diff --git a/.mailmap b/.mailmap index 825fae8e6b7bd..2ed1cf8691753 100644 --- a/.mailmap +++ b/.mailmap @@ -10,6 +10,8 @@ # Please keep this list dictionary sorted. # Aaron Durbin +Abel Vesa +Abel Vesa Abhinav Kumar Adam Oldham Adam Radford @@ -85,6 +87,7 @@ Christian Borntraeger Christian Brauner Christian Brauner Christian Brauner +Christian Marangi Christophe Ricard Christoph Hellwig Colin Ian King @@ -165,6 +168,7 @@ Jan Glauber Jan Glauber Jan Glauber Jarkko Sakkinen +Jarkko Sakkinen Jason Gunthorpe Jason Gunthorpe Jason Gunthorpe diff --git a/Documentation/ABI/testing/sysfs-ata b/Documentation/ABI/testing/sysfs-ata index 2f726c9147522..3daecac48964f 100644 --- a/Documentation/ABI/testing/sysfs-ata +++ b/Documentation/ABI/testing/sysfs-ata @@ -107,13 +107,14 @@ Description: described in ATA8 7.16 and 7.17. Only valid if the device is not a PM. - pio_mode: (RO) Transfer modes supported by the device when - in PIO mode. Mostly used by PATA device. + pio_mode: (RO) PIO transfer mode used by the device. + Mostly used by PATA devices. - xfer_mode: (RO) Current transfer mode + xfer_mode: (RO) Current transfer mode. Mostly used by + PATA devices. - dma_mode: (RO) Transfer modes supported by the device when - in DMA mode. Mostly used by PATA device. + dma_mode: (RO) DMA transfer mode used by the device. + Mostly used by PATA devices. class: (RO) Device class. Can be "ata" for disk, "atapi" for packet device, "pmp" for PM, or diff --git a/Documentation/ABI/testing/sysfs-bus-iio-vf610 b/Documentation/ABI/testing/sysfs-bus-iio-vf610 index 308a6756d3bf3..491ead8044888 100644 --- a/Documentation/ABI/testing/sysfs-bus-iio-vf610 +++ b/Documentation/ABI/testing/sysfs-bus-iio-vf610 @@ -1,4 +1,4 @@ -What: /sys/bus/iio/devices/iio:deviceX/conversion_mode +What: /sys/bus/iio/devices/iio:deviceX/in_conversion_mode KernelVersion: 4.2 Contact: linux-iio@vger.kernel.org Description: diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu index 2ad01cad7f1c8..bcc974d276dc4 100644 --- a/Documentation/ABI/testing/sysfs-devices-system-cpu +++ b/Documentation/ABI/testing/sysfs-devices-system-cpu @@ -526,6 +526,7 @@ What: /sys/devices/system/cpu/vulnerabilities /sys/devices/system/cpu/vulnerabilities/srbds /sys/devices/system/cpu/vulnerabilities/tsx_async_abort /sys/devices/system/cpu/vulnerabilities/itlb_multihit + /sys/devices/system/cpu/vulnerabilities/mmio_stale_data Date: January 2018 Contact: Linux kernel mailing list Description: Information about CPU vulnerabilities diff --git a/Documentation/ABI/testing/sysfs-driver-bd9571mwv-regulator b/Documentation/ABI/testing/sysfs-driver-bd9571mwv-regulator index 42214b4ff14a1..90596d8bb51c0 100644 --- a/Documentation/ABI/testing/sysfs-driver-bd9571mwv-regulator +++ b/Documentation/ABI/testing/sysfs-driver-bd9571mwv-regulator @@ -26,6 +26,6 @@ Description: Read/write the current state of DDR Backup Mode, which controls DDR Backup Mode must be explicitly enabled by the user, to invoke step 1. - See also Documentation/devicetree/bindings/mfd/bd9571mwv.txt. + See also Documentation/devicetree/bindings/mfd/rohm,bd9571mwv.yaml. Users: User space applications for embedded boards equipped with a BD9571MWV PMIC. diff --git a/Documentation/admin-guide/hw-vuln/index.rst b/Documentation/admin-guide/hw-vuln/index.rst index 8cbc711cda935..4df436e7c4177 100644 --- a/Documentation/admin-guide/hw-vuln/index.rst +++ b/Documentation/admin-guide/hw-vuln/index.rst @@ -17,3 +17,4 @@ are configurable at compile, boot or run time. special-register-buffer-data-sampling.rst core-scheduling.rst l1d_flush.rst + processor_mmio_stale_data.rst diff --git a/Documentation/admin-guide/hw-vuln/processor_mmio_stale_data.rst b/Documentation/admin-guide/hw-vuln/processor_mmio_stale_data.rst new file mode 100644 index 0000000000000..9393c50b5afc9 --- /dev/null +++ b/Documentation/admin-guide/hw-vuln/processor_mmio_stale_data.rst @@ -0,0 +1,246 @@ +========================================= +Processor MMIO Stale Data Vulnerabilities +========================================= + +Processor MMIO Stale Data Vulnerabilities are a class of memory-mapped I/O +(MMIO) vulnerabilities that can expose data. The sequences of operations for +exposing data range from simple to very complex. Because most of the +vulnerabilities require the attacker to have access to MMIO, many environments +are not affected. System environments using virtualization where MMIO access is +provided to untrusted guests may need mitigation. These vulnerabilities are +not transient execution attacks. However, these vulnerabilities may propagate +stale data into core fill buffers where the data can subsequently be inferred +by an unmitigated transient execution attack. Mitigation for these +vulnerabilities includes a combination of microcode update and software +changes, depending on the platform and usage model. Some of these mitigations +are similar to those used to mitigate Microarchitectural Data Sampling (MDS) or +those used to mitigate Special Register Buffer Data Sampling (SRBDS). + +Data Propagators +================ +Propagators are operations that result in stale data being copied or moved from +one microarchitectural buffer or register to another. Processor MMIO Stale Data +Vulnerabilities are operations that may result in stale data being directly +read into an architectural, software-visible state or sampled from a buffer or +register. + +Fill Buffer Stale Data Propagator (FBSDP) +----------------------------------------- +Stale data may propagate from fill buffers (FB) into the non-coherent portion +of the uncore on some non-coherent writes. Fill buffer propagation by itself +does not make stale data architecturally visible. Stale data must be propagated +to a location where it is subject to reading or sampling. + +Sideband Stale Data Propagator (SSDP) +------------------------------------- +The sideband stale data propagator (SSDP) is limited to the client (including +Intel Xeon server E3) uncore implementation. The sideband response buffer is +shared by all client cores. For non-coherent reads that go to sideband +destinations, the uncore logic returns 64 bytes of data to the core, including +both requested data and unrequested stale data, from a transaction buffer and +the sideband response buffer. As a result, stale data from the sideband +response and transaction buffers may now reside in a core fill buffer. + +Primary Stale Data Propagator (PSDP) +------------------------------------ +The primary stale data propagator (PSDP) is limited to the client (including +Intel Xeon server E3) uncore implementation. Similar to the sideband response +buffer, the primary response buffer is shared by all client cores. For some +processors, MMIO primary reads will return 64 bytes of data to the core fill +buffer including both requested data and unrequested stale data. This is +similar to the sideband stale data propagator. + +Vulnerabilities +=============== +Device Register Partial Write (DRPW) (CVE-2022-21166) +----------------------------------------------------- +Some endpoint MMIO registers incorrectly handle writes that are smaller than +the register size. Instead of aborting the write or only copying the correct +subset of bytes (for example, 2 bytes for a 2-byte write), more bytes than +specified by the write transaction may be written to the register. On +processors affected by FBSDP, this may expose stale data from the fill buffers +of the core that created the write transaction. + +Shared Buffers Data Sampling (SBDS) (CVE-2022-21125) +---------------------------------------------------- +After propagators may have moved data around the uncore and copied stale data +into client core fill buffers, processors affected by MFBDS can leak data from +the fill buffer. It is limited to the client (including Intel Xeon server E3) +uncore implementation. + +Shared Buffers Data Read (SBDR) (CVE-2022-21123) +------------------------------------------------ +It is similar to Shared Buffer Data Sampling (SBDS) except that the data is +directly read into the architectural software-visible state. It is limited to +the client (including Intel Xeon server E3) uncore implementation. + +Affected Processors +=================== +Not all the CPUs are affected by all the variants. For instance, most +processors for the server market (excluding Intel Xeon E3 processors) are +impacted by only Device Register Partial Write (DRPW). + +Below is the list of affected Intel processors [#f1]_: + + =================== ============ ========= + Common name Family_Model Steppings + =================== ============ ========= + HASWELL_X 06_3FH 2,4 + SKYLAKE_L 06_4EH 3 + BROADWELL_X 06_4FH All + SKYLAKE_X 06_55H 3,4,6,7,11 + BROADWELL_D 06_56H 3,4,5 + SKYLAKE 06_5EH 3 + ICELAKE_X 06_6AH 4,5,6 + ICELAKE_D 06_6CH 1 + ICELAKE_L 06_7EH 5 + ATOM_TREMONT_D 06_86H All + LAKEFIELD 06_8AH 1 + KABYLAKE_L 06_8EH 9 to 12 + ATOM_TREMONT 06_96H 1 + ATOM_TREMONT_L 06_9CH 0 + KABYLAKE 06_9EH 9 to 13 + COMETLAKE 06_A5H 2,3,5 + COMETLAKE_L 06_A6H 0,1 + ROCKETLAKE 06_A7H 1 + =================== ============ ========= + +If a CPU is in the affected processor list, but not affected by a variant, it +is indicated by new bits in MSR IA32_ARCH_CAPABILITIES. As described in a later +section, mitigation largely remains the same for all the variants, i.e. to +clear the CPU fill buffers via VERW instruction. + +New bits in MSRs +================ +Newer processors and microcode update on existing affected processors added new +bits to IA32_ARCH_CAPABILITIES MSR. These bits can be used to enumerate +specific variants of Processor MMIO Stale Data vulnerabilities and mitigation +capability. + +MSR IA32_ARCH_CAPABILITIES +-------------------------- +Bit 13 - SBDR_SSDP_NO - When set, processor is not affected by either the + Shared Buffers Data Read (SBDR) vulnerability or the sideband stale + data propagator (SSDP). +Bit 14 - FBSDP_NO - When set, processor is not affected by the Fill Buffer + Stale Data Propagator (FBSDP). +Bit 15 - PSDP_NO - When set, processor is not affected by Primary Stale Data + Propagator (PSDP). +Bit 17 - FB_CLEAR - When set, VERW instruction will overwrite CPU fill buffer + values as part of MD_CLEAR operations. Processors that do not + enumerate MDS_NO (meaning they are affected by MDS) but that do + enumerate support for both L1D_FLUSH and MD_CLEAR implicitly enumerate + FB_CLEAR as part of their MD_CLEAR support. +Bit 18 - FB_CLEAR_CTRL - Processor supports read and write to MSR + IA32_MCU_OPT_CTRL[FB_CLEAR_DIS]. On such processors, the FB_CLEAR_DIS + bit can be set to cause the VERW instruction to not perform the + FB_CLEAR action. Not all processors that support FB_CLEAR will support + FB_CLEAR_CTRL. + +MSR IA32_MCU_OPT_CTRL +--------------------- +Bit 3 - FB_CLEAR_DIS - When set, VERW instruction does not perform the FB_CLEAR +action. This may be useful to reduce the performance impact of FB_CLEAR in +cases where system software deems it warranted (for example, when performance +is more critical, or the untrusted software has no MMIO access). Note that +FB_CLEAR_DIS has no impact on enumeration (for example, it does not change +FB_CLEAR or MD_CLEAR enumeration) and it may not be supported on all processors +that enumerate FB_CLEAR. + +Mitigation +========== +Like MDS, all variants of Processor MMIO Stale Data vulnerabilities have the +same mitigation strategy to force the CPU to clear the affected buffers before +an attacker can extract the secrets. + +This is achieved by using the otherwise unused and obsolete VERW instruction in +combination with a microcode update. The microcode clears the affected CPU +buffers when the VERW instruction is executed. + +Kernel reuses the MDS function to invoke the buffer clearing: + + mds_clear_cpu_buffers() + +On MDS affected CPUs, the kernel already invokes CPU buffer clear on +kernel/userspace, hypervisor/guest and C-state (idle) transitions. No +additional mitigation is needed on such CPUs. + +For CPUs not affected by MDS or TAA, mitigation is needed only for the attacker +with MMIO capability. Therefore, VERW is not required for kernel/userspace. For +virtualization case, VERW is only needed at VMENTER for a guest with MMIO +capability. + +Mitigation points +----------------- +Return to user space +^^^^^^^^^^^^^^^^^^^^ +Same mitigation as MDS when affected by MDS/TAA, otherwise no mitigation +needed. + +C-State transition +^^^^^^^^^^^^^^^^^^ +Control register writes by CPU during C-state transition can propagate data +from fill buffer to uncore buffers. Execute VERW before C-state transition to +clear CPU fill buffers. + +Guest entry point +^^^^^^^^^^^^^^^^^ +Same mitigation as MDS when processor is also affected by MDS/TAA, otherwise +execute VERW at VMENTER only for MMIO capable guests. On CPUs not affected by +MDS/TAA, guest without MMIO access cannot extract secrets using Processor MMIO +Stale Data vulnerabilities, so there is no need to execute VERW for such guests. + +Mitigation control on the kernel command line +--------------------------------------------- +The kernel command line allows to control the Processor MMIO Stale Data +mitigations at boot time with the option "mmio_stale_data=". The valid +arguments for this option are: + + ========== ================================================================= + full If the CPU is vulnerable, enable mitigation; CPU buffer clearing + on exit to userspace and when entering a VM. Idle transitions are + protected as well. It does not automatically disable SMT. + full,nosmt Same as full, with SMT disabled on vulnerable CPUs. This is the + complete mitigation. + off Disables mitigation completely. + ========== ================================================================= + +If the CPU is affected and mmio_stale_data=off is not supplied on the kernel +command line, then the kernel selects the appropriate mitigation. + +Mitigation status information +----------------------------- +The Linux kernel provides a sysfs interface to enumerate the current +vulnerability status of the system: whether the system is vulnerable, and +which mitigations are active. The relevant sysfs file is: + + /sys/devices/system/cpu/vulnerabilities/mmio_stale_data + +The possible values in this file are: + + .. list-table:: + + * - 'Not affected' + - The processor is not vulnerable + * - 'Vulnerable' + - The processor is vulnerable, but no mitigation enabled + * - 'Vulnerable: Clear CPU buffers attempted, no microcode' + - The processor is vulnerable, but microcode is not updated. The + mitigation is enabled on a best effort basis. + * - 'Mitigation: Clear CPU buffers' + - The processor is vulnerable and the CPU buffer clearing mitigation is + enabled. + +If the processor is vulnerable then the following information is appended to +the above information: + + ======================== =========================================== + 'SMT vulnerable' SMT is enabled + 'SMT disabled' SMT is disabled + 'SMT Host state unknown' Kernel runs in a VM, Host SMT state unknown + ======================== =========================================== + +References +---------- +.. [#f1] Affected Processors + https://www.intel.com/content/www/us/en/developer/topic-technology/software-security-guidance/processors-affected-consolidated-product-cpu-model.html diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 8090130b544b0..2522b11e593f2 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -2469,7 +2469,6 @@ protected: nVHE-based mode with support for guests whose state is kept private from the host. - Not valid if the kernel is running in EL2. Defaults to VHE/nVHE based on hardware support. Setting mode to "protected" will disable kexec and hibernation @@ -3176,6 +3175,7 @@ srbds=off [X86,INTEL] no_entry_flush [PPC] no_uaccess_flush [PPC] + mmio_stale_data=off [X86] Exceptions: This does not have any effect on @@ -3197,6 +3197,7 @@ Equivalent to: l1tf=flush,nosmt [X86] mds=full,nosmt [X86] tsx_async_abort=full,nosmt [X86] + mmio_stale_data=full,nosmt [X86] mminit_loglevel= [KNL] When CONFIG_DEBUG_MEMORY_INIT is set, this @@ -3206,6 +3207,40 @@ log everything. Information is printed at KERN_DEBUG so loglevel=8 may also need to be specified. + mmio_stale_data= + [X86,INTEL] Control mitigation for the Processor + MMIO Stale Data vulnerabilities. + + Processor MMIO Stale Data is a class of + vulnerabilities that may expose data after an MMIO + operation. Exposed data could originate or end in + the same CPU buffers as affected by MDS and TAA. + Therefore, similar to MDS and TAA, the mitigation + is to clear the affected CPU buffers. + + This parameter controls the mitigation. The + options are: + + full - Enable mitigation on vulnerable CPUs + + full,nosmt - Enable mitigation and disable SMT on + vulnerable CPUs. + + off - Unconditionally disable mitigation + + On MDS or TAA affected machines, + mmio_stale_data=off can be prevented by an active + MDS or TAA mitigation as these vulnerabilities are + mitigated with the same mechanism so in order to + disable this mitigation, you need to specify + mds=off and tsx_async_abort=off too. + + Not specifying this option is equivalent to + mmio_stale_data=full. + + For details see: + Documentation/admin-guide/hw-vuln/processor_mmio_stale_data.rst + module.sig_enforce [KNL] When CONFIG_MODULE_SIG is set, this means that modules without (valid) signatures will fail to load. diff --git a/Documentation/arm/tcm.rst b/Documentation/arm/tcm.rst index b256f97838839..1dc6c39220f98 100644 --- a/Documentation/arm/tcm.rst +++ b/Documentation/arm/tcm.rst @@ -34,7 +34,7 @@ CPU so it is usually wise not to overlap any physical RAM with the TCM. The TCM memory can then be remapped to another address again using -the MMU, but notice that the TCM if often used in situations where +the MMU, but notice that the TCM is often used in situations where the MMU is turned off. To avoid confusion the current Linux implementation will map the TCM 1 to 1 from physical to virtual memory in the location specified by the kernel. Currently Linux diff --git a/Documentation/arm64/sme.rst b/Documentation/arm64/sme.rst index 8ba677b87e90f..937147f58cc54 100644 --- a/Documentation/arm64/sme.rst +++ b/Documentation/arm64/sme.rst @@ -371,7 +371,7 @@ The regset data starts with struct user_za_header, containing: Appendix A. SME programmer's model (informative) ================================================= -This section provides a minimal description of the additions made by SVE to the +This section provides a minimal description of the additions made by SME to the ARMv8-A programmer's model that are relevant to this document. Note: This section is for information only and not intended to be complete or diff --git a/Documentation/devicetree/bindings/clock/idt,versaclock5.yaml b/Documentation/devicetree/bindings/clock/idt,versaclock5.yaml index be66f1e8b5476..7c331bfbe370e 100644 --- a/Documentation/devicetree/bindings/clock/idt,versaclock5.yaml +++ b/Documentation/devicetree/bindings/clock/idt,versaclock5.yaml @@ -45,7 +45,7 @@ description: | The case where SH and SP are both 1 is likely not very interesting. maintainers: - - Luca Ceresoli + - Luca Ceresoli properties: compatible: diff --git a/Documentation/devicetree/bindings/cpufreq/brcm,stb-avs-cpu-freq.txt b/Documentation/devicetree/bindings/cpufreq/brcm,stb-avs-cpu-freq.txt index 73470ecd1f12f..ce91a91976976 100644 --- a/Documentation/devicetree/bindings/cpufreq/brcm,stb-avs-cpu-freq.txt +++ b/Documentation/devicetree/bindings/cpufreq/brcm,stb-avs-cpu-freq.txt @@ -16,7 +16,7 @@ has been processed. See [2] for more information on the brcm,l2-intc node. firmware. On some SoCs, this firmware supports DFS and DVFS in addition to Adaptive Voltage Scaling. -[2] Documentation/devicetree/bindings/interrupt-controller/brcm,l2-intc.txt +[2] Documentation/devicetree/bindings/interrupt-controller/brcm,l2-intc.yaml Node brcm,avs-cpu-data-mem diff --git a/Documentation/devicetree/bindings/display/arm,malidp.yaml b/Documentation/devicetree/bindings/display/arm,malidp.yaml index 795a08ac9f128..2a17ec6fc97c0 100644 --- a/Documentation/devicetree/bindings/display/arm,malidp.yaml +++ b/Documentation/devicetree/bindings/display/arm,malidp.yaml @@ -71,11 +71,6 @@ properties: - description: number of output lines for the green channel (G) - description: number of output lines for the blue channel (B) - arm,malidp-arqos-high-level: - $ref: /schemas/types.yaml#/definitions/uint32 - description: - integer describing the ARQoS levels of DP500's QoS signaling - arm,malidp-arqos-value: $ref: /schemas/types.yaml#/definitions/uint32 description: @@ -113,7 +108,7 @@ examples: clocks = <&oscclk2>, <&fpgaosc0>, <&fpgaosc1>, <&fpgaosc1>; clock-names = "pxlclk", "mclk", "aclk", "pclk"; arm,malidp-output-port-lines = /bits/ 8 <8 8 8>; - arm,malidp-arqos-high-level = <0xd000d000>; + arm,malidp-arqos-value = <0xd000d000>; port { dp0_output: endpoint { diff --git a/Documentation/devicetree/bindings/display/msm/dpu-sc7180.yaml b/Documentation/devicetree/bindings/display/msm/dpu-sc7180.yaml index b41991eaa454a..d3c3e4b078971 100644 --- a/Documentation/devicetree/bindings/display/msm/dpu-sc7180.yaml +++ b/Documentation/devicetree/bindings/display/msm/dpu-sc7180.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Qualcomm Display DPU dt properties for SC7180 target maintainers: - - Krishna Manikandan + - Krishna Manikandan description: | Device tree bindings for MSM Mobile Display Subsystem(MDSS) that encapsulates diff --git a/Documentation/devicetree/bindings/display/msm/dpu-sc7280.yaml b/Documentation/devicetree/bindings/display/msm/dpu-sc7280.yaml index 6e417d06fc790..f427eec3d3a45 100644 --- a/Documentation/devicetree/bindings/display/msm/dpu-sc7280.yaml +++ b/Documentation/devicetree/bindings/display/msm/dpu-sc7280.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Qualcomm Display DPU dt properties for SC7280 maintainers: - - Krishna Manikandan + - Krishna Manikandan description: | Device tree bindings for MSM Mobile Display Subsystem (MDSS) that encapsulates diff --git a/Documentation/devicetree/bindings/display/msm/dpu-sdm845.yaml b/Documentation/devicetree/bindings/display/msm/dpu-sdm845.yaml index 1a42491efdbcb..2bb8896beffc6 100644 --- a/Documentation/devicetree/bindings/display/msm/dpu-sdm845.yaml +++ b/Documentation/devicetree/bindings/display/msm/dpu-sdm845.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Qualcomm Display DPU dt properties for SDM845 target maintainers: - - Krishna Manikandan + - Krishna Manikandan description: | Device tree bindings for MSM Mobile Display Subsystem(MDSS) that encapsulates diff --git a/Documentation/devicetree/bindings/display/msm/dsi-controller-main.yaml b/Documentation/devicetree/bindings/display/msm/dsi-controller-main.yaml index 7095ec3c890da..880bfe930830c 100644 --- a/Documentation/devicetree/bindings/display/msm/dsi-controller-main.yaml +++ b/Documentation/devicetree/bindings/display/msm/dsi-controller-main.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Qualcomm Display DSI controller maintainers: - - Krishna Manikandan + - Krishna Manikandan allOf: - $ref: "../dsi-controller.yaml#" diff --git a/Documentation/devicetree/bindings/display/msm/dsi-phy-10nm.yaml b/Documentation/devicetree/bindings/display/msm/dsi-phy-10nm.yaml index 2d5a766d028f1..716f921e3532e 100644 --- a/Documentation/devicetree/bindings/display/msm/dsi-phy-10nm.yaml +++ b/Documentation/devicetree/bindings/display/msm/dsi-phy-10nm.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Qualcomm Display DSI 10nm PHY maintainers: - - Krishna Manikandan + - Krishna Manikandan allOf: - $ref: dsi-phy-common.yaml# diff --git a/Documentation/devicetree/bindings/display/msm/dsi-phy-14nm.yaml b/Documentation/devicetree/bindings/display/msm/dsi-phy-14nm.yaml index 81dbee4803c0b..1342d74ecfe0f 100644 --- a/Documentation/devicetree/bindings/display/msm/dsi-phy-14nm.yaml +++ b/Documentation/devicetree/bindings/display/msm/dsi-phy-14nm.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Qualcomm Display DSI 14nm PHY maintainers: - - Krishna Manikandan + - Krishna Manikandan allOf: - $ref: dsi-phy-common.yaml# diff --git a/Documentation/devicetree/bindings/display/msm/dsi-phy-20nm.yaml b/Documentation/devicetree/bindings/display/msm/dsi-phy-20nm.yaml index b8de785ce8156..9c1f9140c731b 100644 --- a/Documentation/devicetree/bindings/display/msm/dsi-phy-20nm.yaml +++ b/Documentation/devicetree/bindings/display/msm/dsi-phy-20nm.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Qualcomm Display DSI 20nm PHY maintainers: - - Krishna Manikandan + - Krishna Manikandan allOf: - $ref: dsi-phy-common.yaml# diff --git a/Documentation/devicetree/bindings/display/msm/dsi-phy-28nm.yaml b/Documentation/devicetree/bindings/display/msm/dsi-phy-28nm.yaml index 69eecaa64b187..3d8540a06fe22 100644 --- a/Documentation/devicetree/bindings/display/msm/dsi-phy-28nm.yaml +++ b/Documentation/devicetree/bindings/display/msm/dsi-phy-28nm.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Qualcomm Display DSI 28nm PHY maintainers: - - Krishna Manikandan + - Krishna Manikandan allOf: - $ref: dsi-phy-common.yaml# diff --git a/Documentation/devicetree/bindings/display/msm/dsi-phy-common.yaml b/Documentation/devicetree/bindings/display/msm/dsi-phy-common.yaml index 502bdda902354..76d40f7933dde 100644 --- a/Documentation/devicetree/bindings/display/msm/dsi-phy-common.yaml +++ b/Documentation/devicetree/bindings/display/msm/dsi-phy-common.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Description of Qualcomm Display DSI PHY common dt properties maintainers: - - Krishna Manikandan + - Krishna Manikandan description: | This defines the DSI PHY dt properties which are common for all diff --git a/Documentation/devicetree/bindings/hwmon/ti,tmp401.yaml b/Documentation/devicetree/bindings/hwmon/ti,tmp401.yaml index fe0ac08faa1a7..0e8ddf0ad7890 100644 --- a/Documentation/devicetree/bindings/hwmon/ti,tmp401.yaml +++ b/Documentation/devicetree/bindings/hwmon/ti,tmp401.yaml @@ -40,9 +40,8 @@ properties: value to be used for converting remote channel measurements to temperature. $ref: /schemas/types.yaml#/definitions/int32 - items: - minimum: -128 - maximum: 127 + minimum: -128 + maximum: 127 ti,beta-compensation: description: diff --git a/Documentation/devicetree/bindings/hwmon/vexpress.txt b/Documentation/devicetree/bindings/hwmon/vexpress.txt index 9c27ed694bbbf..4a4df4ffc460b 100644 --- a/Documentation/devicetree/bindings/hwmon/vexpress.txt +++ b/Documentation/devicetree/bindings/hwmon/vexpress.txt @@ -9,7 +9,7 @@ Requires node properties: "arm,vexpress-power" "arm,vexpress-energy" - "arm,vexpress-sysreg,func" when controlled via vexpress-sysreg - (see Documentation/devicetree/bindings/arm/vexpress-sysreg.txt + (see Documentation/devicetree/bindings/arm/vexpress-config.yaml for more details) Optional node properties: diff --git a/Documentation/devicetree/bindings/interrupt-controller/socionext,uniphier-aidet.yaml b/Documentation/devicetree/bindings/interrupt-controller/socionext,uniphier-aidet.yaml index f89ebde76dab3..de7c5e59bae14 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/socionext,uniphier-aidet.yaml +++ b/Documentation/devicetree/bindings/interrupt-controller/socionext,uniphier-aidet.yaml @@ -30,6 +30,7 @@ properties: - socionext,uniphier-ld11-aidet - socionext,uniphier-ld20-aidet - socionext,uniphier-pxs3-aidet + - socionext,uniphier-nx1-aidet reg: maxItems: 1 diff --git a/Documentation/devicetree/bindings/iommu/xen,grant-dma.yaml b/Documentation/devicetree/bindings/iommu/xen,grant-dma.yaml new file mode 100644 index 0000000000000..be1539d234f96 --- /dev/null +++ b/Documentation/devicetree/bindings/iommu/xen,grant-dma.yaml @@ -0,0 +1,39 @@ +# SPDX-License-Identifier: (GPL-2.0-only or BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/iommu/xen,grant-dma.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Xen specific IOMMU for virtualized devices (e.g. virtio) + +maintainers: + - Stefano Stabellini + +description: + The Xen IOMMU represents the Xen grant table interface. Grant mappings + are to be used with devices connected to the Xen IOMMU using the "iommus" + property, which also specifies the ID of the backend domain. + The binding is required to restrict memory access using Xen grant mappings. + +properties: + compatible: + const: xen,grant-dma + + '#iommu-cells': + const: 1 + description: + The single cell is the domid (domain ID) of the domain where the backend + is running. + +required: + - compatible + - "#iommu-cells" + +additionalProperties: false + +examples: + - | + iommu { + compatible = "xen,grant-dma"; + #iommu-cells = <1>; + }; diff --git a/Documentation/devicetree/bindings/memory-controllers/nvidia,tegra186-mc.yaml b/Documentation/devicetree/bindings/memory-controllers/nvidia,tegra186-mc.yaml index c7cfa6c2cd81c..935d63d181d9e 100644 --- a/Documentation/devicetree/bindings/memory-controllers/nvidia,tegra186-mc.yaml +++ b/Documentation/devicetree/bindings/memory-controllers/nvidia,tegra186-mc.yaml @@ -150,7 +150,6 @@ allOf: description: 5 memory controller channels and 1 for stream-id registers reg-names: - maxItems: 6 items: - const: sid - const: broadcast @@ -170,7 +169,6 @@ allOf: description: 17 memory controller channels and 1 for stream-id registers reg-names: - minItems: 18 items: - const: sid - const: broadcast @@ -202,7 +200,6 @@ allOf: description: 17 memory controller channels and 1 for stream-id registers reg-names: - minItems: 18 items: - const: sid - const: broadcast diff --git a/Documentation/devicetree/bindings/mfd/maxim,max77714.yaml b/Documentation/devicetree/bindings/mfd/maxim,max77714.yaml index 74a6867d3c826..edac14af101e5 100644 --- a/Documentation/devicetree/bindings/mfd/maxim,max77714.yaml +++ b/Documentation/devicetree/bindings/mfd/maxim,max77714.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: MAX77714 PMIC with GPIO, RTC and watchdog from Maxim Integrated. maintainers: - - Luca Ceresoli + - Luca Ceresoli description: | MAX77714 is a Power Management IC with 4 buck regulators, 9 diff --git a/Documentation/devicetree/bindings/mmc/brcm,sdhci-brcmstb.yaml b/Documentation/devicetree/bindings/mmc/brcm,sdhci-brcmstb.yaml index b672202fff4e4..5ecdac9de484b 100644 --- a/Documentation/devicetree/bindings/mmc/brcm,sdhci-brcmstb.yaml +++ b/Documentation/devicetree/bindings/mmc/brcm,sdhci-brcmstb.yaml @@ -75,7 +75,6 @@ examples: sd-uhs-sdr104; sdhci,auto-cmd12; interrupts = <0x0 0x26 0x4>; - interrupt-names = "sdio0_0"; clocks = <&scmi_clk 245>; clock-names = "sw_sdio"; }; @@ -94,7 +93,6 @@ examples: non-removable; bus-width = <0x8>; interrupts = <0x0 0x27 0x4>; - interrupt-names = "sdio1_0"; clocks = <&scmi_clk 245>; clock-names = "sw_sdio"; }; diff --git a/Documentation/devicetree/bindings/mmc/marvell,xenon-sdhci.yaml b/Documentation/devicetree/bindings/mmc/marvell,xenon-sdhci.yaml index c79639e9027ed..3ee7588865585 100644 --- a/Documentation/devicetree/bindings/mmc/marvell,xenon-sdhci.yaml +++ b/Documentation/devicetree/bindings/mmc/marvell,xenon-sdhci.yaml @@ -56,6 +56,9 @@ properties: - const: core - const: axi + interrupts: + maxItems: 1 + marvell,xenon-sdhc-id: $ref: /schemas/types.yaml#/definitions/uint32 minimum: 0 @@ -145,7 +148,6 @@ allOf: items: - description: Xenon IP registers - description: Armada 3700 SoC PHY PAD Voltage Control register - minItems: 2 marvell,pad-type: $ref: /schemas/types.yaml#/definitions/string diff --git a/Documentation/devicetree/bindings/nvme/apple,nvme-ans.yaml b/Documentation/devicetree/bindings/nvme/apple,nvme-ans.yaml index ddff9233b1595..34dd1cc671246 100644 --- a/Documentation/devicetree/bindings/nvme/apple,nvme-ans.yaml +++ b/Documentation/devicetree/bindings/nvme/apple,nvme-ans.yaml @@ -55,7 +55,6 @@ properties: maxItems: 1 apple,sart: - maxItems: 1 $ref: /schemas/types.yaml#/definitions/phandle description: | Reference to the SART address filter. diff --git a/Documentation/devicetree/bindings/phy/phy-stih407-usb.txt b/Documentation/devicetree/bindings/phy/phy-stih407-usb.txt index de6a706abcdbe..35f03df001304 100644 --- a/Documentation/devicetree/bindings/phy/phy-stih407-usb.txt +++ b/Documentation/devicetree/bindings/phy/phy-stih407-usb.txt @@ -9,7 +9,7 @@ Required properties: - resets : list of phandle and reset specifier pairs. There should be two entries, one for the whole phy and one for the port - reset-names : list of reset signal names. Should be "global" and "port" -See: Documentation/devicetree/bindings/reset/st,sti-powerdown.txt +See: Documentation/devicetree/bindings/reset/st,stih407-powerdown.yaml See: Documentation/devicetree/bindings/reset/reset.txt Example: diff --git a/Documentation/devicetree/bindings/phy/qcom,qmp-usb3-dp-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,qmp-usb3-dp-phy.yaml index 60dc27834e1df..b078009ed509d 100644 --- a/Documentation/devicetree/bindings/phy/qcom,qmp-usb3-dp-phy.yaml +++ b/Documentation/devicetree/bindings/phy/qcom,qmp-usb3-dp-phy.yaml @@ -8,7 +8,7 @@ $schema: "http://devicetree.org/meta-schemas/core.yaml#" title: Qualcomm QMP USB3 DP PHY controller maintainers: - - Manu Gautam + - Wesley Cheng properties: compatible: diff --git a/Documentation/devicetree/bindings/phy/qcom,qusb2-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,qusb2-phy.yaml index 0ab3dad3f1213..d68ab49345b8f 100644 --- a/Documentation/devicetree/bindings/phy/qcom,qusb2-phy.yaml +++ b/Documentation/devicetree/bindings/phy/qcom,qusb2-phy.yaml @@ -8,7 +8,7 @@ $schema: "http://devicetree.org/meta-schemas/core.yaml#" title: Qualcomm QUSB2 phy controller maintainers: - - Manu Gautam + - Wesley Cheng description: QUSB2 controller supports LS/FS/HS usb connectivity on Qualcomm chipsets. diff --git a/Documentation/devicetree/bindings/phy/qcom,usb-snps-femto-v2.yaml b/Documentation/devicetree/bindings/phy/qcom,usb-snps-femto-v2.yaml index 1ce251de08557..7a0e6a9854da2 100644 --- a/Documentation/devicetree/bindings/phy/qcom,usb-snps-femto-v2.yaml +++ b/Documentation/devicetree/bindings/phy/qcom,usb-snps-femto-v2.yaml @@ -7,7 +7,7 @@ $schema: "http://devicetree.org/meta-schemas/core.yaml#" title: Qualcomm Synopsys Femto High-Speed USB PHY V2 maintainers: - - Wesley Cheng + - Wesley Cheng description: | Qualcomm High-Speed USB PHY diff --git a/Documentation/devicetree/bindings/pinctrl/pinctrl-rk805.txt b/Documentation/devicetree/bindings/pinctrl/pinctrl-rk805.txt index cbcbd31e3ce85..939cb5b6ffeac 100644 --- a/Documentation/devicetree/bindings/pinctrl/pinctrl-rk805.txt +++ b/Documentation/devicetree/bindings/pinctrl/pinctrl-rk805.txt @@ -27,7 +27,7 @@ Required properties: - pins: List of pins. Valid values of pins properties are: gpio0, gpio1. First 2 properties must be added in the RK805 PMIC node, documented in -Documentation/devicetree/bindings/mfd/rk808.txt +Documentation/devicetree/bindings/mfd/rockchip,rk808.yaml Optional properties: ------------------- diff --git a/Documentation/devicetree/bindings/pinctrl/ralink,mt7620-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/ralink,mt7620-pinctrl.yaml index 4d820df24b89f..6f17f39916400 100644 --- a/Documentation/devicetree/bindings/pinctrl/ralink,mt7620-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/ralink,mt7620-pinctrl.yaml @@ -32,31 +32,37 @@ patternProperties: groups: description: The pin group to select. enum: [ + # common + i2c, spi, wdt, + # For MT7620 SoC - ephy, i2c, mdio, nd_sd, pa, pcie, rgmii1, rgmii2, spi, spi refclk, - uartf, uartlite, wdt, wled, + ephy, mdio, nd_sd, pa, pcie, rgmii1, rgmii2, spi refclk, + uartf, uartlite, wled, # For MT7628 and MT7688 SoCs - gpio, i2c, i2s, p0led_an, p0led_kn, p1led_an, p1led_kn, p2led_an, + gpio, i2s, p0led_an, p0led_kn, p1led_an, p1led_kn, p2led_an, p2led_kn, p3led_an, p3led_kn, p4led_an, p4led_kn, perst, pwm0, - pwm1, refclk, sdmode, spi, spi cs1, spis, uart0, uart1, uart2, - wdt, wled_an, wled_kn, + pwm1, refclk, sdmode, spi cs1, spis, uart0, uart1, uart2, + wled_an, wled_kn, ] function: description: The mux function to select. enum: [ + # common + gpio, i2c, refclk, spi, + # For MT7620 SoC - ephy, gpio, gpio i2s, gpio uartf, i2c, i2s uartf, mdio, nand, pa, - pcie refclk, pcie rst, pcm gpio, pcm i2s, pcm uartf, refclk, - rgmii1, rgmii2, sd, spi, spi refclk, uartf, uartlite, wdt refclk, + ephy, gpio i2s, gpio uartf, i2s uartf, mdio, nand, pa, + pcie refclk, pcie rst, pcm gpio, pcm i2s, pcm uartf, + rgmii1, rgmii2, sd, spi refclk, uartf, uartlite, wdt refclk, wdt rst, wled, # For MT7628 and MT7688 SoCs - antenna, debug, gpio, i2c, i2s, jtag, p0led_an, p0led_kn, + antenna, debug, i2s, jtag, p0led_an, p0led_kn, p1led_an, p1led_kn, p2led_an, p2led_kn, p3led_an, p3led_kn, p4led_an, p4led_kn, pcie, pcm, perst, pwm, pwm0, pwm1, pwm_uart2, - refclk, rsvd, sdxc, sdxc d5 d4, sdxc d6, sdxc d7, spi, spi cs1, + rsvd, sdxc, sdxc d5 d4, sdxc d6, sdxc d7, spi cs1, spis, sw_r, uart0, uart1, uart2, utif, wdt, wled_an, wled_kn, -, ] diff --git a/Documentation/devicetree/bindings/pinctrl/ralink,rt305x-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/ralink,rt305x-pinctrl.yaml index 425401c542696..f602a5d6e13a6 100644 --- a/Documentation/devicetree/bindings/pinctrl/ralink,rt305x-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/ralink,rt305x-pinctrl.yaml @@ -33,32 +33,29 @@ patternProperties: groups: description: The pin group to select. enum: [ + # common + i2c, jtag, led, mdio, rgmii, spi, spi_cs1, uartf, uartlite, + # For RT3050, RT3052 and RT3350 SoCs - i2c, jtag, mdio, rgmii, sdram, spi, uartf, uartlite, + sdram, # For RT3352 SoC - i2c, jtag, led, lna, mdio, pa, rgmii, spi, spi_cs1, uartf, - uartlite, - - # For RT5350 SoC - i2c, jtag, led, spi, spi_cs1, uartf, uartlite, + lna, pa ] function: description: The mux function to select. enum: [ + # common + gpio, gpio i2s, gpio uartf, i2c, i2s uartf, jtag, led, mdio, + pcm gpio, pcm i2s, pcm uartf, rgmii, spi, spi_cs1, uartf, + uartlite, wdg_cs1, + # For RT3050, RT3052 and RT3350 SoCs - gpio, gpio i2s, gpio uartf, i2c, i2s uartf, jtag, mdio, pcm gpio, - pcm i2s, pcm uartf, rgmii, sdram, spi, uartf, uartlite, + sdram, # For RT3352 SoC - gpio, gpio i2s, gpio uartf, i2c, i2s uartf, jtag, led, lna, mdio, - pa, pcm gpio, pcm i2s, pcm uartf, rgmii, spi, spi_cs1, uartf, - uartlite, wdg_cs1, - - # For RT5350 SoC - gpio, gpio i2s, gpio uartf, i2c, i2s uartf, jtag, led, pcm gpio, - pcm i2s, pcm uartf, spi, spi_cs1, uartf, uartlite, wdg_cs1, + lna, pa ] required: diff --git a/Documentation/devicetree/bindings/power/supply/maxim,max77976.yaml b/Documentation/devicetree/bindings/power/supply/maxim,max77976.yaml index 675b9b26d2337..f23dcc50793e0 100644 --- a/Documentation/devicetree/bindings/power/supply/maxim,max77976.yaml +++ b/Documentation/devicetree/bindings/power/supply/maxim,max77976.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Maxim Integrated MAX77976 Battery charger maintainers: - - Luca Ceresoli + - Luca Ceresoli description: | The Maxim MAX77976 is a 19Vin / 5.5A, 1-Cell Li+ battery charger diff --git a/Documentation/devicetree/bindings/regulator/qcom,usb-vbus-regulator.yaml b/Documentation/devicetree/bindings/regulator/qcom,usb-vbus-regulator.yaml index 12ed98c28aaa5..dbe78cd4adba5 100644 --- a/Documentation/devicetree/bindings/regulator/qcom,usb-vbus-regulator.yaml +++ b/Documentation/devicetree/bindings/regulator/qcom,usb-vbus-regulator.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: The Qualcomm PMIC VBUS output regulator driver maintainers: - - Wesley Cheng + - Wesley Cheng description: | This regulator driver controls the VBUS output by the Qualcomm PMIC. This diff --git a/Documentation/devicetree/bindings/regulator/vexpress.txt b/Documentation/devicetree/bindings/regulator/vexpress.txt index d775f72487aa3..1c2e92c7831ea 100644 --- a/Documentation/devicetree/bindings/regulator/vexpress.txt +++ b/Documentation/devicetree/bindings/regulator/vexpress.txt @@ -4,7 +4,7 @@ Versatile Express voltage regulators Requires node properties: - "compatible" value: "arm,vexpress-volt" - "arm,vexpress-sysreg,func" when controlled via vexpress-sysreg - (see Documentation/devicetree/bindings/arm/vexpress-sysreg.txt + (see Documentation/devicetree/bindings/arm/vexpress-config.yaml for more details) Required regulator properties: diff --git a/Documentation/devicetree/bindings/spi/microchip,mpfs-spi.yaml b/Documentation/devicetree/bindings/spi/microchip,mpfs-spi.yaml index ece261b8e963f..7326c0a28d160 100644 --- a/Documentation/devicetree/bindings/spi/microchip,mpfs-spi.yaml +++ b/Documentation/devicetree/bindings/spi/microchip,mpfs-spi.yaml @@ -47,6 +47,5 @@ examples: clocks = <&clkcfg CLK_SPI0>; interrupt-parent = <&plic>; interrupts = <54>; - spi-max-frequency = <25000000>; }; ... diff --git a/Documentation/devicetree/bindings/spi/qcom,spi-geni-qcom.yaml b/Documentation/devicetree/bindings/spi/qcom,spi-geni-qcom.yaml index e2c7b934c50d5..78ceb9d67754f 100644 --- a/Documentation/devicetree/bindings/spi/qcom,spi-geni-qcom.yaml +++ b/Documentation/devicetree/bindings/spi/qcom,spi-geni-qcom.yaml @@ -110,7 +110,6 @@ examples: pinctrl-names = "default"; pinctrl-0 = <&qup_spi1_default>; interrupts = ; - spi-max-frequency = <50000000>; #address-cells = <1>; #size-cells = <0>; }; diff --git a/Documentation/devicetree/bindings/usb/dwc3-st.txt b/Documentation/devicetree/bindings/usb/dwc3-st.txt index bf73de0d5b4af..4aa368447b1e8 100644 --- a/Documentation/devicetree/bindings/usb/dwc3-st.txt +++ b/Documentation/devicetree/bindings/usb/dwc3-st.txt @@ -13,7 +13,7 @@ Required properties: - resets : list of phandle and reset specifier pairs. There should be two entries, one for the powerdown and softreset lines of the usb3 IP - reset-names : list of reset signal names. Names should be "powerdown" and "softreset" -See: Documentation/devicetree/bindings/reset/st,sti-powerdown.txt +See: Documentation/devicetree/bindings/reset/st,stih407-powerdown.yaml See: Documentation/devicetree/bindings/reset/reset.txt - #address-cells, #size-cells : should be '1' if the device has sub-nodes diff --git a/Documentation/devicetree/bindings/usb/ehci-st.txt b/Documentation/devicetree/bindings/usb/ehci-st.txt index 065c91d955ad1..d6f2bdee20fc2 100644 --- a/Documentation/devicetree/bindings/usb/ehci-st.txt +++ b/Documentation/devicetree/bindings/usb/ehci-st.txt @@ -17,7 +17,7 @@ See: Documentation/devicetree/bindings/clock/clock-bindings.txt - resets : phandle + reset specifier pairs to the powerdown and softreset lines of the USB IP - reset-names : should be "power" and "softreset" -See: Documentation/devicetree/bindings/reset/st,sti-powerdown.txt +See: Documentation/devicetree/bindings/reset/st,stih407-powerdown.yaml See: Documentation/devicetree/bindings/reset/reset.txt Example: diff --git a/Documentation/devicetree/bindings/usb/generic-ehci.yaml b/Documentation/devicetree/bindings/usb/generic-ehci.yaml index 0b4524b6409ec..1e84e1b7ab271 100644 --- a/Documentation/devicetree/bindings/usb/generic-ehci.yaml +++ b/Documentation/devicetree/bindings/usb/generic-ehci.yaml @@ -136,7 +136,8 @@ properties: Phandle of a companion. phys: - maxItems: 1 + minItems: 1 + maxItems: 3 phy-names: const: usb diff --git a/Documentation/devicetree/bindings/usb/generic-ohci.yaml b/Documentation/devicetree/bindings/usb/generic-ohci.yaml index e2ac846653161..bb6bbd5f129d4 100644 --- a/Documentation/devicetree/bindings/usb/generic-ohci.yaml +++ b/Documentation/devicetree/bindings/usb/generic-ohci.yaml @@ -103,7 +103,8 @@ properties: Overrides the detected port count phys: - maxItems: 1 + minItems: 1 + maxItems: 3 phy-names: const: usb diff --git a/Documentation/devicetree/bindings/usb/ohci-st.txt b/Documentation/devicetree/bindings/usb/ohci-st.txt index 44c998c16f85b..1c735573abc03 100644 --- a/Documentation/devicetree/bindings/usb/ohci-st.txt +++ b/Documentation/devicetree/bindings/usb/ohci-st.txt @@ -15,7 +15,7 @@ See: Documentation/devicetree/bindings/clock/clock-bindings.txt - resets : phandle to the powerdown and reset controller for the USB IP - reset-names : should be "power" and "softreset". -See: Documentation/devicetree/bindings/reset/st,sti-powerdown.txt +See: Documentation/devicetree/bindings/reset/st,stih407-powerdown.yaml See: Documentation/devicetree/bindings/reset/reset.txt Example: diff --git a/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml b/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml index e336fe2e03cca..749e1963ddbb8 100644 --- a/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml +++ b/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Qualcomm SuperSpeed DWC3 USB SoC controller maintainers: - - Manu Gautam + - Wesley Cheng properties: compatible: diff --git a/Documentation/devicetree/bindings/vendor-prefixes.yaml b/Documentation/devicetree/bindings/vendor-prefixes.yaml index 6bb20b4554d7e..0496773a3c4d8 100644 --- a/Documentation/devicetree/bindings/vendor-prefixes.yaml +++ b/Documentation/devicetree/bindings/vendor-prefixes.yaml @@ -143,6 +143,9 @@ patternProperties: description: ASPEED Technology Inc. "^asus,.*": description: AsusTek Computer Inc. + "^atheros,.*": + description: Qualcomm Atheros, Inc. (deprecated, use qca) + deprecated: true "^atlas,.*": description: Atlas Scientific LLC "^atmel,.*": diff --git a/Documentation/devicetree/bindings/watchdog/allwinner,sun4i-a10-wdt.yaml b/Documentation/devicetree/bindings/watchdog/allwinner,sun4i-a10-wdt.yaml index cbcf19f514114..ed6c1ca80dcc4 100644 --- a/Documentation/devicetree/bindings/watchdog/allwinner,sun4i-a10-wdt.yaml +++ b/Documentation/devicetree/bindings/watchdog/allwinner,sun4i-a10-wdt.yaml @@ -64,7 +64,6 @@ if: then: properties: clocks: - minItems: 2 items: - description: High-frequency oscillator input, divided internally - description: Low-frequency oscillator input diff --git a/Documentation/driver-api/gpio/board.rst b/Documentation/driver-api/gpio/board.rst index 4e3adf31c8d1d..b33aa04f213fe 100644 --- a/Documentation/driver-api/gpio/board.rst +++ b/Documentation/driver-api/gpio/board.rst @@ -6,7 +6,7 @@ This document explains how GPIOs can be assigned to given devices and functions. Note that it only applies to the new descriptor-based interface. For a description of the deprecated integer-based GPIO interface please refer to -gpio-legacy.txt (actually, there is no real mapping possible with the old +legacy.rst (actually, there is no real mapping possible with the old interface; you just fetch an integer from somewhere and request the corresponding GPIO). diff --git a/Documentation/driver-api/gpio/consumer.rst b/Documentation/driver-api/gpio/consumer.rst index 47869ca8ccf03..72bcf5f5e3a21 100644 --- a/Documentation/driver-api/gpio/consumer.rst +++ b/Documentation/driver-api/gpio/consumer.rst @@ -4,7 +4,7 @@ GPIO Descriptor Consumer Interface This document describes the consumer interface of the GPIO framework. Note that it describes the new descriptor-based interface. For a description of the -deprecated integer-based GPIO interface please refer to gpio-legacy.txt. +deprecated integer-based GPIO interface please refer to legacy.rst. Guidelines for GPIOs consumers @@ -78,7 +78,7 @@ whether the line is configured active high or active low (see The two last flags are used for use cases where open drain is mandatory, such as I2C: if the line is not already configured as open drain in the mappings -(see board.txt), then open drain will be enforced anyway and a warning will be +(see board.rst), then open drain will be enforced anyway and a warning will be printed that the board configuration needs to be updated to match the use case. Both functions return either a valid GPIO descriptor, or an error code checkable @@ -270,7 +270,7 @@ driven. The same is applicable for open drain or open source output lines: those do not actively drive their output high (open drain) or low (open source), they just switch their output to a high impedance value. The consumer should not need to -care. (For details read about open drain in driver.txt.) +care. (For details read about open drain in driver.rst.) With this, all the gpiod_set_(array)_value_xxx() functions interpret the parameter "value" as "asserted" ("1") or "de-asserted" ("0"). The physical line diff --git a/Documentation/driver-api/gpio/intro.rst b/Documentation/driver-api/gpio/intro.rst index 2e924fb5b3d53..c9c19243b97f8 100644 --- a/Documentation/driver-api/gpio/intro.rst +++ b/Documentation/driver-api/gpio/intro.rst @@ -14,12 +14,12 @@ Due to the history of GPIO interfaces in the kernel, there are two different ways to obtain and use GPIOs: - The descriptor-based interface is the preferred way to manipulate GPIOs, - and is described by all the files in this directory excepted gpio-legacy.txt. + and is described by all the files in this directory excepted legacy.rst. - The legacy integer-based interface which is considered deprecated (but still - usable for compatibility reasons) is documented in gpio-legacy.txt. + usable for compatibility reasons) is documented in legacy.rst. The remainder of this document applies to the new descriptor-based interface. -gpio-legacy.txt contains the same information applied to the legacy +legacy.rst contains the same information applied to the legacy integer-based interface. diff --git a/Documentation/hte/hte.rst b/Documentation/driver-api/hte/hte.rst similarity index 100% rename from Documentation/hte/hte.rst rename to Documentation/driver-api/hte/hte.rst diff --git a/Documentation/hte/index.rst b/Documentation/driver-api/hte/index.rst similarity index 100% rename from Documentation/hte/index.rst rename to Documentation/driver-api/hte/index.rst diff --git a/Documentation/hte/tegra194-hte.rst b/Documentation/driver-api/hte/tegra194-hte.rst similarity index 100% rename from Documentation/hte/tegra194-hte.rst rename to Documentation/driver-api/hte/tegra194-hte.rst diff --git a/Documentation/driver-api/index.rst b/Documentation/driver-api/index.rst index d76a60d95b588..a6d525cd9fc45 100644 --- a/Documentation/driver-api/index.rst +++ b/Documentation/driver-api/index.rst @@ -108,6 +108,7 @@ available subsections can be seen below. xilinx/index xillybus zorro + hte/index .. only:: subproject and html diff --git a/Documentation/features/core/cBPF-JIT/arch-support.txt b/Documentation/features/core/cBPF-JIT/arch-support.txt index 10482dee8703c..a053667a7a8c1 100644 --- a/Documentation/features/core/cBPF-JIT/arch-support.txt +++ b/Documentation/features/core/cBPF-JIT/arch-support.txt @@ -13,6 +13,7 @@ | csky: | TODO | | hexagon: | TODO | | ia64: | TODO | + | loong: | TODO | | m68k: | TODO | | microblaze: | TODO | | mips: | ok | diff --git a/Documentation/features/core/eBPF-JIT/arch-support.txt b/Documentation/features/core/eBPF-JIT/arch-support.txt index bcefb5afc7d65..c0bb9c92937f0 100644 --- a/Documentation/features/core/eBPF-JIT/arch-support.txt +++ b/Documentation/features/core/eBPF-JIT/arch-support.txt @@ -13,6 +13,7 @@ | csky: | TODO | | hexagon: | TODO | | ia64: | TODO | + | loong: | TODO | | m68k: | TODO | | microblaze: | TODO | | mips: | ok | diff --git a/Documentation/features/core/generic-idle-thread/arch-support.txt b/Documentation/features/core/generic-idle-thread/arch-support.txt index d80d99449ac15..c9bfff292816a 100644 --- a/Documentation/features/core/generic-idle-thread/arch-support.txt +++ b/Documentation/features/core/generic-idle-thread/arch-support.txt @@ -13,6 +13,7 @@ | csky: | ok | | hexagon: | ok | | ia64: | ok | + | loong: | ok | | m68k: | TODO | | microblaze: | TODO | | mips: | ok | diff --git a/Documentation/features/core/jump-labels/arch-support.txt b/Documentation/features/core/jump-labels/arch-support.txt index 53eab154925d5..35e2a44b1448b 100644 --- a/Documentation/features/core/jump-labels/arch-support.txt +++ b/Documentation/features/core/jump-labels/arch-support.txt @@ -13,6 +13,7 @@ | csky: | TODO | | hexagon: | TODO | | ia64: | TODO | + | loong: | TODO | | m68k: | TODO | | microblaze: | TODO | | mips: | ok | diff --git a/Documentation/features/core/thread-info-in-task/arch-support.txt b/Documentation/features/core/thread-info-in-task/arch-support.txt index 94926451afb90..9b3e2ce12b440 100644 --- a/Documentation/features/core/thread-info-in-task/arch-support.txt +++ b/Documentation/features/core/thread-info-in-task/arch-support.txt @@ -13,6 +13,7 @@ | csky: | TODO | | hexagon: | TODO | | ia64: | TODO | + | loong: | TODO | | m68k: | TODO | | microblaze: | TODO | | mips: | TODO | diff --git a/Documentation/features/core/tracehook/arch-support.txt b/Documentation/features/core/tracehook/arch-support.txt index b4274b8141b67..9c7ffec5d51d5 100644 --- a/Documentation/features/core/tracehook/arch-support.txt +++ b/Documentation/features/core/tracehook/arch-support.txt @@ -13,6 +13,7 @@ | csky: | ok | | hexagon: | ok | | ia64: | ok | + | loong: | ok | | m68k: | TODO | | microblaze: | TODO | | mips: | ok | diff --git a/Documentation/features/debug/KASAN/arch-support.txt b/Documentation/features/debug/KASAN/arch-support.txt index c15bb4b21b6fd..2fd5fb6f5f236 100644 --- a/Documentation/features/debug/KASAN/arch-support.txt +++ b/Documentation/features/debug/KASAN/arch-support.txt @@ -13,6 +13,7 @@ | csky: | TODO | | hexagon: | TODO | | ia64: | TODO | + | loong: | TODO | | m68k: | TODO | | microblaze: | TODO | | mips: | TODO | diff --git a/Documentation/features/debug/debug-vm-pgtable/arch-support.txt b/Documentation/features/debug/debug-vm-pgtable/arch-support.txt index 4c31fc92a3124..c45711e55c7bf 100644 --- a/Documentation/features/debug/debug-vm-pgtable/arch-support.txt +++ b/Documentation/features/debug/debug-vm-pgtable/arch-support.txt @@ -13,12 +13,13 @@ | csky: | TODO | | hexagon: | TODO | | ia64: | TODO | + | loong: | TODO | | m68k: | TODO | | microblaze: | TODO | | mips: | TODO | | nios2: | TODO | | openrisc: | TODO | - | parisc: | TODO | + | parisc: | ok | | powerpc: | ok | | riscv: | ok | | s390: | ok | diff --git a/Documentation/features/debug/gcov-profile-all/arch-support.txt b/Documentation/features/debug/gcov-profile-all/arch-support.txt index d7a5ac4bc1fef..502c1d4096488 100644 --- a/Documentation/features/debug/gcov-profile-all/arch-support.txt +++ b/Documentation/features/debug/gcov-profile-all/arch-support.txt @@ -13,6 +13,7 @@ | csky: | ok | | hexagon: | TODO | | ia64: | TODO | + | loong: | TODO | | m68k: | TODO | | microblaze: | ok | | mips: | ok | @@ -24,7 +25,7 @@ | s390: | ok | | sh: | ok | | sparc: | TODO | - | um: | TODO | + | um: | ok | | x86: | ok | | xtensa: | TODO | ----------------------- diff --git a/Documentation/features/debug/kcov/arch-support.txt b/Documentation/features/debug/kcov/arch-support.txt index 136e14c2b6039..afb90bebded23 100644 --- a/Documentation/features/debug/kcov/arch-support.txt +++ b/Documentation/features/debug/kcov/arch-support.txt @@ -13,6 +13,7 @@ | csky: | TODO | | hexagon: | TODO | | ia64: | TODO | + | loong: | TODO | | m68k: | TODO | | microblaze: | TODO | | mips: | ok | diff --git a/Documentation/features/debug/kgdb/arch-support.txt b/Documentation/features/debug/kgdb/arch-support.txt index 5b3f3d8ae4622..04120d278c221 100644 --- a/Documentation/features/debug/kgdb/arch-support.txt +++ b/Documentation/features/debug/kgdb/arch-support.txt @@ -13,6 +13,7 @@ | csky: | TODO | | hexagon: | ok | | ia64: | TODO | + | loong: | TODO | | m68k: | TODO | | microblaze: | ok | | mips: | ok | diff --git a/Documentation/features/debug/kmemleak/arch-support.txt b/Documentation/features/debug/kmemleak/arch-support.txt index 7a2eab4fdf9d9..e487c356ab206 100644 --- a/Documentation/features/debug/kmemleak/arch-support.txt +++ b/Documentation/features/debug/kmemleak/arch-support.txt @@ -13,6 +13,7 @@ | csky: | ok | | hexagon: | TODO | | ia64: | TODO | + | loong: | TODO | | m68k: | TODO | | microblaze: | ok | | mips: | ok | diff --git