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 10abcb948dSMauro Carvalho Chehab /sys/devices/system/cpu/cpuX/ 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 written to the file to remove CPU's 5412633e80SNathan Fontenot is architecture specific. 55657348a0SAlex Chiang 56abcb948dSMauro Carvalho ChehabWhat: /sys/devices/system/cpu/cpuX/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 70abcb948dSMauro Carvalho ChehabWhat: /sys/devices/system/cpu/cpuX/topology/core_id 71abcb948dSMauro Carvalho Chehab /sys/devices/system/cpu/cpuX/topology/core_siblings 72abcb948dSMauro Carvalho Chehab /sys/devices/system/cpu/cpuX/topology/core_siblings_list 73abcb948dSMauro Carvalho Chehab /sys/devices/system/cpu/cpuX/topology/physical_package_id 74abcb948dSMauro Carvalho Chehab /sys/devices/system/cpu/cpuX/topology/thread_siblings 75abcb948dSMauro Carvalho Chehab /sys/devices/system/cpu/cpuX/topology/thread_siblings_list 76ab28e944STony Luck /sys/devices/system/cpu/cpuX/topology/ppin 77663fb2fcSAlex ChiangDate: December 2008 78663fb2fcSAlex ChiangContact: Linux kernel mailing list <linux-kernel@vger.kernel.org> 79663fb2fcSAlex ChiangDescription: CPU topology files that describe a logical CPU's relationship 80663fb2fcSAlex Chiang to other cores and threads in the same physical package. 81663fb2fcSAlex Chiang 82abcb948dSMauro Carvalho Chehab One cpuX directory is created per logical CPU in the system, 83663fb2fcSAlex Chiang e.g. /sys/devices/system/cpu/cpu42/. 84663fb2fcSAlex Chiang 85663fb2fcSAlex Chiang Briefly, the files above are: 86663fb2fcSAlex Chiang 87abcb948dSMauro Carvalho Chehab core_id: the CPU core ID of cpuX. Typically it is the 88663fb2fcSAlex Chiang hardware platform's identifier (rather than the kernel's). 89663fb2fcSAlex Chiang The actual value is architecture and platform dependent. 90663fb2fcSAlex Chiang 91abcb948dSMauro Carvalho Chehab core_siblings: internal kernel map of cpuX's hardware threads 92663fb2fcSAlex Chiang within the same physical_package_id. 93663fb2fcSAlex Chiang 94663fb2fcSAlex Chiang core_siblings_list: human-readable list of the logical CPU 95abcb948dSMauro Carvalho Chehab numbers within the same physical_package_id as cpuX. 96663fb2fcSAlex Chiang 97abcb948dSMauro Carvalho Chehab physical_package_id: physical package id of cpuX. Typically 98663fb2fcSAlex Chiang corresponds to a physical socket number, but the actual value 99663fb2fcSAlex Chiang is architecture and platform dependent. 100663fb2fcSAlex Chiang 101abcb948dSMauro Carvalho Chehab thread_siblings: internal kernel map of cpuX's hardware 102abcb948dSMauro Carvalho Chehab threads within the same core as cpuX 103663fb2fcSAlex Chiang 104abcb948dSMauro Carvalho Chehab thread_siblings_list: human-readable list of cpuX's hardware 105abcb948dSMauro Carvalho Chehab threads within the same core as cpuX 106663fb2fcSAlex Chiang 107ab28e944STony Luck ppin: human-readable Protected Processor Identification 108ab28e944STony Luck Number of the socket the cpu# belongs to. There should be 109ab28e944STony Luck one per physical_package_id. File is readable only to 110ab28e944STony Luck admin. 111ab28e944STony Luck 1124f4cfa6cSMauro Carvalho Chehab See Documentation/admin-guide/cputopology.rst for more information. 113663fb2fcSAlex Chiang 114663fb2fcSAlex Chiang 1157395683aSHanjun GuoWhat: /sys/devices/system/cpu/cpuidle/available_governors 1167395683aSHanjun Guo /sys/devices/system/cpu/cpuidle/current_driver 117b6d8ef86SAishwarya Pant /sys/devices/system/cpu/cpuidle/current_governor 1187395683aSHanjun Guo /sys/devices/system/cpu/cpuidle/current_governer_ro 119c1fb5c47SAlex ChiangDate: September 2007 120c1fb5c47SAlex ChiangContact: Linux kernel mailing list <linux-kernel@vger.kernel.org> 121c1fb5c47SAlex ChiangDescription: Discover cpuidle policy and mechanism 122c1fb5c47SAlex Chiang 123c1fb5c47SAlex Chiang Various CPUs today support multiple idle levels that are 124c1fb5c47SAlex Chiang differentiated by varying exit latencies and power 125c1fb5c47SAlex Chiang consumption during idle. 126c1fb5c47SAlex Chiang 127c1fb5c47SAlex Chiang Idle policy (governor) is differentiated from idle mechanism 1287395683aSHanjun Guo (driver). 129b6d8ef86SAishwarya Pant 130b6d8ef86SAishwarya Pant available_governors: (RO) displays a space separated list of 1317395683aSHanjun Guo available governors. 1327395683aSHanjun Guo 1337395683aSHanjun Guo current_driver: (RO) displays current idle mechanism. 134b6d8ef86SAishwarya Pant 135b6d8ef86SAishwarya Pant current_governor: (RW) displays current idle policy. Users can 136b6d8ef86SAishwarya Pant switch the governor at runtime by writing to this file. 137c1fb5c47SAlex Chiang 1387395683aSHanjun Guo current_governor_ro: (RO) displays current idle policy. 1397395683aSHanjun Guo 140671c3095SMauro Carvalho Chehab See Documentation/admin-guide/pm/cpuidle.rst and 141671c3095SMauro Carvalho Chehab Documentation/driver-api/pm/cpuidle.rst for more information. 