12ceb3fb0SAlex ChiangWhat: /sys/devices/system/cpu/ 22ceb3fb0SAlex ChiangDate: pre-git history 32ceb3fb0SAlex ChiangContact: Linux kernel mailing list <linux-kernel@vger.kernel.org> 42ceb3fb0SAlex ChiangDescription: 52ceb3fb0SAlex Chiang A collection of both global and individual CPU attributes 62ceb3fb0SAlex Chiang 72ceb3fb0SAlex Chiang Individual CPU attributes are contained in subdirectories 82ceb3fb0SAlex Chiang named by the kernel's logical CPU number, e.g.: 92ceb3fb0SAlex Chiang 102ceb3fb0SAlex Chiang /sys/devices/system/cpu/cpu#/ 112ceb3fb0SAlex Chiang 12d93fc863SAlex ChiangWhat: /sys/devices/system/cpu/kernel_max 13d93fc863SAlex Chiang /sys/devices/system/cpu/offline 14d93fc863SAlex Chiang /sys/devices/system/cpu/online 15d93fc863SAlex Chiang /sys/devices/system/cpu/possible 16d93fc863SAlex Chiang /sys/devices/system/cpu/present 17d93fc863SAlex ChiangDate: December 2008 18d93fc863SAlex ChiangContact: Linux kernel mailing list <linux-kernel@vger.kernel.org> 19d93fc863SAlex ChiangDescription: CPU topology files that describe kernel limits related to 20d93fc863SAlex Chiang hotplug. Briefly: 21d93fc863SAlex Chiang 22d93fc863SAlex Chiang kernel_max: the maximum cpu index allowed by the kernel 23d93fc863SAlex Chiang configuration. 24d93fc863SAlex Chiang 25d93fc863SAlex Chiang offline: cpus that are not online because they have been 26d93fc863SAlex Chiang HOTPLUGGED off or exceed the limit of cpus allowed by the 27d93fc863SAlex Chiang kernel configuration (kernel_max above). 28d93fc863SAlex Chiang 29d93fc863SAlex Chiang online: cpus that are online and being scheduled. 30d93fc863SAlex Chiang 31d93fc863SAlex Chiang possible: cpus that have been allocated resources and can be 32d93fc863SAlex Chiang brought online if they are present. 33d93fc863SAlex Chiang 34d93fc863SAlex Chiang present: cpus that have been identified as being present in 35d93fc863SAlex Chiang the system. 36d93fc863SAlex Chiang 374f4cfa6cSMauro Carvalho Chehab See Documentation/admin-guide/cputopology.rst for more information. 38d93fc863SAlex Chiang 39d93fc863SAlex Chiang 4012633e80SNathan FontenotWhat: /sys/devices/system/cpu/probe 4112633e80SNathan Fontenot /sys/devices/system/cpu/release 4212633e80SNathan FontenotDate: November 2009 4312633e80SNathan FontenotContact: Linux kernel mailing list <linux-kernel@vger.kernel.org> 4412633e80SNathan FontenotDescription: Dynamic addition and removal of CPU's. This is not hotplug 4512633e80SNathan Fontenot removal, this is meant complete removal/addition of the CPU 4612633e80SNathan Fontenot from the system. 4712633e80SNathan Fontenot 4812633e80SNathan Fontenot probe: writes to this file will dynamically add a CPU to the 4912633e80SNathan Fontenot system. Information written to the file to add CPU's is 5012633e80SNathan Fontenot architecture specific. 5112633e80SNathan Fontenot 5212633e80SNathan Fontenot release: writes to this file dynamically remove a CPU from 5312633e80SNathan Fontenot the system. Information writtento the file to remove CPU's 5412633e80SNathan Fontenot is architecture specific. 55657348a0SAlex Chiang 56657348a0SAlex ChiangWhat: /sys/devices/system/cpu/cpu#/node 57657348a0SAlex ChiangDate: October 2009 58657348a0SAlex ChiangContact: Linux memory management mailing list <linux-mm@kvack.org> 59657348a0SAlex ChiangDescription: Discover NUMA node a CPU belongs to 60657348a0SAlex Chiang 61657348a0SAlex Chiang When CONFIG_NUMA is enabled, a symbolic link that points 62657348a0SAlex Chiang to the corresponding NUMA node directory. 63657348a0SAlex Chiang 64657348a0SAlex Chiang For example, the following symlink is created for cpu42 65657348a0SAlex Chiang in NUMA node 2: 66657348a0SAlex Chiang 67657348a0SAlex Chiang /sys/devices/system/cpu/cpu42/node2 -> ../../node/node2 68657348a0SAlex Chiang 69657348a0SAlex Chiang 70663fb2fcSAlex ChiangWhat: /sys/devices/system/cpu/cpu#/topology/core_id 71663fb2fcSAlex Chiang /sys/devices/system/cpu/cpu#/topology/core_siblings 72663fb2fcSAlex Chiang /sys/devices/system/cpu/cpu#/topology/core_siblings_list 73663fb2fcSAlex Chiang /sys/devices/system/cpu/cpu#/topology/physical_package_id 74663fb2fcSAlex Chiang /sys/devices/system/cpu/cpu#/topology/thread_siblings 75663fb2fcSAlex Chiang /sys/devices/system/cpu/cpu#/topology/thread_siblings_list 76663fb2fcSAlex ChiangDate: December 2008 77663fb2fcSAlex ChiangContact: Linux kernel mailing list <linux-kernel@vger.kernel.org> 78663fb2fcSAlex ChiangDescription: CPU topology files that describe a logical CPU's relationship 79663fb2fcSAlex Chiang to other cores and threads in the same physical package. 80663fb2fcSAlex Chiang 81663fb2fcSAlex Chiang One cpu# directory is created per logical CPU in the system, 82663fb2fcSAlex Chiang e.g. /sys/devices/system/cpu/cpu42/. 83663fb2fcSAlex Chiang 84663fb2fcSAlex Chiang Briefly, the files above are: 85663fb2fcSAlex Chiang 86663fb2fcSAlex Chiang core_id: the CPU core ID of cpu#. Typically it is the 87663fb2fcSAlex Chiang hardware platform's identifier (rather than the kernel's). 