kernel/linux.git/tools/power/cpupower/utils, branch v6.12.91

cpupower: Fix a bug where the -t option of the set subcommand was not working.

2025-09-09T16:58:02+00:00

[ Upstream commit b3eaf14f4c63fd6abc7b68c6d7a07c5680a6d8e5 ] The set subcommand's -t option is documented as being available for boost configuration, but it was not actually functioning due to a bug in the option handling. Link: https://lore.kernel.org/r/20250522061122.2149188-2-fj5851bi@fujitsu.com Signed-off-by: Shinji Nomoto Signed-off-by: Shuah Khan Signed-off-by: Sasha Levin

pm: cpupower: Fix the snapshot-order of tsc,mperf, clock in mperf_stop()

2025-08-20T16:30:27+00:00

[ Upstream commit cda7ac8ce7de84cf32a3871ba5f318aa3b79381e ] In the function mperf_start(), mperf_monitor snapshots the time, tsc and finally the aperf,mperf MSRs. However, this order of snapshotting in is reversed in mperf_stop(). As a result, the C0 residency (which is computed as delta_mperf * 100 / delta_tsc) is under-reported on CPUs that is 100% busy. Fix this by snapshotting time, tsc and then aperf,mperf in mperf_stop() in the same order as in mperf_start(). Link: https://lore.kernel.org/r/20250612122355.19629-2-gautham.shenoy@amd.com Signed-off-by: Gautham R. Shenoy Signed-off-by: Shuah Khan Signed-off-by: Sasha Levin

cpupower: fix TSC MHz calculation

2025-02-08T08:57:05+00:00

[ Upstream commit 9d6c0e58514f8b57cd9c2c755e41623d6a966025 ] Commit 'cpupower: Make TSC read per CPU for Mperf monitor' (c2adb1877b7) changes TSC counter reads per cpu, but left time diff global (from start of all cpus to end of all cpus), thus diff(time) is too large for a cpu's tsc counting, resulting in far less than acutal TSC_Mhz and thus `cpupower monitor` showing far less than actual cpu realtime frequency. /proc/cpuinfo shows frequency: cat /proc/cpuinfo | egrep -e 'processor' -e 'MHz' ... processor : 171 cpu MHz : 4108.498 ... before fix (System 100% busy): | Mperf || Idle_Stats CPU| C0 | Cx | Freq || POLL | C1 | C2 171| 0.77| 99.23| 2279|| 0.00| 0.00| 0.00 after fix (System 100% busy): | Mperf || Idle_Stats CPU| C0 | Cx | Freq || POLL | C1 | C2 171| 0.46| 99.54| 4095|| 0.00| 0.00| 0.00 Fixes: c2adb1877b76 ("cpupower: Make TSC read per CPU for Mperf monitor") Signed-off-by: He Rongguang Signed-off-by: Shuah Khan Signed-off-by: Sasha Levin

tools/cpupower: display residency value in idle-info

2024-08-09T16:32:33+00:00

Update cpuidle tool to display the residency value of cpuidle states. This addition provides a clearer and more detailed view of idle state information when using cpuidle-info. -------------------------------- Before Patch: -------------------------------- $ cpupower idle-info CPUidle driver: intel_idle CPUidle governor: menu analyzing CPU 28: Number of idle states: 3 Available idle states: POLL C1 C1E POLL: Flags/Description: CPUIDLE CORE POLL IDLE Latency: 0 Usage: 7448 Duration: 207170 C1: Flags/Description: MWAIT 0x00 Latency: 2 Usage: 7023 Duration: 3736853 C1E: Flags/Description: MWAIT 0x01 Latency: 10 Usage: 18468 Duration: 11396212 -------------------------------- After Patch: -------------------------------- $ cpupower idle-info CPUidle driver: intel_idle CPUidle governor: menu analyzing CPU 12: Number of idle states: 3 Available idle states: POLL C1 C1E POLL: Flags/Description: CPUIDLE CORE POLL IDLE Latency: 0 Residency: 0 Usage: 1950 Duration: 38458 C1: Flags/Description: MWAIT 0x00 Latency: 2 Residency: 2 Usage: 10688 Duration: 7133020 C1E: Flags/Description: MWAIT 0x01 Latency: 10 Residency: 20 Usage: 22356 Duration: 15687259 -------------------------------- Signed-off-by: Aboorva Devarajan Signed-off-by: Shuah Khan