142c1fb5c47SAlex Chiang 143c1fb5c47SAlex Chiang 14426d6ba2fSMauro Carvalho ChehabWhat: /sys/devices/system/cpu/cpuX/cpuidle/state<N>/name 145b6d8ef86SAishwarya Pant /sys/devices/system/cpu/cpuX/cpuidle/stateN/latency 146b6d8ef86SAishwarya Pant /sys/devices/system/cpu/cpuX/cpuidle/stateN/power 147b6d8ef86SAishwarya Pant /sys/devices/system/cpu/cpuX/cpuidle/stateN/time 148b6d8ef86SAishwarya Pant /sys/devices/system/cpu/cpuX/cpuidle/stateN/usage 14904dab58aSRafael J. Wysocki /sys/devices/system/cpu/cpuX/cpuidle/stateN/above 15004dab58aSRafael J. Wysocki /sys/devices/system/cpu/cpuX/cpuidle/stateN/below 151b6d8ef86SAishwarya PantDate: September 2007 152b6d8ef86SAishwarya PantKernelVersion: v2.6.24 153b6d8ef86SAishwarya PantContact: Linux power management list <linux-pm@vger.kernel.org> 154b6d8ef86SAishwarya PantDescription: 155b6d8ef86SAishwarya Pant The directory /sys/devices/system/cpu/cpuX/cpuidle contains per 156b6d8ef86SAishwarya Pant logical CPU specific cpuidle information for each online cpu X. 157b6d8ef86SAishwarya Pant The processor idle states which are available for use have the 158b6d8ef86SAishwarya Pant following attributes: 159b6d8ef86SAishwarya Pant 16034433332SMauro Carvalho Chehab ======== ==== ================================================= 161b6d8ef86SAishwarya Pant name: (RO) Name of the idle state (string). 162b6d8ef86SAishwarya Pant 163b6d8ef86SAishwarya Pant latency: (RO) The latency to exit out of this idle state (in 164b6d8ef86SAishwarya Pant microseconds). 165b6d8ef86SAishwarya Pant 166b6d8ef86SAishwarya Pant power: (RO) The power consumed while in this idle state (in 167b6d8ef86SAishwarya Pant milliwatts). 168b6d8ef86SAishwarya Pant 16934433332SMauro Carvalho Chehab time: (RO) The total time spent in this idle state 17034433332SMauro Carvalho Chehab (in microseconds). 171b6d8ef86SAishwarya Pant 172b6d8ef86SAishwarya Pant usage: (RO) Number of times this state was entered (a count). 173b6d8ef86SAishwarya Pant 17404dab58aSRafael J. Wysocki above: (RO) Number of times this state was entered, but the 17534433332SMauro Carvalho Chehab observed CPU idle duration was too short for it 17634433332SMauro Carvalho Chehab (a count). 17704dab58aSRafael J. Wysocki 17804dab58aSRafael J. Wysocki below: (RO) Number of times this state was entered, but the 17934433332SMauro Carvalho Chehab observed CPU idle duration was too long for it 18034433332SMauro Carvalho Chehab (a count). 18134433332SMauro Carvalho Chehab ======== ==== ================================================= 182b6d8ef86SAishwarya Pant 18326d6ba2fSMauro Carvalho ChehabWhat: /sys/devices/system/cpu/cpuX/cpuidle/state<N>/desc 184b6d8ef86SAishwarya PantDate: February 2008 185b6d8ef86SAishwarya PantKernelVersion: v2.6.25 186b6d8ef86SAishwarya PantContact: Linux power management list <linux-pm@vger.kernel.org> 187b6d8ef86SAishwarya PantDescription: 188b6d8ef86SAishwarya Pant (RO) A small description about the idle state (string). 189b6d8ef86SAishwarya Pant 190b6d8ef86SAishwarya Pant 19126d6ba2fSMauro Carvalho ChehabWhat: /sys/devices/system/cpu/cpuX/cpuidle/state<N>/disable 192b6d8ef86SAishwarya PantDate: March 2012 193b6d8ef86SAishwarya PantKernelVersion: v3.10 194b6d8ef86SAishwarya PantContact: Linux power management list <linux-pm@vger.kernel.org> 195b6d8ef86SAishwarya PantDescription: 196b6d8ef86SAishwarya Pant (RW) Option to disable this idle state (bool). The behavior and 197b6d8ef86SAishwarya Pant the effect of the disable variable depends on the implementation 198b6d8ef86SAishwarya Pant of a particular governor. In the ladder governor, for example, 199b6d8ef86SAishwarya Pant it is not coherent, i.e. if one is disabling a light state, then 200b6d8ef86SAishwarya Pant all deeper states are disabled as well, but the disable variable 201b6d8ef86SAishwarya Pant does not reflect it. Likewise, if one enables a deep state but a 202b6d8ef86SAishwarya Pant lighter state still is disabled, then this has no effect. 203b6d8ef86SAishwarya Pant 20426d6ba2fSMauro Carvalho ChehabWhat: /sys/devices/system/cpu/cpuX/cpuidle/state<N>/default_status 20575a80267SRafael J. WysockiDate: December 2019 20675a80267SRafael J. WysockiKernelVersion: v5.6 20775a80267SRafael J. WysockiContact: Linux power management list <linux-pm@vger.kernel.org> 20875a80267SRafael J. WysockiDescription: 20975a80267SRafael J. Wysocki (RO) The default status of this state, "enabled" or "disabled". 210b6d8ef86SAishwarya Pant 21126d6ba2fSMauro Carvalho ChehabWhat: /sys/devices/system/cpu/cpuX/cpuidle/state<N>/residency 212b6d8ef86SAishwarya PantDate: March 2014 213b6d8ef86SAishwarya PantKernelVersion: v3.15 214b6d8ef86SAishwarya PantContact: Linux power management list <linux-pm@vger.kernel.org> 215b6d8ef86SAishwarya PantDescription: 216b6d8ef86SAishwarya Pant (RO) Display the target residency i.e. the minimum amount of 217b6d8ef86SAishwarya Pant time (in microseconds) this cpu should spend in this idle state 218b6d8ef86SAishwarya Pant to make the transition worth the effort. 