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

Pull scheduler updates from Ingo Molnar:
 "The main changes in this cycle are:

   - 'Nested Sleep Debugging', activated when CONFIG_DEBUG_ATOMIC_SLEEP=y.

     This instruments might_sleep() checks to catch places that nest
     blocking primitives - such as mutex usage in a wait loop.  Such
     bugs can result in hard to debug races/hangs.

     Another category of invalid nesting that this facility will detect
     is the calling of blocking functions from within schedule() ->
     sched_submit_work() -> blk_schedule_flush_plug().

     There's some potential for false positives (if secondary blocking
     primitives themselves are not ready yet for this facility), but the
     kernel will warn once about such bugs per bootup, so the warning
     isn't much of a nuisance.

     This feature comes with a number of fixes, for problems uncovered
     with it, so no messages are expected normally.

   - Another round of sched/numa optimizations and refinements, for
     CONFIG_NUMA_BALANCING=y.

   - Another round of sched/dl fixes and refinements.

  Plus various smaller fixes and cleanups"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (54 commits)
  sched: Add missing rcu protection to wake_up_all_idle_cpus
  sched/deadline: Introduce start_hrtick_dl() for !CONFIG_SCHED_HRTICK
  sched/numa: Init numa balancing fields of init_task
  sched/deadline: Remove unnecessary definitions in cpudeadline.h
  sched/cpupri: Remove unnecessary definitions in cpupri.h
  sched/deadline: Fix rq->dl.pushable_tasks bug in push_dl_task()
  sched/fair: Fix stale overloaded status in the busiest group finding logic
  sched: Move p->nr_cpus_allowed check to select_task_rq()
  sched/completion: Document when to use wait_for_completion_io_*()
  sched: Update comments about CLONE_NEWUTS and CLONE_NEWIPC
  sched/fair: Kill task_struct::numa_entry and numa_group::task_list
  sched: Refactor task_struct to use numa_faults instead of numa_* pointers
  sched/deadline: Don't check CONFIG_SMP in switched_from_dl()
  sched/deadline: Reschedule from switched_from_dl() after a successful pull
  sched/deadline: Push task away if the deadline is equal to curr during wakeup
  sched/deadline: Add deadline rq status print
  sched/deadline: Fix artificial overrun introduced by yield_task_dl()
  sched/rt: Clean up check_preempt_equal_prio()
  sched/core: Use dl_bw_of() under rcu_read_lock_sched()
  sched: Check if we got a shallowest_idle_cpu before searching for least_loaded_cpu
  ...

16 files changed, 721 insertions, 213 deletions

diff --git a/kernel/audit.c b/kernel/audit.c
index cebb11db4d34..1f37f15117e5 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -499,7 +499,6 @@ static int kauditd_thread(void *dummy)
 	set_freezable();
 	while (!kthread_should_stop()) {
 		struct sk_buff *skb;
-		DECLARE_WAITQUEUE(wait, current);
 
 		flush_hold_queue();
 
@@ -514,16 +513,8 @@ static int kauditd_thread(void *dummy)
 				audit_printk_skb(skb);
 			continue;
 		}
-		set_current_state(TASK_INTERRUPTIBLE);
-		add_wait_queue(&kauditd_wait, &wait);
 
-		if (!skb_queue_len(&audit_skb_queue)) {
-			try_to_freeze();
-			schedule();
-		}
-
-		__set_current_state(TASK_RUNNING);
-		remove_wait_queue(&kauditd_wait, &wait);
+		wait_event_freezable(kauditd_wait, skb_queue_len(&audit_skb_queue));
 	}
 	return 0;
 }
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 1f107c74087b..723cfc9d0ad7 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -506,6 +506,16 @@ static int validate_change(struct cpuset *cur, struct cpuset *trial)
 			goto out;
 	}
 
+	/*
+	 * We can't shrink if we won't have enough room for SCHED_DEADLINE
+	 * tasks.
+	 */
+	ret = -EBUSY;
+	if (is_cpu_exclusive(cur) &&
+	    !cpuset_cpumask_can_shrink(cur->cpus_allowed,
+				       trial->cpus_allowed))
+		goto out;
+
 	ret = 0;
 out:
 	rcu_read_unlock();
@@ -1429,17 +1439,8 @@ static int cpuset_can_attach(struct cgroup_subsys_state *css,
 		goto out_unlock;
 
 	cgroup_taskset_for_each(task, tset) {
-		/*
-		 * Kthreads which disallow setaffinity shouldn't be moved
-		 * to a new cpuset; we don't want to change their cpu
-		 * affinity and isolating such threads by their set of
-		 * allowed nodes is unnecessary.  Thus, cpusets are not
-		 * applicable for such threads.  This prevents checking for
-		 * success of set_cpus_allowed_ptr() on all attached tasks
-		 * before cpus_allowed may be changed.
-		 */
-		ret = -EINVAL;
-		if (task->flags & PF_NO_SETAFFINITY)
+		ret = task_can_attach(task, cs->cpus_allowed);
+		if (ret)
 			goto out_unlock;
 		ret = security_task_setscheduler(task);
 		if (ret)
diff --git a/kernel/exit.c b/kernel/exit.c
index 5d30019ff953..232c4bc8bcc9 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -997,6 +997,8 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 
 		get_task_struct(p);
 		read_unlock(&tasklist_lock);
+		sched_annotate_sleep();
+
 		if ((exit_code & 0x7f) == 0) {
 			why = CLD_EXITED;
 			status = exit_code >> 8;
@@ -1079,6 +1081,7 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 	 * thread can reap it because we its state == DEAD/TRACE.
 	 */
 	read_unlock(&tasklist_lock);
+	sched_annotate_sleep();
 
 	retval = wo->wo_rusage
 		? getrusage(p, RUSAGE_BOTH, wo->wo_rusage) : 0;
@@ -1210,6 +1213,7 @@ unlock_sig:
 	pid = task_pid_vnr(p);
 	why = ptrace ? CLD_TRAPPED : CLD_STOPPED;
 	read_unlock(&tasklist_lock);
+	sched_annotate_sleep();
 
 	if (unlikely(wo->wo_flags & WNOWAIT))
 		return wait_noreap_copyout(wo, p, pid, uid, why, exit_code);
@@ -1272,6 +1276,7 @@ static int wait_task_continued(struct wait_opts *wo, struct task_struct *p)
 	pid = task_pid_vnr(p);
 	get_task_struct(p);
 	read_unlock(&tasklist_lock);
+	sched_annotate_sleep();
 
 	if (!wo->wo_info) {
 		retval = wo->wo_rusage
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index dadbf88c22c4..454195194d4a 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -378,8 +378,14 @@ done:
 	 * reschedule now, before we try-lock the mutex. This avoids getting
 	 * scheduled out right after we obtained the mutex.
 	 */
-	if (need_resched())
+	if (need_resched()) {
+		/*
+		 * We _should_ have TASK_RUNNING here, but just in case
+		 * we do not, make it so, otherwise we might get stuck.
+		 */
+		__set_current_state(TASK_RUNNING);
 		schedule_preempt_disabled();
+	}
 
 	return false;
 }
diff --git a/kernel/module.c b/kernel/module.c
index 88cec1ddb1e3..e52a8739361a 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -3097,6 +3097,32 @@ static int may_init_module(void)
 }
 
 /*
+ * Can't use wait_event_interruptible() because our condition
+ * 'finished_loading()' contains a blocking primitive itself (mutex_lock).
+ */
+static int wait_finished_loading(struct module *mod)
+{
+	DEFINE_WAIT_FUNC(wait, woken_wake_function);
+	int ret = 0;
+
+	add_wait_queue(&module_wq, &wait);
+	for (;;) {
+		if (finished_loading(mod->name))
+			break;
+
+		if (signal_pending(current)) {
+			ret = -ERESTARTSYS;
+			break;
+		}
+
+		wait_woken(&wait, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
+	}
+	remove_wait_queue(&module_wq, &wait);
+
+	return ret;
+}
+
+/*
  * We try to place it in the list now to make sure it's unique before
  * we dedicate too many resources.  In particular, temporary percpu
  * memory exhaustion.
@@ -3116,8 +3142,8 @@ again:
 		    || old->state == MODULE_STATE_UNFORMED) {
 			/* Wait in case it fails to load. */
 			mutex_unlock(&module_mutex);
-			err = wait_event_interruptible(module_wq,
-					       finished_loading(mod->name));
+
+			err = wait_finished_loading(mod);
 			if (err)
 				goto out_unlocked;
 			goto again;
diff --git a/kernel/sched/completion.c b/kernel/sched/completion.c
index a63f4dc27909..607f852b4d04 100644
--- a/kernel/sched/completion.c
+++ b/kernel/sched/completion.c
@@ -148,7 +148,7 @@ EXPORT_SYMBOL(wait_for_completion_timeout);
  *
  * This waits to be signaled for completion of a specific task. It is NOT
  * interruptible and there is no timeout. The caller is accounted as waiting
- * for IO.
+ * for IO (which traditionally means blkio only).
  */
 void __sched wait_for_completion_io(struct completion *x)
 {
@@ -163,7 +163,8 @@ EXPORT_SYMBOL(wait_for_completion_io);
  *
  * This waits for either a completion of a specific task to be signaled or for a
  * specified timeout to expire. The timeout is in jiffies. It is not
- * interruptible. The caller is accounted as waiting for IO.
+ * interruptible. The caller is accounted as waiting for IO (which traditionally
+ * means blkio only).
  *
  * Return: 0 if timed out, and positive (at least 1, or number of jiffies left
  * till timeout) if completed.
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index e67a6e88e125..bb398c0c5f08 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1008,6 +1008,9 @@ inline int task_curr(const struct task_struct *p)
 	return cpu_curr(task_cpu(p)) == p;
 }
 
