Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip into next

Pull scheduler updates from Ingo Molnar:
 "The main scheduling related changes in this cycle were:

   - various sched/numa updates, for better performance

   - tree wide cleanup of open coded nice levels

   - nohz fix related to rq->nr_running use

   - cpuidle changes and continued consolidation to improve the
     kernel/sched/idle.c high level idle scheduling logic.  As part of
     this effort I pulled cpuidle driver changes from Rafael as well.

   - standardized idle polling amongst architectures

   - continued work on preparing better power/energy aware scheduling

   - sched/rt updates

   - misc fixlets and cleanups"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (49 commits)
  sched/numa: Decay ->wakee_flips instead of zeroing
  sched/numa: Update migrate_improves/degrades_locality()
  sched/numa: Allow task switch if load imbalance improves
  sched/rt: Fix 'struct sched_dl_entity' and dl_task_time() comments, to match the current upstream code
  sched: Consolidate open coded implementations of nice level frobbing into nice_to_rlimit() and rlimit_to_nice()
  sched: Initialize rq->age_stamp on processor start
  sched, nohz: Change rq->nr_running to always use wrappers
  sched: Fix the rq->next_balance logic in rebalance_domains() and idle_balance()
  sched: Use clamp() and clamp_val() to make sys_nice() more readable
  sched: Do not zero sg->cpumask and sg->sgp->power in build_sched_groups()
  sched/numa: Fix initialization of sched_domain_topology for NUMA
  sched: Call select_idle_sibling() when not affine_sd
  sched: Simplify return logic in sched_read_attr()
  sched: Simplify return logic in sched_copy_attr()
  sched: Fix exec_start/task_hot on migrated tasks
  arm64: Remove TIF_POLLING_NRFLAG
  metag: Remove TIF_POLLING_NRFLAG
  sched/idle: Make cpuidle_idle_call() void
  sched/idle: Reflow cpuidle_idle_call()
  sched/idle: Delay clearing the polling bit
  ...

11 files changed, 522 insertions, 339 deletions

diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c
index dbafeac18e4d..0955b885d0dc 100644
--- a/kernel/locking/locktorture.c
+++ b/kernel/locking/locktorture.c
@@ -216,7 +216,7 @@ static int lock_torture_writer(void *arg)
 	static DEFINE_TORTURE_RANDOM(rand);
 
 	VERBOSE_TOROUT_STRING("lock_torture_writer task started");
-	set_user_nice(current, 19);
+	set_user_nice(current, MAX_NICE);
 
 	do {
 		if ((torture_random(&rand) & 0xfffff) == 0)
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 8233cd4047d7..155721f7f909 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -54,9 +54,11 @@ static void freeze_begin(void)
 
 static void freeze_enter(void)
 {
+	cpuidle_use_deepest_state(true);
 	cpuidle_resume();
 	wait_event(suspend_freeze_wait_head, suspend_freeze_wake);
 	cpuidle_pause();
+	cpuidle_use_deepest_state(false);
 }
 
 void freeze_wake(void)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index a62a7dec3986..913c6d6cc2c1 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -522,6 +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
@@ -537,17 +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);
 }
 
@@ -3018,7 +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));
@@ -3042,17 +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;
 
@@ -3642,13 +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;
 }
 
 /**
@@ -3808,7 +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;
@@ -3818,12 +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;
 }
 
 /**
@@ -5093,10 +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;
@@ -5305,7 +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;
 	}
@@ -5336,7 +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;
 	}
@@ -5610,17 +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;
@@ -5633,21 +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.
@@ -5815,8 +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) {
@@ -5866,44 +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;
 
@@ -5991,99 +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)];
@@ -6227,7 +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;
@@ -6235,18 +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)
 		};
 	}
 
@@ -6404,7 +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;
 
@@ -6974,6 +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/deadline.c b/kernel/sched/deadline.c
index 800e99b99075..f9ca7d19781a 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -520,7 +520,7 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
 	 * 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;
@@ -741,7 +741,7 @@ 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);
@@ -755,7 +755,7 @@ 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 0fdb96de81a5..c9617b73bcc0 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)
@@ -1738,6 +1776,7 @@ 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)
@@ -1786,6 +1825,17 @@ 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);
 
 	/*
@@ -1800,7 +1850,7 @@ 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)
@@ -3301,7 +3351,7 @@ 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);
@@ -3352,7 +3402,7 @@ 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)
@@ -3884,7 +3934,7 @@ 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);
 }
@@ -3944,7 +3994,7 @@ 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);
@@ -4015,7 +4065,7 @@ 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;
 	}
 
@@ -4449,10 +4499,10 @@ 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;
 	}
@@ -4520,6 +4570,9 @@ 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 */
 
@@ -5070,6 +5123,7 @@ 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 ||
@@ -5083,21 +5137,29 @@ 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))
@@ -5112,16 +5174,23 @@ 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
@@ -5564,6 +5633,7 @@ 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
@@ -5572,7 +5642,11 @@ 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 */
@@ -6640,17 +6714,44 @@ 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);
 
@@ -6660,8 +6761,15 @@ 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.
@@ -6671,20 +6779,20 @@ 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);
@@ -6696,10 +6804,13 @@ 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();
@@ -6717,20 +6828,13 @@ 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_bal