From b9df501985d7acd9b13da0bfb5ba547778647e29 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 8 May 2017 16:51:41 +0200
Subject: [PATCH] sched/fair: Rewrite cfs_rq->removed_*avg
References: bnc#1066110 Scheduler utilisation tracking
Patch-mainline: v4.15-rc1
Git-commit: 2a2f5d4e44ed160a5ed822c94e04f918f9fbb487
Since on wakeup migration we don't hold the rq->lock for the old CPU
we cannot update its state. Instead we add the removed 'load' to an
atomic variable and have the next update on that CPU collect and
process it.
Currently we have 2 atomic variables; which already have the issue
that they can be read out-of-sync. Also, two atomic ops on a single
cacheline is already more expensive than an uncontended lock.
Since we want to add more, convert the thing over to an explicit
cacheline with a lock in.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
kernel/sched/debug.c | 8 ++++----
kernel/sched/fair.c | 51 +++++++++++++++++++++++++++++++++++----------------
kernel/sched/sched.h | 13 +++++++++----
3 files changed, 48 insertions(+), 24 deletions(-)
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 2db8e9c7c083..12a5283cad0f 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -519,10 +519,10 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
cfs_rq->runnable_load_avg);
SEQ_printf(m, " .%-30s: %lu\n", "util_avg",
cfs_rq->avg.util_avg);
- SEQ_printf(m, " .%-30s: %ld\n", "removed_load_avg",
- atomic_long_read(&cfs_rq->removed_load_avg));
- SEQ_printf(m, " .%-30s: %ld\n", "removed_util_avg",
- atomic_long_read(&cfs_rq->removed_util_avg));
+ SEQ_printf(m, " .%-30s: %ld\n", "removed.load_avg",
+ cfs_rq->removed.load_avg);
+ SEQ_printf(m, " .%-30s: %ld\n", "removed.util_avg",
+ cfs_rq->removed.util_avg);
#ifdef CONFIG_FAIR_GROUP_SCHED
SEQ_printf(m, " .%-30s: %lu\n", "tg_load_avg_contrib",
cfs_rq->tg_load_avg_contrib);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 0c02e7683811..f2421f929ed0 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3500,36 +3500,47 @@ static inline void set_tg_cfs_propagate(struct cfs_rq *cfs_rq) {}
static inline int
update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
{
+ unsigned long removed_load = 0, removed_util = 0;
struct sched_avg *sa = &cfs_rq->avg;
- int decayed, removed_load = 0, removed_util = 0;
+ int decayed = 0;
- if (atomic_long_read(&cfs_rq->removed_load_avg)) {
- s64 r = atomic_long_xchg(&cfs_rq->removed_load_avg, 0);
+ if (cfs_rq->removed.nr) {
+ unsigned long r;
+
+ raw_spin_lock(&cfs_rq->removed.lock);
+ swap(cfs_rq->removed.util_avg, removed_util);
+ swap(cfs_rq->removed.load_avg, removed_load);
+ cfs_rq->removed.nr = 0;
+ raw_spin_unlock(&cfs_rq->removed.lock);
+
+ /*
+ * The LOAD_AVG_MAX for _sum is a slight over-estimate,
+ * which is safe due to sub_positive() clipping at 0.
+ */
+ r = removed_load;
sub_positive(&sa->load_avg, r);
sub_positive(&sa->load_sum, r * LOAD_AVG_MAX);
- removed_load = 1;
- set_tg_cfs_propagate(cfs_rq);
- }
- if (atomic_long_read(&cfs_rq->removed_util_avg)) {
- long r = atomic_long_xchg(&cfs_rq->removed_util_avg, 0);
+ r = removed_util;
sub_positive(&sa->util_avg, r);
sub_positive(&sa->util_sum, r * LOAD_AVG_MAX);
- removed_util = 1;
+
set_tg_cfs_propagate(cfs_rq);
+
+ decayed = 1;
}
- decayed = __update_load_avg_cfs_rq(now, cpu_of(rq_of(cfs_rq)), cfs_rq);
+ decayed |= __update_load_avg_cfs_rq(now, cpu_of(rq_of(cfs_rq)), cfs_rq);
#ifndef CONFIG_64BIT
smp_wmb();
cfs_rq->load_last_update_time_copy = sa->last_update_time;
#endif
- if (decayed || removed_util)
+ if (decayed)
cfs_rq_util_change(cfs_rq);
- return decayed || removed_load;
+ return decayed;
}
/*
@@ -3650,6 +3661,7 @@ void sync_entity_load_avg(struct sched_entity *se)
void remove_entity_load_avg(struct sched_entity *se)
{
struct cfs_rq *cfs_rq = cfs_rq_of(se);
+ unsigned long flags;
/*
* tasks cannot exit without having gone through wake_up_new_task() ->
@@ -3659,11 +3671,19 @@ void remove_entity_load_avg(struct sched_entity *se)
* Similarly for groups, they will have passed through
* post_init_entity_util_avg() before unregister_sched_fair_group()
* calls this.
+ *
+ * XXX in case entity_is_task(se) && task_of(se)->on_rq == MIGRATING
+ * we could actually get the right time, since we're called with
+ * rq->lock held, see detach_task().
*/
sync_entity_load_avg(se);
- atomic_long_add(se->avg.load_avg, &cfs_rq->removed_load_avg);
- atomic_long_add(se->avg.util_avg, &cfs_rq->removed_util_avg);
+
+ raw_spin_lock_irqsave(&cfs_rq->removed.lock, flags);
+ ++cfs_rq->removed.nr;
+ cfs_rq->removed.util_avg += se->avg.util_avg;
+ cfs_rq->removed.load_avg += se->avg.load_avg;
+ raw_spin_unlock_irqrestore(&cfs_rq->removed.lock, flags);
}
static inline unsigned long cfs_rq_runnable_load_avg(struct cfs_rq *cfs_rq)
@@ -9376,8 +9396,7 @@ void init_cfs_rq(struct cfs_rq *cfs_rq)
#ifdef CONFIG_FAIR_GROUP_SCHED
cfs_rq->propagate_avg = 0;
#endif
- atomic_long_set(&cfs_rq->removed_load_avg, 0);
- atomic_long_set(&cfs_rq->removed_util_avg, 0);
+ raw_spin_lock_init(&cfs_rq->removed.lock);
#endif
}
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index d88bb4dcc3ca..f02fabc43633 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -424,14 +424,19 @@ struct cfs_rq {
struct sched_avg avg;
u64 runnable_load_sum;
unsigned long runnable_load_avg;
+#ifndef CONFIG_64BIT
+ u64 load_last_update_time_copy;
+#endif
#ifdef CONFIG_FAIR_GROUP_SCHED
unsigned long tg_load_avg_contrib;
unsigned long propagate_avg;
#endif
- atomic_long_t removed_load_avg, removed_util_avg;
-#ifndef CONFIG_64BIT
- u64 load_last_update_time_copy;
-#endif
+ struct {
+ raw_spinlock_t lock ____cacheline_aligned;
+ int nr;
+ unsigned long load_avg;
+ unsigned long util_avg;
+ } removed;
#ifdef CONFIG_FAIR_GROUP_SCHED
/*