[PATCH v9 1/9] sched/fair: fix unfairness at wakeup

[Vincent Guittot <vincent.guittot@linaro.org>]

At wake up, the vruntime of a task is updated to not be more older than
a sched_latency period behind the min_vruntime. This prevents long sleeping
task to get unlimited credit at wakeup.
Such waking task should preempt current one to use its CPU bandwidth but
wakeup_gran() can be larger than sched_latency, filter out the
wakeup preemption and as a results steals some CPU bandwidth to
the waking task.

Make sure that a task, which vruntime has been capped, will preempt current
task and use its CPU bandwidth even if wakeup_gran() is in the same range
as sched_latency.

If the waking task failed to preempt current it could to wait up to
sysctl_sched_min_granularity before preempting it during next tick.

Strictly speaking, we should use cfs->min_vruntime instead of
curr->vruntime but it doesn't worth the additional overhead and complexity
as the vruntime of current should be close to min_vruntime if not equal.

Reported-by: Youssef Esmat <youssefesmat@chromium.org>
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
---
 kernel/sched/fair.c  | 46 ++++++++++++++++++++------------------------
 kernel/sched/sched.h | 34 +++++++++++++++++++++++++++++++-
 2 files changed, 54 insertions(+), 26 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 4cc56c91e06e..c8a697f8db88 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4645,33 +4645,17 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
 {
 	u64 vruntime = cfs_rq->min_vruntime;
 
-	/*
-	 * The 'current' period is already promised to the current tasks,
-	 * however the extra weight of the new task will slow them down a
-	 * little, place the new task so that it fits in the slot that
-	 * stays open at the end.
-	 */
-	if (initial && sched_feat(START_DEBIT))
-		vruntime += sched_vslice(cfs_rq, se);
-
-	/* sleeps up to a single latency don't count. */
-	if (!initial) {
-		unsigned long thresh;
-
-		if (se_is_idle(se))
-			thresh = sysctl_sched_min_granularity;
-		else
-			thresh = sysctl_sched_latency;
-
+	if (!initial)
+		/* sleeps up to a single latency don't count. */
+		vruntime -= get_sleep_latency(se_is_idle(se));
+	else if (sched_feat(START_DEBIT))
 		/*
-		 * Halve their sleep time's effect, to allow
-		 * for a gentler effect of sleepers:
+		 * The 'current' period is already promised to the current tasks,
+		 * however the extra weight of the new task will slow them down a
+		 * little, place the new task so that it fits in the slot that
+		 * stays open at the end.
 		 */
-		if (sched_feat(GENTLE_FAIR_SLEEPERS))
-			thresh >>= 1;
-
-		vruntime -= thresh;
-	}
+		vruntime += sched_vslice(cfs_rq, se);
 
 	/* ensure we never gain time by being placed backwards. */
 	se->vruntime = max_vruntime(se->vruntime, vruntime);
@@ -7520,6 +7504,18 @@ wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se)
 		return -1;
 
 	gran = wakeup_gran(se);
+
+	/*
+	 * At wake up, the vruntime of a task is capped to not be older than
+	 * a sched_latency period compared to min_vruntime. This prevents long
+	 * sleeping task to get unlimited credit at wakeup. Such waking up task
+	 * has to preempt current in order to not lose its share of CPU
+	 * bandwidth but wakeup_gran() can become higher than scheduling period
+	 * for low priority task. Make sure that long sleeping task will get a
+	 * chance to preempt current.
+	 */
+	gran = min_t(s64, gran, get_latency_max());
+
 	if (vdiff > gran)
 		return 1;
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 771f8ddb7053..842ce0094d9c 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2453,9 +2453,9 @@ extern void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags);
 extern const_debug unsigned int sysctl_sched_nr_migrate;
 extern const_debug unsigned int sysctl_sched_migration_cost;
 
-#ifdef CONFIG_SCHED_DEBUG
 extern unsigned int sysctl_sched_latency;
 extern unsigned int sysctl_sched_min_granularity;
+#ifdef CONFIG_SCHED_DEBUG
 extern unsigned int sysctl_sched_idle_min_granularity;
 extern unsigned int sysctl_sched_wakeup_granularity;
 extern int sysctl_resched_latency_warn_ms;
@@ -2470,6 +2470,38 @@ extern unsigned int sysctl_numa_balancing_scan_size;
 extern unsigned int sysctl_numa_balancing_hot_threshold;
 #endif
 
+static inline unsigned long get_sleep_latency(bool idle)
+{
+	unsigned long thresh;
+
+	if (idle)
+		thresh = sysctl_sched_min_granularity;
+	else
+		thresh = sysctl_sched_latency;
+
+	/*
+	 * Halve their sleep time's effect, to allow
+	 * for a gentler effect of sleepers:
+	 */
+	if (sched_feat(GENTLE_FAIR_SLEEPERS))
+		thresh >>= 1;
+
+	return thresh;
+}
+
+static inline unsigned long get_latency_max(void)
+{
+	unsigned long thresh = get_sleep_latency(false);
+
+	 /*
+	  * If the waking task failed to preempt current it could to wait up to
+	  * sysctl_sched_min_granularity before preempting it during next tick.
+	  */
+	thresh -= sysctl_sched_min_granularity;
+
+	return thresh;
+}
+
 #ifdef CONFIG_SCHED_HRTICK
 
 /*
-- 
2.17.1