219b6d8ef86SAishwarya Pant 22026d6ba2fSMauro Carvalho ChehabWhat: /sys/devices/system/cpu/cpuX/cpuidle/state<N>/s2idle/ 22164bdff69SRafael J. WysockiDate: March 2018 22264bdff69SRafael J. WysockiKernelVersion: v4.17 22364bdff69SRafael J. WysockiContact: Linux power management list <linux-pm@vger.kernel.org> 22464bdff69SRafael J. WysockiDescription: 22564bdff69SRafael J. Wysocki Idle state usage statistics related to suspend-to-idle. 22664bdff69SRafael J. Wysocki 22764bdff69SRafael J. Wysocki This attribute group is only present for states that can be 22864bdff69SRafael J. Wysocki used in suspend-to-idle with suspended timekeeping. 22964bdff69SRafael J. Wysocki 23026d6ba2fSMauro Carvalho ChehabWhat: /sys/devices/system/cpu/cpuX/cpuidle/state<N>/s2idle/time 23164bdff69SRafael J. WysockiDate: March 2018 23264bdff69SRafael J. WysockiKernelVersion: v4.17 23364bdff69SRafael J. WysockiContact: Linux power management list <linux-pm@vger.kernel.org> 23464bdff69SRafael J. WysockiDescription: 23564bdff69SRafael J. Wysocki Total time spent by the CPU in suspend-to-idle (with scheduler 23664bdff69SRafael J. Wysocki tick suspended) after requesting this state. 23764bdff69SRafael J. Wysocki 23826d6ba2fSMauro Carvalho ChehabWhat: /sys/devices/system/cpu/cpuX/cpuidle/state<N>/s2idle/usage 23964bdff69SRafael J. WysockiDate: March 2018 24064bdff69SRafael J. WysockiKernelVersion: v4.17 24164bdff69SRafael J. WysockiContact: Linux power management list <linux-pm@vger.kernel.org> 24264bdff69SRafael J. WysockiDescription: 24364bdff69SRafael J. Wysocki Total number of times this state has been requested by the CPU 24464bdff69SRafael J. Wysocki while entering suspend-to-idle. 245b6d8ef86SAishwarya Pant 246abcb948dSMauro Carvalho ChehabWhat: /sys/devices/system/cpu/cpuX/cpufreq/* 2470cda8b91SAlex ChiangDate: pre-git history 248dec102aaSViresh KumarContact: linux-pm@vger.kernel.org 2490cda8b91SAlex ChiangDescription: Discover and change clock speed of CPUs 2500cda8b91SAlex Chiang 2510cda8b91SAlex Chiang Clock scaling allows you to change the clock speed of the 2520cda8b91SAlex Chiang CPUs on the fly. This is a nice method to save battery 2530cda8b91SAlex Chiang power, because the lower the clock speed, the less power 2540cda8b91SAlex Chiang the CPU consumes. 2550cda8b91SAlex Chiang 2560cda8b91SAlex Chiang There are many knobs to tweak in this directory. 2570cda8b91SAlex Chiang 2580cda8b91SAlex Chiang See files in Documentation/cpu-freq/ for more information. 2590cda8b91SAlex Chiang 2600cda8b91SAlex Chiang 261abcb948dSMauro Carvalho ChehabWhat: /sys/devices/system/cpu/cpuX/cpufreq/freqdomain_cpus 262f4fd3797SLan TianyuDate: June 2013 263dec102aaSViresh KumarContact: linux-pm@vger.kernel.org 264f4fd3797SLan TianyuDescription: Discover CPUs in the same CPU frequency coordination domain 265f4fd3797SLan Tianyu 266f4fd3797SLan Tianyu freqdomain_cpus is the list of CPUs (online+offline) that share 267f4fd3797SLan Tianyu the same clock/freq domain (possibly at the hardware level). 268f4fd3797SLan Tianyu That information may be hidden from the cpufreq core and the 269f4fd3797SLan Tianyu value of related_cpus may be different from freqdomain_cpus. This 270f4fd3797SLan Tianyu attribute is useful for user space DVFS controllers to get better 271f4fd3797SLan Tianyu power/performance results for platforms using acpi-cpufreq. 272f4fd3797SLan Tianyu 273cfdc589fSIonela Voinescu This file is only present if the acpi-cpufreq or the cppc-cpufreq 274cfdc589fSIonela Voinescu drivers are in use. 275f4fd3797SLan Tianyu 276f4fd3797SLan Tianyu 277eecaaba5SBorislav PetkovWhat: /sys/devices/system/cpu/cpu*/cache/index3/cache_disable_{0,1} 278468727abSAlex ChiangDate: August 2008 279468727abSAlex ChiangKernelVersion: 2.6.27 280ea8e080bSAravind GopalakrishnanContact: Linux kernel mailing list <linux-kernel@vger.kernel.org> 281eecaaba5SBorislav PetkovDescription: Disable L3 cache indices 282468727abSAlex Chiang 283eecaaba5SBorislav Petkov These files exist in every CPU's cache/index3 directory. Each 284eecaaba5SBorislav Petkov cache_disable_{0,1} file corresponds to one disable slot which 285eecaaba5SBorislav Petkov can be used to disable a cache index. Reading from these files 286eecaaba5SBorislav Petkov on a processor with this functionality will return the currently 287eecaaba5SBorislav Petkov disabled index for that node. There is one L3 structure per 288eecaaba5SBorislav Petkov node, or per internal node on MCM machines. Writing a valid 2893e42d1deSCarlos Bilbao index to one of these files will cause the specified cache 290eecaaba5SBorislav Petkov index to be disabled. 291eecaaba5SBorislav Petkov 292eecaaba5SBorislav Petkov All AMD processors with L3 caches provide this functionality. 293eecaaba5SBorislav Petkov For details, see BKDGs at 2942fa4928aSAnatoly Pugachev https://www.amd.com/en/support/tech-docs?keyword=bios+kernel 295615b7300SAndre Przywara 296615b7300SAndre Przywara 297615b7300SAndre PrzywaraWhat: /sys/devices/system/cpu/cpufreq/boost 298615b7300SAndre PrzywaraDate: August 2012 299615b7300SAndre PrzywaraContact: Linux kernel mailing list <linux-kernel@vger.kernel.org> 300615b7300SAndre PrzywaraDescription: Processor frequency boosting control 301615b7300SAndre Przywara 302615b7300SAndre Przywara This switch controls the boost setting for the whole system. 