 2000 /* milliseconds */ +#define DBC_AUTOSUSPEND_DELAY 15000 /* milliseconds */ + /* * Private structure for DbC hardware state: */ @@ -166,6 +168,7 @@ struct xhci_dbc { unsigned long xfer_timestamp; unsigned long state_timestamp; unsigned resume_required:1; + unsigned pending_rpm_put:1; struct dbc_ep eps[2]; const struct dbc_driver *driver; diff --git a/drivers/usb/host/xhci-sideband.c b/drivers/usb/host/xhci-sideband.c index 23153e136d4b..a5deeee4d5dc 100644 --- a/drivers/usb/host/xhci-sideband.c +++ b/drivers/usb/host/xhci-sideband.c @@ -58,6 +58,8 @@ xhci_ring_to_sgtable(struct xhci_sideband *sb, struct xhci_ring *ring) if (sg_alloc_table_from_pages(sgt, pages, n_pages, 0, sz, GFP_KERNEL)) goto err; + kvfree(pages); + /* * Save first segment dma address to sg dma_address field for the sideband * client to have access to the IOVA of the ring. diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 6922cc5496c1..f44ccee5fa07 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -3785,6 +3785,7 @@ static int xhci_free_streams(struct usb_hcd *hcd, struct usb_device *udev, struct xhci_virt_device *vdev; struct xhci_command *command; struct xhci_input_control_ctx *ctrl_ctx; + struct xhci_stream_info *stream_info[EP_CTX_PER_DEV]; unsigned int ep_index; unsigned long flags; u32 changed_ep_bitmask; @@ -3845,10 +3846,15 @@ static int xhci_free_streams(struct usb_hcd *hcd, struct usb_device *udev, if (ret < 0) return ret; + /* + * dma_free_coherent() called by xhci_free_stream_info() may sleep, + * so save stream_info pointers and clear references under lock, + * then free the memory outside lock. + */ spin_lock_irqsave(&xhci->lock, flags); for (i = 0; i < num_eps; i++) { ep_index = xhci_get_endpoint_index(&eps[i]->desc); - xhci_free_stream_info(xhci, vdev->eps[ep_index].stream_info); + stream_info[i] = vdev->eps[ep_index].stream_info; vdev->eps[ep_index].stream_info = NULL; /* FIXME Unset maxPstreams in endpoint context and * update deq ptr to point to normal string ring. @@ -3858,6 +3864,9 @@ static int xhci_free_streams(struct usb_hcd *hcd, struct usb_device *udev, } spin_unlock_irqrestore(&xhci->lock, flags); + for (i = 0; i < num_eps; i++) + xhci_free_stream_info(xhci, stream_info[i]); + return 0; } diff --git a/drivers/usb/misc/chaoskey.c b/drivers/usb/misc/chaoskey.c index d8016540953f..9c06f7775301 100644 --- a/drivers/usb/misc/chaoskey.c +++ b/drivers/usb/misc/chaoskey.c @@ -320,7 +320,6 @@ static int chaoskey_release(struct inode *inode, struct file *file) mutex_unlock(&dev->lock); destruction: mutex_unlock(&chaoskey_list_lock); - usb_dbg(interface, "release success"); return rv; } diff --git a/drivers/usb/misc/idmouse.c b/drivers/usb/misc/idmouse.c index 0f6b3464c2d6..3e37adf2bb57 100644 --- a/drivers/usb/misc/idmouse.c +++ b/drivers/usb/misc/idmouse.c @@ -63,6 +63,7 @@ MODULE_DEVICE_TABLE(usb, idmouse_table); /* structure to hold all of our device specific stuff */ struct usb_idmouse { + struct kref kref; struct usb_device *udev; /* save off the usb device pointer */ struct usb_interface *interface; /* the interface for this device */ @@ -209,8 +210,10 @@ static int idmouse_resume(struct usb_interface *intf) return 0; } -static inline void idmouse_delete(struct usb_idmouse *dev) +static inline void idmouse_delete(struct kref *kref) { + struct usb_idmouse *dev = container_of(kref, struct usb_idmouse, kref); + kfree(dev->bulk_in_buffer); kfree(dev); } @@ -254,6 +257,8 @@ static int idmouse_open(struct inode *inode, struct file *file) /* increment our usage count for the driver */ ++dev->open; + kref_get(&dev->kref); + /* save our object in the file's private structure */ file->private_data = dev; @@ -277,16 +282,11 @@ static int idmouse_release(struct inode *inode, struct file *file) /* lock our device */ mutex_lock(&dev->lock); - --dev->open; + mutex_unlock(&dev->lock); + + kref_put(&dev->kref, idmouse_delete); - if (!dev->present) { - /* the device was unplugged before the file was released */ - mutex_unlock(&dev->lock); - idmouse_delete(dev); - } else { - mutex_unlock(&dev->lock); - } return 0; } @@ -334,6 +334,7 @@ static int idmouse_probe(struct usb_interface *interface, if (dev == NULL) return -ENOMEM; + kref_init(&dev->kref); mutex_init(&dev->lock); dev->udev = udev; dev->interface = interface; @@ -342,8 +343,7 @@ static int idmouse_probe(struct usb_interface *interface, result = usb_find_bulk_in_endpoint(iface_desc, &endpoint); if (result) { dev_err(&interface->dev, "Unable to find bulk-in endpoint.\n"); - idmouse_delete(dev); - return result; + goto err_put_kref; } dev->orig_bi_size = usb_endpoint_maxp(endpoint); @@ -351,8 +351,8 @@ static int idmouse_probe(struct usb_interface *interface, dev->bulk_in_endpointAddr = endpoint->bEndpointAddress; dev->bulk_in_buffer = kmalloc(IMGSIZE + dev->bulk_in_size, GFP_KERNEL); if (!dev->bulk_in_buffer) { - idmouse_delete(dev); - return -ENOMEM; + result = -ENOMEM; + goto err_put_kref; } /* allow device read, write and ioctl */ @@ -364,14 +364,18 @@ static int idmouse_probe(struct usb_interface *interface, if (result) { /* something prevented us from registering this device */ dev_err(&interface->dev, "Unable to allocate minor number.\n"); - idmouse_delete(dev); - return result; + goto err_put_kref; } /* be noisy */ dev_info(&interface->dev,"%s now attached\n",DRIVER_DESC); return 0; + +err_put_kref: + kref_put(&dev->kref, idmouse_delete); + + return result; } static void idmouse_disconnect(struct usb_interface *interface) @@ -387,14 +391,9 @@ static void idmouse_disconnect(struct usb_interface *interface) /* prevent device read, write and ioctl */ dev->present = 0; - /* if the device is opened, idmouse_release will clean this up */ - if (!dev->open) { - mutex_unlock(&dev->lock); - idmouse_delete(dev); - } else { - /* unlock */ - mutex_unlock(&dev->lock); - } + mutex_unlock(&dev->lock); + + kref_put(&dev->kref, idmouse_delete); dev_info(&interface->dev, "disconnected\n"); } diff --git a/drivers/usb/misc/iowarrior.c b/drivers/usb/misc/iowarrior.c index 22504c0a2841..de2b236ef903 100644 --- a/drivers/usb/misc/iowarrior.c +++ b/drivers/usb/misc/iowarrior.c @@ -72,6 +72,7 @@ static struct usb_driver iowarrior_driver; /* Structure to hold all of our device specific stuff */ struct iowarrior { + struct kref kref; struct mutex mutex; /* locks this structure */ struct usb_device *udev; /* save off the usb device pointer */ struct usb_interface *interface; /* the interface for this device */ @@ -240,8 +241,10 @@ static void iowarrior_write_callback(struct urb *urb) /* * iowarrior_delete */ -static inline void iowarrior_delete(struct iowarrior *dev) +static inline void iowarrior_delete(struct kref *kref) { + struct iowarrior *dev = container_of(kref, struct iowarrior, kref); + kfree(dev->int_in_buffer); usb_free_urb(dev->int_in_urb); kfree(dev->read_queue); @@ -637,6 +640,9 @@ static int iowarrior_open(struct inode *inode, struct file *file) } /* increment our usage count for the driver */ ++dev->opened; + + kref_get(&dev->kref); + /* save our object in the file's private structure */ file->private_data = dev; retval = 0; @@ -652,7 +658,6 @@ static int iowarrior_open(struct inode *inode, struct file *file) static int iowarrior_release(struct inode *inode, struct file *file) { struct iowarrior *dev; - int retval = 0; dev = file->private_data; if (!dev) @@ -660,29 +665,18 @@ static int iowarrior_release(struct inode *inode, struct file *file) /* lock our device */ mutex_lock(&dev->mutex); + dev->opened = 0; /* we're closing now */ - if (dev->opened <= 0) { - retval = -ENODEV; /* close called more than once */ - mutex_unlock(&dev->mutex); - } else { - dev->opened = 0; /* we're closing now */ - retval = 0; - if (dev->present) { - /* - The device is still connected so we only shutdown - pending read-/write-ops. - */ - usb_kill_urb(dev->int_in_urb); - wake_up_interruptible(&dev->read_wait); - wake_up_interruptible(&dev->write_wait); - mutex_unlock(&dev->mutex); - } else { - /* The device was unplugged, cleanup resources */ - mutex_unlock(&dev->mutex); - iowarrior_delete(dev); - } + if (dev->present) { + usb_kill_urb(dev->int_in_urb); + wake_up_interruptible(&dev->read_wait); + wake_up_interruptible(&dev->write_wait); } - return retval; + mutex_unlock(&dev->mutex); + + kref_put(&dev->kref, iowarrior_delete); + + return 0; } static __poll_t iowarrior_poll(struct file *file, poll_table * wait) @@ -767,6 +761,7 @@ static int iowarrior_probe(struct usb_interface *interface, if (!dev) return retval; + kref_init(&dev->kref); mutex_init(&dev->mutex); atomic_set(&dev->intr_idx, 0); @@ -885,7 +880,8 @@ static int iowarrior_probe(struct usb_interface *interface, return retval; error: - iowarrior_delete(dev); + kref_put(&dev->kref, iowarrior_delete); + return retval; } @@ -905,21 +901,18 @@ static void iowarrior_disconnect(struct usb_interface *interface) /* prevent device read, write and ioctl */ dev->present = 0; + /* write urbs are not stopped on close() so kill unconditionally */ + usb_kill_anchored_urbs(&dev->submitted); + if (dev->opened) { - /* There is a process that holds a filedescriptor to the device , - so we only shutdown read-/write-ops going on. - Deleting the device is postponed until close() was called. - */ usb_kill_urb(dev->int_in_urb); - usb_kill_anchored_urbs(&dev->submitted); wake_up_interruptible(&dev->read_wait); wake_up_interruptible(&dev->write_wait); - mutex_unlock(&dev->mutex); - } else { - /* no process is using the device, cleanup now */ - mutex_unlock(&dev->mutex); - iowarrior_delete(dev); } + + mutex_unlock(&dev->mutex); + + kref_put(&dev->kref, iowarrior_delete); } /* usb specific object needed to register this driver with the usb subsystem */ diff --git a/drivers/usb/misc/ldusb.c b/drivers/usb/misc/ldusb.c index c74f142f6637..71132a15e771 100644 --- a/drivers/usb/misc/ldusb.c +++ b/drivers/usb/misc/ldusb.c @@ -150,6 +150,7 @@ MODULE_PARM_DESC(min_interrupt_out_interval, "Minimum interrupt out interval in /* Structure to hold all of our device specific stuff */ struct ld_usb { + struct kref kref; struct mutex mutex; /* locks this structure */ struct usb_interface *intf; /* save off the usb interface pointer */ unsigned long disconnected:1; @@ -201,8 +202,10 @@ static void ld_usb_abort_transfers(struct ld_usb *dev) /* * ld_usb_delete */ -static void ld_usb_delete(struct ld_usb *dev) +static void ld_usb_delete(struct kref *kref) { + struct ld_usb *dev = container_of(kref, struct ld_usb, kref); + /* free data structures */ usb_free_urb(dev->interrupt_in_urb); usb_free_urb(dev->interrupt_out_urb); @@ -355,6 +358,8 @@ static int ld_usb_open(struct inode *inode, struct file *file) goto unlock_exit; } + kref_get(&dev->kref); + /* save device in the file's private structure */ file->private_data = dev; @@ -381,17 +386,8 @@ static int ld_usb_release(struct inode *inode, struct file *file) mutex_lock(&dev->mutex); - if (dev->open_count != 1) { - retval = -ENODEV; + if (dev->disconnected) goto unlock_exit; - } - if (dev->disconnected) { - /* the device was unplugged before the file was released */ - mutex_unlock(&dev->mutex); - /* unlock here as ld_usb_delete frees dev */ - ld_usb_delete(dev); - goto exit; - } /* wait until write transfer is finished */ if (dev->interrupt_out_busy) @@ -401,7 +397,7 @@ static int ld_usb_release(struct inode *inode, struct file *file) unlock_exit: mutex_unlock(&dev->mutex); - + kref_put(&dev->kref, ld_usb_delete); exit: return retval; } @@ -659,6 +655,8 @@ static int ld_usb_probe(struct usb_interface *intf, const struct usb_device_id * dev = kzalloc_obj(*dev); if (!dev) goto exit; + + kref_init(&dev->kref); mutex_init(&dev->mutex); spin_lock_init(&dev->rbsl); dev->intf = intf; @@ -740,7 +738,7 @@ static int ld_usb_probe(struct usb_interface *intf, const struct usb_device_id * return retval; error: - ld_usb_delete(dev); + kref_put(&dev->kref, ld_usb_delete); return retval; } @@ -768,18 +766,18 @@ static void ld_usb_disconnect(struct usb_interface *intf) mutex_lock(&dev->mutex); - /* if the device is not opened, then we clean up right now */ - if (!dev->open_count) { - mutex_unlock(&dev->mutex); - ld_usb_delete(dev); - } else { - dev->disconnected = 1; + dev->disconnected = 1; + + if (dev->open_count) { /* wake up pollers */ wake_up_interruptible_all(&dev->read_wait); wake_up_interruptible_all(&dev->write_wait); - mutex_unlock(&dev->mutex); } + mutex_unlock(&dev->mutex); + + kref_put(&dev->kref, ld_usb_delete); + dev_info(&intf->dev, "LD USB Device #%d now disconnected\n", (minor - USB_LD_MINOR_BASE)); } diff --git a/drivers/usb/misc/legousbtower.c b/drivers/usb/misc/legousbtower.c index 052ffc2e71ee..18dd4115befb 100644 --- a/drivers/usb/misc/legousbtower.c +++ b/drivers/usb/misc/legousbtower.c @@ -185,6 +185,7 @@ MODULE_DEVICE_TABLE(usb, tower_table); /* Structure to hold all of our device specific stuff */ struct lego_usb_tower { + struct kref kref; struct mutex lock; /* locks this structure */ struct usb_device *udev; /* save off the usb device pointer */ unsigned char minor; /* the starting minor number for this device */ @@ -220,7 +221,6 @@ struct lego_usb_tower { /* local function prototypes */ static ssize_t tower_read(struct file *file, char __user *buffer, size_t count, loff_t *ppos); static ssize_t tower_write(struct file *file, const char __user *buffer, size_t count, loff_t *ppos); -static inline void tower_delete(struct lego_usb_tower *dev); static int tower_open(struct inode *inode, struct file *file); static int tower_release(struct inode *inode, struct file *file); static __poll_t tower_poll(struct file *file, poll_table *wait); @@ -286,8 +286,10 @@ static inline void lego_usb_tower_debug_data(struct device *dev, /* * tower_delete */ -static inline void tower_delete(struct lego_usb_tower *dev) +static inline void tower_delete(struct kref *kref) { + struct lego_usb_tower *dev = container_of(kref, struct lego_usb_tower, kref); + /* free data structures */ usb_free_urb(dev->interrupt_in_urb); usb_free_urb(dev->interrupt_out_urb); @@ -381,6 +383,8 @@ static int tower_open(struct inode *inode, struct file *file) dev->open_count = 1; + kref_get(&dev->kref); + unlock_exit: mutex_unlock(&dev->lock); @@ -404,14 +408,8 @@ static int tower_release(struct inode *inode, struct file *file) mutex_lock(&dev->lock); - if (dev->disconnected) { - /* the device was unplugged before the file was released */ - - /* unlock here as tower_delete frees dev */ - mutex_unlock(&dev->lock); - tower_delete(dev); - goto exit; - } + if (dev->disconnected) + goto out_unlock; /* wait until write transfer is finished */ if (dev->interrupt_out_busy) { @@ -425,7 +423,9 @@ static int tower_release(struct inode *inode, struct file *file) dev->open_count = 0; +out_unlock: mutex_unlock(&dev->lock); + kref_put(&dev->kref, tower_delete); exit: return retval; } @@ -752,6 +752,7 @@ static int tower_probe(struct usb_interface *interface, const struct usb_device_ if (!dev) goto exit; + kref_init(&dev->kref); mutex_init(&dev->lock); dev->udev = usb_get_dev(udev); spin_lock_init(&dev->read_buffer_lock); @@ -828,7 +829,7 @@ static int tower_probe(struct usb_interface *interface, const struct usb_device_ return retval; error: - tower_delete(dev); + kref_put(&dev->kref, tower_delete); return retval; } @@ -856,18 +857,18 @@ static void tower_disconnect(struct usb_interface *interface) mutex_lock(&dev->lock); - /* if the device is not opened, then we clean up right now */ - if (!dev->open_count) { - mutex_unlock(&dev->lock); - tower_delete(dev); - } else { - dev->disconnected = 1; + dev->disconnected = 1; + + if (dev->open_count) { /* wake up pollers */ wake_up_interruptible_all(&dev->read_wait); wake_up_interruptible_all(&dev->write_wait); - mutex_unlock(&dev->lock); } + mutex_unlock(&dev->lock); + + kref_put(&dev->kref, tower_delete); + dev_info(&interface->dev, "LEGO USB Tower #%d now disconnected\n", (minor - LEGO_USB_TOWER_MINOR_BASE)); } diff --git a/drivers/usb/misc/usbio.c b/drivers/usb/misc/usbio.c index 02d1e0760f0c..3c2474dca810 100644 --- a/drivers/usb/misc/usbio.c +++ b/drivers/usb/misc/usbio.c @@ -344,6 +344,10 @@ int usbio_bulk_msg(struct auxiliary_device *adev, u8 type, u8 cmd, bool last, if (ibuf_len < bpkt_len) return -ENOSPC; + /* The device must not claim more payload than it actually sent. */ + if (bpkt_len > act - sizeof(*bpkt)) + return -EPROTO; + memcpy(ibuf, bpkt->data, bpkt_len); return bpkt_len; @@ -518,7 +522,7 @@ static int usbio_resume(struct usb_interface *intf) static void usbio_disconnect(struct usb_interface *intf) { struct usbio_device *usbio = usb_get_intfdata(intf); - struct usbio_client *client; + struct usbio_client *client, *next; /* Wakeup any clients waiting for a reply */ usbio->rxdat_len = 0; @@ -535,7 +539,7 @@ static void usbio_disconnect(struct usb_interface *intf) usb_kill_urb(usbio->urb); usb_free_urb(usbio->urb); - list_for_each_entry_reverse(client, &usbio->cli_list, link) { + list_for_each_entry_safe_reverse(client, next, &usbio->cli_list, link) { auxiliary_device_delete(&client->auxdev); auxiliary_device_uninit(&client->auxdev); } diff --git a/drivers/usb/misc/uss720.c b/drivers/usb/misc/uss720.c index b7d3c44b970e..1ce48f5832d7 100644 --- a/drivers/usb/misc/uss720.c +++ b/drivers/usb/misc/uss720.c @@ -732,8 +732,11 @@ static int uss720_probe(struct usb_interface *intf, * here. */ ret = get_1284_register(pp, 0, ®, GFP_KERNEL); dev_dbg(&intf->dev, "reg: %7ph\n", priv->reg); - if (ret < 0) + if (ret < 0) { + priv->pp = NULL; + parport_del_port(pp); goto probe_abort; + } ret = usb_find_last_int_in_endpoint(interface, &epd); if (!ret) { diff --git a/drivers/usb/mtu3/mtu3_gadget.c b/drivers/usb/mtu3/mtu3_gadget.c index da29f467943f..f224f2ee379a 100644 --- a/drivers/usb/mtu3/mtu3_gadget.c +++ b/drivers/usb/mtu3/mtu3_gadget.c @@ -305,6 +305,7 @@ static int mtu3_gadget_queue(struct usb_ep *ep, if (mtu3_prepare_transfer(mep)) { ret = -EAGAIN; + usb_gadget_unmap_request(&mtu->g, req, mep->is_in); goto error; } diff --git a/drivers/usb/serial/digi_acceleport.c b/drivers/usb/serial/digi_acceleport.c index 6899aebfd6ae..dea039163661 100644 --- a/drivers/usb/serial/digi_acceleport.c +++ b/drivers/usb/serial/digi_acceleport.c @@ -392,12 +392,14 @@ static int digi_write_oob_command(struct usb_serial_port *port, len &= ~3; memcpy(oob_port->write_urb->transfer_buffer, buf, len); oob_port->write_urb->transfer_buffer_length = len; + ret = usb_submit_urb(oob_port->write_urb, GFP_ATOMIC); - if (ret == 0) { - oob_priv->dp_write_urb_in_use = 1; - count -= len; - buf += len; - } + if (ret) + break; + + oob_priv->dp_write_urb_in_use = 1; + count -= len; + buf += len; } spin_unlock_irqrestore(&oob_priv->dp_port_lock, flags); if (ret) @@ -427,20 +429,22 @@ static int digi_write_inb_command(struct usb_serial_port *port, int len; struct digi_port *priv = usb_get_serial_port_data(port); unsigned char *data = port->write_urb->transfer_buffer; + unsigned long expire; unsigned long flags; dev_dbg(&port->dev, "digi_write_inb_command: TOP: port=%d, count=%d\n", priv->dp_port_num, count); if (timeout) - timeout += jiffies; - else - timeout = ULONG_MAX; + expire = jiffies + timeout; spin_lock_irqsave(&priv->dp_port_lock, flags); while (count > 0 && ret == 0) { - while (priv->dp_write_urb_in_use && - time_before(jiffies, timeout)) { + while (priv->dp_write_urb_in_use) { + if (timeout && time_after(jiffies, expire)) { + ret = -ETIMEDOUT; + break; + } cond_wait_interruptible_timeout_irqrestore( &priv->write_wait, DIGI_RETRY_TIMEOUT, &priv->dp_port_lock, flags); @@ -449,6 +453,9 @@ static int digi_write_inb_command(struct usb_serial_port *port, spin_lock_irqsave(&priv->dp_port_lock, flags); } + if (ret) + break; + /* len must be a multiple of 4 and small enough to */ /* guarantee the write will send buffered data first, */ /* so commands are in order with data and not split */ @@ -1069,6 +1076,7 @@ static int digi_open(struct tty_struct *tty, struct usb_serial_port *port) unsigned char buf[32]; struct digi_port *priv = usb_get_serial_port_data(port); struct ktermios not_termios; + int throttled; /* be sure the device is started up */ if (digi_startup_device(port->serial) != 0) @@ -1096,6 +1104,21 @@ static int digi_open(struct tty_struct *tty, struct usb_serial_port *port) not_termios.c_iflag = ~tty->termios.c_iflag; digi_set_termios(tty, port, ¬_termios); } + + spin_lock_irq(&priv->dp_port_lock); + throttled = priv->dp_throttle_restart; + priv->dp_throttled = 0; + priv->dp_throttle_restart = 0; + spin_unlock_irq(&priv->dp_port_lock); + + if (throttled) { + ret = usb_submit_urb(port->read_urb, GFP_KERNEL); + if (ret) { + dev_err(&port->dev, "failed to submit read urb: %d\n", ret); + return ret; + } + } + return 0; } diff --git a/drivers/usb/serial/keyspan_pda.c b/drivers/usb/serial/keyspan_pda.c index 3b99f9676c35..f05bcce60600 100644 --- a/drivers/usb/serial/keyspan_pda.c +++ b/drivers/usb/serial/keyspan_pda.c @@ -516,7 +516,7 @@ static int keyspan_pda_write_start(struct usb_serial_port *port) if (count == room) schedule_work(&priv->unthrottle_work); - return count; + return 0; } static void keyspan_pda_write_bulk_callback(struct urb *urb) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 4c4009b8a46d..7275f4e7f569 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -1325,6 +1325,22 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_CC864_SINGLE) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_DE910_DUAL) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_UE910_V2) }, + { USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x0990, 0xff, 0xff, 0x30), /* Telit FE990D50 (RNDIS) */ + .driver_info = NCTRL(6) }, + { USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x0990, 0xff, 0xff, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x0990, 0xff, 0xff, 0x60) }, + { USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x0991, 0xff, 0xff, 0x30), /* Telit FE990D50 (rmnet) */ + .driver_info = NCTRL(5) }, + { USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x0991, 0xff, 0xff, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x0991, 0xff, 0xff, 0x60) }, + { USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x0992, 0xff, 0xff, 0x30), /* Telit FE990D50 (MBIM) */ + .driver_info = NCTRL(6) }, + { USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x0992, 0xff, 0xff, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x0992, 0xff, 0xff, 0x60) }, + { USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x0993, 0xff, 0xff, 0x30), /* Telit FE990D50 (ECM) */ + .driver_info = NCTRL(6) }, + { USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x0993, 0xff, 0xff, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x0993, 0xff, 0xff, 0x60) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1031, 0xff), /* Telit LE910C1-EUX */ .driver_info = NCTRL(0) | RSVD(3) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1033, 0xff), /* Telit LE910C1-EUX (ECM) */ diff --git a/drivers/usb/storage/ene_ub6250.c b/drivers/usb/storage/ene_ub6250.c index 8770de01a384..ed49a3bc859c 100644 --- a/drivers/usb/storage/ene_ub6250.c +++ b/drivers/usb/storage/ene_ub6250.c @@ -2305,7 +2305,8 @@ static int ene_transport(struct scsi_cmnd *srb, struct us_data *us) /*US_DEBUG(usb_stor_show_command(us, srb)); */ scsi_set_resid(srb, 0); - if (unlikely(!(info->SD_Status & SD_Ready) || (info->MS_Status & MS_Ready))) + if (unlikely(!(info->SD_Status & SD_Ready) && + !(info->MS_Status & MS_Ready))) result = ene_init(us); if (result == USB_STOR_XFER_GOOD) { result = USB_STOR_TRANSPORT_ERROR; diff --git a/drivers/usb/storage/usb.c b/drivers/usb/storage/usb.c index fa83fe0defe2..064c7fc8e368 100644 --- a/drivers/usb/storage/usb.c +++ b/drivers/usb/storage/usb.c @@ -570,7 +570,7 @@ void usb_stor_adjust_quirks(struct usb_device *udev, u64 *fflags) US_FL_INITIAL_READ10 | US_FL_WRITE_CACHE | US_FL_NO_ATA_1X | US_FL_NO_REPORT_OPCODES | US_FL_MAX_SECTORS_240 | US_FL_NO_REPORT_LUNS | - US_FL_ALWAYS_SYNC); + US_FL_ALWAYS_SYNC | US_FL_NO_SAME); p = quirks; while (*p) { diff --git a/drivers/usb/typec/anx7411.c b/drivers/usb/typec/anx7411.c index 604868ebf422..41df115912b9 100644 --- a/drivers/usb/typec/anx7411.c +++ b/drivers/usb/typec/anx7411.c @@ -1537,7 +1537,9 @@ static int anx7411_i2c_probe(struct i2c_client *client) if (anx7411_typec_check_connection(plat)) dev_err(dev, "check status\n"); - pm_runtime_enable(dev); + ret = devm_pm_runtime_enable(dev); + if (ret) + goto free_wq; return 0; diff --git a/drivers/usb/typec/class.c b/drivers/usb/typec/class.c index 0977581ad1b6..0595e8cb83aa 100644 --- a/drivers/usb/typec/class.c +++ b/drivers/usb/typec/class.c @@ -1619,6 +1619,7 @@ static ssize_t select_usb_power_delivery_store(struct device *dev, return -EINVAL; ret = port->ops->pd_set(port, pd); + put_device(&pd->dev); if (ret) return ret; diff --git a/drivers/usb/typec/mux.c b/drivers/usb/typec/mux.c index db5e4a4c0a99..9b908c46bd7d 100644 --- a/drivers/usb/typec/mux.c +++ b/drivers/usb/typec/mux.c @@ -275,9 +275,7 @@ static int mux_fwnode_match(struct device *dev, const void *fwnode) static void *typec_mux_match(const struct fwnode_handle *fwnode, const char *id, void *data) { - struct typec_mux_dev **mux_devs = data; struct device *dev; - int i; /* * Device graph (OF graph) does not give any means to identify the @@ -293,14 +291,6 @@ static void *typec_mux_match(const struct fwnode_handle *fwnode, dev = class_find_device(&typec_mux_class, NULL, fwnode, mux_fwnode_match); - /* Skip duplicates */ - for (i = 0; i < TYPEC_MUX_MAX_DEVS; i++) - if (to_typec_mux_dev(dev) == mux_devs[i]) { - put_device(dev); - return NULL; - } - - return dev ? to_typec_mux_dev(dev) : ERR_PTR(-EPROBE_DEFER); } @@ -326,8 +316,7 @@ struct typec_mux *fwnode_typec_mux_get(struct fwnode_handle *fwnode) return ERR_PTR(-ENOMEM); count = fwnode_connection_find_matches(fwnode, "mode-switch", - (void **)mux_devs, - typec_mux_match, + NULL, typec_mux_match, (void **)mux_devs, ARRAY_SIZE(mux_devs)); if (count <= 0) { diff --git a/drivers/usb/typec/mux/ps883x.c b/drivers/usb/typec/mux/ps883x.c index f52443638ee2..64e0a61b776a 100644 --- a/drivers/usb/typec/mux/ps883x.c +++ b/drivers/usb/typec/mux/ps883x.c @@ -206,12 +206,12 @@ static int ps883x_set(struct ps883x_retimer *retimer, struct typec_retimer_state CONN_STATUS_1_DP_HPD_LEVEL; switch (state->mode) { + case TYPEC_DP_STATE_D: + cfg0 |= CONN_STATUS_0_USB_3_1_CONNECTED; + fallthrough; case TYPEC_DP_STATE_C: cfg1 |= CONN_STATUS_1_DP_SINK_REQUESTED | CONN_STATUS_1_DP_PIN_ASSIGNMENT_C_D; - fallthrough; - case TYPEC_DP_STATE_D: - cfg1 |= CONN_STATUS_0_USB_3_1_CONNECTED; break; default: /* MODE_E */ break; diff --git a/drivers/usb/typec/tcpm/tcpci_rt1711h.c b/drivers/usb/typec/tcpm/tcpci_rt1711h.c index 9d3b1fcf7e27..af8356df6b98 100644 --- a/drivers/usb/typec/tcpm/tcpci_rt1711h.c +++ b/drivers/usb/typec/tcpm/tcpci_rt1711h.c @@ -294,6 +294,8 @@ static int rt1711h_sw_reset(struct rt1711h_chip *chip) return 0; } +static void rt1711h_unregister_tcpci_port(void *tcpci); + static int rt1711h_probe(struct i2c_client *client) { int ret; @@ -339,6 +341,10 @@ static int rt1711h_probe(struct i2c_client *client) if (IS_ERR_OR_NULL(chip->tcpci)) return PTR_ERR(chip->tcpci); + ret = devm_add_action_or_reset(chip->dev, rt1711h_unregister_tcpci_port, chip->tcpci); + if (ret) + return ret; + ret = devm_request_threaded_irq(chip->dev, client->irq, NULL, rt1711h_irq, IRQF_ONESHOT | IRQF_TRIGGER_LOW, @@ -356,11 +362,9 @@ static int rt1711h_probe(struct i2c_client *client) return 0; } -static void rt1711h_remove(struct i2c_client *client) +static void rt1711h_unregister_tcpci_port(void *tcpci) { - struct rt1711h_chip *chip = i2c_get_clientdata(client); - - tcpci_unregister_port(chip->tcpci); + tcpci_unregister_port(tcpci); } static const struct rt1711h_chip_info rt1711h = { @@ -393,7 +397,6 @@ static struct i2c_driver rt1711h_i2c_driver = { .of_match_table = rt1711h_of_match, }, .probe = rt1711h_probe, - .remove = rt1711h_remove, .id_table = rt1711h_id, }; module_i2c_driver(rt1711h_i2c_driver); diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index 7ef746a90a17..89eec20a2064 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -2000,6 +2000,11 @@ static void svdm_consume_modes(struct tcpm_port *port, const u32 *p, int cnt, return; } + if (pmdata->svid_index < 0 || pmdata->svid_index >= pmdata->nsvids) { + tcpm_log(port, "Invalid SVID index %d", pmdata->svid_index); + return; + } + for (i = 1; i < cnt; i++) { if (pmdata->altmodes >= ALTMODE_DISCOVERY_MAX) { /* Already logged in svdm_consume_svids() */ @@ -3088,7 +3093,7 @@ static int tcpm_altmode_enter(struct typec_altmode *altmode, u32 *vdo) if (svdm_version < 0) return svdm_version; - header = VDO(altmode->svid, vdo ? 2 : 1, svdm_version, CMD_ENTER_MODE); + header = VDO(altmode->svid, 1, svdm_version, CMD_ENTER_MODE); header |= VDO_OPOS(altmode->mode); return tcpm_queue_vdm_unlocked(port, header, vdo, vdo ? 1 : 0, TCPC_TX_SOP); @@ -3136,7 +3141,7 @@ static int tcpm_cable_altmode_enter(struct typec_altmode *altmode, enum typec_pl if (svdm_version < 0) return svdm_version; - header = VDO(altmode->svid, vdo ? 2 : 1, svdm_version, CMD_ENTER_MODE); + header = VDO(altmode->svid, 1, svdm_version, CMD_ENTER_MODE); header |= VDO_OPOS(altmode->mode); return tcpm_queue_vdm_unlocked(port, header, vdo, vdo ? 1 : 0, TCPC_TX_SOP_PRIME); diff --git a/drivers/usb/typec/ucsi/displayport.c b/drivers/usb/typec/ucsi/displayport.c index 67a0991a7b76..7067f2561b84 100644 --- a/drivers/usb/typec/ucsi/displayport.c +++ b/drivers/usb/typec/ucsi/displayport.c @@ -166,12 +166,12 @@ static int ucsi_displayport_status_update(struct ucsi_dp *dp) * that Multi-function is preferred. */ if (DP_CAP_CAPABILITY(cap) & DP_CAP_UFP_D) { - dp->data.status |= DP_STATUS_CON_UFP_D; + dp->data.status |= DP_STATUS_CON_DFP_D; if (DP_CAP_UFP_D_PIN_ASSIGN(cap) & BIT(DP_PIN_ASSIGN_D)) dp->data.status |= DP_STATUS_PREFER_MULTI_FUNC; } else { - dp->data.status |= DP_STATUS_CON_DFP_D; + dp->data.status |= DP_STATUS_CON_UFP_D; if (DP_CAP_DFP_D_PIN_ASSIGN(cap) & BIT(DP_PIN_ASSIGN_D)) dp->data.status |= DP_STATUS_PREFER_MULTI_FUNC; @@ -185,13 +185,12 @@ static int ucsi_displayport_status_update(struct ucsi_dp *dp) static int ucsi_displayport_configure(struct ucsi_dp *dp) { - u32 pins = DP_CONF_GET_PIN_ASSIGN(dp->data.conf); u64 command; if (!dp->override) return 0; - command = UCSI_CMD_SET_NEW_CAM(dp->con->num, 1, dp->offset, pins); + command = UCSI_CMD_SET_NEW_CAM(dp->con->num, 1, dp->offset, dp->data.conf); return ucsi_send_command(dp->con->ucsi, command, NULL, 0); } diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c index 92166a3725b1..6a6723e8fb12 100644 --- a/drivers/usb/typec/ucsi/ucsi.c +++ b/drivers/usb/typec/ucsi/ucsi.c @@ -2017,6 +2017,26 @@ static void ucsi_resume_work(struct work_struct *work) } } +int ucsi_suspend(struct ucsi *ucsi) +{ + int i; + + /* + * Cancel pending work so it cannot access the firmware after the ACPI + * EC is stopped for suspend; state is re-read on resume. + */ + cancel_delayed_work_sync(&ucsi->work); + + if (!ucsi->connector) + return 0; + + for (i = 0; i < ucsi->cap.num_connectors; i++) + cancel_work_sync(&ucsi->connector[i].work); + + return 0; +} +EXPORT_SYMBOL_GPL(ucsi_suspend); + int ucsi_resume(struct ucsi *ucsi) { if (ucsi->connector) diff --git a/drivers/usb/typec/ucsi/ucsi.h b/drivers/usb/typec/ucsi/ucsi.h index 325ed1e5ca80..6e1608d88ec3 100644 --- a/drivers/usb/typec/ucsi/ucsi.h +++ b/drivers/usb/typec/ucsi/ucsi.h @@ -582,6 +582,7 @@ int ucsi_write_message_out_command(struct ucsi *ucsi, u64 command, void *msg_out, size_t msg_out_size); void ucsi_altmode_update_active(struct ucsi_connector *con); +int ucsi_suspend(struct ucsi *ucsi); int ucsi_resume(struct ucsi *ucsi); void ucsi_notify_common(struct ucsi *ucsi, u32 cci); diff --git a/drivers/usb/typec/ucsi/ucsi_acpi.c b/drivers/usb/typec/ucsi/ucsi_acpi.c index 60b12961e1a4..18286d3e9cc5 100644 --- a/drivers/usb/typec/ucsi/ucsi_acpi.c +++ b/drivers/usb/typec/ucsi/ucsi_acpi.c @@ -263,6 +263,13 @@ static void ucsi_acpi_remove(struct platform_device *pdev) ucsi_acpi_notify); } +static int ucsi_acpi_suspend(struct device *dev) +{ + struct ucsi_acpi *ua = dev_get_drvdata(dev); + + return ucsi_suspend(ua->ucsi); +} + static int ucsi_acpi_resume(struct device *dev) { struct ucsi_acpi *ua = dev_get_drvdata(dev); @@ -270,7 +277,8 @@ static int ucsi_acpi_resume(struct device *dev) return ucsi_resume(ua->ucsi); } -static DEFINE_SIMPLE_DEV_PM_OPS(ucsi_acpi_pm_ops, NULL, ucsi_acpi_resume); +static DEFINE_SIMPLE_DEV_PM_OPS(ucsi_acpi_pm_ops, ucsi_acpi_suspend, + ucsi_acpi_resume); static const struct acpi_device_id ucsi_acpi_match[] = { { "PNP0CA0", 0 }, diff --git a/drivers/usb/typec/ucsi/ucsi_ccg.c b/drivers/usb/typec/ucsi/ucsi_ccg.c index d46ca942026e..91c2958a708c 100644 --- a/drivers/usb/typec/ucsi/ucsi_ccg.c +++ b/drivers/usb/typec/ucsi/ucsi_ccg.c @@ -1521,8 +1521,8 @@ static void ucsi_ccg_remove(struct i2c_client *client) cancel_work_sync(&uc->work); pm_runtime_disable(uc->dev); ucsi_unregister(uc->ucsi); - ucsi_destroy(uc->ucsi); free_irq(uc->irq, uc); + ucsi_destroy(uc->ucsi); } static const struct of_device_id ucsi_ccg_of_match_table[] = { diff --git a/drivers/usb/typec/ucsi/ucsi_huawei_gaokun.c b/drivers/usb/typec/ucsi/ucsi_huawei_gaokun.c index ad669d2f8b9c..ca1b534cb183 100644 --- a/drivers/usb/typec/ucsi/ucsi_huawei_gaokun.c +++ b/drivers/usb/typec/ucsi/ucsi_huawei_gaokun.c @@ -84,6 +84,8 @@ struct gaokun_ucsi_port { struct auxiliary_device *bridge; struct typec_mux *typec_mux; + struct typec_mux_state state; + struct typec_altmode dp_alt; int idx; enum gaokun_ucsi_ccx ccx; @@ -292,24 +294,22 @@ static int gaokun_ucsi_refresh(struct gaokun_ucsi *uec) static void gaokun_ucsi_handle_usb_mode(struct gaokun_ucsi_port *port) { struct gaokun_ucsi *uec = port->ucsi; - struct typec_mux_state state = {}; - struct typec_altmode dp_alt = {}; int idx = port->idx, ret; /* * For every typec port on this platform, the only mode-switch is * controlled by its qmp combo phy which consumes svid and mode only. */ - dp_alt.svid = port->svid; - state.mode = port->mode; - state.alt = &dp_alt; + port->dp_alt.svid = port->svid; + port->state.mode = port->mode; + port->state.alt = &port->dp_alt; if (idx >= uec->num_ports) { dev_warn(uec->dev, "altmode port out of range: %d\n", idx); return; } - ret = typec_mux_set(port->typec_mux, &state); + ret = typec_mux_set(port->typec_mux, &port->state); if (ret) dev_err(uec->dev, "failed to set mux %d\n", ret); diff --git a/drivers/usb/usbip/vudc.h b/drivers/usb/usbip/vudc.h index faf61c9c6a98..5ef0e7d9b23a 100644 --- a/drivers/usb/usbip/vudc.h +++ b/drivers/usb/usbip/vudc.h @@ -38,7 +38,6 @@ struct vep { struct vrequest { struct usb_request req; - struct vudc *udc; struct list_head req_entry; /* Request queue */ }; diff --git a/drivers/usb/usbip/vudc_dev.c b/drivers/usb/usbip/vudc_dev.c index c5f079c5a1ea..5ef88117965d 100644 --- a/drivers/usb/usbip/vudc_dev.c +++ b/drivers/usb/usbip/vudc_dev.c @@ -333,7 +333,6 @@ static int vep_queue(struct usb_ep *_ep, struct usb_request *_req, static int vep_dequeue(struct