+/*
+ * Can drop rq->lock because from sched_class::switched_from() methods drop it.
+ */
 static inline void check_class_changed(struct rq *rq, struct task_struct *p,
 				       const struct sched_class *prev_class,
 				       int oldprio)
@@ -1015,6 +1018,7 @@ static inline void check_class_changed(struct rq *rq, struct task_struct *p,
 	if (prev_class != p->sched_class) {
 		if (prev_class->switched_from)
 			prev_class->switched_from(rq, p);
+		/* Possble rq->lock 'hole'.  */
 		p->sched_class->switched_to(rq, p);
 	} else if (oldprio != p->prio || dl_task(p))
 		p->sched_class->prio_changed(rq, p, oldprio);
@@ -1054,7 +1058,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 	 * ttwu() will sort out the placement.
 	 */
 	WARN_ON_ONCE(p->state != TASK_RUNNING && p->state != TASK_WAKING &&
-			!(task_preempt_count(p) & PREEMPT_ACTIVE));
+			!p->on_rq);
 
 #ifdef CONFIG_LOCKDEP
 	/*
@@ -1407,7 +1411,8 @@ out:
 static inline
 int select_task_rq(struct task_struct *p, int cpu, int sd_flags, int wake_flags)
 {
-	cpu = p->sched_class->select_task_rq(p, cpu, sd_flags, wake_flags);
+	if (p->nr_cpus_allowed > 1)
+		cpu = p->sched_class->select_task_rq(p, cpu, sd_flags, wake_flags);
 
 	/*
 	 * In order not to call set_task_cpu() on a blocking task we need
@@ -1623,8 +1628,10 @@ void wake_up_if_idle(int cpu)
 	struct rq *rq = cpu_rq(cpu);
 	unsigned long flags;
 
-	if (!is_idle_task(rq->curr))
-		return;
+	rcu_read_lock();
+
+	if (!is_idle_task(rcu_dereference(rq->curr)))
+		goto out;
 
 	if (set_nr_if_polling(rq->idle)) {
 		trace_sched_wake_idle_without_ipi(cpu);
@@ -1635,6 +1642,9 @@ void wake_up_if_idle(int cpu)
 		/* Else cpu is not in idle, do nothing here */
 		raw_spin_unlock_irqrestore(&rq->lock, flags);
 	}
+
+out:
+	rcu_read_unlock();
 }
 
 bool cpus_share_cache(int this_cpu, int that_cpu)
@@ -1853,12 +1863,10 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 	p->numa_scan_seq = p->mm ? p->mm->numa_scan_seq : 0;
 	p->numa_scan_period = sysctl_numa_balancing_scan_delay;
 	p->numa_work.next = &p->numa_work;
-	p->numa_faults_memory = NULL;
-	p->numa_faults_buffer_memory = NULL;
+	p->numa_faults = NULL;
 	p->last_task_numa_placement = 0;
 	p->last_sum_exec_runtime = 0;
 
-	INIT_LIST_HEAD(&p->numa_entry);
 	p->numa_group = NULL;
 #endif /* CONFIG_NUMA_BALANCING */
 }
@@ -2034,25 +2042,6 @@ static inline int dl_bw_cpus(int i)
 }
 #endif
 
-static inline
-void __dl_clear(struct dl_bw *dl_b, u64 tsk_bw)
-{
-	dl_b->total_bw -= tsk_bw;
-}
-
-static inline
-void __dl_add(struct dl_bw *dl_b, u64 tsk_bw)
-{
-	dl_b->total_bw += tsk_bw;
-}
-
-static inline
-bool __dl_overflow(struct dl_bw *dl_b, int cpus, u64 old_bw, u64 new_bw)
-{
-	return dl_b->bw != -1 &&
-	       dl_b->bw * cpus < dl_b->total_bw - old_bw + new_bw;
-}
-
 /*
  * We must be sure that accepting a new task (or allowing changing the
  * parameters of an existing one) is consistent with the bandwidth
@@ -2220,7 +2209,6 @@ prepare_task_switch(struct rq *rq, struct task_struct *prev,
 
 /**
  * finish_task_switch - clean up after a task-switch
- * @rq: runqueue associated with task-switch
  * @prev: the thread we just switched away from.
  *
  * finish_task_switch must be called after the context switch, paired
@@ -2232,10 +2220,16 @@ prepare_task_switch(struct rq *rq, struct task_struct *prev,
  * so, we finish that here outside of the runqueue lock. (Doing it
  * with the lock held can cause deadlocks; see schedule() for
  * details.)
+ *
+ * The context switch have flipped the stack from under us and restored the
+ * local variables which were saved when this task called schedule() in the
+ * past. prev == current is still correct but we need to recalculate this_rq
+ * because prev may have moved to another CPU.
  */
-static void finish_task_switch(struct rq *rq, struct task_struct *prev)
+static struct rq *finish_task_switch(struct task_struct *prev)
 	__releases(rq->lock)
 {
+	struct rq *rq = this_rq();
 	struct mm_struct *mm = rq->prev_mm;
 	long prev_state;
 
@@ -2275,6 +2269,7 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev)
 	}
 
 	tick_nohz_task_switch(current);
+	return rq;
 }
 
 #ifdef CONFIG_SMP
@@ -2309,25 +2304,22 @@ static inline void post_schedule(struct rq *rq)
 asmlinkage __visible void schedule_tail(struct task_struct *prev)
 	__releases(rq->lock)
 {
-	struct rq *rq = this_rq();
-
-	finish_task_switch(rq, prev);
+	struct rq *rq;
 
-	/*
-	 * FIXME: do we need to worry about rq being invalidated by the
-	 * task_switch?
-	 */
+	/* finish_task_switch() drops rq->lock and enables preemtion */
+	preempt_disable();
+	rq = finish_task_switch(prev);
 	post_schedule(rq);
+	preempt_enable();
 
 	if (current->set_child_tid)
 		put_user(task_pid_vnr(current), current->set_child_tid);
 }
 
 /*
- * context_switch - switch to the new MM and the new
- * thread's register state.
+ * context_switch - switch to the new MM and the new thread's register state.
  */
-static inline void
+static inline struct rq *
 context_switch(struct rq *rq, struct task_struct *prev,
 	       struct task_struct *next)
 {
@@ -2366,14 +2358,9 @@ context_switch(struct rq *rq, struct task_struct *prev,
 	context_tracking_task_switch(prev, next);
 	/* Here we just switch the register state and the stack. */
 	switch_to(prev, next, prev);
-
 	barrier();
-	/*
-	 * this_rq must be evaluated again because prev may have moved
-	 * CPUs since it called schedule(), thus the 'rq' on its stack
-	 * frame will be invalid.
-	 */
-	finish_task_switch(this_rq(), prev);
+
+	return finish_task_switch(prev);
 }
 
 /*
@@ -2826,15 +2813,8 @@ need_resched:
 		rq->curr = next;
 		++*switch_count;
 
-		context_switch(rq, prev, next); /* unlocks the rq */
-		/*
-		 * The context switch have flipped the stack from under us
-		 * and restored the local variables which were saved when
-		 * this task called schedule() in the past. prev == current
-		 * is still correct, but it can be moved to another cpu/rq.
-		 */
-		cpu = smp_processor_id();
-		rq = cpu_rq(cpu);
+		rq = context_switch(rq, prev, next); /* unlocks the rq */
+		cpu = cpu_of(rq);
 	} else
 		raw_spin_unlock_irq(&rq->lock);
 
@@ -4653,6 +4633,81 @@ void init_idle(struct task_struct *idle, int cpu)
 #endif
 }
 
