Merge branch 'perf/urgent' into perf/core, to resolve conflict and to prepare for new patches

Conflicts:
	arch/x86/kernel/traps.c

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

23 files changed, 377 insertions, 250 deletions

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 9fcdaa705b6c..3f1ca934a237 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -348,7 +348,7 @@ struct cgrp_cset_link {
  * reference-counted, to improve performance when child cgroups
  * haven't been created.
  */
-static struct css_set init_css_set = {
+struct css_set init_css_set = {
 	.refcount		= ATOMIC_INIT(1),
 	.cgrp_links		= LIST_HEAD_INIT(init_css_set.cgrp_links),
 	.tasks			= LIST_HEAD_INIT(init_css_set.tasks),
@@ -1495,7 +1495,7 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
 	 */
 	if (!use_task_css_set_links)
 		cgroup_enable_task_cg_lists();
-retry:
+
 	mutex_lock(&cgroup_tree_mutex);
 	mutex_lock(&cgroup_mutex);
 
@@ -1503,7 +1503,7 @@ retry:
 	ret = parse_cgroupfs_options(data, &opts);
 	if (ret)
 		goto out_unlock;
-
+retry:
 	/* look for a matching existing root */
 	if (!opts.subsys_mask && !opts.none && !opts.name) {
 		cgrp_dfl_root_visible = true;
@@ -1562,9 +1562,9 @@ retry:
 		if (!atomic_inc_not_zero(&root->cgrp.refcnt)) {
 			mutex_unlock(&cgroup_mutex);
 			mutex_unlock(&cgroup_tree_mutex);
-			kfree(opts.release_agent);
-			kfree(opts.name);
 			msleep(10);
+			mutex_lock(&cgroup_tree_mutex);
+			mutex_lock(&cgroup_mutex);
 			goto retry;
 		}
 
diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c
index 2bc4a2256444..345628c78b5b 100644
--- a/kernel/cgroup_freezer.c
+++ b/kernel/cgroup_freezer.c
@@ -21,6 +21,7 @@
 #include <linux/uaccess.h>
 #include <linux/freezer.h>
 #include <linux/seq_file.h>
+#include <linux/mutex.h>
 
 /*
  * A cgroup is freezing if any FREEZING flags are set.  FREEZING_SELF is
@@ -42,9 +43,10 @@ enum freezer_state_flags {
 struct freezer {
 	struct cgroup_subsys_state	css;
 	unsigned int			state;
-	spinlock_t			lock;
 };
 
+static DEFINE_MUTEX(freezer_mutex);
+
 static inline struct freezer *css_freezer(struct cgroup_subsys_state *css)
 {
 	return css ? container_of(css, struct freezer, css) : NULL;
@@ -93,7 +95,6 @@ freezer_css_alloc(struct cgroup_subsys_state *parent_css)
 	if (!freezer)
 		return ERR_PTR(-ENOMEM);
 
-	spin_lock_init(&freezer->lock);
 	return &freezer->css;
 }
 
@@ -110,14 +111,7 @@ static int freezer_css_online(struct cgroup_subsys_state *css)
 	struct freezer *freezer = css_freezer(css);
 	struct freezer *parent = parent_freezer(freezer);
 
-	/*
-	 * The following double locking and freezing state inheritance
-	 * guarantee that @cgroup can never escape ancestors' freezing
-	 * states.  See css_for_each_descendant_pre() for details.
-	 */
-	if (parent)
-		spin_lock_irq(&parent->lock);
-	spin_lock_nested(&freezer->lock, SINGLE_DEPTH_NESTING);
+	mutex_lock(&freezer_mutex);
 
 	freezer->state |= CGROUP_FREEZER_ONLINE;
 
@@ -126,10 +120,7 @@ static int freezer_css_online(struct cgroup_subsys_state *css)
 		atomic_inc(&system_freezing_cnt);
 	}
 
-	spin_unlock(&freezer->lock);
-	if (parent)
-		spin_unlock_irq(&parent->lock);
-
+	mutex_unlock(&freezer_mutex);
 	return 0;
 }
 
@@ -144,14 +135,14 @@ static void freezer_css_offline(struct cgroup_subsys_state *css)
 {
 	struct freezer *freezer = css_freezer(css);
 
-	spin_lock_irq(&freezer->lock);
+	mutex_lock(&freezer_mutex);
 
 	if (freezer->state & CGROUP_FREEZING)
 		atomic_dec(&system_freezing_cnt);
 
 	freezer->state = 0;
 
-	spin_unlock_irq(&freezer->lock);
+	mutex_unlock(&freezer_mutex);
 }
 
 static void freezer_css_free(struct cgroup_subsys_state *css)
@@ -175,7 +166,7 @@ static void freezer_attach(struct cgroup_subsys_state *new_css,
 	struct task_struct *task;
 	bool clear_frozen = false;
 
-	spin_lock_irq(&freezer->lock);
+	mutex_lock(&freezer_mutex);
 
 	/*
 	 * Make the new tasks conform to the current state of @new_css.
@@ -197,21 +188,13 @@ static void freezer_attach(struct cgroup_subsys_state *new_css,
 		}
 	}
 
-	spin_unlock_irq(&freezer->lock);
-
-	/*
-	 * Propagate FROZEN clearing upwards.  We may race with
-	 * update_if_frozen(), but as long as both work bottom-up, either
-	 * update_if_frozen() sees child's FROZEN cleared or we clear the
-	 * parent's FROZEN later.  No parent w/ !FROZEN children can be
-	 * left FROZEN.
-	 */
+	/* propagate FROZEN clearing upwards */
 	while (clear_frozen && (freezer = parent_freezer(freezer))) {
-		spin_lock_irq(&freezer->lock);
 		freezer->state &= ~CGROUP_FROZEN;
 		clear_frozen = freezer->state & CGROUP_FREEZING;
-		spin_unlock_irq(&freezer->lock);
 	}
+
+	mutex_unlock(&freezer_mutex);
 }
 
 /**
@@ -228,9 +211,6 @@ static void freezer_fork(struct task_struct *task)
 {
 	struct freezer *freezer;
 
-	rcu_read_lock();
-	freezer = task_freezer(task);
-
 	/*
 	 * The root cgroup is non-freezable, so we can skip locking the
 	 * freezer.  This is safe regardless of race with task migration.
@@ -238,24 +218,18 @@ static void freezer_fork(struct task_struct *task)
 	 * to do.  If we lost and root is the new cgroup, noop is still the
 	 * right thing to do.
 	 */
-	if (!parent_freezer(freezer))
-		goto out;
+	if (task_css_is_root(task, freezer_cgrp_id))
+		return;
 
-	/*
-	 * Grab @freezer->lock and freeze @task after verifying @task still
-	 * belongs to @freezer and it's freezing.  The former is for the
-	 * case where we have raced against task migration and lost and
-	 * @task is already in a different cgroup which may not be frozen.
-	 * This isn't strictly necessary as freeze_task() is allowed to be
-	 * called spuriously but let's do it anyway for, if nothing else,
-	 * documentation.
-	 */
-	spin_lock_irq(&freezer->lock);
-	if (freezer == task_freezer(task) && (freezer->state & CGROUP_FREEZING))
+	mutex_lock(&freezer_mutex);
+	rcu_read_lock();
+
+	freezer = task_freezer(task);
+	if (freezer->state & CGROUP_FREEZING)
 		freeze_task(task);
-	spin_unlock_irq(&freezer->lock);
-out:
+
 	rcu_read_unlock();
+	mutex_unlock(&freezer_mutex);
 }
 