88663fb2fcSAlex Chiang The actual value is architecture and platform dependent. 89663fb2fcSAlex Chiang 90663fb2fcSAlex Chiang core_siblings: internal kernel map of cpu#'s hardware threads 91663fb2fcSAlex Chiang within the same physical_package_id. 92663fb2fcSAlex Chiang 93663fb2fcSAlex Chiang core_siblings_list: human-readable list of the logical CPU 94663fb2fcSAlex Chiang numbers within the same physical_package_id as cpu#. 95663fb2fcSAlex Chiang 96663fb2fcSAlex Chiang physical_package_id: physical package id of cpu#. Typically 97663fb2fcSAlex Chiang corresponds to a physical socket number, but the actual value 98663fb2fcSAlex Chiang is architecture and platform dependent. 99663fb2fcSAlex Chiang 100663fb2fcSAlex Chiang thread_siblings: internel kernel map of cpu#'s hardware 101663fb2fcSAlex Chiang threads within the same core as cpu# 102663fb2fcSAlex Chiang 103663fb2fcSAlex Chiang thread_siblings_list: human-readable list of cpu#'s hardware 104663fb2fcSAlex Chiang threads within the same core as cpu# 105663fb2fcSAlex Chiang 1064f4cfa6cSMauro Carvalho Chehab See Documentation/admin-guide/cputopology.rst for more information. 107663fb2fcSAlex Chiang 108663fb2fcSAlex Chiang 1097395683aSHanjun GuoWhat: /sys/devices/system/cpu/cpuidle/available_governors 1107395683aSHanjun Guo /sys/devices/system/cpu/cpuidle/current_driver 111b6d8ef86SAishwarya Pant /sys/devices/system/cpu/cpuidle/current_governor 1127395683aSHanjun Guo /sys/devices/system/cpu/cpuidle/current_governer_ro 113c1fb5c47SAlex ChiangDate: September 2007 114c1fb5c47SAlex ChiangContact: Linux kernel mailing list <linux-kernel@vger.kernel.org> 115c1fb5c47SAlex ChiangDescription: Discover cpuidle policy and mechanism 116c1fb5c47SAlex Chiang 117c1fb5c47SAlex Chiang Various CPUs today support multiple idle levels that are 118c1fb5c47SAlex Chiang differentiated by varying exit latencies and power 119c1fb5c47SAlex Chiang consumption during idle. 120c1fb5c47SAlex Chiang 121c1fb5c47SAlex Chiang Idle policy (governor) is differentiated from idle mechanism 1227395683aSHanjun Guo (driver). 123b6d8ef86SAishwarya Pant 124b6d8ef86SAishwarya Pant available_governors: (RO) displays a space separated list of 1257395683aSHanjun Guo available governors. 1267395683aSHanjun Guo 1277395683aSHanjun Guo current_driver: (RO) displays current idle mechanism. 128b6d8ef86SAishwarya Pant 129b6d8ef86SAishwarya Pant current_governor: (RW) displays current idle policy. Users can 130b6d8ef86SAishwarya Pant switch the governor at runtime by writing to this file. 131c1fb5c47SAlex Chiang 1327395683aSHanjun Guo current_governor_ro: (RO) displays current idle policy. 1337395683aSHanjun Guo 134671c3095SMauro Carvalho Chehab See Documentation/admin-guide/pm/cpuidle.rst and 135671c3095SMauro Carvalho Chehab Documentation/driver-api/pm/cpuidle.rst for more information. 136c1fb5c47SAlex Chiang 137c1fb5c47SAlex Chiang 138b6d8ef86SAishwarya PantWhat: /sys/devices/system/cpu/cpuX/cpuidle/stateN/name 139b6d8ef86SAishwarya Pant /sys/devices/system/cpu/cpuX/cpuidle/stateN/latency 140b6d8ef86SAishwarya Pant /sys/devices/system/cpu/cpuX/cpuidle/stateN/power 141b6d8ef86SAishwarya Pant /sys/devices/system/cpu/cpuX/cpuidle/stateN/time 142b6d8ef86SAishwarya Pant /sys/devices/system/cpu/cpuX/cpuidle/stateN/usage 14304dab58aSRafael J. Wysocki /sys/devices/system/cpu/cpuX/cpuidle/stateN/above 14404dab58aSRafael J. Wysocki /sys/devices/system/cpu/cpuX/cpuidle/stateN/below 145b6d8ef86SAishwarya PantDate: September 2007 146b6d8ef86SAishwarya PantKernelVersion: v2.6.24 147b6d8ef86SAishwarya PantContact: Linux power management list <linux-pm@vger.kernel.org> 148b6d8ef86SAishwarya PantDescription: 149b6d8ef86SAishwarya Pant The directory /sys/devices/system/cpu/cpuX/cpuidle contains per 150b6d8ef86SAishwarya Pant logical CPU specific cpuidle information for each online cpu X. 151b6d8ef86SAishwarya Pant The processor idle states which are available for use have the 152b6d8ef86SAishwarya Pant following attributes: 153b6d8ef86SAishwarya Pant 15434433332SMauro Carvalho Chehab ======== ==== ================================================= 155b6d8ef86SAishwarya Pant name: (RO) Name of the idle state (string). 156b6d8ef86SAishwarya Pant 157b6d8ef86SAishwarya Pant latency: (RO) The latency to exit out of this idle state (in 158b6d8ef86SAishwarya Pant microseconds). 159b6d8ef86SAishwarya Pant 160b6d8ef86SAishwarya Pant power: (RO) The power consumed while in this idle state (in 161b6d8ef86SAishwarya Pant milliwatts). 162b6d8ef86SAishwarya Pant 16334433332SMauro Carvalho Chehab time: (RO) The total time spent in this idle state 16434433332SMauro Carvalho Chehab (in microseconds). 165b6d8ef86SAishwarya Pant 166b6d8ef86SAishwarya Pant usage: (RO) Number of times this state was entered (a count). 167b6d8ef86SAishwarya Pant 16804dab58aSRafael J. Wysocki above: (RO) Number of times this state was entered, but the 16934433332SMauro Carvalho Chehab observed CPU idle duration was too short for it 17034433332SMauro Carvalho Chehab (a count). 