Merge branch 'next' (accumulated 3.16 merge window patches) into master

Now that 3.15 is released, this merges the 'next' branch into 'master',
bringing us to the normal situation where my 'master' branch is the
merge window.

* accumulated work in next: (6809 commits)
  ufs: sb mutex merge + mutex_destroy
  powerpc: update comments for generic idle conversion
  cris: update comments for generic idle conversion
  idle: remove cpu_idle() forward declarations
  nbd: zero from and len fields in NBD_CMD_DISCONNECT.
  mm: convert some level-less printks to pr_*
  MAINTAINERS: adi-buildroot-devel is moderated
  MAINTAINERS: add linux-api for review of API/ABI changes
  mm/kmemleak-test.c: use pr_fmt for logging
  fs/dlm/debug_fs.c: replace seq_printf by seq_puts
  fs/dlm/lockspace.c: convert simple_str to kstr
  fs/dlm/config.c: convert simple_str to kstr
  mm: mark remap_file_pages() syscall as deprecated
  mm: memcontrol: remove unnecessary memcg argument from soft limit functions
  mm: memcontrol: clean up memcg zoneinfo lookup
  mm/memblock.c: call kmemleak directly from memblock_(alloc|free)
  mm/mempool.c: update the kmemleak stack trace for mempool allocations
  lib/radix-tree.c: update the kmemleak stack trace for radix tree allocations
  mm: introduce kmemleak_update_trace()
  mm/kmemleak.c: use %u to print ->checksum
  ...

9 files changed, 542 insertions, 351 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 084d17f89139..48e78b657d23 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -90,6 +90,22 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/sched.h>
 
+#ifdef smp_mb__before_atomic
+void __smp_mb__before_atomic(void)
+{
+	smp_mb__before_atomic();
+}
+EXPORT_SYMBOL(__smp_mb__before_atomic);
+#endif
+
+#ifdef smp_mb__after_atomic
+void __smp_mb__after_atomic(void)
+{
+	smp_mb__after_atomic();
+}
+EXPORT_SYMBOL(__smp_mb__after_atomic);
+#endif
+
 void start_bandwidth_timer(struct hrtimer *period_timer, ktime_t period)
 {
 	unsigned long delta;
@@ -506,6 +522,39 @@ static inline void init_hrtick(void)
 #endif	/* CONFIG_SCHED_HRTICK */
 
 /*
+ * cmpxchg based fetch_or, macro so it works for different integer types
+ */
+#define fetch_or(ptr, val)						\
+({	typeof(*(ptr)) __old, __val = *(ptr);				\
+ 	for (;;) {							\
+ 		__old = cmpxchg((ptr), __val, __val | (val));		\
+ 		if (__old == __val)					\
+ 			break;						\
+ 		__val = __old;						\
+ 	}								\
+ 	__old;								\
+})
+
+#ifdef TIF_POLLING_NRFLAG
+/*
+ * Atomically set TIF_NEED_RESCHED and test for TIF_POLLING_NRFLAG,
+ * this avoids any races wrt polling state changes and thereby avoids
+ * spurious IPIs.
+ */
+static bool set_nr_and_not_polling(struct task_struct *p)
+{
+	struct thread_info *ti = task_thread_info(p);
+	return !(fetch_or(&ti->flags, _TIF_NEED_RESCHED) & _TIF_POLLING_NRFLAG);
+}
+#else
+static bool set_nr_and_not_polling(struct task_struct *p)
+{
+	set_tsk_need_resched(p);
+	return true;
+}
+#endif
+
+/*
  * resched_task - mark a task 'to be rescheduled now'.
  *
  * On UP this means the setting of the need_resched flag, on SMP it
@@ -521,17 +570,15 @@ void resched_task(struct task_struct *p)
 	if (test_tsk_need_resched(p))
 		return;
 
-	set_tsk_need_resched(p);
-
 	cpu = task_cpu(p);
+
 	if (cpu == smp_processor_id()) {
+		set_tsk_need_resched(p);
 		set_preempt_need_resched();
 		return;
 	}
 
-	/* NEED_RESCHED must be visible before we test polling */
-	smp_mb();
-	if (!tsk_is_polling(p))
+	if (set_nr_and_not_polling(p))
 		smp_send_reschedule(cpu);
 }
 
@@ -1320,7 +1367,7 @@ out:
 		 * leave kernel.
 		 */
 		if (p->mm && printk_ratelimit()) {
-			printk_sched("process %d (%s) no longer affine to cpu%d\n",
+			printk_deferred("process %d (%s) no longer affine to cpu%d\n",
 					task_pid_nr(p), p->comm, cpu);
 		}
 	}
@@ -3002,7 +3049,7 @@ EXPORT_SYMBOL(set_user_nice);
 int can_nice(const struct task_struct *p, const int nice)
 {
 	/* convert nice value [19,-20] to rlimit style value [1,40] */
-	int nice_rlim = 20 - nice;
+	int nice_rlim = nice_to_rlimit(nice);
 
 	return (nice_rlim <= task_rlimit(p, RLIMIT_NICE) ||
 		capable(CAP_SYS_NICE));
@@ -3026,17 +3073,10 @@ SYSCALL_DEFINE1(nice, int, increment)
 	 * We don't have to worry. Conceptually one call occurs first
 	 * and we have a single winner.
 	 */
-	if (increment < -40)
-		increment = -40;
-	if (increment > 40)
-		increment = 40;
-
+	increment = clamp(increment, -NICE_WIDTH, NICE_WIDTH);
 	nice = task_nice(current) + increment;
-	if (nice < MIN_NICE)
-		nice = MIN_NICE;
-	if (nice > MAX_NICE)
-		nice = MAX_NICE;
 
+	nice = clamp_val(nice, MIN_NICE, MAX_NICE);
 	if (increment < 0 && !can_nice(current, nice))
 		return -EPERM;
 
@@ -3626,13 +3666,11 @@ static int sched_copy_attr(struct sched_attr __user *uattr,
 	 */
 	attr->sched_nice = clamp(attr->sched_nice, MIN_NICE, MAX_NICE);
 
-out:
-	return ret;
+	return 0;
 
 err_size:
 	put_user(sizeof(*attr), &uattr->size);
-	ret = -E2BIG;
-	goto out;
+	return -E2BIG;
 }
 
 /**
@@ -3792,7 +3830,7 @@ static int sched_read_attr(struct sched_attr __user *uattr,
 
 		for (; addr < end; addr++) {
 			if (*addr)
-				goto err_size;
+				return -EFBIG;
 		}
 
 		attr->size = usize;
@@ -3802,12 +3840,7 @@ static int sched_read_attr(struct sched_attr __user *uattr,
 	if (ret)
 		return -EFAULT;
 
-out:
-	return ret;
-
-err_size:
-	ret = -E2BIG;
-	goto out;
+	return 0;
 }
 
 /**
@@ -4084,6 +4117,7 @@ static void __cond_resched(void)
 
 int __sched _cond_resched(void)
 {
+	rcu_cond_resched();
 	if (should_resched()) {
 		__cond_resched();
 		return 1;
@@ -4102,15 +4136,18 @@ EXPORT_SYMBOL(_cond_resched);
  */
 int __cond_resched_lock(spinlock_t *lock)
 {
+	bool need_rcu_resched = rcu_should_resched();
 	int resched = should_resched();
 	int ret = 0;
 
 	lockdep_assert_held(lock);
 
-	if (spin_needbreak(lock) || resched) {
+	if (spin_needbreak(lock) || resched || need_rcu_resched) {
 		spin_unlock(lock);
 		if (resched)
 			__cond_resched();
+		else if (unlikely(need_rcu_resched))
+			rcu_resched();
 		else
 			cpu_relax();
 		ret = 1;
@@ -4124,6 +4161,7 @@ int __sched __cond_resched_softirq(void)
 {
 	BUG_ON(!in_softirq());
 