303615b7300SAndre Przywara Boosting allows the CPU and the firmware to run at a frequency 3043e42d1deSCarlos Bilbao beyond it's nominal limit. 30534433332SMauro Carvalho Chehab 3063ba9b1b8STom Saeger More details can be found in 3073ba9b1b8STom Saeger Documentation/admin-guide/pm/cpufreq.rst 308c4fd675fSZhang Yanfei 309c4fd675fSZhang Yanfei 310abcb948dSMauro Carvalho ChehabWhat: /sys/devices/system/cpu/cpuX/crash_notes 311abcb948dSMauro Carvalho Chehab /sys/devices/system/cpu/cpuX/crash_notes_size 312c4fd675fSZhang YanfeiDate: April 2013 313c4fd675fSZhang YanfeiContact: kexec@lists.infradead.org 314c4fd675fSZhang YanfeiDescription: address and size of the percpu note. 315c4fd675fSZhang Yanfei 316c4fd675fSZhang Yanfei crash_notes: the physical address of the memory that holds the 317abcb948dSMauro Carvalho Chehab note of cpuX. 318c4fd675fSZhang Yanfei 319abcb948dSMauro Carvalho Chehab crash_notes_size: size of the note of cpuX. 320fbe299e0SRamkumar Ramachandra 321fbe299e0SRamkumar Ramachandra 322fbe299e0SRamkumar RamachandraWhat: /sys/devices/system/cpu/intel_pstate/max_perf_pct 323fbe299e0SRamkumar Ramachandra /sys/devices/system/cpu/intel_pstate/min_perf_pct 324fbe299e0SRamkumar Ramachandra /sys/devices/system/cpu/intel_pstate/no_turbo 325fbe299e0SRamkumar RamachandraDate: February 2013 326fbe299e0SRamkumar RamachandraContact: linux-pm@vger.kernel.org 327fbe299e0SRamkumar RamachandraDescription: Parameters for the Intel P-state driver 328fbe299e0SRamkumar Ramachandra 329fbe299e0SRamkumar Ramachandra Logic for selecting the current P-state in Intel 330fbe299e0SRamkumar Ramachandra Sandybridge+ processors. The three knobs control 331fbe299e0SRamkumar Ramachandra limits for the P-state that will be requested by the 332fbe299e0SRamkumar Ramachandra driver. 333fbe299e0SRamkumar Ramachandra 334fbe299e0SRamkumar Ramachandra max_perf_pct: limits the maximum P state that will be requested by 335fbe299e0SRamkumar Ramachandra the driver stated as a percentage of the available performance. 336fbe299e0SRamkumar Ramachandra 337fbe299e0SRamkumar Ramachandra min_perf_pct: limits the minimum P state that will be requested by 338fbe299e0SRamkumar Ramachandra the driver stated as a percentage of the available performance. 339fbe299e0SRamkumar Ramachandra 340fbe299e0SRamkumar Ramachandra no_turbo: limits the driver to selecting P states below the turbo 341fbe299e0SRamkumar Ramachandra frequency range. 342fbe299e0SRamkumar Ramachandra 3433ba9b1b8STom Saeger More details can be found in 3443ba9b1b8STom Saeger Documentation/admin-guide/pm/intel_pstate.rst 345246246cbSSudeep Holla 346246246cbSSudeep HollaWhat: /sys/devices/system/cpu/cpu*/cache/index*/<set_of_attributes_mentioned_below> 347246246cbSSudeep HollaDate: July 2014(documented, existed before August 2008) 348246246cbSSudeep HollaContact: Sudeep Holla <sudeep.holla@arm.com> 349246246cbSSudeep Holla Linux kernel mailing list <linux-kernel@vger.kernel.org> 350246246cbSSudeep HollaDescription: Parameters for the CPU cache attributes 351246246cbSSudeep Holla 352246246cbSSudeep Holla allocation_policy: 35334433332SMauro Carvalho Chehab - WriteAllocate: 35434433332SMauro Carvalho Chehab allocate a memory location to a cache line 355246246cbSSudeep Holla on a cache miss because of a write 35634433332SMauro Carvalho Chehab - ReadAllocate: 35734433332SMauro Carvalho Chehab allocate a memory location to a cache line 358246246cbSSudeep Holla on a cache miss because of a read 35934433332SMauro Carvalho Chehab - ReadWriteAllocate: 36034433332SMauro Carvalho Chehab both writeallocate and readallocate 361246246cbSSudeep Holla 36234433332SMauro Carvalho Chehab attributes: 36334433332SMauro Carvalho Chehab LEGACY used only on IA64 and is same as write_policy 364246246cbSSudeep Holla 36534433332SMauro Carvalho Chehab coherency_line_size: 36634433332SMauro Carvalho Chehab the minimum amount of data in bytes that gets 367246246cbSSudeep Holla transferred from memory to cache 368246246cbSSudeep Holla 36934433332SMauro Carvalho Chehab level: 37034433332SMauro Carvalho Chehab the cache hierarchy in the multi-level cache configuration 371246246cbSSudeep Holla 37234433332SMauro Carvalho Chehab number_of_sets: 37334433332SMauro Carvalho Chehab total number of sets in the cache, a set is a 374246246cbSSudeep Holla collection of cache lines with the same cache index 375246246cbSSudeep Holla 37634433332SMauro Carvalho Chehab physical_line_partition: 37734433332SMauro Carvalho Chehab number of physical cache line per cache tag 378246246cbSSudeep Holla 37934433332SMauro Carvalho Chehab shared_cpu_list: 38034433332SMauro Carvalho Chehab the list of logical cpus sharing the cache 381246246cbSSudeep Holla 38234433332SMauro Carvalho Chehab shared_cpu_map: 38334433332SMauro Carvalho Chehab logical cpu mask containing the list of cpus sharing 384246246cbSSudeep Holla the cache 385246246cbSSudeep Holla 38634433332SMauro Carvalho Chehab size: 38734433332SMauro Carvalho Chehab the total cache size in kB 388246246cbSSudeep Holla 389246246cbSSudeep