Merge branch 'pm-cpufreq-sched' into pm-cpufreq

6 files changed, 122 insertions, 75 deletions

diff --git a/kernel/sched/cpufreq.c b/kernel/sched/cpufreq.c
index 1141954e73b4..dbc51442ecbc 100644
--- a/kernel/sched/cpufreq.c
+++ b/kernel/sched/cpufreq.c
@@ -33,7 +33,7 @@ DEFINE_PER_CPU(struct update_util_data *, cpufreq_update_util_data);
  */
 void cpufreq_add_update_util_hook(int cpu, struct update_util_data *data,
 			void (*func)(struct update_util_data *data, u64 time,
-				     unsigned long util, unsigned long max))
+				     unsigned int flags))
 {
 	if (WARN_ON(!data || !func))
 		return;
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index a84641b222c1..69e06898997d 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -12,7 +12,6 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/cpufreq.h>
-#include <linux/module.h>
 #include <linux/slab.h>
 #include <trace/events/power.h>
 
@@ -48,11 +47,14 @@ struct sugov_cpu {
 	struct sugov_policy *sg_policy;
 
 	unsigned int cached_raw_freq;
+	unsigned long iowait_boost;
+	unsigned long iowait_boost_max;
+	u64 last_update;
 
 	/* The fields below are only needed when sharing a policy. */
 	unsigned long util;
 	unsigned long max;
-	u64 last_update;
+	unsigned int flags;
 };
 
 static DEFINE_PER_CPU(struct sugov_cpu, sugov_cpu);
@@ -144,24 +146,75 @@ static unsigned int get_next_freq(struct sugov_cpu *sg_cpu, unsigned long util,
 	return cpufreq_driver_resolve_freq(policy, freq);
 }
 
+static void sugov_get_util(unsigned long *util, unsigned long *max)
+{
+	struct rq *rq = this_rq();
+	unsigned long cfs_max;
+
+	cfs_max = arch_scale_cpu_capacity(NULL, smp_processor_id());
+
+	*util = min(rq->cfs.avg.util_avg, cfs_max);
+	*max = cfs_max;
+}
+
+static void sugov_set_iowait_boost(struct sugov_cpu *sg_cpu, u64 time,
+				   unsigned int flags)
+{
+	if (flags & SCHED_CPUFREQ_IOWAIT) {
+		sg_cpu->iowait_boost = sg_cpu->iowait_boost_max;
+	} else if (sg_cpu->iowait_boost) {
+		s64 delta_ns = time - sg_cpu->last_update;
+
+		/* Clear iowait_boost if the CPU apprears to have been idle. */
+		if (delta_ns > TICK_NSEC)
+			sg_cpu->iowait_boost = 0;
+	}
+}
+
+static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, unsigned long *util,
+			       unsigned long *max)
+{
+	unsigned long boost_util = sg_cpu->iowait_boost;
+	unsigned long boost_max = sg_cpu->iowait_boost_max;
+
+	if (!boost_util)
+		return;
+
+	if (*util * boost_max < *max * boost_util) {
+		*util = boost_util;
+		*max = boost_max;
+	}
+	sg_cpu->iowait_boost >>= 1;
+}
+
 static void sugov_update_single(struct update_util_data *hook, u64 time,
-				unsigned long util, unsigned long max)
+				unsigned int flags)
 {
 	struct sugov_cpu *sg_cpu = container_of(hook, struct sugov_cpu, update_util);
 	struct sugov_policy *sg_policy = sg_cpu->sg_policy;
 	struct cpufreq_policy *policy = sg_policy->policy;
+	unsigned long util, max;
 	unsigned int next_f;
 
+	sugov_set_iowait_boost(sg_cpu, time, flags);
+	sg_cpu->last_update = time;
+
 	if (!sugov_should_update_freq(sg_policy, time))
 		return;
 
-	next_f = util == ULONG_MAX ? policy->cpuinfo.max_freq :
-			get_next_freq(sg_cpu, util, max);
+	if (flags & SCHED_CPUFREQ_RT_DL) {
+		next_f = policy->cpuinfo.max_freq;
+	} else {
+		sugov_get_util(&util, &max);
+		sugov_iowait_boost(sg_cpu, &util, &max);
+		next_f = get_next_freq(sg_cpu, util, max);
+	}
 	sugov_update_commit(sg_policy, time, next_f);
 }
 
 static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu,
-					   unsigned long util, unsigned long max)
+					   unsigned long util, unsigned long max,
+					   unsigned int flags)
 {
 	struct sugov_policy *sg_policy = sg_cpu->sg_policy;
 	struct cpufreq_policy *policy = sg_policy->policy;
@@ -169,9 +222,11 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu,
 	u64 last_freq_update_time = sg_policy->last_freq_update_time;
 	unsigned int j;
 
-	if (util == ULONG_MAX)
+	if (flags & SCHED_CPUFREQ_RT_DL)
 		return max_f;
 
