Documentation/ABI/testing/sysfs-devices-system-cpu

   1 What:           /sys/devices/system/cpu/
   2 Date:           pre-git history
   3 Contact:        Linux kernel mailing list <linux-kernel@vger.kernel.org>
   4 Description:
   5                 A collection of both global and individual CPU attributes
   6
   7                 Individual CPU attributes are contained in subdirectories
   8                 named by the kernel's logical CPU number, e.g.:
   9
  10                 /sys/devices/system/cpu/cpuX/
  11
  12 What:           /sys/devices/system/cpu/kernel_max
  13                 /sys/devices/system/cpu/offline
  14                 /sys/devices/system/cpu/online
  15                 /sys/devices/system/cpu/possible
  16                 /sys/devices/system/cpu/present
  17 Date:           December 2008
  18 Contact:        Linux kernel mailing list <linux-kernel@vger.kernel.org>
  19 Description:    CPU topology files that describe kernel limits related to
  20                 hotplug. Briefly:
  21
  22                 kernel_max: the maximum cpu index allowed by the kernel
  23                 configuration.
  24
  25                 offline: cpus that are not online because they have been
  26                 HOTPLUGGED off or exceed the limit of cpus allowed by the
  27                 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 be
  32                 brought online if they are present.
  33
  34                 present: cpus that have been identified as being present in
  35                 the system.
  36
  37                 See Documentation/admin-guide/cputopology.rst for more information.
  38
  39
  40 What:           /sys/devices/system/cpu/probe
  41                 /sys/devices/system/cpu/release
  42 Date:           November 2009
  43 Contact:        Linux kernel mailing list <linux-kernel@vger.kernel.org>
  44 Description:    Dynamic addition and removal of CPU's.  This is not hotplug
  45                 removal, this is meant complete removal/addition of the CPU
  46                 from the system.
  47
  48                 probe: writes to this file will dynamically add a CPU to the
  49                 system.  Information written to the file to add CPU's is
  50                 architecture specific.
  51
  52                 release: writes to this file dynamically remove a CPU from
  53                 the system.  Information written to the file to remove CPU's
  54                 is architecture specific.
  55
  56 What:           /sys/devices/system/cpu/cpuX/node
  57 Date:           October 2009
  58 Contact:        Linux memory management mailing list <linux-mm@kvack.org>
  59 Description:    Discover NUMA node a CPU belongs to
  60
  61                 When CONFIG_NUMA is enabled, a symbolic link that points
  62                 to the corresponding NUMA node directory.
  63
  64                 For example, the following symlink is created for cpu42
  65                 in NUMA node 2:
  66
  67                 /sys/devices/system/cpu/cpu42/node2 -> ../../node/node2
  68
  69
  70 What:           /sys/devices/system/cpu/cpuX/topology/core_siblings
  71                 /sys/devices/system/cpu/cpuX/topology/core_siblings_list
  72                 /sys/devices/system/cpu/cpuX/topology/physical_package_id
  73                 /sys/devices/system/cpu/cpuX/topology/thread_siblings
  74                 /sys/devices/system/cpu/cpuX/topology/thread_siblings_list
  75                 /sys/devices/system/cpu/cpuX/topology/ppin
  76 Date:           December 2008
  77 Contact:        Linux kernel mailing list <linux-kernel@vger.kernel.org>
  78 Description:    CPU topology files that describe a logical CPU's relationship
  79                 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 threads
  87                 within the same physical_package_id.
  88
  89                 core_siblings_list: human-readable list of the logical CPU
  90                 numbers within the same physical_package_id as cpuX.
  91
  92                 physical_package_id: physical package id of cpuX. Typically
  93                 corresponds to a physical socket number, but the actual value
  94                 is architecture and platform dependent.
  95
  96                 thread_siblings: internal kernel map of cpuX's hardware
  97                 threads within the same core as cpuX
  98
  99                 thread_siblings_list: human-readable list of cpuX's hardware
 100                 threads within the same core as cpuX
 101
 102                 ppin: human-readable Protected Processor Identification
 103                 Number of the socket the cpu# belongs to. There should be
 104                 one per physical_package_id. File is readable only to
 105                 admin.