17104dab58aSRafael J. Wysocki 17204dab58aSRafael J. Wysocki below: (RO) Number of times this state was entered, but the 17334433332SMauro Carvalho Chehab observed CPU idle duration was too long for it 17434433332SMauro Carvalho Chehab (a count). 17534433332SMauro Carvalho Chehab ======== ==== ================================================= 176b6d8ef86SAishwarya Pant 177b6d8ef86SAishwarya PantWhat: /sys/devices/system/cpu/cpuX/cpuidle/stateN/desc 178b6d8ef86SAishwarya PantDate: February 2008 179b6d8ef86SAishwarya PantKernelVersion: v2.6.25 180b6d8ef86SAishwarya PantContact: Linux power management list <linux-pm@vger.kernel.org> 181b6d8ef86SAishwarya PantDescription: 182b6d8ef86SAishwarya Pant (RO) A small description about the idle state (string). 183b6d8ef86SAishwarya Pant 184b6d8ef86SAishwarya Pant 185b6d8ef86SAishwarya PantWhat: /sys/devices/system/cpu/cpuX/cpuidle/stateN/disable 186b6d8ef86SAishwarya PantDate: March 2012 187b6d8ef86SAishwarya PantKernelVersion: v3.10 188b6d8ef86SAishwarya PantContact: Linux power management list <linux-pm@vger.kernel.org> 189b6d8ef86SAishwarya PantDescription: 190b6d8ef86SAishwarya Pant (RW) Option to disable this idle state (bool). The behavior and 191b6d8ef86SAishwarya Pant the effect of the disable variable depends on the implementation 192b6d8ef86SAishwarya Pant of a particular governor. In the ladder governor, for example, 193b6d8ef86SAishwarya Pant it is not coherent, i.e. if one is disabling a light state, then 194b6d8ef86SAishwarya Pant all deeper states are disabled as well, but the disable variable 195b6d8ef86SAishwarya Pant does not reflect it. Likewise, if one enables a deep state but a 196b6d8ef86SAishwarya Pant lighter state still is disabled, then this has no effect. 197b6d8ef86SAishwarya Pant 19875a80267SRafael J. WysockiWhat: /sys/devices/system/cpu/cpuX/cpuidle/stateN/default_status 19975a80267SRafael J. WysockiDate: December 2019 20075a80267SRafael J. WysockiKernelVersion: v5.6 20175a80267SRafael J. WysockiContact: Linux power management list <linux-pm@vger.kernel.org> 20275a80267SRafael J. WysockiDescription: 20375a80267SRafael J. Wysocki (RO) The default status of this state, "enabled" or "disabled". 204b6d8ef86SAishwarya Pant 205b6d8ef86SAishwarya PantWhat: /sys/devices/system/cpu/cpuX/cpuidle/stateN/residency 206b6d8ef86SAishwarya PantDate: March 2014 207b6d8ef86SAishwarya PantKernelVersion: v3.15 208b6d8ef86SAishwarya PantContact: Linux power management list <linux-pm@vger.kernel.org> 209b6d8ef86SAishwarya PantDescription: 210b6d8ef86SAishwarya Pant (RO) Display the target residency i.e. the minimum amount of 211b6d8ef86SAishwarya Pant time (in microseconds) this cpu should spend in this idle state 212b6d8ef86SAishwarya Pant to make the transition worth the effort. 213b6d8ef86SAishwarya Pant 21464bdff69SRafael J. WysockiWhat: /sys/devices/system/cpu/cpuX/cpuidle/stateN/s2idle/ 21564bdff69SRafael J. WysockiDate: March 2018 21664bdff69SRafael J. WysockiKernelVersion: v4.17 21764bdff69SRafael J. WysockiContact: Linux power management list <linux-pm@vger.kernel.org> 21864bdff69SRafael J. WysockiDescription: 21964bdff69SRafael J. Wysocki Idle state usage statistics related to suspend-to-idle. 22064bdff69SRafael J. Wysocki 22164bdff69SRafael J. Wysocki This attribute group is only present for states that can be 22264bdff69SRafael J. Wysocki used in suspend-to-idle with suspended timekeeping. 22364bdff69SRafael J. Wysocki 22464bdff69SRafael J. WysockiWhat: /sys/devices/system/cpu/cpuX/cpuidle/stateN/s2idle/time 22564bdff69SRafael J. WysockiDate: March 2018 22664bdff69SRafael J. WysockiKernelVersion: v4.17 22764bdff69SRafael J. WysockiContact: Linux power management list <linux-pm@vger.kernel.org> 22864bdff69SRafael J. WysockiDescription: 22964bdff69SRafael J. Wysocki Total time spent by the CPU in suspend-to-idle (with scheduler 23064bdff69SRafael J. Wysocki tick suspended) after requesting this state. 23164bdff69SRafael J. Wysocki 23264bdff69SRafael J. WysockiWhat: /sys/devices/system/cpu/cpuX/cpuidle/stateN/s2idle/usage 23364bdff69SRafael J. WysockiDate: March 2018 23464bdff69SRafael J. WysockiKernelVersion: v4.17 23564bdff69SRafael J. WysockiContact: Linux power management list <linux-pm@vger.kernel.org> 23664bdff69SRafael J. WysockiDescription: 23764bdff69SRafael J. Wysocki Total number of times this state has been requested by the CPU 23864bdff69SRafael J. Wysocki while entering suspend-to-idle. 239b6d8ef86SAishwarya Pant 2400cda8b91SAlex ChiangWhat: /sys/devices/system/cpu/cpu#/cpufreq/* 2410cda8b91SAlex ChiangDate: pre-git history 242dec102aaSViresh KumarContact: linux-pm@vger.kernel.org 2430cda8b91SAlex ChiangDescription: Discover and change clock speed of CPUs 2440cda8b91SAlex Chiang 2450cda8b91SAlex Chiang Clock scaling allows you to change the clock speed of the 2460cda8b91SAlex Chiang CPUs on the fly. This is a nice method to save battery 2470cda8b91SAlex Chiang power, because the lower the clock speed, the less power 2480cda8b91SAlex Chiang the CPU consumes. 2490cda8b91SAlex Chiang 2500cda8b91SAlex Chiang There are many knobs to tweak in this directory. 