Merge branches 'pm-cpuidle' and 'pm-cpufreq'

Merge CPU power management updates for 6.6-rc1:

 - Rework the menu and teo cpuidle governors to avoid calling
   tick_nohz_get_sleep_length(), which is likely to become quite
   expensive going forward, too often and improve making decisions
   regarding whether or not to stop the scheduler tick in the teo
   governor (Rafael Wysocki).

 - Improve the performance of cpufreq_stats_create_table() in some
   cases (Liao Chang).

 - Fix two issues in the amd-pstate-ut cpufreq driver (Swapnil Sapkal).

 - Use clamp() helper macro to improve the code readability in
   cpufreq_verify_within_limits() (Liao Chang).

 - Set stale CPU frequency to minimum in intel_pstate (Doug Smythies).

* pm-cpuidle:
  cpuidle: teo: Avoid unnecessary variable assignments
  cpuidle: menu: Skip tick_nohz_get_sleep_length() call in some cases
  cpuidle: teo: Gather statistics regarding whether or not to stop the tick
  cpuidle: teo: Skip tick_nohz_get_sleep_length() call in some cases
  cpuidle: teo: Do not call tick_nohz_get_sleep_length() upfront
  cpuidle: teo: Drop utilized from struct teo_cpu
  cpuidle: teo: Avoid stopping the tick unnecessarily when bailing out
  cpuidle: teo: Update idle duration estimate when choosing shallower state

* pm-cpufreq:
  cpufreq: amd-pstate-ut: Fix kernel panic when loading the driver
  cpufreq: amd-pstate-ut: Remove module parameter access
  cpufreq: Use clamp() helper macro to improve the code readability
  cpufreq: intel_pstate: set stale CPU frequency to minimum
  cpufreq: stats: Improve the performance of cpufreq_stats_create_table()

Author: rafaeljw

drivers/cpufreq/amd-pstate-ut.c

@@ -64,27 +64,9 @@ static struct amd_pstate_ut_struct amd_pstate_ut_cases[] = {
 static bool get_shared_mem(void)
 {
 	bool result = false;
-	char path[] = "/sys/module/amd_pstate/parameters/shared_mem";
-	char buf[5] = {0};
-	struct file *filp = NULL;
-	loff_t pos = 0;
-	ssize_t ret;
-
-	if (!boot_cpu_has(X86_FEATURE_CPPC)) {
-		filp = filp_open(path, O_RDONLY, 0);
-		if (IS_ERR(filp))
-			pr_err("%s unable to open %s file!\n", __func__, path);
-		else {
-			ret = kernel_read(filp, &buf, sizeof(buf), &pos);
-			if (ret < 0)
-				pr_err("%s read %s file fail ret=%ld!\n",
-					__func__, path, (long)ret);
-			filp_close(filp, NULL);
-		}
 
-		if ('Y' == *buf)
-			result = true;
-	}
+	if (!boot_cpu_has(X86_FEATURE_CPPC))
+		result = true;
 
 	return result;
 }
@@ -158,7 +140,7 @@ static void amd_pstate_ut_check_perf(u32 index)
 			if (ret) {
 				amd_pstate_ut_cases[index].result = AMD_PSTATE_UT_RESULT_FAIL;
 				pr_err("%s cppc_get_perf_caps ret=%d error!\n", __func__, ret);
-				return;
+				goto skip_test;
 			}
 
 			nominal_perf = cppc_perf.nominal_perf;
@@ -169,7 +151,7 @@ static void amd_pstate_ut_check_perf(u32 index)
 			if (ret) {
 				amd_pstate_ut_cases[index].result = AMD_PSTATE_UT_RESULT_FAIL;
 				pr_err("%s read CPPC_CAP1 ret=%d error!\n", __func__, ret);
-				return;
+				goto skip_test;
 			}
 
 			nominal_perf = AMD_CPPC_NOMINAL_PERF(cap1);
@@ -187,7 +169,7 @@ static void amd_pstate_ut_check_perf(u32 index)
 				nominal_perf, cpudata->nominal_perf,
 				lowest_nonlinear_perf, cpudata->lowest_nonlinear_perf,
 				lowest_perf, cpudata->lowest_perf);
-			return;
+			goto skip_test;
 		}
 
