Merge branch 'sched/urgent' into sched/core, to pick up fixes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

3 files changed, 78 insertions, 40 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index c1b537bc4b90..e406ba0c6891 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1536,7 +1536,9 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
 	for (;;) {
 		/* Any allowed, online CPU? */
 		for_each_cpu(dest_cpu, tsk_cpus_allowed(p)) {
-			if (!cpu_active(dest_cpu))
+			if (!(p->flags & PF_KTHREAD) && !cpu_active(dest_cpu))
+				continue;
+			if (!cpu_online(dest_cpu))
 				continue;
 			goto out;
 		}
@@ -5147,14 +5149,16 @@ void show_state_filter(unsigned long state_filter)
 		/*
 		 * reset the NMI-timeout, listing all files on a slow
 		 * console might take a lot of time:
+		 * Also, reset softlockup watchdogs on all CPUs, because
+		 * another CPU might be blocked waiting for us to process
+		 * an IPI.
 		 */
 		touch_nmi_watchdog();
+		touch_all_softlockup_watchdogs();
 		if (!state_filter || (p->state & state_filter))
 			sched_show_task(p);
 	}
 
-	touch_all_softlockup_watchdogs();
-
 #ifdef CONFIG_SCHED_DEBUG
 	if (!state_filter)
 		sysrq_sched_debug_show();
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 40d5ace002a9..73063560b9ec 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -735,8 +735,6 @@ void post_init_entity_util_avg(struct sched_entity *se)
 	}
 }
 
-static inline unsigned long cfs_rq_runnable_load_avg(struct cfs_rq *cfs_rq);
-static inline unsigned long cfs_rq_load_avg(struct cfs_rq *cfs_rq);
 #else
 void init_entity_runnable_average(struct sched_entity *se)
 {
@@ -2473,28 +2471,22 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 # ifdef CONFIG_SMP
-static inline long calc_tg_weight(struct task_group *tg, struct cfs_rq *cfs_rq)
+static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg)
 {
-	long tg_weight;
+	long tg_weight, load, shares;
 
 	/*
-	 * Use this CPU's real-time load instead of the last load contribution
-	 * as the updating of the contribution is delayed, and we will use the
-	 * the real-time load to calc the share. See update_tg_load_avg().
+	 * This really should be: cfs_rq->avg.load_avg, but instead we use
+	 * cfs_rq->load.weight, which is its upper bound. This helps ramp up
+	 * the shares for small weight interactive tasks.
 	 */
-	tg_weight = atomic_long_read(&tg->load_avg);
-	tg_weight -= cfs_rq->tg_load_avg_contrib;
-	tg_weight += cfs_rq->load.weight;
+	load = scale_load_down(cfs_rq->load.weight);
 
-	return tg_weight;
-}
-
-static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg)
-{
-	long tg_weight, load, shares;
+	tg_weight = atomic_long_read(&tg->load_avg);
 
-	tg_weight = calc_tg_weight(tg, cfs_rq);
-	load = cfs_rq->load.weight;
+	/* Ensure tg_weight >= load */
+	tg_weight -= cfs_rq->tg_load_avg_contrib;
+	tg_weight += load;
 
 	shares = (tg->shares * load);
 	if (tg_weight)
@@ -2513,6 +2505,7 @@ static inline long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg)
 	return tg->shares;
 }
 # endif /* CONFIG_SMP */
+
 static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
 			    unsigned long weight)
 {
@@ -2878,6 +2871,23 @@ static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq)
 	}
 }
 
+/*
+ * Unsigned subtract and clamp on underflow.
+ *
+ * Explicitly do a load-store to ensure the intermediate value never hits
+ * memory. This allows lockless observations without ever seeing the negative
+ * values.
+ */
+#define sub_positive(_ptr, _val) do {				\
+	typeof(_ptr) ptr = (_ptr);				\
+	typeof(*ptr) val = (_val);				\
+	typeof(*ptr) res, var = READ_ONCE(*ptr);		\
+	res = var - val;					\
+	if (res > var)						\
+		res = 0;					\
+	WRITE_ONCE(*ptr, res);					\
+} while (0)
+
 /* Group cfs_rq's load_avg is used for task_h_load and update_cfs_share */
 static inline int
 update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq, bool update_freq)
@@ -2887,15 +2897,15 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq, bool update_freq)
 
 	if (atomic_long_read(&cfs_rq->removed_load_avg)) {
 		s64 r = atomic_long_xchg(&cfs_rq->removed_load_avg, 0);
-		sa->load_avg = max_t(long, sa->load_avg - r, 0);
-		sa->load_sum = max_t(s64, sa->load_sum - r * LOAD_AVG_MAX, 0);
+		sub_positive(&sa->load_avg, r);
+		sub_positive(&sa->load_sum, r * LOAD_AVG_MAX);
 		removed_load = 1;
 	}
 
 	if (atomic_long_read(&cfs_rq->removed_util_avg)) {
 		long r = atomic_long_xchg(&cfs_rq->removed_util_avg, 0);
-		sa->util_avg = max_t(long, sa->util_avg - r, 0);
-		sa->util_sum = max_t(s32, sa->util_sum - r * LOAD_AVG_MAX, 0);
+		sub_positive(&sa->util_avg, r);
+		sub_positive(&sa->util_sum, r * LOAD_AVG_MAX);
 		removed_util = 1;
 	}
 
