[tip:sched/core] sched/cpufreq: Use the DEADLINE utilization signal

[tip-bot for Juri Lelli]

Commit-ID:  d4edd662ac1657126df7ffd74a278958b133a77d
Gitweb:     https://git.kernel.org/tip/d4edd662ac1657126df7ffd74a278958b133a77d
Author:     Juri Lelli <juri.lelli@xxxxxxx>
AuthorDate: Mon, 4 Dec 2017 11:23:18 +0100
Committer:  Ingo Molnar <mingo@xxxxxxxxxx>
CommitDate: Wed, 10 Jan 2018 11:30:32 +0100

sched/cpufreq: Use the DEADLINE utilization signal

SCHED_DEADLINE tracks active utilization signal with a per dl_rq
variable named running_bw.

Make use of that to drive CPU frequency selection: add up FAIR and
DEADLINE contribution to get the required CPU capacity to handle both
requirements (while RT still selects max frequency).

Co-authored-by: Claudio Scordino <claudio@xxxxxxxxxxxxxxx>
Signed-off-by: Juri Lelli <juri.lelli@xxxxxxx>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Acked-by: Viresh Kumar <viresh.kumar@xxxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Luca Abeni <luca.abeni@xxxxxxxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Rafael J . Wysocki <rafael.j.wysocki@xxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: alessio.balsini@xxxxxxx
Cc: bristot@xxxxxxxxxx
Cc: dietmar.eggemann@xxxxxxx
Cc: joelaf@xxxxxxxxxx
Cc: juri.lelli@xxxxxxxxxx
Cc: mathieu.poirier@xxxxxxxxxx
Cc: morten.rasmussen@xxxxxxx
Cc: patrick.bellasi@xxxxxxx
Cc: rjw@xxxxxxxxxxxxx
Cc: rostedt@xxxxxxxxxxx
Cc: tkjos@xxxxxxxxxxx
Cc: tommaso.cucinotta@xxxxxxxxxxxxxxx
Cc: vincent.guittot@xxxxxxxxxx
Link: http://lkml.kernel.org/r/20171204102325.5110-2-juri.lelli@xxxxxxxxxx
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
---
 include/linux/sched/cpufreq.h    |  2 --
 kernel/sched/cpufreq_schedutil.c | 25 +++++++++++++++----------
 kernel/sched/sched.h             | 10 ++++++++++
 3 files changed, 25 insertions(+), 12 deletions(-)

diff --git a/include/linux/sched/cpufreq.h b/include/linux/sched/cpufreq.h
index d1ad3d8..0b55834 100644
--- a/include/linux/sched/cpufreq.h
+++ b/include/linux/sched/cpufreq.h
@@ -12,8 +12,6 @@
 #define SCHED_CPUFREQ_DL	(1U << 1)
 #define SCHED_CPUFREQ_IOWAIT	(1U << 2)
 
-#define SCHED_CPUFREQ_RT_DL	(SCHED_CPUFREQ_RT | SCHED_CPUFREQ_DL)
-
 #ifdef CONFIG_CPU_FREQ
 struct update_util_data {
        void (*func)(struct update_util_data *data, u64 time, unsigned int flags);
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 6dd1ec9..8d266bc 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -179,12 +179,17 @@ static unsigned int get_next_freq(struct sugov_policy *sg_policy,
 static void sugov_get_util(unsigned long *util, unsigned long *max, int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
-	unsigned long cfs_max;
+	unsigned long util_cfs = cpu_util_cfs(rq);
+	unsigned long util_dl  = cpu_util_dl(rq);
 
-	cfs_max = arch_scale_cpu_capacity(NULL, cpu);
+	*max = arch_scale_cpu_capacity(NULL, cpu);
 
-	*util = min(rq->cfs.avg.util_avg, cfs_max);
-	*max = cfs_max;
+	/*
+	 * Ideally we would like to set util_dl as min/guaranteed freq and
+	 * util_cfs + util_dl as requested freq. However, cpufreq is not yet
+	 * ready for such an interface. So, we only do the latter for now.
+	 */
+	*util = min(util_cfs + util_dl, *max);
 }
 
 static void sugov_set_iowait_boost(struct sugov_cpu *sg_cpu, u64 time)
@@ -271,7 +276,7 @@ static void sugov_update_single(struct update_util_data *hook, u64 time,
 
 	busy = sugov_cpu_is_busy(sg_cpu);
 
-	if (flags & SCHED_CPUFREQ_RT_DL) {
+	if (flags & SCHED_CPUFREQ_RT) {
 		next_f = policy->cpuinfo.max_freq;
 	} else {
 		sugov_get_util(&util, &max, sg_cpu->cpu);
@@ -316,7 +321,7 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, u64 time)
 			j_sg_cpu->iowait_boost_pending = false;
 			continue;
 		}
-		if (j_sg_cpu->flags & SCHED_CPUFREQ_RT_DL)
+		if (j_sg_cpu->flags & SCHED_CPUFREQ_RT)
 			return policy->cpuinfo.max_freq;
 
 		j_util = j_sg_cpu->util;
@@ -352,7 +357,7 @@ static void sugov_update_shared(struct update_util_data *hook, u64 time,
 	sg_cpu->last_update = time;
 
 	if (sugov_should_update_freq(sg_policy, time)) {
-		if (flags & SCHED_CPUFREQ_RT_DL)
+		if (flags & SCHED_CPUFREQ_RT)
 			next_f = sg_policy->policy->cpuinfo.max_freq;
 		else
 			next_f = sugov_next_freq_shared(sg_cpu, time);
@@ -382,9 +387,9 @@ static void sugov_irq_work(struct irq_work *irq_work)
 	sg_policy = container_of(irq_work, struct sugov_policy, irq_work);
 
 	/*
-	 * For RT and deadline tasks, the schedutil governor shoots the
-	 * frequency to maximum. Special care must be taken to ensure that this
-	 * kthread doesn't result in the same behavior.
+	 * For RT tasks, the schedutil governor shoots the frequency to maximum.
+	 * Special care must be taken to ensure that this kthread doesn't result
+	 * in the same behavior.
 	 *
 	 * This is (mostly) guaranteed by the work_in_progress flag. The flag is
 	 * updated only at the end of the sugov_work() function and before that
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 43f5d6e..136ab50 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2084,3 +2084,13 @@ static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {}
 #else /* arch_scale_freq_capacity */
 #define arch_scale_freq_invariant()	(false)
 #endif
+
+static inline unsigned long cpu_util_dl(struct rq *rq)
+{
+	return (rq->dl.running_bw * SCHED_CAPACITY_SCALE) >> BW_SHIFT;
+}
+
+static inline unsigned long cpu_util_cfs(struct rq *rq)
+{
+	return rq->cfs.avg.util_avg;
+}