+	rcu_cond_resched();  /* BH disabled OK, just recording QSes. */
 	if (should_resched()) {
 		local_bh_enable();
 		__cond_resched();
@@ -5072,10 +5110,20 @@ static struct notifier_block migration_notifier = {
 	.priority = CPU_PRI_MIGRATION,
 };
 
+static void __cpuinit set_cpu_rq_start_time(void)
+{
+	int cpu = smp_processor_id();
+	struct rq *rq = cpu_rq(cpu);
+	rq->age_stamp = sched_clock_cpu(cpu);
+}
+
 static int sched_cpu_active(struct notifier_block *nfb,
 				      unsigned long action, void *hcpu)
 {
 	switch (action & ~CPU_TASKS_FROZEN) {
+	case CPU_STARTING:
+		set_cpu_rq_start_time();
+		return NOTIFY_OK;
 	case CPU_DOWN_FAILED:
 		set_cpu_active((long)hcpu, true);
 		return NOTIFY_OK;
@@ -5284,7 +5332,8 @@ static int sd_degenerate(struct sched_domain *sd)
 			 SD_BALANCE_FORK |
 			 SD_BALANCE_EXEC |
 			 SD_SHARE_CPUPOWER |
-			 SD_SHARE_PKG_RESOURCES)) {
+			 SD_SHARE_PKG_RESOURCES |
+			 SD_SHARE_POWERDOMAIN)) {
 		if (sd->groups != sd->groups->next)
 			return 0;
 	}
@@ -5315,7 +5364,8 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent)
 				SD_BALANCE_EXEC |
 				SD_SHARE_CPUPOWER |
 				SD_SHARE_PKG_RESOURCES |
-				SD_PREFER_SIBLING);
+				SD_PREFER_SIBLING |
+				SD_SHARE_POWERDOMAIN);
 		if (nr_node_ids == 1)
 			pflags &= ~SD_SERIALIZE;
 	}
@@ -5589,17 +5639,6 @@ static int __init isolated_cpu_setup(char *str)
 
 __setup("isolcpus=", isolated_cpu_setup);
 
-static const struct cpumask *cpu_cpu_mask(int cpu)
-{
-	return cpumask_of_node(cpu_to_node(cpu));
-}
-
-struct sd_data {
-	struct sched_domain **__percpu sd;
-	struct sched_group **__percpu sg;
-	struct sched_group_power **__percpu sgp;
-};
-
 struct s_data {
 	struct sched_domain ** __percpu sd;
 	struct root_domain	*rd;
@@ -5612,21 +5651,6 @@ enum s_alloc {
 	sa_none,
 };
 
-struct sched_domain_topology_level;
-
-typedef struct sched_domain *(*sched_domain_init_f)(struct sched_domain_topology_level *tl, int cpu);
-typedef const struct cpumask *(*sched_domain_mask_f)(int cpu);
-
-#define SDTL_OVERLAP	0x01
-
-struct sched_domain_topology_level {
-	sched_domain_init_f init;
-	sched_domain_mask_f mask;
-	int		    flags;
-	int		    numa_level;
-	struct sd_data      data;
-};
-
 /*
  * Build an iteration mask that can exclude certain CPUs from the upwards
  * domain traversal.
@@ -5794,8 +5818,6 @@ build_sched_groups(struct sched_domain *sd, int cpu)
 			continue;
 
 		group = get_group(i, sdd, &sg);
-		cpumask_clear(sched_group_cpus(sg));
-		sg->sgp->power = 0;
 		cpumask_setall(sched_group_mask(sg));
 
 		for_each_cpu(j, span) {
@@ -5845,44 +5867,11 @@ static void init_sched_groups_power(int cpu, struct sched_domain *sd)
 	atomic_set(&sg->sgp->nr_busy_cpus, sg->group_weight);
 }
 
-int __weak arch_sd_sibling_asym_packing(void)
-{
-       return 0*SD_ASYM_PACKING;
-}
-
 /*
  * Initializers for schedule domains
  * Non-inlined to reduce accumulated stack pressure in build_sched_domains()
  */
 
-#ifdef CONFIG_SCHED_DEBUG
-# define SD_INIT_NAME(sd, type)		sd->name = #type
-#else
-# define SD_INIT_NAME(sd, type)		do { } while (0)
-#endif
-
-#define SD_INIT_FUNC(type)						\
-static noinline struct sched_domain *					\
-sd_init_##type(struct sched_domain_topology_level *tl, int cpu) 	\
-{									\
-	struct sched_domain *sd = *per_cpu_ptr(tl->data.sd, cpu);	\
-	*sd = SD_##type##_INIT;						\
-	SD_INIT_NAME(sd, type);						\
-	sd->private = &tl->data;					\
-	return sd;							\
-}
-
-SD_INIT_FUNC(CPU)
-#ifdef CONFIG_SCHED_SMT
- SD_INIT_FUNC(SIBLING)
-#endif
-#ifdef CONFIG_SCHED_MC
- SD_INIT_FUNC(MC)
-#endif
-#ifdef CONFIG_SCHED_BOOK
- SD_INIT_FUNC(BOOK)
-#endif
-
 static int default_relax_domain_level = -1;
 int sched_domain_level_max;
 
@@ -5970,99 +5959,154 @@ static void claim_allocations(int cpu, struct sched_domain *sd)
 		*per_cpu_ptr(sdd->sgp, cpu) = NULL;
 }
 
-#ifdef CONFIG_SCHED_SMT
-static const struct cpumask *cpu_smt_mask(int cpu)
-{
-	return topology_thread_cpumask(cpu);
-}
-#endif
-
-/*
- * Topology list, bottom-up.
- */
-static struct sched_domain_topology_level default_topology[] = {
-#ifdef CONFIG_SCHED_SMT
-	{ sd_init_SIBLING, cpu_smt_mask, },
-#endif
-#ifdef CONFIG_SCHED_MC
-	{ sd_init_MC, cpu_coregroup_mask, },
-#endif
-#ifdef CONFIG_SCHED_BOOK
-	{ sd_init_BOOK, cpu_book_mask, },
-#endif
-	{ sd_init_CPU, cpu_cpu_mask, },
-	{ NULL, },
-};
-
-static struct sched_domain_topology_level *sched_domain_topology = default_topology;
-
-#define for_each_sd_topology(tl)			\
-	for (tl = sched_domain_topology; tl->init; tl++)
-
 #ifdef CONFIG_NUMA
-
 static int sched_domains_numa_levels;
 static int *sched_domains_numa_distance;
 static struct cpumask ***sched_domains_numa_masks;
 static int sched_domains_curr_level;
+#endif
 
-static inline int sd_local_flags(int level)
-{
-	if (sched_domains_numa_distance[level] > RECLAIM_DISTANCE)
-		return 0;
-
-	return SD_BALANCE_EXEC | SD_BALANCE_FORK | SD_WAKE_AFFINE;
-}
+/*
+ * SD_flags allowed in topology descriptions.
+ *
+ * SD_SHARE_CPUPOWER      - describes SMT topologies
+ * SD_SHARE_PKG_RESOURCES - describes shared caches
+ * SD_NUMA                - describes NUMA topologies
+ * SD_SHARE_POWERDOMAIN   - describes shared power domain
+ *
+ * Odd one out:
+ * SD_ASYM_PACKING        - describes SMT quirks
+ */
+#define TOPOLOGY_SD_FLAGS		\
+	(SD_SHARE_CPUPOWER |		\
+	 SD_SHARE_PKG_RESOURCES |	\
+	 SD_NUMA |			\
+	 SD_ASYM_PACKING |		\
+	 SD_SHARE_POWERDOMAIN)
 
 static struct sched_domain *
-sd_numa_init(struct sched_domain_topology_level *tl, int cpu)
+sd_init(struct sched_domain_topology_level *tl, int cpu)
 {
 	struct sched_domain *sd = *per_cpu_ptr(tl->data.sd, cpu);
-	int level = tl->numa_level;
-	int sd_weight = cpumask_weight(
-			sched_domains_numa_masks[level][cpu_to_node(cpu)]);
+	int sd_weight, sd_flags = 0;
+
+#ifdef CONFIG_NUMA
+	/*
+	 * Ugly hack to pass state to sd_numa_mask()...
+	 */
+	sched_domains_curr_level = tl->numa_level;
+#endif
+
+	sd_weight = cpumask_weight(tl->mask(cpu));
+
+	if (tl->sd_flags)
+		sd_flags = (*tl->sd_flags)();
+	if (WARN_ONCE(sd_flags & ~TOPOLOGY_SD_FLAGS,
+			"wrong sd_flags in topology description\n"))
+		sd_flags &= ~TOPOLOGY_SD_FLAGS;
 
