From 6cacd115a8aafdc3f0f47c30af9d3a55a18074db Mon Sep 17 00:00:00 2001 From: Srinivas Pandruvada Date: Sun, 29 May 2016 23:31:23 -0700 Subject: cpufreq: intel_pstate: Downgrade print level for _PPC Downgrade pr_info to pr_debug for the "_PPC limits will be enforced" message. In server systems with many cores this message is annoying. Signed-off-by: Srinivas Pandruvada [ rjw: Changelog ] Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/intel_pstate.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/cpufreq/intel_pstate.c') diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 3a9c4325d6e2..0d159b513469 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -449,7 +449,7 @@ static void intel_pstate_init_acpi_perf_limits(struct cpufreq_policy *policy) cpu->acpi_perf_data.states[0].core_frequency = policy->cpuinfo.max_freq / 1000; cpu->valid_pss_table = true; - pr_info("_PPC limits will be enforced\n"); + pr_debug("_PPC limits will be enforced\n"); return; -- cgit From 2c2c1af4497514da1be2b571066859701dd79231 Mon Sep 17 00:00:00 2001 From: Srinivas Pandruvada Date: Tue, 7 Jun 2016 17:38:52 -0700 Subject: cpufreq: intel_pstate: Fix code ordering in intel_pstate_set_policy() The limits->max_perf is rounded_up but immediately overwritten by another assignment to limits->max_perf. Move that operation to the correct location. While here also added a pr_debug() call in ->set_policy to aid in debugging. Fixes: 785ee2788141 (cpufreq: intel_pstate: Fix limits->max_perf rounding error) Signed-off-by: Srinivas Pandruvada [ rjw : Subject & changelog ] Cc: 4.4+ # 4.4+ Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/intel_pstate.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'drivers/cpufreq/intel_pstate.c') diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 0d159b513469..724b9056aa6b 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -1460,6 +1460,9 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy) intel_pstate_clear_update_util_hook(policy->cpu); + pr_debug("set_policy cpuinfo.max %u policy->max %u\n", + policy->cpuinfo.max_freq, policy->max); + cpu = all_cpu_data[0]; if (cpu->pstate.max_pstate_physical > cpu->pstate.max_pstate && policy->max < policy->cpuinfo.max_freq && @@ -1495,13 +1498,13 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy) limits->max_sysfs_pct); limits->max_perf_pct = max(limits->min_policy_pct, limits->max_perf_pct); - limits->max_perf = round_up(limits->max_perf, FRAC_BITS); /* Make sure min_perf_pct <= max_perf_pct */ limits->min_perf_pct = min(limits->max_perf_pct, limits->min_perf_pct); limits->min_perf = div_fp(limits->min_perf_pct, 100); limits->max_perf = div_fp(limits->max_perf_pct, 100); + limits->max_perf = round_up(limits->max_perf, FRAC_BITS); out: intel_pstate_set_update_util_hook(policy->cpu); -- cgit From 983e600e88835f0321d1a0ea06f52d48b7b5a544 Mon Sep 17 00:00:00 2001 From: Srinivas Pandruvada Date: Tue, 7 Jun 2016 17:38:53 -0700 Subject: cpufreq: intel_pstate: Fix ->set_policy() interface for no_turbo When turbo is disabled, the ->set_policy() interface is broken. For example, when turbo is disabled and cpuinfo.max = 2900000 (full max turbo frequency), setting the limits results in frequency less than the requested one: Set 1000000 KHz results in 0700000 KHz Set 1500000 KHz results in 1100000 KHz Set 2000000 KHz results in 1500000 KHz This is because the limits->max_perf fraction is calculated using the max turbo frequency as the reference, but when the max P-State is capped in intel_pstate_get_min_max(), the reference is not the max turbo P-State. This results in reducing max P-State. One option is to always use max turbo as reference for calculating limits. But this will not be correct. By definition the intel_pstate sysfs limits, shows percentage of available performance. So when BIOS has disabled turbo, the available performance is max non turbo. So the max_perf_pct should still show 100%. Signed-off-by: Srinivas Pandruvada [ rjw : Subject & changelog, rewrite in fewer lines of code ] Cc: All applicable Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/intel_pstate.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'drivers/cpufreq/intel_pstate.c') diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 724b9056aa6b..ee367e9b7d2e 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -1561,8 +1561,11 @@ static int intel_pstate_cpu_init(struct cpufreq_policy *policy) /* cpuinfo and default policy values */ policy->cpuinfo.min_freq = cpu->pstate.min_pstate * cpu->pstate.scaling; - policy->cpuinfo.max_freq = - cpu->pstate.turbo_pstate * cpu->pstate.scaling; + update_turbo_state(); + policy->cpuinfo.max_freq = limits->turbo_disabled ? + cpu->pstate.max_pstate : cpu->pstate.turbo_pstate; + policy->cpuinfo.max_freq *= cpu->pstate.scaling; + intel_pstate_init_acpi_perf_limits(policy); policy->cpuinfo.transition_latency = CPUFREQ_ETERNAL; cpumask_set_cpu(policy->cpu, policy->cpus); -- cgit From b00345d1994d588fa2687e1238fcd542f0320cba Mon Sep 17 00:00:00 2001 From: Srinivas Pandruvada Date: Tue, 14 Jun 2016 23:12:59 -0700 Subject: cpufreq: intel_pstate: Adjust _PSS[0] freqeuency if needed The maximum turbo P-State used by the intel_pstate driver