Merge tag 'v3.16-rc7' into perf/core, to merge in the latest fixes before applying new changes

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

36 files changed, 528 insertions, 216 deletions

diff --git a/kernel/Kconfig.locks b/kernel/Kconfig.locks
index 35536d9c096..76768ee812b 100644
--- a/kernel/Kconfig.locks
+++ b/kernel/Kconfig.locks
@@ -220,9 +220,16 @@ config INLINE_WRITE_UNLOCK_IRQRESTORE
 
 endif
 
+config ARCH_SUPPORTS_ATOMIC_RMW
+	bool
+
 config MUTEX_SPIN_ON_OWNER
 	def_bool y
-	depends on SMP && !DEBUG_MUTEXES
+	depends on SMP && !DEBUG_MUTEXES && ARCH_SUPPORTS_ATOMIC_RMW
+
+config RWSEM_SPIN_ON_OWNER
+       def_bool y
+       depends on SMP && RWSEM_XCHGADD_ALGORITHM && ARCH_SUPPORTS_ATOMIC_RMW
 
 config ARCH_USE_QUEUE_RWLOCK
 	bool
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 7868fc3c0bc..70776aec256 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -1648,10 +1648,13 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
 			 int flags, const char *unused_dev_name,
 			 void *data)
 {
+	struct super_block *pinned_sb = NULL;
+	struct cgroup_subsys *ss;
 	struct cgroup_root *root;
 	struct cgroup_sb_opts opts;
 	struct dentry *dentry;
 	int ret;
+	int i;
 	bool new_sb;
 
 	/*
@@ -1677,6 +1680,27 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
 		goto out_unlock;
 	}
 
+	/*
+	 * Destruction of cgroup root is asynchronous, so subsystems may
+	 * still be dying after the previous unmount.  Let's drain the
+	 * dying subsystems.  We just need to ensure that the ones
+	 * unmounted previously finish dying and don't care about new ones
+	 * starting.  Testing ref liveliness is good enough.
+	 */
+	for_each_subsys(ss, i) {
+		if (!(opts.subsys_mask & (1 << i)) ||
+		    ss->root == &cgrp_dfl_root)
+			continue;
+
+		if (!percpu_ref_tryget_live(&ss->root->cgrp.self.refcnt)) {
+			mutex_unlock(&cgroup_mutex);
+			msleep(10);
+			ret = restart_syscall();
+			goto out_free;
+		}
+		cgroup_put(&ss->root->cgrp);
+	}
+
 	for_each_root(root) {
 		bool name_match = false;
 
@@ -1717,15 +1741,23 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
 		}
 
 		/*
-		 * A root's lifetime is governed by its root cgroup.
-		 * tryget_live failure indicate that the root is being
-		 * destroyed.  Wait for destruction to complete so that the
-		 * subsystems are free.  We can use wait_queue for the wait
-		 * but this path is super cold.  Let's just sleep for a bit
-		 * and retry.
+		 * We want to reuse @root whose lifetime is governed by its
+		 * ->cgrp.  Let's check whether @root is alive and keep it
+		 * that way.  As cgroup_kill_sb() can happen anytime, we
+		 * want to block it by pinning the sb so that @root doesn't
+		 * get killed before mount is complete.
+		 *
+		 * With the sb pinned, tryget_live can reliably indicate
+		 * whether @root can be reused.  If it's being killed,
+		 * drain it.  We can use wait_queue for the wait but this
+		 * path is super cold.  Let's just sleep a bit and retry.
 		 */
-		if (!percpu_ref_tryget_live(&root->cgrp.self.refcnt)) {
+		pinned_sb = kernfs_pin_sb(root->kf_root, NULL);
+		if (IS_ERR(pinned_sb) ||
+		    !percpu_ref_tryget_live(&root->cgrp.self.refcnt)) {
 			mutex_unlock(&cgroup_mutex);
+			if (!IS_ERR_OR_NULL(pinned_sb))
+				deactivate_super(pinned_sb);
 			msleep(10);
 			ret = restart_syscall();
 			goto out_free;
@@ -1770,6 +1802,16 @@ out_free:
 				CGROUP_SUPER_MAGIC, &new_sb);
 	if (IS_ERR(dentry) || !new_sb)
 		cgroup_put(&root->cgrp);
+
+	/*
+	 * If @pinned_sb, we're reusing an existing root and holding an
+	 * extra ref on its sb.  Mount is complete.  Put the extra ref.
+	 */
+	if (pinned_sb) {
+		WARN_ON(new_sb);
+		deactivate_super(pinned_sb);
+	}
+
 	return dentry;
 }
 
