summaryrefslogtreecommitdiff
path: root/drivers/cpufreq/amd-pstate.c
AgeCommit message (Collapse)Author
2025-02-06cpufreq/amd-pstate: Fix cpufreq_policy ref countingDhananjay Ugwekar
amd_pstate_update_limits() takes a cpufreq_policy reference but doesn't decrement the refcount in one of the exit paths, fix that. Fixes: 45722e777fd9 ("cpufreq: amd-pstate: Optimize amd_pstate_update_limits()") Signed-off-by: Dhananjay Ugwekar <dhananjay.ugwekar@amd.com> Reviewed-by: Mario Limonciello <mario.limonciello@amd.com> Link: https://lore.kernel.org/r/20250205112523.201101-10-dhananjay.ugwekar@amd.com Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
2025-02-05cpufreq/amd-pstate: Fix max_perf updation with schedutilDhananjay Ugwekar
In adjust_perf() callback, we are setting the max_perf to highest_perf, as opposed to the correct limit value i.e. max_limit_perf. Fix that. Fixes: 3f7b835fa4d0 ("cpufreq/amd-pstate: Move limit updating code") Signed-off-by: Dhananjay Ugwekar <dhananjay.ugwekar@amd.com> Reviewed-by: Mario Limonciello <mario.limonciello@amd.com> Link: https://lore.kernel.org/r/20250205112523.201101-3-dhananjay.ugwekar@amd.com Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
2025-02-05cpufreq/amd-pstate: Remove the goto label in amd_pstate_update_limitsDhananjay Ugwekar
Scope based guard/cleanup macros should not be used together with goto labels. Hence, remove the goto label. Fixes: 6c093d5a5b73 ("cpufreq/amd-pstate: convert mutex use to guard()") Signed-off-by: Dhananjay Ugwekar <dhananjay.ugwekar@amd.com> Reviewed-by: Mario Limonciello <mario.limonciello@amd.com> Link: https://lore.kernel.org/r/20250205112523.201101-2-dhananjay.ugwekar@amd.com Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
2025-02-03cpufreq/amd-pstate: Fix per-policy boost flag incorrect when failLifeng Zheng
Commit c8c68c38b56f ("cpufreq: amd-pstate: initialize core precision boost state") sets per-policy boost flag to false when boost fail. However, this boost flag will be set to reverse value in store_local_boost() and cpufreq_boost_trigger_state() in cpufreq.c. This will cause the per-policy boost flag set to true when fail to set boost. Remove the extra assignment in amd_pstate_set_boost() and keep all operations on per-policy boost flag outside of set_boost() to fix this problem. Fixes: c8c68c38b56f ("cpufreq: amd-pstate: initialize core precision boost state") Signed-off-by: Lifeng Zheng <zhenglifeng1@huawei.com> Reviewed-by: Mario Limonciello <mario.limonciello@amd.com> Link: https://lore.kernel.org/r/20250110091949.3610770-1-zhenglifeng1@huawei.com Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
2025-01-03cpufreq/amd-pstate: Refactor max frequency calculationNaresh Solanki
The previous approach introduced roundoff errors during division when calculating the boost ratio. This, in turn, affected the maximum frequency calculation, often resulting in reporting lower frequency values. For example, on the Glinda SoC based board with the following parameters: max_perf = 208 nominal_perf = 100 nominal_freq = 2600 MHz The Linux kernel previously calculated the frequency as: freq = ((max_perf * 1024 / nominal_perf) * nominal_freq) / 1024 freq = 5405 MHz // Integer arithmetic. With the updated formula: freq = (max_perf * nominal_freq) / nominal_perf freq = 5408 MHz This change ensures more accurate frequency calculations by eliminating unnecessary shifts and divisions, thereby improving precision. Signed-off-by: Naresh Solanki <naresh.solanki@9elements.com> [ML: trim the changelog from commit message] Reviewed-by: Mario Limonciello <mario.limonciello@amd.com> Link: https://lore.kernel.org/r/20241219201833.2750998-1-naresh.solanki@9elements.com Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
2025-01-03cpufreq/amd-pstate: Fix prefcore rankingsMario Limonciello