 	*sd = (struct sched_domain){
 		.min_interval		= sd_weight,
 		.max_interval		= 2*sd_weight,
 		.busy_factor		= 32,
 		.imbalance_pct		= 125,
-		.cache_nice_tries	= 2,
-		.busy_idx		= 3,
-		.idle_idx		= 2,
+
+		.cache_nice_tries	= 0,
+		.busy_idx		= 0,
+		.idle_idx		= 0,
 		.newidle_idx		= 0,
 		.wake_idx		= 0,
 		.forkexec_idx		= 0,
 
 		.flags			= 1*SD_LOAD_BALANCE
 					| 1*SD_BALANCE_NEWIDLE
-					| 0*SD_BALANCE_EXEC
-					| 0*SD_BALANCE_FORK
+					| 1*SD_BALANCE_EXEC
+					| 1*SD_BALANCE_FORK
 					| 0*SD_BALANCE_WAKE
-					| 0*SD_WAKE_AFFINE
+					| 1*SD_WAKE_AFFINE
 					| 0*SD_SHARE_CPUPOWER
 					| 0*SD_SHARE_PKG_RESOURCES
-					| 1*SD_SERIALIZE
+					| 0*SD_SERIALIZE
 					| 0*SD_PREFER_SIBLING
-					| 1*SD_NUMA
-					| sd_local_flags(level)
+					| 0*SD_NUMA
+					| sd_flags
 					,
+
 		.last_balance		= jiffies,
 		.balance_interval	= sd_weight,
+		.smt_gain		= 0,
 		.max_newidle_lb_cost	= 0,
 		.next_decay_max_lb_cost	= jiffies,
+#ifdef CONFIG_SCHED_DEBUG
+		.name			= tl->name,
+#endif
 	};
-	SD_INIT_NAME(sd, NUMA);
-	sd->private = &tl->data;
 
 	/*
-	 * Ugly hack to pass state to sd_numa_mask()...
+	 * Convert topological properties into behaviour.
 	 */
-	sched_domains_curr_level = tl->numa_level;
+
+	if (sd->flags & SD_SHARE_CPUPOWER) {
+		sd->imbalance_pct = 110;
+		sd->smt_gain = 1178; /* ~15% */
+
+	} else if (sd->flags & SD_SHARE_PKG_RESOURCES) {
+		sd->imbalance_pct = 117;
+		sd->cache_nice_tries = 1;
+		sd->busy_idx = 2;
+
+#ifdef CONFIG_NUMA
+	} else if (sd->flags & SD_NUMA) {
+		sd->cache_nice_tries = 2;
+		sd->busy_idx = 3;
+		sd->idle_idx = 2;
+
+		sd->flags |= SD_SERIALIZE;
+		if (sched_domains_numa_distance[tl->numa_level] > RECLAIM_DISTANCE) {
+			sd->flags &= ~(SD_BALANCE_EXEC |
+				       SD_BALANCE_FORK |
+				       SD_WAKE_AFFINE);
+		}
+
+#endif
+	} else {
+		sd->flags |= SD_PREFER_SIBLING;
+		sd->cache_nice_tries = 1;
+		sd->busy_idx = 2;
+		sd->idle_idx = 1;
+	}
+
+	sd->private = &tl->data;
 
 	return sd;
 }
 
+/*
+ * Topology list, bottom-up.
+ */
+static struct sched_domain_topology_level default_topology[] = {
+#ifdef CONFIG_SCHED_SMT
+	{ cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT) },
+#endif
+#ifdef CONFIG_SCHED_MC
+	{ cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) },
+#endif
+	{ cpu_cpu_mask, SD_INIT_NAME(DIE) },
+	{ NULL, },
+};
+
+struct sched_domain_topology_level *sched_domain_topology = default_topology;
+
+#define for_each_sd_topology(tl)			\
+	for (tl = sched_domain_topology; tl->mask; tl++)
+
+void set_sched_topology(struct sched_domain_topology_level *tl)
+{
+	sched_domain_topology = tl;
+}
+
+#ifdef CONFIG_NUMA
+
 static const struct cpumask *sd_numa_mask(int cpu)
 {
 	return sched_domains_numa_masks[sched_domains_curr_level][cpu_to_node(cpu)];
@@ -6206,7 +6250,10 @@ static void sched_init_numa(void)
 		}
 	}
 
-	tl = kzalloc((ARRAY_SIZE(default_topology) + level) *
+	/* Compute default topology size */
+	for (i = 0; sched_domain_topology[i].mask; i++);
+
+	tl = kzalloc((i + level + 1) *
 			sizeof(struct sched_domain_topology_level), GFP_KERNEL);
 	if (!tl)
 		return;
@@ -6214,18 +6261,19 @@ static void sched_init_numa(void)
 	/*
 	 * Copy the default topology bits..
 	 */
-	for (i = 0; default_topology[i].init; i++)
-		tl[i] = default_topology[i];
+	for (i = 0; sched_domain_topology[i].mask; i++)
+		tl[i] = sched_domain_topology[i];
 
 	/*
 	 * .. and append 'j' levels of NUMA goodness.
 	 */
 	for (j = 0; j < level; i++, j++) {
 		tl[i] = (struct sched_domain_topology_level){
-			.init = sd_numa_init,
 			.mask = sd_numa_mask,
+			.sd_flags = cpu_numa_flags,
 			.flags = SDTL_OVERLAP,
 			.numa_level = j,
+			SD_INIT_NAME(NUMA)
 		};
 	}
 
@@ -6383,7 +6431,7 @@ struct sched_domain *build_sched_domain(struct sched_domain_topology_level *tl,
 		const struct cpumask *cpu_map, struct sched_domain_attr *attr,
 		struct sched_domain *child, int cpu)
 {
-	struct sched_domain *sd = tl->init(tl, cpu);
+	struct sched_domain *sd = sd_init(tl, cpu);
 	if (!sd)
 		return child;
 
@@ -6953,6 +7001,7 @@ void __init sched_init(void)
 	if (cpu_isolated_map == NULL)
 		zalloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT);
 	idle_thread_set_boot_cpu();
+	set_cpu_rq_start_time();
 #endif
 	init_sched_fair_class();
 
diff --git a/kernel/sched/cpupri.c b/kernel/sched/cpupri.c
index 8834243abee2..981fcd7dc394 100644
--- a/kernel/sched/cpupri.c
+++ b/kernel/sched/cpupri.c
@@ -165,7 +165,7 @@ void cpupri_set(struct cpupri *cp, int cpu, int newpri)
 		 * do a write memory barrier, and then update the count, to
 		 * make sure the vector is visible when count is set.
 		 */
-		smp_mb__before_atomic_inc();
+		smp_mb__before_atomic();
 		atomic_inc(&(vec)->count);
 		do_mb = 1;
 	}
@@ -185,14 +185,14 @@ void cpupri_set(struct cpupri *cp, int cpu, int newpri)
 		 * the new priority vec.
 		 */
 		if (do_mb)
-			smp_mb__after_atomic_inc();
+			smp_mb__after_atomic();
 