@@ -3328,7 +3370,7 @@ bool css_has_online_children(struct cgroup_subsys_state *css)
 
 	rcu_read_lock();
 	css_for_each_child(child, css) {
-		if (css->flags & CSS_ONLINE) {
+		if (child->flags & CSS_ONLINE) {
 			ret = true;
 			break;
 		}
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index f6b33c69622..116a4164720 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1181,7 +1181,13 @@ done:
 
 int current_cpuset_is_being_rebound(void)
 {
-	return task_cs(current) == cpuset_being_rebound;
+	int ret;
+
+	rcu_read_lock();
+	ret = task_cs(current) == cpuset_being_rebound;
+	rcu_read_unlock();
+
+	return ret;
 }
 
 static int update_relax_domain_level(struct cpuset *cs, s64 val)
@@ -1617,7 +1623,17 @@ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of,
 	 * resources, wait for the previously scheduled operations before
 	 * proceeding, so that we don't end up keep removing tasks added
 	 * after execution capability is restored.
+	 *
+	 * cpuset_hotplug_work calls back into cgroup core via
+	 * cgroup_transfer_tasks() and waiting for it from a cgroupfs
+	 * operation like this one can lead to a deadlock through kernfs
+	 * active_ref protection.  Let's break the protection.  Losing the
+	 * protection is okay as we check whether @cs is online after
+	 * grabbing cpuset_mutex anyway.  This only happens on the legacy
+	 * hierarchies.
 	 */
+	css_get(&cs->css);
+	kernfs_break_active_protection(of->kn);
 	flush_work(&cpuset_hotplug_work);
 
 	mutex_lock(&cpuset_mutex);
@@ -1645,6 +1661,8 @@ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of,
 	free_trial_cpuset(trialcs);
 out_unlock:
 	mutex_unlock(&cpuset_mutex);
+	kernfs_unbreak_active_protection(of->kn);
+	css_put(&cs->css);
 	return retval ?: nbytes;
 }
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 47996766e3d..1cf24b3e42e 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2320,7 +2320,7 @@ static void perf_event_context_sched_out(struct task_struct *task, int ctxn,
 	next_parent = rcu_dereference(next_ctx->parent_ctx);
 
 	/* If neither context have a parent context; they cannot be clones. */
-	if (!parent && !next_parent)
+	if (!parent || !next_parent)
 		goto unlock;
 
 	if (next_parent == ctx || next_ctx == parent || next_parent == parent) {
@@ -7464,7 +7464,19 @@ __perf_event_exit_task(struct perf_event *child_event,
 			 struct perf_event_context *child_ctx,
 			 struct task_struct *child)
 {
-	perf_remove_from_context(child_event, true);
+	/*
+	 * Do not destroy the 'original' grouping; because of the context
+	 * switch optimization the original events could've ended up in a
+	 * random child task.
+	 *
+	 * If we were to destroy the original group, all group related
+	 * operations would cease to function properly after this random
+	 * child dies.
+	 *
+	 * Do destroy all inherited groups, we don't care about those
+	 * and being thorough is better.
+	 */
+	perf_remove_from_context(child_event, !!child_event->parent);
 
 	/*
 	 * It can happen that the parent exits first, and has events
@@ -7480,7 +7492,7 @@ __perf_event_exit_task(struct perf_event *child_event,
 static void perf_event_exit_task_context(struct task_struct *child, int ctxn)
 {
 	struct perf_event *child_event, *next;
-	struct perf_event_context *child_ctx;
+	struct perf_event_context *child_ctx, *parent_ctx;
 	unsigned long flags;
 
 	if (likely(!child->perf_event_ctxp[ctxn])) {
@@ -7505,6 +7517,15 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn)
 	raw_spin_lock(&child_ctx->lock);
 	task_ctx_sched_out(child_ctx);
 	child->perf_event_ctxp[ctxn] = NULL;
+
+	/*
+	 * In order to avoid freeing: child_ctx->parent_ctx->task
+	 * under perf_event_context::lock, grab another reference.
+	 */
+	parent_ctx = child_ctx->parent_ctx;
+	if (parent_ctx)
+		get_ctx(parent_ctx);
+
 	/*
 	 * If this context is a clone; unclone it so it can't get
 	 * swapped to another process while we're removing all
@@ -7515,6 +7536,13 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn)
 	raw_spin_unlock_irqrestore(&child_ctx->lock, flags);
 