 		if (!((highest_perf >= nominal_perf) &&
@@ -198,11 +180,15 @@ static void amd_pstate_ut_check_perf(u32 index)
 			pr_err("%s cpu%d highest=%d >= nominal=%d > lowest_nonlinear=%d > lowest=%d > 0, the formula is incorrect!\n",
 				__func__, cpu, highest_perf, nominal_perf,
 				lowest_nonlinear_perf, lowest_perf);
-			return;
+			goto skip_test;
 		}
+		cpufreq_cpu_put(policy);
 	}
 
 	amd_pstate_ut_cases[index].result = AMD_PSTATE_UT_RESULT_PASS;
+	return;
+skip_test:
+	cpufreq_cpu_put(policy);
 }
 
 /*
@@ -230,14 +216,14 @@ static void amd_pstate_ut_check_freq(u32 index)
 			pr_err("%s cpu%d max=%d >= nominal=%d > lowest_nonlinear=%d > min=%d > 0, the formula is incorrect!\n",
 				__func__, cpu, cpudata->max_freq, cpudata->nominal_freq,
 				cpudata->lowest_nonlinear_freq, cpudata->min_freq);
-			return;
+			goto skip_test;
 		}
 
 		if (cpudata->min_freq != policy->min) {
 			amd_pstate_ut_cases[index].result = AMD_PSTATE_UT_RESULT_FAIL;
 			pr_err("%s cpu%d cpudata_min_freq=%d policy_min=%d, they should be equal!\n",
 				__func__, cpu, cpudata->min_freq, policy->min);
-			return;
+			goto skip_test;
 		}
 
 		if (cpudata->boost_supported) {
@@ -249,16 +235,20 @@ static void amd_pstate_ut_check_freq(u32 index)
 				pr_err("%s cpu%d policy_max=%d should be equal cpu_max=%d or cpu_nominal=%d !\n",
 					__func__, cpu, policy->max, cpudata->max_freq,
 					cpudata->nominal_freq);
-				return;
+				goto skip_test;
 			}
 		} else {
 			amd_pstate_ut_cases[index].result = AMD_PSTATE_UT_RESULT_FAIL;
 			pr_err("%s cpu%d must support boost!\n", __func__, cpu);
-			return;
+			goto skip_test;
 		}
+		cpufreq_cpu_put(policy);
 	}
 
 	amd_pstate_ut_cases[index].result = AMD_PSTATE_UT_RESULT_PASS;
+	return;
+skip_test:
+	cpufreq_cpu_put(policy);
 }
 
 static int __init amd_pstate_ut_init(void)

drivers/cpufreq/cpufreq_stats.c

@@ -243,7 +243,8 @@ void cpufreq_stats_create_table(struct cpufreq_policy *policy)
 
 	/* Find valid-unique entries */
 	cpufreq_for_each_valid_entry(pos, policy->freq_table)
-		if (freq_table_get_index(stats, pos->frequency) == -1)
+		if (policy->freq_table_sorted != CPUFREQ_TABLE_UNSORTED ||
+		    freq_table_get_index(stats, pos->frequency) == -1)
 			stats->freq_table[i++] = pos->frequency;
 
 	stats->state_num = i;

drivers/cpufreq/intel_pstate.c

@@ -2609,6 +2609,11 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
 			intel_pstate_clear_update_util_hook(policy->cpu);
 		intel_pstate_hwp_set(policy->cpu);
 	}
+	/*
+	 * policy->cur is never updated with the intel_pstate driver, but it
+	 * is used as a stale frequency value. So, keep it within limits.
+	 */
+	policy->cur = policy->min;
 
 	mutex_unlock(&intel_pstate_limits_lock);
 

drivers/cpuidle/governors/gov.h

@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/* Common definitions for cpuidle governors. */
+
+#ifndef __CPUIDLE_GOVERNOR_H
+#define __CPUIDLE_GOVERNOR_H
+
+/*
+ * Idle state target residency threshold used for deciding whether or not to
+ * check the time till the closest expected timer event.
+ */
+#define RESIDENCY_THRESHOLD_NS	(15 * NSEC_PER_USEC)
+
+#endif /* __CPUIDLE_GOVERNOR_H */