commit 50a062a76200 ("cpufreq/amd-pstate: Store the boost numerator as highest perf again") updated the value stored for highest perf to no longer store the highest perf value but instead the boost numerator. This is a fixed value for systems with preferred cores and not appropriate for use ITMT rankings. Update the value used for ITMT rankings to be the preferred core ranking. Reported-and-tested-by: Sebastian <sobrus@gmail.com> Closes: https://bugzilla.kernel.org/show_bug.cgi?id=219640 Fixes: 50a062a76200 ("cpufreq/amd-pstate: Store the boost numerator as highest perf again") Reviewed-by: Dhananjay Ugwekar <dhananjay.ugwekar@amd.com> Link: https://lore.kernel.org/r/20250102141204.3413202-1-superm1@kernel.org Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
2024-12-11cpufreq/amd-pstate: Drop boost_state variableMario Limonciello
Currently boost_state is cached for every processor in cpudata structure and driver boost state is set for every processor. Both of these aren't necessary as the driver only needs to set once and the policy stores whether boost is enabled. Move the driver boost setting to registration and adjust all references to cached value to pull from the policy instead. Reviewed-by: Gautham R. Shenoy <gautham.shenoy@amd.com> Link: https://lore.kernel.org/r/20241209185248.16301-16-mario.limonciello@amd.com Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
2024-12-11cpufreq/amd-pstate: Set different default EPP policy for Epyc and RyzenMario Limonciello
For Ryzen systems the EPP policy set by the BIOS is generally configured to performance as this is the default register value for the CPPC request MSR. If a user doesn't use additional software to configure EPP then the system will default biased towards performance and consume extra battery. Instead configure the default to "balanced_performance" for this case. Suggested-by: Artem S. Tashkinov <aros@gmx.com> Reviewed-by: Dhananjay Ugwekar <dhananjay.ugwekar@amd.com> Tested-by: Dhananjay Ugwekar <dhananjay.ugwekar@amd.com> Closes: https://bugzilla.kernel.org/show_bug.cgi?id=219526 Reviewed-by: Gautham R. Shenoy <gautham.shenoy@amd.com> Link: https://lore.kernel.org/r/20241209185248.16301-15-mario.limonciello@amd.com Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
2024-12-11cpufreq/amd-pstate: Drop ret variable from amd_pstate_set_energy_pref_index()Mario Limonciello
The ret variable is not necessary. Reviewed-and-tested-by: Dhananjay Ugwekar <dhananjay.ugwekar@amd.com> Reviewed-by: Gautham R. Shenoy <gautham.shenoy@amd.com> Link: https://lore.kernel.org/r/20241209185248.16301-14-mario.limonciello@amd.com Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
2024-12-11cpufreq/amd-pstate: Always write EPP value when updating perfMario Limonciello
For MSR systems the EPP value is in the same register as perf targets and so divding them into two separate MSR writes is wasteful. In msr_update_perf(), update both EPP and perf values in one write to MSR_AMD_CPPC_REQ, and cache them if successful. To accomplish this plumb the EPP value into the update_perf call and modify all its callers to check the return value. As this unifies calls, ensure that the MSR write is necessary before flushing a write out. Also drop the comparison from the passive flow tracing. Reviewed-by: Gautham R. Shenoy <gautham.shenoy@amd.com> Link: https://lore.kernel.org/r/20241209185248.16301-13-mario.limonciello@amd.com Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
2024-12-11cpufreq/amd-pstate: Cache EPP value and use that everywhereMario Limonciello
Cache the value in cpudata->epp_cached, and use that for all callers. As all callers use cached value merge amd_pstate_get_energy_pref_index() into show_energy_performance_preference(). Check if the EPP value is changed before writing it to MSR or shared memory region. Reviewed-by: Gautham R. Shenoy <gautham.shenoy@amd.com> Link: https://lore.kernel.org/r/20241209185248.16301-12-mario.limonciello@amd.com Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
2024-12-11cpufreq/amd-pstate: Move limit updating codeMario Limonciello
The limit updating code in amd_pstate_epp_update_limit() should not only apply to EPP updates. Move it to amd_pstate_update_min_max_limit() so other callers can benefit as well. With this move it's not necessary to have clamp_t calls anymore because the verify callback is called when setting limits. Reviewed-by: Gautham R. Shenoy <gautham.shenoy@amd.com> Link: https://lore.kernel.org/r/20241209185248.16301-11-mario.limonciello@amd.com Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