usb_ep *_ep, struct usb_request *_req) { struct vep *ep; - struct vrequest *req; struct vudc *udc; struct vrequest *lst; unsigned long flags; @@ -343,8 +342,7 @@ static int vep_dequeue(struct usb_ep *_ep, struct usb_request *_req) return ret; ep = to_vep(_ep); - req = to_vrequest(_req); - udc = req->udc; + udc = ep_to_vudc(ep); if (!udc->driver) return -ESHUTDOWN; diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index c7b723c18620..c7caffb31935 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -3346,6 +3346,8 @@ static int nfs_open_permission_mask(int openflags) mask |= MAY_READ; if ((openflags & O_ACCMODE) != O_RDONLY) mask |= MAY_WRITE; + if (openflags & O_TRUNC) + mask |= MAY_WRITE; } return mask; diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index acaeff7ddfdf..e4533f583632 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -851,17 +851,19 @@ void nfs_super_set_maxbytes(struct super_block *sb, __u64 maxfilesize) } /* - * Record the page as unstable (an extra writeback period) and mark its - * inode as dirty. + * Record the request's range as unstable (an extra writeback period) and + * mark its inode as dirty. */ -static inline void nfs_folio_mark_unstable(struct folio *folio, +static inline void nfs_folio_mark_unstable(struct nfs_page *req, struct nfs_commit_info *cinfo) { + struct folio *folio = nfs_page_to_folio(req); + if (folio && !cinfo->dreq) { struct inode *inode = folio->mapping->host; - long nr = folio_nr_pages(folio); + long nr = DIV_ROUND_UP(req->wb_bytes, PAGE_SIZE); - /* This page is really still in write-back - just that the + /* This range is really still in write-back - just that the * writeback is happening on the server now. */ node_stat_mod_folio(folio, NR_WRITEBACK, nr); diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c index 0ff43dbcb7cd..648c95b78eea 100644 --- a/fs/nfs/pnfs_nfs.c +++ b/fs/nfs/pnfs_nfs.c @@ -1199,7 +1199,7 @@ pnfs_layout_mark_request_commit(struct nfs_page *req, nfs_request_add_commit_list_locked(req, list, cinfo); mutex_unlock(&NFS_I(cinfo->inode)->commit_mutex); - nfs_folio_mark_unstable(nfs_page_to_folio(req), cinfo); + nfs_folio_mark_unstable(req, cinfo); return; out_resched: mutex_unlock(&NFS_I(cinfo->inode)->commit_mutex); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index fcffb8c9e9df..d2b03ceaeb4f 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -807,7 +807,7 @@ nfs_request_add_commit_list(struct nfs_page *req, struct nfs_commit_info *cinfo) mutex_lock(&NFS_I(cinfo->inode)->commit_mutex); nfs_request_add_commit_list_locked(req, &cinfo->mds->list, cinfo); mutex_unlock(&NFS_I(cinfo->inode)->commit_mutex); - nfs_folio_mark_unstable(nfs_page_to_folio(req), cinfo); + nfs_folio_mark_unstable(req, cinfo); } EXPORT_SYMBOL_GPL(nfs_request_add_commit_list); @@ -866,10 +866,12 @@ nfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg, nfs_request_add_commit_list(req, cinfo); } -static void nfs_folio_clear_commit(struct folio *folio) +static void nfs_folio_clear_commit(struct nfs_page *req) { + struct folio *folio = nfs_page_to_folio(req); + if (folio) { - long nr = folio_nr_pages(folio); + long nr = DIV_ROUND_UP(req->wb_bytes, PAGE_SIZE); node_stat_mod_folio(folio, NR_WRITEBACK, -nr); bdi_wb_stat_mod(folio->mapping->host, WB_WRITEBACK, -nr); @@ -889,7 +891,7 @@ static void nfs_clear_request_commit(struct nfs_commit_info *cinfo, nfs_request_remove_commit_list(req, cinfo); } mutex_unlock(&NFS_I(inode)->commit_mutex); - nfs_folio_clear_commit(nfs_page_to_folio(req)); + nfs_folio_clear_commit(req); } } @@ -1741,7 +1743,7 @@ void nfs_retry_commit(struct list_head *page_list, req = nfs_list_entry(page_list->next); nfs_list_remove_request(req); nfs_mark_request_commit(req, lseg, cinfo, ds_commit_idx); - nfs_folio_clear_commit(nfs_page_to_folio(req)); + nfs_folio_clear_commit(req); nfs_unlock_and_release_request(req); } } @@ -1813,7 +1815,7 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data) req = nfs_list_entry(data->pages.next); nfs_list_remove_request(req); folio = nfs_page_to_folio(req); - nfs_folio_clear_commit(folio); + nfs_folio_clear_commit(req); dprintk("NFS: commit (%s/%llu %d@%lld)", nfs_req_openctx(req)->dentry->d_sb->s_id, diff --git a/fs/ntfs/aops.c b/fs/ntfs/aops.c index f2bb56506046..173de4cbee0f 100644 --- a/fs/ntfs/aops.c +++ b/fs/ntfs/aops.c @@ -249,6 +249,8 @@ static int ntfs_writepages(struct address_space *mapping, .wbc = wbc, .ops = &ntfs_writeback_ops, }; + bool need_iput = false; + int ret; if (NVolShutdown(ni->vol)) return -EIO; @@ -265,7 +267,20 @@ static int ntfs_writepages(struct address_space *mapping, return -EOPNOTSUPP; } - return iomap_writepages(&wpc); + /* + * Prevent eviction in writeback to avoid deadlock in + * ntfs_drop_big_inode(). + */ + if ((ni->type == AT_DATA || ni->type == AT_INDEX_ALLOCATION) && + igrab(inode)) + need_iput = true; + + ret = iomap_writepages(&wpc); + + if (need_iput) + iput(inode); + + return ret; } static int ntfs_swap_activate(struct swap_info_struct *sis, diff --git a/fs/ntfs/attrib.c b/fs/ntfs/attrib.c index dd8828098511..239b7bcbaedf 100644 --- a/fs/ntfs/attrib.c +++ b/fs/ntfs/attrib.c @@ -175,7 +175,10 @@ int ntfs_map_runlist_nolock(struct ntfs_inode *ni, s64 vcn, struct ntfs_attr_sea err = -EIO; goto err_out; } - WARN_ON(!ctx->attr->non_resident); + if (unlikely(!ctx->attr->non_resident)) { + err = -EIO; + goto err_out; + } } a = ctx->attr; /* @@ -5325,6 +5328,7 @@ int ntfs_non_resident_attr_insert_range(struct ntfs_inode *ni, s64 start_vcn, s6 ret = ntfs_attr_map_whole_runlist(ni); if (ret) { up_write(&ni->runlist.lock); + kfree(hole_rl); return ret; } @@ -5536,6 +5540,7 @@ int ntfs_attr_fallocate(struct ntfs_inode *ni, loff_t start, loff_t byte_len, bo s64 old_data_size; s64 vcn_start, vcn_end, vcn_uninit, vcn, try_alloc_cnt; s64 lcn, alloc_cnt; + s64 rl_lcn, rl_length, rl_vcn; int err = 0; struct runlist_element *rl; bool balloc; @@ -5615,19 +5620,23 @@ int ntfs_attr_fallocate(struct ntfs_inode *ni, loff_t start, loff_t byte_len, bo while (vcn < vcn_uninit) { down_read(&ni->runlist.lock); rl = ntfs_attr_find_vcn_nolock(ni, vcn, NULL); - up_read(&ni->runlist.lock); if (IS_ERR(rl)) { + up_read(&ni->runlist.lock); err = PTR_ERR(rl); goto out; } + rl_lcn = rl->lcn; + rl_length = rl->length; + rl_vcn = rl->vcn; + up_read(&ni->runlist.lock); - if (rl->lcn > 0) { - vcn += rl->length - (vcn - rl->vcn); - } else if (rl->lcn == LCN_DELALLOC || rl->lcn == LCN_HOLE) { - try_alloc_cnt = min(rl->length - (vcn - rl->vcn), + if (rl_lcn > 0) { + vcn += rl_length - (vcn - rl_vcn); + } else if (rl_lcn == LCN_DELALLOC || rl_lcn == LCN_HOLE) { + try_alloc_cnt = min(rl_length - (vcn - rl_vcn), vcn_uninit - vcn); - if (rl->lcn == LCN_DELALLOC) { + if (rl_lcn == LCN_DELALLOC) { vcn += try_alloc_cnt; continue; } @@ -5642,11 +5651,14 @@ int ntfs_attr_fallocate(struct ntfs_inode *ni, loff_t start, loff_t byte_len, bo if (err) goto out; - err = ntfs_dio_zero_range(VFS_I(ni), - lcn << vol->cluster_size_bits, - alloc_cnt << vol->cluster_size_bits); - if (err > 0) - goto out; + if (balloc) { + err = ntfs_dio_zero_range(VFS_I(ni), + lcn << vol->cluster_size_bits, + alloc_cnt << + vol->cluster_size_bits); + if (err > 0) + goto out; + } if (signal_pending(current)) goto out; diff --git a/fs/ntfs/attrlist.c b/fs/ntfs/attrlist.c index afb13038ba42..be3086d34338 100644 --- a/fs/ntfs/attrlist.c +++ b/fs/ntfs/attrlist.c @@ -57,6 +57,15 @@ int ntfs_attrlist_update(struct ntfs_inode *base_ni) struct ntfs_inode *attr_ni; int err; + /* + * generic_shutdown_super() clears SB_ACTIVE before evicting cached + * inodes. Do not look up the attribute-list inode after SB_ACTIVE has + * been cleared; it may already be I_FREEING, and waiting on it can + * self-deadlock. + */ + if (!(VFS_I(base_ni)->i_sb->s_flags & SB_ACTIVE)) + return -EIO; + attr_vi = ntfs_attr_iget(VFS_I(base_ni), AT_ATTRIBUTE_LIST, AT_UNNAMED, 0); if (IS_ERR(attr_vi)) { err = PTR_ERR(attr_vi); diff --git a/fs/ntfs/dir.c b/fs/ntfs/dir.c index 4b6bd5f30c65..6fa9ae3377cb 100644 --- a/fs/ntfs/dir.c +++ b/fs/ntfs/dir.c @@ -23,6 +23,13 @@ __le16 I30[5] = { cpu_to_le16('$'), cpu_to_le16('I'), cpu_to_le16('3'), cpu_to_le16('0'), 0 }; +static inline u64 ntfs_check_mref(u64 mref) +{ + if (IS_ERR_MREF(mref)) + return ERR_MREF(-EIO); + return mref; +} + /* * ntfs_lookup_inode_by_name - find an inode in a directory given its name * @dir_ni: ntfs inode of the directory in which to search for the name @@ -178,7 +185,7 @@ u64 ntfs_lookup_inode_by_name(struct ntfs_inode *dir_ni, const __le16 *uname, mref = le64_to_cpu(ie->data.dir.indexed_file); ntfs_attr_put_search_ctx(ctx); unmap_mft_record(dir_ni); - return mref; + return ntfs_check_mref(mref); } /* * For a case insensitive mount, we also perform a case @@ -273,7 +280,7 @@ u64 ntfs_lookup_inode_by_name(struct ntfs_inode *dir_ni, const __le16 *uname, if (name) { ntfs_attr_put_search_ctx(ctx); unmap_mft_record(dir_ni); - return name->mref; + return ntfs_check_mref(name->mref); } ntfs_debug("Entry not found."); err = -ENOENT; @@ -413,7 +420,7 @@ u64 ntfs_lookup_inode_by_name(struct ntfs_inode *dir_ni, const __le16 *uname, mref = le64_to_cpu(ie->data.dir.indexed_file); kfree(kaddr); iput(ia_vi); - return mref; + return ntfs_check_mref(mref); } /* * For a case insensitive mount, we also perform a case @@ -538,7 +545,7 @@ u64 ntfs_lookup_inode_by_name(struct ntfs_inode *dir_ni, const __le16 *uname, if (name) { kfree(kaddr); iput(ia_vi); - return name->mref; + return ntfs_check_mref(name->mref); } ntfs_debug("Entry not found."); err = -ENOENT; diff --git a/fs/ntfs/index.c b/fs/ntfs/index.c index c5f2cf75b750..faa7ee920a3a 100644 --- a/fs/ntfs/index.c +++ b/fs/ntfs/index.c @@ -110,6 +110,10 @@ static int ntfs_ib_write(struct ntfs_index_context *icx, struct index_block *ib) ret = ntfs_inode_attr_pwrite(VFS_I(icx->ia_ni), ntfs_ib_vcn_to_pos(icx, vcn), icx->block_size, (u8 *)ib, icx->sync_write); + + /* Perform data restoration before returning */ + post_write_mst_fixup((struct ntfs_record *)ib); + if (ret != icx->block_size) { ntfs_debug("Failed to write index block %lld, inode %llu", vcn, (unsigned long long)icx->idx_ni->mft_no); @@ -147,7 +151,6 @@ int ntfs_icx_ib_sync_write(struct ntfs_index_context *icx) icx->ib = NULL; icx->ib_dirty = false; } else { - post_write_mst_fixup((struct ntfs_record *)icx->ib); icx->sync_write = false; } diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c index c2715521e562..7381a18cfadd 100644 --- a/fs/ntfs/inode.c +++ b/fs/ntfs/inode.c @@ -1191,6 +1191,15 @@ static int ntfs_read_locked_inode(struct inode *vi) !S_ISFIFO(vi->i_mode) && !S_ISSOCK(vi->i_mode) && !S_ISLNK(vi->i_mode)) vi->i_flags |= S_IMMUTABLE; + /* + * System files such as $Bitmap and $MFT are maintained by the driver + * itself, and writing them from userspace corrupts the volume. + * Always make them immutable regardless of the sys_immutable option. + * Directories are skipped so the root and $Extend stay usable. + */ + if (ni->mft_no < FILE_first_user && S_ISREG(vi->i_mode)) + vi->i_flags |= S_IMMUTABLE; + /* * The number of 512-byte blocks used on disk (for stat). This is in so * far inaccurate as it doesn't account for any named streams or other diff --git a/fs/ntfs/mft.c b/fs/ntfs/mft.c index a5019e80951b..fd20d7abd6f5 100644 --- a/fs/ntfs/mft.c +++ b/fs/ntfs/mft.c @@ -2637,7 +2637,6 @@ static int ntfs_write_mft_block(struct folio *folio, struct writeback_control *w s64 vcn = ntfs_pidx_to_cluster(vol, folio->index); s64 end_vcn = ntfs_bytes_to_cluster(vol, ni->allocated_size); unsigned int folio_sz; - struct runlist_element *rl = NULL; loff_t i_size = i_size_read(vi); ntfs_debug("Entering for inode 0x%llx, attribute type 0x%x, folio index 0x%lx.", @@ -2682,6 +2681,7 @@ static int ntfs_write_mft_block(struct folio *folio, struct writeback_control *w &tni, &ref_inos[nr_ref_inos])) { unsigned int mft_record_off = 0; s64 vcn_off = vcn; + s64 rl_len = 0; /* * The record should be written. If a locked ntfs @@ -2701,8 +2701,12 @@ static int ntfs_write_mft_block(struct folio *folio, struct writeback_control *w } if (vol->cluster_size < folio_size(folio)) { + struct runlist_element *rl; + down_write(&ni->runlist.lock); rl = ntfs_attr_vcn_to_rl(ni, vcn_off, &lcn); + if (!IS_ERR(rl)) + rl_len = rl->length - (vcn_off - rl->vcn); up_write(&ni->runlist.lock); if (IS_ERR(rl) || lcn < 0) { err = -EIO; @@ -2733,7 +2737,7 @@ static int ntfs_write_mft_block(struct folio *folio, struct writeback_control *w if (vol->cluster_size == NTFS_BLOCK_SIZE && (mft_record_off || - (rl && rl->length - (vcn_off - rl->vcn) == 1) || + rl_len == 1 || mft_ofs + NTFS_BLOCK_SIZE >= PAGE_SIZE)) folio_sz = NTFS_BLOCK_SIZE; else diff --git a/fs/ntfs/namei.c b/fs/ntfs/namei.c index a19626a135bd..5ff25e9aaa32 100644 --- a/fs/ntfs/namei.c +++ b/fs/ntfs/namei.c @@ -1266,6 +1266,7 @@ static int ntfs_rename(struct mnt_idmap *idmap, struct inode *old_dir, struct ntfs_volume *vol = NTFS_SB(sb); struct ntfs_inode *old_ni, *new_ni = NULL; struct ntfs_inode *old_dir_ni = NTFS_I(old_dir), *new_dir_ni = NTFS_I(new_dir); + bool new_dir_first = false; if (NVolShutdown(old_dir_ni->vol)) return -EIO; @@ -1301,36 +1302,39 @@ static int ntfs_rename(struct mnt_idmap *idmap, struct inode *old_dir, old_inode = old_dentry->d_inode; new_inode = new_dentry->d_inode; old_ni = NTFS_I(old_inode); + if (new_inode) + new_ni = NTFS_I(new_inode); + if (old_dir != new_dir) + new_dir_first = is_subdir(new_dentry->d_parent, + old_dentry->d_parent); if (!(vol->vol_flags & VOLUME_IS_DIRTY)) ntfs_set_volume_flags(vol, VOLUME_IS_DIRTY); mutex_lock_nested(&old_ni->mrec_lock, NTFS_INODE_MUTEX_NORMAL); - mutex_lock_nested(&old_dir_ni->mrec_lock, NTFS_INODE_MUTEX_PARENT); + if (new_ni) + mutex_lock_nested(&new_ni->mrec_lock, NTFS_INODE_MUTEX_NORMAL_2); - if (NInoBeingDeleted(old_ni) || NInoBeingDeleted(old_dir_ni)) { + if (old_dir == new_dir) { + mutex_lock_nested(&old_dir_ni->mrec_lock, NTFS_INODE_MUTEX_PARENT); + } else if (new_dir_first) { + mutex_lock_nested(&new_dir_ni->mrec_lock, NTFS_INODE_MUTEX_PARENT); + mutex_lock_nested(&old_dir_ni->mrec_lock, NTFS_INODE_MUTEX_PARENT_2); + } else { + mutex_lock_nested(&old_dir_ni->mrec_lock, NTFS_INODE_MUTEX_PARENT); + mutex_lock_nested(&new_dir_ni->mrec_lock, NTFS_INODE_MUTEX_PARENT_2); + } + + if (NInoBeingDeleted(old_ni) || NInoBeingDeleted(old_dir_ni) || + (new_ni && NInoBeingDeleted(new_ni)) || + (old_dir != new_dir && NInoBeingDeleted(new_dir_ni))) { err = -ENOENT; - goto unlock_old; + goto err_out; } is_dir = S_ISDIR(old_inode->i_mode); if (new_inode) { - new_ni = NTFS_I(new_inode); - mutex_lock_nested(&new_ni->mrec_lock, NTFS_INODE_MUTEX_NORMAL_2); - if (old_dir != new_dir) { - mutex_lock_nested(&new_dir_ni->mrec_lock, NTFS_INODE_MUTEX_PARENT_2); - if (NInoBeingDeleted(new_dir_ni)) { - err = -ENOENT; - goto err_out; - } - } - - if (NInoBeingDeleted(new_ni)) { - err = -ENOENT; - goto err_out; - } - if (is_dir) { struct mft_record *ni_mrec; @@ -1348,14 +1352,6 @@ static int ntfs_rename(struct mnt_idmap *idmap, struct inode *old_dir, err = ntfs_delete(new_ni, new_dir_ni, uname_new, new_name_len, false); if (err) goto err_out; - } else { - if (old_dir != new_dir) { - mutex_lock_nested(&new_dir_ni->mrec_lock, NTFS_INODE_MUTEX_PARENT_2); - if (NInoBeingDeleted(new_dir_ni)) { - err = -ENOENT; - goto err_out; - } - } } err = __ntfs_link(old_ni, new_dir_ni, uname_new, new_name_len); @@ -1386,13 +1382,17 @@ static int ntfs_rename(struct mnt_idmap *idmap, struct inode *old_dir, inode_inc_iversion(new_dir); err_out: - if (old_dir != new_dir) + if (old_dir == new_dir) { + mutex_unlock(&old_dir_ni->mrec_lock); + } else if (new_dir_first) { + mutex_unlock(&old_dir_ni->mrec_lock); mutex_unlock(&new_dir_ni->mrec_lock); - if (new_inode) + } else { + mutex_unlock(&new_dir_ni->mrec_lock); + mutex_unlock(&old_dir_ni->mrec_lock); + } + if (new_ni) mutex_unlock(&new_ni->mrec_lock); - -unlock_old: - mutex_unlock(&old_dir_ni->mrec_lock); mutex_unlock(&old_ni->mrec_lock); if (uname_new) kmem_cache_free(ntfs_name_cache, uname_new); diff --git a/fs/proc/page.c b/fs/proc/page.c index f9b2c2c906cd..7d9387143435 100644 --- a/fs/proc/page.c +++ b/fs/proc/page.c @@ -173,7 +173,7 @@ u64 stable_page_flags(const struct page *page) u |= 1 << KPF_MMAP; if (is_anon) { u |= 1 << KPF_ANON; - if (mapping & FOLIO_MAPPING_KSM) + if ((mapping & FOLIO_MAPPING_FLAGS) == FOLIO_MAPPING_KSM) u |= 1 << KPF_KSM; } diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c index af2cbab14497..cc9966ff6cdf 100644 --- a/fs/resctrl/rdtgroup.c +++ b/fs/resctrl/rdtgroup.c @@ -74,6 +74,8 @@ static int rdtgroup_setup_root(struct rdt_fs_context *ctx); static void rdtgroup_destroy_root(void); +static void mon_put_kn_priv(void); + struct dentry *debugfs_resctrl; /* @@ -585,14 +587,20 @@ static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of, * * On resource group creation via a mkdir, an extra kernfs_node reference is * taken to ensure that the rdtgroup structure remains accessible for the - * rdtgroup_kn_unlock() calls where it is removed. + * rdtgroup_kn_unlock() calls where it is removed. The default group is + * statically allocated: it does not have an extra reference but will have + * RDT_DELETED set on unmount to support safe access to its associated files + * via rdtgroup_kn_lock_live/rdtgroup_kn_unlock(). * - * Drop the extra reference here, then free the rdtgroup structure. + * For all but the default group: drop the extra reference, then free the + * rdtgroup structure. * * Return: void */ static void rdtgroup_remove(struct rdtgroup *rdtgrp) { + if (rdtgrp == &rdtgroup_default) + return; kernfs_put(rdtgrp->kn); kfree(rdtgrp); } @@ -2812,6 +2820,12 @@ static int rdt_get_tree(struct fs_context *fc) goto out; } + /* Avoid races from pending operations from a previous mount */ + if (atomic_read(&rdtgroup_default.waitcount) != 0) { + ret = -EBUSY; + goto out; + } + ret = setup_rmid_lru_list(); if (ret) goto out; @@ -2893,6 +2907,7 @@ static int rdt_get_tree(struct fs_context *fc) kernfs_remove(kn_mondata); out_mongrp: if (resctrl_arch_mon_capable()) { + mon_put_kn_priv(); rdtgroup_unassign_cntrs(&rdtgroup_default); kernfs_remove(kn_mongrp); } @@ -3069,10 +3084,6 @@ static void rmdir_all_sub(void) if (rdtgrp == &rdtgroup_default) continue; - if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP || - rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) - rdtgroup_pseudo_lock_remove(rdtgrp); - /* * Give any CPUs back to the default group. We cannot copy * cpu_online_mask because a CPU might have executed the @@ -3083,7 +3094,13 @@ static void rmdir_all_sub(void) rdtgroup_unassign_cntrs(rdtgrp); - free_rmid(rdtgrp->closid, rdtgrp->mon.rmid); + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP || + rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) { + rdtgroup_pseudo_lock_remove(rdtgrp); + } else { + /* Pseudo-locked group's RMID is freed during setup. */ + free_rmid(rdtgrp->closid, rdtgrp->mon.rmid); + } kernfs_remove(rdtgrp->kn); list_del(&rdtgrp->rdtgroup_list); @@ -3174,6 +3191,7 @@ static void resctrl_fs_teardown(void) mon_put_kn_priv(); rdt_pseudo_lock_release(); rdtgroup_default.mode = RDT_MODE_SHAREABLE; + rdtgroup_default.flags = RDT_DELETED; closid_exit(); schemata_list_destroy(); rdtgroup_destroy_root(); @@ -4274,6 +4292,7 @@ static int rdtgroup_setup_root(struct rdt_fs_context *ctx) ctx->kfc.root = rdt_root; rdtgroup_default.kn = kernfs_root_to_node(rdt_root); + rdtgroup_default.flags = 0; return 0; } diff --git a/fs/smb/client/cifs_fs_sb.h b/fs/smb/client/cifs_fs_sb.h index 84e7e366b0ff..d6494e1d93cc 100644 --- a/fs/smb/client/cifs_fs_sb.h +++ b/fs/smb/client/cifs_fs_sb.h @@ -56,6 +56,7 @@ struct cifs_sb_info { struct smb3_fs_context *ctx; atomic_t active; atomic_t mnt_cifs_flags; + atomic_t outstanding_rreq; /* nr of rreqs not yet fully deinitialized */ struct delayed_work prune_tlinks; struct rcu_head rcu; diff --git a/fs/smb/client/cifsacl.c b/fs/smb/client/cifsacl.c index 07cf0e578233..9424281a7674 100644 --- a/fs/smb/client/cifsacl.c +++ b/fs/smb/client/cifsacl.c @@ -962,7 +962,7 @@ static void parse_dacl(struct smb_acl *pdacl, char *end_of_acl, */ fattr->cf_mode &= ~07777; fattr->cf_mode |= - le32_to_cpu(ppace[i]->sid.sub_auth[2]); + le32_to_cpu(ppace[i]->sid.sub_auth[2]) & 07777; break; } else { if (compare_sids(&(ppace[i]->sid), pownersid) == 0) { diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c index ea4fc0fa68ca..4df6ca03a8de 100644 --- a/fs/smb/client/cifsfs.c +++ b/fs/smb/client/cifsfs.c @@ -311,6 +311,18 @@ static void cifs_kill_sb(struct super_block *sb) /* Wait for all opened files to release */ flush_workqueue(deferredclose_wq); + /* + * Wait for all in-flight netfs I/O requests to finish their + * cleanup_work so that any cifsFileInfo final puts they queue + * to fileinfo_put_wq/serverclose_wq have been queued, then + * drain the workqueue so the cfile dentry refs are dropped to + * avoid the busy dentry warning. + */ + wait_var_event(&cifs_sb->outstanding_rreq, + !atomic_read(&cifs_sb->outstanding_rreq)); + flush_workqueue(serverclose_wq); + flush_workqueue(fileinfo_put_wq); + /* finally release root dentry */ dput(cifs_sb->root); cifs_sb->root = NULL; diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h index 99f9e6dca62b..08e94633a9c1 100644 --- a/fs/smb/client/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -250,6 +250,7 @@ struct cifs_open_info_data { bool adjust_tz; bool reparse_point; bool contains_posix_file_info; + bool unknown_nlink; struct { /* ioctl response buffer */ struct { diff --git a/fs/smb/client/cifsproto.h b/fs/smb/client/cifsproto.h index c4ababcb51a3..00168839c123 100644 --- a/fs/smb/client/cifsproto.h +++ b/fs/smb/client/cifsproto.h @@ -317,7 +317,7 @@ int generate_smb311signingkey(struct cifs_ses *ses, #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY #endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ -void cifs_autodisable_serverino(struct cifs_sb_info *cifs_sb); +void cifs_autodisable_serverino(struct cifs_sb_info *cifs_sb, const char *reason, int rc); bool couldbe_mf_symlink(const struct cifs_fattr *fattr); int check_mf_symlink(unsigned int xid, struct cifs_tcon *tcon, struct cifs_sb_info *cifs_sb, struct cifs_fattr *fattr, diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c index d39175cdf1b1..40162d5554ea 100644 --- a/fs/smb/client/cifssmb.c +++ b/fs/smb/client/cifssmb.c @@ -5829,38 +5829,6 @@ CIFSSMBSetFileDisposition(const unsigned int xid, struct cifs_tcon *tcon, return rc; } -static int -CIFSSMBSetPathInfoFB(const unsigned int xid, struct cifs_tcon *tcon, - const char *fileName, const FILE_BASIC_INFO *data, - const struct nls_table *nls_codepage, - struct cifs_sb_info *cifs_sb) -{ - int oplock = 0; - struct cifs_open_parms oparms; - struct cifs_fid fid; - int rc; - - oparms = (struct cifs_open_parms) { - .tcon = tcon, - .cifs_sb = cifs_sb, - .desired_access = GENERIC_WRITE, - .create_options = cifs_create_options(cifs_sb, 0), - .disposition = FILE_OPEN, - .path = fileName, - .fid = &fid, - }; - - rc = CIFS_open(xid, &oparms, &oplock, NULL); - if (rc) - goto out; - - rc = CIFSSMBSetFileInfo(xid, tcon, data, fid.netfid, current->tgid); - CIFSSMBClose(xid, tcon, fid.netfid); -out: - - return rc; -} - int CIFSSMBSetPathInfo(const unsigned int xid, struct cifs_tcon *tcon, const char *fileName, const FILE_BASIC_INFO *data, @@ -5939,10 +5907,6 @@ CIFSSMBSetPathInfo(const unsigned int xid, struct cifs_tcon *tcon, if (rc == -EAGAIN) goto SetTimesRetry; - if (rc == -EOPNOTSUPP) - return CIFSSMBSetPathInfoFB(xid, tcon, fileName, data, - nls_codepage, cifs_sb); - return rc; } diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c index 85aec302c89e..ba749ec25a59 100644 --- a/fs/smb/client/connect.c +++ b/fs/smb/client/connect.c @@ -3485,6 +3485,7 @@ int cifs_setup_cifs_sb(struct cifs_sb_info *cifs_sb) spin_lock_init(&cifs_sb->tlink_tree_lock); cifs_sb->tlink_tree = RB_ROOT; + atomic_set(&cifs_sb->outstanding_rreq, 0); cifs_dbg(FYI, "file mode: %04ho dir mode: %04ho\n", ctx->file_mode, ctx->dir_mode); @@ -3875,7 +3876,7 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx) * After reconnecting to a different server, unique ids won't match anymore, so we disable * serverino. This prevents dentry revalidation to think the dentry are stale (ESTALE). */ - cifs_autodisable_serverino(cifs_sb); + cifs_autodisable_serverino(cifs_sb, "DFS failover may potentially connect to a different server, inode numbers won't match anymore", 0); /* * Force the use of prefix path to support failover on DFS paths that resolve to targets * that have different prefix paths. diff --git a/fs/smb/client/dfs_cache.c b/fs/smb/client/dfs_cache.c index 83f8cf2f8d2b..8cd93cd2f00f 100644 --- a/fs/smb/client/dfs_cache.c +++ b/fs/smb/client/dfs_cache.c @@ -363,10 +363,10 @@ static struct cache_dfs_tgt *alloc_target(const char *name, int path_consumed) { struct cache_dfs_tgt *t; - t = kmalloc_obj(*t, GFP_ATOMIC); + t = kmalloc_obj(*t, GFP_KERNEL); if (!t) return ERR_PTR(-ENOMEM); - t->name = kstrdup(name, GFP_ATOMIC); + t->name = kstrdup(name, GFP_KERNEL); if (!t->name) { kfree(t); return ERR_PTR(-ENOMEM); @@ -626,7 +626,7 @@ static int update_cache_entry_locked(struct cache_entry *ce, const struct dfs_in target = READ_ONCE(ce->tgthint); if (target) { - th = kstrdup(target->name, GFP_ATOMIC); + th = kstrdup(target->name, GFP_KERNEL); if (!th) return -ENOMEM; } @@ -760,11 +760,11 @@ static int setup_referral(const char *path, struct cache_entry *ce, memset(ref, 0, sizeof(*ref)); - ref->path_name = kstrdup(path, GFP_ATOMIC); + ref->path_name = kstrdup(path, GFP_KERNEL); if (!ref->path_name) return -ENOMEM; - ref->node_name = kstrdup(target, GFP_ATOMIC); + ref->node_name = kstrdup(target, GFP_KERNEL); if (!ref->node_name) { rc = -ENOMEM; goto err_free_path; @@ -1328,7 +1328,7 @@ int dfs_cache_remount_fs(struct cifs_sb_info *cifs_sb) * After reconnecting to a different server, unique ids won't match anymore, so we disable * serverino. This prevents dentry revalidation to think the dentry are stale (ESTALE). */ - cifs_autodisable_serverino(cifs_sb); + cifs_autodisable_serverino(cifs_sb, "DFS failover may potentially connect to a different server, inode numbers won't match anymore", 0); /* * Force the use of prefix path to support failover on DFS paths that resolve to targets * that have different prefix paths. diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index 5a25635bc62a..968740e7c9c3 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -288,6 +288,7 @@ static int cifs_init_request(struct netfs_io_request *rreq, struct file *file) return smb_EIO1(smb_eio_trace_not_netfs_writeback, rreq->origin); } + atomic_inc(&cifs_sb->outstanding_rreq); return 0; } @@ -302,16 +303,20 @@ static void cifs_rreq_done(struct netfs_io_request *rreq) /* we do not want atime to be less than mtime, it broke some apps */ atime = inode_set_atime_to_ts(inode, current_time(inode)); mtime = inode_get_mtime(inode); - if (timespec64_compare(&atime, &mtime)) + if (timespec64_compare(&atime, &mtime) < 0) inode_set_atime_to_ts(inode, inode_get_mtime(inode)); } static void cifs_free_request(struct netfs_io_request *rreq) { struct cifs_io_request *req = container_of(rreq, struct cifs_io_request, rreq); + struct cifs_sb_info *cifs_sb = CIFS_SB(rreq->inode->i_sb); if (req->cfile) cifsFileInfo_put(req->cfile); + + if (atomic_dec_and_test(&cifs_sb->outstanding_rreq)) + wake_up_var(&cifs_sb->outstanding_rreq); } static void cifs_free_subrequest(struct netfs_io_subrequest *subreq) diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c index 1dbcfd163ff0..deed04dd9b91 100644 --- a/fs/smb/client/inode.c +++ b/fs/smb/client/inode.c @@ -909,6 +909,8 @@ static void cifs_open_info_to_fattr(struct cifs_fattr *fattr, struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb); memset(fattr, 0, sizeof(*fattr)); + if (data->unknown_nlink) + fattr->cf_flags |= CIFS_FATTR_UNKNOWN_NLINK; fattr->cf_cifsattrs = le32_to_cpu(info->Attributes); if (info->DeletePending) fattr->cf_flags |= CIFS_FATTR_DELETE_PENDING; @@ -1145,7 +1147,7 @@ static void cifs_set_fattr_ino(int xid, struct cifs_tcon *tcon, struct super_blo fattr->cf_uniqueid = CIFS_I(*inode)->uniqueid; else { fattr->cf_uniqueid = iunique(sb, ROOT_I); - cifs_autodisable_serverino(cifs_sb); + cifs_autodisable_serverino(cifs_sb, "Cannot retrieve inode number via get_srv_inum", rc); } return; } @@ -1642,7 +1644,7 @@ cifs_iget(struct super_block *sb, struct cifs_fattr *fattr) fattr->cf_flags &= ~CIFS_FATTR_INO_COLLISION; if (inode_has_hashed_dentries(inode)) { - cifs_autodisable_serverino(CIFS_SB(sb)); + cifs_autodisable_serverino(CIFS_SB(sb), "Inode number collision detected", 0); iput(inode); fattr->cf_uniqueid = iunique(sb, ROOT_I); goto retry_iget5_locked; @@ -1708,8 +1710,9 @@ struct inode *cifs_root_iget(struct super_block *sb) iget_root: if (!rc) { if (fattr.cf_flags & CIFS_FATTR_JUNCTION) { + cifs_dbg(VFS, "Removing junction mark and disabling 'serverino' to prevent inode collisions\n"); fattr.cf_flags &= ~CIFS_FATTR_JUNCTION; - cifs_autodisable_serverino(cifs_sb); + cifs_autodisable_serverino(cifs_sb, "Cannot retrieve attributes for junction point", rc); } inode = cifs_iget(sb, &fattr); } @@ -2812,9 +2815,7 @@ cifs_revalidate_mapping(struct inode *inode) } skip_invalidate: - clear_bit_unlock(CIFS_INO_LOCK, flags); - smp_mb__after_atomic(); - wake_up_bit(flags, CIFS_INO_LOCK); + clear_and_wake_up_bit(CIFS_INO_LOCK, flags); return rc; } diff --git a/fs/smb/client/link.c b/fs/smb/client/link.c index dd127917a340..8d5d6aca742a 100644 --- a/fs/smb/client/link.c +++ b/fs/smb/client/link.c @@ -234,7 +234,7 @@ cifs_query_mf_symlink(unsigned int xid, struct cifs_tcon *tcon, struct cifs_open_parms oparms; struct cifs_io_parms io_parms = {0}; int buf_type = CIFS_NO_BUFFER; - struct cifs_open_info_data query_data; + struct cifs_open_info_data query_data = {}; oparms = (struct cifs_open_parms) { .tcon = tcon, @@ -320,7 +320,7 @@ smb3_query_mf_symlink(unsigned int xid, struct cifs_tcon *tcon, int buf_type = CIFS_NO_BUFFER; __le16 *utf16_path; __u8 oplock = SMB2_OPLOCK_LEVEL_NONE; - struct smb2_file_all_info *pfile_info = NULL; + struct cifs_open_info_data data = {}; oparms = (struct cifs_open_parms) { .tcon = tcon, @@ -336,20 +336,12 @@ smb3_query_mf_symlink(unsigned int xid, struct cifs_tcon *tcon, if (utf16_path == NULL) return -ENOMEM; - pfile_info = kzalloc(sizeof(struct smb2_file_all_info) + PATH_MAX * 2, - GFP_KERNEL); - - if (pfile_info == NULL) { - kfree(utf16_path); - return -ENOMEM; - } - - rc = SMB2_open(xid, &oparms, utf16_path, &oplock, pfile_info, NULL, + rc = SMB2_open(xid, &oparms, utf16_path, &oplock, &data, NULL, NULL, NULL); if (rc) goto qmf_out_open_fail; - if (pfile_info->EndOfFile != cpu_to_le64(CIFS_MF_SYMLINK_FILE_SIZE)) { + if (data.fi.EndOfFile != cpu_to_le64(CIFS_MF_SYMLINK_FILE_SIZE)) { /* it's not a symlink */ rc = -ENOENT; /* Is there a better rc to return? */ goto qmf_out; @@ -367,7 +359,6 @@ smb3_query_mf_symlink(unsigned int xid, struct cifs_tcon *tcon, SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid); qmf_out_open_fail: kfree(utf16_path); - kfree(pfile_info); return rc; } diff --git a/fs/smb/client/misc.c b/fs/smb/client/misc.c index 0c54b9b79a2c..e4bac2a0b85d 100644 --- a/fs/smb/client/misc.c +++ b/fs/smb/client/misc.c @@ -278,7 +278,7 @@ dump_smb(void *buf, int smb_buf_length) } void -cifs_autodisable_serverino(struct cifs_sb_info *cifs_sb) +cifs_autodisable_serverino(struct cifs_sb_info *cifs_sb, const char *reason, int rc) { unsigned int sbflags = cifs_sb_flags(cifs_sb); @@ -290,6 +290,10 @@ cifs_autodisable_serverino(struct cifs_sb_info *cifs_sb) atomic_andnot(CIFS_MOUNT_SERVER_INUM, &cifs_sb->mnt_cifs_flags); cifs_sb->mnt_cifs_serverino_autodisabled = true; + if (rc) + cifs_dbg(VFS, "%s: %d\n", reason, rc); + else + cifs_dbg(VFS, "%s\n", reason); cifs_dbg(VFS, "Autodisabling the use of server inode numbers on %s\n", tcon ? tcon->tree_name : "new server"); cifs_dbg(VFS, "The server doesn't seem to support them properly or the files might be on different servers (DFS)\n"); @@ -752,6 +756,10 @@ parse_dfs_referrals(struct get_dfs_referral_rsp *rsp, u32 rsp_size, node->ref_flag = le16_to_cpu(ref->ReferralEntryFlags); /* copy DfsPath */ + if (le16_to_cpu(ref->DfsPathOffset) > data_end - (char *)ref) { + rc = -EINVAL; + goto parse_DFS_referrals_exit; + } temp = (char *)ref + le16_to_cpu(ref->DfsPathOffset); max_len = data_end - temp; node->path_name = cifs_strndup_from_utf16(temp, max_len, @@ -762,6 +770,10 @@ parse_dfs_referrals(struct get_dfs_referral_rsp *rsp, u32 rsp_size, } /* copy link target UNC */ + if (le16_to_cpu(ref->NetworkAddressOffset) > data_end - (char *)ref) { + rc = -EINVAL; + goto parse_DFS_referrals_exit; + } temp = (char *)ref + le16_to_cpu(ref->NetworkAddressOffset); max_len = data_end - temp; node->node_name = cifs_strndup_from_utf16(temp, max_len, diff --git a/fs/smb/client/readdir.c b/fs/smb/client/readdir.c index a50c86bbe60f..ee5996e6d7d8 100644 --- a/fs/smb/client/readdir.c +++ b/fs/smb/client/readdir.c @@ -415,7 +415,7 @@ _initiate_cifs_search(const unsigned int xid, struct file *file, if (rc == 0) { cifsFile->invalidHandle = false; } else if (rc == -EOPNOTSUPP && (sbflags & CIFS_MOUNT_SERVER_INUM)) { - cifs_autodisable_serverino(cifs_sb); + cifs_autodisable_serverino(cifs_sb, "Cannot retrieve inode number via query_dir_first", rc); goto ffirst_retry; } error_exit: @@ -1029,7 +1029,7 @@ static int cifs_filldir(char *find_entry, struct file *file, fattr.cf_uniqueid = de.ino; } else { fattr.cf_uniqueid = iunique(sb, ROOT_I); - cifs_autodisable_serverino(cifs_sb); + cifs_autodisable_serverino(cifs_sb, "Cannot retrieve inode number from readdir", 0); } if ((sbflags & CIFS_MOUNT_MF_SYMLINKS) && couldbe_mf_symlink(&fattr)) diff --git a/fs/smb/client/reparse.c b/fs/smb/client/reparse.c index cd1e1eaee67a..5cc5b0410d48 100644 --- a/fs/smb/client/reparse.c +++ b/fs/smb/client/reparse.c @@ -67,6 +67,7 @@ static int create_native_symlink(const unsigned int xid, struct inode *inode, char *sym = NULL; struct kvec iov; bool directory; + int path_len; int rc = 0; if (strlen(symname) > REPARSE_SYM_PATH_MAX) @@ -168,7 +169,21 @@ static int create_native_symlink(const unsigned int xid, struct inode *inode, if (!