 106
 107                 See Documentation/admin-guide/cputopology.rst for more information.
 108
 109
 110 What:           /sys/devices/system/cpu/cpuidle/available_governors
 111                 /sys/devices/system/cpu/cpuidle/current_driver
 112                 /sys/devices/system/cpu/cpuidle/current_governor
 113                 /sys/devices/system/cpu/cpuidle/current_governer_ro
 114                 /sys/devices/system/cpu/cpuidle/intel_c1_demotion
 115 Date:           September 2007
 116 Contact:        Linux kernel mailing list <linux-kernel@vger.kernel.org>
 117 Description:    Discover cpuidle policy and mechanism
 118
 119                 Various CPUs today support multiple idle levels that are
 120                 differentiated by varying exit latencies and power
 121                 consumption during idle.
 122
 123                 Idle policy (governor) is differentiated from idle mechanism
 124                 (driver).
 125
 126                 available_governors: (RO) displays a space separated list of
 127                 available governors.
 128
 129                 current_driver: (RO) displays current idle mechanism.
 130
 131                 current_governor: (RW) displays current idle policy. Users can
 132                 switch the governor at runtime by writing to this file.
 133
 134                 current_governor_ro: (RO) displays current idle policy.
 135
 136                 intel_c1_demotion: (RW) enables/disables the C1 demotion
 137                 feature on Intel CPUs.
 138
 139                 See Documentation/admin-guide/pm/cpuidle.rst,
 140                 Documentation/admin-guide/pm/intel_idle.rst, and
 141                 Documentation/driver-api/pm/cpuidle.rst for more information.
 142
 143
 144 What:           /sys/devices/system/cpu/cpuX/cpuidle/state<N>/name
 145                 /sys/devices/system/cpu/cpuX/cpuidle/stateN/latency
 146                 /sys/devices/system/cpu/cpuX/cpuidle/stateN/power
 147                 /sys/devices/system/cpu/cpuX/cpuidle/stateN/time
 148                 /sys/devices/system/cpu/cpuX/cpuidle/stateN/usage
 149                 /sys/devices/system/cpu/cpuX/cpuidle/stateN/above
 150                 /sys/devices/system/cpu/cpuX/cpuidle/stateN/below
 151 Date:           September 2007
 152 KernelVersion:  v2.6.24
 153 Contact:        Linux power management list <linux-pm@vger.kernel.org>
 154 Description:
 155                 The directory /sys/devices/system/cpu/cpuX/cpuidle contains per
 156                 logical CPU specific cpuidle information for each online cpu X.
 157                 The processor idle states which are available for use have the
 158                 following attributes:
 159
 160                 ======== ==== =================================================
 161                 name:    (RO) Name of the idle state (string).
 162
 163                 latency: (RO) The latency to exit out of this idle state (in
 164                               microseconds).
 165
 166                 power:   (RO) The power consumed while in this idle state (in
 167                               milliwatts).
 168
 169                 time:    (RO) The total time spent in this idle state
 170                               (in microseconds).
 171
 172                 usage:   (RO) Number of times this state was entered (a count).
 173
 174                 above:   (RO) Number of times this state was entered, but the
 175                               observed CPU idle duration was too short for it
 176                               (a count).
 177
 178                 below:   (RO) Number of times this state was entered, but the
 179                               observed CPU idle duration was too long for it
 180                               (a count).
 181                 ======== ==== =================================================
 182
 183 What:           /sys/devices/system/cpu/cpuX/cpuidle/state<N>/desc
 184 Date:           February 2008
 185 KernelVersion:  v2.6.25
 186 Contact:        Linux power management list <linux-pm@vger.kernel.org>
 187 Description:
 188                 (RO) A small description about the idle state (string).
 189
 190
 191 What:           /sys/devices/system/cpu/cpuX/cpuidle/state<N>/disable
 192 Date:           March 2012
 193 KernelVersion:  v3.10
 194 Contact:        Linux power management list <linux-pm@vger.kernel.org>
 195 Description:
 196                 (RW) Option to disable this idle state (bool). The behavior and
 197                 the effect of the disable variable depends on the implementation
 198                 of a particular governor. In the ladder governor, for example,
 199                 it is not coherent, i.e. if one is disabling a light state, then
 200                 all deeper states are disabled as well, but the disable variable
 201                 does not reflect it. Likewise, if one enables a deep state but a
 202                 lighter state still is disabled, then this has no effect.
 203
 204 What:           /sys/devices/system/cpu/cpuX/cpuidle/state<N>/default_status
 205 Date:           December 2019
 206 KernelVersion:  v5.6
 207 Contact:        Linux power management list <linux-pm@vger.kernel.org>
 208 Description:
 209                 (RO) The default status of this state, "enabled" or "disabled".