+int cpuset_cpumask_can_shrink(const struct cpumask *cur,
+			      const struct cpumask *trial)
+{
+	int ret = 1, trial_cpus;
+	struct dl_bw *cur_dl_b;
+	unsigned long flags;
+
+	rcu_read_lock_sched();
+	cur_dl_b = dl_bw_of(cpumask_any(cur));
+	trial_cpus = cpumask_weight(trial);
+
+	raw_spin_lock_irqsave(&cur_dl_b->lock, flags);
+	if (cur_dl_b->bw != -1 &&
+	    cur_dl_b->bw * trial_cpus < cur_dl_b->total_bw)
+		ret = 0;
+	raw_spin_unlock_irqrestore(&cur_dl_b->lock, flags);
+	rcu_read_unlock_sched();
+
+	return ret;
+}
+
+int task_can_attach(struct task_struct *p,
+		    const struct cpumask *cs_cpus_allowed)
+{
+	int ret = 0;
+
+	/*
+	 * Kthreads which disallow setaffinity shouldn't be moved
+	 * to a new cpuset; we don't want to change their cpu
+	 * affinity and isolating such threads by their set of
+	 * allowed nodes is unnecessary.  Thus, cpusets are not
+	 * applicable for such threads.  This prevents checking for
+	 * success of set_cpus_allowed_ptr() on all attached tasks
+	 * before cpus_allowed may be changed.
+	 */
+	if (p->flags & PF_NO_SETAFFINITY) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+#ifdef CONFIG_SMP
+	if (dl_task(p) && !cpumask_intersects(task_rq(p)->rd->span,
+					      cs_cpus_allowed)) {
+		unsigned int dest_cpu = cpumask_any_and(cpu_active_mask,
+							cs_cpus_allowed);
+		struct dl_bw *dl_b;
+		bool overflow;
+		int cpus;
+		unsigned long flags;
+
+		rcu_read_lock_sched();
+		dl_b = dl_bw_of(dest_cpu);
+		raw_spin_lock_irqsave(&dl_b->lock, flags);
+		cpus = dl_bw_cpus(dest_cpu);
+		overflow = __dl_overflow(dl_b, cpus, 0, p->dl.dl_bw);
+		if (overflow)
+			ret = -EBUSY;
+		else {
+			/*
+			 * We reserve space for this task in the destination
+			 * root_domain, as we can't fail after this point.
+			 * We will free resources in the source root_domain
+			 * later on (see set_cpus_allowed_dl()).
+			 */
+			__dl_add(dl_b, p->dl.dl_bw);
+		}
+		raw_spin_unlock_irqrestore(&dl_b->lock, flags);
+		rcu_read_unlock_sched();
+
+	}
+#endif
+out:
+	return ret;
+}
+
 #ifdef CONFIG_SMP
 /*
  * move_queued_task - move a queued task to new rq.
@@ -6103,7 +6158,9 @@ static void claim_allocations(int cpu, struct sched_domain *sd)
 
 #ifdef CONFIG_NUMA
 static int sched_domains_numa_levels;
+enum numa_topology_type sched_numa_topology_type;
 static int *sched_domains_numa_distance;
+int sched_max_numa_distance;
 static struct cpumask ***sched_domains_numa_masks;
 static int sched_domains_curr_level;
 #endif
@@ -6275,7 +6332,7 @@ static void sched_numa_warn(const char *str)
 	printk(KERN_WARNING "\n");
 }
 
-static bool find_numa_distance(int distance)
+bool find_numa_distance(int distance)
 {
 	int i;
 
@@ -6290,6 +6347,56 @@ static bool find_numa_distance(int distance)
 	return false;
 }
 
+/*
+ * A system can have three types of NUMA topology:
+ * NUMA_DIRECT: all nodes are directly connected, or not a NUMA system
+ * NUMA_GLUELESS_MESH: some nodes reachable through intermediary nodes
+ * NUMA_BACKPLANE: nodes can reach other nodes through a backplane
+ *
+ * The difference between a glueless mesh topology and a backplane
+ * topology lies in whether communication between not directly
+ * connected nodes goes through intermediary nodes (where programs
+ * could run), or through backplane controllers. This affects
+ * placement of programs.
+ *
+ * The type of topology can be discerned with the following tests:
+ * - If the maximum distance between any nodes is 1 hop, the system
+ *   is directly connected.
+ * - If for two nodes A and B, located N > 1 hops away from each other,
+ *   there is an intermediary node C, which is < N hops away from both
+ *   nodes A and B, the system is a glueless mesh.
+ */
+static void init_numa_topology_type(void)
+{
+	int a, b, c, n;
+
+	n = sched_max_numa_distance;
+
+	if (n <= 1)
+		sched_numa_topology_type = NUMA_DIRECT;
+
+	for_each_online_node(a) {
+		for_each_online_node(b) {
+			/* Find two nodes furthest removed from each other. */
+			if (node_distance(a, b) < n)
+				continue;
+
+			/* Is there an intermediary node between a and b? */
+			for_each_online_node(c) {
+				if (node_distance(a, c) < n &&
+				    node_distance(b, c) < n) {
+					sched_numa_topology_type =
+							NUMA_GLUELESS_MESH;
+					return;
+				}
+			}
+
+			sched_numa_topology_type = NUMA_BACKPLANE;
+			return;
+		}
+	}
+}
+
 static void sched_init_numa(void)
 {
 	int next_distance, curr_distance = node_distance(0, 0);
@@ -6426,6 +6533,9 @@ static void sched_init_numa(void)
 	sched_domain_topology = tl;
 
 	sched_domains_numa_levels = level;
+	sched_max_numa_distance = sched_domains_numa_distance[level - 1];
+
+	init_numa_topology_type();
 }
 
 static void sched_domains_numa_masks_set(int cpu)
@@ -7178,6 +7288,25 @@ static inline int preempt_count_equals(int preempt_offset)
 
 void __might_sleep(const char *file, int line, int preempt_offset)
 {
+	/*
+	 * Blocking primitives will set (and therefore destroy) current->state,
+	 * since we will exit with TASK_RUNNING make sure we enter with it,
+	 * otherwise we will destroy state.
+	 */
+	if (WARN_ONCE(current->state != TASK_RUNNING,
+			"do not call blocking ops when !TASK_RUNNING; "
+			"state=%lx set at [<%p>] %pS\n",
+			current->state,
+			(void *)current->task_state_change,
+			(void *)current->task_state_change))
+		__set_current_state(TASK_RUNNING);
+
+	___might_sleep(file, line, preempt_offset);
+}
+EXPORT_SYMBOL(__might_sleep);
+
+void ___might_sleep(const char *file, int line, int preempt_offset)
+{
 	static unsigned long prev_jiffy;	/* ratelimiting */
 
 	rcu_sleep_check(); /* WARN_ON_ONCE() by default, no rate limit reqd. */
@@ -7209,7 +7338,7 @@ void __might_sleep(const char *file, int line, int preempt_offset)
 #endif
 	dump_stack();
 }
-EXPORT_SYMBOL(__might_sleep);
+EXPORT_SYMBOL(___might_sleep);
 #endif
 
 #ifdef CONFIG_MAGIC_SYSRQ
diff --git a/kernel/sched/cpudeadline.h b/kernel/sched/cpudeadline.h
index 538c9796ad4a..020039bd1326 100644
--- a/kernel/sched/cpudeadline.h
+++ b/kernel/sched/cpudeadline.h
@@ -25,9 +25,6 @@ int cpudl_find(struct cpudl *cp, struct task_struct *p,
 void cpudl_set(struct cpudl *cp, int cpu, u64 dl, int is_valid);
 int cpudl_init(struct cpudl *cp);
 void cpudl_cleanup(struct cpudl *cp);
-#else
-#define cpudl_set(cp, cpu, dl) do { } while (0)
-#define cpudl_init() do { } while (0)
 #endif /* CONFIG_SMP */
 
 #endif /* _LINUX_CPUDL_H */
diff --git a/kernel/sched/cpupri.h b/kernel/sched/cpupri.h
index 6b033347fdfd..63cbb9ca0496 100644
--- a/kernel/sched/cpupri.h
+++ b/kernel/sched/cpupri.h
@@ -26,9 +26,6 @@ int  cpupri_find(struct cpupri *cp,
 void cpupri_set(struct cpupri *cp, int cpu, int pri);
 int cpupri_init(struct cpupri *cp);
 void cpupri_cleanup(struct cpupri *cp);
-#else
-#define cpupri_set(cp, cpu, pri) do { } while (0)
-#define cpupri_init() do { } while (0)
 #endif
 
 #endif /* _LINUX_CPUPRI_H */
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 28fa9d9e9201..e5db8c6feebd 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -563,11 +563,6 @@ void init_dl_task_timer(struct sched_dl_entity *dl_se)
 {
 	struct hrtimer *timer = &dl_se->dl_timer;
 