a/Documentation/features/debug/kprobes-on-ftrace/arch-support.txt b/Documentation/features/debug/kprobes-on-ftrace/arch-support.txt index db02ab1941386..b3697f4c806e8 100644 --- a/Documentation/features/debug/kprobes-on-ftrace/arch-support.txt +++ b/Documentation/features/debug/kprobes-on-ftrace/arch-support.txt @@ -13,6 +13,7 @@ | csky: | ok | | hexagon: | TODO | | ia64: | TODO | + | loong: | TODO | | m68k: | TODO | | microblaze: | TODO | | mips: | TODO | diff --git a/Documentation/features/debug/kprobes/arch-support.txt b/Documentation/features/debug/kprobes/arch-support.txt index ec186e7deebc7..452385ac9e067 100644 --- a/Documentation/features/debug/kprobes/arch-support.txt +++ b/Documentation/features/debug/kprobes/arch-support.txt @@ -13,6 +13,7 @@ | csky: | ok | | hexagon: | TODO | | ia64: | ok | + | loong: | TODO | | m68k: | TODO | | microblaze: | TODO | | mips: | ok | diff --git a/Documentation/features/debug/kretprobes/arch-support.txt b/Documentation/features/debug/kretprobes/arch-support.txt index 4b7865e693f60..daecf046e72b4 100644 --- a/Documentation/features/debug/kretprobes/arch-support.txt +++ b/Documentation/features/debug/kretprobes/arch-support.txt @@ -13,6 +13,7 @@ | csky: | ok | | hexagon: | TODO | | ia64: | ok | + | loong: | TODO | | m68k: | TODO | | microblaze: | TODO | | mips: | ok | diff --git a/Documentation/features/debug/optprobes/arch-support.txt b/Documentation/features/debug/optprobes/arch-support.txt index 5d9befa041c73..adb1bd055bfdd 100644 --- a/Documentation/features/debug/optprobes/arch-support.txt +++ b/Documentation/features/debug/optprobes/arch-support.txt @@ -13,6 +13,7 @@ | csky: | TODO | | hexagon: | TODO | | ia64: | TODO | + | loong: | TODO | | m68k: | TODO | | microblaze: | TODO | | mips: | TODO | diff --git a/Documentation/features/debug/stackprotector/arch-support.txt b/Documentation/features/debug/stackprotector/arch-support.txt index d97fd38460e69..ddcd7161d14ce 100644 --- a/Documentation/features/debug/stackprotector/arch-support.txt +++ b/Documentation/features/debug/stackprotector/arch-support.txt @@ -13,6 +13,7 @@ | csky: | ok | | hexagon: | TODO | | ia64: | TODO | + | loong: | TODO | | m68k: | TODO | | microblaze: | TODO | | mips: | ok | diff --git a/Documentation/features/debug/uprobes/arch-support.txt b/Documentation/features/debug/uprobes/arch-support.txt index d30e3475904ec..25121200f9f9e 100644 --- a/Documentation/features/debug/uprobes/arch-support.txt +++ b/Documentation/features/debug/uprobes/arch-support.txt @@ -13,6 +13,7 @@ | csky: | ok | | hexagon: | TODO | | ia64: | TODO | + | loong: | TODO | | m68k: | TODO | | microblaze: | TODO | | mips: | ok | diff --git a/Documentation/features/debug/user-ret-profiler/arch-support.txt b/Documentation/features/debug/user-ret-profiler/arch-support.txt index 9ae1fa2eb27cb..f2fcff8e77b79 100644 --- a/Documentation/features/debug/user-ret-profiler/arch-support.txt +++ b/Documentation/features/debug/user-ret-profiler/arch-support.txt @@ -13,6 +13,7 @@ | csky: | TODO | | hexagon: | TODO | | ia64: | TODO | + | loong: | TODO | | m68k: | TODO | | microblaze: | TODO | | mips: | TODO | diff --git a/Documentation/features/io/dma-contiguous/arch-support.txt b/Documentation/features/io/dma-contiguous/arch-support.txt index 9e09988eb6545..95e485c87e36d 100644 --- a/Documentation/features/io/dma-contiguous/arch-support.txt +++ b/Documentation/features/io/dma-contiguous/arch-support.txt @@ -13,6 +13,7 @@ | csky: | ok | | hexagon: | TODO | | ia64: | TODO | + | loong: | ok | | m68k: | TODO | | microblaze: | ok | | mips: | ok | diff --git a/Documentation/features/locking/cmpxchg-local/arch-support.txt b/Documentation/features/locking/cmpxchg-local/arch-support.txt index 5c4ec316dbac0..8b1a8d9e1c797 100644 --- a/Documentation/features/locking/cmpxchg-local/arch-support.txt +++ b/Documentation/features/locking/cmpxchg-local/arch-support.txt @@ -13,6 +13,7 @@ | csky: | TODO | | hexagon: | TODO | | ia64: | TODO | + | loong: | TODO | | m68k: | TODO | | microblaze: | TODO | | mips: | TODO | diff --git a/Documentation/features/locking/lockdep/arch-support.txt b/Documentation/features/locking/lockdep/arch-support.txt index 65007c1ac44f6..ab69e8f56a377 100644 --- a/Documentation/features/locking/lockdep/arch-support.txt +++ b/Documentation/features/locking/lockdep/arch-support.txt @@ -13,6 +13,7 @@ | csky: | ok | | hexagon: | ok | | ia64: | TODO | + | loong: | ok | | m68k: | TODO | | microblaze: | ok | | mips: | ok | diff --git a/Documentation/features/locking/queued-rwlocks/arch-support.txt b/Documentation/features/locking/queued-rwlocks/arch-support.txt index 20056670fb09e..0bfb72a08d82d 100644 --- a/Documentation/features/locking/queued-rwlocks/arch-support.txt +++ b/Documentation/features/locking/queued-rwlocks/arch-support.txt @@ -13,6 +13,7 @@ | csky: | ok | | hexagon: | TODO | | ia64: | TODO | + | loong: | ok | | m68k: | TODO | | microblaze: | TODO | | mips: | ok | @@ -20,7 +21,7 @@ | openrisc: | ok | | parisc: | TODO | | powerpc: | ok | - | riscv: | TODO | + | riscv: | ok | | s390: | TODO | | sh: | TODO | | sparc: | ok | diff --git a/Documentation/features/locking/queued-spinlocks/arch-support.txt b/Documentation/features/locking/queued-spinlocks/arch-support.txt index 707514faac7be..d2f2201febc8f 100644 --- a/Documentation/features/locking/queued-spinlocks/arch-support.txt +++ b/Documentation/features/locking/queued-spinlocks/arch-support.txt @@ -13,6 +13,7 @@ | csky: | TODO | | hexagon: | TODO | | ia64: | TODO | + | loong: | TODO | | m68k: | TODO | | microblaze: | TODO | | mips: | ok | diff --git a/Documentation/features/perf/kprobes-event/arch-support.txt b/Documentation/features/perf/kprobes-event/arch-support.txt index 9f31ce9b9f2a4..0d0647b067624 100644 --- a/Documentation/features/perf/kprobes-event/arch-support.txt +++ b/Documentation/features/perf/kprobes-event/arch-support.txt @@ -7,12 +7,13 @@ | arch |status| ----------------------- | alpha: | TODO | - | arc: | TODO | + | arc: | ok | | arm: | ok | | arm64: | ok | | csky: | ok | | hexagon: | ok | | ia64: | TODO | + | loong: | ok | | m68k: | TODO | | microblaze: | TODO | | mips: | ok | diff --git a/Documentation/features/perf/perf-regs/arch-support.txt b/Documentation/features/perf/perf-regs/arch-support.txt index f148c4329c7ad..13c297bbf05cc 100644 --- a/Documentation/features/perf/perf-regs/arch-support.txt +++ b/Documentation/features/perf/perf-regs/arch-support.txt @@ -13,6 +13,7 @@ | csky: | ok | | hexagon: | TODO | | ia64: | TODO | + | loong: | TODO | | m68k: | TODO | | microblaze: | TODO | | mips: | ok | diff --git a/Documentation/features/perf/perf-stackdump/arch-support.txt b/Documentation/features/perf/perf-stackdump/arch-support.txt index 32c88b6a910cf..931687eec6719 100644 --- a/Documentation/features/perf/perf-stackdump/arch-support.txt +++ b/Documentation/features/perf/perf-stackdump/arch-support.txt @@ -13,6 +13,7 @@ | csky: | ok | | hexagon: | TODO | | ia64: | TODO | + | loong: | TODO | | m68k: | TODO | | microblaze: | TODO | | mips: | ok | diff --git a/Documentation/features/sched/membarrier-sync-core/arch-support.txt b/Documentation/features/sched/membarrier-sync-core/arch-support.txt index d82a1f0cdc910..336d728b8a455 100644 --- a/Documentation/features/sched/membarrier-sync-core/arch-support.txt +++ b/Documentation/features/sched/membarrier-sync-core/arch-support.txt @@ -36,6 +36,7 @@ | csky: | TODO | | hexagon: | TODO | | ia64: | TODO | + | loong: | TODO | | m68k: | TODO | | microblaze: | TODO | | mips: | TODO | diff --git a/Documentation/features/sched/numa-balancing/arch-support.txt b/Documentation/features/sched/numa-balancing/arch-support.txt index 2687564e5fa87..76d0121183723 100644 --- a/Documentation/features/sched/numa-balancing/arch-support.txt +++ b/Documentation/features/sched/numa-balancing/arch-support.txt @@ -13,6 +13,7 @@ | csky: | .. | | hexagon: | .. | | ia64: | TODO | + | loong: | ok | | m68k: | .. | | microblaze: | .. | | mips: | TODO | diff --git a/Documentation/features/seccomp/seccomp-filter/arch-support.txt b/Documentation/features/seccomp/seccomp-filter/arch-support.txt index 1b4109199e9d1..a86b8b1f3d10a 100644 --- a/Documentation/features/seccomp/seccomp-filter/arch-support.txt +++ b/Documentation/features/seccomp/seccomp-filter/arch-support.txt @@ -13,6 +13,7 @@ | csky: | ok | | hexagon: | TODO | | ia64: | TODO | + | loong: | ok | | m68k: | TODO | | microblaze: | TODO | | mips: | ok | diff --git a/Documentation/features/time/arch-tick-broadcast/arch-support.txt b/Documentation/features/time/arch-tick-broadcast/arch-support.txt index 27327256bd058..364169f00ee2f 100644 --- a/Documentation/features/time/arch-tick-broadcast/arch-support.txt +++ b/Documentation/features/time/arch-tick-broadcast/arch-support.txt @@ -13,6 +13,7 @@ | csky: | TODO | | hexagon: | TODO | | ia64: | TODO | + | loong: | ok | | m68k: | TODO | | microblaze: | TODO | | mips: | ok | diff --git a/Documentation/features/time/clockevents/arch-support.txt b/Documentation/features/time/clockevents/arch-support.txt index b9a4bda2c8f55..6ea274790e471 100644 --- a/Documentation/features/time/clockevents/arch-support.txt +++ b/Documentation/features/time/clockevents/arch-support.txt @@ -13,6 +13,7 @@ | csky: | ok | | hexagon: | ok | | ia64: | TODO | + | loong: | ok | | m68k: | TODO | | microblaze: | ok | | mips: | ok | diff --git a/Documentation/features/time/context-tracking/arch-support.txt b/Documentation/features/time/context-tracking/arch-support.txt index 4aa51c9fa32b0..c9e0a16290e68 100644 --- a/Documentation/features/time/context-tracking/arch-support.txt +++ b/Documentation/features/time/context-tracking/arch-support.txt @@ -13,6 +13,7 @@ | csky: | ok | | hexagon: | TODO | | ia64: | TODO | + | loong: | ok | | m68k: | TODO | | microblaze: | TODO | | mips: | ok | diff --git a/Documentation/features/time/irq-time-acct/arch-support.txt b/Documentation/features/time/irq-time-acct/arch-support.txt index 0306ece41faae..fd17d8de5ef1e 100644 --- a/Documentation/features/time/irq-time-acct/arch-support.txt +++ b/Documentation/features/time/irq-time-acct/arch-support.txt @@ -13,6 +13,7 @@ | csky: | TODO | | hexagon: | TODO | | ia64: | .. | + | loong: | ok | | m68k: | TODO | | microblaze: | TODO | | mips: | ok | diff --git a/Documentation/features/time/virt-cpuacct/arch-support.txt b/Documentation/features/time/virt-cpuacct/arch-support.txt index 5d64e40c0092e..1a859ac05e9ef 100644 --- a/Documentation/features/time/virt-cpuacct/arch-support.txt +++ b/Documentation/features/time/virt-cpuacct/arch-support.txt @@ -13,6 +13,7 @@ | csky: | ok | | hexagon: | TODO | | ia64: | ok | + | loong: | ok | | m68k: | TODO | | microblaze: | TODO | | mips: | ok | diff --git a/Documentation/features/vm/ELF-ASLR/arch-support.txt b/Documentation/features/vm/ELF-ASLR/arch-support.txt index 92c9db24a6a39..b1229953391b2 100644 --- a/Documentation/features/vm/ELF-ASLR/arch-support.txt +++ b/Documentation/features/vm/ELF-ASLR/arch-support.txt @@ -13,6 +13,7 @@ | csky: | TODO | | hexagon: | TODO | | ia64: | TODO | + | loong: | TODO | | m68k: | TODO | | microblaze: | TODO | | mips: | ok | diff --git a/Documentation/features/vm/PG_uncached/arch-support.txt b/Documentation/features/vm/PG_uncached/arch-support.txt index 7424fea37614b..02f325fbfcd0d 100644 --- a/Documentation/features/vm/PG_uncached/arch-support.txt +++ b/Documentation/features/vm/PG_uncached/arch-support.txt @@ -13,6 +13,7 @@ | csky: | TODO | | hexagon: | TODO | | ia64: | ok | + | loong: | TODO | | m68k: | TODO | | microblaze: | TODO | | mips: | TODO | diff --git a/Documentation/features/vm/THP/arch-support.txt b/Documentation/features/vm/THP/arch-support.txt index 60985067626b0..9bfff977ef55b 100644 --- a/Documentation/features/vm/THP/arch-support.txt +++ b/Documentation/features/vm/THP/arch-support.txt @@ -13,6 +13,7 @@ | csky: | .. | | hexagon: | .. | | ia64: | TODO | + | loong: | ok | | m68k: | .. | | microblaze: | .. | | mips: | ok | diff --git a/Documentation/features/vm/TLB/arch-support.txt b/Documentation/features/vm/TLB/arch-support.txt index f2dcbec6020ea..039e4e91ada33 100644 --- a/Documentation/features/vm/TLB/arch-support.txt +++ b/Documentation/features/vm/TLB/arch-support.txt @@ -13,6 +13,7 @@ | csky: | TODO | | hexagon: | TODO | | ia64: | TODO | + | loong: | TODO | | m68k: | .. | | microblaze: | .. | | mips: | TODO | diff --git a/Documentation/features/vm/huge-vmap/arch-support.txt b/Documentation/features/vm/huge-vmap/arch-support.txt index 680090df03e19..13b4940e0c3a7 100644 --- a/Documentation/features/vm/huge-vmap/arch-support.txt +++ b/Documentation/features/vm/huge-vmap/arch-support.txt @@ -13,6 +13,7 @@ | csky: | TODO | | hexagon: | TODO | | ia64: | TODO | + | loong: | TODO | | m68k: | TODO | | microblaze: | TODO | | mips: | TODO | diff --git a/Documentation/features/vm/ioremap_prot/arch-support.txt b/Documentation/features/vm/ioremap_prot/arch-support.txt index 205a90e820501..b01bf7bca3e6d 100644 --- a/Documentation/features/vm/ioremap_prot/arch-support.txt +++ b/Documentation/features/vm/ioremap_prot/arch-support.txt @@ -13,6 +13,7 @@ | csky: | TODO | | hexagon: | TODO | | ia64: | TODO | + | loong: | ok | | m68k: | TODO | | microblaze: | TODO | | mips: | ok | diff --git a/Documentation/features/vm/pte_special/arch-support.txt b/Documentation/features/vm/pte_special/arch-support.txt index 9f16d6e4e11e0..fc3687b5e89bf 100644 --- a/Documentation/features/vm/pte_special/arch-support.txt +++ b/Documentation/features/vm/pte_special/arch-support.txt @@ -13,12 +13,13 @@ | csky: | TODO | | hexagon: | TODO | | ia64: | TODO | + | loong: | ok | | m68k: | TODO | | microblaze: | TODO | | mips: | ok | | nios2: | TODO | | openrisc: | TODO | - | parisc: | TODO | + | parisc: | ok | | powerpc: | ok | | riscv: | ok | | s390: | ok | diff --git a/Documentation/filesystems/btrfs.rst b/Documentation/filesystems/btrfs.rst index d0904f6028197..992eddb0e11b8 100644 --- a/Documentation/filesystems/btrfs.rst +++ b/Documentation/filesystems/btrfs.rst @@ -19,13 +19,23 @@ The main Btrfs features include: * Subvolumes (separate internal filesystem roots) * Object level mirroring and striping * Checksums on data and metadata (multiple algorithms available) - * Compression + * Compression (multiple algorithms available) + * Reflink, deduplication + * Scrub (on-line checksum verification) + * Hierarchical quota groups (subvolume and snapshot support) * Integrated multiple device support, with several raid algorithms * Offline filesystem check - * Efficient incremental backup and FS mirroring + * Efficient incremental backup and FS mirroring (send/receive) + * Trim/discard * Online filesystem defragmentation + * Swapfile support + * Zoned mode + * Read/write metadata verification + * Online resize (shrink, grow) -For more information please refer to the wiki +For more information please refer to the documentation site or wiki + + https://btrfs.readthedocs.io https://btrfs.wiki.kernel.org diff --git a/Documentation/filesystems/ext4/attributes.rst b/Documentation/filesystems/ext4/attributes.rst index 871d2da7a0a91..87814696a65b5 100644 --- a/Documentation/filesystems/ext4/attributes.rst +++ b/Documentation/filesystems/ext4/attributes.rst @@ -13,8 +13,8 @@ disappeared as of Linux 3.0. There are two places where extended attributes can be found. The first place is between the end of each inode entry and the beginning of the -next inode entry. For example, if inode.i\_extra\_isize = 28 and -sb.inode\_size = 256, then there are 256 - (128 + 28) = 100 bytes +next inode entry. For example, if inode.i_extra_isize = 28 and +sb.inode_size = 256, then there are 256 - (128 + 28) = 100 bytes available for in-inode extended attribute storage. The second place where extended attributes can be found is in the block pointed to by ``inode.i_file_acl``. As of Linux 3.11, it is not possible for this @@ -38,8 +38,8 @@ Extended attributes, when stored after the inode, have a header - Name - Description * - 0x0 - - \_\_le32 - - h\_magic + - __le32 + - h_magic - Magic number for identification, 0xEA020000. This value is set by the Linux driver, though e2fsprogs doesn't seem to check it(?) @@ -55,28 +55,28 @@ The beginning of an extended attribute block is in - Name - Description * - 0x0 - - \_\_le32 - - h\_magic + - __le32 + - h_magic - Magic number for identification, 0xEA020000. * - 0x4 - - \_\_le32 - - h\_refcount + - __le32 + - h_refcount - Reference count. * - 0x8 - - \_\_le32 - - h\_blocks + - __le32 + - h_blocks - Number of disk blocks used. * - 0xC - - \_\_le32 - - h\_hash + - __le32 + - h_hash - Hash value of all attributes. * - 0x10 - - \_\_le32 - - h\_checksum + - __le32 + - h_checksum - Checksum of the extended attribute block. * - 0x14 - - \_\_u32 - - h\_reserved[3] + - __u32 + - h_reserved[3] - Zero. The checksum is calculated against the FS UUID, the 64-bit block number @@ -100,46 +100,46 @@ Attributes stored inside an inode do not need be stored in sorted order. - Name - Description * - 0x0 - - \_\_u8 - - e\_name\_len + - __u8 + - e_name_len - Length of name. * - 0x1 - - \_\_u8 - - e\_name\_index + - __u8 + - e_name_index - Attribute name index. There is a discussion of this below. * - 0x2 - - \_\_le16 - - e\_value\_offs + - __le16 + - e_value_offs - Location of this attribute's value on the disk block where it is stored. Multiple attributes can share the same value. For an inode attribute this value is relative to the start of the first entry; for a block this value is relative to the start of the block (i.e. the header). * - 0x4 - - \_\_le32 - - e\_value\_inum + - __le32 + - e_value_inum - The inode where the value is stored. Zero indicates the value is in the same block as this entry. This field is only used if the - INCOMPAT\_EA\_INODE feature is enabled. + INCOMPAT_EA_INODE feature is enabled. * - 0x8 - - \_\_le32 - - e\_value\_size + - __le32 + - e_value_size - Length of attribute value. * - 0xC - - \_\_le32 - - e\_hash + - __le32 + - e_hash - Hash value of attribute name and attribute value. The kernel doesn't update the hash for in-inode attributes, so for that case this value must be zero, because e2fsck validates any non-zero hash regardless of where the xattr lives. * - 0x10 - char - - e\_name[e\_name\_len] + - e_name[e_name_len] - Attribute name. Does not include trailing NULL. Attribute values can follow the end of the entry table. There appears to be a requirement that they be aligned to 4-byte boundaries. The values are stored starting at the end of the block and grow towards the -xattr\_header/xattr\_entry table. When the two collide, the overflow is +xattr_header/xattr_entry table. When the two collide, the overflow is put into a separate disk block. If the disk block fills up, the filesystem returns -ENOSPC. @@ -167,15 +167,15 @@ the key name. Here is a map of name index values to key prefixes: * - 1 - “user.” * - 2 - - “system.posix\_acl\_access” + - “system.posix_acl_access” * - 3 - - “system.posix\_acl\_default” + - “system.posix_acl_default” * - 4 - “trusted.” * - 6 - “security.” * - 7 - - “system.” (inline\_data only?) + - “system.” (inline_data only?) * - 8 - “system.richacl” (SuSE kernels only?) diff --git a/Documentation/filesystems/ext4/bigalloc.rst b/Documentation/filesystems/ext4/bigalloc.rst index 72075aa608e4d..976a180b209c2 100644 --- a/Documentation/filesystems/ext4/bigalloc.rst +++ b/Documentation/filesystems/ext4/bigalloc.rst @@ -23,7 +23,7 @@ means that a block group addresses 32 gigabytes instead of 128 megabytes, also shrinking the amount of file system overhead for metadata. The administrator can set a block cluster size at mkfs time (which is -stored in the s\_log\_cluster\_size field in the superblock); from then +stored in the s_log_cluster_size field in the superblock); from then on, the block bitmaps track clusters, not individual blocks. This means that block groups can be several gigabytes in size (instead of just 128MiB); however, the minimum allocation unit becomes a cluster, not a diff --git a/Documentation/filesystems/ext4/bitmaps.rst b/Documentation/filesystems/ext4/bitmaps.rst index c7546dbc197ae..91c45d86e9bb5 100644 --- a/Documentation/filesystems/ext4/bitmaps.rst +++ b/Documentation/filesystems/ext4/bitmaps.rst @@ -9,15 +9,15 @@ group. The inode bitmap records which entries in the inode table are in use. As with most bitmaps, one bit represents the usage status of one data -block or inode table entry. This implies a block group size of 8 \* -number\_of\_bytes\_in\_a\_logical\_block. +block or inode table entry. This implies a block group size of 8 * +number_of_bytes_in_a_logical_block. NOTE: If ``BLOCK_UNINIT`` is set for a given block group, various parts of the kernel and e2fsprogs code pretends that the block bitmap contains zeros (i.e. all blocks in the group are free). However, it is not necessarily the case that no blocks are in use -- if ``meta_bg`` is set, the bitmaps and group descriptor live inside the group. Unfortunately, -ext2fs\_test\_block\_bitmap2() will return '0' for those locations, +ext2fs_test_block_bitmap2() will return '0' for those locations, which produces confusing debugfs output. Inode Table diff --git a/Documentation/filesystems/ext4/blockgroup.rst b/Documentation/filesystems/ext4/blockgroup.rst index d5d652addce5e..46d78f860623f 100644 --- a/Documentation/filesystems/ext4/blockgroup.rst +++ b/Documentation/filesystems/ext4/blockgroup.rst @@ -56,39 +56,39 @@ established that the super block and the group descriptor table, if present, will be at the beginning of the block group. The bitmaps and the inode table can be anywhere, and it is quite possible for the bitmaps to come after the inode table, or for both to be in different -groups (flex\_bg). Leftover space is used for file data blocks, indirect +groups (flex_bg). Leftover space is used for file data blocks, indirect block maps, extent tree blocks, and extended attributes. Flexible Block Groups --------------------- Starting in ext4, there is a new feature called flexible block groups -(flex\_bg). In a flex\_bg, several block groups are tied together as one +(flex_bg). In a flex_bg, several block groups are tied together as one logical block group; the bitmap spaces and the inode table space in the -first block group of the flex\_bg are expanded to include the bitmaps -and inode tables of all other block groups in the flex\_bg. For example, -if the flex\_bg size is 4, then group 0 will contain (in order) the +first block group of the flex_bg are expanded to include the bitmaps +and inode tables of all other block groups in the flex_bg. For example, +if the flex_bg size is 4, then group 0 will contain (in order) the superblock, group descriptors, data block bitmaps for groups 0-3, inode bitmaps for groups 0-3, inode tables for groups 0-3, and the remaining space in group 0 is for file data. The effect of this is to group the block group metadata close together for faster loading, and to enable large files to be continuous on disk. Backup copies of the superblock and group descriptors are always at the beginning of block groups, even -if flex\_bg is enabled. The number of block groups that make up a -flex\_bg is given by 2 ^ ``sb.s_log_groups_per_flex``. +if flex_bg is enabled. The number of block groups that make up a +flex_bg is given by 2 ^ ``sb.s_log_groups_per_flex``. Meta Block Groups ----------------- -Without the option META\_BG, for safety concerns, all block group +Without the option META_BG, for safety concerns, all block group descriptors copies are kept in the first block group. Given the default 128MiB(2^27 bytes) block group size and 64-byte group descriptors, ext4 can have at most 2^27/64 = 2^21 block groups. This limits the entire filesystem size to 2^21 * 2^27 = 2^48bytes or 256TiB. The solution to this problem is to use the metablock group feature -(META\_BG), which is already in ext3 for all 2.6 releases. With the -META\_BG feature, ext4 filesystems are partitioned into many metablock +(META_BG), which is already in ext3 for all 2.6 releases. With the +META_BG feature, ext4 filesystems are partitioned into many metablock groups. Each metablock group is a cluster of block groups whose group descriptor structures can be stored in a single disk block. For ext4 filesystems with 4 KB block size, a single metablock group partition @@ -110,7 +110,7 @@ bytes, a meta-block group contains 32 block groups for filesystems with a 1KB block size, and 128 block groups for filesystems with a 4KB blocksize. Filesystems can either be created using this new block group descriptor layout, or existing filesystems can be resized on-line, and -the field s\_first\_meta\_bg in the superblock will indicate the first +the field s_first_meta_bg in the superblock will indicate the first block group using this new layout. Please see an important note about ``BLOCK_UNINIT`` in the section about @@ -121,15 +121,15 @@ Lazy Block Group Initialization A new feature for ext4 are three block group descriptor flags that enable mkfs to skip initializing other parts of the block group -metadata. Specifically, the INODE\_UNINIT and BLOCK\_UNINIT flags mean +metadata. Specifically, the INODE_UNINIT and BLOCK_UNINIT flags mean that the inode and block bitmaps for that group can be calculated and therefore the on-disk bitmap blocks are not initialized. This is generally the case for an empty block group or a block group containing -only fixed-location block group metadata. The INODE\_ZEROED flag means +only fixed-location block group metadata. The INODE_ZEROED flag means that the inode table has been initialized; mkfs will unset this flag and rely on the kernel to initialize the inode tables in the background. By not writing zeroes to the bitmaps and inode table, mkfs time is -reduced considerably. Note the feature flag is RO\_COMPAT\_GDT\_CSUM, -but the dumpe2fs output prints this as “uninit\_bg”. They are the same +reduced considerably. Note the feature flag is RO_COMPAT_GDT_CSUM, +but the dumpe2fs output prints this as “uninit_bg”. They are the same thing. diff --git a/Documentation/filesystems/ext4/blockmap.rst b/Documentation/filesystems/ext4/blockmap.rst index 30e25750d88a4..2bd990402a5c4 100644 --- a/Documentation/filesystems/ext4/blockmap.rst +++ b/Documentation/filesystems/ext4/blockmap.rst @@ -1,7 +1,7 @@ .. SPDX-License-Identifier: GPL-2.0 +---------------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+ -| i.i\_block Offset | Where It Points | +| i.i_block Offset | Where It Points | +=====================+==============================================================================================================================================================================================================================+ | 0 to 11 | Direct map to file blocks 0 to 11. | +---------------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+ diff --git a/Documentation/filesystems/ext4/checksums.rst b/Documentation/filesystems/ext4/checksums.rst index 5519e253810d6..e232749daf5f3 100644 --- a/Documentation/filesystems/ext4/checksums.rst +++ b/Documentation/filesystems/ext4/checksums.rst @@ -4,7 +4,7 @@ Checksums --------- Starting in early 2012, metadata checksums were added to all major ext4 -and jbd2 data structures. The associated feature flag is metadata\_csum. +and jbd2 data structures. The associated feature flag is metadata_csum. The desired checksum algorithm is indicated in the superblock, though as of October 2012 the only supported algorithm is crc32c. Some data structures did not have space to fit a full 32-bit checksum, so only the @@ -20,7 +20,7 @@ encounters directory blocks that lack sufficient empty space to add a checksum, it will request that you run ``e2fsck -D`` to have the directories rebuilt with checksums. This has the added benefit of removing slack space from the directory files and rebalancing the htree -indexes. If you \_ignore\_ this step, your directories will not be +indexes. If you _ignore_ this step, your directories will not be protected by a checksum! The following table describes the data elements that go into each type @@ -35,39 +35,39 @@ of checksum. The checksum function is whatever the superblock describes - Length - Ingredients * - Superblock - - \_\_le32 + - __le32 - The entire superblock up to the checksum field. The UUID lives inside the superblock. * - MMP - - \_\_le32 + - __le32 - UUID + the entire MMP block up to the checksum field. * - Extended Attributes - - \_\_le32 + - __le32 - UUID + the entire extended attribute block. The checksum field is set to zero. * - Directory Entries - - \_\_le32 + - __le32 - UUID + inode number + inode generation + the directory block up to the fake entry enclosing the checksum field. * - HTREE Nodes - - \_\_le32 + - __le32 - UUID + inode number + inode generation + all valid extents + HTREE tail. The checksum field is set to zero. * - Extents - - \_\_le32 + - __le32 - UUID + inode number + inode generation + the entire extent block up to the checksum field. * - Bitmaps - - \_\_le32 or \_\_le16 + - __le32 or __le16 - UUID + the entire bitmap. Checksums are stored in the group descriptor, and truncated if the group descriptor size is 32 bytes (i.e. ^64bit) * - Inodes - - \_\_le32 + - __le32 - UUID + inode number + inode generation + the entire inode. The checksum field is set to zero. Each inode has its own checksum. * - Group Descriptors - - \_\_le16 - - If metadata\_csum, then UUID + group number + the entire descriptor; - else if gdt\_csum, then crc16(UUID + group number + the entire + - __le16 + - If metadata_csum, then UUID + group number + the entire descriptor; + else if gdt_csum, then crc16(UUID + group number + the entire descriptor). In all cases, only the lower 16 bits are stored. diff --git a/Documentation/filesystems/ext4/directory.rst b/Documentation/filesystems/ext4/directory.rst index 55f618b371445..6eece8e31df8b 100644 --- a/Documentation/filesystems/ext4/directory.rst +++ b/Documentation/filesystems/ext4/directory.rst @@ -42,24 +42,24 @@ is at most 263 bytes long, though on disk you'll need to reference - Name - Description * - 0x0 - - \_\_le32 + - __le32 - inode - Number of the inode that this directory entry points to. * - 0x4 - - \_\_le16 - - rec\_len + - __le16 + - rec_len - Length of this directory entry. Must be a multiple of 4. * - 0x6 - - \_\_le16 - - name\_len + - __le16 + - name_len - Length of the file name. * - 0x8 - char - - name[EXT4\_NAME\_LEN] + - name[EXT4_NAME_LEN] - File name. Since file names cannot be longer than 255 bytes, the new directory -entry format shortens the name\_len field and uses the space for a file +entry format shortens the name_len field and uses the space for a file type flag, probably to avoid having to load every inode during directory tree traversal. This format is ``ext4_dir_entry_2``, which is at most 263 bytes long, though on disk you'll need to reference @@ -74,24 +74,24 @@ tree traversal. This format is ``ext4_dir_entry_2``, which is at most - Name - Description * - 0x0 - - \_\_le32 + - __le32 - inode - Number of the inode that this directory entry points to. * - 0x4 - - \_\_le16 - - rec\_len + - __le16 + - rec_len - Length of this directory entry. * - 0x6 - - \_\_u8 - - name\_len + - __u8 + - name_len - Length of the file name. * - 0x7 - - \_\_u8 - - file\_type + - __u8 + - file_type - File type code, see ftype_ table below. * - 0x8 - char - - name[EXT4\_NAME\_LEN] + - name[EXT4_NAME_LEN] - File name. .. _ftype: @@ -137,19 +137,19 @@ entry uses this extension, it may be up to 271 bytes. - Name - Description * - 0x0 - - \_\_le32 + - __le32 - hash - The hash of the directory name * - 0x4 - - \_\_le32 - - minor\_hash + - __le32 + - minor_hash - The minor hash of the directory name In order to add checksums to these classic directory blocks, a phony ``struct ext4_dir_entry`` is placed at the end of each leaf block to hold the checksum. The directory entry is 12 bytes long. The inode -number and name\_len fields are set to zero to fool old software into +number and name_len fields are set to zero to fool old software into ignoring an apparently empty directory entry, and the checksum is stored in the place where the name normally goes. The structure is ``struct ext4_dir_entry_tail``: @@ -163,24 +163,24 @@ in the place where the name normally goes. The structure is - Name - Description * - 0x0 - - \_\_le32 - - det\_reserved\_zero1 + - __le32 + - det_reserved_zero1 - Inode number, which must be zero. * - 0x4 - - \_\_le16 - - det\_rec\_len + - __le16 + - det_rec_len - Length of this directory entry, which must be 12. * - 0x6 - - \_\_u8 - - det\_reserved\_zero2 + - __u8 + - det_reserved_zero2 - Length of the file name, which must be zero. * - 0x7 - - \_\_u8 - - det\_reserved\_ft + - __u8 + - det_reserved_ft - File type, which must be 0xDE. * - 0x8 - - \_\_le32 - - det\_checksum + - __le32 + - det_checksum - Directory leaf block checksum. The leaf directory block checksum is calculated against the FS UUID, the @@ -194,7 +194,7 @@ Hash Tree Directories A linear array of directory entries isn't great for performance, so a new feature was added to ext3 to provide a faster (but peculiar) balanced tree keyed off a hash of the directory entry name. If the -EXT4\_INDEX\_FL (0x1000) flag is set in the inode, this directory uses a +EXT4_INDEX_FL (0x1000) flag is set in the inode, this directory uses a hashed btree (htree) to organize and find directory entries. For backwards read-only compatibility with ext2, this tree is actually hidden inside the directory file, masquerading as “empty” directory data @@ -206,14 +206,14 @@ rest of the directory block is empty so that it moves on. The root of the tree always lives in the first data block of the directory. By ext2 custom, the '.' and '..' entries must appear at the beginning of this first block, so they are put here as two -``struct ext4_dir_entry_2``\ s and not stored in the tree. The rest of +``struct ext4_dir_entry_2`` s and not stored in the tree. The rest of the root node contains metadata about the tree and finally a hash->block map to find nodes that are lower in the htree. If ``dx_root.info.indirect_levels`` is non-zero then the htree has two levels; the data block pointed to by the root node's map is an interior node, which is indexed by a minor hash. Interior nodes in this tree contains a zeroed out ``struct ext4_dir_entry_2`` followed by a -minor\_hash->block map to find leafe nodes. Leaf nodes contain a linear +minor_hash->block map to find leafe nodes. Leaf nodes contain a linear array of all ``struct ext4_dir_entry_2``; all of these entries (presumably) hash to the same value. If there is an overflow, the entries simply overflow into the next leaf node, and the @@ -245,83 +245,83 @@ of a data block: - Name - Description * - 0x0 - - \_\_le32 + - __le32 - dot.inode - inode number of this directory. * - 0x4 - - \_\_le16 - - dot.rec\_len + - __le16 + - dot.rec_len - Length of this record, 12. * - 0x6 - u8 - - dot.name\_len + - dot.name_len - Length of the name, 1. * - 0x7 - u8 - - dot.file\_type + - dot.file_type - File type of this entry, 0x2 (directory) (if the feature flag is set). * - 0x8 - char - dot.name[4] - - “.\\0\\0\\0” + - “.\0\0\0” * - 0xC - - \_\_le32 + - __le32 - dotdot.inode - inode number of parent directory. * - 0x10 - - \_\_le16 - - dotdot.rec\_len - - block\_size - 12. The record length is long enough to cover all htree + - __le16 + - dotdot.rec_len + - block_size - 12. The record length is long enough to cover all htree data. * - 0x12 - u8 - - dotdot.name\_len + - dotdot.name_len - Length of the name, 2. * - 0x13 - u8 - - dotdot.file\_type + - dotdot.file_type - File type of this entry, 0x2 (directory) (if the feature flag is set). * - 0x14 - char - - dotdot\_name[4] - - “..\\0\\0” + - dotdot_name[4] + - “..\0\0” * - 0x18 - - \_\_le32 - - struct dx\_root\_info.reserved\_zero + - __le32 + - struct dx_root_info.reserved_zero - Zero. * - 0x1C - u8 - - struct dx\_root\_info.hash\_version + - struct dx_root_info.hash_version - Hash type, see dirhash_ table below. * - 0x1D - u8 - - struct dx\_root\_info.info\_length + - struct dx_root_info.info_length - Length of the tree information, 0x8. * - 0x1E - u8 - - struct dx\_root\_info.indirect\_levels - - Depth of the htree. Cannot be larger than 3 if the INCOMPAT\_LARGEDIR + - struct dx_root_info.indirect_levels + - Depth of the htree. Cannot be larger than 3 if the INCOMPAT_LARGEDIR feature is set; cannot be larger than 2 otherwise. * - 0x1F - u8 - - struct dx\_root\_info.unused\_flags + - struct dx_root_info.unused_flags - * - 0x20 - - \_\_le16 + - __le16 - limit - - Maximum number of dx\_entries that can follow this header, plus 1 for + - Maximum number of dx_entries that can follow this header, plus 1 for the header itself. * - 0x22 - - \_\_le16 + - __le16 - count - - Actual number of dx\_entries that follow this header, plus 1 for the + - Actual number of dx_entries that follow this header, plus 1 for the header itself. * - 0x24 - - \_\_le32 + - __le32 - block - The block number (within the directory file) that goes with hash=0. * - 0x28 - - struct dx\_entry + - struct dx_entry - entries[0] - As many 8-byte ``struct dx_entry`` as fits in the rest of the data block. @@ -362,38 +362,38 @@ also the full length of a data block: - Name - Description * - 0x0 - - \_\_le32 + - __le32 - fake.inode - Zero, to make it look like this entry is not in use. * - 0x4 - - \_\_le16 - - fake.rec\_len - - The size of the block, in order to hide all of the dx\_node data. + - __le16 + - fake.rec_len + - The size of the block, in order to hide all of the dx_node data. * - 0x6 - u8 - - name\_len + - name_len - Zero. There is no name for this “unused” directory entry. * - 0x7 - u8 - - file\_type + - file_type - Zero. There is no file type for this “unused” directory entry. * - 0x8 - - \_\_le16 + - __le16 - limit - - Maximum number of dx\_entries that can follow this header, plus 1 for + - Maximum number of dx_entries that can follow this header, plus 1 for the header itself. * - 0xA - - \_\_le16 + - __le16 - count - - Actual number of dx\_entries that follow this header, plus 1 for the + - Actual number of dx_entries that follow this header, plus 1 for the header itself. * - 0xE - - \_\_le32 + - __le32 - block - The block number (within the directory file) that goes with the lowest hash value of this block. This value is stored in the parent block. * - 0x12 - - struct dx\_entry + - struct dx_entry - entries[0] - As many 8-byte ``struct dx_entry`` as fits in the rest of the data block. @@ -410,11 +410,11 @@ long: - Name - Description * - 0x0 - - \_\_le32 + - __le32 - hash - Hash code. * - 0x4 - - \_\_le32 + - __le32 - block - Block number (within the directory file, not filesystem blocks) of the next node in the htree. @@ -423,13 +423,13 @@ long: author.) If metadata checksums are enabled, the last 8 bytes of the directory -block (precisely the length of one dx\_entry) are used to store a +block (precisely the length of one dx_entry) are used to store a ``struct dx_tail``, which contains the checksum. The ``limit`` and -``count`` entries in the dx\_root/dx\_node structures are adjusted as -necessary to fit the dx\_tail into the block. If there is no space for -the dx\_tail, the user is notified to run e2fsck -D to rebuild the +``count`` entries in the dx_root/dx_node structures are adjusted as +necessary to fit the dx_tail into the block. If there is no space for +the dx_tail, the user is notified to run e2fsck -D to rebuild the directory index (which will ensure that there's space for the checksum. -The dx\_tail structure is 8 bytes long and looks like this: +The dx_tail structure is 8 bytes long and looks like this: .. list-table:: :widths: 8 8 24 40 @@ -441,13 +441,13 @@ The dx\_tail structure is 8 bytes long and looks like this: - Description * - 0x0 - u32 - - dt\_reserved + - dt_reserved - Zero. * - 0x4 - - \_\_le32 - - dt\_checksum + - __le32 + - dt_checksum - Checksum of the htree directory block. The checksum is calculated against the FS UUID, the htree index header -(dx\_root or dx\_node), all of the htree indices (dx\_entry) that are in -use, and the tail block (dx\_tail). +(dx_root or dx_node), all of the htree indices (dx_entry) that are in +use, and the tail block (dx_tail). diff --git a/Documentation/filesystems/ext4/eainode.rst b/Documentation/filesystems/ext4/eainode.rst index ecc0d01a0a72c..7a2ef26b064ac 100644 --- a/Documentation/filesystems/ext4/eainode.rst +++ b/Documentation/filesystems/ext4/eainode.rst @@ -5,14 +5,14 @@ Large Extended Attribute Values To enable ext4 to store extended attribute values that do not fit in the inode or in the single extended attribute block attached to an inode, -the EA\_INODE feature allows us to store the value in the data blocks of +the EA_INODE feature allows us to store the value in the data blocks of a regular file inode. This “EA inode” is linked only from the extended attribute name index and must not appear in a directory entry. The -inode's i\_atime field is used to store a checksum of the xattr value; -and i\_ctime/i\_version store a 64-bit reference count, which enables +inode's i_atime field is used to store a checksum of the xattr value; +and i_ctime/i_version store a 64-bit reference count, which enables sharing of large xattr values between multiple owning inodes. For backward compatibility with older versions of this feature, the -i\_mtime/i\_generation *may* store a back-reference to the inode number -and i\_generation of the **one** owning inode (in cases where the EA +i_mtime/i_generation *may* store a back-reference to the inode number +and i_generation of the **one** owning inode (in cases where the EA inode is not referenced by multiple inodes) to verify that the EA inode is the correct one being accessed. diff --git a/Documentation/filesystems/ext4/group_descr.rst b/Documentation/filesystems/ext4/group_descr.rst index 7ba6114e7f5c2..392ec44f8fb00 100644 --- a/Documentation/filesystems/ext4/group_descr.rst +++ b/Documentation/filesystems/ext4/group_descr.rst @@ -7,34 +7,34 @@ Each block group on the filesystem has one of these descriptors associated with it. As noted in the Layout section above, the group descriptors (if present) are the second item in the block group. The standard configuration is for each block group to contain a full copy of -the block group descriptor table unless the sparse\_super feature flag +the block group descriptor table unless the sparse_super feature flag is set. Notice how the group descriptor records the location of both bitmaps and the inode table (i.e. they can float). This means that within a block group, the only data structures with fixed locations are the superblock -and the group descriptor table. The flex\_bg mechanism uses this +and the group descriptor table. The flex_bg mechanism uses this property to group several block groups into a flex group and lay out all of the groups' bitmaps and inode tables into one long run in the first group of the flex group. -If the meta\_bg feature flag is set, then several block groups are -grouped together into a meta group. Note that in the meta\_bg case, +If the meta_bg feature flag is set, then several block groups are +grouped together into a meta group. Note that in the meta_bg case, however, the first and last two block groups within the larger meta group contain only group descriptors for the groups inside the meta group. -flex\_bg and meta\_bg do not appear to be mutually exclusive features. +flex_bg and meta_bg do not appear to be mutually exclusive features. In ext2, ext3, and ext4 (when the 64bit feature is not enabled), the block group descriptor was only 32 bytes long and therefore ends at -bg\_checksum. On an ext4 filesystem with the 64bit feature enabled, the +bg_checksum. On an ext4 filesystem with the 64bit feature enabled, the block group descriptor expands to at least the 64 bytes described below; the size is stored in the superblock. -If gdt\_csum is set and metadata\_csum is not set, the block group +If gdt_csum is set and metadata_csum is not set, the block group checksum is the crc16 of the FS UUID, the group number, and the group -descriptor structure. If metadata\_csum is set, then the block group +descriptor structure. If metadata_csum is set, then the block group checksum is the lower 16 bits of the checksum of the FS UUID, the group number, and the group descriptor structure. Both block and inode bitmap checksums are calculated against the FS UUID, the group number, and the @@ -51,59 +51,59 @@ The block group descriptor is laid out in ``struct ext4_group_desc``. - Name - Description * - 0x0 - - \_\_le32 - - bg\_block\_bitmap\_lo + - __le32 + - bg_block_bitmap_lo - Lower 32-bits of location of block bitmap. * - 0x4 - - \_\_le32 - - bg\_inode\_bitmap\_lo + - __le32 + - bg_inode_bitmap_lo - Lower 32-bits of location of inode bitmap. * - 0x8 - - \_\_le32 - - bg\_inode\_table\_lo + - __le32 + - bg_inode_table_lo - Lower 32-bits of location of inode table. * - 0xC - - \_\_le16 - - bg\_free\_blocks\_count\_lo + - __le16 + - bg_free_blocks_count_lo - Lower 16-bits of free block count. * - 0xE - - \_\_le16 - - bg\_free\_inodes\_count\_lo + - __le16 + - bg_free_inodes_count_lo - Lower 16-bits of free inode count. * - 0x10 - - \_\_le16 - - bg\_used\_dirs\_count\_lo + - __le16 + - bg_used_dirs_count_lo - Lower 16-bits of directory count. * - 0x12 - - \_\_le16 - - bg\_flags + - __le16 + - bg_flags - Block group flags. See the bgflags_ table below. * - 0x14 - - \_\_le32 - - bg\_exclude\_bitmap\_lo + - __le32 + - bg_exclude_bitmap_lo - Lower 32-bits of location of snapshot exclusion bitmap. * - 0x18 - - \_\_le16 - - bg\_block\_bitmap\_csum\_lo + - __le16 + - bg_block_bitmap_csum_lo - Lower 16-bits of the block bitmap checksum. * - 0x1A - - \_\_le16 - - bg\_inode\_bitmap\_csum\_lo + - __le16 + - bg_inode_bitmap_csum_lo - Lower 16-bits of the inode bitmap checksum. * - 0x1C - - \_\_le16 - - bg\_itable\_unused\_lo + - __le16 + - bg_itable_unused_lo - Lower 16-bits of unused inode count. If set, we needn't scan past the - ``(sb.s_inodes_per_group - gdt.bg_itable_unused)``\ th entry in the + ``(sb.s_inodes_per_group - gdt.bg_itable_unused)`` th entry in the inode table for this group. * - 0x1E - - \_\_le16 - - bg\_checksum - - Group descriptor checksum; crc16(sb\_uuid+group\_num+bg\_desc) if the - RO\_COMPAT\_GDT\_CSUM feature is set, or - crc32c(sb\_uuid+group\_num+bg\_desc) & 0xFFFF if the - RO\_COMPAT\_METADATA\_CSUM feature is set. The bg\_checksum - field in bg\_desc is skipped when calculating crc16 checksum, + - __le16 + - bg_checksum + - Group descriptor checksum; crc16(sb_uuid+group_num+bg_desc) if the + RO_COMPAT_GDT_CSUM feature is set, or + crc32c(sb_uuid+group_num+bg_desc) & 0xFFFF if the + RO_COMPAT_METADATA_CSUM feature is set. The bg_checksum + field in bg_desc is skipped when calculating crc16 checksum, and set to zero if crc32c checksum is used. * - - @@ -111,48 +111,48 @@ The block group descriptor is laid out in ``struct ext4_group_desc``. - These fields only exist if the 64bit feature is enabled and s_desc_size > 32. * - 0x20 - - \_\_le32 - - bg\_block\_bitmap\_hi + - __le32 + - bg_block_bitmap_hi - Upper 32-bits of location of block bitmap. * - 0x24 - - \_\_le32 - - bg\_inode\_bitmap\_hi + - __le32 + - bg_inode_bitmap_hi - Upper 32-bits of location of inodes bitmap. * - 0x28 - - \_\_le32 - - bg\_inode\_table\_hi + - __le32 + - bg_inode_table_hi - Upper 32-bits of location of inodes table. * - 0x2C - - \_\_le16 - - bg\_free\_blocks\_count\_hi + - __le16 + - bg_free_blocks_count_hi - Upper 16-bits of free block count. * - 0x2E - - \_\_le16 - - bg\_free\_inodes\_count\_hi + - __le16 + - bg_free_inodes_count_hi - Upper 16-bits of free inode count. * - 0x30 - - \_\_le16 - - bg\_used\_dirs\_count\_hi + - __le16 + - bg_used_dirs_count_hi - Upper 16-bits of directory count. * - 0x32 - - \_\_le16 - - bg\_itable\_unused\_hi + - __le16 + - bg_itable_unused_hi - Upper 16-bits of unused inode count. * - 0x34 - - \_\_le32 - - bg\_exclude\_bitmap\_hi + - __le32 + - bg_exclude_bitmap_hi - Upper 32-bits of location of snapshot exclusion bitmap. * - 0x38 - - \_\_le16 - - bg\_block\_bitmap\_csum\_hi + - __le16 + - bg_block_bitmap_csum_hi - Upper 16-bits of the block bitmap checksum. * - 0x3A - - \_\_le16 - - bg\_inode\_bitmap\_csum\_hi + - __le16 + - bg_inode_bitmap_csum_hi - Upper 16-bits of the inode bitmap checksum. * - 0x3C - - \_\_u32 - - bg\_reserved + - __u32 + - bg_reserved - Padding to 64 bytes. .. _bgflags: @@ -166,8 +166,8 @@ Block group flags can be any combination of the following: * - Value - Description * - 0x1 - - inode table and bitmap are not initialized (EXT4\_BG\_INODE\_UNINIT). + - inode table and bitmap are not initialized (EXT4_BG_INODE_UNINIT). * - 0x2 - - block bitmap is not initialized (EXT4\_BG\_BLOCK\_UNINIT). + - block bitmap is not initialized (EXT4_BG_BLOCK_UNINIT). * - 0x4 - - inode table is zeroed (EXT4\_BG\_INODE\_ZEROED). + - inode table is zeroed (EXT4_BG_INODE_ZEROED). diff --git a/Documentation/filesystems/ext4/ifork.rst b/Documentation/filesystems/ext4/ifork.rst index b9816d5a896b7..dc31f505e6c83 100644 --- a/Documentation/filesystems/ext4/ifork.rst +++ b/Documentation/filesystems/ext4/ifork.rst @@ -1,6 +1,6 @@ .. SPDX-License-Identifier: GPL-2.0 -The Contents of inode.i\_block +The Contents of inode.i_block ------------------------------ Depending on the type of file an inode describes, the 60 bytes of @@ -47,7 +47,7 @@ In ext4, the file to logical block map has been replaced with an extent tree. Under the old scheme, allocating a contiguous run of 1,000 blocks requires an indirect block to map all 1,000 entries; with extents, the mapping is reduced to a single ``struct ext4_extent`` with -``ee_len = 1000``. If flex\_bg is enabled, it is possible to allocate +``ee_len = 1000``. If flex_bg is enabled, it is possible to allocate very large files with a single extent, at a considerable reduction in metadata block use, and some improvement in disk efficiency. The inode must have the extents flag (0x80000) flag set for this feature to be in @@ -76,28 +76,28 @@ which is 12 bytes long: - Name - Description * - 0x0 - - \_\_le16 - - eh\_magic + - __le16 + - eh_magic - Magic number, 0xF30A. * - 0x2 - - \_\_le16 - - eh\_entries + - __le16 + - eh_entries - Number of valid entries following the header. * - 0x4 - - \_\_le16 - - eh\_max + - __le16 + - eh_max - Maximum number of entries that could follow the header. * - 0x6 - - \_\_le16 - - eh\_depth + - __le16 + - eh_depth - Depth of this extent node in the extent tree. 0 = this extent node points to data blocks; otherwise, this extent node points to other extent nodes. The extent tree can be at most 5 levels deep: a logical block number can be at most ``2^32``, and the smallest ``n`` that satisfies ``4*(((blocksize - 12)/12)^n) >= 2^32`` is 5. * - 0x8 - - \_\_le32 - - eh\_generation + - __le32 + - eh_generation - Generation of the tree. (Used by Lustre, but not standard ext4). Internal nodes of the extent tree, also known as index nodes, are @@ -112,22 +112,22 @@ recorded as ``struct ext4_extent_idx``, and are 12 bytes long: - Name - Description * - 0x0 - - \_\_le32 - - ei\_block + - __le32 + - ei_block - This index node covers file blocks from 'block' onward. * - 0x4 - - \_\_le32 - - ei\_leaf\_lo + - __le32 + - ei_leaf_lo - Lower 32-bits of the block number of the extent node that is the next level lower in the tree. The tree node pointed to can be either another internal node or a leaf node, described below. * - 0x8 - - \_\_le16 - - ei\_leaf\_hi + - __le16 + - ei_leaf_hi - Upper 16-bits of the previous field. * - 0xA - - \_\_u16 - - ei\_unused + - __u16 + - ei_unused - Leaf nodes of the extent tree are recorded as ``struct ext4_extent``, @@ -142,24 +142,24 @@ and are also 12 bytes long: - Name - Description * - 0x0 - - \_\_le32 - - ee\_block + - __le32 + - ee_block - First file block number that this extent covers. * - 0x4 - - \_\_le16 - - ee\_len + - __le16 + - ee_len - Number of blocks covered by extent. If the value of this field is <= 32768, the extent is initialized. If the value of the field is > 32768, the extent is uninitialized and the actual extent length is ``ee_len`` - 32768. Therefore, the maximum length of a initialized extent is 32768 blocks, and the maximum length of an uninitialized extent is 32767. * - 0x6 - - \_\_le16 - - ee\_start\_hi + - __le16 + - ee_start_hi - Upper 16-bits of the block number to which this extent points. * - 0x8 - - \_\_le32 - - ee\_start\_lo + - __le32 + - ee_start_lo - Lower 32-bits of the block number to which this extent points. Prior to the introduction of metadata checksums, the extent header + @@ -182,8 +182,8 @@ including) the checksum itself. - Name - Description * - 0x0 - - \_\_le32 - - eb\_checksum + - __le32 + - eb_checksum - Checksum of the extent block, crc32c(uuid+inum+igeneration+extentblock) Inline Data diff --git a/Documentation/filesystems/ext4/inlinedata.rst b/Documentation/filesystems/ext4/inlinedata.rst index d1075178ce0b2..a728af0d2fd0c 100644 --- a/Documentation/filesystems/ext4/inlinedata.rst +++ b/Documentation/filesystems/ext4/inlinedata.rst @@ -11,12 +11,12 @@ file is smaller than 60 bytes, then the data are stored inline in attribute space, then it might be found as an extended attribute “system.data” within the inode body (“ibody EA”). This of course constrains the amount of extended attributes one can attach to an inode. -If the data size increases beyond i\_block + ibody EA, a regular block +If the data size increases beyond i_block + ibody EA, a regular block is allocated and the contents moved to that block. Pending a change to compact the extended attribute key used to store inline data, one ought to be able to store 160 bytes of data in a -256-byte inode (as of June 2015, when i\_extra\_isize is 28). Prior to +256-byte inode (as of June 2015, when i_extra_isize is 28). Prior to that, the limit was 156 bytes due to inefficient use of inode space. The inline data feature requires the presence of an extended attribute @@ -25,12 +25,12 @@ for “system.data”, even if the attribute value is zero length. Inline Directories ~~~~~~~~~~~~~~~~~~ -The first four bytes of i\_block are the inode number of the parent +The first four bytes of i_block are the inode number of the parent directory. Following that is a 56-byte space for an array of directory entries; see ``struct ext4_dir_entry``. If there is a “system.data” attribute in the inode body, the EA value is an array of ``struct ext4_dir_entry`` as well. Note that for inline directories, the -i\_block and EA space are treated as separate dirent blocks; directory +i_block and EA space are treated as separate dirent blocks; directory entries cannot span the two. Inline directory entries are not checksummed, as the inode checksum diff --git a/Documentation/filesystems/ext4/inodes.rst b/Documentation/filesystems/ext4/inodes.rst index 6c5ce666e63f3..cfc6c16599312 100644 --- a/Documentation/filesystems/ext4/inodes.rst +++ b/Documentation/filesystems/ext4/inodes.rst @@ -38,138 +38,138 @@ The inode table entry is laid out in ``struct ext4_inode``. - Name - Description * - 0x0 - - \_\_le16 - - i\_mode + - __le16 + - i_mode - File mode. See the table i_mode_ below. * - 0x2 - - \_\_le16 - - i\_uid + - __le16 + - i_uid - Lower 16-bits of Owner UID. * - 0x4 - - \_\_le32 - - i\_size\_lo + - __le32 + - i_size_lo - Lower 32-bits of size in bytes. * - 0x8 - - \_\_le32 - - i\_atime - - Last access time, in seconds since the epoch. However, if the EA\_INODE + - __le32 + - i_atime + - Last access time, in seconds since the epoch. However, if the EA_INODE inode flag is set, this inode stores an extended attribute value and this field contains the checksum