cpufreq_cooling: Get effective CPU utilization from scheduler

index d2003a7d5ab5..b81265aec4a0 100644
@@ -5117,6 +5117,114 @@ struct task_struct *idle_task(int cpu)
 	return cpu_rq(cpu)->idle;
 }
 
+#ifdef CONFIG_SMP
+/*
+ * This function computes an effective utilization for the given CPU, to be
+ * used for frequency selection given the linear relation: f = u * f_max.
+ *
+ * The scheduler tracks the following metrics:
+ *
+ *   cpu_util_{cfs,rt,dl,irq}()
+ *   cpu_bw_dl()
+ *
+ * Where the cfs,rt and dl util numbers are tracked with the same metric and
+ * synchronized windows and are thus directly comparable.
+ *
+ * The cfs,rt,dl utilization are the running times measured with rq->clock_task
+ * which excludes things like IRQ and steal-time. These latter are then accrued
+ * in the irq utilization.
+ *
+ * The DL bandwidth number otoh is not a measured metric but a value computed
+ * based on the task model parameters and gives the minimal utilization
+ * required to meet deadlines.
+ */
+unsigned long schedutil_cpu_util(int cpu, unsigned long util_cfs,
+				 unsigned long max, enum schedutil_type type,
+				 struct task_struct *p)
+{
+	unsigned long dl_util, util, irq;
+	struct rq *rq = cpu_rq(cpu);
+
+	if (!uclamp_is_used() &&
+	    type == FREQUENCY_UTIL && rt_rq_is_runnable(&rq->rt)) {
+		return max;
+	}
+
+	/*
+	 * Early check to see if IRQ/steal time saturates the CPU, can be
+	 * because of inaccuracies in how we track these -- see
+	 * update_irq_load_avg().
+	 */
+	irq = cpu_util_irq(rq);
+	if (unlikely(irq >= max))
+		return max;
+
+	/*
+	 * Because the time spend on RT/DL tasks is visible as 'lost' time to
+	 * CFS tasks and we use the same metric to track the effective
+	 * utilization (PELT windows are synchronized) we can directly add them
+	 * to obtain the CPU's actual utilization.
+	 *
+	 * CFS and RT utilization can be boosted or capped, depending on
+	 * utilization clamp constraints requested by currently RUNNABLE
+	 * tasks.
+	 * When there are no CFS RUNNABLE tasks, clamps are released and
+	 * frequency will be gracefully reduced with the utilization decay.
+	 */
+	util = util_cfs + cpu_util_rt(rq);
+	if (type == FREQUENCY_UTIL)
+		util = uclamp_rq_util_with(rq, util, p);
+
+	dl_util = cpu_util_dl(rq);
+
+	/*
+	 * For frequency selection we do not make cpu_util_dl() a permanent part
+	 * of this sum because we want to use cpu_bw_dl() later on, but we need
+	 * to check if the CFS+RT+DL sum is saturated (ie. no idle time) such
+	 * that we select f_max when there is no idle time.
+	 *
+	 * NOTE: numerical errors or stop class might cause us to not quite hit
+	 * saturation when we should -- something for later.
+	 */
+	if (util + dl_util >= max)
+		return max;
+
+	/*
+	 * OTOH, for energy computation we need the estimated running time, so
+	 * include util_dl and ignore dl_bw.
+	 */
+	if (type == ENERGY_UTIL)
+		util += dl_util;
+
+	/*
+	 * There is still idle time; further improve the number by using the
+	 * irq metric. Because IRQ/steal time is hidden from the task clock we
+	 * need to scale the task numbers:
+	 *
+	 *              max - irq
+	 *   U' = irq + --------- * U
+	 *                 max
+	 */
+	util = scale_irq_capacity(util, irq, max);
+	util += irq;
+
+	/*
+	 * Bandwidth required by DEADLINE must always be granted while, for
+	 * FAIR and RT, we use blocked utilization of IDLE CPUs as a mechanism
+	 * to gracefully reduce the frequency when no tasks show up for longer
+	 * periods of time.
+	 *
+	 * Ideally we would like to set bw_dl as min/guaranteed freq and util +
+	 * bw_dl as requested freq. However, cpufreq is not yet ready for such
+	 * an interface. So, we only do the latter for now.
+	 */
+	if (type == FREQUENCY_UTIL)
+		util += cpu_bw_dl(rq);
+
+	return min(max, util);
+}
+#endif /* CONFIG_SMP */
+
 /**
  * find_process_by_pid - find a process with a matching PID value.
  * @pid: the pid in question.

