Changes in sysfs-devices-system-cpu

f4818881 - x86/its: Enable Indirect Target Selection mitigation

Sat, 22 Jun 2024 03:23:23 +0000

x86/its: Enable Indirect Target Selection mitigationIndirect Target Selection (ITS) is a bug in some pre-ADL Intel CPUs witheIBRS. It affects prediction of indirect branch and RETs in thelower half of cacheline. Due to ITS such branches may get wrongly predictedto a target of (direct or indirect) branch that is located in the upperhalf of the cacheline.Scope of impact===============Guest/host isolation--------------------When eIBRS is used for guest/host isolation, the indirect branches in theVMM may still be predicted with targets corresponding to branches in theguest.Intra-mode----------cBPF or other native gadgets can be used for intra-mode training anddisclosure using ITS.User/kernel isolation---------------------When eIBRS is enabled user/kernel isolation is not impacted.Indirect Branch Prediction Barrier (IBPB)-----------------------------------------After an IBPB, indirect branches may be predicted with targetscorresponding to direct branches which were executed prior to IBPB. This ismitigated by a microcode update.Add cmdline parameter indirect_target_selection=off|on|force to control themitigation to relocate the affected branches to an ITS-safe thunk i.e.located in the upper half of cacheline. Also add the sysfs reporting.When retpoline mitigation is deployed, ITS safe-thunks are not needed,because retpoline sequence is already ITS-safe. Similarly, when call depthtracking (CDT) mitigation is deployed (retbleed=stuff), ITS safe returnthunk is not used, as CDT prevents RSB-underflow.To not overcomplicate things, ITS mitigation is not supported withspectre-v2 lfence;jmp mitigation. Moreover, it is less practical to deploylfence;jmp mitigation on ITS affected parts anyways.Signed-off-by: Pawan Gupta Signed-off-by: Dave Hansen Reviewed-by: Josh Poimboeuf Reviewed-by: Alexandre Chartre List of files: /linux-6.15/Documentation/ABI/testing/sysfs-devices-system-cpu

c91c6062 - Document/kexec: generalize crash hotplug description

Mon, 12 Aug 2024 04:16:51 +0000

Document/kexec: generalize crash hotplug descriptionCommit 79365026f869 ("crash: add a new kexec flag for hotplug support")generalizes the crash hotplug support to allow architectures to updatemultiple kexec segments on CPU/Memory hotplug and not just elfcorehdr. Therefore, update the relevant kernel documentation to reflect the same.No functional change.Link: https://lkml.kernel.org/r/20240812041651.703156-1-sourabhjain@linux.ibm.comSigned-off-by: Sourabh Jain Reviewed-by: Petr Tesarik Acked-by: Baoquan He Cc: Hari Bathini Cc: Petr Tesarik Cc: Sourabh Jain Cc: Jonathan Corbet Signed-off-by: Andrew Morton List of files: /linux-6.15/Documentation/ABI/testing/sysfs-devices-system-cpu

6c17ea1f - cpu/SMT: Enable SMT only if a core is online

Wed, 31 Jul 2024 03:01:12 +0000

cpu/SMT: Enable SMT only if a core is onlineIf a core is offline then enabling SMT should not online CPUs ofthis core. By enabling SMT, what is intended is either changing the SMTvalue from "off" to "on" or setting the SMT level (threads per core) from alower to higher value.On PowerPC the ppc64_cpu utility can be used, among other things, toperform the following functions:ppc64_cpu --cores-on # Get the number of online coresppc64_cpu --cores-on=X # Put exactly X cores onlineppc64_cpu --offline-cores=X[,Y,...] # Put specified cores offlineppc64_cpu --smt={on|off|value} # Enable, disable or change SMT levelIf the user has decided to offline certain cores, enabling SMT shouldnot online CPUs in those cores. This patch fixes the issue and changesthe behaviour as described, by introducing an arch specific functiontopology_is_core_online(). It is currently implemented only for PowerPC.Fixes: 73c58e7e1412 ("powerpc: Add HOTPLUG_SMT support")Reported-by: Tyrel Datwyler Closes: https://groups.google.com/g/powerpc-utils-devel/c/wrwVzAAnRlI/m/5KJSoqP4BAAJSigned-off-by: Nysal Jan K.A Reviewed-by: Shrikanth Hegde Reviewed-by: Thomas Gleixner Signed-off-by: Michael Ellerman Link: https://msgid.link/20240731030126.956210-2-nysal@linux.ibm.com List of files: /linux-6.15/Documentation/ABI/testing/sysfs-devices-system-cpu

4e1a7df4 - cpumask: Add enabled cpumask for present CPUs that can be brought online