Holla type: 390246246cbSSudeep Holla - Instruction: cache that only holds instructions 391246246cbSSudeep Holla - Data: cache that only caches data 392246246cbSSudeep Holla - Unified: cache that holds both data and instructions 393246246cbSSudeep Holla 39434433332SMauro Carvalho Chehab ways_of_associativity: 39534433332SMauro Carvalho Chehab degree of freedom in placing a particular block 396246246cbSSudeep Holla of memory in the cache 397246246cbSSudeep Holla 398246246cbSSudeep Holla write_policy: 39934433332SMauro Carvalho Chehab - WriteThrough: 40034433332SMauro Carvalho Chehab data is written to both the cache line 401246246cbSSudeep Holla and to the block in the lower-level memory 40234433332SMauro Carvalho Chehab - WriteBack: 40334433332SMauro Carvalho Chehab data is written only to the cache line and 404246246cbSSudeep Holla the modified cache line is written to main 405246246cbSSudeep Holla memory only when it is replaced 4061b028984SShilpasri G Bhat 4071d78dc59STony Luck 4081d78dc59STony LuckWhat: /sys/devices/system/cpu/cpu*/cache/index*/id 4091d78dc59STony LuckDate: September 2016 4101d78dc59STony LuckContact: Linux kernel mailing list <linux-kernel@vger.kernel.org> 4111d78dc59STony LuckDescription: Cache id 4121d78dc59STony Luck 4131d78dc59STony Luck The id provides a unique number for a specific instance of 4141d78dc59STony Luck a cache of a particular type. E.g. there may be a level 4151d78dc59STony Luck 3 unified cache on each socket in a server and we may 4161d78dc59STony Luck assign them ids 0, 1, 2, ... 4171d78dc59STony Luck 4181d78dc59STony Luck Note that id value can be non-contiguous. E.g. level 1 4191d78dc59STony Luck caches typically exist per core, but there may not be a 4201d78dc59STony Luck power of two cores on a socket, so these caches may be 4211d78dc59STony Luck numbered 0, 1, 2, 3, 4, 5, 8, 9, 10, ... 4221d78dc59STony Luck 4231b028984SShilpasri G BhatWhat: /sys/devices/system/cpu/cpuX/cpufreq/throttle_stats 4241b028984SShilpasri G Bhat /sys/devices/system/cpu/cpuX/cpufreq/throttle_stats/turbo_stat 4251b028984SShilpasri G Bhat /sys/devices/system/cpu/cpuX/cpufreq/throttle_stats/sub_turbo_stat 4261b028984SShilpasri G Bhat /sys/devices/system/cpu/cpuX/cpufreq/throttle_stats/unthrottle 4271b028984SShilpasri G Bhat /sys/devices/system/cpu/cpuX/cpufreq/throttle_stats/powercap 4281b028984SShilpasri G Bhat /sys/devices/system/cpu/cpuX/cpufreq/throttle_stats/overtemp 4291b028984SShilpasri G Bhat /sys/devices/system/cpu/cpuX/cpufreq/throttle_stats/supply_fault 4301b028984SShilpasri G Bhat /sys/devices/system/cpu/cpuX/cpufreq/throttle_stats/overcurrent 4311b028984SShilpasri G Bhat /sys/devices/system/cpu/cpuX/cpufreq/throttle_stats/occ_reset 4321b028984SShilpasri G BhatDate: March 2016 4331b028984SShilpasri G BhatContact: Linux kernel mailing list <linux-kernel@vger.kernel.org> 4341b028984SShilpasri G Bhat Linux for PowerPC mailing list <linuxppc-dev@ozlabs.org> 4351b028984SShilpasri G BhatDescription: POWERNV CPUFreq driver's frequency throttle stats directory and 4361b028984SShilpasri G Bhat attributes 4371b028984SShilpasri G Bhat 4381b028984SShilpasri G Bhat 'cpuX/cpufreq/throttle_stats' directory contains the CPU frequency 4391b028984SShilpasri G Bhat throttle stat attributes for the chip. The throttle stats of a cpu 4401b028984SShilpasri G Bhat is common across all the cpus belonging to a chip. Below are the 4411b028984SShilpasri G Bhat throttle attributes exported in the 'throttle_stats' directory: 4421b028984SShilpasri G Bhat 4431b028984SShilpasri G Bhat - turbo_stat : This file gives the total number of times the max 4441b028984SShilpasri G Bhat frequency is throttled to lower frequency in turbo (at and above 4451b028984SShilpasri G Bhat nominal frequency) range of frequencies. 4461b028984SShilpasri G Bhat 4471b028984SShilpasri G Bhat - sub_turbo_stat : This file gives the total number of times the 4481b028984SShilpasri G Bhat max frequency is throttled to lower frequency in sub-turbo(below 4491b028984SShilpasri G Bhat nominal frequency) range of frequencies. 4501b028984SShilpasri G Bhat 4511b028984SShilpasri G Bhat - unthrottle : This file gives the total number of times the max 4521b028984SShilpasri G Bhat frequency is unthrottled after being throttled. 4531b028984SShilpasri G Bhat 4541b028984SShilpasri G Bhat - powercap : This file gives the total number of times the max 4551b028984SShilpasri G Bhat frequency is throttled due to 'Power Capping'. 4561b028984SShilpasri G Bhat 4571b028984SShilpasri G Bhat - overtemp : This file gives the total number of times the max 4581b028984SShilpasri G Bhat frequency is throttled due to 'CPU Over Temperature'. 4591b028984SShilpasri G Bhat 4601b028984SShilpasri G Bhat - supply_fault : This file gives the total number of times the 4611b028984SShilpasri G Bhat max frequency is throttled due to 'Power Supply Failure'. 4621b028984SShilpasri G Bhat 4631b028984SShilpasri G Bhat - overcurrent : This file gives the total number of times the 4641b028984SShilpasri G Bhat max frequency is throttled due to 'Overcurrent'. 