 /**
@@ -281,22 +255,24 @@ static void update_if_frozen(struct cgroup_subsys_state *css)
 	struct css_task_iter it;
 	struct task_struct *task;
 
-	WARN_ON_ONCE(!rcu_read_lock_held());
-
-	spin_lock_irq(&freezer->lock);
+	lockdep_assert_held(&freezer_mutex);
 
 	if (!(freezer->state & CGROUP_FREEZING) ||
 	    (freezer->state & CGROUP_FROZEN))
-		goto out_unlock;
+		return;
 
 	/* are all (live) children frozen? */
+	rcu_read_lock();
 	css_for_each_child(pos, css) {
 		struct freezer *child = css_freezer(pos);
 
 		if ((child->state & CGROUP_FREEZER_ONLINE) &&
-		    !(child->state & CGROUP_FROZEN))
-			goto out_unlock;
+		    !(child->state & CGROUP_FROZEN)) {
+			rcu_read_unlock();
+			return;
+		}
 	}
+	rcu_read_unlock();
 
 	/* are all tasks frozen? */
 	css_task_iter_start(css, &it);
@@ -317,21 +293,29 @@ static void update_if_frozen(struct cgroup_subsys_state *css)
 	freezer->state |= CGROUP_FROZEN;
 out_iter_end:
 	css_task_iter_end(&it);
-out_unlock:
-	spin_unlock_irq(&freezer->lock);
 }
 
 static int freezer_read(struct seq_file *m, void *v)
 {
 	struct cgroup_subsys_state *css = seq_css(m), *pos;
 
+	mutex_lock(&freezer_mutex);
 	rcu_read_lock();
 
 	/* update states bottom-up */
-	css_for_each_descendant_post(pos, css)
+	css_for_each_descendant_post(pos, css) {
+		if (!css_tryget(pos))
+			continue;
+		rcu_read_unlock();
+
 		update_if_frozen(pos);
 
+		rcu_read_lock();
+		css_put(pos);
+	}
+
 	rcu_read_unlock();
+	mutex_unlock(&freezer_mutex);
 
 	seq_puts(m, freezer_state_strs(css_freezer(css)->state));
 	seq_putc(m, '\n');
@@ -373,7 +357,7 @@ static void freezer_apply_state(struct freezer *freezer, bool freeze,
 				unsigned int state)
 {
 	/* also synchronizes against task migration, see freezer_attach() */
-	lockdep_assert_held(&freezer->lock);
+	lockdep_assert_held(&freezer_mutex);
 
 	if (!(freezer->state & CGROUP_FREEZER_ONLINE))
 		return;
@@ -414,31 +398,29 @@ static void freezer_change_state(struct freezer *freezer, bool freeze)
 	 * descendant will try to inherit its parent's FREEZING state as
 	 * CGROUP_FREEZING_PARENT.
 	 */
+	mutex_lock(&freezer_mutex);
 	rcu_read_lock();
 	css_for_each_descendant_pre(pos, &freezer->css) {
 		struct freezer *pos_f = css_freezer(pos);
 		struct freezer *parent = parent_freezer(pos_f);
 
-		spin_lock_irq(&pos_f->lock);
+		if (!css_tryget(pos))
+			continue;
+		rcu_read_unlock();
 
-		if (pos_f == freezer) {
+		if (pos_f == freezer)
 			freezer_apply_state(pos_f, freeze,
 					    CGROUP_FREEZING_SELF);
-		} else {
-			/*
-			 * Our update to @parent->state is already visible
-			 * which is all we need.  No need to lock @parent.
-			 * For more info on synchronization, see
-			 * freezer_post_create().
-			 */
+		else
 			freezer_apply_state(pos_f,
 					    parent->state & CGROUP_FREEZING,
 					    CGROUP_FREEZING_PARENT);
-		}
 
-		spin_unlock_irq(&pos_f->lock);
+		rcu_read_lock();
+		css_put(pos);
 	}
 	rcu_read_unlock();
+	mutex_unlock(&freezer_mutex);
 }
 
 static int freezer_write(struct cgroup_subsys_state *css, struct cftype *cft,
diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c
index 6cb20d2e7ee0..019d45008448 100644
--- a/kernel/context_tracking.c
+++ b/kernel/context_tracking.c
@@ -120,7 +120,7 @@ void context_tracking_user_enter(void)
  * instead of preempt_schedule() to exit user context if needed before
  * calling the scheduler.
  */
-asmlinkage void __sched notrace preempt_schedule_context(void)
+asmlinkage __visible void __sched notrace preempt_schedule_context(void)
 {
 	enum ctx_state prev_ctx;
 
diff --git a/kernel/cpu.c b/kernel/cpu.c
index a9e710eef0e2..247979a1b815 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -726,10 +726,12 @@ void set_cpu_present(unsigned int cpu, bool present)
 
 void set_cpu_online(unsigned int cpu, bool online)
 {
-	if (online)
+	if (online) {
 		cpumask_set_cpu(cpu, to_cpumask(cpu_online_bits));
-	else
+		cpumask_set_cpu(cpu, to_cpumask(cpu_active_bits));
+	} else {
 		cpumask_clear_cpu(cpu, to_cpumask(cpu_online_bits));
+	}
 }
 
 void set_cpu_active(unsigned int cpu, bool active)
diff --git a/kernel/events/core.c b/kernel/events/core.c
index e9ef0c6646af..8fac2056d51e 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2973,6 +2973,22 @@ out:
 	local_irq_restore(flags);
 }
 
+void perf_event_exec(void)
+{
+	struct perf_event_context *ctx;
+	int ctxn;
+
+	rcu_read_lock();
+	for_each_task_context_nr(ctxn) {
+		ctx = current->perf_event_ctxp[ctxn];
+		if (!ctx)
+			continue;
+
+		perf_event_enable_on_exec(ctx);
+	}
+	rcu_read_unlock();
+}
+
 /*
  * Cross CPU call to read the hardware event
  */
@@ -3195,7 +3211,8 @@ static void free_event_rcu(struct rcu_head *head)
 }
 
 static void ring_buffer_put(struct ring_buffer *rb);
-static void ring_buffer_detach(struct perf_event *event, struct ring_buffer *rb);
+static void ring_buffer_attach(struct perf_event *event,
+			       struct ring_buffer *rb);
 
 static void unaccount_event_cpu(struct perf_event *event, int cpu)
 {
@@ -3259,8 +3276,6 @@ static void _free_event(struct perf_event *event)
 	unaccount_event(event);
 
 	if (event->rb) {
-		struct ring_buffer *rb;
-
 		/*
 		 * Can happen when we close an event with re-directed output.
 		 *
@@ -3268,12 +3283,7 @@ static void _free_event(struct perf_event *event)
 		 * over us; possibly making our ring_buffer_put() the last.
 		 */
 		mutex_lock(&event->mmap_mutex);
-		rb = event->rb;
-		if (rb) {
-			rcu_assign_pointer(event->rb, NULL);
-			ring_buffer_detach(event, rb);
-			ring_buffer_put(rb); /* could be last */
-		}
+		ring_buffer_attach(event, NULL);
 		mutex_unlock(&event->mmap_mutex);
 	}
 