 	/*
+	 * Now that we no longer hold perf_event_context::lock, drop
+	 * our extra child_ctx->parent_ctx reference.
+	 */
+	if (parent_ctx)
+		put_ctx(parent_ctx);
+
+	/*
 	 * Report the task dead after unscheduling the events so that we
 	 * won't get any samples after PERF_RECORD_EXIT. We can however still
 	 * get a few PERF_RECORD_READ events.
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index c445e392e93..6f3254e8c13 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -846,7 +846,7 @@ static void __uprobe_unregister(struct uprobe *uprobe, struct uprobe_consumer *u
 {
 	int err;
 
-	if (!consumer_del(uprobe, uc))	/* WARN? */
+	if (WARN_ON(!consumer_del(uprobe, uc)))
 		return;
 
 	err = register_for_each_vma(uprobe, NULL);
@@ -927,7 +927,7 @@ int uprobe_apply(struct inode *inode, loff_t offset,
 	int ret = -ENOENT;
 
 	uprobe = find_uprobe(inode, offset);
-	if (!uprobe)
+	if (WARN_ON(!uprobe))
 		return ret;
 
 	down_write(&uprobe->register_rwsem);
@@ -952,7 +952,7 @@ void uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consume
 	struct uprobe *uprobe;
 
 	uprobe = find_uprobe(inode, offset);
-	if (!uprobe)
+	if (WARN_ON(!uprobe))
 		return;
 
 	down_write(&uprobe->register_rwsem);
diff --git a/kernel/fork.c b/kernel/fork.c
index d2799d1fc95..6a13c46cd87 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1487,7 +1487,9 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 
 	total_forks++;
 	spin_unlock(&current->sighand->siglock);
+	syscall_tracepoint_update(p);
 	write_unlock_irq(&tasklist_lock);
+
 	proc_fork_connector(p);
 	cgroup_post_fork(p);
 	if (clone_flags & CLONE_THREAD)
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 7339e42a85a..1487a123db5 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -455,9 +455,9 @@ EXPORT_SYMBOL_GPL(irq_alloc_hwirqs);
  */
 void irq_free_hwirqs(unsigned int from, int cnt)
 {
-	int i;
+	int i, j;
 
-	for (i = from; cnt > 0; i++, cnt--) {
+	for (i = from, j = cnt; j > 0; i++, j--) {
 		irq_set_status_flags(i, _IRQ_NOREQUEST | _IRQ_NOPROBE);
 		arch_teardown_hwirq(i);
 	}
diff --git a/kernel/kexec.c b/kernel/kexec.c
index 6748688813d..369f41a9412 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -1617,6 +1617,7 @@ static int __init crash_save_vmcoreinfo_init(void)
 #ifdef CONFIG_MEMORY_FAILURE
 	VMCOREINFO_NUMBER(PG_hwpoison);
 #endif
+	VMCOREINFO_NUMBER(PG_head_mask);
 	VMCOREINFO_NUMBER(PAGE_BUDDY_MAPCOUNT_VALUE);
 
 	arch_crash_save_vmcoreinfo();
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 3214289df5a..734e9a7d280 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -2037,19 +2037,23 @@ static int __init populate_kprobe_blacklist(unsigned long *start,
 {
 	unsigned long *iter;
 	struct kprobe_blacklist_entry *ent;
-	unsigned long offset = 0, size = 0;
+	unsigned long entry, offset = 0, size = 0;
 
 	for (iter = start; iter < end; iter++) {
-		if (!kallsyms_lookup_size_offset(*iter, &size, &offset)) {
-			pr_err("Failed to find blacklist %p\n", (void *)*iter);
+		entry = arch_deref_entry_point((void *)*iter);
+
+		if (!kernel_text_address(entry) ||
+		    !kallsyms_lookup_size_offset(entry, &size, &offset)) {
+			pr_err("Failed to find blacklist at %p\n",
+				(void *)entry);
 			continue;
 		}
 
 		ent = kmalloc(sizeof(*ent), GFP_KERNEL);
 		if (!ent)
 			return -ENOMEM;
-		ent->start_addr = *iter;
-		ent->end_addr = *iter + size;
+		ent->start_addr = entry;
+		ent->end_addr = entry + size;
 		INIT_LIST_HEAD(&ent->list);
 		list_add_tail(&ent->list, &kprobe_blacklist);
 	}
diff --git a/kernel/locking/mcs_spinlock.c b/kernel/locking/mcs_spinlock.c
index 838dc9e0066..be9ee1559fc 100644
--- a/kernel/locking/mcs_spinlock.c
+++ b/kernel/locking/mcs_spinlock.c
@@ -14,21 +14,47 @@
  * called from interrupt context and we have preemption disabled while
  * spinning.
  */
-static DEFINE_PER_CPU_SHARED_ALIGNED(struct optimistic_spin_queue, osq_node);
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct optimistic_spin_node, osq_node);
+
+/*
+ * We use the value 0 to represent "no CPU", thus the encoded value
+ * will be the CPU number incremented by 1.
+ */
+static inline int encode_cpu(int cpu_nr)
+{
+	return cpu_nr + 1;
+}
+
+static inline struct optimistic_spin_node *decode_cpu(int encoded_cpu_val)
+{
+	int cpu_nr = encoded_cpu_val - 1;
+
+	return per_cpu_ptr(&osq_node, cpu_nr);
+}
 