(sbflags & CIFS_MOUNT_POSIX_PATHS) && symname[0] == '/') sym[0] = sym[1] = sym[2] = sym[5] = '_'; - path = cifs_convert_path_to_utf16(sym, cifs_sb); + /* + * On a POSIX paths mount the symlink target is stored verbatim, so + * convert it with cifs_strndup_to_utf16(). cifs_convert_path_to_utf16() + * must not be used here: it strips a leading path separator (it is + * meant for share-relative SMB paths), which would corrupt an absolute + * POSIX symlink target such as "/foo/bar". Using NO_MAP_UNI_RSVD also + * matches the readback path in smb2_parse_native_symlink(). + */ + if (sbflags & CIFS_MOUNT_POSIX_PATHS) + path = cifs_strndup_to_utf16(sym, strlen(sym), &path_len, + cifs_sb->local_nls, + NO_MAP_UNI_RSVD); + else + path = cifs_convert_path_to_utf16(sym, cifs_sb); + if (!path) { rc = -ENOMEM; goto out; diff --git a/fs/smb/client/smb1ops.c b/fs/smb/client/smb1ops.c index d34b3d99f6ed..dc5a8c1da623 100644 --- a/fs/smb/client/smb1ops.c +++ b/fs/smb/client/smb1ops.c @@ -505,21 +505,27 @@ static int cifs_is_path_accessible(const unsigned int xid, struct cifs_tcon *tcon, struct cifs_sb_info *cifs_sb, const char *full_path) { - int rc; - FILE_ALL_INFO *file_info; + int rc = -EOPNOTSUPP; + FILE_ALL_INFO file_info; - file_info = kmalloc_obj(FILE_ALL_INFO); - if (file_info == NULL) - return -ENOMEM; + if (tcon->ses->capabilities & CAP_NT_SMBS) + rc = CIFSSMBQPathInfo(xid, tcon, full_path, &file_info, + 0 /* not legacy */, cifs_sb->local_nls, + cifs_remap(cifs_sb)); - rc = CIFSSMBQPathInfo(xid, tcon, full_path, file_info, - 0 /* not legacy */, cifs_sb->local_nls, - cifs_remap(cifs_sb)); + /* + * Non-UNICODE variant of fallback functions below expands wildcards, + * so they cannot be used for querying paths with wildcard characters. + * Therefore for such paths returns -ENOENT as they cannot exist. + */ + if ((rc == -EOPNOTSUPP || rc == -EINVAL) && + !(tcon->ses->capabilities & CAP_UNICODE) && + strpbrk(full_path, "*?\"><")) + rc = -ENOENT; if (rc == -EOPNOTSUPP || rc == -EINVAL) - rc = SMBQueryInformation(xid, tcon, full_path, file_info, + rc = SMBQueryInformation(xid, tcon, full_path, &file_info, cifs_sb->local_nls, cifs_remap(cifs_sb)); - kfree(file_info); return rc; } @@ -949,7 +955,7 @@ smb_set_file_info(struct inode *inode, const char *full_path, struct cifs_open_parms oparms; struct cifsFileInfo *open_file; FILE_BASIC_INFO new_buf; - struct cifs_open_info_data query_data; + struct cifs_open_info_data query_data = {}; __le64 write_time = buf->LastWriteTime; struct cifsInodeInfo *cinode = CIFS_I(inode); struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); diff --git a/fs/smb/client/smb2file.c b/fs/smb/client/smb2file.c index 6860eff31693..5ef919bce52d 100644 --- a/fs/smb/client/smb2file.c +++ b/fs/smb/client/smb2file.c @@ -154,8 +154,6 @@ int smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *smb2_path; __u8 smb2_oplock; struct cifs_open_info_data *data = buf; - struct smb2_file_all_info file_info = {}; - struct smb2_file_all_info *smb2_data = data ? &file_info : NULL; struct kvec err_iov = {}; int err_buftype = CIFS_NO_BUFFER; struct cifs_fid *fid = oparms->fid; @@ -182,14 +180,14 @@ int smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms, } smb2_oplock = SMB2_OPLOCK_LEVEL_BATCH; - rc = SMB2_open(xid, oparms, smb2_path, &smb2_oplock, smb2_data, NULL, &err_iov, + rc = SMB2_open(xid, oparms, smb2_path, &smb2_oplock, data, NULL, &err_iov, &err_buftype); if (rc == -EACCES && retry_without_read_attributes) { free_rsp_buf(err_buftype, err_iov.iov_base); memset(&err_iov, 0, sizeof(err_iov)); err_buftype = CIFS_NO_BUFFER; oparms->desired_access &= ~FILE_READ_ATTRIBUTES; - rc = SMB2_open(xid, oparms, smb2_path, &smb2_oplock, smb2_data, NULL, &err_iov, + rc = SMB2_open(xid, oparms, smb2_path, &smb2_oplock, data, NULL, &err_iov, &err_buftype); } if (rc && data) { @@ -202,9 +200,9 @@ int smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms, oparms->path, &data->symlink_target); if (!rc) { - memset(smb2_data, 0, sizeof(*smb2_data)); + memset(&data->fi, 0, sizeof(data->fi)); oparms->create_options |= OPEN_REPARSE_POINT; - rc = SMB2_open(xid, oparms, smb2_path, &smb2_oplock, smb2_data, + rc = SMB2_open(xid, oparms, smb2_path, &smb2_oplock, data, NULL, NULL, NULL); oparms->create_options &= ~OPEN_REPARSE_POINT; } @@ -238,23 +236,22 @@ int smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms, rc = 0; } - if (smb2_data) { + if (data) { /* if open response does not have IndexNumber field - get it */ - if (smb2_data->IndexNumber == 0) { + if (data->fi.IndexNumber == 0) { rc = SMB2_get_srv_num(xid, oparms->tcon, fid->persistent_fid, fid->volatile_fid, - &smb2_data->IndexNumber); + &data->fi.IndexNumber); if (rc) { /* * let get_inode_info disable server inode * numbers */ - smb2_data->IndexNumber = 0; + data->fi.IndexNumber = 0; rc = 0; } } - memcpy(&data->fi, smb2_data, sizeof(data->fi)); } *oplock = smb2_oplock; diff --git a/fs/smb/client/smb2misc.c b/fs/smb/client/smb2misc.c index 2a7355ce1a07..6270b33147d2 100644 --- a/fs/smb/client/smb2misc.c +++ b/fs/smb/client/smb2misc.c @@ -19,6 +19,8 @@ #include "nterr.h" #include "cached_dir.h" +static unsigned int __smb2_calc_size(void *buf, bool *have_data); + static int check_smb2_hdr(struct smb2_hdr *shdr, __u64 mid) { @@ -145,6 +147,7 @@ smb2_check_message(char *buf, unsigned int pdu_len, unsigned int len, int command; __u32 calc_len; /* calculated length */ __u64 mid; + bool have_data; /* If server is a channel, select the primary channel */ pserver = SERVER_IS_CHAN(server) ? server->primary_server : server; @@ -228,7 +231,8 @@ smb2_check_message(char *buf, unsigned int pdu_len, unsigned int len, } } - calc_len = smb2_calc_size(buf); + have_data = false; + calc_len = __smb2_calc_size(buf, &have_data); /* For SMB2_IOCTL, OutputOffset and OutputLength are optional, so might * be 0, and not a real miscalculation */ @@ -247,8 +251,13 @@ smb2_check_message(char *buf, unsigned int pdu_len, unsigned int len, /* Windows 7 server returns 24 bytes more */ if (calc_len + 24 == len && command == SMB2_OPLOCK_BREAK_HE) return 0; - /* server can return one byte more due to implied bcc[0] */ - if (calc_len == len + 1) + /* + * Server can return one byte more due to implied bcc[0]. + * Allow it only when there is no data area; if data_length > 0 + * the +1 gap indicates an overreported data length rather than + * the bcc[0] omission. + */ + if (calc_len == len + 1 && !have_data) return 0; /* @@ -409,14 +418,17 @@ smb2_get_data_area_len(int *off, int *len, struct smb2_hdr *shdr) /* * Calculate the size of the SMB message based on the fixed header * portion, the number of word parameters and the data portion of the message. + * If have_data is non-NULL, it is set to true when a non-empty data area was + * found (data_length > 0), allowing callers to distinguish the implied bcc[0] + * case (no data area) from an overreported data length. */ -unsigned int -smb2_calc_size(void *buf) +static unsigned int +__smb2_calc_size(void *buf, bool *have_data) { struct smb2_pdu *pdu = buf; struct smb2_hdr *shdr = &pdu->hdr; int offset; /* the offset from the beginning of SMB to data area */ - int data_length; /* the length of the variable length data area */ + int data_length = 0; /* the length of the variable length data area */ /* Structure Size has already been checked to make sure it is 64 */ int len = le16_to_cpu(shdr->StructureSize); @@ -449,9 +461,17 @@ smb2_calc_size(void *buf) } calc_size_exit: cifs_dbg(FYI, "SMB2 len %d\n", len); + if (have_data) + *have_data = (data_length > 0); return len; } +unsigned int +smb2_calc_size(void *buf) +{ + return __smb2_calc_size(buf, NULL); +} + /* Note: caller must free return buffer */ __le16 * cifs_convert_path_to_utf16(const char *from, struct cifs_sb_info *cifs_sb) diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index 06e9322a762a..6bce44b171e4 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -1772,8 +1772,8 @@ smb2_ioctl_query_info(const unsigned int xid, if (le32_to_cpu(io_rsp->OutputCount) < qi.input_buffer_length) qi.input_buffer_length = le32_to_cpu(io_rsp->OutputCount); if (qi.input_buffer_length > 0 && - le32_to_cpu(io_rsp->OutputOffset) + qi.input_buffer_length - > rsp_iov[1].iov_len) { + size_add(le32_to_cpu(io_rsp->OutputOffset), + qi.input_buffer_length) > rsp_iov[1].iov_len) { rc = -EFAULT; goto out; } @@ -5237,7 +5237,7 @@ int __cifs_sfu_make_node(unsigned int xid, struct inode *inode, { struct TCP_Server_Info *server = tcon->ses->server; struct cifs_open_parms oparms; - struct cifs_open_info_data idata; + struct cifs_open_info_data idata = {}; struct cifs_io_parms io_parms = {}; struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); struct cifs_fid fid; @@ -5286,16 +5286,13 @@ int __cifs_sfu_make_node(unsigned int xid, struct inode *inode, data = (u8 *)symname_utf16; break; case S_IFSOCK: - type_len = 8; - strscpy(type, "LnxSOCK"); - data = (u8 *)&pdev; - data_len = sizeof(pdev); + /* SFU socket is system file with one zero byte */ + type_len = 1; + type[0] = '\0'; break; case S_IFIFO: - type_len = 8; - strscpy(type, "LnxFIFO"); - data = (u8 *)&pdev; - data_len = sizeof(pdev); + /* SFU fifo is system file which is empty */ + type_len = 0; break; default: rc = -EPERM; diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index 95c0efe9d43b..8f83ab377db1 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -3287,7 +3287,7 @@ SMB2_open_free(struct smb_rqst *rqst) int SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path, - __u8 *oplock, struct smb2_file_all_info *buf, + __u8 *oplock, struct cifs_open_info_data *buf, struct create_posix_rsp *posix, struct kvec *err_iov, int *buftype) { @@ -3302,6 +3302,7 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path, int rc = 0; int flags = 0; int retries = 0, cur_sleep = 0; + struct smb2_file_all_info *file_info = buf ? &buf->fi : NULL; replay_again: /* reinitialize for possible replay */ @@ -3370,21 +3371,22 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path, oparms->fid->mid = le64_to_cpu(rsp->hdr.MessageId); #endif /* CIFS_DEBUG2 */ - if (buf) { - buf->CreationTime = rsp->CreationTime; - buf->LastAccessTime = rsp->LastAccessTime; - buf->LastWriteTime = rsp->LastWriteTime; - buf->ChangeTime = rsp->ChangeTime; - buf->AllocationSize = rsp->AllocationSize; - buf->EndOfFile = rsp->EndofFile; - buf->Attributes = rsp->FileAttributes; - buf->NumberOfLinks = cpu_to_le32(1); - buf->DeletePending = 0; /* successful open = not delete pending */ + if (file_info) { + file_info->CreationTime = rsp->CreationTime; + file_info->LastAccessTime = rsp->LastAccessTime; + file_info->LastWriteTime = rsp->LastWriteTime; + file_info->ChangeTime = rsp->ChangeTime; + file_info->AllocationSize = rsp->AllocationSize; + file_info->EndOfFile = rsp->EndofFile; + file_info->Attributes = rsp->FileAttributes; + file_info->NumberOfLinks = cpu_to_le32(1); + buf->unknown_nlink = true; + file_info->DeletePending = 0; /* successful open = not delete pending */ } rc = smb2_parse_contexts(server, &rsp_iov, &oparms->fid->epoch, - oparms->fid->lease_key, oplock, buf, posix); + oparms->fid->lease_key, oplock, file_info, posix); trace_smb3_open_done(xid, rsp->PersistentFileId, tcon->tid, ses->Suid, oparms->create_options, oparms->desired_access, diff --git a/fs/smb/client/smb2proto.h b/fs/smb/client/smb2proto.h index 78a4e1c340f9..e01effe45ae2 100644 --- a/fs/smb/client/smb2proto.h +++ b/fs/smb/client/smb2proto.h @@ -136,7 +136,7 @@ int SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree, struct cifs_tcon *tcon, const struct nls_table *cp); int SMB2_tdis(const unsigned int xid, struct cifs_tcon *tcon); int SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, - __le16 *path, __u8 *oplock, struct smb2_file_all_info *buf, + __le16 *path, __u8 *oplock, struct cifs_open_info_data *buf, struct create_posix_rsp *posix, struct kvec *err_iov, int *buftype); int SMB2_open_init(struct cifs_tcon *tcon, struct TCP_Server_Info *server, diff --git a/fs/smb/server/auth.c b/fs/smb/server/auth.c index 86f521e849d5..4e7b6f0e6b8c 100644 --- a/fs/smb/server/auth.c +++ b/fs/smb/server/auth.c @@ -133,16 +133,17 @@ static int calc_ntlmv2_hash(struct ksmbd_conn *conn, struct ksmbd_session *sess, * @blen: NTLMv2 blob length * @domain_name: domain name * @cryptkey: session crypto key + * @sess_key: derived session key output buffer * * Return: 0 on success, error number on error */ int ksmbd_auth_ntlmv2(struct ksmbd_conn *conn, struct ksmbd_session *sess, struct ntlmv2_resp *ntlmv2, int blen, char *domain_name, - char *cryptkey) + char *cryptkey, char *sess_key) { char ntlmv2_hash[CIFS_ENCPWD_SIZE]; char ntlmv2_rsp[CIFS_HMAC_MD5_HASH_SIZE]; - char sess_key[SMB2_NTLMV2_SESSKEY_SIZE]; + char base_key[SMB2_NTLMV2_SESSKEY_SIZE]; struct hmac_md5_ctx ctx; int rc; @@ -165,7 +166,7 @@ int ksmbd_auth_ntlmv2(struct ksmbd_conn *conn, struct ksmbd_session *sess, /* Generate the session key */ hmac_md5_usingrawkey(ntlmv2_hash, CIFS_HMAC_MD5_HASH_SIZE, ntlmv2_rsp, CIFS_HMAC_MD5_HASH_SIZE, - sess_key); + base_key); if (crypto_memneq(ntlmv2->ntlmv2_hash, ntlmv2_rsp, CIFS_HMAC_MD5_HASH_SIZE)) { @@ -173,12 +174,12 @@ int ksmbd_auth_ntlmv2(struct ksmbd_conn *conn, struct ksmbd_session *sess, goto out; } - memcpy(sess->sess_key, sess_key, sizeof(sess_key)); + memcpy(sess_key, base_key, sizeof(base_key)); rc = 0; out: memzero_explicit(ntlmv2_hash, sizeof(ntlmv2_hash)); memzero_explicit(ntlmv2_rsp, sizeof(ntlmv2_rsp)); - memzero_explicit(sess_key, sizeof(sess_key)); + memzero_explicit(base_key, sizeof(base_key)); return rc; } @@ -189,12 +190,13 @@ int ksmbd_auth_ntlmv2(struct ksmbd_conn *conn, struct ksmbd_session *sess, * @blob_len: length of the @authblob message * @conn: connection * @sess: session of connection + * @sess_key: derived session key output buffer * * Return: 0 on success, error number on error */ int ksmbd_decode_ntlmssp_auth_blob(struct authenticate_message *authblob, int blob_len, struct ksmbd_conn *conn, - struct ksmbd_session *sess) + struct ksmbd_session *sess, char *sess_key) { char *domain_name; unsigned int nt_off, dn_off; @@ -234,7 +236,7 @@ int ksmbd_decode_ntlmssp_auth_blob(struct authenticate_message *authblob, ret = ksmbd_auth_ntlmv2(conn, sess, (struct ntlmv2_resp *)((char *)authblob + nt_off), nt_len - CIFS_ENCPWD_SIZE, - domain_name, conn->ntlmssp.cryptkey); + domain_name, conn->ntlmssp.cryptkey, sess_key); kfree(domain_name); if (ret) return ret; @@ -257,8 +259,8 @@ int ksmbd_decode_ntlmssp_auth_blob(struct authenticate_message *authblob, if (!ctx_arc4) return -ENOMEM; - arc4_setkey(ctx_arc4, sess->sess_key, SMB2_NTLMV2_SESSKEY_SIZE); - arc4_crypt(ctx_arc4, sess->sess_key, + arc4_setkey(ctx_arc4, sess_key, SMB2_NTLMV2_SESSKEY_SIZE); + arc4_crypt(ctx_arc4, sess_key, (char *)authblob + sess_key_off, sess_key_len); kfree_sensitive(ctx_arc4); } @@ -400,7 +402,8 @@ ksmbd_build_ntlmssp_challenge_blob(struct challenge_message *chgblob, #ifdef CONFIG_SMB_SERVER_KERBEROS5 int ksmbd_krb5_authenticate(struct ksmbd_session *sess, char *in_blob, - int in_len, char *out_blob, int *out_len) + int in_len, char *out_blob, int *out_len, + char *sess_key) { struct ksmbd_spnego_authen_response *resp; struct ksmbd_login_response_ext *resp_ext = NULL; @@ -448,14 +451,14 @@ int ksmbd_krb5_authenticate(struct ksmbd_session *sess, char *in_blob, } else { if (!ksmbd_compare_user(sess->user, user)) { ksmbd_debug(AUTH, "different user tried to reuse session\n"); - retval = -EPERM; + retval = -EKEYREJECTED; ksmbd_free_user(user); goto out; } ksmbd_free_user(user); } - memcpy(sess->sess_key, resp->payload, resp->session_key_len); + memcpy(sess_key, resp->payload, resp->session_key_len); memcpy(out_blob, resp->payload + resp->session_key_len, resp->spnego_blob_len); *out_len = resp->spnego_blob_len; @@ -466,7 +469,8 @@ int ksmbd_krb5_authenticate(struct ksmbd_session *sess, char *in_blob, } #else int ksmbd_krb5_authenticate(struct ksmbd_session *sess, char *in_blob, - int in_len, char *out_blob, int *out_len) + int in_len, char *out_blob, int *out_len, + char *sess_key) { return -EOPNOTSUPP; } @@ -525,7 +529,7 @@ struct derivation { bool binding; }; -static void generate_key(struct ksmbd_conn *conn, struct ksmbd_session *sess, +static void generate_key(struct ksmbd_conn *conn, const char *sess_key, struct kvec label, struct kvec context, __u8 *key, unsigned int key_size) { @@ -536,7 +540,7 @@ static void generate_key(struct ksmbd_conn *conn, struct ksmbd_session *sess, unsigned char prfhash[SMB2_HMACSHA256_SIZE]; struct hmac_sha256_ctx ctx; - hmac_sha256_init_usingrawkey(&ctx, sess->sess_key, + hmac_sha256_init_usingrawkey(&ctx, sess_key, SMB2_NTLMV2_SESSKEY_SIZE); hmac_sha256_update(&ctx, i, 4); hmac_sha256_update(&ctx, label.iov_base, label.iov_len); @@ -559,18 +563,21 @@ static int generate_smb3signingkey(struct ksmbd_session *sess, const struct derivation *signing) { struct channel *chann; - char *key; + char *key, *sess_key; chann = lookup_chann_list(sess, conn); if (!chann) return 0; - if (conn->dialect >= SMB30_PROT_ID && signing->binding) + if (conn->dialect >= SMB30_PROT_ID && signing->binding) { key = chann->smb3signingkey; - else + sess_key = chann->sess_key; + } else { key = sess->smb3signingkey; + sess_key = sess->sess_key; + } - generate_key(conn, sess, signing->label, signing->context, key, + generate_key(conn, sess_key, signing->label, signing->context, key, SMB3_SIGN_KEY_SIZE); if (!(conn->dialect >= SMB30_PROT_ID && signing->binding)) @@ -627,11 +634,11 @@ static void generate_smb3encryptionkey(struct ksmbd_conn *conn, struct ksmbd_session *sess, const struct derivation_twin *ptwin) { - generate_key(conn, sess, ptwin->encryption.label, + generate_key(conn, sess->sess_key, ptwin->encryption.label, ptwin->encryption.context, sess->smb3encryptionkey, SMB3_ENC_DEC_KEY_SIZE); - generate_key(conn, sess, ptwin->decryption.label, + generate_key(conn, sess->sess_key, ptwin->decryption.label, ptwin->decryption.context, sess->smb3decryptionkey, SMB3_ENC_DEC_KEY_SIZE); diff --git a/fs/smb/server/auth.h b/fs/smb/server/auth.h index 5767aabc63c9..f14b7c033264 100644 --- a/fs/smb/server/auth.h +++ b/fs/smb/server/auth.h @@ -41,17 +41,18 @@ int ksmbd_crypt_message(struct ksmbd_work *work, struct kvec *iov, void ksmbd_copy_gss_neg_header(void *buf); int ksmbd_auth_ntlmv2(struct ksmbd_conn *conn, struct ksmbd_session *sess, struct ntlmv2_resp *ntlmv2, int blen, char *domain_name, - char *cryptkey); + char *cryptkey, char *sess_key); int ksmbd_decode_ntlmssp_auth_blob(struct authenticate_message *authblob, int blob_len, struct ksmbd_conn *conn, - struct ksmbd_session *sess); + struct ksmbd_session *sess, char *sess_key); int ksmbd_decode_ntlmssp_neg_blob(struct negotiate_message *negblob, int blob_len, struct ksmbd_conn *conn); unsigned int ksmbd_build_ntlmssp_challenge_blob(struct challenge_message *chgblob, struct ksmbd_conn *conn); int ksmbd_krb5_authenticate(struct ksmbd_session *sess, char *in_blob, - int in_len, char *out_blob, int *out_len); + int in_len, char *out_blob, int *out_len, + char *sess_key); void ksmbd_sign_smb2_pdu(struct ksmbd_conn *conn, char *key, struct kvec *iov, int n_vec, char *sig); void ksmbd_sign_smb3_pdu(struct ksmbd_conn *conn, char *key, struct kvec *iov, diff --git a/fs/smb/server/mgmt/user_session.c b/fs/smb/server/mgmt/user_session.c index de58aed76cb4..d6331184ebfc 100644 --- a/fs/smb/server/mgmt/user_session.c +++ b/fs/smb/server/mgmt/user_session.c @@ -255,7 +255,7 @@ static void free_channel_list(struct ksmbd_session *sess) down_write(&sess->chann_lock); xa_for_each(&sess->ksmbd_chann_list, index, chann) { xa_erase(&sess->ksmbd_chann_list, index); - kfree(chann); + kfree_sensitive(chann); } xa_destroy(&sess->ksmbd_chann_list); @@ -449,7 +449,7 @@ static int ksmbd_chann_del(struct ksmbd_conn *conn, struct ksmbd_session *sess) if (!chann) return -ENOENT; - kfree(chann); + kfree_sensitive(chann); return 0; } diff --git a/fs/smb/server/mgmt/user_session.h b/fs/smb/server/mgmt/user_session.h index 6aebd385be84..8893a9aaede7 100644 --- a/fs/smb/server/mgmt/user_session.h +++ b/fs/smb/server/mgmt/user_session.h @@ -19,6 +19,7 @@ struct ksmbd_file_table; struct channel { + char sess_key[SMB2_NTLMV2_SESSKEY_SIZE]; __u8 smb3signingkey[SMB3_SIGN_KEY_SIZE]; struct ksmbd_conn *conn; }; diff --git a/fs/smb/server/server.c b/fs/smb/server/server.c index 36a5ea4828ad..f5baba934840 100644 --- a/fs/smb/server/server.c +++ b/fs/smb/server/server.c @@ -199,6 +199,12 @@ static void __handle_ksmbd_work(struct ksmbd_work *work, else conn->ops->set_rsp_status(work, STATUS_USER_SESSION_DELETED); + if (conn->ops->is_sign_req(work, conn->ops->get_cmd_val(work))) { + struct smb2_hdr *rsp_hdr; + + rsp_hdr = ksmbd_resp_buf_curr(work); + rsp_hdr->Flags |= SMB2_FLAGS_SIGNED; + } goto send; } else if (rc > 0) { rc = conn->ops->get_ksmbd_tcon(work); @@ -237,8 +243,14 @@ static void __handle_ksmbd_work(struct ksmbd_work *work, if (work->sess && (work->sess->sign || smb3_11_final_sess_setup_resp(work) || - conn->ops->is_sign_req(work, command))) - conn->ops->set_sign_rsp(work); + conn->ops->is_sign_req(work, command))) { + if (command == SMB2_SESSION_SETUP_HE && + work->sess->dialect >= SMB30_PROT_ID && + conn->dialect < SMB30_PROT_ID) + smb3_set_sign_rsp(work); + else + conn->ops->set_sign_rsp(work); + } } while (is_chained == true); send: diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 097f51fc7ed6..b73167785e87 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -61,6 +61,9 @@ static void __wbuf(struct ksmbd_work *work, void **req, void **rsp) (FILE_ATTRIBUTE_MASK & ~(FILE_ATTRIBUTE_INTEGRITY_STREAM | \ FILE_ATTRIBUTE_NO_SCRUB_DATA)) +/* Windows reports automatic write-time updates at roughly 15 ms resolution. */ +#define KSMBD_WRITE_TIME_RESOLUTION (15ULL * 10000) + /** * check_session_id() - check for valid session id in smb header * @conn: connection instance @@ -95,6 +98,47 @@ struct channel *lookup_chann_list(struct ksmbd_session *sess, struct ksmbd_conn return chann; } +#define KSMBD_MAX_CHANNELS 32 + +static int register_session_channel(struct ksmbd_session *sess, + struct ksmbd_conn *conn, + const char *sess_key) +{ + struct channel *chann, *old; + unsigned long index; + unsigned int count = 0; + int rc = 0; + + down_write(&sess->chann_lock); + if (xa_load(&sess->ksmbd_chann_list, (long)conn)) + goto out; + + xa_for_each(&sess->ksmbd_chann_list, index, chann) + count++; + if (count >= KSMBD_MAX_CHANNELS) { + rc = -ENOSPC; + goto out; + } + + chann = kmalloc_obj(struct channel, KSMBD_DEFAULT_GFP); + if (!chann) { + rc = -ENOMEM; + goto out; + } + + chann->conn = conn; + memcpy(chann->sess_key, sess_key, sizeof(chann->sess_key)); + old = xa_store(&sess->ksmbd_chann_list, (long)conn, chann, + KSMBD_DEFAULT_GFP); + if (xa_is_err(old)) { + kfree_sensitive(chann); + rc = xa_err(old); + } +out: + up_write(&sess->chann_lock); + return rc; +} + /** * smb2_get_ksmbd_tcon() - get tree connection information using a tree id. * @work: smb work @@ -1644,9 +1688,11 @@ static int ntlm_authenticate(struct ksmbd_work *work, { struct ksmbd_conn *conn = work->conn; struct ksmbd_session *sess = work->sess; - struct channel *chann = NULL, *old; struct ksmbd_user *user; + char channel_key[SMB2_NTLMV2_SESSKEY_SIZE] = {}; + char *auth_key = conn->binding ? channel_key : sess->sess_key; u64 prev_id; + bool binding = conn->binding; int sz, rc; ksmbd_debug(SMB, "authenticate phase\n"); @@ -1688,7 +1734,7 @@ static int ntlm_authenticate(struct ksmbd_work *work, if (!ksmbd_compare_user(sess->user, user)) { ksmbd_free_user(user); - return -EPERM; + return -EKEYREJECTED; } ksmbd_free_user(user); } else { @@ -1705,11 +1751,13 @@ static int ntlm_authenticate(struct ksmbd_work *work, sz = conn->mechTokenLen; else sz = le16_to_cpu(req->SecurityBufferLength); - rc = ksmbd_decode_ntlmssp_auth_blob(authblob, sz, conn, sess); + rc = ksmbd_decode_ntlmssp_auth_blob(authblob, sz, conn, sess, + auth_key); if (rc) { set_user_flag(sess->user, KSMBD_USER_FLAG_BAD_PASSWORD); ksmbd_debug(SMB, "authentication failed\n"); - return -EPERM; + rc = -EPERM; + goto out; } } @@ -1744,37 +1792,30 @@ static int ntlm_authenticate(struct ksmbd_work *work, binding_session: if (conn->dialect >= SMB30_PROT_ID) { - chann = lookup_chann_list(sess, conn); - if (!chann) { - chann = kmalloc_obj(struct channel, KSMBD_DEFAULT_GFP); - if (!chann) - return -ENOMEM; - - chann->conn = conn; - down_write(&sess->chann_lock); - old = xa_store(&sess->ksmbd_chann_list, (long)conn, chann, - KSMBD_DEFAULT_GFP); - up_write(&sess->chann_lock); - if (xa_is_err(old)) { - kfree(chann); - return xa_err(old); - } - } + rc = register_session_channel(sess, conn, auth_key); + if (rc) + goto out; } if (conn->ops->generate_signingkey) { rc = conn->ops->generate_signingkey(sess, conn); if (rc) { ksmbd_debug(SMB, "SMB3 signing key generation failed\n"); - return -EINVAL; + rc = -EINVAL; + goto out; } } if (!ksmbd_conn_lookup_dialect(conn)) { pr_err("fail to verify the dialect\n"); - return -ENOENT; + rc = -ENOENT; + goto out; } - return 0; + rc = 0; +out: + if (binding) + memzero_explicit(channel_key, sizeof(channel_key)); + return rc; } #ifdef CONFIG_SMB_SERVER_KERBEROS5 @@ -1785,8 +1826,10 @@ static int krb5_authenticate(struct ksmbd_work *work, struct ksmbd_conn *conn = work->conn; struct ksmbd_session *sess = work->sess; char *in_blob, *out_blob; - struct channel *chann = NULL, *old; + char channel_key[SMB2_NTLMV2_SESSKEY_SIZE] = {}; + char *auth_key = conn->binding ? channel_key : sess->sess_key; u64 prev_sess_id; + bool binding = conn->binding; int in_len, out_len; int retval; @@ -1799,10 +1842,12 @@ static int krb5_authenticate(struct ksmbd_work *work, (le16_to_cpu(rsp->SecurityBufferOffset) + 4); retval = ksmbd_krb5_authenticate(sess, in_blob, in_len, - out_blob, &out_len); + out_blob, &out_len, auth_key); if (retval) { ksmbd_debug(SMB, "krb5 authentication failed\n"); - return -EINVAL; + if (retval != -EKEYREJECTED) + retval = -EINVAL; + goto out; } /* Check previous session */ @@ -1839,37 +1884,30 @@ static int krb5_authenticate(struct ksmbd_work *work, binding_session: if (conn->dialect >= SMB30_PROT_ID) { - chann = lookup_chann_list(sess, conn); - if (!chann) { - chann = kmalloc_obj(struct channel, KSMBD_DEFAULT_GFP); - if (!chann) - return -ENOMEM; - - chann->conn = conn; - down_write(&sess->chann_lock); - old = xa_store(&sess->ksmbd_chann_list, (long)conn, - chann, KSMBD_DEFAULT_GFP); - up_write(&sess->chann_lock); - if (xa_is_err(old)) { - kfree(chann); - return xa_err(old); - } - } + retval = register_session_channel(sess, conn, auth_key); + if (retval) + goto out; } if (conn->ops->generate_signingkey) { retval = conn->ops->generate_signingkey(sess, conn); if (retval) { ksmbd_debug(SMB, "SMB3 signing key generation failed\n"); - return -EINVAL; + retval = -EINVAL; + goto out; } } if (!ksmbd_conn_lookup_dialect(conn)) { pr_err("fail to verify the dialect\n"); - return -ENOENT; + retval = -ENOENT; + goto out; } - return 0; + retval = 0; +out: + if (binding) + memzero_explicit(channel_key, sizeof(channel_key)); + return retval; } #else static int krb5_authenticate(struct ksmbd_work *work, @@ -1975,12 +2013,35 @@ int smb2_sess_setup(struct ksmbd_work *work) } else if ((conn->dialect < SMB30_PROT_ID || server_conf.flags & KSMBD_GLOBAL_FLAG_SMB3_MULTICHANNEL) && (req->Flags & SMB2_SESSION_REQ_FLAG_BINDING)) { - sess = NULL; + sess = ksmbd_session_lookup_slowpath(le64_to_cpu(req->hdr.SessionId)); + if (sess) { + int sign_ret; + + work->sess = sess; + if (sess->dialect >= SMB30_PROT_ID) + sign_ret = smb3_check_sign_req(work); + else + sign_ret = smb2_check_sign_req(work); + if (sess->state != SMB2_SESSION_VALID || + !(req->hdr.Flags & SMB2_FLAGS_SIGNED) || + !sign_ret) { + ksmbd_user_session_put(sess); + work->sess = NULL; + sess = NULL; + } + } rc = -EACCES; goto out_err; } else { sess = ksmbd_session_lookup(conn, le64_to_cpu(req->hdr.SessionId)); + if (!sess) { + sess = ksmbd_session_lookup_slowpath(le64_to_cpu(req->hdr.SessionId)); + if (sess && !lookup_chann_list(sess, conn)) { + ksmbd_user_session_put(sess); + sess = NULL; + } + } if (!sess) { rc = -ENOENT; goto out_err; @@ -2091,12 +2152,19 @@ int smb2_sess_setup(struct ksmbd_work *work) rsp->hdr.Status = STATUS_REQUEST_NOT_ACCEPTED; else if (rc == -EFAULT) rsp->hdr.Status = STATUS_NETWORK_SESSION_EXPIRED; - else if (rc == -ENOMEM) + else if (rc == -ENOMEM || rc == -ENOSPC) rsp->hdr.Status = STATUS_INSUFFICIENT_RESOURCES; else if (rc == -EOPNOTSUPP) rsp->hdr.Status = STATUS_NOT_SUPPORTED; + else if (rc == -EKEYREJECTED) + rsp->hdr.Status = STATUS_ACCESS_DENIED; else if (rc) rsp->hdr.Status = STATUS_LOGON_FAILURE; + if ((rsp->hdr.Status == STATUS_USER_SESSION_DELETED || + (rsp->hdr.Status == STATUS_INVALID_PARAMETER && + (req->Flags & SMB2_SESSION_REQ_FLAG_BINDING))) && + (req->hdr.Flags & SMB2_FLAGS_SIGNED)) + rsp->hdr.Flags |= SMB2_FLAGS_SIGNED; if (conn->mechToken) { kfree(conn->mechToken); @@ -2104,6 +2172,17 @@ int smb2_sess_setup(struct ksmbd_work *work) } if (rc < 0) { + if (sess && conn->dialect == SMB311_PROT_ID && + (req->Flags & SMB2_SESSION_REQ_FLAG_BINDING)) { + struct preauth_session *preauth_sess; + + preauth_sess = ksmbd_preauth_session_lookup(conn, sess->id); + if (preauth_sess) { + list_del(&preauth_sess->preauth_entry); + kfree(preauth_sess); + } + } + /* * SecurityBufferOffset should be set to zero * in session setup error response. @@ -2130,8 +2209,16 @@ int smb2_sess_setup(struct ksmbd_work *work) sess->last_active = jiffies; sess->state = SMB2_SESSION_EXPIRED; } - ksmbd_user_session_put(sess); - work->sess = NULL; + /* + * Keep the binding session reference until the response is + * signed and sent. Error responses for a signed binding + * request are signed with the existing session signing key. + */ + if (!(req->Flags & SMB2_SESSION_REQ_FLAG_BINDING) || + work->sess != sess) { + ksmbd_user_session_put(sess); + work->sess = NULL; + } if (try_delay) { ksmbd_conn_set_need_reconnect(conn); ssleep(5); @@ -3943,6 +4030,7 @@ int smb2_open(struct ksmbd_work *work) time = ksmbd_UnixTimeToNT(stat.atime); rsp->LastAccessTime = cpu_to_le64(time); time = ksmbd_UnixTimeToNT(stat.mtime); + fp->open_mtime = time; rsp->LastWriteTime = cpu_to_le64(time); rsp->ChangeTime = cpu_to_le64(fp->change_time); /* @@ -6409,6 +6497,9 @@ int smb2_close(struct ksmbd_work *work) time = ksmbd_UnixTimeToNT(stat.atime); rsp->LastAccessTime = cpu_to_le64(time); time = ksmbd_UnixTimeToNT(stat.mtime); + if (time > fp->open_mtime && + time - fp->open_mtime < KSMBD_WRITE_TIME_RESOLUTION) + time = fp->open_mtime; rsp->LastWriteTime = cpu_to_le64(time); rsp->ChangeTime = cpu_to_le64(fp->change_time); ksmbd_fd_put(work, fp); @@ -7080,6 +7171,8 @@ int smb2_set_info(struct ksmbd_work *work) rsp->hdr.Status = STATUS_INVALID_PARAMETER; else if (rc == -EMSGSIZE) rsp->hdr.Status = STATUS_INFO_LENGTH_MISMATCH; + else if (rc == -ENOSPC || rc == -EFBIG) + rsp->hdr.Status = STATUS_DISK_FULL; else if (rc == -ESHARE) rsp->hdr.Status = STATUS_SHARING_VIOLATION; else if (rc == -ENOENT) @@ -9483,7 +9576,6 @@ bool smb2_is_sign_req(struct ksmbd_work *work, unsigned int command) if ((rcv_hdr2->Flags & SMB2_FLAGS_SIGNED) && command != SMB2_NEGOTIATE_HE && - command != SMB2_SESSION_SETUP_HE && command != SMB2_OPLOCK_BREAK_HE) return true; @@ -9595,9 +9687,13 @@ int smb3_check_sign_req(struct ksmbd_work *work) } else { chann = lookup_chann_list(work->sess, conn); if (!chann) { - return 0; + if (le16_to_cpu(hdr->Command) != SMB2_SESSION_SETUP_HE || + !