of the value. * - 0xC - - \_\_le32 - - i\_ctime + - __le32 + - i_ctime - Last inode change time, in seconds since the epoch. However, if the - EA\_INODE inode flag is set, this inode stores an extended attribute + EA_INODE inode flag is set, this inode stores an extended attribute value and this field contains the lower 32 bits of the attribute value's reference count. * - 0x10 - - \_\_le32 - - i\_mtime + - __le32 + - i_mtime - Last data modification time, in seconds since the epoch. However, if the - EA\_INODE inode flag is set, this inode stores an extended attribute + EA_INODE inode flag is set, this inode stores an extended attribute value and this field contains the number of the inode that owns the extended attribute. * - 0x14 - - \_\_le32 - - i\_dtime + - __le32 + - i_dtime - Deletion Time, in seconds since the epoch. * - 0x18 - - \_\_le16 - - i\_gid + - __le16 + - i_gid - Lower 16-bits of GID. * - 0x1A - - \_\_le16 - - i\_links\_count + - __le16 + - i_links_count - Hard link count. Normally, ext4 does not permit an inode to have more than 65,000 hard links. This applies to files as well as directories, which means that there cannot be more than 64,998 subdirectories in a directory (each subdirectory's '..' entry counts as a hard link, as does - the '.' entry in the directory itself). With the DIR\_NLINK feature + the '.' entry in the directory itself). With the DIR_NLINK feature enabled, ext4 supports more than 64,998 subdirectories by setting this field to 1 to indicate that the number of hard links is not known. * - 0x1C - - \_\_le32 - - i\_blocks\_lo - - Lower 32-bits of “block” count. If the huge\_file feature flag is not + - __le32 + - i_blocks_lo + - Lower 32-bits of “block” count. If the huge_file feature flag is not set on the filesystem, the file consumes ``i_blocks_lo`` 512-byte blocks - on disk. If huge\_file is set and EXT4\_HUGE\_FILE\_FL is NOT set in + on disk. If huge_file is set and EXT4_HUGE_FILE_FL is NOT set in ``inode.i_flags``, then the file consumes ``i_blocks_lo + (i_blocks_hi - << 32)`` 512-byte blocks on disk. If huge\_file is set and - EXT4\_HUGE\_FILE\_FL IS set in ``inode.i_flags``, then this file + << 32)`` 512-byte blocks on disk. If huge_file is set and + EXT4_HUGE_FILE_FL IS set in ``inode.i_flags``, then this file consumes (``i_blocks_lo + i_blocks_hi`` << 32) filesystem blocks on disk. * - 0x20 - - \_\_le32 - - i\_flags + - __le32 + - i_flags - Inode flags. See the table i_flags_ below. * - 0x24 - 4 bytes - - i\_osd1 + - i_osd1 - See the table i_osd1_ for more details. * - 0x28 - 60 bytes - - i\_block[EXT4\_N\_BLOCKS=15] - - Block map or extent tree. See the section “The Contents of inode.i\_block”. + - i_block[EXT4_N_BLOCKS=15] + - Block map or extent tree. See the section “The Contents of inode.i_block”. * - 0x64 - - \_\_le32 - - i\_generation + - __le32 + - i_generation - File version (for NFS). * - 0x68 - - \_\_le32 - - i\_file\_acl\_lo + - __le32 + - i_file_acl_lo - Lower 32-bits of extended attribute block. ACLs are of course one of many possible extended attributes; I think the name of this field is a result of the first use of extended attributes being for ACLs. * - 0x6C - - \_\_le32 - - i\_size\_high / i\_dir\_acl + - __le32 + - i_size_high / i_dir_acl - Upper 32-bits of file/directory size. In ext2/3 this field was named - i\_dir\_acl, though it was usually set to zero and never used. + i_dir_acl, though it was usually set to zero and never used. * - 0x70 - - \_\_le32 - - i\_obso\_faddr + - __le32 + - i_obso_faddr - (Obsolete) fragment address. * - 0x74 - 12 bytes - - i\_osd2 + - i_osd2 - See the table i_osd2_ for more details. * - 0x80 - - \_\_le16 - - i\_extra\_isize + - __le16 + - i_extra_isize - Size of this inode - 128. Alternately, the size of the extended inode fields beyond the original ext2 inode, including this field. * - 0x82 - - \_\_le16 - - i\_checksum\_hi + - __le16 + - i_checksum_hi - Upper 16-bits of the inode checksum. * - 0x84 - - \_\_le32 - - i\_ctime\_extra + - __le32 + - i_ctime_extra - Extra change time bits. This provides sub-second precision. See Inode Timestamps section. * - 0x88 - - \_\_le32 - - i\_mtime\_extra + - __le32 + - i_mtime_extra - Extra modification time bits. This provides sub-second precision. * - 0x8C - - \_\_le32 - - i\_atime\_extra + - __le32 + - i_atime_extra - Extra access time bits. This provides sub-second precision. * - 0x90 - - \_\_le32 - - i\_crtime + - __le32 + - i_crtime - File creation time, in seconds since the epoch. * - 0x94 - - \_\_le32 - - i\_crtime\_extra + - __le32 + - i_crtime_extra - Extra file creation time bits. This provides sub-second precision. * - 0x98 - - \_\_le32 - - i\_version\_hi + - __le32 + - i_version_hi - Upper 32-bits for version number. * - 0x9C - - \_\_le32 - - i\_projid + - __le32 + - i_projid - Project ID. .. _i_mode: @@ -183,45 +183,45 @@ The ``i_mode`` value is a combination of the following flags: * - Value - Description * - 0x1 - - S\_IXOTH (Others may execute) + - S_IXOTH (Others may execute) * - 0x2 - - S\_IWOTH (Others may write) + - S_IWOTH (Others may write) * - 0x4 - - S\_IROTH (Others may read) + - S_IROTH (Others may read) * - 0x8 - - S\_IXGRP (Group members may execute) + - S_IXGRP (Group members may execute) * - 0x10 - - S\_IWGRP (Group members may write) + - S_IWGRP (Group members may write) * - 0x20 - - S\_IRGRP (Group members may read) + - S_IRGRP (Group members may read) * - 0x40 - - S\_IXUSR (Owner may execute) + - S_IXUSR (Owner may execute) * - 0x80 - - S\_IWUSR (Owner may write) + - S_IWUSR (Owner may write) * - 0x100 - - S\_IRUSR (Owner may read) + - S_IRUSR (Owner may read) * - 0x200 - - S\_ISVTX (Sticky bit) + - S_ISVTX (Sticky bit) * - 0x400 - - S\_ISGID (Set GID) + - S_ISGID (Set GID) * - 0x800 - - S\_ISUID (Set UID) + - S_ISUID (Set UID) * - - These are mutually-exclusive file types: * - 0x1000 - - S\_IFIFO (FIFO) + - S_IFIFO (FIFO) * - 0x2000 - - S\_IFCHR (Character device) + - S_IFCHR (Character device) * - 0x4000 - - S\_IFDIR (Directory) + - S_IFDIR (Directory) * - 0x6000 - - S\_IFBLK (Block device) + - S_IFBLK (Block device) * - 0x8000 - - S\_IFREG (Regular file) + - S_IFREG (Regular file) * - 0xA000 - - S\_IFLNK (Symbolic link) + - S_IFLNK (Symbolic link) * - 0xC000 - - S\_IFSOCK (Socket) + - S_IFSOCK (Socket) .. _i_flags: @@ -234,56 +234,56 @@ The ``i_flags`` field is a combination of these values: * - Value - Description * - 0x1 - - This file requires secure deletion (EXT4\_SECRM\_FL). (not implemented) + - This file requires secure deletion (EXT4_SECRM_FL). (not implemented) * - 0x2 - This file should be preserved, should undeletion be desired - (EXT4\_UNRM\_FL). (not implemented) + (EXT4_UNRM_FL). (not implemented) * - 0x4 - - File is compressed (EXT4\_COMPR\_FL). (not really implemented) + - File is compressed (EXT4_COMPR_FL). (not really implemented) * - 0x8 - - All writes to the file must be synchronous (EXT4\_SYNC\_FL). + - All writes to the file must be synchronous (EXT4_SYNC_FL). * - 0x10 - - File is immutable (EXT4\_IMMUTABLE\_FL). + - File is immutable (EXT4_IMMUTABLE_FL). * - 0x20 - - File can only be appended (EXT4\_APPEND\_FL). + - File can only be appended (EXT4_APPEND_FL). * - 0x40 - - The dump(1) utility should not dump this file (EXT4\_NODUMP\_FL). + - The dump(1) utility should not dump this file (EXT4_NODUMP_FL). * - 0x80 - - Do not update access time (EXT4\_NOATIME\_FL). + - Do not update access time (EXT4_NOATIME_FL). * - 0x100 - - Dirty compressed file (EXT4\_DIRTY\_FL). (not used) + - Dirty compressed file (EXT4_DIRTY_FL). (not used) * - 0x200 - - File has one or more compressed clusters (EXT4\_COMPRBLK\_FL). (not used) + - File has one or more compressed clusters (EXT4_COMPRBLK_FL). (not used) * - 0x400 - - Do not compress file (EXT4\_NOCOMPR\_FL). (not used) + - Do not compress file (EXT4_NOCOMPR_FL). (not used) * - 0x800 - - Encrypted inode (EXT4\_ENCRYPT\_FL). This bit value previously was - EXT4\_ECOMPR\_FL (compression error), which was never used. + - Encrypted inode (EXT4_ENCRYPT_FL). This bit value previously was + EXT4_ECOMPR_FL (compression error), which was never used. * - 0x1000 - - Directory has hashed indexes (EXT4\_INDEX\_FL). + - Directory has hashed indexes (EXT4_INDEX_FL). * - 0x2000 - - AFS magic directory (EXT4\_IMAGIC\_FL). + - AFS magic directory (EXT4_IMAGIC_FL). * - 0x4000 - File data must always be written through the journal - (EXT4\_JOURNAL\_DATA\_FL). + (EXT4_JOURNAL_DATA_FL). * - 0x8000 - - File tail should not be merged (EXT4\_NOTAIL\_FL). (not used by ext4) + - File tail should not be merged (EXT4_NOTAIL_FL). (not used by ext4) * - 0x10000 - All directory entry data should be written synchronously (see - ``dirsync``) (EXT4\_DIRSYNC\_FL). + ``dirsync``) (EXT4_DIRSYNC_FL). * - 0x20000 - - Top of directory hierarchy (EXT4\_TOPDIR\_FL). + - Top of directory hierarchy (EXT4_TOPDIR_FL). * - 0x40000 - - This is a huge file (EXT4\_HUGE\_FILE\_FL). + - This is a huge file (EXT4_HUGE_FILE_FL). * - 0x80000 - - Inode uses extents (EXT4\_EXTENTS\_FL). + - Inode uses extents (EXT4_EXTENTS_FL). * - 0x100000 - - Verity protected file (EXT4\_VERITY\_FL). + - Verity protected file (EXT4_VERITY_FL). * - 0x200000 - Inode stores a large extended attribute value in its data blocks - (EXT4\_EA\_INODE\_FL). + (EXT4_EA_INODE_FL). * - 0x400000 - - This file has blocks allocated past EOF (EXT4\_EOFBLOCKS\_FL). + - This file has blocks allocated past EOF (EXT4_EOFBLOCKS_FL). (deprecated) * - 0x01000000 - Inode is a snapshot (``EXT4_SNAPFILE_FL``). (not in mainline) @@ -294,21 +294,21 @@ The ``i_flags`` field is a combination of these values: - Snapshot shrink has completed (``EXT4_SNAPFILE_SHRUNK_FL``). (not in mainline) * - 0x10000000 - - Inode has inline data (EXT4\_INLINE\_DATA\_FL). + - Inode has inline data (EXT4_INLINE_DATA_FL). * - 0x20000000 - - Create children with the same project ID (EXT4\_PROJINHERIT\_FL). + - Create children with the same project ID (EXT4_PROJINHERIT_FL). * - 0x80000000 - - Reserved for ext4 library (EXT4\_RESERVED\_FL). + - Reserved for ext4 library (EXT4_RESERVED_FL). * - - Aggregate flags: * - 0x705BDFFF - User-visible flags. * - 0x604BC0FF - - User-modifiable flags. Note that while EXT4\_JOURNAL\_DATA\_FL and - EXT4\_EXTENTS\_FL can be set with setattr, they are not in the kernel's - EXT4\_FL\_USER\_MODIFIABLE mask, since it needs to handle the setting of + - User-modifiable flags. Note that while EXT4_JOURNAL_DATA_FL and + EXT4_EXTENTS_FL can be set with setattr, they are not in the kernel's + EXT4_FL_USER_MODIFIABLE mask, since it needs to handle the setting of these flags in a special manner and they are masked out of the set of - flags that are saved directly to i\_flags. + flags that are saved directly to i_flags. .. _i_osd1: @@ -325,9 +325,9 @@ Linux: - Name - Description * - 0x0 - - \_\_le32 - - l\_i\_version - - Inode version. However, if the EA\_INODE inode flag is set, this inode + - __le32 + - l_i_version + - Inode version. However, if the EA_INODE inode flag is set, this inode stores an extended attribute value and this field contains the upper 32 bits of the attribute value's reference count. @@ -342,8 +342,8 @@ Hurd: - Name - Description * - 0x0 - - \_\_le32 - - h\_i\_translator + - __le32 + - h_i_translator - ?? Masix: @@ -357,8 +357,8 @@ Masix: - Name - Description * - 0x0 - - \_\_le32 - - m\_i\_reserved + - __le32 + - m_i_reserved - ?? .. _i_osd2: @@ -376,30 +376,30 @@ Linux: - Name - Description * - 0x0 - - \_\_le16 - - l\_i\_blocks\_high + - __le16 + - l_i_blocks_high - Upper 16-bits of the block count. Please see the note attached to - i\_blocks\_lo. + i_blocks_lo. * - 0x2 - - \_\_le16 - - l\_i\_file\_acl\_high + - __le16 + - l_i_file_acl_high - Upper 16-bits of the extended attribute block (historically, the file ACL location). See the Extended Attributes section below. * - 0x4 - - \_\_le16 - - l\_i\_uid\_high + - __le16 + - l_i_uid_high - Upper 16-bits of the Owner UID. * - 0x6 - - \_\_le16 - - l\_i\_gid\_high + - __le16 + - l_i_gid_high - Upper 16-bits of the GID. * - 0x8 - - \_\_le16 - - l\_i\_checksum\_lo + - __le16 + - l_i_checksum_lo - Lower 16-bits of the inode checksum. * - 0xA - - \_\_le16 - - l\_i\_reserved + - __le16 + - l_i_reserved - Unused. Hurd: @@ -413,24 +413,24 @@ Hurd: - Name - Description * - 0x0 - - \_\_le16 - - h\_i\_reserved1 + - __le16 + - h_i_reserved1 - ?? * - 0x2 - - \_\_u16 - - h\_i\_mode\_high + - __u16 + - h_i_mode_high - Upper 16-bits of the file mode. * - 0x4 - - \_\_le16 - - h\_i\_uid\_high + - __le16 + - h_i_uid_high - Upper 16-bits of the Owner UID. * - 0x6 - - \_\_le16 - - h\_i\_gid\_high + - __le16 + - h_i_gid_high - Upper 16-bits of the GID. * - 0x8 - - \_\_u32 - - h\_i\_author + - __u32 + - h_i_author - Author code? Masix: @@ -444,17 +444,17 @@ Masix: - Name - Description * - 0x0 - - \_\_le16 - - h\_i\_reserved1 + - __le16 + - h_i_reserved1 - ?? * - 0x2 - - \_\_u16 - - m\_i\_file\_acl\_high + - __u16 + - m_i_file_acl_high - Upper 16-bits of the extended attribute block (historically, the file ACL location). * - 0x4 - - \_\_u32 - - m\_i\_reserved2[2] + - __u32 + - m_i_reserved2[2] - ?? Inode Size @@ -466,11 +466,11 @@ In ext2 and ext3, the inode structure size was fixed at 128 bytes on-disk inode at format time for all inodes in the filesystem to provide space beyond the end of the original ext2 inode. The on-disk inode record size is recorded in the superblock as ``s_inode_size``. The -number of bytes actually used by struct ext4\_inode beyond the original +number of bytes actually used by struct ext4_inode beyond the original 128-byte ext2 inode is recorded in the ``i_extra_isize`` field for each -inode, which allows struct ext4\_inode to grow for a new kernel without +inode, which allows struct ext4_inode to grow for a new kernel without having to upgrade all of the on-disk inodes. Access to fields beyond -EXT2\_GOOD\_OLD\_INODE\_SIZE should be verified to be within +EXT2_GOOD_OLD_INODE_SIZE should be verified to be within ``i_extra_isize``. By default, ext4 inode records are 256 bytes, and (as of August 2019) the inode structure is 160 bytes (``i_extra_isize = 32``). The extra space between the end of the inode @@ -516,7 +516,7 @@ creation time (crtime); this field is 64-bits wide and decoded in the same manner as 64-bit [cma]time. Neither crtime nor dtime are accessible through the regular stat() interface, though debugfs will report them. -We use the 32-bit signed time value plus (2^32 \* (extra epoch bits)). +We use the 32-bit signed time value plus (2^32 * (extra epoch bits)). In other words: .. list-table:: @@ -525,8 +525,8 @@ In other words: * - Extra epoch bits - MSB of 32-bit time - - Adjustment for signed 32-bit to 64-bit tv\_sec - - Decoded 64-bit tv\_sec + - Adjustment for signed 32-bit to 64-bit tv_sec + - Decoded 64-bit tv_sec - valid time range * - 0 0 - 1 diff --git a/Documentation/filesystems/ext4/journal.rst b/Documentation/filesystems/ext4/journal.rst index 5fad38860f174..a6bef5293a600 100644 --- a/Documentation/filesystems/ext4/journal.rst +++ b/Documentation/filesystems/ext4/journal.rst @@ -63,8 +63,8 @@ Generally speaking, the journal has this format: :header-rows: 1 * - Superblock - - descriptor\_block (data\_blocks or revocation\_block) [more data or - revocations] commmit\_block + - descriptor_block (data_blocks or revocation_block) [more data or + revocations] commmit_block - [more transactions...] * - - One transaction @@ -93,8 +93,8 @@ superblock. * - 1024 bytes of padding - ext4 Superblock - Journal Superblock - - descriptor\_block (data\_blocks or revocation\_block) [more data or - revocations] commmit\_block + - descriptor_block (data_blocks or revocation_block) [more data or + revocations] commmit_block - [more transactions...] * - - @@ -117,17 +117,17 @@ Every block in the journal starts with a common 12-byte header - Name - Description * - 0x0 - - \_\_be32 - - h\_magic + - __be32 + - h_magic - jbd2 magic number, 0xC03B3998. * - 0x4 - - \_\_be32 - - h\_blocktype + - __be32 + - h_blocktype - Description of what this block contains. See the jbd2_blocktype_ table below. * - 0x8 - - \_\_be32 - - h\_sequence + - __be32 + - h_sequence - The transaction ID that goes with this block. .. _jbd2_blocktype: @@ -177,99 +177,99 @@ which is 1024 bytes long: - - Static information describing the journal. * - 0x0 - - journal\_header\_t (12 bytes) - - s\_header + - journal_header_t (12 bytes) + - s_header - Common header identifying this as a superblock. * - 0xC - - \_\_be32 - - s\_blocksize + - __be32 + - s_blocksize - Journal device block size. * - 0x10 - - \_\_be32 - - s\_maxlen + - __be32 + - s_maxlen - Total number of blocks in this journal. * - 0x14 - - \_\_be32 - - s\_first + - __be32 + - s_first - First block of log information. * - - - - Dynamic information describing the current state of the log. * - 0x18 - - \_\_be32 - - s\_sequence + - __be32 + - s_sequence - First commit ID expected in log. * - 0x1C - - \_\_be32 - - s\_start + - __be32 + - s_start - Block number of the start of log. Contrary to the comments, this field being zero does not imply that the journal is clean! * - 0x20 - - \_\_be32 - - s\_errno - - Error value, as set by jbd2\_journal\_abort(). + - __be32 + - s_errno + - Error value, as set by jbd2_journal_abort(). * - - - - The remaining fields are only valid in a v2 superblock. * - 0x24 - - \_\_be32 - - s\_feature\_compat; + - __be32 + - s_feature_compat; - Compatible feature set. See the table jbd2_compat_ below. * - 0x28 - - \_\_be32 - - s\_feature\_incompat + - __be32 + - s_feature_incompat - Incompatible feature set. See the table jbd2_incompat_ below. * - 0x2C - - \_\_be32 - - s\_feature\_ro\_compat + - __be32 + - s_feature_ro_compat - Read-only compatible feature set. There aren't any of these currently. * - 0x30 - - \_\_u8 - - s\_uuid[16] + - __u8 + - s_uuid[16] - 128-bit uuid for journal. This is compared against the copy in the ext4 super block at mount time. * - 0x40 - - \_\_be32 - - s\_nr\_users + - __be32 + - s_nr_users - Number of file systems sharing this journal. * - 0x44 - - \_\_be32 - - s\_dynsuper + - __be32 + - s_dynsuper - Location of dynamic super block copy. (Not used?) * - 0x48 - - \_\_be32 - - s\_max\_transaction + - __be32 + - s_max_transaction - Limit of journal blocks per transaction. (Not used?) * - 0x4C - - \_\_be32 - - s\_max\_trans\_data + - __be32 + - s_max_trans_data - Limit of data blocks per transaction. (Not used?) * - 0x50 - - \_\_u8 - - s\_checksum\_type + - __u8 + - s_checksum_type - Checksum algorithm used for the journal. See jbd2_checksum_type_ for more info. * - 0x51 - - \_\_u8[3] - - s\_padding2 + - __u8[3] + - s_padding2 - * - 0x54 - - \_\_be32 - - s\_num\_fc\_blocks + - __be32 + - s_num_fc_blocks - Number of fast commit blocks in the journal. * - 0x58 - - \_\_u32 - - s\_padding[42] + - __u32 + - s_padding[42] - * - 0xFC - - \_\_be32 - - s\_checksum + - __be32 + - s_checksum - Checksum of the entire superblock, with this field set to zero. * - 0x100 - - \_\_u8 - - s\_users[16\*48] + - __u8 + - s_users[16*48] - ids of all file systems sharing the log. e2fsprogs/Linux don't allow shared external journals, but I imagine Lustre (or ocfs2?), which use the jbd2 code, might. @@ -286,7 +286,7 @@ The journal compat features are any combination of the following: - Description * - 0x1 - Journal maintains checksums on the data blocks. - (JBD2\_FEATURE\_COMPAT\_CHECKSUM) + (JBD2_FEATURE_COMPAT_CHECKSUM) .. _jbd2_incompat: @@ -299,23 +299,23 @@ The journal incompat features are any combination of the following: * - Value - Description * - 0x1 - - Journal has block revocation records. (JBD2\_FEATURE\_INCOMPAT\_REVOKE) + - Journal has block revocation records. (JBD2_FEATURE_INCOMPAT_REVOKE) * - 0x2 - Journal can deal with 64-bit block numbers. - (JBD2\_FEATURE\_INCOMPAT\_64BIT) + (JBD2_FEATURE_INCOMPAT_64BIT) * - 0x4 - - Journal commits asynchronously. (JBD2\_FEATURE\_INCOMPAT\_ASYNC\_COMMIT) + - Journal commits asynchronously. (JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT) * - 0x8 - This journal uses v2 of the checksum on-disk format. Each journal metadata block gets its own checksum, and the block tags in the descriptor table contain checksums for each of the data blocks in the - journal. (JBD2\_FEATURE\_INCOMPAT\_CSUM\_V2) + journal. (JBD2_FEATURE_INCOMPAT_CSUM_V2) * - 0x10 - This journal uses v3 of the checksum on-disk format. This is the same as v2, but the journal block tag size is fixed regardless of the size of - block numbers. (JBD2\_FEATURE\_INCOMPAT\_CSUM\_V3) + block numbers. (JBD2_FEATURE_INCOMPAT_CSUM_V3) * - 0x20 - - Journal has fast commit blocks. (JBD2\_FEATURE\_INCOMPAT\_FAST\_COMMIT) + - Journal has fast commit blocks. (JBD2_FEATURE_INCOMPAT_FAST_COMMIT) .. _jbd2_checksum_type: @@ -355,11 +355,11 @@ Descriptor blocks consume at least 36 bytes, but use a full block: - Name - Descriptor * - 0x0 - - journal\_header\_t + - journal_header_t - (open coded) - Common block header. * - 0xC - - struct journal\_block\_tag\_s + - struct journal_block_tag_s - open coded array[] - Enough tags either to fill up the block or to describe all the data blocks that follow this descriptor block. @@ -367,7 +367,7 @@ Descriptor blocks consume at least 36 bytes, but use a full block: Journal block tags have any of the following formats, depending on which journal feature and block tag flags are set. -If JBD2\_FEATURE\_INCOMPAT\_CSUM\_V3 is set, the journal block tag is +If JBD2_FEATURE_INCOMPAT_CSUM_V3 is set, the journal block tag is defined as ``struct journal_block_tag3_s``, which looks like the following. The size is 16 or 32 bytes. @@ -380,24 +380,24 @@ following. The size is 16 or 32 bytes. - Name - Descriptor * - 0x0 - - \_\_be32 - - t\_blocknr + - __be32 + - t_blocknr - Lower 32-bits of the location of where the corresponding data block should end up on disk. * - 0x4 - - \_\_be32 - - t\_flags + - __be32 + - t_flags - Flags that go with the descriptor. See the table jbd2_tag_flags_ for more info. * - 0x8 - - \_\_be32 - - t\_blocknr\_high + - __be32 + - t_blocknr_high - Upper 32-bits of the location of where the corresponding data block - should end up on disk. This is zero if JBD2\_FEATURE\_INCOMPAT\_64BIT is + should end up on disk. This is zero if JBD2_FEATURE_INCOMPAT_64BIT is not enabled. * - 0xC - - \_\_be32 - - t\_checksum + - __be32 + - t_checksum - Checksum of the journal UUID, the sequence number, and the data block. * - - @@ -433,7 +433,7 @@ The journal tag flags are any combination of the following: * - 0x8 - This is the last tag in this descriptor block. -If JBD2\_FEATURE\_INCOMPAT\_CSUM\_V3 is NOT set, the journal block tag +If JBD2_FEATURE_INCOMPAT_CSUM_V3 is NOT set, the journal block tag is defined as ``struct journal_block_tag_s``, which looks like the following. The size is 8, 12, 24, or 28 bytes: @@ -446,18 +446,18 @@ following. The size is 8, 12, 24, or 28 bytes: - Name - Descriptor * - 0x0 - - \_\_be32 - - t\_blocknr + - __be32 + - t_blocknr - Lower 32-bits of the location of where the corresponding data block should end up on disk. * - 0x4 - - \_\_be16 - - t\_checksum + - __be16 + - t_checksum - Checksum of the journal UUID, the sequence number, and the data block. Note that only the lower 16 bits are stored. * - 0x6 - - \_\_be16 - - t\_flags + - __be16 + - t_flags - Flags that go with the descriptor. See the table jbd2_tag_flags_ for more info. * - @@ -466,8 +466,8 @@ following. The size is 8, 12, 24, or 28 bytes: - This next field is only present if the super block indicates support for 64-bit block numbers. * - 0x8 - - \_\_be32 - - t\_blocknr\_high + - __be32 + - t_blocknr_high - Upper 32-bits of the location of where the corresponding data block should end up on disk. * - @@ -483,8 +483,8 @@ following. The size is 8, 12, 24, or 28 bytes: ``j_uuid`` field in ``struct journal_s``, but only tune2fs touches that field. -If JBD2\_FEATURE\_INCOMPAT\_CSUM\_V2 or -JBD2\_FEATURE\_INCOMPAT\_CSUM\_V3 are set, the end of the block is a +If JBD2_FEATURE_INCOMPAT_CSUM_V2 or +JBD2_FEATURE_INCOMPAT_CSUM_V3 are set, the end of the block is a ``struct jbd2_journal_block_tail``, which looks like this: .. list-table:: @@ -496,8 +496,8 @@ JBD2\_FEATURE\_INCOMPAT\_CSUM\_V3 are set, the end of the block is a - Name - Descriptor * - 0x0 - - \_\_be32 - - t\_checksum + - __be32 + - t_checksum - Checksum of the journal UUID + the descriptor block, with this field set to zero. @@ -538,25 +538,25 @@ length, but use a full block: - Name - Description * - 0x0 - - journal\_header\_t - - r\_header + - journal_header_t + - r_header - Common block header. * - 0xC - - \_\_be32 - - r\_count + - __be32 + - r_count - Number of bytes used in this block. * - 0x10 - - \_\_be32 or \_\_be64 + - __be32 or __be64 - blocks[0] - Blocks to revoke. -After r\_count is a linear array of block numbers that are effectively +After r_count is a linear array of block numbers that are effectively revoked by this transaction. The size of each block number is 8 bytes if the superblock advertises 64-bit block number support, or 4 bytes otherwise. -If JBD2\_FEATURE\_INCOMPAT\_CSUM\_V2 or -JBD2\_FEATURE\_INCOMPAT\_CSUM\_V3 are set, the end of the revocation +If JBD2_FEATURE_INCOMPAT_CSUM_V2 or +JBD2_FEATURE_INCOMPAT_CSUM_V3 are set, the end of the revocation block is a ``struct jbd2_journal_revoke_tail``, which has this format: .. list-table:: @@ -568,8 +568,8 @@ block is a ``struct jbd2_journal_revoke_tail``, which has this format: - Name - Description * - 0x0 - - \_\_be32 - - r\_checksum + - __be32 + - r_checksum - Checksum of the journal UUID + revocation block Commit Block @@ -592,38 +592,38 @@ bytes long (but uses a full block): - Name - Descriptor * - 0x0 - - journal\_header\_s + - journal_header_s - (open coded) - Common block header. * - 0xC - unsigned char - - h\_chksum\_type + - h_chksum_type - The type of checksum to use to verify the integrity of the data blocks in the transaction. See jbd2_checksum_type_ for more info. * - 0xD - unsigned char - - h\_chksum\_size + - h_chksum_size - The number of bytes used by the checksum. Most likely 4. * - 0xE - unsigned char - - h\_padding[2] + - h_padding[2] - * - 0x10 - - \_\_be32 - - h\_chksum[JBD2\_CHECKSUM\_BYTES] + - __be32 + - h_chksum[JBD2_CHECKSUM_BYTES] - 32 bytes of space to store checksums. If - JBD2\_FEATURE\_INCOMPAT\_CSUM\_V2 or JBD2\_FEATURE\_INCOMPAT\_CSUM\_V3 + JBD2_FEATURE_INCOMPAT_CSUM_V2 or JBD2_FEATURE_INCOMPAT_CSUM_V3 are set, the first ``__be32`` is the checksum of the journal UUID and the entire commit block, with this field zeroed. If - JBD2\_FEATURE\_COMPAT\_CHECKSUM is set, the first ``__be32`` is the + JBD2_FEATURE_COMPAT_CHECKSUM is set, the first ``__be32`` is the crc32 of all the blocks already written to the transaction. * - 0x30 - - \_\_be64 - - h\_commit\_sec + - __be64 + - h_commit_sec - The time that the transaction was committed, in seconds since the epoch. * - 0x38 - - \_\_be32 - - h\_commit\_nsec + - __be32 + - h_commit_nsec - Nanoseconds component of the above timestamp. Fast commits diff --git a/Documentation/filesystems/ext4/mmp.rst b/Documentation/filesystems/ext4/mmp.rst index 25660981d93c2..174dd6538737d 100644 --- a/Documentation/filesystems/ext4/mmp.rst +++ b/Documentation/filesystems/ext4/mmp.rst @@ -7,8 +7,8 @@ Multiple mount protection (MMP) is a feature that protects the filesystem against multiple hosts trying to use the filesystem simultaneously. When a filesystem is opened (for mounting, or fsck, etc.), the MMP code running on the node (call it node A) checks a -sequence number. If the sequence number is EXT4\_MMP\_SEQ\_CLEAN, the -open continues. If the sequence number is EXT4\_MMP\_SEQ\_FSCK, then +sequence number. If the sequence number is EXT4_MMP_SEQ_CLEAN, the +open continues. If the sequence number is EXT4_MMP_SEQ_FSCK, then fsck is (hopefully) running, and open fails immediately. Otherwise, the open code will wait for twice the specified MMP check interval and check the sequence number again. If the sequence number has changed, then the @@ -40,38 +40,38 @@ The MMP structure (``struct mmp_struct``) is as follows: - Name - Description * - 0x0 - - \_\_le32 - - mmp\_magic + - __le32 + - mmp_magic - Magic number for MMP, 0x004D4D50 (“MMP”). * - 0x4 - - \_\_le32 - - mmp\_seq + - __le32 + - mmp_seq - Sequence number, updated periodically. * - 0x8 - - \_\_le64 - - mmp\_time + - __le64 + - mmp_time - Time that the MMP block was last updated. * - 0x10 - char[64] - - mmp\_nodename + - mmp_nodename - Hostname of the node that opened the filesystem. * - 0x50 - char[32] - - mmp\_bdevname + - mmp_bdevname - Block device name of the filesystem. * - 0x70 - - \_\_le16 - - mmp\_check\_interval + - __le16 + - mmp_check_interval - The MMP re-check interval, in seconds. * - 0x72 - - \_\_le16 - - mmp\_pad1 + - __le16 + - mmp_pad1 - Zero. * - 0x74 - - \_\_le32[226] - - mmp\_pad2 + - __le32[226] + - mmp_pad2 - Zero. * - 0x3FC - - \_\_le32 - - mmp\_checksum + - __le32 + - mmp_checksum - Checksum of the MMP block. diff --git a/Documentation/filesystems/ext4/overview.rst b/Documentation/filesystems/ext4/overview.rst index 123ebfde47ee1..0fad6eda6e15d 100644 --- a/Documentation/filesystems/ext4/overview.rst +++ b/Documentation/filesystems/ext4/overview.rst @@ -7,7 +7,7 @@ An ext4 file system is split into a series of block groups. To reduce performance difficulties due to fragmentation, the block allocator tries very hard to keep each file's blocks within the same group, thereby reducing seek times. The size of a block group is specified in -``sb.s_blocks_per_group`` blocks, though it can also calculated as 8 \* +``sb.s_blocks_per_group`` blocks, though it can also calculated as 8 * ``block_size_in_bytes``. With the default block size of 4KiB, each group will contain 32,768 blocks, for a length of 128MiB. The number of block groups is the size of the device divided by the size of a block group. diff --git a/Documentation/filesystems/ext4/special_inodes.rst b/Documentation/filesystems/ext4/special_inodes.rst index 94f304e3a0a7b..fc0636901fa0e 100644 --- a/Documentation/filesystems/ext4/special_inodes.rst +++ b/Documentation/filesystems/ext4/special_inodes.rst @@ -34,7 +34,7 @@ ext4 reserves some inode for special features, as follows: * - 10 - Replica inode, used for some non-upstream feature? * - 11 - - Traditional first non-reserved inode. Usually this is the lost+found directory. See s\_first\_ino in the superblock. + - Traditional first non-reserved inode. Usually this is the lost+found directory. See s_first_ino in the superblock. Note that there are also some inodes allocated from non-reserved inode numbers for other filesystem features which are not referenced from standard directory @@ -47,9 +47,9 @@ hierarchy. These are generally reference from the superblock. They are: * - Superblock field - Description - * - s\_lpf\_ino + * - s_lpf_ino - Inode number of lost+found directory. - * - s\_prj\_quota\_inum + * - s_prj_quota_inum - Inode number of quota file tracking project quotas - * - s\_orphan\_file\_inum + * - s_orphan_file_inum - Inode number of file tracking orphan inodes. diff --git a/Documentation/filesystems/ext4/super.rst b/Documentation/filesystems/ext4/super.rst index f6a548e957bb9..268888522e35c 100644 --- a/Documentation/filesystems/ext4/super.rst +++ b/Documentation/filesystems/ext4/super.rst @@ -7,7 +7,7 @@ The superblock records various information about the enclosing filesystem, such as block counts, inode counts, supported features, maintenance information, and more. -If the sparse\_super feature flag is set, redundant copies of the +If the sparse_super feature flag is set, redundant copies of the superblock and group descriptors are kept only in the groups whose group number is either 0 or a power of 3, 5, or 7. If the flag is not set, redundant copies are kept in all groups. @@ -27,107 +27,107 @@ The ext4 superblock is laid out as follows in - Name - Description * - 0x0 - - \_\_le32 - - s\_inodes\_count + - __le32 + - s_inodes_count - Total inode count. * - 0x4 - - \_\_le32 - - s\_blocks\_count\_lo + - __le32 + - s_blocks_count_lo - Total block count. * - 0x8 - - \_\_le32 - - s\_r\_blocks\_count\_lo + - __le32 + - s_r_blocks_count_lo - This number of blocks can only be allocated by the super-user. * - 0xC - - \_\_le32 - - s\_free\_blocks\_count\_lo + - __le32 + - s_free_blocks_count_lo - Free block count. * - 0x10 - - \_\_le32 - - s\_free\_inodes\_count + - __le32 + - s_free_inodes_count - Free inode count. * - 0x14 - - \_\_le32 - - s\_first\_data\_block + - __le32 + - s_first_data_block - First data block. This must be at least 1 for 1k-block filesystems and is typically 0 for all other block sizes. * - 0x18 - - \_\_le32 - - s\_log\_block\_size - - Block size is 2 ^ (10 + s\_log\_block\_size). + - __le32 + - s_log_block_size + - Block size is 2 ^ (10 + s_log_block_size). * - 0x1C - - \_\_le32 - - s\_log\_cluster\_size - - Cluster size is 2 ^ (10 + s\_log\_cluster\_size) blocks if bigalloc is - enabled. Otherwise s\_log\_cluster\_size must equal s\_log\_block\_size. + - __le32 + - s_log_cluster_size + - Cluster size is 2 ^ (10 + s_log_cluster_size) blocks if bigalloc is + enabled. Otherwise s_log_cluster_size must equal s_log_block_size. * - 0x20 - - \_\_le32 - - s\_blocks\_per\_group + - __le32 + - s_blocks_per_group - Blocks per group. * - 0x24 - - \_\_le32 - - s\_clusters\_per\_group + - __le32 + - s_clusters_per_group - Clusters per group, if bigalloc is enabled. Otherwise - s\_clusters\_per\_group must equal s\_blocks\_per\_group. + s_clusters_per_group must equal s_blocks_per_group. * - 0x28 - - \_\_le32 - - s\_inodes\_per\_group + - __le32 + - s_inodes_per_group - Inodes per group. * - 0x2C - - \_\_le32 - - s\_mtime + - __le32 + - s_mtime - Mount time, in seconds since the epoch. * - 0x30 - - \_\_le32 - - s\_wtime + - __le32 + - s_wtime - Write time, in seconds since the epoch. * - 0x34 - - \_\_le16 - - s\_mnt\_count + - __le16 + - s_mnt_count - Number of mounts since the last fsck. * - 0x36 - - \_\_le16 - - s\_max\_mnt\_count + - __le16 + - s_max_mnt_count - Number of mounts beyond which a fsck is needed. * - 0x38 - - \_\_le16 - - s\_magic + - __le16 + - s_magic - Magic signature, 0xEF53 * - 0x3A - - \_\_le16 - - s\_state + - __le16 + - s_state - File system state. See super_state_ for more info. * - 0x3C - - \_\_le16 - - s\_errors + - __le16 + - s_errors - Behaviour when detecting errors. See super_errors_ for more info. * - 0x3E - - \_\_le16 - - s\_minor\_rev\_level + - __le16 + - s_minor_rev_level - Minor revision level. * - 0x40 - - \_\_le32 - - s\_lastcheck + - __le32 + - s_lastcheck - Time of last check, in seconds since the epoch. * - 0x44 - - \_\_le32 - - s\_checkinterval + - __le32 + - s_checkinterval - Maximum time between checks, in seconds. * - 0x48 - - \_\_le32 - - s\_creator\_os + - __le32 + - s_creator_os - Creator OS. See the table super_creator_ for more info. * - 0x4C - - \_\_le32 - - s\_rev\_level + - __le32 + - s_rev_level - Revision level. See the table super_revision_ for more info. * - 0x50 - - \_\_le16 - - s\_def\_resuid + - __le16 + - s_def_resuid - Default uid for reserved blocks. * - 0x52 - - \_\_le16 - - s\_def\_resgid + - __le16 + - s_def_resgid - Default gid for reserved blocks. * - - @@ -143,50 +143,50 @@ The ext4 superblock is laid out as follows in about a feature in either the compatible or incompatible feature set, it must abort and not try to meddle with things it doesn't understand... * - 0x54 - - \_\_le32 - - s\_first\_ino + - __le32 + - s_first_ino - First non-reserved inode. * - 0x58 - - \_\_le16 - - s\_inode\_size + - __le16 + - s_inode_size - Size of inode structure, in bytes. * - 0x5A - - \_\_le16 - - s\_block\_group\_nr + - __le16 + - s_block_group_nr - Block group # of this superblock. * - 0x5C - - \_\_le32 - - s\_feature\_compat + - __le32 + - s_feature_compat - Compatible feature set flags. Kernel can still read/write this fs even if it doesn't understand a flag; fsck should not do that. See the super_compat_ table for more info. * - 0x60 - - \_\_le32 - - s\_feature\_incompat + - __le32 + - s_feature_incompat - Incompatible feature set. If the kernel or fsck doesn't understand one of these bits, it should stop. See the super_incompat_ table for more info. * - 0x64 - - \_\_le32 - - s\_feature\_ro\_compat + - __le32 + - s_feature_ro_compat - Readonly-compatible feature set. If the kernel doesn't understand one of these bits, it can still mount read-only. See the super_rocompat_ table for more info. * - 0x68 - - \_\_u8 - - s\_uuid[16] + - __u8 + - s_uuid[16] - 128-bit UUID for volume. * - 0x78 - char - - s\_volume\_name[16] + - s_volume_name[16] - Volume label. * - 0x88 - char - - s\_last\_mounted[64] + - s_last_mounted[64] - Directory where filesystem was last mounted. * - 0xC8 - - \_\_le32 - - s\_algorithm\_usage\_bitmap + - __le32 + - s_algorithm_usage_bitmap - For compression (Not used in e2fsprogs/Linux) * - - @@ -194,18 +194,18 @@ The ext4 superblock is laid out as follows in - Performance hints. Directory preallocation should only happen if the EXT4_FEATURE_COMPAT_DIR_PREALLOC flag is on. * - 0xCC - - \_\_u8 - - s\_prealloc\_blocks + - __u8 + - s_prealloc_blocks - #. of blocks to try to preallocate for ... files? (Not used in e2fsprogs/Linux) * - 0xCD - - \_\_u8 - - s\_prealloc\_dir\_blocks + - __u8 + - s_prealloc_dir_blocks - #. of blocks to preallocate for directories. (Not used in e2fsprogs/Linux) * - 0xCE - - \_\_le16 - - s\_reserved\_gdt\_blocks + - __le16 + - s_reserved_gdt_blocks - Number of reserved GDT entries for future filesystem expansion. * - - @@ -213,281 +213,281 @@ The ext4 superblock is laid out as follows in - Journalling support is valid only if EXT4_FEATURE_COMPAT_HAS_JOURNAL is set. * - 0xD0 - - \_\_u8 - - s\_journal\_uuid[16] + - __u8 + - s_journal_uuid[16] - UUID of journal superblock * - 0xE0 - - \_\_le32 - - s\_journal\_inum + - __le32 + - s_journal_inum - inode number of journal file. * - 0xE4 - - \_\_le32 - - s\_journal\_dev + - __le32 + - s_journal_dev - Device number of journal file, if the external journal feature flag is set. * - 0xE8 - - \_\_le32 - - s\_last\_orphan + - __le32 + - s_last_orphan - Start of list of orphaned inodes to delete. * - 0xEC - - \_\_le32 - - s\_hash\_seed[4] + - __le32 + - s_hash_seed[4] - HTREE hash seed. * - 0xFC - - \_\_u8 - - s\_def\_hash\_version + - __u8 + - s_def_hash_version - Default hash algorithm to use for directory hashes. See super_def_hash_ for more info. * - 0xFD - - \_\_u8 - - s\_jnl\_backup\_type - - If this value is 0 or EXT3\_JNL\_BACKUP\_BLOCKS (1), then the + - __u8 + - s_jnl_backup_type + - If this value is 0 or EXT3_JNL_BACKUP_BLOCKS (1), then the ``s_jnl_blocks`` field contains a duplicate copy of the inode's ``i_block[]`` array and ``i_size``. * - 0xFE - - \_\_le16 - - s\_desc\_size + - __le16 + - s_desc_size - Size of group descriptors, in bytes, if the 64bit incompat feature flag is set. * - 0x100 - - \_\_le32 - - s\_default\_mount\_opts + - __le32 + - s_default_mount_opts - Default mount options. See the super_mountopts_ table for more info. * - 0x104 - - \_\_le32 - - s\_first\_meta\_bg - - First metablock block group, if the meta\_bg feature is enabled. + - __le32 + - s_first_meta_bg + - First metablock block group, if the meta_bg feature is enabled. * - 0x108 - - \_\_le32 - - s\_mkfs\_time + - __le32 + - s_mkfs_time - When the filesystem was created, in seconds since the epoch. * - 0x10C - - \_\_le32 - - s\_jnl\_blocks[17] + - __le32 + - s_jnl_blocks[17] - Backup copy of the journal inode's ``i_block[]`` array in the first 15 - elements and i\_size\_high and i\_size in the 16th and 17th elements, + elements and i_size_high and i_size in the 16th and 17th elements, respectively. * - - - - 64bit support is valid only if EXT4_FEATURE_COMPAT_64BIT is set. * - 0x150 - - \_\_le32 - - s\_blocks\_count\_hi + - __le32 + - s_blocks_count_hi - High 32-bits of the block count. * - 0x154 - - \_\_le32 - - s\_r\_blocks\_count\_hi + - __le32 + - s_r_blocks_count_hi - High 32-bits of the reserved block count. * - 0x158 - - \_\_le32 - - s\_free\_blocks\_count\_hi + - __le32 + - s_free_blocks_count_hi - High 32-bits of the free block count. * - 0x15C - - \_\_le16 - - s\_min\_extra\_isize + - __le16 + - s_min_extra_isize - All inodes have at least # bytes. * - 0x15E - - \_\_le16 - - s\_want\_extra\_isize + - __le16 + - s_want_extra_isize - New inodes should reserve # bytes. * - 0x160 - - \_\_le32 - - s\_flags + - __le32 + - s_flags - Miscellaneous flags. See the super_flags_ table for more info. * - 0x164 - - \_\_le16 - - s\_raid\_stride + - __le16 + - s_raid_stride - RAID stride. This is the number of logical blocks read from or written to the disk before moving to the next disk. This affects the placement of filesystem metadata, which will hopefully make RAID storage faster. * - 0x166 - - \_\_le16 - - s\_mmp\_interval + - __le16 + - s_mmp_interval - #. seconds to wait in multi-mount prevention (MMP) checking. In theory, MMP is a mechanism to record in the superblock which host and device have mounted the filesystem, in order to prevent multiple mounts. This feature does not seem to be implemented... * - 0x168 - - \_\_le64 - - s\_mmp\_block + - __le64 + - s_mmp_block - Block # for multi-mount protection data. * - 0x170 - - \_\_le32 - - s\_raid\_stripe\_width + - __le32 + - s_raid_stripe_width - RAID stripe width. This is the number of logical blocks read from or written to the disk before coming back to the current disk. This is used by the block allocator to try to reduce the number of read-modify-write operations in a RAID5/6. * - 0x174 - - \_\_u8 - - s\_log\_groups\_per\_flex + - __u8 + - s_log_groups_per_flex - Size of a flexible block group is 2 ^ ``s_log_groups_per_flex``. * - 0x175 - - \_\_u8 - - s\_checksum\_type + - __u8 + - s_checksum_type - Metadata checksum algorithm type. The only valid value is 1 (crc32c). * - 0x176 - - \_\_le16 - - s\_reserved\_pad + - __le16 + - s_reserved_pad - * - 0x178 - - \_\_le64 - - s\_kbytes\_written + - __le64 + - s_kbytes_written - Number of KiB written to this filesystem over its lifetime. * - 0x180 - - \_\_le32 - - s\_snapshot\_inum + - __le32 + - s_snapshot_inum - inode number of active snapshot. (Not used in e2fsprogs/Linux.) * - 0x184 - - \_\_le32 - - s\_snapshot\_id + - __le32 + - s_snapshot_id - Sequential ID of active snapshot. (Not used in e2fsprogs/Linux.) * - 0x188 - - \_\_le64 - - s\_snapshot\_r\_blocks\_count + - __le64 + - s_snapshot_r_blocks_count - Number of blocks reserved for active snapshot's future use. (Not used in e2fsprogs/Linux.) * - 0x190 - - \_\_le32 - - s\_snapshot\_list + - __le32 + - s_snapshot_list - inode number of the head of the on-disk snapshot list. (Not used in e2fsprogs/Linux.) * - 0x194 - - \_\_le32 - - s\_error\_count + - __le32 + - s_error_count - Number of errors seen. * - 0x198 - - \_\_le32 - - s\_first\_error\_time + - __le32 + - s_first_error_time - First time an error happened, in seconds since the epoch. * - 0x19C - - \_\_le32 - - s\_first\_error\_ino + - __le32 + - s_first_error_ino - inode involved in first error. * - 0x1A0 - - \_\_le64 - - s\_first\_error\_block + - __le64 + - s_first_error_block - Number of block involved of first error. * - 0x1A8 - - \_\_u8 - - s\_first\_error\_func[32] + - __u8 + - s_first_error_func[32] - Name of function where the error happened. * - 0x1C8 - - \_\_le32 - - s\_first\_error\_line + - __le32 + - s_first_error_line - Line number where error happened. * - 0x1CC - - \_\_le32 - - s\_last\_error\_time + - __le32 + - s_last_error_time - Time of most recent error, in seconds since the epoch. * - 0x1D0 - - \_\_le32 - - s\_last\_error\_ino + - __le32 + - s_last_error_ino - inode involved in most recent error. * - 0x1D4 - - \_\_le32 - - s\_last\_error\_line + - __le32 + - s_last_error_line - Line number where most recent error happened. * - 0x1D8 - - \_\_le64 - - s\_last\_error\_block + - __le64 + - s_last_error_block - Number of block involved in most recent error. * - 0x1E0 - - \_\_u8 - - s\_last\_error\_func[32] + - __u8 + - s_last_error_func[32] - Name of function where the most recent error happened. * - 0x200 - - \_\_u8 - - s\_mount\_opts[64] + - __u8 + - s_mount_opts[64] - ASCIIZ string of mount options. * - 0x240 - - \_\_le32 - - s\_usr\_quota\_inum + - __le32 + - s_usr_quota_inum - Inode number of user `quota `__ file. * - 0x244 - - \_\_le32 - - s\_grp\_quota\_inum + - __le32 + - s_grp_quota_inum - Inode number of group `quota `__ file. * - 0x248 - - \_\_le32 - - s\_overhead\_blocks + - __le32 + - s_overhead_blocks - Overhead blocks/clusters in fs. (Huh? This field is always zero, which means that the kernel calculates it dynamically.) * - 0x24C - - \_\_le32 - - s\_backup\_bgs[2] - - Block groups containing superblock backups (if sparse\_super2) + - __le32 + - s_backup_bgs[2] + - Block groups containing superblock backups (if sparse_super2) * - 0x254 - - \_\_u8 - - s\_encrypt\_algos[4] + - __u8 + - s_encrypt_algos[4] - Encryption algorithms in use. There can be up to four algorithms in use at any time; valid algorithm codes are given in the super_encrypt_ table below. * - 0x258 - - \_\_u8 - - s\_encrypt\_pw\_salt[16] + - __u8 + - s_encrypt_pw_salt[16] - Salt for the string2key algorithm for encryption. * - 0x268 - - \_\_le32 - - s\_lpf\_ino + - __le32 + - s_lpf_ino - Inode number of lost+found * - 0x26C - - \_\_le32 - - s\_prj\_quota\_inum + - __le32 + - s_prj_quota_inum - Inode that tracks project quotas. * - 0x270 - - \_\_le32 - - s\_checksum\_seed - - Checksum seed used for metadata\_csum calculations. This value is - crc32c(~0, $orig\_fs\_uuid). + - __le32 + - s_checksum_seed + - Checksum seed used for metadata_csum calculations. This value is + crc32c(~0, $orig_fs_uuid). * - 0x274 - - \_\_u8 - - s\_wtime_hi + - __u8 + - s_wtime_hi - Upper 8 bits of the s_wtime field. * - 0x275 - - \_\_u8 - - s\_mtime_hi + - __u8 + - s_mtime_hi - Upper 8 bits of the s_mtime field. * - 0x276 - - \_\_u8 - - s\_mkfs_time_hi + - __u8 + - s_mkfs_time_hi - Upper 8 bits of the s_mkfs_time field. * - 0x277 - - \_\_u8 - - s\_lastcheck_hi + - __u8 + - s_lastcheck_hi - Upper 8 bits of the s_lastcheck_hi field. * - 0x278 - - \_\_u8 - - s\_first_error_time_hi + - __u8 + - s_first_error_time_hi - Upper 8 bits of the s_first_error_time_hi field. * - 0x279 - - \_\_u8 - - s\_last_error_time_hi + - __u8 + - s_last_error_time_hi - Upper 8 bits of the s_last_error_time_hi field. * - 0x27A - - \_\_u8 - - s\_pad[2] + - __u8 + - s_pad[2] - Zero padding. * - 0x27C - - \_\_le16 - - s\_encoding + - __le16 + - s_encoding - Filename charset encoding. * - 0x27E - - \_\_le16 - - s\_encoding_flags + - __le16 + - s_encoding_flags - Filename charset encoding flags. * - 0x280 - - \_\_le32 - - s\_orphan\_file\_inum + - __le32 + - s_orphan_file_inum - Orphan file inode number. * - 0x284 - - \_\_le32 - - s\_reserved[94] + - __le32 + - s_reserved[94] - Padding to the end of the block. * - 0x3FC - - \_\_le32 - - s\_checksum + - __le32 + - s_checksum - Superblock checksum. .. _super_state: @@ -574,44 +574,44 @@ following: * - Value - Description * - 0x1 - - Directory preallocation (COMPAT\_DIR\_PREALLOC). + - Directory preallocation (COMPAT_DIR_PREALLOC). * - 0x2 - “imagic inodes”. Not clear from the code what this does - (COMPAT\_IMAGIC\_INODES). + (COMPAT_IMAGIC_INODES). * - 0x4 - - Has a journal (COMPAT\_HAS\_JOURNAL). + - Has a journal (COMPAT_HAS_JOURNAL). * - 0x8 - - Supports extended attributes (COMPAT\_EXT\_ATTR). + - Supports extended attributes (COMPAT_EXT_ATTR). * - 0x10 - Has reserved GDT blocks for filesystem expansion - (COMPAT\_RESIZE\_INODE). Requires RO\_COMPAT\_SPARSE\_SUPER. + (COMPAT_RESIZE_INODE). Requires RO_COMPAT_SPARSE_SUPER. * - 0x20 - - Has directory indices (COMPAT\_DIR\_INDEX). + - Has directory indices (COMPAT_DIR_INDEX). * - 0x40 - “Lazy BG”. Not in Linux kernel, seems to have been for uninitialized - block groups? (COMPAT\_LAZY\_BG) + block groups? (COMPAT_LAZY_BG) * - 0x80 - - “Exclude inode”. Not used. (COMPAT\_EXCLUDE\_INODE). + - “Exclude inode”. Not used. (COMPAT_EXCLUDE_INODE). * - 0x100 - “Exclude bitmap”. Seems to be used to indicate the presence of snapshot-related exclude bitmaps? Not defined in kernel or used in - e2fsprogs (COMPAT\_EXCLUDE\_BITMAP). + e2fsprogs (COMPAT_EXCLUDE_BITMAP). * - 0x200 - - Sparse Super Block, v2. If this flag is set, the SB field s\_backup\_bgs + - Sparse Super Block, v2. If this flag is set, the SB field s_backup_bgs points to the two block groups that contain backup superblocks - (COMPAT\_SPARSE\_SUPER2). + (COMPAT_SPARSE_SUPER2). * - 0x400 - Fast commits supported. Although fast commits blocks are backward incompatible, fast commit blocks are not always present in the journal. If fast commit blocks are present in the journal, JBD2 incompat feature - (JBD2\_FEATURE\_INCOMPAT\_FAST\_COMMIT) gets - set (COMPAT\_FAST\_COMMIT). + (JBD2_FEATURE_INCOMPAT_FAST_COMMIT) gets + set (COMPAT_FAST_COMMIT). * - 0x1000 - Orphan file allocated. This is the special file for more efficient tracking of unlinked but still open inodes. When there may be any entries in the file, we additionally set proper rocompat feature - (RO\_COMPAT\_ORPHAN\_PRESENT). + (RO_COMPAT_ORPHAN_PRESENT). .. _super_incompat: @@ -625,45 +625,45 @@ following: * - Value - Description * - 0x1 - - Compression (INCOMPAT\_COMPRESSION). + - Compression (INCOMPAT_COMPRESSION). * - 0x2 - - Directory entries record the file type. See ext4\_dir\_entry\_2 below - (INCOMPAT\_FILETYPE). + - Directory entries record the file type. See ext4_dir_entry_2 below + (INCOMPAT_FILETYPE). * - 0x4 - - Filesystem needs recovery (INCOMPAT\_RECOVER). + - Filesystem needs recovery (INCOMPAT_RECOVER). * - 0x8 - - Filesystem has a separate journal device (INCOMPAT\_JOURNAL\_DEV). + - Filesystem has a separate journal device (INCOMPAT_JOURNAL_DEV). * - 0x10 - Meta block groups. See the earlier discussion of this feature - (INCOMPAT\_META\_BG). + (INCOMPAT_META_BG). * - 0x40 - - Files in this filesystem use extents (INCOMPAT\_EXTENTS). + - Files in this filesystem use extents (INCOMPAT_EXTENTS). * - 0x80 - - Enable a filesystem size of 2^64 blocks (INCOMPAT\_64BIT). + - Enable a filesystem size of 2^64 blocks (INCOMPAT_64BIT). * - 0x100 - - Multiple mount protection (INCOMPAT\_MMP). + - Multiple mount protection (INCOMPAT_MMP). * - 0x200 - Flexible block groups. See the earlier discussion of this feature - (INCOMPAT\_FLEX\_BG). + (INCOMPAT_FLEX_BG). * - 0x400 - Inodes can be used to store large extended attribute values - (INCOMPAT\_EA\_INODE). + (INCOMPAT_EA_INODE). * - 0x1000 - - Data in directory entry (INCOMPAT\_DIRDATA). (Not implemented?) + - Data in directory entry (INCOMPAT_DIRDATA). (Not implemented?) * - 0x2000 - Metadata checksum seed is stored in the superblock. This feature enables - the administrator to change the UUID of a metadata\_csum filesystem + the administrator to change the UUID of a metadata_csum filesystem while the filesystem is mounted; without it, the checksum definition - requires all metadata blocks to be rewritten (INCOMPAT\_CSUM\_SEED). + requires all metadata blocks to be rewritten (INCOMPAT_CSUM_SEED). * - 0x4000 - - Large directory >2GB or 3-level htree (INCOMPAT\_LARGEDIR). Prior to + - Large directory >2GB or 3-level htree (INCOMPAT_LARGEDIR). Prior to this feature, directories could not be larger than 4GiB and could not have an htree more than 2 levels deep. If this feature is enabled, directories can be larger than 4GiB and have a maximum htree depth of 3. * - 0x8000 - - Data in inode (INCOMPAT\_INLINE\_DATA). + - Data in inode (INCOMPAT_INLINE_DATA). * - 0x10000 - - Encrypted inodes are present on the filesystem. (INCOMPAT\_ENCRYPT). + - Encrypted inodes are present on the filesystem. (INCOMPAT_ENCRYPT). .. _super_rocompat: @@ -678,54 +678,54 @@ the following: - Description * - 0x1 - Sparse superblocks. See the earlier discussion of this feature - (RO\_COMPAT\_SPARSE\_SUPER). + (RO_COMPAT_SPARSE_SUPER). * - 0x2 - This filesystem has been used to store a file greater than 2GiB - (RO\_COMPAT\_LARGE\_FILE). + (RO_COMPAT_LARGE_FILE). * - 0x4 - - Not used in kernel or e2fsprogs (RO\_COMPAT\_BTREE\_DIR). + - Not used in kernel or e2fsprogs (RO_COMPAT_BTREE_DIR). * - 0x8 - This filesystem has files whose sizes are represented in units of logical blocks, not 512-byte sectors. This implies a very large file - indeed! (RO\_COMPAT\_HUGE\_FILE) + indeed! (RO_COMPAT_HUGE_FILE) * - 0x10 - Group descriptors have checksums. In addition to detecting corruption, this is useful for lazy formatting with uninitialized groups - (RO\_COMPAT\_GDT\_CSUM). + (RO_COMPAT_GDT_CSUM). * - 0x20 - Indicates that the old ext3 32,000 subdirectory limit no longer applies - (RO\_COMPAT\_DIR\_NLINK). A directory's i\_links\_count will be set to 1 + (RO_COMPAT_DIR_NLINK). A directory's i_links_count will be set to 1 if it is incremented past 64,999. * - 0x40 - Indicates that large inodes exist on this filesystem - (RO\_COMPAT\_EXTRA\_ISIZE). + (RO_COMPAT_EXTRA_ISIZE). * - 0x80 - - This filesystem has a snapshot (RO\_COMPAT\_HAS\_SNAPSHOT). + - This filesystem has a snapshot (RO_COMPAT_HAS_SNAPSHOT). * - 0x100 - - `Quota `__ (RO\_COMPAT\_QUOTA). + - `Quota `__ (RO_COMPAT_QUOTA). * - 0x200 - This filesystem supports “bigalloc”, which means that file extents are tracked in units of clusters (of blocks) instead of blocks - (RO\_COMPAT\_BIGALLOC). + (RO_COMPAT_BIGALLOC). * - 0x400 - This filesystem supports metadata checksumming. - (RO\_COMPAT\_METADATA\_CSUM; implies RO\_COMPAT\_GDT\_CSUM, though - GDT\_CSUM must not be set) + (RO_COMPAT_METADATA_CSUM; implies RO_COMPAT_GDT_CSUM, though + GDT_CSUM must not be set) * - 0x800 - Filesystem supports replicas. This feature is neither in the kernel nor - e2fsprogs. (RO\_COMPAT\_REPLICA) + e2fsprogs. (RO_COMPAT_REPLICA) * - 0x1000 - Read-only filesystem image; the kernel will not mount this image read-write and most tools will refuse to write to the image. - (RO\_COMPAT\_READONLY) + (RO_COMPAT_READONLY) * - 0x2000 - - Filesystem tracks project quotas. (RO\_COMPAT\_PROJECT) + - Filesystem tracks project quotas. (RO_COMPAT_PROJECT) * - 0x8000 - - Verity inodes may be present on the filesystem. (RO\_COMPAT\_VERITY) + - Verity inodes may be present on the filesystem. (RO_COMPAT_VERITY) * - 0x10000 - Indicates orphan file may have valid orphan entries and thus we need to clean them up when mounting the filesystem - (RO\_COMPAT\_ORPHAN\_PRESENT). + (RO_COMPAT_ORPHAN_PRESENT). .. _super_def_hash: @@ -761,36 +761,36 @@ The ``s_default_mount_opts`` field is any combination of the following: * - Value - Description * - 0x0001 - - Print debugging info upon (re)mount. (EXT4\_DEFM\_DEBUG) + - Print debugging info upon (re)mount. (EXT4_DEFM_DEBUG) * - 0x0002 - New files take the gid of the containing directory (instead of the fsgid - of the current process). (EXT4\_DEFM\_BSDGROUPS) + of the current process). (EXT4_DEFM_BSDGROUPS) * - 0x0004 - - Support userspace-provided extended attributes. (EXT4\_DEFM\_XATTR\_USER) + - Support userspace-provided extended attributes. (EXT4_DEFM_XATTR_USER) * - 0x0008 - - Support POSIX access control lists (ACLs). (EXT4\_DEFM\_ACL) + - Support POSIX access control lists (ACLs). (EXT4_DEFM_ACL) * - 0x0010 - - Do not support 32-bit UIDs. (EXT4\_DEFM\_UID16) + - Do not support 32-bit UIDs. (EXT4_DEFM_UID16) * - 0x0020 - All data and metadata are commited to the journal. - (EXT4\_DEFM\_JMODE\_DATA) + (EXT4_DEFM_JMODE_DATA) * - 0x0040 - All data are flushed to the disk before metadata are committed to the - journal. (EXT4\_DEFM\_JMODE\_ORDERED) + journal. (EXT4_DEFM_JMODE_ORDERED) * - 0x0060 - Data ordering is not preserved; data may be written after the metadata - has been