2024-12-11cpufreq/amd-pstate: Change amd_pstate_update_perf() to return an intMario Limonciello
As msr_update_perf() calls an MSR it's possible that it fails. Pass this return code up to the caller. Reviewed-by: Gautham R. Shenoy <gautham.shenoy@amd.com> Link: https://lore.kernel.org/r/20241209185248.16301-10-mario.limonciello@amd.com Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
2024-12-11cpufreq/amd-pstate: store all values in cpudata struct in khzMario Limonciello
Storing values in the cpudata structure in different units leads to confusion and hardcoded conversions elsewhere. After ratios are calculated store everything in khz for any future use. Adjust all relevant consumers for this change as well. Suggested-by: Dhananjay Ugwekar <Dhananjay.Ugwekar@amd.com> Reviewed-by: Gautham R. Shenoy <gautham.shenoy@amd.com> Link: https://lore.kernel.org/r/20241209185248.16301-9-mario.limonciello@amd.com Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
2024-12-11cpufreq/amd-pstate: Only update the cached value in msr_set_epp() on successMario Limonciello
If writing the MSR MSR_AMD_CPPC_REQ fails then the cached value in the amd_cpudata structure should not be updated. Reviewed-by: Gautham R. Shenoy <gautham.shenoy@amd.com> Link: https://lore.kernel.org/r/20241209185248.16301-8-mario.limonciello@amd.com Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
2024-12-11cpufreq/amd-pstate: Use FIELD_PREP and FIELD_GET macrosMario Limonciello
The FIELD_PREP and FIELD_GET macros improve readability and help to avoid shifting bugs. Reviewed-by: Gautham R. Shenoy <gautham.shenoy@amd.com> Link: https://lore.kernel.org/r/20241209185248.16301-7-mario.limonciello@amd.com Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
2024-12-11cpufreq/amd-pstate: Drop cached epp_policy variableMario Limonciello
epp_policy is not used by any of the current code and there is no need to cache it. Reviewed-by: Gautham R. Shenoy <gautham.shenoy@amd.com> Link: https://lore.kernel.org/r/20241209185248.16301-6-mario.limonciello@amd.com Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
2024-12-11cpufreq/amd-pstate: convert mutex use to guard()Mario Limonciello
Using scoped guard declaration will unlock mutexes automatically. Reviewed-by: Gautham R. Shenoy <gautham.shenoy@amd.com> Link: https://lore.kernel.org/r/20241209185248.16301-5-mario.limonciello@amd.com Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
2024-12-11cpufreq/amd-pstate: Add trace event for EPP perf updatesMario Limonciello
In "active" mode the most important thing for debugging whether an issue is hardware or software based is to look at what was the last thing written to the CPPC request MSR or shared memory region. The 'amd_pstate_epp_perf' trace event shows the values being written for all CPUs. Reviewed-by: Perry Yuan <perry.yuan@amd.com> Reviewed-by: Gautham R. Shenoy <gautham.shenoy@amd.com> Link: https://lore.kernel.org/r/20241209185248.16301-4-mario.limonciello@amd.com Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
2024-12-11cpufreq/amd-pstate: Merge amd_pstate_epp_cpu_offline() and ↵Dhananjay Ugwekar
amd_pstate_epp_offline() amd_pstate_epp_offline() is only called from within amd_pstate_epp_cpu_offline() and doesn't make much sense to have it at all. Hence, remove it. Also remove the unncessary debug print in the offline path while at it. Signed-off-by: Dhananjay Ugwekar <Dhananjay.Ugwekar@amd.com> Reviewed-by: Gautham R. Shenoy <gautham.shenoy@amd.com> Reviewed-by: Mario Limonciello <mario.limonciello@amd.com> Link: https://lore.kernel.org/r/20241204144842.164178-6-Dhananjay.Ugwekar@amd.com Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
2024-12-11cpufreq/amd-pstate: Remove the cppc_state check in offline/online functionsDhananjay Ugwekar
Only amd_pstate_epp driver (i.e. cppc_state = ACTIVE) enters the amd_pstate_epp_offline() and amd_pstate_epp_cpu_online() functions, so remove the unnecessary if condition checking if cppc_state is equal to AMD_PSTATE_ACTIVE. Signed-off-by: Dhananjay Ugwekar <Dhananjay.Ugwekar@amd.com> Reviewed-by: Mario Limonciello <mario.limonciello@amd.com> Reviewed-by: Gautham R. Shenoy <gautham.shenoy@amd.com> Link: https://lore.kernel.org/r/20241204144842.164178-5-Dhananjay.Ugwekar@amd.com Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