112 lines not on this page · raw message

index df80bfcea92e..0db6bcf0881f 100644
@@ -2484,7 +2484,6 @@ static inline unsigned long capacity_orig_of(int cpu)
 {
 	return cpu_rq(cpu)->cpu_capacity_orig;
 }
-#endif
 
 /**
  * enum schedutil_type - CPU utilization type

@@ -2501,8 +2500,6 @@ enum schedutil_type {
 	ENERGY_UTIL,
 };
 
-#ifdef CONFIG_CPU_FREQ_GOV_SCHEDUTIL
-
 unsigned long schedutil_cpu_util(int cpu, unsigned long util_cfs,
 				 unsigned long max, enum schedutil_type type,
 				 struct task_struct *p);

@@ -2533,14 +2530,7 @@ static inline unsigned long cpu_util_rt(struct rq *rq)
 {
 	return READ_ONCE(rq->avg_rt.util_avg);
 }
-#else /* CONFIG_CPU_FREQ_GOV_SCHEDUTIL */
-static inline unsigned long schedutil_cpu_util(int cpu, unsigned long util_cfs,
-				 unsigned long max, enum schedutil_type type,
-				 struct task_struct *p)
-{
-	return 0;
-}
-#endif /* CONFIG_CPU_FREQ_GOV_SCHEDUTIL */
+#endif
 
 #ifdef CONFIG_HAVE_SCHED_AVG_IRQ
 static inline unsigned long cpu_util_irq(struct rq *rq)

index 063cd120b459..3a2fe4fe6155 100644
@@ -1926,6 +1926,11 @@ extern long sched_getaffinity(pid_t pid, struct cpumask *mask);
 #define TASK_SIZE_OF(tsk)	TASK_SIZE
 #endif
 
+#ifdef CONFIG_SMP
+/* Returns effective CPU energy utilization, as seen by the scheduler */
+unsigned long sched_cpu_util(int cpu, unsigned long max);
+#endif /* CONFIG_SMP */
+
 #ifdef CONFIG_RSEQ
 
 /*

index b81265aec4a0..0a24b93dd7f3 100644
@@ -5138,8 +5138,8 @@ struct task_struct *idle_task(int cpu)
  * based on the task model parameters and gives the minimal utilization
  * required to meet deadlines.
  */
-unsigned long schedutil_cpu_util(int cpu, unsigned long util_cfs,
-				 unsigned long max, enum schedutil_type type,
+unsigned long effective_cpu_util(int cpu, unsigned long util_cfs,
+				 unsigned long max, enum cpu_util_type type,
 				 struct task_struct *p)
 {
 	unsigned long dl_util, util, irq;

@@ -5223,6 +5223,12 @@ unsigned long schedutil_cpu_util(int cpu, unsigned long util_cfs,
 
 	return min(max, util);
 }
+
+unsigned long sched_cpu_util(int cpu, unsigned long max)
+{
+	return effective_cpu_util(cpu, cpu_util_cfs(cpu_rq(cpu)), max,
+				  ENERGY_UTIL, NULL);
+}
 #endif /* CONFIG_SMP */
 
 /**

index 2d44befb322b..e71627a3792b 100644
@@ -178,7 +178,7 @@ static unsigned long sugov_get_util(struct sugov_cpu *sg_cpu)
 	sg_cpu->max = max;
 	sg_cpu->bw_dl = cpu_bw_dl(rq);
 
-	return schedutil_cpu_util(sg_cpu->cpu, util, max, FREQUENCY_UTIL, NULL);
+	return effective_cpu_util(sg_cpu->cpu, util, max, FREQUENCY_UTIL, NULL);
 }
 