 210
 211 What:           /sys/devices/system/cpu/cpuX/cpuidle/state<N>/residency
 212 Date:           March 2014
 213 KernelVersion:  v3.15
 214 Contact:        Linux power management list <linux-pm@vger.kernel.org>
 215 Description:
 216                 (RO) Display the target residency i.e. the minimum amount of
 217                 time (in microseconds) this cpu should spend in this idle state
 218                 to make the transition worth the effort.
 219
 220 What:           /sys/devices/system/cpu/cpuX/cpuidle/state<N>/s2idle/
 221 Date:           March 2018
 222 KernelVersion:  v4.17
 223 Contact:        Linux power management list <linux-pm@vger.kernel.org>
 224 Description:
 225                 Idle state usage statistics related to suspend-to-idle.
 226
 227                 This attribute group is only present for states that can be
 228                 used in suspend-to-idle with suspended timekeeping.
 229
 230 What:           /sys/devices/system/cpu/cpuX/cpuidle/state<N>/s2idle/time
 231 Date:           March 2018
 232 KernelVersion:  v4.17
 233 Contact:        Linux power management list <linux-pm@vger.kernel.org>
 234 Description:
 235                 Total time spent by the CPU in suspend-to-idle (with scheduler
 236                 tick suspended) after requesting this state.
 237
 238 What:           /sys/devices/system/cpu/cpuX/cpuidle/state<N>/s2idle/usage
 239 Date:           March 2018
 240 KernelVersion:  v4.17
 241 Contact:        Linux power management list <linux-pm@vger.kernel.org>
 242 Description:
 243                 Total number of times this state has been requested by the CPU
 244                 while entering suspend-to-idle.
 245
 246 What:           /sys/devices/system/cpu/cpuX/cpufreq/*
 247 Date:           pre-git history
 248 Contact:        linux-pm@vger.kernel.org
 249 Description:    Discover and change clock speed of CPUs
 250
 251                 Clock scaling allows you to change the clock speed of the
 252                 CPUs on the fly. This is a nice method to save battery
 253                 power, because the lower the clock speed, the less power
 254                 the CPU consumes.
 255
 256                 There are many knobs to tweak in this directory.
 257
 258                 See files in Documentation/cpu-freq/ for more information.
 259
 260
 261 What:           /sys/devices/system/cpu/cpuX/cpufreq/freqdomain_cpus
 262 Date:           June 2013
 263 Contact:        linux-pm@vger.kernel.org
 264 Description:    Discover CPUs in the same CPU frequency coordination domain
 265
 266                 freqdomain_cpus is the list of CPUs (online+offline) that share
 267                 the same clock/freq domain (possibly at the hardware level).
 268                 That information may be hidden from the cpufreq core and the
 269                 value of related_cpus may be different from freqdomain_cpus. This
 270                 attribute is useful for user space DVFS controllers to get better
 271                 power/performance results for platforms using acpi-cpufreq.
 272
 273                 This file is only present if the acpi-cpufreq or the cppc-cpufreq
 274                 drivers are in use.
 275
 276 What:           /sys/devices/system/cpu/cpuX/cpufreq/auto_select
 277 Date:           May 2025
 278 Contact:        linux-pm@vger.kernel.org
 279 Description:    Autonomous selection enable
 280
 281                 Read/write interface to control autonomous selection enable
 282                         Read returns autonomous selection status:
 283                                 0: autonomous selection is disabled
 284                                 1: autonomous selection is enabled
 285
 286                         Write 'y' or '1' or 'on' to enable autonomous selection.
 287                         Write 'n' or '0' or 'off' to disable autonomous selection.
 288
 289                 This file is only present if the cppc-cpufreq driver is in use.
 290
 291 What:           /sys/devices/system/cpu/cpuX/cpufreq/auto_act_window
 292 Date:           May 2025
 293 Contact:        linux-pm@vger.kernel.org
 294 Description:    Autonomous activity window
 295
 296                 This file indicates a moving utilization sensitivity window to
 297                 the platform's autonomous selection policy.
 298
 299                 Read/write an integer represents autonomous activity window (in
 300                 microseconds) from/to this file. The max value to write is
 301                 1270000000 but the max significand is 127. This means that if 128
 302                 is written to this file, 127 will be stored. If the value is
 303                 greater than 130, only the first two digits will be saved as
 304                 significand.
 305
 306                 Writing a zero value to this file enable the platform to
 307                 determine an appropriate Activity Window depending on the workload.
 308
 309                 Writing to this file only has meaning when Autonomous Selection is
 310                 enabled.