-	if (hrtimer_active(timer)) {
-		hrtimer_try_to_cancel(timer);
-		return;
-	}
-
 	hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	timer->function = dl_task_timer;
 }
@@ -633,7 +628,7 @@ static void update_curr_dl(struct rq *rq)
 
 	sched_rt_avg_update(rq, delta_exec);
 
-	dl_se->runtime -= delta_exec;
+	dl_se->runtime -= dl_se->dl_yielded ? 0 : delta_exec;
 	if (dl_runtime_exceeded(rq, dl_se)) {
 		__dequeue_task_dl(rq, curr, 0);
 		if (likely(start_dl_timer(dl_se, curr->dl.dl_boosted)))
@@ -933,7 +928,7 @@ select_task_rq_dl(struct task_struct *p, int cpu, int sd_flag, int flags)
 	struct task_struct *curr;
 	struct rq *rq;
 
-	if (sd_flag != SD_BALANCE_WAKE && sd_flag != SD_BALANCE_FORK)
+	if (sd_flag != SD_BALANCE_WAKE)
 		goto out;
 
 	rq = cpu_rq(cpu);
@@ -1018,6 +1013,10 @@ static void start_hrtick_dl(struct rq *rq, struct task_struct *p)
 {
 	hrtick_start(rq, p->dl.runtime);
 }
+#else /* !CONFIG_SCHED_HRTICK */
+static void start_hrtick_dl(struct rq *rq, struct task_struct *p)
+{
+}
 #endif
 
 static struct sched_dl_entity *pick_next_dl_entity(struct rq *rq,
@@ -1071,10 +1070,8 @@ struct task_struct *pick_next_task_dl(struct rq *rq, struct task_struct *prev)
 	/* Running task will never be pushed. */
        dequeue_pushable_dl_task(rq, p);
 
-#ifdef CONFIG_SCHED_HRTICK
 	if (hrtick_enabled(rq))
 		start_hrtick_dl(rq, p);
-#endif
 
 	set_post_schedule(rq);
 
@@ -1093,10 +1090,8 @@ static void task_tick_dl(struct rq *rq, struct task_struct *p, int queued)
 {
 	update_curr_dl(rq);
 
-#ifdef CONFIG_SCHED_HRTICK
 	if (hrtick_enabled(rq) && queued && p->dl.runtime > 0)
 		start_hrtick_dl(rq, p);
-#endif
 }
 
 static void task_fork_dl(struct task_struct *p)
@@ -1333,6 +1328,7 @@ static int push_dl_task(struct rq *rq)
 {
 	struct task_struct *next_task;
 	struct rq *later_rq;
+	int ret = 0;
 
 	if (!rq->dl.overloaded)
 		return 0;
@@ -1378,7 +1374,6 @@ retry:
 			 * The task is still there. We don't try
 			 * again, some other cpu will pull it when ready.
 			 */
-			dequeue_pushable_dl_task(rq, next_task);
 			goto out;
 		}
 
@@ -1394,6 +1389,7 @@ retry:
 	deactivate_task(rq, next_task, 0);
 	set_task_cpu(next_task, later_rq->cpu);
 	activate_task(later_rq, next_task, 0);
+	ret = 1;
 
 	resched_curr(later_rq);
 
@@ -1402,7 +1398,7 @@ retry:
 out:
 	put_task_struct(next_task);
 
-	return 1;
+	return ret;
 }
 
 static void push_dl_tasks(struct rq *rq)
@@ -1508,7 +1504,7 @@ static void task_woken_dl(struct rq *rq, struct task_struct *p)
 	    p->nr_cpus_allowed > 1 &&
 	    dl_task(rq->curr) &&
 	    (rq->curr->nr_cpus_allowed < 2 ||
-	     dl_entity_preempt(&rq->curr->dl, &p->dl))) {
+	     !dl_entity_preempt(&p->dl, &rq->curr->dl))) {
 		push_dl_tasks(rq);
 	}
 }
@@ -1517,10 +1513,33 @@ static void set_cpus_allowed_dl(struct task_struct *p,
 				const struct cpumask *new_mask)
 {
 	struct rq *rq;
+	struct root_domain *src_rd;
 	int weight;
 
 	BUG_ON(!dl_task(p));
 
+	rq = task_rq(p);
+	src_rd = rq->rd;
+	/*
+	 * Migrating a SCHED_DEADLINE task between exclusive
+	 * cpusets (different root_domains) entails a bandwidth
+	 * update. We already made space for us in the destination
+	 * domain (see cpuset_can_attach()).
+	 */
+	if (!cpumask_intersects(src_rd->span, new_mask)) {
+		struct dl_bw *src_dl_b;
+
+		src_dl_b = dl_bw_of(cpu_of(rq));
+		/*
+		 * We now free resources of the root_domain we are migrating
+		 * off. In the worst case, sched_setattr() may temporary fail
+		 * until we complete the update.
+		 */
+		raw_spin_lock(&src_dl_b->lock);
+		__dl_clear(src_dl_b, p->dl.dl_bw);
+		raw_spin_unlock(&src_dl_b->lock);
+	}
+
 	/*
 	 * Update only if the task is actually running (i.e.,
 	 * it is on the rq AND it is not throttled).
@@ -1537,8 +1556,6 @@ static void set_cpus_allowed_dl(struct task_struct *p,
 	if ((p->nr_cpus_allowed > 1) == (weight > 1))
 		return;
 
-	rq = task_rq(p);
-
 	/*
 	 * The process used to be able to migrate OR it can now migrate
 	 */
@@ -1586,22 +1603,48 @@ void init_sched_dl_class(void)
 
 #endif /* CONFIG_SMP */
 
+/*
+ *  Ensure p's dl_timer is cancelled. May drop rq->lock for a while.
+ */
+static void cancel_dl_timer(struct rq *rq, struct task_struct *p)
+{
+	struct hrtimer *dl_timer = &p->dl.dl_timer;
+
+	/* Nobody will change task's class if pi_lock is held */
+	lockdep_assert_held(&p->pi_lock);
+
+	if (hrtimer_active(dl_timer)) {
+		int ret = hrtimer_try_to_cancel(dl_timer);
+
+		if (unlikely(ret == -1)) {
+			/*
+			 * Note, p may migrate OR new deadline tasks
+			 * may appear in rq when we are unlocking it.
+			 * A caller of us must be fine with that.
+			 */
+			raw_spin_unlock(&rq->lock);
+			hrtimer_cancel(dl_timer);
+			raw_spin_lock(&rq->lock);
+		}
+	}
+}
+
 static void switched_from_dl(struct rq *rq, struct task_struct *p)
 {
-	if (hrtimer_active(&p->dl.dl_timer) && !dl_policy(p->policy))
-		hrtimer_try_to_cancel(&p->dl.dl_timer);
+	cancel_dl_timer(rq, p);
 
 	__dl_clear_params(p);
 
-#ifdef CONFIG_SMP
 	/*
 	 * Since this might be the only -deadline task on the rq,
 	 * this is the right place to try to pull some other one
 	 * from an overloaded cpu, if any.
 	 */
-	if (!rq->dl.dl_nr_running)
-		pull_dl_task(rq);
-#endif
+	if (!task_on_rq_queued(p) || rq->dl.dl_nr_running)
+		return;
+
+	if (pull_dl_task(rq))
+		resched_curr(rq);
 }
 
 /*
@@ -1622,7 +1665,8 @@ static void switched_to_dl(struct rq *rq, struct task_struct *p)
 
 	if (task_on_rq_queued(p) && rq->curr != p) {
 #ifdef CONFIG_SMP
-		if (rq->dl.overloaded && push_dl_task(rq) && rq != task_rq(p))
+		if (p->nr_cpus_allowed > 1 && rq->dl.overloaded &&
+			push_dl_task(rq) && rq != task_rq(p))
 			/* Only reschedule if pushing failed */
 			check_resched = 0;
 #endif /* CONFIG_SMP */
@@ -1704,3 +1748,12 @@ const struct sched_class dl_sched_class = {
 
 	.update_curr		= update_curr_dl,
 };
+
+#ifdef CONFIG_SCHED_DEBUG
+extern void print_dl_rq(struct seq_file *m, int cpu, struct dl_rq *dl_rq);
+
+void print_dl_stats(struct seq_file *m, int cpu)
+{
+	print_dl_rq(m, cpu, &cpu_rq(cpu)->dl);
+}
+#endif /* CONFIG_SCHED_DEBUG */
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index ce33780d8f20..92cc52001e74 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -261,6 +261,12 @@ void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq)
 #undef P
 }
 