2510cda8b91SAlex Chiang 2520cda8b91SAlex Chiang See files in Documentation/cpu-freq/ for more information. 2530cda8b91SAlex Chiang 2540cda8b91SAlex Chiang 255f4fd3797SLan TianyuWhat: /sys/devices/system/cpu/cpu#/cpufreq/freqdomain_cpus 256f4fd3797SLan TianyuDate: June 2013 257dec102aaSViresh KumarContact: linux-pm@vger.kernel.org 258f4fd3797SLan TianyuDescription: Discover CPUs in the same CPU frequency coordination domain 259f4fd3797SLan Tianyu 260f4fd3797SLan Tianyu freqdomain_cpus is the list of CPUs (online+offline) that share 261f4fd3797SLan Tianyu the same clock/freq domain (possibly at the hardware level). 262f4fd3797SLan Tianyu That information may be hidden from the cpufreq core and the 263f4fd3797SLan Tianyu value of related_cpus may be different from freqdomain_cpus. This 264f4fd3797SLan Tianyu attribute is useful for user space DVFS controllers to get better 265f4fd3797SLan Tianyu power/performance results for platforms using acpi-cpufreq. 266f4fd3797SLan Tianyu 267cfdc589fSIonela Voinescu This file is only present if the acpi-cpufreq or the cppc-cpufreq 268cfdc589fSIonela Voinescu drivers are in use. 269f4fd3797SLan Tianyu 270f4fd3797SLan Tianyu 271eecaaba5SBorislav PetkovWhat: /sys/devices/system/cpu/cpu*/cache/index3/cache_disable_{0,1} 272468727abSAlex ChiangDate: August 2008 273468727abSAlex ChiangKernelVersion: 2.6.27 274ea8e080bSAravind GopalakrishnanContact: Linux kernel mailing list <linux-kernel@vger.kernel.org> 275eecaaba5SBorislav PetkovDescription: Disable L3 cache indices 276468727abSAlex Chiang 277eecaaba5SBorislav Petkov These files exist in every CPU's cache/index3 directory. Each 278eecaaba5SBorislav Petkov cache_disable_{0,1} file corresponds to one disable slot which 279eecaaba5SBorislav Petkov can be used to disable a cache index. Reading from these files 280eecaaba5SBorislav Petkov on a processor with this functionality will return the currently 281eecaaba5SBorislav Petkov disabled index for that node. There is one L3 structure per 282eecaaba5SBorislav Petkov node, or per internal node on MCM machines. Writing a valid 283eecaaba5SBorislav Petkov index to one of these files will cause the specificed cache 284eecaaba5SBorislav Petkov index to be disabled. 285eecaaba5SBorislav Petkov 286eecaaba5SBorislav Petkov All AMD processors with L3 caches provide this functionality. 287eecaaba5SBorislav Petkov For details, see BKDGs at 288*2fa4928aSAnatoly Pugachev https://www.amd.com/en/support/tech-docs?keyword=bios+kernel 289615b7300SAndre Przywara 290615b7300SAndre Przywara 291615b7300SAndre PrzywaraWhat: /sys/devices/system/cpu/cpufreq/boost 292615b7300SAndre PrzywaraDate: August 2012 293615b7300SAndre PrzywaraContact: Linux kernel mailing list <linux-kernel@vger.kernel.org> 294615b7300SAndre PrzywaraDescription: Processor frequency boosting control 295615b7300SAndre Przywara 296615b7300SAndre Przywara This switch controls the boost setting for the whole system. 297615b7300SAndre Przywara Boosting allows the CPU and the firmware to run at a frequency 298615b7300SAndre Przywara beyound it's nominal limit. 29934433332SMauro Carvalho Chehab 3003ba9b1b8STom Saeger More details can be found in 3013ba9b1b8STom Saeger Documentation/admin-guide/pm/cpufreq.rst 302c4fd675fSZhang Yanfei 303c4fd675fSZhang Yanfei 304c4fd675fSZhang YanfeiWhat: /sys/devices/system/cpu/cpu#/crash_notes 305c4fd675fSZhang Yanfei /sys/devices/system/cpu/cpu#/crash_notes_size 306c4fd675fSZhang YanfeiDate: April 2013 307c4fd675fSZhang YanfeiContact: kexec@lists.infradead.org 308c4fd675fSZhang YanfeiDescription: address and size of the percpu note. 309c4fd675fSZhang Yanfei 310c4fd675fSZhang Yanfei crash_notes: the physical address of the memory that holds the 311c4fd675fSZhang Yanfei note of cpu#. 312c4fd675fSZhang Yanfei 313c4fd675fSZhang Yanfei crash_notes_size: size of the note of cpu#. 314fbe299e0SRamkumar Ramachandra 315fbe299e0SRamkumar Ramachandra 316fbe299e0SRamkumar RamachandraWhat: /sys/devices/system/cpu/intel_pstate/max_perf_pct 317fbe299e0SRamkumar Ramachandra /sys/devices/system/cpu/intel_pstate/min_perf_pct 318fbe299e0SRamkumar Ramachandra /sys/devices/system/cpu/intel_pstate/no_turbo 319fbe299e0SRamkumar RamachandraDate: February 2013 320fbe299e0SRamkumar RamachandraContact: linux-pm@vger.kernel.org 321fbe299e0SRamkumar RamachandraDescription: Parameters for the Intel P-state driver 322fbe299e0SRamkumar Ramachandra 323fbe299e0SRamkumar Ramachandra Logic for selecting the current P-state in Intel 324fbe299e0SRamkumar Ramachandra Sandybridge+ processors. The three knobs control 325fbe299e0SRamkumar Ramachandra limits for the P-state that will be requested by the 326fbe299e0SRamkumar Ramachandra driver. 327fbe299e0SRamkumar Ramachandra 328fbe299e0SRamkumar Ramachandra max_perf_pct: limits the maximum P state that will be requested by 329fbe299e0SRamkumar Ramachandra the driver stated as a percentage of the available performance. 330fbe299e0SRamkumar Ramachandra 331fbe299e0SRamkumar Ramachandra min_perf_pct: limits the minimum P state that will be requested by 332fbe299e0SRamkumar Ramachandra the driver stated as a percentage of the available performance. 