Merge back earlier cpufreq material for 6.15

Author: rafaeljw

Documentation/admin-guide/kernel-parameters.txt

@@ -2316,6 +2316,9 @@
 			per_cpu_perf_limits
 			  Allow per-logical-CPU P-State performance control limits using
 			  cpufreq sysfs interface
+			no_cas
+			  Do not enable capacity-aware scheduling (CAS) on
+			  hybrid systems
 
 	intremap=	[X86-64,Intel-IOMMU,EARLY]
 			on	enable Interrupt Remapping (default)

Documentation/admin-guide/pm/intel_pstate.rst

@@ -696,6 +696,9 @@ of them have to be prepended with the ``intel_pstate=`` prefix.
 	Use per-logical-CPU P-State limits (see `Coordination of P-state
 	Limits`_ for details).
 
+``no_cas``
+	Do not enable capacity-aware scheduling (CAS) which is enabled by
+	default on hybrid systems.
 
 Diagnostics and Tuning
 ======================

drivers/cpufreq/cpufreq_governor.c

@@ -145,7 +145,23 @@ unsigned int dbs_update(struct cpufreq_policy *policy)
 		time_elapsed = update_time - j_cdbs->prev_update_time;
 		j_cdbs->prev_update_time = update_time;
 
-		idle_time = cur_idle_time - j_cdbs->prev_cpu_idle;
+		/*
+		 * cur_idle_time could be smaller than j_cdbs->prev_cpu_idle if
+		 * it's obtained from get_cpu_idle_time_jiffy() when NOHZ is
+		 * off, where idle_time is calculated by the difference between
+		 * time elapsed in jiffies and "busy time" obtained from CPU
+		 * statistics.  If a CPU is 100% busy, the time elapsed and busy
+		 * time should grow with the same amount in two consecutive
+		 * samples, but in practice there could be a tiny difference,
+		 * making the accumulated idle time decrease sometimes.  Hence,
+		 * in this case, idle_time should be regarded as 0 in order to
+		 * make the further process correct.
+		 */
+		if (cur_idle_time > j_cdbs->prev_cpu_idle)
+			idle_time = cur_idle_time - j_cdbs->prev_cpu_idle;
+		else
+			idle_time = 0;
+
 		j_cdbs->prev_cpu_idle = cur_idle_time;
 
 		if (ignore_nice) {
@@ -162,7 +178,7 @@ unsigned int dbs_update(struct cpufreq_policy *policy)
 			 * calls, so the previous load value can be used then.
 			 */
 			load = j_cdbs->prev_load;
-		} else if (unlikely((int)idle_time > 2 * sampling_rate &&
+		} else if (unlikely(idle_time > 2 * sampling_rate &&
 				    j_cdbs->prev_load)) {
 			/*
 			 * If the CPU had gone completely idle and a task has
@@ -189,30 +205,15 @@ unsigned int dbs_update(struct cpufreq_policy *policy)
 			load = j_cdbs->prev_load;
 			j_cdbs->prev_load = 0;
 		} else {
-			if (time_elapsed >= idle_time) {
+			if (time_elapsed > idle_time)
 				load = 100 * (time_elapsed - idle_time) / time_elapsed;
-			} else {
-				/*
-				 * That can happen if idle_time is returned by
-				 * get_cpu_idle_time_jiffy().  In that case
-				 * idle_time is roughly equal to the difference
-				 * between time_elapsed and "busy time" obtained
-				 * from CPU statistics.  Then, the "busy time"
-				 * can end up being greater than time_elapsed
-				 * (for example, if jiffies_64 and the CPU
-				 * statistics are updated by different CPUs),
-				 * so idle_time may in fact be negative.  That
-				 * means, though, that the CPU was busy all
-				 * the time (on the rough average) during the
-				 * last sampling interval and 100 can be
-				 * returned as the load.
-				 */
-				load = (int)idle_time < 0 ? 100 : 0;
-			}
+			else
+				load = 0;
+
 			j_cdbs->prev_load = load;
 		}
 
-		if (unlikely((int)idle_time > 2 * sampling_rate)) {
+		if (unlikely(idle_time > 2 * sampling_rate)) {
 			unsigned int periods = idle_time / sampling_rate;
 
 			if (periods < idle_periods)

drivers/cpufreq/intel_pstate.c

@@ -936,6 +936,8 @@ static struct freq_attr *hwp_cpufreq_attrs[] = {
 	NULL,
 };
 
+static bool no_cas __ro_after_init;
+
 static struct cpudata *hybrid_max_perf_cpu __read_mostly;
 /*
  * Protects hybrid_max_perf_cpu, the capacity_perf fields in struct cpudata,
@@ -1041,6 +1043,10 @@ static void hybrid_refresh_cpu_capacity_scaling(void)
 
 static void hybrid_init_cpu_capacity_scaling(bool refresh)
 {
+	/* Bail out if enabling capacity-aware scheduling is prohibited. */
+	if (no_cas)
+		return;
+
 	/*
 	 * If hybrid_max_perf_cpu is set at this point, the hybrid CPU capacity
 	 * scaling has been enabled already and the driver is just changing the
@@ -3688,6 +3694,15 @@ static int __init intel_pstate_init(void)
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
 		return -ENODEV;
 
+	/*
+	 * The Intel pstate driver will be ignored if the platform
+	 * firmware has its own power management modes.
+	 */
+	if (intel_pstate_platform_pwr_mgmt_exists()) {
+		pr_info("P-states controlled by the platform\n");
+		return -ENODEV;
+	}
+
 	id = x86_match_cpu(hwp_support_ids);
 	if (id) {
 		hwp_forced = intel_pstate_hwp_is_enabled();
@@ -3743,15 +3758,6 @@ static int __init intel_pstate_init(void)
 		default_driver = &intel_cpufreq;
 
 hwp_cpu_matched:
-	/*
-	 * The Intel pstate driver will be ignored if the platform
-	 * firmware has its own power management modes.
-	 */
-	if (intel_pstate_platform_pwr_mgmt_exists()) {
-		pr_info("P-states controlled by the platform\n");
-		return -ENODEV;
-	}
-
 	if (!hwp_active && hwp_only)
 		return -ENOTSUPP;
 
@@ -3835,6 +3841,9 @@ static int __init intel_pstate_setup(char *str)
 	if (!strcmp(str, "no_hwp"))
 		no_hwp = 1;
 
+	if (!strcmp(str, "no_cas"))
+		no_cas = true;
+
 	if (!strcmp(str, "force"))
 		force_load = 1;
 	if (!strcmp(str, "hwp_only"))