may be limited by ACPI _PSS table entry 0. After commit 9522a2ff9cde (cpufreq: intel_pstate: Enforce _PPC limits), the maximum performance on servers will be capped by the _PSS table entry 0 by default. Even though that is formally correct, it may lead to preformance regressions in some cases. Namely, if the _PSS table entry 0 is not the maximum turbo P-State, performance measured after commit 9522a2ff9cde will not match the performance measured before that commit on the same system. For this reason, modify the code to always use the maximum turbo frequency as the one that corresponds to _PSS table entry 0 if turbo is enabled in the BIOS. This way, the performance levels from before commit 9522a2ff9cde will be restored on the affected systems. Fixes: 9522a2ff9cde (cpufreq: intel_pstate: Enforce _PPC limits) Suggested-by: Rafael J. Wysocki Signed-off-by: Srinivas Pandruvada [ rjw : Changelog ] Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/intel_pstate.c | 22 ++-------------------- 1 file changed, 2 insertions(+), 20 deletions(-) (limited to 'drivers/cpufreq/intel_pstate.c') diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index ee367e9b7d2e..fe9dc17ea873 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -372,26 +372,9 @@ static bool intel_pstate_get_ppc_enable_status(void) return acpi_ppc; } -/* - * The max target pstate ratio is a 8 bit value in both PLATFORM_INFO MSR and - * in TURBO_RATIO_LIMIT MSR, which pstate driver stores in max_pstate and - * max_turbo_pstate fields. The PERF_CTL MSR contains 16 bit value for P state - * ratio, out of it only high 8 bits are used. For example 0x1700 is setting - * target ratio 0x17. The _PSS control value stores in a format which can be - * directly written to PERF_CTL MSR. But in intel_pstate driver this shift - * occurs during write to PERF_CTL (E.g. for cores core_set_pstate()). - * This function converts the _PSS control value to intel pstate driver format - * for comparison and assignment. - */ -static int convert_to_native_pstate_format(struct cpudata *cpu, int index) -{ - return cpu->acpi_perf_data.states[index].control >> 8; -} - static void intel_pstate_init_acpi_perf_limits(struct cpufreq_policy *policy) { struct cpudata *cpu; - int turbo_pss_ctl; int ret; int i; @@ -441,11 +424,10 @@ static void intel_pstate_init_acpi_perf_limits(struct cpufreq_policy *policy) * max frequency, which will cause a reduced performance as * this driver uses real max turbo frequency as the max * frequency. So correct this frequency in _PSS table to - * correct max turbo frequency based on the turbo ratio. + * correct max turbo frequency based on the turbo state. * Also need to convert to MHz as _PSS freq is in MHz. */ - turbo_pss_ctl = convert_to_native_pstate_format(cpu, 0); - if (turbo_pss_ctl > cpu->pstate.max_pstate) + if (!limits->turbo_disabled) cpu->acpi_perf_data.states[0].core_frequency = policy->cpuinfo.max_freq / 1000; cpu->valid_pss_table = true; -- cgit From 5ab666e09541e64ce2fd73411c3b5b9e4ad334b1 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 27 Jun 2016 23:47:15 +0200 Subject: intel_pstate: Do not clear utilization update hooks on policy changes intel_pstate_set_policy() is invoked by the cpufreq core during driver initialization, on changes of policy attributes (minimim and maximum frequency, for example) via sysfs and via CPU notifications from the platform firmware. On some platforms the latter may occur relatively often. Commit bb6ab52f2bef (intel_pstate: Do not set utilization update hook too early) made intel_pstate_set_policy() clear the CPU's utilization update hook before updating the policy attributes for it (and set the hook again after doind that), but that involves invoking synchronize_sched() and adds overhead to the CPU notifications mentioned above and to the sched-RCU handling in general. That extra overhead is arguably not necessary, because updating policy attributes when the CPU's utilization update hook is active should not lead to any adverse effects, so drop the clearing of the hook from intel_pstate_set_policy() and make it check if the hook has been set already when attempting to set it. Fixes: bb6ab52f2bef (intel_pstate: Do not set utilization update hook too early) Reported-by: Jisheng Zhang Tested-by: Jisheng Zhang Tested-by: Doug Smythies Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/intel_pstate.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'drivers/cpufreq/intel_pstate.c') diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index fe9dc17ea873..1fa1a32928d7 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -1400,6 +1400,9 @@ static void intel_pstate_set_update_util_hook(unsigned int cpu_num) { struct cpudata *cpu = all_cpu_data[cpu_num]; + if (cpu->update_util_set) + return; + /* Prevent intel_pstate_update_util() from using stale data. */ cpu->sample.time = 0; cpufreq_add_update_util_hook(cpu_num, &cpu->update_util, @@ -1440,8 +1443,6 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy) if (!policy->cpuinfo.max_freq) return -ENODEV; - intel_pstate_clear_update_util_hook(policy->cpu); - pr_debug("set_policy cpuinfo.max %u policy->max %u\n", policy->cpuinfo.max_freq, policy->max); -- cgit