(hdr->Flags & SMB2_FLAGS_SIGNED)) + return 0; + signing_key = work->sess->smb3signingkey; + } else { + signing_key = chann->smb3signingkey; } - signing_key = chann->smb3signingkey; } if (!signing_key) { @@ -9632,13 +9728,14 @@ void smb3_set_sign_rsp(struct ksmbd_work *work) struct channel *chann; char signature[SMB2_CMACAES_SIZE]; struct kvec *iov; + u16 command = conn->ops->get_cmd_val(work); int n_vec = 1; char *signing_key; hdr = ksmbd_resp_buf_curr(work); - if (conn->binding == false && - le16_to_cpu(hdr->Command) == SMB2_SESSION_SETUP_HE) { + if (command == SMB2_SESSION_SETUP_HE && + (!conn->binding || hdr->Status != STATUS_SUCCESS)) { signing_key = work->sess->smb3signingkey; } else { chann = lookup_chann_list(work->sess, work->conn); diff --git a/fs/smb/server/smbacl.c b/fs/smb/server/smbacl.c index 9c59c8f73b66..67b39b4d218c 100644 --- a/fs/smb/server/smbacl.c +++ b/fs/smb/server/smbacl.c @@ -258,6 +258,7 @@ static int sid_to_id(struct mnt_idmap *idmap, struct smb_sid *psid, uint sidtype, struct smb_fattr *fattr) { + const struct smb_sid *sid_prefix; int rc = -EINVAL; /* @@ -279,6 +280,12 @@ static int sid_to_id(struct mnt_idmap *idmap, kuid_t uid; uid_t id; + /* Only the server domain RID has a local uid representation. */ + sid_prefix = &server_conf.domain_sid; + if (psid->num_subauth != sid_prefix->num_subauth + 1 || + compare_sids(psid, sid_prefix)) + return -EINVAL; + id = le32_to_cpu(psid->sub_auth[psid->num_subauth - 1]); uid = KUIDT_INIT(id); uid = from_vfsuid(idmap, &init_user_ns, VFSUIDT_INIT(uid)); @@ -290,6 +297,12 @@ static int sid_to_id(struct mnt_idmap *idmap, kgid_t gid; gid_t id; + /* Local gids are represented by S-1-22-2-. */ + sid_prefix = &sid_unix_groups; + if (psid->num_subauth != sid_prefix->num_subauth + 1 || + compare_sids(psid, sid_prefix)) + return -EINVAL; + id = le32_to_cpu(psid->sub_auth[psid->num_subauth - 1]); gid = KGIDT_INIT(id); gid = from_vfsgid(idmap, &init_user_ns, VFSGIDT_INIT(gid)); @@ -900,9 +913,9 @@ int parse_sec_desc(struct mnt_idmap *idmap, struct smb_ntsd *pntsd, rc = sid_to_id(idmap, owner_sid_ptr, SIDOWNER, fattr); if (rc) { - pr_err("%s: Error %d mapping Owner SID to uid\n", - __func__, rc); + ksmbd_debug(SMB, "Owner SID has no Unix uid mapping\n"); owner_sid_ptr = NULL; + rc = 0; } } @@ -918,9 +931,9 @@ int parse_sec_desc(struct mnt_idmap *idmap, struct smb_ntsd *pntsd, } rc = sid_to_id(idmap, group_sid_ptr, SIDUNIX_GROUP, fattr); if (rc) { - pr_err("%s: Error %d mapping Group SID to gid\n", - __func__, rc); + ksmbd_debug(SMB, "Group SID has no Unix gid mapping\n"); group_sid_ptr = NULL; + rc = 0; } } diff --git a/fs/smb/server/vfs_cache.h b/fs/smb/server/vfs_cache.h index 287f3e675cd3..b9e27307a26c 100644 --- a/fs/smb/server/vfs_cache.h +++ b/fs/smb/server/vfs_cache.h @@ -105,6 +105,7 @@ struct ksmbd_file { __u64 change_time; __u64 allocation_size; __u64 itime; + __u64 open_mtime; bool is_nt_open; bool attrib_only; diff --git a/include/drm/drm_exec.h b/include/drm/drm_exec.h index 8725ba92ff91..cc2937185a9f 100644 --- a/include/drm/drm_exec.h +++ b/include/drm/drm_exec.h @@ -101,17 +101,6 @@ drm_exec_obj(struct drm_exec *exec, unsigned long index) #define drm_exec_for_each_locked_object_reverse(exec, obj) \ __drm_exec_for_each_locked_object_reverse(exec, obj, __UNIQUE_ID(drm_exec)) -/* - * Helper to drm_exec_until_all_locked(). Don't use directly. - * - * Since labels can't be defined local to the loop's body we use a jump pointer - * to make sure that the retry is only used from within the loop's body. - */ -#define __drm_exec_until_all_locked(exec, _label) \ -_label: \ - for (void *const __maybe_unused __drm_exec_retry_ptr = &&_label; \ - drm_exec_cleanup(exec);) - /** * drm_exec_until_all_locked - loop until all GEM objects are locked * @exec: drm_exec object @@ -119,9 +108,18 @@ _label: \ * Core functionality of the drm_exec object. Loops until all GEM objects are * locked and no more contention exists. At the beginning of the loop it is * guaranteed that no GEM object is locked. + * + * A global label name drm_exec_retry is used, if you need to use more than one + * instance of this macro in the same function the label needs to be made local + * to the block with the __label__ keyword. */ #define drm_exec_until_all_locked(exec) \ - __drm_exec_until_all_locked(exec, __UNIQUE_ID(drm_exec)) + for (bool const __maybe_unused __drm_exec_loop = false; \ + drm_exec_cleanup(exec);) \ + if (false) { \ +drm_exec_retry: __maybe_unused; \ + continue; \ + } else /** * drm_exec_retry_on_contention - restart the loop to grap all locks @@ -129,12 +127,14 @@ _label: \ * * Control flow helper to continue when a contention was detected and we need to * clean up and re-start the loop to prepare all GEM objects. + * The __drm_exec_loop check exists to prevent usage outside of an + * drm_exec_until_all_locked() loop. */ #define drm_exec_retry_on_contention(exec) \ do { \ if (unlikely(drm_exec_is_contended(exec))) \ - goto *__drm_exec_retry_ptr; \ - } while (0) + goto drm_exec_retry; \ + } while (__drm_exec_loop) /** * drm_exec_is_contended - check for contention @@ -154,12 +154,14 @@ static inline bool drm_exec_is_contended(struct drm_exec *exec) * * Unconditionally retry the loop to lock all objects. For consistency, * the exec object needs to be newly initialized. + * The __drm_exec_loop check exists to prevent usage outside of an + * drm_exec_until_all_locked() loop. */ #define drm_exec_retry(_exec) \ do { \ WARN_ON((_exec)->contended != DRM_EXEC_DUMMY); \ - goto *__drm_exec_retry_ptr; \ - } while (0) + goto drm_exec_retry; \ + } while (__drm_exec_loop) /** * drm_exec_ticket - return the ww_acquire_ctx for this exec context diff --git a/include/linux/damon.h b/include/linux/damon.h index 6f7edb3590ef..02ac34537df9 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -843,11 +843,13 @@ struct damon_attrs { * including damon_call() and damos_walk(). * * @ops: Set of monitoring operations for given use cases. + * @probes: Head of probes (&damon_probe) list. * @addr_unit: Scale factor for core to ops address conversion. * @min_region_sz: Minimum region size. * @pause: Pause kdamond main loop. * @adaptive_targets: Head of monitoring targets (&damon_target) list. * @schemes: Head of schemes (&damos) list. + * @rnd_state: Per-ctx PRNG state for damon_rand(). */ struct damon_ctx { struct damon_attrs attrs; @@ -905,7 +907,6 @@ struct damon_ctx { struct list_head adaptive_targets; struct list_head schemes; - /* Per-ctx PRNG state for damon_rand(); kdamond is the sole consumer. */ struct rnd_state rnd_state; }; @@ -1065,9 +1066,13 @@ static inline bool damon_target_has_pid(const struct damon_ctx *ctx) static inline unsigned int damon_max_nr_accesses(const struct damon_attrs *attrs) { - /* {aggr,sample}_interval are unsigned long, hence could overflow */ - return min(attrs->aggr_interval / attrs->sample_interval, + unsigned long sample_interval; + unsigned long max_nr_accesses; + + sample_interval = attrs->sample_interval ? : 1; + max_nr_accesses = min(attrs->aggr_interval / sample_interval, (unsigned long)UINT_MAX); + return max_nr_accesses ? : 1; } diff --git a/include/linux/fs.h b/include/linux/fs.h index d10897b3a1e3..50ce731a2b78 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2444,6 +2444,11 @@ static inline struct mnt_idmap *file_mnt_idmap(const struct file *file) return mnt_idmap(file->f_path.mnt); } +static inline bool file_owner_or_capable(const struct file *file) +{ + return inode_owner_or_capable(file_mnt_idmap(file), file_inode(file)); +} + /** * is_idmapped_mnt - check whether a mount is mapped * @mnt: the mount to check diff --git a/include/linux/glob.h b/include/linux/glob.h index 861327b33e41..91595e750936 100644 --- a/include/linux/glob.h +++ b/include/linux/glob.h @@ -6,5 +6,6 @@ #include /* For __pure */ bool __pure glob_match(char const *pat, char const *str); +bool __pure glob_match_len(char const *pat, char const *str, size_t len); #endif /* _LINUX_GLOB_H */ diff --git a/include/linux/hid-sensor-hub.h b/include/linux/hid-sensor-hub.h index e71056553108..ab5cc8db3fbb 100644 --- a/include/linux/hid-sensor-hub.h +++ b/include/linux/hid-sensor-hub.h @@ -43,6 +43,8 @@ struct hid_sensor_hub_attribute_info { * @attr_usage_id: Usage Id of a field, e.g. X-axis for a gyro. * @raw_size: Response size for a read request. * @raw_data: Place holder for received response. + * @index: Current write index into raw_data for multi-byte reads. + * @max_raw_size: Total buffer size for multi-byte reads; 0 for single-value reads. */ struct sensor_hub_pending { bool status; @@ -51,6 +53,8 @@ struct sensor_hub_pending { u32 attr_usage_id; int raw_size; u8 *raw_data; + u32 index; + u32 max_raw_size; }; /** @@ -183,6 +187,27 @@ int sensor_hub_input_attr_get_raw_value(struct hid_sensor_hub_device *hsdev, bool is_signed ); +/** + * sensor_hub_input_attr_read_values() - Synchronous multi-byte read request + * @hsdev: Hub device instance. + * @usage_id: Attribute usage id of parent physical device as per spec + * @attr_usage_id: Attribute usage id as per spec + * @report_id: Report id to look for + * @flag: Synchronous or asynchronous read + * @buffer_size: Size of the buffer in bytes + * @buffer: Buffer to store the read data + * + * Issues a synchronous or asynchronous read request for an input attribute, + * accumulating data into the provided buffer until it is full. + * Return: 0 on success, -ETIMEDOUT if the device did not respond, or a + * negative error code. + */ +int sensor_hub_input_attr_read_values(struct hid_sensor_hub_device *hsdev, + u32 usage_id, u32 attr_usage_id, + u32 report_id, + enum sensor_hub_read_flags flag, + u32 buffer_size, u8 *buffer); + /** * sensor_hub_set_feature() - Feature set request * @hsdev: Hub device instance. diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index dccbeb25f701..6032eea2539a 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -293,6 +293,11 @@ static inline void in_dev_put(struct in_device *idev) #define __in_dev_put(idev) refcount_dec(&(idev)->refcnt) #define in_dev_hold(idev) refcount_inc(&(idev)->refcnt) +static inline bool in_dev_hold_safe(struct in_device *idev) +{ + return refcount_inc_not_zero(&idev->refcnt); +} + #endif /* __KERNEL__ */ static __inline__ __be32 inet_make_mask(int logmask) diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h index 61e876e255e8..f23d4b218da0 100644 --- a/include/linux/page_ext.h +++ b/include/linux/page_ext.h @@ -120,14 +120,18 @@ struct page_ext_iter { * page_ext_iter_begin() - Prepare for iterating through page extensions. * @iter: page extension iterator. * @pfn: PFN of the page we're interested in. + * @count: maximum number of page extensions to return. * * Must be called with RCU read lock taken. * * Return: NULL if no page_ext exists for this page. */ static inline struct page_ext *page_ext_iter_begin(struct page_ext_iter *iter, - unsigned long pfn) + unsigned long pfn, unsigned long count) { + if (!count) + return NULL; + iter->index = 0; iter->start_pfn = pfn; iter->page_ext = page_ext_lookup(pfn); @@ -138,19 +142,22 @@ static inline struct page_ext *page_ext_iter_begin(struct page_ext_iter *iter, /** * page_ext_iter_next() - Get next page extension * @iter: page extension iterator. + * @count: maximum number of page extensions to return. * * Must be called with RCU read lock taken. * * Return: NULL if no next page_ext exists. */ -static inline struct page_ext *page_ext_iter_next(struct page_ext_iter *iter) +static inline struct page_ext *page_ext_iter_next(struct page_ext_iter *iter, + unsigned long count) { unsigned long pfn; if (WARN_ON_ONCE(!iter->page_ext)) return NULL; - iter->index++; + if (++iter->index >= count) + return NULL; pfn = iter->start_pfn + iter->index; if (page_ext_iter_next_fast_possible(pfn)) @@ -183,9 +190,9 @@ static inline struct page_ext *page_ext_iter_get(const struct page_ext_iter *ite * IMPORTANT: must be called with RCU read lock taken. */ #define for_each_page_ext(__page, __pgcount, __page_ext, __iter) \ - for (__page_ext = page_ext_iter_begin(&__iter, page_to_pfn(__page));\ - __page_ext && __iter.index < __pgcount; \ - __page_ext = page_ext_iter_next(&__iter)) + for (__page_ext = page_ext_iter_begin(&__iter, page_to_pfn(__page), __pgcount); \ + __page_ext; \ + __page_ext = page_ext_iter_next(&__iter, __pgcount)) #else /* !CONFIG_PAGE_EXTENSION */ struct page_ext; diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index f8b406b0a1af..3c2b8c355ab3 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -190,6 +190,7 @@ int rpc_switch_client_transport(struct rpc_clnt *, const struct rpc_timeout *); void rpc_shutdown_client(struct rpc_clnt *); +void rpc_hold_client(struct rpc_clnt *); void rpc_release_client(struct rpc_clnt *); void rpc_task_release_transport(struct rpc_task *); void rpc_task_release_client(struct rpc_task *); diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 4a0c36f40fe2..e0d838c9ce93 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -292,13 +292,18 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) { \ } \ static inline bool \ + __trace_##name##_enabled(void) \ + { \ + return static_branch_unlikely(&__tracepoint_##name.key);\ + } \ + static inline bool \ trace_##name##_enabled(void) \ { \ if (IS_ENABLED(CONFIG_LOCKDEP)) { \ WARN_ONCE(!rcu_is_watching(), \ "RCU not watching for tracepoint"); \ } \ - return static_branch_unlikely(&__tracepoint_##name.key);\ + return __trace_##name##_enabled(); \ } #define __DECLARE_TRACE(name, proto, args, cond, data_proto) \ @@ -457,6 +462,11 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) { \ } \ static inline bool \ + __trace_##name##_enabled(void) \ + { \ + return false; \ + } \ + static inline bool \ trace_##name##_enabled(void) \ { \ return false; \ diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 539bbbe54b14..8ced27a8229b 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -446,6 +446,11 @@ static inline void in6_dev_hold(struct inet6_dev *idev) refcount_inc(&idev->refcnt); } +static inline bool in6_dev_hold_safe(struct inet6_dev *idev) +{ + return refcount_inc_not_zero(&idev->refcnt); +} + /* called with rcu_read_lock held */ static inline bool ip6_ignore_linkdown(const struct net_device *dev) { diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 38186a245f14..50f0eef71fb1 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -3413,8 +3413,9 @@ static inline struct hci_iso_hdr *hci_iso_hdr(const struct sk_buff *skb) #define hci_iso_flags_pack(pb, ts) ((pb & 0x03) | ((ts & 0x01) << 2)) /* ISO data length and flags pack/unpack */ -#define hci_iso_data_len_pack(h, f) ((__u16) ((h) | ((f) << 14))) -#define hci_iso_data_len(h) ((h) & 0x3fff) +#define hci_iso_data_len_pack(h, f) ((__u16) (((h) & 0x0fff) | \ + (((f) & 0x3) << 14))) +#define hci_iso_data_len(h) ((h) & 0x0fff) #define hci_iso_data_flags(h) ((h) >> 14) /* codec transport types */ diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 7e15da47fe3a..4ca09298e11a 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -985,6 +985,7 @@ enum { HCI_CONN_AUTH_FAILURE, HCI_CONN_PER_ADV, HCI_CONN_BIG_CREATED, + HCI_CONN_CREATE, HCI_CONN_CREATE_CIS, HCI_CONN_CREATE_BIG_SYNC, HCI_CONN_BIG_SYNC, diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h index 1640cc9bf83a..ef6ce1c20a4f 100644 --- a/include/net/bluetooth/l2cap.h +++ b/include/net/bluetooth/l2cap.h @@ -617,7 +617,8 @@ struct l2cap_chan { struct l2cap_ops { char *name; - struct l2cap_chan *(*new_connection) (struct l2cap_chan *chan); + int (*new_connection)(struct l2cap_chan *chan, + struct l2cap_chan *new_chan); int (*recv) (struct l2cap_chan * chan, struct sk_buff *skb); void (*teardown) (struct l2cap_chan *chan, int err); @@ -882,9 +883,10 @@ static inline __u16 __next_seq(struct l2cap_chan *chan, __u16 seq) return (seq + 1) % (chan->tx_win_max + 1); } -static inline struct l2cap_chan *l2cap_chan_no_new_connection(struct l2cap_chan *chan) +static inline int l2cap_chan_no_new_connection(struct l2cap_chan *chan, + struct l2cap_chan *new_chan) { - return NULL; + return -EOPNOTSUPP; } static inline int l2cap_chan_no_recv(struct l2cap_chan *chan, struct sk_buff *skb) @@ -961,7 +963,7 @@ int l2cap_chan_send(struct l2cap_chan *chan, struct msghdr *msg, size_t len, void l2cap_chan_busy(struct l2cap_chan *chan, int busy); void l2cap_chan_rx_avail(struct l2cap_chan *chan, ssize_t rx_avail); int l2cap_chan_check_security(struct l2cap_chan *chan, bool initiator); -void l2cap_chan_set_defaults(struct l2cap_chan *chan); +void l2cap_chan_set_defaults(struct l2cap_chan *chan, struct l2cap_chan *pchan); int l2cap_ertm_init(struct l2cap_chan *chan); void l2cap_chan_add(struct l2cap_conn *conn, struct l2cap_chan *chan); void __l2cap_chan_add(struct l2cap_conn *conn, struct l2cap_chan *chan); diff --git a/include/net/gue.h b/include/net/gue.h index dfca298bec9c..caefd6da8693 100644 --- a/include/net/gue.h +++ b/include/net/gue.h @@ -80,7 +80,7 @@ static inline size_t guehdr_flags_len(__be16 flags) static inline size_t guehdr_priv_flags_len(__be32 flags) { - return 0; + return (flags & GUE_PFLAG_REMCSUM) ? GUE_PLEN_REMCSUM : 0; } /* Validate standard and private flags. Returns non-zero (meaning invalid) diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 49297fec448a..417ff51f62fc 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -752,7 +752,8 @@ struct ip_vs_protocol { void (*state_transition)(struct ip_vs_conn *cp, int direction, const struct sk_buff *skb, - struct ip_vs_proto_data *pd); + struct ip_vs_proto_data *pd, + unsigned int iph_len); int (*register_app)(struct netns_ipvs *ipvs, struct ip_vs_app *inc); diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h index 13c87baf018e..04acb6791dbd 100644 --- a/include/net/mana/mana.h +++ b/include/net/mana/mana.h @@ -305,6 +305,14 @@ struct mana_recv_buf_oob { void *buf_va; bool from_pool; /* allocated from a page pool */ + /* head page of the page_pool fragment; valid only when + * from_pool && frag_count > 1. + */ + struct page *pp_page; + /* Fragment offset plus rxq->headroom, passed to + * page_pool_dma_sync_for_cpu(). + */ + u32 dma_sync_offset; /* SGL of the buffer going to be sent as part of the work request. */ u32 num_sge; diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index 7b23b245a5a8..ce414118962f 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -155,11 +155,12 @@ struct flow_offload_tuple { tun_num:2, in_vlan_ingress:2; u16 mtu; + u32 dst_cookie; + struct dst_entry *dst_cache; + union { struct { - struct dst_entry *dst_cache; u32 ifidx; - u32 dst_cookie; }; struct { u32 ifidx; @@ -357,6 +358,8 @@ static inline int nf_flow_register_bpf(void) void nf_flow_offload_add(struct nf_flowtable *flowtable, struct flow_offload *flow); +void nf_flow_offload_refresh(struct nf_flowtable *flowtable, + struct flow_offload *flow); void nf_flow_offload_del(struct nf_flowtable *flowtable, struct flow_offload *flow); void nf_flow_offload_stats(struct nf_flowtable *flowtable, diff --git a/include/net/tc_act/tc_pedit.h b/include/net/tc_act/tc_pedit.h index cb7b82f2cbc7..97754ea0a827 100644 --- a/include/net/tc_act/tc_pedit.h +++ b/include/net/tc_act/tc_pedit.h @@ -37,17 +37,15 @@ static inline bool is_tcf_pedit(const struct tc_action *a) return false; } -static inline int tcf_pedit_nkeys(const struct tc_action *a) +/* Must be called with act->tcfa_lock held to ensure consistency of parallel + * reads of the same action's pedit keys (e.g. flow_offload count vs fill). + * Note, this is only used for pedit offload. + */ +static inline int tcf_pedit_nkeys_locked(const struct tc_action *a) { - struct tcf_pedit_parms *parms; - int nkeys; - - rcu_read_lock(); - parms = to_pedit_parms(a); - nkeys = parms->tcfp_nkeys; - rcu_read_unlock(); - - return nkeys; + lockdep_assert_held(&a->tcfa_lock); + return rcu_dereference_protected(to_pedit(a)->parms, + lockdep_is_held(&a->tcfa_lock))->tcfp_nkeys; } static inline u32 tcf_pedit_htype(const struct tc_action *a, int index) diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c index 3cd29477fff2..b6b969b55e12 100644 --- a/io_uring/kbuf.c +++ b/io_uring/kbuf.c @@ -287,8 +287,6 @@ static int io_ring_buffers_peek(struct io_kiocb *req, struct buf_sel_arg *arg, iov = kmalloc_objs(struct iovec, nr_avail); if (unlikely(!iov)) return -ENOMEM; - if (arg->mode & KBUF_MODE_FREE) - kfree(arg->iovs); arg->iovs = iov; nr_iovs = nr_avail; } else if (nr_avail < nr_iovs) { @@ -330,6 +328,9 @@ static int io_ring_buffers_peek(struct io_kiocb *req, struct buf_sel_arg *arg, buf = io_ring_head_to_buf(br, ++head, bl->mask); } while (--nr_iovs); + if (arg->mode & KBUF_MODE_FREE) + kfree(arg->iovs); + if (head == tail) req->flags |= REQ_F_BL_EMPTY; diff --git a/io_uring/memmap.c b/io_uring/memmap.c index da1f6c5d07f8..23e8a85111bc 100644 --- a/io_uring/memmap.c +++ b/io_uring/memmap.c @@ -337,7 +337,7 @@ unsigned long io_uring_get_unmapped_area(struct file *filp, unsigned long addr, ptr = io_uring_validate_mmap_request(filp, pgoff); if (IS_ERR(ptr)) - return -ENOMEM; + return PTR_ERR(ptr); /* * Some architectures have strong cache aliasing requirements. diff --git a/io_uring/msg_ring.c b/io_uring/msg_ring.c index 3ff9098573db..3067c9343991 100644 --- a/io_uring/msg_ring.c +++ b/io_uring/msg_ring.c @@ -93,19 +93,38 @@ static void io_msg_remote_post(struct io_ring_ctx *ctx, struct io_kiocb *req, io_req_task_work_add_remote(req, IOU_F_TWQ_LAZY_WAKE); } +static int io_msg_ring_cqe_flags(struct io_ring_ctx *target_ctx, + const struct io_msg *msg, u32 *flags) +{ + *flags = 0; + + if (!(msg->flags & IORING_MSG_RING_FLAGS_PASS)) + return 0; + + *flags = msg->cqe_flags; + if ((*flags & IORING_CQE_F_32) && + !(target_ctx->flags & (IORING_SETUP_CQE32 | + IORING_SETUP_CQE_MIXED))) + return -EINVAL; + + return 0; +} + static int io_msg_data_remote(struct io_ring_ctx *target_ctx, struct io_msg *msg) { struct io_kiocb *target; - u32 flags = 0; + u32 flags; + int ret; - target = kmem_cache_alloc(req_cachep, GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO) ; + ret = io_msg_ring_cqe_flags(target_ctx, msg, &flags); + if (ret) + return ret; + + target = kmem_cache_alloc(req_cachep, GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO); if (unlikely(!target)) return -ENOMEM; - if (msg->flags & IORING_MSG_RING_FLAGS_PASS) - flags = msg->cqe_flags; - io_msg_remote_post(target_ctx, target, msg->len, flags, msg->user_data); return 0; } @@ -130,8 +149,9 @@ static int __io_msg_ring_data(struct io_ring_ctx *target_ctx, if (io_msg_need_remote(target_ctx)) return io_msg_data_remote(target_ctx, msg); - if (msg->flags & IORING_MSG_RING_FLAGS_PASS) - flags = msg->cqe_flags; + ret = io_msg_ring_cqe_flags(target_ctx, msg, &flags); + if (ret) + return ret; ret = -EOVERFLOW; if (target_ctx->flags & IORING_SETUP_IOPOLL) { diff --git a/io_uring/tw.c b/io_uring/tw.c index a4c872870d81..e6ee15571e85 100644 --- a/io_uring/tw.c +++ b/io_uring/tw.c @@ -139,11 +139,11 @@ void tctx_task_work(struct callback_head *cb) */ static void io_ctx_mark_taskrun(struct io_ring_ctx *ctx) { - if (ctx->flags & IORING_SETUP_TASKRUN_FLAG) { - struct io_rings *rings; + lockdep_assert_in_rcu_read_lock(); + + if (ctx->flags & IORING_SETUP_TASKRUN_FLAG) { + struct io_rings *rings = rcu_dereference(ctx->rings_rcu); - guard(rcu)(); - rings = rcu_dereference(ctx->rings_rcu); atomic_or(IORING_SQ_TASKRUN, &rings->sq_flags); } } @@ -153,6 +153,9 @@ void io_req_local_work_add(struct io_kiocb *req, unsigned flags) struct io_ring_ctx *ctx = req->ctx; int nr_wait; + /* pairs with synchronize_rcu() in io_ring_exit_work() */ + guard(rcu)(); + /* * We don't know how many requests there are in the link and whether * they can even be queued lazily, fall back to non-lazy. diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c index 7b25dcd9d05f..c14c22cff49e 100644 --- a/io_uring/uring_cmd.c +++ b/io_uring/uring_cmd.c @@ -90,7 +90,7 @@ static void io_uring_cmd_del_cancelable(struct io_uring_cmd *cmd, } /* - * Mark this command as concelable, then io_uring_try_cancel_uring_cmd() + * Mark this command as cancelable, then io_uring_try_cancel_uring_cmd() * will try to cancel this issued command by sending ->uring_cmd() with * issue_flags of IO_URING_F_CANCEL. * @@ -168,7 +168,7 @@ void __io_uring_cmd_done(struct io_uring_cmd *ioucmd, s32 ret, u64 res2, } io_req_uring_cleanup(req, issue_flags); if (req->flags & REQ_F_IOPOLL) { - /* order with io_iopoll_req_issued() checking ->iopoll_complete */ + /* order with io_do_iopoll() checking ->iopoll_completed */ smp_store_release(&req->iopoll_completed, 1); } else if (issue_flags & IO_URING_F_COMPLETE_DEFER) { if (WARN_ON_ONCE(issue_flags & IO_URING_F_UNLOCKED)) diff --git a/kernel/audit.c b/kernel/audit.c index dcc657d35776..562476937fa7 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -62,6 +62,7 @@ #include #include #include +#include #include "audit.h" @@ -950,7 +951,7 @@ static int kauditd_thread(void *dummy) * do the multicast send and rotate records from the * main queue to the retry/hold queues */ wait_event_freezable(kauditd_wait, - (skb_queue_len(&audit_queue) ? 1 : 0)); + (skb_queue_len_lockless(&audit_queue) ? 1 : 0)); } return 0; @@ -1283,7 +1284,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh, s.rate_limit = audit_rate_limit; s.backlog_limit = audit_backlog_limit; s.lost = atomic_read(&audit_lost); - s.backlog = skb_queue_len(&audit_queue); + s.backlog = skb_queue_len_lockless(&audit_queue); s.feature_bitmap = AUDIT_FEATURE_BITMAP_ALL; s.backlog_wait_time = audit_backlog_wait_time; s.backlog_wait_time_actual = atomic_read(&audit_backlog_wait_time_actual); @@ -1627,7 +1628,7 @@ static void audit_receive(struct sk_buff *skb) /* can't block with the ctrl lock, so penalize the sender now */ if (audit_backlog_limit && - (skb_queue_len(&audit_queue) > audit_backlog_limit)) { + (skb_queue_len_lockless(&audit_queue) > audit_backlog_limit)) { DECLARE_WAITQUEUE(wait, current); /* wake kauditd to try and flush the queue */ @@ -1933,7 +1934,7 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask, long stime = audit_backlog_wait_time; while (audit_backlog_limit && - (skb_queue_len(&audit_queue) > audit_backlog_limit)) { + (skb_queue_len_lockless(&audit_queue) > audit_backlog_limit)) { /* wake kauditd to try and flush the queue */ wake_up_interruptible(&kauditd_wait); @@ -1953,7 +1954,7 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask, } else { if (audit_rate_check() && printk_ratelimit()) pr_warn("audit_backlog=%d > audit_backlog_limit=%d\n", - skb_queue_len(&audit_queue), + skb_queue_len_lockless(&audit_queue), audit_backlog_limit); audit_log_lost("backlog limit exceeded"); return NULL; @@ -2080,7 +2081,8 @@ void audit_log_format(struct audit_buffer *ab, const char *fmt, ...) void audit_log_n_hex(struct audit_buffer *ab, const unsigned char *buf, size_t len) { - int i, avail, new_len; + int avail; + size_t i, new_len; unsigned char *ptr; struct sk_buff *skb; @@ -2090,7 +2092,12 @@ void audit_log_n_hex(struct audit_buffer *ab, const unsigned char *buf, BUG_ON(!ab->skb); skb = ab->skb; avail = skb_tailroom(skb); - new_len = len<<1; + + if (check_shl_overflow(len, 1, &new_len)) { + audit_log_format(ab, "?"); + return; + } + if (new_len >= avail) { /* Round the buffer request up to the next multiple */ new_len = AUDIT_BUFSIZ*(((new_len-avail)/AUDIT_BUFSIZ) + 1); diff --git a/kernel/events/core.c b/kernel/events/core.c index d7f3e2c2ecb1..ba5bd6a78fe7 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -7150,6 +7150,8 @@ static int map_range(struct perf_buffer *rb, struct vm_area_struct *vma) int err = 0; unsigned long pagenum; + guard(mutex)(&rb->aux_mutex); + /* * We map this as a VM_PFNMAP VMA. * diff --git a/kernel/exit.c b/kernel/exit.c index 1056422bc101..2c0b1c02920f 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -212,7 +212,12 @@ static void __exit_signal(struct release_task_post *post, struct task_struct *ts __unhash_process(post, tsk, group_dead); write_sequnlock(&sig->stats_lock); - tsk->sighand = NULL; + /* + * Ensure that all preceeding state is visible. Pairs with + * the smp_acquire__after_ctrl_dep() in the sighand == NULL + * path of lock_task_sighand(). + */ + smp_store_release(&tsk->sighand, NULL); spin_unlock(&sighand->siglock); __cleanup_sighand(sighand); diff --git a/kernel/signal.c b/kernel/signal.c index 9c2b32c4d755..bbc0fd4cc4d7 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1362,8 +1362,16 @@ struct sighand_struct *lock_task_sighand(struct task_struct *tsk, rcu_read_lock(); for (;;) { sighand = rcu_dereference(tsk->sighand); - if (unlikely(sighand == NULL)) + if (unlikely(sighand == NULL)) { + /* + * Pairs with the smp_store_release() in + * __exit_signal(). It ensures that all state + * modifications to the task preceeding the store are + * visible to the callers of lock_task_sighand(). + */ + smp_acquire__after_ctrl_dep(); break; + } /* * This sighand can be already freed and even reused, but diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index 5e633d8750d1..a7d3e8229c4b 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -461,6 +461,109 @@ static void disarm_timer(struct k_itimer *timer, struct task_struct *p) trigger_base_recalc_expires(timer, p); } +/* + * Lookup the task via timer->it.cpu.pid and attempt to lock the task's sighand. + * + * This can race with the reaping of the task: + * + * CPU0 CPU1 + * + * // Finds task + * p = pid_task(pid, pid_type); __exit_signal(p) + * lock(p, sighand); + * posix_cpu_timers*_exit(); + * sighand = lock_task_sighand(p); unhash_task(p); + * p->sighand = NULL; + * unlock(sighand); + * + * In this case sighand is NULL, which means the task and the associated timer + * queue cannot be longer accessed safely. + * + * __exit_signal() invokes posix_cpu_timers_exit() and if the thread group is + * dead it also invokes posix_cpu_timers_group_exit(). These functions delete + * all pending timers from the related timer queues. The POSIX timers (k_itimer) + * themself are still accessible, but not longer connected to the task. + * + * exec() works slightly differently. The task which exec()'s terminates all + * other threads in the thread group and runs __exit_signal() on them. As the + * thread group is not dead they only clean up the per task timers via + * posix_cpu_timers_exit(). + * + * As the TGID on exec() stays the same per process timers stay queued, if they + * are armed. This works without a problem when exec() is done by the thread + * group leader. If a non-leader thread exec()'s this can end up in the + * following scenario: + * + * CPU0 CPU1 + * // Returns old leader + * p = pid_task(pid, pid_type); de_thread() + * switch_leader() + * release_task(old leader) + * __exit_signal() + * old_leader->sighand = NULL; + * // Returns NULL + * sighand = lock_task_sighand(p) + * + * That's problematic for several functions: + * + * - posix_cpu_timer_del(): If the timer is still enqueued on the task the + * underlying k_itimer will be freed which results in a UAF in + * run_posix_cpu_timers() or on timerqueue related add/delete operations. + * If the timer is not enqueued, the failure is harmless + * + * - posix_cpu_timer_set(): Independent of the enqueued state that results in a + * transient failure which is user space visible (-ESRCH) for regular posix + * timers. But for the use case in do_cpu_nanosleep() it's the same UAF + * problem just that the timer is allocated on the stack. + * + * - posix_cpu_timer_rearm(): Timer is not enqueued at that point, but this + * silently ignores the rearm request, which is a functional problem as the + * timer wont expire anymore. + */ +static struct task_struct *timer_lock_sighand(struct k_itimer *timer, unsigned long *flags) +{ + enum pid_type type = clock_pid_type(timer->it_clock); + struct cpu_timer *ctmr = &timer->it.cpu; + + guard(rcu)(); + + for (;;) { + struct task_struct *t = pid_task(timer->it.cpu.pid, type); + + /* Fail if the task cannot be found. */ + if (!t) + break; + + /* Try to lock the task's sighand */ + if (lock_task_sighand(t, flags)) + return t; + + /* + * The next PID lookup might either fail or return the new + * leader. This is correct for both exit() and exec(). + */ + } + + /* + * If the timer is still enqueued, warn. There is nothing safe to do + * here as there might be two timers in there which are removed in + * parallel and that will cause more damage than good. This should never + * happen! + * + * Ensure that the stores to the timer and timerqueue are visible: + * + * __exit_signal() + * posix_cpu_timers*_exit() + * write_seqlock(seqlock) + * smp_wmb(); <------- + * __unhash_process() | !pid_task() + * ----> smp_rmb(); + * WARN_ON_ONCE(...) + */ + smp_rmb(); + WARN_ON_ONCE(ctmr->head || timerqueue_node_queued(&ctmr->node)); + return NULL; +} /* * Clean up a CPU-clock timer that is about to be destroyed. @@ -470,29 +573,13 @@ static void disarm_timer(struct k_itimer *timer, struct task_struct *p) */ static int posix_cpu_timer_del(struct k_itimer *timer) { - struct cpu_timer *ctmr = &timer->it.cpu; - struct sighand_struct *sighand; struct task_struct *p; unsigned long flags; int ret = 0; - rcu_read_lock(); - p = cpu_timer_task_rcu(timer); - if (!p) - goto out; + p = timer_lock_sighand(timer, &flags); - /* - * Protect against sighand release/switch in exit/exec and process/ - * thread timer list entry concurrent read/writes. - */ - sighand = lock_task_sighand(p, &flags); - if (unlikely(sighand == NULL)) { - /* - * This raced with the reaping of the task. The exit cleanup - * should have removed this timer from the timer queue. - */ - WARN_ON_ONCE(ctmr->head || timerqueue_node_queued(&ctmr->node)); - } else { + if (likely(p)) { if (timer->it.cpu.firing) { /* * Prevent signal delivery. The timer cannot be dequeued @@ -508,11 +595,8 @@ static int posix_cpu_timer_del(struct k_itimer *timer) unlock_task_sighand(p, &flags); } -out: - rcu_read_unlock(); - if (!ret) { - put_pid(ctmr->pid); + put_pid(timer->it.cpu.pid); timer->it_status = POSIX_TIMER_DISARMED; } return ret; @@ -626,21 +710,17 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags, clockid_t clkid = CPUCLOCK_WHICH(timer->it_clock); struct cpu_timer *ctmr = &timer->it.cpu; u64 old_expires, new_expires, now; - struct sighand_struct *sighand; struct task_struct *p; unsigned long flags; int ret = 0; - rcu_read_lock(); - p = cpu_timer_task_rcu(timer); - if (!p) { - /* - * If p has just been reaped, we can no - * longer get any information about it at all. - */ - rcu_read_unlock(); + p = timer_lock_sighand(timer, &flags); + /* + * If p has just been reaped, we can no longer get any information about + * it at all. + */ + if (!p) return -ESRCH; - } /* * Use the to_ktime conversion because that clamps the maximum @@ -648,20 +728,6 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags, */ new_expires = ktime_to_ns(timespec64_to_ktime(new->it_value)); - /* - * Protect against sighand release/switch in exit/exec and p->cpu_timers - * and p->signal->cpu_timers read/write in arm_timer() - */ - sighand = lock_task_sighand(p, &flags); - /* - * If p has just been reaped, we can no - * longer get any information about it at all. - */ - if (unlikely(sighand == NULL)) { - rcu_read_unlock(); - return -ESRCH; - } - /* Retrieve the current expiry time before disarming the timer */ old_expires = cpu_timer_getexpires(ctmr); @@ -698,7 +764,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags, /* Retry if the timer expiry is running concurrently */ if (unlikely(ret)) { unlock_task_sighand(p, &flags); - goto out; + return ret; } /* Convert relative expiry time to absolute */ @@ -733,8 +799,6 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags, */ if (!sigev_none && new_expires && now >= new_expires) cpu_timer_fire(timer); -out: - rcu_read_unlock(); return ret; } @@ -1018,19 +1082,12 @@ static void check_process_timers(struct task_struct *tsk, static bool posix_cpu_timer_rearm(struct k_itimer *timer) { clockid_t clkid = CPUCLOCK_WHICH(timer->it_clock); - struct sighand_struct *sighand; struct task_struct *p; unsigned long flags; u64 now; - guard(rcu)(); - p = cpu_timer_task_rcu(timer); - if (!p) - return true; - - /* Protect timer list r/w in arm_timer() */ - sighand = lock_task_sighand(p, &flags); - if (unlikely(sighand == NULL)) + p = timer_lock_sighand(timer, &flags); + if (unlikely(!p)) return true; /* diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 56a328e94395..804ccae694d2 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -270,7 +270,8 @@ unsigned ring_buffer_event_length(struct ring_buffer_event *event) if (event->type_len > RINGBUF_TYPE_DATA_TYPE_LEN_MAX) return length; length -= RB_EVNT_HDR_SIZE; - if (length > RB_MAX_SMALL_DATA + sizeof(event->array[0])) + if (length > RB_MAX_SMALL_DATA + sizeof(event->array[0]) || + RB_FORCE_8BYTE_ALIGNMENT) length -= sizeof(event->array[0]); return length; } @@ -2329,10 +2330,7 @@ static struct ring_buffer_desc *ring_buffer_desc(struct trace_buffer_desc *trace size_t len; int i; - if (!trace_desc) - return NULL; - - if (cpu >= trace_desc->nr_cpus) + if (!trace_desc || !trace_desc->nr_cpus) return NULL; end = (struct ring_buffer_desc *)((void *)trace_desc + trace_desc->struct_len); @@ -7174,7 +7172,7 @@ int ring_buffer_read_page(struct trace_buffer *buffer, rpos = reader->read; pos += event_size; - if (rpos >= event_size) + if (rpos >= size) break; event = rb_reader_event(cpu_buffer); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 1146b83b711a..18710c190c92 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -87,7 +87,7 @@ void __init disable_tracing_selftest(const char *reason) /* Pipe tracepoints to printk */ static struct trace_iterator *tracepoint_print_iter; -int tracepoint_printk; +static int tracepoint_printk; static bool tracepoint_printk_stop_on_boot __initdata; static bool traceoff_after_boot __initdata; static DEFINE_STATIC_KEY_FALSE(tracepoint_printk_key); @@ -5015,7 +5015,6 @@ int tracing_set_tracer(struct trace_array *tr, const char *buf) RING_BUFFER_ALL_CPUS); if (ret < 0) return ret; - ret = 0; } list_for_each_entry(t, &tr->tracers, list) { diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 609325f57942..6385cd662d8d 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -1056,11 +1056,9 @@ static int regex_match_end(char *str, struct regex *r, int len) return 0; } -static int regex_match_glob(char *str, struct regex *r, int len __maybe_unused) +static int regex_match_glob(char *str, struct regex *r, int len) { - if (glob_match(r->pattern, str)) - return 1; - return 0; + return glob_match_len(r->pattern, str, len) ? 