drivers/cpuidle/governors/menu.c

@@ -19,6 +19,8 @@
 #include <linux/sched/stat.h>
 #include <linux/math64.h>
 
+#include "gov.h"
+
 #define BUCKETS 12
 #define INTERVAL_SHIFT 3
 #define INTERVALS (1UL << INTERVAL_SHIFT)
@@ -166,8 +168,7 @@ static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev);
  * of points is below a threshold. If it is... then use the
  * average of these 8 points as the estimated value.
  */
-static unsigned int get_typical_interval(struct menu_device *data,
-					 unsigned int predicted_us)
+static unsigned int get_typical_interval(struct menu_device *data)
 {
 	int i, divisor;
 	unsigned int min, max, thresh, avg;
@@ -195,11 +196,7 @@ static unsigned int get_typical_interval(struct menu_device *data,
 		}
 	}
 
-	/*
-	 * If the result of the computation is going to be discarded anyway,
-	 * avoid the computation altogether.
-	 */
-	if (min >= predicted_us)
+	if (!max)
 		return UINT_MAX;
 
 	if (divisor == INTERVALS)
@@ -267,7 +264,6 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 {
 	struct menu_device *data = this_cpu_ptr(&menu_devices);
 	s64 latency_req = cpuidle_governor_latency_req(dev->cpu);
-	unsigned int predicted_us;
 	u64 predicted_ns;
 	u64 interactivity_req;
 	unsigned int nr_iowaiters;
@@ -279,16 +275,41 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 		data->needs_update = 0;
 	}
 
-	/* determine the expected residency time, round up */
-	delta = tick_nohz_get_sleep_length(&delta_tick);
-	if (unlikely(delta < 0)) {
-		delta = 0;
-		delta_tick = 0;
-	}
-	data->next_timer_ns = delta;
-
 	nr_iowaiters = nr_iowait_cpu(dev->cpu);
-	data->bucket = which_bucket(data->next_timer_ns, nr_iowaiters);
+
+	/* Find the shortest expected idle interval. */
+	predicted_ns = get_typical_interval(data) * NSEC_PER_USEC;
+	if (predicted_ns > RESIDENCY_THRESHOLD_NS) {
+		unsigned int timer_us;
+
+		/* Determine the time till the closest timer. */
+		delta = tick_nohz_get_sleep_length(&delta_tick);
+		if (unlikely(delta < 0)) {
+			delta = 0;
+			delta_tick = 0;
+		}
+
+		data->next_timer_ns = delta;
+		data->bucket = which_bucket(data->next_timer_ns, nr_iowaiters);
+
+		/* Round up the result for half microseconds. */
+		timer_us = div_u64((RESOLUTION * DECAY * NSEC_PER_USEC) / 2 +
+					data->next_timer_ns *
+						data->correction_factor[data->bucket],
+				   RESOLUTION * DECAY * NSEC_PER_USEC);
+		/* Use the lowest expected idle interval to pick the idle state. */
+		predicted_ns = min((u64)timer_us * NSEC_PER_USEC, predicted_ns);
+	} else {
+		/*
+		 * Because the next timer event is not going to be determined
+		 * in this case, assume that without the tick the closest timer
+		 * will be in distant future and that the closest tick will occur
+		 * after 1/2 of the tick period.
+		 */
+		data->next_timer_ns = KTIME_MAX;
+		delta_tick = TICK_NSEC / 2;
+		data->bucket = which_bucket(KTIME_MAX, nr_iowaiters);
+	}
 
 	if (unlikely(drv->state_count <= 1 || latency_req == 0) ||
 	    ((data->next_timer_ns < drv->states[1].target_residency_ns ||
@@ -303,16 +324,6 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 		return 0;
 	}
 
-	/* Round up the result for half microseconds. */
-	predicted_us = div_u64(data->next_timer_ns *
-			       data->correction_factor[data->bucket] +
-			       (RESOLUTION * DECAY * NSEC_PER_USEC) / 2,
-			       RESOLUTION * DECAY * NSEC_PER_USEC);
-	/* Use the lowest expected idle interval to pick the idle state. */
-	predicted_ns = (u64)min(predicted_us,
-				get_typical_interval(data, predicted_us)) *
-				NSEC_PER_USEC;
-
 	if (tick_nohz_tick_stopped()) {
 		/*
 		 * If the tick is already stopped, the cost of possible short