1 files changed, 90 insertions, 148 deletions

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index fbdca89c677f..26958431deb7 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -689,21 +689,16 @@ u64 avg_vruntime(struct cfs_rq *cfs_rq)
  *
  * XXX could add max_slice to the augmented data to track this.
  */
-static s64 entity_lag(u64 avruntime, struct sched_entity *se)
+static void update_entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	s64 vlag, limit;
 
-	vlag = avruntime - se->vruntime;
-	limit = calc_delta_fair(max_t(u64, 2*se->slice, TICK_NSEC), se);
-
-	return clamp(vlag, -limit, limit);
-}
-
-static void update_entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se)
-{
 	SCHED_WARN_ON(!se->on_rq);
 
-	se->vlag = entity_lag(avg_vruntime(cfs_rq), se);
+	vlag = avg_vruntime(cfs_rq) - se->vruntime;
+	limit = calc_delta_fair(max_t(u64, 2*se->slice, TICK_NSEC), se);
+
+	se->vlag = clamp(vlag, -limit, limit);
 }
 
 /*
@@ -1159,8 +1154,6 @@ static inline void update_curr_task(struct task_struct *p, s64 delta_exec)
 	trace_sched_stat_runtime(p, delta_exec);
 	account_group_exec_runtime(p, delta_exec);
 	cgroup_account_cputime(p, delta_exec);
-	if (p->dl_server)
-		dl_server_update(p->dl_server, delta_exec);
 }
 
 static inline bool did_preempt_short(struct cfs_rq *cfs_rq, struct sched_entity *curr)
@@ -1237,11 +1230,16 @@ static void update_curr(struct cfs_rq *cfs_rq)
 		update_curr_task(p, delta_exec);
 
 		/*
-		 * Any fair task that runs outside of fair_server should
-		 * account against fair_server such that it can account for
-		 * this time and possibly avoid running this period.
+		 * If the fair_server is active, we need to account for the
+		 * fair_server time whether or not the task is running on
+		 * behalf of fair_server or not:
+		 *  - If the task is running on behalf of fair_server, we need
+		 *    to limit its time based on the assigned runtime.
+		 *  - Fair task that runs outside of fair_server should account
+		 *    against fair_server such that it can account for this time
+		 *    and possibly avoid running this period.
 		 */
-		if (p->dl_server != &rq->fair_server)
+		if (dl_server_active(&rq->fair_server))
 			dl_server_update(&rq->fair_server, delta_exec);
 	}
 
@@ -3399,11 +3397,17 @@ retry_pids:
 
 		/* Initialise new per-VMA NUMAB state. */
 		if (!vma->numab_state) {
-			vma->numab_state = kzalloc(sizeof(struct vma_numab_state),
-				GFP_KERNEL);
-			if (!vma->numab_state)
+			struct vma_numab_state *ptr;
+
+			ptr = kzalloc(sizeof(*ptr), GFP_KERNEL);
+			if (!ptr)
 				continue;
 
+			if (cmpxchg(&vma->numab_state, NULL, ptr)) {
+				kfree(ptr);
+				continue;
+			}
+
 			vma->numab_state->start_scan_seq = mm->numa_scan_seq;
 
 			vma->numab_state->next_scan = now +
@@ -3765,137 +3769,32 @@ static inline void
 dequeue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { }
 #endif
 