 311
 312                 This file is only present if the cppc-cpufreq driver is in use.
 313
 314 What:           /sys/devices/system/cpu/cpuX/cpufreq/energy_performance_preference_val
 315 Date:           May 2025
 316 Contact:        linux-pm@vger.kernel.org
 317 Description:    Energy performance preference
 318
 319                 Read/write an 8-bit integer from/to this file. This file
 320                 represents a range of values from 0 (performance preference) to
 321                 0xFF (energy efficiency preference) that influences the rate of
 322                 performance increase/decrease and the result of the hardware's
 323                 energy efficiency and performance optimization policies.
 324
 325                 Writing to this file only has meaning when Autonomous Selection is
 326                 enabled.
 327
 328                 This file is only present if the cppc-cpufreq driver is in use.
 329
 330
 331 What:           /sys/devices/system/cpu/cpu*/cache/index3/cache_disable_{0,1}
 332 Date:           August 2008
 333 KernelVersion:  2.6.27
 334 Contact:        Linux kernel mailing list <linux-kernel@vger.kernel.org>
 335 Description:    Disable L3 cache indices
 336
 337                 These files exist in every CPU's cache/index3 directory. Each
 338                 cache_disable_{0,1} file corresponds to one disable slot which
 339                 can be used to disable a cache index. Reading from these files
 340                 on a processor with this functionality will return the currently
 341                 disabled index for that node. There is one L3 structure per
 342                 node, or per internal node on MCM machines. Writing a valid
 343                 index to one of these files will cause the specified cache
 344                 index to be disabled.
 345
 346                 All AMD processors with L3 caches provide this functionality.
 347                 For details, see BKDGs at
 348                 https://www.amd.com/en/support/tech-docs?keyword=bios+kernel
 349
 350
 351 What:           /sys/devices/system/cpu/cpufreq/boost
 352 Date:           August 2012
 353 Contact:        Linux kernel mailing list <linux-kernel@vger.kernel.org>
 354 Description:    Processor frequency boosting control
 355
 356                 This switch controls the boost setting for the whole system.
 357                 Boosting allows the CPU and the firmware to run at a frequency
 358                 beyond its nominal limit.
 359
 360                 More details can be found in
 361                 Documentation/admin-guide/pm/cpufreq.rst
 362
 363
 364 What:           /sys/devices/system/cpu/cpuX/crash_notes
 365                 /sys/devices/system/cpu/cpuX/crash_notes_size
 366 Date:           April 2013
 367 Contact:        kexec@lists.infradead.org
 368 Description:    address and size of the percpu note.
 369
 370                 crash_notes: the physical address of the memory that holds the
 371                 note of cpuX.
 372
 373                 crash_notes_size: size of the note of cpuX.
 374
 375
 376 What:           /sys/devices/system/cpu/intel_pstate/max_perf_pct
 377                 /sys/devices/system/cpu/intel_pstate/min_perf_pct
 378                 /sys/devices/system/cpu/intel_pstate/no_turbo
 379 Date:           February 2013
 380 Contact:        linux-pm@vger.kernel.org
 381 Description:    Parameters for the Intel P-state driver
 382
 383                 Logic for selecting the current P-state in Intel
 384                 Sandybridge+ processors. The three knobs control
 385                 limits for the P-state that will be requested by the
 386                 driver.
 387
 388                 max_perf_pct: limits the maximum P state that will be requested by
 389                 the driver stated as a percentage of the available performance.
 390
 391                 min_perf_pct: limits the minimum P state that will be requested by
 392                 the driver stated as a percentage of the available performance.
 393
 394                 no_turbo: limits the driver to selecting P states below the turbo
 395                 frequency range.
