Merge commit '9f12600fe425bc28f0ccba034a77783c09c15af4' into for-linus

Backmerge of dcache.c changes from mainline.  It's that, or complete
rebase...

Conflicts:
	fs/splice.c

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

18 files changed, 244 insertions, 211 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/events/core.c b/kernel/events/core.c
index f83a71a3e46d..440eefc67397 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1443,6 +1443,11 @@ group_sched_out(struct perf_event *group_event,
 		cpuctx->exclusive = 0;
 }
 
+struct remove_event {
+	struct perf_event *event;
+	bool detach_group;
+};
+
 /*
  * Cross CPU call to remove a performance event
  *
@@ -1451,12 +1456,15 @@ group_sched_out(struct perf_event *group_event,
  */
 static int __perf_remove_from_context(void *info)
 {
-	struct perf_event *event = info;
+	struct remove_event *re = info;
+	struct perf_event *event = re->event;
 	struct perf_event_context *ctx = event->ctx;
 	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
 
 	raw_spin_lock(&ctx->lock);
 	event_sched_out(event, cpuctx, ctx);
+	if (re->detach_group)
+		perf_group_detach(event);
 	list_del_event(event, ctx);
 	if (!ctx->nr_events && cpuctx->task_ctx == ctx) {
 		ctx->is_active = 0;
@@ -1481,10 +1489,14 @@ static int __perf_remove_from_context(void *info)
  * When called from perf_event_exit_task, it's OK because the
  * context has been detached from its task.
  */
-static void perf_remove_from_context(struct perf_event *event)
+static void perf_remove_from_context(struct perf_event *event, bool detach_group)
 {
 	struct perf_event_context *ctx = event->ctx;
 	struct task_struct *task = ctx->task;
+	struct remove_event re = {
+		.event = event,
+		.detach_group = detach_group,
+	};
 
 	lockdep_assert_held(&ctx->mutex);
 
@@ -1493,12 +1505,12 @@ static void perf_remove_from_context(struct perf_event *event)
 		 * Per cpu events are removed via an smp call and
 		 * the removal is always successful.
 		 */
-		cpu_function_call(event->cpu, __perf_remove_from_context, event);
+		cpu_function_call(event->cpu, __perf_remove_from_context, &re);
 		return;
 	}
 
 retry:
-	if (!task_function_call(task, __perf_remove_from_context, event))
+	if (!task_function_call(task, __perf_remove_from_context, &re))
 		return;
 
 	raw_spin_lock_irq(&ctx->lock);
@@ -1515,6 +1527,8 @@ retry:
 	 * Since the task isn't running, its safe to remove the event, us
 	 * holding the ctx->lock ensures the task won't get scheduled in.
 	 */
+	if (detach_group)
+		perf_group_detach(event);
 	list_del_event(event, ctx);
 	raw_spin_unlock_irq(&ctx->lock);
 }
@@ -3178,7 +3192,8 @@ 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)
 {
@@ -3238,8 +3253,6 @@ 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.
 		 *
@@ -3247,12 +3260,7 @@ 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);
 	}
 
@@ -3281,10 +3289,7 @@ int perf_event_release_kernel(struct perf_event *event)
 	 *     to trigger the AB-BA case.
 	 */
 	mutex_lock_nested(&ctx->mutex, SINGLE_DEPTH_NESTING);
-	raw_spin_lock_irq(&ctx->lock);
-	perf_group_detach(event);
-	raw_spin_unlock_irq(&ctx->lock);
-	perf_remove_from_context(event);
+	perf_remove_from_context(event, true);
 	mutex_unlock(&ctx->mutex);
 
 	free_event(event);
@@ -3839,28 +3844,47 @@ 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)
@@ -3929,7 +3953,7 @@ 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);
@@ -3937,18 +3961,14 @@ 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
@@ -3978,11 +3998,9 @@ 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);
 
@@ -4007,6 +4025,7 @@ again:
 	vma->vm_mm->pinned_vm -= mmap_locked;
 	free_uid(mmap_user);
 
+out_put:
 	ring_buffer_put(rb); /* could be last */
 }
 
@@ -4124,7 +4143,6 @@ 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);
@@ -5408,6 +5426,9 @@ 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);
@@ -5654,8 +5675,14 @@ 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);
 
@@ -6914,7 +6941,7 @@ 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)
@@ -6942,8 +6969,6 @@ 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);
@@ -6951,23 +6976,7 @@ 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:
@@ -7018,6 +7027,9 @@ 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;
 	}
 