4651b028984SShilpasri G Bhat 4661b028984SShilpasri G Bhat - occ_reset : This file gives the total number of times the max 4671b028984SShilpasri G Bhat frequency is throttled due to 'OCC Reset'. 4681b028984SShilpasri G Bhat 4691b028984SShilpasri G Bhat The sysfs attributes representing different throttle reasons like 4701b028984SShilpasri G Bhat powercap, overtemp, supply_fault, overcurrent and occ_reset map to 4711b028984SShilpasri G Bhat the reasons provided by OCC firmware for throttling the frequency. 4721b028984SShilpasri G Bhat 4731b028984SShilpasri G BhatWhat: /sys/devices/system/cpu/cpufreq/policyX/throttle_stats 4741b028984SShilpasri G Bhat /sys/devices/system/cpu/cpufreq/policyX/throttle_stats/turbo_stat 4751b028984SShilpasri G Bhat /sys/devices/system/cpu/cpufreq/policyX/throttle_stats/sub_turbo_stat 4761b028984SShilpasri G Bhat /sys/devices/system/cpu/cpufreq/policyX/throttle_stats/unthrottle 4771b028984SShilpasri G Bhat /sys/devices/system/cpu/cpufreq/policyX/throttle_stats/powercap 4781b028984SShilpasri G Bhat /sys/devices/system/cpu/cpufreq/policyX/throttle_stats/overtemp 4791b028984SShilpasri G Bhat /sys/devices/system/cpu/cpufreq/policyX/throttle_stats/supply_fault 4801b028984SShilpasri G Bhat /sys/devices/system/cpu/cpufreq/policyX/throttle_stats/overcurrent 4811b028984SShilpasri G Bhat /sys/devices/system/cpu/cpufreq/policyX/throttle_stats/occ_reset 4821b028984SShilpasri G BhatDate: March 2016 4831b028984SShilpasri G BhatContact: Linux kernel mailing list <linux-kernel@vger.kernel.org> 4841b028984SShilpasri G Bhat Linux for PowerPC mailing list <linuxppc-dev@ozlabs.org> 4851b028984SShilpasri G BhatDescription: POWERNV CPUFreq driver's frequency throttle stats directory and 4861b028984SShilpasri G Bhat attributes 4871b028984SShilpasri G Bhat 4881b028984SShilpasri G Bhat 'policyX/throttle_stats' directory and all the attributes are same as 4891b028984SShilpasri G Bhat the /sys/devices/system/cpu/cpuX/cpufreq/throttle_stats directory and 4901b028984SShilpasri G Bhat attributes which give the frequency throttle information of the chip. 491f8d9f924SSteve Capper 492f8d9f924SSteve CapperWhat: /sys/devices/system/cpu/cpuX/regs/ 493f8d9f924SSteve Capper /sys/devices/system/cpu/cpuX/regs/identification/ 494f8d9f924SSteve Capper /sys/devices/system/cpu/cpuX/regs/identification/midr_el1 495f8d9f924SSteve Capper /sys/devices/system/cpu/cpuX/regs/identification/revidr_el1 496*d69d5649SMark Brown /sys/devices/system/cpu/cpuX/regs/identification/smidr_el1 497f8d9f924SSteve CapperDate: June 2016 498f8d9f924SSteve CapperContact: Linux ARM Kernel Mailing list <linux-arm-kernel@lists.infradead.org> 499f8d9f924SSteve CapperDescription: AArch64 CPU registers 50034433332SMauro Carvalho Chehab 501f8d9f924SSteve Capper 'identification' directory exposes the CPU ID registers for 502*d69d5649SMark Brown identifying model and revision of the CPU and SMCU. 503a2b60670SJuri Lelli 5047af33504SWill DeaconWhat: /sys/devices/system/cpu/aarch32_el0 5057af33504SWill DeaconDate: May 2021 5067af33504SWill DeaconContact: Linux ARM Kernel Mailing list <linux-arm-kernel@lists.infradead.org> 5077af33504SWill DeaconDescription: Identifies the subset of CPUs in the system that can execute 5087af33504SWill Deacon AArch32 (32-bit ARM) applications. If present, the same format as 5097af33504SWill Deacon /sys/devices/system/cpu/{offline,online,possible,present} is used. 5107af33504SWill Deacon If absent, then all or none of the CPUs can execute AArch32 5117af33504SWill Deacon applications and execve() will behave accordingly. 5127af33504SWill Deacon 513abcb948dSMauro Carvalho ChehabWhat: /sys/devices/system/cpu/cpuX/cpu_capacity 514a2b60670SJuri LelliDate: December 2016 515a2b60670SJuri LelliContact: Linux kernel mailing list <linux-kernel@vger.kernel.org> 516a2b60670SJuri LelliDescription: information about CPUs heterogeneity. 517a2b60670SJuri Lelli 518abcb948dSMauro Carvalho Chehab cpu_capacity: capacity of cpuX. 51987590ce6SThomas Gleixner 52087590ce6SThomas GleixnerWhat: /sys/devices/system/cpu/vulnerabilities 52187590ce6SThomas Gleixner /sys/devices/system/cpu/vulnerabilities/meltdown 52287590ce6SThomas Gleixner /sys/devices/system/cpu/vulnerabilities/spectre_v1 52387590ce6SThomas Gleixner /sys/devices/system/cpu/vulnerabilities/spectre_v2 524c456442cSKonrad Rzeszutek Wilk /sys/devices/system/cpu/vulnerabilities/spec_store_bypass 525d90a7a0eSJiri Kosina /sys/devices/system/cpu/vulnerabilities/l1tf 5268a4b06d3SThomas Gleixner /sys/devices/system/cpu/vulnerabilities/mds 5277e5b3c26SMark Gross /sys/devices/system/cpu/vulnerabilities/srbds 528a7a248c5SPawan Gupta /sys/devices/system/cpu/vulnerabilities/tsx_async_abort 529db4d30fbSVineela Tummalapalli /sys/devices/system/cpu/vulnerabilities/itlb_multihit 5308d50cdf8SPawan Gupta /sys/devices/system/cpu/vulnerabilities/mmio_stale_data 5319ecccfaaSDavid WoodhouseDate: January 2018 53287590ce6SThomas GleixnerContact: Linux kernel mailing list <linux-kernel@vger.kernel.org> 53387590ce6SThomas GleixnerDescription: Information about CPU vulnerabilities 