716 lines · plain
1What: /sys/devices/system/cpu/2Date: pre-git history3Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org>4Description:5 A collection of both global and individual CPU attributes6 7 Individual CPU attributes are contained in subdirectories8 named by the kernel's logical CPU number, e.g.:9 10 /sys/devices/system/cpu/cpuX/11 12What: /sys/devices/system/cpu/kernel_max13 /sys/devices/system/cpu/offline14 /sys/devices/system/cpu/online15 /sys/devices/system/cpu/possible16 /sys/devices/system/cpu/present17Date: December 200818Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org>19Description: CPU topology files that describe kernel limits related to20 hotplug. Briefly:21 22 kernel_max: the maximum cpu index allowed by the kernel23 configuration.24 25 offline: cpus that are not online because they have been26 HOTPLUGGED off or exceed the limit of cpus allowed by the27 kernel configuration (kernel_max above).28 29 online: cpus that are online and being scheduled.30 31 possible: cpus that have been allocated resources and can be32 brought online if they are present.33 34 present: cpus that have been identified as being present in35 the system.36 37 See Documentation/admin-guide/cputopology.rst for more information.38 39 40What: /sys/devices/system/cpu/probe41 /sys/devices/system/cpu/release42Date: November 200943Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org>44Description: Dynamic addition and removal of CPU's. This is not hotplug45 removal, this is meant complete removal/addition of the CPU46 from the system.47 48 probe: writes to this file will dynamically add a CPU to the49 system. Information written to the file to add CPU's is50 architecture specific.51 52 release: writes to this file dynamically remove a CPU from53 the system. Information written to the file to remove CPU's54 is architecture specific.55 56What: /sys/devices/system/cpu/cpuX/node57Date: October 200958Contact: Linux memory management mailing list <linux-mm@kvack.org>59Description: Discover NUMA node a CPU belongs to60 61 When CONFIG_NUMA is enabled, a symbolic link that points62 to the corresponding NUMA node directory.63 64 For example, the following symlink is created for cpu4265 in NUMA node 2:66 67 /sys/devices/system/cpu/cpu42/node2 -> ../../node/node268 69 70What: /sys/devices/system/cpu/cpuX/topology/core_siblings71 /sys/devices/system/cpu/cpuX/topology/core_siblings_list72 /sys/devices/system/cpu/cpuX/topology/physical_package_id73 /sys/devices/system/cpu/cpuX/topology/thread_siblings74 /sys/devices/system/cpu/cpuX/topology/thread_siblings_list75 /sys/devices/system/cpu/cpuX/topology/ppin76Date: December 200877Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org>78Description: CPU topology files that describe a logical CPU's relationship79 to other cores and threads in the same physical package.80 81 One cpuX directory is created per logical CPU in the system,82 e.g. /sys/devices/system/cpu/cpu42/.83 84 Briefly, the files above are:85 86 core_siblings: internal kernel map of cpuX's hardware threads87 within the same physical_package_id.88 89 core_siblings_list: human-readable list of the logical CPU90 numbers within the same physical_package_id as cpuX.91 92 physical_package_id: physical package id of cpuX. Typically93 corresponds to a physical socket number, but the actual value94 is architecture and platform dependent.95 96 thread_siblings: internal kernel map of cpuX's hardware97 threads within the same core as cpuX98 99 thread_siblings_list: human-readable list of cpuX's hardware100 threads within the same core as cpuX101 102 ppin: human-readable Protected Processor Identification103 Number of the socket the cpu# belongs to. There should be104 one per physical_package_id. File is readable only to105 admin.106 107 See Documentation/admin-guide/cputopology.rst for more information.108 109 110What: /sys/devices/system/cpu/cpuidle/available_governors111 /sys/devices/system/cpu/cpuidle/current_driver112 /sys/devices/system/cpu/cpuidle/current_governor113 /sys/devices/system/cpu/cpuidle/current_governer_ro114Date: September 2007115Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org>116Description: Discover cpuidle policy and mechanism117 118 Various CPUs today support multiple idle levels that are119 differentiated by varying exit latencies and power120 consumption during idle.121 122 Idle policy (governor) is differentiated from idle mechanism123 (driver).124 125 available_governors: (RO) displays a space separated list of126 available governors.127 128 current_driver: (RO) displays current idle mechanism.129 130 current_governor: (RW) displays current idle policy. Users can131 switch the governor at runtime by writing to this file.132 133 current_governor_ro: (RO) displays current idle policy.134 135 See Documentation/admin-guide/pm/cpuidle.rst and136 Documentation/driver-api/pm/cpuidle.rst for more information.137 138 139What: /sys/devices/system/cpu/cpuX/cpuidle/state<N>/name140 /sys/devices/system/cpu/cpuX/cpuidle/stateN/latency141 /sys/devices/system/cpu/cpuX/cpuidle/stateN/power142 /sys/devices/system/cpu/cpuX/cpuidle/stateN/time143 /sys/devices/system/cpu/cpuX/cpuidle/stateN/usage144 /sys/devices/system/cpu/cpuX/cpuidle/stateN/above145 /sys/devices/system/cpu/cpuX/cpuidle/stateN/below146Date: September 2007147KernelVersion: v2.6.24148Contact: Linux power management list <linux-pm@vger.kernel.org>149Description:150 The directory /sys/devices/system/cpu/cpuX/cpuidle contains per151 logical CPU specific cpuidle information for each online cpu X.152 The processor idle states which are available for use have the153 following attributes:154 155 ======== ==== =================================================156 name: (RO) Name of the idle state (string).157 158 latency: (RO) The latency to exit out of this idle state (in159 microseconds).160 161 power: (RO) The power consumed while in this idle state (in162 milliwatts).163 164 time: (RO) The total time spent in this idle state165 (in microseconds).166 167 usage: (RO) Number of times this state was entered (a count).168 169 above: (RO) Number of times this state was entered, but the170 observed CPU idle duration was too short for it171 (a count).172 173 below: (RO) Number of times this state was entered, but the174 observed CPU idle duration was too long for it175 (a count).176 ======== ==== =================================================177 178What: /sys/devices/system/cpu/cpuX/cpuidle/state<N>/desc179Date: February 2008180KernelVersion: v2.6.25181Contact: Linux power management list <linux-pm@vger.kernel.org>182Description:183 (RO) A small description about the idle state (string).184 185 186What: /sys/devices/system/cpu/cpuX/cpuidle/state<N>/disable187Date: March 2012188KernelVersion: v3.10189Contact: Linux power management list <linux-pm@vger.kernel.org>190Description:191 (RW) Option to disable this idle state (bool). The behavior and192 the effect of the disable variable depends on the implementation193 of a particular governor. In the ladder governor, for example,194 it is not coherent, i.e. if one is disabling a light state, then195 all deeper states are disabled as well, but the disable variable196 does not reflect it. Likewise, if one enables a deep state but a197 lighter state still is disabled, then this has no effect.198 199What: /sys/devices/system/cpu/cpuX/cpuidle/state<N>/default_status200Date: December 2019201KernelVersion: v5.6202Contact: Linux power management list <linux-pm@vger.kernel.org>203Description:204 (RO) The default status of this state, "enabled" or "disabled".205 206What: /sys/devices/system/cpu/cpuX/cpuidle/state<N>/residency207Date: March 2014208KernelVersion: v3.15209Contact: Linux power management list <linux-pm@vger.kernel.org>210Description:211 (RO) Display the target residency i.e. the minimum amount of212 time (in microseconds) this cpu should spend in this idle state213 to make the transition worth the effort.214 