 	/*
@@ -7165,7 +7177,7 @@ SYSCALL_DEFINE5(perf_event_open,
 		struct perf_event_context *gctx = group_leader->ctx;
 
 		mutex_lock(&gctx->mutex);
-		perf_remove_from_context(group_leader);
+		perf_remove_from_context(group_leader, false);
 
 		/*
 		 * Removing from the context ends up with disabled
@@ -7175,7 +7187,7 @@ SYSCALL_DEFINE5(perf_event_open,
 		perf_event__state_init(group_leader);
 		list_for_each_entry(sibling, &group_leader->sibling_list,
 				    group_entry) {
-			perf_remove_from_context(sibling);
+			perf_remove_from_context(sibling, false);
 			perf_event__state_init(sibling);
 			put_ctx(gctx);
 		}
@@ -7305,7 +7317,7 @@ void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu)
 	mutex_lock(&src_ctx->mutex);
 	list_for_each_entry_safe(event, tmp, &src_ctx->event_list,
 				 event_entry) {
-		perf_remove_from_context(event);
+		perf_remove_from_context(event, false);
 		unaccount_event_cpu(event, src_cpu);
 		put_ctx(src_ctx);
 		list_add(&event->migrate_entry, &events);
@@ -7367,13 +7379,7 @@ __perf_event_exit_task(struct perf_event *child_event,
 			 struct perf_event_context *child_ctx,
 			 struct task_struct *child)
 {
-	if (child_event->parent) {
-		raw_spin_lock_irq(&child_ctx->lock);
-		perf_group_detach(child_event);
-		raw_spin_unlock_irq(&child_ctx->lock);
-	}
-
-	perf_remove_from_context(child_event);
+	perf_remove_from_context(child_event, !!child_event->parent);
 
 	/*
 	 * It can happen that the parent exits first, and has events
@@ -7724,6 +7730,8 @@ int perf_event_init_context(struct task_struct *child, int ctxn)
 	 * swapped under us.
 	 */
 	parent_ctx = perf_pin_task_context(parent, ctxn);
+	if (!parent_ctx)
+		return 0;
 
 	/*
 	 * No need to check if parent_ctx != NULL here; since we saw
@@ -7835,6 +7843,7 @@ 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;
 
@@ -7857,14 +7866,14 @@ static void perf_pmu_rotate_stop(struct pmu *pmu)
 
 static void __perf_event_exit_context(void *__info)
 {
+	struct remove_event re = { .detach_group = false };
 	struct perf_event_context *ctx = __info;
-	struct perf_event *event;
 
 	perf_pmu_rotate_stop(ctx->pmu);
 
 	rcu_read_lock();
-	list_for_each_entry_rcu(event, &ctx->event_list, event_entry)
-		__perf_remove_from_context(event);
+	list_for_each_entry_rcu(re.event, &ctx->event_list, event_entry)
+		__perf_remove_from_context(&re);
 	rcu_read_unlock();
 }
 
@@ -7892,6 +7901,7 @@ 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/hrtimer.c b/kernel/hrtimer.c
index 6b715c0af1b1..e0501fe7140d 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/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 268a45ea238c..204d3d281809 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();
@@ -2592,8 +2592,14 @@ 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:
@@ -2741,7 +2747,7 @@ 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;
 
@@ -2751,7 +2757,7 @@ 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(),
@@ -2783,7 +2789,7 @@ 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,
@@ -2813,7 +2819,7 @@ 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;
 
@@ -3124,6 +3130,7 @@ __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,
@@ -3639,6 +3646,7 @@ 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)
@@ -3783,6 +3791,7 @@ 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)
@@ -6017,6 +6026,8 @@ 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..ab001b5d5048 100644
--- a/kernel/sched/cpudeadline.c
+++ b/kernel/sched/cpudeadline.c
@@ -210,7 +210,5 @@ int cpudl_init(struct cpudl *cp)
  */
 void cpudl_cleanup(struct cpudl *cp)
 {
-	/*
-	 * nothing to do for the moment
-	 */
+	free_cpumask_var(cp->free_cpus);
 }
diff --git a/kernel/sched/cpupri.c b/kernel/sched/cpupri.c
index 8b836b376d91..3031bac8aa3e 100644
--- a/kernel/sched/cpupri.c
+++ b/kernel/sched/cpupri.c
@@ -70,8 +70,7 @@ 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];
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;
 	}
 
 	/*