1 : 0; } /** diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c index e6871230bde9..dc15658a887c 100644 --- a/kernel/trace/trace_events_synth.c +++ b/kernel/trace/trace_events_synth.c @@ -839,8 +839,10 @@ static struct synth_field *parse_synth_field(int argc, char **argv, seq_buf_puts(&s, "__data_loc "); seq_buf_puts(&s, field->type); - if (WARN_ON_ONCE(!seq_buf_buffer_left(&s))) + if (WARN_ON_ONCE(!seq_buf_buffer_left(&s))) { + kfree(type); goto free; + } s.buffer[s.len] = '\0'; kfree(field->type); @@ -1446,13 +1448,13 @@ static int __create_synth_event(const char *name, const char *raw_fields) if (cmd_version > 1 && n_fields_this_loop >= 1) { synth_err(SYNTH_ERR_INVALID_CMD, errpos(field_str)); ret = -EINVAL; - goto err_free_arg; + goto err_free_field; } if (n_fields == SYNTH_FIELDS_MAX) { synth_err(SYNTH_ERR_TOO_MANY_FIELDS, 0); ret = -EINVAL; - goto err_free_arg; + goto err_free_field; } fields[n_fields++] = field; @@ -1491,6 +1493,8 @@ static int __create_synth_event(const char *name, const char *raw_fields) kfree(saved_fields); return ret; + err_free_field: + free_synth_field(field); err_free_arg: argv_free(argv); err: diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c index c4ba484f7b38..8c82ecb735f4 100644 --- a/kernel/trace/trace_events_user.c +++ b/kernel/trace/trace_events_user.c @@ -109,6 +109,9 @@ struct user_event_enabler { /* Track enable bit, flags, etc. Aligned for bitops. */ unsigned long values; + + /* Defer the event put and enabler free past an RCU grace period. */ + struct rcu_work put_rwork; }; /* Bits 0-5 are for the bit to update upon enable/disable (0-63 allowed) */ @@ -396,15 +399,37 @@ static struct user_event_group *user_event_group_create(void) return NULL; }; -static void user_event_enabler_destroy(struct user_event_enabler *enabler, - bool locked) +static void delayed_user_event_enabler_put(struct work_struct *work) +{ + struct user_event_enabler *enabler = container_of(to_rcu_work(work), + struct user_event_enabler, put_rwork); + + /* No longer tracking the event via the enabler */ + user_event_put(enabler->event, false); + + /* Run from queue_rcu_work(), the RCU grace period has elapsed */ + kfree(enabler); +} + +static void user_event_enabler_destroy(struct user_event_enabler *enabler) { list_del_rcu(&enabler->mm_enablers_link); - /* No longer tracking the event via the enabler */ - user_event_put(enabler->event, locked); - - kfree(enabler); + /* + * The enabler is removed from an RCU-traversed list + * (user_event_mm_dup() walks mm->enablers under rcu_read_lock() only), + * and readers there dereference enabler->event and take a new ref on + * it. Both the put of that event reference and the free of the enabler + * therefore have to wait for a grace period so no reader can be looking + * at the enabler or racing the last put of its event. + * + * The put itself must not run in RCU context: when it drops the last + * reference user_event_put() takes event_mutex, which cannot be taken + * from a softirq/RCU callback. Defer both to a work item scheduled + * after a grace period via queue_rcu_work(). + */ + INIT_RCU_WORK(&enabler->put_rwork, delayed_user_event_enabler_put); + queue_rcu_work(system_percpu_wq, &enabler->put_rwork); } static int user_event_mm_fault_in(struct user_event_mm *mm, unsigned long uaddr, @@ -464,7 +489,7 @@ static void user_event_enabler_fault_fixup(struct work_struct *work) /* User asked for enabler to be removed during fault */ if (test_bit(ENABLE_VAL_FREEING_BIT, ENABLE_BITOPS(enabler))) { - user_event_enabler_destroy(enabler, true); + user_event_enabler_destroy(enabler); goto out; } @@ -764,7 +789,7 @@ 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, mm_enablers_link) - user_event_enabler_destroy(enabler, false); + user_event_enabler_destroy(enabler); mmdrop(mm->mm); kfree(mm); @@ -2645,7 +2670,7 @@ static long user_events_ioctl_unreg(unsigned long uarg) flags |= enabler->values & ENABLE_VAL_COMPAT_MASK; if (!test_bit(ENABLE_VAL_FAULTING_BIT, ENABLE_BITOPS(enabler))) - user_event_enabler_destroy(enabler, true); + user_event_enabler_destroy(enabler); /* Removed at least one */ ret = 0; diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index f283391a4dc8..cd37f2013758 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -458,12 +458,12 @@ func_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set) ftrace_func_t func; u32 new_flags; - /* Do nothing if already set. */ - if (!!set == !!(tr->current_trace_flags->val & bit)) + /* We can change this flag only when current tracer is function. */ + if (tr->current_trace != &function_trace) return 0; - /* We can change this flag only when not running. */ - if (tr->current_trace != &function_trace) + /* Do nothing if already set. */ + if (!!set == !!(tr->current_trace_flags->val & bit)) return 0; new_flags = (tr->current_trace_flags->val & ~bit) | (set ? bit : 0); diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c index 5e83c4f6f2b4..0e1265acd1cc 100644 --- a/kernel/trace/trace_osnoise.c +++ b/kernel/trace/trace_osnoise.c @@ -179,7 +179,9 @@ static void osnoise_unregister_instance(struct trace_array *tr) if (!found) return; - kvfree_rcu_mightsleep(inst); + /* Do a full sync to ensure that tr remains valid, not just inst */ + synchronize_rcu(); + kvfree(inst); } /* diff --git a/kernel/trace/trace_preemptirq.c b/kernel/trace/trace_preemptirq.c index 0c42b15c3800..b63e3558948f 100644 --- a/kernel/trace/trace_preemptirq.c +++ b/kernel/trace/trace_preemptirq.c @@ -30,7 +30,7 @@ #else #define trace(point, args) \ do { \ - if (trace_##point##_enabled()) { \ + if (__trace_##point##_enabled()) { \ bool exit_rcu = false; \ if (in_nmi()) \ break; \ diff --git a/kernel/trace/trace_remote.c b/kernel/trace/trace_remote.c index 2a6cc000ec98..0f6ef5c36d84 100644 --- a/kernel/trace/trace_remote.c +++ b/kernel/trace/trace_remote.c @@ -979,33 +979,30 @@ EXPORT_SYMBOL_GPL(trace_remote_free_buffer); int trace_remote_alloc_buffer(struct trace_buffer_desc *desc, size_t desc_size, size_t buffer_size, const struct cpumask *cpumask) { + size_t min_desc_size = trace_buffer_desc_size(buffer_size, cpumask_weight(cpumask)); unsigned int nr_pages = max(DIV_ROUND_UP(buffer_size, PAGE_SIZE), 2UL) + 1; - void *desc_end = desc + desc_size; struct ring_buffer_desc *rb_desc; int cpu, ret = -ENOMEM; - if (desc_size < struct_size(desc, __data, 0)) + if (desc_size < min_desc_size) return -EINVAL; desc->nr_cpus = 0; - desc->struct_len = struct_size(desc, __data, 0); + desc->struct_len = min_desc_size; - rb_desc = (struct ring_buffer_desc *)&desc->__data[0]; + rb_desc = __first_ring_buffer_desc(desc); for_each_cpu(cpu, cpumask) { unsigned int id; - if ((void *)rb_desc + struct_size(rb_desc, page_va, nr_pages) > desc_end) { - ret = -EINVAL; - goto err; - } - rb_desc->cpu = cpu; rb_desc->nr_page_va = 0; rb_desc->meta_va = (unsigned long)__get_free_page(GFP_KERNEL); if (!rb_desc->meta_va) goto err; + desc->nr_cpus++; + for (id = 0; id < nr_pages; id++) { rb_desc->page_va[id] = (unsigned long)__get_free_page(GFP_KERNEL); if (!rb_desc->page_va[id]) @@ -1013,9 +1010,6 @@ int trace_remote_alloc_buffer(struct trace_buffer_desc *desc, size_t desc_size, rb_desc->nr_page_va++; } - desc->nr_cpus++; - desc->struct_len += offsetof(struct ring_buffer_desc, page_va); - desc->struct_len += struct_size(rb_desc, page_va, rb_desc->nr_page_va); rb_desc = __next_ring_buffer_desc(rb_desc); } diff --git a/lib/glob.c b/lib/glob.c index 7aca76c25bcb..c80d9dd736b4 100644 --- a/lib/glob.c +++ b/lib/glob.c @@ -11,6 +11,9 @@ MODULE_DESCRIPTION("glob(7) matching"); MODULE_LICENSE("Dual MIT/GPL"); +static bool __pure glob_match_str(char const *pat, char const *str, + char const *str_end); + /** * glob_match - Shell-style pattern matching, like !fnmatch(pat, str, 0) * @pat: Shell-style pattern to match, e.g. "*.[ch]". @@ -40,6 +43,29 @@ MODULE_LICENSE("Dual MIT/GPL"); * An opening bracket without a matching close is matched literally. */ bool __pure glob_match(char const *pat, char const *str) +{ + return glob_match_str(pat, str, NULL); +} +EXPORT_SYMBOL(glob_match); + +/** + * glob_match_len - glob match against a length-bounded string + * @pat: Shell-style pattern to match. + * @str: String to match. Need not be NUL-terminated. + * @len: Number of bytes of @str that may be read. + * + * Like glob_match(), but @str is only read up to @len bytes, so it can be + * used on buffers that are not NUL-terminated (e.g. trace event fields). + * A NUL byte within @len still terminates the string. + */ +bool __pure glob_match_len(char const *pat, char const *str, size_t len) +{ + return glob_match_str(pat, str, str + len); +} +EXPORT_SYMBOL(glob_match_len); + +static bool __pure glob_match_str(char const *pat, char const *str, + char const *str_end) { /* * Backtrack to previous * on mismatch and retry starting one @@ -55,9 +81,11 @@ bool __pure glob_match(char const *pat, char const *str) * on mismatch, or true after matching the trailing nul bytes. */ for (;;) { - unsigned char c = *str++; + unsigned char c = (str_end && str >= str_end) ? '\0' : *str; unsigned char d = *pat++; + str++; + switch (d) { case '?': /* Wildcard: anything but nul */ if (c == '\0') @@ -125,4 +153,3 @@ bool __pure glob_match(char const *pat, char const *str) } } } -EXPORT_SYMBOL(glob_match); diff --git a/mm/compaction.c b/mm/compaction.c index b776f35ad020..f08765ade014 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -1875,15 +1875,14 @@ static void compaction_free(struct folio *dst, unsigned long data) int order = folio_order(dst); struct page *page = &dst->page; - if (folio_put_testzero(dst)) { - free_pages_prepare(page, order); + if (folio_put_testzero(dst) && free_pages_prepare(page, order)) { list_add(&dst->lru, &cc->freepages[order]); cc->nr_freepages += 1 << order; } cc->nr_migratepages += 1 << order; /* - * someone else has referenced the page, we cannot take it back to our - * free list. + * someone else has referenced the page or free_pages_prepare() fails, + * we cannot take it back to our free list. */ } diff --git a/mm/damon/ops-common.c b/mm/damon/ops-common.c index 5c93ef2bb8a9..d1842e2b00ef 100644 --- a/mm/damon/ops-common.c +++ b/mm/damon/ops-common.c @@ -143,6 +143,7 @@ int damon_hot_score(struct damon_ctx *c, struct damon_region *r, * Transform it to fit in [0, DAMOS_MAX_SCORE] */ hotness = hotness * DAMOS_MAX_SCORE / DAMON_MAX_SUBSCORE; + hotness = max(min(hotness, DAMOS_MAX_SCORE), 0); return hotness; } diff --git a/mm/damon/sysfs-schemes.c b/mm/damon/sysfs-schemes.c index 329cfd0bbe9f..0134111c3c1f 100644 --- a/mm/damon/sysfs-schemes.c +++ b/mm/damon/sysfs-schemes.c @@ -1993,22 +1993,19 @@ static int damon_sysfs_access_pattern_add_dirs( err = damon_sysfs_access_pattern_add_range_dir(access_pattern, &access_pattern->sz, "sz"); if (err) - goto put_sz_out; + return err; err = damon_sysfs_access_pattern_add_range_dir(access_pattern, &access_pattern->nr_accesses, "nr_accesses"); if (err) - goto put_nr_accesses_sz_out; + goto put_sz_out; err = damon_sysfs_access_pattern_add_range_dir(access_pattern, &access_pattern->age, "age"); if (err) - goto put_age_nr_accesses_sz_out; + goto put_nr_accesses_sz_out; return 0; -put_age_nr_accesses_sz_out: - kobject_put(&access_pattern->age->kobj); - access_pattern->age = NULL; put_nr_accesses_sz_out: kobject_put(&access_pattern->nr_accesses->kobj); access_pattern->nr_accesses = NULL; @@ -2516,12 +2513,12 @@ static int damon_sysfs_scheme_add_dirs(struct damon_sysfs_scheme *scheme) goto put_filters_watermarks_quotas_access_pattern_out; err = damon_sysfs_scheme_set_tried_regions(scheme); if (err) - goto put_tried_regions_out; + goto put_stats_out; return 0; -put_tried_regions_out: - kobject_put(&scheme->tried_regions->kobj); - scheme->tried_regions = NULL; +put_stats_out: + kobject_put(&scheme->stats->kobj); + scheme->stats = NULL; put_filters_watermarks_quotas_access_pattern_out: kobject_put(&scheme->ops_filters->kobj); scheme->ops_filters = NULL; diff --git a/mm/filemap.c b/mm/filemap.c index 5af62e6abca5..58eb9d240643 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -4704,7 +4704,7 @@ static inline bool can_do_cachestat(struct file *f) { if (f->f_mode & FMODE_WRITE) return true; - if (inode_owner_or_capable(file_mnt_idmap(f), file_inode(f))) + if (file_owner_or_capable(f)) return true; return file_permission(f, MAY_WRITE) == 0; } diff --git a/mm/madvise.c b/mm/madvise.c index cd9bb077072c..77552b03d318 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -336,8 +336,7 @@ static inline bool can_do_file_pageout(struct vm_area_struct *vma) * otherwise we'd be including shared non-exclusive mappings, which * opens a side channel. */ - return inode_owner_or_capable(&nop_mnt_idmap, - file_inode(vma->vm_file)) || + return file_owner_or_capable(vma->vm_file) || file_permission(vma->vm_file, MAY_WRITE) == 0; } diff --git a/mm/mincore.c b/mm/mincore.c index 296f2e3922b5..c8757c5085bf 100644 --- a/mm/mincore.c +++ b/mm/mincore.c @@ -227,8 +227,7 @@ static inline bool can_do_mincore(struct vm_area_struct *vma) * for writing; otherwise we'd be including shared non-exclusive * mappings, which opens a side channel. */ - return inode_owner_or_capable(&nop_mnt_idmap, - file_inode(vma->vm_file)) || + return file_owner_or_capable(vma->vm_file) || file_permission(vma->vm_file, MAY_WRITE) == 0; } diff --git a/mm/shrinker.c b/mm/shrinker.c index 7082d01c8c9d..a70aab124a0e 100644 --- a/mm/shrinker.c +++ b/mm/shrinker.c @@ -59,12 +59,14 @@ static inline int shrinker_unit_alloc(struct shrinker_info *new, return 0; } -void free_shrinker_info(struct mem_cgroup *memcg) +static void __free_shrinker_info(struct mem_cgroup *memcg) { struct mem_cgroup_per_node *pn; struct shrinker_info *info; int nid; + lockdep_assert_held(&shrinker_mutex); + for_each_node(nid) { pn = memcg->nodeinfo[nid]; info = rcu_dereference_protected(pn->shrinker_info, true); @@ -74,6 +76,13 @@ void free_shrinker_info(struct mem_cgroup *memcg) } } +void free_shrinker_info(struct mem_cgroup *memcg) +{ + mutex_lock(&shrinker_mutex); + __free_shrinker_info(memcg); + mutex_unlock(&shrinker_mutex); +} + int alloc_shrinker_info(struct mem_cgroup *memcg) { int nid, ret = 0; @@ -98,8 +107,8 @@ int alloc_shrinker_info(struct mem_cgroup *memcg) return ret; err: + __free_shrinker_info(memcg); mutex_unlock(&shrinker_mutex); - free_shrinker_info(memcg); return -ENOMEM; } diff --git a/mm/shrinker_debug.c b/mm/shrinker_debug.c index cda4e86428c8..cafb56630132 100644 --- a/mm/shrinker_debug.c +++ b/mm/shrinker_debug.c @@ -183,10 +183,12 @@ int shrinker_debugfs_add(struct shrinker *shrinker) } shrinker->debugfs_entry = entry; - debugfs_create_file("count", 0440, entry, shrinker, - &shrinker_debugfs_count_fops); - debugfs_create_file("scan", 0220, entry, shrinker, - &shrinker_debugfs_scan_fops); + if (shrinker->count_objects) + debugfs_create_file("count", 0440, entry, shrinker, + &shrinker_debugfs_count_fops); + if (shrinker->scan_objects) + debugfs_create_file("scan", 0220, entry, shrinker, + &shrinker_debugfs_scan_fops); return 0; } diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c index c40c9e02391b..a6fe4820f65b 100644 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@ -546,7 +546,7 @@ static bool batadv_is_orig_node_eligible(struct batadv_dat_candidate *res, * the one with the lowest address */ if (tmp_max == max && max_orig_node && - batadv_compare_eth(candidate->orig, max_orig_node->orig)) + memcmp(candidate->orig, max_orig_node->orig, ETH_ALEN) >= 0) goto out; ret = true; diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c index 8a006a0473a8..2e20a2cb64cb 100644 --- a/net/batman-adv/fragmentation.c +++ b/net/batman-adv/fragmentation.c @@ -518,8 +518,10 @@ int batadv_frag_send_packet(struct sk_buff *skb, mtu = min_t(unsigned int, mtu, BATADV_FRAG_MAX_FRAG_SIZE); max_fragment_size = mtu - header_size; - if (skb->len == 0 || max_fragment_size == 0) - return -EINVAL; + if (skb->len == 0 || max_fragment_size == 0) { + ret = -EINVAL; + goto free_skb; + } num_fragments = (skb->len - 1) / max_fragment_size + 1; max_fragment_size = (skb->len - 1) / num_fragments + 1; @@ -545,7 +547,7 @@ int batadv_frag_send_packet(struct sk_buff *skb, */ if (skb_has_frag_list(skb) && __skb_linearize(skb)) { ret = -ENOMEM; - goto free_skb; + goto put_primary_if; } /* Create one header to be copied to all fragments */ diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index 4d3807a645b7..67bed3ee77e7 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -259,6 +259,7 @@ int batadv_mesh_init(struct net_device *mesh_iface) void batadv_mesh_free(struct net_device *mesh_iface) { struct batadv_priv *bat_priv = netdev_priv(mesh_iface); + struct batadv_meshif_vlan *vlan; WRITE_ONCE(bat_priv->mesh_state, BATADV_MESH_DEACTIVATING); @@ -273,6 +274,13 @@ void batadv_mesh_free(struct net_device *mesh_iface) batadv_mcast_free(bat_priv); + /* destroy the "untagged" VLAN */ + vlan = batadv_meshif_vlan_get(bat_priv, BATADV_NO_FLAGS); + if (vlan) { + batadv_meshif_destroy_vlan(bat_priv, vlan); + batadv_meshif_vlan_put(vlan); + } + /* Free the TT and the originator tables only after having terminated * all the other depending components which may use these structures for * their purposes. @@ -368,7 +376,7 @@ void batadv_skb_set_priority(struct sk_buff *skb, int offset) switch (ethhdr->h_proto) { case htons(ETH_P_8021Q): - vhdr = skb_header_pointer(skb, offset + sizeof(*vhdr), + vhdr = skb_header_pointer(skb, offset, sizeof(*vhdr), &vhdr_tmp); if (!vhdr) return; diff --git a/net/batman-adv/mesh-interface.c b/net/batman-adv/mesh-interface.c index 511f70e0706a..fbfd99268de4 100644 --- a/net/batman-adv/mesh-interface.c +++ b/net/batman-adv/mesh-interface.c @@ -195,6 +195,9 @@ static netdev_tx_t batadv_interface_tx(struct sk_buff *skb, if (READ_ONCE(bat_priv->mesh_state) != BATADV_MESH_ACTIVE) goto dropped; + if (!pskb_may_pull(skb, ETH_HLEN)) + goto dropped; + /* reset control block to avoid left overs from previous users */ memset(skb->cb, 0, sizeof(struct batadv_skb_cb)); @@ -592,8 +595,8 @@ int batadv_meshif_create_vlan(struct batadv_priv *bat_priv, unsigned short vid) * @bat_priv: the bat priv with all the mesh interface information * @vlan: the object to remove */ -static void batadv_meshif_destroy_vlan(struct batadv_priv *bat_priv, - struct batadv_meshif_vlan *vlan) +void batadv_meshif_destroy_vlan(struct batadv_priv *bat_priv, + struct batadv_meshif_vlan *vlan) { /* explicitly remove the associated TT local entry because it is marked * with the NOPURGE flag @@ -1088,22 +1091,13 @@ static int batadv_meshif_newlink(struct net_device *dev, static void batadv_meshif_destroy_netlink(struct net_device *mesh_iface, struct list_head *head) { - struct batadv_priv *bat_priv = netdev_priv(mesh_iface); struct batadv_hard_iface *hard_iface; - struct batadv_meshif_vlan *vlan; while (!list_empty(&mesh_iface->adj_list.lower)) { hard_iface = netdev_adjacent_get_private(mesh_iface->adj_list.lower.next); batadv_hardif_disable_interface(hard_iface); } - /* destroy the "untagged" VLAN */ - vlan = batadv_meshif_vlan_get(bat_priv, BATADV_NO_FLAGS); - if (vlan) { - batadv_meshif_destroy_vlan(bat_priv, vlan); - batadv_meshif_vlan_put(vlan); - } - unregister_netdevice_queue(mesh_iface, head); } diff --git a/net/batman-adv/mesh-interface.h b/net/batman-adv/mesh-interface.h index 53756c5a45e0..5e1e83e04ffb 100644 --- a/net/batman-adv/mesh-interface.h +++ b/net/batman-adv/mesh-interface.h @@ -21,6 +21,8 @@ void batadv_interface_rx(struct net_device *mesh_iface, bool batadv_meshif_is_valid(const struct net_device *net_dev); extern struct rtnl_link_ops batadv_link_ops; int batadv_meshif_create_vlan(struct batadv_priv *bat_priv, unsigned short vid); +void batadv_meshif_destroy_vlan(struct batadv_priv *bat_priv, + struct batadv_meshif_vlan *vlan); void batadv_meshif_vlan_release(struct kref *ref); struct batadv_meshif_vlan *batadv_meshif_vlan_get(struct batadv_priv *bat_priv, unsigned short vid); diff --git a/net/batman-adv/multicast_forw.c b/net/batman-adv/multicast_forw.c index b8668a80b94a..1404a3b7adfb 100644 --- a/net/batman-adv/multicast_forw.c +++ b/net/batman-adv/multicast_forw.c @@ -927,11 +927,11 @@ static int batadv_mcast_forw_packet(struct batadv_priv *bat_priv, { struct batadv_tvlv_mcast_tracker *mcast_tracker; struct batadv_neigh_node *neigh_node; - unsigned long offset, num_dests_off; struct sk_buff *nexthop_skb; unsigned char *skb_net_hdr; bool local_recv = false; unsigned int tvlv_len; + unsigned long offset; bool xmitted = false; u8 *dest, *next_dest; u16 num_dests; @@ -940,9 +940,8 @@ static int batadv_mcast_forw_packet(struct batadv_priv *bat_priv, /* (at least) TVLV part needs to be linearized */ SKB_LINEAR_ASSERT(skb); - /* check if num_dests is within skb length */ - num_dests_off = offsetof(struct batadv_tvlv_mcast_tracker, num_dests); - if (num_dests_off > skb_network_header_len(skb)) + /* check if batadv_tvlv_mcast_tracker header is within skb length */ + if (sizeof(*mcast_tracker) > skb_network_header_len(skb)) return -EINVAL; skb_net_hdr = skb_network_header(skb); diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 4bfad36a4b70..dae5e1d8c038 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -2971,7 +2971,7 @@ static bool batadv_send_tt_request(struct batadv_priv *bat_priv, out: batadv_hardif_put(primary_if); - if (ret && tt_req_node) { + if (!ret && tt_req_node) { spin_lock_bh(&bat_priv->tt.req_list_lock); if (!hlist_unhashed(&tt_req_node->list)) { hlist_del_init(&tt_req_node->list); @@ -4033,7 +4033,8 @@ static int batadv_tt_tvlv_unicast_handler_v1(struct batadv_priv *bat_priv, u16 tvlv_value_len) { struct batadv_tvlv_tt_data *tt_data; - u16 tt_vlan_len, tt_num_entries; + u16 tt_num_entries; + size_t tt_vlan_len; char tt_flag; bool ret; diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c index cb1e329d66fd..d504a363a30f 100644 --- a/net/bluetooth/6lowpan.c +++ b/net/bluetooth/6lowpan.c @@ -632,7 +632,7 @@ static struct l2cap_chan *chan_create(void) if (!chan) return NULL; - l2cap_chan_set_defaults(chan); + l2cap_chan_set_defaults(chan, NULL); chan->chan_type = L2CAP_CHAN_CONN_ORIENTED; chan->mode = L2CAP_MODE_LE_FLOWCTL; @@ -745,21 +745,6 @@ static inline void chan_ready_cb(struct l2cap_chan *chan) ifup(dev->netdev); } -static inline struct l2cap_chan *chan_new_conn_cb(struct l2cap_chan *pchan) -{ - struct l2cap_chan *chan; - - chan = chan_create(); - if (!chan) - return NULL; - - chan->ops = pchan->ops; - - BT_DBG("chan %p pchan %p", chan, pchan); - - return chan; -} - static void unregister_dev(struct lowpan_btle_dev *dev) { struct hci_dev *hdev = READ_ONCE(dev->hdev); @@ -797,20 +782,10 @@ static void chan_close_cb(struct l2cap_chan *chan) struct lowpan_btle_dev *dev = NULL; struct lowpan_peer *peer; int err = -ENOENT; - bool last = false, remove = true; + bool last = false; BT_DBG("chan %p conn %p", chan, chan->conn); - if (chan->conn && chan->conn->hcon) { - if (!is_bt_6lowpan(chan->conn->hcon)) - return; - - /* If conn is set, then the netdev is also there and we should - * not remove it. - */ - remove = false; - } - spin_lock(&devices_lock); list_for_each_entry_rcu(entry, &bt_6lowpan_devices, list) { @@ -837,10 +812,8 @@ static void chan_close_cb(struct l2cap_chan *chan) ifdown(dev->netdev); - if (remove) { - INIT_WORK(&entry->delete_netdev, delete_netdev); - schedule_work(&entry->delete_netdev); - } + INIT_WORK(&entry->delete_netdev, delete_netdev); + schedule_work(&entry->delete_netdev); } else { spin_unlock(&devices_lock); } @@ -901,7 +874,6 @@ static long chan_get_sndtimeo_cb(struct l2cap_chan *chan) static const struct l2cap_ops bt_6lowpan_chan_ops = { .name = "L2CAP 6LoWPAN channel", - .new_connection = chan_new_conn_cb, .recv = chan_recv_cb, .close = chan_close_cb, .state_change = chan_state_change_cb, @@ -1029,16 +1001,19 @@ static int get_l2cap_conn(char *buf, bdaddr_t *addr, u8 *addr_type, hci_dev_lock(hdev); hcon = hci_conn_hash_lookup_le(hdev, addr, le_addr_type); - hci_dev_unlock(hdev); - hci_dev_put(hdev); - - if (!hcon) + if (!hcon) { + hci_dev_unlock(hdev); + hci_dev_put(hdev); return -ENOENT; + } - *conn = (struct l2cap_conn *)hcon->l2cap_data; + *conn = l2cap_conn_hold_unless_zero(hcon->l2cap_data); BT_DBG("conn %p dst %pMR type %u", *conn, &hcon->dst, hcon->dst_type); + hci_dev_unlock(hdev); + hci_dev_put(hdev); + return 0; } @@ -1093,23 +1068,15 @@ static void disconnect_all_peers(void) } while (nchans); } -struct set_enable { - struct work_struct work; - bool flag; -}; - -static void do_enable_set(struct work_struct *work) +static void do_enable_set(bool flag) { - struct set_enable *set_enable = container_of(work, - struct set_enable, work); - - if (!set_enable->flag || enable_6lowpan != set_enable->flag) + if (!flag || enable_6lowpan != flag) /* Disconnect existing connections if 6lowpan is * disabled */ disconnect_all_peers(); - enable_6lowpan = set_enable->flag; + enable_6lowpan = flag; mutex_lock(&set_lock); if (listen_chan) { @@ -1121,22 +1088,11 @@ static void do_enable_set(struct work_struct *work) listen_chan = bt_6lowpan_listen(); mutex_unlock(&set_lock); - - kfree(set_enable); } static int lowpan_enable_set(void *data, u64 val) { - struct set_enable *set_enable; - - set_enable = kzalloc_obj(*set_enable); - if (!set_enable) - return -ENOMEM; - - set_enable->flag = !!val; - INIT_WORK(&set_enable->work, do_enable_set); - - schedule_work(&set_enable->work); + do_enable_set(!!val); return 0; } @@ -1185,18 +1141,22 @@ static ssize_t lowpan_control_write(struct file *fp, if (conn) { struct lowpan_peer *peer; - if (!is_bt_6lowpan(conn->hcon)) + if (!is_bt_6lowpan(conn->hcon)) { + l2cap_conn_put(conn); return -EINVAL; + } peer = lookup_peer(conn); if (peer) { BT_DBG("6LoWPAN connection already exists"); + l2cap_conn_put(conn); return -EALREADY; } BT_DBG("conn %p dst %pMR type %d user %u", conn, &conn->hcon->dst, conn->hcon->dst_type, addr_type); + l2cap_conn_put(conn); } ret = bt_6lowpan_connect(&addr, addr_type); @@ -1212,6 +1172,8 @@ static ssize_t lowpan_control_write(struct file *fp, return ret; ret = bt_6lowpan_disconnect(conn, addr_type); + if (conn) + l2cap_conn_put(conn); if (ret < 0) return ret; diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index bcbc11c9cb15..a2290ffdc2c1 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -305,7 +305,7 @@ struct sock *bt_accept_dequeue(struct sock *parent, struct socket *newsock) restart: for (sk = bt_accept_get(parent, NULL); sk; sk = next) { - /* Prevent early freeing of sk due to unlink and sock_kill */ + /* The reference from bt_accept_get() keeps sk alive. */ lock_sock(sk); /* Check sk has not already been unlinked via @@ -321,13 +321,11 @@ struct sock *bt_accept_dequeue(struct sock *parent, struct socket *newsock) next = bt_accept_get(parent, sk); - /* sk is safely in the parent list so reduce reference count */ - sock_put(sk); - /* FIXME: Is this check still needed */ if (sk->sk_state == BT_CLOSED) { bt_accept_unlink(sk); release_sock(sk); + sock_put(sk); continue; } @@ -337,16 +335,6 @@ struct sock *bt_accept_dequeue(struct sock *parent, struct socket *newsock) if (newsock) sock_graft(sk, newsock); - /* Hand the caller a reference taken while sk is - * still locked. bt_accept_unlink() just dropped - * the accept-queue reference; without this hold a - * concurrent teardown (e.g. l2cap_conn_del() -> - * l2cap_sock_kill()) could free sk between - * release_sock() and the caller using it. Every - * caller drops this with sock_put() when done. - */ - sock_hold(sk); - release_sock(sk); if (next) sock_put(next); @@ -354,6 +342,7 @@ struct sock *bt_accept_dequeue(struct sock *parent, struct socket *newsock) } release_sock(sk); + sock_put(sk); } return NULL; diff --git a/net/bluetooth/bnep/core.c b/net/bluetooth/bnep/core.c index add9a8f7535d..f7d88c33e23e 100644 --- a/net/bluetooth/bnep/core.c +++ b/net/bluetooth/bnep/core.c @@ -559,14 +559,18 @@ static int bnep_session(void *arg) return 0; } -static struct device *bnep_get_device(struct bnep_session *session) +static struct l2cap_conn *bnep_get_conn(struct bnep_session *session) { - struct l2cap_conn *conn = l2cap_pi(session->sock->sk)->chan->conn; + struct l2cap_chan *chan = l2cap_pi(session->sock->sk)->chan; + struct l2cap_conn *conn; - if (!conn || !conn->hcon) - return NULL; + l2cap_chan_lock(chan); + conn = chan->conn; + if (conn) + l2cap_conn_get(conn); + l2cap_chan_unlock(chan); - return &conn->hcon->dev; + return conn; } static const struct device_type bnep_type = { @@ -578,6 +582,7 @@ int bnep_add_connection(struct bnep_connadd_req *req, struct socket *sock) u32 valid_flags = BIT(BNEP_SETUP_RESPONSE); struct net_device *dev; struct bnep_session *s, *ss; + struct l2cap_conn *conn = NULL; u8 dst[ETH_ALEN], src[ETH_ALEN]; int err; @@ -637,10 +642,18 @@ int bnep_add_connection(struct bnep_connadd_req *req, struct socket *sock) bnep_set_default_proto_filter(s); #endif - SET_NETDEV_DEV(dev, bnep_get_device(s)); + conn = bnep_get_conn(s); + if (!conn) { + err = -ENOTCONN; + goto failed; + } + + SET_NETDEV_DEV(dev, &conn->hcon->dev); SET_NETDEV_DEVTYPE(dev, &bnep_type); err = register_netdev(dev); + l2cap_conn_put(conn); + conn = NULL; if (err) goto failed; @@ -662,6 +675,8 @@ int bnep_add_connection(struct bnep_connadd_req *req, struct socket *sock) return 0; failed: + if (conn) + l2cap_conn_put(conn); up_write(&bnep_session_sem); free_netdev(dev); return err; diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index c335372e4062..1966cd153d97 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -3178,26 +3178,11 @@ int hci_abort_conn(struct hci_conn *conn, u8 reason) conn->abort_reason = reason; - /* If the connection is pending check the command opcode since that - * might be blocking on hci_cmd_sync_work while waiting its respective - * event so we need to hci_cmd_sync_cancel to cancel it. - * - * hci_connect_le serializes the connection attempts so only one - * connection can be in BT_CONNECT at time. + /* Cancel the connect attempt. A return of 0 means the create command + * was still queued and got dequeued, so there is nothing to disconnect. */ - if (conn->state == BT_CONNECT && READ_ONCE(hdev->req_status) == HCI_REQ_PEND) { - switch (hci_skb_event(hdev->sent_cmd)) { - case HCI_EV_CONN_COMPLETE: - case HCI_EV_LE_CONN_COMPLETE: - case HCI_EV_LE_ENHANCED_CONN_COMPLETE: - case HCI_EVT_LE_CIS_ESTABLISHED: - hci_cmd_sync_cancel(hdev, ECANCELED); - break; - } - /* Cancel connect attempt if still queued/pending */ - } else if (!hci_cancel_connect_sync(hdev, conn)) { + if (!hci_cancel_connect_sync(hdev, conn)) return 0; - } /* Run immediately if on cmd_sync_work since this may be called * as a result to MGMT_OP_DISCONNECT/MGMT_OP_UNPAIR which does diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 3be8c3581c6c..c896d4edd013 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -6633,6 +6633,11 @@ static int hci_le_create_conn_sync(struct hci_dev *hdev, void *data) bt_dev_dbg(hdev, "conn %p", conn); + /* Hold a reference so conn stays valid for the HCI_CONN_CREATE + * clear_bit() at done. + */ + hci_conn_get(conn); + clear_bit(HCI_CONN_SCANNING, &conn->flags); conn->state = BT_CONNECT; @@ -6645,6 +6650,7 @@ static int hci_le_create_conn_sync(struct hci_dev *hdev, void *data) hdev->le_scan_type == LE_SCAN_ACTIVE && !hci_dev_test_flag(hdev, HCI_LE_SIMULTANEOUS_ROLES)) { hci_conn_del(conn); + hci_conn_put(conn); return -EBUSY; } @@ -6690,6 +6696,12 @@ static int hci_le_create_conn_sync(struct hci_dev *hdev, void *data) &own_addr_type); if (err) goto done; + + /* Mark create connection in flight so hci_cancel_connect_sync() can + * cancel it while blocking on the connection complete event. + */ + set_bit(HCI_CONN_CREATE, &conn->flags); + /* Send command LE Extended Create Connection if supported */ if (use_ext_conn(hdev)) { err = hci_le_ext_create_conn_sync(hdev, conn, own_addr_type); @@ -6725,11 +6737,14 @@ static int hci_le_create_conn_sync(struct hci_dev *hdev, void *data) conn->conn_timeout, NULL); done: + clear_bit(HCI_CONN_CREATE, &conn->flags); + if (err == -ETIMEDOUT) hci_le_connect_cancel_sync(hdev, conn, 0x00); /* Re-enable advertising after the connection attempt is finished. */ hci_resume_advertising_sync(hdev); + hci_conn_put(conn); return err; } @@ -7004,10 +7019,25 @@ static int hci_acl_create_conn_sync(struct hci_dev *hdev, void *data) else cp.role_switch = 0x00; - return __hci_cmd_sync_status_sk(hdev, HCI_OP_CREATE_CONN, - sizeof(cp), &cp, - HCI_EV_CONN_COMPLETE, - conn->conn_timeout, NULL); + /* Hold a reference so conn stays valid for the HCI_CONN_CREATE + * clear_bit() below. + */ + hci_conn_get(conn); + + /* Mark create connection in flight so hci_cancel_connect_sync() can + * cancel it while blocking on the connection complete event. + */ + set_bit(HCI_CONN_CREATE, &conn->flags); + + err = __hci_cmd_sync_status_sk(hdev, HCI_OP_CREATE_CONN, + sizeof(cp), &cp, + HCI_EV_CONN_COMPLETE, + conn->conn_timeout, NULL); + + clear_bit(HCI_CONN_CREATE, &conn->flags); + hci_conn_put(conn); + + return err; } int hci_connect_acl_sync(struct hci_dev *hdev, struct hci_conn *conn) @@ -7059,22 +7089,97 @@ int hci_connect_le_sync(struct hci_dev *hdev, struct hci_conn *conn) return (err == -EEXIST) ? 