 		/*
 		 * When removing from the vector, we decrement the counter first
 		 * do a memory barrier and then clear the mask.
 		 */
 		atomic_dec(&(vec)->count);
-		smp_mb__after_atomic_inc();
+		smp_mb__after_atomic();
 		cpumask_clear_cpu(cpu, vec->mask);
 	}
 
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 14bc348ba3b4..2b8cbf09d1a4 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -348,12 +348,7 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se,
 	 * entity.
 	 */
 	if (dl_time_before(dl_se->deadline, rq_clock(rq))) {
-		static bool lag_once = false;
-
-		if (!lag_once) {
-			lag_once = true;
-			printk_sched("sched: DL replenish lagged to much\n");
-		}
+		printk_deferred_once("sched: DL replenish lagged to much\n");
 		dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline;
 		dl_se->runtime = pi_se->dl_runtime;
 	}
@@ -528,7 +523,7 @@ again:
 	 * We need to take care of a possible races here. In fact, the
 	 * task might have changed its scheduling policy to something
 	 * different from SCHED_DEADLINE or changed its reservation
-	 * parameters (through sched_setscheduler()).
+	 * parameters (through sched_setattr()).
 	 */
 	if (!dl_task(p) || dl_se->dl_new)
 		goto unlock;
@@ -749,7 +744,7 @@ void inc_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
 
 	WARN_ON(!dl_prio(prio));
 	dl_rq->dl_nr_running++;
-	inc_nr_running(rq_of_dl_rq(dl_rq));
+	add_nr_running(rq_of_dl_rq(dl_rq), 1);
 
 	inc_dl_deadline(dl_rq, deadline);
 	inc_dl_migration(dl_se, dl_rq);
@@ -763,7 +758,7 @@ void dec_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
 	WARN_ON(!dl_prio(prio));
 	WARN_ON(!dl_rq->dl_nr_running);
 	dl_rq->dl_nr_running--;
-	dec_nr_running(rq_of_dl_rq(dl_rq));
+	sub_nr_running(rq_of_dl_rq(dl_rq), 1);
 
 	dec_dl_deadline(dl_rq, dl_se->deadline);
 	dec_dl_migration(dl_se, dl_rq);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 8cbe2d2c16de..17de1956ddad 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1095,6 +1095,34 @@ static void task_numa_assign(struct task_numa_env *env,
 	env->best_cpu = env->dst_cpu;
 }
 
+static bool load_too_imbalanced(long orig_src_load, long orig_dst_load,
+				long src_load, long dst_load,
+				struct task_numa_env *env)
+{
+	long imb, old_imb;
+
+	/* We care about the slope of the imbalance, not the direction. */
+	if (dst_load < src_load)
+		swap(dst_load, src_load);
+
+	/* Is the difference below the threshold? */
+	imb = dst_load * 100 - src_load * env->imbalance_pct;
+	if (imb <= 0)
+		return false;
+
+	/*
+	 * The imbalance is above the allowed threshold.
+	 * Compare it with the old imbalance.
+	 */
+	if (orig_dst_load < orig_src_load)
+		swap(orig_dst_load, orig_src_load);
+
+	old_imb = orig_dst_load * 100 - orig_src_load * env->imbalance_pct;
+
+	/* Would this change make things worse? */
+	return (old_imb > imb);
+}
+
 /*
  * This checks if the overall compute and NUMA accesses of the system would
  * be improved if the source tasks was migrated to the target dst_cpu taking
@@ -1107,7 +1135,8 @@ static void task_numa_compare(struct task_numa_env *env,
 	struct rq *src_rq = cpu_rq(env->src_cpu);
 	struct rq *dst_rq = cpu_rq(env->dst_cpu);
 	struct task_struct *cur;
-	long dst_load, src_load;
+	long orig_src_load, src_load;
+	long orig_dst_load, dst_load;
 	long load;
 	long imp = (groupimp > 0) ? groupimp : taskimp;
 
@@ -1181,13 +1210,13 @@ static void task_numa_compare(struct task_numa_env *env,
 	 * In the overloaded case, try and keep the load balanced.
 	 */
 balance:
-	dst_load = env->dst_stats.load;
-	src_load = env->src_stats.load;
+	orig_dst_load = env->dst_stats.load;
+	orig_src_load = env->src_stats.load;
 
 	/* XXX missing power terms */
 	load = task_h_load(env->p);
-	dst_load += load;
-	src_load -= load;
+	dst_load = orig_dst_load + load;
+	src_load = orig_src_load - load;
 
 	if (cur) {
 		load = task_h_load(cur);
@@ -1195,11 +1224,8 @@ balance:
 		src_load += load;
 	}
 
-	/* make src_load the smaller */
-	if (dst_load < src_load)
-		swap(dst_load, src_load);
-
-	if (src_load * env->imbalance_pct < dst_load * 100)
+	if (load_too_imbalanced(orig_src_load, orig_dst_load,
+				src_load, dst_load, env))
 		goto unlock;
 
 assign:
@@ -1301,7 +1327,16 @@ static int task_numa_migrate(struct task_struct *p)
 	if (env.best_cpu == -1)
 		return -EAGAIN;
 
-	sched_setnuma(p, env.dst_nid);
+	/*
+	 * If the task is part of a workload that spans multiple NUMA nodes,
+	 * and is migrating into one of the workload's active nodes, remember
+	 * this node as the task's preferred numa node, so the workload can
+	 * settle down.
+	 * A task that migrated to a second choice node will be better off
+	 * trying for a better one later. Do not set the preferred node here.
+	 */
+	if (p->numa_group && node_isset(env.dst_nid, p->numa_group->active_nodes))
+		sched_setnuma(p, env.dst_nid);
 
 	/*
 	 * Reset the scan period if the task is being rescheduled on an
@@ -1326,12 +1361,15 @@ static int task_numa_migrate(struct task_struct *p)
 /* Attempt to migrate a task to a CPU on the preferred node. */
 static void numa_migrate_preferred(struct task_struct *p)
 {
+	unsigned long interval = HZ;
+
 	/* This task has no NUMA fault statistics yet */
 	if (unlikely(p->numa_preferred_nid == -1 || !p->numa_faults_memory))
 		return;
 
 	/* Periodically retry migrating the task to the preferred node */
-	p->numa_migrate_retry = jiffies + HZ;
+	interval = min(interval, msecs_to_jiffies(p->numa_scan_period) / 16);
+	p->numa_migrate_retry = jiffies + interval;
 
 	/* Success if task is already running on preferred CPU */
 	if (task_node(p) == p->numa_preferred_nid)
@@ -1739,6 +1777,7 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags)
 	struct task_struct *p = current;
 	bool migrated = flags & TNF_MIGRATED;
 	int cpu_node = task_node(current);
+	int local = !!(flags & TNF_FAULT_LOCAL);
 	int priv;
 
 	if (!numabalancing_enabled)
@@ -1787,6 +1826,17 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags)
 			task_numa_group(p, last_cpupid, flags, &priv);
 	}
 
+	/*
+	 * If a workload spans multiple NUMA nodes, a shared fault that
+	 * occurs wholly within the set of nodes that the workload is
+	 * actively using should be counted as local. This allows the
+	 * scan rate to slow down when a workload has settled down.
+	 */
+	if (!priv && !local && p->numa_group &&
+			node_isset(cpu_node, p->numa_group->active_nodes) &&
+			node_isset(mem_node, p->numa_group->active_nodes))
+		local = 1;
+
 	task_numa_placement(p);
 