@@ -3870,28 +3880,47 @@ unlock:
 static void ring_buffer_attach(struct perf_event *event,
 			       struct ring_buffer *rb)
 {
+	struct ring_buffer *old_rb = NULL;
 	unsigned long flags;
 
-	if (!list_empty(&event->rb_entry))
-		return;
+	if (event->rb) {
+		/*
+		 * Should be impossible, we set this when removing
+		 * event->rb_entry and wait/clear when adding event->rb_entry.
+		 */
+		WARN_ON_ONCE(event->rcu_pending);
 
-	spin_lock_irqsave(&rb->event_lock, flags);
-	if (list_empty(&event->rb_entry))
-		list_add(&event->rb_entry, &rb->event_list);
-	spin_unlock_irqrestore(&rb->event_lock, flags);
-}
+		old_rb = event->rb;
+		event->rcu_batches = get_state_synchronize_rcu();
+		event->rcu_pending = 1;
 
-static void ring_buffer_detach(struct perf_event *event, struct ring_buffer *rb)
-{
-	unsigned long flags;
+		spin_lock_irqsave(&old_rb->event_lock, flags);
+		list_del_rcu(&event->rb_entry);
+		spin_unlock_irqrestore(&old_rb->event_lock, flags);
+	}
 
-	if (list_empty(&event->rb_entry))
-		return;
+	if (event->rcu_pending && rb) {
+		cond_synchronize_rcu(event->rcu_batches);
+		event->rcu_pending = 0;
+	}
+
+	if (rb) {
+		spin_lock_irqsave(&rb->event_lock, flags);
+		list_add_rcu(&event->rb_entry, &rb->event_list);
+		spin_unlock_irqrestore(&rb->event_lock, flags);
+	}
+
+	rcu_assign_pointer(event->rb, rb);
 
-	spin_lock_irqsave(&rb->event_lock, flags);
-	list_del_init(&event->rb_entry);
-	wake_up_all(&event->waitq);
-	spin_unlock_irqrestore(&rb->event_lock, flags);
+	if (old_rb) {
+		ring_buffer_put(old_rb);
+		/*
+		 * Since we detached before setting the new rb, so that we
+		 * could attach the new rb, we could have missed a wakeup.
+		 * Provide it now.
+		 */
+		wake_up_all(&event->waitq);
+	}
 }
 
 static void ring_buffer_wakeup(struct perf_event *event)
@@ -3960,7 +3989,7 @@ static void perf_mmap_close(struct vm_area_struct *vma)
 {
 	struct perf_event *event = vma->vm_file->private_data;
 
-	struct ring_buffer *rb = event->rb;
+	struct ring_buffer *rb = ring_buffer_get(event);
 	struct user_struct *mmap_user = rb->mmap_user;
 	int mmap_locked = rb->mmap_locked;
 	unsigned long size = perf_data_size(rb);
@@ -3968,18 +3997,14 @@ static void perf_mmap_close(struct vm_area_struct *vma)
 	atomic_dec(&rb->mmap_count);
 
 	if (!atomic_dec_and_mutex_lock(&event->mmap_count, &event->mmap_mutex))
-		return;
+		goto out_put;
 
-	/* Detach current event from the buffer. */
-	rcu_assign_pointer(event->rb, NULL);
-	ring_buffer_detach(event, rb);
+	ring_buffer_attach(event, NULL);
 	mutex_unlock(&event->mmap_mutex);
 
 	/* If there's still other mmap()s of this buffer, we're done. */
-	if (atomic_read(&rb->mmap_count)) {
-		ring_buffer_put(rb); /* can't be last */
-		return;
-	}
+	if (atomic_read(&rb->mmap_count))
+		goto out_put;
 
 	/*
 	 * No other mmap()s, detach from all other events that might redirect
@@ -4009,11 +4034,9 @@ again:
 		 * still restart the iteration to make sure we're not now
 		 * iterating the wrong list.
 		 */
-		if (event->rb == rb) {
-			rcu_assign_pointer(event->rb, NULL);
-			ring_buffer_detach(event, rb);
-			ring_buffer_put(rb); /* can't be last, we still have one */
-		}
+		if (event->rb == rb)
+			ring_buffer_attach(event, NULL);
+
 		mutex_unlock(&event->mmap_mutex);
 		put_event(event);
 
@@ -4038,6 +4061,7 @@ again:
 	vma->vm_mm->pinned_vm -= mmap_locked;
 	free_uid(mmap_user);
 
+out_put:
 	ring_buffer_put(rb); /* could be last */
 }
 
@@ -4155,7 +4179,6 @@ again:
 	vma->vm_mm->pinned_vm += extra;
 
 	ring_buffer_attach(event, rb);
-	rcu_assign_pointer(event->rb, rb);
 
 	perf_event_init_userpage(event);
 	perf_event_update_userpage(event);
@@ -5070,18 +5093,6 @@ static void perf_event_comm_event(struct perf_comm_event *comm_event)
 void perf_event_comm(struct task_struct *task)
 {
 	struct perf_comm_event comm_event;
-	struct perf_event_context *ctx;
-	int ctxn;
-
-	rcu_read_lock();
-	for_each_task_context_nr(ctxn) {
-		ctx = task->perf_event_ctxp[ctxn];
-		if (!ctx)
-			continue;
-
-		perf_event_enable_on_exec(ctx);
-	}
-	rcu_read_unlock();
 
 	if (!atomic_read(&nr_comm_events))
 		return;
@@ -5439,6 +5450,9 @@ struct swevent_htable {
 
 	/* Recursion avoidance in each contexts */
 	int				recursion[PERF_NR_CONTEXTS];
+
+	/* Keeps track of cpu being initialized/exited */
+	bool				online;
 };
 
 static DEFINE_PER_CPU(struct swevent_htable, swevent_htable);
@@ -5685,8 +5699,14 @@ static int perf_swevent_add(struct perf_event *event, int flags)
 	hwc->state = !(flags & PERF_EF_START);
 
 	head = find_swevent_head(swhash, event);
-	if (WARN_ON_ONCE(!head))
+	if (!head) {
+		/*
+		 * We can race with cpu hotplug code. Do not
+		 * WARN if the cpu just got unplugged.
+		 */
+		WARN_ON_ONCE(swhash->online);
 		return -EINVAL;
+	}
 
 	hlist_add_head_rcu(&event->hlist_entry, head);
 
@@ -6956,7 +6976,7 @@ err_size:
 static int
 perf_event_set_output(struct perf_event *event, struct perf_event *output_event)
 {
-	struct ring_buffer *rb = NULL, *old_rb = NULL;
+	struct ring_buffer *rb = NULL;
 	int ret = -EINVAL;
 
 	if (!output_event)
@@ -6984,8 +7004,6 @@ set:
 	if (atomic_read(&event->mmap_count))
 		goto unlock;
 
-	old_rb = event->rb;
-
 	if (output_event) {
 		/* get the rb we want to redirect to */
 		rb = ring_buffer_get(output_event);
@@ -6993,23 +7011,7 @@ set:
 			goto unlock;
 	}
 