+void print_dl_rq(struct seq_file *m, int cpu, struct dl_rq *dl_rq)
+{
+	SEQ_printf(m, "\ndl_rq[%d]:\n", cpu);
+	SEQ_printf(m, "  .%-30s: %ld\n", "dl_nr_running", dl_rq->dl_nr_running);
+}
+
 extern __read_mostly int sched_clock_running;
 
 static void print_cpu(struct seq_file *m, int cpu)
@@ -329,6 +335,7 @@ do {									\
 	spin_lock_irqsave(&sched_debug_lock, flags);
 	print_cfs_stats(m, cpu);
 	print_rt_stats(m, cpu);
+	print_dl_stats(m, cpu);
 
 	print_rq(m, rq, cpu);
 	spin_unlock_irqrestore(&sched_debug_lock, flags);
@@ -528,8 +535,8 @@ static void sched_show_numa(struct task_struct *p, struct seq_file *m)
 			unsigned long nr_faults = -1;
 			int cpu_current, home_node;
 
-			if (p->numa_faults_memory)
-				nr_faults = p->numa_faults_memory[2*node + i];
+			if (p->numa_faults)
+				nr_faults = p->numa_faults[2*node + i];
 
 			cpu_current = !i ? (task_node(p) == node) :
 				(pol && node_isset(node, pol->v.nodes));
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index ef2b104b254c..df2cdf77f899 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -873,7 +873,6 @@ struct numa_group {
 	spinlock_t lock; /* nr_tasks, tasks */
 	int nr_tasks;
 	pid_t gid;
-	struct list_head task_list;
 
 	struct rcu_head rcu;
 	nodemask_t active_nodes;
@@ -901,18 +900,24 @@ pid_t task_numa_group_id(struct task_struct *p)
 	return p->numa_group ? p->numa_group->gid : 0;
 }
 
-static inline int task_faults_idx(int nid, int priv)
+/*
+ * The averaged statistics, shared & private, memory & cpu,
+ * occupy the first half of the array. The second half of the
+ * array is for current counters, which are averaged into the
+ * first set by task_numa_placement.
+ */
+static inline int task_faults_idx(enum numa_faults_stats s, int nid, int priv)
 {
-	return NR_NUMA_HINT_FAULT_TYPES * nid + priv;
+	return NR_NUMA_HINT_FAULT_TYPES * (s * nr_node_ids + nid) + priv;
 }
 
 static inline unsigned long task_faults(struct task_struct *p, int nid)
 {
-	if (!p->numa_faults_memory)
+	if (!p->numa_faults)
 		return 0;
 
-	return p->numa_faults_memory[task_faults_idx(nid, 0)] +
-		p->numa_faults_memory[task_faults_idx(nid, 1)];
+	return p->numa_faults[task_faults_idx(NUMA_MEM, nid, 0)] +
+		p->numa_faults[task_faults_idx(NUMA_MEM, nid, 1)];
 }
 
 static inline unsigned long group_faults(struct task_struct *p, int nid)
@@ -920,14 +925,79 @@ static inline unsigned long group_faults(struct task_struct *p, int nid)
 	if (!p->numa_group)
 		return 0;
 
-	return p->numa_group->faults[task_faults_idx(nid, 0)] +
-		p->numa_group->faults[task_faults_idx(nid, 1)];
+	return p->numa_group->faults[task_faults_idx(NUMA_MEM, nid, 0)] +
+		p->numa_group->faults[task_faults_idx(NUMA_MEM, nid, 1)];
 }
 
 static inline unsigned long group_faults_cpu(struct numa_group *group, int nid)
 {
-	return group->faults_cpu[task_faults_idx(nid, 0)] +
-		group->faults_cpu[task_faults_idx(nid, 1)];
+	return group->faults_cpu[task_faults_idx(NUMA_MEM, nid, 0)] +
+		group->faults_cpu[task_faults_idx(NUMA_MEM, nid, 1)];
+}
+
+/* Handle placement on systems where not all nodes are directly connected. */
+static unsigned long score_nearby_nodes(struct task_struct *p, int nid,
+					int maxdist, bool task)
+{
+	unsigned long score = 0;
+	int node;
+
+	/*
+	 * All nodes are directly connected, and the same distance
+	 * from each other. No need for fancy placement algorithms.
+	 */
+	if (sched_numa_topology_type == NUMA_DIRECT)
+		return 0;
+
+	/*
+	 * This code is called for each node, introducing N^2 complexity,
+	 * which should be ok given the number of nodes rarely exceeds 8.
+	 */
+	for_each_online_node(node) {
+		unsigned long faults;
+		int dist = node_distance(nid, node);
+
+		/*
+		 * The furthest away nodes in the system are not interesting
+		 * for placement; nid was already counted.
+		 */
+		if (dist == sched_max_numa_distance || node == nid)
+			continue;
+
+		/*
+		 * On systems with a backplane NUMA topology, compare groups
+		 * of nodes, and move tasks towards the group with the most
+		 * memory accesses. When comparing two nodes at distance
+		 * "hoplimit", only nodes closer by than "hoplimit" are part
+		 * of each group. Skip other nodes.
+		 */
+		if (sched_numa_topology_type == NUMA_BACKPLANE &&
+					dist > maxdist)
+			continue;
+
+		/* Add up the faults from nearby nodes. */
+		if (task)
+			faults = task_faults(p, node);
+		else
+			faults = group_faults(p, node);
+
+		/*
+		 * On systems with a glueless mesh NUMA topology, there are
+		 * no fixed "groups of nodes". Instead, nodes that are not
+		 * directly connected bounce traffic through intermediate
+		 * nodes; a numa_group can occupy any set of nodes.
+		 * The further away a node is, the less the faults count.
+		 * This seems to result in good task placement.
+		 */
+		if (sched_numa_topology_type == NUMA_GLUELESS_MESH) {
+			faults *= (sched_max_numa_distance - dist);
+			faults /= (sched_max_numa_distance - LOCAL_DISTANCE);
+		}
+
+		score += faults;
+	}
+
+	return score;
 }
 
 /*
@@ -936,11 +1006,12 @@ static inline unsigned long group_faults_cpu(struct numa_group *group, int nid)
  * larger multiplier, in order to group tasks together that are almost
  * evenly spread out between numa nodes.
  */
-static inline unsigned long task_weight(struct task_struct *p, int nid)
+static inline unsigned long task_weight(struct task_struct *p, int nid,
+					int dist)
 {
-	unsigned long total_faults;
+	unsigned long faults, total_faults;
 
-	if (!p->numa_faults_memory)
+	if (!p->numa_faults)
 		return 0;
 
 	total_faults = p->total_numa_faults;
@@ -948,15 +1019,29 @@ static inline unsigned long task_weight(struct task_struct *p, int nid)
 	if (!total_faults)
 		return 0;
 
-	return 1000 * task_faults(p, nid) / total_faults;
+	faults = task_faults(p, nid);
+	faults += score_nearby_nodes(p, nid, dist, true);
+
+	return 1000 * faults / total_faults;
 }
 
-static inline unsigned long group_weight(struct task_struct *p, int nid)
+static inline unsigned long group_weight(struct task_struct *p, int nid,
+					 int dist)
 {
-	if (!p->numa_group || !p->numa_group->total_faults)
+	unsigned long faults, total_faults;
+
+	if (!p->numa_group)
 		return 0;
 
-	return 1000 * group_faults(p, nid) / p->numa_group->total_faults;
+	total_faults = p->numa_group->total_faults;
+
+	if (!total_faults)
+		return 0;
+
+	faults = group_faults(p, nid);
+	faults += score_nearby_nodes(p, nid, dist, false);
+
+	return 1000 * faults / total_faults;
 }
 
 bool should_numa_migrate_memory(struct task_struct *p, struct page * page,
@@ -1089,6 +1174,7 @@ struct task_numa_env {
 	struct numa_stats src_stats, dst_stats;
 
 	int imbalance_pct;
+	int dist;
 
 	struct task_struct *best_task;
 	long best_imp;
@@ -1168,6 +1254,7 @@ static void task_numa_compare(struct task_numa_env *env,
 	long load;
 	long imp = env->p->numa_group ? groupimp : taskimp;
 	long moveimp = imp;
+	int dist = env->dist;
 
 	rcu_read_lock();
 