 396
 397                 More details can be found in
 398                 Documentation/admin-guide/pm/intel_pstate.rst
 399
 400 What:           /sys/devices/system/cpu/cpu*/cache/index*/<set_of_attributes_mentioned_below>
 401 Date:           July 2014(documented, existed before August 2008)
 402 Contact:        Sudeep Holla <sudeep.holla@arm.com>
 403                 Linux kernel mailing list <linux-kernel@vger.kernel.org>
 404 Description:    Parameters for the CPU cache attributes
 405
 406                 allocation_policy:
 407                         - WriteAllocate:
 408                                         allocate a memory location to a cache line
 409                                         on a cache miss because of a write
 410                         - ReadAllocate:
 411                                         allocate a memory location to a cache line
 412                                         on a cache miss because of a read
 413                         - ReadWriteAllocate:
 414                                         both writeallocate and readallocate
 415
 416                 coherency_line_size:
 417                                      the minimum amount of data in bytes that gets
 418                                      transferred from memory to cache
 419
 420                 level:
 421                         the cache hierarchy in the multi-level cache configuration
 422
 423                 number_of_sets:
 424                                 total number of sets in the cache, a set is a
 425                                 collection of cache lines with the same cache index
 426
 427                 physical_line_partition:
 428                                 number of physical cache line per cache tag
 429
 430                 shared_cpu_list:
 431                                 the list of logical cpus sharing the cache
 432
 433                 shared_cpu_map:
 434                                 logical cpu mask containing the list of cpus sharing
 435                                 the cache
 436
 437                 size:
 438                         the total cache size in kB
 439
 440                 type:
 441                         - Instruction: cache that only holds instructions
 442                         - Data: cache that only caches data
 443                         - Unified: cache that holds both data and instructions
 444
 445                 ways_of_associativity:
 446                         degree of freedom in placing a particular block
 447                         of memory in the cache
 448
 449                 write_policy:
 450                         - WriteThrough:
 451                                         data is written to both the cache line
 452                                         and to the block in the lower-level memory
 453                         - WriteBack:
 454                                      data is written only to the cache line and
 455                                      the modified cache line is written to main
 456                                      memory only when it is replaced
 457
 458
 459 What:           /sys/devices/system/cpu/cpu*/cache/index*/id
 460 Date:           September 2016
 461 Contact:        Linux kernel mailing list <linux-kernel@vger.kernel.org>
 462 Description:    Cache id
 463
 464                 The id provides a unique number for a specific instance of
 465                 a cache of a particular type. E.g. there may be a level
 466                 3 unified cache on each socket in a server and we may
 467                 assign them ids 0, 1, 2, ...
 468
 469                 Note that id value can be non-contiguous. E.g. level 1
 470                 caches typically exist per core, but there may not be a
 471                 power of two cores on a socket, so these caches may be
 472                 numbered 0, 1, 2, 3, 4, 5, 8, 9, 10, ...
 473
 474 What:           /sys/devices/system/cpu/cpuX/cpufreq/throttle_stats
 475                 /sys/devices/system/cpu/cpuX/cpufreq/throttle_stats/turbo_stat
 476                 /sys/devices/system/cpu/cpuX/cpufreq/throttle_stats/sub_turbo_stat
 477                 /sys/devices/system/cpu/cpuX/cpufreq/throttle_stats/unthrottle
 478                 /sys/devices/system/cpu/cpuX/cpufreq/throttle_stats/powercap
 479                 /sys/devices/system/cpu/cpuX/cpufreq/throttle_stats/overtemp
 480                 /sys/devices/system/cpu/cpuX/cpufreq/throttle_stats/supply_fault
 481                 /sys/devices/system/cpu/cpuX/cpufreq/throttle_stats/overcurrent
 482                 /sys/devices/system/cpu/cpuX/cpufreq/throttle_stats/occ_reset
 483 Date:           March 2016
 484 Contact:        Linux kernel mailing list <linux-kernel@vger.kernel.org>
 485                 Linux for PowerPC mailing list <linuxppc-dev@lists.ozlabs.org>
 486 Description:    POWERNV CPUFreq driver's frequency throttle stats directory and
 487                 attributes
 488
 489                 'cpuX/cpufreq/throttle_stats' directory contains the CPU frequency
 490                 throttle stat attributes for the chip. The throttle stats of a cpu
 491                 is common across all the cpus belonging to a chip. Below are the
 492                 throttle attributes exported in the 'throttle_stats' directory:
 493
 494                 - turbo_stat : This file gives the total number of times the max
 495                   frequency is throttled to lower frequency in turbo (at and above
 496                   nominal frequency) range of frequencies.
 497
 498                 - sub_turbo_stat : This file gives the total number of times the
 499                   max frequency is throttled to lower frequency in sub-turbo(below
 500                   nominal frequency) range of frequencies.
 501
 502                 - unthrottle : This file gives the total number of times the max
 503                   frequency is unthrottled after being throttled.
 504
 505                 - powercap : This file gives the total number of times the max
 506                   frequency is throttled due to 'Power Capping'.
 507
 508                 - overtemp : This file gives the total number of times the max
 509                   frequency is throttled due to 'CPU Over Temperature'.
 510
 511                 - supply_fault : This file gives the total number of times the
 512                   max frequency is throttled due to 'Power Supply Failure'.
 513
 514                 - overcurrent : This file gives the total number of times the
 515                   max frequency is throttled due to 'Overcurrent'.
 516
 517                 - occ_reset : This file gives the total number of times the max
 518                   frequency is throttled due to 'OCC Reset'.