333fbe299e0SRamkumar Ramachandra 334fbe299e0SRamkumar Ramachandra no_turbo: limits the driver to selecting P states below the turbo 335fbe299e0SRamkumar Ramachandra frequency range. 336fbe299e0SRamkumar Ramachandra 3373ba9b1b8STom Saeger More details can be found in 3383ba9b1b8STom Saeger Documentation/admin-guide/pm/intel_pstate.rst 339246246cbSSudeep Holla 340246246cbSSudeep HollaWhat: /sys/devices/system/cpu/cpu*/cache/index*/<set_of_attributes_mentioned_below> 341246246cbSSudeep HollaDate: July 2014(documented, existed before August 2008) 342246246cbSSudeep HollaContact: Sudeep Holla <sudeep.holla@arm.com> 343246246cbSSudeep Holla Linux kernel mailing list <linux-kernel@vger.kernel.org> 344246246cbSSudeep HollaDescription: Parameters for the CPU cache attributes 345246246cbSSudeep Holla 346246246cbSSudeep Holla allocation_policy: 34734433332SMauro Carvalho Chehab - WriteAllocate: 34834433332SMauro Carvalho Chehab allocate a memory location to a cache line 349246246cbSSudeep Holla on a cache miss because of a write 35034433332SMauro Carvalho Chehab - ReadAllocate: 35134433332SMauro Carvalho Chehab allocate a memory location to a cache line 352246246cbSSudeep Holla on a cache miss because of a read 35334433332SMauro Carvalho Chehab - ReadWriteAllocate: 35434433332SMauro Carvalho Chehab both writeallocate and readallocate 355246246cbSSudeep Holla 35634433332SMauro Carvalho Chehab attributes: 35734433332SMauro Carvalho Chehab LEGACY used only on IA64 and is same as write_policy 358246246cbSSudeep Holla 35934433332SMauro Carvalho Chehab coherency_line_size: 36034433332SMauro Carvalho Chehab the minimum amount of data in bytes that gets 361246246cbSSudeep Holla transferred from memory to cache 362246246cbSSudeep Holla 36334433332SMauro Carvalho Chehab level: 36434433332SMauro Carvalho Chehab the cache hierarchy in the multi-level cache configuration 365246246cbSSudeep Holla 36634433332SMauro Carvalho Chehab number_of_sets: 36734433332SMauro Carvalho Chehab total number of sets in the cache, a set is a 368246246cbSSudeep Holla collection of cache lines with the same cache index 369246246cbSSudeep Holla 37034433332SMauro Carvalho Chehab physical_line_partition: 37134433332SMauro Carvalho Chehab number of physical cache line per cache tag 372246246cbSSudeep Holla 37334433332SMauro Carvalho Chehab shared_cpu_list: 37434433332SMauro Carvalho Chehab the list of logical cpus sharing the cache 375246246cbSSudeep Holla 37634433332SMauro Carvalho Chehab shared_cpu_map: 37734433332SMauro Carvalho Chehab logical cpu mask containing the list of cpus sharing 378246246cbSSudeep Holla the cache 379246246cbSSudeep Holla 38034433332SMauro Carvalho Chehab size: 38134433332SMauro Carvalho Chehab the total cache size in kB 382246246cbSSudeep Holla 383246246cbSSudeep Holla type: 384246246cbSSudeep Holla - Instruction: cache that only holds instructions 385246246cbSSudeep Holla - Data: cache that only caches data 386246246cbSSudeep Holla - Unified: cache that holds both data and instructions 387246246cbSSudeep Holla 38834433332SMauro Carvalho Chehab ways_of_associativity: 38934433332SMauro Carvalho Chehab degree of freedom in placing a particular block 390246246cbSSudeep Holla of memory in the cache 391246246cbSSudeep Holla 392246246cbSSudeep Holla write_policy: 39334433332SMauro Carvalho Chehab - WriteThrough: 39434433332SMauro Carvalho Chehab data is written to both the cache line 395246246cbSSudeep Holla and to the block in the lower-level memory 39634433332SMauro Carvalho Chehab - WriteBack: 39734433332SMauro Carvalho Chehab data is written only to the cache line and 398246246cbSSudeep Holla the modified cache line is written to main 399246246cbSSudeep Holla memory only when it is replaced 4001b028984SShilpasri G Bhat 4011d78dc59STony Luck 4021d78dc59STony LuckWhat: /sys/devices/system/cpu/cpu*/cache/index*/id 4031d78dc59STony LuckDate: September 2016 4041d78dc59STony LuckContact: Linux kernel mailing list <linux-kernel@vger.kernel.org> 4051d78dc59STony LuckDescription: Cache id 4061d78dc59STony Luck 4071d78dc59STony Luck The id provides a unique number for a specific instance of 4081d78dc59STony Luck a cache of a particular type. E.g. there may be a level 4091d78dc59STony Luck 3 unified cache on each socket in a server and we may 4101d78dc59STony Luck assign them ids 0, 1, 2, ... 4111d78dc59STony Luck 4121d78dc59STony Luck Note that id value can be non-contiguous. E.g. level 1 4131d78dc59STony Luck caches typically exist per core, but there may not be a 4141d78dc59STony Luck power of two cores on a socket, so these caches may be 4151d78dc59STony Luck numbered 0, 1, 2, 3, 4, 5, 8, 9, 10, ... 