-static void reweight_eevdf(struct sched_entity *se, u64 avruntime,
-			   unsigned long weight)
-{
-	unsigned long old_weight = se->load.weight;
-	s64 vlag, vslice;
-
-	/*
-	 * VRUNTIME
-	 * --------
-	 *
-	 * COROLLARY #1: The virtual runtime of the entity needs to be
-	 * adjusted if re-weight at !0-lag point.
-	 *
-	 * Proof: For contradiction assume this is not true, so we can
-	 * re-weight without changing vruntime at !0-lag point.
-	 *
-	 *             Weight	VRuntime   Avg-VRuntime
-	 *     before    w          v            V
-	 *      after    w'         v'           V'
-	 *
-	 * Since lag needs to be preserved through re-weight:
-	 *
-	 *	lag = (V - v)*w = (V'- v')*w', where v = v'
-	 *	==>	V' = (V - v)*w/w' + v		(1)
-	 *
-	 * Let W be the total weight of the entities before reweight,
-	 * since V' is the new weighted average of entities:
-	 *
-	 *	V' = (WV + w'v - wv) / (W + w' - w)	(2)
-	 *
-	 * by using (1) & (2) we obtain:
-	 *
-	 *	(WV + w'v - wv) / (W + w' - w) = (V - v)*w/w' + v
-	 *	==> (WV-Wv+Wv+w'v-wv)/(W+w'-w) = (V - v)*w/w' + v
-	 *	==> (WV - Wv)/(W + w' - w) + v = (V - v)*w/w' + v
-	 *	==>	(V - v)*W/(W + w' - w) = (V - v)*w/w' (3)
-	 *
-	 * Since we are doing at !0-lag point which means V != v, we
-	 * can simplify (3):
-	 *
-	 *	==>	W / (W + w' - w) = w / w'
-	 *	==>	Ww' = Ww + ww' - ww
-	 *	==>	W * (w' - w) = w * (w' - w)
-	 *	==>	W = w	(re-weight indicates w' != w)
-	 *
-	 * So the cfs_rq contains only one entity, hence vruntime of
-	 * the entity @v should always equal to the cfs_rq's weighted
-	 * average vruntime @V, which means we will always re-weight
-	 * at 0-lag point, thus breach assumption. Proof completed.
-	 *
-	 *
-	 * COROLLARY #2: Re-weight does NOT affect weighted average
-	 * vruntime of all the entities.
-	 *
-	 * Proof: According to corollary #1, Eq. (1) should be:
-	 *
-	 *	(V - v)*w = (V' - v')*w'
-	 *	==>    v' = V' - (V - v)*w/w'		(4)
-	 *
-	 * According to the weighted average formula, we have:
-	 *
-	 *	V' = (WV - wv + w'v') / (W - w + w')
-	 *	   = (WV - wv + w'(V' - (V - v)w/w')) / (W - w + w')
-	 *	   = (WV - wv + w'V' - Vw + wv) / (W - w + w')
-	 *	   = (WV + w'V' - Vw) / (W - w + w')
-	 *
-	 *	==>  V'*(W - w + w') = WV + w'V' - Vw
-	 *	==>	V' * (W - w) = (W - w) * V	(5)
-	 *
-	 * If the entity is the only one in the cfs_rq, then reweight
-	 * always occurs at 0-lag point, so V won't change. Or else
-	 * there are other entities, hence W != w, then Eq. (5) turns
-	 * into V' = V. So V won't change in either case, proof done.
-	 *
-	 *
-	 * So according to corollary #1 & #2, the effect of re-weight
-	 * on vruntime should be:
-	 *
-	 *	v' = V' - (V - v) * w / w'		(4)
-	 *	   = V  - (V - v) * w / w'
-	 *	   = V  - vl * w / w'
-	 *	   = V  - vl'
-	 */
-	if (avruntime != se->vruntime) {
-		vlag = entity_lag(avruntime, se);
-		vlag = div_s64(vlag * old_weight, weight);
-		se->vruntime = avruntime - vlag;
-	}
-
-	/*
-	 * DEADLINE
-	 * --------
-	 *
-	 * When the weight changes, the virtual time slope changes and
-	 * we should adjust the relative virtual deadline accordingly.
-	 *
-	 *	d' = v' + (d - v)*w/w'
-	 *	   = V' - (V - v)*w/w' + (d - v)*w/w'
-	 *	   = V  - (V - v)*w/w' + (d - v)*w/w'
-	 *	   = V  + (d - V)*w/w'
-	 */
-	vslice = (s64)(se->deadline - avruntime);
-	vslice = div_s64(vslice * old_weight, weight);
-	se->deadline = avruntime + vslice;
-}
+static void place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags);
 
 static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
 			    unsigned long weight)
 {
 	bool curr = cfs_rq->curr == se;
-	u64 avruntime;
 
 	if (se->on_rq) {
 		/* commit outstanding execution time */
 		update_curr(cfs_rq);
-		avruntime = avg_vruntime(cfs_rq);
+		update_entity_lag(cfs_rq, se);
+		se->deadline -= se->vruntime;
+		se->rel_deadline = 1;
 		if (!curr)
 			__dequeue_entity(cfs_rq, se);
 		update_load_sub(&cfs_rq->load, se->load.weight);
 	}
 	dequeue_load_avg(cfs_rq, se);
 
