[GIT pull] scheduler fixes for 4.7

[Thomas Gleixner]

Linus,

please pull the latest sched-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git sched-urgent-for-linus

A couple of scheduler fixes:

 - Force watchdog reset while processing sysrq-w
 - Fix a deadlock when enabling trace events in the scheduler
 - Fixes to the throttled next buddy logic
 - Fixes for the average accounting (missing serialization and underflow
   handling)
 - Allow kernel threads for fallback to online but not active cpus

Thanks,

	tglx

------------------>
Andrey Ryabinin (1):
      kernel/sysrq, watchdog, sched/core: Reset watchdog on all CPUs while processing sysrq-w

Josh Poimboeuf (1):
      sched/debug: Fix deadlock when enabling sched events

Konstantin Khlebnikov (2):
      sched/fair: Initialize throttle_count for new task-groups lazily
      sched/fair: Do not announce throttled next buddy in dequeue_task_fair()

Peter Zijlstra (2):
      sched/fair: Fix post_init_entity_util_avg() serialization
      sched/fair: Fix cfs_rq avg tracking underflow

Tejun Heo (1):
      sched/core: Allow kthreads to fall back to online && !active cpus


 kernel/sched/core.c  | 13 ++++++----
 kernel/sched/fair.c  | 72 +++++++++++++++++++++++++++++++++++++++++-----------
 kernel/sched/sched.h |  2 +-
 3 files changed, 66 insertions(+), 21 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 017d5394f5dc..51d7105f529a 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;
 		}
@@ -2535,10 +2537,9 @@ void wake_up_new_task(struct task_struct *p)
 	 */
 	set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0));
 #endif
-	/* Post initialize new task's util average when its cfs_rq is set */
+	rq = __task_rq_lock(p, &rf);
 	post_init_entity_util_avg(&p->se);
 
-	rq = __task_rq_lock(p, &rf);
 	activate_task(rq, p, 0);
 	p->on_rq = TASK_ON_RQ_QUEUED;
 	trace_sched_wakeup_new(p);
@@ -5148,14 +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 218f8e83db73..bdcbeea90c95 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2904,6 +2904,23 @@ 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)
@@ -2913,15 +2930,15 @@ 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;
 	}
 
@@ -2994,10 +3011,10 @@ 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);
 }
@@ -3246,7 +3263,7 @@ 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");
@@ -4185,6 +4202,26 @@ 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;
@@ -4500,15 +4537,14 @@ 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;
@@ -8496,8 +8532,9 @@ void free_fair_sched_group(struct task_group *tg)
 
 int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
 {
-	struct cfs_rq *cfs_rq;
 	struct sched_entity *se;
+	struct cfs_rq *cfs_rq;
+	struct rq *rq;
 	int i;
 
 	tg->cfs_rq = kzalloc(sizeof(cfs_rq) * nr_cpu_ids, GFP_KERNEL);
@@ -8512,6 +8549,8 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
 	init_cfs_bandwidth(tg_cfs_bandwidth(tg));
 
 	for_each_possible_cpu(i) {
+		rq = cpu_rq(i);
+
 		cfs_rq = kzalloc_node(sizeof(struct cfs_rq),
 				      GFP_KERNEL, cpu_to_node(i));
 		if (!cfs_rq)
@@ -8525,7 +8564,10 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
 		init_cfs_rq(cfs_rq);
 		init_tg_cfs_entry(tg, cfs_rq, se, i, parent->se[i]);
 		init_entity_runnable_average(se);
+
+		raw_spin_lock_irq(&rq->lock);
 		post_init_entity_util_avg(se);
+		raw_spin_unlock_irq(&rq->lock);
 	}
 
 	return 1;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 72f1f3087b04..7cbeb92a1cb9 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 */