Wed, 29 May 2024 13:34:46 +0000

cpumask: Add enabled cpumask for present CPUs that can be brought onlineThe 'offline' file in sysfs shows all offline CPUs, including thosethat aren't present. User-space is expected to remove not-present CPUsfrom this list to learn which CPUs could be brought online.CPUs can be present but not-enabled. These CPUs can't be brought onlineuntil the firmware policy changes, which comes with an ACPI notificationthat will register the CPUs.With only the offline and present files, user-space is unable todetermine which CPUs it can try to bring online. Add a new CPU maskthat shows this based on all the registered CPUs.Signed-off-by: James Morse Tested-by: Miguel Luis Tested-by: Vishnu Pajjuri Tested-by: Jianyong Wu Acked-by: Thomas Gleixner Signed-off-by: Russell King (Oracle) Reviewed-by: Gavin Shan Signed-off-by: Jonathan Cameron Link: https://lore.kernel.org/r/20240529133446.28446-20-Jonathan.Cameron@huawei.comSigned-off-by: Catalin Marinas List of files: /linux-6.15/Documentation/ABI/testing/sysfs-devices-system-cpu

61564d34 - x86/sev: Provide guest VMPL level to userspace

Wed, 05 Jun 2024 15:18:50 +0000

x86/sev: Provide guest VMPL level to userspaceRequesting an attestation report from userspace involves providing the VMPLlevel for the report. Currently any value from 0-3 is valid because Linuxenforces running at VMPL0.When an SVSM is present, though, Linux will not be running at VMPL0 and onlyVMPL values starting at the VMPL level Linux is running at to 3 are valid. Inorder to allow userspace to determine the minimum VMPL value that can besupplied to an attestation report, create a sysfs entry that can be used toretrieve the current VMPL level of the kernel. [ bp: Add CONFIG_SYSFS ifdeffery. ]Signed-off-by: Tom Lendacky Signed-off-by: Borislav Petkov (AMD) Link: https://lore.kernel.org/r/fff846da0d8d561f9fdaf297dcf8cd907545a25b.1717600736.git.thomas.lendacky@amd.com List of files: /linux-6.15/Documentation/ABI/testing/sysfs-devices-system-cpu

fae57306 - Documentation: Fix the address of the linuxppc-dev mailing list

Fri, 03 May 2024 02:10:12 +0000

Documentation: Fix the address of the linuxppc-dev mailing listThis list was moved many years ago.Signed-off-by: Stephen Rothwell Signed-off-by: Michael Ellerman Link: https://msgid.link/20240503121012.3ba5000b@canb.auug.org.au List of files: /linux-6.15/Documentation/ABI/testing/sysfs-devices-system-cpu

8076fcde - x86/rfds: Mitigate Register File Data Sampling (RFDS)

Mon, 11 Mar 2024 19:29:43 +0000

x86/rfds: Mitigate Register File Data Sampling (RFDS)RFDS is a CPU vulnerability that may allow userspace to infer kernelstale data previously used in floating point registers, vector registersand integer registers. RFDS only affects certain Intel Atom processors.Intel released a microcode update that uses VERW instruction to clearthe affected CPU buffers. Unlike MDS, none of the affected cores supportSMT.Add RFDS bug infrastructure and enable the VERW based mitigation bydefault, that clears the affected buffers just before exiting touserspace. Also add sysfs reporting and cmdline parameter"reg_file_data_sampling" to control the mitigation.For details see:Documentation/admin-guide/hw-vuln/reg-file-data-sampling.rstSigned-off-by: Pawan Gupta Signed-off-by: Dave Hansen Reviewed-by: Thomas Gleixner Acked-by: Josh Poimboeuf List of files: /linux-6.15/Documentation/ABI/testing/sysfs-devices-system-cpu

94483490 - Documentation: Drop or replace remaining mentions of IA64

Fri, 13 Jan 2023 17:32:57 +0000

Documentation: Drop or replace remaining mentions of IA64Drop or update mentions of IA64, as appropriate.Signed-off-by: Ard Biesheuvel List of files: /linux-6.15/Documentation/ABI/testing/sysfs-devices-system-cpu