-	if (old_rb)
-		ring_buffer_detach(event, old_rb);
-
-	if (rb)
-		ring_buffer_attach(event, rb);
-
-	rcu_assign_pointer(event->rb, rb);
-
-	if (old_rb) {
-		ring_buffer_put(old_rb);
-		/*
-		 * Since we detached before setting the new rb, so that we
-		 * could attach the new rb, we could have missed a wakeup.
-		 * Provide it now.
-		 */
-		wake_up_all(&event->waitq);
-	}
+	ring_buffer_attach(event, rb);
 
 	ret = 0;
 unlock:
@@ -7060,6 +7062,9 @@ SYSCALL_DEFINE5(perf_event_open,
 	if (attr.freq) {
 		if (attr.sample_freq > sysctl_perf_event_sample_rate)
 			return -EINVAL;
+	} else {
+		if (attr.sample_period & (1ULL << 63))
+			return -EINVAL;
 	}
 
 	/*
@@ -7872,6 +7877,7 @@ static void perf_event_init_cpu(int cpu)
 	struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu);
 
 	mutex_lock(&swhash->hlist_mutex);
+	swhash->online = true;
 	if (swhash->hlist_refcount > 0) {
 		struct swevent_hlist *hlist;
 
@@ -7929,6 +7935,7 @@ static void perf_event_exit_cpu(int cpu)
 	perf_event_exit_cpu_context(cpu);
 
 	mutex_lock(&swhash->hlist_mutex);
+	swhash->online = false;
 	swevent_hlist_release(swhash);
 	mutex_unlock(&swhash->hlist_mutex);
 }
diff --git a/kernel/futex.c b/kernel/futex.c
index 5f589279e462..81dbe773ce4c 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -745,7 +745,8 @@ void exit_pi_state_list(struct task_struct *curr)
 
 static int
 lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
-		union futex_key *key, struct futex_pi_state **ps)
+		union futex_key *key, struct futex_pi_state **ps,
+		struct task_struct *task)
 {
 	struct futex_pi_state *pi_state = NULL;
 	struct futex_q *this, *next;
@@ -786,6 +787,16 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
 					return -EINVAL;
 			}
 
+			/*
+			 * Protect against a corrupted uval. If uval
+			 * is 0x80000000 then pid is 0 and the waiter
+			 * bit is set. So the deadlock check in the
+			 * calling code has failed and we did not fall
+			 * into the check above due to !pid.
+			 */
+			if (task && pi_state->owner == task)
+				return -EDEADLK;
+
 			atomic_inc(&pi_state->refcount);
 			*ps = pi_state;
 
@@ -803,6 +814,11 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
 	if (!p)
 		return -ESRCH;
 
+	if (!p->mm) {
+		put_task_struct(p);
+		return -EPERM;
+	}
+
 	/*
 	 * We need to look at the task state flags to figure out,
 	 * whether the task is exiting. To protect against the do_exit
@@ -935,7 +951,7 @@ retry:
 	 * We dont have the lock. Look up the PI state (or create it if
 	 * we are the first waiter):
 	 */
-	ret = lookup_pi_state(uval, hb, key, ps);
+	ret = lookup_pi_state(uval, hb, key, ps, task);
 
 	if (unlikely(ret)) {
 		switch (ret) {
@@ -1347,7 +1363,7 @@ void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key,
  *
  * Return:
  *  0 - failed to acquire the lock atomically;
- *  1 - acquired the lock;
+ * >0 - acquired the lock, return value is vpid of the top_waiter
  * <0 - error
  */
 static int futex_proxy_trylock_atomic(u32 __user *pifutex,
@@ -1358,7 +1374,7 @@ static int futex_proxy_trylock_atomic(u32 __user *pifutex,
 {
 	struct futex_q *top_waiter = NULL;
 	u32 curval;
-	int ret;
+	int ret, vpid;
 
 	if (get_futex_value_locked(&curval, pifutex))
 		return -EFAULT;
@@ -1386,11 +1402,13 @@ static int futex_proxy_trylock_atomic(u32 __user *pifutex,
 	 * the contended case or if set_waiters is 1.  The pi_state is returned
 	 * in ps in contended cases.
 	 */
+	vpid = task_pid_vnr(top_waiter->task);
 	ret = futex_lock_pi_atomic(pifutex, hb2, key2, ps, top_waiter->task,
 				   set_waiters);
-	if (ret == 1)
+	if (ret == 1) {
 		requeue_pi_wake_futex(top_waiter, key2, hb2);
-
+		return vpid;
+	}
 	return ret;
 }
 
@@ -1421,7 +1439,6 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags,
 	struct futex_pi_state *pi_state = NULL;
 	struct futex_hash_bucket *hb1, *hb2;
 	struct futex_q *this, *next;
-	u32 curval2;
 
 	if (requeue_pi) {
 		/*
@@ -1509,16 +1526,25 @@ retry_private:
 		 * At this point the top_waiter has either taken uaddr2 or is
 		 * waiting on it.  If the former, then the pi_state will not
 		 * exist yet, look it up one more time to ensure we have a
-		 * reference to it.
+		 * reference to it. If the lock was taken, ret contains the
+		 * vpid of the top waiter task.
 		 */
-		if (ret == 1) {
+		if (ret > 0) {
 			WARN_ON(pi_state);
 			drop_count++;
 			task_count++;
-			ret = get_futex_value_locked(&curval2, uaddr2);
-			if (!ret)
-				ret = lookup_pi_state(curval2, hb2, &key2,
-						      &pi_state);
+			/*
+			 * If we acquired the lock, then the user
+			 * space value of uaddr2 should be vpid. It
+			 * cannot be changed by the top waiter as it
+			 * is blocked on hb2 lock if it tries to do
+			 * so. If something fiddled with it behind our
+			 * back the pi state lookup might unearth
+			 * it. So we rather use the known value than
+			 * rereading and handing potential crap to
+			 * lookup_pi_state.
+			 */
+			ret = lookup_pi_state(ret, hb2, &key2, &pi_state, NULL);
 		}
 
 		switch (ret) {
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index d10eba8089d1..3ab28993f6e0 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -990,11 +990,8 @@ int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
 	/* Remove an active timer from the queue: */
 	ret = remove_hrtimer(timer, base);
 
-	/* Switch the timer base, if necessary: */
-	new_base = switch_hrtimer_base(timer, base, mode & HRTIMER_MODE_PINNED);
-
 	if (mode & HRTIMER_MODE_REL) {
-		tim = ktime_add_safe(tim, new_base->get_time());
+		tim = ktime_add_safe(tim, base->get_time());
 		/*
 		 * CONFIG_TIME_LOW_RES is a temporary way for architectures
 		 * to signal that they simply return xtime in
@@ -1009,6 +1006,9 @@ int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
 
 	hrtimer_set_expires_range_ns(timer, tim, delta_ns);
 
+	/* Switch the timer base, if necessary: */
+	new_base = switch_hrtimer_base(timer, base, mode & HRTIMER_MODE_PINNED);
+
 	timer_stats_hrtimer_set_start_info(timer);
 
 	leftmost = enqueue_hrtimer(timer, new_base);
diff --git a/kernel/kexec.c b/kernel/kexec.c
index c8380ad203bc..28c57069ef68 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -1683,6 +1683,14 @@ int kernel_kexec(void)
 		kexec_in_progress = true;
 		kernel_restart_prepare(NULL);
 		migrate_to_reboot_cpu();
+
+		/*
+		 * migrate_to_reboot_cpu() disables CPU hotplug assuming that
+		 * no further code needs to use CPU hotplug (which is true in
+		 * the reboot case). However, the kexec path depends on using
+		 * CPU hotplug again; so re-enable it here.
+		 */
+		cpu_hotplug_enable();
 		printk(KERN_EMERG "Starting new kernel\n");
 		machine_shutdown();
 	}
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index b0e9467922e1..d24e4339b46d 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -4188,7 +4188,7 @@ void debug_show_held_locks(struct task_struct *task)
 }
 EXPORT_SYMBOL_GPL(debug_show_held_locks);
 