 	/*
@@ -1801,7 +1851,7 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags)
 
 	p->numa_faults_buffer_memory[task_faults_idx(mem_node, priv)] += pages;
 	p->numa_faults_buffer_cpu[task_faults_idx(cpu_node, priv)] += pages;
-	p->numa_faults_locality[!!(flags & TNF_FAULT_LOCAL)] += pages;
+	p->numa_faults_locality[local] += pages;
 }
 
 static void reset_ptenuma_scan(struct task_struct *p)
@@ -3302,7 +3352,7 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq)
 	}
 
 	if (!se)
-		rq->nr_running -= task_delta;
+		sub_nr_running(rq, task_delta);
 
 	cfs_rq->throttled = 1;
 	cfs_rq->throttled_clock = rq_clock(rq);
@@ -3353,7 +3403,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
 	}
 
 	if (!se)
-		rq->nr_running += task_delta;
+		add_nr_running(rq, task_delta);
 
 	/* determine whether we need to wake up potentially idle cpu */
 	if (rq->curr == rq->idle && rq->cfs.nr_running)
@@ -3885,7 +3935,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 
 	if (!se) {
 		update_rq_runnable_avg(rq, rq->nr_running);
-		inc_nr_running(rq);
+		add_nr_running(rq, 1);
 	}
 	hrtick_update(rq);
 }
@@ -3945,7 +3995,7 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	}
 
 	if (!se) {
-		dec_nr_running(rq);
+		sub_nr_running(rq, 1);
 		update_rq_runnable_avg(rq, 1);
 	}
 	hrtick_update(rq);
@@ -4016,7 +4066,7 @@ static void record_wakee(struct task_struct *p)
 	 * about the loss.
 	 */
 	if (jiffies > current->wakee_flip_decay_ts + HZ) {
-		current->wakee_flips = 0;
+		current->wakee_flips >>= 1;
 		current->wakee_flip_decay_ts = jiffies;
 	}
 
@@ -4450,10 +4500,10 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f
 			sd = tmp;
 	}
 
-	if (affine_sd) {
-		if (cpu != prev_cpu && wake_affine(affine_sd, p, sync))
-			prev_cpu = cpu;
+	if (affine_sd && cpu != prev_cpu && wake_affine(affine_sd, p, sync))
+		prev_cpu = cpu;
 
+	if (sd_flag & SD_BALANCE_WAKE) {
 		new_cpu = select_idle_sibling(p, prev_cpu);
 		goto unlock;
 	}
@@ -4521,6 +4571,9 @@ migrate_task_rq_fair(struct task_struct *p, int next_cpu)
 		atomic_long_add(se->avg.load_avg_contrib,
 						&cfs_rq->removed_load);
 	}
+
+	/* We have migrated, no longer consider this task hot */
+	se->exec_start = 0;
 }
 #endif /* CONFIG_SMP */
 
@@ -5071,6 +5124,7 @@ task_hot(struct task_struct *p, u64 now)
 /* Returns true if the destination node has incurred more faults */
 static bool migrate_improves_locality(struct task_struct *p, struct lb_env *env)
 {
+	struct numa_group *numa_group = rcu_dereference(p->numa_group);
 	int src_nid, dst_nid;
 
 	if (!sched_feat(NUMA_FAVOUR_HIGHER) || !p->numa_faults_memory ||
@@ -5084,21 +5138,29 @@ static bool migrate_improves_locality(struct task_struct *p, struct lb_env *env)
 	if (src_nid == dst_nid)
 		return false;
 
-	/* Always encourage migration to the preferred node. */
-	if (dst_nid == p->numa_preferred_nid)
-		return true;
+	if (numa_group) {
+		/* Task is already in the group's interleave set. */
+		if (node_isset(src_nid, numa_group->active_nodes))
+			return false;
+
+		/* Task is moving into the group's interleave set. */
+		if (node_isset(dst_nid, numa_group->active_nodes))
+			return true;
 
-	/* If both task and group weight improve, this move is a winner. */
-	if (task_weight(p, dst_nid) > task_weight(p, src_nid) &&
-	    group_weight(p, dst_nid) > group_weight(p, src_nid))
+		return group_faults(p, dst_nid) > group_faults(p, src_nid);
+	}
+
+	/* Encourage migration to the preferred node. */
+	if (dst_nid == p->numa_preferred_nid)
 		return true;
 
-	return false;
+	return task_faults(p, dst_nid) > task_faults(p, src_nid);
 }
 
 
 static bool migrate_degrades_locality(struct task_struct *p, struct lb_env *env)
 {
+	struct numa_group *numa_group = rcu_dereference(p->numa_group);
 	int src_nid, dst_nid;
 
 	if (!sched_feat(NUMA) || !sched_feat(NUMA_RESIST_LOWER))
@@ -5113,16 +5175,23 @@ static bool migrate_degrades_locality(struct task_struct *p, struct lb_env *env)
 	if (src_nid == dst_nid)
 		return false;
 
+	if (numa_group) {
+		/* Task is moving within/into the group's interleave set. */
+		if (node_isset(dst_nid, numa_group->active_nodes))
+			return false;
+
+		/* Task is moving out of the group's interleave set. */
+		if (node_isset(src_nid, numa_group->active_nodes))
+			return true;
+
+		return group_faults(p, dst_nid) < group_faults(p, src_nid);
+	}
+
 	/* Migrating away from the preferred node is always bad. */
 	if (src_nid == p->numa_preferred_nid)
 		return true;
 
-	/* If either task or group weight get worse, don't do it. */
-	if (task_weight(p, dst_nid) < task_weight(p, src_nid) ||
-	    group_weight(p, dst_nid) < group_weight(p, src_nid))
-		return true;
-
-	return false;
+	return task_faults(p, dst_nid) < task_faults(p, src_nid);
 }
 
 #else
@@ -5565,6 +5634,7 @@ static unsigned long scale_rt_power(int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
 	u64 total, available, age_stamp, avg;
+	s64 delta;
 
 	/*
 	 * Since we're reading these variables without serialization make sure
@@ -5573,7 +5643,11 @@ static unsigned long scale_rt_power(int cpu)
 	age_stamp = ACCESS_ONCE(rq->age_stamp);
 	avg = ACCESS_ONCE(rq->rt_avg);
 
-	total = sched_avg_period() + (rq_clock(rq) - age_stamp);
+	delta = rq_clock(rq) - age_stamp;
+	if (unlikely(delta < 0))
+		delta = 0;
+
+	total = sched_avg_period() + delta;
 
 	if (unlikely(total < avg)) {
 		/* Ensures that power won't end up being negative */
@@ -6641,17 +6715,44 @@ out:
 	return ld_moved;
 }
 
+static inline unsigned long
+get_sd_balance_interval(struct sched_domain *sd, int cpu_busy)
+{
+	unsigned long interval = sd->balance_interval;
+
+	if (cpu_busy)
+		interval *= sd->busy_factor;
+
+	/* scale ms to jiffies */
+	interval = msecs_to_jiffies(interval);
+	interval = clamp(interval, 1UL, max_load_balance_interval);
+
+	return interval;
+}
+
+static inline void
+update_next_balance(struct sched_domain *sd, int cpu_busy, unsigned long *next_balance)
+{
+	unsigned long interval, next;
+
+	interval = get_sd_balance_interval(sd, cpu_busy);
+	next = sd->last_balance + interval;
+
+	if (time_after(*next_balance, next))
+		*next_balance = next;
+}
+
 /*
  * idle_balance is called by schedule() if this_cpu is about to become
  * idle. Attempts to pull tasks from other CPUs.
  */
 static int idle_balance(struct rq *this_rq)
 {
+	unsigned long next_balance = jiffies + HZ;
+	int this_cpu = this_rq->cpu;
 	struct sched_domain *sd;
 	int pulled_task = 0;
-	unsigned long next_balance = jiffies + HZ;
 	u64 curr_cost = 0;
-	int this_cpu = this_rq->cpu;
 
 	idle_enter_fair(this_rq);
 
