summaryrefslogtreecommitdiff
path: root/drivers/cpufreq/intel_pstate.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2016-10-14 12:46:13 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2016-10-14 12:46:13 -0700
commitef98988ba369da88bab8a4d457407e71bbe160fa (patch)
treed421d3401aab6d4f654f85707c584bdf6fe3d0ec /drivers/cpufreq/intel_pstate.c
parentf34d3606f76a8121b9d4940d2dd436bebeb2f9d7 (diff)
parent383731d98e768e15f4a8d69ae87957b933323ed7 (diff)
downloadlinux-sh-ef98988ba369da88bab8a4d457407e71bbe160fa.tar.gz
Merge tag 'pm-extra-4.9-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm
Pull more power management updates from Rafael Wysocki: "This includes a couple of fixes for cpufreq regressions introduced in 4.8, a rework of the intel_pstate algorithm used on Atom processors (that took some time to test) plus a fix and a couple of cleanups in that driver, a CPPC cpufreq driver fix, and a some devfreq fixes and cleanups (core and exynos-nocp). Specifics: - Fix two cpufreq regressions causing undesirable changes in behavior to appear (one in the core and one in the conservative governor) introduced during the 4.8 cycle (Aaro Koskinen, Rafael Wysocki). - Fix the way the intel_pstate driver accesses MSRs related to the hardware-managed P-states (HWP) feature during the initialization which currently is unsafe and may cause the processor to generate a general protection fault (Srinivas Pandruvada). - Rework the intel_pstate's P-state selection algorithm used on Atom processors to avoid known problems with the current one and to make the computation more straightforward, which also happens to improve performance in multiple benchmarks a bit (Rafael Wysocki). - Improve two comments in the intel_pstate driver (Rafael Wysocki). - Fix the desired performance computation in the CPPC cpufreq driver (Hoan Tran). - Fix the devfreq core to avoid printing misleading error messages in some cases (Tobias Jakobi). - Fix the error code path in devfreq_add_device() to use proper locking around list modifications (Axel Lin). - Fix a build failure and remove a couple of redundant updates of variables in the exynos-nocp devfreq driver (Axel Lin)" * tag 'pm-extra-4.9-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: cpufreq: CPPC: Correct desired_perf calculation cpufreq: conservative: Fix next frequency selection cpufreq: skip invalid entries when searching the frequency cpufreq: intel_pstate: Fix struct pstate_adjust_policy kerneldoc cpufreq: intel_pstate: Proportional algorithm for Atom PM / devfreq: Skip status update on uninitialized previous_freq PM / devfreq: Add proper locking around list_del() PM / devfreq: exynos-nocp: Remove redundant code PM / devfreq: exynos-nocp: Select REGMAP_MMIO cpufreq: intel_pstate: Clarify comment in get_target_pstate_use_performance() cpufreq: intel_pstate: Fix unsafe HWP MSR access
Diffstat (limited to 'drivers/cpufreq/intel_pstate.c')
-rw-r--r--drivers/cpufreq/intel_pstate.c43
1 files changed, 32 insertions, 11 deletions
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 806f2039571e..f535f8123258 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -225,7 +225,7 @@ struct cpudata {
static struct cpudata **all_cpu_data;
/**
- * struct pid_adjust_policy - Stores static PID configuration data
+ * struct pstate_adjust_policy - Stores static PID configuration data
* @sample_rate_ms: PID calculation sample rate in ms
* @sample_rate_ns: Sample rate calculation in ns
* @deadband: PID deadband
@@ -562,12 +562,12 @@ static void intel_pstate_hwp_set(const struct cpumask *cpumask)
int min, hw_min, max, hw_max, cpu, range, adj_range;
u64 value, cap;
- rdmsrl(MSR_HWP_CAPABILITIES, cap);
- hw_min = HWP_LOWEST_PERF(cap);
- hw_max = HWP_HIGHEST_PERF(cap);
- range = hw_max - hw_min;
-
for_each_cpu(cpu, cpumask) {
+ rdmsrl_on_cpu(cpu, MSR_HWP_CAPABILITIES, &cap);
+ hw_min = HWP_LOWEST_PERF(cap);
+ hw_max = HWP_HIGHEST_PERF(cap);
+ range = hw_max - hw_min;
+
rdmsrl_on_cpu(cpu, MSR_HWP_REQUEST, &value);
adj_range = limits->min_perf_pct * range / 100;
min = hw_min + adj_range;
@@ -1232,6 +1232,7 @@ static inline int32_t get_target_pstate_use_cpu_load(struct cpudata *cpu)
{
struct sample *sample = &cpu->sample;
int32_t busy_frac, boost;
+ int target, avg_pstate;
busy_frac = div_fp(sample->mperf, sample->tsc);
@@ -1242,7 +1243,26 @@ static inline int32_t get_target_pstate_use_cpu_load(struct cpudata *cpu)
busy_frac = boost;
sample->busy_scaled = busy_frac * 100;
- return get_avg_pstate(cpu) - pid_calc(&cpu->pid, sample->busy_scaled);
+
+ target = limits->no_turbo || limits->turbo_disabled ?
+ cpu->pstate.max_pstate : cpu->pstate.turbo_pstate;
+ target += target >> 2;
+ target = mul_fp(target, busy_frac);
+ if (target < cpu->pstate.min_pstate)
+ target = cpu->pstate.min_pstate;
+
+ /*
+ * If the average P-state during the previous cycle was higher than the
+ * current target, add 50% of the difference to the target to reduce
+ * possible performance oscillations and offset possible performance
+ * loss related to moving the workload from one CPU to another within
+ * a package/module.
+ */
+ avg_pstate = get_avg_pstate(cpu);
+ if (avg_pstate > target)
+ target += (avg_pstate - target) >> 1;
+
+ return target;
}
static inline int32_t get_target_pstate_use_performance(struct cpudata *cpu)
@@ -1251,10 +1271,11 @@ static inline int32_t get_target_pstate_use_performance(struct cpudata *cpu)
u64 duration_ns;
/*
- * perf_scaled is the average performance during the last sampling
- * period scaled by the ratio of the maximum P-state to the P-state
- * requested last time (in percent). That measures the system's
- * response to the previous P-state selection.
+ * perf_scaled is the ratio of the average P-state during the last
+ * sampling period to the P-state requested last time (in percent).
+ *
+ * That measures the system's response to the previous P-state
+ * selection.
*/
max_pstate = cpu->pstate.max_pstate_physical;
current_pstate = cpu->pstate.current_pstate;