88a6f899 - crash: memory and CPU hotplug sysfs attributes

Mon, 14 Aug 2023 21:44:42 +0000

crash: memory and CPU hotplug sysfs attributesIntroduce the crash_hotplug attribute for memory and CPUs for use byuserspace. These attributes directly facilitate the udev rule formanaging userspace re-loading of the crash kernel upon hot un/plugchanges.For memory, expose the crash_hotplug attribute to the/sys/devices/system/memory directory. For example: # udevadm info --attribute-walk /sys/devices/system/memory/memory81 looking at device '/devices/system/memory/memory81': KERNEL=="memory81" SUBSYSTEM=="memory" DRIVER=="" ATTR{online}=="1" ATTR{phys_device}=="0" ATTR{phys_index}=="00000051" ATTR{removable}=="1" ATTR{state}=="online" ATTR{valid_zones}=="Movable" looking at parent device '/devices/system/memory': KERNELS=="memory" SUBSYSTEMS=="" DRIVERS=="" ATTRS{auto_online_blocks}=="offline" ATTRS{block_size_bytes}=="8000000" ATTRS{crash_hotplug}=="1"For CPUs, expose the crash_hotplug attribute to the/sys/devices/system/cpu directory. For example: # udevadm info --attribute-walk /sys/devices/system/cpu/cpu0 looking at device '/devices/system/cpu/cpu0': KERNEL=="cpu0" SUBSYSTEM=="cpu" DRIVER=="processor" ATTR{crash_notes}=="277c38600" ATTR{crash_notes_size}=="368" ATTR{online}=="1" looking at parent device '/devices/system/cpu': KERNELS=="cpu" SUBSYSTEMS=="" DRIVERS=="" ATTRS{crash_hotplug}=="1" ATTRS{isolated}=="" ATTRS{kernel_max}=="8191" ATTRS{nohz_full}==" (null)" ATTRS{offline}=="4-7" ATTRS{online}=="0-3" ATTRS{possible}=="0-7" ATTRS{present}=="0-3"With these sysfs attributes in place, it is possible to efficientlyinstruct the udev rule to skip crash kernel reloading for kernelsconfigured with crash hotplug support.For example, the following is the proposed udev rule change for RHELsystem 98-kexec.rules (as the first lines of the rule file): # The kernel updates the crash elfcorehdr for CPU and memory changes SUBSYSTEM=="cpu", ATTRS{crash_hotplug}=="1", GOTO="kdump_reload_end" SUBSYSTEM=="memory", ATTRS{crash_hotplug}=="1", GOTO="kdump_reload_end"When examined in the context of 98-kexec.rules, the above rules test ifcrash_hotplug is set, and if so, the userspace initiatedunload-then-reload of the crash kernel is skipped.CPU and memory checks are separated in accordance with CONFIG_HOTPLUG_CPUand CONFIG_MEMORY_HOTPLUG kernel config options. If an architecturesupports, for example, memory hotplug but not CPU hotplug, then the/sys/devices/system/memory/crash_hotplug attribute file is present, butthe /sys/devices/system/cpu/crash_hotplug attribute file will NOT bepresent. Thus the udev rule skips userspace processing of memory hotun/plug events, but the udev rule will evaluate false for CPU events, thusallowing userspace to process CPU hot un/plug events (ie theunload-then-reload of the kdump capture kernel).Link: https://lkml.kernel.org/r/20230814214446.6659-5-eric.devolder@oracle.comSigned-off-by: Eric DeVolder Reviewed-by: Sourabh Jain Acked-by: Hari Bathini Acked-by: Baoquan He Cc: Akhil Raj Cc: Bjorn Helgaas Cc: Borislav Petkov (AMD) Cc: Boris Ostrovsky Cc: Dave Hansen Cc: Dave Young Cc: David Hildenbrand Cc: Eric W. Biederman Cc: Greg Kroah-Hartman Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Jonathan Corbet Cc: Konrad Rzeszutek Wilk Cc: Mimi Zohar Cc: Naveen N. Rao Cc: Oscar Salvador Cc: "Rafael J. Wysocki" Cc: Sean Christopherson Cc: Takashi Iwai Cc: Thomas Gleixner Cc: Thomas Weißschuh Cc: Valentin Schneider Cc: Vivek Goyal Cc: Vlastimil Babka Signed-off-by: Andrew Morton List of files: /linux-6.15/Documentation/ABI/testing/sysfs-devices-system-cpu