 519
 520                 The sysfs attributes representing different throttle reasons like
 521                 powercap, overtemp, supply_fault, overcurrent and occ_reset map to
 522                 the reasons provided by OCC firmware for throttling the frequency.
 523
 524 What:           /sys/devices/system/cpu/cpufreq/policyX/throttle_stats
 525                 /sys/devices/system/cpu/cpufreq/policyX/throttle_stats/turbo_stat
 526                 /sys/devices/system/cpu/cpufreq/policyX/throttle_stats/sub_turbo_stat
 527                 /sys/devices/system/cpu/cpufreq/policyX/throttle_stats/unthrottle
 528                 /sys/devices/system/cpu/cpufreq/policyX/throttle_stats/powercap
 529                 /sys/devices/system/cpu/cpufreq/policyX/throttle_stats/overtemp
 530                 /sys/devices/system/cpu/cpufreq/policyX/throttle_stats/supply_fault
 531                 /sys/devices/system/cpu/cpufreq/policyX/throttle_stats/overcurrent
 532                 /sys/devices/system/cpu/cpufreq/policyX/throttle_stats/occ_reset
 533 Date:           March 2016
 534 Contact:        Linux kernel mailing list <linux-kernel@vger.kernel.org>
 535                 Linux for PowerPC mailing list <linuxppc-dev@lists.ozlabs.org>
 536 Description:    POWERNV CPUFreq driver's frequency throttle stats directory and
 537                 attributes
 538
 539                 'policyX/throttle_stats' directory and all the attributes are same as
 540                 the /sys/devices/system/cpu/cpuX/cpufreq/throttle_stats directory and
 541                 attributes which give the frequency throttle information of the chip.
 542
 543 What:           /sys/devices/system/cpu/cpuX/regs/
 544                 /sys/devices/system/cpu/cpuX/regs/identification/
 545                 /sys/devices/system/cpu/cpuX/regs/identification/midr_el1
 546                 /sys/devices/system/cpu/cpuX/regs/identification/revidr_el1
 547                 /sys/devices/system/cpu/cpuX/regs/identification/aidr_el1
 548                 /sys/devices/system/cpu/cpuX/regs/identification/smidr_el1
 549 Date:           June 2016
 550 Contact:        Linux ARM Kernel Mailing list <linux-arm-kernel@lists.infradead.org>
 551 Description:    AArch64 CPU registers
 552
 553                 'identification' directory exposes the CPU ID registers for
 554                 identifying model and revision of the CPU and SMCU.
 555
 556 What:           /sys/devices/system/cpu/aarch32_el0
 557 Date:           May 2021
 558 Contact:        Linux ARM Kernel Mailing list <linux-arm-kernel@lists.infradead.org>
 559 Description:    Identifies the subset of CPUs in the system that can execute
 560                 AArch32 (32-bit ARM) applications. If present, the same format as
 561                 /sys/devices/system/cpu/{offline,online,possible,present} is used.
 562                 If absent, then all or none of the CPUs can execute AArch32
 563                 applications and execve() will behave accordingly.
 564
 565 What:           /sys/devices/system/cpu/cpuX/cpu_capacity
 566 Date:           December 2016
 567 Contact:        Linux kernel mailing list <linux-kernel@vger.kernel.org>
 568 Description:    information about CPUs heterogeneity.
 569
 570                 cpu_capacity: capacity of cpuX.