215What: /sys/devices/system/cpu/cpuX/cpuidle/state<N>/s2idle/216Date: March 2018217KernelVersion: v4.17218Contact: Linux power management list <linux-pm@vger.kernel.org>219Description:220 Idle state usage statistics related to suspend-to-idle.221 222 This attribute group is only present for states that can be223 used in suspend-to-idle with suspended timekeeping.224 225What: /sys/devices/system/cpu/cpuX/cpuidle/state<N>/s2idle/time226Date: March 2018227KernelVersion: v4.17228Contact: Linux power management list <linux-pm@vger.kernel.org>229Description:230 Total time spent by the CPU in suspend-to-idle (with scheduler231 tick suspended) after requesting this state.232 233What: /sys/devices/system/cpu/cpuX/cpuidle/state<N>/s2idle/usage234Date: March 2018235KernelVersion: v4.17236Contact: Linux power management list <linux-pm@vger.kernel.org>237Description:238 Total number of times this state has been requested by the CPU239 while entering suspend-to-idle.240 241What: /sys/devices/system/cpu/cpuX/cpufreq/*242Date: pre-git history243Contact: linux-pm@vger.kernel.org244Description: Discover and change clock speed of CPUs245 246 Clock scaling allows you to change the clock speed of the247 CPUs on the fly. This is a nice method to save battery248 power, because the lower the clock speed, the less power249 the CPU consumes.250 251 There are many knobs to tweak in this directory.252 253 See files in Documentation/cpu-freq/ for more information.254 255 256What: /sys/devices/system/cpu/cpuX/cpufreq/freqdomain_cpus257Date: June 2013258Contact: linux-pm@vger.kernel.org259Description: Discover CPUs in the same CPU frequency coordination domain260 261 freqdomain_cpus is the list of CPUs (online+offline) that share262 the same clock/freq domain (possibly at the hardware level).263 That information may be hidden from the cpufreq core and the264 value of related_cpus may be different from freqdomain_cpus. This265 attribute is useful for user space DVFS controllers to get better266 power/performance results for platforms using acpi-cpufreq.267 268 This file is only present if the acpi-cpufreq or the cppc-cpufreq269 drivers are in use.270 271 272What: /sys/devices/system/cpu/cpu*/cache/index3/cache_disable_{0,1}273Date: August 2008274KernelVersion: 2.6.27275Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org>276Description: Disable L3 cache indices277 278 These files exist in every CPU's cache/index3 directory. Each279 cache_disable_{0,1} file corresponds to one disable slot which280 can be used to disable a cache index. Reading from these files281 on a processor with this functionality will return the currently282 disabled index for that node. There is one L3 structure per283 node, or per internal node on MCM machines. Writing a valid284 index to one of these files will cause the specified cache285 index to be disabled.286 287 All AMD processors with L3 caches provide this functionality.288 For details, see BKDGs at289 https://www.amd.com/en/support/tech-docs?keyword=bios+kernel290 291 292What: /sys/devices/system/cpu/cpufreq/boost293Date: August 2012294Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org>295Description: Processor frequency boosting control296 297 This switch controls the boost setting for the whole system.298 Boosting allows the CPU and the firmware to run at a frequency299 beyond its nominal limit.300 301 More details can be found in302 Documentation/admin-guide/pm/cpufreq.rst303 304 305What: /sys/devices/system/cpu/cpuX/crash_notes306 /sys/devices/system/cpu/cpuX/crash_notes_size307Date: April 2013308Contact: kexec@lists.infradead.org309Description: address and size of the percpu note.310 311 crash_notes: the physical address of the memory that holds the312 note of cpuX.313 314 crash_notes_size: size of the note of cpuX.315 316 317What: /sys/devices/system/cpu/intel_pstate/max_perf_pct318 /sys/devices/system/cpu/intel_pstate/min_perf_pct319 /sys/devices/system/cpu/intel_pstate/no_turbo320Date: February 