7f48405c - cpu/SMT: Allow enabling partial SMT states via sysfs

Wed, 05 Jul 2023 14:51:40 +0000

cpu/SMT: Allow enabling partial SMT states via sysfsAdd support to the /sys/devices/system/cpu/smt/control interface forenabling a specified number of SMT threads per core, including partialSMT states where not all threads are brought online.The current interface accepts "on" and "off", to enable either 1 or allSMT threads per core.This commit allows writing an integer, between 1 and the number of SMTthreads supported by the machine. Writing 1 is a synonym for "off", 2 ormore enables SMT with the specified number of threads.When reading the file, if all threads are online "on" is returned, toavoid changing behaviour for existing users. If some other number ofthreads is online then the integer value is returned.Architectures like x86 only supporting 1 thread or all threads, should notdefine CONFIG_SMT_NUM_THREADS_DYNAMIC. Architecture supporting partial SMTstates, like PowerPC, should define it.[ ldufour: Slightly reword the commit's description ][ ldufour: Remove switch() in __store_smt_control() ][ ldufour: Rix build issue in control_show() ]Reported-by: kernel test robot Signed-off-by: Michael Ellerman Signed-off-by: Laurent Dufour Signed-off-by: Thomas Gleixner Tested-by: Zhang Rui Link: https://lore.kernel.org/r/20230705145143.40545-8-ldufour@linux.ibm.com List of files: /linux-6.15/Documentation/ABI/testing/sysfs-devices-system-cpu

8974eb58 - x86/speculation: Add Gather Data Sampling mitigation

Thu, 13 Jul 2023 02:43:11 +0000

x86/speculation: Add Gather Data Sampling mitigationGather Data Sampling (GDS) is a hardware vulnerability which allowsunprivileged speculative access to data which was previously stored invector registers.Intel processors that support AVX2 and AVX512 have gather instructionsthat fetch non-contiguous data elements from memory. On vulnerablehardware, when a gather instruction is transiently executed andencounters a fault, stale data from architectural or internal vectorregisters may get transiently stored to the destination vectorregister allowing an attacker to infer the stale data using typicalside channel techniques like cache timing attacks.This mitigation is different from many earlier ones for two reasons.First, it is enabled by default and a bit must be set to *DISABLE* it.This is the opposite of normal mitigation polarity. This means GDS canbe mitigated simply by updating microcode and leaving the new controlbit alone.Second, GDS has a "lock" bit. This lock bit is there because themitigation affects the hardware security features KeyLocker and SGX.It needs to be enabled and *STAY* enabled for these features to bemitigated against GDS.The mitigation is enabled in the microcode by default. Disable it bysetting gather_data_sampling=off or by disabling all mitigations withmitigations=off. The mitigation status can be checked by reading: /sys/devices/system/cpu/vulnerabilities/gather_data_samplingSigned-off-by: Daniel Sneddon Signed-off-by: Dave Hansen Acked-by: Josh Poimboeuf List of files: /linux-6.15/Documentation/ABI/testing/sysfs-devices-system-cpu

e4624435 - docs: arm64: Move arm64 documentation under Documentation/arch/

Mon, 12 Jun 2023 12:06:39 +0000

docs: arm64: Move arm64 documentation under Documentation/arch/Architecture-specific documentation is being moved into Documentation/arch/as a way of cleaning up the top-level documentation directory and makingthe docs hierarchy more closely match the source hierarchy. MoveDocumentation/arm64 into arch/ (along with the Chinese equvalenttranslations) and fix up documentation references.Cc: Will Deacon Cc: Alex Shi Cc: Hu Haowen Cc: Paolo Bonzini Acked-by: Catalin Marinas Reviewed-by: Yantengsi Signed-off-by: Jonathan Corbet List of files: /linux-6.15/Documentation/ABI/testing/sysfs-devices-system-cpu

8a7f0e8a - Documentation/ABI: correct possessive "its" typos

Mon, 01 Aug 2022 02:52:07 +0000

Documentation/ABI: correct possessive "its" typosCorrect all uses of "it's" that are meant to be possessive "its".Signed-off-by: Randy Dunlap Cc: Jonathan Corbet Cc: Greg Kroah-Hartman Link: https://lore.kernel.org/r/20220801025207.29971-1-rdunlap@infradead.orgSigned-off-by: Jonathan Corbet List of files: /linux-6.15/Documentation/ABI/testing/sysfs-devices-system-cpu

00da0cb3 - Documentation/ABI: Mention retbleed vulnerability info file for sysfs

Mon, 01 Aug 2022 09:15:30 +0000

Documentation/ABI: Mention retbleed vulnerability info file for sysfsWhile reporting for the AMD retbleed vulnerability was added in 6b80b59b3555 ("x86/bugs: Report AMD retbleed vulnerability")the new sysfs file was not mentioned so far in the ABI documentation forsysfs-devices-system-cpu. Fix that.Fixes: 6b80b59b3555 ("x86/bugs: Report AMD retbleed vulnerability")Signed-off-by: Salvatore Bonaccorso Signed-off-by: Borislav Petkov Link: https://lore.kernel.org/r/20220801091529.325327-1-carnil@debian.org List of files: /linux-6.15/Documentation/ABI/testing/sysfs-devices-system-cpu