-	if (se->on_rq) {
-		reweight_eevdf(se, avruntime, weight);
-	} else {
-		/*
-		 * Because we keep se->vlag = V - v_i, while: lag_i = w_i*(V - v_i),
-		 * we need to scale se->vlag when w_i changes.
-		 */
-		se->vlag = div_s64(se->vlag * se->load.weight, weight);
-	}
+	/*
+	 * Because we keep se->vlag = V - v_i, while: lag_i = w_i*(V - v_i),
+	 * we need to scale se->vlag when w_i changes.
+	 */
+	se->vlag = div_s64(se->vlag * se->load.weight, weight);
+	if (se->rel_deadline)
+		se->deadline = div_s64(se->deadline * se->load.weight, weight);
 
 	update_load_set(&se->load, weight);
 
@@ -3910,6 +3809,7 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
 	enqueue_load_avg(cfs_rq, se);
 	if (se->on_rq) {
 		update_load_add(&cfs_rq->load, se->load.weight);
+		place_entity(cfs_rq, se, 0);
 		if (!curr)
 			__enqueue_entity(cfs_rq, se);
 
@@ -4056,7 +3956,11 @@ static void update_cfs_group(struct sched_entity *se)
 	struct cfs_rq *gcfs_rq = group_cfs_rq(se);
 	long shares;
 
-	if (!gcfs_rq)
+	/*
+	 * When a group becomes empty, preserve its weight. This matters for
+	 * DELAY_DEQUEUE.
+	 */
+	if (!gcfs_rq || !gcfs_rq->load.weight)
 		return;
 
 	if (throttled_hierarchy(gcfs_rq))
@@ -5350,7 +5254,7 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 
 	se->vruntime = vruntime - lag;
 
-	if (sched_feat(PLACE_REL_DEADLINE) && se->rel_deadline) {
+	if (se->rel_deadline) {
 		se->deadline += se->vruntime;
 		se->rel_deadline = 0;
 		return;
@@ -5465,9 +5369,33 @@ static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
 
 static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq);
 
-static inline void finish_delayed_dequeue_entity(struct sched_entity *se)
+static void set_delayed(struct sched_entity *se)
+{
+	se->sched_delayed = 1;
+	for_each_sched_entity(se) {
+		struct cfs_rq *cfs_rq = cfs_rq_of(se);
+
+		cfs_rq->h_nr_delayed++;
+		if (cfs_rq_throttled(cfs_rq))
+			break;
+	}
+}
+
+static void clear_delayed(struct sched_entity *se)
 {
 	se->sched_delayed = 0;
+	for_each_sched_entity(se) {
+		struct cfs_rq *cfs_rq = cfs_rq_of(se);
+
+		cfs_rq->h_nr_delayed--;
+		if (cfs_rq_throttled(cfs_rq))
+			break;
+	}
+}
+
+static inline void finish_delayed_dequeue_entity(struct sched_entity *se)
+{
+	clear_delayed(se);
 	if (sched_feat(DELAY_ZERO) && se->vlag > 0)
 		se->vlag = 0;
 }
@@ -5478,6 +5406,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	bool sleep = flags & DEQUEUE_SLEEP;
 
 	update_curr(cfs_rq);
+	clear_buddies(cfs_rq, se);
 
 	if (flags & DEQUEUE_DELAYED) {
 		SCHED_WARN_ON(!se->sched_delayed);
@@ -5494,10 +5423,8 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 
 		if (sched_feat(DELAY_DEQUEUE) && delay &&
 		    !entity_eligible(cfs_rq, se)) {
-			if (cfs_rq->next == se)
-				cfs_rq->next = NULL;
 			update_load_avg(cfs_rq, se, 0);
-			se->sched_delayed = 1;
+			set_delayed(se);
 			return false;
 		}
 	}
@@ -5520,8 +5447,6 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 
 	update_stats_dequeue_fair(cfs_rq, se, flags);
 