written. (EXT4\_DEFM\_JMODE\_WBACK) + has been written. (EXT4_DEFM_JMODE_WBACK) * - 0x0100 - - Disable write flushes. (EXT4\_DEFM\_NOBARRIER) + - Disable write flushes. (EXT4_DEFM_NOBARRIER) * - 0x0200 - Track which blocks in a filesystem are metadata and therefore should not be used as data blocks. This option will be enabled by default on 3.18, - hopefully. (EXT4\_DEFM\_BLOCK\_VALIDITY) + hopefully. (EXT4_DEFM_BLOCK_VALIDITY) * - 0x0400 - Enable DISCARD support, where the storage device is told about blocks - becoming unused. (EXT4\_DEFM\_DISCARD) + becoming unused. (EXT4_DEFM_DISCARD) * - 0x0800 - - Disable delayed allocation. (EXT4\_DEFM\_NODELALLOC) + - Disable delayed allocation. (EXT4_DEFM_NODELALLOC) .. _super_flags: @@ -820,12 +820,12 @@ The ``s_encrypt_algos`` list can contain any of the following: * - Value - Description * - 0 - - Invalid algorithm (ENCRYPTION\_MODE\_INVALID). + - Invalid algorithm (ENCRYPTION_MODE_INVALID). * - 1 - - 256-bit AES in XTS mode (ENCRYPTION\_MODE\_AES\_256\_XTS). + - 256-bit AES in XTS mode (ENCRYPTION_MODE_AES_256_XTS). * - 2 - - 256-bit AES in GCM mode (ENCRYPTION\_MODE\_AES\_256\_GCM). + - 256-bit AES in GCM mode (ENCRYPTION_MODE_AES_256_GCM). * - 3 - - 256-bit AES in CBC mode (ENCRYPTION\_MODE\_AES\_256\_CBC). + - 256-bit AES in CBC mode (ENCRYPTION_MODE_AES_256_CBC). Total size of the superblock is 1024 bytes. diff --git a/Documentation/filesystems/netfs_library.rst b/Documentation/filesystems/netfs_library.rst index a80a59941d2fe..4d19b19bcc086 100644 --- a/Documentation/filesystems/netfs_library.rst +++ b/Documentation/filesystems/netfs_library.rst @@ -37,30 +37,31 @@ The network filesystem helper library needs a place to store a bit of state for its use on each netfs inode it is helping to manage. To this end, a context structure is defined:: - struct netfs_i_context { + struct netfs_inode { + struct inode inode; const struct netfs_request_ops *ops; - struct fscache_cookie *cache; + struct fscache_cookie *cache; }; -A network filesystem that wants to use netfs lib must place one of these -directly after the VFS ``struct inode`` it allocates, usually as part of its -own struct. This can be done in a way similar to the following:: +A network filesystem that wants to use netfs lib must place one of these in its +inode wrapper struct instead of the VFS ``struct inode``. This can be done in +a way similar to the following:: struct my_inode { - struct { - /* These must be contiguous */ - struct inode vfs_inode; - struct netfs_i_context netfs_ctx; - }; + struct netfs_inode netfs; /* Netfslib context and vfs inode */ ... }; -This allows netfslib to find its state by simple offset from the inode pointer, -thereby allowing the netfslib helper functions to be pointed to directly by the -VFS/VM operation tables. +This allows netfslib to find its state by using ``container_of()`` from the +inode pointer, thereby allowing the netfslib helper functions to be pointed to +directly by the VFS/VM operation tables. The structure contains the following fields: + * ``inode`` + + The VFS inode structure. + * ``ops`` The set of operations provided by the network filesystem to netfslib. @@ -78,19 +79,17 @@ To help deal with the per-inode context, a number helper functions are provided. Firstly, a function to perform basic initialisation on a context and set the operations table pointer:: - void netfs_i_context_init(struct inode *inode, - const struct netfs_request_ops *ops); + void netfs_inode_init(struct netfs_inode *ctx, + const struct netfs_request_ops *ops); -then two functions to cast between the VFS inode structure and the netfs -context:: +then a function to cast from the VFS inode structure to the netfs context:: - struct netfs_i_context *netfs_i_context(struct inode *inode); - struct inode *netfs_inode(struct netfs_i_context *ctx); + struct netfs_inode *netfs_node(struct inode *inode); and finally, a function to get the cache cookie pointer from the context attached to an inode (or NULL if fscache is disabled):: - struct fscache_cookie *netfs_i_cookie(struct inode *inode); + struct fscache_cookie *netfs_i_cookie(struct netfs_inode *ctx); Buffered Read Helpers @@ -137,8 +136,9 @@ Three read helpers are provided:: void netfs_readahead(struct readahead_control *ractl); int netfs_read_folio(struct file *file, - struct folio *folio); - int netfs_write_begin(struct file *file, + struct folio *folio); + int netfs_write_begin(struct netfs_inode *ctx, + struct file *file, struct address_space *mapping, loff_t pos, unsigned int len, @@ -158,9 +158,10 @@ The helpers manage the read request, calling back into the network filesystem through the suppplied table of operations. Waits will be performed as necessary before returning for helpers that are meant to be synchronous. -If an error occurs and netfs_priv is non-NULL, ops->cleanup() will be called to -deal with it. If some parts of the request are in progress when an error -occurs, the request will get partially completed if sufficient data is read. +If an error occurs, the ->free_request() will be called to clean up the +netfs_io_request struct allocated. If some parts of the request are in +progress when an error occurs, the request will get partially completed if +sufficient data is read. Additionally, there is:: @@ -208,8 +209,7 @@ The above fields are the ones the netfs can use. They are: * ``netfs_priv`` The network filesystem's private data. The value for this can be passed in - to the helper functions or set during the request. The ->cleanup() op will - be called if this is non-NULL at the end. + to the helper functions or set during the request. * ``start`` * ``len`` @@ -294,6 +294,7 @@ through which it can issue requests and negotiate:: struct netfs_request_ops { void (*init_request)(struct netfs_io_request *rreq, struct file *file); + void (*free_request)(struct netfs_io_request *rreq); int (*begin_cache_operation)(struct netfs_io_request *rreq); void (*expand_readahead)(struct netfs_io_request *rreq); bool (*clamp_length)(struct netfs_io_subrequest *subreq); @@ -302,7 +303,6 @@ through which it can issue requests and negotiate:: int (*check_write_begin)(struct file *file, loff_t pos, unsigned len, struct folio *folio, void **_fsdata); void (*done)(struct netfs_io_request *rreq); - void (*cleanup)(struct address_space *mapping, void *netfs_priv); }; The operations are as follows: @@ -310,7 +310,12 @@ The operations are as follows: * ``init_request()`` [Optional] This is called to initialise the request structure. It is given - the file for reference and can modify the ->netfs_priv value. + the file for reference. + + * ``free_request()`` + + [Optional] This is called as the request is being deallocated so that the + filesystem can clean up any state it has attached there. * ``begin_cache_operation()`` @@ -384,11 +389,6 @@ The operations are as follows: [Optional] This is called after the folios in the request have all been unlocked (and marked uptodate if applicable). - * ``cleanup`` - - [Optional] This is called as the request is being deallocated so that the - filesystem can clean up ->netfs_priv. - Read Helper Procedure diff --git a/Documentation/index.rst b/Documentation/index.rst index 8f9be0e658b4d..67036a05b771f 100644 --- a/Documentation/index.rst +++ b/Documentation/index.rst @@ -137,7 +137,6 @@ needed). scheduler/index mhi/index peci/index - hte/index Architecture-agnostic documentation ----------------------------------- diff --git a/Documentation/kbuild/llvm.rst b/Documentation/kbuild/llvm.rst index b854bb4131647..6b2bac8e9ce08 100644 --- a/Documentation/kbuild/llvm.rst +++ b/Documentation/kbuild/llvm.rst @@ -129,18 +129,24 @@ yet. Bug reports are always welcome at the issue tracker below! * - arm64 - Supported - ``LLVM=1`` + * - hexagon + - Maintained + - ``LLVM=1`` * - mips - Maintained - - ``CC=clang`` + - ``LLVM=1`` * - powerpc - Maintained - ``CC=clang`` * - riscv - Maintained - - ``CC=clang`` + - ``LLVM=1`` * - s390 - Maintained - ``CC=clang`` + * - um (User Mode) + - Maintained + - ``LLVM=1`` * - x86 - Supported - ``LLVM=1`` diff --git a/Documentation/loongarch/introduction.rst b/Documentation/loongarch/introduction.rst index 2bf40ad370dfa..216b3f390e806 100644 --- a/Documentation/loongarch/introduction.rst +++ b/Documentation/loongarch/introduction.rst @@ -45,10 +45,12 @@ Name Alias Usage Preserved ``$r23``-``$r31`` ``$s0``-``$s8`` Static registers Yes ================= =============== =================== ============ -Note: The register ``$r21`` is reserved in the ELF psABI, but used by the Linux -kernel for storing the percpu base address. It normally has no ABI name, but is -called ``$u0`` in the kernel. You may also see ``$v0`` or ``$v1`` in some old code, -however they are deprecated aliases of ``$a0`` and ``$a1`` respectively. +.. Note:: + The register ``$r21`` is reserved in the ELF psABI, but used by the Linux + kernel for storing the percpu base address. It normally has no ABI name, + but is called ``$u0`` in the kernel. You may also see ``$v0`` or ``$v1`` + in some old code,however they are deprecated aliases of ``$a0`` and ``$a1`` + respectively. FPRs ---- @@ -69,8 +71,9 @@ Name Alias Usage Preserved ``$f24``-``$f31`` ``$fs0``-``$fs7`` Static registers Yes ================= ================== =================== ============ -Note: You may see ``$fv0`` or ``$fv1`` in some old code, however they are deprecated -aliases of ``$fa0`` and ``$fa1`` respectively. +.. Note:: + You may see ``$fv0`` or ``$fv1`` in some old code, however they are + deprecated aliases of ``$fa0`` and ``$fa1`` respectively. VRs ---- diff --git a/Documentation/loongarch/irq-chip-model.rst b/Documentation/loongarch/irq-chip-model.rst index 8d88f7ab2e5e9..7988f41923639 100644 --- a/Documentation/loongarch/irq-chip-model.rst +++ b/Documentation/loongarch/irq-chip-model.rst @@ -145,12 +145,16 @@ Documentation of Loongson's LS7A chipset: https://github.com/loongson/LoongArch-Documentation/releases/latest/download/Loongson-7A1000-usermanual-2.00-EN.pdf (in English) -Note: CPUINTC is CSR.ECFG/CSR.ESTAT and its interrupt controller described -in Section 7.4 of "LoongArch Reference Manual, Vol 1"; LIOINTC is "Legacy I/O -Interrupts" described in Section 11.1 of "Loongson 3A5000 Processor Reference -Manual"; EIOINTC is "Extended I/O Interrupts" described in Section 11.2 of -"Loongson 3A5000 Processor Reference Manual"; HTVECINTC is "HyperTransport -Interrupts" described in Section 14.3 of "Loongson 3A5000 Processor Reference -Manual"; PCH-PIC/PCH-MSI is "Interrupt Controller" described in Section 5 of -"Loongson 7A1000 Bridge User Manual"; PCH-LPC is "LPC Interrupts" described in -Section 24.3 of "Loongson 7A1000 Bridge User Manual". +.. Note:: + - CPUINTC is CSR.ECFG/CSR.ESTAT and its interrupt controller described + in Section 7.4 of "LoongArch Reference Manual, Vol 1"; + - LIOINTC is "Legacy I/OInterrupts" described in Section 11.1 of + "Loongson 3A5000 Processor Reference Manual"; + - EIOINTC is "Extended I/O Interrupts" described in Section 11.2 of + "Loongson 3A5000 Processor Reference Manual"; + - HTVECINTC is "HyperTransport Interrupts" described in Section 14.3 of + "Loongson 3A5000 Processor Reference Manual"; + - PCH-PIC/PCH-MSI is "Interrupt Controller" described in Section 5 of + "Loongson 7A1000 Bridge User Manual"; + - PCH-LPC is "LPC Interrupts" described in Section 24.3 of + "Loongson 7A1000 Bridge User Manual". diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index 04216564a03cb..9f41961d11d52 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -2925,6 +2925,43 @@ plpmtud_probe_interval - INTEGER Default: 0 +reconf_enable - BOOLEAN + Enable or disable extension of Stream Reconfiguration functionality + specified in RFC6525. This extension provides the ability to "reset" + a stream, and it includes the Parameters of "Outgoing/Incoming SSN + Reset", "SSN/TSN Reset" and "Add Outgoing/Incoming Streams". + + - 1: Enable extension. + - 0: Disable extension. + + Default: 0 + +intl_enable - BOOLEAN + Enable or disable extension of User Message Interleaving functionality + specified in RFC8260. This extension allows the interleaving of user + messages sent on different streams. With this feature enabled, I-DATA + chunk will replace DATA chunk to carry user messages if also supported + by the peer. Note that to use this feature, one needs to set this option + to 1 and also needs to set socket options SCTP_FRAGMENT_INTERLEAVE to 2 + and SCTP_INTERLEAVING_SUPPORTED to 1. + + - 1: Enable extension. + - 0: Disable extension. + + Default: 0 + +ecn_enable - BOOLEAN + Control use of Explicit Congestion Notification (ECN) by SCTP. + Like in TCP, ECN is used only when both ends of the SCTP connection + indicate support for it. This feature is useful in avoiding losses + due to congestion by allowing supporting routers to signal congestion + before having to drop packets. + + 1: Enable ecn. + 0: Disable ecn. + + Default: 1 + ``/proc/sys/net/core/*`` ======================== diff --git a/Documentation/networking/phy.rst b/Documentation/networking/phy.rst index d43da709bf40a..704f31da51672 100644 --- a/Documentation/networking/phy.rst +++ b/Documentation/networking/phy.rst @@ -104,7 +104,7 @@ Whenever possible, use the PHY side RGMII delay for these reasons: * PHY device drivers in PHYLIB being reusable by nature, being able to configure correctly a specified delay enables more designs with similar delay - requirements to be operate correctly + requirements to be operated correctly For cases where the PHY is not capable of providing this delay, but the Ethernet MAC driver is capable of doing so, the correct phy_interface_t value diff --git a/Documentation/process/changes.rst b/Documentation/process/changes.rst index 34415ae1af1b5..19c286c23786f 100644 --- a/Documentation/process/changes.rst +++ b/Documentation/process/changes.rst @@ -32,6 +32,7 @@ you probably needn't concern yourself with pcmciautils. GNU C 5.1 gcc --version Clang/LLVM (optional) 11.0.0 clang --version GNU make 3.81 make --version +bash 4.2 bash --version binutils 2.23 ld -v flex 2.5.35 flex --version bison 2.0 bison --version @@ -84,6 +85,12 @@ Make You will need GNU make 3.81 or later to build the kernel. +Bash +---- + +Some bash scripts are used for the kernel build. +Bash 4.2 or newer is needed. + Binutils -------- @@ -362,6 +369,11 @@ Make - +Bash +---- + +- + Binutils -------- diff --git a/Documentation/translations/zh_CN/loongarch/introduction.rst b/Documentation/translations/zh_CN/loongarch/introduction.rst index e31a1a928c484..11686ee0caeb1 100644 --- a/Documentation/translations/zh_CN/loongarch/introduction.rst +++ b/Documentation/translations/zh_CN/loongarch/introduction.rst @@ -46,10 +46,11 @@ LA64中每个寄存器为64位宽。 ``$r0`` 的内容总是固定为0，而其 ``$r23``-``$r31`` ``$s0``-``$s8`` 静态寄存器 是 ================= =============== =================== ========== -注意：``$r21``寄存器在ELF psABI中保留未使用，但是在Linux内核用于保存每CPU -变量基地址。该寄存器没有ABI命名，不过在内核中称为``$u0``。在一些遗留代码 -中有时可能见到``$v0``和``$v1``，它们是``$a0``和``$a1``的别名，属于已经废弃 -的用法。 +.. note:: + 注意： ``$r21`` 寄存器在ELF psABI中保留未使用，但是在Linux内核用于保 + 存每CPU变量基地址。该寄存器没有ABI命名，不过在内核中称为 ``$u0`` 。在 + 一些遗留代码中有时可能见到 ``$v0`` 和 ``$v1`` ，它们是 ``$a0`` 和 + ``$a1`` 的别名，属于已经废弃的用法。 浮点寄存器 ---------- @@ -68,8 +69,9 @@ LA64中每个寄存器为64位宽。 ``$r0`` 的内容总是固定为0，而其 ``$f24``-``$f31`` ``$fs0``-``$fs7`` 静态寄存器 是 ================= ================== =================== ========== -注意：在一些遗留代码中有时可能见到 ``$v0`` 和 ``$v1`` ，它们是 ``$a0`` -和 ``$a1`` 的别名，属于已经废弃的用法。 +.. note:: + 注意：在一些遗留代码中有时可能见到 ``$v0`` 和 ``$v1`` ，它们是 + ``$a0`` 和 ``$a1`` 的别名，属于已经废弃的用法。 向量寄存器 diff --git a/Documentation/translations/zh_CN/loongarch/irq-chip-model.rst b/Documentation/translations/zh_CN/loongarch/irq-chip-model.rst index 2a4c3ad38be4a..fb5d23b49ed55 100644 --- a/Documentation/translations/zh_CN/loongarch/irq-chip-model.rst +++ b/Documentation/translations/zh_CN/loongarch/irq-chip-model.rst @@ -147,9 +147,11 @@ PCH-LPC:: https://github.com/loongson/LoongArch-Documentation/releases/latest/download/Loongson-7A1000-usermanual-2.00-EN.pdf (英文版) -注：CPUINTC即《龙芯架构参考手册卷一》第7.4节所描述的CSR.ECFG/CSR.ESTAT寄存器及其中断 -控制逻辑；LIOINTC即《龙芯3A5000处理器使用手册》第11.1节所描述的“传统I/O中断”；EIOINTC -即《龙芯3A5000处理器使用手册》第11.2节所描述的“扩展I/O中断”；HTVECINTC即《龙芯3A5000 -处理器使用手册》第14.3节所描述的“HyperTransport中断”；PCH-PIC/PCH-MSI即《龙芯7A1000桥 -片用户手册》第5章所描述的“中断控制器”；PCH-LPC即《龙芯7A1000桥片用户手册》第24.3节所 -描述的“LPC中断”。 +.. note:: + - CPUINTC：即《龙芯架构参考手册卷一》第7.4节所描述的CSR.ECFG/CSR.ESTAT寄存器及其 + 中断控制逻辑； + - LIOINTC：即《龙芯3A5000处理器使用手册》第11.1节所描述的“传统I/O中断”； + - EIOINTC：即《龙芯3A5000处理器使用手册》第11.2节所描述的“扩展I/O中断”； + - HTVECINTC：即《龙芯3A5000处理器使用手册》第14.3节所描述的“HyperTransport中断”； + - PCH-PIC/PCH-MSI：即《龙芯7A1000桥片用户手册》第5章所描述的“中断控制器”； + - PCH-LPC：即《龙芯7A1000桥片用户手册》第24.3节所描述的“LPC中断”。 diff --git a/Documentation/usb/usbmon.rst b/Documentation/usb/usbmon.rst index b0bd510807993..6d5ec1e62d093 100644 --- a/Documentation/usb/usbmon.rst +++ b/Documentation/usb/usbmon.rst @@ -42,7 +42,7 @@ if usbmon is built into the kernel:: # modprobe usbmon # -Verify that bus sockets are present: +Verify that bus sockets are present:: # ls /sys/kernel/debug/usb/usbmon 0s 0u 1s 1t 1u 2s 2t 2u 3s 3t 3u 4s 4t 4u diff --git a/Documentation/vm/hwpoison.rst b/Documentation/vm/hwpoison.rst index c742de1769d18..b9d5253c13057 100644 --- a/Documentation/vm/hwpoison.rst +++ b/Documentation/vm/hwpoison.rst @@ -120,7 +120,8 @@ Testing unpoison-pfn Software-unpoison page at PFN echoed into this file. This way a page can be reused again. This only works for Linux - injected failures, not for real memory failures. + injected failures, not for real memory failures. Once any hardware + memory failure happens, this feature is disabled. Note these injection interfaces are not stable and might change between kernel versions diff --git a/MAINTAINERS b/MAINTAINERS index a6d3bd9d2a8d0..282b34eae7502 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -427,6 +427,7 @@ ACPI VIOT DRIVER M: Jean-Philippe Brucker L: linux-acpi@vger.kernel.org L: iommu@lists.linux-foundation.org +L: iommu@lists.linux.dev S: Maintained F: drivers/acpi/viot.c F: include/linux/acpi_viot.h @@ -960,6 +961,7 @@ AMD IOMMU (AMD-VI) M: Joerg Roedel R: Suravee Suthikulpanit L: iommu@lists.linux-foundation.org +L: iommu@lists.linux.dev S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu.git F: drivers/iommu/amd/ @@ -1507,7 +1509,7 @@ F: drivers/clocksource/arm_arch_timer.c ARM HDLCD DRM DRIVER M: Liviu Dudau S: Supported -F: Documentation/devicetree/bindings/display/arm,hdlcd.txt +F: Documentation/devicetree/bindings/display/arm,hdlcd.yaml F: drivers/gpu/drm/arm/hdlcd_* ARM INTEGRATOR, VERSATILE AND REALVIEW SUPPORT @@ -1542,7 +1544,7 @@ M: Mihail Atanassov L: Mali DP Maintainers S: Supported T: git git://anongit.freedesktop.org/drm/drm-misc -F: Documentation/devicetree/bindings/display/arm,komeda.txt +F: Documentation/devicetree/bindings/display/arm,komeda.yaml F: Documentation/gpu/komeda-kms.rst F: drivers/gpu/drm/arm/display/include/ F: drivers/gpu/drm/arm/display/komeda/ @@ -1564,7 +1566,7 @@ M: Brian Starkey L: Mali DP Maintainers S: Supported T: git git://anongit.freedesktop.org/drm/drm-misc -F: Documentation/devicetree/bindings/display/arm,malidp.txt +F: Documentation/devicetree/bindings/display/arm,malidp.yaml F: Documentation/gpu/afbc.rst F: drivers/gpu/drm/arm/ @@ -2009,7 +2011,7 @@ L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained T: git git://github.com/ulli-kroll/linux.git F: Documentation/devicetree/bindings/arm/gemini.yaml -F: Documentation/devicetree/bindings/net/cortina,gemini-ethernet.txt +F: Documentation/devicetree/bindings/net/cortina,gemini-ethernet.yaml F: Documentation/devicetree/bindings/pinctrl/cortina,gemini-pinctrl.txt F: Documentation/devicetree/bindings/rtc/faraday,ftrtc010.yaml F: arch/arm/boot/dts/gemini* @@ -2467,6 +2469,7 @@ ARM/NXP S32G ARCHITECTURE M: Chester Lin R: Andreas Färber R: Matthias Brugger +R: NXP S32 Linux Team L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained F: arch/arm64/boot/dts/freescale/s32g*.dts* @@ -3662,7 +3665,7 @@ BPF JIT for ARM M: Shubham Bansal L: netdev@vger.kernel.org L: bpf@vger.kernel.org -S: Maintained +S: Odd Fixes F: arch/arm/net/ BPF JIT for ARM64 @@ -3686,14 +3689,15 @@ BPF JIT for NFP NICs M: Jakub Kicinski L: netdev@vger.kernel.org L: bpf@vger.kernel.org -S: Supported +S: Odd Fixes F: drivers/net/ethernet/netronome/nfp/bpf/ BPF JIT for POWERPC (32-BIT AND 64-BIT) M: Naveen N. Rao +M: Michael Ellerman L: netdev@vger.kernel.org L: bpf@vger.kernel.org -S: Maintained +S: Supported F: arch/powerpc/net/ BPF JIT for RISC-V (32-bit) @@ -3719,7 +3723,7 @@ M: Heiko Carstens M: Vasily Gorbik L: netdev@vger.kernel.org L: bpf@vger.kernel.org -S: Maintained +S: Supported F: arch/s390/net/ X: arch/s390/net/pnet.c @@ -3727,14 +3731,14 @@ BPF JIT for SPARC (32-BIT AND 64-BIT) M: David S. Miller L: netdev@vger.kernel.org L: bpf@vger.kernel.org -S: Maintained +S: Odd Fixes F: arch/sparc/net/ BPF JIT for X86 32-BIT M: Wang YanQing L: netdev@vger.kernel.org L: bpf@vger.kernel.org -S: Maintained +S: Odd Fixes F: arch/x86/net/bpf_jit_comp32.c BPF JIT for X86 64-BIT @@ -3757,6 +3761,26 @@ F: include/linux/bpf_lsm.h F: kernel/bpf/bpf_lsm.c F: security/bpf/ +BPF L7 FRAMEWORK +M: John Fastabend +M: Jakub Sitnicki +L: netdev@vger.kernel.org +L: bpf@vger.kernel.org +S: Maintained +F: include/linux/skmsg.h +F: net/core/skmsg.c +F: net/core/sock_map.c +F: net/ipv4/tcp_bpf.c +F: net/ipv4/udp_bpf.c +F: net/unix/unix_bpf.c + +BPFTOOL +M: Quentin Monnet +L: bpf@vger.kernel.org +S: Maintained +F: kernel/bpf/disasm.* +F: tools/bpf/bpftool/ + BROADCOM B44 10/100 ETHERNET DRIVER M: Michael Chan L: netdev@vger.kernel.org @@ -3789,12 +3813,12 @@ N: bcmbca N: bcm[9]?47622 BROADCOM BCM2711/BCM2835 ARM ARCHITECTURE -M: Nicolas Saenz Julienne +M: Florian Fainelli R: Broadcom internal kernel review list L: linux-rpi-kernel@lists.infradead.org (moderated for non-subscribers) L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained -T: git git://git.kernel.org/pub/scm/linux/kernel/git/nsaenz/linux-rpi.git +T: git git://github.com/broadcom/stblinux.git F: Documentation/devicetree/bindings/pci/brcm,stb-pcie.yaml F: drivers/pci/controller/pcie-brcmstb.c F: drivers/staging/vc04_services @@ -5955,6 +5979,7 @@ M: Christoph Hellwig M: Marek Szyprowski R: Robin Murphy L: iommu@lists.linux-foundation.org +L: iommu@lists.linux.dev S: Supported W: http://git.infradead.org/users/hch/dma-mapping.git T: git git://git.infradead.org/users/hch/dma-mapping.git @@ -5967,6 +5992,7 @@ F: kernel/dma/ DMA MAPPING BENCHMARK M: Xiang Chen L: iommu@lists.linux-foundation.org +L: iommu@lists.linux.dev F: kernel/dma/map_benchmark.c F: tools/testing/selftests/dma/ @@ -6078,7 +6104,7 @@ M: Sakari Ailus L: linux-media@vger.kernel.org S: Maintained T: git git://linuxtv.org/media_tree.git -F: Documentation/devicetree/bindings/media/i2c/dongwoon,dw9807-vcm.txt +F: Documentation/devicetree/bindings/media/i2c/dongwoon,dw9807-vcm.yaml F: drivers/media/i2c/dw9807-vcm.c DOUBLETALK DRIVER @@ -7551,6 +7577,7 @@ F: drivers/gpu/drm/exynos/exynos_dp* EXYNOS SYSMMU (IOMMU) driver M: Marek Szyprowski L: iommu@lists.linux-foundation.org +L: iommu@lists.linux.dev S: Maintained F: drivers/iommu/exynos-iommu.c @@ -7647,6 +7674,7 @@ F: include/uapi/scsi/fc/ FILE LOCKING (flock() and fcntl()/lockf()) M: Jeff Layton +M: Chuck Lever L: linux-fsdevel@vger.kernel.org S: Maintained F: fs/fcntl.c @@ -8471,6 +8499,7 @@ F: Documentation/devicetree/bindings/gpio/ F: Documentation/driver-api/gpio/ F: drivers/gpio/ F: include/asm-generic/gpio.h +F: include/dt-bindings/gpio/ F: include/linux/gpio.h F: include/linux/gpio/ F: include/linux/of_gpio.h @@ -9081,7 +9110,7 @@ HTE SUBSYSTEM M: Dipen Patel S: Maintained F: Documentation/devicetree/bindings/timestamp/ -F: Documentation/hte/ +F: Documentation/driver-api/hte/ F: drivers/hte/ F: include/linux/hte.h @@ -9124,6 +9153,7 @@ F: drivers/media/platform/st/sti/hva HWPOISON MEMORY FAILURE HANDLING M: Naoya Horiguchi +R: Miaohe Lin L: linux-mm@kvack.org S: Maintained F: mm/hwpoison-inject.c @@ -9268,6 +9298,7 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/wsa/linux.git F: Documentation/devicetree/bindings/i2c/i2c.txt F: Documentation/i2c/ F: drivers/i2c/* +F: include/dt-bindings/i2c/i2c.h F: include/linux/i2c-dev.h F: include/linux/i2c-smbus.h F: include/linux/i2c.h @@ -9283,6 +9314,7 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/wsa/linux.git F: Documentation/devicetree/bindings/i2c/ F: drivers/i2c/algos/ F: drivers/i2c/busses/ +F: include/dt-bindings/i2c/ I2C-TAOS-EVM DRIVER M: Jean Delvare @@ -9967,6 +9999,7 @@ INTEL IOMMU (VT-d) M: David Woodhouse M: Lu Baolu L: iommu@lists.linux-foundation.org +L: iommu@lists.linux.dev S: Supported T: git git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu.git F: drivers/iommu/intel/ @@ -10346,6 +10379,7 @@ IOMMU DRIVERS M: Joerg Roedel M: Will Deacon L: iommu@lists.linux-foundation.org +L: iommu@lists.linux.dev S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu.git F: Documentation/devicetree/bindings/iommu/ @@ -10739,6 +10773,7 @@ W: http://kernelnewbies.org/KernelJanitors KERNEL NFSD, SUNRPC, AND LOCKD SERVERS M: Chuck Lever +M: Jeff Layton L: linux-nfs@vger.kernel.org S: Supported W: http://nfs.sourceforge.net/ @@ -10821,6 +10856,7 @@ M: Marc Zyngier R: James Morse R: Alexandru Elisei R: Suzuki K Poulose +R: Oliver Upton L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) L: kvmarm@lists.cs.columbia.edu (moderated for non-subscribers) S: Maintained @@ -10863,7 +10899,6 @@ F: arch/riscv/include/asm/kvm* F: arch/riscv/include/uapi/asm/kvm* F: arch/riscv/kvm/ F: tools/testing/selftests/kvm/*/riscv/ -F: tools/testing/selftests/kvm/riscv/ KERNEL VIRTUAL MACHINE for s390 (KVM/s390) M: Christian Borntraeger @@ -10888,28 +10923,51 @@ F: tools/testing/selftests/kvm/*/s390x/ F: tools/testing/selftests/kvm/s390x/ KERNEL VIRTUAL MACHINE FOR X86 (KVM/x86) +M: Sean Christopherson M: Paolo Bonzini -R: Sean Christopherson -R: Vitaly Kuznetsov -R: Wanpeng Li -R: Jim Mattson -R: Joerg Roedel L: kvm@vger.kernel.org S: Supported -W: http://www.linux-kvm.org T: git git://git.kernel.org/pub/scm/virt/kvm/kvm.git F: arch/x86/include/asm/kvm* -F: arch/x86/include/asm/pvclock-abi.h F: arch/x86/include/asm/svm.h F: arch/x86/include/asm/vmx*.h F: arch/x86/include/uapi/asm/kvm* F: arch/x86/include/uapi/asm/svm.h F: arch/x86/include/uapi/asm/vmx.h -F: arch/x86/kernel/kvm.c -F: arch/x86/kernel/kvmclock.c F: arch/x86/kvm/ F: arch/x86/kvm/*/ +KVM PARAVIRT (KVM/paravirt) +M: Paolo Bonzini +R: Wanpeng Li +R: Vitaly Kuznetsov +L: kvm@vger.kernel.org +S: Supported +T: git git://git.kernel.org/pub/scm/virt/kvm/kvm.git +F: arch/x86/kernel/kvm.c +F: arch/x86/kernel/kvmclock.c +F: arch/x86/include/asm/pvclock-abi.h +F: include/linux/kvm_para.h +F: include/uapi/linux/kvm_para.h +F: include/uapi/asm-generic/kvm_para.h +F: include/asm-generic/kvm_para.h +F: arch/um/include/asm/kvm_para.h +F: arch/x86/include/asm/kvm_para.h +F: arch/x86/include/uapi/asm/kvm_para.h + +KVM X86 HYPER-V (KVM/hyper-v) +M: Vitaly Kuznetsov +M: Sean Christopherson +M: Paolo Bonzini +L: kvm@vger.kernel.org +S: Supported +T: git git://git.kernel.org/pub/scm/virt/kvm/kvm.git +F: arch/x86/kvm/hyperv.* +F: arch/x86/kvm/kvm_onhyperv.* +F: arch/x86/kvm/svm/hyperv.* +F: arch/x86/kvm/svm/svm_onhyperv.* +F: arch/x86/kvm/vmx/evmcs.* + KERNFS M: Greg Kroah-Hartman M: Tejun Heo @@ -11088,20 +11146,6 @@ S: Maintained F: include/net/l3mdev.h F: net/l3mdev -L7 BPF FRAMEWORK -M: John Fastabend -M: Daniel Borkmann -M: Jakub Sitnicki -L: netdev@vger.kernel.org -L: bpf@vger.kernel.org -S: Maintained -F: include/linux/skmsg.h -F: net/core/skmsg.c -F: net/core/sock_map.c -F: net/ipv4/tcp_bpf.c -F: net/ipv4/udp_bpf.c -F: net/unix/unix_bpf.c - LANDLOCK SECURITY MODULE M: Mickaël Salaün L: linux-security-module@vger.kernel.org @@ -11257,6 +11301,7 @@ M: Damien Le Moal L: linux-ide@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/dlemoal/libata.git +F: Documentation/ABI/testing/sysfs-ata F: Documentation/devicetree/bindings/ata/ F: drivers/ata/ F: include/linux/ata.h @@ -11580,6 +11625,7 @@ F: drivers/gpu/drm/bridge/lontium-lt8912b.c LOONGARCH M: Huacai Chen R: WANG Xuerui +L: loongarch@lists.linux.dev S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/chenhuacai/linux-loongson.git F: arch/loongarch/ @@ -12493,6 +12539,7 @@ F: drivers/i2c/busses/i2c-mt65xx.c MEDIATEK IOMMU DRIVER M: Yong Wu L: iommu@lists.linux-foundation.org +L: iommu@lists.linux.dev L: linux-mediatek@lists.infradead.org (moderated for non-subscribers) S: Supported F: Documentation/devicetree/bindings/iommu/mediatek* @@ -12696,7 +12743,6 @@ L: netdev@vger.kernel.org S: Supported W: http://www.mellanox.com Q: https://patchwork.kernel.org/project/netdevbpf/list/ -F: drivers/net/ethernet/mellanox/mlx5/core/accel/* F: drivers/net/ethernet/mellanox/mlx5/core/en_accel/* F: drivers/net/ethernet/mellanox/mlx5/core/fpga/* F: include/linux/mlx5/mlx5_ifc_fpga.h @@ -12836,9 +12882,8 @@ M: Andrew Morton L: linux-mm@kvack.org S: Maintained W: http://www.linux-mm.org -T: quilt https://ozlabs.org/~akpm/mmotm/ -T: quilt https://ozlabs.org/~akpm/mmots/ -T: git git://github.com/hnaz/linux-mm.git +T: git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm +T: quilt git://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new F: include/linux/gfp.h F: include/linux/memory_hotplug.h F: include/linux/mm.h @@ -12848,6 +12893,18 @@ F: include/linux/vmalloc.h F: mm/ F: tools/testing/selftests/vm/ +MEMORY HOT(UN)PLUG +M: David Hildenbrand +M: Oscar Salvador +L: linux-mm@kvack.org +S: Maintained +F: Documentation/admin-guide/mm/memory-hotplug.rst +F: Documentation/core-api/memory-hotplug.rst +F: drivers/base/memory.c +F: include/linux/memory_hotplug.h +F: mm/memory_hotplug.c +F: tools/testing/selftests/memory-hotplug/ + MEMORY TECHNOLOGY DEVICES (MTD) M: Miquel Raynal M: Richard Weinberger @@ -13792,6 +13849,7 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git F: Documentation/devicetree/bindings/net/ F: drivers/connector/ F: drivers/net/ +F: include/dt-bindings/net/ F: include/linux/etherdevice.h F: include/linux/fcdevice.h F: include/linux/fddidevice.h @@ -13943,7 +14001,6 @@ F: net/ipv6/tcp*.c NETWORKING [TLS] M: Boris Pismenny M: John Fastabend -M: Daniel Borkmann M: Jakub Kicinski L: netdev@vger.kernel.org S: Maintained @@ -14252,7 +14309,7 @@ F: drivers/iio/gyro/fxas21002c_i2c.c F: drivers/iio/gyro/fxas21002c_spi.c NXP i.MX CLOCK DRIVERS -M: Abel Vesa +M: Abel Vesa L: linux-clk@vger.kernel.org L: linux-imx@nxp.com S: Maintained @@ -14860,6 +14917,7 @@ F: include/dt-bindings/ OPENCOMPUTE PTP CLOCK DRIVER M: Jonathan Lemon +M: Vadim Fedorenko L: netdev@vger.kernel.org S: Maintained F: drivers/ptp/ptp_ocp.c @@ -15824,6 +15882,14 @@ S: Maintained F: Documentation/devicetree/bindings/iio/chemical/plantower,pms7003.yaml F: drivers/iio/chemical/pms7003.c +PLATFORM FEATURE INFRASTRUCTURE +M: Juergen Gross +S: Maintained +F: arch/*/include/asm/platform-feature.h +F: include/asm-generic/platform-feature.h +F: include/linux/platform-feature.h +F: kernel/platform-feature.c + PLDMFW LIBRARY M: Jacob Keller S: Maintained @@ -16471,7 +16537,7 @@ F: Documentation/devicetree/bindings/opp/opp-v2-kryo-cpu.yaml F: drivers/cpufreq/qcom-cpufreq-nvmem.c QUALCOMM CRYPTO DRIVERS -M: Thara Gopinath +M: Thara Gopinath L: linux-crypto@vger.kernel.org L: linux-arm-msm@vger.kernel.org S: Maintained @@ -16526,6 +16592,7 @@ F: drivers/i2c/busses/i2c-qcom-cci.c QUALCOMM IOMMU M: Rob Clark L: iommu@lists.linux-foundation.org +L: iommu@lists.linux.dev L: linux-arm-msm@vger.kernel.org S: Maintained F: drivers/iommu/arm/arm-smmu/qcom_iommu.c @@ -16581,7 +16648,7 @@ F: include/linux/if_rmnet.h QUALCOMM TSENS THERMAL DRIVER M: Amit Kucheria -M: Thara Gopinath +M: Thara Gopinath L: linux-pm@vger.kernel.org L: linux-arm-msm@vger.kernel.org S: Maintained @@ -18760,7 +18827,7 @@ F: drivers/pinctrl/spear/ SPI NOR SUBSYSTEM M: Tudor Ambarus -M: Pratyush Yadav +M: Pratyush Yadav R: Michael Walle L: linux-mtd@lists.infradead.org S: Maintained @@ -19151,6 +19218,7 @@ F: arch/x86/boot/video* SWIOTLB SUBSYSTEM M: Christoph Hellwig L: iommu@lists.linux-foundation.org +L: iommu@lists.linux.dev S: Supported W: http://git.infradead.org/users/hch/dma-mapping.git T: git git://git.infradead.org/users/hch/dma-mapping.git @@ -19220,7 +19288,7 @@ F: arch/arc/plat-axs10x SYNOPSYS AXS10x RESET CONTROLLER DRIVER M: Eugeniy Paltsev S: Supported -F: Documentation/devicetree/bindings/reset/snps,axs10x-reset.txt +F: Documentation/devicetree/bindings/reset/snps,axs10x-reset.yaml F: drivers/reset/reset-axs10x.c SYNOPSYS CREG GPIO DRIVER @@ -19288,7 +19356,7 @@ R: Andy Shevchenko R: Mika Westerberg R: Jan Dabros L: linux-i2c@vger.kernel.org -S: Maintained +S: Supported F: drivers/i2c/busses/i2c-designware-* SYNOPSYS DESIGNWARE MMC/SD/SDIO DRIVER @@ -20695,6 +20763,7 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/usb.git F: Documentation/devicetree/bindings/usb/ F: Documentation/usb/ F: drivers/usb/ +F: include/dt-bindings/usb/ F: include/linux/usb.h F: include/linux/usb/ @@ -21825,6 +21894,7 @@ M: Juergen Gross M: Stefano Stabellini L: xen-devel@lists.xenproject.org (moderated for non-subscribers) L: iommu@lists.linux-foundation.org +L: iommu@lists.linux.dev S: Supported F: arch/x86/xen/*swiotlb* F: drivers/xen/*swiotlb* diff --git a/Makefile b/Makefile index c43d825a3c4c5..8973b285ce6c7 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 19 SUBLEVEL = 0 -EXTRAVERSION = -rc1 +EXTRAVERSION = -rc4 NAME = Superb Owl # *DOCUMENTATION* @@ -788,6 +788,7 @@ stackp-flags-$(CONFIG_STACKPROTECTOR_STRONG) := -fstack-protector-strong KBUILD_CFLAGS += $(stackp-flags-y) KBUILD_CFLAGS-$(CONFIG_WERROR) += -Werror +KBUILD_CFLAGS-$(CONFIG_CC_NO_ARRAY_BOUNDS) += -Wno-array-bounds KBUILD_CFLAGS += $(KBUILD_CFLAGS-y) $(CONFIG_CC_IMPLICIT_FALLTHROUGH) ifdef CONFIG_CC_IS_CLANG @@ -805,6 +806,9 @@ endif KBUILD_CFLAGS += $(call cc-disable-warning, unused-but-set-variable) KBUILD_CFLAGS += $(call cc-disable-warning, unused-const-variable) +# These result in bogus false positives +KBUILD_CFLAGS += $(call cc-disable-warning, dangling-pointer) + ifdef CONFIG_FRAME_POINTER KBUILD_CFLAGS += -fno-omit-frame-pointer -fno-optimize-sibling-calls else @@ -1137,7 +1141,7 @@ KBUILD_MODULES := 1 autoksyms_recursive: descend modules.order $(Q)$(CONFIG_SHELL) $(srctree)/scripts/adjust_autoksyms.sh \ - "$(MAKE) -f $(srctree)/Makefile vmlinux" + "$(MAKE) -f $(srctree)/Makefile autoksyms_recursive" endif autoksyms_h := $(if $(CONFIG_TRIM_UNUSED_KSYMS), include/generated/autoksyms.h) diff --git a/arch/arm/boot/dts/Makefile b/arch/arm/boot/dts/Makefile index 184899808ee73..5112f493f4946 100644 --- a/arch/arm/boot/dts/Makefile +++ b/arch/arm/boot/dts/Makefile @@ -1586,7 +1586,6 @@ dtb-$(CONFIG_ARCH_ASPEED) += \ aspeed-bmc-lenovo-hr630.dtb \ aspeed-bmc-lenovo-hr855xg2.dtb \ aspeed-bmc-microsoft-olympus.dtb \ - aspeed-bmc-nuvia-dc-scm.dtb \ aspeed-bmc-opp-lanyang.dtb \ aspeed-bmc-opp-mihawk.dtb \ aspeed-bmc-opp-mowgli.dtb \ @@ -1599,6 +1598,7 @@ dtb-$(CONFIG_ARCH_ASPEED) += \ aspeed-bmc-opp-witherspoon.dtb \ aspeed-bmc-opp-zaius.dtb \ aspeed-bmc-portwell-neptune.dtb \ + aspeed-bmc-qcom-dc-scm-v1.dtb \ aspeed-bmc-quanta-q71l.dtb \ aspeed-bmc-quanta-s6q.dtb \ aspeed-bmc-supermicro-x11spi.dtb \ diff --git a/arch/arm/boot/dts/aspeed-bmc-nuvia-dc-scm.dts b/arch/arm/boot/dts/aspeed-bmc-qcom-dc-scm-v1.dts similarity index 97% rename from arch/arm/boot/dts/aspeed-bmc-nuvia-dc-scm.dts rename to arch/arm/boot/dts/aspeed-bmc-qcom-dc-scm-v1.dts index f4a97cfb0f238..259ef3f54c5cc 100644 --- a/arch/arm/boot/dts/aspeed-bmc-nuvia-dc-scm.dts +++ b/arch/arm/boot/dts/aspeed-bmc-qcom-dc-scm-v1.dts @@ -6,8 +6,8 @@ #include "aspeed-g6.dtsi" / { - model = "Nuvia DC-SCM BMC"; - compatible = "nuvia,dc-scm-bmc", "aspeed,ast2600"; + model = "Qualcomm DC-SCM V1 BMC"; + compatible = "qcom,dc-scm-v1-bmc", "aspeed,ast2600"; aliases { serial4 = &uart5; diff --git a/arch/arm/boot/dts/at91-sama5d3_ksz9477_evb.dts b/arch/arm/boot/dts/at91-sama5d3_ksz9477_evb.dts index 443e8b0228977..14af1fd6d247d 100644 --- a/arch/arm/boot/dts/at91-sama5d3_ksz9477_evb.dts +++ b/arch/arm/boot/dts/at91-sama5d3_ksz9477_evb.dts @@ -120,26 +120,31 @@ port@0 { reg = <0>; label = "lan1"; + phy-mode = "internal"; }; port@1 { reg = <1>; label = "lan2"; + phy-mode = "internal"; }; port@2 { reg = <2>; label = "lan3"; + phy-mode = "internal"; }; port@3 { reg = <3>; label = "lan4"; + phy-mode = "internal"; }; port@4 { reg = <4>; label = "lan5"; + phy-mode = "internal"; }; port@5 { diff --git a/arch/arm/boot/dts/bcm2711-rpi-400.dts b/arch/arm/boot/dts/bcm2711-rpi-400.dts index f4d2fc20397c7..c53d9eb0b8027 100644 --- a/arch/arm/boot/dts/bcm2711-rpi-400.dts +++ b/arch/arm/boot/dts/bcm2711-rpi-400.dts @@ -28,12 +28,12 @@ &expgpio { gpio-line-names = "BT_ON", "WL_ON", - "", + "PWR_LED_OFF", "GLOBAL_RESET", "VDD_SD_IO_SEL", - "CAM_GPIO", + "GLOBAL_SHUTDOWN", "SD_PWR_ON", - "SD_OC_N"; + "SHUTDOWN_REQUEST"; }; &genet_mdio { diff --git a/arch/arm/boot/dts/imx6qdl-colibri.dtsi b/arch/arm/boot/dts/imx6qdl-colibri.dtsi index c383e0e4110c8..7df270cea2928 100644 --- a/arch/arm/boot/dts/imx6qdl-colibri.dtsi +++ b/arch/arm/boot/dts/imx6qdl-colibri.dtsi @@ -593,7 +593,7 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_atmel_conn>; reg = <0x4a>; - reset-gpios = <&gpio1 14 GPIO_ACTIVE_HIGH>; /* SODIMM 106 */ + reset-gpios = <&gpio1 14 GPIO_ACTIVE_LOW>; /* SODIMM 106 */ status = "disabled"; }; }; diff --git a/arch/arm/boot/dts/imx6qdl.dtsi b/arch/arm/boot/dts/imx6qdl.dtsi index d27beb47f9a3b..652feff334966 100644 --- a/arch/arm/boot/dts/imx6qdl.dtsi +++ b/arch/arm/boot/dts/imx6qdl.dtsi @@ -762,7 +762,7 @@ regulator-name = "vddpu"; regulator-min-microvolt = <725000>; regulator-max-microvolt = <1450000>; - regulator-enable-ramp-delay = <150>; + regulator-enable-ramp-delay = <380>; anatop-reg-offset = <0x140>; anatop-vol-bit-shift = <9>; anatop-vol-bit-width = <5>; diff --git a/arch/arm/boot/dts/imx7s.dtsi b/arch/arm/boot/dts/imx7s.dtsi index 008e3da460f1b..039eed79d2e73 100644 --- a/arch/arm/boot/dts/imx7s.dtsi +++ b/arch/arm/boot/dts/imx7s.dtsi @@ -120,6 +120,7 @@ compatible = "usb-nop-xceiv"; clocks = <&clks IMX7D_USB_HSIC_ROOT_CLK>; clock-names = "main_clk"; + power-domains = <&pgc_hsic_phy>; #phy-cells = <0>; }; @@ -1153,7 +1154,6 @@ compatible = "fsl,imx7d-usb", "fsl,imx27-usb"; reg = <0x30b30000 0x200>; interrupts = ; - power-domains = <&pgc_hsic_phy>; clocks = <&clks IMX7D_USB_CTRL_CLK>; fsl,usbphy = <&usbphynop3>; fsl,usbmisc = <&usbmisc3 0>; diff --git a/arch/arm/boot/dts/stm32mp15-scmi.dtsi b/arch/arm/boot/dts/stm32mp15-scmi.dtsi new file mode 100644 index 0000000000000..e90cf3acd0b31 --- /dev/null +++ b/arch/arm/boot/dts/stm32mp15-scmi.dtsi @@ -0,0 +1,47 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) +/* + * Copyright (C) STMicroelectronics 2022 - All Rights Reserved + * Author: Alexandre Torgue for STMicroelectronics. + */ + +/ { + firmware { + optee: optee { + compatible = "linaro,optee-tz"; + method = "smc"; + }; + + scmi: scmi { + compatible = "linaro,scmi-optee"; + #address-cells = <1>; + #size-cells = <0>; + linaro,optee-channel-id = <0>; + shmem = <&scmi_shm>; + + scmi_clk: protocol@14 { + reg = <0x14>; + #clock-cells = <1>; + }; + + scmi_reset: protocol@16 { + reg = <0x16>; + #reset-cells = <1>; + }; + }; + }; + + soc { + scmi_sram: sram@2ffff000 { + compatible = "mmio-sram"; + reg = <0x2ffff000 0x1000>; + #address-cells = <1>; + #size-cells = <1>; + ranges = <0 0x2ffff000 0x1000>; + + scmi_shm: scmi-sram@0 { + compatible = "arm,scmi-shmem"; + reg = <0 0x80>; + }; + }; + }; +}; diff --git a/arch/arm/boot/dts/stm32mp151.dtsi b/arch/arm/boot/dts/stm32mp151.dtsi index 1b2fd3426a810..7fdc324b3cf95 100644 --- a/arch/arm/boot/dts/stm32mp151.dtsi +++ b/arch/arm/boot/dts/stm32mp151.dtsi @@ -115,33 +115,6 @@ status = "disabled"; }; - firmware { - optee: optee { - compatible = "linaro,optee-tz"; - method = "smc"; - status = "disabled"; - }; - - scmi: scmi { - compatible = "linaro,scmi-optee"; - #address-cells = <1>; - #size-cells = <0>; - linaro,optee-channel-id = <0>; - shmem = <&scmi_shm>; - status = "disabled"; - - scmi_clk: protocol@14 { - reg = <0x14>; - #clock-cells = <1>; - }; - - scmi_reset: protocol@16 { - reg = <0x16>; - #reset-cells = <1>; - }; - }; - }; - soc { compatible = "simple-bus"; #address-cells = <1>; @@ -149,20 +122,6 @@ interrupt-parent = <&intc>; ranges; - scmi_sram: sram@2ffff000 { - compatible = "mmio-sram"; - reg = <0x2ffff000 0x1000>; - #address-cells = <1>; - #size-cells = <1>; - ranges = <0 0x2ffff000 0x1000>; - - scmi_shm: scmi-sram@0 { - compatible = "arm,scmi-shmem"; - reg = <0 0x80>; - status = "disabled"; - }; - }; - timers2: timer@40000000 { #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm/boot/dts/stm32mp157a-dk1-scmi.dts b/arch/arm/boot/dts/stm32mp157a-dk1-scmi.dts index e3d3f3f30c7da..36371d6ed6604 100644 --- a/arch/arm/boot/dts/stm32mp157a-dk1-scmi.dts +++ b/arch/arm/boot/dts/stm32mp157a-dk1-scmi.dts @@ -7,6 +7,7 @@ /dts-v1/; #include "stm32mp157a-dk1.dts" +#include "stm32mp15-scmi.dtsi" / { model = "STMicroelectronics STM32MP157A-DK1 SCMI Discovery Board"; @@ -54,10 +55,6 @@ resets = <&scmi_reset RST_SCMI_MCU>; }; -&optee { - status = "okay"; -}; - &rcc { compatible = "st,stm32mp1-rcc-secure", "syscon"; clock-names = "hse", "hsi", "csi", "lse", "lsi"; @@ -76,11 +73,3 @@ &rtc { clocks = <&scmi_clk CK_SCMI_RTCAPB>, <&scmi_clk CK_SCMI_RTC>; }; - -&scmi { - status = "okay"; -}; - -&scmi_shm { - status = "okay"; -}; diff --git a/arch/arm/boot/dts/stm32mp157c-dk2-scmi.dts b/arch/arm/boot/dts/stm32mp157c-dk2-scmi.dts index 45dcd299aa9e7..03226a5969046 100644 --- a/arch/arm/boot/dts/stm32mp157c-dk2-scmi.dts +++ b/arch/arm/boot/dts/stm32mp157c-dk2-scmi.dts @@ -7,6 +7,7 @@ /dts-v1/; #include "stm32mp157c-dk2.dts" +#include "stm32mp15-scmi.dtsi" / { model = "STMicroelectronics STM32MP157C-DK2 SCMI Discovery Board"; @@ -63,10 +64,6 @@ resets = <&scmi_reset RST_SCMI_MCU>; }; -&optee { - status = "okay"; -}; - &rcc { compatible = "st,stm32mp1-rcc-secure", "syscon"; clock-names = "hse", "hsi", "csi", "lse", "lsi"; @@ -85,11 +82,3 @@ &rtc { clocks = <&scmi_clk CK_SCMI_RTCAPB>, <&scmi_clk CK_SCMI_RTC>; }; - -&scmi { - status = "okay"; -}; - -&scmi_shm { - status = "okay"; -}; diff --git a/arch/arm/boot/dts/stm32mp157c-ed1-scmi.dts b/arch/arm/boot/dts/stm32mp157c-ed1-scmi.dts index 458e0ca3cded3..c1a79272c0688 100644 --- a/arch/arm/boot/dts/stm32mp157c-ed1-scmi.dts +++ b/arch/arm/boot/dts/stm32mp157c-ed1-scmi.dts @@ -7,6 +7,7 @@ /dts-v1/; #include "stm32mp157c-ed1.dts" +#include "stm32mp15-scmi.dtsi" / { model = "STMicroelectronics STM32MP157C-ED1 SCMI eval daughter"; @@ -59,10 +60,6 @@ resets = <&scmi_reset RST_SCMI_MCU>; }; -&optee { - status = "okay"; -}; - &rcc { compatible = "st,stm32mp1-rcc-secure", "syscon"; clock-names = "hse", "hsi", "csi", "lse", "lsi"; @@ -81,11 +78,3 @@ &rtc { clocks = <&scmi_clk CK_SCMI_RTCAPB>, <&scmi_clk CK_SCMI_RTC>; }; - -&scmi { - status = "okay"; -}; - -&scmi_shm { - status = "okay"; -}; diff --git a/arch/arm/boot/dts/stm32mp157c-ev1-scmi.dts b/arch/arm/boot/dts/stm32mp157c-ev1-scmi.dts index df9c113edb4b5..7842384ddbe45 100644 --- a/arch/arm/boot/dts/stm32mp157c-ev1-scmi.dts +++ b/arch/arm/boot/dts/stm32mp157c-ev1-scmi.dts @@ -7,6 +7,7 @@ /dts-v1/; #include "stm32mp157c-ev1.dts" +#include "stm32mp15-scmi.dtsi" / { model = "STMicroelectronics STM32MP157C-EV1 SCMI eval daughter on eval mother"; @@ -68,10 +69,6 @@ resets = <&scmi_reset RST_SCMI_MCU>; }; -&optee { - status = "okay"; -}; - &rcc { compatible = "st,stm32mp1-rcc-secure", "syscon"; clock-names = "hse", "hsi", "csi", "lse", "lsi"; @@ -90,11 +87,3 @@ &rtc { clocks = <&scmi_clk CK_SCMI_RTCAPB>, <&scmi_clk CK_SCMI_RTC>; }; - -&scmi { - status = "okay"; -}; - -&scmi_shm { - status = "okay"; -}; diff --git a/arch/arm/include/asm/xen/xen-ops.h b/arch/arm/include/asm/xen/xen-ops.h new file mode 100644 index 0000000000000..7ebb7eb0bd937 --- /dev/null +++ b/arch/arm/include/asm/xen/xen-ops.h @@ -0,0 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include diff --git a/arch/arm/mach-axxia/platsmp.c b/arch/arm/mach-axxia/platsmp.c index 512943eae30a5..2e203626eda52 100644 --- a/arch/arm/mach-axxia/platsmp.c +++ b/arch/arm/mach-axxia/platsmp.c @@ -39,6 +39,7 @@ static int axxia_boot_secondary(unsigned int cpu, struct task_struct *idle) return -ENOENT; syscon = of_iomap(syscon_np, 0); + of_node_put(syscon_np); if (!syscon) return -ENOMEM; diff --git a/arch/arm/mach-cns3xxx/core.c b/arch/arm/mach-cns3xxx/core.c index e4f4b20b83a2d..3fc4ec830e3a3 100644 --- a/arch/arm/mach-cns3xxx/core.c +++ b/arch/arm/mach-cns3xxx/core.c @@ -372,6 +372,7 @@ static void __init cns3xxx_init(void) /* De-Asscer SATA Reset */ cns3xxx_pwr_soft_rst(CNS3XXX_PWR_SOFTWARE_RST(SATA)); } + of_node_put(dn); dn = of_find_compatible_node(NULL, NULL, "cavium,cns3420-sdhci"); if (of_device_is_available(dn)) { @@ -385,6 +386,7 @@ static void __init cns3xxx_init(void) cns3xxx_pwr_clk_en(CNS3XXX_PWR_CLK_EN(SDIO)); cns3xxx_pwr_soft_rst(CNS3XXX_PWR_SOFTWARE_RST(SDIO)); } + of_node_put(dn); pm_power_off = cns3xxx_power_off; diff --git a/arch/arm/mach-exynos/exynos.c b/arch/arm/mach-exynos/exynos.c index 8b48326be9fd5..51a247ca4da8c 100644 --- a/arch/arm/mach-exynos/exynos.c +++ b/arch/arm/mach-exynos/exynos.c @@ -149,6 +149,7 @@ static void exynos_map_pmu(void) np = of_find_matching_node(NULL, exynos_dt_pmu_match); if (np) pmu_base_addr = of_iomap(np, 0); + of_node_put(np); } static void __init exynos_init_irq(void) diff --git a/arch/arm/mach-spear/time.c b/arch/arm/mach-spear/time.c index d1fdb6066f7bb..c7c17c0f936cf 100644 --- a/arch/arm/mach-spear/time.c +++ b/arch/arm/mach-spear/time.c @@ -218,13 +218,13 @@ void __init spear_setup_of_timer(void) irq = irq_of_parse_and_map(np, 0); if (!irq) { pr_err("%s: No irq passed for timer via DT\n", __func__); - return; + goto err_put_np; } gpt_base = of_iomap(np, 0); if (!gpt_base) { pr_err("%s: of iomap failed\n", __func__); - return; + goto err_put_np; } gpt_clk = clk_get_sys("gpt0", NULL); @@ -239,6 +239,8 @@ void __init spear_setup_of_timer(void) goto err_prepare_enable_clk; } + of_node_put(np); + spear_clockevent_init(irq); spear_clocksource_init(); @@ -248,4 +250,6 @@ void __init spear_setup_of_timer(void) clk_put(gpt_clk); err_iomap: iounmap(gpt_base); +err_put_np: + of_node_put(np); } diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index 82ffac621854f..059cce0185706 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -33,7 +33,7 @@ #include #include #include -#include +#include #include "dma.h" #include "mm.h" @@ -2287,10 +2287,7 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, set_dma_ops(dev, dma_ops); -#ifdef CONFIG_XEN - if (xen_initial_domain()) - dev->dma_ops = &xen_swiotlb_dma_ops; -#endif + xen_setup_dma_ops(dev); dev->archdata.dma_ops_setup = true; } diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c index 07eb69f9e7df3..1f9c3ba328333 100644 --- a/arch/arm/xen/enlighten.c +++ b/arch/arm/xen/enlighten.c @@ -443,6 +443,8 @@ static int __init xen_guest_init(void) if (!xen_domain()) return 0; + xen_set_restricted_virtio_memory_access(); + if (!acpi_disabled) xen_acpi_guest_init(); else diff --git a/arch/arm64/boot/dts/exynos/exynos7885.dtsi b/arch/arm64/boot/dts/exynos/exynos7885.dtsi index 3170661f5b672..9c233c56558ce 100644 --- a/arch/arm64/boot/dts/exynos/exynos7885.dtsi +++ b/arch/arm64/boot/dts/exynos/exynos7885.dtsi @@ -280,8 +280,8 @@ interrupts = ; pinctrl-names = "default"; pinctrl-0 = <&uart0_bus>; - clocks = <&cmu_peri CLK_GOUT_UART0_EXT_UCLK>, - <&cmu_peri CLK_GOUT_UART0_PCLK>; + clocks = <&cmu_peri CLK_GOUT_UART0_PCLK>, + <&cmu_peri CLK_GOUT_UART0_EXT_UCLK>; clock-names = "uart", "clk_uart_baud0"; samsung,uart-fifosize = <64>; status = "disabled"; @@ -293,8 +293,8 @@ interrupts = ; pinctrl-names = "default"; pinctrl-0 = <&uart1_bus>; - clocks = <&cmu_peri CLK_GOUT_UART1_EXT_UCLK>, - <&cmu_peri CLK_GOUT_UART1_PCLK>; + clocks = <&cmu_peri CLK_GOUT_UART1_PCLK>, + <&cmu_peri CLK_GOUT_UART1_EXT_UCLK>; clock-names = "uart", "clk_uart_baud0"; samsung,uart-fifosize = <256>; status = "disabled"; @@ -306,8 +306,8 @@ interrupts = ; pinctrl-names = "default"; pinctrl-0 = <&uart2_bus>; - clocks = <&cmu_peri CLK_GOUT_UART2_EXT_UCLK>, - <&cmu_peri CLK_GOUT_UART2_PCLK>; + clocks = <&cmu_peri CLK_GOUT_UART2_PCLK>, + <&cmu_peri CLK_GOUT_UART2_EXT_UCLK>; clock-names = "uart", "clk_uart_baud0"; samsung,uart-fifosize = <256>; status = "disabled"; diff --git a/arch/arm64/boot/dts/freescale/s32g2.dtsi b/arch/arm64/boot/dts/freescale/s32g2.dtsi index 59ea8a25aa4c1..824d401e7a2c5 100644 --- a/arch/arm64/boot/dts/freescale/s32g2.dtsi +++ b/arch/arm64/boot/dts/freescale/s32g2.dtsi @@ -79,7 +79,7 @@ }; }; - soc { + soc@0 { compatible = "simple-bus"; #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arm64/boot/dts/ti/k3-am64-main.dtsi b/arch/arm64/boot/dts/ti/k3-am64-main.dtsi index f64b368c6c371..cdb530597c5eb 100644 --- a/arch/arm64/boot/dts/ti/k3-am64-main.dtsi +++ b/arch/arm64/boot/dts/ti/k3-am64-main.dtsi @@ -456,13 +456,11 @@ clock-names = "clk_ahb", "clk_xin"; mmc-ddr-1_8v; mmc-hs200-1_8v; - mmc-hs400-1_8v; ti,trm-icp = <0x2>; ti,otap-del-sel-legacy = <0x0>; ti,otap-del-sel-mmc-hs = <0x0>; ti,otap-del-sel-ddr52 = <0x6>; ti,otap-del-sel-hs200 = <0x7>; - ti,otap-del-sel-hs400 = <0x4>; }; sdhci1: mmc@fa00000 { diff --git a/arch/arm64/boot/dts/ti/k3-j721s2-main.dtsi b/arch/arm64/boot/dts/ti/k3-j721s2-main.dtsi index be7f39299894e..19966f72c5b38 100644 --- a/arch/arm64/boot/dts/ti/k3-j721s2-main.dtsi +++ b/arch/arm64/boot/dts/ti/k3-j721s2-main.dtsi @@ -33,7 +33,7 @@ ranges; #interrupt-cells = <3>; interrupt-controller; - reg = <0x00 0x01800000 0x00 0x200000>, /* GICD */ + reg = <0x00 0x01800000 0x00 0x100000>, /* GICD */ <0x00 0x01900000 0x00 0x100000>, /* GICR */ <0x00 0x6f000000 0x00 0x2000>, /* GICC */ <0x00 0x6f010000 0x00 0x1000>, /* GICH */ diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 47a1e25e25bbc..de32152cea048 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -362,11 +362,6 @@ struct kvm_vcpu_arch { struct arch_timer_cpu timer_cpu; struct kvm_pmu pmu; - /* - * Anything that is not used directly from assembly code goes - * here. - */ - /* * Guest registers we preserve during guest debugging. * diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index 55f998c3dc284..42ff95dba6da4 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -843,9 +843,9 @@ #define ID_AA64SMFR0_F32F32_SHIFT 32 #define ID_AA64SMFR0_FA64 0x1 -#define ID_AA64SMFR0_I16I64 0x4 +#define ID_AA64SMFR0_I16I64 0xf #define ID_AA64SMFR0_F64F64 0x1 -#define ID_AA64SMFR0_I8I32 0x4 +#define ID_AA64SMFR0_I8I32 0xf #define ID_AA64SMFR0_F16F32 0x1 #define ID_AA64SMFR0_B16F32 0x1 #define ID_AA64SMFR0_F32F32 0x1 diff --git a/arch/arm64/include/asm/virt.h b/arch/arm64/include/asm/virt.h index 3c8af033a9976..0e80db4327b60 100644 --- a/arch/arm64/include/asm/virt.h +++ b/arch/arm64/include/asm/virt.h @@ -113,6 +113,9 @@ static __always_inline bool has_vhe(void) /* * Code only run in VHE/NVHE hyp context can assume VHE is present or * absent. Otherwise fall back to caps. + * This allows the compiler to discard VHE-specific code from the + * nVHE object, reducing the number of external symbol references + * needed to link. */ if (is_vhe_hyp_code()) return true; diff --git a/arch/arm64/include/asm/xen/xen-ops.h b/arch/arm64/include/asm/xen/xen-ops.h new file mode 100644 index 0000000000000..7ebb7eb0bd937 --- /dev/null +++ b/arch/arm64/include/asm/xen/xen-ops.h @@ -0,0 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 42ea2bd856c60..8d88433de81da 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -1974,15 +1974,7 @@ static void cpu_enable_mte(struct arm64_cpu_capabilities const *cap) #ifdef CONFIG_KVM static bool is_kvm_protected_mode(const struct arm64_cpu_capabilities *entry, int __unused) { - if (kvm_get_mode() != KVM_MODE_PROTECTED) - return false; - - if (is_kernel_in_hyp_mode()) { - pr_warn("Protected KVM not available with VHE\n"); - return false; - } - - return true; + return kvm_get_mode() == KVM_MODE_PROTECTED; } #endif /* CONFIG_KVM */ @@ -3109,7 +3101,6 @@ void cpu_set_feature(unsigned int num) WARN_ON(num >= MAX_CPU_FEATURES); elf_hwcap |= BIT(num); } -EXPORT_SYMBOL_GPL(cpu_set_feature); bool cpu_have_feature(unsigned int num) { diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S index d42a205ef6259..bd5df50e46432 100644 --- a/arch/arm64/kernel/entry-ftrace.S +++ b/arch/arm64/kernel/entry-ftrace.S @@ -102,7 +102,6 @@ SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL) * x19-x29 per the AAPCS, and we created frame records upon entry, so we need * to restore x0-x8, x29, and x30. */ -ftrace_common_return: /* Restore function arguments */ ldp x0, x1, [sp] ldp x2, x3, [sp, #S_X2] diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 819979398127e..aecf3071efddd 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -331,7 +331,7 @@ void task_set_vl_onexec(struct task_struct *task, enum vec_type type, * trapping to the kernel. * * When stored, Z0-Z31 (incorporating Vn in bits[127:0] or the - * corresponding Zn), P0-P15 and FFR are encoded in in + * corresponding Zn), P0-P15 and FFR are encoded in * task->thread.sve_state, formatted appropriately for vector * length task->thread.sve_vl or, if SVCR.SM is set, * task->thread.sme_vl. @@ -1916,10 +1916,15 @@ void __efi_fpsimd_begin(void) if (system_supports_sme()) { svcr = read_sysreg_s(SYS_SVCR); - if (!system_supports_fa64()) - ffr = svcr & SVCR_SM_MASK; + __this_cpu_write(efi_sm_state, + svcr & SVCR_SM_MASK); - __this_cpu_write(efi_sm_state, ffr); + /* + * Unless we have FA64 FFR does not + * exist in streaming mode. + */ + if (!system_supports_fa64()) + ffr = !