@@ -6661,8 +6762,15 @@ static int idle_balance(struct rq *this_rq)
 	 */
 	this_rq->idle_stamp = rq_clock(this_rq);
 
-	if (this_rq->avg_idle < sysctl_sched_migration_cost)
+	if (this_rq->avg_idle < sysctl_sched_migration_cost) {
+		rcu_read_lock();
+		sd = rcu_dereference_check_sched_domain(this_rq->sd);
+		if (sd)
+			update_next_balance(sd, 0, &next_balance);
+		rcu_read_unlock();
+
 		goto out;
+	}
 
 	/*
 	 * Drop the rq->lock, but keep IRQ/preempt disabled.
@@ -6672,20 +6780,20 @@ static int idle_balance(struct rq *this_rq)
 	update_blocked_averages(this_cpu);
 	rcu_read_lock();
 	for_each_domain(this_cpu, sd) {
-		unsigned long interval;
 		int continue_balancing = 1;
 		u64 t0, domain_cost;
 
 		if (!(sd->flags & SD_LOAD_BALANCE))
 			continue;
 
-		if (this_rq->avg_idle < curr_cost + sd->max_newidle_lb_cost)
+		if (this_rq->avg_idle < curr_cost + sd->max_newidle_lb_cost) {
+			update_next_balance(sd, 0, &next_balance);
 			break;
+		}
 
 		if (sd->flags & SD_BALANCE_NEWIDLE) {
 			t0 = sched_clock_cpu(this_cpu);
 
-			/* If we've pulled tasks over stop searching: */
 			pulled_task = load_balance(this_cpu, this_rq,
 						   sd, CPU_NEWLY_IDLE,
 						   &continue_balancing);
@@ -6697,10 +6805,13 @@ static int idle_balance(struct rq *this_rq)
 			curr_cost += domain_cost;
 		}
 
-		interval = msecs_to_jiffies(sd->balance_interval);
-		if (time_after(next_balance, sd->last_balance + interval))
-			next_balance = sd->last_balance + interval;
-		if (pulled_task)
+		update_next_balance(sd, 0, &next_balance);
+
+		/*
+		 * Stop searching for tasks to pull if there are
+		 * now runnable tasks on this rq.
+		 */
+		if (pulled_task || this_rq->nr_running > 0)
 			break;
 	}
 	rcu_read_unlock();
@@ -6718,20 +6829,13 @@ static int idle_balance(struct rq *this_rq)
 	if (this_rq->cfs.h_nr_running && !pulled_task)
 		pulled_task = 1;
 
-	if (pulled_task || time_after(jiffies, this_rq->next_balance)) {
-		/*
-		 * We are going idle. next_balance may be set based on
-		 * a busy processor. So reset next_balance.
-		 */
+out:
+	/* Move the next balance forward */
+	if (time_after(this_rq->next_balance, next_balance))
 		this_rq->next_balance = next_balance;
-	}
 
-out:
 	/* Is there a task of a high priority class? */
-	if (this_rq->nr_running != this_rq->cfs.h_nr_running &&
-	    ((this_rq->stop && this_rq->stop->on_rq) ||
-	     this_rq->dl.dl_nr_running ||
-	     (this_rq->rt.rt_nr_running && !rt_rq_throttled(&this_rq->rt))))
+	if (this_rq->nr_running != this_rq->cfs.h_nr_running)
 		pulled_task = -1;
 
 	if (pulled_task) {
@@ -7012,16 +7116,9 @@ static void rebalance_domains(struct rq *rq, enum cpu_idle_type idle)
 			break;
 		}
 
-		interval = sd->balance_interval;
-		if (idle != CPU_IDLE)
-			interval *= sd->busy_factor;
-
-		/* scale ms to jiffies */
-		interval = msecs_to_jiffies(interval);
-		interval = clamp(interval, 1UL, max_load_balance_interval);
+		interval = get_sd_balance_interval(sd, idle != CPU_IDLE);
 
 		need_serialize = sd->flags & SD_SERIALIZE;
-
 		if (need_serialize) {
 			if (!spin_trylock(&balancing))
 				goto out;
@@ -7037,6 +7134,7 @@ static void rebalance_domains(struct rq *rq, enum cpu_idle_type idle)
 				idle = idle_cpu(cpu) ? CPU_IDLE : CPU_NOT_IDLE;
 			}
 			sd->last_balance = jiffies;
+			interval = get_sd_balance_interval(sd, idle != CPU_IDLE);
 		}
 		if (need_serialize)
 			spin_unlock(&balancing);
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 8f4390a079c7..25b9423abce9 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -67,24 +67,21 @@ void __weak arch_cpu_idle(void)
  * cpuidle_idle_call - the main idle function
  *
  * NOTE: no locks or semaphores should be used here
- * return non-zero on failure
  */
-static int cpuidle_idle_call(void)
+static void cpuidle_idle_call(void)
 {
 	struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices);
 	struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
-	int next_state, entered_state, ret;
+	int next_state, entered_state;
 	bool broadcast;
 
 	/*
 	 * Check if the idle task must be rescheduled. If it is the
-	 * case, exit the function after re-enabling the local irq and
-	 * set again the polling flag
+	 * case, exit the function after re-enabling the local irq.
 	 */
-	if (current_clr_polling_and_test()) {
+	if (need_resched()) {
 		local_irq_enable();
-		__current_set_polling();
-		return 0;
+		return;
 	}
 
 	/*
@@ -101,96 +98,79 @@ static int cpuidle_idle_call(void)
 	rcu_idle_enter();
 
 	/*
-	 * Check if the cpuidle framework is ready, otherwise fallback
-	 * to the default arch specific idle method
+	 * Ask the cpuidle framework to choose a convenient idle state.
+	 * Fall back to the default arch idle method on errors.
 	 */
-	ret = cpuidle_enabled(drv, dev);
-
-	if (!ret) {
+	next_state = cpuidle_select(drv, dev);
+	if (next_state < 0) {
+use_default:
 		/*
-		 * Ask the governor to choose an idle state it thinks
-		 * it is convenient to go to. There is *always* a
-		 * convenient idle state
+		 * We can't use the cpuidle framework, let's use the default
+		 * idle routine.
 		 */
-		next_state = cpuidle_select(drv, dev);
-
-		/*
-		 * The idle task must be scheduled, it is pointless to
-		 * go to idle, just update no idle residency and get
-		 * out of this function
-		 */
-		if (current_clr_polling_and_test()) {
-			dev->last_residency = 0;
-			entered_state = next_state;
+		if (current_clr_polling_and_test())
 			local_irq_enable();
-		} else {
-			broadcast = !!(drv->states[next_state].flags &
-				       CPUIDLE_FLAG_TIMER_STOP);
-
-			if (broadcast)
-				/*
-				 * Tell the time framework to switch
-				 * to a broadcast timer because our
-				 * local timer will be shutdown. If a
-				 * local timer is used from another
-				 * cpu as a broadcast timer, this call
-				 * may fail if it is not available
-				 */
-				ret = clockevents_notify(
-					CLOCK_EVT_NOTIFY_BROADCAST_ENTER,
-					&dev->cpu);
-
-			if (!ret) {
-				trace_cpu_idle_rcuidle(next_state, dev->cpu);
-
-				/*
-				 * Enter the idle state previously
-				 * returned by the governor
-				 * decision. This function will block
-				 * until an interrupt occurs and will
-				 * take care of re-enabling the local
-				 * interrupts
-				 */
-				entered_state = cpuidle_enter(drv, dev,
-							      next_state);
-
-				trace_cpu_idle_rcuidle(PWR_EVENT_EXIT,
-						       dev->cpu);
-
-				if (broadcast)
-					clockevents_notify(
-						CLOCK_EVT_NOTIFY_BROADCAST_EXIT,
-						&dev->cpu);
-
-				/*
-				 * Give the governor an opportunity to reflect on the
-				 * outcome
-				 */
-				cpuidle_reflect(dev, entered_state);
-			}
-		}
+		else
+			arch_cpu_idle();
+
+		goto exit_idle;
 	}
 