-	clear_buddies(cfs_rq, se);
-
 	update_entity_lag(cfs_rq, se);
 	if (sched_feat(PLACE_REL_DEADLINE) && !sleep) {
 		se->deadline -= se->vruntime;
@@ -5911,7 +5836,7 @@ static bool throttle_cfs_rq(struct cfs_rq *cfs_rq)
 	struct rq *rq = rq_of(cfs_rq);
 	struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
 	struct sched_entity *se;
-	long task_delta, idle_task_delta, dequeue = 1;
+	long task_delta, idle_task_delta, delayed_delta, dequeue = 1;
 	long rq_h_nr_running = rq->cfs.h_nr_running;
 
 	raw_spin_lock(&cfs_b->lock);
@@ -5944,6 +5869,7 @@ static bool throttle_cfs_rq(struct cfs_rq *cfs_rq)
 
 	task_delta = cfs_rq->h_nr_running;
 	idle_task_delta = cfs_rq->idle_h_nr_running;
+	delayed_delta = cfs_rq->h_nr_delayed;
 	for_each_sched_entity(se) {
 		struct cfs_rq *qcfs_rq = cfs_rq_of(se);
 		int flags;
@@ -5967,6 +5893,7 @@ static bool throttle_cfs_rq(struct cfs_rq *cfs_rq)
 
 		qcfs_rq->h_nr_running -= task_delta;
 		qcfs_rq->idle_h_nr_running -= idle_task_delta;
+		qcfs_rq->h_nr_delayed -= delayed_delta;
 
 		if (qcfs_rq->load.weight) {
 			/* Avoid re-evaluating load for this entity: */
@@ -5989,6 +5916,7 @@ static bool throttle_cfs_rq(struct cfs_rq *cfs_rq)
 
 		qcfs_rq->h_nr_running -= task_delta;
 		qcfs_rq->idle_h_nr_running -= idle_task_delta;
+		qcfs_rq->h_nr_delayed -= delayed_delta;
 	}
 
 	/* At this point se is NULL and we are at root level*/
@@ -6014,7 +5942,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
 	struct rq *rq = rq_of(cfs_rq);
 	struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
 	struct sched_entity *se;
-	long task_delta, idle_task_delta;
+	long task_delta, idle_task_delta, delayed_delta;
 	long rq_h_nr_running = rq->cfs.h_nr_running;
 
 	se = cfs_rq->tg->se[cpu_of(rq)];
@@ -6050,6 +5978,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
 
 	task_delta = cfs_rq->h_nr_running;
 	idle_task_delta = cfs_rq->idle_h_nr_running;
+	delayed_delta = cfs_rq->h_nr_delayed;
 	for_each_sched_entity(se) {
 		struct cfs_rq *qcfs_rq = cfs_rq_of(se);
 
@@ -6067,6 +5996,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
 
 		qcfs_rq->h_nr_running += task_delta;
 		qcfs_rq->idle_h_nr_running += idle_task_delta;
+		qcfs_rq->h_nr_delayed += delayed_delta;
 
 		/* end evaluation on encountering a throttled cfs_rq */
 		if (cfs_rq_throttled(qcfs_rq))
@@ -6084,6 +6014,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
 
 		qcfs_rq->h_nr_running += task_delta;
 		qcfs_rq->idle_h_nr_running += idle_task_delta;
+		qcfs_rq->h_nr_delayed += delayed_delta;
 