4161d78dc59STony Luck 4171b028984SShilpasri G BhatWhat: /sys/devices/system/cpu/cpuX/cpufreq/throttle_stats 4181b028984SShilpasri G Bhat /sys/devices/system/cpu/cpuX/cpufreq/throttle_stats/turbo_stat 4191b028984SShilpasri G Bhat /sys/devices/system/cpu/cpuX/cpufreq/throttle_stats/sub_turbo_stat 4201b028984SShilpasri G Bhat /sys/devices/system/cpu/cpuX/cpufreq/throttle_stats/unthrottle 4211b028984SShilpasri G Bhat /sys/devices/system/cpu/cpuX/cpufreq/throttle_stats/powercap 4221b028984SShilpasri G Bhat /sys/devices/system/cpu/cpuX/cpufreq/throttle_stats/overtemp 4231b028984SShilpasri G Bhat /sys/devices/system/cpu/cpuX/cpufreq/throttle_stats/supply_fault 4241b028984SShilpasri G Bhat /sys/devices/system/cpu/cpuX/cpufreq/throttle_stats/overcurrent 4251b028984SShilpasri G Bhat /sys/devices/system/cpu/cpuX/cpufreq/throttle_stats/occ_reset 4261b028984SShilpasri G BhatDate: March 2016 4271b028984SShilpasri G BhatContact: Linux kernel mailing list <linux-kernel@vger.kernel.org> 4281b028984SShilpasri G Bhat Linux for PowerPC mailing list <linuxppc-dev@ozlabs.org> 4291b028984SShilpasri G BhatDescription: POWERNV CPUFreq driver's frequency throttle stats directory and 4301b028984SShilpasri G Bhat attributes 4311b028984SShilpasri G Bhat 4321b028984SShilpasri G Bhat 'cpuX/cpufreq/throttle_stats' directory contains the CPU frequency 4331b028984SShilpasri G Bhat throttle stat attributes for the chip. The throttle stats of a cpu 4341b028984SShilpasri G Bhat is common across all the cpus belonging to a chip. Below are the 4351b028984SShilpasri G Bhat throttle attributes exported in the 'throttle_stats' directory: 4361b028984SShilpasri G Bhat 4371b028984SShilpasri G Bhat - turbo_stat : This file gives the total number of times the max 4381b028984SShilpasri G Bhat frequency is throttled to lower frequency in turbo (at and above 4391b028984SShilpasri G Bhat nominal frequency) range of frequencies. 4401b028984SShilpasri G Bhat 4411b028984SShilpasri G Bhat - sub_turbo_stat : This file gives the total number of times the 4421b028984SShilpasri G Bhat max frequency is throttled to lower frequency in sub-turbo(below 4431b028984SShilpasri G Bhat nominal frequency) range of frequencies. 4441b028984SShilpasri G Bhat 4451b028984SShilpasri G Bhat - unthrottle : This file gives the total number of times the max 4461b028984SShilpasri G Bhat frequency is unthrottled after being throttled. 4471b028984SShilpasri G Bhat 4481b028984SShilpasri G Bhat - powercap : This file gives the total number of times the max 4491b028984SShilpasri G Bhat frequency is throttled due to 'Power Capping'. 4501b028984SShilpasri G Bhat 4511b028984SShilpasri G Bhat - overtemp : This file gives the total number of times the max 4521b028984SShilpasri G Bhat frequency is throttled due to 'CPU Over Temperature'. 4531b028984SShilpasri G Bhat 4541b028984SShilpasri G Bhat - supply_fault : This file gives the total number of times the 4551b028984SShilpasri G Bhat max frequency is throttled due to 'Power Supply Failure'. 4561b028984SShilpasri G Bhat 4571b028984SShilpasri G Bhat - overcurrent : This file gives the total number of times the 4581b028984SShilpasri G Bhat max frequency is throttled due to 'Overcurrent'. 4591b028984SShilpasri G Bhat 4601b028984SShilpasri G Bhat - occ_reset : This file gives the total number of times the max 4611b028984SShilpasri G Bhat frequency is throttled due to 'OCC Reset'. 4621b028984SShilpasri G Bhat 4631b028984SShilpasri G Bhat The sysfs attributes representing different throttle reasons like 4641b028984SShilpasri G Bhat powercap, overtemp, supply_fault, overcurrent and occ_reset map to 4651b028984SShilpasri G Bhat the reasons provided by OCC firmware for throttling the frequency. 4661b028984SShilpasri G Bhat 4671b028984SShilpasri G BhatWhat: /sys/devices/system/cpu/cpufreq/policyX/throttle_stats 4681b028984SShilpasri G Bhat /sys/devices/system/cpu/cpufreq/policyX/throttle_stats/turbo_stat 4691b028984SShilpasri G Bhat /sys/devices/system/cpu/cpufreq/policyX/throttle_stats/sub_turbo_stat 4701b028984SShilpasri G Bhat /sys/devices/system/cpu/cpufreq/policyX/throttle_stats/unthrottle 4711b028984SShilpasri G Bhat /sys/devices/system/cpu/cpufreq/policyX/throttle_stats/powercap 4721b028984SShilpasri G Bhat /sys/devices/system/cpu/cpufreq/policyX/throttle_stats/overtemp 4731b028984SShilpasri G Bhat /sys/devices/system/cpu/cpufreq/policyX/throttle_stats/supply_fault 4741b028984SShilpasri G Bhat /sys/devices/system/cpu/cpufreq/policyX/throttle_stats/overcurrent 4751b028984SShilpasri G Bhat /sys/devices/system/cpu/cpufreq/policyX/throttle_stats/occ_reset 4761b028984SShilpasri G BhatDate: March 2016 4771b028984SShilpasri G BhatContact: Linux kernel mailing list <linux-kernel@vger.kernel.org> 4781b028984SShilpasri G Bhat Linux for PowerPC mailing list <linuxppc-dev@ozlabs.org> 4791b028984SShilpasri G BhatDescription: POWERNV CPUFreq driver's frequency throttle stats directory and 4801b028984SShilpasri G Bhat attributes 4811b028984SShilpasri G Bhat 4821b028984SShilpasri G Bhat 'policyX/throttle_stats' directory and all the attributes are same as 4831b028984SShilpasri G Bhat the /sys/devices/system/cpu/cpuX/cpufreq/throttle_stats directory and 4841b028984SShilpasri G Bhat attributes which give the frequency throttle information of the chip. 485f8d9f924SSteve Capper 486f8d9f924SSteve