2024-12-11cpufreq/amd-pstate: Refactor amd_pstate_epp_reenable() and ↵Dhananjay Ugwekar
amd_pstate_epp_offline() Replace similar code chunks with amd_pstate_update_perf() and amd_pstate_set_epp() function calls. Signed-off-by: Dhananjay Ugwekar <Dhananjay.Ugwekar@amd.com> Reviewed-by: Mario Limonciello <mario.limonciello@amd.com> Reviewed-by: Gautham R. Shenoy <gautham.shenoy@amd.com> Link: https://lore.kernel.org/r/20241204144842.164178-4-Dhananjay.Ugwekar@amd.com [ML: Fix LKP reported error about unused variable] Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
2024-12-11cpufreq/amd-pstate: Move the invocation of amd_pstate_update_perf()Dhananjay Ugwekar
amd_pstate_update_perf() should not be a part of shmem_set_epp() function, so move it to the amd_pstate_epp_update_limit() function, where it is needed. Signed-off-by: Dhananjay Ugwekar <Dhananjay.Ugwekar@amd.com> Reviewed-by: Mario Limonciello <mario.limonciello@amd.com> Reviewed-by: Gautham R. Shenoy <gautham.shenoy@amd.com> Link: https://lore.kernel.org/r/20241204144842.164178-3-Dhananjay.Ugwekar@amd.com Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
2024-12-11cpufreq/amd-pstate: Convert the amd_pstate_get/set_epp() to static callsDhananjay Ugwekar
MSR and shared memory based systems have different mechanisms to get and set the epp value. Split those mechanisms into different functions and assign them appropriately to the static calls at boot time. This eliminates the need for the "if(cpu_feature_enabled(X86_FEATURE_CPPC))" checks at runtime. Also, propagate the error code from rdmsrl_on_cpu() and cppc_get_epp_perf() to *_get_epp()'s caller, instead of returning -EIO unconditionally. Signed-off-by: Dhananjay Ugwekar <Dhananjay.Ugwekar@amd.com> Reviewed-by: Mario Limonciello <mario.limonciello@amd.com> Reviewed-by: Gautham R. Shenoy <gautham.shenoy@amd.com> Link: https://lore.kernel.org/r/20241204144842.164178-2-Dhananjay.Ugwekar@amd.com Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
2024-12-10cpufreq/amd-pstate: Use boost numerator for upper bound of frequenciesMario Limonciello
commit 18d9b5227121 ("cpufreq/amd-pstate: Use nominal perf for limits when boost is disabled") introduced different semantics for min/max limits based upon whether the user turned off boost from sysfs. This however is not necessary when the highest perf value is the boost numerator. Suggested-by: Dhananjay Ugwekar <Dhananjay.Ugwekar@amd.com> Reviewed-by: Gautham R. Shenoy <gautham.shenoy@amd.com> Fixes: 18d9b5227121 ("cpufreq/amd-pstate: Use nominal perf for limits when boost is disabled") Link: https://lore.kernel.org/r/20241209185248.16301-3-mario.limonciello@amd.com Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
2024-12-10cpufreq/amd-pstate: Store the boost numerator as highest perf againMario Limonciello
commit ad4caad58d91d ("cpufreq: amd-pstate: Merge amd_pstate_highest_perf_set() into amd_get_boost_ratio_numerator()") changed the semantics for highest perf and commit 18d9b52271213 ("cpufreq/amd-pstate: Use nominal perf for limits when boost is disabled") worked around those semantic changes. This however is a confusing result and furthermore makes it awkward to change frequency limits and boost due to the scaling differences. Restore the boost numerator to highest perf again. Suggested-by: Dhananjay Ugwekar <Dhananjay.Ugwekar@amd.com> Reviewed-by: Gautham R. Shenoy <gautham.shenoy@amd.com> Fixes: ad4caad58d91 ("cpufreq: amd-pstate: Merge amd_pstate_highest_perf_set() into amd_get_boost_ratio_numerator()") Link: https://lore.kernel.org/r/20241209185248.16301-2-mario.limonciello@amd.com Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
2024-12-09cpufreq/amd-pstate: Detect preferred core support before driver registrationK Prateek Nayak