@@ -1208,8 +1295,8 @@ static void task_numa_compare(struct task_numa_env *env,
 		 * in any group then look only at task weights.
 		 */
 		if (cur->numa_group == env->p->numa_group) {
-			imp = taskimp + task_weight(cur, env->src_nid) -
-			      task_weight(cur, env->dst_nid);
+			imp = taskimp + task_weight(cur, env->src_nid, dist) -
+			      task_weight(cur, env->dst_nid, dist);
 			/*
 			 * Add some hysteresis to prevent swapping the
 			 * tasks within a group over tiny differences.
@@ -1223,11 +1310,11 @@ static void task_numa_compare(struct task_numa_env *env,
 			 * instead.
 			 */
 			if (cur->numa_group)
-				imp += group_weight(cur, env->src_nid) -
-				       group_weight(cur, env->dst_nid);
+				imp += group_weight(cur, env->src_nid, dist) -
+				       group_weight(cur, env->dst_nid, dist);
 			else
-				imp += task_weight(cur, env->src_nid) -
-				       task_weight(cur, env->dst_nid);
+				imp += task_weight(cur, env->src_nid, dist) -
+				       task_weight(cur, env->dst_nid, dist);
 		}
 	}
 
@@ -1326,7 +1413,7 @@ static int task_numa_migrate(struct task_struct *p)
 	};
 	struct sched_domain *sd;
 	unsigned long taskweight, groupweight;
-	int nid, ret;
+	int nid, ret, dist;
 	long taskimp, groupimp;
 
 	/*
@@ -1354,29 +1441,45 @@ static int task_numa_migrate(struct task_struct *p)
 		return -EINVAL;
 	}
 
-	taskweight = task_weight(p, env.src_nid);
-	groupweight = group_weight(p, env.src_nid);
-	update_numa_stats(&env.src_stats, env.src_nid);
 	env.dst_nid = p->numa_preferred_nid;
-	taskimp = task_weight(p, env.dst_nid) - taskweight;
-	groupimp = group_weight(p, env.dst_nid) - groupweight;
+	dist = env.dist = node_distance(env.src_nid, env.dst_nid);
+	taskweight = task_weight(p, env.src_nid, dist);
+	groupweight = group_weight(p, env.src_nid, dist);
+	update_numa_stats(&env.src_stats, env.src_nid);
+	taskimp = task_weight(p, env.dst_nid, dist) - taskweight;
+	groupimp = group_weight(p, env.dst_nid, dist) - groupweight;
 	update_numa_stats(&env.dst_stats, env.dst_nid);
 
 	/* Try to find a spot on the preferred nid. */
 	task_numa_find_cpu(&env, taskimp, groupimp);
 
-	/* No space available on the preferred nid. Look elsewhere. */
-	if (env.best_cpu == -1) {
+	/*
+	 * Look at other nodes in these cases:
+	 * - there is no space available on the preferred_nid
+	 * - the task is part of a numa_group that is interleaved across
+	 *   multiple NUMA nodes; in order to better consolidate the group,
+	 *   we need to check other locations.
+	 */
+	if (env.best_cpu == -1 || (p->numa_group &&
+			nodes_weight(p->numa_group->active_nodes) > 1)) {
 		for_each_online_node(nid) {
 			if (nid == env.src_nid || nid == p->numa_preferred_nid)
 				continue;
 
+			dist = node_distance(env.src_nid, env.dst_nid);
+			if (sched_numa_topology_type == NUMA_BACKPLANE &&
+						dist != env.dist) {
+				taskweight = task_weight(p, env.src_nid, dist);
+				groupweight = group_weight(p, env.src_nid, dist);
+			}
+
 			/* Only consider nodes where both task and groups benefit */
-			taskimp = task_weight(p, nid) - taskweight;
-			groupimp = group_weight(p, nid) - groupweight;
+			taskimp = task_weight(p, nid, dist) - taskweight;
+			groupimp = group_weight(p, nid, dist) - groupweight;
 			if (taskimp < 0 && groupimp < 0)
 				continue;
 
+			env.dist = dist;
 			env.dst_nid = nid;
 			update_numa_stats(&env.dst_stats, env.dst_nid);
 			task_numa_find_cpu(&env, taskimp, groupimp);
@@ -1431,7 +1534,7 @@ 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))
+	if (unlikely(p->numa_preferred_nid == -1 || !p->numa_faults))
 		return;
 
 	/* Periodically retry migrating the task to the preferred node */
@@ -1580,6 +1683,92 @@ static u64 numa_get_avg_runtime(struct task_struct *p, u64 *period)
 	return delta;
 }
 
+/*
+ * Determine the preferred nid for a task in a numa_group. This needs to
+ * be done in a way that produces consistent results with group_weight,
+ * otherwise workloads might not converge.
+ */
+static int preferred_group_nid(struct task_struct *p, int nid)
+{
+	nodemask_t nodes;
+	int dist;
+
+	/* Direct connections between all NUMA nodes. */
+	if (sched_numa_topology_type == NUMA_DIRECT)
+		return nid;
+
+	/*
+	 * On a system with glueless mesh NUMA topology, group_weight
+	 * scores nodes according to the number of NUMA hinting faults on
+	 * both the node itself, and on nearby nodes.
+	 */
+	if (sched_numa_topology_type == NUMA_GLUELESS_MESH) {
+		unsigned long score, max_score = 0;
+		int node, max_node = nid;
+
+		dist = sched_max_numa_distance;
+
+		for_each_online_node(node) {
+			score = group_weight(p, node, dist);
+			if (score > max_score) {
+				max_score = score;
+				max_node = node;
+			}
+		}
+		return max_node;
+	}
+
+	/*
+	 * Finding the preferred nid in a system with NUMA backplane
+	 * interconnect topology is more involved. The goal is to locate
+	 * tasks from numa_groups near each other in the system, and
+	 * untangle workloads from different sides of the system. This requires
+	 * searching down the hierarchy of node groups, recursively searching
+	 * inside the highest scoring group of nodes. The nodemask tricks
+	 * keep the complexity of the search down.
+	 */
+	nodes = node_online_map;
+	for (dist = sched_max_numa_distance; dist > LOCAL_DISTANCE; dist--) {
+		unsigned long max_faults = 0;
+		nodemask_t max_group;
+		int a, b;
+
+		/* Are there nodes at this distance from each other? */
+		if (!find_numa_distance(dist))
+			continue;
+
+		for_each_node_mask(a, nodes) {
+			unsigned long faults = 0;
+			nodemask_t this_group;
+			nodes_clear(this_group);
+
+			/* Sum group's NUMA faults; includes a==b case. */
+			for_each_node_mask(b, nodes) {
+				if (node_distance(a, b) < dist) {
+					faults += group_faults(p, b);
+					node_set(b, this_group);
+					node_clear(b, nodes);
+				}
+			}
+
+			/* Remember the top group. */
+			if (faults > max_faults) {
+				max_faults = faults;
+				max_group = this_group;
+				/*
+				 * subtle: at the smallest distance there is
+				 * just one node left in each "group", the
+				 * winner is the preferred nid.
+				 */
+				nid = a;
+			}
+		}
+		/* Next round, evaluate the nodes within max_group. */
+		nodes = max_group;
+	}
+	return nid;
+}
+
 static void task_numa_placement(struct task_struct *p)
 {
 	int seq, nid, max_nid = -1, max_group_nid = -1;
@@ -1607,18 +1796,23 @@ static void task_numa_placement(struct task_struct *p)
 
 	/* Find the node with the highest number of faults */
 	for_each_online_node(nid) {
+		/* Keep track of the offsets in numa_faults array */
+		int mem_idx, membuf_idx, cpu_idx, cpubuf_idx;
 		unsigned long faults = 0, group_faults = 0;
-		int priv, i;
+		int priv;
 
 		for (priv = 0; priv < NR_NUMA_HINT_FAULT_TYPES; priv++) {
 			long diff, f_diff, f_weight;
 
-			i = task_faults_idx(nid, priv);
+			mem_idx = task_faults_idx(NUMA_MEM, nid, priv);
+			membuf_idx = task_faults_idx(NUMA_MEMBUF, nid, priv);
+			cpu_idx = task_faults_idx(NUMA_CPU, nid, priv);
+			cpubuf_idx = task_faults_idx(NUMA_CPUBUF, nid, priv);
 
 			/* Decay existing window, copy faults since last scan */
-			diff = p->numa_faults_buffer_memory[i] - p->numa_faults_memory[i] / 2;
-			fault_types[priv] += p->numa_faults_buffer_memory[i];
-			p->numa_faults_buffer_memory[i] = 0;
+			diff = p->numa_faults[membuf_idx] - p->numa_faults[mem_idx] / 2;
+			fault_types[priv] += p->numa_faults[membuf_idx];
+			p->numa_faults[membuf_idx] = 0;
 
 			/*
 			 * Normalize the faults_from, so all tasks in a group
@@ -1628,21 +1822,27 @@ static void task_numa_placement(struct task_struct *p)
 			 * faults are less important.
 			 */
 			f_weight = div64_u64(runtime << 16, period + 1);
-			f_weight = (f_weight * p->numa_faults_buffer_cpu[i]) /
+			f_weight = (f_weight * p->numa_faults[cpubuf_idx]) /
 				   (total_faults + 1);
-			f_diff = f_weight - p->numa_faults_cpu[i] / 2;
-			p->numa_faults_buffer_cpu[i] = 0;
+			f_diff = f_weight - p->numa_faults[cpu_idx] / 2;
+			p->numa_faults[cpubuf_idx] = 0;
 