(svcr & SVCR_SM_MASK); } sve_save_state(sve_state + sve_ffr_offset(sve_max_vl()), @@ -1964,8 +1969,13 @@ void __efi_fpsimd_end(void) sysreg_clear_set_s(SYS_SVCR, 0, SVCR_SM_MASK); + + /* + * Unless we have FA64 FFR does not + * exist in streaming mode. + */ if (!system_supports_fa64()) - ffr = efi_sm_state; + ffr = false; } } diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c index f447c4a36f694..ea5dc7c90f465 100644 --- a/arch/arm64/kernel/ftrace.c +++ b/arch/arm64/kernel/ftrace.c @@ -78,47 +78,76 @@ static struct plt_entry *get_ftrace_plt(struct module *mod, unsigned long addr) } /* - * Turn on the call to ftrace_caller() in instrumented function + * Find the address the callsite must branch to in order to reach '*addr'. + * + * Due to the limited range of 'BL' instructions, modules may be placed too far + * away to branch directly and must use a PLT. + * + * Returns true when '*addr' contains a reachable target address, or has been + * modified to contain a PLT address. Returns false otherwise. */ -int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) +static bool ftrace_find_callable_addr(struct dyn_ftrace *rec, + struct module *mod, + unsigned long *addr) { unsigned long pc = rec->ip; - u32 old, new; - long offset = (long)pc - (long)addr; + long offset = (long)*addr - (long)pc; + struct plt_entry *plt; - if (offset < -SZ_128M || offset >= SZ_128M) { - struct module *mod; - struct plt_entry *plt; + /* + * When the target is within range of the 'BL' instruction, use 'addr' + * as-is and branch to that directly. + */ + if (offset >= -SZ_128M && offset < SZ_128M) + return true; - if (!IS_ENABLED(CONFIG_ARM64_MODULE_PLTS)) - return -EINVAL; + /* + * When the target is outside of the range of a 'BL' instruction, we + * must use a PLT to reach it. We can only place PLTs for modules, and + * only when module PLT support is built-in. + */ + if (!IS_ENABLED(CONFIG_ARM64_MODULE_PLTS)) + return false; - /* - * On kernels that support module PLTs, the offset between the - * branch instruction and its target may legally exceed the - * range of an ordinary relative 'bl' opcode. In this case, we - * need to branch via a trampoline in the module. - * - * NOTE: __module_text_address() must be called with preemption - * disabled, but we can rely on ftrace_lock to ensure that 'mod' - * retains its validity throughout the remainder of this code. - */ + /* + * 'mod' is only set at module load time, but if we end up + * dealing with an out-of-range condition, we can assume it + * is due to a module being loaded far away from the kernel. + * + * NOTE: __module_text_address() must be called with preemption + * disabled, but we can rely on ftrace_lock to ensure that 'mod' + * retains its validity throughout the remainder of this code. + */ + if (!mod) { preempt_disable(); mod = __module_text_address(pc); preempt_enable(); + } - if (WARN_ON(!mod)) - return -EINVAL; + if (WARN_ON(!mod)) + return false; - plt = get_ftrace_plt(mod, addr); - if (!plt) { - pr_err("ftrace: no module PLT for %ps\n", (void *)addr); - return -EINVAL; - } - - addr = (unsigned long)plt; + plt = get_ftrace_plt(mod, *addr); + if (!plt) { + pr_err("ftrace: no module PLT for %ps\n", (void *)*addr); + return false; } + *addr = (unsigned long)plt; + return true; +} + +/* + * Turn on the call to ftrace_caller() in instrumented function + */ +int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) +{ + unsigned long pc = rec->ip; + u32 old, new; + + if (!ftrace_find_callable_addr(rec, NULL, &addr)) + return -EINVAL; + old = aarch64_insn_gen_nop(); new = aarch64_insn_gen_branch_imm(pc, addr, AARCH64_INSN_BRANCH_LINK); @@ -132,6 +161,11 @@ int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, unsigned long pc = rec->ip; u32 old, new; + if (!ftrace_find_callable_addr(rec, NULL, &old_addr)) + return -EINVAL; + if (!ftrace_find_callable_addr(rec, NULL, &addr)) + return -EINVAL; + old = aarch64_insn_gen_branch_imm(pc, old_addr, AARCH64_INSN_BRANCH_LINK); new = aarch64_insn_gen_branch_imm(pc, addr, AARCH64_INSN_BRANCH_LINK); @@ -181,54 +215,15 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr) { unsigned long pc = rec->ip; - bool validate = true; u32 old = 0, new; - long offset = (long)pc - (long)addr; - if (offset < -SZ_128M || offset >= SZ_128M) { - u32 replaced; - - if (!IS_ENABLED(CONFIG_ARM64_MODULE_PLTS)) - return -EINVAL; - - /* - * 'mod' is only set at module load time, but if we end up - * dealing with an out-of-range condition, we can assume it - * is due to a module being loaded far away from the kernel. - */ - if (!mod) { - preempt_disable(); - mod = __module_text_address(pc); - preempt_enable(); - - if (WARN_ON(!mod)) - return -EINVAL; - } - - /* - * The instruction we are about to patch may be a branch and - * link instruction that was redirected via a PLT entry. In - * this case, the normal validation will fail, but we can at - * least check that we are dealing with a branch and link - * instruction that points into the right module. - */ - if (aarch64_insn_read((void *)pc, &replaced)) - return -EFAULT; - - if (!aarch64_insn_is_bl(replaced) || - !within_module(pc + aarch64_get_branch_offset(replaced), - mod)) - return -EINVAL; - - validate = false; - } else { - old = aarch64_insn_gen_branch_imm(pc, addr, - AARCH64_INSN_BRANCH_LINK); - } + if (!ftrace_find_callable_addr(rec, mod, &addr)) + return -EINVAL; + old = aarch64_insn_gen_branch_imm(pc, addr, AARCH64_INSN_BRANCH_LINK); new = aarch64_insn_gen_nop(); - return ftrace_modify_code(pc, old, new, validate); + return ftrace_modify_code(pc, old, new, true); } void arch_ftrace_update_code(int command) diff --git a/arch/arm64/kernel/mte.c b/arch/arm64/kernel/mte.c index 57b30bcf9f21d..f6b00743c3994 100644 --- a/arch/arm64/kernel/mte.c +++ b/arch/arm64/kernel/mte.c @@ -244,6 +244,11 @@ static void mte_update_gcr_excl(struct task_struct *task) SYS_GCR_EL1); } +#ifdef CONFIG_KASAN_HW_TAGS +/* Only called from assembly, silence sparse */ +void __init kasan_hw_tags_enable(struct alt_instr *alt, __le32 *origptr, + __le32 *updptr, int nr_inst); + void __init kasan_hw_tags_enable(struct alt_instr *alt, __le32 *origptr, __le32 *updptr, int nr_inst) { @@ -252,6 +257,7 @@ void __init kasan_hw_tags_enable(struct alt_instr *alt, __le32 *origptr, if (kasan_hw_tags_enabled()) *updptr = cpu_to_le32(aarch64_insn_gen_nop()); } +#endif void mte_thread_init_user(void) { diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index cf3a759f10d4e..fea3223704b63 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -303,14 +303,13 @@ void __init __no_sanitize_address setup_arch(char **cmdline_p) early_fixmap_init(); early_ioremap_init(); + setup_machine_fdt(__fdt_pointer); + /* * Initialise the static keys early as they may be enabled by the - * cpufeature code, early parameters, and DT setup. + * cpufeature code and early parameters. */ jump_label_init(); - - setup_machine_fdt(__fdt_pointer); - parse_early_param(); /* diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c index 4e39ace073af0..3b8d062e30ea4 100644 --- a/arch/arm64/kvm/arch_timer.c +++ b/arch/arm64/kvm/arch_timer.c @@ -1230,6 +1230,9 @@ bool kvm_arch_timer_get_input_level(int vintid) struct kvm_vcpu *vcpu = kvm_get_running_vcpu(); struct arch_timer_context *timer; + if (WARN(!vcpu, "No vcpu context!\n")) + return false; + if (vintid == vcpu_vtimer(vcpu)->irq.irq) timer = vcpu_vtimer(vcpu); else if (vintid == vcpu_ptimer(vcpu)->irq.irq) diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 400bb0fe2745b..83a7f61354d3f 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -150,8 +150,10 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) if (ret) goto out_free_stage2_pgd; - if (!zalloc_cpumask_var(&kvm->arch.supported_cpus, GFP_KERNEL)) + if (!zalloc_cpumask_var(&kvm->arch.supported_cpus, GFP_KERNEL)) { + ret = -ENOMEM; goto out_free_stage2_pgd; + } cpumask_copy(kvm->arch.supported_cpus, cpu_possible_mask); kvm_vgic_early_init(kvm); @@ -2110,11 +2112,11 @@ static int finalize_hyp_mode(void) return 0; /* - * Exclude HYP BSS from kmemleak so that it doesn't get peeked - * at, which would end badly once the section is inaccessible. - * None of other sections should ever be introspected. + * Exclude HYP sections from kmemleak so that they don't get peeked + * at, which would end badly once inaccessible. */ kmemleak_free_part(__hyp_bss_start, __hyp_bss_end - __hyp_bss_start); + kmemleak_free_part(__va(hyp_mem_base), hyp_mem_size); return pkvm_drop_host_privileges(); } @@ -2271,7 +2273,11 @@ static int __init early_kvm_mode_cfg(char *arg) return -EINVAL; if (strcmp(arg, "protected") == 0) { - kvm_mode = KVM_MODE_PROTECTED; + if (!is_kernel_in_hyp_mode()) + kvm_mode = KVM_MODE_PROTECTED; + else + pr_warn_once("Protected KVM not available with VHE\n"); + return 0; } diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c index 3d251a4d2cf7b..6012b08ecb14e 100644 --- a/arch/arm64/kvm/fpsimd.c +++ b/arch/arm64/kvm/fpsimd.c @@ -80,6 +80,7 @@ void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu) vcpu->arch.flags &= ~KVM_ARM64_FP_ENABLED; vcpu->arch.flags |= KVM_ARM64_FP_HOST; + vcpu->arch.flags &= ~KVM_ARM64_HOST_SVE_ENABLED; if (read_sysreg(cpacr_el1) & CPACR_EL1_ZEN_EL0EN) vcpu->arch.flags |= KVM_ARM64_HOST_SVE_ENABLED; @@ -93,6 +94,7 @@ void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu) * operations. Do this for ZA as well for now for simplicity. */ if (system_supports_sme()) { + vcpu->arch.flags &= ~KVM_ARM64_HOST_SME_ENABLED; if (read_sysreg(cpacr_el1) & CPACR_EL1_SMEN_EL0EN) vcpu->arch.flags |= KVM_ARM64_HOST_SME_ENABLED; diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c index 78edf077fa3b6..1e78acf9662eb 100644 --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c @@ -314,15 +314,11 @@ static int host_stage2_adjust_range(u64 addr, struct kvm_mem_range *range) int host_stage2_idmap_locked(phys_addr_t addr, u64 size, enum kvm_pgtable_prot prot) { - hyp_assert_lock_held(&host_kvm.lock); - return host_stage2_try(__host_stage2_idmap, addr, addr + size, prot); } int host_stage2_set_owner_locked(phys_addr_t addr, u64 size, u8 owner_id) { - hyp_assert_lock_held(&host_kvm.lock); - return host_stage2_try(kvm_pgtable_stage2_set_owner, &host_kvm.pgt, addr, size, &host_s2_pool, owner_id); } diff --git a/arch/arm64/kvm/hyp/nvhe/sys_regs.c b/arch/arm64/kvm/hyp/nvhe/sys_regs.c index b6d86e423319f..35a4331ba5f31 100644 --- a/arch/arm64/kvm/hyp/nvhe/sys_regs.c +++ b/arch/arm64/kvm/hyp/nvhe/sys_regs.c @@ -243,15 +243,9 @@ u64 pvm_read_id_reg(const struct kvm_vcpu *vcpu, u32 id) case SYS_ID_AA64MMFR2_EL1: return get_pvm_id_aa64mmfr2(vcpu); default: - /* - * Should never happen because all cases are covered in - * pvm_sys_reg_descs[]. - */ - WARN_ON(1); - break; + /* Unhandled ID register, RAZ */ + return 0; } - - return 0; } static u64 read_id_reg(const struct kvm_vcpu *vcpu, @@ -332,6 +326,16 @@ static bool pvm_gic_read_sre(struct kvm_vcpu *vcpu, /* Mark the specified system register as an AArch64 feature id register. */ #define AARCH64(REG) { SYS_DESC(REG), .access = pvm_access_id_aarch64 } +/* + * sys_reg_desc initialiser for architecturally unallocated cpufeature ID + * register with encoding Op0=3, Op1=0, CRn=0, CRm=crm, Op2=op2 + * (1 <= crm < 8, 0 <= Op2 < 8). + */ +#define ID_UNALLOCATED(crm, op2) { \ + Op0(3), Op1(0), CRn(0), CRm(crm), Op2(op2), \ + .access = pvm_access_id_aarch64, \ +} + /* Mark the specified system register as Read-As-Zero/Write-Ignored */ #define RAZ_WI(REG) { SYS_DESC(REG), .access = pvm_access_raz_wi } @@ -375,24 +379,46 @@ static const struct sys_reg_desc pvm_sys_reg_descs[] = { AARCH32(SYS_MVFR0_EL1), AARCH32(SYS_MVFR1_EL1), AARCH32(SYS_MVFR2_EL1), + ID_UNALLOCATED(3,3), AARCH32(SYS_ID_PFR2_EL1), AARCH32(SYS_ID_DFR1_EL1), AARCH32(SYS_ID_MMFR5_EL1), + ID_UNALLOCATED(3,7), /* AArch64 ID registers */ /* CRm=4 */ AARCH64(SYS_ID_AA64PFR0_EL1), AARCH64(SYS_ID_AA64PFR1_EL1), + ID_UNALLOCATED(4,2), + ID_UNALLOCATED(4,3), AARCH64(SYS_ID_AA64ZFR0_EL1), + ID_UNALLOCATED(4,5), + ID_UNALLOCATED(4,6), + ID_UNALLOCATED(4,7), AARCH64(SYS_ID_AA64DFR0_EL1), AARCH64(SYS_ID_AA64DFR1_EL1), + ID_UNALLOCATED(5,2), + ID_UNALLOCATED(5,3), AARCH64(SYS_ID_AA64AFR0_EL1), AARCH64(SYS_ID_AA64AFR1_EL1), + ID_UNALLOCATED(5,6), + ID_UNALLOCATED(5,7), AARCH64(SYS_ID_AA64ISAR0_EL1), AARCH64(SYS_ID_AA64ISAR1_EL1), + AARCH64(SYS_ID_AA64ISAR2_EL1), + ID_UNALLOCATED(6,3), + ID_UNALLOCATED(6,4), + ID_UNALLOCATED(6,5), + ID_UNALLOCATED(6,6), + ID_UNALLOCATED(6,7), AARCH64(SYS_ID_AA64MMFR0_EL1), AARCH64(SYS_ID_AA64MMFR1_EL1), AARCH64(SYS_ID_AA64MMFR2_EL1), + ID_UNALLOCATED(7,3), + ID_UNALLOCATED(7,4), + ID_UNALLOCATED(7,5), + ID_UNALLOCATED(7,6), + ID_UNALLOCATED(7,7), /* Scalable Vector Registers are restricted. */ diff --git a/arch/arm64/kvm/vgic/vgic-mmio-v2.c b/arch/arm64/kvm/vgic/vgic-mmio-v2.c index 77a67e9d3d14b..e070cda86e12f 100644 --- a/arch/arm64/kvm/vgic/vgic-mmio-v2.c +++ b/arch/arm64/kvm/vgic/vgic-mmio-v2.c @@ -429,11 +429,11 @@ static const struct vgic_register_region vgic_v2_dist_registers[] = { VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_PENDING_SET, vgic_mmio_read_pending, vgic_mmio_write_spending, - NULL, vgic_uaccess_write_spending, 1, + vgic_uaccess_read_pending, vgic_uaccess_write_spending, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_PENDING_CLEAR, vgic_mmio_read_pending, vgic_mmio_write_cpending, - NULL, vgic_uaccess_write_cpending, 1, + vgic_uaccess_read_pending, vgic_uaccess_write_cpending, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_ACTIVE_SET, vgic_mmio_read_active, vgic_mmio_write_sactive, diff --git a/arch/arm64/kvm/vgic/vgic-mmio-v3.c b/arch/arm64/kvm/vgic/vgic-mmio-v3.c index f7aa7bcd6fb8c..f15e29cc63ce1 100644 --- a/arch/arm64/kvm/vgic/vgic-mmio-v3.c +++ b/arch/arm64/kvm/vgic/vgic-mmio-v3.c @@ -353,42 +353,6 @@ static unsigned long vgic_mmio_read_v3_idregs(struct kvm_vcpu *vcpu, return 0; } -static unsigned long vgic_v3_uaccess_read_pending(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len) -{ - u32 intid = VGIC_ADDR_TO_INTID(addr, 1); - u32 value = 0; - int i; - - /* - * pending state of interrupt is latched in pending_latch variable. - * Userspace will save and restore pending state and line_level - * separately. - * Refer to Documentation/virt/kvm/devices/arm-vgic-v3.rst - * for handling of ISPENDR and ICPENDR. - */ - for (i = 0; i < len * 8; i++) { - struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); - bool state = irq->pending_latch; - - if (irq->hw && vgic_irq_is_sgi(irq->intid)) { - int err; - - err = irq_get_irqchip_state(irq->host_irq, - IRQCHIP_STATE_PENDING, - &state); - WARN_ON(err); - } - - if (state) - value |= (1U << i); - - vgic_put_irq(vcpu->kvm, irq); - } - - return value; -} - static int vgic_v3_uaccess_write_pending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) @@ -666,7 +630,7 @@ static const struct vgic_register_region vgic_v3_dist_registers[] = { VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ISPENDR, vgic_mmio_read_pending, vgic_mmio_write_spending, - vgic_v3_uaccess_read_pending, vgic_v3_uaccess_write_pending, 1, + vgic_uaccess_read_pending, vgic_v3_uaccess_write_pending, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ICPENDR, vgic_mmio_read_pending, vgic_mmio_write_cpending, @@ -750,7 +714,7 @@ static const struct vgic_register_region vgic_v3_rd_registers[] = { VGIC_ACCESS_32bit), REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ISPENDR0, vgic_mmio_read_pending, vgic_mmio_write_spending, - vgic_v3_uaccess_read_pending, vgic_v3_uaccess_write_pending, 4, + vgic_uaccess_read_pending, vgic_v3_uaccess_write_pending, 4, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ICPENDR0, vgic_mmio_read_pending, vgic_mmio_write_cpending, diff --git a/arch/arm64/kvm/vgic/vgic-mmio.c b/arch/arm64/kvm/vgic/vgic-mmio.c index 49837d3a3ef56..997d0fce20883 100644 --- a/arch/arm64/kvm/vgic/vgic-mmio.c +++ b/arch/arm64/kvm/vgic/vgic-mmio.c @@ -226,8 +226,9 @@ int vgic_uaccess_write_cenable(struct kvm_vcpu *vcpu, return 0; } -unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len) +static unsigned long __read_pending(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + bool is_user) { u32 intid = VGIC_ADDR_TO_INTID(addr, 1); u32 value = 0; @@ -239,6 +240,15 @@ unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu, unsigned long flags; bool val; + /* + * When used from userspace with a GICv3 model: + * + * Pending state of interrupt is latched in pending_latch + * variable. Userspace will save and restore pending state + * and line_level separately. + * Refer to Documentation/virt/kvm/devices/arm-vgic-v3.rst + * for handling of ISPENDR and ICPENDR. + */ raw_spin_lock_irqsave(&irq->irq_lock, flags); if (irq->hw && vgic_irq_is_sgi(irq->intid)) { int err; @@ -248,10 +258,20 @@ unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu, IRQCHIP_STATE_PENDING, &val); WARN_RATELIMIT(err, "IRQ %d", irq->host_irq); - } else if (vgic_irq_is_mapped_level(irq)) { + } else if (!is_user && vgic_irq_is_mapped_level(irq)) { val = vgic_get_phys_line_level(irq); } else { - val = irq_is_pending(irq); + switch (vcpu->kvm->arch.vgic.vgic_model) { + case KVM_DEV_TYPE_ARM_VGIC_V3: + if (is_user) { + val = irq->pending_latch; + break; + } + fallthrough; + default: + val = irq_is_pending(irq); + break; + } } value |= ((u32)val << i); @@ -263,6 +283,18 @@ unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu, return value; } +unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len) +{ + return __read_pending(vcpu, addr, len, false); +} + +unsigned long vgic_uaccess_read_pending(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len) +{ + return __read_pending(vcpu, addr, len, true); +} + static bool is_vgic_v2_sgi(struct kvm_vcpu *vcpu, struct vgic_irq *irq) { return (vgic_irq_is_sgi(irq->intid) && diff --git a/arch/arm64/kvm/vgic/vgic-mmio.h b/arch/arm64/kvm/vgic/vgic-mmio.h index 3fa696f198a37..6082d4b66d398 100644 --- a/arch/arm64/kvm/vgic/vgic-mmio.h +++ b/arch/arm64/kvm/vgic/vgic-mmio.h @@ -149,6 +149,9 @@ int vgic_uaccess_write_cenable(struct kvm_vcpu *vcpu, unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len); +unsigned long vgic_uaccess_read_pending(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len); + void vgic_mmio_write_spending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val); diff --git a/arch/arm64/kvm/vmid.c b/arch/arm64/kvm/vmid.c index 8d5f0506fd87f..d78ae63d7c15f 100644 --- a/arch/arm64/kvm/vmid.c +++ b/arch/arm64/kvm/vmid.c @@ -66,7 +66,7 @@ static void flush_context(void) * the next context-switch, we broadcast TLB flush + I-cache * invalidation over the inner shareable domain on rollover. */ - kvm_call_hyp(__kvm_flush_vm_context); + kvm_call_hyp(__kvm_flush_vm_context); } static bool check_update_reserved_vmid(u64 vmid, u64 newvmid) diff --git a/arch/arm64/mm/cache.S b/arch/arm64/mm/cache.S index 0ea6cc25dc663..21c907987080f 100644 --- a/arch/arm64/mm/cache.S +++ b/arch/arm64/mm/cache.S @@ -218,8 +218,6 @@ SYM_FUNC_ALIAS(__dma_flush_area, __pi___dma_flush_area) */ SYM_FUNC_START(__pi___dma_map_area) add x1, x0, x1 - cmp w2, #DMA_FROM_DEVICE - b.eq __pi_dcache_inval_poc b __pi_dcache_clean_poc SYM_FUNC_END(__pi___dma_map_area) SYM_FUNC_ALIAS(__dma_map_area, __pi___dma_map_area) diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index 6719f9efea093..6099c81b93223 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -9,9 +9,9 @@ #include #include #include -#include #include +#include void arch_sync_dma_for_device(phys_addr_t paddr, size_t size, enum dma_data_direction dir) @@ -52,8 +52,5 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, if (iommu) iommu_setup_dma_ops(dev, dma_base, dma_base + size - 1); -#ifdef CONFIG_XEN - if (xen_swiotlb_detect()) - dev->dma_ops = &xen_swiotlb_dma_ops; -#endif + xen_setup_dma_ops(dev); } diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 8ab4035dea274..42f2e9a8616c3 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -1478,6 +1478,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) bpf_jit_binary_free(header); prog->bpf_func = NULL; prog->jited = 0; + prog->jited_len = 0; goto out_off; } bpf_jit_binary_lock_ro(header); diff --git a/arch/arm64/tools/gen-sysreg.awk b/arch/arm64/tools/gen-sysreg.awk index 89bfb74e28de5..5c55509eb43f5 100755 --- a/arch/arm64/tools/gen-sysreg.awk +++ b/arch/arm64/tools/gen-sysreg.awk @@ -253,7 +253,7 @@ END { next } -/0b[01]+/ && block = "Enum" { +/0b[01]+/ && block == "Enum" { expect_fields(2) val = $1 name = $2 diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig index 80657bf83b056..1920d52653b41 100644 --- a/arch/loongarch/Kconfig +++ b/arch/loongarch/Kconfig @@ -343,6 +343,7 @@ config NR_CPUS config NUMA bool "NUMA Support" + select SMP select ACPI_NUMA if ACPI help Say Y to compile the kernel with NUMA (Non-Uniform Memory Access) diff --git a/arch/loongarch/include/asm/branch.h b/arch/loongarch/include/asm/branch.h index 3f33c89f35b48..9a133e4c068e2 100644 --- a/arch/loongarch/include/asm/branch.h +++ b/arch/loongarch/include/asm/branch.h @@ -12,10 +12,9 @@ static inline unsigned long exception_era(struct pt_regs *regs) return regs->csr_era; } -static inline int compute_return_era(struct pt_regs *regs) +static inline void compute_return_era(struct pt_regs *regs) { regs->csr_era += 4; - return 0; } #endif /* _ASM_BRANCH_H */ diff --git a/arch/loongarch/include/asm/hardirq.h b/arch/loongarch/include/asm/hardirq.h index befe8184aa082..0ef3b18f89803 100644 --- a/arch/loongarch/include/asm/hardirq.h +++ b/arch/loongarch/include/asm/hardirq.h @@ -19,7 +19,7 @@ typedef struct { unsigned int __softirq_pending; } ____cacheline_aligned irq_cpustat_t; -DECLARE_PER_CPU_ALIGNED(irq_cpustat_t, irq_stat); +DECLARE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat); #define __ARCH_IRQ_STAT diff --git a/arch/loongarch/include/asm/percpu.h b/arch/loongarch/include/asm/percpu.h index 34f15a6fb1e7b..e6569f18c6ddf 100644 --- a/arch/loongarch/include/asm/percpu.h +++ b/arch/loongarch/include/asm/percpu.h @@ -6,6 +6,7 @@ #define __ASM_PERCPU_H #include +#include /* Use r21 for fast access */ register unsigned long __my_cpu_offset __asm__("$r21"); diff --git a/arch/loongarch/include/asm/pgtable.h b/arch/loongarch/include/asm/pgtable.h index 5dc84d8f18d60..d9e86cfa53e22 100644 --- a/arch/loongarch/include/asm/pgtable.h +++ b/arch/loongarch/include/asm/pgtable.h @@ -426,6 +426,11 @@ static inline void update_mmu_cache_pmd(struct vm_area_struct *vma, #define kern_addr_valid(addr) (1) +static inline unsigned long pmd_pfn(pmd_t pmd) +{ + return (pmd_val(pmd) & _PFN_MASK) >> _PFN_SHIFT; +} + #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* We don't have hardware dirty/accessed bits, generic_pmdp_establish is fine.*/ @@ -497,11 +502,6 @@ static inline pmd_t pmd_mkyoung(pmd_t pmd) return pmd; } -static inline unsigned long pmd_pfn(pmd_t pmd) -{ - return (pmd_val(pmd) & _PFN_MASK) >> _PFN_SHIFT; -} - static inline struct page *pmd_page(pmd_t pmd) { if (pmd_trans_huge(pmd)) diff --git a/arch/loongarch/include/asm/smp.h b/arch/loongarch/include/asm/smp.h index 551e1f37c7053..71189b28bfb27 100644 --- a/arch/loongarch/include/asm/smp.h +++ b/arch/loongarch/include/asm/smp.h @@ -9,10 +9,16 @@ #include #include #include -#include #include #include +extern int smp_num_siblings; +extern int num_processors; +extern int disabled_cpus; +extern cpumask_t cpu_sibling_map[]; +extern cpumask_t cpu_core_map[]; +extern cpumask_t cpu_foreign_map[]; + void loongson3_smp_setup(void); void loongson3_prepare_cpus(unsigned int max_cpus); void loongson3_boot_secondary(int cpu, struct task_struct *idle); @@ -25,26 +31,11 @@ int loongson3_cpu_disable(void); void loongson3_cpu_die(unsigned int cpu); #endif -#ifdef CONFIG_SMP - static inline void plat_smp_setup(void) { loongson3_smp_setup(); } -#else /* !CONFIG_SMP */ - -static inline void plat_smp_setup(void) { } - -#endif /* !CONFIG_SMP */ - -extern int smp_num_siblings; -extern int num_processors; -extern int disabled_cpus; -extern cpumask_t cpu_sibling_map[]; -extern cpumask_t cpu_core_map[]; -extern cpumask_t cpu_foreign_map[]; - static inline int raw_smp_processor_id(void) { #if defined(__VDSO__) diff --git a/arch/loongarch/include/asm/timex.h b/arch/loongarch/include/asm/timex.h index d3ed99a4fdbd9..fb41e9e7a222c 100644 --- a/arch/loongarch/include/asm/timex.h +++ b/arch/loongarch/include/asm/timex.h @@ -12,13 +12,6 @@ #include #include -/* - * Standard way to access the cycle counter. - * Currently only used on SMP for scheduling. - * - * We know that all SMP capable CPUs have cycle counters. - */ - typedef unsigned long cycles_t; #define get_cycles get_cycles diff --git a/arch/loongarch/kernel/acpi.c b/arch/loongarch/kernel/acpi.c index b16c3dea5eeb9..bb729ee8a2370 100644 --- a/arch/loongarch/kernel/acpi.c +++ b/arch/loongarch/kernel/acpi.c @@ -138,6 +138,7 @@ void __init acpi_boot_table_init(void) } } +#ifdef CONFIG_SMP static int set_processor_mask(u32 id, u32 flags) { @@ -166,15 +167,18 @@ static int set_processor_mask(u32 id, u32 flags) return cpu; } +#endif static void __init acpi_process_madt(void) { +#ifdef CONFIG_SMP int i; for (i = 0; i < NR_CPUS; i++) { __cpu_number_map[i] = -1; __cpu_logical_map[i] = -1; } +#endif loongson_sysconf.nr_cpus = num_processors; } diff --git a/arch/loongarch/kernel/cacheinfo.c b/arch/loongarch/kernel/cacheinfo.c index 8c9fe29e98f00..b38f5489d0945 100644 --- a/arch/loongarch/kernel/cacheinfo.c +++ b/arch/loongarch/kernel/cacheinfo.c @@ -4,6 +4,7 @@ * * Copyright (C) 2020-2022 Loongson Technology Corporation Limited */ +#include #include /* Populates leaf and increments to next leaf */ diff --git a/arch/loongarch/kernel/cpu-probe.c b/arch/loongarch/kernel/cpu-probe.c index 6c87ea36b2573..529ab8f44ec6d 100644 --- a/arch/loongarch/kernel/cpu-probe.c +++ b/arch/loongarch/kernel/cpu-probe.c @@ -263,7 +263,7 @@ void cpu_probe(void) c->cputype = CPU_UNKNOWN; c->processor_id = read_cpucfg(LOONGARCH_CPUCFG0); - c->fpu_vers = (read_cpucfg(LOONGARCH_CPUCFG2) >> 3) & 0x3; + c->fpu_vers = (read_cpucfg(LOONGARCH_CPUCFG2) & CPUCFG2_FPVERS) >> 3; c->fpu_csr0 = FPU_CSR_RN; c->fpu_mask = FPU_CSR_RSVD; diff --git a/arch/loongarch/kernel/head.S b/arch/loongarch/kernel/head.S index e596dfcd924b3..d01e62dd414f2 100644 --- a/arch/loongarch/kernel/head.S +++ b/arch/loongarch/kernel/head.S @@ -14,8 +14,6 @@ __REF -SYM_ENTRY(_stext, SYM_L_GLOBAL, SYM_A_NONE) - SYM_CODE_START(kernel_entry) # kernel entry point /* Config direct window and set PG */ diff --git a/arch/loongarch/kernel/irq.c b/arch/loongarch/kernel/irq.c index 4b671d305ede7..b34b8d792aa4d 100644 --- a/arch/loongarch/kernel/irq.c +++ b/arch/loongarch/kernel/irq.c @@ -22,6 +22,8 @@ #include DEFINE_PER_CPU(unsigned long, irq_stack); +DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat); +EXPORT_PER_CPU_SYMBOL(irq_stat); struct irq_domain *cpu_domain; struct irq_domain *liointc_domain; @@ -56,8 +58,11 @@ int arch_show_interrupts(struct seq_file *p, int prec) void __init init_IRQ(void) { - int i, r, ipi_irq; + int i; +#ifdef CONFIG_SMP + int r, ipi_irq; static int ipi_dummy_dev; +#endif unsigned int order = get_order(IRQ_STACK_SIZE); struct page *page; diff --git a/arch/loongarch/kernel/process.c b/arch/loongarch/kernel/process.c index 6d944d65f6002..bfa0dfe8b7d75 100644 --- a/arch/loongarch/kernel/process.c +++ b/arch/loongarch/kernel/process.c @@ -120,10 +120,12 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) /* * Copy architecture-specific thread state */ -int copy_thread(unsigned long clone_flags, unsigned long usp, - unsigned long kthread_arg, struct task_struct *p, unsigned long tls) +int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) { unsigned long childksp; + unsigned long tls = args->tls; + unsigned long usp = args->stack; + unsigned long clone_flags = args->flags; struct pt_regs *childregs, *regs = current_pt_regs(); childksp = (unsigned long)task_stack_page(p) + THREAD_SIZE - 32; @@ -136,12 +138,12 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, p->thread.csr_crmd = csr_read32(LOONGARCH_CSR_CRMD); p->thread.csr_prmd = csr_read32(LOONGARCH_CSR_PRMD); p->thread.csr_ecfg = csr_read32(LOONGARCH_CSR_ECFG); - if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { + if (unlikely(args->fn)) { /* kernel thread */ - p->thread.reg23 = usp; /* fn */ - p->thread.reg24 = kthread_arg; p->thread.reg03 = childksp; - p->thread.reg01 = (unsigned long) ret_from_kernel_thread; + p->thread.reg23 = (unsigned long)args->fn; + p->thread.reg24 = (unsigned long)args->fn_arg; + p->thread.reg01 = (unsigned long)ret_from_kernel_thread; memset(childregs, 0, sizeof(struct pt_regs)); childregs->csr_euen = p->thread.csr_euen; childregs->csr_crmd = p->thread.csr_crmd; diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c index 185e4035811ad..c74860b53375a 100644 --- a/arch/loongarch/kernel/setup.c +++ b/arch/loongarch/kernel/setup.c @@ -39,7 +39,6 @@ #include #include #include -#include #include #define SMBIOS_BIOSSIZE_OFFSET 0x09 @@ -349,8 +348,6 @@ static void __init prefill_possible_map(void) nr_cpu_ids = possible; } -#else -static inline void prefill_possible_map(void) {} #endif void __init setup_arch(char **cmdline_p) @@ -367,8 +364,10 @@ void __init setup_arch(char **cmdline_p) arch_mem_init(cmdline_p); resource_init(); +#ifdef CONFIG_SMP plat_smp_setup(); prefill_possible_map(); +#endif paging_init(); } diff --git a/arch/loongarch/kernel/smp.c b/arch/loongarch/kernel/smp.c index b8c53b755a25a..73cec62504fbe 100644 --- a/arch/loongarch/kernel/smp.c +++ b/arch/loongarch/kernel/smp.c @@ -66,8 +66,6 @@ static cpumask_t cpu_core_setup_map; struct secondary_data cpuboot_data; static DEFINE_PER_CPU(int, cpu_state); -DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat); -EXPORT_PER_CPU_SYMBOL(irq_stat); enum ipi_msg_type { IPI_RESCHEDULE, diff --git a/arch/loongarch/kernel/traps.c b/arch/loongarch/kernel/traps.c index e4060f84a2216..1bf58c65e2bf0 100644 --- a/arch/loongarch/kernel/traps.c +++ b/arch/loongarch/kernel/traps.c @@ -475,8 +475,7 @@ asmlinkage void noinstr do_ri(struct pt_regs *regs) die_if_kernel("Reserved instruction in kernel code", regs); - if (unlikely(compute_return_era(regs) < 0)) - goto out; + compute_return_era(regs); if (unlikely(get_user(opcode, era) < 0)) { status = SIGSEGV; diff --git a/arch/loongarch/kernel/vmlinux.lds.S b/arch/loongarch/kernel/vmlinux.lds.S index 9d508158fe1a6..69c76f26c1c57 100644 --- a/arch/loongarch/kernel/vmlinux.lds.S +++ b/arch/loongarch/kernel/vmlinux.lds.S @@ -37,6 +37,7 @@ SECTIONS HEAD_TEXT_SECTION . = ALIGN(PECOFF_SEGMENT_ALIGN); + _stext = .; .text : { TEXT_TEXT SCHED_TEXT @@ -101,6 +102,7 @@ SECTIONS STABS_DEBUG DWARF_DEBUG + ELF_DETAILS .gptab.sdata : { *(.gptab.data) diff --git a/arch/loongarch/mm/tlb.c b/arch/loongarch/mm/tlb.c index e272f8ac57d16..9818ce11546bc 100644 --- a/arch/loongarch/mm/tlb.c +++ b/arch/loongarch/mm/tlb.c @@ -281,15 +281,16 @@ void setup_tlb_handler(int cpu) if (pcpu_handlers[cpu]) return; - page = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL, get_order(vec_sz)); + page = alloc_pages_node(cpu_to_node(cpu), GFP_ATOMIC, get_order(vec_sz)); if (!page) return; addr = page_address(page); - pcpu_handlers[cpu] = virt_to_phys(addr); + pcpu_handlers[cpu] = (unsigned long)addr; memcpy((void *)addr, (void *)eentry, vec_sz); local_flush_icache_range((unsigned long)addr, (unsigned long)addr + vec_sz); - csr_write64(pcpu_handlers[cpu], LOONGARCH_CSR_TLBRENTRY); + csr_write64(pcpu_handlers[cpu], LOONGARCH_CSR_EENTRY); + csr_write64(pcpu_handlers[cpu], LOONGARCH_CSR_MERRENTRY); csr_write64(pcpu_handlers[cpu] + 80*VECSIZE, LOONGARCH_CSR_TLBRENTRY); } #endif diff --git a/arch/mips/boot/dts/ingenic/x1000.dtsi b/arch/mips/boot/dts/ingenic/x1000.dtsi index b0a034b468bbb..42e69664efd93 100644 --- a/arch/mips/boot/dts/ingenic/x1000.dtsi +++ b/arch/mips/boot/dts/ingenic/x1000.dtsi @@ -111,8 +111,9 @@ clocks = <&cgu X1000_CLK_RTCLK>, <&cgu X1000_CLK_EXCLK>, - <&cgu X1000_CLK_PCLK>; - clock-names = "rtc", "ext", "pclk"; + <&cgu X1000_CLK_PCLK>, + <&cgu X1000_CLK_TCU>; + clock-names = "rtc", "ext", "pclk", "tcu"; interrupt-controller; #interrupt-cells = <1>; diff --git a/arch/mips/boot/dts/ingenic/x1830.dtsi b/arch/mips/boot/dts/ingenic/x1830.dtsi index dbf21afaccb1a..65a5da71c1994 100644 --- a/arch/mips/boot/dts/ingenic/x1830.dtsi +++ b/arch/mips/boot/dts/ingenic/x1830.dtsi @@ -104,8 +104,9 @@ clocks = <&cgu X1830_CLK_RTCLK>, <&cgu X1830_CLK_EXCLK>, - <&cgu X1830_CLK_PCLK>; - clock-names = "rtc", "ext", "pclk"; + <&cgu X1830_CLK_PCLK>, + <&cgu X1830_CLK_TCU>; + clock-names = "rtc", "ext", "pclk", "tcu"; interrupt-controller; #interrupt-cells = <1>; diff --git a/arch/mips/generic/board-ranchu.c b/arch/mips/generic/board-ranchu.c index a89aaad59cb18..930c450418822 100644 --- a/arch/mips/generic/board-ranchu.c +++ b/arch/mips/generic/board-ranchu.c @@ -44,6 +44,7 @@ static __init unsigned int ranchu_measure_hpt_freq(void) __func__); rtc_base = of_iomap(np, 0); + of_node_put(np); if (!rtc_base) panic("%s(): Failed to ioremap Goldfish RTC base!", __func__); diff --git a/arch/mips/lantiq/falcon/sysctrl.c b/arch/mips/lantiq/falcon/sysctrl.c index 5204fc6d6d502..1187729d8cbb1 100644 --- a/arch/mips/lantiq/falcon/sysctrl.c +++ b/arch/mips/lantiq/falcon/sysctrl.c @@ -208,6 +208,12 @@ void __init ltq_soc_init(void) of_address_to_resource(np_sysgpe, 0, &res_sys[2])) panic("Failed to get core resources"); + of_node_put(np_status); + of_node_put(np_ebu); + of_node_put(np_sys1); + of_node_put(np_syseth); + of_node_put(np_sysgpe); + if ((request_mem_region(res_status.start, resource_size(&res_status), res_status.name) < 0) || (request_mem_region(res_ebu.start, resource_size(&res_ebu), diff --git a/arch/mips/lantiq/irq.c b/arch/mips/lantiq/irq.c index b732495f138af..20622bf0a9b3d 100644 --- a/arch/mips/lantiq/irq.c +++ b/arch/mips/lantiq/irq.c @@ -408,6 +408,7 @@ int __init icu_of_init(struct device_node *node, struct device_node *parent) if (!ltq_eiu_membase) panic("Failed to remap eiu memory"); } + of_node_put(eiu_node); return 0; } diff --git a/arch/mips/lantiq/xway/sysctrl.c b/arch/mips/lantiq/xway/sysctrl.c index 084f6caba5f23..d444a1b98a724 100644 --- a/arch/mips/lantiq/xway/sysctrl.c +++ b/arch/mips/lantiq/xway/sysctrl.c @@ -441,6 +441,10 @@ void __init ltq_soc_init(void) of_address_to_resource(np_ebu, 0, &res_ebu)) panic("Failed to get core resources"); + of_node_put(np_pmu); + of_node_put(np_cgu); + of_node_put(np_ebu); + if (!request_mem_region(res_pmu.start, resource_size(&res_pmu), res_pmu.name) || !request_mem_region(res_cgu.start, resource_size(&res_cgu), diff --git a/arch/mips/mti-malta/malta-time.c b/arch/mips/mti-malta/malta-time.c index bbf1e38e14319..2cb708cdf01a0 100644 --- a/arch/mips/mti-malta/malta-time.c +++ b/arch/mips/mti-malta/malta-time.c @@ -214,6 +214,8 @@ static void update_gic_frequency_dt(void) if (of_update_property(node, &gic_frequency_prop) < 0) pr_err("error updating gic frequency property\n"); + + of_node_put(node); } #endif diff --git a/arch/mips/pic32/pic32mzda/init.c b/arch/mips/pic32/pic32mzda/init.c index 129915616763a..d9c8c4e46aff9 100644 --- a/arch/mips/pic32/pic32mzda/init.c +++ b/arch/mips/pic32/pic32mzda/init.c @@ -98,13 +98,18 @@ static int __init pic32_of_prepare_platform_data(struct of_dev_auxdata *lookup) np = of_find_compatible_node(NULL, NULL, lookup->compatible); if (np) { lookup->name = (char *)np->name; - if (lookup->phys_addr) + if (lookup->phys_addr) { + of_node_put(np); continue; + } if (!of_address_to_resource(np, 0, &res)) lookup->phys_addr = res.start; + of_node_put(np); } } + of_node_put(root); + return 0; } diff --git a/arch/mips/pic32/pic32mzda/time.c b/arch/mips/pic32/pic32mzda/time.c index 7174e9abbb1ba..777b515c52c8d 100644 --- a/arch/mips/pic32/pic32mzda/time.c +++ b/arch/mips/pic32/pic32mzda/time.c @@ -32,6 +32,9 @@ static unsigned int pic32_xlate_core_timer_irq(void) goto default_map; irq = irq_of_parse_and_map(node, 0); + + of_node_put(node); + if (!irq) goto default_map; diff --git a/arch/mips/ralink/of.c b/arch/mips/ralink/of.c index 587c7b9987697..ea8072acf8d94 100644 --- a/arch/mips/ralink/of.c +++ b/arch/mips/ralink/of.c @@ -40,6 +40,8 @@ __iomem void *plat_of_remap_node(const char *node) if (of_address_to_resource(np, 0, &res)) panic("Failed to get resource for %s", node); + of_node_put(np); + if (!request_mem_region(res.start, resource_size(&res), res.name)) diff --git a/arch/mips/vr41xx/common/icu.c b/arch/mips/vr41xx/common/icu.c index 7b7f25b4b057e..9240bcdbe74e4 100644 --- a/arch/mips/vr41xx/common/icu.c +++ b/arch/mips/vr41xx/common/icu.c @@ -640,8 +640,6 @@ static int icu_get_irq(unsigned int irq) printk(KERN_ERR "spurious ICU interrupt: %04x,%04x\n", pend1, pend2); - atomic_inc(&irq_err_count); - return -1; } diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index 5f2448dc5a2b2..fa400055b2d50 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -10,6 +10,7 @@ config PARISC select ARCH_WANT_FRAME_POINTERS select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_STRICT_KERNEL_RWX + select ARCH_HAS_STRICT_MODULE_RWX select ARCH_HAS_UBSAN_SANITIZE_ALL select ARCH_HAS_PTE_SPECIAL select ARCH_NO_SG_CHAIN diff --git a/arch/parisc/include/asm/fb.h b/arch/parisc/include/asm/fb.h index d63a2acb91f2b..55d29c4f716e6 100644 --- a/arch/parisc/include/asm/fb.h +++ b/arch/parisc/include/asm/fb.h @@ -12,7 +12,7 @@ static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma, pgprot_val(vma->vm_page_prot) |= _PAGE_NO_CACHE; } -#if defined(CONFIG_STI_CONSOLE) || defined(CONFIG_FB_STI) +#if defined(CONFIG_FB_STI) int fb_is_primary_device(struct fb_info *info); #else static inline int fb_is_primary_device(struct fb_info *info) diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c index c8a11fcecf4c6..a9bc578e4c52e 100644 --- a/arch/parisc/kernel/cache.c +++ b/arch/parisc/kernel/cache.c @@ -722,7 +722,10 @@ void flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned lon return; if (parisc_requires_coherency()) { - flush_user_cache_page(vma, vmaddr); + if (vma->vm_flags & VM_SHARED) + flush_data_cache(); + else + flush_user_cache_page(vma, vmaddr); return; } diff --git a/arch/parisc/math-emu/decode_exc.c b/arch/parisc/math-emu/decode_exc.c index 494ca41df05d0..d41ddb3430b5b 100644 --- a/arch/parisc/math-emu/decode_exc.c +++ b/arch/parisc/math-emu/decode_exc.c @@ -102,7 +102,7 @@ decode_fpu(unsigned int Fpu_register[], unsigned int trap_counts[]) * that happen. Want to keep this overhead low, but still provide * some information to the customer. All exits from this routine * need to restore Fpu_register[0] - */ + */ bflags=(Fpu_register[0] & 0xf8000000); Fpu_register[0] &= 0x07ffffff; diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index be68c1f02b794..c2ce2e60c8f0f 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -223,7 +223,6 @@ config PPC select HAVE_HARDLOCKUP_DETECTOR_PERF if PERF_EVENTS && HAVE_PERF_EVENTS_NMI && !HAVE_HARDLOCKUP_DETECTOR_ARCH select HAVE_HW_BREAKPOINT if PERF_EVENTS && (PPC_BOOK3S || PPC_8xx) select HAVE_IOREMAP_PROT - select HAVE_IRQ_EXIT_ON_IRQ_STACK select HAVE_IRQ_TIME_ACCOUNTING select HAVE_KERNEL_GZIP select HAVE_KERNEL_LZMA if DEFAULT_UIMAGE @@ -786,7 +785,6 @@ config THREAD_SHIFT range 13 15 default "15" if PPC_256K_PAGES default "14" if PPC64 - default "14" if KASAN default "13" help Used to define the stack size. The default is almost always what you diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h index 125328d1b9802..af58f1ed3952e 100644 --- a/arch/powerpc/include/asm/thread_info.h +++ b/arch/powerpc/include/asm/thread_info.h @@ -14,10 +14,16 @@ #ifdef __KERNEL__ -#if defined(CONFIG_VMAP_STACK) && CONFIG_THREAD_SHIFT < PAGE_SHIFT +#ifdef CONFIG_KASAN +#define MIN_THREAD_SHIFT (CONFIG_THREAD_SHIFT + 1) +#else +#define MIN_THREAD_SHIFT CONFIG_THREAD_SHIFT +#endif + +#if defined(CONFIG_VMAP_STACK) && MIN_THREAD_SHIFT < PAGE_SHIFT #define THREAD_SHIFT PAGE_SHIFT #else -#define THREAD_SHIFT CONFIG_THREAD_SHIFT +#define THREAD_SHIFT MIN_THREAD_SHIFT #endif #define THREAD_SIZE (1 << THREAD_SHIFT) diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 2e2a2a9bcf43f..f91f0f29a566a 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -37,6 +37,8 @@ KASAN_SANITIZE_paca.o := n KASAN_SANITIZE_setup_64.o := n KASAN_SANITIZE_mce.o := n KASAN_SANITIZE_mce_power.o := n +KASAN_SANITIZE_udbg.o := n +KASAN_SANITIZE_udbg_16550.o := n # we have to be particularly careful in ppc64 to exclude code that # runs with translations off, as we cannot access the shadow with diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index b62046bf3bb88..0fbda89cd1bb5 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1855,7 +1855,7 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp) tm_reclaim_current(0); #endif - memset(regs->gpr, 0, sizeof(regs->gpr)); + memset(®s->gpr[1], 0, sizeof(regs->gpr) - sizeof(regs->gpr[0])); regs->ctr = 0; regs->link = 0; regs->xer = 0; @@ -2158,12 +2158,12 @@ static unsigned long ___get_wchan(struct task_struct *p) return 0; do { - sp = *(unsigned long *)sp; + sp = READ_ONCE_NOCHECK(*(unsigned long *)sp); if (!validate_sp(sp, p, STACK_FRAME_OVERHEAD) || task_is_running(p)) return 0; if (count > 0) { - ip = ((unsigned long *)sp)[STACK_FRAME_LR_SAVE]; + ip = READ_ONCE_NOCHECK(((unsigned long *)sp)[STACK_FRAME_LR_SAVE]); if (!in_sched_functions(ip)) return ip; } diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 04694ec423f66..13d6cb1888350 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -2302,7 +2302,7 @@ static void __init prom_init_stdout(void) static int __init prom_find_machine_type(void) { - char compat[256]; + static char compat[256] __prombss; int len, i = 0; #ifdef CONFIG_PPC64 phandle rtas; diff --git a/arch/powerpc/kernel/ptrace/ptrace-fpu.c b/arch/powerpc/kernel/ptrace/ptrace-fpu.c index 5dca19361316e..09c49632bfe59 100644 --- a/arch/powerpc/kernel/ptrace/ptrace-fpu.c +++ b/arch/powerpc/kernel/ptrace/ptrace-fpu.c @@ -17,9 +17,13 @@ int ptrace_get_fpr(struct task_struct *child, int index, unsigned long *data) #ifdef CONFIG_PPC_FPU_REGS flush_fp_to_thread(child); - if (fpidx < (PT_FPSCR - PT_FPR0)) - memcpy(data, &child->thread.TS_FPR(fpidx), sizeof(long)); - else + if (fpidx < (PT_FPSCR - PT_FPR0)) { + if (IS_ENABLED(CONFIG_PPC32)) + // On 32-bit the index we are passed refers to 32-bit words + *data = ((u32 *)child->thread.fp_state.fpr)[fpidx]; + else + memcpy(data, &child->thread.TS_FPR(fpidx), sizeof(long)); + } else *data = child->thread.fp_state.fpscr; #else *data = 0; @@ -39,9 +43,13 @@ int ptrace_put_fpr(struct task_struct *child, int index, unsigned long data) #ifdef CONFIG_PPC_FPU_REGS flush_fp_to_thread(child); - if (fpidx < (PT_FPSCR - PT_FPR0)) - memcpy(&child->thread.TS_FPR(fpidx), &data, sizeof(long)); - else + if (fpidx < (PT_FPSCR - PT_FPR0)) { + if (IS_ENABLED(CONFIG_PPC32)) + // On 32-bit the index we are passed refers to 32-bit words + ((u32 *)child->thread.fp_state.fpr)[fpidx] = data; + else + memcpy(&child->thread.TS_FPR(fpidx), &data, sizeof(long)); + } else child->thread.fp_state.fpscr = data; #endif diff --git a/arch/powerpc/kernel/ptrace/ptrace.c b/arch/powerpc/kernel/ptrace/ptrace.c index 4d2dc22d4a2d5..5d7a72b41ae71 100644 --- a/arch/powerpc/kernel/ptrace/ptrace.c +++ b/arch/powerpc/kernel/ptrace/ptrace.c @@ -444,4 +444,7 @@ void __init pt_regs_check(void) * real registers. */ BUILD_BUG_ON(PT_DSCR < sizeof(struct user_pt_regs) / sizeof(unsigned long)); + + // ptrace_get/put_fpr() rely on PPC32 and VSX being incompatible + BUILD_BUG_ON(IS_ENABLED(CONFIG_PPC32) && IS_ENABLED(CONFIG_VSX)); } diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index 9bb43aa53d43e..6931339722948 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -993,8 +993,8 @@ int rtas_call_reentrant(int token, int nargs, int nret, int *outputs, ...) * * Return: A pointer to the specified errorlog or NULL if not found. */ -struct pseries_errorlog *get_pseries_errorlog(struct rtas_error_log *log, - uint16_t section_id) +noinstr struct pseries_errorlog *get_pseries_errorlog(struct rtas_error_log *log, + uint16_t section_id) { struct rtas_ext_event_log_v6 *ext_log = (struct rtas_ext_event_log_v6 *)log->buffer; @@ -1071,7 +1071,7 @@ static struct rtas_filter rtas_filters[] __ro_after_init = { { "get-time-of-day", -1, -1, -1, -1, -1 }, { "ibm,get-vpd", -1, 0, -1, 1, 2 }, { "ibm,lpar-perftools", -1, 2, 3, -1, -1 }, - { "ibm,platform-dump", -1, 4, 5, -1, -1 }, + { "ibm,platform-dump", -1, 4, 5, -1, -1 }, /* Special cased */ { "ibm,read-slot-reset-state", -1, -1, -1, -1, -1 }, { "ibm,scan-log-dump", -1, 0, 1, -1, -1 }, { "ibm,set-dynamic-indicator", -1, 2, -1, -1, -1 }, @@ -1120,6 +1120,15 @@ static bool block_rtas_call(int token, int nargs, size = 1; end = base + size - 1; + + /* + * Special case for ibm,platform-dump - NULL buffer + * address is used to indicate end of dump processing + */ + if (!strcmp(f->name, "ibm,platform-dump") && + base == 0) + return false; + if (!in_rmo_buf(base, end)) goto err; } diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index eb0077b302e24..1a02629ec70b0 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -935,12 +935,6 @@ void __init setup_arch(char **cmdline_p) /* Print various info about the machine that has been gathered so far. */ print_system_info(); - /* Reserve large chunks of memory for use by CMA for KVM. */ - kvm_cma_reserve(); - - /* Reserve large chunks of memory for us by CMA for hugetlb */ - gigantic_hugetlb_cma_reserve(); - klp_init_thread_info(&init_task); setup_initial_init_mm(_stext, _etext, _edata, _end); @@ -955,6 +949,13 @@ void __init setup_arch(char **cmdline_p) initmem_init(); + /* + * Reserve large chunks of memory for use by CMA for KVM and hugetlb. These must + * be called after initmem_init(), so that pageblock_order is initialised. + */ + kvm_cma_reserve(); + gigantic_hugetlb_cma_reserve(); + early_memtest(min_low_pfn << PAGE_SHIFT, max_low_pfn << PAGE_SHIFT); if (ppc_md.setup_arch) diff --git a/arch/powerpc/kexec/crash.c b/arch/powerpc/kexec/crash.c index d85fa9fc6f3ca..80f54723cf6d1 100644 --- a/arch/powerpc/kexec/crash.c +++ b/arch/powerpc/kexec/crash.c @@ -224,7 +224,7 @@ void crash_kexec_secondary(struct pt_regs *regs) /* wait for all the CPUs to hit real mode but timeout if they don't come in */ #if defined(CONFIG_SMP) && defined(CONFIG_PPC64) -static void __maybe_unused crash_kexec_wait_realmode(int cpu) +noinstr static void __maybe_unused crash_kexec_wait_realmode(int cpu) { unsigned int msecs; int i; diff --git a/arch/powerpc/mm/nohash/kaslr_booke.c b/arch/powerpc/mm/nohash/kaslr_booke.c index 1f3f9fedf1bc2..0d04f9d5da8d2 100644 --- a/arch/powerpc/mm/nohash/kaslr_booke.c +++ b/arch/powerpc/mm/nohash/kaslr_booke.c @@ -19,7 +19,6 @@ #include #include #include -#include #include struct regions { @@ -37,10 +36,6 @@ struct regions { int reserved_mem_size_cells; }; -/* Simplified build-specific string for starting entropy. */ -static const char build_str[] = UTS_RELEASE " (" LINUX_COMPILE_BY "@" - LINUX_COMPILE_HOST ") (" LINUX_COMPILER ") " UTS_VERSION; - struct regions __initdata regions; static __init void kaslr_get_cmdline(void *fdt) @@ -71,7 +66,8 @@ static unsigned long __init get_boot_seed(void *fdt) { unsigned long hash = 0; - hash = rotate_xor(hash, build_str, sizeof(build_str)); + /* build-specific string for starting entropy. */ + hash = rotate_xor(hash, linux_banner, strlen(linux_banner)); hash = rotate_xor(hash, fdt, fdt_totalsize(fdt)); return hash; diff --git a/arch/powerpc/platforms/microwatt/microwatt.h b/arch/powerpc/platforms/microwatt/microwatt.h new file mode 100644 index 0000000000000..335417e95e66f --- /dev/null +++ b/arch/powerpc/platforms/microwatt/microwatt.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _MICROWATT_H +#define _MICROWATT_H + +void microwatt_rng_init(void); + +#endif /* _MICROWATT_H */ diff --git a/arch/powerpc/platforms/microwatt/rng.c b/arch/powerpc/platforms/microwatt/rng.c index 7bc4d1cbfaf04..8ece87d005c86 100644 --- a/arch/powerpc/platforms/microwatt/rng.c +++ b/arch/powerpc/platforms/microwatt/rng.c @@ -11,6 +11,7 @@ #include #include #include +#include "microwatt.h" #define DARN_ERR 0xFFFFFFFFFFFFFFFFul @@ -29,7 +30,7 @@ static int microwatt_get_random_darn(unsigned long *v) return 1; } -static __init int rng_init(void) +void __init microwatt_rng_init(void) { unsigned long val; int i; @@ -37,12 +38,7 @@ static __init int rng_init(void) for (i = 0; i < 10; i++) { if (microwatt_get_random_darn(&val)) { ppc_md.get_random_seed = microwatt_get_random_darn; - return 0; + return; } } - - pr_warn("Unable to use DARN for get_random_seed()\n"); - - return -EIO; } -machine_subsys_initcall(, rng_init); diff --git a/arch/powerpc/platforms/microwatt/setup.c b/arch/powerpc/platforms/microwatt/setup.c index 0b02603bdb747..6b32539395a48 100644 --- a/arch/powerpc/platforms/microwatt/setup.c +++ b/arch/powerpc/platforms/microwatt/setup.c @@ -16,6 +16,8 @@ #include #include +#include "microwatt.h" + static void __init microwatt_init_IRQ(void) { xics_init(); @@ -32,10 +34,16 @@ static int __init microwatt_populate(void) } machine_arch_initcall(microwatt, microwatt_populate); +static void __init microwatt_setup_arch(void) +{ + microwatt_rng_init(); +} + define_machine(microwatt) { .name = "microwatt", .probe = microwatt_probe, .init_IRQ = microwatt_init_IRQ, + .setup_arch = microwatt_setup_arch, .progress = udbg_progress, .calibrate_decr = generic_calibrate_decr, }; diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile index 6488b38421999..19f0fc5c6f1b4 100644 --- a/arch/powerpc/platforms/powernv/Makefile +++ b/arch/powerpc/platforms/powernv/Makefile @@ -4,6 +4,7 @@ # in particular, idle code runs a bunch of things in real mode KASAN_SANITIZE_idle.o := n KASAN_SANITIZE_pci-ioda.o := n +KASAN_SANITIZE_pci-ioda-tce.o := n # pnv_machine_check_early KASAN_SANITIZE_setup.o := n diff --git a/arch/powerpc/platforms/powernv/powernv.h b/arch/powerpc/platforms/powernv/powernv.h index e297bf4abfcb8..866efdc103fdd 100644 --- a/arch/powerpc/platforms/powernv/powernv.h +++ b/arch/powerpc/platforms/powernv/powernv.h @@ -42,4 +42,6 @@ ssize_t memcons_copy(struct memcons *mc, char *to, loff_t pos, size_t count); u32 __init memcons_get_size(struct memcons *mc); struct memcons *__init memcons_init(struct device_node *node, const char *mc_prop_name); +void pnv_rng_init(void); + #endif /* _POWERNV_H */ diff --git a/arch/powerpc/platforms/powernv/rng.c b/arch/powerpc/platforms/powernv/rng.c index e3d44b36ae98f..463c78c52cc5d 100644 --- a/arch/powerpc/platforms/powernv/rng.c +++ b/arch/powerpc/platforms/powernv/rng.c @@ -17,6 +17,7 @@ #include #include #include +#include "powernv.h" #define DARN_ERR 0xFFFFFFFFFFFFFFFFul @@ -28,7 +29,6 @@ struct powernv_rng { static DEFINE_PER_CPU(struct powernv_rng *, powernv_rng); - int powernv_hwrng_present(void) { struct powernv_rng *rng; @@ -98,9 +98,6 @@ static int __init initialise_darn(void) return 0; } } - - pr_warn("Unable to use DARN for get_random_seed()\n"); - return -EIO; } @@ -163,32 +160,55 @@ static __init int rng_create(struct device_node *dn) rng_init_per_cpu(rng, dn); - pr_info_once("Registering arch random hook.\n"); - ppc_md.get_random_seed = powernv_get_random_long; return 0; } -static __init int rng_init(void) +static int __init pnv_get_random_long_early(unsigned long *v) { struct device_node *dn; - int rc; + + if (!slab_is_available()) + return 0; + + if (cmpxchg(&ppc_md.get_random_seed, pnv_get_random_long_early, + NULL) != pnv_get_random_long_early) + return 0; for_each_compatible_node(dn, NULL, "ibm,power-rng") { - rc = rng_create(dn); - if (rc) { - pr_err("Failed creating rng for %pOF (%d).\n", - dn, rc); + if (rng_create(dn)) continue; - } - /* Create devices for hwrng driver */ of_platform_device_create(dn, NULL, NULL); } - initialise_darn(); + if (!ppc_md.get_random_seed) + return 0; + return ppc_md.get_random_seed(v); +} + +void __init pnv_rng_init(void) +{ + struct device_node *dn; + /* Prefer darn over the rest. */ + if (!initialise_darn()) + return; + + dn = of_find_compatible_node(NULL, NULL, "ibm,power-rng"); + if (dn) + ppc_md.get_random_seed = pnv_get_random_long_early; + + of_node_put(dn); +} + +static int __init pnv_rng_late_init(void) +{ + unsigned long v; + /* In case it wasn't called during init for some other reason. */ + if (ppc_md.get_random_seed == pnv_get_random_long_early) + pnv_get_random_long_early(&v); return 0; } -machine_subsys_initcall(powernv, rng_init); +machine_subsys_initcall(powernv, pnv_rng_late_init); diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index 824c3ad7a0faf..dac545aa03082 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -203,6 +203,8 @@ static void __init pnv_setup_arch(void) pnv_check_guarded_cores(); /* XXX PMCS */ + + pnv_rng_init(); } static void __init pnv_init(void) diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c index 181b855b30509..82cae08976bcd 100644 --- a/arch/powerpc/platforms/pseries/papr_scm.c +++ b/arch/powerpc/platforms/pseries/papr_scm.c @@ -465,6 +465,9 @@ static int papr_scm_pmu_check_events(struct papr_scm_priv *p, struct nvdimm_pmu u32 available_events; int index, rc = 0; + if (!p->stat_buffer_len) + return -ENOENT; + available_events = (p->stat_buffer_len - sizeof(struct papr_scm_perf_stats)) / sizeof(struct papr_scm_perf_stat); if (available_events == 0) diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h index f5c916c839c98..1d75b7742ef00 100644 --- a/arch/powerpc/platforms/pseries/pseries.h +++ b/arch/powerpc/platforms/pseries/pseries.h @@ -122,4 +122,6 @@ void pseries_lpar_read_hblkrm_characteristics(void); static inline void pseries_lpar_read_hblkrm_characteristics(void) { } #endif +void pseries_rng_init(void); + #endif /* _PSERIES_PSERIES_H */ diff --git a/arch/powerpc/platforms/pseries/rng.c b/arch/powerpc/platforms/pseries/rng.c index 6268545947b83..6ddfdeaace9ef 100644 --- a/arch/powerpc/platforms/pseries/rng.c +++ b/arch/powerpc/platforms/pseries/rng.c @@ -10,6 +10,7 @@ #include #include #include +#include "pseries.h" static int pseries_get_random_long(unsigned long *v) @@ -24,19 +25,13 @@ static int pseries_get_random_long(unsigned long *v) return 0; } -static __init int rng_init(void) +void __init pseries_rng_init(void) { struct device_node *dn; dn = of_find_compatible_node(NULL, NULL, "ibm,random"); if (!dn) - return -ENODEV; - - pr_info("Registering arch random hook.\n"); - + return; ppc_md.get_random_seed = pseries_get_random_long; - of_node_put(dn); - return 0; } -machine_subsys_initcall(pseries, rng_init); diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index afb074269b42b..ee4f1db495159 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -839,6 +839,7 @@ static void __init pSeries_setup_arch(void) } ppc_md.pcibios_root_bridge_prepare = pseries_root_bridge_prepare; + pseries_rng_init(); } static void pseries_panic(char *str) diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index c22f581559484..32ffef9f6e5b4 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -364,8 +364,13 @@ config RISCV_ISA_SVPBMT select RISCV_ALTERNATIVE default y help - Adds support to dynamically detect the presence of the SVPBMT extension - (Supervisor-mode: page-based memory types) and enable its usage. + Adds support to dynamically detect the presence of the SVPBMT + ISA-extension (Supervisor-mode: page-based memory types) and + enable its usage. + + The memory type for a page contains a combination of attributes + that indicate the cacheability, idempotency, and ordering + properties for access to that page. The SVPBMT extension is only available on 64Bit cpus. diff --git a/arch/riscv/Kconfig.erratas b/arch/riscv/Kconfig.erratas index ebfcd5cc6eaf2..457ac72c9b36d 100644 --- a/arch/riscv/Kconfig.erratas +++ b/arch/riscv/Kconfig.erratas @@ -35,6 +35,7 @@ config ERRATA_SIFIVE_CIP_1200 config ERRATA_THEAD bool "T-HEAD errata" + depends on !XIP_KERNEL select RISCV_ALTERNATIVE help All T-HEAD errata Kconfig depend on this Kconfig. Disabling diff --git a/arch/riscv/boot/dts/microchip/mpfs.dtsi b/arch/riscv/boot/dts/microchip/mpfs.dtsi index 8c32591341942..3095d08453a11 100644 --- a/arch/riscv/boot/dts/microchip/mpfs.dtsi +++ b/arch/riscv/boot/dts/microchip/mpfs.dtsi @@ -192,6 +192,15 @@ riscv,ndev = <186>; }; + pdma: dma-controller@3000000 { + compatible = "sifive,fu540-c000-pdma", "sifive,pdma0"; + reg = <0x0 0x3000000 0x0 0x8000>; + interrupt-parent = <&plic>; + interrupts = <5 6>, <7 8>, <9 10>, <11 12>; + dma-channels = <4>; + #dma-cells = <1>; + }; + clkcfg: clkcfg@20002000 { compatible = "microchip,mpfs-clkcfg"; reg = <0x0 0x20002000 0x0 0x1000>, <0x0 0x3E001000 0x0 0x1000>; diff --git a/arch/riscv/include/asm/errata_list.h b/arch/riscv/include/asm/errata_list.h index 9e2888dbb5b13..416ead0f9a655 100644 --- a/arch/riscv/include/asm/errata_list.h +++ b/arch/riscv/include/asm/errata_list.h @@ -75,20 +75,20 @@ asm volatile(ALTERNATIVE( \ "nop\n\t" \ "nop\n\t" \ "nop", \ - "li t3, %2\n\t" \ - "slli t3, t3, %4\n\t" \ + "li t3, %1\n\t" \ + "slli t3, t3, %3\n\t" \ "and t3, %0, t3\n\t" \ "bne t3, zero, 2f\n\t" \ - "li t3, %3\n\t" \ - "slli t3, t3, %4\n\t" \ + "li t3, %2\n\t" \ + "slli t3, t3, %3\n\t" \ "or %0, %0, t3\n\t" \ "2:", THEAD_VENDOR_ID, \ ERRATA_THEAD_PBMT, CONFIG_ERRATA_THEAD_PBMT) \ : "+r"(_val) \ - : "0"(_val), \ - "I"(_PAGE_MTMASK_THEAD >> ALT_THEAD_PBMT_SHIFT), \ + : "I"(_PAGE_MTMASK_THEAD >> ALT_THEAD_PBMT_SHIFT), \ "I"(_PAGE_PMA_THEAD >> ALT_THEAD_PBMT_SHIFT), \ - "I"(ALT_THEAD_PBMT_SHIFT)) + "I"(ALT_THEAD_PBMT_SHIFT) \ + : "t3") #else #define ALT_THEAD_PMA(_val) #endif diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c index a6f62a6d1edd9..12b05ce164bbe 100644 --- a/arch/riscv/kernel/cpufeature.c +++ b/arch/riscv/kernel/cpufeature.c @@ -293,7 +293,6 @@ void __init_or_module riscv_cpufeature_patch_func(struct alt_entry *begin, unsigned int stage) { u32 cpu_req_feature = cpufeature_probe(stage); - u32 cpu_apply_feature = 0; struct alt_entry *alt; u32 tmp; @@ -307,10 +306,8 @@ void __init_or_module riscv_cpufeature_patch_func(struct alt_entry *begin, } tmp = (1U << alt->errata_id); - if (cpu_req_feature & tmp) { + if (cpu_req_feature & tmp) patch_text_nosync(alt->old_ptr, alt->alt_ptr, alt->alt_len); - cpu_apply_feature |= tmp; - } } } #endif diff --git a/arch/riscv/kvm/vmid.c b/arch/riscv/kvm/vmid.c index 9f764df125db9..6cd93995fb65e 100644 --- a/arch/riscv/kvm/vmid.c +++ b/arch/riscv/kvm/vmid.c @@ -97,7 +97,7 @@ void kvm_riscv_gstage_vmid_update(struct kvm_vcpu *vcpu) * We ran out of VMIDs so we increment vmid_version and * start assigning VMIDs from 1. * - * This also means existing VMIDs assignement to all Guest + * This also means existing VMIDs assignment to all Guest * instances is invalid and we have force VMID re-assignement * for all Guest instances. The Guest instances that were not * running will automatically pick-up new VMIDs because will diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index b1a88f6cc3494..91c0b80a8bf04 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -125,6 +125,7 @@ config S390 select CLONE_BACKWARDS2 select DMA_OPS if PCI select DYNAMIC_FTRACE if FUNCTION_TRACER + select GCC12_NO_ARRAY_BOUNDS select GENERIC_ALLOCATOR select GENERIC_CPU_AUTOPROBE select GENERIC_CPU_VULNERABILITIES @@ -768,7 +769,6 @@ menu "Virtualization" config PROTECTED_VIRTUALIZATION_GUEST def_bool n prompt "Protected virtualization guest support" - select ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS help Select this option, if you want to be able to run this kernel as a protected virtualization KVM guest. diff --git a/arch/s390/Makefile b/arch/s390/Makefile index d73611b35164f..495c68a4df1e9 100644 --- a/arch/s390/Makefile +++ b/arch/s390/Makefile @@ -32,15 +32,7 @@ KBUILD_CFLAGS_DECOMPRESSOR += -fno-stack-protector KBUILD_CFLAGS_DECOMPRESSOR += $(call cc-disable-warning, address-of-packed-member) KBUILD_CFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO),-g) KBUILD_CFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO_DWARF4), $(call cc-option, -gdwarf-4,)) - -ifdef CONFIG_CC_IS_GCC - ifeq ($(call cc-ifversion, -ge, 1200, y), y) - ifeq ($(call cc-ifversion, -lt, 1300, y), y) - KBUILD_CFLAGS += $(call cc-disable-warning, array-bounds) - KBUILD_CFLAGS_DECOMPRESSOR += $(call cc-disable-warning, array-bounds) - endif - endif -endif +KBUILD_CFLAGS_DECOMPRESSOR += $(if $(CONFIG_CC_NO_ARRAY_BOUNDS),-Wno-array-bounds) UTS_MACHINE := s390x STACK_SIZE := $(if $(CONFIG_KASAN),65536,16384) diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c index a2c1c55daec03..28124d0fa1d5e 100644 --- a/arch/s390/kernel/crash_dump.c +++ b/arch/s390/kernel/crash_dump.c @@ -219,6 +219,11 @@ ssize_t copy_oldmem_page(struct iov_iter *iter, unsigned long pfn, size_t csize, unsigned long src; int rc; + if (!