+
 	/*
-	 * We can't use the cpuidle framework, let's use the default
-	 * idle routine
+	 * The idle task must be scheduled, it is pointless to
+	 * go to idle, just update no idle residency and get
+	 * out of this function
 	 */
-	if (ret)
-		arch_cpu_idle();
+	if (current_clr_polling_and_test()) {
+		dev->last_residency = 0;
+		entered_state = next_state;
+		local_irq_enable();
+		goto exit_idle;
+	}
+
+	broadcast = !!(drv->states[next_state].flags & CPUIDLE_FLAG_TIMER_STOP);
 
+	/*
+	 * Tell the time framework to switch to a broadcast timer
+	 * because our local timer will be shutdown. If a local timer
+	 * is used from another cpu as a broadcast timer, this call may
+	 * fail if it is not available
+	 */
+	if (broadcast &&
+	    clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &dev->cpu))
+		goto use_default;
+
+	trace_cpu_idle_rcuidle(next_state, dev->cpu);
+
+	/*
+	 * Enter the idle state previously returned by the governor decision.
+	 * This function will block until an interrupt occurs and will take
+	 * care of re-enabling the local interrupts
+	 */
+	entered_state = cpuidle_enter(drv, dev, next_state);
+
+	trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, dev->cpu);
+
+	if (broadcast)
+		clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &dev->cpu);
+
+	/*
+	 * Give the governor an opportunity to reflect on the outcome
+	 */
+	cpuidle_reflect(dev, entered_state);
+
+exit_idle:
 	__current_set_polling();
 
 	/*
-	 * It is up to the idle functions to enable back the local
-	 * interrupt
+	 * It is up to the idle functions to reenable local interrupts
 	 */
 	if (WARN_ON_ONCE(irqs_disabled()))
 		local_irq_enable();
 
 	rcu_idle_exit();
 	start_critical_timings();
-
-	return 0;
 }
 
 /*
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index bd2267ad404f..b3512f1afce9 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -79,6 +79,8 @@ void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq)
 	rt_rq->overloaded = 0;
 	plist_head_init(&rt_rq->pushable_tasks);
 #endif
+	/* We start is dequeued state, because no RT tasks are queued */
+	rt_rq->rt_queued = 0;
 
 	rt_rq->rt_time = 0;
 	rt_rq->rt_throttled = 0;
@@ -112,6 +114,13 @@ static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se)
 	return rt_se->rt_rq;
 }
 
+static inline struct rq *rq_of_rt_se(struct sched_rt_entity *rt_se)
+{
+	struct rt_rq *rt_rq = rt_se->rt_rq;
+
+	return rt_rq->rq;
+}
+
 void free_rt_sched_group(struct task_group *tg)
 {
 	int i;
@@ -211,10 +220,16 @@ static inline struct rq *rq_of_rt_rq(struct rt_rq *rt_rq)
 	return container_of(rt_rq, struct rq, rt);
 }
 
-static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se)
+static inline struct rq *rq_of_rt_se(struct sched_rt_entity *rt_se)
 {
 	struct task_struct *p = rt_task_of(rt_se);
-	struct rq *rq = task_rq(p);
+
+	return task_rq(p);
+}
+
+static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se)
+{
+	struct rq *rq = rq_of_rt_se(rt_se);
 
 	return &rq->rt;
 }
@@ -391,6 +406,9 @@ static inline void set_post_schedule(struct rq *rq)
 }
 #endif /* CONFIG_SMP */
 
+static void enqueue_top_rt_rq(struct rt_rq *rt_rq);
+static void dequeue_top_rt_rq(struct rt_rq *rt_rq);
+
 static inline int on_rt_rq(struct sched_rt_entity *rt_se)
 {
 	return !list_empty(&rt_se->run_list);
@@ -452,8 +470,11 @@ static void sched_rt_rq_enqueue(struct rt_rq *rt_rq)
 	rt_se = rt_rq->tg->rt_se[cpu];
 
 	if (rt_rq->rt_nr_running) {
-		if (rt_se && !on_rt_rq(rt_se))
+		if (!rt_se)
+			enqueue_top_rt_rq(rt_rq);
+		else if (!on_rt_rq(rt_se))
 			enqueue_rt_entity(rt_se, false);
+
 		if (rt_rq->highest_prio.curr < curr->prio)
 			resched_task(curr);
 	}
@@ -466,10 +487,17 @@ static void sched_rt_rq_dequeue(struct rt_rq *rt_rq)
 
 	rt_se = rt_rq->tg->rt_se[cpu];
 
-	if (rt_se && on_rt_rq(rt_se))
+	if (!rt_se)
+		dequeue_top_rt_rq(rt_rq);
+	else if (on_rt_rq(rt_se))
 		dequeue_rt_entity(rt_se);
 }
 
+static inline int rt_rq_throttled(struct rt_rq *rt_rq)
+{
+	return rt_rq->rt_throttled && !rt_rq->rt_nr_boosted;
+}
+
 static int rt_se_boosted(struct sched_rt_entity *rt_se)
 {
 	struct rt_rq *rt_rq = group_rt_rq(rt_se);
@@ -532,12 +560,23 @@ static inline struct rt_rq *group_rt_rq(struct sched_rt_entity *rt_se)
 
 static inline void sched_rt_rq_enqueue(struct rt_rq *rt_rq)
 {
-	if (rt_rq->rt_nr_running)
-		resched_task(rq_of_rt_rq(rt_rq)->curr);
+	struct rq *rq = rq_of_rt_rq(rt_rq);
+
+	if (!rt_rq->rt_nr_running)
+		return;
+
+	enqueue_top_rt_rq(rt_rq);
+	resched_task(rq->curr);
 }
 
 static inline void sched_rt_rq_dequeue(struct rt_rq *rt_rq)
 {
+	dequeue_top_rt_rq(rt_rq);
+}
+
+static inline int rt_rq_throttled(struct rt_rq *rt_rq)
+{
+	return rt_rq->rt_throttled;
 }
 
 static inline const struct cpumask *sched_rt_period_mask(void)
@@ -851,14 +890,8 @@ static int sched_rt_runtime_exceeded(struct rt_rq *rt_rq)
 		 * but accrue some time due to boosting.
 		 */
 		if (likely(rt_b->rt_runtime)) {
-			static bool once = false;
-
 			rt_rq->rt_throttled = 1;
-
-			if (!once) {
-				once = true;
-				printk_sched("sched: RT throttling activated\n");
-			}
+			printk_deferred_once("sched: RT throttling activated\n");
 		} else {
 			/*
 			 * In case we did anyway, make it go away,
@@ -922,6 +955,38 @@ static void update_curr_rt(struct rq *rq)
 	}
 }
 
+static void
+dequeue_top_rt_rq(struct rt_rq *rt_rq)
+{
+	struct rq *rq = rq_of_rt_rq(rt_rq);
+
+	BUG_ON(&rq->rt != rt_rq);
+
+	if (!rt_rq->rt_queued)
+		return;
+
+	BUG_ON(!rq->nr_running);
+
+	sub_nr_running(rq, rt_rq->rt_nr_running);
+	rt_rq->rt_queued = 0;
+}
+
+static void
+enqueue_top_rt_rq(struct rt_rq *rt_rq)
+{
+	struct rq *rq = rq_of_rt_rq(rt_rq);
+
+	BUG_ON(&rq->rt != rt_rq);
+
+	if (rt_rq->rt_queued)
+		return;
+	if (rt_rq_throttled(rt_rq) || !rt_rq->rt_nr_running)
+		return;
+
+	add_nr_running(rq, rt_rq->rt_nr_running);
+	rt_rq->rt_queued = 1;
+}
+
 #if defined CONFIG_SMP
 
 static void
@@ -1045,12 +1110,23 @@ void dec_rt_group(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) {}
 #endif /* CONFIG_RT_GROUP_SCHED */
 
 static inline
+unsigned int rt_se_nr_running(struct sched_rt_entity *rt_se)
+{
+	struct rt_rq *group_rq = group_rt_rq(rt_se);
+
+	if (group_rq)
+		return group_rq->rt_nr_running;
+	else
+		return 1;
+}
+
+static inline
 void inc_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
 {
 	int prio = rt_se_prio(rt_se);
 