Booting with amd-pstate on 3rd Generation EPYC system incorrectly enabled ITMT support despite the system not supporting Preferred Core ranking. amd_pstate_init_prefcore() called during amd_pstate*_cpu_init() requires "amd_pstate_prefcore" to be set correctly however the preferred core support is detected only after driver registration which is too late. Swap the function calls around to detect preferred core support before registring the driver via amd_pstate_register_driver(). This ensures amd_pstate*_cpu_init() sees the correct value of "amd_pstate_prefcore" considering the platform support. Fixes: 279f838a61f9 ("x86/amd: Detect preferred cores in amd_get_boost_ratio_numerator()") Fixes: ff2653ded4d9 ("cpufreq/amd-pstate: Move registration after static function call update") Signed-off-by: K Prateek Nayak <kprateek.nayak@amd.com> Acked-by: Mario Limonciello <mario.limonciello@amd.com> Link: https://lore.kernel.org/r/20241210032557.754-1-kprateek.nayak@amd.com Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
2024-11-19Merge tag 'x86_cpu_for_v6.13' of ↵Linus Torvalds
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip Pull x86 cpuid updates from Borislav Petkov: - Add a feature flag which denotes AMD CPUs supporting workload classification with the purpose of using such hints when making scheduling decisions - Determine the boost enumerator for each AMD core based on its type: efficiency or performance, in the cppc driver - Add the type of a CPU to the topology CPU descriptor with the goal of supporting and making decisions based on the type of the respective core - Add a feature flag to denote AMD cores which have heterogeneous topology and enable SD_ASYM_PACKING for those - Check microcode revisions before disabling PCID on Intel - Cleanups and fixlets * tag 'x86_cpu_for_v6.13' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: x86/cpu: Remove redundant CONFIG_NUMA guard around numa_add_cpu() x86/cpu: Fix FAM5_QUARK_X1000 to use X86_MATCH_VFM() x86/cpu: Fix formatting of cpuid_bits[] in scattered.c x86/cpufeatures: Add X86_FEATURE_AMD_WORKLOAD_CLASS feature bit x86/amd: Use heterogeneous core topology for identifying boost numerator x86/cpu: Add CPU type to struct cpuinfo_topology x86/cpu: Enable SD_ASYM_PACKING for PKG domain on AMD x86/cpufeatures: Add X86_FEATURE_AMD_HETEROGENEOUS_CORES x86/cpufeatures: Rename X86_FEATURE_FAST_CPPC to have AMD prefix x86/mm: Don't disable PCID when INVLPG has been fixed by microcode
2024-10-29cpufreq/amd-pstate: Move registration after static function call updateMario Limonciello
On shared memory designs the static functions need to work before registration is done or the system can hang at bootup. Move the registration later in amd_pstate_init() to solve this. Fixes: b427ac408475 ("cpufreq/amd-pstate: Remove the redundant amd_pstate_set_driver() call") Reported-by: Klara Modin <klarasmodin@gmail.com> Closes: https://lore.kernel.org/linux-pm/cf9c146d-bacf-444e-92e2-15ebf513af96@gmail.com/#t Tested-by: Klara Modin <klarasmodin@gmail.com> Tested-by: Dhananjay Ugwekar <dhananjay.ugwekar@amd.com> Link: https://lore.kernel.org/r/20241028145542.1739160-2-superm1@kernel.org Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
2024-10-29cpufreq/amd-pstate: Push adjust_perf vfunc init into cpu_initMario Limonciello
As the driver can be changed in and out of different modes it's possible that adjust_perf is assigned when it shouldn't be. This could happen if an MSR design is started up in passive mode and then switches to active mode. To solve this explicitly clear `adjust_perf` in amd_pstate_epp_cpu_init(). Tested-by: Klara Modin <klarasmodin@gmail.com> Tested-by: Dhananjay Ugwekar <dhananjay.ugwekar@amd.com> Link: https://lore.kernel.org/r/20241028145542.1739160-1-superm1@kernel.org Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
2024-10-28cpufreq/amd-pstate: Align offline flow of shared memory and MSR based systemsDhananjay Ugwekar
Set min_perf to lowest_perf for shared memory systems, similar to the MSR based systems. Signed-off-by: Dhananjay Ugwekar <Dhananjay.Ugwekar@amd.com> Reviewed-by: Mario Limonciello <mario.limonciello@amd.com> Reviewed-by: Gautham R. Shenoy <gautham.shenoy@amd.com> Link: https://lore.kernel.org/r/20241023102108.5980-5-Dhananjay.Ugwekar@amd.com Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