0 : err; } -int hci_cancel_connect_sync(struct hci_dev *hdev, struct hci_conn *conn) +static int hci_acl_cancel_create_conn_sync(struct hci_dev *hdev, + struct hci_conn *conn) { - if (conn->state != BT_OPEN) - return -EINVAL; + struct hci_cmd_sync_work_entry *entry; + int err = -EBUSY; - switch (conn->type) { - case ACL_LINK: - return !hci_cmd_sync_dequeue_once(hdev, - hci_acl_create_conn_sync, - conn, NULL); - case LE_LINK: - return !hci_cmd_sync_dequeue_once(hdev, hci_le_create_conn_sync, - conn, create_le_conn_complete); + /* cmd_sync_work_lock makes the HCI_CONN_CREATE test and the cancel + * atomic against the worker, which takes this lock to dequeue every + * entry: while it is held no other command can become pending, so + * hci_cmd_sync_cancel() cannot cancel an unrelated command. + */ + mutex_lock(&hdev->cmd_sync_work_lock); + + /* In flight: this connection owns the pending request, cancel it. */ + if (test_bit(HCI_CONN_CREATE, &conn->flags)) { + hci_cmd_sync_cancel(hdev, ECANCELED); + goto unlock; } - return -ENOENT; + /* Still queued: a successful dequeue means it never started, so there + * is nothing to disconnect. + */ + entry = _hci_cmd_sync_lookup_entry(hdev, hci_acl_create_conn_sync, conn, + NULL); + if (entry) { + _hci_cmd_sync_cancel_entry(hdev, entry, -ECANCELED); + err = 0; + } + +unlock: + mutex_unlock(&hdev->cmd_sync_work_lock); + return err; +} + +static int hci_le_cancel_create_conn_sync(struct hci_dev *hdev, + struct hci_conn *conn) +{ + struct hci_cmd_sync_work_entry *entry; + int err = -EBUSY; + + /* cmd_sync_work_lock keeps the HCI_CONN_CREATE test and the cancel + * atomic against the cmd_sync worker. + */ + mutex_lock(&hdev->cmd_sync_work_lock); + + if (test_bit(HCI_CONN_CREATE, &conn->flags)) { + hci_cmd_sync_cancel(hdev, ECANCELED); + goto unlock; + } + + entry = _hci_cmd_sync_lookup_entry(hdev, hci_le_create_conn_sync, conn, + create_le_conn_complete); + if (entry) { + _hci_cmd_sync_cancel_entry(hdev, entry, -ECANCELED); + err = 0; + } + +unlock: + mutex_unlock(&hdev->cmd_sync_work_lock); + return err; +} + +static int hci_cis_cancel_create_conn_sync(struct hci_dev *hdev, + struct hci_conn *conn) +{ + /* LE Create CIS is shared by the whole CIG and cannot be dequeued + * per-connection, so only an in-flight command can be cancelled. + * cmd_sync_work_lock keeps the test and the cancel atomic against the + * cmd_sync worker. + */ + mutex_lock(&hdev->cmd_sync_work_lock); + + if (test_bit(HCI_CONN_CREATE_CIS, &conn->flags)) + hci_cmd_sync_cancel(hdev, ECANCELED); + + mutex_unlock(&hdev->cmd_sync_work_lock); + return -EBUSY; +} + +int hci_cancel_connect_sync(struct hci_dev *hdev, struct hci_conn *conn) +{ + switch (conn->type) { + case ACL_LINK: + return hci_acl_cancel_create_conn_sync(hdev, conn); + case LE_LINK: + return hci_le_cancel_create_conn_sync(hdev, conn); + case CIS_LINK: + return hci_cis_cancel_create_conn_sync(hdev, conn); + default: + return -ENOENT; + } } int hci_le_conn_update_sync(struct hci_dev *hdev, struct hci_conn *conn, diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c index 793a481d7066..2e95a153912c 100644 --- a/net/bluetooth/iso.c +++ b/net/bluetooth/iso.c @@ -1590,6 +1590,7 @@ static void iso_conn_big_sync(struct sock *sk) { int err; struct hci_dev *hdev; + struct iso_conn *conn; bdaddr_t src, dst; u8 src_type; @@ -1612,8 +1613,17 @@ static void iso_conn_big_sync(struct sock *sk) hci_dev_lock(hdev); lock_sock(sk); + /* The socket lock was dropped for hci_get_route(), so the connection + * may have been torn down meanwhile: iso_chan_del() clears conn and + * the broadcast teardown path can clear conn->hcon on its own. Check + * both before dereferencing conn->hcon. + */ + conn = iso_pi(sk)->conn; + if (!conn || !conn->hcon) + goto unlock; + if (!test_and_set_bit(BT_SK_BIG_SYNC, &iso_pi(sk)->flags)) { - err = hci_conn_big_create_sync(hdev, iso_pi(sk)->conn->hcon, + err = hci_conn_big_create_sync(hdev, conn->hcon, &iso_pi(sk)->qos, iso_pi(sk)->sync_handle, iso_pi(sk)->bc_num_bis, @@ -1622,6 +1632,7 @@ static void iso_conn_big_sync(struct sock *sk) bt_dev_err(hdev, "hci_big_create_sync: %d", err); } +unlock: release_sock(sk); hci_dev_unlock(hdev); hci_dev_put(hdev); @@ -2529,7 +2540,7 @@ int iso_recv(struct hci_dev *hdev, u16 handle, struct sk_buff *skb, u16 flags) switch (pb) { case ISO_START: case ISO_SINGLE: - if (conn->rx_len) { + if (conn->rx_skb || conn->rx_len) { BT_ERR("Unexpected start frame (len %d)", skb->len); kfree_skb(conn->rx_skb); conn->rx_skb = NULL; @@ -2610,12 +2621,14 @@ int iso_recv(struct hci_dev *hdev, u16 handle, struct sk_buff *skb, u16 flags) break; case ISO_CONT: - BT_DBG("Cont: frag len %d (expecting %d)", skb->len, + case ISO_END: + BT_DBG("%s: frag len %d (expecting %d)", + (pb == ISO_END) ? "End" : "Cont", skb->len, conn->rx_len); - if (!conn->rx_len) { - BT_ERR("Unexpected continuation frame (len %d)", - skb->len); + if (!conn->rx_skb) { + BT_ERR("Unexpected ISO %s frame (len %d)", + (pb == ISO_END) ? "End" : "Cont", skb->len); goto drop; } @@ -2631,17 +2644,9 @@ int iso_recv(struct hci_dev *hdev, u16 handle, struct sk_buff *skb, u16 flags) skb_copy_from_linear_data(skb, skb_put(conn->rx_skb, skb->len), skb->len); conn->rx_len -= skb->len; - break; - case ISO_END: - if (!conn->rx_len) { - BT_ERR("Unexpected end frame (len %d)", skb->len); - goto drop; - } - - skb_copy_from_linear_data(skb, skb_put(conn->rx_skb, skb->len), - skb->len); - conn->rx_len -= skb->len; + if (pb == ISO_CONT) + break; if (!conn->rx_len) { struct sk_buff *rx_skb = conn->rx_skb; @@ -2652,6 +2657,13 @@ int iso_recv(struct hci_dev *hdev, u16 handle, struct sk_buff *skb, u16 flags) */ conn->rx_skb = NULL; iso_recv_frame(conn, rx_skb); + } else { + BT_ERR("ISO fragment incomplete (len %d, expected %d)", + skb->len, conn->rx_len); + kfree_skb(conn->rx_skb); + conn->rx_skb = NULL; + conn->rx_len = 0; + goto drop; } break; } diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 62133eef9d2f..538ae9aa3479 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -522,7 +522,10 @@ void l2cap_chan_put(struct l2cap_chan *c) } EXPORT_SYMBOL_GPL(l2cap_chan_put); -void l2cap_chan_set_defaults(struct l2cap_chan *chan) +/* Initialise @chan with default values, inheriting from the parent channel + * @pchan when it is given. + */ +void l2cap_chan_set_defaults(struct l2cap_chan *chan, struct l2cap_chan *pchan) { chan->fcs = L2CAP_FCS_CRC16; chan->max_tx = L2CAP_DEFAULT_MAX_TX; @@ -536,6 +539,31 @@ void l2cap_chan_set_defaults(struct l2cap_chan *chan) chan->retrans_timeout = L2CAP_DEFAULT_RETRANS_TO; chan->monitor_timeout = L2CAP_DEFAULT_MONITOR_TO; + if (pchan) { + BT_DBG("chan %p pchan %p", chan, pchan); + + chan->chan_type = pchan->chan_type; + chan->imtu = pchan->imtu; + chan->omtu = pchan->omtu; + chan->mode = pchan->mode; + chan->fcs = pchan->fcs; + chan->max_tx = pchan->max_tx; + chan->tx_win = pchan->tx_win; + chan->tx_win_max = pchan->tx_win_max; + chan->sec_level = pchan->sec_level; + chan->conf_state = pchan->conf_state; + chan->flags = pchan->flags; + chan->tx_credits = pchan->tx_credits; + chan->rx_credits = pchan->rx_credits; + + if (chan->chan_type == L2CAP_CHAN_FIXED) { + chan->scid = pchan->scid; + chan->dcid = pchan->scid; + } + + return; + } + chan->conf_state = 0; set_bit(CONF_NOT_COMPLETE, &chan->conf_state); @@ -1775,19 +1803,13 @@ static void l2cap_conn_del(struct hci_conn *hcon, int err) disable_delayed_work_sync(&conn->info_timer); disable_delayed_work_sync(&conn->id_addr_timer); + cancel_work_sync(&conn->pending_rx_work); + mutex_lock(&conn->lock); kfree_skb(conn->rx_skb); skb_queue_purge(&conn->pending_rx); - - /* We can not call flush_work(&conn->pending_rx_work) here since we - * might block if we are running on a worker from the same workqueue - * pending_rx_work is waiting on. - */ - if (work_pending(&conn->pending_rx_work)) - cancel_work_sync(&conn->pending_rx_work); - ida_destroy(&conn->tx_ida); l2cap_unregister_all_users(conn); @@ -3051,13 +3073,24 @@ static struct sk_buff *l2cap_build_cmd(struct l2cap_conn *conn, u8 code, return NULL; } -static inline int l2cap_get_conf_opt(void **ptr, int *type, int *olen, - unsigned long *val) +static inline int l2cap_get_conf_opt(void **ptr, void *end, int *type, + int *olen, unsigned long *val) { struct l2cap_conf_opt *opt = *ptr; int len; + /* opt->len is attacker-controlled. Validate that the full option + * (header + value) actually fits in the buffer before touching + * opt->val, otherwise the switch below reads past the end of the + * caller's buffer. + */ + if (end - *ptr < L2CAP_CONF_OPT_SIZE) + return -EINVAL; + len = L2CAP_CONF_OPT_SIZE + opt->len; + if (end - *ptr < len) + return -EINVAL; + *ptr += len; *type = opt->type; @@ -3429,6 +3462,7 @@ static int l2cap_parse_conf_req(struct l2cap_chan *chan, void *data, size_t data void *ptr = rsp->data; void *endptr = data + data_size; void *req = chan->conf_req; + void *req_end = req + chan->conf_len; int len = chan->conf_len; int type, hint, olen; unsigned long val; @@ -3442,9 +3476,11 @@ static int l2cap_parse_conf_req(struct l2cap_chan *chan, void *data, size_t data BT_DBG("chan %p", chan); while (len >= L2CAP_CONF_OPT_SIZE) { - len -= l2cap_get_conf_opt(&req, &type, &olen, &val); - if (len < 0) + int ret = l2cap_get_conf_opt(&req, req_end, &type, &olen, &val); + + if (ret < 0) break; + len -= ret; hint = type & L2CAP_CONF_HINT; type &= L2CAP_CONF_MASK; @@ -3672,6 +3708,7 @@ static int l2cap_parse_conf_rsp(struct l2cap_chan *chan, void *rsp, int len, struct l2cap_conf_req *req = data; void *ptr = req->data; void *endptr = data + size; + void *rsp_end = rsp + len; int type, olen; unsigned long val; struct l2cap_conf_rfc rfc = { .mode = L2CAP_MODE_BASIC }; @@ -3680,9 +3717,11 @@ static int l2cap_parse_conf_rsp(struct l2cap_chan *chan, void *rsp, int len, BT_DBG("chan %p, rsp %p, len %d, req %p", chan, rsp, len, data); while (len >= L2CAP_CONF_OPT_SIZE) { - len -= l2cap_get_conf_opt(&rsp, &type, &olen, &val); - if (len < 0) + int ret = l2cap_get_conf_opt(&rsp, rsp_end, &type, &olen, &val); + + if (ret < 0) break; + len -= ret; switch (type) { case L2CAP_CONF_MTU: @@ -3933,6 +3972,7 @@ static void l2cap_conf_rfc_get(struct l2cap_chan *chan, void *rsp, int len) { int type, olen; unsigned long val; + void *rsp_end = rsp + len; /* Use sane default values in case a misbehaving remote device * did not send an RFC or extended window size option. */ @@ -3951,9 +3991,11 @@ static void l2cap_conf_rfc_get(struct l2cap_chan *chan, void *rsp, int len) return; while (len >= L2CAP_CONF_OPT_SIZE) { - len -= l2cap_get_conf_opt(&rsp, &type, &olen, &val); - if (len < 0) + int ret = l2cap_get_conf_opt(&rsp, rsp_end, &type, &olen, &val); + + if (ret < 0) break; + len -= ret; switch (type) { case L2CAP_CONF_RFC: @@ -4010,6 +4052,38 @@ static inline int l2cap_command_rej(struct l2cap_conn *conn, return 0; } +/* Allocate and initialise a channel for an incoming connection. + * + * The channel inherits its configuration from @pchan and is linked into @conn + * before ->new_connection() runs, so the conn list reference keeps it alive if + * the callback exposes it (e.g. via the socket accept queue) before this + * returns. The l2cap_chan_create() reference is taken over by the subsystem on + * success and dropped here on failure. + */ +static struct l2cap_chan *l2cap_new_connection(struct l2cap_conn *conn, + struct l2cap_chan *pchan) +{ + struct l2cap_chan *chan; + + chan = l2cap_chan_create(); + if (!chan) + return NULL; + + l2cap_chan_set_defaults(chan, pchan); + chan->ops = pchan->ops; + + __l2cap_chan_add(conn, chan); + + if (pchan->ops->new_connection && + pchan->ops->new_connection(pchan, chan) < 0) { + l2cap_chan_del(chan, 0); + l2cap_chan_put(chan); + return NULL; + } + + return chan; +} + static void l2cap_connect(struct l2cap_conn *conn, struct l2cap_cmd_hdr *cmd, u8 *data, u8 rsp_code) { @@ -4056,7 +4130,7 @@ static void l2cap_connect(struct l2cap_conn *conn, struct l2cap_cmd_hdr *cmd, goto response; } - chan = pchan->ops->new_connection(pchan); + chan = l2cap_new_connection(conn, pchan); if (!chan) goto response; @@ -4074,8 +4148,6 @@ static void l2cap_connect(struct l2cap_conn *conn, struct l2cap_cmd_hdr *cmd, chan->psm = psm; chan->dcid = scid; - __l2cap_chan_add(conn, chan); - dcid = chan->scid; __set_chan_timer(chan, chan->ops->get_sndtimeo(chan)); @@ -4807,6 +4879,7 @@ static void l2cap_put_ident(struct l2cap_conn *conn, u8 code, u8 id) case L2CAP_ECHO_RSP: case L2CAP_INFO_RSP: case L2CAP_CONN_PARAM_UPDATE_RSP: + case L2CAP_LE_CONN_RSP: case L2CAP_ECRED_CONN_RSP: case L2CAP_ECRED_RECONF_RSP: /* First do a lookup since the remote may send bogus ids that @@ -4958,7 +5031,7 @@ static int l2cap_le_connect_req(struct l2cap_conn *conn, goto response_unlock; } - chan = pchan->ops->new_connection(pchan); + chan = l2cap_new_connection(conn, pchan); if (!chan) { result = L2CAP_CR_LE_NO_MEM; goto response_unlock; @@ -4973,8 +5046,6 @@ static int l2cap_le_connect_req(struct l2cap_conn *conn, chan->omtu = mtu; chan->remote_mps = mps; - __l2cap_chan_add(conn, chan); - l2cap_le_flowctl_init(chan, __le16_to_cpu(req->credits)); dcid = chan->scid; @@ -5182,7 +5253,7 @@ static inline int l2cap_ecred_conn_req(struct l2cap_conn *conn, continue; } - chan = pchan->ops->new_connection(pchan); + chan = l2cap_new_connection(conn, pchan); if (!chan) { result = L2CAP_CR_LE_NO_MEM; continue; @@ -5197,8 +5268,6 @@ static inline int l2cap_ecred_conn_req(struct l2cap_conn *conn, chan->omtu = mtu; chan->remote_mps = mps; - __l2cap_chan_add(conn, chan); - l2cap_ecred_init(chan, __le16_to_cpu(req->credits)); /* Init response */ @@ -6704,6 +6773,7 @@ static void l2cap_chan_le_send_credits(struct l2cap_chan *chan) struct l2cap_conn *conn = chan->conn; struct l2cap_le_credits pkt; u16 return_credits = l2cap_le_rx_credits(chan); + int ident; if (chan->mode != L2CAP_MODE_LE_FLOWCTL && chan->mode != L2CAP_MODE_EXT_FLOWCTL) @@ -6721,9 +6791,18 @@ static void l2cap_chan_le_send_credits(struct l2cap_chan *chan) pkt.cid = cpu_to_le16(chan->scid); pkt.credits = cpu_to_le16(return_credits); - chan->ident = l2cap_get_ident(conn); + ident = l2cap_get_ident(conn); - l2cap_send_cmd(conn, chan->ident, L2CAP_LE_CREDITS, sizeof(pkt), &pkt); + l2cap_send_cmd(conn, ident, L2CAP_LE_CREDITS, sizeof(pkt), &pkt); + + /* L2CAP_LE_CREDITS has no response so the ident is never released by + * l2cap_put_ident() - release it right away, otherwise the tx_ida + * range is exhausted after 254 packets and from then on credits are + * sent with the invalid ident 0, which some remote stacks ignore, + * stalling the channel. + */ + if (ident > 0) + ida_free(&conn->tx_ida, ident); } void l2cap_chan_rx_avail(struct l2cap_chan *chan, ssize_t rx_avail) @@ -7478,14 +7557,12 @@ static void l2cap_connect_cfm(struct hci_conn *hcon, u8 status) goto next; l2cap_chan_lock(pchan); - chan = pchan->ops->new_connection(pchan); + chan = l2cap_new_connection(conn, pchan); if (chan) { bacpy(&chan->src, &hcon->src); bacpy(&chan->dst, &hcon->dst); chan->src_type = bdaddr_src_type(hcon); chan->dst_type = dst_type; - - __l2cap_chan_add(conn, chan); } l2cap_chan_unlock(pchan); @@ -7702,6 +7779,7 @@ struct l2cap_conn *l2cap_conn_hold_unless_zero(struct l2cap_conn *c) return c; } +EXPORT_SYMBOL(l2cap_conn_hold_unless_zero); int l2cap_recv_acldata(struct hci_dev *hdev, u16 handle, struct sk_buff *skb, u16 flags) diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index 4853f1b33449..4058ff50cc27 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -43,7 +43,8 @@ static struct bt_sock_list l2cap_sk_list = { static const struct proto_ops l2cap_sock_ops; static void l2cap_sock_init(struct sock *sk, struct sock *parent); static struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock, - int proto, gfp_t prio, int kern); + int proto, gfp_t prio, int kern, + struct l2cap_chan *chan); static void l2cap_sock_cleanup_listen(struct sock *parent); bool l2cap_is_socket(struct socket *sock) @@ -1284,6 +1285,23 @@ static int l2cap_sock_recvmsg(struct socket *sock, struct msghdr *msg, return err; } +/* Release the sock's ref on chan and clear the pointer so that the ref is + * dropped exactly once even if both l2cap_sock_kill() and + * l2cap_sock_destruct() run. Setting chan->data to NULL first stops any other + * task from dereferencing the now-dead sock pointer. + */ +static void l2cap_sock_put_chan(struct sock *sk) +{ + struct l2cap_chan *chan = l2cap_pi(sk)->chan; + + if (!chan) + return; + + chan->data = NULL; + l2cap_pi(sk)->chan = NULL; + l2cap_chan_put(chan); +} + /* Kill socket (only if zapped and orphan) * Must be called on unlocked socket, with l2cap channel lock. */ @@ -1294,13 +1312,9 @@ static void l2cap_sock_kill(struct sock *sk) BT_DBG("sk %p state %s", sk, state_to_string(sk->sk_state)); - /* Sock is dead, so set chan data to NULL, avoid other task use invalid - * sock pointer. - */ - l2cap_pi(sk)->chan->data = NULL; - /* Kill poor orphan */ + l2cap_sock_put_chan(sk); - l2cap_chan_put(l2cap_pi(sk)->chan); + /* Kill poor orphan */ sock_set_flag(sk, SOCK_DEAD); sock_put(sk); } @@ -1492,8 +1506,8 @@ static void l2cap_sock_cleanup_listen(struct sock *parent) /* Close not yet accepted channels. * - * bt_accept_dequeue() now returns sk with an extra reference held - * (taken while sk was still locked) so a concurrent l2cap_conn_del() + * bt_accept_dequeue() returns sk with its temporary queue-walk + * reference held, so a concurrent l2cap_conn_del() * -> l2cap_sock_kill() cannot free sk under us. * * cleanup_listen() runs under the parent sk lock, so unlike @@ -1543,12 +1557,13 @@ static void l2cap_sock_cleanup_listen(struct sock *parent) } } -static struct l2cap_chan *l2cap_sock_new_connection_cb(struct l2cap_chan *chan) +static int l2cap_sock_new_connection_cb(struct l2cap_chan *chan, + struct l2cap_chan *new_chan) { struct sock *sk, *parent = chan->data; if (!parent) - return NULL; + return -EINVAL; lock_sock(parent); @@ -1556,25 +1571,28 @@ static struct l2cap_chan *l2cap_sock_new_connection_cb(struct l2cap_chan *chan) if (sk_acceptq_is_full(parent)) { BT_DBG("backlog full %d", parent->sk_ack_backlog); release_sock(parent); - return NULL; + return -ENOBUFS; } sk = l2cap_sock_alloc(sock_net(parent), NULL, BTPROTO_L2CAP, - GFP_ATOMIC, 0); + GFP_ATOMIC, 0, new_chan); if (!sk) { release_sock(parent); - return NULL; - } + return -ENOMEM; + } bt_sock_reclassify_lock(sk, BTPROTO_L2CAP); l2cap_sock_init(sk, parent); + /* The conn list reference taken by l2cap_new_connection() keeps new_chan + * alive once release_sock() lets another task free this socket. + */ bt_accept_enqueue(parent, sk, false); release_sock(parent); - return l2cap_pi(sk)->chan; + return 0; } static int l2cap_sock_recv_cb(struct l2cap_chan *chan, struct sk_buff *skb) @@ -1871,10 +1889,7 @@ static void l2cap_sock_destruct(struct sock *sk) BT_DBG("sk %p", sk); - if (l2cap_pi(sk)->chan) { - l2cap_pi(sk)->chan->data = NULL; - l2cap_chan_put(l2cap_pi(sk)->chan); - } + l2cap_sock_put_chan(sk); list_for_each_entry_safe(rx_busy, next, &l2cap_pi(sk)->rx_busy, list) { kfree_skb(rx_busy->skb); @@ -1907,30 +1922,12 @@ static void l2cap_sock_init(struct sock *sk, struct sock *parent) BT_DBG("sk %p", sk); if (parent) { - struct l2cap_chan *pchan = l2cap_pi(parent)->chan; - sk->sk_type = parent->sk_type; bt_sk(sk)->flags = bt_sk(parent)->flags; - chan->chan_type = pchan->chan_type; - chan->imtu = pchan->imtu; - chan->omtu = pchan->omtu; - chan->conf_state = pchan->conf_state; - chan->mode = pchan->mode; - chan->fcs = pchan->fcs; - chan->max_tx = pchan->max_tx; - chan->tx_win = pchan->tx_win; - chan->tx_win_max = pchan->tx_win_max; - chan->sec_level = pchan->sec_level; - chan->flags = pchan->flags; - chan->tx_credits = pchan->tx_credits; - chan->rx_credits = pchan->rx_credits; - - if (chan->chan_type == L2CAP_CHAN_FIXED) { - chan->scid = pchan->scid; - chan->dcid = pchan->scid; - } - + /* Channel configuration is inherited from the parent by + * l2cap_new_connection(). + */ security_sk_clone(parent, sk); } else { switch (sk->sk_type) { @@ -1956,7 +1953,7 @@ static void l2cap_sock_init(struct sock *sk, struct sock *parent) chan->mode = L2CAP_MODE_BASIC; } - l2cap_chan_set_defaults(chan); + l2cap_chan_set_defaults(chan, NULL); } /* Default config options */ @@ -1975,10 +1972,10 @@ static struct proto l2cap_proto = { }; static struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock, - int proto, gfp_t prio, int kern) + int proto, gfp_t prio, int kern, + struct l2cap_chan *chan) { struct sock *sk; - struct l2cap_chan *chan; sk = bt_sock_alloc(net, sock, &l2cap_proto, proto, prio, kern); if (!sk) @@ -1989,16 +1986,7 @@ static struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock, INIT_LIST_HEAD(&l2cap_pi(sk)->rx_busy); - chan = l2cap_chan_create(); - if (!chan) { - sk_free(sk); - if (sock) - sock->sk = NULL; - return NULL; - } - - l2cap_chan_hold(chan); - + /* The sock takes ownership of the caller's reference on chan. */ l2cap_pi(sk)->chan = chan; return sk; @@ -2008,6 +1996,7 @@ static int l2cap_sock_create(struct net *net, struct socket *sock, int protocol, int kern) { struct sock *sk; + struct l2cap_chan *chan; BT_DBG("sock %p", sock); @@ -2022,10 +2011,16 @@ static int l2cap_sock_create(struct net *net, struct socket *sock, int protocol, sock->ops = &l2cap_sock_ops; - sk = l2cap_sock_alloc(net, sock, protocol, GFP_ATOMIC, kern); - if (!sk) + chan = l2cap_chan_create(); + if (!chan) return -ENOMEM; + sk = l2cap_sock_alloc(net, sock, protocol, GFP_ATOMIC, kern, chan); + if (!sk) { + l2cap_chan_put(chan); + return -ENOMEM; + } + l2cap_sock_init(sk, NULL); bt_sock_link(&l2cap_sk_list, sk); return 0; diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index d23ca1dd0893..733a4b70e10c 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -5375,6 +5375,8 @@ static void mgmt_add_adv_patterns_monitor_complete(struct hci_dev *hdev, if (monitor->state == ADV_MONITOR_STATE_NOT_REGISTERED) monitor->state = ADV_MONITOR_STATE_REGISTERED; hci_update_passive_scan(hdev); + } else { + hci_free_adv_monitor(hdev, monitor); } mgmt_cmd_complete(cmd->sk, cmd->hdev->id, cmd->opcode, @@ -7658,6 +7660,8 @@ static void add_device_complete(struct hci_dev *hdev, void *data, int err) if (!err) { struct hci_conn_params *params; + hci_dev_lock(hdev); + params = hci_conn_params_lookup(hdev, &cp->addr.bdaddr, le_addr_type(cp->addr.type)); @@ -7666,6 +7670,7 @@ static void add_device_complete(struct hci_dev *hdev, void *data, int err) device_flags_changed(NULL, hdev, &cp->addr.bdaddr, cp->addr.type, hdev->conn_flags, params ? params->flags : 0); + hci_dev_unlock(hdev); } mgmt_cmd_complete(cmd->sk, hdev->id, MGMT_OP_ADD_DEVICE, diff --git a/net/bluetooth/msft.c b/net/bluetooth/msft.c index 2f008167cbaa..d7badce8746c 100644 --- a/net/bluetooth/msft.c +++ b/net/bluetooth/msft.c @@ -291,7 +291,7 @@ static int msft_le_monitor_advertisement_cb(struct hci_dev *hdev, u16 opcode, monitor->state = ADV_MONITOR_STATE_OFFLOADED; unlock: - if (status) + if (status && msft->resuming) hci_free_adv_monitor(hdev, monitor); hci_dev_unlock(hdev); diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index fcc597be5bbd..c05f79b7aa31 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -570,10 +570,23 @@ static void __sco_sock_close(struct sock *sk) /* Must be called on unlocked socket. */ static void sco_sock_close(struct sock *sk) { + struct sco_conn *conn; + + lock_sock(sk); + conn = sco_pi(sk)->conn; + if (conn) + sco_conn_hold(conn); + release_sock(sk); + + if (conn) + disable_delayed_work_sync(&conn->timeout_work); + lock_sock(sk); - sco_sock_clear_timer(sk); __sco_sock_close(sk); release_sock(sk); + + if (conn) + sco_conn_put(conn); } static void sco_sock_init(struct sock *sk, struct sock *parent) diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index 031d3022cb1e..c4470958b0d5 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -3201,34 +3201,19 @@ static const struct l2cap_ops smp_chan_ops = { .get_sndtimeo = l2cap_chan_no_get_sndtimeo, }; -static inline struct l2cap_chan *smp_new_conn_cb(struct l2cap_chan *pchan) +static inline int smp_new_conn_cb(struct l2cap_chan *chan, + struct l2cap_chan *new_chan) { - struct l2cap_chan *chan; - - BT_DBG("pchan %p", pchan); - - chan = l2cap_chan_create(); - if (!chan) - return NULL; - - chan->chan_type = pchan->chan_type; - chan->ops = &smp_chan_ops; - chan->scid = pchan->scid; - chan->dcid = chan->scid; - chan->imtu = pchan->imtu; - chan->omtu = pchan->omtu; - chan->mode = pchan->mode; + new_chan->ops = &smp_chan_ops; /* Other L2CAP channels may request SMP routines in order to * change the security level. This means that the SMP channel * lock must be considered in its own category to avoid lockdep * warnings. */ - atomic_set(&chan->nesting, L2CAP_NESTING_SMP); + atomic_set(&new_chan->nesting, L2CAP_NESTING_SMP); - BT_DBG("created chan %p", chan); - - return chan; + return 0; } static const struct l2cap_ops smp_root_chan_ops = { @@ -3288,7 +3273,7 @@ static struct l2cap_chan *smp_add_cid(struct hci_dev *hdev, u16 cid) l2cap_add_scid(chan, cid); - l2cap_chan_set_defaults(chan); + l2cap_chan_set_defaults(chan, NULL); if (cid == L2CAP_CID_SMP) { u8 bdaddr_type; diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index f20c039e44c8..96c9a8f57c87 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -403,6 +403,9 @@ ebt_check_match(struct ebt_entry_match *m, struct xt_mtchk_param *par, left - sizeof(struct ebt_entry_match) < m->match_size) return -EINVAL; + if (strnlen(m->u.name, XT_EXTENSION_MAXNAMELEN) == XT_EXTENSION_MAXNAMELEN) + return -EINVAL; + match = xt_find_match(NFPROTO_BRIDGE, m->u.name, m->u.revision); if (IS_ERR(match) || match->family != NFPROTO_BRIDGE) { if (!IS_ERR(match)) @@ -921,8 +924,7 @@ static int translate_table(struct net *net, const char *name, * if an error occurs */ newinfo->chainstack = - vmalloc_array(nr_cpu_ids, - sizeof(*(newinfo->chainstack))); + vcalloc(nr_cpu_ids, sizeof(*(newinfo->chainstack))); if (!newinfo->chainstack) return -ENOMEM; for_each_possible_cpu(i) { @@ -1434,6 +1436,8 @@ static int update_counters(struct net *net, sockptr_t arg, unsigned int len) if (copy_from_sockptr(&hlp, arg, sizeof(hlp))) return -EFAULT; + hlp.name[sizeof(hlp.name) - 1] = '\0'; + if (len != sizeof(hlp) + hlp.num_counters * sizeof(struct ebt_counter)) return -EINVAL; @@ -2273,6 +2277,8 @@ static int compat_copy_ebt_replace_from_user(struct ebt_replace *repl, memcpy(repl, &tmp, offsetof(struct ebt_replace, hook_entry)); + repl->name[sizeof(repl->name) - 1] = '\0'; + /* starting with hook_entry, 32 vs. 64 bit structures are different */ for (i = 0; i < NF_BR_NUMHOOKS; i++) repl->hook_entry[i] = compat_ptr(tmp.hook_entry[i]); @@ -2395,6 +2401,8 @@ static int compat_update_counters(struct net *net, sockptr_t arg, if (copy_from_sockptr(&hlp, arg, sizeof(hlp))) return -EFAULT; + hlp.name[sizeof(hlp.name) - 1] = '\0'; + /* try real handler in case userland supplied needed padding */ if (len != sizeof(hlp) + hlp.num_counters * sizeof(struct ebt_counter)) return update_counters(net, arg, len); diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h index 4ca2eca2e94b..3e969a070f9f 100644 --- a/net/ethtool/netlink.h +++ b/net/ethtool/netlink.h @@ -114,6 +114,34 @@ static inline void ethnl_update_u8(u8 *dst, const struct nlattr *attr, *mod = true; } +/** + * ethnl_update_u8_u32() - update u8 value from an NLA_U32 attribute + * @dst: value to update + * @attr: netlink attribute with new value or null + * @mod: pointer to bool for modification tracking + * + * Some attributes are NLA_U32 on the wire but are stored in a u8. Read the + * full 32-bit value from NLA_U32 netlink attribute @attr and narrow it into + * the u8 pointed to by @dst; do nothing if @attr is null. + * Bool pointed to by @mod is set to true if this function changed the value + * of *dst, otherwise it is left as is. + */ +static inline void ethnl_update_u8_u32(u8 *dst, const struct nlattr *attr, + bool *mod) +{ + u32 val; + + if (!attr) + return; + val = nla_get_u32(attr); + DEBUG_NET_WARN_ON_ONCE(val > U8_MAX); + if (*dst == val) + return; + + *dst = val; + *mod = true; +} + /** * ethnl_update_bool32() - update u32 used as bool from NLA_U8 attribute * @dst: value to update diff --git a/net/ethtool/rss.c b/net/ethtool/rss.c index d8adc78e3775..d4a1a4724b67 100644 --- a/net/ethtool/rss.c +++ b/net/ethtool/rss.c @@ -570,7 +570,7 @@ static const struct nla_policy ethnl_rss_flows_policy[] = { const struct nla_policy ethnl_rss_set_policy[ETHTOOL_A_RSS_FLOW_HASH + 1] = { [ETHTOOL_A_RSS_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), [ETHTOOL_A_RSS_CONTEXT] = { .type = NLA_U32, }, - [ETHTOOL_A_RSS_HFUNC] = NLA_POLICY_MIN(NLA_U32, 1), + [ETHTOOL_A_RSS_HFUNC] = NLA_POLICY_RANGE(NLA_U32, 1, U8_MAX), [ETHTOOL_A_RSS_INDIR] = { .type = NLA_BINARY, }, [ETHTOOL_A_RSS_HKEY] = NLA_POLICY_MIN(NLA_BINARY, 1), [ETHTOOL_A_RSS_INPUT_XFRM] = @@ -851,7 +851,7 @@ ethnl_rss_set(struct ethnl_req_info *req_info, struct genl_info *info) indir_mod = !!tb[ETHTOOL_A_RSS_INDIR]; rxfh.hfunc = data.hfunc; - ethnl_update_u8(&rxfh.hfunc, tb[ETHTOOL_A_RSS_HFUNC], &mod); + ethnl_update_u8_u32(&rxfh.hfunc, tb[ETHTOOL_A_RSS_HFUNC], &mod); if (rxfh.hfunc == data.hfunc) rxfh.hfunc = ETH_RSS_HASH_NO_CHANGE; @@ -860,7 +860,8 @@ ethnl_rss_set(struct ethnl_req_info *req_info, struct genl_info *info) goto exit_free_indir; rxfh.input_xfrm = data.input_xfrm; - ethnl_update_u8(&rxfh.input_xfrm, tb[ETHTOOL_A_RSS_INPUT_XFRM], &mod); + ethnl_update_u8_u32(&rxfh.input_xfrm, tb[ETHTOOL_A_RSS_INPUT_XFRM], + &mod); xfrm_sym = rxfh.input_xfrm || data.input_xfrm; if (rxfh.input_xfrm == data.input_xfrm) rxfh.input_xfrm = RXH_XFRM_NO_CHANGE; @@ -934,7 +935,7 @@ const struct ethnl_request_ops ethnl_rss_request_ops = { const struct nla_policy ethnl_rss_create_policy[ETHTOOL_A_RSS_INPUT_XFRM + 1] = { [ETHTOOL_A_RSS_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), [ETHTOOL_A_RSS_CONTEXT] = NLA_POLICY_MIN(NLA_U32, 1), - [ETHTOOL_A_RSS_HFUNC] = NLA_POLICY_MIN(NLA_U32, 1), + [ETHTOOL_A_RSS_HFUNC] = NLA_POLICY_RANGE(NLA_U32, 1, U8_MAX), [ETHTOOL_A_RSS_INDIR] = NLA_POLICY_MIN(NLA_BINARY, 1), [ETHTOOL_A_RSS_HKEY] = NLA_POLICY_MIN(NLA_BINARY, 1), [ETHTOOL_A_RSS_INPUT_XFRM] = @@ -1048,14 +1049,15 @@ int ethnl_rss_create_doit(struct sk_buff *skb, struct genl_info *info) goto exit_clean_data; indir_user_size = ret; - ethnl_update_u8(&rxfh.hfunc, tb[ETHTOOL_A_RSS_HFUNC], &mod); + ethnl_update_u8_u32(&rxfh.hfunc, tb[ETHTOOL_A_RSS_HFUNC], &mod); ret = rss_set_prep_hkey(dev, info, &data, &rxfh, &mod); if (ret) goto exit_free_indir; rxfh.input_xfrm = RXH_XFRM_NO_CHANGE; - ethnl_update_u8(&rxfh.input_xfrm, tb[ETHTOOL_A_RSS_INPUT_XFRM], &mod); + ethnl_update_u8_u32(&rxfh.input_xfrm, tb[ETHTOOL_A_RSS_INPUT_XFRM], + &mod); ctx = ethtool_rxfh_ctx_alloc(ops, data.indir_size, data.hkey_size); if (!ctx) { diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index b6337a47c141..bb2d4441a492 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -217,13 +217,18 @@ static void ip_sf_list_clear_all(struct ip_sf_list *psf) static void igmp_stop_timer(struct ip_mc_list *im) { + bool put = false; + spin_lock_bh(&im->lock); if (timer_delete(&im->timer)) - refcount_dec(&im->refcnt); + put = true; WRITE_ONCE(im->tm_running, 0); WRITE_ONCE(im->reporter, 0); im->unsolicit_count = 0; spin_unlock_bh(&im->lock); + + if (put) + ip_ma_put(im); } /* It must be called with locked im->lock */ @@ -248,20 +253,26 @@ static void igmp_gq_start_timer(struct in_device *in_dev) return; in_dev->mr_gq_running = 1; - if (!mod_timer(&in_dev->mr_gq_timer, exp)) - in_dev_hold(in_dev); + if (in_dev_hold_safe(in_dev)) { + if (mod_timer(&in_dev->mr_gq_timer, exp)) + in_dev_put(in_dev); + } } static void igmp_ifc_start_timer(struct in_device *in_dev, int delay) { - int tv = get_random_u32_below(delay); + if (in_dev_hold_safe(in_dev)) { + int tv = get_random_u32_below(delay); - if (!mod_timer(&in_dev->mr_ifc_timer, jiffies+tv+2)) - in_dev_hold(in_dev); + if (mod_timer(&in_dev->mr_ifc_timer, jiffies + tv + 2)) + in_dev_put(in_dev); + } } static void igmp_mod_timer(struct ip_mc_list *im, int max_delay) { + bool put = false; + spin_lock_bh(&im->lock); im->unsolicit_count = 0; if (timer_delete(&im->timer)) { @@ -271,10 +282,13 @@ static void igmp_mod_timer(struct ip_mc_list *im, int max_delay) spin_unlock_bh(&im->lock); return; } - refcount_dec(&im->refcnt); + put = true; } igmp_start_timer(im, max_delay); spin_unlock_bh(&im->lock); + + if (put) + ip_ma_put(im); } @@ -1922,6 +1936,7 @@ void ip_mc_destroy_dev(struct in_device *in_dev) #endif while ((i = rtnl_dereference(in_dev->mc_list)) != NULL) { + ip_mc_hash_remove(in_dev, i); in_dev->mc_list = i->next_rcu; WRITE_ONCE(in_dev->mc_count, in_dev->mc_count - 1); ip_mc_clear_src(i); diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 04b811b3be97..4d2b9377ba2d 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -1083,8 +1083,10 @@ static void mld_gq_start_work(struct inet6_dev *idev) mc_assert_locked(idev); idev->mc_gq_running = 1; - if (!mod_delayed_work(mld_wq, &idev->mc_gq_work, tv + 2)) - in6_dev_hold(idev); + if (in6_dev_hold_safe(idev)) { + if (mod_delayed_work(mld_wq, &idev->mc_gq_work, tv + 2)) + in6_dev_put(idev); + } } static void mld_gq_stop_work(struct inet6_dev *idev) @@ -1102,8 +1104,10 @@ static void mld_ifc_start_work(struct inet6_dev *idev, unsigned long delay) mc_assert_locked(idev); - if (!mod_delayed_work(mld_wq, &idev->mc_ifc_work, tv + 2)) - in6_dev_hold(idev); + if (in6_dev_hold_safe(idev)) { + if (mod_delayed_work(mld_wq, &idev->mc_ifc_work, tv + 2)) + in6_dev_put(idev); + } } static void mld_ifc_stop_work(struct inet6_dev *idev) @@ -1121,8 +1125,10 @@ static void mld_dad_start_work(struct inet6_dev *idev, unsigned long delay) mc_assert_locked(idev); - if (!mod_delayed_work(mld_wq, &idev->mc_dad_work, tv + 2)) - in6_dev_hold(idev); + if (in6_dev_hold_safe(idev)) { + if (mod_delayed_work(mld_wq, &idev->mc_dad_work, tv + 2)) + in6_dev_put(idev); + } } static void mld_dad_stop_work(struct inet6_dev *idev) @@ -1395,18 +1401,23 @@ static void mld_process_v2(struct inet6_dev *idev, struct mld2_query *mld, void igmp6_event_query(struct sk_buff *skb) { struct inet6_dev *idev = __in6_dev_get(skb->dev); + bool put = false; if (!idev || idev->dead) goto out; spin_lock_bh(&idev->mc_query_lock); - if (skb_queue_len(&idev->mc_query_queue) < MLD_MAX_SKBS) { + if (skb_queue_len(&idev->mc_query_queue) < MLD_MAX_SKBS && + in6_dev_hold_safe(idev)) { __skb_queue_tail(&idev->mc_query_queue, skb); - if (!mod_delayed_work(mld_wq, &idev->mc_query_work, 0)) - in6_dev_hold(idev); + if (mod_delayed_work(mld_wq, &idev->mc_query_work, 0)) + put = true; skb = NULL; } spin_unlock_bh(&idev->mc_query_lock); + + if (put) + in6_dev_put(idev); out: kfree_skb(skb); } @@ -1570,18 +1581,23 @@ static void mld_query_work(struct work_struct *work) void igmp6_event_report(struct sk_buff *skb) { struct inet6_dev *idev = __in6_dev_get(skb->dev); + bool put = false; if (!idev || idev->dead) goto out; spin_lock_bh(&idev->mc_report_lock); - if (skb_queue_len(&idev->mc_report_queue) < MLD_MAX_SKBS) { + if (skb_queue_len(&idev->mc_report_queue) < MLD_MAX_SKBS && + in6_dev_hold_safe(idev)) { __skb_queue_tail(&idev->mc_report_queue, skb); - if (!mod_delayed_work(mld_wq, &idev->mc_report_work, 0)) - in6_dev_hold(idev); + if (mod_delayed_work(mld_wq, &idev->mc_report_work, 0)) + put = true; skb = NULL; } spin_unlock_bh(&idev->mc_report_lock); + + if (put) + in6_dev_put(idev); out: kfree_skb(skb); } diff --git a/net/ipv6/netfilter/ip6t_ah.c b/net/ipv6/netfilter/ip6t_ah.c index 70da2f2ce064..1258783ed876 100644 --- a/net/ipv6/netfilter/ip6t_ah.c +++ b/net/ipv6/netfilter/ip6t_ah.c @@ -56,6 +56,11 @@ static bool ah_mt6(const struct sk_buff *skb, struct xt_action_param *par) } hdrlen = ipv6_authlen(ah); + if (skb->len - ptr < hdrlen) { + /* Packet smaller than its length field */ + par->hotdrop = true; + return false; + } pr_debug("IPv6 AH LEN %u %u ", hdrlen, ah->hdrlen); pr_debug("RES %04X ", ah->reserved); diff --git a/net/ipv6/netfilter/ip6t_hbh.c b/net/ipv6/netfilter/ip6t_hbh.c index 450dd53846a2..6d1a5d2026a6 100644 --- a/net/ipv6/netfilter/ip6t_hbh.c +++ b/net/ipv6/netfilter/ip6t_hbh.c @@ -75,6 +75,7 @@ hbh_mt6(const struct sk_buff *skb, struct xt_action_param *par) hdrlen = ipv6_optlen(oh); if (skb->len - ptr < hdrlen) { /* Packet smaller than it's length field */ + par->hotdrop = true; return false; } diff --git a/net/ipv6/netfilter/ip6t_rt.c b/net/ipv6/netfilter/ip6t_rt.c index 5561bd9cea81..278b52752f36 100644 --- a/net/ipv6/netfilter/ip6t_rt.c +++ b/net/ipv6/netfilter/ip6t_rt.c @@ -56,7 +56,8 @@ static bool rt_mt6(const struct sk_buff *skb, struct xt_action_param *par) hdrlen = ipv6_optlen(rh); if (skb->len - ptr < hdrlen) { - /* Pcket smaller than its length field */ + /* Packet smaller than its length field */ + par->hotdrop = true; return false; } diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 64ab23ff559b..599c49bf0a0a 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -348,7 +348,8 @@ static int nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *skb, skb_network_header(skb)[fq->nhoffset] = skb_transport_header(skb)[0]; memmove(skb->head + sizeof(struct frag_hdr), skb->head, (skb->data - skb->head) - sizeof(struct frag_hdr)); - skb->mac_header += sizeof(struct frag_hdr); + if (skb_mac_header_was_set(skb)) + skb->mac_header += sizeof(struct frag_hdr); skb->network_header += sizeof(struct frag_hdr); skb_reset_transport_header(skb); @@ -418,7 +419,7 @@ find_prev_fhdr(struct sk_buff *skb, u8 *prevhdrp, int *prevhoff, int *fhoff) return -1; } if (skb_copy_bits(skb, start, &hdr, sizeof(hdr))) - BUG(); + return -1; if (nexthdr == NEXTHDR_AUTH) hdrlen = ipv6_authlen(&hdr); else diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 8ed1be1ecccc..b0447c33dbf0 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -312,6 +312,7 @@ static int llc_ui_autobind(struct socket *sock, struct sockaddr_llc *addr) /* assign new connection to its SAP */ llc_sap_add_socket(sap, sk); sock_reset_flag(sk, SOCK_ZAPPED); + llc_sap_put(sap); rc = 0; out: dev_put(dev); diff --git a/net/mac802154/iface.c b/net/mac802154/iface.c index 000be60d9580..b823720630e7 100644 --- a/net/mac802154/iface.c +++ b/net/mac802154/iface.c @@ -703,7 +703,7 @@ void ieee802154_remove_interfaces(struct ieee802154_local *local) mutex_lock(&local->iflist_mtx); list_for_each_entry_safe(sdata, tmp, &local->interfaces, list) { - list_del(&sdata->list); + list_del_rcu(&sdata->list); unregister_netdevice(sdata->dev); } diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index dedf59b661dd..8231317b0f1f 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -75,15 +75,17 @@ struct hbucket { struct htable_gc { struct delayed_work dwork; struct ip_set *set; /* Set the gc belongs to */ + spinlock_t lock; /* Lock to exclude gc and resize */ u32 region; /* Last gc run position */ }; /* The hash table: the table size stored here in order to make resizing easy */ struct htable { - atomic_t ref; /* References for resizing */ + bool resizing; /* Mark ongoing resize */ atomic_t uref; /* References for dumping and gc */ u8 htable_bits; /* size of hash table == 2^htable_bits */ u32 maxelem; /* Maxelem per region */ + struct list_head ad; /* Resize add|del backlist */ struct ip_set_region *hregion; /* Region locks and ext sizes */ struct hbucket __rcu *bucket[]; /* hashtable buckets */ }; @@ -301,11 +303,13 @@ struct htype { u8 netmask; /* netmask value for subnets to store */ union nf_inet_addr bitmask; /* stores bitmask */ #endif - struct list_head ad; /* Resize add|del backlist */ - struct mtype_elem next; /* temporary storage for uadd */ #ifdef IP_SET_HASH_WITH_NETS struct net_prefixes nets[NLEN]; /* book-keeping of prefixes */ #endif + /* Because 'next' is IPv4/IPv6 dependent, no elements of this + * structure and referred in create() may come after 'next'. + */ + struct mtype_elem next; /* temporary storage for uadd */ }; /* ADD|DEL entries saved during resize */ @@ -451,13 +455,14 @@ static void mtype_destroy(struct ip_set *set) { struct htype *h = set->data; + struct htable *t = (__force struct htable *)h->table; struct list_head *l, *lt; - mtype_ahash_destroy(set, (__force struct htable *)h->table, true); - list_for_each_safe(l, lt, &h->ad) { + list_for_each_safe(l, lt, &t->ad) { list_del(l); kfree(l); } + mtype_ahash_destroy(set, t, true); kfree(h); set->data = NULL; @@ -569,9 +574,10 @@ mtype_gc(struct work_struct *work) set = gc->set; h = set->data; - spin_lock_bh(&set->lock); - t = ipset_dereference_set(h->table, set); + rcu_read_lock_bh(); + t = rcu_dereference_bh(h->table); atomic_inc(&t->uref); + rcu_read_unlock_bh(); numof_locks = ahash_numof_locks(t->htable_bits); r = gc->region++; if (r >= numof_locks) { @@ -580,11 +586,13 @@ mtype_gc(struct work_struct *work) next_run = (IPSET_GC_PERIOD(set->timeout) * HZ) / numof_locks; if (next_run < HZ/10) next_run = HZ/10; - spin_unlock_bh(&set->lock); - mtype_gc_do(set, h, t, r); + spin_lock_bh(&gc->lock); + if (!t->resizing) + mtype_gc_do(set, h, t, r); + spin_unlock_bh(&gc->lock); - if (atomic_dec_and_test(&t->uref) && atomic_read(&t->ref)) { + if (atomic_dec_and_test(&t->uref) && t->resizing) { pr_debug("Table destroy after resize by expire: %p\n", t); mtype_ahash_destroy(set, t, false); } @@ -668,15 +676,18 @@ mtype_resize(struct ip_set *set, bool retried) } t->htable_bits = htable_bits; t->maxelem = h->maxelem / ahash_numof_locks(htable_bits); + INIT_LIST_HEAD(&t->ad); for (i = 0; i < ahash_numof_locks(htable_bits); i++) spin_lock_init(&t->hregion[i].lock); /* There can't be another parallel resizing, - * but dumping, gc, kernel side add/del are possible + * but dumping and kernel side add/del are possible */ orig = ipset_dereference_bh_nfnl(h->table); - atomic_set(&orig->ref, 1); atomic_inc(&orig->uref); + spin_lock_bh(&h->gc.lock); + orig->resizing = true; + spin_unlock_bh(&h->gc.lock); pr_debug("attempt to resize set %s from %u to %u, t %p\n", set->name, orig->htable_bits, htable_bits, orig); for (r = 0; r < ahash_numof_locks(orig->htable_bits); r++) { @@ -768,7 +779,7 @@ mtype_resize(struct ip_set *set, bool retried) * Kernel-side add cannot trigger a resize and userspace actions * are serialized by the mutex. */ - list_for_each_safe(l, lt, &h->ad) { + list_for_each_safe(l, lt, &orig->ad) { x = list_entry(l, struct mtype_resize_ad, list); if (x->ad == IPSET_ADD) { mtype_add(set, &x->d, &x->ext, &x->mext, x->flags); @@ -792,11 +803,24 @@ mtype_resize(struct ip_set *set, bool retried) cleanup: rcu_read_unlock_bh(); - atomic_set(&orig->ref, 0); + spin_lock_bh(&h->gc.lock); + orig->resizing = false; + spin_unlock_bh(&h->gc.lock); + /* Make sure parallel readers see that orig->resizing is false + * before we decrement uref */ + synchronize_rcu(); atomic_dec(&orig->uref); mtype_ahash_destroy(set, t, false); if (ret == -EAGAIN) goto retry; + + /* Cleanup the backlog of ADD/DEL elements */ + spin_lock_bh(&set->lock); + list_for_each_safe(l, lt, &orig->ad) { + list_del(l); + kfree(l); + } + spin_unlock_bh(&set->lock); goto out; hbwarn: @@ -860,15 +884,13 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, key = HKEY(value, h->initval, t->htable_bits); r = ahash_region(key); atomic_inc(&t->uref); + rcu_read_unlock_bh(); elements = t->hregion[r].elements; maxelem = t->maxelem; if (elements >= maxelem) { u32 e; - if (SET_WITH_TIMEOUT(set)) { - rcu_read_unlock_bh(); + if (SET_WITH_TIMEOUT(set)) mtype_gc_do(set, h, t, r); - rcu_read_lock_bh(); - } maxelem = h->maxelem; elements = 0; for (e = 0; e < ahash_numof_locks(t->htable_bits); e++) @@ -876,7 +898,6 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, if (elements >= maxelem && SET_WITH_FORCEADD(set)) forceadd = true; } - rcu_read_unlock_bh(); spin_lock_bh(&t->hregion[r].lock); n = rcu_dereference_bh(hbucket(t, key)); @@ -1003,7 +1024,7 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, ret = 0; resize: spin_unlock_bh(&t->hregion[r].lock); - if (atomic_read(&t->ref) && ext->target) { + if (t->resizing && ext && ext->target) { /* Resize is in process and kernel side add, save values */ struct mtype_resize_ad *x; @@ -1017,7 +1038,7 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, memcpy(&x->mext, mext, sizeof(struct ip_set_ext)); x->flags = flags; spin_lock_bh(&set->lock); - list_add_tail(&x->list, &h->ad); + list_add_tail(&x->list, &t->ad); spin_unlock_bh(&set->lock); } goto out; @@ -1030,7 +1051,7 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, unlock: spin_unlock_bh(&t->hregion[r].lock); out: - if (atomic_dec_and_test(&t->uref) && atomic_read(&t->ref)) { + if (atomic_dec_and_test(&t->uref) && t->resizing) { pr_debug("Table destroy after resize by add: %p\n", t); mtype_ahash_destroy(set, t, false); } @@ -1093,7 +1114,7 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext, #endif ip_set_ext_destroy(set, data); - if (atomic_read(&t->ref) && ext->target) { + if (t->resizing && ext && ext->target) { /* Resize is in process and kernel side del, * save values */ @@ -1141,10 +1162,10 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext, spin_unlock_bh(&t->hregion[r].lock); if (x) { spin_lock_bh(&set->lock); - list_add(&x->list, &h->ad); + list_add(&x->list, &t->ad); spin_unlock_bh(&set->lock); } - if (atomic_dec_and_test(&t->uref) && atomic_read(&t->ref)) { + if (atomic_dec_and_test(&t->uref) && t->resizing) { pr_debug("Table destroy after resize by del: %p\n", t); mtype_ahash_destroy(set, t, false); } @@ -1353,7 +1374,7 @@ mtype_uref(struct ip_set *set, struct netlink_callback *cb, bool start) rcu_read_unlock_bh(); } else if (cb->args[IPSET_CB_PRIVATE]) { t = (struct htable *)cb->args[IPSET_CB_PRIVATE]; - if (atomic_dec_and_test(&t->uref) && atomic_read(&t->ref)) { + if (atomic_dec_and_test(&t->uref) && t->resizing) { pr_debug("Table destroy after resize " " by dump: %p\n", t); mtype_ahash_destroy(set, t, false); @@ -1566,7 +1587,13 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, if (tb[IPSET_ATTR_MAXELEM]) maxelem = ip_set_get_h32(tb[IPSET_ATTR_MAXELEM]); - hsize = sizeof(*h); +#ifdef IP_SET_PROTO_UNDEF + hsize = sizeof(struct htype); +#else + hsize = set->family == NFPROTO_IPV6 ? + sizeof(struct IPSET_TOKEN(HTYPE, 6)) : + sizeof(struct IPSET_TOKEN(HTYPE, 4)); +#endif h = kzalloc(hsize, GFP_KERNEL); if (!h) return -ENOMEM; @@ -1593,6 +1620,7 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, return -ENOMEM; } h->gc.set = set; + spin_lock_init(&h->gc.lock); for (i = 0; i < ahash_numof_locks(hbits); i++) spin_lock_init(&t->hregion[i].lock); h->maxelem = maxelem; @@ -1619,9 +1647,8 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, } t->htable_bits = hbits; t->maxelem = h->maxelem / ahash_numof_locks(hbits); + INIT_LIST_HEAD(&t->ad); RCU_INIT_POINTER(h->table, t); - - INIT_LIST_HEAD(&h->ad); set->data = h; #ifndef IP_SET_PROTO_UNDEF if (set->family == NFPROTO_IPV4) { diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index cb36641f8d1c..6ed2622363f0 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -1420,8 +1420,8 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p, int dest_af, cp->app = NULL; cp->app_data = NULL; /* reset struct ip_vs_seq */ - cp->in_seq.delta = 0; - cp->out_seq.delta = 0; + memset(&cp->in_seq, 0, sizeof(cp->in_seq)); + memset(&cp->out_seq, 0, sizeof(cp->out_seq)); if (unlikely(flags & IP_VS_CONN_F_NO_CPORT)) { int af_id = ip_vs_af_index(cp->af); diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index d40b404c1bf6..35cbe821c259 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -398,10 +398,10 @@ ip_vs_conn_stats(struct ip_vs_conn *cp, struct ip_vs_service *svc) static inline void ip_vs_set_state(struct ip_vs_conn *cp, int direction, const struct sk_buff *skb, - struct ip_vs_proto_data *pd) + struct ip_vs_proto_data *pd, unsigned int iph_len) { if (likely(pd->pp->state_transition)) - pd->pp->state_transition(cp, direction, skb, pd); + pd->pp->state_transition(cp, direction, skb, pd, iph_len); } static inline int @@ -803,7 +803,7 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb, ip_vs_in_stats(cp, skb); /* set state */ - ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pd); + ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pd, iph->len); /* transmit the first SYN packet */ ret = cp->packet_xmit(skb, cp, pd->pp, iph); @@ -1484,7 +1484,7 @@ handle_response(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, after_nat: ip_vs_out_stats(cp, skb); - ip_vs_set_state(cp, IP_VS_DIR_OUTPUT, skb, pd); + ip_vs_set_state(cp, IP_VS_DIR_OUTPUT, skb, pd, iph->len); skb->ipvs_property = 1; if (!(cp->flags & IP_VS_CONN_F_NFCT)) ip_vs_notrack(skb); @@ -1767,6 +1767,8 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, bool tunnel, new_cp = false; union nf_inet_addr *raddr; char *outer_proto = "IPIP"; + unsigned int hlen_ipip; + int ulen = 0; *related = 1; @@ -1803,9 +1805,10 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, /* Now find the contained IP header */ offset += sizeof(_icmph); cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph); - if (cih == NULL) + if (!(cih && cih->version == 4 && cih->ihl >= 5)) return NF_ACCEPT; /* The packet looks wrong, ignore */ raddr = (union nf_inet_addr *)&cih->daddr; + hlen_ipip = cih->ihl * 4; /* Special case for errors for IPIP/UDP/GRE tunnel packets */ tunnel = false; @@ -1821,9 +1824,9 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, /* Only for known tunnel */ if (!dest || dest->tun_type != IP_VS_CONN_F_TUNNEL_TYPE_IPIP) return NF_ACCEPT; - offset += cih->ihl * 4; + offset += hlen_ipip; cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph); - if (cih == NULL) + if (!(cih && cih->version == 4 && cih->ihl >= 5)) return NF_ACCEPT; /* The packet looks wrong, ignore */ tunnel = true; } else if ((cih->protocol == IPPROTO_UDP || /* Can be UDP encap */ @@ -1831,12 +1834,11 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, /* Error for our tunnel must arrive at LOCAL_IN */ (skb_rtable(skb)->rt_flags & RTCF_LOCAL)) { __u8 iproto; - int ulen; /* Non-first fragment has no UDP/GRE header */ if (unlikely(cih->frag_off & htons(IP_OFFSET))) return NF_ACCEPT; - offset2 = offset + cih->ihl * 4; + offset2 = offset + hlen_ipip; if (cih->protocol == IPPROTO_UDP) { ulen = ipvs_udp_decap(ipvs, skb, offset2, AF_INET, raddr, &iproto); @@ -1905,6 +1907,7 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, } if (tunnel) { + unsigned int hlen_orig = cih->ihl * 4; __be32 info = ic->un.gateway; __u8 type = ic->type; __u8 code = ic->code; @@ -1921,6 +1924,9 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, goto ignore_tunnel; offset2 -= ihl + sizeof(_icmph); skb_reset_network_header(skb); + /* Ensure the IP header is present in headroom */ + if (!pskb_may_pull(skb, hlen_ipip)) + goto ignore_tunnel; IP_VS_DBG(12, "ICMP for %s %pI4->%pI4: mtu=%u\n", outer_proto, &ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr, mtu); @@ -1936,8 +1942,8 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, if (dest_dst) mtu = dst_mtu(dest_dst->dst_cache); } - if (mtu > 68 + sizeof(struct iphdr)) - mtu -= sizeof(struct iphdr); + if (mtu > 68 + hlen_ipip + ulen) + mtu -= hlen_ipip + ulen; info = htonl(mtu); } /* Strip outer IP, ICMP and IPIP/UDP/GRE, go to IP header of @@ -1946,6 +1952,9 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, if (pskb_pull(skb, offset2) == NULL) goto ignore_tunnel; skb_reset_network_header(skb); + /* Ensure the IP header is present in headroom */ + if (!pskb_may_pull(skb, hlen_orig)) + goto ignore_tunnel; IP_VS_DBG(12, "Sending ICMP for %pI4->%pI4: t=%u, c=%u, i=%u\n", &ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr, type, code, ntohl(info)); @@ -2233,7 +2242,7 @@ ip_vs_in_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state IP_VS_DBG_PKT(11, af, pp, skb, iph.off, "Incoming packet"); ip_vs_in_stats(cp, skb); - ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pd); + ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pd, iph.len); if (cp->packet_xmit) ret = cp->packet_xmit(skb, cp, pp, &iph); /* do not touch skb anymore */ diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index 63c78a1f3918..c67317be17df 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -372,20 +372,15 @@ static const char *sctp_state_name(int state) static inline void set_sctp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp, - int direction, const struct sk_buff *skb) + int direction, const struct sk_buff *skb, + unsigned int iph_len) { struct sctp_chunkhdr _sctpch, *sch; unsigned char chunk_type; int event, next_state; - int ihl, cofs; + int cofs; -#ifdef CONFIG_IP_VS_IPV6 - ihl = cp->af == AF_INET ? ip_hdrlen(skb) : sizeof(struct ipv6hdr); -#else - ihl = ip_hdrlen(skb); -#endif - - cofs = ihl + sizeof(struct sctphdr); + cofs = iph_len + sizeof(struct sctphdr); sch = skb_header_pointer(skb, cofs, sizeof(_sctpch), &_sctpch); if (sch == NULL) return; @@ -468,10 +463,11 @@ set_sctp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp, static void sctp_state_transition(struct ip_vs_conn *cp, int direction, - const struct sk_buff *skb, struct ip_vs_proto_data *pd) + const struct sk_buff *skb, struct ip_vs_proto_data *pd, + unsigned int iph_len) { spin_lock_bh(&cp->lock); - set_sctp_state(pd, cp, direction, skb); + set_sctp_state(pd, cp, direction, skb, iph_len); spin_unlock_bh(&cp->lock); } diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c index 8cc0a8ce6241..f86b763efcc4 100644 --- a/net/netfilter/ipvs/ip_vs_proto_tcp.c +++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c @@ -579,17 +579,12 @@ set_tcp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp, static void tcp_state_transition(struct ip_vs_conn *cp, int direction, const struct sk_buff *skb, - struct ip_vs_proto_data *pd) + struct ip_vs_proto_data *pd, + unsigned int iph_len) { struct tcphdr _tcph, *th; -#ifdef CONFIG_IP_VS_IPV6 - int ihl = cp->af == AF_INET ? ip_hdrlen(skb) : sizeof(struct ipv6hdr); -#else - int ihl = ip_hdrlen(skb); -#endif - - th = skb_header_pointer(skb, ihl, sizeof(_tcph), &_tcph); + th = skb_header_pointer(skb, iph_len, sizeof(_tcph), &_tcph); if (th == NULL) return; diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c index f9de632e38cd..58f9e255927e 100644 --- a/net/netfilter/ipvs/ip_vs_proto_udp.c +++ b/net/netfilter/ipvs/ip_vs_proto_udp.c @@ -444,7 +444,8 @@ static const char * udp_state_name(int state) static void udp_state_transition(struct ip_vs_conn *cp, int direction, const struct sk_buff *skb, - struct ip_vs_proto_data *pd) + struct ip_vs_proto_data *pd, + unsigned int iph_len) { if (unlikely(!pd)) { pr_err("UDP no ns data\n"); diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 99c5b9d671a0..2a829b5e8240 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -127,12 +127,18 @@ static int flow_offload_fill_route(struct flow_offload *flow, switch (route->tuple[dir].xmit_type) { case FLOW_OFFLOAD_XMIT_DIRECT: + if (flow_tuple->tun_num) { + flow_tuple->dst_cache = dst; + flow_tuple->dst_cookie = + flow_offload_dst_cookie(flow_tuple); + } memcpy(flow_tuple->out.h_dest, route->tuple[dir].out.h_dest, ETH_ALEN); memcpy(flow_tuple->out.h_source, route->tuple[dir].out.h_source, ETH_ALEN); flow_tuple->out.ifidx = route->tuple[dir].out.ifindex; - dst_release(dst); + if (!flow_tuple->tun_num) + dst_release(dst); break; case FLOW_OFFLOAD_XMIT_XFRM: case FLOW_OFFLOAD_XMIT_NEIGH: @@ -152,9 +158,7 @@ static int flow_offload_fill_route(struct flow_offload *flow, static void nft_flow_dst_release(struct flow_offload *flow, enum flow_offload_tuple_dir dir) { - if (flow->tuplehash[dir].tuple.xmit_type == FLOW_OFFLOAD_XMIT_NEIGH || - flow->tuplehash[dir].tuple.xmit_type == FLOW_OFFLOAD_XMIT_XFRM) - dst_release(flow->tuplehash[dir].tuple.dst_cache); + dst_release(flow->tuplehash[dir].tuple.dst_cache); } void flow_offload_route_init(struct flow_offload *flow, @@ -345,10 +349,8 @@ int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow) nf_ct_refresh(flow->ct, NF_CT_DAY); - if (nf_flowtable_hw_offload(flow_table)) { - __set_bit(NF_FLOW_HW, &flow->flags); + if (nf_flowtable_hw_offload(flow_table)) nf_flow_offload_add(flow_table, flow); - } return 0; } @@ -369,7 +371,8 @@ void flow_offload_refresh(struct nf_flowtable *flow_table, test_bit(NF_FLOW_CLOSING, &flow->flags)) return; - nf_flow_offload_add(flow_table, flow); + if (test_bit(NF_FLOW_HW, &flow->flags)) + nf_flow_offload_refresh(flow_table, flow); } EXPORT_SYMBOL_GPL(flow_offload_refresh); diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c index 29e93ac1e2e4..0b78decce8a9 100644 --- a/net/netfilter/nf_flow_table_ip.c +++ b/net/netfilter/nf_flow_table_ip.c @@ -299,8 +299,7 @@ static bool nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu) static inline bool nf_flow_dst_check(struct flow_offload_tuple *tuple) { - if (tuple->xmit_type != FLOW_OFFLOAD_XMIT_NEIGH && - tuple->xmit_type != FLOW_OFFLOAD_XMIT_XFRM) + if (!tuple->dst_cache) return true; return dst_check(tuple->dst_cache, tuple->dst_cookie); @@ -590,10 +589,10 @@ static int nf_flow_pppoe_push(struct sk_buff *skb, u16 id, static int nf_flow_tunnel_ipip_push(struct net *net, struct sk_buff *skb, struct flow_offload_tuple *tuple, - __be32 *ip_daddr) + struct dst_entry *dst, __be32 *ip_daddr) { struct iphdr *iph = (struct iphdr *)skb_network_header(skb); - struct rtable *rt = dst_rtable(tuple->dst_cache); + struct rtable *rt = dst_rtable(dst); u8 tos = iph->tos, ttl = iph->ttl; __be16 frag_off = iph->frag_off; u32 headroom = sizeof(*iph); @@ -636,21 +635,22 @@ static int nf_flow_tunnel_ipip_push(struct net *net, struct sk_buff *skb, static int nf_flow_tunnel_v4_push(struct net *net, struct sk_buff *skb, struct flow_offload_tuple *tuple, - __be32 *ip_daddr) + struct dst_entry *dst, __be32 *ip_daddr) { if (tuple->tun_num) - return nf_flow_tunnel_ipip_push(net, skb, tuple, ip_daddr); + return nf_flow_tunnel_ipip_push(net, skb, tuple, dst, ip_daddr); return 0; } static int nf_flow_tunnel_ip6ip6_push(struct net *net, struct sk_buff *skb, struct flow_offload_tuple *tuple, + struct dst_entry *dst, struct in6_addr **ip6_daddr) { struct ipv6hdr *ip6h = (struct ipv6hdr *)skb_network_header(skb); - struct rtable *rt = dst_rtable(tuple->dst_cache); __u8 dsfield = ipv6_get_dsfield(ip6h); + struct rtable *rt = dst_rtable(dst); struct flowi6 fl6 = { .daddr = tuple->tun.src_v6, .saddr = tuple->tun.dst_v6, @@ -696,10 +696,11 @@ static int nf_flow_tunnel_ip6ip6_push(struct net *net, struct sk_buff *skb, static int nf_flow_tunnel_v6_push(struct net *net, struct sk_buff *skb, struct flow_offload_tuple *tuple, + struct dst_entry *dst, struct in6_addr **ip6_daddr) { if (tuple->tun_num) - return nf_flow_tunnel_ip6ip6_push(net, skb, tuple, ip6_daddr); + return nf_flow_tunnel_ip6ip6_push(net, skb, tuple, dst, ip6_daddr); return 0; } @@ -842,7 +843,8 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, other_tuple = &flow->tuplehash[!dir].tuple; ip_daddr = other_tuple->src_v4.s_addr; - if (nf_flow_tunnel_v4_push(state->net, skb, other_tuple, &ip_daddr) < 0) + if (nf_flow_tunnel_v4_push(state->net, skb, other_tuple, + tuplehash->tuple.dst_cache, &ip_daddr) < 0) return NF_DROP; switch (tuplehash->tuple.xmit_type) { @@ -1158,6 +1160,7 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, ip6_daddr = &other_tuple->src_v6; if (nf_flow_tunnel_v6_push(state->net, skb, other_tuple, + tuplehash->tuple.dst_cache, &ip6_daddr) < 0) return NF_DROP; diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index 002ec15d988b..801a3dd9ceea 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -1101,9 +1101,17 @@ nf_flow_offload_work_alloc(struct nf_flowtable *flowtable, return offload; } +static bool nf_flow_offload_unsupported(struct flow_offload *flow) +{ + if (flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.tun_num || + flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.tun_num) + return true; -void nf_flow_offload_add(struct nf_flowtable *flowtable, - struct flow_offload *flow) + return false; +} + +void nf_flow_offload_refresh(struct nf_flowtable *flowtable, + struct flow_offload *flow) { struct flow_offload_work *offload; @@ -1114,6 +1122,16 @@ void nf_flow_offload_add(struct nf_flowtable *flowtable, flow_offload_queue_work(offload); } +void nf_flow_offload_add(struct nf_flowtable *flowtable, + struct flow_offload *flow) +{ + if (nf_flow_offload_unsupported(flow)) + return; + + set_bit(NF_FLOW_HW, &flow->flags); + nf_flow_offload_refresh(flowtable, flow); +} + void nf_flow_offload_del(struct nf_flowtable *flowtable, struct flow_offload *flow) { diff --git a/net/netfilter/nf_nat_sip.c b/net/netfilter/nf_nat_sip.c index 67c04d8143ab..aea02f6aff09 100644 --- a/net/netfilter/nf_nat_sip.c +++ b/net/netfilter/nf_nat_sip.c @@ -289,13 +289,24 @@ static unsigned int nf_nat_sip(struct sk_buff *skb, unsigned int protoff, /* Mangle destination port for Cisco phones, then fix up checksums */ if (dir == IP_CT_DIR_REPLY && ct_sip_info->forced_dport) { + int doff = *dptr - (const char *)skb->data; struct udphdr *uh; + if (doff <= 0) { + DEBUG_NET_WARN_ON_ONCE(1); + return NF_DROP; + } + + /* ct_sip_info->forced_dport only expected with UDP */ + if (nf_ct_protonum(ct) != IPPROTO_UDP) + return NF_DROP; + if (skb_ensure_writable(skb, skb->len)) { nf_ct_helper_log(skb, ct, "cannot mangle packet"); return NF_DROP; } + *dptr = skb->data + doff; uh = (void *)skb->data + protoff; uh->dest = ct_sip_info->forced_dport; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 4884f7f7aaee..a9eaf9455c77 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -6563,6 +6563,9 @@ static int nft_get_set_elem(struct nft_ctx *ctx, const struct nft_set *set, if (err < 0) return err; + if (!elem.priv) + return 0; + err = -ENOMEM; skb = nlmsg_new(NLMSG_GOODSIZE, GFP_ATOMIC); if (skb == NULL) diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c index 2cbcca9110db..f062ac210343 100644 --- a/net/netfilter/nfnetlink_cthelper.c +++ b/net/netfilter/nfnetlink_cthelper.c @@ -316,6 +316,8 @@ nfnl_cthelper_update_policy_one(const struct nf_conntrack_expect_policy *policy, new_policy->max_expected = ntohl(nla_get_be32(tb[NFCTH_POLICY_EXPECT_MAX])); + if (!new_policy->max_expected) + new_policy->max_expected = NF_CT_EXPECT_MAX_CNT; if (new_policy->max_expected > NF_CT_EXPECT_MAX_CNT) return -EINVAL; diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index fa3657599861..5fee61b3813c 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -676,7 +676,7 @@ __build_packet_message(struct nfnl_log_net *log, goto nla_put_failure; if (skb_copy_bits(skb, 0, nla_data(nla), data_len)) - BUG(); + goto nla_put_failure; } nlh->nlmsg_len = inst->skb->tail - old_tail; @@ -698,6 +698,21 @@ static const struct nf_loginfo default_loginfo = { }, }; +static unsigned int nfulnl_get_copy_len(const struct nf_loginfo *li, + const struct sk_buff *skb, + unsigned int copy_len) +{ + unsigned int len = skb->len; + + if ((li->u.ulog.flags & NF_LOG_F_COPY_LEN) && + li->u.ulog.copy_len < copy_len) + copy_len = li->u.ulog.copy_len; + if (!skb_frags_readable(skb)) + len = skb_headlen(skb); + + return min(len, copy_len); +} + /* log handler for internal netfilter logging api */ static void nfulnl_log_packet(struct net *net, @@ -790,14 +805,7 @@ nfulnl_log_packet(struct net *net, break; case NFULNL_COPY_PACKET: - data_len = inst->copy_range; - if ((li->u.ulog.flags & NF_LOG_F_COPY_LEN) && - (li->u.ulog.copy_len < data_len)) - data_len = li->u.ulog.copy_len; - - if (data_len > skb->len) - data_len = skb->len; - + data_len = nfulnl_get_copy_len(li, skb, inst->copy_range); size += nla_total_size(data_len); break; diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 35d4c6c628ff..b8aaf39cb4d8 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -690,6 +690,17 @@ static int nfqnl_put_master_ifindex(struct sk_buff *nlskb, int attr, } #endif +static unsigned int nfqnl_get_data_len(const struct sk_buff *entskb, + unsigned int copy_range) +{ + unsigned int data_len = entskb->len; + + if (!skb_frags_readable(entskb)) + data_len = skb_headlen(entskb); + + return min(data_len, copy_range); +} + static struct sk_buff * nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, struct nf_queue_entry *entry, @@ -755,10 +766,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, nf_queue_checksum_help(entskb)) return NULL; - data_len = READ_ONCE(queue->copy_range); - if (data_len > entskb->len) - data_len = entskb->len; - + data_len = nfqnl_get_data_len(entskb, READ_ONCE(queue->copy_range)); hlen = skb_zerocopy_headlen(entskb); hlen = min_t(unsigned int, hlen, data_len); size += sizeof(struct nlattr) + hlen; diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index ba512e94b402..19887439847d 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -103,13 +103,13 @@ void nft_lookup_eval(const struct nft_expr *expr, bool found; ext = nft_set_do_lookup(net, set, ®s->data[priv->sreg]); + if (!ext) + ext = nft_set_catchall_lookup(net, set); + found = !!ext ^ priv->invert; if (!found) { - ext = nft_set_catchall_lookup(net, set); - if (!ext) { - regs->verdict.code = NFT_BREAK; - return; - } + regs->verdict.code = NFT_BREAK; + return; } if (ext) { diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 018bbb6df4ce..6222e9bb57bc 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -184,10 +184,14 @@ nft_rbtree_get(const struct net *net, const struct nft_set *set, if (!interval || nft_set_elem_expired(interval->from)) return ERR_PTR(-ENOENT); - if (flags & NFT_SET_ELEM_INTERVAL_END) + if (flags & NFT_SET_ELEM_INTERVAL_END) { + if (!interval->to) + return NULL; + rbe = container_of(interval->to, struct nft_rbtree_elem, ext); - else + } else { rbe = container_of(interval->from, struct nft_rbtree_elem, ext); + } return &rbe->priv; } diff --git a/net/netfilter/xt_connmark.c b/net/netfilter/xt_connmark.c index 4277084de2e7..2cf27f7d59b9 100644 --- a/net/netfilter/xt_connmark.c +++ b/net/netfilter/xt_connmark.c @@ -112,6 +112,16 @@ static int connmark_tg_check(const struct xt_tgchk_param *par) return ret; } +static int connmark_tg_check_v2(const struct xt_tgchk_param *par) +{ + const struct xt_connmark_tginfo2 *info = par->targinfo; + + if (info->shift_dir > D_SHIFT_RIGHT || info->shift_bits >= 32) + return -EINVAL; + + return connmark_tg_check(par); +} + static void connmark_tg_destroy(const struct xt_tgdtor_param *par) { nf_ct_netns_put(par->net, par->family); @@ -162,7 +172,7 @@ static struct xt_target connmark_tg_reg[] __read_mostly = { .name = "CONNMARK", .revision = 2, .family = NFPROTO_IPV4, - .checkentry = connmark_tg_check, + .checkentry = connmark_tg_check_v2, .target = connmark_tg_v2, .targetsize = sizeof(struct xt_connmark_tginfo2), .destroy = connmark_tg_destroy, @@ -183,7 +193,7 @@ static struct xt_target connmark_tg_reg[] __read_mostly = { .name = "CONNMARK", .revision = 2, .family = NFPROTO_IPV6, - .checkentry = connmark_tg_check, + .checkentry = connmark_tg_check_v2, .target = connmark_tg_v2, .targetsize = sizeof(struct xt_connmark_tginfo2), .destroy = connmark_tg_destroy, diff --git a/net/netfilter/xt_rateest.c b/net/netfilter/xt_rateest.c index b1d736c15fcb..7c05b6342578 100644 --- a/net/netfilter/xt_rateest.c +++ b/net/netfilter/xt_rateest.c @@ -16,7 +16,7 @@ xt_rateest_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_rateest_match_info *info = par->matchinfo; struct gnet_stats_rate_est64 sample = {0}; - u_int32_t bps1, bps2, pps1, pps2; + u64 bps1, bps2, pps1, pps2; bool ret = true; gen_estimator_read(&info->est1->rate_est, &sample); diff --git a/net/netfilter/xt_u32.c b/net/netfilter/xt_u32.c index 117d4615d668..dabbaa742874 100644 --- a/net/netfilter/xt_u32.c +++ b/net/netfilter/xt_u32.c @@ -14,8 +14,8 @@ #include #include -static bool u32_match_it(const struct xt_u32 *data, - const struct sk_buff *skb) +static int u32_match_it(const struct xt_u32 *data, + const struct sk_buff *skb) { const struct xt_u32_test *ct; unsigned int testind; @@ -40,7 +40,8 @@ static bool u32_match_it(const struct xt_u32 *data, return false; if (skb_copy_bits(skb, pos, &n, sizeof(n)) < 0) - BUG(); + return -1; + val = ntohl(n); nnums = ct->nnums; @@ -68,7 +69,7 @@ static bool u32_match_it(const struct xt_u32 *data, if (skb_copy_bits(skb, at + pos, &n, sizeof(n)) < 0) - BUG(); + return -1; val = ntohl(n); break; } @@ -90,9 +91,14 @@ static bool u32_match_it(const struct xt_u32 *data, static bool u32_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_u32 *data = par->matchinfo; - bool ret; + int ret; ret = u32_match_it(data, skb); + if (ret < 0) { + par->hotdrop = true; + return false; + } + return ret ^ data->invert; } @@ -100,7 +106,7 @@ static int u32_mt_checkentry(const struct xt_mtchk_param *par) { const struct xt_u32 *data = par->matchinfo; const struct xt_u32_test *ct; - unsigned int i; + unsigned int i, j; if (data->ntests > ARRAY_SIZE(data->tests)) return -EINVAL; @@ -111,6 +117,16 @@ static int u32_mt_checkentry(const struct xt_mtchk_param *par) if (ct->nnums > ARRAY_SIZE(ct->location) || ct->nvalues > ARRAY_SIZE(ct->value)) return -EINVAL; + + for (j = 1; j < ct->nnums; ++j) { + switch (ct->location[j].nextop) { + case XT_U32_LEFTSH: + case XT_U32_RIGHTSH: + if (ct->location[j].number >= 32) + return -EINVAL; + break; + } + } } return 0; diff --git a/net/sched/act_api.c b/net/sched/act_api.c index b68be143a067..f141634df214 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -148,10 +148,15 @@ static void offload_action_hw_count_dec(struct tc_action *act, static unsigned int tcf_offload_act_num_actions_single(struct tc_action *act) { - if (is_tcf_pedit(act)) - return tcf_pedit_nkeys(act); - else - return 1; + unsigned int count; + + if (is_tcf_pedit(act)) { + spin_lock_bh(&act->tcfa_lock); + count = tcf_pedit_nkeys_locked(act); + spin_unlock_bh(&act->tcfa_lock); + return count; + } + return 1; } static bool tc_act_skip_hw(u32 flags) diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index 0d652dea4a69..d4d47a9921f4 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -567,9 +567,18 @@ static int tcf_pedit_offload_act_setup(struct tc_action *act, void *entry_data, { if (bind) { struct flow_action_entry *entry = entry_data; + int nkeys = tcf_pedit_nkeys_locked(act); int k; - for (k = 0; k < tcf_pedit_nkeys(act); k++) { + /* If the required keys exceed the remaining capacity return + * -ENOSPC to abort the offload and fallback to software. + */ + if (nkeys > *index_inc) { + NL_SET_ERR_MSG_MOD(extack, "Not enough space to offload all pedit keys"); + return -ENOSPC; + } + + for (k = 0; k < nkeys; k++) { switch (tcf_pedit_cmd(act, k)) { case TCA_PEDIT_KEY_EX_CMD_SET: entry->id = FLOW_ACTION_MANGLE; @@ -606,7 +615,7 @@ static int tcf_pedit_offload_act_setup(struct tc_action *act, void *entry_data, return -EOPNOTSUPP; } - for (k = 1; k < tcf_pedit_nkeys(act); k++) { + for (k = 1; k < tcf_pedit_nkeys_locked(act); k++) { if (cmd != tcf_pedit_cmd(act, k)) { NL_SET_ERR_MSG_MOD(extack, "Unsupported pedit command offload"); return -EOPNOTSUPP; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 3e67600a4a1a..ffeea6db8337 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -3886,12 +3886,21 @@ int tc_setup_action(struct flow_action *flow_action, entry = &flow_action->entries[j]; spin_lock_bh(&act->tcfa_lock); + + /* Abort the offload if we have exhausted the allocated capacity */ + if (j >= flow_action->num_entries) { + NL_SET_ERR_MSG_MOD(extack, "Flow action buffer overflow"); + err = -ENOSPC; + goto err_out_locked; + } + err = tcf_act_get_user_cookie(entry, act); if (err) goto err_out_locked; - index = 0; - err = tc_setup_offload_act(act, entry, &index, extack); + index = flow_action->num_entries - j; + err = tc_setup_offload_act(act, entry, &index, + extack); if (err) goto err_out_locked; @@ -3945,10 +3954,13 @@ unsigned int tcf_exts_num_actions(struct tcf_exts *exts) int i; tcf_exts_for_each_action(i, act, exts) { - if (is_tcf_pedit(act)) - num_acts += tcf_pedit_nkeys(act); - else + if (is_tcf_pedit(act)) { + spin_lock_bh(&act->tcfa_lock); + num_acts += tcf_pedit_nkeys_locked(act); + spin_unlock_bh(&act->tcfa_lock); + } else { num_acts++; + } } return num_acts; } diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index a3c185505afc..f78f8e950776 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -1389,10 +1389,7 @@ static u32 cake_calc_overhead(struct cake_sched_data *qd, u32 len, u32 off) if (qd->min_netlen > len) WRITE_ONCE(qd->min_netlen, len); - len += q->rate_overhead; - - if (len < q->rate_mpu) - len = q->rate_mpu; + len = max((s32)len + q->rate_overhead, (s32)q->rate_mpu); if (q->atm_mode == CAKE_ATM_ATM) { len += 47; diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c index 24ba31f8c828..5c42a29a981c 100644 --- a/net/sched/sch_teql.c +++ b/net/sched/sch_teql.c @@ -311,14 +311,14 @@ static netdev_tx_t teql_master_xmit(struct sk_buff *skb, struct net_device *dev) int subq = skb_get_queue_mapping(skb); struct sk_buff *skb_res = NULL; - rcu_read_lock_bh(); - - start = rcu_dereference_bh(master->slaves); - restart: nores = 0; busy = 0; + rcu_read_lock(); + + start = rcu_dereference(master->slaves); + q = start; if (!q) goto drop; @@ -345,17 +345,17 @@ static netdev_tx_t teql_master_xmit(struct sk_buff *skb, struct net_device *dev) netdev_start_xmit(skb, slave, slave_txq, false) == NETDEV_TX_OK) { __netif_tx_unlock(slave_txq); - spin_lock_bh(&master->slaves_lock); + spin_lock(&master->slaves_lock); if (rcu_dereference_protected(master->slaves, lockdep_is_held(&master->slaves_lock)) == q) rcu_assign_pointer(master->slaves, rcu_dereference_protected(NEXT_SLAVE(q), lockdep_is_held(&master->slaves_lock))); - spin_unlock_bh(&master->slaves_lock); + spin_unlock(&master->slaves_lock); netif_wake_queue(dev); master->tx_packets++; master->tx_bytes += length; - rcu_read_unlock_bh(); + rcu_read_unlock(); return NETDEV_TX_OK; } __netif_tx_unlock(slave_txq); @@ -364,37 +364,38 @@ static netdev_tx_t teql_master_xmit(struct sk_buff *skb, struct net_device *dev) busy = 1; break; case 1: - spin_lock_bh(&master->slaves_lock); + spin_lock(&master->slaves_lock); if (rcu_dereference_protected(master->slaves, lockdep_is_held(&master->slaves_lock)) == q) rcu_assign_pointer(master->slaves, rcu_dereference_protected(NEXT_SLAVE(q), lockdep_is_held(&master->slaves_lock))); - spin_unlock_bh(&master->slaves_lock); - rcu_read_unlock_bh(); + spin_unlock(&master->slaves_lock); + rcu_read_unlock(); return NETDEV_TX_OK; default: nores = 1; break; } __skb_pull(skb, skb_network_offset(skb)); - } while ((q = rcu_dereference_bh(NEXT_SLAVE(q))) != start); + } while ((q = rcu_dereference(NEXT_SLAVE(q))) != start); if (nores && skb_res == NULL) { skb_res = skb; + rcu_read_unlock(); goto restart; } if (busy) { netif_stop_queue(dev); - rcu_read_unlock_bh(); + rcu_read_unlock(); return NETDEV_TX_BUSY; } master->tx_errors++; drop: master->tx_dropped++; - rcu_read_unlock_bh(); + rcu_read_unlock(); dev_kfree_skb(skb); return NETDEV_TX_OK; } diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c index 619b3bab3824..32d6d03df321 100644 --- a/net/smc/smc_cdc.c +++ b/net/smc/smc_cdc.c @@ -470,9 +470,9 @@ static void smc_cdc_rx_handler(struct ib_wc *wc, void *buf) { struct smc_link *link = (struct smc_link *)wc->qp->qp_context; struct smc_cdc_msg *cdc = buf; + struct smc_sock *smc = NULL; struct smc_connection *conn; struct smc_link_group *lgr; - struct smc_sock *smc; if (wc->byte_len < offsetof(struct smc_cdc_msg, reserved)) return; /* short message */ @@ -483,21 +483,26 @@ static void smc_cdc_rx_handler(struct ib_wc *wc, void *buf) lgr = smc_get_lgr(link); read_lock_bh(&lgr->conns_lock); conn = smc_lgr_find_conn(ntohl(cdc->token), lgr); - read_unlock_bh(&lgr->conns_lock); - if (!conn || conn->out_of_sync) + if (!conn || conn->out_of_sync) { + read_unlock_bh(&lgr->conns_lock); return; + } smc = container_of(conn, struct smc_sock, conn); + sock_hold(&smc->sk); + read_unlock_bh(&lgr->conns_lock); if (cdc->prod_flags.failover_validation) { smc_cdc_msg_validate(smc, cdc, link); - return; + goto out; } if (smc_cdc_before(ntohs(cdc->seqno), conn->local_rx_ctrl.seqno)) /* received seqno is old */ - return; + goto out; smc_cdc_msg_recv(smc, cdc); +out: + sock_put(&smc->sk); } static struct smc_wr_rx_handler smc_cdc_rx_handlers[] = { diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index bc8ca470718b..efa26899bc7d 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1026,8 +1026,23 @@ rpc_free_auth(struct rpc_clnt *clnt) return NULL; } -/* - * Release reference to the RPC client +/** + * rpc_hold_client - acquire a reference on an rpc_clnt + * @clnt: rpc_clnt to pin + * + * Pairs with rpc_release_client(). + */ +void rpc_hold_client(struct rpc_clnt *clnt) +{ + refcount_inc(&clnt->cl_count); +} + +/** + * rpc_release_client - release a reference on an rpc_clnt + * @clnt: rpc_clnt to release + * + * Pairs with rpc_hold_client(). The rpc_clnt's resources are + * freed once its reference count drops to zero. */ void rpc_release_client(struct rpc_clnt *clnt) diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 2e1fe6013361..359407aae03e 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -2734,8 +2734,11 @@ static void xs_tcp_tls_setup_socket(struct work_struct *work) lower_xprt = rcu_dereference(lower_clnt->cl_xprt); rcu_read_unlock(); - if (wait_on_bit_lock(&lower_xprt->state, XPRT_LOCKED, TASK_KILLABLE)) + if (wait_on_bit_lock(&lower_xprt->state, XPRT_LOCKED, TASK_KILLABLE)) { + /* XPRT_LOCKED was never acquired. */ + rpc_shutdown_client(lower_clnt); goto out_unlock; + } status = xs_tls_handshake_sync(lower_xprt, &upper_xprt->xprtsec); if (status) { @@ -2758,6 +2761,7 @@ static void xs_tcp_tls_setup_socket(struct work_struct *work) out_unlock: current_restore_flags(pflags, PF_MEMALLOC); upper_transport->clnt = NULL; + rpc_release_client(upper_clnt); xprt_unlock_connect(upper_xprt, upper_transport); return; @@ -2805,7 +2809,15 @@ static void xs_connect(struct rpc_xprt *xprt, struct rpc_task *task) } else dprintk("RPC: xs_connect scheduled xprt %p\n", xprt); - transport->clnt = task->tk_client; + /* + * Only the TLS connect_worker reads transport->clnt; pinning + * the upper rpc_clnt unconditionally would form a cycle with + * cl_xprt and prevent xprt destruction. + */ + if (xprt->xprtsec.policy != RPC_XPRTSEC_NONE) { + rpc_hold_client(task->tk_client); + transport->clnt = task->tk_client; + } queue_delayed_work(xprtiod_workqueue, &transport->connect_worker, delay); diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 9324e4ed20a3..d4afc90fd796 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -2115,6 +2115,17 @@ int tls_sw_read_sock(struct sock *sk, read_descriptor_t *desc, goto read_sock_requeue; } + /* An empty data record (legal in TLS 1.3) gives a zero + * read_actor return, indistinguishable from the consumer + * stalling; the used <= 0 path would requeue it at the + * head of rx_list and block all later records. Consume it + * here instead. + */ + if (rxm->full_len == 0) { + consume_skb(skb); + continue; + } + used = read_actor(desc, skb, rxm->offset, rxm->full_len); if (used <= 0) { if (!copied) diff --git a/samples/damon/mtier.c b/samples/damon/mtier.c index eb1143de8df1..3785b0c7ffb1 100644 --- a/samples/damon/mtier.c +++ b/samples/damon/mtier.c @@ -120,6 +120,9 @@ static struct damon_ctx *damon_sample_mtier_build_ctx(bool promote) addr.end = promote ? node1_end_addr : node0_end_addr; } + if (addr.start >= addr.end) + goto free_out; + range.start = addr.start; range.end = addr.end; diff --git a/samples/ftrace/ftrace-ops.c b/samples/ftrace/ftrace-ops.c index 68d6685c80bd..152ffc1a30b6 100644 --- a/samples/ftrace/ftrace-ops.c +++ b/samples/ftrace/ftrace-ops.c @@ -232,8 +232,8 @@ static int __init ftrace_ops_sample_init(void) ops_destroy(ops_irrelevant, nr_ops_irrelevant); /* - * The benchmark completed sucessfully, but there's no reason to keep - * the module around. Return an error do the user doesn't have to + * The benchmark completed successfully, but there's no reason to keep + * the module around. Return an error so the user doesn't have to * manually unload the module. */ return -EINVAL; diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 1a713d96206f..70a3388c047d 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -4994,9 +4994,8 @@ static int selinux_socket_socketpair(struct socket *socka, Need to determine whether we should perform a name_bind permission check between the socket and the port number. */ -static int selinux_socket_bind(struct socket *sock, struct sockaddr *address, int addrlen) +static int __selinux_socket_bind(struct sock *sk, struct sockaddr *address, int addrlen) { - struct sock *sk = sock->sk; struct sk_security_struct *sksec = selinux_sock(sk); u16 family; int err; @@ -5126,13 +5125,17 @@ static int selinux_socket_bind(struct socket *sock, struct sockaddr *address, in return -EAFNOSUPPORT; } +static int selinux_socket_bind(struct socket *sock, struct sockaddr *address, int addrlen) +{ + return __selinux_socket_bind(sock->sk, address, addrlen); +} + /* This supports connect(2) and SCTP connect services such as sctp_connectx(3) * and sctp_sendmsg(3) as described in Documentation/security/SCTP.rst */ -static int selinux_socket_connect_helper(struct socket *sock, +static int selinux_socket_connect_helper(struct sock *sk, struct sockaddr *address, int addrlen) { - struct sock *sk = sock->sk; struct sk_security_struct *sksec = selinux_sock(sk); int err; @@ -5221,7 +5224,7 @@ static int selinux_socket_connect(struct socket *sock, int err; struct sock *sk = sock->sk; - err = selinux_socket_connect_helper(sock, address, addrlen); + err = selinux_socket_connect_helper(sk, address, addrlen); if (err) return err; @@ -5262,7 +5265,24 @@ static int selinux_socket_accept(struct socket *sock, struct socket *newsock) static int selinux_socket_sendmsg(struct socket *sock, struct msghdr *msg, int size) { - return sock_has_perm(sock->sk, SOCKET__WRITE); + int rc; + struct sockaddr *const addr = msg->msg_name; + const int addrlen = msg->msg_namelen; + + rc = sock_has_perm(sock->sk, SOCKET__WRITE); + if (rc) + return rc; + + if (addr && (msg->msg_flags & MSG_FASTOPEN) && + (sk_is_tcp(sock->sk) || + (sk_is_inet(sock->sk) && sock->sk->sk_type == SOCK_STREAM && + sock->sk->sk_protocol == IPPROTO_MPTCP))) { + rc = selinux_socket_connect(sock, addr, addrlen); + if (rc) + return rc; + } + + return 0; } static int selinux_socket_recvmsg(struct socket *sock, struct msghdr *msg, @@ -5706,13 +5726,11 @@ static int selinux_sctp_bind_connect(struct sock *sk, int optname, int len, err = 0, walk_size = 0; void *addr_buf; struct sockaddr *addr; - struct socket *sock; if (!selinux_policycap_extsockclass()) return 0; /* Process one or more addresses that may be IPv4 or IPv6 */ - sock = sk->sk_socket; addr_buf = address; while (walk_size < addrlen) { @@ -5741,14 +5759,14 @@ static int selinux_sctp_bind_connect(struct sock *sk, int optname, case SCTP_PRIMARY_ADDR: case SCTP_SET_PEER_PRIMARY_ADDR: case SCTP_SOCKOPT_BINDX_ADD: - err = selinux_socket_bind(sock, addr, len); + err = __selinux_socket_bind(sk, addr, len); break; /* Connect checks */ case SCTP_SOCKOPT_CONNECTX: case SCTP_PARAM_SET_PRIMARY: case SCTP_PARAM_ADD_IP: case SCTP_SENDMSG_CONNECT: - err = selinux_socket_connect_helper(sock, addr, len); + err = selinux_socket_connect_helper(sk, addr, len); if (err) return err; diff --git a/tools/include/linux/overflow.h b/tools/include/linux/overflow.h index 3427d7880326..98963688143f 100644 --- a/tools/include/linux/overflow.h +++ b/tools/include/linux/overflow.h @@ -1,4 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 OR MIT */ +#include #ifndef __LINUX_OVERFLOW_H #define __LINUX_OVERFLOW_H diff --git a/tools/testing/selftests/arm64/gcs/libc-gcs.c b/tools/testing/selftests/arm64/gcs/libc-gcs.c index 72e82bfbecc9..ddb0b2b20155 100644 --- a/tools/testing/selftests/arm64/gcs/libc-gcs.c +++ b/tools/testing/selftests/arm64/gcs/libc-gcs.c @@ -130,7 +130,7 @@ TEST(gcs_find_terminator) * We can access a GCS via ptrace * * This could usefully have a fixture but note that each test is - * fork()ed into a new child whcih causes issues. Might be better to + * fork()ed into a new child which causes issues. Might be better to * lift at least some of this out into a separate, non-harness, test * program. */ diff --git a/tools/testing/selftests/arm64/pauth/pac.c b/tools/testing/selftests/arm64/pauth/pac.c index 67d138057707..f4b859c75a5a 100644 --- a/tools/testing/selftests/arm64/pauth/pac.c +++ b/tools/testing/selftests/arm64/pauth/pac.c @@ -292,7 +292,7 @@ TEST(single_thread_different_keys) /* * fork() does not change keys. Only exec() does so call a worker program. - * Its only job is to sign a value and report back the resutls + * Its only job is to sign a value and report back the results */ TEST(exec_changed_keys) { diff --git a/tools/testing/selftests/gpio/.gitignore b/tools/testing/selftests/gpio/.gitignore index ededb077a3a6..16f74de479f1 100644 --- a/tools/testing/selftests/gpio/.gitignore +++ b/tools/testing/selftests/gpio/.gitignore @@ -2,3 +2,4 @@ gpio-mockup-cdev gpio-chip-info gpio-line-name +gpio-cdev-uaf diff --git a/tools/testing/selftests/hid/Makefile b/tools/testing/selftests/hid/Makefile index 96071b4800e8..2f423de83147 100644 --- a/tools/testing/selftests/hid/Makefile +++ b/tools/testing/selftests/hid/Makefile @@ -24,7 +24,7 @@ CXX ?= $(CROSS_COMPILE)g++ HOSTPKG_CONFIG := pkg-config -CFLAGS += -g -O0 -rdynamic -Wall -Werror -I$(OUTPUT) +CFLAGS += -g -O0 -rdynamic -Wall -Werror -I$(OUTPUT) $(KHDR_INCLUDES) CFLAGS += -I$(OUTPUT)/tools/include LDLIBS += -lelf -lz -lrt -lpthread diff --git a/tools/testing/selftests/hid/hid_bpf.c b/tools/testing/selftests/hid/hid_bpf.c index 1e979fb3542b..b851339308c2 100644 --- a/tools/testing/selftests/hid/hid_bpf.c +++ b/tools/testing/selftests/hid/hid_bpf.c @@ -86,6 +86,20 @@ static void load_programs(const struct test_program programs[], self->skel = hid__open(); ASSERT_OK_PTR(self->skel) TEARDOWN_LOG("Error while calling hid__open"); + /* + * Disable all struct_ops maps by default so libbpf does not autoload + * programs referenced by maps that are unrelated to the current test. + */ + bpf_object__for_each_map(iter_map, *self->skel->skeleton->obj) { + if (bpf_map__type(iter_map) == BPF_MAP_TYPE_STRUCT_OPS) { + err = bpf_map__set_autocreate(iter_map, false); + ASSERT_OK(err) TH_LOG("can not disable struct_ops map '%s'", + bpf_map__name(iter_map)); + } + + bpf_map__set_autoattach(iter_map, false); + } + for (int i = 0; i < progs_count; i++) { struct bpf_program *prog; struct bpf_map *map; @@ -102,6 +116,10 @@ static void load_programs(const struct test_program programs[], ASSERT_OK_PTR(map) TH_LOG("can not find struct_ops by name '%s'", programs[i].name + 4); + err = bpf_map__set_autocreate(map, true); + ASSERT_OK(err) TH_LOG("can not enable struct_ops map '%s'", + programs[i].name + 4); + /* hid_id is the first field of struct hid_bpf_ops */ ops_hid_id = bpf_map__initial_value(map, NULL); ASSERT_OK_PTR(ops_hid_id) TH_LOG("unable to retrieve struct_ops data"); @@ -109,13 +127,6 @@ static void load_programs(const struct test_program programs[], *ops_hid_id = self->hid.hid_id; } - /* we disable the auto-attach feature of all maps because we - * only want the tested one to be manually attached in the next - * call to bpf_map__attach_struct_ops() - */ - bpf_object__for_each_map(iter_map, *self->skel->skeleton->obj) - bpf_map__set_autoattach(iter_map, false); - err = hid__load(self->skel); ASSERT_OK(err) TH_LOG("hid_skel_load failed: %d", err); @@ -887,6 +898,17 @@ TEST_F(hid_bpf, test_rdesc_fixup) ASSERT_EQ(rpt_desc.value[4], 0x42); } +TEST_F(hid_bpf, test_rdesc_fixup_get_data_overflow) +{ + const struct test_program progs[] = { + { .name = "hid_rdesc_fixup_get_data_overflow" }, + }; + + LOAD_PROGRAMS(progs); + + ASSERT_EQ(self->skel->bss->get_data_overflow_check, 1); +} + static int libbpf_print_fn(enum libbpf_print_level level, const char *format, va_list args) { diff --git a/tools/testing/selftests/hid/progs/hid.c b/tools/testing/selftests/hid/progs/hid.c index 5ecc845ef792..b21fbb13c926 100644 --- a/tools/testing/selftests/hid/progs/hid.c +++ b/tools/testing/selftests/hid/progs/hid.c @@ -13,6 +13,7 @@ struct attach_prog_args { __u64 callback_check = 52; __u64 callback2_check = 52; +__u64 get_data_overflow_check; SEC("?struct_ops/hid_device_event") int BPF_PROG(hid_first_event, struct hid_bpf_ctx *hid_ctx, enum hid_report_type type) @@ -240,6 +241,20 @@ struct hid_bpf_ops rdesc_fixup = { .hid_rdesc_fixup = (void *)hid_rdesc_fixup, }; +SEC("?struct_ops.s/hid_rdesc_fixup") +int BPF_PROG(hid_rdesc_fixup_get_data_overflow, struct hid_bpf_ctx *hid_ctx) +{ + if (!hid_bpf_get_data(hid_ctx, 2 /* offset */, ~0ULL /* size */)) + get_data_overflow_check = 1; + + return 0; +} + +SEC(".struct_ops.link") +struct hid_bpf_ops rdesc_fixup_get_data_overflow = { + .hid_rdesc_fixup = (void *)hid_rdesc_fixup_get_data_overflow, +}; + SEC("?struct_ops/hid_device_event") int BPF_PROG(hid_test_insert1, struct hid_bpf_ctx *hid_ctx, enum hid_report_type type) { diff --git a/tools/testing/selftests/hid/tests/test_multitouch.py b/tools/testing/selftests/hid/tests/test_multitouch.py index fa4fb2054bd4..7897340118b4 100644 --- a/tools/testing/selftests/hid/tests/test_multitouch.py +++ b/tools/testing/selftests/hid/tests/test_multitouch.py @@ -513,6 +513,79 @@ class SmartTechDigitizer(Digitizer): return absinfo is not None and absinfo.resolution == 3 +class MinWin8TSParallelBigContactMax(Digitizer): + """A parallel Win8 touchscreen that advertises a ContactCountMaximum much + larger than the number of contacts it actually reports. + + Such firmware makes the driver allocate that many input slots (up to 255) + while the input report only carries a few contacts. This is what used to + drive the per-slot bit operations on mt_io_flags out of bounds. The number + of contacts a HID report can describe is limited by the descriptor size, + so a large ContactCountMaximum can only be expressed this way, decoupled + from the number of finger collections.""" + + def __init__(self, n_fingers=5, contact_max=250): + self.phys_max = 120, 90 + rdesc_finger_str = f""" + Usage Page (Digitizers) + Usage (Finger) + Collection (Logical) + Report Size (1) + Report Count (1) + Logical Minimum (0) + Logical Maximum (1) + Usage (Tip Switch) + Input (Data,Var,Abs) + Report Size (7) + Logical Maximum (127) + Input (Cnst,Var,Abs) + Report Size (8) + Logical Maximum (255) + Usage (Contact Id) + Input (Data,Var,Abs) + Report Size (16) + Unit Exponent (-1) + Unit (SILinear: cm) + Logical Maximum (4095) + Physical Minimum (0) + Physical Maximum ({self.phys_max[0]}) + Usage Page (Generic Desktop) + Usage (X) + Input (Data,Var,Abs) + Physical Maximum ({self.phys_max[1]}) + Usage (Y) + Input (Data,Var,Abs) + End Collection +""" + rdesc_str = f""" + Usage Page (Digitizers) + Usage (Touch Screen) + Collection (Application) + Report ID (1) + {rdesc_finger_str * n_fingers} + Unit Exponent (-4) + Unit (SILinear: s) + Logical Maximum (65535) + Physical Maximum (65535) + Usage Page (Digitizers) + Usage (Scan Time) + Input (Data,Var,Abs) + Report Size (8) + Logical Maximum (255) + Usage (Contact Count) + Input (Data,Var,Abs) + Report ID (2) + Logical Maximum ({contact_max}) + Usage (Contact Max) + Feature (Data,Var,Abs) + End Collection + {Digitizer.msCertificationBlob(68)} +""" + super().__init__( + f"uhid test parallel big contact max {contact_max}", rdesc_str + ) + + class BaseTest: class TestMultitouch(base.BaseTestCase.TestUhid): kernel_modules = [KERNEL_MODULE] @@ -1735,6 +1808,47 @@ class TestMinWin8TSParallel(BaseTest.TestWin8Multitouch): return MinWin8TSParallel(10) +class TestMinWin8TSParallelBigContactMax(base.BaseTestCase.TestUhid): + """Regression test for the out-of-bounds bit operations on + struct mt_device.mt_io_flags. + + A Win8 touchscreen may advertise a ContactCountMaximum much larger than + the number of contacts it reports. The driver used to keep the per-slot + active state in the bits of a single unsigned long while indexing + set_bit()/clear_bit() by the slot number, so such a device drove those bit + operations out of bounds. The sticky-fingers release timer made it fatal: + mt_release_contacts() cleared one bit per slot, overwrote the adjacent + struct mt_device members and panicked the kernel. + + Send a single contact, let the 100ms sticky-fingers timer release it, and + check that the kernel reports the release cleanly instead of crashing.""" + + kernel_modules = [KERNEL_MODULE] + + def create_device(self): + return MinWin8TSParallelBigContactMax() + + def test_sticky_fingers_release_big_contact_max(self): + uhdev = self.uhdev + evdev = uhdev.get_evdev() + + assert evdev.num_slots == uhdev.max_contacts + + t0 = Touch(1, 5, 10) + r = uhdev.event([t0]) + events = uhdev.next_sync_events() + self.debug_reports(r, uhdev, events) + assert evdev.slots[0][libevdev.EV_ABS.ABS_MT_TRACKING_ID] == 0 + + # do not release the contact; the sticky-fingers timer must do it + # after 100ms, which is where the out-of-bounds release used to hit + time.sleep(0.2) + events = uhdev.next_sync_events() + self.debug_reports(r, uhdev, events) + assert libevdev.InputEvent(libevdev.EV_KEY.BTN_TOUCH, 0) in events + assert evdev.slots[0][libevdev.EV_ABS.ABS_MT_TRACKING_ID] == -1 + + class TestMinWin8TSHybrid(BaseTest.TestWin8Multitouch): def create_device(self): return MinWin8TSHybrid() diff --git a/tools/testing/selftests/mm/hmm-tests.c b/tools/testing/selftests/mm/hmm-tests.c index e4c49699f3f7..2f2b9879d100 100644 --- a/tools/testing/selftests/mm/hmm-tests.c +++ b/tools/testing/selftests/mm/hmm-tests.c @@ -23,6 +23,7 @@ #include #include #include +#include #include #include #include diff --git a/tools/testing/selftests/mm/ksft_process_madv.sh b/tools/testing/selftests/mm/ksft_process_madv.sh index 2c3137ae8bc8..edad2d2d888f 100755 --- a/tools/testing/selftests/mm/ksft_process_madv.sh +++ b/tools/testing/selftests/mm/ksft_process_madv.sh @@ -1,4 +1,4 @@ #!/bin/sh -e # SPDX-License-Identifier: GPL-2.0 -./run_vmtests.sh -t mmap +./run_vmtests.sh -t process_madv diff --git a/tools/testing/selftests/mm/pagemap_ioctl.c b/tools/testing/selftests/mm/pagemap_ioctl.c index 762306177ad8..6f8971d5b3ce 100644 --- a/tools/testing/selftests/mm/pagemap_ioctl.c +++ b/tools/testing/selftests/mm/pagemap_ioctl.c @@ -1368,7 +1368,7 @@ void *thread_proc(void *mem) ksft_exit_fail_msg("pthread_barrier_wait\n"); for (i = 0; i < access_per_thread; ++i) - __atomic_add_fetch(m + i * (0x1000 / sizeof(*m)), 1, __ATOMIC_SEQ_CST); + __atomic_add_fetch(m + i * (page_size / sizeof(*m)), 1, __ATOMIC_SEQ_CST); ret = pthread_barrier_wait(&end_barrier); if (ret && ret != PTHREAD_BARRIER_SERIAL_THREAD) @@ -1403,15 +1403,15 @@ static void transact_test(int page_size) if (pthread_barrier_init(&end_barrier, NULL, nthreads + 1)) ksft_exit_fail_msg("pthread_barrier_init\n"); - mem = mmap(NULL, 0x1000 * nthreads * pages_per_thread, PROT_READ | PROT_WRITE, + mem = mmap(NULL, page_size * nthreads * pages_per_thread, PROT_READ | PROT_WRITE, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); if (mem == MAP_FAILED) ksft_exit_fail_msg("Error mmap %s.\n", strerror(errno)); - wp_init(mem, 0x1000 * nthreads * pages_per_thread); - wp_addr_range(mem, 0x1000 * nthreads * pages_per_thread); + wp_init(mem, page_size * nthreads * pages_per_thread); + wp_addr_range(mem, page_size * nthreads * pages_per_thread); - memset(mem, 0, 0x1000 * nthreads * pages_per_thread); + memset(mem, 0, page_size * nthreads * pages_per_thread); count = get_dirty_pages_reset(mem, nthreads * pages_per_thread, 1, page_size); ksft_test_result(count > 0, "%s count %u\n", __func__, count); @@ -1420,7 +1420,7 @@ static void transact_test(int page_size) finish = 0; for (i = 0; i < nthreads; ++i) - pthread_create(&th, NULL, thread_proc, mem + 0x1000 * i * pages_per_thread); + pthread_create(&th, NULL, thread_proc, mem + page_size * i * pages_per_thread); extra_pages = 0; for (i = 0; i < iter_count; ++i) { diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh index b3827b43782b..d46d2cec89e4 100644 --- a/tools/testing/selftests/net/lib.sh +++ b/tools/testing/selftests/net/lib.sh @@ -70,12 +70,33 @@ ksft_exit_status_merge() $ksft_xfail $ksft_pass $ksft_skip $ksft_fail } +timestamp_ms() +{ + local now + local seconds + local nanoseconds + + now=$(date -u +%s:%N) || return + seconds=${now%:*} + nanoseconds=${now#*:} + + if [[ $nanoseconds =~ ^[0-9]+$ ]]; then + nanoseconds=${nanoseconds:0:9} + else + nanoseconds=0 + fi + + echo $((seconds * 1000 + 10#$nanoseconds / 1000000)) +} + loopy_wait() { local sleep_cmd=$1; shift local timeout_ms=$1; shift + local start_time + local current_time - local start_time="$(date -u +%s%3N)" + start_time=$(timestamp_ms) || return while true do local out @@ -84,7 +105,7 @@ loopy_wait() return 0 fi - local current_time="$(date -u +%s%3N)" + current_time=$(timestamp_ms) || return if ((current_time - start_time > timeout_ms)); then echo -n "$out" return 1 diff --git a/tools/testing/selftests/net/tcp_mmap.c b/tools/testing/selftests/net/tcp_mmap.c index 4fcce5150850..2544ae35d07a 100644 --- a/tools/testing/selftests/net/tcp_mmap.c +++ b/tools/testing/selftests/net/tcp_mmap.c @@ -313,6 +313,8 @@ void *child_thread(void *arg) tcp_info_get_rcv_mss(fd)); } error: + if (ctx) + EVP_MD_CTX_free(ctx); munmap(buffer, buffer_sz); close(fd); if (zflg) @@ -606,6 +608,8 @@ int main(int argc, char *argv[]) EVP_DigestFinal_ex(ctx, digest, &digest_len); send(fd, digest, (size_t)SHA256_DIGEST_LENGTH, 0); } + if (ctx) + EVP_MD_CTX_free(ctx); close(fd); munmap(buffer, buffer_sz); return 0; diff --git a/tools/testing/selftests/riscv/vector/validate_v_ptrace.c b/tools/testing/selftests/riscv/vector/validate_v_ptrace.c index 74b6f6bcf067..a388b7963d47 100644 --- a/tools/testing/selftests/riscv/vector/validate_v_ptrace.c +++ b/tools/testing/selftests/riscv/vector/validate_v_ptrace.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only #include +#include #include #include #include @@ -25,9 +26,9 @@ TEST(ptrace_v_not_enabled) SKIP(return, "Vector not supported"); chld_lock = 1; - pid = fork(); + pid = (pid_t)syscall(SYS_clone, SIGCHLD, 0, NULL, 0, NULL); ASSERT_LE(0, pid) - TH_LOG("fork: %m"); + TH_LOG("clone: %m"); if (pid == 0) { while (chld_lock == 1) @@ -74,7 +75,7 @@ TEST(ptrace_v_not_enabled) ASSERT_EQ(-1, ret); /* cleanup */ - + free(regset_data); ASSERT_EQ(0, kill(pid, SIGKILL)); } } @@ -206,7 +207,7 @@ TEST(ptrace_v_early_debug) EXPECT_EQ(vl_csr, regset_data->vl); /* cleanup */ - + free(regset_data); ASSERT_EQ(0, kill(pid, SIGKILL)); } } @@ -330,7 +331,7 @@ TEST(ptrace_v_syscall_clobbering) EXPECT_EQ(0UL, regset_data->vl); /* cleanup */ - + free(regset_data); ASSERT_EQ(0, kill(pid, SIGKILL)); } } @@ -648,7 +649,7 @@ TEST_F(v_csr_invalid, ptrace_v_invalid_values) ASSERT_EQ(ret, -1); /* cleanup */ - + free(regset_data); ASSERT_EQ(0, kill(pid, SIGKILL)); } } @@ -910,7 +911,7 @@ TEST_F(v_csr_valid, ptrace_v_valid_values) EXPECT_EQ(regset_data->vlenb, vlenb); /* cleanup */ - + free(regset_data); ASSERT_EQ(0, kill(pid, SIGKILL)); } } diff --git a/tools/testing/selftests/rseq/Makefile b/tools/testing/selftests/rseq/Makefile index 50d69e22ee7a..aba6317f6cb8 100644 --- a/tools/testing/selftests/rseq/Makefile +++ b/tools/testing/selftests/rseq/Makefile @@ -5,9 +5,13 @@ CLANG_FLAGS += -no-integrated-as endif top_srcdir = ../../../.. +include $(top_srcdir)/scripts/subarch.include +ARCH ?= $(SUBARCH) +LINUX_TOOL_ARCH_INCLUDE = $(top_srcdir)/tools/arch/$(ARCH)/include CFLAGS += -O2 -Wall -g -I./ $(KHDR_INCLUDES) -L$(OUTPUT) -Wl,-rpath=./ \ - $(CLANG_FLAGS) -I$(top_srcdir)/tools/include + $(CLANG_FLAGS) -I$(top_srcdir)/tools/include \ + -I$(LINUX_TOOL_ARCH_INCLUDE) LDLIBS += -lpthread -ldl # Own dependencies because we only want to build against 1st prerequisite, but diff --git a/tools/testing/selftests/user_events/abi_test.c b/tools/testing/selftests/user_events/abi_test.c index 85892b3b719c..b71813eaf5c0 100644 --- a/tools/testing/selftests/user_events/abi_test.c +++ b/tools/testing/selftests/user_events/abi_test.c @@ -132,6 +132,33 @@ static int event_delete(void) return ret; } +/* + * Deleting an event drops its last reference, but an unregister may defer + * that put (and the freeing of the associated enabler) past an RCU grace + * period. The delete can therefore transiently fail with -EBUSY while the + * previous reference is still being dropped. Retry only on that transient + * failure; treat an already-deleted event (-ENOENT) as success and return + * any other error immediately rather than spinning for the full timeout. + */ +static int wait_for_event_delete(void) +{ + int i, ret; + + for (i = 0; i < 10000; ++i) { + ret = event_delete(); + + if (ret == 0 || errno == ENOENT) + return 0; + + if (errno != EBUSY) + return ret; + + usleep(1000); + } + + return ret; +} + static int reg_enable_multi(void *enable, int size, int bit, int flags, char *args) { @@ -262,7 +289,7 @@ TEST_F(user, flags) { ASSERT_TRUE(event_exists()); /* Ensure we can delete it */ - ASSERT_EQ(0, event_delete()); + ASSERT_EQ(0, wait_for_event_delete()); /* USER_EVENT_REG_MAX or above is not allowed */ ASSERT_EQ(-1, reg_enable_flags(&self->check, sizeof(int), 0, diff --git a/tools/testing/selftests/user_events/perf_test.c b/tools/testing/selftests/user_events/perf_test.c index cafec0e52eb3..5727cb5b914c 100644 --- a/tools/testing/selftests/user_events/perf_test.c +++ b/tools/testing/selftests/user_events/perf_test.c @@ -85,6 +85,7 @@ static int get_offset(void) static int clear(int *check) { struct user_unreg unreg = {0}; + int i, ret; unreg.size = sizeof(unreg); unreg.disable_bit = 31; @@ -99,13 +100,32 @@ static int clear(int *check) if (errno != ENOENT) return -1; - if (ioctl(fd, DIAG_IOCSDEL, "__test_event") == -1) - if (errno != ENOENT) + /* + * Deleting the event drops its last reference, but the unregister + * above defers that put (and the freeing of the enabler) past an RCU + * grace period. The delete can therefore transiently fail with -EBUSY + * until that reference is dropped. Retry for up to ~10 seconds so the + * event is actually gone before the next test registers the same name. + */ + for (i = 0; i < 10000; ++i) { + ret = ioctl(fd, DIAG_IOCSDEL, "__test_event"); + + if (ret == 0 || errno == ENOENT) { + ret = 0; + break; + } + + if (errno != EBUSY) { + close(fd); return -1; + } + + usleep(1000); + } close(fd); - return 0; + return ret; } FIXTURE(user) { diff --git a/tools/usb/usbip/libsrc/usbip_common.c b/tools/usb/usbip/libsrc/usbip_common.c index b8d7d480595a..f4734f552d31 100644 --- a/tools/usb/usbip/libsrc/usbip_common.c +++ b/tools/usb/usbip/libsrc/usbip_common.c @@ -29,6 +29,8 @@ static const struct speed_string speed_strings[] = { { USB_SPEED_HIGH, "480", "High Speed(480Mbps)" }, { USB_SPEED_WIRELESS, "53.3-480", "Wireless"}, { USB_SPEED_SUPER, "5000", "Super Speed(5000Mbps)" }, + { USB_SPEED_SUPER_PLUS, "10000", "Super Speed Plus(10000Mbps)" }, + { USB_SPEED_SUPER_PLUS, "20000", "Super Speed Plus(20000Mbps)" }, { 0, NULL, NULL } }; diff --git a/tools/usb/usbip/libsrc/usbip_device_driver.c b/tools/usb/usbip/libsrc/usbip_device_driver.c index 1dfbb76ab26c..c9b3619d86f3 100644 --- a/tools/usb/usbip/libsrc/usbip_device_driver.c +++ b/tools/usb/usbip/libsrc/usbip_device_driver.c @@ -57,6 +57,10 @@ static struct { .speed = USB_SPEED_SUPER, .name = "super-speed", }, + { + .speed = USB_SPEED_SUPER_PLUS, + .name = "super-speed-plus", + }, }; static diff --git a/tools/usb/usbip/libsrc/vhci_driver.c b/tools/usb/usbip/libsrc/vhci_driver.c index 8159fd98680b..4ca3783ee5b7 100644 --- a/tools/usb/usbip/libsrc/vhci_driver.c +++ b/tools/usb/usbip/libsrc/vhci_driver.c @@ -338,6 +338,7 @@ int usbip_vhci_get_free_port(uint32_t speed) switch (speed) { case USB_SPEED_SUPER: + case USB_SPEED_SUPER_PLUS: if (vhci_driver->idev[i].hub != HUB_SPEED_SUPER) continue; break; diff --git a/tools/virtio/asm/percpu_types.h b/tools/virtio/asm/percpu_types.h new file mode 100644 index 000000000000..4eb53d93c099 --- /dev/null +++ b/tools/virtio/asm/percpu_types.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_PERCPU_TYPES_H +#define _ASM_PERCPU_TYPES_H + +#define __percpu_qual + +#endif /* _ASM_PERCPU_TYPES_H */ diff --git a/tools/virtio/linux/completion.h b/tools/virtio/linux/completion.h new file mode 100644 index 000000000000..5e54b679721b --- /dev/null +++ b/tools/virtio/linux/completion.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_COMPLETION_H +#define _LINUX_COMPLETION_H + +struct completion { + unsigned int done; +}; + +#endif /* _LINUX_COMPLETION_H */ diff --git a/tools/virtio/linux/device.h b/tools/virtio/linux/device.h index 075c2140d975..abf100cb0023 100644 --- a/tools/virtio/linux/device.h +++ b/tools/virtio/linux/device.h @@ -1,4 +1,5 @@ #ifndef LINUX_DEVICE_H +#define LINUX_DEVICE_H struct device { void *parent; diff --git a/tools/virtio/linux/dma-mapping.h b/tools/virtio/linux/dma-mapping.h index 8d1a16cb20db..b9fc5e8338e3 100644 --- a/tools/virtio/linux/dma-mapping.h +++ b/tools/virtio/linux/dma-mapping.h @@ -61,5 +61,6 @@ enum dma_data_direction { #define DMA_MAPPING_ERROR (~(dma_addr_t)0) #define DMA_ATTR_CPU_CACHE_CLEAN (1UL << 11) +#define DMA_ATTR_DEBUGGING_IGNORE_CACHELINES 0 #endif diff --git a/tools/virtio/linux/mod_devicetable.h b/tools/virtio/linux/mod_devicetable.h new file mode 100644 index 000000000000..3ba594b8229d --- /dev/null +++ b/tools/virtio/linux/mod_devicetable.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_MOD_DEVICETABLE_H +#define _LINUX_MOD_DEVICETABLE_H + +#include + +struct virtio_device_id { + __u32 device; + __u32 vendor; +}; + +#define VIRTIO_DEV_ANY_ID 0xffffffff + +#endif /* _LINUX_MOD_DEVICETABLE_H */ diff --git a/tools/virtio/linux/virtio_features.h b/tools/virtio/linux/virtio_features.h new file mode 100644 index 000000000000..04cbb9622ec7 --- /dev/null +++ b/tools/virtio/linux/virtio_features.h @@ -0,0 +1,79 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_VIRTIO_FEATURES_H +#define _LINUX_VIRTIO_FEATURES_H + +#include +#include +#include + +#define VIRTIO_FEATURES_U64S 2 +#define VIRTIO_FEATURES_BITS (VIRTIO_FEATURES_U64S * 64) + +#define VIRTIO_BIT(b) (1ULL << ((b) & 0x3f)) +#define VIRTIO_U64(b) ((b) >> 6) + +#define VIRTIO_DECLARE_FEATURES(name) \ + union { \ + u64 name; \ + u64 name##_array[VIRTIO_FEATURES_U64S];\ + } + +static inline bool virtio_features_chk_bit(unsigned int bit) +{ + return bit < VIRTIO_FEATURES_BITS; +} + +static inline bool virtio_features_test_bit(const u64 *features, + unsigned int bit) +{ + return virtio_features_chk_bit(bit) && + !!(features[VIRTIO_U64(bit)] & VIRTIO_BIT(bit)); +} + +static inline void virtio_features_set_bit(u64 *features, unsigned int bit) +{ + if (virtio_features_chk_bit(bit)) + features[VIRTIO_U64(bit)] |= VIRTIO_BIT(bit); +} + +static inline void virtio_features_clear_bit(u64 *features, unsigned int bit) +{ + if (virtio_features_chk_bit(bit)) + features[VIRTIO_U64(bit)] &= ~VIRTIO_BIT(bit); +} + +static inline void virtio_features_zero(u64 *features) +{ + memset(features, 0, sizeof(features[0]) * VIRTIO_FEATURES_U64S); +} + +static inline void virtio_features_from_u64(u64 *features, u64 from) +{ + virtio_features_zero(features); + features[0] = from; +} + +static inline bool virtio_features_equal(const u64 *f1, const u64 *f2) +{ + int i; + + for (i = 0; i < VIRTIO_FEATURES_U64S; ++i) + if (f1[i] != f2[i]) + return false; + return true; +} + +static inline void virtio_features_copy(u64 *to, const u64 *from) +{ + memcpy(to, from, sizeof(to[0]) * VIRTIO_FEATURES_U64S); +} + +static inline void virtio_features_andnot(u64 *to, const u64 *f1, const u64 *f2) +{ + int i; + + for (i = 0; i < VIRTIO_FEATURES_U64S; i++) + to[i] = f1[i] & ~f2[i]; +} + +#endif /* _LINUX_VIRTIO_FEATURES_H */