cpupower: Change the var type of the 'monitor' subcommand display mode

2024-06-20T16:08:08+00:00

There is a type 'enum operation_mode_e' contains the display modes of the 'monitor' subcommand. This type isn't used though, instead the variable 'mode' is of a simple 'int' type. Change 'mode' variable type from 'int' to 'enum operation_mode_e' in order to improve compiler type checking. Built and tested this with different monitor cmdline params. Everything works as expected, that is nothing changed and no regressions encountered. Signed-off-by: Roman Storozhenko Signed-off-by: Shuah Khan

tools/power/cpupower: Fix Pstate frequency reporting on AMD Family 1Ah CPUs

2024-05-28T15:22:57+00:00

Update cpupower's P-State frequency calculation and reporting with AMD Family 1Ah+ processors, when using the acpi-cpufreq driver. This is due to a change in the PStateDef MSR layout in AMD Family 1Ah+. Tested on 4th and 5th Gen AMD EPYC system Signed-off-by: Ananth Narayan Signed-off-by: Dhananjay Ugwekar Reviewed-by: Mario Limonciello Signed-off-by: Shuah Khan

cpupower: Fix cpuidle_set to accept only numeric values for idle-set operation.

2023-07-18T22:07:08+00:00

For both the d and e options in 'cpupower idle_set' command, an atoi() conversion is done without checking if the input argument is all numeric. So, an atoi conversion is done on any character provided as input and the CPU idle_set operation continues with that integer value, which may not be what is intended or entirely correct. The output of cpuidle-set before patch is as follows: [root@xxx cpupower]# cpupower idle-set -e 1$ Idlestate 1 enabled on CPU 0 [snip] Idlestate 1 enabled on CPU 47 [root@xxx cpupower]# cpupower idle-set -e 11 Idlestate 11 not available on CPU 0 [snip] Idlestate 11 not available on CPU 47 [root@xxx cpupower]# cpupower idle-set -d 12 Idlestate 12 not available on CPU 0 [snip] Idlestate 12 not available on CPU 47 [root@xxx cpupower]# cpupower idle-set -d qw Idlestate 0 disabled on CPU 0 [snip] Idlestate 0 disabled on CPU 47 This patch adds a check for both d and e options in cpuidle-set.c to see that the idle_set value is all numeric before doing a string-to-int conversion using strtol(). The output of cpuidle-set after the patch is as below: [root@xxx cpupower]# ./cpupower idle-set -e 1$ Bad idle_set value: 1$. Integer expected [root@xxx cpupower]# ./cpupower idle-set -e 11 Idlestate 11 not available on CPU 0 [snip] Idlestate 11 not available on CPU 47 [root@xxx cpupower]# ./cpupower idle-set -d 12 Idlestate 12 not available on CPU 0 [snip] Idlestate 12 not available on CPU 47 [root@xxx cpupower]# ./cpupower idle-set -d qw Bad idle_set value: qw. Integer expected Signed-off-by: Brahadambal Srinivasan Signed-off-by: Likhitha Korrapati Tested-by: Pavithra Prakash Reviewed-by: Rick Lindsley Signed-off-by: Shuah Khan

cpupower: Add turbo-boost support in cpupower

2023-07-18T22:07:01+00:00

If boost sysfs (/sys/devices/system/cpu/cpufreq/boost) file is present turbo-boost is feature is supported in the hardware. By default this feature should be enabled. But to disable/enable it write to the sysfs file. Use the same to control this feature via cpupower. To enable: cpupower set --turbo-boost 1 To disable: cpupower set --turbo-boost 0 Acked-by: Huang Rui Reviewed-by: Gautham R. Shenoy Reviewed-by: Mario Limonciello Signed-off-by: Wyes Karny Tested-by: Perry Yuan Signed-off-by: Shuah Khan

cpupower: Add support for amd_pstate mode change

2023-07-18T22:06:56+00:00

amd_pstate supports changing of its mode dynamically via `status` sysfs file. Add the same capability in cpupower. To change the mode to active mode use below command: cpupower set --amd-pstate-mode active Acked-by: Huang Rui Reviewed-by: Gautham R. Shenoy Reviewed-by: Mario Limonciello Signed-off-by: Wyes Karny Tested-by: Perry Yuan Signed-off-by: Shuah Khan

cpupower: Add EPP value change support

2023-07-18T22:06:49+00:00

amd_pstate and intel_pstate active mode drivers support energy performance preference feature. Through this user can convey it's energy/performance preference to platform. Add this value change capability to cpupower. To change the EPP value use below command: cpupower set --epp performance Reviewed-by: Mario Limonciello Signed-off-by: Wyes Karny Tested-by: Perry Yuan Acked-by: Huang Rui Signed-off-by: Shuah Khan