+	sugov_iowait_boost(sg_cpu, &util, &max);
+
 	for_each_cpu(j, policy->cpus) {
 		struct sugov_cpu *j_sg_cpu;
 		unsigned long j_util, j_max;
@@ -186,41 +241,50 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu,
 		 * frequency update and the time elapsed between the last update
 		 * of the CPU utilization and the last frequency update is long
 		 * enough, don't take the CPU into account as it probably is
-		 * idle now.
+		 * idle now (and clear iowait_boost for it).
 		 */
 		delta_ns = last_freq_update_time - j_sg_cpu->last_update;
-		if (delta_ns > TICK_NSEC)
+		if (delta_ns > TICK_NSEC) {
+			j_sg_cpu->iowait_boost = 0;
 			continue;
-
-		j_util = j_sg_cpu->util;
-		if (j_util == ULONG_MAX)
+		}
+		if (j_sg_cpu->flags & SCHED_CPUFREQ_RT_DL)
 			return max_f;
 
+		j_util = j_sg_cpu->util;
 		j_max = j_sg_cpu->max;
 		if (j_util * max > j_max * util) {
 			util = j_util;
 			max = j_max;
 		}
+
+		sugov_iowait_boost(j_sg_cpu, &util, &max);
 	}
 
 	return get_next_freq(sg_cpu, util, max);
 }
 
 static void sugov_update_shared(struct update_util_data *hook, u64 time,
-				unsigned long util, unsigned long max)
+				unsigned int flags)
 {
 	struct sugov_cpu *sg_cpu = container_of(hook, struct sugov_cpu, update_util);
 	struct sugov_policy *sg_policy = sg_cpu->sg_policy;
+	unsigned long util, max;
 	unsigned int next_f;
 
+	sugov_get_util(&util, &max);
+
 	raw_spin_lock(&sg_policy->update_lock);
 
 	sg_cpu->util = util;
 	sg_cpu->max = max;
+	sg_cpu->flags = flags;
+
+	sugov_set_iowait_boost(sg_cpu, time, flags);
 	sg_cpu->last_update = time;
 
 	if (sugov_should_update_freq(sg_policy, time)) {
-		next_f = sugov_next_freq_shared(sg_cpu, util, max);
+		next_f = sugov_next_freq_shared(sg_cpu, util, max, flags);
 		sugov_update_commit(sg_policy, time, next_f);
 	}
 
@@ -444,10 +508,13 @@ static int sugov_start(struct cpufreq_policy *policy)
 
 		sg_cpu->sg_policy = sg_policy;
 		if (policy_is_shared(policy)) {
-			sg_cpu->util = ULONG_MAX;
+			sg_cpu->util = 0;
 			sg_cpu->max = 0;
+			sg_cpu->flags = SCHED_CPUFREQ_RT;
 			sg_cpu->last_update = 0;
 			sg_cpu->cached_raw_freq = 0;
+			sg_cpu->iowait_boost = 0;
+			sg_cpu->iowait_boost_max = policy->cpuinfo.max_freq;
 			cpufreq_add_update_util_hook(cpu, &sg_cpu->update_util,
 						     sugov_update_shared);
 		} else {
@@ -495,28 +562,15 @@ static struct cpufreq_governor schedutil_gov = {
 	.limits = sugov_limits,
 };
 
-static int __init sugov_module_init(void)
-{
-	return cpufreq_register_governor(&schedutil_gov);
-}
-
-static void __exit sugov_module_exit(void)
-{
-	cpufreq_unregister_governor(&schedutil_gov);
-}
-
-MODULE_AUTHOR("Rafael J. Wysocki <rafael.j.wysocki@intel.com>");
-MODULE_DESCRIPTION("Utilization-based CPU frequency selection");
-MODULE_LICENSE("GPL");
-
 #ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_SCHEDUTIL
 struct cpufreq_governor *cpufreq_default_governor(void)
 {
 	return &schedutil_gov;
 }
-
-fs_initcall(sugov_module_init);
-#else
-module_init(sugov_module_init);
 #endif
-module_exit(sugov_module_exit);
+
+static int __init sugov_register(void)
+{
+	return cpufreq_register_governor(&schedutil_gov);
+}
+fs_initcall(sugov_register);
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 1ce8867283dc..974779656999 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -735,9 +735,8 @@ static void update_curr_dl(struct rq *rq)
 		return;
 	}
 