 /**

index 290f9e38378c..0e1c8eb7ad53 100644
@@ -6499,7 +6499,7 @@ compute_energy(struct task_struct *p, int dst_cpu, struct perf_domain *pd)
 		 * is already enough to scale the EM reported power
 		 * consumption at the (eventually clamped) cpu_capacity.
 		 */
-		sum_util += schedutil_cpu_util(cpu, util_cfs, cpu_cap,
+		sum_util += effective_cpu_util(cpu, util_cfs, cpu_cap,
 					       ENERGY_UTIL, NULL);
 
 		/*

@@ -6509,7 +6509,7 @@ compute_energy(struct task_struct *p, int dst_cpu, struct perf_domain *pd)
 		 * NOTE: in case RT tasks are running, by default the
 		 * FREQUENCY_UTIL's utilization can be max OPP.
 		 */
-		cpu_util = schedutil_cpu_util(cpu, util_cfs, cpu_cap,
+		cpu_util = effective_cpu_util(cpu, util_cfs, cpu_cap,
 					      FREQUENCY_UTIL, tsk);
 		max_util = max(max_util, cpu_util);
 	}

@@ -6607,7 +6607,7 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
 			 * IOW, placing the task there would make the CPU
 			 * overutilized. Take uclamp into account to see how
 			 * much capacity we can get out of the CPU; this is
-			 * aligned with schedutil_cpu_util().
+			 * aligned with sched_cpu_util().
 			 */
 			util = uclamp_rq_util_with(cpu_rq(cpu), util, p);
 			if (!fits_capacity(util, cpu_cap))

index 0db6bcf0881f..495e7ea278ce 100644
@@ -2486,22 +2486,22 @@ static inline unsigned long capacity_orig_of(int cpu)
 }
 
 /**
- * enum schedutil_type - CPU utilization type
+ * enum cpu_util_type - CPU utilization type
  * @FREQUENCY_UTIL:	Utilization used to select frequency
  * @ENERGY_UTIL:	Utilization used during energy calculation
  *
  * The utilization signals of all scheduling classes (CFS/RT/DL) and IRQ time
  * need to be aggregated differently depending on the usage made of them. This
- * enum is used within schedutil_freq_util() to differentiate the types of
+ * enum is used within effective_cpu_util() to differentiate the types of
  * utilization expected by the callers, and adjust the aggregation accordingly.
  */
-enum schedutil_type {
+enum cpu_util_type {
 	FREQUENCY_UTIL,
 	ENERGY_UTIL,
 };
 
-unsigned long schedutil_cpu_util(int cpu, unsigned long util_cfs,
-				 unsigned long max, enum schedutil_type type,
+unsigned long effective_cpu_util(int cpu, unsigned long util_cfs,
+				 unsigned long max, enum cpu_util_type type,
 				 struct task_struct *p);
 
 static inline unsigned long cpu_bw_dl(struct rq *rq)

index cc2959f22f01..cee59b95633b 100644
@@ -76,7 +76,9 @@ struct cpufreq_cooling_device {
 	struct em_perf_domain *em;
 	struct cpufreq_policy *policy;
 	struct list_head node;
+#ifndef CONFIG_SMP
 	struct time_in_idle *idle_time;
+#endif
 	struct freq_qos_request qos_req;
 };
 

@@ -132,14 +134,25 @@ static u32 cpu_power_to_freq(struct cpufreq_cooling_device *cpufreq_cdev,
 }
 
 /**
- * get_load() - get load for a cpu since last updated
- * @cpufreq_cdev:	&struct cpufreq_cooling_device for this cpu
- * @cpu:	cpu number
- * @cpu_idx:	index of the cpu in time_in_idle*
+ * get_load() - get load for a cpu
+ * @cpufreq_cdev: struct cpufreq_cooling_device for the cpu
+ * @cpu: cpu number
+ * @cpu_idx: index of the cpu in time_in_idle array
  *
  * Return: The average load of cpu @cpu in percentage since this
  * function was last called.
  */
+#ifdef CONFIG_SMP
+static u32 get_load(struct cpufreq_cooling_device *cpufreq_cdev, int cpu,
+		    int cpu_idx)
+{
+	unsigned long max = arch_scale_cpu_capacity(cpu);
+	unsigned long util;
+
+	util = sched_cpu_util(cpu, max);
+	return (util * 100) / max;
+}
+#else /* !CONFIG_SMP */
 static u32 get_load(struct cpufreq_cooling_device *cpufreq_cdev, int cpu,
 		    int cpu_idx)
 {