53487590ce6SThomas Gleixner 53587590ce6SThomas Gleixner The files are named after the code names of CPU 53687590ce6SThomas Gleixner vulnerabilities. The output of those files reflects the 53787590ce6SThomas Gleixner state of the CPUs in the system. Possible output values: 53887590ce6SThomas Gleixner 53934433332SMauro Carvalho Chehab ================ ============================================== 54087590ce6SThomas Gleixner "Not affected" CPU is not affected by the vulnerability 54187590ce6SThomas Gleixner "Vulnerable" CPU is affected and no mitigation in effect 5429ecccfaaSDavid Woodhouse "Mitigation: $M" CPU is affected and mitigation $M is in effect 54334433332SMauro Carvalho Chehab ================ ============================================== 54405736e4aSThomas Gleixner 5455999bbe7SThomas Gleixner See also: Documentation/admin-guide/hw-vuln/index.rst 546d90a7a0eSJiri Kosina 54705736e4aSThomas GleixnerWhat: /sys/devices/system/cpu/smt 54805736e4aSThomas Gleixner /sys/devices/system/cpu/smt/active 54905736e4aSThomas Gleixner /sys/devices/system/cpu/smt/control 55005736e4aSThomas GleixnerDate: June 2018 55105736e4aSThomas GleixnerContact: Linux kernel mailing list <linux-kernel@vger.kernel.org> 5523e42d1deSCarlos BilbaoDescription: Control Symmetric Multi Threading (SMT) 55305736e4aSThomas Gleixner 55405736e4aSThomas Gleixner active: Tells whether SMT is active (enabled and siblings online) 55505736e4aSThomas Gleixner 55605736e4aSThomas Gleixner control: Read/write interface to control SMT. Possible 55705736e4aSThomas Gleixner values: 55805736e4aSThomas Gleixner 55934433332SMauro Carvalho Chehab ================ ========================================= 56005736e4aSThomas Gleixner "on" SMT is enabled 56105736e4aSThomas Gleixner "off" SMT is disabled 56205736e4aSThomas Gleixner "forceoff" SMT is force disabled. Cannot be changed. 56305736e4aSThomas Gleixner "notsupported" SMT is not supported by the CPU 564de7b77e5SJosh Poimboeuf "notimplemented" SMT runtime toggling is not 565de7b77e5SJosh Poimboeuf implemented for the architecture 56634433332SMauro Carvalho Chehab ================ ========================================= 56705736e4aSThomas Gleixner 56805736e4aSThomas Gleixner If control status is "forceoff" or "notsupported" writes 56905736e4aSThomas Gleixner are rejected. 570b9c273baSRafael J. Wysocki 571abcb948dSMauro Carvalho ChehabWhat: /sys/devices/system/cpu/cpuX/power/energy_perf_bias 572b9c273baSRafael J. WysockiDate: March 2019 573b9c273baSRafael J. WysockiContact: linux-pm@vger.kernel.org 574b9c273baSRafael J. WysockiDescription: Intel Energy and Performance Bias Hint (EPB) 575b9c273baSRafael J. Wysocki 576b9c273baSRafael J. Wysocki EPB for the given CPU in a sliding scale 0 - 15, where a value 577b9c273baSRafael J. Wysocki of 0 corresponds to a hint preference for highest performance 578b9c273baSRafael J. Wysocki and a value of 15 corresponds to the maximum energy savings. 579b9c273baSRafael J. Wysocki 580b9c273baSRafael J. Wysocki In order to change the EPB value for the CPU, write either 581b9c273baSRafael J. Wysocki a number in the 0 - 15 sliding scale above, or one of the 582b9c273baSRafael J. Wysocki strings: "performance", "balance-performance", "normal", 583b9c273baSRafael J. Wysocki "balance-power", "power" (that represent values reflected by 584b9c273baSRafael J. Wysocki their meaning), to this attribute. 585b9c273baSRafael J. Wysocki 586b9c273baSRafael J. Wysocki This attribute is present for all online CPUs supporting the 587b9c273baSRafael J. Wysocki Intel EPB feature. 588203dffacSFenghua Yu 589203dffacSFenghua YuWhat: /sys/devices/system/cpu/umwait_control 590203dffacSFenghua Yu /sys/devices/system/cpu/umwait_control/enable_c02 591203dffacSFenghua Yu /sys/devices/system/cpu/umwait_control/max_time 592203dffacSFenghua YuDate: May 2019 593203dffacSFenghua YuContact: Linux kernel mailing list <linux-kernel@vger.kernel.org> 594203dffacSFenghua YuDescription: Umwait control 595203dffacSFenghua Yu 596203dffacSFenghua Yu enable_c02: Read/write interface to control umwait C0.2 state 597203dffacSFenghua Yu Read returns C0.2 state status: 598203dffacSFenghua Yu 0: C0.2 is disabled 599203dffacSFenghua Yu 1: C0.2 is enabled 600203dffacSFenghua Yu 601203dffacSFenghua Yu Write 'y' or '1' or 'on' to enable C0.2 state. 602203dffacSFenghua Yu Write 'n' or '0' or 'off' to disable C0.2 state. 603203dffacSFenghua Yu 604203dffacSFenghua Yu The interface is case insensitive. 605203dffacSFenghua Yu 606203dffacSFenghua Yu max_time: Read/write interface to control umwait maximum time 607203dffacSFenghua Yu in TSC-quanta that the CPU can reside in either C0.1 608203dffacSFenghua Yu or C0.2 state. The time is an unsigned 32-bit number. 609203dffacSFenghua Yu Note that a value of zero means there is no limit. 