CapperWhat: /sys/devices/system/cpu/cpuX/regs/ 487f8d9f924SSteve Capper /sys/devices/system/cpu/cpuX/regs/identification/ 488f8d9f924SSteve Capper /sys/devices/system/cpu/cpuX/regs/identification/midr_el1 489f8d9f924SSteve Capper /sys/devices/system/cpu/cpuX/regs/identification/revidr_el1 490f8d9f924SSteve CapperDate: June 2016 491f8d9f924SSteve CapperContact: Linux ARM Kernel Mailing list <linux-arm-kernel@lists.infradead.org> 492f8d9f924SSteve CapperDescription: AArch64 CPU registers 49334433332SMauro Carvalho Chehab 494f8d9f924SSteve Capper 'identification' directory exposes the CPU ID registers for 495f8d9f924SSteve Capper identifying model and revision of the CPU. 496a2b60670SJuri Lelli 497a2b60670SJuri LelliWhat: /sys/devices/system/cpu/cpu#/cpu_capacity 498a2b60670SJuri LelliDate: December 2016 499a2b60670SJuri LelliContact: Linux kernel mailing list <linux-kernel@vger.kernel.org> 500a2b60670SJuri LelliDescription: information about CPUs heterogeneity. 501a2b60670SJuri Lelli 502a2b60670SJuri Lelli cpu_capacity: capacity of cpu#. 50387590ce6SThomas Gleixner 50487590ce6SThomas GleixnerWhat: /sys/devices/system/cpu/vulnerabilities 50587590ce6SThomas Gleixner /sys/devices/system/cpu/vulnerabilities/meltdown 50687590ce6SThomas Gleixner /sys/devices/system/cpu/vulnerabilities/spectre_v1 50787590ce6SThomas Gleixner /sys/devices/system/cpu/vulnerabilities/spectre_v2 508c456442cSKonrad Rzeszutek Wilk /sys/devices/system/cpu/vulnerabilities/spec_store_bypass 509d90a7a0eSJiri Kosina /sys/devices/system/cpu/vulnerabilities/l1tf 5108a4b06d3SThomas Gleixner /sys/devices/system/cpu/vulnerabilities/mds 5117e5b3c26SMark Gross /sys/devices/system/cpu/vulnerabilities/srbds 512a7a248c5SPawan Gupta /sys/devices/system/cpu/vulnerabilities/tsx_async_abort 513db4d30fbSVineela Tummalapalli /sys/devices/system/cpu/vulnerabilities/itlb_multihit 5149ecccfaaSDavid WoodhouseDate: January 2018 51587590ce6SThomas GleixnerContact: Linux kernel mailing list <linux-kernel@vger.kernel.org> 51687590ce6SThomas GleixnerDescription: Information about CPU vulnerabilities 51787590ce6SThomas Gleixner 51887590ce6SThomas Gleixner The files are named after the code names of CPU 51987590ce6SThomas Gleixner vulnerabilities. The output of those files reflects the 52087590ce6SThomas Gleixner state of the CPUs in the system. Possible output values: 52187590ce6SThomas Gleixner 52234433332SMauro Carvalho Chehab ================ ============================================== 52387590ce6SThomas Gleixner "Not affected" CPU is not affected by the vulnerability 52487590ce6SThomas Gleixner "Vulnerable" CPU is affected and no mitigation in effect 5259ecccfaaSDavid Woodhouse "Mitigation: $M" CPU is affected and mitigation $M is in effect 52634433332SMauro Carvalho Chehab ================ ============================================== 52705736e4aSThomas Gleixner 5285999bbe7SThomas Gleixner See also: Documentation/admin-guide/hw-vuln/index.rst 529d90a7a0eSJiri Kosina 53005736e4aSThomas GleixnerWhat: /sys/devices/system/cpu/smt 53105736e4aSThomas Gleixner /sys/devices/system/cpu/smt/active 53205736e4aSThomas Gleixner /sys/devices/system/cpu/smt/control 53305736e4aSThomas GleixnerDate: June 2018 53405736e4aSThomas GleixnerContact: Linux kernel mailing list <linux-kernel@vger.kernel.org> 53505736e4aSThomas GleixnerDescription: Control Symetric Multi Threading (SMT) 53605736e4aSThomas Gleixner 53705736e4aSThomas Gleixner active: Tells whether SMT is active (enabled and siblings online) 53805736e4aSThomas Gleixner 53905736e4aSThomas Gleixner control: Read/write interface to control SMT. Possible 54005736e4aSThomas Gleixner values: 54105736e4aSThomas Gleixner 54234433332SMauro Carvalho Chehab ================ ========================================= 54305736e4aSThomas Gleixner "on" SMT is enabled 54405736e4aSThomas Gleixner "off" SMT is disabled 54505736e4aSThomas Gleixner "forceoff" SMT is force disabled. Cannot be changed. 54605736e4aSThomas Gleixner "notsupported" SMT is not supported by the CPU 547de7b77e5SJosh Poimboeuf "notimplemented" SMT runtime toggling is not 548de7b77e5SJosh Poimboeuf implemented for the architecture 54934433332SMauro Carvalho Chehab ================ ========================================= 55005736e4aSThomas Gleixner 55105736e4aSThomas Gleixner If control status is "forceoff" or "notsupported" writes 55205736e4aSThomas Gleixner are rejected. 553b9c273baSRafael J. Wysocki 554b9c273baSRafael J. WysockiWhat: /sys/devices/system/cpu/cpu#/power/energy_perf_bias 555b9c273baSRafael J. WysockiDate: March 2019 556b9c273baSRafael J. WysockiContact: linux-pm@vger.kernel.org 557b9c273baSRafael J. WysockiDescription: Intel Energy and Performance Bias Hint (EPB) 558b9c273baSRafael J. Wysocki 559b9c273baSRafael J. Wysocki EPB for the given CPU in a sliding scale 0 - 15, where a value 560b9c273baSRafael J. Wysocki of 0 corresponds to a hint preference for highest performance 561b9c273baSRafael J. Wysocki and a value of 15 corresponds to the maximum energy savings. 