 571
 572 What:           /sys/devices/system/cpu/vulnerabilities
 573                 /sys/devices/system/cpu/vulnerabilities/gather_data_sampling
 574                 /sys/devices/system/cpu/vulnerabilities/indirect_target_selection
 575                 /sys/devices/system/cpu/vulnerabilities/itlb_multihit
 576                 /sys/devices/system/cpu/vulnerabilities/l1tf
 577                 /sys/devices/system/cpu/vulnerabilities/mds
 578                 /sys/devices/system/cpu/vulnerabilities/meltdown
 579                 /sys/devices/system/cpu/vulnerabilities/mmio_stale_data
 580                 /sys/devices/system/cpu/vulnerabilities/old_microcode
 581                 /sys/devices/system/cpu/vulnerabilities/reg_file_data_sampling
 582                 /sys/devices/system/cpu/vulnerabilities/retbleed
 583                 /sys/devices/system/cpu/vulnerabilities/spec_store_bypass
 584                 /sys/devices/system/cpu/vulnerabilities/spectre_v1
 585                 /sys/devices/system/cpu/vulnerabilities/spectre_v2
 586                 /sys/devices/system/cpu/vulnerabilities/srbds
 587                 /sys/devices/system/cpu/vulnerabilities/tsa
 588                 /sys/devices/system/cpu/vulnerabilities/tsx_async_abort
 589 Date:           January 2018
 590 Contact:        Linux kernel mailing list <linux-kernel@vger.kernel.org>
 591 Description:    Information about CPU vulnerabilities
 592
 593                 The files are named after the code names of CPU
 594                 vulnerabilities. The output of those files reflects the
 595                 state of the CPUs in the system. Possible output values:
 596
 597                 ================  ==============================================
 598                 "Not affected"    CPU is not affected by the vulnerability
 599                 "Vulnerable"      CPU is affected and no mitigation in effect
 600                 "Mitigation: $M"  CPU is affected and mitigation $M is in effect
 601                 ================  ==============================================
 602
 603                 See also: Documentation/admin-guide/hw-vuln/index.rst
 604
 605 What:           /sys/devices/system/cpu/smt
 606                 /sys/devices/system/cpu/smt/active
 607                 /sys/devices/system/cpu/smt/control
 608 Date:           June 2018
 609 Contact:        Linux kernel mailing list <linux-kernel@vger.kernel.org>
 610 Description:    Control Symmetric Multi Threading (SMT)
 611
 612                 active:  Tells whether SMT is active (enabled and siblings online)
 613
 614                 control: Read/write interface to control SMT. Possible
 615                          values:
 616
 617                          ================ =========================================
 618                          "on"             SMT is enabled
 619                          "off"            SMT is disabled
 620                          "<N>"            SMT is enabled with N threads per core.
 621                          "forceoff"       SMT is force disabled. Cannot be changed.
 622                          "notsupported"   SMT is not supported by the CPU
 623                          "notimplemented" SMT runtime toggling is not
 624                                           implemented for the architecture
 625                          ================ =========================================
 626
 627                          If control status is "forceoff" or "notsupported" writes
 628                          are rejected. Note that enabling SMT on PowerPC skips
 629                          offline cores.
 630
 631 What:           /sys/devices/system/cpu/cpuX/power/energy_perf_bias
 632 Date:           March 2019
 633 Contact:        linux-pm@vger.kernel.org
 634 Description:    Intel Energy and Performance Bias Hint (EPB)
 635
 636                 EPB for the given CPU in a sliding scale 0 - 15, where a value
 637                 of 0 corresponds to a hint preference for highest performance
 638                 and a value of 15 corresponds to the maximum energy savings.
 639
 640                 In order to change the EPB value for the CPU, write either
 641                 a number in the 0 - 15 sliding scale above, or one of the
 642                 strings: "performance", "balance-performance", "normal",
 643                 "balance-power", "power" (that represent values reflected by
 644                 their meaning), to this attribute.
 645
 646                 This attribute is present for all online CPUs supporting the
 647                 Intel EPB feature.
 648
 649 What:           /sys/devices/system/cpu/umwait_control
 650                 /sys/devices/system/cpu/umwait_control/enable_c02
 651                 /sys/devices/system/cpu/umwait_control/max_time
 652 Date:           May 2019
 653 Contact:        Linux kernel mailing list <linux-kernel@vger.kernel.org>
 654 Description:    Umwait control
 655
 656                 enable_c02: Read/write interface to control umwait C0.2 state
 657                         Read returns C0.2 state status:
 658                                 0: C0.2 is disabled
 659                                 1: C0.2 is enabled
 660
 661                         Write 'y' or '1'  or 'on' to enable C0.2 state.
 662                         Write 'n' or '0'  or 'off' to disable C0.2 state.
 663
 664                         The interface is case insensitive.
 665
 666                 max_time: Read/write interface to control umwait maximum time
 667                           in TSC-quanta that the CPU can reside in either C0.1
 668                           or C0.2 state. The time is an unsigned 32-bit number.
 669                           Note that a value of zero means there is no limit.
 670                           Low order two bits must be zero.
 671
 672 What:           /sys/devices/system/cpu/sev
 673                 /sys/devices/system/cpu/sev/vmpl
 674 Date:           May 2024
 675 Contact:        Linux kernel mailing list <linux-kernel@vger.kernel.org>
 676 Description:    Secure Encrypted Virtualization (SEV) information
 677
 678                 This directory is only present when running as an SEV-SNP guest.
 679
 680                 vmpl: Reports the Virtual Machine Privilege Level (VMPL) at which
 681                       the SEV-SNP guest is running.