-asmlinkage void lockdep_sys_exit(void)
+asmlinkage __visible void lockdep_sys_exit(void)
 {
 	struct task_struct *curr = current;
 
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index aa4dff04b594..a620d4d08ca6 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -343,9 +343,16 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 	 * top_waiter can be NULL, when we are in the deboosting
 	 * mode!
 	 */
-	if (top_waiter && (!task_has_pi_waiters(task) ||
-			   top_waiter != task_top_pi_waiter(task)))
-		goto out_unlock_pi;
+	if (top_waiter) {
+		if (!task_has_pi_waiters(task))
+			goto out_unlock_pi;
+		/*
+		 * If deadlock detection is off, we stop here if we
+		 * are not the top pi waiter of the task.
+		 */
+		if (!detect_deadlock && top_waiter != task_top_pi_waiter(task))
+			goto out_unlock_pi;
+	}
 
 	/*
 	 * When deadlock detection is off then we check, if further
@@ -361,7 +368,12 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 		goto retry;
 	}
 
-	/* Deadlock detection */
+	/*
+	 * Deadlock detection. If the lock is the same as the original
+	 * lock which caused us to walk the lock chain or if the
+	 * current lock is owned by the task which initiated the chain
+	 * walk, we detected a deadlock.
+	 */
 	if (lock == orig_lock || rt_mutex_owner(lock) == top_task) {
 		debug_rt_mutex_deadlock(deadlock_detect, orig_waiter, lock);
 		raw_spin_unlock(&lock->wait_lock);
@@ -527,6 +539,18 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 	unsigned long flags;
 	int chain_walk = 0, res;
 
+	/*
+	 * Early deadlock detection. We really don't want the task to
+	 * enqueue on itself just to untangle the mess later. It's not
+	 * only an optimization. We drop the locks, so another waiter
+	 * can come in before the chain walk detects the deadlock. So
+	 * the other will detect the deadlock and return -EDEADLOCK,
+	 * which is wrong, as the other waiter is not in a deadlock
+	 * situation.
+	 */
+	if (detect_deadlock && owner == task)
+		return -EDEADLK;
+
 	raw_spin_lock_irqsave(&task->pi_lock, flags);
 	__rt_mutex_adjust_prio(task);
 	waiter->task = task;
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 18fb7a2fb14b..1ea328aafdc9 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -1586,7 +1586,7 @@ swsusp_alloc(struct memory_bitmap *orig_bm, struct memory_bitmap *copy_bm,
 	return -ENOMEM;
 }
 
-asmlinkage int swsusp_save(void)
+asmlinkage __visible int swsusp_save(void)
 {
 	unsigned int nr_pages, nr_highmem;
 
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index a45b50962295..7228258b85ec 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -1674,7 +1674,7 @@ EXPORT_SYMBOL(printk_emit);
  *
  * See the vsnprintf() documentation for format string extensions over C99.
  */
-asmlinkage int printk(const char *fmt, ...)
+asmlinkage __visible int printk(const char *fmt, ...)
 {
 	va_list args;
 	int r;
@@ -1737,7 +1737,7 @@ void early_vprintk(const char *fmt, va_list ap)
 	}
 }
 
-asmlinkage void early_printk(const char *fmt, ...)
+asmlinkage __visible void early_printk(const char *fmt, ...)
 {
 	va_list ap;
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 00781cc38047..a8c0fde25e4a 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2192,7 +2192,7 @@ static inline void post_schedule(struct rq *rq)
  * schedule_tail - first thing a freshly forked thread must call.
  * @prev: the thread we just switched away from.
  */
-asmlinkage void schedule_tail(struct task_struct *prev)
+asmlinkage __visible void schedule_tail(struct task_struct *prev)
 	__releases(rq->lock)
 {
 	struct rq *rq = this_rq();
@@ -2594,8 +2594,14 @@ pick_next_task(struct rq *rq, struct task_struct *prev)
 	if (likely(prev->sched_class == class &&
 		   rq->nr_running == rq->cfs.h_nr_running)) {
 		p = fair_sched_class.pick_next_task(rq, prev);
-		if (likely(p && p != RETRY_TASK))
-			return p;
+		if (unlikely(p == RETRY_TASK))
+			goto again;
+
+		/* assumes fair_sched_class->next == idle_sched_class */
+		if (unlikely(!p))
+			p = idle_sched_class.pick_next_task(rq, prev);
+
+		return p;
 	}
 
 again:
@@ -2743,7 +2749,7 @@ static inline void sched_submit_work(struct task_struct *tsk)
 		blk_schedule_flush_plug(tsk);
 }
 
-asmlinkage void __sched schedule(void)
+asmlinkage __visible void __sched schedule(void)
 {
 	struct task_struct *tsk = current;
 
@@ -2753,7 +2759,7 @@ asmlinkage void __sched schedule(void)
 EXPORT_SYMBOL(schedule);
 
 #ifdef CONFIG_CONTEXT_TRACKING
-asmlinkage void __sched schedule_user(void)
+asmlinkage __visible void __sched schedule_user(void)
 {
 	/*
 	 * If we come here after a random call to set_need_resched(),
@@ -2785,7 +2791,7 @@ void __sched schedule_preempt_disabled(void)
  * off of preempt_enable. Kernel preemptions off return from interrupt
  * occur there and call schedule directly.
  */
-asmlinkage void __sched notrace preempt_schedule(void)
+asmlinkage __visible void __sched notrace preempt_schedule(void)
 {
 	/*
 	 * If there is a non-zero preempt_count or interrupts are disabled,
@@ -2816,7 +2822,7 @@ EXPORT_SYMBOL(preempt_schedule);
  * Note, that this is called and return with irqs disabled. This will
  * protect us against recursive calling from irq.
  */
-asmlinkage void __sched preempt_schedule_irq(void)
+asmlinkage __visible void __sched preempt_schedule_irq(void)
 {
 	enum ctx_state prev_state;
 
@@ -3127,6 +3133,7 @@ __setparam_dl(struct task_struct *p, const struct sched_attr *attr)
 	dl_se->dl_bw = to_ratio(dl_se->dl_period, dl_se->dl_runtime);
 	dl_se->dl_throttled = 0;
 	dl_se->dl_new = 1;
+	dl_se->dl_yielded = 0;
 }
 
