2 files changed, 55 insertions, 9 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index a03464249..8d5a9fa8a 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -741,6 +741,9 @@ static inline void dequeue_task(struct rq *rq, struct task_struct *p, int flags)
 
 void activate_task(struct rq *rq, struct task_struct *p, int flags)
 {
+	if (task_on_rq_migrating(p))
+		flags |= ENQUEUE_MIGRATED;
+
 	if (task_contributes_to_load(p))
 		rq->nr_uninterruptible--;
 
@@ -3316,8 +3319,7 @@ static noinline void __schedule_bug(struct task_struct *prev)
 		print_ip_sym(preempt_disable_ip);
 		pr_cont("\n");
 	}
-	if (panic_on_warn)
-		panic("scheduling while atomic\n");
+	check_panic_on_warn("scheduling while atomic");
 
 	dump_stack();
 	add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
@@ -4951,14 +4953,14 @@ SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len,
 	if (len & (sizeof(unsigned long)-1))
 		return -EINVAL;
 
-	if (!alloc_cpumask_var(&mask, GFP_KERNEL))
+	if (!zalloc_cpumask_var(&mask, GFP_KERNEL))
 		return -ENOMEM;
 
 	ret = sched_getaffinity(pid, mask);
 	if (ret == 0) {
 		unsigned int retlen = min(len, cpumask_size());
 
-		if (copy_to_user(user_mask_ptr, mask, retlen))
+		if (copy_to_user(user_mask_ptr, cpumask_bits(mask), retlen))
 			ret = -EFAULT;
 		else
 			ret = retlen;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 84e7efda9..eb67f42fb 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3854,6 +3854,29 @@ static void check_spread(struct cfs_rq *cfs_rq, struct sched_entity *se)
 #endif
 }
 
+static inline bool entity_is_long_sleeper(struct sched_entity *se)
+{
+	struct cfs_rq *cfs_rq;
+	u64 sleep_time;
+
+	if (se->exec_start == 0)
+		return false;
+
+	cfs_rq = cfs_rq_of(se);
+
+	sleep_time = rq_clock_task(rq_of(cfs_rq));
+
+	/* Happen while migrating because of clock task divergence */
+	if (sleep_time <= se->exec_start)
+		return false;
+
+	sleep_time -= se->exec_start;
+	if (sleep_time > ((1ULL << 63) / scale_load_down(NICE_0_LOAD)))
+		return true;
+
+	return false;
+}
+
 static void
 place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
 {
@@ -3882,8 +3905,29 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
 		vruntime -= thresh;
 	}
 
-	/* ensure we never gain time by being placed backwards. */
-	se->vruntime = max_vruntime(se->vruntime, vruntime);
+	/*
+	 * Pull vruntime of the entity being placed to the base level of
+	 * cfs_rq, to prevent boosting it if placed backwards.
+	 * However, min_vruntime can advance much faster than real time, with
+	 * the extreme being when an entity with the minimal weight always runs
+	 * on the cfs_rq. If the waking entity slept for a long time, its
+	 * vruntime difference from min_vruntime may overflow s64 and their
+	 * comparison may get inversed, so ignore the entity's original
+	 * vruntime in that case.
+	 * The maximal vruntime speedup is given by the ratio of normal to
+	 * minimal weight: scale_load_down(NICE_0_LOAD) / MIN_SHARES.
+	 * When placing a migrated waking entity, its exec_start has been set
+	 * from a different rq. In order to take into account a possible
+	 * divergence between new and prev rq's clocks task because of irq and
+	 * stolen time, we take an additional margin.
+	 * So, cutting off on the sleep time of
+	 *     2^63 / scale_load_down(NICE_0_LOAD) ~ 104 days
+	 * should be safe.
+	 */
+	if (entity_is_long_sleeper(se))
+		se->vruntime = vruntime;
+	else
+		se->vruntime = max_vruntime(se->vruntime, vruntime);
 }
 
 static void check_enqueue_throttle(struct cfs_rq *cfs_rq);
@@ -3978,6 +4022,9 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 
 	if (flags & ENQUEUE_WAKEUP)
 		place_entity(cfs_rq, se, 0);
+	/* Entity has migrated, no longer consider this task hot */
+	if (flags & ENQUEUE_MIGRATED)
+		se->exec_start = 0;
 
 	check_schedstat_required();
 	update_stats_enqueue(cfs_rq, se, flags);
@@ -6544,9 +6591,6 @@ static void migrate_task_rq_fair(struct task_struct *p, int new_cpu)
 	/* Tell new CPU we are migrated */
 	p->se.avg.last_update_time = 0;
 
-	/* We have migrated, no longer consider this task hot */
-	p->se.exec_start = 0;
-
 	update_scan_period(p, new_cpu);
 }