cpufreq: intel_pstate: Rework iowait boosting to be less aggressive

The current iowait boosting mechanism in intel_pstate_update_util()
is quite aggressive, as it goes to the maximum P-state right away,
and may cause excessive amounts of energy to be used, which is not
desirable and arguably isn't necessary too.

Follow commit a5a0809bc58e ("cpufreq: schedutil: Make iowait boost
more energy efficient") that reworked the analogous iowait boost
mechanism in the schedutil governor and make the iowait boosting
in intel_pstate_update_util() work along the same lines.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

1 files changed, 18 insertions, 18 deletions

diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 9a6cb3a1be50..002f5169d4eb 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -50,6 +50,8 @@
 #define int_tofp(X) ((int64_t)(X) << FRAC_BITS)
 #define fp_toint(X) ((X) >> FRAC_BITS)
 
+#define ONE_EIGHTH_FP ((int64_t)1 << (FRAC_BITS - 3))
+
 #define EXT_BITS 6
 #define EXT_FRAC_BITS (EXT_BITS + FRAC_BITS)
 #define fp_ext_toint(X) ((X) >> EXT_FRAC_BITS)
@@ -1671,17 +1673,14 @@ static inline int32_t get_avg_pstate(struct cpudata *cpu)
 static inline int32_t get_target_pstate(struct cpudata *cpu)
 {
 	struct sample *sample = &cpu->sample;
-	int32_t busy_frac, boost;
+	int32_t busy_frac;
 	int target, avg_pstate;
 
 	busy_frac = div_fp(sample->mperf << cpu->aperf_mperf_shift,
 			   sample->tsc);
 
-	boost = cpu->iowait_boost;
-	cpu->iowait_boost >>= 1;
-
-	if (busy_frac < boost)
-		busy_frac = boost;
+	if (busy_frac < cpu->iowait_boost)
+		busy_frac = cpu->iowait_boost;
 
 	sample->busy_scaled = busy_frac * 100;
 
@@ -1758,29 +1757,30 @@ static void intel_pstate_update_util(struct update_util_data *data, u64 time,
 	if (smp_processor_id() != cpu->cpu)
 		return;
 
+	delta_ns = time - cpu->last_update;
 	if (flags & SCHED_CPUFREQ_IOWAIT) {
-		cpu->iowait_boost = int_tofp(1);
-		cpu->last_update = time;
-		/*
-		 * The last time the busy was 100% so P-state was max anyway
-		 * so avoid overhead of computation.
-		 */
-		if (fp_toint(cpu->sample.busy_scaled) == 100)
-			return;
-
-		goto set_pstate;
+		/* Start over if the CPU may have been idle. */
+		if (delta_ns > TICK_NSEC) {
+			cpu->iowait_boost = ONE_EIGHTH_FP;
+		} else if (cpu->iowait_boost) {
+			cpu->iowait_boost <<= 1;
+			if (cpu->iowait_boost > int_tofp(1))
+				cpu->iowait_boost = int_tofp(1);
+		} else {
+			cpu->iowait_boost = ONE_EIGHTH_FP;
+		}
 	} else if (cpu->iowait_boost) {
 		/* Clear iowait_boost if the CPU may have been idle. */
-		delta_ns = time - cpu->last_update;
 		if (delta_ns > TICK_NSEC)
 			cpu->iowait_boost = 0;
+		else
+			cpu->iowait_boost >>= 1;
 	}
 	cpu->last_update = time;
 	delta_ns = time - cpu->sample.time;
 	if ((s64)delta_ns < INTEL_PSTATE_SAMPLING_INTERVAL)
 		return;
 
-set_pstate:
 	if (intel_pstate_sample(cpu, time))
 		intel_pstate_adjust_pstate(cpu);
 }