 static void __setscheduler_params(struct task_struct *p,
@@ -3191,17 +3198,40 @@ __getparam_dl(struct task_struct *p, struct sched_attr *attr)
  * We ask for the deadline not being zero, and greater or equal
  * than the runtime, as well as the period of being zero or
  * greater than deadline. Furthermore, we have to be sure that
- * user parameters are above the internal resolution (1us); we
- * check sched_runtime only since it is always the smaller one.
+ * user parameters are above the internal resolution of 1us (we
+ * check sched_runtime only since it is always the smaller one) and
+ * below 2^63 ns (we have to check both sched_deadline and
+ * sched_period, as the latter can be zero).
  */
 static bool
 __checkparam_dl(const struct sched_attr *attr)
 {
-	return attr && attr->sched_deadline != 0 &&
-		(attr->sched_period == 0 ||
-		(s64)(attr->sched_period   - attr->sched_deadline) >= 0) &&
-		(s64)(attr->sched_deadline - attr->sched_runtime ) >= 0  &&
-		attr->sched_runtime >= (2 << (DL_SCALE - 1));
+	/* deadline != 0 */
+	if (attr->sched_deadline == 0)
+		return false;
+
+	/*
+	 * Since we truncate DL_SCALE bits, make sure we're at least
+	 * that big.
+	 */
+	if (attr->sched_runtime < (1ULL << DL_SCALE))
+		return false;
+
+	/*
+	 * Since we use the MSB for wrap-around and sign issues, make
+	 * sure it's not set (mind that period can be equal to zero).
+	 */
+	if (attr->sched_deadline & (1ULL << 63) ||
+	    attr->sched_period & (1ULL << 63))
+		return false;
+
+	/* runtime <= deadline <= period (if period != 0) */
+	if ((attr->sched_period != 0 &&
+	     attr->sched_period < attr->sched_deadline) ||
+	    attr->sched_deadline < attr->sched_runtime)
+		return false;
+
+	return true;
 }
 
 /*
@@ -3642,6 +3672,7 @@ SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param)
  * sys_sched_setattr - same as above, but with extended sched_attr
  * @pid: the pid in question.
  * @uattr: structure containing the extended parameters.
+ * @flags: for future extension.
  */
 SYSCALL_DEFINE3(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr,
 			       unsigned int, flags)
@@ -3653,8 +3684,12 @@ SYSCALL_DEFINE3(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr,
 	if (!uattr || pid < 0 || flags)
 		return -EINVAL;
 
-	if (sched_copy_attr(uattr, &attr))
-		return -EFAULT;
+	retval = sched_copy_attr(uattr, &attr);
+	if (retval)
+		return retval;
+
+	if (attr.sched_policy < 0)
+		return -EINVAL;
 
 	rcu_read_lock();
 	retval = -ESRCH;
@@ -3704,7 +3739,7 @@ SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid)
  */
 SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param)
 {
-	struct sched_param lp;
+	struct sched_param lp = { .sched_priority = 0 };
 	struct task_struct *p;
 	int retval;
 
@@ -3721,11 +3756,8 @@ SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param)
 	if (retval)
 		goto out_unlock;
 
-	if (task_has_dl_policy(p)) {
-		retval = -EINVAL;
-		goto out_unlock;
-	}
-	lp.sched_priority = p->rt_priority;
+	if (task_has_rt_policy(p))
+		lp.sched_priority = p->rt_priority;
 	rcu_read_unlock();
 
 	/*
@@ -3786,6 +3818,7 @@ err_size:
  * @pid: the pid in question.
  * @uattr: structure containing the extended parameters.
  * @size: sizeof(attr) for fwd/bwd comp.
+ * @flags: for future extension.
  */
 SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
 		unsigned int, size, unsigned int, flags)
@@ -5046,7 +5079,6 @@ static int sched_cpu_active(struct notifier_block *nfb,
 				      unsigned long action, void *hcpu)
 {
 	switch (action & ~CPU_TASKS_FROZEN) {
-	case CPU_STARTING:
 	case CPU_DOWN_FAILED:
 		set_cpu_active((long)hcpu, true);
 		return NOTIFY_OK;
@@ -6020,6 +6052,8 @@ sd_numa_init(struct sched_domain_topology_level *tl, int cpu)
 					,
 		.last_balance		= jiffies,
 		.balance_interval	= sd_weight,
+		.max_newidle_lb_cost	= 0,
+		.next_decay_max_lb_cost	= jiffies,
 	};
 	SD_INIT_NAME(sd, NUMA);
 	sd->private = &tl->data;
diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c
index 5b9bb42b2d47..bd95963dae80 100644
--- a/kernel/sched/cpudeadline.c
+++ b/kernel/sched/cpudeadline.c
@@ -13,6 +13,7 @@
 
 #include <linux/gfp.h>
 #include <linux/kernel.h>
+#include <linux/slab.h>
 #include "cpudeadline.h"
 
 static inline int parent(int i)
@@ -39,8 +40,10 @@ static void cpudl_exchange(struct cpudl *cp, int a, int b)
 {
 	int cpu_a = cp->elements[a].cpu, cpu_b = cp->elements[b].cpu;
 
-	swap(cp->elements[a], cp->elements[b]);
-	swap(cp->cpu_to_idx[cpu_a], cp->cpu_to_idx[cpu_b]);
+	swap(cp->elements[a].cpu, cp->elements[b].cpu);
+	swap(cp->elements[a].dl , cp->elements[b].dl );
+
+	swap(cp->elements[cpu_a].idx, cp->elements[cpu_b].idx);
 }
 
 static void cpudl_heapify(struct cpudl *cp, int idx)
@@ -140,7 +143,7 @@ void cpudl_set(struct cpudl *cp, int cpu, u64 dl, int is_valid)
 	WARN_ON(!cpu_present(cpu));
 
 	raw_spin_lock_irqsave(&cp->lock, flags);
-	old_idx = cp->cpu_to_idx[cpu];
+	old_idx = cp->elements[cpu].idx;
 	if (!is_valid) {
 		/* remove item */
 		if (old_idx == IDX_INVALID) {
@@ -155,8 +158,8 @@ void cpudl_set(struct cpudl *cp, int cpu, u64 dl, int is_valid)
 		cp->elements[old_idx].dl = cp->elements[cp->size - 1].dl;
 		cp->elements[old_idx].cpu = new_cpu;
 		cp->size--;
-		cp->cpu_to_idx[new_cpu] = old_idx;
-		cp->cpu_to_idx[cpu] = IDX_INVALID;
+		cp->elements[new_cpu].idx = old_idx;
+		cp->elements[cpu].idx = IDX_INVALID;
 		while (old_idx > 0 && dl_time_before(
 				cp->elements[parent(old_idx)].dl,
 				cp->elements[old_idx].dl)) {
@@ -173,7 +176,7 @@ void cpudl_set(struct cpudl *cp, int cpu, u64 dl, int is_valid)
 		cp->size++;
 		cp->elements[cp->size - 1].dl = 0;
 		cp->elements[cp->size - 1].cpu = cpu;
-		cp->cpu_to_idx[cpu] = cp->size - 1;
+		cp->elements[cpu].idx = cp->size - 1;
 		cpudl_change_key(cp, cp->size - 1, dl);
 		cpumask_clear_cpu(cpu, cp->free_cpus);
 	} else {
@@ -195,10 +198,21 @@ int cpudl_init(struct cpudl *cp)
 	memset(cp, 0, sizeof(*cp));
 	raw_spin_lock_init(&cp->lock);
 	cp->size = 0;
-	for (i = 0; i < NR_CPUS; i++)
-		cp->cpu_to_idx[i] = IDX_INVALID;
-	if (!alloc_cpumask_var(&cp->free_cpus, GFP_KERNEL))
+
+	cp->elements = kcalloc(nr_cpu_ids,
+			       sizeof(struct cpudl_item),
+			       GFP_KERNEL);
+	if (!cp->elements)
+		return -ENOMEM;
+
+	if (!alloc_cpumask_var(&cp->free_cpus, GFP_KERNEL)) {
+		kfree(cp->elements);
 		return -ENOMEM;
+	}
+
+	for_each_possible_cpu(i)
+		cp->elements[i].idx = IDX_INVALID;
+
 	cpumask_setall(cp->free_cpus);
 
 	return 0;
@@ -210,7 +224,6 @@ int cpudl_init(struct cpudl *cp)
  */
 void cpudl_cleanup(struct cpudl *cp)
 {
-	/*
-	 * nothing to do for the moment
-	 */
+	free_cpumask_var(cp->free_cpus);
+	kfree(cp->elements);
 }
diff --git a/kernel/sched/cpudeadline.h b/kernel/sched/cpudeadline.h
index a202789a412c..538c9796ad4a 100644
--- a/kernel/sched/cpudeadline.h
+++ b/kernel/sched/cpudeadline.h
@@ -5,17 +5,17 @@
 