2024-10-28cpufreq/amd-pstate: Call cppc_set_epp_perf in the reenable functionDhananjay Ugwekar
The EPP value being set in perf_ctrls.energy_perf is not being propagated to the shared memory, fix that. Signed-off-by: Dhananjay Ugwekar <Dhananjay.Ugwekar@amd.com> Reviewed-by: Mario Limonciello <mario.limonciello@amd.com> Reviewed-by: Perry Yuan <perry.yuan@amd.com> Reviewed-by: Gautham R. Shenoy <gautham.shenoy@amd.com> Link: https://lore.kernel.org/r/20241023102108.5980-4-Dhananjay.Ugwekar@amd.com Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
2024-10-28cpufreq/amd-pstate: Do not attempt to clear MSR_AMD_CPPC_ENABLEDhananjay Ugwekar
MSR_AMD_CPPC_ENABLE is a write once register, i.e. attempting to clear it is futile, it will not take effect. Hence, return if disable (0) argument is passed to the msr_cppc_enable() Signed-off-by: Dhananjay Ugwekar <Dhananjay.Ugwekar@amd.com> Reviewed-by: Mario Limonciello <mario.limonciello@amd.com> Reviewed-by: Gautham R. Shenoy <gautham.shenoy@amd.com> Link: https://lore.kernel.org/r/20241023102108.5980-3-Dhananjay.Ugwekar@amd.com Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
2024-10-28cpufreq/amd-pstate: Rename functions that enable CPPCDhananjay Ugwekar
Explicitly rename functions that enable CPPC as *_cppc_*. Signed-off-by: Dhananjay Ugwekar <Dhananjay.Ugwekar@amd.com> Reviewed-by: Mario Limonciello <mario.limonciello@amd.com> Reviewed-by: Perry Yuan <perry.yuan@amd.com> Link: https://lore.kernel.org/r/20241023102108.5980-2-Dhananjay.Ugwekar@amd.com Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
2024-10-28amd-pstate: Switch to amd-pstate by default on some Server platformsSwapnil Sapkal
Currently the default cpufreq driver for all the AMD EPYC servers is acpi-cpufreq. Going forward, switch to amd-pstate as the default driver on the AMD EPYC server platforms with CPU family 0x1A or higher. The default mode will be active mode. Testing shows that amd-pstate with active mode and performance governor provides comparable or better performance per-watt against acpi-cpufreq + performance governor. Likewise, amd-pstate with active mode and powersave governor with the energy_performance_preference=power (EPP=255) provides comparable or better performance per-watt against acpi-cpufreq + schedutil governor for a wide range of workloads. Users can still revert to using acpi-cpufreq driver on these platforms with the "amd_pstate=disable" kernel commandline parameter. Signed-off-by: Swapnil Sapkal <swapnil.sapkal@amd.com> Signed-off-by: Gautham R. Shenoy <gautham.shenoy@amd.com> Reviewed-by: Mario Limonciello <mario.limonciello@amd.com> Link: https://lore.kernel.org/r/20241021101836.9047-3-gautham.shenoy@amd.com Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
2024-10-28amd-pstate: Set min_perf to nominal_perf for active mode performance govGautham R. Shenoy
The amd-pstate driver sets CPPC_REQ.min_perf to CPPC_REQ.max_perf when in active mode with performance governor. Typically CPPC_REQ.max_perf is set to CPPC.highest_perf. This causes frequency throttling on power-limited platforms which causes performance regressions on certain classes of workloads. Hence, set the CPPC_REQ.min_perf to the CPPC.nominal_perf or CPPC_REQ.max_perf, whichever is lower of the two. Fixes: ffa5096a7c33 ("cpufreq: amd-pstate: implement Pstate EPP support for the AMD processors") Signed-off-by: Gautham R. Shenoy <gautham.shenoy@amd.com> Reviewed-by: Mario Limonciello <mario.limonciello@amd.com> Link: https://lore.kernel.org/r/20241021101836.9047-2-gautham.shenoy@amd.com Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
2024-10-28cpufreq/amd-pstate: Remove the redundant amd_pstate_set_driver() callDhananjay Ugwekar
amd_pstate_set_driver() is called twice, once in amd_pstate_init() and once as part of amd_pstate_register_driver(). Move around code and eliminate the redundancy. Signed-off-by: Dhananjay Ugwekar <Dhananjay.Ugwekar@amd.com> Reviewed-by: Mario Limonciello <mario.limonciello@amd.com> Link: https://lore.kernel.org/r/20241017100528.300143-5-Dhananjay.Ugwekar@amd.com Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
2024-10-28cpufreq/amd-pstate: Remove the switch case in amd_pstate_init()Dhananjay Ugwekar