-			p->numa_faults_memory[i] += diff;
-			p->numa_faults_cpu[i] += f_diff;
-			faults += p->numa_faults_memory[i];
+			p->numa_faults[mem_idx] += diff;
+			p->numa_faults[cpu_idx] += f_diff;
+			faults += p->numa_faults[mem_idx];
 			p->total_numa_faults += diff;
 			if (p->numa_group) {
-				/* safe because we can only change our own group */
-				p->numa_group->faults[i] += diff;
-				p->numa_group->faults_cpu[i] += f_diff;
+				/*
+				 * safe because we can only change our own group
+				 *
+				 * mem_idx represents the offset for a given
+				 * nid and priv in a specific region because it
+				 * is at the beginning of the numa_faults array.
+				 */
+				p->numa_group->faults[mem_idx] += diff;
+				p->numa_group->faults_cpu[mem_idx] += f_diff;
 				p->numa_group->total_faults += diff;
-				group_faults += p->numa_group->faults[i];
+				group_faults += p->numa_group->faults[mem_idx];
 			}
 		}
 
@@ -1662,7 +1862,7 @@ static void task_numa_placement(struct task_struct *p)
 	if (p->numa_group) {
 		update_numa_active_node_mask(p->numa_group);
 		spin_unlock_irq(group_lock);
-		max_nid = max_group_nid;
+		max_nid = preferred_group_nid(p, max_group_nid);
 	}
 
 	if (max_faults) {
@@ -1705,7 +1905,6 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags,
 
 		atomic_set(&grp->refcount, 1);
 		spin_lock_init(&grp->lock);
-		INIT_LIST_HEAD(&grp->task_list);
 		grp->gid = p->pid;
 		/* Second half of the array tracks nids where faults happen */
 		grp->faults_cpu = grp->faults + NR_NUMA_HINT_FAULT_TYPES *
@@ -1714,11 +1913,10 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags,
 		node_set(task_node(current), grp->active_nodes);
 
 		for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++)
-			grp->faults[i] = p->numa_faults_memory[i];
+			grp->faults[i] = p->numa_faults[i];
 
 		grp->total_faults = p->total_numa_faults;
 
-		list_add(&p->numa_entry, &grp->task_list);
 		grp->nr_tasks++;
 		rcu_assign_pointer(p->numa_group, grp);
 	}
@@ -1773,13 +1971,12 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags,
 	double_lock_irq(&my_grp->lock, &grp->lock);
 
 	for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++) {
-		my_grp->faults[i] -= p->numa_faults_memory[i];
-		grp->faults[i] += p->numa_faults_memory[i];
+		my_grp->faults[i] -= p->numa_faults[i];
+		grp->faults[i] += p->numa_faults[i];
 	}
 	my_grp->total_faults -= p->total_numa_faults;
 	grp->total_faults += p->total_numa_faults;
 
-	list_move(&p->numa_entry, &grp->task_list);
 	my_grp->nr_tasks--;
 	grp->nr_tasks++;
 
@@ -1799,27 +1996,23 @@ no_join:
 void task_numa_free(struct task_struct *p)
 {
 	struct numa_group *grp = p->numa_group;
-	void *numa_faults = p->numa_faults_memory;
+	void *numa_faults = p->numa_faults;
 	unsigned long flags;
 	int i;
 
 	if (grp) {
 		spin_lock_irqsave(&grp->lock, flags);
 		for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++)
-			grp->faults[i] -= p->numa_faults_memory[i];
+			grp->faults[i] -= p->numa_faults[i];
 		grp->total_faults -= p->total_numa_faults;
 
-		list_del(&p->numa_entry);
 		grp->nr_tasks--;
 		spin_unlock_irqrestore(&grp->lock, flags);
 		RCU_INIT_POINTER(p->numa_group, NULL);
 		put_numa_group(grp);
 	}
 
-	p->numa_faults_memory = NULL;
-	p->numa_faults_buffer_memory = NULL;
-	p->numa_faults_cpu= NULL;
-	p->numa_faults_buffer_cpu = NULL;
+	p->numa_faults = NULL;
 	kfree(numa_faults);
 }
 
@@ -1842,24 +2035,14 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags)
 		return;
 
 	/* Allocate buffer to track faults on a per-node basis */
-	if (unlikely(!p->numa_faults_memory)) {
-		int size = sizeof(*p->numa_faults_memory) *
+	if (unlikely(!p->numa_faults)) {
+		int size = sizeof(*p->numa_faults) *
 			   NR_NUMA_HINT_FAULT_BUCKETS * nr_node_ids;
 
-		p->numa_faults_memory = kzalloc(size, GFP_KERNEL|__GFP_NOWARN);
-		if (!p->numa_faults_memory)
+		p->numa_faults = kzalloc(size, GFP_KERNEL|__GFP_NOWARN);
+		if (!p->numa_faults)
 			return;
 
-		BUG_ON(p->numa_faults_buffer_memory);
-		/*
-		 * The averaged statistics, shared & private, memory & cpu,
-		 * occupy the first half of the array. The second half of the
-		 * array is for current counters, which are averaged into the
-		 * first set by task_numa_placement.
-		 */
-		p->numa_faults_cpu = p->numa_faults_memory + (2 * nr_node_ids);
-		p->numa_faults_buffer_memory = p->numa_faults_memory + (4 * nr_node_ids);
-		p->numa_faults_buffer_cpu = p->numa_faults_memory + (6 * nr_node_ids);
 		p->total_numa_faults = 0;
 		memset(p->numa_faults_locality, 0, sizeof(p->numa_faults_locality));
 	}
@@ -1899,8 +2082,8 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags)
 	if (migrated)
 		p->numa_pages_migrated += pages;
 
-	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[task_faults_idx(NUMA_MEMBUF, mem_node, priv)] += pages;
+	p->numa_faults[task_faults_idx(NUMA_CPUBUF, cpu_node, priv)] += pages;
 	p->numa_faults_locality[local] += pages;
 }
 
@@ -4469,7 +4652,7 @@ find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
 				latest_idle_timestamp = rq->idle_stamp;
 				shallowest_idle_cpu = i;
 			}
-		} else {
+		} else if (shallowest_idle_cpu == -1) {
 			load = weighted_cpuload(i);
 			if (load < min_load || (load == min_load && i == this_cpu)) {
 				min_load = load;
@@ -4547,9 +4730,6 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f
 	int want_affine = 0;
 	int sync = wake_flags & WF_SYNC;
 
-	if (p->nr_cpus_allowed == 1)
-		return prev_cpu;
-
 	if (sd_flag & SD_BALANCE_WAKE)
 		want_affine = cpumask_test_cpu(cpu, tsk_cpus_allowed(p));
 
@@ -5189,7 +5369,7 @@ 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 ||
+	if (!sched_feat(NUMA_FAVOUR_HIGHER) || !p->numa_faults ||
 	    !(env->sd->flags & SD_NUMA)) {
 		return false;
 	}
@@ -5228,7 +5408,7 @@ static bool migrate_degrades_locality(struct task_struct *p, struct lb_env *env)
 	if (!sched_feat(NUMA) || !sched_feat(NUMA_RESIST_LOWER))
 		return false;
 
-	if (!p->numa_faults_memory || !(env->sd->flags & SD_NUMA))
+	if (!p->numa_faults || !(env->sd->flags & SD_NUMA))
 		return false;
 
 	src_nid = cpu_to_node(env->src_cpu);
@@ -6172,8 +6352,10 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
 		 * with a large weight task outweighs the tasks on the system).
 		 */
 		if (prefer_sibling && sds->local &&
-		    sds->local_stat.group_has_free_capacity)
+		    sds->local_stat.group_has_free_capacity) {
 			sgs->group_capacity_factor = min(sgs->group_capacity_factor, 1U);
+			sgs->group_type = group_classify(sg, sgs);
+		}
 
 		if (update_sd_pick_busiest(env, sds, sg, sgs)) {
 			sds->busiest = sg;
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 20bca398084a..ee15f5a0d1c1 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1301,9 +1301,6 @@ select_task_rq_rt(struct task_struct *p, int cpu, int sd_flag, int flags)
 	struct task_struct *curr;
 	struct rq *rq;
 