610203dffacSFenghua Yu Low order two bits must be zero. 611734560acSRyan Grimm 612734560acSRyan GrimmWhat: /sys/devices/system/cpu/svm 613734560acSRyan GrimmDate: August 2019 614734560acSRyan GrimmContact: Linux kernel mailing list <linux-kernel@vger.kernel.org> 615734560acSRyan Grimm Linux for PowerPC mailing list <linuxppc-dev@ozlabs.org> 616734560acSRyan GrimmDescription: Secure Virtual Machine 617734560acSRyan Grimm 618734560acSRyan Grimm If 1, it means the system is using the Protected Execution 619734560acSRyan Grimm Facility in POWER9 and newer processors. i.e., it is a Secure 620734560acSRyan Grimm Virtual Machine. 621bde752c3SGautham R. Shenoy 622bde752c3SGautham R. ShenoyWhat: /sys/devices/system/cpu/cpuX/purr 623bde752c3SGautham R. ShenoyDate: Apr 2005 624bde752c3SGautham R. ShenoyContact: Linux for PowerPC mailing list <linuxppc-dev@ozlabs.org> 625bde752c3SGautham R. ShenoyDescription: PURR ticks for this CPU since the system boot. 626bde752c3SGautham R. Shenoy 627bde752c3SGautham R. Shenoy The Processor Utilization Resources Register (PURR) is 628bde752c3SGautham R. Shenoy a 64-bit counter which provides an estimate of the 629bde752c3SGautham R. Shenoy resources used by the CPU thread. The contents of this 630bde752c3SGautham R. Shenoy register increases monotonically. This sysfs interface 631bde752c3SGautham R. Shenoy exposes the number of PURR ticks for cpuX. 632bde752c3SGautham R. Shenoy 633bde752c3SGautham R. ShenoyWhat: /sys/devices/system/cpu/cpuX/spurr 634bde752c3SGautham R. ShenoyDate: Dec 2006 635bde752c3SGautham R. ShenoyContact: Linux for PowerPC mailing list <linuxppc-dev@ozlabs.org> 636bde752c3SGautham R. ShenoyDescription: SPURR ticks for this CPU since the system boot. 637bde752c3SGautham R. Shenoy 638bde752c3SGautham R. Shenoy The Scaled Processor Utilization Resources Register 639bde752c3SGautham R. Shenoy (SPURR) is a 64-bit counter that provides a frequency 640bde752c3SGautham R. Shenoy invariant estimate of the resources used by the CPU 641bde752c3SGautham R. Shenoy thread. The contents of this register increases 642bde752c3SGautham R. Shenoy monotonically. This sysfs interface exposes the number 643bde752c3SGautham R. Shenoy of SPURR ticks for cpuX. 644bde752c3SGautham R. Shenoy 645bde752c3SGautham R. ShenoyWhat: /sys/devices/system/cpu/cpuX/idle_purr 646bde752c3SGautham R. ShenoyDate: Apr 2020 647bde752c3SGautham R. ShenoyContact: Linux for PowerPC mailing list <linuxppc-dev@ozlabs.org> 648bde752c3SGautham R. ShenoyDescription: PURR ticks for cpuX when it was idle. 649bde752c3SGautham R. Shenoy 650bde752c3SGautham R. Shenoy This sysfs interface exposes the number of PURR ticks 651bde752c3SGautham R. Shenoy for cpuX when it was idle. 652bde752c3SGautham R. Shenoy 653bde752c3SGautham R. ShenoyWhat: /sys/devices/system/cpu/cpuX/idle_spurr 654bde752c3SGautham R. ShenoyDate: Apr 2020 655bde752c3SGautham R. ShenoyContact: Linux for PowerPC mailing list <linuxppc-dev@ozlabs.org> 656bde752c3SGautham R. ShenoyDescription: SPURR ticks for cpuX when it was idle. 657bde752c3SGautham R. Shenoy 658bde752c3SGautham R. Shenoy This sysfs interface exposes the number of SPURR ticks 659bde752c3SGautham R. Shenoy for cpuX when it was idle. 66080c7c36fSPeter Collingbourne 66180c7c36fSPeter CollingbourneWhat: /sys/devices/system/cpu/cpuX/mte_tcf_preferred 66280c7c36fSPeter CollingbourneDate: July 2021 66380c7c36fSPeter CollingbourneContact: Linux ARM Kernel Mailing list <linux-arm-kernel@lists.infradead.org> 66480c7c36fSPeter CollingbourneDescription: Preferred MTE tag checking mode 66580c7c36fSPeter Collingbourne 66680c7c36fSPeter Collingbourne When a user program specifies more than one MTE tag checking 66780c7c36fSPeter Collingbourne mode, this sysfs node is used to specify which mode should 66880c7c36fSPeter Collingbourne be preferred when scheduling a task on that CPU. Possible 66980c7c36fSPeter Collingbourne values: 67080c7c36fSPeter Collingbourne 67180c7c36fSPeter Collingbourne ================ ============================================== 67280c7c36fSPeter Collingbourne "sync" Prefer synchronous mode 6739986c765SEvgenii Stepanov "asymm" Prefer asymmetric mode 67480c7c36fSPeter Collingbourne "async" Prefer asynchronous mode 67580c7c36fSPeter Collingbourne ================ ============================================== 67680c7c36fSPeter Collingbourne 67780c7c36fSPeter Collingbourne See also: Documentation/arm64/memory-tagging-extension.rst 6783722e7c3SKohei Tarumizu 6793722e7c3SKohei TarumizuWhat: /sys/devices/system/cpu/nohz_full 6803722e7c3SKohei TarumizuDate: Apr 2015 6813722e7c3SKohei TarumizuContact: Linux kernel mailing list <linux-kernel@vger.kernel.org> 6823722e7c3SKohei TarumizuDescription: 6833722e7c3SKohei Tarumizu (RO) the list of CPUs that are in nohz_full mode. 6843722e7c3SKohei Tarumizu These CPUs are set by boot parameter "nohz_full=". 68502bf6074SKohei Tarumizu 68602bf6074SKohei TarumizuWhat: /sys/devices/system/cpu/isolated 68702bf6074SKohei TarumizuDate: Apr 2015 68802bf6074SKohei TarumizuContact: Linux kernel mailing list <linux-kernel@vger.kernel.org> 68902bf6074SKohei TarumizuDescription: 69002bf6074SKohei Tarumizu (RO) the list of CPUs that are isolated and don't 69102bf6074SKohei Tarumizu participate in load balancing. These CPUs are set by 69202bf6074SKohei Tarumizu boot parameter "isolcpus=". 693