2013321Contact: linux-pm@vger.kernel.org322Description: Parameters for the Intel P-state driver323 324 Logic for selecting the current P-state in Intel325 Sandybridge+ processors. The three knobs control326 limits for the P-state that will be requested by the327 driver.328 329 max_perf_pct: limits the maximum P state that will be requested by330 the driver stated as a percentage of the available performance.331 332 min_perf_pct: limits the minimum P state that will be requested by333 the driver stated as a percentage of the available performance.334 335 no_turbo: limits the driver to selecting P states below the turbo336 frequency range.337 338 More details can be found in339 Documentation/admin-guide/pm/intel_pstate.rst340 341What: /sys/devices/system/cpu/cpu*/cache/index*/<set_of_attributes_mentioned_below>342Date: July 2014(documented, existed before August 2008)343Contact: Sudeep Holla <sudeep.holla@arm.com>344 Linux kernel mailing list <linux-kernel@vger.kernel.org>345Description: Parameters for the CPU cache attributes346 347 allocation_policy:348 - WriteAllocate:349 allocate a memory location to a cache line350 on a cache miss because of a write351 - ReadAllocate:352 allocate a memory location to a cache line353 on a cache miss because of a read354 - ReadWriteAllocate:355 both writeallocate and readallocate356 357 coherency_line_size:358 the minimum amount of data in bytes that gets359 transferred from memory to cache360 361 level:362 the cache hierarchy in the multi-level cache configuration363 364 number_of_sets:365 total number of sets in the cache, a set is a366 collection of cache lines with the same cache index367 368 physical_line_partition:369 number of physical cache line per cache tag370 371 shared_cpu_list:372 the list of logical cpus sharing the cache373 374 shared_cpu_map:375 logical cpu mask containing the list of cpus sharing376 the cache377 378 size:379 the total cache size in kB380 381 type:382 - Instruction: cache that only holds instructions383 - Data: cache that only caches data384 - Unified: cache that holds both data and instructions385 386 ways_of_associativity:387 degree of freedom in placing a particular block388 of memory in the cache389 390 write_policy:391 - WriteThrough:392 data is written to both the cache line393 and to the block in the lower-level memory394 - WriteBack:395 data is written only to the cache line and396 the modified cache line is written to main397 memory only when it is replaced398 399 400What: /sys/devices/system/cpu/cpu*/cache/index*/id401Date: September 2016402Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org>403Description: Cache id404 405 The id provides a unique number for a specific instance of406 a cache of a particular type. E.g. there may be a level407 3 unified cache on each socket in a server and we may408 assign them ids 0, 1, 2, ...409 410 Note that id value can be non-contiguous. E.g. level 1411 caches typically exist per core, but there may not be a412 power of two cores on a socket, so these caches may be413 numbered 0, 1, 2, 3, 4, 5, 8, 9, 10, ...414 415What: /sys/devices/system/cpu/cpuX/cpufreq/throttle_stats416 /sys/devices/system/cpu/cpuX/cpufreq/throttle_stats/turbo_stat417 /sys/devices/system/cpu/cpuX/cpufreq/throttle_stats/sub_turbo_stat418 /sys/devices/system/cpu/cpuX/cpufreq/throttle_stats/unthrottle419 /sys/devices/system/cpu/cpuX/cpufreq/throttle_stats/powercap420 /sys/devices/system/cpu/cpuX/cpufreq/throttle_stats/overtemp421 /sys/devices/system/cpu/cpuX/cpufreq/throttle_stats/supply_fault422 /sys/devices/system/cpu/cpuX/cpufreq/throttle_stats/overcurrent423 /sys/devices/system/cpu/cpuX/cpufreq/throttle_stats/occ_reset424Date: March 2016425Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org>426 Linux for PowerPC mailing list <linuxppc-dev@lists.ozlabs.org>427Description: POWERNV CPUFreq driver's frequency throttle stats directory and428 attributes429 430 'cpuX/cpufreq/throttle_stats' directory contains the CPU