Linux kernel mirror (for testing) git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
kernel os linux
1
fork

Configure Feed

Select the types of activity you want to include in your feed.

Documentation/amd-pstate: Add documentation for amd_pstate_floor_{freq,count}

Add documentation for the sysfs files
/sys/devices/system/cpu/cpufreq/policy*/amd_pstate_floor_freq
and
/sys/devices/system/cpu/cpufreq/policy*/amd_pstate_floor_count.

Reviewed-by: Mario Limonciello (AMD) <superm1@kernel.org>
Signed-off-by: Gautham R. Shenoy <gautham.shenoy@amd.com>
Signed-off-by: Mario Limonciello (AMD) <superm1@kernel.org>

authored by

Gautham R. Shenoy and committed by
Mario Limonciello (AMD)
88d2ca6a a5bc4c44

+32
+32
Documentation/admin-guide/pm/amd-pstate.rst
··· 242 242 /sys/devices/system/cpu/cpufreq/policy0/amd_pstate_hw_prefcore 243 243 /sys/devices/system/cpu/cpufreq/policy0/amd_pstate_lowest_nonlinear_freq 244 244 /sys/devices/system/cpu/cpufreq/policy0/amd_pstate_max_freq 245 + /sys/devices/system/cpu/cpufreq/policy0/amd_pstate_floor_freq 246 + /sys/devices/system/cpu/cpufreq/policy0/amd_pstate_floor_count 245 247 /sys/devices/system/cpu/cpufreq/policy0/amd_pstate_prefcore_ranking 246 248 247 249 ··· 278 276 larger numbers are preferred at the time of reading. This can change at 279 277 runtime based on platform conditions. This attribute is read-only. This file 280 278 is only visible on platforms which support the preferred core feature. 279 + 280 + ``amd_pstate_floor_freq`` 281 + 282 + The floor frequency associated with each CPU. Userspace can write any 283 + value between ``cpuinfo_min_freq`` and ``scaling_max_freq`` into this 284 + file. When the system is under power or thermal constraints, the 285 + platform firmware will attempt to throttle the CPU frequency to the 286 + value specified in ``amd_pstate_floor_freq`` before throttling it 287 + further. This allows userspace to specify different floor frequencies 288 + to different CPUs. For optimal results, threads of the same core 289 + should have the same floor frequency value. This file is only visible 290 + on platforms that support the CPPC Performance Priority feature. 291 + 292 + 293 + ``amd_pstate_floor_count`` 294 + 295 + The number of distinct Floor Performance levels supported by the 296 + platform. For example, if this value is 2, then the number of unique 297 + values obtained from the command ``cat 298 + /sys/devices/system/cpu/cpufreq/policy*/amd_pstate_floor_freq | 299 + sort -n | uniq`` should be at most this number for the behavior 300 + described in ``amd_pstate_floor_freq`` to take effect. A zero value 301 + implies that the platform supports unlimited floor performance levels. 302 + This file is only visible on platforms that support the CPPC 303 + Performance Priority feature. 304 + 305 + **Note**: When ``amd_pstate_floor_count`` is non-zero, the frequency to 306 + which the CPU is throttled under power or thermal constraints is 307 + undefined when the number of unique values of ``amd_pstate_floor_freq`` 308 + across all CPUs in the system exceeds ``amd_pstate_floor_count``. 281 309 282 310 ``energy_performance_available_preferences`` 283 311