1d248d23 - ABI: testing/sysfs-devices-system-cpu: remove duplicated core_id

Sun, 26 Jun 2022 09:32:21 +0000

ABI: testing/sysfs-devices-system-cpu: remove duplicated core_idThis was already defined at stable/sysfs-devices-system-cpu withthe same description, as pointed by get_abi.pl: Warning: /sys/devices/system/cpu/cpuX/topology/core_id is defined 2 times: Documentation/ABI/stable/sysfs-devices-system-cpu:38 Documentation/ABI/testing/sysfs-devices-system-cpu:69Remove the duplicated one.Signed-off-by: Mauro Carvalho Chehab Link: https://lore.kernel.org/r/1e92337c1ef74f5eb9e1c1871e20b858b490d269.1656235926.git.mchehab@kernel.orgSigned-off-by: Greg Kroah-Hartman List of files: /linux-6.15/Documentation/ABI/testing/sysfs-devices-system-cpu

d69d5649 - arm64/sme: Expose SMIDR through sysfs

Tue, 07 Jun 2022 13:28:57 +0000

arm64/sme: Expose SMIDR through sysfsWe currently expose MIDR and REVID to userspace through sysfs to enable itto make decisions based on the specific implementation. Since SME supportsimplementations where streaming mode is provided by a separate hardwareunit called a SMCU it provides a similar ID register SMIDR. Expose it touserspace via sysfs when the system supports SME along with the other IDregisters.Since we disable the SME priority mapping feature if it is supported byhardware we currently mask out the SMPS bit which reports that it issupported.Signed-off-by: Mark Brown Link: https://lore.kernel.org/r/20220607132857.1358361-1-broonie@kernel.orgSigned-off-by: Will Deacon List of files: /linux-6.15/Documentation/ABI/testing/sysfs-devices-system-cpu

8d50cdf8 - x86/speculation/mmio: Add sysfs reporting for Processor MMIO Stale Data

Fri, 20 May 2022 03:32:13 +0000

x86/speculation/mmio: Add sysfs reporting for Processor MMIO Stale DataAdd the sysfs reporting file for Processor MMIO Stale Datavulnerability. It exposes the vulnerability and mitigation state similarto the existing files for the other hardware vulnerabilities.Signed-off-by: Pawan Gupta Signed-off-by: Borislav Petkov List of files: /linux-6.15/Documentation/ABI/testing/sysfs-devices-system-cpu

9986c765 - docs: sysfs-devices-system-cpu: document "asymm" value for mte_tcf_preferred

Wed, 09 Mar 2022 21:59:43 +0000

docs: sysfs-devices-system-cpu: document "asymm" value for mte_tcf_preferredIt was added in commit 766121ba5de3 ("arm64/mte: Add userspace interfacefor enabling asymmetric mode").Signed-off-by: Evgenii Stepanov Reviewed-by: Mark Brown Link: https://lore.kernel.org/r/20220309215943.87831-1-eugenis@google.comSigned-off-by: Will Deacon List of files: /linux-6.15/Documentation/ABI/testing/sysfs-devices-system-cpu

ab28e944 - topology/sysfs: Add PPIN in sysfs under cpu topology

Mon, 31 Jan 2022 23:01:11 +0000

topology/sysfs: Add PPIN in sysfs under cpu topologyPPIN is the Protected Processor Identification Number.This is used to identify the socket as a Field Replaceable Unit (FRU).Existing code only displays this when reporting errors. But this makesit inconvenient for large clusters to use it for its intended purposeof inventory control.Add ppin to /sys/devices/system/cpu/cpu*/topology to make whatis already available using RDMSR more easily accessible. Makethe file read only for root in case there are still peopleconcerned about making a unique system "serial number" available.Signed-off-by: Tony Luck Signed-off-by: Borislav Petkov Acked-by: Greg Kroah-Hartman Link: https://lore.kernel.org/r/20220131230111.2004669-6-tony.luck@intel.com List of files: /linux-6.15/Documentation/ABI/testing/sysfs-devices-system-cpu

02bf6074 - docs: document the sysfs ABI for "isolated"

Wed, 01 Dec 2021 11:59:57 +0000

docs: document the sysfs ABI for "isolated"Add missing documentation of sysfs ABI for "isolated". It was added bycommit 59f30abe94bf("show isolated cpus in sysfs"). However, there isno documentation for these interface.Signed-off-by: Kohei Tarumizu Link: https://lore.kernel.org/r/20211201115957.254224-3-tarumizu.kohei@fujitsu.comSigned-off-by: Greg Kroah-Hartman List of files: /linux-6.15/Documentation/ABI/testing/sysfs-devices-system-cpu