frequency431 throttle stat attributes for the chip. The throttle stats of a cpu432 is common across all the cpus belonging to a chip. Below are the433 throttle attributes exported in the 'throttle_stats' directory:434 435 - turbo_stat : This file gives the total number of times the max436 frequency is throttled to lower frequency in turbo (at and above437 nominal frequency) range of frequencies.438 439 - sub_turbo_stat : This file gives the total number of times the440 max frequency is throttled to lower frequency in sub-turbo(below441 nominal frequency) range of frequencies.442 443 - unthrottle : This file gives the total number of times the max444 frequency is unthrottled after being throttled.445 446 - powercap : This file gives the total number of times the max447 frequency is throttled due to 'Power Capping'.448 449 - overtemp : This file gives the total number of times the max450 frequency is throttled due to 'CPU Over Temperature'.451 452 - supply_fault : This file gives the total number of times the453 max frequency is throttled due to 'Power Supply Failure'.454 455 - overcurrent : This file gives the total number of times the456 max frequency is throttled due to 'Overcurrent'.457 458 - occ_reset : This file gives the total number of times the max459 frequency is throttled due to 'OCC Reset'.460 461 The sysfs attributes representing different throttle reasons like462 powercap, overtemp, supply_fault, overcurrent and occ_reset map to463 the reasons provided by OCC firmware for throttling the frequency.464 465What: /sys/devices/system/cpu/cpufreq/policyX/throttle_stats466 /sys/devices/system/cpu/cpufreq/policyX/throttle_stats/turbo_stat467 /sys/devices/system/cpu/cpufreq/policyX/throttle_stats/sub_turbo_stat468 /sys/devices/system/cpu/cpufreq/policyX/throttle_stats/unthrottle469 /sys/devices/system/cpu/cpufreq/policyX/throttle_stats/powercap470 /sys/devices/system/cpu/cpufreq/policyX/throttle_stats/overtemp471 /sys/devices/system/cpu/cpufreq/policyX/throttle_stats/supply_fault472 /sys/devices/system/cpu/cpufreq/policyX/throttle_stats/overcurrent473 /sys/devices/system/cpu/cpufreq/policyX/throttle_stats/occ_reset474Date: March 2016475Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org>476 Linux for PowerPC mailing list <linuxppc-dev@lists.ozlabs.org>477Description: POWERNV CPUFreq driver's frequency throttle stats directory and478 attributes479 480 'policyX/throttle_stats' directory and all the attributes are same as481 the /sys/devices/system/cpu/cpuX/cpufreq/throttle_stats directory and482 attributes which give the frequency throttle information of the chip.483 484What: /sys/devices/system/cpu/cpuX/regs/485 /sys/devices/system/cpu/cpuX/regs/identification/486 /sys/devices/system/cpu/cpuX/regs/identification/midr_el1487 /sys/devices/system/cpu/cpuX/regs/identification/revidr_el1488 /sys/devices/system/cpu/cpuX/regs/identification/smidr_el1489Date: June 2016490Contact: Linux ARM Kernel Mailing list <linux-arm-kernel@lists.infradead.org>491Description: AArch64 CPU registers492 493 'identification' directory exposes the CPU ID registers for494 identifying model and revision of the CPU and SMCU.495 496What: /sys/devices/system/cpu/aarch32_el0497Date: May 2021498Contact: Linux ARM Kernel Mailing list <linux-arm-kernel@lists.infradead.org>499Description: Identifies the subset of CPUs in the system that can execute500 AArch32 (32-bit ARM) applications. If present, the same format as501 /sys/devices/system/cpu/{offline,online,possible,present} is used.502 If absent, then all or none of the CPUs can execute AArch32503 applications and execve() will behave accordingly.504 505What: /sys/devices/system/cpu/cpuX/cpu_capacity506Date: December 2016507Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org>508Description: information about CPUs heterogeneity.509 510 cpu_capacity: capacity of cpuX.511 512What: /sys/devices/system/cpu/vulnerabilities513 /sys/devices/system/cpu/vulnerabilities/gather_data_sampling514 /sys/devices/system/cpu/vulnerabilities/itlb_multihit515 /sys/devices/system/cpu/vulnerabilities/l1tf516 /sys/devices/system/cpu/vulnerabilities/mds517 /sys/devices/system/cpu/vulnerabilities/meltdown518 /sys/devices/system/cpu/vulnerabilities/mmio_stale_data519 /sys/devices/system/cpu/vulnerabilities/reg_file_data_sampling520 /sys/devices/system/cpu/vulnerabilities/retbleed521 /sys/devices/system/cpu/vulnerabilities/spec_store_bypass522 /sys/devices/system/cpu/vulnerabilities/spectre_v1523 /sys/devices/system/cpu/vulnerabilities/spectre_v2524 /sys/devices/system/cpu/vulnerabilities/srbds525 /sys/devices/system/cpu/vulnerabilities/tsx_async_abort526Date: January 2018527Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org>528Description: Information about CPU vulnerabilities529 530 The files are named after the code names of CPU531 vulnerabilities. The output of those files reflects the532 state of the CPUs in the system. Possible output values:533 534 ================ ==============================================535 "Not affected" CPU is not affected by the vulnerability536 "Vulnerable" CPU is affected and no mitigation in effect537 "Mitigation: $M" CPU is affected and mitigation $M is in effect538 ================ ==============================================539 540 See also: Documentation/admin-guide/hw-vuln/index.rst541 542What: /sys/devices/system/cpu/smt543 /sys/devices/system/cpu/smt/active544 /sys/devices/system/cpu/smt/control545Date: June 2018546Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org>547Description: Control Symmetric Multi Threading (SMT)548 549 active: Tells whether SMT is active (enabled and siblings online)550 551 control: Read/write interface to control SMT. Possible552 values:553 554 ================ =========================================555 "on" SMT is enabled556 "off" SMT is disabled557 "<N>" SMT is enabled with N threads per core.558 "forceoff" SMT is force disabled. Cannot be changed.559 "notsupported" SMT is not supported by the CPU560 "notimplemented" SMT runtime toggling is not561 implemented for the architecture562 ================ =========================================563 564 If control status is "forceoff" or "notsupported" writes565 are rejected. Note that enabling SMT on PowerPC skips566 offline cores.567 568What: /sys/devices/system/cpu/cpuX/power/energy_perf_bias569Date: March 2019570Contact: linux-pm@vger.kernel.org571Description: Intel Energy and Performance Bias Hint (EPB)572 573 EPB for the given CPU in a sliding scale 0 - 15, where a value574 of 0 corresponds to a hint preference for highest performance575 and a value of 15 corresponds to the maximum energy savings.576 577 In order to change the EPB value for the CPU, write either578 a number in the 0 - 15 sliding scale above, or one of the579 strings: "performance", "balance-performance", "normal",580 "balance-power", "power" (that represent values reflected by581 their meaning), to this attribute.582 583 This attribute is present for all online CPUs supporting the584 Intel EPB feature.585 586What: /sys/devices/system/cpu/umwait_control587 /sys/devices/system/cpu/umwait_control/enable_c02588 /sys/devices/system/cpu/umwait_control/max_time589Date: May 2019590Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org>591Description: Umwait control592 593 enable_c02: Read/write interface to control umwait C0.2 state594 Read returns C0.2 state status:595 0: C0.2 is disabled596 1: C0.2 is enabled597 598 Write 'y' or '1' or 'on' to enable C0.2 state.599 Write 'n' or '0' or 'off' to disable C0.2 state.600 601 The interface is case insensitive.602 603 max_time: Read/write interface to control umwait maximum time604 in TSC-quanta that the CPU can reside in either C0.1605 or C0.2 state. The time is an unsigned 32-bit number.606 Note that a value of zero means there is no limit.607 Low order two bits must be zero.608 609What: /sys/devices/system/cpu/sev610 /sys/devices/system/cpu/sev/vmpl611Date: May 