-	/* kick cpufreq (see the comment in linux/cpufreq.h). */
-	if (cpu_of(rq) == smp_processor_id())
-		cpufreq_trigger_update(rq_clock(rq));
+	/* kick cpufreq (see the comment in kernel/sched/sched.h). */
+	cpufreq_update_this_cpu(rq, SCHED_CPUFREQ_DL);
 
 	schedstat_set(curr->se.statistics.exec_max,
 		      max(curr->se.statistics.exec_max, delta_exec));
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 039de34f1521..a5cd07b25aa1 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2875,12 +2875,7 @@ static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force) {}
 
 static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq)
 {
-	struct rq *rq = rq_of(cfs_rq);
-	int cpu = cpu_of(rq);
-
-	if (cpu == smp_processor_id() && &rq->cfs == cfs_rq) {
-		unsigned long max = rq->cpu_capacity_orig;
-
+	if (&this_rq()->cfs == cfs_rq) {
 		/*
 		 * There are a few boundary cases this might miss but it should
 		 * get called often enough that that should (hopefully) not be
@@ -2897,8 +2892,7 @@ static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq)
 		 *
 		 * See cpu_util().
 		 */
-		cpufreq_update_util(rq_clock(rq),
-				    min(cfs_rq->avg.util_avg, max), max);
+		cpufreq_update_util(rq_of(cfs_rq), 0);
 	}
 }
 
@@ -3159,10 +3153,7 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq, bool update_freq)
 
 static inline void update_load_avg(struct sched_entity *se, int not_used)
 {
-	struct cfs_rq *cfs_rq = cfs_rq_of(se);
-	struct rq *rq = rq_of(cfs_rq);
-
-	cpufreq_trigger_update(rq_clock(rq));
+	cpufreq_update_util(rq_of(cfs_rq_of(se)), 0);
 }
 
 static inline void
@@ -4509,6 +4500,14 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	struct cfs_rq *cfs_rq;
 	struct sched_entity *se = &p->se;
 
+	/*
+	 * If in_iowait is set, the code below may not trigger any cpufreq
+	 * utilization updates, so do it here explicitly with the IOWAIT flag
+	 * passed.
+	 */
+	if (p->in_iowait)
+		cpufreq_update_this_cpu(rq, SCHED_CPUFREQ_IOWAIT);
+
 	for_each_sched_entity(se) {
 		if (se->on_rq)
 			break;
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index d5690b722691..2516b8df6dbb 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -957,9 +957,8 @@ static void update_curr_rt(struct rq *rq)
 	if (unlikely((s64)delta_exec <= 0))
 		return;
 
-	/* Kick cpufreq (see the comment in linux/cpufreq.h). */
-	if (cpu_of(rq) == smp_processor_id())
-		cpufreq_trigger_update(rq_clock(rq));
+	/* Kick cpufreq (see the comment in kernel/sched/sched.h). */
+	cpufreq_update_this_cpu(rq, SCHED_CPUFREQ_RT);
 
 	schedstat_set(curr->se.statistics.exec_max,
 		      max(curr->se.statistics.exec_max, delta_exec));
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index c64fc5114004..b7fc1ced4380 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1763,27 +1763,13 @@ DECLARE_PER_CPU(struct update_util_data *, cpufreq_update_util_data);
 
 /**
  * cpufreq_update_util - Take a note about CPU utilization changes.
- * @time: Current time.
- * @util: Current utilization.
- * @max: Utilization ceiling.
+ * @rq: Runqueue to carry out the update for.
+ * @flags: Update reason flags.
  *
- * This function is called by the scheduler on every invocation of
- * update_load_avg() on the CPU whose utilization is being updated.
+ * This function is called by the scheduler on the CPU whose utilization is
+ * being updated.
  *
  * It can only be called from RCU-sched read-side critical sections.
- */
-static inline void cpufreq_update_util(u64 time, unsigned long util, unsigned long max)
-{
-       struct update_util_data *data;
-
-       data = rcu_dereference_sched(*this_cpu_ptr(&cpufreq_update_util_data));
-       if (data)
-               data->func(data, time, util, max);
-}
-
-/**
- * cpufreq_trigger_update - Trigger CPU performance state evaluation if needed.
- * @time: Current time.
  *
  * The way cpufreq is currently arranged requires it to evaluate the CPU
  * performance state (frequency/voltage) on a regular basis to prevent it from
@@ -1797,13 +1783,23 @@ static inline void cpufreq_update_util(u64 time, unsigned long util, unsigned lo
  * but that really is a band-aid.  Going forward it should be replaced with
  * solutions targeted more specifically at RT and DL tasks.
  */
-static inline void cpufreq_trigger_update(u64 time)
+static inline void cpufreq_update_util(struct rq *rq, unsigned int flags)
+{
+	struct update_util_data *data;
+
+	data = rcu_dereference_sched(*this_cpu_ptr(&cpufreq_update_util_data));
+	if (data)
+		data->func(data, rq_clock(rq), flags);
+}
+
+static inline void cpufreq_update_this_cpu(struct rq *rq, unsigned int flags)
 {
-	cpufreq_update_util(time, ULONG_MAX, 0);
+	if (cpu_of(rq) == smp_processor_id())
+		cpufreq_update_util(rq, flags);
 }
 #else
-static inline void cpufreq_update_util(u64 time, unsigned long util, unsigned long max) {}
-static inline void cpufreq_trigger_update(u64 time) {}
+static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {}
+static inline void cpufreq_update_this_cpu(struct rq *rq, unsigned int flags) {}
 #endif /* CONFIG_CPU_FREQ */
 
 #ifdef arch_scale_freq_capacity