(iter_is_iovec(iter) || iov_iter_is_kvec(iter))) + return -EINVAL; + /* Multi-segment iterators are not supported */ + if (iter->nr_segs > 1) + return -EINVAL; if (!csize) return 0; src = pfn_to_phys(pfn) + offset; @@ -228,7 +233,10 @@ ssize_t copy_oldmem_page(struct iov_iter *iter, unsigned long pfn, size_t csize, rc = copy_oldmem_user(iter->iov->iov_base, src, csize); else rc = copy_oldmem_kernel(iter->kvec->iov_base, src, csize); - return rc; + if (rc < 0) + return rc; + iov_iter_advance(iter, csize); + return csize; } /* diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c index 483ab5e10164d..f7dd3c849e68c 100644 --- a/arch/s390/kernel/perf_cpum_cf.c +++ b/arch/s390/kernel/perf_cpum_cf.c @@ -516,6 +516,26 @@ static int __hw_perf_event_init(struct perf_event *event, unsigned int type) return err; } +/* Events CPU_CYLCES and INSTRUCTIONS can be submitted with two different + * attribute::type values: + * - PERF_TYPE_HARDWARE: + * - pmu->type: + * Handle both type of invocations identical. They address the same hardware. + * The result is different when event modifiers exclude_kernel and/or + * exclude_user are also set. + */ +static int cpumf_pmu_event_type(struct perf_event *event) +{ + u64 ev = event->attr.config; + + if (cpumf_generic_events_basic[PERF_COUNT_HW_CPU_CYCLES] == ev || + cpumf_generic_events_basic[PERF_COUNT_HW_INSTRUCTIONS] == ev || + cpumf_generic_events_user[PERF_COUNT_HW_CPU_CYCLES] == ev || + cpumf_generic_events_user[PERF_COUNT_HW_INSTRUCTIONS] == ev) + return PERF_TYPE_HARDWARE; + return PERF_TYPE_RAW; +} + static int cpumf_pmu_event_init(struct perf_event *event) { unsigned int type = event->attr.type; @@ -525,7 +545,7 @@ static int cpumf_pmu_event_init(struct perf_event *event) err = __hw_perf_event_init(event, type); else if (event->pmu->type == type) /* Registered as unknown PMU */ - err = __hw_perf_event_init(event, PERF_TYPE_RAW); + err = __hw_perf_event_init(event, cpumf_pmu_event_type(event)); else return -ENOENT; diff --git a/arch/s390/kernel/perf_pai_crypto.c b/arch/s390/kernel/perf_pai_crypto.c index 8c1545946d85e..b38b4ae01589b 100644 --- a/arch/s390/kernel/perf_pai_crypto.c +++ b/arch/s390/kernel/perf_pai_crypto.c @@ -193,8 +193,9 @@ static int paicrypt_event_init(struct perf_event *event) /* PAI crypto PMU registered as PERF_TYPE_RAW, check event type */ if (a->type != PERF_TYPE_RAW && event->pmu->type != a->type) return -ENOENT; - /* PAI crypto event must be valid */ - if (a->config > PAI_CRYPTO_BASE + paicrypt_cnt) + /* PAI crypto event must be in valid range */ + if (a->config < PAI_CRYPTO_BASE || + a->config > PAI_CRYPTO_BASE + paicrypt_cnt) return -EINVAL; /* Allow only CPU wide operation, no process context for now. */ if (event->hw.target || event->cpu == -1) @@ -208,6 +209,12 @@ static int paicrypt_event_init(struct perf_event *event) if (rc) return rc; + /* Event initialization sets last_tag to 0. When later on the events + * are deleted and re-added, do not reset the event count value to zero. + * Events are added, deleted and re-added when 2 or more events + * are active at the same time. + */ + event->hw.last_tag = 0; cpump->event = event; event->destroy = paicrypt_event_destroy; @@ -242,9 +249,12 @@ static void paicrypt_start(struct perf_event *event, int flags) { u64 sum; - sum = paicrypt_getall(event); /* Get current value */ - local64_set(&event->hw.prev_count, sum); - local64_set(&event->count, 0); + if (!event->hw.last_tag) { + event->hw.last_tag = 1; + sum = paicrypt_getall(event); /* Get current value */ + local64_set(&event->count, 0); + local64_set(&event->hw.prev_count, sum); + } } static int paicrypt_add(struct perf_event *event, int flags) diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index 6fb6bf64326f9..6a0ac00d5a42b 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -31,6 +31,7 @@ #include #include #include +#include #include #include #include @@ -168,22 +169,14 @@ bool force_dma_unencrypted(struct device *dev) return is_prot_virt_guest(); } -#ifdef CONFIG_ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS - -int arch_has_restricted_virtio_memory_access(void) -{ - return is_prot_virt_guest(); -} -EXPORT_SYMBOL(arch_has_restricted_virtio_memory_access); - -#endif - /* protected virtualization */ static void pv_init(void) { if (!is_prot_virt_guest()) return; + platform_set(PLATFORM_VIRTIO_RESTRICTED_MEM_ACCESS); + /* make sure bounce buffers are shared */ swiotlb_init(true, SWIOTLB_FORCE | SWIOTLB_VERBOSE); swiotlb_update_mem_attributes(); diff --git a/arch/um/drivers/virt-pci.c b/arch/um/drivers/virt-pci.c index 5c092a9153eae..0278470231841 100644 --- a/arch/um/drivers/virt-pci.c +++ b/arch/um/drivers/virt-pci.c @@ -544,6 +544,8 @@ static int um_pci_init_vqs(struct um_pci_device *dev) dev->cmd_vq = vqs[0]; dev->irq_vq = vqs[1]; + virtio_device_ready(dev->vdev); + for (i = 0; i < NUM_IRQ_MSGS; i++) { void *msg = kzalloc(MAX_IRQ_MSG_SIZE, GFP_KERNEL); @@ -587,7 +589,7 @@ static int um_pci_virtio_probe(struct virtio_device *vdev) dev->irq = irq_alloc_desc(numa_node_id()); if (dev->irq < 0) { err = dev->irq; - goto error; + goto err_reset; } um_pci_devices[free].dev = dev; vdev->priv = dev; @@ -604,6 +606,9 @@ static int um_pci_virtio_probe(struct virtio_device *vdev) um_pci_rescan(); return 0; +err_reset: + virtio_reset_device(vdev); + vdev->config->del_vqs(vdev); error: mutex_unlock(&um_pci_mtx); kfree(dev); diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 9783ebc4e0212..be0b95e51df66 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1542,7 +1542,6 @@ config X86_CPA_STATISTICS config X86_MEM_ENCRYPT select ARCH_HAS_FORCE_DMA_UNENCRYPTED select DYNAMIC_PHYSICAL_MASK - select ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS def_bool n config AMD_MEM_ENCRYPT diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c index 03deb4d6920d5..928dcf7a20d98 100644 --- a/arch/x86/coco/tdx/tdx.c +++ b/arch/x86/coco/tdx/tdx.c @@ -124,6 +124,51 @@ static u64 get_cc_mask(void) return BIT_ULL(gpa_width - 1); } +/* + * The TDX module spec states that #VE may be injected for a limited set of + * reasons: + * + * - Emulation of the architectural #VE injection on EPT violation; + * + * - As a result of guest TD execution of a disallowed instruction, + * a disallowed MSR access, or CPUID virtualization; + * + * - A notification to the guest TD about anomalous behavior; + * + * The last one is opt-in and is not used by the kernel. + * + * The Intel Software Developer's Manual describes cases when instruction + * length field can be used in section "Information for VM Exits Due to + * Instruction Execution". + * + * For TDX, it ultimately means GET_VEINFO provides reliable instruction length + * information if #VE occurred due to instruction execution, but not for EPT + * violations. + */ +static int ve_instr_len(struct ve_info *ve) +{ + switch (ve->exit_reason) { + case EXIT_REASON_HLT: + case EXIT_REASON_MSR_READ: + case EXIT_REASON_MSR_WRITE: + case EXIT_REASON_CPUID: + case EXIT_REASON_IO_INSTRUCTION: + /* It is safe to use ve->instr_len for #VE due instructions */ + return ve->instr_len; + case EXIT_REASON_EPT_VIOLATION: + /* + * For EPT violations, ve->insn_len is not defined. For those, + * the kernel must decode instructions manually and should not + * be using this function. + */ + WARN_ONCE(1, "ve->instr_len is not defined for EPT violations"); + return 0; + default: + WARN_ONCE(1, "Unexpected #VE-type: %lld\n", ve->exit_reason); + return ve->instr_len; + } +} + static u64 __cpuidle __halt(const bool irq_disabled, const bool do_sti) { struct tdx_hypercall_args args = { @@ -147,7 +192,7 @@ static u64 __cpuidle __halt(const bool irq_disabled, const bool do_sti) return __tdx_hypercall(&args, do_sti ? TDX_HCALL_ISSUE_STI : 0); } -static bool handle_halt(void) +static int handle_halt(struct ve_info *ve) { /* * Since non safe halt is mainly used in CPU offlining @@ -158,9 +203,9 @@ static bool handle_halt(void) const bool do_sti = false; if (__halt(irq_disabled, do_sti)) - return false; + return -EIO; - return true; + return ve_instr_len(ve); } void __cpuidle tdx_safe_halt(void) @@ -180,7 +225,7 @@ void __cpuidle tdx_safe_halt(void) WARN_ONCE(1, "HLT instruction emulation failed\n"); } -static bool read_msr(struct pt_regs *regs) +static int read_msr(struct pt_regs *regs, struct ve_info *ve) { struct tdx_hypercall_args args = { .r10 = TDX_HYPERCALL_STANDARD, @@ -194,14 +239,14 @@ static bool read_msr(struct pt_regs *regs) * (GHCI), section titled "TDG.VP.VMCALL". */ if (__tdx_hypercall(&args, TDX_HCALL_HAS_OUTPUT)) - return false; + return -EIO; regs->ax = lower_32_bits(args.r11); regs->dx = upper_32_bits(args.r11); - return true; + return ve_instr_len(ve); } -static bool write_msr(struct pt_regs *regs) +static int write_msr(struct pt_regs *regs, struct ve_info *ve) { struct tdx_hypercall_args args = { .r10 = TDX_HYPERCALL_STANDARD, @@ -215,10 +260,13 @@ static bool write_msr(struct pt_regs *regs) * can be found in TDX Guest-Host-Communication Interface * (GHCI) section titled "TDG.VP.VMCALL". */ - return !__tdx_hypercall(&args, 0); + if (__tdx_hypercall(&args, 0)) + return -EIO; + + return ve_instr_len(ve); } -static bool handle_cpuid(struct pt_regs *regs) +static int handle_cpuid(struct pt_regs *regs, struct ve_info *ve) { struct tdx_hypercall_args args = { .r10 = TDX_HYPERCALL_STANDARD, @@ -236,7 +284,7 @@ static bool handle_cpuid(struct pt_regs *regs) */ if (regs->ax < 0x40000000 || regs->ax > 0x4FFFFFFF) { regs->ax = regs->bx = regs->cx = regs->dx = 0; - return true; + return ve_instr_len(ve); } /* @@ -245,7 +293,7 @@ static bool handle_cpuid(struct pt_regs *regs) * (GHCI), section titled "VP.VMCALL". */ if (__tdx_hypercall(&args, TDX_HCALL_HAS_OUTPUT)) - return false; + return -EIO; /* * As per TDX GHCI CPUID ABI, r12-r15 registers contain contents of @@ -257,7 +305,7 @@ static bool handle_cpuid(struct pt_regs *regs) regs->cx = args.r14; regs->dx = args.r15; - return true; + return ve_instr_len(ve); } static bool mmio_read(int size, unsigned long addr, unsigned long *val) @@ -283,10 +331,10 @@ static bool mmio_write(int size, unsigned long addr, unsigned long val) EPT_WRITE, addr, val); } -static bool handle_mmio(struct pt_regs *regs, struct ve_info *ve) +static int handle_mmio(struct pt_regs *regs, struct ve_info *ve) { + unsigned long *reg, val, vaddr; char buffer[MAX_INSN_SIZE]; - unsigned long *reg, val; struct insn insn = {}; enum mmio_type mmio; int size, extend_size; @@ -294,34 +342,49 @@ static bool handle_mmio(struct pt_regs *regs, struct ve_info *ve) /* Only in-kernel MMIO is supported */ if (WARN_ON_ONCE(user_mode(regs))) - return false; + return -EFAULT; if (copy_from_kernel_nofault(buffer, (void *)regs->ip, MAX_INSN_SIZE)) - return false; + return -EFAULT; if (insn_decode(&insn, buffer, MAX_INSN_SIZE, INSN_MODE_64)) - return false; + return -EINVAL; mmio = insn_decode_mmio(&insn, &size); if (WARN_ON_ONCE(mmio == MMIO_DECODE_FAILED)) - return false; + return -EINVAL; if (mmio != MMIO_WRITE_IMM && mmio != MMIO_MOVS) { reg = insn_get_modrm_reg_ptr(&insn, regs); if (!reg) - return false; + return -EINVAL; } - ve->instr_len = insn.length; + /* + * Reject EPT violation #VEs that split pages. + * + * MMIO accesses are supposed to be naturally aligned and therefore + * never cross page boundaries. Seeing split page accesses indicates + * a bug or a load_unaligned_zeropad() that stepped into an MMIO page. + * + * load_unaligned_zeropad() will recover using exception fixups. + */ + vaddr = (unsigned long)insn_get_addr_ref(&insn, regs); + if (vaddr / PAGE_SIZE != (vaddr + size - 1) / PAGE_SIZE) + return -EFAULT; /* Handle writes first */ switch (mmio) { case MMIO_WRITE: memcpy(&val, reg, size); - return mmio_write(size, ve->gpa, val); + if (!mmio_write(size, ve->gpa, val)) + return -EIO; + return insn.length; case MMIO_WRITE_IMM: val = insn.immediate.value; - return mmio_write(size, ve->gpa, val); + if (!mmio_write(size, ve->gpa, val)) + return -EIO; + return insn.length; case MMIO_READ: case MMIO_READ_ZERO_EXTEND: case MMIO_READ_SIGN_EXTEND: @@ -334,15 +397,15 @@ static bool handle_mmio(struct pt_regs *regs, struct ve_info *ve) * decoded or handled properly. It was likely not using io.h * helpers or accessed MMIO accidentally. */ - return false; + return -EINVAL; default: WARN_ONCE(1, "Unknown insn_decode_mmio() decode value?"); - return false; + return -EINVAL; } /* Handle reads */ if (!mmio_read(size, ve->gpa, &val)) - return false; + return -EIO; switch (mmio) { case MMIO_READ: @@ -364,13 +427,13 @@ static bool handle_mmio(struct pt_regs *regs, struct ve_info *ve) default: /* All other cases has to be covered with the first switch() */ WARN_ON_ONCE(1); - return false; + return -EINVAL; } if (extend_size) memset(reg, extend_val, extend_size); memcpy(reg, &val, size); - return true; + return insn.length; } static bool handle_in(struct pt_regs *regs, int size, int port) @@ -421,13 +484,14 @@ static bool handle_out(struct pt_regs *regs, int size, int port) * * Return True on success or False on failure. */ -static bool handle_io(struct pt_regs *regs, u32 exit_qual) +static int handle_io(struct pt_regs *regs, struct ve_info *ve) { + u32 exit_qual = ve->exit_qual; int size, port; - bool in; + bool in, ret; if (VE_IS_IO_STRING(exit_qual)) - return false; + return -EIO; in = VE_IS_IO_IN(exit_qual); size = VE_GET_IO_SIZE(exit_qual); @@ -435,9 +499,13 @@ static bool handle_io(struct pt_regs *regs, u32 exit_qual) if (in) - return handle_in(regs, size, port); + ret = handle_in(regs, size, port); else - return handle_out(regs, size, port); + ret = handle_out(regs, size, port); + if (!ret) + return -EIO; + + return ve_instr_len(ve); } /* @@ -447,13 +515,19 @@ static bool handle_io(struct pt_regs *regs, u32 exit_qual) __init bool tdx_early_handle_ve(struct pt_regs *regs) { struct ve_info ve; + int insn_len; tdx_get_ve_info(&ve); if (ve.exit_reason != EXIT_REASON_IO_INSTRUCTION) return false; - return handle_io(regs, ve.exit_qual); + insn_len = handle_io(regs, &ve); + if (insn_len < 0) + return false; + + regs->ip += insn_len; + return true; } void tdx_get_ve_info(struct ve_info *ve) @@ -486,54 +560,65 @@ void tdx_get_ve_info(struct ve_info *ve) ve->instr_info = upper_32_bits(out.r10); } -/* Handle the user initiated #VE */ -static bool virt_exception_user(struct pt_regs *regs, struct ve_info *ve) +/* + * Handle the user initiated #VE. + * + * On success, returns the number of bytes RIP should be incremented (>=0) + * or -errno on error. + */ +static int virt_exception_user(struct pt_regs *regs, struct ve_info *ve) { switch (ve->exit_reason) { case EXIT_REASON_CPUID: - return handle_cpuid(regs); + return handle_cpuid(regs, ve); default: pr_warn("Unexpected #VE: %lld\n", ve->exit_reason); - return false; + return -EIO; } } -/* Handle the kernel #VE */ -static bool virt_exception_kernel(struct pt_regs *regs, struct ve_info *ve) +/* + * Handle the kernel #VE. + * + * On success, returns the number of bytes RIP should be incremented (>=0) + * or -errno on error. + */ +static int virt_exception_kernel(struct pt_regs *regs, struct ve_info *ve) { switch (ve->exit_reason) { case EXIT_REASON_HLT: - return handle_halt(); + return handle_halt(ve); case EXIT_REASON_MSR_READ: - return read_msr(regs); + return read_msr(regs, ve); case EXIT_REASON_MSR_WRITE: - return write_msr(regs); + return write_msr(regs, ve); case EXIT_REASON_CPUID: - return handle_cpuid(regs); + return handle_cpuid(regs, ve); case EXIT_REASON_EPT_VIOLATION: return handle_mmio(regs, ve); case EXIT_REASON_IO_INSTRUCTION: - return handle_io(regs, ve->exit_qual); + return handle_io(regs, ve); default: pr_warn("Unexpected #VE: %lld\n", ve->exit_reason); - return false; + return -EIO; } } bool tdx_handle_virt_exception(struct pt_regs *regs, struct ve_info *ve) { - bool ret; + int insn_len; if (user_mode(regs)) - ret = virt_exception_user(regs, ve); + insn_len = virt_exception_user(regs, ve); else - ret = virt_exception_kernel(regs, ve); + insn_len = virt_exception_kernel(regs, ve); + if (insn_len < 0) + return false; /* After successful #VE handling, move the IP */ - if (ret) - regs->ip += ve->instr_len; + regs->ip += insn_len; - return ret; + return true; } static bool tdx_tlb_flush_required(bool private) diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 8b392b6b7b934..3de6d8b533672 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include @@ -405,6 +406,11 @@ void __init hyperv_init(void) } if (hv_isolation_type_snp()) { + /* Negotiate GHCB Version. */ + if (!hv_ghcb_negotiate_protocol()) + hv_ghcb_terminate(SEV_TERM_SET_GEN, + GHCB_SEV_ES_PROT_UNSUPPORTED); + hv_ghcb_pg = alloc_percpu(union hv_ghcb *); if (!hv_ghcb_pg) goto free_vp_assist_page; diff --git a/arch/x86/hyperv/ivm.c b/arch/x86/hyperv/ivm.c index 2b994117581e2..1dbcbd9da74d4 100644 --- a/arch/x86/hyperv/ivm.c +++ b/arch/x86/hyperv/ivm.c @@ -53,6 +53,8 @@ union hv_ghcb { } hypercall; } __packed __aligned(HV_HYP_PAGE_SIZE); +static u16 hv_ghcb_version __ro_after_init; + u64 hv_ghcb_hypercall(u64 control, void *input, void *output, u32 input_size) { union hv_ghcb *hv_ghcb; @@ -96,12 +98,85 @@ u64 hv_ghcb_hypercall(u64 control, void *input, void *output, u32 input_size) return status; } +static inline u64 rd_ghcb_msr(void) +{ + return __rdmsr(MSR_AMD64_SEV_ES_GHCB); +} + +static inline void wr_ghcb_msr(u64 val) +{ + native_wrmsrl(MSR_AMD64_SEV_ES_GHCB, val); +} + +static enum es_result hv_ghcb_hv_call(struct ghcb *ghcb, u64 exit_code, + u64 exit_info_1, u64 exit_info_2) +{ + /* Fill in protocol and format specifiers */ + ghcb->protocol_version = hv_ghcb_version; + ghcb->ghcb_usage = GHCB_DEFAULT_USAGE; + + ghcb_set_sw_exit_code(ghcb, exit_code); + ghcb_set_sw_exit_info_1(ghcb, exit_info_1); + ghcb_set_sw_exit_info_2(ghcb, exit_info_2); + + VMGEXIT(); + + if (ghcb->save.sw_exit_info_1 & GENMASK_ULL(31, 0)) + return ES_VMM_ERROR; + else + return ES_OK; +} + +void hv_ghcb_terminate(unsigned int set, unsigned int reason) +{ + u64 val = GHCB_MSR_TERM_REQ; + + /* Tell the hypervisor what went wrong. */ + val |= GHCB_SEV_TERM_REASON(set, reason); + + /* Request Guest Termination from Hypvervisor */ + wr_ghcb_msr(val); + VMGEXIT(); + + while (true) + asm volatile("hlt\n" : : : "memory"); +} + +bool hv_ghcb_negotiate_protocol(void) +{ + u64 ghcb_gpa; + u64 val; + + /* Save ghcb page gpa. */ + ghcb_gpa = rd_ghcb_msr(); + + /* Do the GHCB protocol version negotiation */ + wr_ghcb_msr(GHCB_MSR_SEV_INFO_REQ); + VMGEXIT(); + val = rd_ghcb_msr(); + + if (GHCB_MSR_INFO(val) != GHCB_MSR_SEV_INFO_RESP) + return false; + + if (GHCB_MSR_PROTO_MAX(val) < GHCB_PROTOCOL_MIN || + GHCB_MSR_PROTO_MIN(val) > GHCB_PROTOCOL_MAX) + return false; + + hv_ghcb_version = min_t(size_t, GHCB_MSR_PROTO_MAX(val), + GHCB_PROTOCOL_MAX); + + /* Write ghcb page back after negotiating protocol. */ + wr_ghcb_msr(ghcb_gpa); + VMGEXIT(); + + return true; +} + void hv_ghcb_msr_write(u64 msr, u64 value) { union hv_ghcb *hv_ghcb; void **ghcb_base; unsigned long flags; - struct es_em_ctxt ctxt; if (!hv_ghcb_pg) return; @@ -120,8 +195,7 @@ void hv_ghcb_msr_write(u64 msr, u64 value) ghcb_set_rax(&hv_ghcb->ghcb, lower_32_bits(value)); ghcb_set_rdx(&hv_ghcb->ghcb, upper_32_bits(value)); - if (sev_es_ghcb_hv_call(&hv_ghcb->ghcb, false, &ctxt, - SVM_EXIT_MSR, 1, 0)) + if (hv_ghcb_hv_call(&hv_ghcb->ghcb, SVM_EXIT_MSR, 1, 0)) pr_warn("Fail to write msr via ghcb %llx.\n", msr); local_irq_restore(flags); @@ -133,7 +207,6 @@ void hv_ghcb_msr_read(u64 msr, u64 *value) union hv_ghcb *hv_ghcb; void **ghcb_base; unsigned long flags; - struct es_em_ctxt ctxt; /* Check size of union hv_ghcb here. */ BUILD_BUG_ON(sizeof(union hv_ghcb) != HV_HYP_PAGE_SIZE); @@ -152,8 +225,7 @@ void hv_ghcb_msr_read(u64 msr, u64 *value) } ghcb_set_rcx(&hv_ghcb->ghcb, msr); - if (sev_es_ghcb_hv_call(&hv_ghcb->ghcb, false, &ctxt, - SVM_EXIT_MSR, 0, 0)) + if (hv_ghcb_hv_call(&hv_ghcb->ghcb, SVM_EXIT_MSR, 0, 0)) pr_warn("Fail to read msr via ghcb %llx.\n", msr); else *value = (u64)lower_32_bits(hv_ghcb->ghcb.save.rax) diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 393f2bbb5e3a8..03acc823838a7 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -446,5 +446,6 @@ #define X86_BUG_TAA X86_BUG(22) /* CPU is affected by TSX Async Abort(TAA) */ #define X86_BUG_ITLB_MULTIHIT X86_BUG(23) /* CPU may incur MCE during certain page attribute changes */ #define X86_BUG_SRBDS X86_BUG(24) /* CPU may leak RNG bits if not mitigated */ +#define X86_BUG_MMIO_STALE_DATA X86_BUG(25) /* CPU is affected by Processor MMIO Stale Data vulnerabilities */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/e820/api.h b/arch/x86/include/asm/e820/api.h index 5a39ed59b6db7..e8f58ddd06d97 100644 --- a/arch/x86/include/asm/e820/api.h +++ b/arch/x86/include/asm/e820/api.h @@ -4,9 +4,6 @@ #include -struct device; -struct resource; - extern struct e820_table *e820_table; extern struct e820_table *e820_table_kexec; extern struct e820_table *e820_table_firmware; @@ -46,8 +43,6 @@ extern void e820__register_nosave_regions(unsigned long limit_pfn); extern int e820__get_entry_type(u64 start, u64 end); -extern void remove_e820_regions(struct device *dev, struct resource *avail); - /* * Returns true iff the specified range [start,end) is completely contained inside * the ISA region. diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 71943dce691ed..9636742a80f29 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -323,7 +323,7 @@ static inline u32 efi64_convert_status(efi_status_t status) #define __efi64_argmap_get_memory_space_descriptor(phys, desc) \ (__efi64_split(phys), (desc)) -#define __efi64_argmap_set_memory_space_descriptor(phys, size, flags) \ +#define __efi64_argmap_set_memory_space_attributes(phys, size, flags) \ (__efi64_split(phys), __efi64_split(size), __efi64_split(flags)) /* diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 959d66b9be94d..9217bd6cf0d14 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -653,6 +653,7 @@ struct kvm_vcpu_arch { u64 ia32_misc_enable_msr; u64 smbase; u64 smi_count; + bool at_instruction_boundary; bool tpr_access_reporting; bool xsaves_enabled; bool xfd_no_write_intercept; @@ -1046,14 +1047,77 @@ struct kvm_x86_msr_filter { }; enum kvm_apicv_inhibit { + + /********************************************************************/ + /* INHIBITs that are relevant to both Intel's APICv and AMD's AVIC. */ + /********************************************************************/ + + /* + * APIC acceleration is disabled by a module parameter + * and/or not supported in hardware. + */ APICV_INHIBIT_REASON_DISABLE, + + /* + * APIC acceleration is inhibited because AutoEOI feature is + * being used by a HyperV guest. + */ APICV_INHIBIT_REASON_HYPERV, + + /* + * APIC acceleration is inhibited because the userspace didn't yet + * enable the kernel/split irqchip. + */ + APICV_INHIBIT_REASON_ABSENT, + + /* APIC acceleration is inhibited because KVM_GUESTDBG_BLOCKIRQ + * (out of band, debug measure of blocking all interrupts on this vCPU) + * was enabled, to avoid AVIC/APICv bypassing it. + */ + APICV_INHIBIT_REASON_BLOCKIRQ, + + /* + * For simplicity, the APIC acceleration is inhibited + * first time either APIC ID or APIC base are changed by the guest + * from their reset values. + */ + APICV_INHIBIT_REASON_APIC_ID_MODIFIED, + APICV_INHIBIT_REASON_APIC_BASE_MODIFIED, + + /******************************************************/ + /* INHIBITs that are relevant only to the AMD's AVIC. */ + /******************************************************/ + + /* + * AVIC is inhibited on a vCPU because it runs a nested guest. + * + * This is needed because unlike APICv, the peers of this vCPU + * cannot use the doorbell mechanism to signal interrupts via AVIC when + * a vCPU runs nested. + */ APICV_INHIBIT_REASON_NESTED, + + /* + * On SVM, the wait for the IRQ window is implemented with pending vIRQ, + * which cannot be injected when the AVIC is enabled, thus AVIC + * is inhibited while KVM waits for IRQ window. + */ APICV_INHIBIT_REASON_IRQWIN, + + /* + * PIT (i8254) 're-inject' mode, relies on EOI intercept, + * which AVIC doesn't support for edge triggered interrupts. + */ APICV_INHIBIT_REASON_PIT_REINJ, + + /* + * AVIC is inhibited because the guest has x2apic in its CPUID. + */ APICV_INHIBIT_REASON_X2APIC, - APICV_INHIBIT_REASON_BLOCKIRQ, - APICV_INHIBIT_REASON_ABSENT, + + /* + * AVIC is disabled because SEV doesn't support it. + */ APICV_INHIBIT_REASON_SEV, }; @@ -1300,6 +1364,8 @@ struct kvm_vcpu_stat { u64 nested_run; u64 directed_yield_attempted; u64 directed_yield_successful; + u64 preemption_reported; + u64 preemption_other; u64 guest_mode; }; diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index a82f603d4312d..61f0c206bff0f 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -179,9 +179,13 @@ int hv_set_mem_host_visibility(unsigned long addr, int numpages, bool visible); #ifdef CONFIG_AMD_MEM_ENCRYPT void hv_ghcb_msr_write(u64 msr, u64 value); void hv_ghcb_msr_read(u64 msr, u64 *value); +bool hv_ghcb_negotiate_protocol(void); +void hv_ghcb_terminate(unsigned int set, unsigned int reason); #else static inline void hv_ghcb_msr_write(u64 msr, u64 value) {} static inline void hv_ghcb_msr_read(u64 msr, u64 *value) {} +static inline bool hv_ghcb_negotiate_protocol(void) { return false; } +static inline void hv_ghcb_terminate(unsigned int set, unsigned int reason) {} #endif extern bool hv_isolation_type_snp(void); diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 403e83b4adc88..d27e0581b7777 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -116,6 +116,30 @@ * Not susceptible to * TSX Async Abort (TAA) vulnerabilities. */ +#define ARCH_CAP_SBDR_SSDP_NO BIT(13) /* + * Not susceptible to SBDR and SSDP + * variants of Processor MMIO stale data + * vulnerabilities. + */ +#define ARCH_CAP_FBSDP_NO BIT(14) /* + * Not susceptible to FBSDP variant of + * Processor MMIO stale data + * vulnerabilities. + */ +#define ARCH_CAP_PSDP_NO BIT(15) /* + * Not susceptible to PSDP variant of + * Processor MMIO stale data + * vulnerabilities. + */ +#define ARCH_CAP_FB_CLEAR BIT(17) /* + * VERW clears CPU fill buffer + * even on MDS_NO CPUs. + */ +#define ARCH_CAP_FB_CLEAR_CTRL BIT(18) /* + * MSR_IA32_MCU_OPT_CTRL[FB_CLEAR_DIS] + * bit available to control VERW + * behavior. + */ #define MSR_IA32_FLUSH_CMD 0x0000010b #define L1D_FLUSH BIT(0) /* @@ -133,6 +157,7 @@ #define MSR_IA32_MCU_OPT_CTRL 0x00000123 #define RNGDS_MITG_DIS BIT(0) /* SRBDS support */ #define RTM_ALLOW BIT(1) /* TSX development mode */ +#define FB_CLEAR_DIS BIT(3) /* CPU Fill buffer clear disable */ #define MSR_IA32_SYSENTER_CS 0x00000174 #define MSR_IA32_SYSENTER_ESP 0x00000175 diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index acbaeaf83b61a..da251a5645b0e 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -269,6 +269,8 @@ DECLARE_STATIC_KEY_FALSE(mds_idle_clear); DECLARE_STATIC_KEY_FALSE(switch_mm_cond_l1d_flush); +DECLARE_STATIC_KEY_FALSE(mmio_stale_data_clear); + #include /** diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h index f52a886d35cf8..70533fdcbf02c 100644 --- a/arch/x86/include/asm/pci_x86.h +++ b/arch/x86/include/asm/pci_x86.h @@ -69,6 +69,8 @@ void pcibios_scan_specific_bus(int busn); /* pci-irq.c */ +struct pci_dev; + struct irq_info { u8 bus, devfn; /* Bus, device and function */ struct { @@ -246,3 +248,9 @@ static inline void mmio_config_writel(void __iomem *pos, u32 val) # define x86_default_pci_init_irq NULL # define x86_default_pci_fixup_irqs NULL #endif + +#if defined(CONFIG_PCI) && defined(CONFIG_ACPI) +extern bool pci_use_e820; +#else +#define pci_use_e820 false +#endif diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index 7590ac2570b96..f8b9ee97a8913 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -108,19 +108,16 @@ extern unsigned long _brk_end; void *extend_brk(size_t size, size_t align); /* - * Reserve space in the brk section. The name must be unique within the file, - * and somewhat descriptive. The size is in bytes. + * Reserve space in the .brk section, which is a block of memory from which the + * caller is allowed to allocate very early (before even memblock is available) + * by calling extend_brk(). All allocated memory will be eventually converted + * to memblock. Any leftover unallocated memory will be freed. * - * The allocation is done using inline asm (rather than using a section - * attribute on a normal variable) in order to allow the use of @nobits, so - * that it doesn't take up any space in the vmlinux file. + * The size is in bytes. */ -#define RESERVE_BRK(name, size) \ - asm(".pushsection .brk_reservation,\"aw\",@nobits\n\t" \ - ".brk." #name ":\n\t" \ - ".skip " __stringify(size) "\n\t" \ - ".size .brk." #name ", " __stringify(size) "\n\t" \ - ".popsection\n\t") +#define RESERVE_BRK(name, size) \ + __section(".bss..brk") __aligned(1) __used \ + static char __brk_##name[size] extern void probe_roms(void); #ifdef __i386__ @@ -133,12 +130,19 @@ asmlinkage void __init x86_64_start_reservations(char *real_mode_data); #endif /* __i386__ */ #endif /* _SETUP */ -#else -#define RESERVE_BRK(name,sz) \ - .pushsection .brk_reservation,"aw",@nobits; \ -.brk.name: \ -1: .skip sz; \ - .size .brk.name,.-1b; \ + +#else /* __ASSEMBLY */ + +.macro __RESERVE_BRK name, size + .pushsection .bss..brk, "aw" +SYM_DATA_START(__brk_\name) + .skip \size +SYM_DATA_END(__brk_\name) .popsection +.endm + +#define RESERVE_BRK(name, size) __RESERVE_BRK name, size + #endif /* __ASSEMBLY__ */ + #endif /* _ASM_X86_SETUP_H */ diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 35f222aa66bfc..913e593a3b45f 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -439,7 +439,7 @@ do { \ [ptr] "+m" (*_ptr), \ [old] "+a" (__old) \ : [new] ltype (__new) \ - : "memory", "cc"); \ + : "memory"); \ if (unlikely(__err)) \ goto label; \ if (unlikely(!success)) \ diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 03364dc40d8d9..4c8b6ae802ac3 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -36,10 +36,6 @@ KCSAN_SANITIZE := n OBJECT_FILES_NON_STANDARD_test_nx.o := y -ifdef CONFIG_FRAME_POINTER -OBJECT_FILES_NON_STANDARD_ftrace_$(BITS).o := y -endif - # If instrumentation of this dir is enabled, boot hangs during first second. # Probably could be more selective here, but note that files related to irqs, # boot, dumpstack/stacktrace, etc are either non-interesting or can lead to diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index d879a6c93609a..74c62cc47a5ff 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -41,8 +41,10 @@ static void __init spectre_v2_select_mitigation(void); static void __init ssb_select_mitigation(void); static void __init l1tf_select_mitigation(void); static void __init mds_select_mitigation(void); -static void __init mds_print_mitigation(void); +static void __init md_clear_update_mitigation(void); +static void __init md_clear_select_mitigation(void); static void __init taa_select_mitigation(void); +static void __init mmio_select_mitigation(void); static void __init srbds_select_mitigation(void); static void __init l1d_flush_select_mitigation(void); @@ -85,6 +87,10 @@ EXPORT_SYMBOL_GPL(mds_idle_clear); */ DEFINE_STATIC_KEY_FALSE(switch_mm_cond_l1d_flush); +/* Controls CPU Fill buffer clear before KVM guest MMIO accesses */ +DEFINE_STATIC_KEY_FALSE(mmio_stale_data_clear); +EXPORT_SYMBOL_GPL(mmio_stale_data_clear); + void __init check_bugs(void) { identify_boot_cpu(); @@ -117,17 +123,10 @@ void __init check_bugs(void) spectre_v2_select_mitigation(); ssb_select_mitigation(); l1tf_select_mitigation(); - mds_select_mitigation(); - taa_select_mitigation(); + md_clear_select_mitigation(); srbds_select_mitigation(); l1d_flush_select_mitigation(); - /* - * As MDS and TAA mitigations are inter-related, print MDS - * mitigation until after TAA mitigation selection is done. - */ - mds_print_mitigation(); - arch_smt_update(); #ifdef CONFIG_X86_32 @@ -267,14 +266,6 @@ static void __init mds_select_mitigation(void) } } -static void __init mds_print_mitigation(void) -{ - if (!boot_cpu_has_bug(X86_BUG_MDS) || cpu_mitigations_off()) - return; - - pr_info("%s\n", mds_strings[mds_mitigation]); -} - static int __init mds_cmdline(char *str) { if (!boot_cpu_has_bug(X86_BUG_MDS)) @@ -329,7 +320,7 @@ static void __init taa_select_mitigation(void) /* TSX previously disabled by tsx=off */ if (!boot_cpu_has(X86_FEATURE_RTM)) { taa_mitigation = TAA_MITIGATION_TSX_DISABLED; - goto out; + return; } if (cpu_mitigations_off()) { @@ -343,7 +334,7 @@ static void __init taa_select_mitigation(void) */ if (taa_mitigation == TAA_MITIGATION_OFF && mds_mitigation == MDS_MITIGATION_OFF) - goto out; + return; if (boot_cpu_has(X86_FEATURE_MD_CLEAR)) taa_mitigation = TAA_MITIGATION_VERW; @@ -375,18 +366,6 @@ static void __init taa_select_mitigation(void) if (taa_nosmt || cpu_mitigations_auto_nosmt()) cpu_smt_disable(false); - - /* - * Update MDS mitigation, if necessary, as the mds_user_clear is - * now enabled for TAA mitigation. - */ - if (mds_mitigation == MDS_MITIGATION_OFF && - boot_cpu_has_bug(X86_BUG_MDS)) { - mds_mitigation = MDS_MITIGATION_FULL; - mds_select_mitigation(); - } -out: - pr_info("%s\n", taa_strings[taa_mitigation]); } static int __init tsx_async_abort_parse_cmdline(char *str) @@ -410,6 +389,151 @@ static int __init tsx_async_abort_parse_cmdline(char *str) } early_param("tsx_async_abort", tsx_async_abort_parse_cmdline); +#undef pr_fmt +#define pr_fmt(fmt) "MMIO Stale Data: " fmt + +enum mmio_mitigations { + MMIO_MITIGATION_OFF, + MMIO_MITIGATION_UCODE_NEEDED, + MMIO_MITIGATION_VERW, +}; + +/* Default mitigation for Processor MMIO Stale Data vulnerabilities */ +static enum mmio_mitigations mmio_mitigation __ro_after_init = MMIO_MITIGATION_VERW; +static bool mmio_nosmt __ro_after_init = false; + +static const char * const mmio_strings[] = { + [MMIO_MITIGATION_OFF] = "Vulnerable", + [MMIO_MITIGATION_UCODE_NEEDED] = "Vulnerable: Clear CPU buffers attempted, no microcode", + [MMIO_MITIGATION_VERW] = "Mitigation: Clear CPU buffers", +}; + +static void __init mmio_select_mitigation(void) +{ + u64 ia32_cap; + + if (!boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA) || + cpu_mitigations_off()) { + mmio_mitigation = MMIO_MITIGATION_OFF; + return; + } + + if (mmio_mitigation == MMIO_MITIGATION_OFF) + return; + + ia32_cap = x86_read_arch_cap_msr(); + + /* + * Enable CPU buffer clear mitigation for host and VMM, if also affected + * by MDS or TAA. Otherwise, enable mitigation for VMM only. + */ + if (boot_cpu_has_bug(X86_BUG_MDS) || (boot_cpu_has_bug(X86_BUG_TAA) && + boot_cpu_has(X86_FEATURE_RTM))) + static_branch_enable(&mds_user_clear); + else + static_branch_enable(&mmio_stale_data_clear); + + /* + * If Processor-MMIO-Stale-Data bug is present and Fill Buffer data can + * be propagated to uncore buffers, clearing the Fill buffers on idle + * is required irrespective of SMT state. + */ + if (!(ia32_cap & ARCH_CAP_FBSDP_NO)) + static_branch_enable(&mds_idle_clear); + + /* + * Check if the system has the right microcode. + * + * CPU Fill buffer clear mitigation is enumerated by either an explicit + * FB_CLEAR or by the presence of both MD_CLEAR and L1D_FLUSH on MDS + * affected systems. + */ + if ((ia32_cap & ARCH_CAP_FB_CLEAR) || + (boot_cpu_has(X86_FEATURE_MD_CLEAR) && + boot_cpu_has(X86_FEATURE_FLUSH_L1D) && + !(ia32_cap & ARCH_CAP_MDS_NO))) + mmio_mitigation = MMIO_MITIGATION_VERW; + else + mmio_mitigation = MMIO_MITIGATION_UCODE_NEEDED; + + if (mmio_nosmt || cpu_mitigations_auto_nosmt()) + cpu_smt_disable(false); +} + +static int __init mmio_stale_data_parse_cmdline(char *str) +{ + if (!boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA)) + return 0; + + if (!str) + return -EINVAL; + + if (!strcmp(str, "off")) { + mmio_mitigation = MMIO_MITIGATION_OFF; + } else if (!strcmp(str, "full")) { + mmio_mitigation = MMIO_MITIGATION_VERW; + } else if (!strcmp(str, "full,nosmt")) { + mmio_mitigation = MMIO_MITIGATION_VERW; + mmio_nosmt = true; + } + + return 0; +} +early_param("mmio_stale_data", mmio_stale_data_parse_cmdline); + +#undef pr_fmt +#define pr_fmt(fmt) "" fmt + +static void __init md_clear_update_mitigation(void) +{ + if (cpu_mitigations_off()) + return; + + if (!static_key_enabled(&mds_user_clear)) + goto out; + + /* + * mds_user_clear is now enabled. Update MDS, TAA and MMIO Stale Data + * mitigation, if necessary. + */ + if (mds_mitigation == MDS_MITIGATION_OFF && + boot_cpu_has_bug(X86_BUG_MDS)) { + mds_mitigation = MDS_MITIGATION_FULL; + mds_select_mitigation(); + } + if (taa_mitigation == TAA_MITIGATION_OFF && + boot_cpu_has_bug(X86_BUG_TAA)) { + taa_mitigation = TAA_MITIGATION_VERW; + taa_select_mitigation(); + } + if (mmio_mitigation == MMIO_MITIGATION_OFF && + boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA)) { + mmio_mitigation = MMIO_MITIGATION_VERW; + mmio_select_mitigation(); + } +out: + if (boot_cpu_has_bug(X86_BUG_MDS)) + pr_info("MDS: %s\n", mds_strings[mds_mitigation]); + if (boot_cpu_has_bug(X86_BUG_TAA)) + pr_info("TAA: %s\n", taa_strings[taa_mitigation]); + if (boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA)) + pr_info("MMIO Stale Data: %s\n", mmio_strings[mmio_mitigation]); +} + +static void __init md_clear_select_mitigation(void) +{ + mds_select_mitigation(); + taa_select_mitigation(); + mmio_select_mitigation(); + + /* + * As MDS, TAA and MMIO Stale Data mitigations are inter-related, update + * and print their mitigation after MDS, TAA and MMIO Stale Data + * mitigation selection is done. + */ + md_clear_update_mitigation(); +} + #undef pr_fmt #define pr_fmt(fmt) "SRBDS: " fmt @@ -478,11 +602,13 @@ static void __init srbds_select_mitigation(void) return; /* - * Check to see if this is one of the MDS_NO systems supporting - * TSX that are only exposed to SRBDS when TSX is enabled. + * Check to see if this is one of the MDS_NO systems supporting TSX that + * are only exposed to SRBDS when TSX is enabled or when CPU is affected + * by Processor MMIO Stale Data vulnerability. */ ia32_cap = x86_read_arch_cap_msr(); - if ((ia32_cap & ARCH_CAP_MDS_NO) && !boot_cpu_has(X86_FEATURE_RTM)) + if ((ia32_cap & ARCH_CAP_MDS_NO) && !boot_cpu_has(X86_FEATURE_RTM) && + !boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA)) srbds_mitigation = SRBDS_MITIGATION_TSX_OFF; else if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) srbds_mitigation = SRBDS_MITIGATION_HYPERVISOR; @@ -1116,6 +1242,8 @@ static void update_indir_branch_cond(void) /* Update the static key controlling the MDS CPU buffer clear in idle */ static void update_mds_branch_idle(void) { + u64 ia32_cap = x86_read_arch_cap_msr(); + /* * Enable the idle clearing if SMT is active on CPUs which are * affected only by MSBDS and not any other MDS variant. @@ -1127,14 +1255,17 @@ static void update_mds_branch_idle(void) if (!boot_cpu_has_bug(X86_BUG_MSBDS_ONLY)) return; - if (sched_smt_active()) + if (sched_smt_active()) { static_branch_enable(&mds_idle_clear); - else + } else if (mmio_mitigation == MMIO_MITIGATION_OFF || + (ia32_cap & ARCH_CAP_FBSDP_NO)) { static_branch_disable(&mds_idle_clear); + } } #define MDS_MSG_SMT "MDS CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/mds.html for more details.\n" #define TAA_MSG_SMT "TAA CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/tsx_async_abort.html for more details.\n" +#define MMIO_MSG_SMT "MMIO Stale Data CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/processor_mmio_stale_data.html for more details.\n" void cpu_bugs_smt_update(void) { @@ -1179,6 +1310,16 @@ void cpu_bugs_smt_update(void) break; } + switch (mmio_mitigation) { + case MMIO_MITIGATION_VERW: + case MMIO_MITIGATION_UCODE_NEEDED: + if (sched_smt_active()) + pr_warn_once(MMIO_MSG_SMT); + break; + case MMIO_MITIGATION_OFF: + break; + } + mutex_unlock(&spec_ctrl_mutex); } @@ -1781,6 +1922,20 @@ static ssize_t tsx_async_abort_show_state(char *buf) sched_smt_active() ? "vulnerable" : "disabled"); } +static ssize_t mmio_stale_data_show_state(char *buf) +{ + if (mmio_mitigation == MMIO_MITIGATION_OFF) + return sysfs_emit(buf, "%s\n", mmio_strings[mmio_mitigation]); + + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) { + return sysfs_emit(buf, "%s; SMT Host state unknown\n", + mmio_strings[mmio_mitigation]); + } + + return sysfs_emit(buf, "%s; SMT %s\n", mmio_strings[mmio_mitigation], + sched_smt_active() ? "vulnerable" : "disabled"); +} + static char *stibp_state(void) { if (spectre_v2_in_eibrs_mode(spectre_v2_enabled)) @@ -1881,6 +2036,9 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr case X86_BUG_SRBDS: return srbds_show_state(buf); + case X86_BUG_MMIO_STALE_DATA: + return mmio_stale_data_show_state(buf); + default: break; } @@ -1932,4 +2090,9 @@ ssize_t cpu_show_srbds(struct device *dev, struct device_attribute *attr, char * { return cpu_show_common(dev, attr, buf, X86_BUG_SRBDS); } + +ssize_t cpu_show_mmio_stale_data(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_MMIO_STALE_DATA); +} #endif diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index c296cb1c01133..4730b0a58f24a 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1211,18 +1211,42 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { X86_FEATURE_ANY, issues) #define SRBDS BIT(0) +/* CPU is affected by X86_BUG_MMIO_STALE_DATA */ +#define MMIO BIT(1) +/* CPU is affected by Shared Buffers Data Sampling (SBDS), a variant of X86_BUG_MMIO_STALE_DATA */ +#define MMIO_SBDS BIT(2) static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_INTEL_STEPPINGS(IVYBRIDGE, X86_STEPPING_ANY, SRBDS), VULNBL_INTEL_STEPPINGS(HASWELL, X86_STEPPING_ANY, SRBDS), VULNBL_INTEL_STEPPINGS(HASWELL_L, X86_STEPPING_ANY, SRBDS), VULNBL_INTEL_STEPPINGS(HASWELL_G, X86_STEPPING_ANY, SRBDS), + VULNBL_INTEL_STEPPINGS(HASWELL_X, BIT(2) | BIT(4), MMIO), + VULNBL_INTEL_STEPPINGS(BROADWELL_D, X86_STEPPINGS(0x3, 0x5), MMIO), VULNBL_INTEL_STEPPINGS(BROADWELL_G, X86_STEPPING_ANY, SRBDS), + VULNBL_INTEL_STEPPINGS(BROADWELL_X, X86_STEPPING_ANY, MMIO), VULNBL_INTEL_STEPPINGS(BROADWELL, X86_STEPPING_ANY, SRBDS), + VULNBL_INTEL_STEPPINGS(SKYLAKE_L, X86_STEPPINGS(0x3, 0x3), SRBDS | MMIO), VULNBL_INTEL_STEPPINGS(SKYLAKE_L, X86_STEPPING_ANY, SRBDS), + VULNBL_INTEL_STEPPINGS(SKYLAKE_X, BIT(3) | BIT(4) | BIT(6) | + BIT(7) | BIT(0xB), MMIO), + VULNBL_INTEL_STEPPINGS(SKYLAKE, X86_STEPPINGS(0x3, 0x3), SRBDS | MMIO), VULNBL_INTEL_STEPPINGS(SKYLAKE, X86_STEPPING_ANY, SRBDS), - VULNBL_INTEL_STEPPINGS(KABYLAKE_L, X86_STEPPINGS(0x0, 0xC), SRBDS), - VULNBL_INTEL_STEPPINGS(KABYLAKE, X86_STEPPINGS(0x0, 0xD), SRBDS), + VULNBL_INTEL_STEPPINGS(KABYLAKE_L, X86_STEPPINGS(0x9, 0xC), SRBDS | MMIO), + VULNBL_INTEL_STEPPINGS(KABYLAKE_L, X86_STEPPINGS(0x0, 0x8), SRBDS), + VULNBL_INTEL_STEPPINGS(KABYLAKE, X86_STEPPINGS(0x9, 0xD), SRBDS | MMIO), + VULNBL_INTEL_STEPPINGS(KABYLAKE, X86_STEPPINGS(0x0, 0x8), SRBDS), + VULNBL_INTEL_STEPPINGS(ICELAKE_L, X86_STEPPINGS(0x5, 0x5), MMIO | MMIO_SBDS), + VULNBL_INTEL_STEPPINGS(ICELAKE_D, X86_STEPPINGS(0x1, 0x1), MMIO), + VULNBL_INTEL_STEPPINGS(ICELAKE_X, X86_STEPPINGS(0x4, 0x6), MMIO), + VULNBL_INTEL_STEPPINGS(COMETLAKE, BIT(2) | BIT(3) | BIT(5), MMIO | MMIO_SBDS), + VULNBL_INTEL_STEPPINGS(COMETLAKE_L, X86_STEPPINGS(0x1, 0x1), MMIO | MMIO_SBDS), + VULNBL_INTEL_STEPPINGS(COMETLAKE_L, X86_STEPPINGS(0x0, 0x0), MMIO), + VULNBL_INTEL_STEPPINGS(LAKEFIELD, X86_STEPPINGS(0x1, 0x1), MMIO | MMIO_SBDS), + VULNBL_INTEL_STEPPINGS(ROCKETLAKE, X86_STEPPINGS(0x1, 0x1), MMIO), + VULNBL_INTEL_STEPPINGS(ATOM_TREMONT, X86_STEPPINGS(0x1, 0x1), MMIO | MMIO_SBDS), + VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_D, X86_STEPPING_ANY, MMIO), + VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_L, X86_STEPPINGS(0x0, 0x0), MMIO | MMIO_SBDS), {} }; @@ -1243,6 +1267,13 @@ u64 x86_read_arch_cap_msr(void) return ia32_cap; } +static bool arch_cap_mmio_immune(u64 ia32_cap) +{ + return (ia32_cap & ARCH_CAP_FBSDP_NO && + ia32_cap & ARCH_CAP_PSDP_NO && + ia32_cap & ARCH_CAP_SBDR_SSDP_NO); +} + static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) { u64 ia32_cap = x86_read_arch_cap_msr(); @@ -1296,12 +1327,27 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) /* * SRBDS affects CPUs which support RDRAND or RDSEED and are listed * in the vulnerability blacklist. + * + * Some of the implications and mitigation of Shared Buffers Data + * Sampling (SBDS) are similar to SRBDS. Give SBDS same treatment as + * SRBDS. */ if ((cpu_has(c, X86_FEATURE_RDRAND) || cpu_has(c, X86_FEATURE_RDSEED)) && - cpu_matches(cpu_vuln_blacklist, SRBDS)) + cpu_matches(cpu_vuln_blacklist, SRBDS | MMIO_SBDS)) setup_force_cpu_bug(X86_BUG_SRBDS); + /* + * Processor MMIO Stale Data bug enumeration + * + * Affected CPU list is generally enough to enumerate the vulnerability, + * but for virtualization case check for ARCH_CAP MSR bits also, VMM may + * not want the guest to enumerate the bug. + */ + if (cpu_matches(cpu_vuln_blacklist, MMIO) && + !arch_cap_mmio_immune(ia32_cap)) + setup_force_cpu_bug(X86_BUG_MMIO_STALE_DATA); + if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN)) return; diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S index 4ec13608d3c62..dfeb227de5617 100644 --- a/arch/x86/kernel/ftrace_64.S +++ b/arch/x86/kernel/ftrace_64.S @@ -175,6 +175,7 @@ SYM_INNER_LABEL(ftrace_caller_end, SYM_L_GLOBAL) jmp ftrace_epilogue SYM_FUNC_END(ftrace_caller); +STACK_FRAME_NON_STANDARD_FP(ftrace_caller) SYM_FUNC_START(ftrace_epilogue) /* @@ -282,6 +283,7 @@ SYM_INNER_LABEL(ftrace_regs_caller_end, SYM_L_GLOBAL) jmp ftrace_epilogue SYM_FUNC_END(ftrace_regs_caller) +STACK_FRAME_NON_STANDARD_FP(ftrace_regs_caller) #else /* ! CONFIG_DYNAMIC_FTRACE */ @@ -311,10 +313,14 @@ trace: jmp ftrace_stub SYM_FUNC_END(__fentry__) EXPORT_SYMBOL(__fentry__) +STACK_FRAME_NON_STANDARD_FP(__fentry__) + #endif /* CONFIG_DYNAMIC_FTRACE */ #ifdef CONFIG_FUNCTION_GRAPH_TRACER -SYM_FUNC_START(return_to_handler) +SYM_CODE_START(return_to_handler) + UNWIND_HINT_EMPTY + ANNOTATE_NOENDBR subq $16, %rsp /* Save the return values */ @@ -339,7 +345,6 @@ SYM_FUNC_START(return_to_handler) int3 .Ldo_rop: mov %rdi, (%rsp) - UNWIND_HINT_FUNC RET -SYM_FUNC_END(return_to_handler) +SYM_CODE_END(return_to_handler) #endif diff --git a/arch/x86/kernel/resource.c b/arch/x86/kernel/resource.c index db2b350a37b77..bba1abd05bfeb 100644 --- a/arch/x86/kernel/resource.c +++ b/arch/x86/kernel/resource.c @@ -1,7 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 -#include #include +#include #include +#include static void resource_clip(struct resource *res, resource_size_t start, resource_size_t end) @@ -24,14 +25,14 @@ static void resource_clip(struct resource *res, resource_size_t start, res->start = end + 1; } -void remove_e820_regions(struct device *dev, struct resource *avail) +static void remove_e820_regions(struct resource *avail) { int i; struct e820_entry *entry; u64 e820_start, e820_end; struct resource orig = *avail; - if (!(avail->flags & IORESOURCE_MEM)) + if (!pci_use_e820) return; for (i = 0; i < e820_table->nr_entries; i++) { @@ -41,7 +42,7 @@ void remove_e820_regions(struct device *dev, struct resource *avail) resource_clip(avail, e820_start, e820_end); if (orig.start != avail->start || orig.end != avail->end) { - dev_info(dev, "clipped %pR to %pR for e820 entry [mem %#010Lx-%#010Lx]\n", + pr_info("clipped %pR to %pR for e820 entry [mem %#010Lx-%#010Lx]\n", &orig, avail, e820_start, e820_end); orig = *avail; } @@ -55,6 +56,9 @@ void arch_remove_reservations(struct resource *avail) * the low 1MB unconditionally, as this area is needed for some ISA * cards requiring a memory range, e.g. the i82365 PCMCIA controller. */ - if (avail->flags & IORESOURCE_MEM) + if (avail->flags & IORESOURCE_MEM) { resource_clip(avail, BIOS_ROM_BASE, BIOS_ROM_END); + + remove_e820_regions(avail); + } } diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 3ebb85327edb1..bd6c6fd373aee 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -67,11 +67,6 @@ RESERVE_BRK(dmi_alloc, 65536); #endif -/* - * Range of the BSS area. The size of the BSS area is determined - * at link time, with RESERVE_BRK() facility reserving additional - * chunks. - */ unsigned long _brk_start = (unsigned long)__brk_base; unsigned long _brk_end = (unsigned long)__brk_base; diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index f5f6dc2e80072..81aba718ecd56 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -385,10 +385,10 @@ SECTIONS __end_of_kernel_reserve = .; . = ALIGN(PAGE_SIZE); - .brk : AT(ADDR(.brk) - LOAD_OFFSET) { + .brk (NOLOAD) : AT(ADDR(.brk) - LOAD_OFFSET) { __brk_base = .; . += 64 * 1024; /* 64k alignment slop space */ - *(.brk_reservation) /* areas brk users have reserved */ + *(.bss..brk) /* areas brk users have reserved */ __brk_limit = .; } diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index f1bdac3f5aa8a..0e68b4c937fcd 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -2039,6 +2039,19 @@ static void apic_manage_nmi_watchdog(struct kvm_lapic *apic, u32 lvt0_val) } } +static void kvm_lapic_xapic_id_updated(struct kvm_lapic *apic) +{ + struct kvm *kvm = apic->vcpu->kvm; + + if (KVM_BUG_ON(apic_x2apic_mode(apic), kvm)) + return; + + if (kvm_xapic_id(apic) == apic->vcpu->vcpu_id) + return; + + kvm_set_apicv_inhibit(apic->vcpu->kvm, APICV_INHIBIT_REASON_APIC_ID_MODIFIED); +} + static int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) { int ret = 0; @@ -2047,10 +2060,12 @@ static int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) switch (reg) { case APIC_ID: /* Local APIC ID */ - if (!apic_x2apic_mode(apic)) + if (!apic_x2apic_mode(apic)) { kvm_apic_set_xapic_id(apic, val >> 24); - else + kvm_lapic_xapic_id_updated(apic); + } else { ret = 1; + } break; case APIC_TASKPRI: @@ -2336,8 +2351,10 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value) MSR_IA32_APICBASE_BASE; if ((value & MSR_IA32_APICBASE_ENABLE) && - apic->base_address != APIC_DEFAULT_PHYS_BASE) - pr_warn_once("APIC base relocation is unsupported by KVM"); + apic->base_address != APIC_DEFAULT_PHYS_BASE) { + kvm_set_apicv_inhibit(apic->vcpu->kvm, + APICV_INHIBIT_REASON_APIC_BASE_MODIFIED); + } } void kvm_apic_update_apicv(struct kvm_vcpu *vcpu) @@ -2648,6 +2665,8 @@ static int kvm_apic_state_fixup(struct kvm_vcpu *vcpu, icr = __kvm_lapic_get_reg64(s->regs, APIC_ICR); __kvm_lapic_set_reg(s->regs, APIC_ICR2, icr >> 32); } + } else { + kvm_lapic_xapic_id_updated(vcpu->arch.apic); } return 0; diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index f4653688fa6db..17252f39bd7c2 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -3411,7 +3411,7 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu) root = mmu_alloc_root(vcpu, i << (30 - PAGE_SHIFT), i << 30, PT32_ROOT_LEVEL, true); mmu->pae_root[i] = root | PT_PRESENT_MASK | - shadow_me_mask; + shadow_me_value; } mmu->root.hpa = __pa(mmu->pae_root); } else { @@ -5179,7 +5179,7 @@ static void __kvm_mmu_free_obsolete_roots(struct kvm *kvm, struct kvm_mmu *mmu) roots_to_free |= KVM_MMU_ROOT_CURRENT; for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) { - if (is_obsolete_root(kvm, mmu->root.hpa)) + if (is_obsolete_root(kvm, mmu->prev_roots[i].hpa)) roots_to_free |= KVM_MMU_ROOT_PREVIOUS(i); } diff --git a/arch/x86/kvm/mmu/tdp_iter.c b/arch/x86/kvm/mmu/tdp_iter.c index 6d3b3e5a5533b..ee4802d7b36cd 100644 --- a/arch/x86/kvm/mmu/tdp_iter.c +++ b/arch/x86/kvm/mmu/tdp_iter.c @@ -145,6 +145,15 @@ static bool try_step_up(struct tdp_iter *iter) return true; } +/* + * Step the iterator back up a level in the paging structure. Should only be + * used when the iterator is below the root level. + */ +void tdp_iter_step_up(struct tdp_iter *iter) +{ + WARN_ON(!try_step_up(iter)); +} + /* * Step to the next SPTE in a pre-order traversal of the paging structure. * To get to the next SPTE, the iterator either steps down towards the goal diff --git a/arch/x86/kvm/mmu/tdp_iter.h b/arch/x86/kvm/mmu/tdp_iter.h index f0af385c56e03..adfca0cf94d3a 100644 --- a/arch/x86/kvm/mmu/tdp_iter.h +++ b/arch/x86/kvm/mmu/tdp_iter.h @@ -114,5 +114,6 @@ void tdp_iter_start(struct tdp_iter *iter, struct kvm_mmu_page *root, int min_level, gfn_t next_last_level_gfn); void tdp_iter_next(struct tdp_iter *iter); void tdp_iter_restart(struct tdp_iter *iter); +void tdp_iter_step_up(struct tdp_iter *iter); #endif /* __KVM_X86_MMU_TDP_ITER_H */ diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 841feaa48be5e..7b9265d671310 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -1742,12 +1742,12 @@ static void zap_collapsible_spte_range(struct kvm *kvm, gfn_t start = slot->base_gfn; gfn_t end = start + slot->npages; struct tdp_iter iter; + int max_mapping_level; kvm_pfn_t pfn; rcu_read_lock(); tdp_root_for_each_pte(iter, root, start, end) { -retry: if (tdp_mmu_iter_cond_resched(kvm, &iter, false, true)) continue; @@ -1755,15 +1755,41 @@ static void zap_collapsible_spte_range(struct kvm *kvm, !is_last_spte(iter.old_spte, iter.level)) continue; + /* + * This is a leaf SPTE. Check if the PFN it maps can + * be mapped at a higher level. + */ pfn = spte_to_pfn(iter.old_spte); - if (kvm_is_reserved_pfn(pfn) || - iter.level >= kvm_mmu_max_mapping_level(kvm, slot, iter.gfn, - pfn, PG_LEVEL_NUM)) + + if (kvm_is_reserved_pfn(pfn)) continue; + max_mapping_level = kvm_mmu_max_mapping_level(kvm, slot, + iter.gfn, pfn, PG_LEVEL_NUM); + + WARN_ON(max_mapping_level < iter.level); + + /* + * If this page is already mapped at the highest + * viable level, there's nothing more to do. + */ + if (max_mapping_level == iter.level) + continue; + + /* + * The page can be remapped at a higher level, so step + * up to zap the parent SPTE. + */ + while (max_mapping_level > iter.level) + tdp_iter_step_up(&iter); + /* Note, a successful atomic zap also does a remote TLB flush. */ - if (tdp_mmu_zap_spte_atomic(kvm, &iter)) - goto retry; + tdp_mmu_zap_spte_atomic(kvm, &iter); + + /* + * If the atomic zap fails, the iter will recurse back into + * the same subtree to retry. + */ } rcu_read_unlock(); diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index 54fe03714f8a6..d1bc5820ea469 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -291,58 +291,91 @@ void avic_ring_doorbell(struct kvm_vcpu *vcpu) static int avic_kick_target_vcpus_fast(struct kvm *kvm, struct kvm_lapic *source, u32 icrl, u32 icrh, u32 index) { - u32 dest, apic_id; - struct kvm_vcpu *vcpu; + u32 l1_physical_id, dest; + struct kvm_vcpu *target_vcpu; int dest_mode = icrl & APIC_DEST_MASK; int shorthand = icrl & APIC_SHORT_MASK; struct kvm_svm *kvm_svm = to_kvm_svm(kvm); - u32 *avic_logical_id_table = page_address(kvm_svm->avic_logical_id_table_page); if (shorthand != APIC_DEST_NOSHORT) return -EINVAL; - /* - * The AVIC incomplete IPI #vmexit info provides index into - * the physical APIC ID table, which can be used to derive - * guest physical APIC ID. - */ + if (apic_x2apic_mode(source)) + dest = icrh; + else + dest = GET_APIC_DEST_FIELD(icrh); + if (dest_mode == APIC_DEST_PHYSICAL) { - apic_id = index; + /* broadcast destination, use slow path */ + if (apic_x2apic_mode(source) && dest == X2APIC_BROADCAST) + return -EINVAL; + if (!apic_x2apic_mode(source) && dest == APIC_BROADCAST) + return -EINVAL; + + l1_physical_id = dest; + + if (WARN_ON_ONCE(l1_physical_id != index)) + return -EINVAL; + } else { - if (!apic_x2apic_mode(source)) { - /* For xAPIC logical mode, the index is for logical APIC table. */ - apic_id = avic_logical_id_table[index] & 0x1ff; + u32 bitmap, cluster; + int logid_index; + + if (apic_x2apic_mode(source)) { + /* 16 bit dest mask, 16 bit cluster id */ + bitmap = dest & 0xFFFF0000; + cluster = (dest >> 16) << 4; + } else if (kvm_lapic_get_reg(source, APIC_DFR) == APIC_DFR_FLAT) { + /* 8 bit dest mask*/ + bitmap = dest; + cluster = 0; } else { - return -EINVAL; + /* 4 bit desk mask, 4 bit cluster id */ + bitmap = dest & 0xF; + cluster = (dest >> 4) << 2; } - } - /* - * Assuming vcpu ID is the same as physical apic ID, - * and use it to retrieve the target vCPU. - */ - vcpu = kvm_get_vcpu_by_id(kvm, apic_id); - if (!vcpu) - return -EINVAL; + if (unlikely(!bitmap)) + /* guest bug: nobody to send the logical interrupt to */ + return 0; - if (apic_x2apic_mode(vcpu->arch.apic)) - dest = icrh; - else - dest = GET_APIC_DEST_FIELD(icrh); + if (!is_power_of_2(bitmap)) + /* multiple logical destinations, use slow path */ + return -EINVAL; - /* - * Try matching the destination APIC ID with the vCPU. - */ - if (kvm_apic_match_dest(vcpu, source, shorthand, dest, dest_mode)) { - vcpu->arch.apic->irr_pending = true; - svm_complete_interrupt_delivery(vcpu, - icrl & APIC_MODE_MASK, - icrl & APIC_INT_LEVELTRIG, - icrl & APIC_VECTOR_MASK); - return 0; + logid_index = cluster + __ffs(bitmap); + + if (apic_x2apic_mode(source)) { + l1_physical_id = logid_index; + } else { + u32 *avic_logical_id_table = + page_address(kvm_svm->avic_logical_id_table_page); + + u32 logid_entry = avic_logical_id_table[logid_index]; + + if (WARN_ON_ONCE(index != logid_index)) + return -EINVAL; + + /* guest bug: non existing/reserved logical destination */ + if (unlikely(!