2024612Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org>613Description: Secure Encrypted Virtualization (SEV) information614 615 This directory is only present when running as an SEV-SNP guest.616 617 vmpl: Reports the Virtual Machine Privilege Level (VMPL) at which618 the SEV-SNP guest is running.619 620 621What: /sys/devices/system/cpu/svm622Date: August 2019623Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org>624 Linux for PowerPC mailing list <linuxppc-dev@lists.ozlabs.org>625Description: Secure Virtual Machine626 627 If 1, it means the system is using the Protected Execution628 Facility in POWER9 and newer processors. i.e., it is a Secure629 Virtual Machine.630 631What: /sys/devices/system/cpu/cpuX/purr632Date: Apr 2005633Contact: Linux for PowerPC mailing list <linuxppc-dev@lists.ozlabs.org>634Description: PURR ticks for this CPU since the system boot.635 636 The Processor Utilization Resources Register (PURR) is637 a 64-bit counter which provides an estimate of the638 resources used by the CPU thread. The contents of this639 register increases monotonically. This sysfs interface640 exposes the number of PURR ticks for cpuX.641 642What: /sys/devices/system/cpu/cpuX/spurr643Date: Dec 2006644Contact: Linux for PowerPC mailing list <linuxppc-dev@lists.ozlabs.org>645Description: SPURR ticks for this CPU since the system boot.646 647 The Scaled Processor Utilization Resources Register648 (SPURR) is a 64-bit counter that provides a frequency649 invariant estimate of the resources used by the CPU650 thread. The contents of this register increases651 monotonically. This sysfs interface exposes the number652 of SPURR ticks for cpuX.653 654What: /sys/devices/system/cpu/cpuX/idle_purr655Date: Apr 2020656Contact: Linux for PowerPC mailing list <linuxppc-dev@lists.ozlabs.org>657Description: PURR ticks for cpuX when it was idle.658 659 This sysfs interface exposes the number of PURR ticks660 for cpuX when it was idle.661 662What: /sys/devices/system/cpu/cpuX/idle_spurr663Date: Apr 2020664Contact: Linux for PowerPC mailing list <linuxppc-dev@lists.ozlabs.org>665Description: SPURR ticks for cpuX when it was idle.666 667 This sysfs interface exposes the number of SPURR ticks668 for cpuX when it was idle.669 670What: /sys/devices/system/cpu/cpuX/mte_tcf_preferred671Date: July 2021672Contact: Linux ARM Kernel Mailing list <linux-arm-kernel@lists.infradead.org>673Description: Preferred MTE tag checking mode674 675 When a user program specifies more than one MTE tag checking676 mode, this sysfs node is used to specify which mode should677 be preferred when scheduling a task on that CPU. Possible678 values:679 680 ================ ==============================================681 "sync" Prefer synchronous mode682 "asymm" Prefer asymmetric mode683 "async" Prefer asynchronous mode684 ================ ==============================================685 686 See also: Documentation/arch/arm64/memory-tagging-extension.rst687 688What: /sys/devices/system/cpu/nohz_full689Date: Apr 2015690Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org>691Description:692 (RO) the list of CPUs that are in nohz_full mode.693 These CPUs are set by boot parameter "nohz_full=".694 695What: /sys/devices/system/cpu/isolated696Date: Apr 2015697Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org>698Description:699 (RO) the list of CPUs that are isolated and don't700 participate in load balancing. These CPUs are set by701 boot parameter "isolcpus=".702 703What: /sys/devices/system/cpu/crash_hotplug704Date: Aug 2023705Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org>706Description:707 (RO) indicates whether or not the kernel updates relevant kexec708 segments on memory hot un/plug and/or on/offline events, avoiding the709 need to reload kdump kernel.710 711What: /sys/devices/system/cpu/enabled712Date: Nov 2022713Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org>714Description:715 (RO) the list of CPUs that can be brought online.716