 #define IDX_INVALID     -1
 
-struct array_item {
+struct cpudl_item {
 	u64 dl;
 	int cpu;
+	int idx;
 };
 
 struct cpudl {
 	raw_spinlock_t lock;
 	int size;
-	int cpu_to_idx[NR_CPUS];
-	struct array_item elements[NR_CPUS];
 	cpumask_var_t free_cpus;
+	struct cpudl_item *elements;
 };
 
 
diff --git a/kernel/sched/cpupri.c b/kernel/sched/cpupri.c
index 8b836b376d91..8834243abee2 100644
--- a/kernel/sched/cpupri.c
+++ b/kernel/sched/cpupri.c
@@ -30,6 +30,7 @@
 #include <linux/gfp.h>
 #include <linux/sched.h>
 #include <linux/sched/rt.h>
+#include <linux/slab.h>
 #include "cpupri.h"
 
 /* Convert between a 140 based task->prio, and our 102 based cpupri */
@@ -70,8 +71,7 @@ int cpupri_find(struct cpupri *cp, struct task_struct *p,
 	int idx = 0;
 	int task_pri = convert_prio(p->prio);
 
-	if (task_pri >= MAX_RT_PRIO)
-		return 0;
+	BUG_ON(task_pri >= CPUPRI_NR_PRIORITIES);
 
 	for (idx = 0; idx < task_pri; idx++) {
 		struct cpupri_vec *vec  = &cp->pri_to_cpu[idx];
@@ -219,8 +219,13 @@ int cpupri_init(struct cpupri *cp)
 			goto cleanup;
 	}
 
+	cp->cpu_to_pri = kcalloc(nr_cpu_ids, sizeof(int), GFP_KERNEL);
+	if (!cp->cpu_to_pri)
+		goto cleanup;
+
 	for_each_possible_cpu(i)
 		cp->cpu_to_pri[i] = CPUPRI_INVALID;
+
 	return 0;
 
 cleanup:
@@ -237,6 +242,7 @@ void cpupri_cleanup(struct cpupri *cp)
 {
 	int i;
 
+	kfree(cp->cpu_to_pri);
 	for (i = 0; i < CPUPRI_NR_PRIORITIES; i++)
 		free_cpumask_var(cp->pri_to_cpu[i].mask);
 }
diff --git a/kernel/sched/cpupri.h b/kernel/sched/cpupri.h
index f6d756173491..6b033347fdfd 100644
--- a/kernel/sched/cpupri.h
+++ b/kernel/sched/cpupri.h
@@ -17,7 +17,7 @@ struct cpupri_vec {
 
 struct cpupri {
 	struct cpupri_vec pri_to_cpu[CPUPRI_NR_PRIORITIES];
-	int               cpu_to_pri[NR_CPUS];
+	int *cpu_to_pri;
 };
 
 #ifdef CONFIG_SMP
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index a95097cb4591..72fdf06ef865 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -332,50 +332,50 @@ out:
  * softirq as those do not count in task exec_runtime any more.
  */
 static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
-						struct rq *rq)
+					 struct rq *rq, int ticks)
 {
-	cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy);
+	cputime_t scaled = cputime_to_scaled(cputime_one_jiffy);
+	u64 cputime = (__force u64) cputime_one_jiffy;
 	u64 *cpustat = kcpustat_this_cpu->cpustat;
 
 	if (steal_account_process_tick())
 		return;
 
+	cputime *= ticks;
+	scaled *= ticks;
+
 	if (irqtime_account_hi_update()) {
-		cpustat[CPUTIME_IRQ] += (__force u64) cputime_one_jiffy;
+		cpustat[CPUTIME_IRQ] += cputime;
 	} else if (irqtime_account_si_update()) {
-		cpustat[CPUTIME_SOFTIRQ] += (__force u64) cputime_one_jiffy;
+		cpustat[CPUTIME_SOFTIRQ] += cputime;
 	} else if (this_cpu_ksoftirqd() == p) {
 		/*
 		 * ksoftirqd time do not get accounted in cpu_softirq_time.
 		 * So, we have to handle it separately here.
 		 * Also, p->stime needs to be updated for ksoftirqd.
 		 */
-		__account_system_time(p, cputime_one_jiffy, one_jiffy_scaled,
-					CPUTIME_SOFTIRQ);
+		__account_system_time(p, cputime, scaled, CPUTIME_SOFTIRQ);
 	} else if (user_tick) {
-		account_user_time(p, cputime_one_jiffy, one_jiffy_scaled);
+		account_user_time(p, cputime, scaled);
 	} else if (p == rq->idle) {
-		account_idle_time(cputime_one_jiffy);
+		account_idle_time(cputime);
 	} else if (p->flags & PF_VCPU) { /* System time or guest time */
-		account_guest_time(p, cputime_one_jiffy, one_jiffy_scaled);
+		account_guest_time(p, cputime, scaled);
 	} else {
-		__account_system_time(p, cputime_one_jiffy, one_jiffy_scaled,
-					CPUTIME_SYSTEM);
+		__account_system_time(p, cputime, scaled,	CPUTIME_SYSTEM);
 	}
 }
 
 static void irqtime_account_idle_ticks(int ticks)
 {
-	int i;
 	struct rq *rq = this_rq();
 
-	for (i = 0; i < ticks; i++)
-		irqtime_account_process_tick(current, 0, rq);
+	irqtime_account_process_tick(current, 0, rq, ticks);
 }
 #else /* CONFIG_IRQ_TIME_ACCOUNTING */
 static inline void irqtime_account_idle_ticks(int ticks) {}
 static inline void irqtime_account_process_tick(struct task_struct *p, int user_tick,
-						struct rq *rq) {}
+						struct rq *rq, int nr_ticks) {}
 #endif /* CONFIG_IRQ_TIME_ACCOUNTING */
 
 /*
@@ -464,7 +464,7 @@ void account_process_tick(struct task_struct *p, int user_tick)
 		return;
 
 	if (sched_clock_irqtime) {
-		irqtime_account_process_tick(p, user_tick, rq);
+		irqtime_account_process_tick(p, user_tick, rq, 1);
 		return;
 	}
 