@@ -161,6 +174,7 @@ static u32 get_load(struct cpufreq_cooling_device *cpufreq_cdev, int cpu,
 
 	return load;
 }
+#endif /* CONFIG_SMP */
 
 /**
  * get_dynamic_power() - calculate the dynamic power

@@ -346,6 +360,36 @@ static inline bool em_is_sane(struct cpufreq_cooling_device *cpufreq_cdev,
 }
 #endif /* CONFIG_THERMAL_GOV_POWER_ALLOCATOR */
 
+#ifdef CONFIG_SMP
+static inline int allocate_idle_time(struct cpufreq_cooling_device *cpufreq_cdev)
+{
+	return 0;
+}
+
+static inline void free_idle_time(struct cpufreq_cooling_device *cpufreq_cdev)
+{
+}
+#else
+static int allocate_idle_time(struct cpufreq_cooling_device *cpufreq_cdev)
+{
+	unsigned int num_cpus = cpumask_weight(cpufreq_cdev->policy->related_cpus);
+
+	cpufreq_cdev->idle_time = kcalloc(num_cpus,
+					  sizeof(*cpufreq_cdev->idle_time),
+					  GFP_KERNEL);
+	if (!cpufreq_cdev->idle_time)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void free_idle_time(struct cpufreq_cooling_device *cpufreq_cdev)
+{
+	kfree(cpufreq_cdev->idle_time);
+	cpufreq_cdev->idle_time = NULL;
+}
+#endif /* CONFIG_SMP */
+
 static unsigned int get_state_freq(struct cpufreq_cooling_device *cpufreq_cdev,
 				   unsigned long state)
 {

@@ -487,7 +531,7 @@ __cpufreq_cooling_register(struct device_node *np,
 	struct thermal_cooling_device *cdev;
 	struct cpufreq_cooling_device *cpufreq_cdev;
 	char dev_name[THERMAL_NAME_LENGTH];
-	unsigned int i, num_cpus;
+	unsigned int i;
 	struct device *dev;
 	int ret;
 	struct thermal_cooling_device_ops *cooling_ops;

@@ -498,7 +542,6 @@ __cpufreq_cooling_register(struct device_node *np,
 		return ERR_PTR(-ENODEV);
 	}
 
-
 	if (IS_ERR_OR_NULL(policy)) {
 		pr_err("%s: cpufreq policy isn't valid: %p\n", __func__, policy);
 		return ERR_PTR(-EINVAL);

@@ -516,12 +559,10 @@ __cpufreq_cooling_register(struct device_node *np,
 		return ERR_PTR(-ENOMEM);
 
 	cpufreq_cdev->policy = policy;
-	num_cpus = cpumask_weight(policy->related_cpus);
-	cpufreq_cdev->idle_time = kcalloc(num_cpus,
-					 sizeof(*cpufreq_cdev->idle_time),
-					 GFP_KERNEL);
-	if (!cpufreq_cdev->idle_time) {
-		cdev = ERR_PTR(-ENOMEM);
+
+	ret = allocate_idle_time(cpufreq_cdev);
+	if (ret) {
+		cdev = ERR_PTR(ret);
 		goto free_cdev;
 	}
 

@@ -581,7 +622,7 @@ __cpufreq_cooling_register(struct device_node *np,
 remove_ida:
 	ida_simple_remove(&cpufreq_ida, cpufreq_cdev->id);
 free_idle_time:
-	kfree(cpufreq_cdev->idle_time);
+	free_idle_time(cpufreq_cdev);
 free_cdev:
 	kfree(cpufreq_cdev);
 	return cdev;

@@ -674,7 +715,7 @@ void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev)
 	thermal_cooling_device_unregister(cdev);
 	freq_qos_remove_request(&cpufreq_cdev->qos_req);
 	ida_simple_remove(&cpufreq_ida, cpufreq_cdev->id);
-	kfree(cpufreq_cdev->idle_time);
+	free_idle_time(cpufreq_cdev);
 	kfree(cpufreq_cdev);
 }
 EXPORT_SYMBOL_GPL(cpufreq_cooling_unregister);