 		/* end evaluation on encountering a throttled cfs_rq */
 		if (cfs_rq_throttled(qcfs_rq))
@@ -6937,7 +6868,7 @@ requeue_delayed_entity(struct sched_entity *se)
 	}
 
 	update_load_avg(cfs_rq, se, 0);
-	se->sched_delayed = 0;
+	clear_delayed(se);
 }
 
 /*
@@ -6951,6 +6882,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	struct cfs_rq *cfs_rq;
 	struct sched_entity *se = &p->se;
 	int idle_h_nr_running = task_has_idle_policy(p);
+	int h_nr_delayed = 0;
 	int task_new = !(flags & ENQUEUE_WAKEUP);
 	int rq_h_nr_running = rq->cfs.h_nr_running;
 	u64 slice = 0;
@@ -6977,6 +6909,9 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	if (p->in_iowait)
 		cpufreq_update_util(rq, SCHED_CPUFREQ_IOWAIT);
 
+	if (task_new)
+		h_nr_delayed = !!se->sched_delayed;
+
 	for_each_sched_entity(se) {
 		if (se->on_rq) {
 			if (se->sched_delayed)
@@ -6999,6 +6934,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 
 		cfs_rq->h_nr_running++;
 		cfs_rq->idle_h_nr_running += idle_h_nr_running;
+		cfs_rq->h_nr_delayed += h_nr_delayed;
 
 		if (cfs_rq_is_idle(cfs_rq))
 			idle_h_nr_running = 1;
@@ -7022,6 +6958,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 
 		cfs_rq->h_nr_running++;
 		cfs_rq->idle_h_nr_running += idle_h_nr_running;
+		cfs_rq->h_nr_delayed += h_nr_delayed;
 
 		if (cfs_rq_is_idle(cfs_rq))
 			idle_h_nr_running = 1;
@@ -7084,6 +7021,7 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags)
 	struct task_struct *p = NULL;
 	int idle_h_nr_running = 0;
 	int h_nr_running = 0;
+	int h_nr_delayed = 0;
 	struct cfs_rq *cfs_rq;
 	u64 slice = 0;
 
@@ -7091,6 +7029,8 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags)
 		p = task_of(se);
 		h_nr_running = 1;
 		idle_h_nr_running = task_has_idle_policy(p);
+		if (!task_sleep && !task_delayed)
+			h_nr_delayed = !!se->sched_delayed;
 	} else {
 		cfs_rq = group_cfs_rq(se);
 		slice = cfs_rq_min_slice(cfs_rq);
@@ -7108,6 +7048,7 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags)
 
 		cfs_rq->h_nr_running -= h_nr_running;
 		cfs_rq->idle_h_nr_running -= idle_h_nr_running;
+		cfs_rq->h_nr_delayed -= h_nr_delayed;
 
 		if (cfs_rq_is_idle(cfs_rq))
 			idle_h_nr_running = h_nr_running;
@@ -7146,6 +7087,7 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags)
 
 		cfs_rq->h_nr_running -= h_nr_running;
 		cfs_rq->idle_h_nr_running -= idle_h_nr_running;
+		cfs_rq->h_nr_delayed -= h_nr_delayed;
 
 		if (cfs_rq_is_idle(cfs_rq))
 			idle_h_nr_running = h_nr_running;
@@ -8774,7 +8716,7 @@ static void check_preempt_wakeup_fair(struct rq *rq, struct task_struct *p, int
 	if (unlikely(throttled_hierarchy(cfs_rq_of(pse))))
 		return;
 
-	if (sched_feat(NEXT_BUDDY) && !(wake_flags & WF_FORK)) {
+	if (sched_feat(NEXT_BUDDY) && !(wake_flags & WF_FORK) && !pse->sched_delayed) {
 		set_next_buddy(pse);
 	}
 
@@ -12568,7 +12510,7 @@ static void _nohz_idle_balance(struct rq *this_rq, unsigned int flags)
 		 * work being done for other CPUs. Next load
 		 * balancing owner will pick it up.
 		 */
-		if (need_resched()) {
+		if (!idle_cpu(this_cpu) && need_resched()) {
 			if (flags & NOHZ_STATS_KICK)
 				has_blocked_load = true;
 			if (flags & NOHZ_NEXT_KICK)