Replace the switch case with a more readable if condition. Signed-off-by: Dhananjay Ugwekar <Dhananjay.Ugwekar@amd.com> Reviewed-by: Mario Limonciello <mario.limonciello@amd.com> Link: https://lore.kernel.org/r/20241017100528.300143-4-Dhananjay.Ugwekar@amd.com Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
2024-10-28cpufreq/amd-pstate: Call amd_pstate_set_driver() in amd_pstate_register_driver()Dhananjay Ugwekar
Replace a similar chunk of code in amd_pstate_register_driver() with amd_pstate_set_driver() call. Signed-off-by: Dhananjay Ugwekar <Dhananjay.Ugwekar@amd.com> Reviewed-by: Mario Limonciello <mario.limonciello@amd.com> Link: https://lore.kernel.org/r/20241017100528.300143-3-Dhananjay.Ugwekar@amd.com Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
2024-10-28cpufreq/amd-pstate: Call amd_pstate_register() in amd_pstate_init()Dhananjay Ugwekar
Replace a similar chunk of code in amd_pstate_init() with amd_pstate_register() call. Suggested-by: Mario Limonciello <mario.limonciello@amd.com> Signed-off-by: Dhananjay Ugwekar <Dhananjay.Ugwekar@amd.com> Reviewed-by: Mario Limonciello <mario.limonciello@amd.com> Link: https://lore.kernel.org/r/20241017100528.300143-2-Dhananjay.Ugwekar@amd.com Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
2024-10-28cpufreq/amd-pstate: Set the initial min_freq to lowest_nonlinear_freqDhananjay Ugwekar
According to the AMD architectural programmer's manual volume 2 [1], in section "17.6.4.1 CPPC_CAPABILITY_1" lowest_nonlinear_perf is described as "Reports the most energy efficient performance level (in terms of performance per watt). Above this threshold, lower performance levels generally result in increased energy efficiency. Reducing performance below this threshold does not result in total energy savings for a given computation, although it reduces instantaneous power consumption". So lowest_nonlinear_perf is the most power efficient performance level, and going below that would lead to a worse performance/watt. Also, setting the minimum frequency to lowest_nonlinear_freq (instead of lowest_freq) allows the CPU to idle at a higher frequency which leads to more time being spent in a deeper idle state (as trivial idle tasks are completed sooner). This has shown a power benefit in some systems, in other systems, power consumption has increased but so has the throughput/watt. Modify the initial policy_data->min set by cpufreq-core to lowest_nonlinear_freq, in the ->verify() callback. Also set the cpudata->req[0] to FREQ_QOS_MIN_DEFAULT_VALUE (i.e. 0), so that it also gets overriden by the check in verify function. Link: https://www.amd.com/content/dam/amd/en/documents/processor-tech-docs/programmer-references/24593.pdf [1] Signed-off-by: Dhananjay Ugwekar <Dhananjay.Ugwekar@amd.com> Reviewed-by: Mario Limonciello <mario.limonciello@amd.com> Link: https://lore.kernel.org/r/20241017053927.25285-3-Dhananjay.Ugwekar@amd.com Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
2024-10-28cpufreq/amd-pstate: Remove the redundant verify() functionDhananjay Ugwekar
Merge the two verify() callback functions and rename the cpufreq_policy_data argument for better readability. Signed-off-by: Dhananjay Ugwekar <Dhananjay.Ugwekar@amd.com> Reviewed-by: Mario Limonciello <mario.limonciello@amd.com> Reviewed-by: Gautham R. Shenoy <gautham.shenoy@amd.com> Link: https://lore.kernel.org/r/20241017053927.25285-2-Dhananjay.Ugwekar@amd.com Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
2024-10-28cpufreq/amd-pstate: Drop needless EPP initializationMario Limonciello
The EPP value doesn't need to be cached to the CPPC request in amd_pstate_epp_update_limit() because it's passed as an argument at the end to amd_pstate_set_epp() and stored at that time. Reviewed-by: Gautham R. Shenoy <gautham.shenoy@amd.com> Reviewed-by: Perry Yuan <perry.yuan@amd.com> Tested-by: Dhananjay Ugwekar <dhananjay.ugwekar@amd.com> Link: https://lore.kernel.org/r/20241012174519.897-4-mario.limonciello@amd.com Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
2024-10-28cpufreq/amd-pstate: Use amd_pstate_update_min_max_limit() for EPP limitsMario Limonciello