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index b08095786cb8..800e99b99075 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -528,6 +528,7 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
 	sched_clock_tick();
 	update_rq_clock(rq);
 	dl_se->dl_throttled = 0;
+	dl_se->dl_yielded = 0;
 	if (p->on_rq) {
 		enqueue_task_dl(rq, p, ENQUEUE_REPLENISH);
 		if (task_has_dl_policy(rq->curr))
@@ -893,10 +894,10 @@ static void yield_task_dl(struct rq *rq)
 	 * We make the task go to sleep until its current deadline by
 	 * forcing its runtime to zero. This way, update_curr_dl() stops
 	 * it and the bandwidth timer will wake it up and will give it
-	 * new scheduling parameters (thanks to dl_new=1).
+	 * new scheduling parameters (thanks to dl_yielded=1).
 	 */
 	if (p->dl.runtime > 0) {
-		rq->curr->dl.dl_new = 1;
+		rq->curr->dl.dl_yielded = 1;
 		p->dl.runtime = 0;
 	}
 	update_curr_dl(rq);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 7570dd969c28..0fdb96de81a5 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6653,6 +6653,7 @@ static int idle_balance(struct rq *this_rq)
 	int this_cpu = this_rq->cpu;
 
 	idle_enter_fair(this_rq);
+
 	/*
 	 * We must set idle_stamp _before_ calling idle_balance(), such that we
 	 * measure the duration of idle_balance() as idle time.
@@ -6705,14 +6706,16 @@ static int idle_balance(struct rq *this_rq)
 
 	raw_spin_lock(&this_rq->lock);
 
+	if (curr_cost > this_rq->max_idle_balance_cost)
+		this_rq->max_idle_balance_cost = curr_cost;
+
 	/*
-	 * While browsing the domains, we released the rq lock.
-	 * A task could have be enqueued in the meantime
+	 * While browsing the domains, we released the rq lock, a task could
+	 * have been enqueued in the meantime. Since we're not going idle,
+	 * pretend we pulled a task.
 	 */
-	if (this_rq->cfs.h_nr_running && !pulled_task) {
+	if (this_rq->cfs.h_nr_running && !pulled_task)
 		pulled_task = 1;
-		goto out;
-	}
 
 	if (pulled_task || time_after(jiffies, this_rq->next_balance)) {
 		/*
@@ -6722,9 +6725,6 @@ static int idle_balance(struct rq *this_rq)
 		this_rq->next_balance = next_balance;
 	}
 
-	if (curr_cost > this_rq->max_idle_balance_cost)
-		this_rq->max_idle_balance_cost = curr_cost;
-
 out:
 	/* Is there a task of a high priority class? */
 	if (this_rq->nr_running != this_rq->cfs.h_nr_running &&
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 33e4648ae0e7..92f24f5e8d52 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -223,7 +223,7 @@ static inline bool lockdep_softirq_start(void) { return false; }
 static inline void lockdep_softirq_end(bool in_hardirq) { }
 #endif
 
-asmlinkage void __do_softirq(void)
+asmlinkage __visible void __do_softirq(void)
 {
 	unsigned long end = jiffies + MAX_SOFTIRQ_TIME;
 	unsigned long old_flags = current->flags;
@@ -299,7 +299,7 @@ restart:
 	tsk_restore_flags(current, old_flags, PF_MEMALLOC);
 }
 
-asmlinkage void do_softirq(void)
+asmlinkage __visible void do_softirq(void)
 {
 	__u32 pending;
 	unsigned long flags;
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index ac5b23cf7212..6620e5837ce2 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -188,7 +188,6 @@ static int tracepoint_add_func(struct tracepoint *tp,
 		WARN_ON_ONCE(1);
 		return PTR_ERR(old);
 	}
-	release_probes(old);
 
 	/*
 	 * rcu_assign_pointer has a smp_wmb() which makes sure that the new
@@ -200,6 +199,7 @@ static int tracepoint_add_func(struct tracepoint *tp,
 	rcu_assign_pointer(tp->funcs, tp_funcs);
 	if (!static_key_enabled(&tp->key))
 		static_key_slow_inc(&tp->key);
+	release_probes(old);
 	return 0;
 }
 
@@ -221,7 +221,6 @@ static int tracepoint_remove_func(struct tracepoint *tp,
 		WARN_ON_ONCE(1);
 		return PTR_ERR(old);
 	}
-	release_probes(old);
 
 	if (!tp_funcs) {
 		/* Removed last function */
@@ -232,6 +231,7 @@ static int tracepoint_remove_func(struct tracepoint *tp,
 			static_key_slow_dec(&tp->key);
 	}
 	rcu_assign_pointer(tp->funcs, tp_funcs);
+	release_probes(old);
 	return 0;
 }
 
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 0ee63af30bd1..8edc87185427 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -1916,6 +1916,12 @@ static void send_mayday(struct work_struct *work)
 
 	/* mayday mayday mayday */
 	if (list_empty(&pwq->mayday_node)) {
+		/*
+		 * If @pwq is for an unbound wq, its base ref may be put at
+		 * any time due to an attribute change.  Pin @pwq until the
+		 * rescuer is done with it.
+		 */
+		get_pwq(pwq);
 		list_add_tail(&pwq->mayday_node, &wq->maydays);
 		wake_up_process(wq->rescuer->task);
 	}
@@ -2398,6 +2404,7 @@ static int rescuer_thread(void *__rescuer)
 	struct worker *rescuer = __rescuer;
 	struct workqueue_struct *wq = rescuer->rescue_wq;
 	struct list_head *scheduled = &rescuer->scheduled;
+	bool should_stop;
 
 	set_user_nice(current, RESCUER_NICE_LEVEL);
 
@@ -2409,11 +2416,15 @@ static int rescuer_thread(void *__rescuer)
 repeat:
 	set_current_state(TASK_INTERRUPTIBLE);
 
-	if (kthread_should_stop()) {
-		__set_current_state(TASK_RUNNING);
-		rescuer->task->flags &= ~PF_WQ_WORKER;
-		return 0;
-	}
+	/*
+	 * By the time the rescuer is requested to stop, the workqueue
+	 * shouldn't have any work pending, but @wq->maydays may still have
+	 * pwq(s) queued.  This can happen by non-rescuer workers consuming
+	 * all the work items before the rescuer got to them.  Go through
+	 * @wq->maydays processing before acting on should_stop so that the
+	 * list is always empty on exit.
+	 */
+	should_stop = kthread_should_stop();
 
 	/* see whether any pwq is asking for help */
 	spin_lock_irq(&wq_mayday_lock);
@@ -2445,6 +2456,12 @@ repeat:
 		process_scheduled_works(rescuer);
 
 		/*
+		 * Put the reference grabbed by send_mayday().  @pool won't
+		 * go away while we're holding its lock.
+		 */
+		put_pwq(pwq);
+
+		/*
 		 * Leave this pool.  If keep_working() is %true, notify a
 		 * regular worker; otherwise, we end up with 0 concurrency
 		 * and stalling the execution.
@@ -2459,6 +2476,12 @@ repeat:
 
 	spin_unlock_irq(&wq_mayday_lock);
 
+	if (should_stop) {
+		__set_current_state(TASK_RUNNING);
+		rescuer->task->flags &= ~PF_WQ_WORKER;
+		return 0;
+	}
+
 	/* rescuers should never participate in concurrency management */
 	WARN_ON_ONCE(!(rescuer->flags & WORKER_NOT_RUNNING));
 	schedule();
@@ -4100,7 +4123,8 @@ static void wq_update_unbound_numa(struct workqueue_struct *wq, int cpu,
 	if (!pwq) {
 		pr_warning("workqueue: allocation failed while updating NUMA affinity of \"%s\"\n",
 			   wq->name);
-		goto out_unlock;
+		mutex_lock(&wq->mutex);
+		goto use_dfl_pwq;
 	}
 
 	/*