(logid_entry & AVIC_LOGICAL_ID_ENTRY_VALID_MASK))) + return 0; + + l1_physical_id = logid_entry & + AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK; + } } - return -EINVAL; + target_vcpu = kvm_get_vcpu_by_id(kvm, l1_physical_id); + if (unlikely(!target_vcpu)) + /* guest bug: non existing vCPU is a target of this IPI*/ + return 0; + + target_vcpu->arch.apic->irr_pending = true; + svm_complete_interrupt_delivery(target_vcpu, + icrl & APIC_MODE_MASK, + icrl & APIC_INT_LEVELTRIG, + icrl & APIC_VECTOR_MASK); + return 0; } static void avic_kick_target_vcpus(struct kvm *kvm, struct kvm_lapic *source, @@ -508,35 +541,6 @@ static int avic_handle_ldr_update(struct kvm_vcpu *vcpu) return ret; } -static int avic_handle_apic_id_update(struct kvm_vcpu *vcpu) -{ - u64 *old, *new; - struct vcpu_svm *svm = to_svm(vcpu); - u32 id = kvm_xapic_id(vcpu->arch.apic); - - if (vcpu->vcpu_id == id) - return 0; - - old = avic_get_physical_id_entry(vcpu, vcpu->vcpu_id); - new = avic_get_physical_id_entry(vcpu, id); - if (!new || !old) - return 1; - - /* We need to move physical_id_entry to new offset */ - *new = *old; - *old = 0ULL; - to_svm(vcpu)->avic_physical_id_cache = new; - - /* - * Also update the guest physical APIC ID in the logical - * APIC ID table entry if already setup the LDR. - */ - if (svm->ldr_reg) - avic_handle_ldr_update(vcpu); - - return 0; -} - static void avic_handle_dfr_update(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -555,10 +559,6 @@ static int avic_unaccel_trap_write(struct kvm_vcpu *vcpu) AVIC_UNACCEL_ACCESS_OFFSET_MASK; switch (offset) { - case APIC_ID: - if (avic_handle_apic_id_update(vcpu)) - return 0; - break; case APIC_LDR: if (avic_handle_ldr_update(vcpu)) return 0; @@ -650,8 +650,6 @@ int avic_init_vcpu(struct vcpu_svm *svm) void avic_apicv_post_state_restore(struct kvm_vcpu *vcpu) { - if (avic_handle_apic_id_update(vcpu) != 0) - return; avic_handle_dfr_update(vcpu); avic_handle_ldr_update(vcpu); } @@ -910,7 +908,9 @@ bool avic_check_apicv_inhibit_reasons(enum kvm_apicv_inhibit reason) BIT(APICV_INHIBIT_REASON_PIT_REINJ) | BIT(APICV_INHIBIT_REASON_X2APIC) | BIT(APICV_INHIBIT_REASON_BLOCKIRQ) | - BIT(APICV_INHIBIT_REASON_SEV); + BIT(APICV_INHIBIT_REASON_SEV) | + BIT(APICV_INHIBIT_REASON_APIC_ID_MODIFIED) | + BIT(APICV_INHIBIT_REASON_APIC_BASE_MODIFIED); return supported & BIT(reason); } @@ -946,7 +946,7 @@ avic_update_iommu_vcpu_affinity(struct kvm_vcpu *vcpu, int cpu, bool r) return ret; } -void __avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu) +void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { u64 entry; int h_physical_id = kvm_cpu_get_apicid(cpu); @@ -978,7 +978,7 @@ void __avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu) avic_update_iommu_vcpu_affinity(vcpu, h_physical_id, true); } -void __avic_vcpu_put(struct kvm_vcpu *vcpu) +void avic_vcpu_put(struct kvm_vcpu *vcpu) { u64 entry; struct vcpu_svm *svm = to_svm(vcpu); @@ -997,25 +997,6 @@ void __avic_vcpu_put(struct kvm_vcpu *vcpu) WRITE_ONCE(*(svm->avic_physical_id_cache), entry); } -static void avic_vcpu_load(struct kvm_vcpu *vcpu) -{ - int cpu = get_cpu(); - - WARN_ON(cpu != vcpu->cpu); - - __avic_vcpu_load(vcpu, cpu); - - put_cpu(); -} - -static void avic_vcpu_put(struct kvm_vcpu *vcpu) -{ - preempt_disable(); - - __avic_vcpu_put(vcpu); - - preempt_enable(); -} void avic_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) { @@ -1042,7 +1023,7 @@ void avic_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) vmcb_mark_dirty(vmcb, VMCB_AVIC); if (activated) - avic_vcpu_load(vcpu); + avic_vcpu_load(vcpu, vcpu->cpu); else avic_vcpu_put(vcpu); @@ -1075,5 +1056,5 @@ void avic_vcpu_unblocking(struct kvm_vcpu *vcpu) if (!kvm_vcpu_apicv_active(vcpu)) return; - avic_vcpu_load(vcpu); + avic_vcpu_load(vcpu, vcpu->cpu); } diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index bed5e1692cef0..ba7cd26f438fc 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -616,6 +616,8 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm) struct kvm_vcpu *vcpu = &svm->vcpu; struct vmcb *vmcb01 = svm->vmcb01.ptr; struct vmcb *vmcb02 = svm->nested.vmcb02.ptr; + u32 pause_count12; + u32 pause_thresh12; /* * Filled at exit: exit_code, exit_code_hi, exit_info_1, exit_info_2, @@ -671,27 +673,25 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm) if (!nested_vmcb_needs_vls_intercept(svm)) vmcb02->control.virt_ext |= VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK; + pause_count12 = svm->pause_filter_enabled ? svm->nested.ctl.pause_filter_count : 0; + pause_thresh12 = svm->pause_threshold_enabled ? svm->nested.ctl.pause_filter_thresh : 0; if (kvm_pause_in_guest(svm->vcpu.kvm)) { - /* use guest values since host doesn't use them */ - vmcb02->control.pause_filter_count = - svm->pause_filter_enabled ? - svm->nested.ctl.pause_filter_count : 0; + /* use guest values since host doesn't intercept PAUSE */ + vmcb02->control.pause_filter_count = pause_count12; + vmcb02->control.pause_filter_thresh = pause_thresh12; - vmcb02->control.pause_filter_thresh = - svm->pause_threshold_enabled ? - svm->nested.ctl.pause_filter_thresh : 0; - - } else if (!vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_PAUSE)) { - /* use host values when guest doesn't use them */ + } else { + /* start from host values otherwise */ vmcb02->control.pause_filter_count = vmcb01->control.pause_filter_count; vmcb02->control.pause_filter_thresh = vmcb01->control.pause_filter_thresh; - } else { - /* - * Intercept every PAUSE otherwise and - * ignore both host and guest values - */ - vmcb02->control.pause_filter_count = 0; - vmcb02->control.pause_filter_thresh = 0; + + /* ... but ensure filtering is disabled if so requested. */ + if (vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_PAUSE)) { + if (!pause_count12) + vmcb02->control.pause_filter_count = 0; + if (!pause_thresh12) + vmcb02->control.pause_filter_thresh = 0; + } } nested_svm_transition_tlb_flush(vcpu); @@ -951,8 +951,11 @@ int nested_svm_vmexit(struct vcpu_svm *svm) vmcb12->control.event_inj = svm->nested.ctl.event_inj; vmcb12->control.event_inj_err = svm->nested.ctl.event_inj_err; - if (!kvm_pause_in_guest(vcpu->kvm) && vmcb02->control.pause_filter_count) + if (!kvm_pause_in_guest(vcpu->kvm)) { vmcb01->control.pause_filter_count = vmcb02->control.pause_filter_count; + vmcb_mark_dirty(vmcb01, VMCB_INTERCEPTS); + + } nested_svm_copy_common_state(svm->nested.vmcb02.ptr, svm->vmcb01.ptr); @@ -982,7 +985,7 @@ int nested_svm_vmexit(struct vcpu_svm *svm) if (svm->tsc_ratio_msr != kvm_default_tsc_scaling_ratio) { WARN_ON(!svm->tsc_scaling_enabled); vcpu->arch.tsc_scaling_ratio = vcpu->arch.l1_tsc_scaling_ratio; - svm_write_tsc_multiplier(vcpu, vcpu->arch.tsc_scaling_ratio); + __svm_write_tsc_multiplier(vcpu->arch.tsc_scaling_ratio); } svm->nested.ctl.nested_cr3 = 0; @@ -1387,7 +1390,7 @@ void nested_svm_update_tsc_ratio_msr(struct kvm_vcpu *vcpu) vcpu->arch.tsc_scaling_ratio = kvm_calc_nested_tsc_multiplier(vcpu->arch.l1_tsc_scaling_ratio, svm->tsc_ratio_msr); - svm_write_tsc_multiplier(vcpu, vcpu->arch.tsc_scaling_ratio); + __svm_write_tsc_multiplier(vcpu->arch.tsc_scaling_ratio); } /* Inverse operation of nested_copy_vmcb_control_to_cache(). asid is copied too. */ diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 51fd985cf21dd..0c240ed04f96c 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -844,7 +844,7 @@ static int __sev_dbg_encrypt_user(struct kvm *kvm, unsigned long paddr, /* If source buffer is not aligned then use an intermediate buffer */ if (!IS_ALIGNED((unsigned long)vaddr, 16)) { - src_tpage = alloc_page(GFP_KERNEL); + src_tpage = alloc_page(GFP_KERNEL_ACCOUNT); if (!src_tpage) return -ENOMEM; @@ -865,7 +865,7 @@ static int __sev_dbg_encrypt_user(struct kvm *kvm, unsigned long paddr, if (!IS_ALIGNED((unsigned long)dst_vaddr, 16) || !IS_ALIGNED(size, 16)) { int dst_offset; - dst_tpage = alloc_page(GFP_KERNEL); + dst_tpage = alloc_page(GFP_KERNEL_ACCOUNT); if (!dst_tpage) { ret = -ENOMEM; goto e_free; @@ -1665,19 +1665,24 @@ static void sev_migrate_from(struct kvm *dst_kvm, struct kvm *src_kvm) { struct kvm_sev_info *dst = &to_kvm_svm(dst_kvm)->sev_info; struct kvm_sev_info *src = &to_kvm_svm(src_kvm)->sev_info; + struct kvm_vcpu *dst_vcpu, *src_vcpu; + struct vcpu_svm *dst_svm, *src_svm; struct kvm_sev_info *mirror; + unsigned long i; dst->active = true; dst->asid = src->asid; dst->handle = src->handle; dst->pages_locked = src->pages_locked; dst->enc_context_owner = src->enc_context_owner; + dst->es_active = src->es_active; src->asid = 0; src->active = false; src->handle = 0; src->pages_locked = 0; src->enc_context_owner = NULL; + src->es_active = false; list_cut_before(&dst->regions_list, &src->regions_list, &src->regions_list); @@ -1704,26 +1709,21 @@ static void sev_migrate_from(struct kvm *dst_kvm, struct kvm *src_kvm) list_del(&src->mirror_entry); list_add_tail(&dst->mirror_entry, &owner_sev_info->mirror_vms); } -} -static int sev_es_migrate_from(struct kvm *dst, struct kvm *src) -{ - unsigned long i; - struct kvm_vcpu *dst_vcpu, *src_vcpu; - struct vcpu_svm *dst_svm, *src_svm; + kvm_for_each_vcpu(i, dst_vcpu, dst_kvm) { + dst_svm = to_svm(dst_vcpu); - if (atomic_read(&src->online_vcpus) != atomic_read(&dst->online_vcpus)) - return -EINVAL; + sev_init_vmcb(dst_svm); - kvm_for_each_vcpu(i, src_vcpu, src) { - if (!src_vcpu->arch.guest_state_protected) - return -EINVAL; - } + if (!dst->es_active) + continue; - kvm_for_each_vcpu(i, src_vcpu, src) { + /* + * Note, the source is not required to have the same number of + * vCPUs as the destination when migrating a vanilla SEV VM. + */ + src_vcpu = kvm_get_vcpu(dst_kvm, i); src_svm = to_svm(src_vcpu); - dst_vcpu = kvm_get_vcpu(dst, i); - dst_svm = to_svm(dst_vcpu); /* * Transfer VMSA and GHCB state to the destination. Nullify and @@ -1740,8 +1740,23 @@ static int sev_es_migrate_from(struct kvm *dst, struct kvm *src) src_svm->vmcb->control.vmsa_pa = INVALID_PAGE; src_vcpu->arch.guest_state_protected = false; } - to_kvm_svm(src)->sev_info.es_active = false; - to_kvm_svm(dst)->sev_info.es_active = true; +} + +static int sev_check_source_vcpus(struct kvm *dst, struct kvm *src) +{ + struct kvm_vcpu *src_vcpu; + unsigned long i; + + if (!sev_es_guest(src)) + return 0; + + if (atomic_read(&src->online_vcpus) != atomic_read(&dst->online_vcpus)) + return -EINVAL; + + kvm_for_each_vcpu(i, src_vcpu, src) { + if (!src_vcpu->arch.guest_state_protected) + return -EINVAL; + } return 0; } @@ -1789,11 +1804,9 @@ int sev_vm_move_enc_context_from(struct kvm *kvm, unsigned int source_fd) if (ret) goto out_dst_vcpu; - if (sev_es_guest(source_kvm)) { - ret = sev_es_migrate_from(kvm, source_kvm); - if (ret) - goto out_source_vcpu; - } + ret = sev_check_source_vcpus(kvm, source_kvm); + if (ret) + goto out_source_vcpu; sev_migrate_from(kvm, source_kvm); kvm_vm_dead(source_kvm); @@ -2914,7 +2927,7 @@ int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in) count, in); } -void sev_es_init_vmcb(struct vcpu_svm *svm) +static void sev_es_init_vmcb(struct vcpu_svm *svm) { struct kvm_vcpu *vcpu = &svm->vcpu; @@ -2967,6 +2980,15 @@ void sev_es_init_vmcb(struct vcpu_svm *svm) } } +void sev_init_vmcb(struct vcpu_svm *svm) +{ + svm->vmcb->control.nested_ctl |= SVM_NESTED_CTL_SEV_ENABLE; + clr_exception_intercept(svm, UD_VECTOR); + + if (sev_es_guest(svm->vcpu.kvm)) + sev_es_init_vmcb(svm); +} + void sev_es_vcpu_reset(struct vcpu_svm *svm) { /* diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 200045f71df04..44bbf25dfeb95 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -465,11 +465,24 @@ static int has_svm(void) return 1; } +void __svm_write_tsc_multiplier(u64 multiplier) +{ + preempt_disable(); + + if (multiplier == __this_cpu_read(current_tsc_ratio)) + goto out; + + wrmsrl(MSR_AMD64_TSC_RATIO, multiplier); + __this_cpu_write(current_tsc_ratio, multiplier); +out: + preempt_enable(); +} + static void svm_hardware_disable(void) { /* Make sure we clean up behind us */ if (tsc_scaling) - wrmsrl(MSR_AMD64_TSC_RATIO, SVM_TSC_RATIO_DEFAULT); + __svm_write_tsc_multiplier(SVM_TSC_RATIO_DEFAULT); cpu_svm_disable(); @@ -515,8 +528,7 @@ static int svm_hardware_enable(void) * Set the default value, even if we don't use TSC scaling * to avoid having stale value in the msr */ - wrmsrl(MSR_AMD64_TSC_RATIO, SVM_TSC_RATIO_DEFAULT); - __this_cpu_write(current_tsc_ratio, SVM_TSC_RATIO_DEFAULT); + __svm_write_tsc_multiplier(SVM_TSC_RATIO_DEFAULT); } @@ -909,7 +921,7 @@ static void grow_ple_window(struct kvm_vcpu *vcpu) struct vmcb_control_area *control = &svm->vmcb->control; int old = control->pause_filter_count; - if (kvm_pause_in_guest(vcpu->kvm) || !old) + if (kvm_pause_in_guest(vcpu->kvm)) return; control->pause_filter_count = __grow_ple_window(old, @@ -930,7 +942,7 @@ static void shrink_ple_window(struct kvm_vcpu *vcpu) struct vmcb_control_area *control = &svm->vmcb->control; int old = control->pause_filter_count; - if (kvm_pause_in_guest(vcpu->kvm) || !old) + if (kvm_pause_in_guest(vcpu->kvm)) return; control->pause_filter_count = @@ -999,11 +1011,12 @@ static void svm_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) vmcb_mark_dirty(svm->vmcb, VMCB_INTERCEPTS); } -void svm_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 multiplier) +static void svm_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 multiplier) { - wrmsrl(MSR_AMD64_TSC_RATIO, multiplier); + __svm_write_tsc_multiplier(multiplier); } + /* Evaluate instruction intercepts that depend on guest CPUID features. */ static void svm_recalc_instruction_intercepts(struct kvm_vcpu *vcpu, struct vcpu_svm *svm) @@ -1199,15 +1212,8 @@ static void init_vmcb(struct kvm_vcpu *vcpu) svm->vmcb->control.int_ctl |= V_GIF_ENABLE_MASK; } - if (sev_guest(vcpu->kvm)) { - svm->vmcb->control.nested_ctl |= SVM_NESTED_CTL_SEV_ENABLE; - clr_exception_intercept(svm, UD_VECTOR); - - if (sev_es_guest(vcpu->kvm)) { - /* Perform SEV-ES specific VMCB updates */ - sev_es_init_vmcb(svm); - } - } + if (sev_guest(vcpu->kvm)) + sev_init_vmcb(svm); svm_hv_init_vmcb(vmcb); init_vmcb_after_set_cpuid(vcpu); @@ -1363,13 +1369,8 @@ static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu) sev_es_prepare_switch_to_guest(hostsa); } - if (tsc_scaling) { - u64 tsc_ratio = vcpu->arch.tsc_scaling_ratio; - if (tsc_ratio != __this_cpu_read(current_tsc_ratio)) { - __this_cpu_write(current_tsc_ratio, tsc_ratio); - wrmsrl(MSR_AMD64_TSC_RATIO, tsc_ratio); - } - } + if (tsc_scaling) + __svm_write_tsc_multiplier(vcpu->arch.tsc_scaling_ratio); if (likely(tsc_aux_uret_slot >= 0)) kvm_set_user_return_msr(tsc_aux_uret_slot, svm->tsc_aux, -1ull); @@ -1392,13 +1393,13 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) indirect_branch_prediction_barrier(); } if (kvm_vcpu_apicv_active(vcpu)) - __avic_vcpu_load(vcpu, cpu); + avic_vcpu_load(vcpu, cpu); } static void svm_vcpu_put(struct kvm_vcpu *vcpu) { if (kvm_vcpu_apicv_active(vcpu)) - __avic_vcpu_put(vcpu); + avic_vcpu_put(vcpu); svm_prepare_host_switch(vcpu); @@ -4255,6 +4256,8 @@ static int svm_check_intercept(struct kvm_vcpu *vcpu, static void svm_handle_exit_irqoff(struct kvm_vcpu *vcpu) { + if (to_svm(vcpu)->vmcb->control.exit_code == SVM_EXIT_INTR) + vcpu->arch.at_instruction_boundary = true; } static void svm_sched_in(struct kvm_vcpu *vcpu, int cpu) diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 21c5460e947aa..9223ac100ef57 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -590,7 +590,7 @@ int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr, bool has_error_code, u32 error_code); int nested_svm_exit_special(struct vcpu_svm *svm); void nested_svm_update_tsc_ratio_msr(struct kvm_vcpu *vcpu); -void svm_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 multiplier); +void __svm_write_tsc_multiplier(u64 multiplier); void nested_copy_vmcb_control_to_cache(struct vcpu_svm *svm, struct vmcb_control_area *control); void nested_copy_vmcb_save_to_cache(struct vcpu_svm *svm, @@ -610,8 +610,8 @@ void avic_init_vmcb(struct vcpu_svm *svm, struct vmcb *vmcb); int avic_incomplete_ipi_interception(struct kvm_vcpu *vcpu); int avic_unaccelerated_access_interception(struct kvm_vcpu *vcpu); int avic_init_vcpu(struct vcpu_svm *svm); -void __avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu); -void __avic_vcpu_put(struct kvm_vcpu *vcpu); +void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu); +void avic_vcpu_put(struct kvm_vcpu *vcpu); void avic_apicv_post_state_restore(struct kvm_vcpu *vcpu); void avic_set_virtual_apic_mode(struct kvm_vcpu *vcpu); void avic_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu); @@ -649,10 +649,10 @@ void __init sev_set_cpu_caps(void); void __init sev_hardware_setup(void); void sev_hardware_unsetup(void); int sev_cpu_init(struct svm_cpu_data *sd); +void sev_init_vmcb(struct vcpu_svm *svm); void sev_free_vcpu(struct kvm_vcpu *vcpu); int sev_handle_vmgexit(struct kvm_vcpu *vcpu); int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in); -void sev_es_init_vmcb(struct vcpu_svm *svm); void sev_es_vcpu_reset(struct vcpu_svm *svm); void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector); void sev_es_prepare_switch_to_guest(struct sev_es_save_area *hostsa); diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index a07e8cd753ec5..3a919e49129bf 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -229,6 +229,9 @@ static const struct { #define L1D_CACHE_ORDER 4 static void *vmx_l1d_flush_pages; +/* Control for disabling CPU Fill buffer clear */ +static bool __read_mostly vmx_fb_clear_ctrl_available; + static int vmx_setup_l1d_flush(enum vmx_l1d_flush_state l1tf) { struct page *page; @@ -360,6 +363,60 @@ static int vmentry_l1d_flush_get(char *s, const struct kernel_param *kp) return sprintf(s, "%s\n", vmentry_l1d_param[l1tf_vmx_mitigation].option); } +static void vmx_setup_fb_clear_ctrl(void) +{ + u64 msr; + + if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES) && + !boot_cpu_has_bug(X86_BUG_MDS) && + !boot_cpu_has_bug(X86_BUG_TAA)) { + rdmsrl(MSR_IA32_ARCH_CAPABILITIES, msr); + if (msr & ARCH_CAP_FB_CLEAR_CTRL) + vmx_fb_clear_ctrl_available = true; + } +} + +static __always_inline void vmx_disable_fb_clear(struct vcpu_vmx *vmx) +{ + u64 msr; + + if (!vmx->disable_fb_clear) + return; + + rdmsrl(MSR_IA32_MCU_OPT_CTRL, msr); + msr |= FB_CLEAR_DIS; + wrmsrl(MSR_IA32_MCU_OPT_CTRL, msr); + /* Cache the MSR value to avoid reading it later */ + vmx->msr_ia32_mcu_opt_ctrl = msr; +} + +static __always_inline void vmx_enable_fb_clear(struct vcpu_vmx *vmx) +{ + if (!vmx->disable_fb_clear) + return; + + vmx->msr_ia32_mcu_opt_ctrl &= ~FB_CLEAR_DIS; + wrmsrl(MSR_IA32_MCU_OPT_CTRL, vmx->msr_ia32_mcu_opt_ctrl); +} + +static void vmx_update_fb_clear_dis(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx) +{ + vmx->disable_fb_clear = vmx_fb_clear_ctrl_available; + + /* + * If guest will not execute VERW, there is no need to set FB_CLEAR_DIS + * at VMEntry. Skip the MSR read/write when a guest has no use case to + * execute VERW. + */ + if ((vcpu->arch.arch_capabilities & ARCH_CAP_FB_CLEAR) || + ((vcpu->arch.arch_capabilities & ARCH_CAP_MDS_NO) && + (vcpu->arch.arch_capabilities & ARCH_CAP_TAA_NO) && + (vcpu->arch.arch_capabilities & ARCH_CAP_PSDP_NO) && + (vcpu->arch.arch_capabilities & ARCH_CAP_FBSDP_NO) && + (vcpu->arch.arch_capabilities & ARCH_CAP_SBDR_SSDP_NO))) + vmx->disable_fb_clear = false; +} + static const struct kernel_param_ops vmentry_l1d_flush_ops = { .set = vmentry_l1d_flush_set, .get = vmentry_l1d_flush_get, @@ -2252,6 +2309,10 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) ret = kvm_set_msr_common(vcpu, msr_info); } + /* FB_CLEAR may have changed, also update the FB_CLEAR_DIS behavior */ + if (msr_index == MSR_IA32_ARCH_CAPABILITIES) + vmx_update_fb_clear_dis(vcpu, vmx); + return ret; } @@ -4553,6 +4614,8 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu); vpid_sync_context(vmx->vpid); + + vmx_update_fb_clear_dis(vcpu, vmx); } static void vmx_enable_irq_window(struct kvm_vcpu *vcpu) @@ -6547,6 +6610,7 @@ static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu) return; handle_interrupt_nmi_irqoff(vcpu, gate_offset(desc)); + vcpu->arch.at_instruction_boundary = true; } static void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu) @@ -6771,6 +6835,11 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, vmx_l1d_flush(vcpu); else if (static_branch_unlikely(&mds_user_clear)) mds_clear_cpu_buffers(); + else if (static_branch_unlikely(&mmio_stale_data_clear) && + kvm_arch_has_assigned_device(vcpu->kvm)) + mds_clear_cpu_buffers(); + + vmx_disable_fb_clear(vmx); if (vcpu->arch.cr2 != native_read_cr2()) native_write_cr2(vcpu->arch.cr2); @@ -6780,6 +6849,8 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, vcpu->arch.cr2 = native_read_cr2(); + vmx_enable_fb_clear(vmx); + guest_state_exit_irqoff(); } @@ -7708,7 +7779,9 @@ static bool vmx_check_apicv_inhibit_reasons(enum kvm_apicv_inhibit reason) ulong supported = BIT(APICV_INHIBIT_REASON_DISABLE) | BIT(APICV_INHIBIT_REASON_ABSENT) | BIT(APICV_INHIBIT_REASON_HYPERV) | - BIT(APICV_INHIBIT_REASON_BLOCKIRQ); + BIT(APICV_INHIBIT_REASON_BLOCKIRQ) | + BIT(APICV_INHIBIT_REASON_APIC_ID_MODIFIED) | + BIT(APICV_INHIBIT_REASON_APIC_BASE_MODIFIED); return supported & BIT(reason); } @@ -8211,6 +8284,8 @@ static int __init vmx_init(void) return r; } + vmx_setup_fb_clear_ctrl(); + for_each_possible_cpu(cpu) { INIT_LIST_HEAD(&per_cpu(loaded_vmcss_on_cpu, cpu)); diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index b98c7e96697a9..8d2342ede0c59 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -348,6 +348,8 @@ struct vcpu_vmx { u64 msr_ia32_feature_control_valid_bits; /* SGX Launch Control public key hash */ u64 msr_ia32_sgxlepubkeyhash[4]; + u64 msr_ia32_mcu_opt_ctrl; + bool disable_fb_clear; struct pt_desc pt_desc; struct lbr_desc lbr_desc; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index e9473c7c73903..1910e1e78b153 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -296,6 +296,8 @@ const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { STATS_DESC_COUNTER(VCPU, nested_run), STATS_DESC_COUNTER(VCPU, directed_yield_attempted), STATS_DESC_COUNTER(VCPU, directed_yield_successful), + STATS_DESC_COUNTER(VCPU, preemption_reported), + STATS_DESC_COUNTER(VCPU, preemption_other), STATS_DESC_ICOUNTER(VCPU, guest_mode) }; @@ -1615,6 +1617,9 @@ static u64 kvm_get_arch_capabilities(void) */ } + /* Guests don't need to know "Fill buffer clear control" exists */ + data &= ~ARCH_CAP_FB_CLEAR_CTRL; + return data; } @@ -4625,6 +4630,19 @@ static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu) struct kvm_memslots *slots; static const u8 preempted = KVM_VCPU_PREEMPTED; + /* + * The vCPU can be marked preempted if and only if the VM-Exit was on + * an instruction boundary and will not trigger guest emulation of any + * kind (see vcpu_run). Vendor specific code controls (conservatively) + * when this is true, for example allowing the vCPU to be marked + * preempted if and only if the VM-Exit was due to a host interrupt. + */ + if (!vcpu->arch.at_instruction_boundary) { + vcpu->stat.preemption_other++; + return; + } + + vcpu->stat.preemption_reported++; if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED)) return; @@ -4654,19 +4672,21 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) { int idx; - if (vcpu->preempted && !vcpu->arch.guest_state_protected) - vcpu->arch.preempted_in_kernel = !static_call(kvm_x86_get_cpl)(vcpu); + if (vcpu->preempted) { + if (!vcpu->arch.guest_state_protected) + vcpu->arch.preempted_in_kernel = !static_call(kvm_x86_get_cpl)(vcpu); - /* - * Take the srcu lock as memslots will be accessed to check the gfn - * cache generation against the memslots generation. - */ - idx = srcu_read_lock(&vcpu->kvm->srcu); - if (kvm_xen_msr_enabled(vcpu->kvm)) - kvm_xen_runstate_set_preempted(vcpu); - else - kvm_steal_time_set_preempted(vcpu); - srcu_read_unlock(&vcpu->kvm->srcu, idx); + /* + * Take the srcu lock as memslots will be accessed to check the gfn + * cache generation against the memslots generation. + */ + idx = srcu_read_lock(&vcpu->kvm->srcu); + if (kvm_xen_msr_enabled(vcpu->kvm)) + kvm_xen_runstate_set_preempted(vcpu); + else + kvm_steal_time_set_preempted(vcpu); + srcu_read_unlock(&vcpu->kvm->srcu, idx); + } static_call(kvm_x86_vcpu_put)(vcpu); vcpu->arch.last_host_tsc = rdtsc(); @@ -9833,6 +9853,7 @@ void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu) return; down_read(&vcpu->kvm->arch.apicv_update_lock); + preempt_disable(); activate = kvm_vcpu_apicv_activated(vcpu); @@ -9853,6 +9874,7 @@ void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu) kvm_make_request(KVM_REQ_EVENT, vcpu); out: + preempt_enable(); up_read(&vcpu->kvm->arch.apicv_update_lock); } EXPORT_SYMBOL_GPL(kvm_vcpu_update_apicv); @@ -10422,6 +10444,13 @@ static int vcpu_run(struct kvm_vcpu *vcpu) vcpu->arch.l1tf_flush_l1d = true; for (;;) { + /* + * If another guest vCPU requests a PV TLB flush in the middle + * of instruction emulation, the rest of the emulation could + * use a stale page translation. Assume that any code after + * this point can start executing an instruction. + */ + vcpu->arch.at_instruction_boundary = false; if (kvm_vcpu_running(vcpu)) { r = vcpu_enter_guest(vcpu); } else { diff --git a/arch/x86/kvm/xen.h b/arch/x86/kvm/xen.h index ee5c4ae0755cd..532a535a9e99f 100644 --- a/arch/x86/kvm/xen.h +++ b/arch/x86/kvm/xen.h @@ -159,8 +159,10 @@ static inline void kvm_xen_runstate_set_preempted(struct kvm_vcpu *vcpu) * behalf of the vCPU. Only if the VMM does actually block * does it need to enter RUNSTATE_blocked. */ - if (vcpu->preempted) - kvm_xen_update_runstate_guest(vcpu, RUNSTATE_runnable); + if (WARN_ON_ONCE(!vcpu->preempted)) + return; + + kvm_xen_update_runstate_guest(vcpu, RUNSTATE_runnable); } /* 32-bit compatibility definitions, also used natively in 32-bit build */ diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c index 11350e2fd7366..9f27e14e185f3 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -12,7 +12,6 @@ #include #include #include -#include /* Override for DMA direct allocation check - ARCH_HAS_FORCE_DMA_UNENCRYPTED */ bool force_dma_unencrypted(struct device *dev) @@ -87,9 +86,3 @@ void __init mem_encrypt_init(void) print_mem_encrypt_feature_info(); } - -int arch_has_restricted_virtio_memory_access(void) -{ - return cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT); -} -EXPORT_SYMBOL_GPL(arch_has_restricted_virtio_memory_access); diff --git a/arch/x86/mm/mem_encrypt_amd.c b/arch/x86/mm/mem_encrypt_amd.c index e8f7953fda83a..f6d038e2cd8e8 100644 --- a/arch/x86/mm/mem_encrypt_amd.c +++ b/arch/x86/mm/mem_encrypt_amd.c @@ -21,6 +21,7 @@ #include #include #include +#include #include #include @@ -242,6 +243,9 @@ void __init sev_setup_arch(void) size = total_mem * 6 / 100; size = clamp_val(size, IO_TLB_DEFAULT_SIZE, SZ_1G); swiotlb_adjust_size(size); + + /* Set restricted memory access for virtio. */ + platform_set(PLATFORM_VIRTIO_RESTRICTED_MEM_ACCESS); } static unsigned long pg_level_to_pfn(int level, pte_t *kpte, pgprot_t *ret_prot) diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index f298b18a9a3d1..c98b8c0ed3b83 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -1420,8 +1420,9 @@ st: if (is_imm8(insn->off)) case BPF_JMP | BPF_CALL: func = (u8 *) __bpf_call_base + imm32; if (tail_call_reachable) { + /* mov rax, qword ptr [rbp - rounded_stack_depth - 8] */ EMIT3_off32(0x48, 0x8B, 0x85, - -(bpf_prog->aux->stack_depth + 8)); + -round_up(bpf_prog->aux->stack_depth, 8) - 8); if (!imm32 || emit_call(&prog, func, image + addrs[i - 1] + 7)) return -EINVAL; } else { diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index a4f43054bc79c..2f82480fd4305 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -8,7 +8,6 @@ #include #include #include -#include struct pci_root_info { struct acpi_pci_root_info common; @@ -20,7 +19,7 @@ struct pci_root_info { #endif }; -static bool pci_use_e820 = true; +bool pci_use_e820 = true; static bool pci_use_crs = true; static bool pci_ignore_seg; @@ -387,11 +386,6 @@ static int pci_acpi_root_prepare_resources(struct acpi_pci_root_info *ci) status = acpi_pci_probe_root_resources(ci); - if (pci_use_e820) { - resource_list_for_each_entry(entry, &ci->resources) - remove_e820_regions(&device->dev, entry->res); - } - if (pci_use_crs) { resource_list_for_each_entry_safe(entry, tmp, &ci->resources) if (resource_is_pcicfg_ioport(entry->res)) diff --git a/arch/x86/xen/enlighten_hvm.c b/arch/x86/xen/enlighten_hvm.c index 517a9d8d8f94d..8b71b1dd76396 100644 --- a/arch/x86/xen/enlighten_hvm.c +++ b/arch/x86/xen/enlighten_hvm.c @@ -195,6 +195,8 @@ static void __init xen_hvm_guest_init(void) if (xen_pv_domain()) return; + xen_set_restricted_virtio_memory_access(); + init_hvm_pv_info(); reserve_shared_info(); diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index f33a4421e7cd6..e3297b15701c6 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -109,6 +109,8 @@ static DEFINE_PER_CPU(struct tls_descs, shadow_tls_desc); static void __init xen_pv_init_platform(void) { + xen_set_restricted_virtio_memory_access(); + populate_extra_pte(fix_to_virt(FIX_PARAVIRT_BOOTMAP)); set_fixmap(FIX_PARAVIRT_BOOTMAP, xen_start_info->shared_info); diff --git a/arch/xtensa/kernel/entry.S b/arch/xtensa/kernel/entry.S index e3eae648ba2e9..ab30bcb462903 100644 --- a/arch/xtensa/kernel/entry.S +++ b/arch/xtensa/kernel/entry.S @@ -2173,7 +2173,7 @@ ENDPROC(ret_from_kernel_thread) #ifdef CONFIG_HIBERNATION - .bss + .section .bss, "aw" .align 4 .Lsaved_regs: #if defined(__XTENSA_WINDOWED_ABI__) diff --git a/arch/xtensa/kernel/time.c b/arch/xtensa/kernel/time.c index e8ceb15286081..16b8a6273772c 100644 --- a/arch/xtensa/kernel/time.c +++ b/arch/xtensa/kernel/time.c @@ -154,6 +154,7 @@ static void __init calibrate_ccount(void) cpu = of_find_compatible_node(NULL, NULL, "cdns,xtensa-cpu"); if (cpu) { clk = of_clk_get(cpu, 0); + of_node_put(cpu); if (!IS_ERR(clk)) { ccount_freq = clk_get_rate(clk); return; diff --git a/arch/xtensa/platforms/xtfpga/setup.c b/arch/xtensa/platforms/xtfpga/setup.c index 538e6748e85a7..c79c1d09ea863 100644 --- a/arch/xtensa/platforms/xtfpga/setup.c +++ b/arch/xtensa/platforms/xtfpga/setup.c @@ -133,6 +133,7 @@ static int __init machine_setup(void) if ((eth = of_find_compatible_node(eth, NULL, "opencores,ethoc"))) update_local_mac(eth); + of_node_put(eth); return 0; } arch_initcall(machine_setup); diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 0d46cb728bbfa..e6d7e6b01a05c 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -7046,6 +7046,7 @@ static void bfq_exit_queue(struct elevator_queue *e) spin_unlock_irq(&bfqd->lock); #endif + blk_stat_disable_accounting(bfqd->queue); wbt_enable_default(bfqd->queue); kfree(bfqd); @@ -7188,7 +7189,12 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e) bfq_init_root_group(bfqd->root_group, bfqd); bfq_init_entity(&bfqd->oom_bfqq.entity, bfqd->root_group); + /* We dispatch from request queue wide instead of hw queue */ + blk_queue_flag_set(QUEUE_FLAG_SQ_SCHED, q); + wbt_disable_default(q); + blk_stat_enable_accounting(q); + return 0; out_free: diff --git a/block/bio.c b/block/bio.c index f92d0223247b7..51c99f2c5c908 100644 --- a/block/bio.c +++ b/block/bio.c @@ -1747,26 +1747,6 @@ int bioset_init(struct bio_set *bs, } EXPORT_SYMBOL(bioset_init); -/* - * Initialize and setup a new bio_set, based on the settings from - * another bio_set. - */ -int bioset_init_from_src(struct bio_set *bs, struct bio_set *src) -{ - int flags; - - flags = 0; - if (src->bvec_pool.min_nr) - flags |= BIOSET_NEED_BVECS; - if (src->rescue_workqueue) - flags |= BIOSET_NEED_RESCUER; - if (src->cache) - flags |= BIOSET_PERCPU_CACHE; - - return bioset_init(bs, src->bio_pool.min_nr, src->front_pad, flags); -} -EXPORT_SYMBOL(bioset_init_from_src); - static int __init init_bio(void) { int i; diff --git a/block/blk-core.c b/block/blk-core.c index 06ff5bbfe8f66..27fb1357ad4b8 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -322,19 +322,6 @@ void blk_cleanup_queue(struct request_queue *q) blk_mq_exit_queue(q); } - /* - * In theory, request pool of sched_tags belongs to request queue. - * However, the current implementation requires tag_set for freeing - * requests, so free the pool now. - * - * Queue has become frozen, there can't be any in-queue requests, so - * it is safe to free requests now. - */ - mutex_lock(&q->sysfs_lock); - if (q->elevator) - blk_mq_sched_free_rqs(q); - mutex_unlock(&q->sysfs_lock); - /* @q is and will stay empty, shutdown and put */ blk_put_queue(q); } diff --git a/block/blk-ia-ranges.c b/block/blk-ia-ranges.c index 56ed48d2954e6..47c89e65b57fa 100644 --- a/block/blk-ia-ranges.c +++ b/block/blk-ia-ranges.c @@ -144,7 +144,6 @@ int disk_register_independent_access_ranges(struct gendisk *disk, } for (i = 0; i < iars->nr_ia_ranges; i++) { - iars->ia_range[i].queue = q; ret = kobject_init_and_add(&iars->ia_range[i].kobj, &blk_ia_range_ktype, &iars->kobj, "%d", i); diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index 7e4136a60e1cc..4d1ce9ef43187 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -711,11 +711,6 @@ void blk_mq_debugfs_register(struct request_queue *q) } } -void blk_mq_debugfs_unregister(struct request_queue *q) -{ - q->sched_debugfs_dir = NULL; -} - static void blk_mq_debugfs_register_ctx(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx) { @@ -746,6 +741,8 @@ void blk_mq_debugfs_register_hctx(struct request_queue *q, void blk_mq_debugfs_unregister_hctx(struct blk_mq_hw_ctx *hctx) { + if (!hctx->queue->debugfs_dir) + return; debugfs_remove_recursive(hctx->debugfs_dir); hctx->sched_debugfs_dir = NULL; hctx->debugfs_dir = NULL; @@ -773,6 +770,8 @@ void blk_mq_debugfs_register_sched(struct request_queue *q) { struct elevator_type *e = q->elevator->type; + lockdep_assert_held(&q->debugfs_mutex); + /* * If the parent directory has not been created yet, return, we will be * called again later on and the directory/files will be created then. @@ -790,6 +789,8 @@ void blk_mq_debugfs_register_sched(struct request_queue *q) void blk_mq_debugfs_unregister_sched(struct request_queue *q) { + lockdep_assert_held(&q->debugfs_mutex); + debugfs_remove_recursive(q->sched_debugfs_dir); q->sched_debugfs_dir = NULL; } @@ -811,6 +812,10 @@ static const char *rq_qos_id_to_name(enum rq_qos_id id) void blk_mq_debugfs_unregister_rqos(struct rq_qos *rqos) { + lockdep_assert_held(&rqos->q->debugfs_mutex); + + if (!rqos->q->debugfs_dir) + return; debugfs_remove_recursive(rqos->debugfs_dir); rqos->debugfs_dir = NULL; } @@ -820,6 +825,8 @@ void blk_mq_debugfs_register_rqos(struct rq_qos *rqos) struct request_queue *q = rqos->q; const char *dir_name = rq_qos_id_to_name(rqos->id); + lockdep_assert_held(&q->debugfs_mutex); + if (rqos->debugfs_dir || !rqos->ops->debugfs_attrs) return; @@ -833,17 +840,13 @@ void blk_mq_debugfs_register_rqos(struct rq_qos *rqos) debugfs_create_files(rqos->debugfs_dir, rqos, rqos->ops->debugfs_attrs); } -void blk_mq_debugfs_unregister_queue_rqos(struct request_queue *q) -{ - debugfs_remove_recursive(q->rqos_debugfs_dir); - q->rqos_debugfs_dir = NULL; -} - void blk_mq_debugfs_register_sched_hctx(struct request_queue *q, struct blk_mq_hw_ctx *hctx) { struct elevator_type *e = q->elevator->type; + lockdep_assert_held(&q->debugfs_mutex); + /* * If the parent debugfs directory has not been created yet, return; * We will be called again later on with appropriate parent debugfs @@ -863,6 +866,10 @@ void blk_mq_debugfs_register_sched_hctx(struct request_queue *q, void blk_mq_debugfs_unregister_sched_hctx(struct blk_mq_hw_ctx *hctx) { + lockdep_assert_held(&hctx->queue->debugfs_mutex); + + if (!hctx->queue->debugfs_dir) + return; debugfs_remove_recursive(hctx->sched_debugfs_dir); hctx->sched_debugfs_dir = NULL; } diff --git a/block/blk-mq-debugfs.h b/block/blk-mq-debugfs.h index 69918f4170d69..9c7d4b6117d41 100644 --- a/block/blk-mq-debugfs.h +++ b/block/blk-mq-debugfs.h @@ -21,7 +21,6 @@ int __blk_mq_debugfs_rq_show(struct seq_file *m, struct request *rq); int blk_mq_debugfs_rq_show(struct seq_file *m, void *v); void blk_mq_debugfs_register(struct request_queue *q); -void blk_mq_debugfs_unregister(struct request_queue *q); void blk_mq_debugfs_register_hctx(struct request_queue *q, struct blk_mq_hw_ctx *hctx); void blk_mq_debugfs_unregister_hctx(struct blk_mq_hw_ctx *hctx); @@ -36,16 +35,11 @@ void blk_mq_debugfs_unregister_sched_hctx(struct blk_mq_hw_ctx *hctx); void blk_mq_debugfs_register_rqos(struct rq_qos *rqos); void blk_mq_debugfs_unregister_rqos(struct rq_qos *rqos); -void blk_mq_debugfs_unregister_queue_rqos(struct request_queue *q); #else static inline void blk_mq_debugfs_register(struct request_queue *q) { } -static inline void blk_mq_debugfs_unregister(struct request_queue *q) -{ -} - static inline void blk_mq_debugfs_register_hctx(struct request_queue *q, struct blk_mq_hw_ctx *hctx) { @@ -87,10 +81,6 @@ static inline void blk_mq_debugfs_register_rqos(struct rq_qos *rqos) static inline void blk_mq_debugfs_unregister_rqos(struct rq_qos *rqos) { } - -static inline void blk_mq_debugfs_unregister_queue_rqos(struct request_queue *q) -{ -} #endif #ifdef CONFIG_BLK_DEBUG_FS_ZONED diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index 9e56a69422b65..a4f7c101b53b2 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -564,6 +564,7 @@ int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e) int ret; if (!e) { + blk_queue_flag_clear(QUEUE_FLAG_SQ_SCHED, q); q->elevator = NULL; q->nr_requests = q->tag_set->queue_depth; return 0; @@ -593,7 +594,9 @@ int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e) if (ret) goto err_free_map_and_rqs; + mutex_lock(&q->debugfs_mutex); blk_mq_debugfs_register_sched(q); + mutex_unlock(&q->debugfs_mutex); queue_for_each_hw_ctx(q, hctx, i) { if (e->ops.init_hctx) { @@ -606,7 +609,9 @@ int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e) return ret; } } + mutex_lock(&q->debugfs_mutex); blk_mq_debugfs_register_sched_hctx(q, hctx); + mutex_unlock(&q->debugfs_mutex); } return 0; @@ -647,14 +652,21 @@ void blk_mq_exit_sched(struct request_queue *q, struct elevator_queue *e) unsigned int flags = 0; queue_for_each_hw_ctx(q, hctx, i) { + mutex_lock(&q->debugfs_mutex); blk_mq_debugfs_unregister_sched_hctx(hctx); + mutex_unlock(&q->debugfs_mutex); + if (e->type->ops.exit_hctx && hctx->sched_data) { e->type->ops.exit_hctx(hctx, i); hctx->sched_data = NULL; } flags = hctx->flags; } + + mutex_lock(&q->debugfs_mutex); blk_mq_debugfs_unregister_sched(q); + mutex_unlock(&q->debugfs_mutex); + if (e->type->ops.exit_sched) e->type->ops.exit_sched(e); blk_mq_sched_tags_teardown(q, flags); diff --git a/block/blk-mq.c b/block/blk-mq.c index e9bf950983c71..93d9d60980fb5 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -579,6 +579,8 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q, if (!blk_mq_hw_queue_mapped(data.hctx)) goto out_queue_exit; cpu = cpumask_first_and(data.hctx->cpumask, cpu_online_mask); + if (cpu >= nr_cpu_ids) + goto out_queue_exit; data.ctx = __blk_mq_get_ctx(q, cpu); if (!q->elevator) @@ -2140,20 +2142,6 @@ void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async) } EXPORT_SYMBOL(blk_mq_run_hw_queue); -/* - * Is the request queue handled by an IO scheduler that does not respect - * hardware queues when dispatching? - */ -static bool blk_mq_has_sqsched(struct request_queue *q) -{ - struct elevator_queue *e = q->elevator; - - if (e && e->type->ops.dispatch_request && - !(e->type->elevator_features & ELEVATOR_F_MQ_AWARE)) - return true; - return false; -} - /* * Return prefered queue to dispatch from (if any) for non-mq aware IO * scheduler. @@ -2186,7 +2174,7 @@ void blk_mq_run_hw_queues(struct request_queue *q, bool async) unsigned long i; sq_hctx = NULL; - if (blk_mq_has_sqsched(q)) + if (blk_queue_sq_sched(q)) sq_hctx = blk_mq_get_sq_hctx(q); queue_for_each_hw_ctx(q, hctx, i) { if (blk_mq_hctx_stopped(hctx)) @@ -2214,7 +2202,7 @@ void blk_mq_delay_run_hw_queues(struct request_queue *q, unsigned long msecs) unsigned long i; sq_hctx = NULL; - if (blk_mq_has_sqsched(q)) + if (blk_queue_sq_sched(q)) sq_hctx = blk_mq_get_sq_hctx(q); queue_for_each_hw_ctx(q, hctx, i) { if (blk_mq_hctx_stopped(hctx)) @@ -2777,15 +2765,20 @@ static inline struct request *blk_mq_get_cached_request(struct request_queue *q, return NULL; } - rq_qos_throttle(q, *bio); - if (blk_mq_get_hctx_type((*bio)->bi_opf) != rq->mq_hctx->type) return NULL; if (op_is_flush(rq->cmd_flags) != op_is_flush((*bio)->bi_opf)) return NULL; - rq->cmd_flags = (*bio)->bi_opf; + /* + * If any qos ->throttle() end up blocking, we will have flushed the + * plug and hence killed the cached_rq list as well. Pop this entry + * before we throttle. + */ plug->cached_rq = rq_list_next(rq); + rq_qos_throttle(q, *bio); + + rq->cmd_flags = (*bio)->bi_opf; INIT_LIST_HEAD(&rq->queuelist); return rq; } @@ -3443,8 +3436,9 @@ static void blk_mq_exit_hctx(struct request_queue *q, if (blk_mq_hw_queue_mapped(hctx)) blk_mq_tag_idle(hctx); - blk_mq_clear_flush_rq_mapping(set->tags[hctx_idx], - set->queue_depth, flush_rq); + if (blk_queue_init_done(q)) + blk_mq_clear_flush_rq_mapping(set->tags[hctx_idx], + set->queue_depth, flush_rq); if (set->ops->exit_request) set->ops->exit_request(set, flush_rq, hctx_idx); @@ -4438,12 +4432,14 @@ static bool blk_mq_elv_switch_none(struct list_head *head, if (!qe) return false; + /* q->elevator needs protection from ->sysfs_lock */ + mutex_lock(&q->sysfs_lock); + INIT_LIST_HEAD(&qe->node); qe->q = q; qe->type = q->elevator->type; list_add(&qe->node, head); - mutex_lock(&q->sysfs_lock); /* * After elevator_switch_mq, the previous elevator_queue will be * released by elevator_release. The reference of the io scheduler diff --git a/block/blk-rq-qos.c b/block/blk-rq-qos.c index e83af7bc75919..d3a75693adbf4 100644 --- a/block/blk-rq-qos.c +++ b/block/blk-rq-qos.c @@ -294,8 +294,6 @@ void rq_qos_wait(struct rq_wait *rqw, void *private_data, void rq_qos_exit(struct request_queue *q) { - blk_mq_debugfs_unregister_queue_rqos(q); - while (q->rq_qos) { struct rq_qos *rqos = q->rq_qos; q->rq_qos = rqos->next; diff --git a/block/blk-rq-qos.h b/block/blk-rq-qos.h index 68267007da1c6..0e46052b018a4 100644 --- a/block/blk-rq-qos.h +++ b/block/blk-rq-qos.h @@ -104,8 +104,11 @@ static inline void rq_qos_add(struct request_queue *q, struct rq_qos *rqos) blk_mq_unfreeze_queue(q); - if (rqos->ops->debugfs_attrs) + if (rqos->ops->debugfs_attrs) { + mutex_lock(&q->debugfs_mutex); blk_mq_debugfs_register_rqos(rqos); + mutex_unlock(&q->debugfs_mutex); + } } static inline void rq_qos_del(struct request_queue *q, struct rq_qos *rqos) @@ -129,7 +132,9 @@ static inline void rq_qos_del(struct request_queue *q, struct rq_qos *rqos) blk_mq_unfreeze_queue(q); + mutex_lock(&q->debugfs_mutex); blk_mq_debugfs_unregister_rqos(rqos); + mutex_unlock(&q->debugfs_mutex); } typedef bool (acquire_inflight_cb_t)(struct rq_wait *rqw, void *private_data); diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 88bd41d4cb593..9b905e9443e49 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -779,14 +779,6 @@ static void blk_release_queue(struct kobject *kobj) if (queue_is_mq(q)) blk_mq_release(q); - blk_trace_shutdown(q); - mutex_lock(&q->debugfs_mutex); - debugfs_remove_recursive(q->debugfs_dir); - mutex_unlock(&q->debugfs_mutex); - - if (queue_is_mq(q)) - blk_mq_debugfs_unregister(q); - bioset_exit(&q->bio_split); if (blk_queue_has_srcu(q)) @@ -836,17 +828,16 @@ int blk_register_queue(struct gendisk *disk) goto unlock; } + if (queue_is_mq(q)) + __blk_mq_register_dev(dev, q); + mutex_lock(&q->sysfs_lock); + mutex_lock(&q->debugfs_mutex); q->debugfs_dir = debugfs_create_dir(kobject_name(q->kobj.parent), blk_debugfs_root); - mutex_unlock(&q->debugfs_mutex); - - if (queue_is_mq(q)) { - __blk_mq_register_dev(dev, q); + if (queue_is_mq(q)) blk_mq_debugfs_register(q); - } - - mutex_lock(&q->sysfs_lock); + mutex_unlock(&q->debugfs_mutex); ret = disk_register_independent_access_ranges(disk, NULL); if (ret) @@ -948,8 +939,15 @@ void blk_unregister_queue(struct gendisk *disk) /* Now that we've deleted all child objects, we can delete the queue. */ kobject_uevent(&q->kobj, KOBJ_REMOVE); kobject_del(&q->kobj); - mutex_unlock(&q->sysfs_dir_lock); + mutex_lock(&q->debugfs_mutex); + blk_trace_shutdown(q); + debugfs_remove_recursive(q->debugfs_dir); + q->debugfs_dir = NULL; + q->sched_debugfs_dir = NULL; + q->rqos_debugfs_dir = NULL; + mutex_unlock(&q->debugfs_mutex); + kobject_put(&disk_to_dev(disk)->kobj); } diff --git a/block/genhd.c b/block/genhd.c index 27205ae47d593..278227ba1d531 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -623,6 +623,7 @@ void del_gendisk(struct gendisk *disk) * Prevent new I/O from crossing bio_queue_enter(). */ blk_queue_start_drain(q); + blk_mq_freeze_queue_wait(q); if (!(disk->flags & GENHD_FL_HIDDEN)) { sysfs_remove_link(&disk_to_dev(disk)->kobj, "bdi"); @@ -646,12 +647,21 @@ void del_gendisk(struct gendisk *disk) pm_runtime_set_memalloc_noio(disk_to_dev(disk), false); device_del(disk_to_dev(disk)); - blk_mq_freeze_queue_wait(q); - blk_throtl_cancel_bios(disk->queue); blk_sync_queue(q); blk_flush_integrity(); + blk_mq_cancel_work_sync(q); + + blk_mq_quiesce_queue(q); + if (q->elevator) { + mutex_lock(&q->sysfs_lock); + elevator_exit(q); + mutex_unlock(&q->sysfs_lock); + } + rq_qos_exit(q); + blk_mq_unquiesce_queue(q); + /* * Allow using passthrough request again after the queue is torn down. */ @@ -1120,31 +1130,6 @@ static const struct attribute_group *disk_attr_groups[] = { NULL }; -static void disk_release_mq(struct request_queue *q) -{ - blk_mq_cancel_work_sync(q); - - /* - * There can't be any non non-passthrough bios in flight here, but - * requests stay around longer, including passthrough ones so we - * still need to freeze the queue here. - */ - blk_mq_freeze_queue(q); - - /* - * Since the I/O scheduler exit code may access cgroup information, - * perform I/O scheduler exit before disassociating from the block - * cgroup controller. - */ - if (q->elevator) { - mutex_lock(&q->sysfs_lock); - elevator_exit(q); - mutex_unlock(&q->sysfs_lock); - } - rq_qos_exit(q); - __blk_mq_unfreeze_queue(q, true); -} - /** * disk_release - releases all allocated resources of the gendisk * @dev: the device representing this disk @@ -1166,9 +1151,6 @@ static void disk_release(struct device *dev) might_sleep(); WARN_ON_ONCE(disk_live(disk)); - if (queue_is_mq(disk->queue)) - disk_release_mq(disk->queue); - blkcg_exit_queue(disk->queue); disk_release_events(disk); diff --git a/block/holder.c b/block/holder.c index 8d750281a1cd9..5283bc804cc14 100644 --- a/block/holder.c +++ b/block/holder.c @@ -79,10 +79,6 @@ int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk) WARN_ON_ONCE(!bdev->bd_holder); - /* FIXME: remove the following once add_disk() handles errors */ - if (WARN_ON(!bdev->bd_holder_dir)) - goto out_unlock; - holder = bd_find_holder_disk(bdev, disk); if (holder) { holder->refcnt++; diff --git a/block/kyber-iosched.c b/block/kyber-iosched.c index 70ff2a599ef61..8f7c745b4a57c 100644 --- a/block/kyber-iosched.c +++ b/block/kyber-iosched.c @@ -421,6 +421,8 @@ static int kyber_init_sched(struct request_queue *q, struct elevator_type *e) blk_stat_enable_accounting(q); + blk_queue_flag_clear(QUEUE_FLAG_SQ_SCHED, q); + eq->elevator_data = kqd; q->elevator = eq; @@ -1033,7 +1035,6 @@ static struct elevator_type kyber_sched = { #endif .elevator_attrs = kyber_sched_attrs, .elevator_name = "kyber", - .elevator_features = ELEVATOR_F_MQ_AWARE, .elevator_owner = THIS_MODULE, }; diff --git a/block/mq-deadline.c b/block/mq-deadline.c index 6ed602b2f80a5..1a9e835e816cd 100644 --- a/block/mq-deadline.c +++ b/block/mq-deadline.c @@ -642,6 +642,9 @@ static int dd_init_sched(struct request_queue *q, struct elevator_type *e) spin_lock_init(&dd->lock); spin_lock_init(&dd->zone_lock); + /* We dispatch from request queue wide instead of hw queue */ + blk_queue_flag_set(QUEUE_FLAG_SQ_SCHED, q); + q->elevator = eq; return 0; diff --git a/certs/.gitignore b/certs/.gitignore index 56637aceaf81c..cec5465f31c1c 100644 --- a/certs/.gitignore +++ b/certs/.gitignore @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only -/blacklist_hashes_checked +/blacklist_hash_list /extract-cert /x509_certificate_list /x509_revocation_list diff --git a/certs/Makefile b/certs/Makefile index bb904f90f1394..88a73b28d254a 100644 --- a/certs/Makefile +++ b/certs/Makefile @@ -3,26 +3,26 @@ # Makefile for the linux kernel signature checking certificates. # -obj-$(CONFIG_SYSTEM_TRUSTED_KEYRING) += system_keyring.o system_certificates.o common.o -obj-$(CONFIG_SYSTEM_BLACKLIST_KEYRING) += blacklist.o common.o +obj-$(CONFIG_SYSTEM_TRUSTED_KEYRING) += system_keyring.o system_certificates.o +obj-$(CONFIG_SYSTEM_BLACKLIST_KEYRING) += blacklist.o obj-$(CONFIG_SYSTEM_REVOCATION_LIST) += revocation_certificates.o ifneq ($(CONFIG_SYSTEM_BLACKLIST_HASH_LIST),) -quiet_cmd_check_blacklist_hashes = CHECK $(patsubst "%",%,$(2)) - cmd_check_blacklist_hashes = $(AWK) -f $(srctree)/scripts/check-blacklist-hashes.awk $(2); touch $@ -$(eval $(call config_filename,SYSTEM_BLACKLIST_HASH_LIST)) +$(obj)/blacklist_hashes.o: $(obj)/blacklist_hash_list +CFLAGS_blacklist_hashes.o := -I $(obj) -$(obj)/blacklist_hashes.o: $(obj)/blacklist_hashes_checked +quiet_cmd_check_and_copy_blacklist_hash_list = GEN $@ + cmd_check_and_copy_blacklist_hash_list = \ + $(AWK) -f $(srctree)/scripts/check-blacklist-hashes.awk $(CONFIG_SYSTEM_BLACKLIST_HASH_LIST) >&2; \ + cat $(CONFIG_SYSTEM_BLACKLIST_HASH_LIST) > $@ -CFLAGS_blacklist_hashes.o += -I$(srctree) - -targets += blacklist_hashes_checked -$(obj)/blacklist_hashes_checked: $(SYSTEM_BLACKLIST_HASH_LIST_SRCPREFIX)$(SYSTEM_BLACKLIST_HASH_LIST_FILENAME) scripts/check-blacklist-hashes.awk FORCE - $(call if_changed,check_blacklist_hashes,$(SYSTEM_BLACKLIST_HASH_LIST_SRCPREFIX)$(CONFIG_SYSTEM_BLACKLIST_HASH_LIST)) +$(obj)/blacklist_hash_list: $(CONFIG_SYSTEM_BLACKLIST_HASH_LIST) FORCE + $(call if_changed,check_and_copy_blacklist_hash_list) obj-$(CONFIG_SYSTEM_BLACKLIST_KEYRING) += blacklist_hashes.o else obj-$(CONFIG_SYSTEM_BLACKLIST_KEYRING) += blacklist_nohashes.o endif +targets += blacklist_hash_list quiet_cmd_extract_certs = CERT $@ cmd_extract_certs = $(obj)/extract-cert $(extract-cert-in) $@ @@ -33,7 +33,7 @@ $(obj)/system_certificates.o: $(obj)/x509_certificate_list $(obj)/x509_certificate_list: $(CONFIG_SYSTEM_TRUSTED_KEYS) $(obj)/extract-cert FORCE $(call if_changed,extract_certs) -targets += x509_certificate_list blacklist_hashes_checked +targets += x509_certificate_list # If module signing is requested, say by allyesconfig, but a key has not been # supplied, then one will need to be generated to make sure the build does not diff --git a/certs/blacklist.c b/certs/blacklist.c index 25094ea736007..41f10601cc724 100644 --- a/certs/blacklist.c +++ b/certs/blacklist.c @@ -15,10 +15,9 @@ #include #include #include -#include +#include #include #include "blacklist.h" -#include "common.h" /* * According to crypto/asymmetric_keys/x509_cert_parser.c:x509_note_pkey_algo(), @@ -365,8 +364,9 @@ static __init int load_revocation_certificate_list(void) if (revocation_certificate_list_size) pr_notice("Loading compiled-in revocation X.509 certificates\n"); - return load_certificate_list(revocation_certificate_list, revocation_certificate_list_size, - blacklist_keyring); + return x509_load_certificate_list(revocation_certificate_list, + revocation_certificate_list_size, + blacklist_keyring); } late_initcall(load_revocation_certificate_list); #endif diff --git a/certs/blacklist_hashes.c b/certs/blacklist_hashes.c index 344892337be07..86d66fe113489 100644 --- a/certs/blacklist_hashes.c +++ b/certs/blacklist_hashes.