562b9c273baSRafael J. Wysocki 563b9c273baSRafael J. Wysocki In order to change the EPB value for the CPU, write either 564b9c273baSRafael J. Wysocki a number in the 0 - 15 sliding scale above, or one of the 565b9c273baSRafael J. Wysocki strings: "performance", "balance-performance", "normal", 566b9c273baSRafael J. Wysocki "balance-power", "power" (that represent values reflected by 567b9c273baSRafael J. Wysocki their meaning), to this attribute. 568b9c273baSRafael J. Wysocki 569b9c273baSRafael J. Wysocki This attribute is present for all online CPUs supporting the 570b9c273baSRafael J. Wysocki Intel EPB feature. 571203dffacSFenghua Yu 572203dffacSFenghua YuWhat: /sys/devices/system/cpu/umwait_control 573203dffacSFenghua Yu /sys/devices/system/cpu/umwait_control/enable_c02 574203dffacSFenghua Yu /sys/devices/system/cpu/umwait_control/max_time 575203dffacSFenghua YuDate: May 2019 576203dffacSFenghua YuContact: Linux kernel mailing list <linux-kernel@vger.kernel.org> 577203dffacSFenghua YuDescription: Umwait control 578203dffacSFenghua Yu 579203dffacSFenghua Yu enable_c02: Read/write interface to control umwait C0.2 state 580203dffacSFenghua Yu Read returns C0.2 state status: 581203dffacSFenghua Yu 0: C0.2 is disabled 582203dffacSFenghua Yu 1: C0.2 is enabled 583203dffacSFenghua Yu 584203dffacSFenghua Yu Write 'y' or '1' or 'on' to enable C0.2 state. 585203dffacSFenghua Yu Write 'n' or '0' or 'off' to disable C0.2 state. 586203dffacSFenghua Yu 587203dffacSFenghua Yu The interface is case insensitive. 588203dffacSFenghua Yu 589203dffacSFenghua Yu max_time: Read/write interface to control umwait maximum time 590203dffacSFenghua Yu in TSC-quanta that the CPU can reside in either C0.1 591203dffacSFenghua Yu or C0.2 state. The time is an unsigned 32-bit number. 592203dffacSFenghua Yu Note that a value of zero means there is no limit. 593203dffacSFenghua Yu Low order two bits must be zero. 594734560acSRyan Grimm 595734560acSRyan GrimmWhat: /sys/devices/system/cpu/svm 596734560acSRyan GrimmDate: August 2019 597734560acSRyan GrimmContact: Linux kernel mailing list <linux-kernel@vger.kernel.org> 598734560acSRyan Grimm Linux for PowerPC mailing list <linuxppc-dev@ozlabs.org> 599734560acSRyan GrimmDescription: Secure Virtual Machine 600734560acSRyan Grimm 601734560acSRyan Grimm If 1, it means the system is using the Protected Execution 602734560acSRyan Grimm Facility in POWER9 and newer processors. i.e., it is a Secure 603734560acSRyan Grimm Virtual Machine. 604bde752c3SGautham R. Shenoy 605bde752c3SGautham R. ShenoyWhat: /sys/devices/system/cpu/cpuX/purr 606bde752c3SGautham R. ShenoyDate: Apr 2005 607bde752c3SGautham R. ShenoyContact: Linux for PowerPC mailing list <linuxppc-dev@ozlabs.org> 608bde752c3SGautham R. ShenoyDescription: PURR ticks for this CPU since the system boot. 609bde752c3SGautham R. Shenoy 610bde752c3SGautham R. Shenoy The Processor Utilization Resources Register (PURR) is 611bde752c3SGautham R. Shenoy a 64-bit counter which provides an estimate of the 612bde752c3SGautham R. Shenoy resources used by the CPU thread. The contents of this 613bde752c3SGautham R. Shenoy register increases monotonically. This sysfs interface 614bde752c3SGautham R. Shenoy exposes the number of PURR ticks for cpuX. 615bde752c3SGautham R. Shenoy 616bde752c3SGautham R. ShenoyWhat: /sys/devices/system/cpu/cpuX/spurr 617bde752c3SGautham R. ShenoyDate: Dec 2006 618bde752c3SGautham R. ShenoyContact: Linux for PowerPC mailing list <linuxppc-dev@ozlabs.org> 619bde752c3SGautham R. ShenoyDescription: SPURR ticks for this CPU since the system boot. 620bde752c3SGautham R. Shenoy 621bde752c3SGautham R. Shenoy The Scaled Processor Utilization Resources Register 622bde752c3SGautham R. Shenoy (SPURR) is a 64-bit counter that provides a frequency 623bde752c3SGautham R. Shenoy invariant estimate of the resources used by the CPU 624bde752c3SGautham R. Shenoy thread. The contents of this register increases 625bde752c3SGautham R. Shenoy monotonically. This sysfs interface exposes the number 626bde752c3SGautham R. Shenoy of SPURR ticks for cpuX. 627bde752c3SGautham R. Shenoy 628bde752c3SGautham R. ShenoyWhat: /sys/devices/system/cpu/cpuX/idle_purr 629bde752c3SGautham R. ShenoyDate: Apr 2020 630bde752c3SGautham R. ShenoyContact: Linux for PowerPC mailing list <linuxppc-dev@ozlabs.org> 631bde752c3SGautham R. ShenoyDescription: PURR ticks for cpuX when it was idle. 632bde752c3SGautham R. Shenoy 633bde752c3SGautham R. Shenoy This sysfs interface exposes the number of PURR ticks 634bde752c3SGautham R. Shenoy for cpuX when it was idle. 635bde752c3SGautham R. Shenoy 636bde752c3SGautham R. ShenoyWhat: /sys/devices/system/cpu/cpuX/idle_spurr 637bde752c3SGautham R. ShenoyDate: Apr 2020 638bde752c3SGautham R. ShenoyContact: Linux for PowerPC mailing list <linuxppc-dev@ozlabs.org> 639bde752c3SGautham R. ShenoyDescription: SPURR ticks for cpuX when it was idle. 640bde752c3SGautham R. Shenoy 641bde752c3SGautham R. Shenoy This sysfs interface exposes the number of SPURR ticks 642bde752c3SGautham R. Shenoy for cpuX when it was idle. 643