-	if (p->nr_cpus_allowed == 1)
-		goto out;
-
 	/* For anything but wake ups, just return the task_cpu */
 	if (sd_flag != SD_BALANCE_WAKE && sd_flag != SD_BALANCE_FORK)
 		goto out;
@@ -1351,16 +1348,22 @@ out:
 
 static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p)
 {
-	if (rq->curr->nr_cpus_allowed == 1)
+	/*
+	 * Current can't be migrated, useless to reschedule,
+	 * let's hope p can move out.
+	 */
+	if (rq->curr->nr_cpus_allowed == 1 ||
+	    !cpupri_find(&rq->rd->cpupri, rq->curr, NULL))
 		return;
 
+	/*
+	 * p is migratable, so let's not schedule it and
+	 * see if it is pushed or pulled somewhere else.
+	 */
 	if (p->nr_cpus_allowed != 1
 	    && cpupri_find(&rq->rd->cpupri, p, NULL))
 		return;
 
-	if (!cpupri_find(&rq->rd->cpupri, rq->curr, NULL))
-		return;
-
 	/*
 	 * There appears to be other cpus that can accept
 	 * current and none to run 'p', so lets reschedule
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 2df8ef067cc5..9a2a45c970e7 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -176,6 +176,25 @@ struct dl_bw {
 	u64 bw, total_bw;
 };
 
+static inline
+void __dl_clear(struct dl_bw *dl_b, u64 tsk_bw)
+{
+	dl_b->total_bw -= tsk_bw;
+}
+
+static inline
+void __dl_add(struct dl_bw *dl_b, u64 tsk_bw)
+{
+	dl_b->total_bw += tsk_bw;
+}
+
+static inline
+bool __dl_overflow(struct dl_bw *dl_b, int cpus, u64 old_bw, u64 new_bw)
+{
+	return dl_b->bw != -1 &&
+	       dl_b->bw * cpus < dl_b->total_bw - old_bw + new_bw;
+}
+
 extern struct mutex sched_domains_mutex;
 
 #ifdef CONFIG_CGROUP_SCHED
@@ -678,7 +697,25 @@ static inline u64 rq_clock_task(struct rq *rq)
 	return rq->clock_task;
 }
 
+#ifdef CONFIG_NUMA
+enum numa_topology_type {
+	NUMA_DIRECT,
+	NUMA_GLUELESS_MESH,
+	NUMA_BACKPLANE,
+};
+extern enum numa_topology_type sched_numa_topology_type;
+extern int sched_max_numa_distance;
+extern bool find_numa_distance(int distance);
+#endif
+
 #ifdef CONFIG_NUMA_BALANCING
+/* The regions in numa_faults array from task_struct */
+enum numa_faults_stats {
+	NUMA_MEM = 0,
+	NUMA_CPU,
+	NUMA_MEMBUF,
+	NUMA_CPUBUF
+};
 extern void sched_setnuma(struct task_struct *p, int node);
 extern int migrate_task_to(struct task_struct *p, int cpu);
 extern int migrate_swap(struct task_struct *, struct task_struct *);
@@ -1127,6 +1164,11 @@ struct sched_class {
 	void (*task_fork) (struct task_struct *p);
 	void (*task_dead) (struct task_struct *p);
 
+	/*
+	 * The switched_from() call is allowed to drop rq->lock, therefore we
+	 * cannot assume the switched_from/switched_to pair is serliazed by
+	 * rq->lock. They are however serialized by p->pi_lock.
+	 */
 	void (*switched_from) (struct rq *this_rq, struct task_struct *task);
 	void (*switched_to) (struct rq *this_rq, struct task_struct *task);
 	void (*prio_changed) (struct rq *this_rq, struct task_struct *task,
@@ -1504,6 +1546,7 @@ extern struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq);
 extern struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq);
 extern void print_cfs_stats(struct seq_file *m, int cpu);
 extern void print_rt_stats(struct seq_file *m, int cpu);
+extern void print_dl_stats(struct seq_file *m, int cpu);
 
 extern void init_cfs_rq(struct cfs_rq *cfs_rq);
 extern void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq);
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index 5a62915f47a8..852143a79f36 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -9,6 +9,7 @@
 #include <linux/mm.h>
 #include <linux/wait.h>
 #include <linux/hash.h>
+#include <linux/kthread.h>
 
 void __init_waitqueue_head(wait_queue_head_t *q, const char *name, struct lock_class_key *key)
 {
@@ -297,6 +298,71 @@ int autoremove_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *
 }
 EXPORT_SYMBOL(autoremove_wake_function);
 
+static inline bool is_kthread_should_stop(void)
+{
+	return (current->flags & PF_KTHREAD) && kthread_should_stop();
+}
+
+/*
+ * DEFINE_WAIT_FUNC(wait, woken_wake_func);
+ *
+ * add_wait_queue(&wq, &wait);
+ * for (;;) {
+ *     if (condition)
+ *         break;
+ *
+ *     p->state = mode;				condition = true;
+ *     smp_mb(); // A				smp_wmb(); // C
+ *     if (!wait->flags & WQ_FLAG_WOKEN)	wait->flags |= WQ_FLAG_WOKEN;
+ *         schedule()				try_to_wake_up();
+ *     p->state = TASK_RUNNING;		    ~~~~~~~~~~~~~~~~~~
+ *     wait->flags &= ~WQ_FLAG_WOKEN;		condition = true;
+ *     smp_mb() // B				smp_wmb(); // C
+ *						wait->flags |= WQ_FLAG_WOKEN;
+ * }
+ * remove_wait_queue(&wq, &wait);
+ *
+ */
+long wait_woken(wait_queue_t *wait, unsigned mode, long timeout)
+{
+	set_current_state(mode); /* A */
+	/*
+	 * The above implies an smp_mb(), which matches with the smp_wmb() from
+	 * woken_wake_function() such that if we observe WQ_FLAG_WOKEN we must
+	 * also observe all state before the wakeup.
+	 */
+	if (!(wait->flags & WQ_FLAG_WOKEN) && !is_kthread_should_stop())
+		timeout = schedule_timeout(timeout);
+	__set_current_state(TASK_RUNNING);
+
+	/*
+	 * The below implies an smp_mb(), it too pairs with the smp_wmb() from
+	 * woken_wake_function() such that we must either observe the wait
+	 * condition being true _OR_ WQ_FLAG_WOKEN such that we will not miss
+	 * an event.
+	 */
+	set_mb(wait->flags, wait->flags & ~WQ_FLAG_WOKEN); /* B */
+
+	return timeout;
+}
+EXPORT_SYMBOL(wait_woken);
+
+int woken_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key)
+{
+	/*
+	 * Although this function is called under waitqueue lock, LOCK
+	 * doesn't imply write barrier and the users expects write
+	 * barrier semantics on wakeup functions.  The following
+	 * smp_wmb() is equivalent to smp_wmb() in try_to_wake_up()
+	 * and is paired with set_mb() in wait_woken().
+	 */
+	smp_wmb(); /* C */
+	wait->flags |= WQ_FLAG_WOKEN;
+
+	return default_wake_function(wait, mode, sync, key);
+}
+EXPORT_SYMBOL(woken_wake_function);
+
 int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *arg)
 {
 	struct wait_bit_key *key = arg;
diff --git a/kernel/smpboot.c b/kernel/smpboot.c
index eb89e1807408..f032fb5284e3 100644
--- a/kernel/smpboot.c
+++ b/kernel/smpboot.c
@@ -110,7 +110,7 @@ static int smpboot_thread_fn(void *data)
 		set_current_state(TASK_INTERRUPTIBLE);
 		preempt_disable();
 		if (kthread_should_stop()) {
-			set_current_state(TASK_RUNNING);
+			__set_current_state(TASK_RUNNING);
 			preempt_enable();
 			if (ht->cleanup)
 				ht->cleanup(td->cpu, cpu_online(td->cpu));
@@ -136,26 +136,27 @@ static int smpboot_thread_fn(void *data)
 		/* Check for state change setup */
 		switch (td->status) {
 		case HP_THREAD_NONE:
+			__set_current_state(TASK_RUNNING);
 			preempt_enable();
 			if (ht->setup)
 				ht->setup(td->cpu);
 			td->status = HP_THREAD_ACTIVE;
-			preempt_disable();
-			break;
+			continue;
+
 		case HP_THREAD_PARKED:
+			__set_current_state(TASK_RUNNING);
 			preempt_enable();
 			if (ht->unpark)
 				ht->unpark(td->cpu);
 			td->status = HP_THREAD_ACTIVE;
-			preempt_disable();
-			break;
+			continue;
 		}
 
 		if (!ht->thread_should_run(td->cpu)) {
-			preempt_enable();
+			preempt_enable_no_resched();
 			schedule();
 		} else {
-			set_current_state(TASK_RUNNING);
+			__set_current_state(TASK_RUNNING);
 			preempt_enable();
 			ht->thread_fn(td->cpu);
 		}