From 14416a42f37d3455e6de7d249df9a76b40a456bf Mon Sep 17 00:00:00 2001 From: Peter Jung Date: Fri, 21 Jun 2024 15:31:56 +0200 Subject: [PATCH 02/10] amd-pstate Signed-off-by: Peter Jung --- drivers/cpufreq/amd-pstate.c | 115 +++++++++++++++++++---------------- drivers/cpufreq/amd-pstate.h | 14 +++-- 2 files changed, 70 insertions(+), 59 deletions(-) diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c index 6c989d859b39..c08463f8dcac 100644 --- a/drivers/cpufreq/amd-pstate.c +++ b/drivers/cpufreq/amd-pstate.c @@ -85,15 +85,6 @@ struct quirk_entry { u32 lowest_freq; }; -/* - * TODO: We need more time to fine tune processors with shared memory solution - * with community together. - * - * There are some performance drops on the CPU benchmarks which reports from - * Suse. We are co-working with them to fine tune the shared memory solution. So - * we disable it by default to go acpi-cpufreq on these processors and add a - * module parameter to be able to enable it manually for debugging. - */ static struct cpufreq_driver *current_pstate_driver; static struct cpufreq_driver amd_pstate_driver; static struct cpufreq_driver amd_pstate_epp_driver; @@ -688,26 +679,6 @@ static void amd_pstate_adjust_perf(unsigned int cpu, cpufreq_cpu_put(policy); } -static int amd_get_min_freq(struct amd_cpudata *cpudata) -{ - return READ_ONCE(cpudata->min_freq); -} - -static int amd_get_max_freq(struct amd_cpudata *cpudata) -{ - return READ_ONCE(cpudata->max_freq); -} - -static int amd_get_nominal_freq(struct amd_cpudata *cpudata) -{ - return READ_ONCE(cpudata->nominal_freq); -} - -static int amd_get_lowest_nonlinear_freq(struct amd_cpudata *cpudata) -{ - return READ_ONCE(cpudata->lowest_nonlinear_freq); -} - static int amd_pstate_set_boost(struct cpufreq_policy *policy, int state) { struct amd_cpudata *cpudata = policy->driver_data; @@ -860,7 +831,37 @@ static void amd_pstate_update_limits(unsigned int cpu) mutex_unlock(&amd_pstate_driver_lock); } -/** +/* + * Get pstate transition delay time from ACPI tables that firmware set + * instead of using hardcode value directly. + */ +static u32 amd_pstate_get_transition_delay_us(unsigned int cpu) +{ + u32 transition_delay_ns; + + transition_delay_ns = cppc_get_transition_latency(cpu); + if (transition_delay_ns == CPUFREQ_ETERNAL) + return AMD_PSTATE_TRANSITION_DELAY; + + return transition_delay_ns / NSEC_PER_USEC; +} + +/* + * Get pstate transition latency value from ACPI tables that firmware + * set instead of using hardcode value directly. + */ +static u32 amd_pstate_get_transition_latency(unsigned int cpu) +{ + u32 transition_latency; + + transition_latency = cppc_get_transition_latency(cpu); + if (transition_latency == CPUFREQ_ETERNAL) + return AMD_PSTATE_TRANSITION_LATENCY; + + return transition_latency; +} + +/* * amd_pstate_init_freq: Initialize the max_freq, min_freq, * nominal_freq and lowest_nonlinear_freq for * the @cpudata object. @@ -881,7 +882,6 @@ static int amd_pstate_init_freq(struct amd_cpudata *cpudata) u32 boost_ratio, lowest_nonlinear_ratio; struct cppc_perf_caps cppc_perf; - ret = cppc_get_perf_caps(cpudata->cpu, &cppc_perf); if (ret) return ret; @@ -917,7 +917,7 @@ static int amd_pstate_init_freq(struct amd_cpudata *cpudata) static int amd_pstate_cpu_init(struct cpufreq_policy *policy) { - int min_freq, max_freq, nominal_freq, lowest_nonlinear_freq, ret; + int min_freq, max_freq, nominal_freq, ret; struct device *dev; struct amd_cpudata *cpudata; @@ -946,20 +946,21 @@ static int amd_pstate_cpu_init(struct cpufreq_policy *policy) if (ret) goto free_cpudata1; - min_freq = amd_get_min_freq(cpudata); - max_freq = amd_get_max_freq(cpudata); - nominal_freq = amd_get_nominal_freq(cpudata); - lowest_nonlinear_freq = amd_get_lowest_nonlinear_freq(cpudata); + min_freq = READ_ONCE(cpudata->min_freq); + max_freq = READ_ONCE(cpudata->max_freq); + nominal_freq = READ_ONCE(cpudata->nominal_freq); - if (min_freq < 0 || max_freq < 0 || min_freq > max_freq) { - dev_err(dev, "min_freq(%d) or max_freq(%d) value is incorrect\n", - min_freq, max_freq); + if (min_freq <= 0 || max_freq <= 0 || + nominal_freq <= 0 || min_freq > max_freq) { + dev_err(dev, + "min_freq(%d) or max_freq(%d) or nominal_freq (%d) value is incorrect, check _CPC in ACPI tables\n", + min_freq, max_freq, nominal_freq); ret = -EINVAL; goto free_cpudata1; } - policy->cpuinfo.transition_latency = AMD_PSTATE_TRANSITION_LATENCY; - policy->transition_delay_us = AMD_PSTATE_TRANSITION_DELAY; + policy->cpuinfo.transition_latency = amd_pstate_get_transition_latency(policy->cpu); + policy->transition_delay_us = amd_pstate_get_transition_delay_us(policy->cpu); policy->min = min_freq; policy->max = max_freq; @@ -1052,7 +1053,7 @@ static ssize_t show_amd_pstate_max_freq(struct cpufreq_policy *policy, int max_freq; struct amd_cpudata *cpudata = policy->driver_data; - max_freq = amd_get_max_freq(cpudata); + max_freq = READ_ONCE(cpudata->max_freq); if (max_freq < 0) return max_freq; @@ -1065,7 +1066,7 @@ static ssize_t show_amd_pstate_lowest_nonlinear_freq(struct cpufreq_policy *poli int freq; struct amd_cpudata *cpudata = policy->driver_data; - freq = amd_get_lowest_nonlinear_freq(cpudata); + freq = READ_ONCE(cpudata->lowest_nonlinear_freq); if (freq < 0) return freq; @@ -1376,7 +1377,7 @@ static bool amd_pstate_acpi_pm_profile_undefined(void) static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy) { - int min_freq, max_freq, nominal_freq, lowest_nonlinear_freq, ret; + int min_freq, max_freq, nominal_freq, ret; struct amd_cpudata *cpudata; struct device *dev; u64 value; @@ -1407,13 +1408,14 @@ static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy) if (ret) goto free_cpudata1; - min_freq = amd_get_min_freq(cpudata); - max_freq = amd_get_max_freq(cpudata); - nominal_freq = amd_get_nominal_freq(cpudata); - lowest_nonlinear_freq = amd_get_lowest_nonlinear_freq(cpudata); - if (min_freq < 0 || max_freq < 0 || min_freq > max_freq) { - dev_err(dev, "min_freq(%d) or max_freq(%d) value is incorrect\n", - min_freq, max_freq); + min_freq = READ_ONCE(cpudata->min_freq); + max_freq = READ_ONCE(cpudata->max_freq); + nominal_freq = READ_ONCE(cpudata->nominal_freq); + if (min_freq <= 0 || max_freq <= 0 || + nominal_freq <= 0 || min_freq > max_freq) { + dev_err(dev, + "min_freq(%d) or max_freq(%d) or nominal_freq(%d) value is incorrect, check _CPC in ACPI tables\n", + min_freq, max_freq, nominal_freq); ret = -EINVAL; goto free_cpudata1; } @@ -1462,6 +1464,13 @@ static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy) static int amd_pstate_epp_cpu_exit(struct cpufreq_policy *policy) { + struct amd_cpudata *cpudata = policy->driver_data; + + if (cpudata) { + kfree(cpudata); + policy->driver_data = NULL; + } + pr_debug("CPU %d exiting\n", policy->cpu); return 0; } @@ -1750,11 +1759,9 @@ static int __init amd_pstate_init(void) /* Disable on the following configs by default: * 1. Undefined platforms * 2. Server platforms - * 3. Shared memory designs */ if (amd_pstate_acpi_pm_profile_undefined() || - amd_pstate_acpi_pm_profile_server() || - !boot_cpu_has(X86_FEATURE_CPPC)) { + amd_pstate_acpi_pm_profile_server()) { pr_info("driver load is disabled, boot with specific mode to enable this\n"); return -ENODEV; } diff --git a/drivers/cpufreq/amd-pstate.h b/drivers/cpufreq/amd-pstate.h index bc341f35908d..e6a28e7f4dbf 100644 --- a/drivers/cpufreq/amd-pstate.h +++ b/drivers/cpufreq/amd-pstate.h @@ -42,13 +42,17 @@ struct amd_aperf_mperf { * @lowest_perf: the absolute lowest performance level of the processor * @prefcore_ranking: the preferred core ranking, the higher value indicates a higher * priority. - * @max_freq: the frequency that mapped to highest_perf - * @min_freq: the frequency that mapped to lowest_perf - * @nominal_freq: the frequency that mapped to nominal_perf - * @lowest_nonlinear_freq: the frequency that mapped to lowest_nonlinear_perf + * @min_limit_perf: Cached value of the performance corresponding to policy->min + * @max_limit_perf: Cached value of the performance corresponding to policy->max + * @min_limit_freq: Cached value of policy->min (in khz) + * @max_limit_freq: Cached value of policy->max (in khz) + * @max_freq: the frequency (in khz) that mapped to highest_perf + * @min_freq: the frequency (in khz) that mapped to lowest_perf + * @nominal_freq: the frequency (in khz) that mapped to nominal_perf + * @lowest_nonlinear_freq: the frequency (in khz) that mapped to lowest_nonlinear_perf * @cur: Difference of Aperf/Mperf/tsc count between last and current sample * @prev: Last Aperf/Mperf/tsc count value read from register - * @freq: current cpu frequency value + * @freq: current cpu frequency value (in khz) * @boost_supported: check whether the Processor or SBIOS supports boost mode * @hw_prefcore: check whether HW supports preferred core featue. * Only when hw_prefcore and early prefcore param are true, -- 2.45.2