 682
 683
 684 What:           /sys/devices/system/cpu/svm
 685 Date:           August 2019
 686 Contact:        Linux kernel mailing list <linux-kernel@vger.kernel.org>
 687                 Linux for PowerPC mailing list <linuxppc-dev@lists.ozlabs.org>
 688 Description:    Secure Virtual Machine
 689
 690                 If 1, it means the system is using the Protected Execution
 691                 Facility in POWER9 and newer processors. i.e., it is a Secure
 692                 Virtual Machine.
 693
 694 What:           /sys/devices/system/cpu/cpuX/purr
 695 Date:           Apr 2005
 696 Contact:        Linux for PowerPC mailing list <linuxppc-dev@lists.ozlabs.org>
 697 Description:    PURR ticks for this CPU since the system boot.
 698
 699                 The Processor Utilization Resources Register (PURR) is
 700                 a 64-bit counter which provides an estimate of the
 701                 resources used by the CPU thread. The contents of this
 702                 register increases monotonically. This sysfs interface
 703                 exposes the number of PURR ticks for cpuX.
 704
 705 What:           /sys/devices/system/cpu/cpuX/spurr
 706 Date:           Dec 2006
 707 Contact:        Linux for PowerPC mailing list <linuxppc-dev@lists.ozlabs.org>
 708 Description:    SPURR ticks for this CPU since the system boot.
 709
 710                 The Scaled Processor Utilization Resources Register
 711                 (SPURR) is a 64-bit counter that provides a frequency
 712                 invariant estimate of the resources used by the CPU
 713                 thread. The contents of this register increases
 714                 monotonically. This sysfs interface exposes the number
 715                 of SPURR ticks for cpuX.
 716
 717 What:           /sys/devices/system/cpu/cpuX/idle_purr
 718 Date:           Apr 2020
 719 Contact:        Linux for PowerPC mailing list <linuxppc-dev@lists.ozlabs.org>
 720 Description:    PURR ticks for cpuX when it was idle.
 721
 722                 This sysfs interface exposes the number of PURR ticks
 723                 for cpuX when it was idle.
 724
 725 What:           /sys/devices/system/cpu/cpuX/idle_spurr
 726 Date:           Apr 2020
 727 Contact:        Linux for PowerPC mailing list <linuxppc-dev@lists.ozlabs.org>
 728 Description:    SPURR ticks for cpuX when it was idle.
 729
 730                 This sysfs interface exposes the number of SPURR ticks
 731                 for cpuX when it was idle.
 732
 733 What:           /sys/devices/system/cpu/cpuX/mte_tcf_preferred
 734 Date:           July 2021
 735 Contact:        Linux ARM Kernel Mailing list <linux-arm-kernel@lists.infradead.org>
 736 Description:    Preferred MTE tag checking mode
 737
 738                 When a user program specifies more than one MTE tag checking
 739                 mode, this sysfs node is used to specify which mode should
 740                 be preferred when scheduling a task on that CPU. Possible
 741                 values:
 742
 743                 ================  ==============================================
 744                 "sync"            Prefer synchronous mode
 745                 "asymm"           Prefer asymmetric mode
 746                 "async"           Prefer asynchronous mode
 747                 ================  ==============================================
 748
 749                 See also: Documentation/arch/arm64/memory-tagging-extension.rst
 750
 751 What:           /sys/devices/system/cpu/nohz_full
 752 Date:           Apr 2015
 753 Contact:        Linux kernel mailing list <linux-kernel@vger.kernel.org>
 754 Description:
 755                 (RO) the list of CPUs that are in nohz_full mode.
 756                 These CPUs are set by boot parameter "nohz_full=".
 757
 758 What:           /sys/devices/system/cpu/isolated
 759 Date:           Apr 2015
 760 Contact:        Linux kernel mailing list <linux-kernel@vger.kernel.org>
 761 Description:
 762                 (RO) the list of CPUs that are isolated and don't
 763                 participate in load balancing. These CPUs are set by
 764                 boot parameter "isolcpus=".
 765
 766 What:           /sys/devices/system/cpu/crash_hotplug
 767 Date:           Aug 2023
 768 Contact:        Linux kernel mailing list <linux-kernel@vger.kernel.org>
 769 Description:
 770                 (RO) indicates whether or not the kernel updates relevant kexec
 771                 segments on memory hot un/plug and/or on/offline events, avoiding the
 772                 need to reload kdump kernel.
 773
 774 What:           /sys/devices/system/cpu/enabled
 775 Date:           Nov 2022
 776 Contact:        Linux kernel mailing list <linux-kernel@vger.kernel.org>
 777 Description:
 778                 (RO) the list of CPUs that can be brought online.