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include "blacklist.h" -const char __initdata *const blacklist_hashes[] = { -#include CONFIG_SYSTEM_BLACKLIST_HASH_LIST +const char __initconst *const blacklist_hashes[] = { +#include "blacklist_hash_list" , NULL }; diff --git a/certs/common.h b/certs/common.h deleted file mode 100644 index abdb5795936b7..0000000000000 --- a/certs/common.h +++ /dev/null @@ -1,9 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ - -#ifndef _CERT_COMMON_H -#define _CERT_COMMON_H - -int load_certificate_list(const u8 cert_list[], const unsigned long list_size, - const struct key *keyring); - -#endif diff --git a/certs/extract-cert.c b/certs/extract-cert.c index f7ef7862f207c..8c1fb9a70d66b 100644 --- a/certs/extract-cert.c +++ b/certs/extract-cert.c @@ -23,6 +23,13 @@ #include #include +/* + * OpenSSL 3.0 deprecates the OpenSSL's ENGINE API. + * + * Remove this if/when that API is no longer used + */ +#pragma GCC diagnostic ignored "-Wdeprecated-declarations" + #define PKEY_ID_PKCS7 2 static __attribute__((noreturn)) diff --git a/certs/system_keyring.c b/certs/system_keyring.c index 05b66ce9d1c9e..5042cc54fa5ec 100644 --- a/certs/system_keyring.c +++ b/certs/system_keyring.c @@ -16,7 +16,6 @@ #include #include #include -#include "common.h" static struct key *builtin_trusted_keys; #ifdef CONFIG_SECONDARY_TRUSTED_KEYRING @@ -183,7 +182,8 @@ __init int load_module_cert(struct key *keyring) pr_notice("Loading compiled-in module X.509 certificates\n"); - return load_certificate_list(system_certificate_list, module_cert_size, keyring); + return x509_load_certificate_list(system_certificate_list, + module_cert_size, keyring); } /* @@ -204,7 +204,7 @@ static __init int load_system_certificate_list(void) size = system_certificate_list_size - module_cert_size; #endif - return load_certificate_list(p, size, builtin_trusted_keys); + return x509_load_certificate_list(p, size, builtin_trusted_keys); } late_initcall(load_system_certificate_list); diff --git a/crypto/Kconfig b/crypto/Kconfig index 19197469cfab3..1d44893a997ba 100644 --- a/crypto/Kconfig +++ b/crypto/Kconfig @@ -15,6 +15,7 @@ source "crypto/async_tx/Kconfig" # menuconfig CRYPTO tristate "Cryptographic API" + select LIB_MEMNEQ help This option provides the core Cryptographic API. diff --git a/crypto/Makefile b/crypto/Makefile index 43bc33e247d19..ceaaa9f34145a 100644 --- a/crypto/Makefile +++ b/crypto/Makefile @@ -4,7 +4,7 @@ # obj-$(CONFIG_CRYPTO) += crypto.o -crypto-y := api.o cipher.o compress.o memneq.o +crypto-y := api.o cipher.o compress.o obj-$(CONFIG_CRYPTO_ENGINE) += crypto_engine.o obj-$(CONFIG_CRYPTO_FIPS) += fips.o diff --git a/crypto/asymmetric_keys/Kconfig b/crypto/asymmetric_keys/Kconfig index 460bc5d0a828c..3df3fe4ed95fa 100644 --- a/crypto/asymmetric_keys/Kconfig +++ b/crypto/asymmetric_keys/Kconfig @@ -75,4 +75,14 @@ config SIGNED_PE_FILE_VERIFICATION This option provides support for verifying the signature(s) on a signed PE binary. +config FIPS_SIGNATURE_SELFTEST + bool "Run FIPS selftests on the X.509+PKCS7 signature verification" + help + This option causes some selftests to be run on the signature + verification code, using some built in data. This is required + for FIPS. + depends on KEYS + depends on ASYMMETRIC_KEY_TYPE + depends on PKCS7_MESSAGE_PARSER + endif # ASYMMETRIC_KEY_TYPE diff --git a/crypto/asymmetric_keys/Makefile b/crypto/asymmetric_keys/Makefile index c38424f55b08d..0d1fa1b692c6b 100644 --- a/crypto/asymmetric_keys/Makefile +++ b/crypto/asymmetric_keys/Makefile @@ -20,7 +20,9 @@ x509_key_parser-y := \ x509.asn1.o \ x509_akid.asn1.o \ x509_cert_parser.o \ + x509_loader.o \ x509_public_key.o +x509_key_parser-$(CONFIG_FIPS_SIGNATURE_SELFTEST) += selftest.o $(obj)/x509_cert_parser.o: \ $(obj)/x509.asn1.h \ diff --git a/crypto/asymmetric_keys/selftest.c b/crypto/asymmetric_keys/selftest.c new file mode 100644 index 0000000000000..fa0bf7f242849 --- /dev/null +++ b/crypto/asymmetric_keys/selftest.c @@ -0,0 +1,224 @@ +/* Self-testing for signature checking. + * + * Copyright (C) 2022 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#include +#include +#include +#include +#include "x509_parser.h" + +struct certs_test { + const u8 *data; + size_t data_len; + const u8 *pkcs7; + size_t pkcs7_len; +}; + +/* + * Set of X.509 certificates to provide public keys for the tests. These will + * be loaded into a temporary keyring for the duration of the testing. + */ +static const __initconst u8 certs_selftest_keys[] = { + "\x30\x82\x05\x55\x30\x82\x03\x3d\xa0\x03\x02\x01\x02\x02\x14\x73" + "\x98\xea\x98\x2d\xd0\x2e\xa8\xb1\xcf\x57\xc7\xf2\x97\xb3\xe6\x1a" + "\xfc\x8c\x0a\x30\x0d\x06\x09\x2a\x86\x48\x86\xf7\x0d\x01\x01\x0b" + "\x05\x00\x30\x34\x31\x32\x30\x30\x06\x03\x55\x04\x03\x0c\x29\x43" + "\x65\x72\x74\x69\x66\x69\x63\x61\x74\x65\x20\x76\x65\x72\x69\x66" + "\x69\x63\x61\x74\x69\x6f\x6e\x20\x73\x65\x6c\x66\x2d\x74\x65\x73" + "\x74\x69\x6e\x67\x20\x6b\x65\x79\x30\x20\x17\x0d\x32\x32\x30\x35" + "\x31\x38\x32\x32\x33\x32\x34\x31\x5a\x18\x0f\x32\x31\x32\x32\x30" + "\x34\x32\x34\x32\x32\x33\x32\x34\x31\x5a\x30\x34\x31\x32\x30\x30" + "\x06\x03\x55\x04\x03\x0c\x29\x43\x65\x72\x74\x69\x66\x69\x63\x61" + "\x74\x65\x20\x76\x65\x72\x69\x66\x69\x63\x61\x74\x69\x6f\x6e\x20" + "\x73\x65\x6c\x66\x2d\x74\x65\x73\x74\x69\x6e\x67\x20\x6b\x65\x79" + "\x30\x82\x02\x22\x30\x0d\x06\x09\x2a\x86\x48\x86\xf7\x0d\x01\x01" + "\x01\x05\x00\x03\x82\x02\x0f\x00\x30\x82\x02\x0a\x02\x82\x02\x01" + "\x00\xcc\xac\x49\xdd\x3b\xca\xb0\x15\x7e\x84\x6a\xb2\x0a\x69\x5f" + "\x1c\x0a\x61\x82\x3b\x4f\x2c\xa3\x95\x2c\x08\x58\x4b\xb1\x5d\x99" + "\xe0\xc3\xc1\x79\xc2\xb3\xeb\xc0\x1e\x6d\x3e\x54\x1d\xbd\xb7\x92" + "\x7b\x4d\xb5\x95\x58\xb2\x52\x2e\xc6\x24\x4b\x71\x63\x80\x32\x77" + "\xa7\x38\x5e\xdb\x72\xae\x6e\x0d\xec\xfb\xb6\x6d\x01\x7f\xe9\x55" + "\x66\xdf\xbf\x1d\x76\x78\x02\x31\xe8\xe5\x07\xf8\xb7\x82\x5c\x0d" + "\xd4\xbb\xfb\xa2\x59\x0d\x2e\x3a\x78\x95\x3a\x8b\x46\x06\x47\x44" + "\x46\xd7\xcd\x06\x6a\x41\x13\xe3\x19\xf6\xbb\x6e\x38\xf4\x83\x01" + "\xa3\xbf\x4a\x39\x4f\xd7\x0a\xe9\x38\xb3\xf5\x94\x14\x4e\xdd\xf7" + "\x43\xfd\x24\xb2\x49\x3c\xa5\xf7\x7a\x7c\xd4\x45\x3d\x97\x75\x68" + "\xf1\xed\x4c\x42\x0b\x70\xca\x85\xf3\xde\xe5\x88\x2c\xc5\xbe\xb6" + "\x97\x34\xba\x24\x02\xcd\x8b\x86\x9f\xa9\x73\xca\x73\xcf\x92\x81" + "\xee\x75\x55\xbb\x18\x67\x5c\xff\x3f\xb5\xdd\x33\x1b\x0c\xe9\x78" + "\xdb\x5c\xcf\xaa\x5c\x43\x42\xdf\x5e\xa9\x6d\xec\xd7\xd7\xff\xe6" + "\xa1\x3a\x92\x1a\xda\xae\xf6\x8c\x6f\x7b\xd5\xb4\x6e\x06\xe9\x8f" + "\xe8\xde\x09\x31\x89\xed\x0e\x11\xa1\xfa\x8a\xe9\xe9\x64\x59\x62" + "\x53\xda\xd1\x70\xbe\x11\xd4\x99\x97\x11\xcf\x99\xde\x0b\x9d\x94" + "\x7e\xaa\xb8\x52\xea\x37\xdb\x90\x7e\x35\xbd\xd9\xfe\x6d\x0a\x48" + "\x70\x28\xdd\xd5\x0d\x7f\x03\x80\x93\x14\x23\x8f\xb9\x22\xcd\x7c" + "\x29\xfe\xf1\x72\xb5\x5c\x0b\x12\xcf\x9c\x15\xf6\x11\x4c\x7a\x45" + "\x25\x8c\x45\x0a\x34\xac\x2d\x9a\x81\xca\x0b\x13\x22\xcd\xeb\x1a" + "\x38\x88\x18\x97\x96\x08\x81\xaa\xcc\x8f\x0f\x8a\x32\x7b\x76\x68" + "\x03\x68\x43\xbf\x11\xba\x55\x60\xfd\x80\x1c\x0d\x9b\x69\xb6\x09" + "\x72\xbc\x0f\x41\x2f\x07\x82\xc6\xe3\xb2\x13\x91\xc4\x6d\x14\x95" + "\x31\xbe\x19\xbd\xbc\xed\xe1\x4c\x74\xa2\xe0\x78\x0b\xbb\x94\xec" + "\x4c\x53\x3a\xa2\xb5\x84\x1d\x4b\x65\x7e\xdc\xf7\xdb\x36\x7d\xbe" + "\x9e\x3b\x36\x66\x42\x66\x76\x35\xbf\xbe\xf0\xc1\x3c\x7c\xe9\x42" + "\x5c\x24\x53\x03\x05\xa8\x67\x24\x50\x02\x75\xff\x24\x46\x3b\x35" + "\x89\x76\xe6\x70\xda\xc5\x51\x8c\x9a\xe5\x05\xb0\x0b\xd0\x2d\xd4" + "\x7d\x57\x75\x94\x6b\xf9\x0a\xad\x0e\x41\x00\x15\xd0\x4f\xc0\x7f" + "\x90\x2d\x18\x48\x8f\x28\xfe\x5d\xa7\xcd\x99\x9e\xbd\x02\x6c\x8a" + "\x31\xf3\x1c\xc7\x4b\xe6\x93\xcd\x42\xa2\xe4\x68\x10\x47\x9d\xfc" + "\x21\x02\x03\x01\x00\x01\xa3\x5d\x30\x5b\x30\x0c\x06\x03\x55\x1d" + "\x13\x01\x01\xff\x04\x02\x30\x00\x30\x0b\x06\x03\x55\x1d\x0f\x04" + "\x04\x03\x02\x07\x80\x30\x1d\x06\x03\x55\x1d\x0e\x04\x16\x04\x14" + "\xf5\x87\x03\xbb\x33\xce\x1b\x73\xee\x02\xec\xcd\xee\x5b\x88\x17" + "\x51\x8f\xe3\xdb\x30\x1f\x06\x03\x55\x1d\x23\x04\x18\x30\x16\x80" + "\x14\xf5\x87\x03\xbb\x33\xce\x1b\x73\xee\x02\xec\xcd\xee\x5b\x88" + "\x17\x51\x8f\xe3\xdb\x30\x0d\x06\x09\x2a\x86\x48\x86\xf7\x0d\x01" + "\x01\x0b\x05\x00\x03\x82\x02\x01\x00\xc0\x2e\x12\x41\x7b\x73\x85" + "\x16\xc8\xdb\x86\x79\xe8\xf5\xcd\x44\xf4\xc6\xe2\x81\x23\x5e\x47" + "\xcb\xab\x25\xf1\x1e\x58\x3e\x31\x7f\x78\xad\x85\xeb\xfe\x14\x88" + "\x60\xf7\x7f\xd2\x26\xa2\xf4\x98\x2a\xfd\xba\x05\x0c\x20\x33\x12" + "\xcc\x4d\x14\x61\x64\x81\x93\xd3\x33\xed\xc8\xff\xf1\x78\xcc\x5f" + "\x51\x9f\x09\xd7\xbe\x0d\x5c\x74\xfd\x9b\xdf\x52\x4a\xc9\xa8\x71" + "\x25\x33\x04\x10\x67\x36\xd0\xb3\x0b\xc9\xa1\x40\x72\xae\x41\x7b" + "\x68\xe6\xe4\x7b\xd0\x28\xf7\x6d\xe7\x3f\x50\xfc\x91\x7c\x91\x56" + "\xd4\xdf\xa6\xbb\xe8\x4d\x1b\x58\xaa\x28\xfa\xc1\x19\xeb\x11\x2f" + "\x24\x8b\x7c\xc5\xa9\x86\x26\xaa\x6e\xb7\x9b\xd5\xf8\x06\xfb\x02" + "\x52\x7b\x9c\x9e\xa1\xe0\x07\x8b\x5e\xe4\xb8\x55\x29\xf6\x48\x52" + "\x1c\x1b\x54\x2d\x46\xd8\xe5\x71\xb9\x60\xd1\x45\xb5\x92\x89\x8a" + "\x63\x58\x2a\xb3\xc6\xb2\x76\xe2\x3c\x82\x59\x04\xae\x5a\xc4\x99" + "\x7b\x2e\x4b\x46\x57\xb8\x29\x24\xb2\xfd\xee\x2c\x0d\xa4\x83\xfa" + "\x65\x2a\x07\x35\x8b\x97\xcf\xbd\x96\x2e\xd1\x7e\x6c\xc2\x1e\x87" + "\xb6\x6c\x76\x65\xb5\xb2\x62\xda\x8b\xe9\x73\xe3\xdb\x33\xdd\x13" + "\x3a\x17\x63\x6a\x76\xde\x8d\x8f\xe0\x47\x61\x28\x3a\x83\xff\x8f" + "\xe7\xc7\xe0\x4a\xa3\xe5\x07\xcf\xe9\x8c\x35\x35\x2e\xe7\x80\x66" + "\x31\xbf\x91\x58\x0a\xe1\x25\x3d\x38\xd3\xa4\xf0\x59\x34\x47\x07" + "\x62\x0f\xbe\x30\xdd\x81\x88\x58\xf0\x28\xb0\x96\xe5\x82\xf8\x05" + "\xb7\x13\x01\xbc\xfa\xc6\x1f\x86\x72\xcc\xf9\xee\x8e\xd9\xd6\x04" + "\x8c\x24\x6c\xbf\x0f\x5d\x37\x39\xcf\x45\xc1\x93\x3a\xd2\xed\x5c" + "\x58\x79\x74\x86\x62\x30\x7e\x8e\xbb\xdd\x7a\xa9\xed\xca\x40\xcb" + "\x62\x47\xf4\xb4\x9f\x52\x7f\x72\x63\xa8\xf0\x2b\xaf\x45\x2a\x48" + "\x19\x6d\xe3\xfb\xf9\x19\x66\x69\xc8\xcc\x62\x87\x6c\x53\x2b\x2d" + "\x6e\x90\x6c\x54\x3a\x82\x25\x41\xcb\x18\x6a\xa4\x22\xa8\xa1\xc4" + "\x47\xd7\x81\x00\x1c\x15\x51\x0f\x1a\xaf\xef\x9f\xa6\x61\x8c\xbd" + "\x6b\x8b\xed\xe6\xac\x0e\xb6\x3a\x4c\x92\xe6\x0f\x91\x0a\x0f\x71" + "\xc7\xa0\xb9\x0d\x3a\x17\x5a\x6f\x35\xc8\xe7\x50\x4f\x46\xe8\x70" + "\x60\x48\x06\x82\x8b\x66\x58\xe6\x73\x91\x9c\x12\x3d\x35\x8e\x46" + "\xad\x5a\xf5\xb3\xdb\x69\x21\x04\xfd\xd3\x1c\xdf\x94\x9d\x56\xb0" + "\x0a\xd1\x95\x76\x8d\xec\x9e\xdd\x0b\x15\x97\x64\xad\xe5\xf2\x62" + "\x02\xfc\x9e\x5f\x56\x42\x39\x05\xb3" +}; + +/* + * Signed data and detached signature blobs that form the verification tests. + */ +static const __initconst u8 certs_selftest_1_data[] = { + "\x54\x68\x69\x73\x20\x69\x73\x20\x73\x6f\x6d\x65\x20\x74\x65\x73" + "\x74\x20\x64\x61\x74\x61\x20\x75\x73\x65\x64\x20\x66\x6f\x72\x20" + "\x73\x65\x6c\x66\x2d\x74\x65\x73\x74\x69\x6e\x67\x20\x63\x65\x72" + "\x74\x69\x66\x69\x63\x61\x74\x65\x20\x76\x65\x72\x69\x66\x69\x63" + "\x61\x74\x69\x6f\x6e\x2e\x0a" +}; + +static const __initconst u8 certs_selftest_1_pkcs7[] = { + "\x30\x82\x02\xab\x06\x09\x2a\x86\x48\x86\xf7\x0d\x01\x07\x02\xa0" + "\x82\x02\x9c\x30\x82\x02\x98\x02\x01\x01\x31\x0d\x30\x0b\x06\x09" + "\x60\x86\x48\x01\x65\x03\x04\x02\x01\x30\x0b\x06\x09\x2a\x86\x48" + "\x86\xf7\x0d\x01\x07\x01\x31\x82\x02\x75\x30\x82\x02\x71\x02\x01" + "\x01\x30\x4c\x30\x34\x31\x32\x30\x30\x06\x03\x55\x04\x03\x0c\x29" + "\x43\x65\x72\x74\x69\x66\x69\x63\x61\x74\x65\x20\x76\x65\x72\x69" + "\x66\x69\x63\x61\x74\x69\x6f\x6e\x20\x73\x65\x6c\x66\x2d\x74\x65" + "\x73\x74\x69\x6e\x67\x20\x6b\x65\x79\x02\x14\x73\x98\xea\x98\x2d" + "\xd0\x2e\xa8\xb1\xcf\x57\xc7\xf2\x97\xb3\xe6\x1a\xfc\x8c\x0a\x30" + "\x0b\x06\x09\x60\x86\x48\x01\x65\x03\x04\x02\x01\x30\x0d\x06\x09" + "\x2a\x86\x48\x86\xf7\x0d\x01\x01\x01\x05\x00\x04\x82\x02\x00\xac" + "\xb0\xf2\x07\xd6\x99\x6d\xc0\xc0\xd9\x8d\x31\x0d\x7e\x04\xeb\xc3" + "\x88\x90\xc4\x58\x46\xd4\xe2\xa0\xa3\x25\xe3\x04\x50\x37\x85\x8c" + "\x91\xc6\xfc\xc5\xd4\x92\xfd\x05\xd8\xb8\xa3\xb8\xba\x89\x13\x00" + "\x88\x79\x99\x51\x6b\x5b\x28\x31\xc0\xb3\x1b\x7a\x68\x2c\x00\xdb" + "\x4b\x46\x11\xf3\xfa\x50\x8e\x19\x89\xa2\x4c\xda\x4c\x89\x01\x11" + "\x89\xee\xd3\xc8\xc1\xe7\xa7\xf6\xb2\xa2\xf8\x65\xb8\x35\x20\x33" + "\xba\x12\x62\xd5\xbd\xaa\x71\xe5\x5b\xc0\x6a\x32\xff\x6a\x2e\x23" + "\xef\x2b\xb6\x58\xb1\xfb\x5f\x82\x34\x40\x6d\x9f\xbc\x27\xac\x37" + "\x23\x99\xcf\x7d\x20\xb2\x39\x01\xc0\x12\xce\xd7\x5d\x2f\xb6\xab" + "\xb5\x56\x4f\xef\xf4\x72\x07\x58\x65\xa9\xeb\x1f\x75\x1c\x5f\x0c" + "\x88\xe0\xa4\xe2\xcd\x73\x2b\x9e\xb2\x05\x7e\x12\xf8\xd0\x66\x41" + "\xcc\x12\x63\xd4\xd6\xac\x9b\x1d\x14\x77\x8d\x1c\x57\xd5\x27\xc6" + "\x49\xa2\x41\x43\xf3\x59\x29\xe5\xcb\xd1\x75\xbc\x3a\x97\x2a\x72" + "\x22\x66\xc5\x3b\xc1\xba\xfc\x53\x18\x98\xe2\x21\x64\xc6\x52\x87" + "\x13\xd5\x7c\x42\xe8\xfb\x9c\x9a\x45\x32\xd5\xa5\x22\x62\x9d\xd4" + "\xcb\xa4\xfa\x77\xbb\x50\x24\x0b\x8b\x88\x99\x15\x56\xa9\x1e\x92" + "\xbf\x5d\x94\x77\xb6\xf1\x67\x01\x60\x06\x58\x5c\xdf\x18\x52\x79" + "\x37\x30\x93\x7d\x87\x04\xf1\xe0\x55\x59\x52\xf3\xc2\xb1\x1c\x5b" + "\x12\x7c\x49\x87\xfb\xf7\xed\xdd\x95\x71\xec\x4b\x1a\x85\x08\xb0" + "\xa0\x36\xc4\x7b\xab\x40\xe0\xf1\x98\xcc\xaf\x19\x40\x8f\x47\x6f" + "\xf0\x6c\x84\x29\x7f\x7f\x04\x46\xcb\x08\x0f\xe0\xc1\xc9\x70\x6e" + "\x95\x3b\xa4\xbc\x29\x2b\x53\x67\x45\x1b\x0d\xbc\x13\xa5\x76\x31" + "\xaf\xb9\xd0\xe0\x60\x12\xd2\xf4\xb7\x7c\x58\x7e\xf6\x2d\xbb\x24" + "\x14\x5a\x20\x24\xa8\x12\xdf\x25\xbd\x42\xce\x96\x7c\x2e\xba\x14" + "\x1b\x81\x9f\x18\x45\xa4\xc6\x70\x3e\x0e\xf0\xd3\x7b\x9c\x10\xbe" + "\xb8\x7a\x89\xc5\x9e\xd9\x97\xdf\xd7\xe7\xc6\x1d\xc0\x20\x6c\xb8" + "\x1e\x3a\x63\xb8\x39\x8e\x8e\x62\xd5\xd2\xb4\xcd\xff\x46\xfc\x8e" + "\xec\x07\x35\x0c\xff\xb0\x05\xe6\xf4\xe5\xfe\xa2\xe3\x0a\xe6\x36" + "\xa7\x4a\x7e\x62\x1d\xc4\x50\x39\x35\x4e\x28\xcb\x4a\xfb\x9d\xdb" + "\xdd\x23\xd6\x53\xb1\x74\x77\x12\xf7\x9c\xf0\x9a\x6b\xf7\xa9\x64" + "\x2d\x86\x21\x2a\xcf\xc6\x54\xf5\xc9\xad\xfa\xb5\x12\xb4\xf3\x51" + "\x77\x55\x3c\x6f\x0c\x32\xd3\x8c\x44\x39\x71\x25\xfe\x96\xd2" +}; + +/* + * List of tests to be run. + */ +#define TEST(data, pkcs7) { data, sizeof(data) - 1, pkcs7, sizeof(pkcs7) - 1 } +static const struct certs_test certs_tests[] __initconst = { + TEST(certs_selftest_1_data, certs_selftest_1_pkcs7), +}; + +int __init fips_signature_selftest(void) +{ + struct key *keyring; + int ret, i; + + pr_notice("Running certificate verification selftests\n"); + + keyring = keyring_alloc(".certs_selftest", + GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, current_cred(), + (KEY_POS_ALL & ~KEY_POS_SETATTR) | + KEY_USR_VIEW | KEY_USR_READ | + KEY_USR_SEARCH, + KEY_ALLOC_NOT_IN_QUOTA, + NULL, NULL); + if (IS_ERR(keyring)) + panic("Can't allocate certs selftest keyring: %ld\n", + PTR_ERR(keyring)); + + ret = x509_load_certificate_list(certs_selftest_keys, + sizeof(certs_selftest_keys) - 1, keyring); + if (ret < 0) + panic("Can't allocate certs selftest keyring: %d\n", ret); + + for (i = 0; i < ARRAY_SIZE(certs_tests); i++) { + const struct certs_test *test = &certs_tests[i]; + struct pkcs7_message *pkcs7; + + pkcs7 = pkcs7_parse_message(test->pkcs7, test->pkcs7_len); + if (IS_ERR(pkcs7)) + panic("Certs selftest %d: pkcs7_parse_message() = %d\n", i, ret); + + pkcs7_supply_detached_data(pkcs7, test->data, test->data_len); + + ret = pkcs7_verify(pkcs7, VERIFYING_MODULE_SIGNATURE); + if (ret < 0) + panic("Certs selftest %d: pkcs7_verify() = %d\n", i, ret); + + ret = pkcs7_validate_trust(pkcs7, keyring); + if (ret < 0) + panic("Certs selftest %d: pkcs7_validate_trust() = %d\n", i, ret); + + pkcs7_free_message(pkcs7); + } + + key_put(keyring); + return 0; +} diff --git a/certs/common.c b/crypto/asymmetric_keys/x509_loader.c similarity index 87% rename from certs/common.c rename to crypto/asymmetric_keys/x509_loader.c index 16a220887a53e..1bc169dee22e0 100644 --- a/certs/common.c +++ b/crypto/asymmetric_keys/x509_loader.c @@ -2,11 +2,11 @@ #include #include -#include "common.h" +#include -int load_certificate_list(const u8 cert_list[], - const unsigned long list_size, - const struct key *keyring) +int x509_load_certificate_list(const u8 cert_list[], + const unsigned long list_size, + const struct key *keyring) { key_ref_t key; const u8 *p, *end; diff --git a/crypto/asymmetric_keys/x509_parser.h b/crypto/asymmetric_keys/x509_parser.h index 97a886cbe01c3..a299c9c56f409 100644 --- a/crypto/asymmetric_keys/x509_parser.h +++ b/crypto/asymmetric_keys/x509_parser.h @@ -40,6 +40,15 @@ struct x509_certificate { bool blacklisted; }; +/* + * selftest.c + */ +#ifdef CONFIG_FIPS_SIGNATURE_SELFTEST +extern int __init fips_signature_selftest(void); +#else +static inline int fips_signature_selftest(void) { return 0; } +#endif + /* * x509_cert_parser.c */ diff --git a/crypto/asymmetric_keys/x509_public_key.c b/crypto/asymmetric_keys/x509_public_key.c index 77ed4e93ad56f..0b4943a4592b7 100644 --- a/crypto/asymmetric_keys/x509_public_key.c +++ b/crypto/asymmetric_keys/x509_public_key.c @@ -244,9 +244,15 @@ static struct asymmetric_key_parser x509_key_parser = { /* * Module stuff */ +extern int __init certs_selftest(void); static int __init x509_key_init(void) { - return register_asymmetric_key_parser(&x509_key_parser); + int ret; + + ret = register_asymmetric_key_parser(&x509_key_parser); + if (ret < 0) + return ret; + return fips_signature_selftest(); } static void __exit x509_key_exit(void) diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 40e816419f48c..9601fa92950a0 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -2010,16 +2010,16 @@ unsigned int ata_read_log_page(struct ata_device *dev, u8 log, return err_mask; } -static bool ata_log_supported(struct ata_device *dev, u8 log) +static int ata_log_supported(struct ata_device *dev, u8 log) { struct ata_port *ap = dev->link->ap; if (dev->horkage & ATA_HORKAGE_NO_LOG_DIR) - return false; + return 0; if (ata_read_log_page(dev, ATA_LOG_DIRECTORY, 0, ap->sector_buf, 1)) - return false; - return get_unaligned_le16(&ap->sector_buf[log * 2]) ? true : false; + return 0; + return get_unaligned_le16(&ap->sector_buf[log * 2]); } static bool ata_identify_page_supported(struct ata_device *dev, u8 page) @@ -2455,15 +2455,20 @@ static void ata_dev_config_cpr(struct ata_device *dev) struct ata_cpr_log *cpr_log = NULL; u8 *desc, *buf = NULL; - if (ata_id_major_version(dev->id) < 11 || - !ata_log_supported(dev, ATA_LOG_CONCURRENT_POSITIONING_RANGES)) + if (ata_id_major_version(dev->id) < 11) + goto out; + + buf_len = ata_log_supported(dev, ATA_LOG_CONCURRENT_POSITIONING_RANGES); + if (buf_len == 0) goto out; /* * Read the concurrent positioning ranges log (0x47). We can have at - * most 255 32B range descriptors plus a 64B header. + * most 255 32B range descriptors plus a 64B header. This log varies in + * size, so use the size reported in the GPL directory. Reading beyond + * the supported length will result in an error. */ - buf_len = (64 + 255 * 32 + 511) & ~511; + buf_len <<= 9; buf = kzalloc(buf_len, GFP_KERNEL); if (!buf) goto out; @@ -5462,7 +5467,7 @@ struct ata_host *ata_host_alloc_pinfo(struct device *dev, const struct ata_port_info * const * ppi, int n_ports) { - const struct ata_port_info *pi; + const struct ata_port_info *pi = &ata_dummy_port_info; struct ata_host *host; int i, j; @@ -5470,7 +5475,7 @@ struct ata_host *ata_host_alloc_pinfo(struct device *dev, if (!host) return NULL; - for (i = 0, j = 0, pi = NULL; i < host->n_ports; i++) { + for (i = 0, j = 0; i < host->n_ports; i++) { struct ata_port *ap = host->ports[i]; if (ppi[j]) diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 42cecf95a4e58..86dbb1cdfabd8 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -2125,7 +2125,7 @@ static unsigned int ata_scsiop_inq_b9(struct ata_scsi_args *args, u8 *rbuf) /* SCSI Concurrent Positioning Ranges VPD page: SBC-5 rev 1 or later */ rbuf[1] = 0xb9; - put_unaligned_be16(64 + (int)cpr_log->nr_cpr * 32 - 4, &rbuf[3]); + put_unaligned_be16(64 + (int)cpr_log->nr_cpr * 32 - 4, &rbuf[2]); for (i = 0; i < cpr_log->nr_cpr; i++, desc += 32) { desc[0] = cpr_log->cpr[i].num; diff --git a/drivers/ata/libata-transport.c b/drivers/ata/libata-transport.c index ca129854a88c7..c380278874990 100644 --- a/drivers/ata/libata-transport.c +++ b/drivers/ata/libata-transport.c @@ -196,7 +196,7 @@ static struct { { XFER_PIO_0, "XFER_PIO_0" }, { XFER_PIO_SLOW, "XFER_PIO_SLOW" } }; -ata_bitfield_name_match(xfer,ata_xfer_names) +ata_bitfield_name_search(xfer, ata_xfer_names) /* * ATA Port attributes diff --git a/drivers/ata/pata_octeon_cf.c b/drivers/ata/pata_octeon_cf.c index 6b5ed3046b44d..35608a0cf552e 100644 --- a/drivers/ata/pata_octeon_cf.c +++ b/drivers/ata/pata_octeon_cf.c @@ -856,12 +856,14 @@ static int octeon_cf_probe(struct platform_device *pdev) int i; res_dma = platform_get_resource(dma_dev, IORESOURCE_MEM, 0); if (!res_dma) { + put_device(&dma_dev->dev); of_node_put(dma_node); return -EINVAL; } cf_port->dma_base = (u64)devm_ioremap(&pdev->dev, res_dma->start, resource_size(res_dma)); if (!cf_port->dma_base) { + put_device(&dma_dev->dev); of_node_put(dma_node); return -EINVAL; } @@ -871,6 +873,7 @@ static int octeon_cf_probe(struct platform_device *pdev) irq = i; irq_handler = octeon_cf_interrupt; } + put_device(&dma_dev->dev); } of_node_put(dma_node); } diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index 2ef23fce0860c..a97776ea9d990 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -564,6 +564,12 @@ ssize_t __weak cpu_show_srbds(struct device *dev, return sysfs_emit(buf, "Not affected\n"); } +ssize_t __weak cpu_show_mmio_stale_data(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sysfs_emit(buf, "Not affected\n"); +} + static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL); static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL); static DEVICE_ATTR(spectre_v2, 0444, cpu_show_spectre_v2, NULL); @@ -573,6 +579,7 @@ static DEVICE_ATTR(mds, 0444, cpu_show_mds, NULL); static DEVICE_ATTR(tsx_async_abort, 0444, cpu_show_tsx_async_abort, NULL); static DEVICE_ATTR(itlb_multihit, 0444, cpu_show_itlb_multihit, NULL); static DEVICE_ATTR(srbds, 0444, cpu_show_srbds, NULL); +static DEVICE_ATTR(mmio_stale_data, 0444, cpu_show_mmio_stale_data, NULL); static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_meltdown.attr, @@ -584,6 +591,7 @@ static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_tsx_async_abort.attr, &dev_attr_itlb_multihit.attr, &dev_attr_srbds.attr, + &dev_attr_mmio_stale_data.attr, NULL }; diff --git a/drivers/base/init.c b/drivers/base/init.c index d8d0fe687111a..397eb9880cecb 100644 --- a/drivers/base/init.c +++ b/drivers/base/init.c @@ -8,6 +8,7 @@ #include #include #include +#include #include "base.h" @@ -20,6 +21,7 @@ void __init driver_init(void) { /* These are the core pieces */ + bdi_init(&noop_backing_dev_info); devtmpfs_init(); devices_init(); buses_init(); diff --git a/drivers/base/memory.c b/drivers/base/memory.c index 084d67fd55cc8..bc60c9cd32308 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -558,7 +558,7 @@ static ssize_t hard_offline_page_store(struct device *dev, if (kstrtoull(buf, 0, &pfn) < 0) return -EINVAL; pfn >>= PAGE_SHIFT; - ret = memory_failure(pfn, 0); + ret = memory_failure(pfn, MF_SW_SIMULATED); if (ret == -EOPNOTSUPP) ret = 0; return ret ? ret : count; diff --git a/drivers/base/regmap/regmap-irq.c b/drivers/base/regmap/regmap-irq.c index 400c7412a7dcf..a6db605707b00 100644 --- a/drivers/base/regmap/regmap-irq.c +++ b/drivers/base/regmap/regmap-irq.c @@ -252,6 +252,7 @@ static void regmap_irq_enable(struct irq_data *data) struct regmap_irq_chip_data *d = irq_data_get_irq_chip_data(data); struct regmap *map = d->map; const struct regmap_irq *irq_data = irq_to_regmap_irq(d, data->hwirq); + unsigned int reg = irq_data->reg_offset / map->reg_stride; unsigned int mask, type; type = irq_data->type.type_falling_val | irq_data->type.type_rising_val; @@ -268,14 +269,14 @@ static void regmap_irq_enable(struct irq_data *data) * at the corresponding offset in regmap_irq_set_type(). */ if (d->chip->type_in_mask && type) - mask = d->type_buf[irq_data->reg_offset / map->reg_stride]; + mask = d->type_buf[reg] & irq_data->mask; else mask = irq_data->mask; if (d->chip->clear_on_unmask) d->clear_status = true; - d->mask_buf[irq_data->reg_offset / map->reg_stride] &= ~mask; + d->mask_buf[reg] &= ~mask; } static void regmap_irq_disable(struct irq_data *data) @@ -386,6 +387,7 @@ static inline int read_sub_irq_data(struct regmap_irq_chip_data *data, subreg = &chip->sub_reg_offsets[b]; for (i = 0; i < subreg->num_regs; i++) { unsigned int offset = subreg->offset[i]; + unsigned int index = offset / map->reg_stride; if (chip->not_fixed_stride) ret = regmap_read(map, @@ -394,7 +396,7 @@ static inline int read_sub_irq_data(struct regmap_irq_chip_data *data, else ret = regmap_read(map, chip->status_base + offset, - &data->status_buf[offset]); + &data->status_buf[index]); if (ret) break; diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index 2221d98638317..c3517ccc31591 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -1880,8 +1880,7 @@ static int _regmap_raw_write_impl(struct regmap *map, unsigned int reg, */ bool regmap_can_raw_write(struct regmap *map) { - return map->bus && map->bus->write && map->format.format_val && - map->format.format_reg; + return map->write && map->format.format_val && map->format.format_reg; } EXPORT_SYMBOL_GPL(regmap_can_raw_write); @@ -2155,10 +2154,9 @@ int regmap_noinc_write(struct regmap *map, unsigned int reg, size_t write_len; int ret; - if (!map->bus) - return -EINVAL; - if (!map->bus->write) + if (!map->write) return -ENOTSUPP; + if (val_len % map->format.val_bytes) return -EINVAL; if (!IS_ALIGNED(reg, map->reg_stride)) @@ -2278,7 +2276,7 @@ int regmap_bulk_write(struct regmap *map, unsigned int reg, const void *val, * Some devices don't support bulk write, for them we have a series of * single write operations. */ - if (!map->bus || !map->format.parse_inplace) { + if (!map->write || !map->format.parse_inplace) { map->lock(map->lock_arg); for (i = 0; i < val_count; i++) { unsigned int ival; @@ -2904,6 +2902,9 @@ int regmap_noinc_read(struct regmap *map, unsigned int reg, size_t read_len; int ret; + if (!map->read) + return -ENOTSUPP; + if (val_len % map->format.val_bytes) return -EINVAL; if (!IS_ALIGNED(reg, map->reg_stride)) @@ -3017,7 +3018,7 @@ int regmap_bulk_read(struct regmap *map, unsigned int reg, void *val, if (val_count == 0) return -EINVAL; - if (map->format.parse_inplace && (vol || map->cache_type == REGCACHE_NONE)) { + if (map->read && map->format.parse_inplace && (vol || map->cache_type == REGCACHE_NONE)) { ret = regmap_raw_read(map, reg, val, val_bytes * val_count); if (ret != 0) return ret; diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index a88ce4426400e..33f04ef78984c 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -2114,9 +2114,11 @@ static void blkfront_closing(struct blkfront_info *info) return; /* No more blkif_request(). */ - blk_mq_stop_hw_queues(info->rq); - blk_mark_disk_dead(info->gd); - set_capacity(info->gd, 0); + if (info->rq && info->gd) { + blk_mq_stop_hw_queues(info->rq); + blk_mark_disk_dead(info->gd); + set_capacity(info->gd, 0); + } for_each_rinfo(info, rinfo, i) { /* No more gnttab callback work. */ @@ -2457,16 +2459,19 @@ static int blkfront_remove(struct xenbus_device *xbdev) dev_dbg(&xbdev->dev, "%s removed", xbdev->nodename); - del_gendisk(info->gd); + if (info->gd) + del_gendisk(info->gd); mutex_lock(&blkfront_mutex); list_del(&info->info_list); mutex_unlock(&blkfront_mutex); blkif_free(info, 0); - xlbd_release_minors(info->gd->first_minor, info->gd->minors); - blk_cleanup_disk(info->gd); - blk_mq_free_tag_set(&info->tag_set); + if (info->gd) { + xlbd_release_minors(info->gd->first_minor, info->gd->minors); + blk_cleanup_disk(info->gd); + blk_mq_free_tag_set(&info->tag_set); + } kfree(info); return 0; diff --git a/drivers/bus/bt1-apb.c b/drivers/bus/bt1-apb.c index b25ff941e7c7f..63b1b4a76671d 100644 --- a/drivers/bus/bt1-apb.c +++ b/drivers/bus/bt1-apb.c @@ -175,10 +175,9 @@ static int bt1_apb_request_rst(struct bt1_apb *apb) int ret; apb->prst = devm_reset_control_get_optional_exclusive(apb->dev, "prst"); - if (IS_ERR(apb->prst)) { - dev_warn(apb->dev, "Couldn't get reset control line\n"); - return PTR_ERR(apb->prst); - } + if (IS_ERR(apb->prst)) + return dev_err_probe(apb->dev, PTR_ERR(apb->prst), + "Couldn't get reset control line\n"); ret = reset_control_deassert(apb->prst); if (ret) @@ -199,10 +198,9 @@ static int bt1_apb_request_clk(struct bt1_apb *apb) int ret; apb->pclk = devm_clk_get(apb->dev, "pclk"); - if (IS_ERR(apb->pclk)) { - dev_err(apb->dev, "Couldn't get APB clock descriptor\n"); - return PTR_ERR(apb->pclk); - } + if (IS_ERR(apb->pclk)) + return dev_err_probe(apb->dev, PTR_ERR(apb->pclk), + "Couldn't get APB clock descriptor\n"); ret = clk_prepare_enable(apb->pclk); if (ret) { diff --git a/drivers/bus/bt1-axi.c b/drivers/bus/bt1-axi.c index e7a6744acc7b8..70e49a6e53746 100644 --- a/drivers/bus/bt1-axi.c +++ b/drivers/bus/bt1-axi.c @@ -135,10 +135,9 @@ static int bt1_axi_request_rst(struct bt1_axi *axi) int ret; axi->arst = devm_reset_control_get_optional_exclusive(axi->dev, "arst"); - if (IS_ERR(axi->arst)) { - dev_warn(axi->dev, "Couldn't get reset control line\n"); - return PTR_ERR(axi->arst); - } + if (IS_ERR(axi->arst)) + return dev_err_probe(axi->dev, PTR_ERR(axi->arst), + "Couldn't get reset control line\n"); ret = reset_control_deassert(axi->arst); if (ret) @@ -159,10 +158,9 @@ static int bt1_axi_request_clk(struct bt1_axi *axi) int ret; axi->aclk = devm_clk_get(axi->dev, "aclk"); - if (IS_ERR(axi->aclk)) { - dev_err(axi->dev, "Couldn't get AXI Interconnect clock\n"); - return PTR_ERR(axi->aclk); - } + if (IS_ERR(axi->aclk)) + return dev_err_probe(axi->dev, PTR_ERR(axi->aclk), + "Couldn't get AXI Interconnect clock\n"); ret = clk_prepare_enable(axi->aclk); if (ret) { diff --git a/drivers/bus/fsl-mc/fsl-mc-bus.c b/drivers/bus/fsl-mc/fsl-mc-bus.c index e81a9700cfd03..6143dbf31f311 100644 --- a/drivers/bus/fsl-mc/fsl-mc-bus.c +++ b/drivers/bus/fsl-mc/fsl-mc-bus.c @@ -1239,14 +1239,14 @@ static int fsl_mc_bus_probe(struct platform_device *pdev) static int fsl_mc_bus_remove(struct platform_device *pdev) { struct fsl_mc *mc = platform_get_drvdata(pdev); + struct fsl_mc_io *mc_io; if (!fsl_mc_is_root_dprc(&mc->root_mc_bus_dev->dev)) return -EINVAL; + mc_io = mc->root_mc_bus_dev->mc_io; fsl_mc_device_remove(mc->root_mc_bus_dev); - - fsl_destroy_mc_io(mc->root_mc_bus_dev->mc_io); - mc->root_mc_bus_dev->mc_io = NULL; + fsl_destroy_mc_io(mc_io); bus_unregister_notifier(&fsl_mc_bus_type, &fsl_mc_nb); diff --git a/drivers/char/Kconfig b/drivers/char/Kconfig index 69fd31ffb8474..0b6c03643ddc6 100644 --- a/drivers/char/Kconfig +++ b/drivers/char/Kconfig @@ -429,28 +429,40 @@ config ADI driver include crash and makedumpfile. config RANDOM_TRUST_CPU - bool "Trust the CPU manufacturer to initialize Linux's CRNG" + bool "Initialize RNG using CPU RNG instructions" + default y depends on ARCH_RANDOM - default n help - Assume that CPU manufacturer (e.g., Intel or AMD for RDSEED or - RDRAND, IBM for the S390 and Power PC architectures) is trustworthy - for the purposes of initializing Linux's CRNG. Since this is not - something that can be independently audited, this amounts to trusting - that CPU manufacturer (perhaps with the insistence or mandate - of a Nation State's intelligence or law enforcement agencies) - has not installed a hidden back door to compromise the CPU's - random number generation facilities. This can also be configured - at boot with "random.trust_cpu=on/off". + Initialize the RNG using random numbers supplied by the CPU's + RNG instructions (e.g. RDRAND), if supported and available. These + random numbers are never used directly, but are rather hashed into + the main input pool, and this happens regardless of whether or not + this option is enabled. Instead, this option controls whether the + they are credited and hence can initialize the RNG. Additionally, + other sources of randomness are always used, regardless of this + setting. Enabling this implies trusting that the CPU can supply high + quality and non-backdoored random numbers. + + Say Y here unless you have reason to mistrust your CPU or believe + its RNG facilities may be faulty. This may also be configured at + boot time with "random.trust_cpu=on/off". config RANDOM_TRUST_BOOTLOADER - bool "Trust the bootloader to initialize Linux's CRNG" - help - Some bootloaders can provide entropy to increase the kernel's initial - device randomness. Say Y here to assume the entropy provided by the - booloader is trustworthy so it will be added to the kernel's entropy - pool. Otherwise, say N here so it will be regarded as device input that - only mixes the entropy pool. This can also be configured at boot with - "random.trust_bootloader=on/off". + bool "Initialize RNG using bootloader-supplied seed" + default y + help + Initialize the RNG using a seed supplied by the bootloader or boot + environment (e.g. EFI or a bootloader-generated device tree). This + seed is not used directly, but is rather hashed into the main input + pool, and this happens regardless of whether or not this option is + enabled. Instead, this option controls whether the seed is credited + and hence can initialize the RNG. Additionally, other sources of + randomness are always used, regardless of this setting. Enabling + this implies trusting that the bootloader can supply high quality and + non-backdoored seeds. + + Say Y here unless you have reason to mistrust your bootloader or + believe its RNG facilities may be faulty. This may also be configured + at boot time with "random.trust_bootloader=on/off". endmenu diff --git a/drivers/char/hw_random/virtio-rng.c b/drivers/char/hw_random/virtio-rng.c index e856df7e285c7..a6f3a8a2aca6d 100644 --- a/drivers/char/hw_random/virtio-rng.c +++ b/drivers/char/hw_random/virtio-rng.c @@ -159,6 +159,8 @@ static int probe_common(struct virtio_device *vdev) goto err_find; } + virtio_device_ready(vdev); + /* we always have a pending entropy request */ request_entropy(vi); diff --git a/drivers/char/lp.c b/drivers/char/lp.c index 0e22e3b0a04e7..38aad99ebb615 100644 --- a/drivers/char/lp.c +++ b/drivers/char/lp.c @@ -1019,7 +1019,7 @@ static struct parport_driver lp_driver = { static int __init lp_init(void) { - int i, err = 0; + int i, err; if (parport_nr[0] == LP_PARPORT_OFF) return 0; diff --git a/drivers/char/random.c b/drivers/char/random.c index b691b9d595033..e3dd1dd3dd226 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -87,7 +87,7 @@ static struct fasync_struct *fasync; /* Control how we warn userspace. */ static struct ratelimit_state urandom_warning = - RATELIMIT_STATE_INIT("warn_urandom_randomness", HZ, 3); + RATELIMIT_STATE_INIT_FLAGS("urandom_warning", HZ, 3, RATELIMIT_MSG_ON_RELEASE); static int ratelimit_disable __read_mostly = IS_ENABLED(CONFIG_WARN_ALL_UNSEEDED_RANDOM); module_param_named(ratelimit_disable, ratelimit_disable, int, 0644); @@ -408,7 +408,7 @@ static ssize_t get_random_bytes_user(struct iov_iter *iter) /* * Immediately overwrite the ChaCha key at index 4 with random - * bytes, in case userspace causes copy_to_user() below to sleep + * bytes, in case userspace causes copy_to_iter() below to sleep * forever, so that we still retain forward secrecy in that case. */ crng_make_state(chacha_state, (u8 *)&chacha_state[4], CHACHA_KEY_SIZE); @@ -650,7 +650,8 @@ static void __cold _credit_init_bits(size_t bits) if (orig < POOL_READY_BITS && new >= POOL_READY_BITS) { crng_reseed(); /* Sets crng_init to CRNG_READY under base_crng.lock. */ - execute_in_process_context(crng_set_ready, &set_ready); + if (static_key_initialized) + execute_in_process_context(crng_set_ready, &set_ready); wake_up_interruptible(&crng_init_wait); kill_fasync(&fasync, SIGIO, POLL_IN); pr_notice("crng init done\n"); @@ -724,9 +725,8 @@ static void __cold _credit_init_bits(size_t bits) * **********************************************************************/ -static bool used_arch_random; -static bool trust_cpu __ro_after_init = IS_ENABLED(CONFIG_RANDOM_TRUST_CPU); -static bool trust_bootloader __ro_after_init = IS_ENABLED(CONFIG_RANDOM_TRUST_BOOTLOADER); +static bool trust_cpu __initdata = IS_ENABLED(CONFIG_RANDOM_TRUST_CPU); +static bool trust_bootloader __initdata = IS_ENABLED(CONFIG_RANDOM_TRUST_BOOTLOADER); static int __init parse_trust_cpu(char *arg) { return kstrtobool(arg, &trust_cpu); @@ -776,7 +776,7 @@ static struct notifier_block pm_notifier = { .notifier_call = random_pm_notifica int __init random_init(const char *command_line) { ktime_t now = ktime_get_real(); - unsigned int i, arch_bytes; + unsigned int i, arch_bits; unsigned long entropy; #if defined(LATENT_ENTROPY_PLUGIN) @@ -784,12 +784,12 @@ int __init random_init(const char *command_line) _mix_pool_bytes(compiletime_seed, sizeof(compiletime_seed)); #endif - for (i = 0, arch_bytes = BLAKE2S_BLOCK_SIZE; + for (i = 0, arch_bits = BLAKE2S_BLOCK_SIZE * 8; i < BLAKE2S_BLOCK_SIZE; i += sizeof(entropy)) { if (!arch_get_random_seed_long_early(&entropy) && !arch_get_random_long_early(&entropy)) { entropy = random_get_entropy(); - arch_bytes -= sizeof(entropy); + arch_bits -= sizeof(entropy) * 8; } _mix_pool_bytes(&entropy, sizeof(entropy)); } @@ -798,11 +798,18 @@ int __init random_init(const char *command_line) _mix_pool_bytes(command_line, strlen(command_line)); add_latent_entropy(); + /* + * If we were initialized by the bootloader before jump labels are + * initialized, then we should enable the static branch here, where + * it's guaranteed that jump labels have been initialized. + */ + if (!static_branch_likely(&crng_is_ready) && crng_init >= CRNG_READY) + crng_set_ready(NULL); + if (crng_ready()) crng_reseed(); else if (trust_cpu) - credit_init_bits(arch_bytes * 8); - used_arch_random = arch_bytes * 8 >= POOL_READY_BITS; + _credit_init_bits(arch_bits); WARN_ON(register_pm_notifier(&pm_notifier)); @@ -811,17 +818,6 @@ int __init random_init(const char *command_line) return 0; } -/* - * Returns whether arch randomness has been mixed into the initial - * state of the RNG, regardless of whether or not that randomness - * was credited. Knowing this is only good for a very limited set - * of uses, such as early init printk pointer obfuscation. - */ -bool rng_has_arch_random(void) -{ - return used_arch_random; -} - /* * Add device- or boot-specific data to the input pool to help * initialize it. @@ -865,13 +861,12 @@ EXPORT_SYMBOL_GPL(add_hwgenerator_randomness); * Handle random seed passed by bootloader, and credit it if * CONFIG_RANDOM_TRUST_BOOTLOADER is set. */ -void __cold add_bootloader_randomness(const void *buf, size_t len) +void __init add_bootloader_randomness(const void *buf, size_t len) { mix_pool_bytes(buf, len); if (trust_bootloader) credit_init_bits(len * 8); } -EXPORT_SYMBOL_GPL(add_bootloader_randomness); #if IS_ENABLED(CONFIG_VMGENID) static BLOCKING_NOTIFIER_HEAD(vmfork_chain); @@ -1014,7 +1009,7 @@ void add_interrupt_randomness(int irq) if (new_count & MIX_INFLIGHT) return; - if (new_count < 64 && !time_is_before_jiffies(fast_pool->last + HZ)) + if (new_count < 1024 && !time_is_before_jiffies(fast_pool->last + HZ)) return; if (unlikely(!fast_pool->mix.func)) diff --git a/drivers/clocksource/hyperv_timer.c b/drivers/clocksource/hyperv_timer.c index ff188ab68496e..bb47610bbd1c4 100644 --- a/drivers/clocksource/hyperv_timer.c +++ b/drivers/clocksource/hyperv_timer.c @@ -565,4 +565,3 @@ void __init hv_init_clocksource(void) hv_sched_clock_offset = hv_read_reference_counter(); hv_setup_sched_clock(read_hv_sched_clock_msr); } -EXPORT_SYMBOL_GPL(hv_init_clocksource); diff --git a/drivers/comedi/drivers/vmk80xx.c b/drivers/comedi/drivers/vmk80xx.c index 46023adc53958..4536ed43f65b2 100644 --- a/drivers/comedi/drivers/vmk80xx.c +++ b/drivers/comedi/drivers/vmk80xx.c @@ -684,7 +684,7 @@ static int vmk80xx_alloc_usb_buffers(struct comedi_device *dev) if (!devpriv->usb_rx_buf) return -ENOMEM; - size = max(usb_endpoint_maxp(devpriv->ep_rx), MIN_BUF_SIZE); + size = max(usb_endpoint_maxp(devpriv->ep_tx), MIN_BUF_SIZE); devpriv->usb_tx_buf = kzalloc(size, GFP_KERNEL); if (!devpriv->usb_tx_buf) return -ENOMEM; diff --git a/drivers/dma-buf/udmabuf.c b/drivers/dma-buf/udmabuf.c index e7330684d3b82..9631f2fd2faf7 100644 --- a/drivers/dma-buf/udmabuf.c +++ b/drivers/dma-buf/udmabuf.c @@ -32,8 +32,11 @@ static vm_fault_t udmabuf_vm_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct udmabuf *ubuf = vma->vm_private_data; + pgoff_t pgoff = vmf->pgoff; - vmf->page = ubuf->pages[vmf->pgoff]; + if (pgoff >= ubuf->pagecount) + return VM_FAULT_SIGBUS; + vmf->page = ubuf->pages[pgoff]; get_page(vmf->page); return 0; } diff --git a/drivers/firewire/core-cdev.c b/drivers/firewire/core-cdev.c index c9fe5903725a5..9c89f7d53e99d 100644 --- a/drivers/firewire/core-cdev.c +++ b/drivers/firewire/core-cdev.c @@ -1211,7 +1211,7 @@ static int ioctl_get_cycle_timer2(struct client *client, union ioctl_arg *arg) struct fw_cdev_get_cycle_timer2 *a = &arg->get_cycle_timer2; struct fw_card *card = client->device->card; struct timespec64 ts = {0, 0}; - u32 cycle_time; + u32 cycle_time = 0; int ret = 0; local_irq_disable(); diff --git a/drivers/firewire/core-device.c b/drivers/firewire/core-device.c index 90ed8fdaba754..adddd8c45d0c1 100644 --- a/drivers/firewire/core-device.c +++ b/drivers/firewire/core-device.c @@ -372,8 +372,7 @@ static ssize_t rom_index_show(struct device *dev, struct fw_device *device = fw_device(dev->parent); struct fw_unit *unit = fw_unit(dev); - return snprintf(buf, PAGE_SIZE, "%d\n", - (int)(unit->directory - device->config_rom)); + return sysfs_emit(buf, "%td\n", unit->directory - device->config_rom); } static struct device_attribute fw_unit_attributes[] = { @@ -403,8 +402,7 @@ static ssize_t guid_show(struct device *dev, int ret; down_read(&fw_device_rwsem); - ret = snprintf(buf, PAGE_SIZE, "0x%08x%08x\n", - device->config_rom[3], device->config_rom[4]); + ret = sysfs_emit(buf, "0x%08x%08x\n", device->config_rom[3], device->config_rom[4]); up_read(&fw_device_rwsem); return ret; diff --git a/drivers/firmware/arm_scmi/base.c b/drivers/firmware/arm_scmi/base.c index 20fba7370f4e5..a52f084a6a87b 100644 --- a/drivers/firmware/arm_scmi/base.c +++ b/drivers/firmware/arm_scmi/base.c @@ -36,7 +36,7 @@ struct scmi_msg_resp_base_attributes { struct scmi_msg_resp_base_discover_agent { __le32 agent_id; - u8 name[SCMI_MAX_STR_SIZE]; + u8 name[SCMI_SHORT_NAME_MAX_SIZE]; }; @@ -119,7 +119,7 @@ scmi_base_vendor_id_get(const struct scmi_protocol_handle *ph, bool sub_vendor) ret = ph->xops->do_xfer(ph, t); if (!ret) - memcpy(vendor_id, t->rx.buf, size); + strscpy(vendor_id, t->rx.buf, size); ph->xops->xfer_put(ph, t); @@ -221,11 +221,17 @@ scmi_base_implementation_list_get(const struct scmi_protocol_handle *ph, calc_list_sz = (1 + (loop_num_ret - 1) / sizeof(u32)) * sizeof(u32); if (calc_list_sz != real_list_sz) { - dev_err(dev, - "Malformed reply - real_sz:%zd calc_sz:%u\n", - real_list_sz, calc_list_sz); - ret = -EPROTO; - break; + dev_warn(dev, + "Malformed reply - real_sz:%zd calc_sz:%u (loop_num_ret:%d)\n", + real_list_sz, calc_list_sz, loop_num_ret); + /* + * Bail out if the expected list size is bigger than the + * total payload size of the received reply. + */ + if (calc_list_sz > real_list_sz) { + ret = -EPROTO; + break; + } } for (loop = 0; loop < loop_num_ret; loop++) @@ -270,7 +276,7 @@ static int scmi_base_discover_agent_get(const struct scmi_protocol_handle *ph, ret = ph->xops->do_xfer(ph, t); if (!ret) { agent_info = t->rx.buf; - strlcpy(name, agent_info->name, SCMI_MAX_STR_SIZE); + strscpy(name, agent_info->name, SCMI_SHORT_NAME_MAX_SIZE); } ph->xops->xfer_put(ph, t); @@ -369,7 +375,7 @@ static int scmi_base_protocol_init(const struct scmi_protocol_handle *ph) int id, ret; u8 *prot_imp; u32 version; - char name[SCMI_MAX_STR_SIZE]; + char name[SCMI_SHORT_NAME_MAX_SIZE]; struct device *dev = ph->dev; struct scmi_revision_info *rev = scmi_revision_area_get(ph); diff --git a/drivers/firmware/arm_scmi/clock.c b/drivers/firmware/arm_scmi/clock.c index 4d36a9a133d1e..c7a83f6e38e5a 100644 --- a/drivers/firmware/arm_scmi/clock.c +++ b/drivers/firmware/arm_scmi/clock.c @@ -153,7 +153,7 @@ static int scmi_clock_attributes_get(const struct scmi_protocol_handle *ph, if (!ret) { u32 latency = 0; attributes = le32_to_cpu(attr->attributes); - strlcpy(clk->name, attr->name, SCMI_MAX_STR_SIZE); + strscpy(clk->name, attr->name, SCMI_SHORT_NAME_MAX_SIZE); /* clock_enable_latency field is present only since SCMI v3.1 */ if (PROTOCOL_REV_MAJOR(version) >= 0x2) latency = le32_to_cpu(attr->clock_enable_latency); @@ -266,9 +266,7 @@ scmi_clock_describe_rates_get(const struct scmi_protocol_handle *ph, u32 clk_id, struct scmi_clock_info *clk) { int ret; - void *iter; - struct scmi_msg_clock_describe_rates *msg; struct scmi_iterator_ops ops = { .prepare_message = iter_clk_describe_prepare_message, .update_state = iter_clk_describe_update_state, @@ -281,7 +279,8 @@ scmi_clock_describe_rates_get(const struct scmi_protocol_handle *ph, u32 clk_id, iter = ph->hops->iter_response_init(ph, &ops, SCMI_MAX_NUM_RATES, CLOCK_DESCRIBE_RATES, - sizeof(*msg), &cpriv); + sizeof(struct scmi_msg_clock_describe_rates), + &cpriv); if (IS_ERR(iter)) return PTR_ERR(iter); diff --git a/drivers/firmware/arm_scmi/perf.c b/drivers/firmware/arm_scmi/perf.c index 8f4051aca2200..bbb0331801ff4 100644 --- a/drivers/firmware/arm_scmi/perf.c +++ b/drivers/firmware/arm_scmi/perf.c @@ -252,7 +252,7 @@ scmi_perf_domain_attributes_get(const struct scmi_protocol_handle *ph, dom_info->mult_factor = (dom_info->sustained_freq_khz * 1000) / dom_info->sustained_perf_level; - strlcpy(dom_info->name, attr->name, SCMI_MAX_STR_SIZE); + strscpy(dom_info->name, attr->name, SCMI_SHORT_NAME_MAX_SIZE); } ph->xops->xfer_put(ph, t); @@ -332,7 +332,6 @@ scmi_perf_describe_levels_get(const struct scmi_protocol_handle *ph, u32 domain, { int ret; void *iter; - struct scmi_msg_perf_describe_levels *msg; struct scmi_iterator_ops ops = { .prepare_message = iter_perf_levels_prepare_message, .update_state = iter_perf_levels_update_state, @@ -345,7 +344,8 @@ scmi_perf_describe_levels_get(const struct scmi_protocol_handle *ph, u32 domain, iter = ph->hops->iter_response_init(ph, &ops, MAX_OPPS, PERF_DESCRIBE_LEVELS, - sizeof(*msg), &ppriv); + sizeof(struct scmi_msg_perf_describe_levels), + &ppriv); if (IS_ERR(iter)) return PTR_ERR(iter); diff --git a/drivers/firmware/arm_scmi/power.c b/drivers/firmware/arm_scmi/power.c index 964882cc87471..356e83631664d 100644 --- a/drivers/firmware/arm_scmi/power.c +++ b/drivers/firmware/arm_scmi/power.c @@ -122,7 +122,7 @@ scmi_power_domain_attributes_get(const struct scmi_protocol_handle *ph, dom_info->state_set_notify = SUPPORTS_STATE_SET_NOTIFY(flags); dom_info->state_set_async = SUPPORTS_STATE_SET_ASYNC(flags); dom_info->state_set_sync = SUPPORTS_STATE_SET_SYNC(flags); - strlcpy(dom_info->name, attr->name, SCMI_MAX_STR_SIZE); + strscpy(dom_info->name, attr->name, SCMI_SHORT_NAME_MAX_SIZE); } ph->xops->xfer_put(ph, t); diff --git a/drivers/firmware/arm_scmi/protocols.h b/drivers/firmware/arm_scmi/protocols.h index 73304af5ec4ac..c679f3fb8718b 100644 --- a/drivers/firmware/arm_scmi/protocols.h +++ b/drivers/firmware/arm_scmi/protocols.h @@ -24,8 +24,6 @@ #include -#define SCMI_SHORT_NAME_MAX_SIZE 16 - #define PROTOCOL_REV_MINOR_MASK GENMASK(15, 0) #define PROTOCOL_REV_MAJOR_MASK GENMASK(31, 16) #define PROTOCOL_REV_MAJOR(x) ((u16)(FIELD_GET(PROTOCOL_REV_MAJOR_MASK, (x)))) diff --git a/drivers/firmware/arm_scmi/reset.c b/drivers/firmware/arm_scmi/reset.c index a420a91020940..673f3eb498f43 100644 --- a/drivers/firmware/arm_scmi/reset.c +++ b/drivers/firmware/arm_scmi/reset.c @@ -116,7 +116,7 @@ scmi_reset_domain_attributes_get(const struct scmi_protocol_handle *ph, dom_info->latency_us = le32_to_cpu(attr->latency); if (dom_info->latency_us == U32_MAX) dom_info->latency_us = 0; - strlcpy(dom_info->name, attr->name, SCMI_MAX_STR_SIZE); + strscpy(dom_info->name, attr->name, SCMI_SHORT_NAME_MAX_SIZE); } ph->xops->xfer_put(ph, t); diff --git a/drivers/firmware/arm_scmi/sensors.c b/drivers/firmware/arm_scmi/sensors.c index 21e0ce89b153a..7288c61178380 100644 --- a/drivers/firmware/arm_scmi/sensors.c +++ b/drivers/firmware/arm_scmi/sensors.c @@ -338,7 +338,6 @@ static int scmi_sensor_update_intervals(const struct scmi_protocol_handle *ph, struct scmi_sensor_info *s) { void *iter; - struct scmi_msg_sensor_list_update_intervals *msg; struct scmi_iterator_ops ops = { .prepare_message = iter_intervals_prepare_message, .update_state = iter_intervals_update_state, @@ -351,22 +350,28 @@ static int scmi_sensor_update_intervals(const struct scmi_protocol_handle *ph, iter = ph->hops->iter_response_init(ph, &ops, s->intervals.count, SENSOR_LIST_UPDATE_INTERVALS, - sizeof(*msg), &upriv); + sizeof(struct scmi_msg_sensor_list_update_intervals), + &upriv); if (IS_ERR(iter)) return PTR_ERR(iter); return ph->hops->iter_response_run(iter); } +struct scmi_apriv { + bool any_axes_support_extended_names; + struct scmi_sensor_info *s; +}; + static void iter_axes_desc_prepare_message(void *message, const unsigned int desc_index, const void *priv) { struct scmi_msg_sensor_axis_description_get *msg = message; - const struct scmi_sensor_info *s = priv; + const struct scmi_apriv *apriv = priv; /* Set the number of sensors to be skipped/already read */ - msg->id = cpu_to_le32(s->id); + msg->id = cpu_to_le32(apriv->s->id); msg->axis_desc_index = cpu_to_le32(desc_index); } @@ -393,19 +398,21 @@ iter_axes_desc_process_response(const struct scmi_protocol_handle *ph, u32 attrh, attrl; struct scmi_sensor_axis_info *a; size_t dsize = SCMI_MSG_RESP_AXIS_DESCR_BASE_SZ; - struct scmi_sensor_info *s = priv; + struct scmi_apriv *apriv = priv; const struct scmi_axis_descriptor *adesc = st->priv; attrl = le32_to_cpu(adesc->attributes_low); + if (SUPPORTS_EXTENDED_AXIS_NAMES(attrl)) + apriv->any_axes_support_extended_names = true; - a = &s->axis[st->desc_index + st->loop_idx]; + a = &apriv->s->axis[st->desc_index + st->loop_idx]; a->id = le32_to_cpu(adesc->id); a->extended_attrs = SUPPORTS_EXTEND_ATTRS(attrl); attrh = le32_to_cpu(adesc->attributes_high); a->scale = S32_EXT(SENSOR_SCALE(attrh)); a->type = SENSOR_TYPE(attrh); - strscpy(a->name, adesc->name, SCMI_MAX_STR_SIZE); + strscpy(a->name, adesc->name, SCMI_SHORT_NAME_MAX_SIZE); if (a->extended_attrs) { unsigned int ares = le32_to_cpu(adesc->resolution); @@ -444,10 +451,19 @@ iter_axes_extended_name_process_response(const struct scmi_protocol_handle *ph, void *priv) { struct scmi_sensor_axis_info *a; - const struct scmi_sensor_info *s = priv; + const struct scmi_apriv *apriv = priv; struct scmi_sensor_axis_name_descriptor *adesc = st->priv; + u32 axis_id = le32_to_cpu(adesc->axis_id); - a = &s->axis[st->desc_index + st->loop_idx]; + if (axis_id >= st->max_resources) + return -EPROTO; + + /* + * Pick the corresponding descriptor based on the axis_id embedded + * in the reply since the list of axes supporting extended names + * can be a subset of all the axes. + */ + a = &apriv->s->axis[axis_id]; strscpy(a->name, adesc->name, SCMI_MAX_STR_SIZE); st->priv = ++adesc; @@ -458,21 +474,36 @@ static int scmi_sensor_axis_extended_names_get(const struct scmi_protocol_handle *ph, struct scmi_sensor_info *s) { + int ret; void *iter; - struct scmi_msg_sensor_axis_description_get *msg; struct scmi_iterator_ops ops = { .prepare_message = iter_axes_desc_prepare_message, .update_state = iter_axes_extended_name_update_state, .process_response = iter_axes_extended_name_process_response, }; + struct scmi_apriv apriv = { + .any_axes_support_extended_names = false, + .s = s, + }; iter = ph->hops->iter_response_init(ph, &ops, s->num_axis, SENSOR_AXIS_NAME_GET, - sizeof(*msg), s); + sizeof(struct scmi_msg_sensor_axis_description_get), + &apriv); if (IS_ERR(iter)) return PTR_ERR(iter); - return ph->hops->iter_response_run(iter); + /* + * Do not cause whole protocol initialization failure when failing to + * get extended names for axes. + */ + ret = ph->hops->iter_response_run(iter); + if (ret) + dev_warn(ph->dev, + "Failed to get axes extended names for %s (ret:%d).\n", + s->name, ret); + + return 0; } static int scmi_sensor_axis_description(const struct scmi_protocol_handle *ph, @@ -481,12 +512,15 @@ static int scmi_sensor_axis_description(const struct scmi_protocol_handle *ph, { int ret; void *iter; - struct scmi_msg_sensor_axis_description_get *msg; struct scmi_iterator_ops ops = { .prepare_message = iter_axes_desc_prepare_message, .update_state = iter_axes_desc_update_state, .process_response = iter_axes_desc_process_response, }; + struct scmi_apriv apriv = { + .any_axes_support_extended_names = false, + .s = s, + }; s->axis = devm_kcalloc(ph->dev, s->num_axis, sizeof(*s->axis), GFP_KERNEL); @@ -495,7 +529,8 @@ static int scmi_sensor_axis_description(const struct scmi_protocol_handle *ph, iter = ph->hops->iter_response_init(ph, &ops, s->num_axis, SENSOR_AXIS_DESCRIPTION_GET, - sizeof(*msg), s); + sizeof(struct scmi_msg_sensor_axis_description_get), + &apriv); if (IS_ERR(iter)) return PTR_ERR(iter); @@ -503,7 +538,8 @@ static int scmi_sensor_axis_description(const struct scmi_protocol_handle *ph, if (ret) return ret; - if (PROTOCOL_REV_MAJOR(version) >= 0x3) + if (PROTOCOL_REV_MAJOR(version) >= 0x3 && + apriv.any_axes_support_extended_names) ret = scmi_sensor_axis_extended_names_get(ph, s); return ret; @@ -598,7 +634,7 @@ iter_sens_descr_process_response(const struct scmi_protocol_handle *ph, SUPPORTS_AXIS(attrh) ? SENSOR_AXIS_NUMBER(attrh) : 0, SCMI_MAX_NUM_SENSOR_AXIS); - strscpy(s->name, sdesc->name, SCMI_MAX_STR_SIZE); + strscpy(s->name, sdesc->name, SCMI_SHORT_NAME_MAX_SIZE); /* * If supported overwrite short name with the extended diff --git a/drivers/firmware/arm_scmi/voltage.c b/drivers/firmware/arm_scmi/voltage.c index 9d195d8719ab3..eaa8d944926a3 100644 --- a/drivers/firmware/arm_scmi/voltage.c +++ b/drivers/firmware/arm_scmi/voltage.c @@ -180,7 +180,6 @@ static int scmi_voltage_levels_get(const struct scmi_protocol_handle *ph, { int ret; void *iter; - struct scmi_msg_cmd_describe_levels *msg; struct scmi_iterator_ops ops = { .prepare_message = iter_volt_levels_prepare_message, .update_state = iter_volt_levels_update_state, @@ -193,7 +192,8 @@ static int scmi_voltage_levels_get(const struct scmi_protocol_handle *ph, iter = ph->hops->iter_response_init(ph, &ops, v->num_levels, VOLTAGE_DESCRIBE_LEVELS, - sizeof(*msg), &vpriv); + sizeof(struct scmi_msg_cmd_describe_levels), + &vpriv); if (IS_ERR(iter)) return PTR_ERR(iter); @@ -225,15 +225,14 @@ static int scmi_voltage_descriptors_get(const struct scmi_protocol_handle *ph, /* Retrieve domain attributes at first ... */ put_unaligned_le32(dom, td->tx.buf); - ret = ph->xops->do_xfer(ph, td); /* Skip domain on comms error */ - if (ret) + if (ph->xops->do_xfer(ph, td)) continue; v = vinfo->domains + dom; v->id = dom; attributes = le32_to_cpu(resp_dom->attr); - strlcpy(v->name, resp_dom->name, SCMI_MAX_STR_SIZE); + strscpy(v->name, resp_dom->name, SCMI_SHORT_NAME_MAX_SIZE); /* * If supported overwrite short name with the extended one; @@ -249,12 +248,8 @@ static int scmi_voltage_descriptors_get(const struct scmi_protocol_handle *ph, v->async_level_set = true; } - ret = scmi_voltage_levels_get(ph, v); /* Skip invalid voltage descriptors */ - if (ret) - continue; - - ph->xops->reset_rx_to_maxsz(ph, td); + scmi_voltage_levels_get(ph, v); } ph->xops->xfer_put(ph, td); diff --git a/drivers/firmware/efi/sysfb_efi.c b/drivers/firmware/efi/sysfb_efi.c index 4c7c9dd7733f9..7882d4b3f2be4 100644 --- a/drivers/firmware/efi/sysfb_efi.c +++ b/drivers/firmware/efi/sysfb_efi.c @@ -26,8 +26,6 @@ #include #include