 	WARN_ON(!rt_prio(prio));
-	rt_rq->rt_nr_running++;
+	rt_rq->rt_nr_running += rt_se_nr_running(rt_se);
 
 	inc_rt_prio(rt_rq, prio);
 	inc_rt_migration(rt_se, rt_rq);
@@ -1062,7 +1138,7 @@ void dec_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
 {
 	WARN_ON(!rt_prio(rt_se_prio(rt_se)));
 	WARN_ON(!rt_rq->rt_nr_running);
-	rt_rq->rt_nr_running--;
+	rt_rq->rt_nr_running -= rt_se_nr_running(rt_se);
 
 	dec_rt_prio(rt_rq, rt_se_prio(rt_se));
 	dec_rt_migration(rt_se, rt_rq);
@@ -1119,6 +1195,8 @@ static void dequeue_rt_stack(struct sched_rt_entity *rt_se)
 		back = rt_se;
 	}
 
+	dequeue_top_rt_rq(rt_rq_of_se(back));
+
 	for (rt_se = back; rt_se; rt_se = rt_se->back) {
 		if (on_rt_rq(rt_se))
 			__dequeue_rt_entity(rt_se);
@@ -1127,13 +1205,18 @@ static void dequeue_rt_stack(struct sched_rt_entity *rt_se)
 
 static void enqueue_rt_entity(struct sched_rt_entity *rt_se, bool head)
 {
+	struct rq *rq = rq_of_rt_se(rt_se);
+
 	dequeue_rt_stack(rt_se);
 	for_each_sched_rt_entity(rt_se)
 		__enqueue_rt_entity(rt_se, head);
+	enqueue_top_rt_rq(&rq->rt);
 }
 
 static void dequeue_rt_entity(struct sched_rt_entity *rt_se)
 {
+	struct rq *rq = rq_of_rt_se(rt_se);
+
 	dequeue_rt_stack(rt_se);
 
 	for_each_sched_rt_entity(rt_se) {
@@ -1142,6 +1225,7 @@ static void dequeue_rt_entity(struct sched_rt_entity *rt_se)
 		if (rt_rq && rt_rq->rt_nr_running)
 			__enqueue_rt_entity(rt_se, false);
 	}
+	enqueue_top_rt_rq(&rq->rt);
 }
 
 /*
@@ -1159,8 +1243,6 @@ enqueue_task_rt(struct rq *rq, struct task_struct *p, int flags)
 
 	if (!task_current(rq, p) && p->nr_cpus_allowed > 1)
 		enqueue_pushable_task(rq, p);
-
-	inc_nr_running(rq);
 }
 
 static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int flags)
@@ -1171,8 +1253,6 @@ static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int flags)
 	dequeue_rt_entity(rt_se);
 
 	dequeue_pushable_task(rq, p);
-
-	dec_nr_running(rq);
 }
 
 /*
@@ -1377,10 +1457,7 @@ pick_next_task_rt(struct rq *rq, struct task_struct *prev)
 	if (prev->sched_class == &rt_sched_class)
 		update_curr_rt(rq);
 
-	if (!rt_rq->rt_nr_running)
-		return NULL;
-
-	if (rt_rq_throttled(rt_rq))
+	if (!rt_rq->rt_queued)
 		return NULL;
 
 	put_prev_task(rq, prev);
@@ -1892,9 +1969,9 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p)
 	 */
 	if (p->on_rq && rq->curr != p) {
 #ifdef CONFIG_SMP
-		if (rq->rt.overloaded && push_rt_task(rq) &&
+		if (p->nr_cpus_allowed > 1 && rq->rt.overloaded &&
 		    /* Don't resched if we changed runqueues */
-		    rq != task_rq(p))
+		    push_rt_task(rq) && rq != task_rq(p))
 			check_resched = 0;
 #endif /* CONFIG_SMP */
 		if (check_resched && p->prio < rq->curr->prio)
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 369b4d663c42..e47679b04d16 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -409,6 +409,8 @@ struct rt_rq {
 	int overloaded;
 	struct plist_head pushable_tasks;
 #endif
+	int rt_queued;
+
 	int rt_throttled;
 	u64 rt_time;
 	u64 rt_runtime;
@@ -423,18 +425,6 @@ struct rt_rq {
 #endif
 };
 
-#ifdef CONFIG_RT_GROUP_SCHED
-static inline int rt_rq_throttled(struct rt_rq *rt_rq)
-{
-	return rt_rq->rt_throttled && !rt_rq->rt_nr_boosted;
-}
-#else
-static inline int rt_rq_throttled(struct rt_rq *rt_rq)
-{
-	return rt_rq->rt_throttled;
-}
-#endif
-
 /* Deadline class' related fields in a runqueue */
 struct dl_rq {
 	/* runqueue is an rbtree, ordered by deadline */
@@ -1216,12 +1206,14 @@ extern void update_idle_cpu_load(struct rq *this_rq);
 
 extern void init_task_runnable_average(struct task_struct *p);
 
-static inline void inc_nr_running(struct rq *rq)
+static inline void add_nr_running(struct rq *rq, unsigned count)
 {
-	rq->nr_running++;
+	unsigned prev_nr = rq->nr_running;
+
+	rq->nr_running = prev_nr + count;
 
 #ifdef CONFIG_NO_HZ_FULL
-	if (rq->nr_running == 2) {
+	if (prev_nr < 2 && rq->nr_running >= 2) {
 		if (tick_nohz_full_cpu(rq->cpu)) {
 			/* Order rq->nr_running write against the IPI */
 			smp_wmb();
@@ -1231,9 +1223,9 @@ static inline void inc_nr_running(struct rq *rq)
 #endif
 }
 
-static inline void dec_nr_running(struct rq *rq)
+static inline void sub_nr_running(struct rq *rq, unsigned count)
 {
-	rq->nr_running--;
+	rq->nr_running -= count;
 }
 
 static inline void rq_last_tick_reset(struct rq *rq)
diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index d6ce65dde541..bfe0edadbfbb 100644
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -41,13 +41,13 @@ pick_next_task_stop(struct rq *rq, struct task_struct *prev)
 static void
 enqueue_task_stop(struct rq *rq, struct task_struct *p, int flags)
 {
-	inc_nr_running(rq);
+	add_nr_running(rq, 1);
 }
 
 static void
 dequeue_task_stop(struct rq *rq, struct task_struct *p, int flags)
 {
-	dec_nr_running(rq);
+	sub_nr_running(rq, 1);
 }
 
 static void yield_task_stop(struct rq *rq)
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index 7d50f794e248..0ffa20ae657b 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -394,7 +394,7 @@ EXPORT_SYMBOL(__wake_up_bit);
  *
  * In order for this to function properly, as it uses waitqueue_active()
  * internally, some kind of memory barrier must be done prior to calling
- * this. Typically, this will be smp_mb__after_clear_bit(), but in some
+ * this. Typically, this will be smp_mb__after_atomic(), but in some
  * cases where bitflags are manipulated non-atomically under a lock, one
  * may need to use a less regular barrier, such fs/inode.c's smp_mb(),
  * because spin_unlock() does not guarantee a memory barrier.