When the EPP updates are set the maximum capable frequency for the CPU is used to set the upper limit instead of that of the policy. Adjust amd_pstate_epp_update_limit() to reuse policy calculation code from amd_pstate_update_min_max_limit(). Reviewed-by: Gautham R. Shenoy <gautham.shenoy@amd.com> Reviewed-by: Perry Yuan <perry.yuan@amd.com> Tested-by: Dhananjay Ugwekar <dhananjay.ugwekar@amd.com> Link: https://lore.kernel.org/r/20241012174519.897-3-mario.limonciello@amd.com Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
2024-10-28cpufreq/amd-pstate: Don't update CPPC request in amd_pstate_cpu_boost_update()Mario Limonciello
When boost is changed the CPPC value is changed in amd_pstate_cpu_boost_update() but then changed again when refresh_frequency_limits() and all it's callbacks occur. The first is a pointless write, so instead just update the limits for the policy and let the policy refresh anchor everything properly. Fixes: c8c68c38b56f ("cpufreq: amd-pstate: initialize core precision boost state") Reviewed-by: Gautham R. Shenoy <gautham.shenoy@amd.com> Reviewed-by: Perry Yuan <perry.yuan@amd.com> Tested-by: Dhananjay Ugwekar <dhananjay.ugwekar@amd.com> Link: https://lore.kernel.org/r/20241012174519.897-2-mario.limonciello@amd.com Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
2024-10-28cpufreq/amd-pstate: Fix non kerneldoc commentMario Limonciello
The comment for amd_cppc_supported() isn't meant to be kernel doc. Fixes: cb817ec6673b7 ("cpufreq: amd-pstate: show CPPC debug message if CPPC is not supported") Link: https://lore.kernel.org/r/20240905162351.1345560-1-superm1@kernel.org Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
2024-10-28cpufreq/amd-pstate: Rename MSR and shared memory specific functionsDhananjay Ugwekar
Existing function names "cppc_*" and "pstate_*" for shared memory and MSR based systems are not intuitive enough, replace them with "shmem_*" and "msr_*" respectively. Signed-off-by: Dhananjay Ugwekar <Dhananjay.Ugwekar@amd.com> Reviewed-by: Mario Limonciello <mario.limonciello@amd.com> Link: https://lore.kernel.org/r/20240917091434.10685-1-Dhananjay.Ugwekar@amd.com Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
2024-10-25x86/cpufeatures: Rename X86_FEATURE_FAST_CPPC to have AMD prefixMario Limonciello
This feature is an AMD unique feature of some processors, so put AMD into the name. Signed-off-by: Mario Limonciello <mario.limonciello@amd.com> Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de> Link: https://lore.kernel.org/r/20241025171459.1093-2-mario.limonciello@amd.com
2024-10-15cpufreq/amd-pstate: Use nominal perf for limits when boost is disabledMario Limonciello
When boost has been disabled the limit for perf should be nominal perf not the highest perf. Using the latter to do calculations will lead to incorrect values that are still above nominal. Fixes: ad4caad58d91 ("cpufreq: amd-pstate: Merge amd_pstate_highest_perf_set() into amd_get_boost_ratio_numerator()") Reported-by: Peter Jung <ptr1337@cachyos.org> Closes: https://bugzilla.kernel.org/show_bug.cgi?id=219348 Reviewed-by: Perry Yuan <perry.yuan@amd.com> Reviewed-by: Gautham R. Shenoy <gautham.shenoy@amd.com> Tested-by: Dhananjay Ugwekar <dhananjay.ugwekar@amd.com> Link: https://lore.kernel.org/r/20241012174519.897-1-mario.limonciello@amd.com Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
2024-10-07cpufreq/amd-pstate: Fix amd_pstate mode switch on shared memory systemsDhananjay Ugwekar
While switching the driver mode between active and passive, Collaborative Processor Performance Control (CPPC) is disabled in amd_pstate_unregister_driver(). But, it is not enabled back while registering the new driver (passive or active). This leads to the new driver mode not working correctly, so enable it back in amd_pstate_register_driver(). Fixes: 3ca7bc818d8c ("cpufreq: amd-pstate: Add guided mode control support via sysfs") Signed-off-by: Dhananjay Ugwekar <Dhananjay.Ugwekar@amd.com> Reviewed-by: Mario Limonciello <mario.limonciello@amd.com> Link: https://lore.kernel.org/r/20241004122303.94283-1-Dhananjay.Ugwekar@amd.com Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
generated by cgit (git 2.34.1) at 2025-07-31 01:04:41 +0000