@@ -2968,10 +2978,10 @@ static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s
 			  &se->avg, se->on_rq * scale_load_down(se->load.weight),
 			  cfs_rq->curr == se, NULL);
 
-	cfs_rq->avg.load_avg = max_t(long, cfs_rq->avg.load_avg - se->avg.load_avg, 0);
-	cfs_rq->avg.load_sum = max_t(s64,  cfs_rq->avg.load_sum - se->avg.load_sum, 0);
-	cfs_rq->avg.util_avg = max_t(long, cfs_rq->avg.util_avg - se->avg.util_avg, 0);
-	cfs_rq->avg.util_sum = max_t(s32,  cfs_rq->avg.util_sum - se->avg.util_sum, 0);
+	sub_positive(&cfs_rq->avg.load_avg, se->avg.load_avg);
+	sub_positive(&cfs_rq->avg.load_sum, se->avg.load_sum);
+	sub_positive(&cfs_rq->avg.util_avg, se->avg.util_avg);
+	sub_positive(&cfs_rq->avg.util_sum, se->avg.util_sum);
 
 	cfs_rq_util_change(cfs_rq);
 }
@@ -3220,7 +3230,7 @@ static inline void check_schedstat_required(void)
 			trace_sched_stat_iowait_enabled()  ||
 			trace_sched_stat_blocked_enabled() ||
 			trace_sched_stat_runtime_enabled())  {
-		pr_warn_once("Scheduler tracepoints stat_sleep, stat_iowait, "
+		printk_deferred_once("Scheduler tracepoints stat_sleep, stat_iowait, "
 			     "stat_blocked and stat_runtime require the "
 			     "kernel parameter schedstats=enabled or "
 			     "kernel.sched_schedstats=1\n");
@@ -4157,6 +4167,26 @@ static void check_enqueue_throttle(struct cfs_rq *cfs_rq)
 	if (!cfs_bandwidth_used())
 		return;
 
+	/* Synchronize hierarchical throttle counter: */
+	if (unlikely(!cfs_rq->throttle_uptodate)) {
+		struct rq *rq = rq_of(cfs_rq);
+		struct cfs_rq *pcfs_rq;
+		struct task_group *tg;
+
+		cfs_rq->throttle_uptodate = 1;
+
+		/* Get closest up-to-date node, because leaves go first: */
+		for (tg = cfs_rq->tg->parent; tg; tg = tg->parent) {
+			pcfs_rq = tg->cfs_rq[cpu_of(rq)];
+			if (pcfs_rq->throttle_uptodate)
+				break;
+		}
+		if (tg) {
+			cfs_rq->throttle_count = pcfs_rq->throttle_count;
+			cfs_rq->throttled_clock_task = rq_clock_task(rq);
+		}
+	}
+
 	/* an active group must be handled by the update_curr()->put() path */
 	if (!cfs_rq->runtime_enabled || cfs_rq->curr)
 		return;
@@ -4472,15 +4502,14 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 
 		/* Don't dequeue parent if it has other entities besides us */
 		if (cfs_rq->load.weight) {
+			/* Avoid re-evaluating load for this entity: */
+			se = parent_entity(se);
 			/*
 			 * Bias pick_next to pick a task from this cfs_rq, as
 			 * p is sleeping when it is within its sched_slice.
 			 */
-			if (task_sleep && parent_entity(se))
-				set_next_buddy(parent_entity(se));
-
-			/* avoid re-evaluating load for this entity */
-			se = parent_entity(se);
+			if (task_sleep && se && !throttled_hierarchy(cfs_rq))
+				set_next_buddy(se);
 			break;
 		}
 		flags |= DEQUEUE_SLEEP;
@@ -4882,19 +4911,24 @@ static long effective_load(struct task_group *tg, int cpu, long wl, long wg)
 		return wl;
 
 	for_each_sched_entity(se) {
-		long w, W;
+		struct cfs_rq *cfs_rq = se->my_q;
+		long W, w = cfs_rq_load_avg(cfs_rq);
 
-		tg = se->my_q->tg;
+		tg = cfs_rq->tg;
 
 		/*
 		 * W = @wg + \Sum rw_j
 		 */
-		W = wg + calc_tg_weight(tg, se->my_q);
+		W = wg + atomic_long_read(&tg->load_avg);
+
+		/* Ensure \Sum rw_j >= rw_i */
+		W -= cfs_rq->tg_load_avg_contrib;
+		W += w;
 
 		/*
 		 * w = rw_i + @wl
 		 */
-		w = cfs_rq_load_avg(se->my_q) + wl;
+		w += wl;
 
 		/*
 		 * wl = S * s'_i; see (2)
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index de607e4febd9..71ce9862abc3 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -437,7 +437,7 @@ struct cfs_rq {
 
 	u64 throttled_clock, throttled_clock_task;
 	u64 throttled_clock_task_time;
-	int throttled, throttle_count;
+	int throttled, throttle_count, throttle_uptodate;
 	struct list_head throttled_list;
 #endif /* CONFIG_CFS_BANDWIDTH */
 #endif /* CONFIG_FAIR_GROUP_SCHED */