 /*
  * Get a stable @node->next pointer, either for unlock() or unqueue() purposes.
  * Can return NULL in case we were the last queued and we updated @lock instead.
  */
-static inline struct optimistic_spin_queue *
-osq_wait_next(struct optimistic_spin_queue **lock,
-	      struct optimistic_spin_queue *node,
-	      struct optimistic_spin_queue *prev)
+static inline struct optimistic_spin_node *
+osq_wait_next(struct optimistic_spin_queue *lock,
+	      struct optimistic_spin_node *node,
+	      struct optimistic_spin_node *prev)
 {
-	struct optimistic_spin_queue *next = NULL;
+	struct optimistic_spin_node *next = NULL;
+	int curr = encode_cpu(smp_processor_id());
+	int old;
+
+	/*
+	 * If there is a prev node in queue, then the 'old' value will be
+	 * the prev node's CPU #, else it's set to OSQ_UNLOCKED_VAL since if
+	 * we're currently last in queue, then the queue will then become empty.
+	 */
+	old = prev ? prev->cpu : OSQ_UNLOCKED_VAL;
 
 	for (;;) {
-		if (*lock == node && cmpxchg(lock, node, prev) == node) {
+		if (atomic_read(&lock->tail) == curr &&
+		    atomic_cmpxchg(&lock->tail, curr, old) == curr) {
 			/*
 			 * We were the last queued, we moved @lock back. @prev
 			 * will now observe @lock and will complete its
@@ -59,18 +85,23 @@ osq_wait_next(struct optimistic_spin_queue **lock,
 	return next;
 }
 
-bool osq_lock(struct optimistic_spin_queue **lock)
+bool osq_lock(struct optimistic_spin_queue *lock)
 {
-	struct optimistic_spin_queue *node = this_cpu_ptr(&osq_node);
-	struct optimistic_spin_queue *prev, *next;
+	struct optimistic_spin_node *node = this_cpu_ptr(&osq_node);
+	struct optimistic_spin_node *prev, *next;
+	int curr = encode_cpu(smp_processor_id());
+	int old;
 
 	node->locked = 0;
 	node->next = NULL;
+	node->cpu = curr;
 
-	node->prev = prev = xchg(lock, node);
-	if (likely(prev == NULL))
+	old = atomic_xchg(&lock->tail, curr);
+	if (old == OSQ_UNLOCKED_VAL)
 		return true;
 
+	prev = decode_cpu(old);
+	node->prev = prev;
 	ACCESS_ONCE(prev->next) = node;
 
 	/*
@@ -149,20 +180,21 @@ unqueue:
 	return false;
 }
 
-void osq_unlock(struct optimistic_spin_queue **lock)
+void osq_unlock(struct optimistic_spin_queue *lock)
 {
-	struct optimistic_spin_queue *node = this_cpu_ptr(&osq_node);
-	struct optimistic_spin_queue *next;
+	struct optimistic_spin_node *node, *next;
+	int curr = encode_cpu(smp_processor_id());
 
 	/*
 	 * Fast path for the uncontended case.
 	 */
-	if (likely(cmpxchg(lock, node, NULL) == node))
+	if (likely(atomic_cmpxchg(&lock->tail, curr, OSQ_UNLOCKED_VAL) == curr))
 		return;
 
 	/*
 	 * Second most likely case.
 	 */
+	node = this_cpu_ptr(&osq_node);
 	next = xchg(&node->next, NULL);
 	if (next) {
 		ACCESS_ONCE(next->locked) = 1;
diff --git a/kernel/locking/mcs_spinlock.h b/kernel/locking/mcs_spinlock.h
index a2dbac4aca6..74356dc0ce2 100644
--- a/kernel/locking/mcs_spinlock.h
+++ b/kernel/locking/mcs_spinlock.h
@@ -118,12 +118,13 @@ void mcs_spin_unlock(struct mcs_spinlock **lock, struct mcs_spinlock *node)
  * mutex_lock()/rwsem_down_{read,write}() etc.
  */
 
-struct optimistic_spin_queue {
-	struct optimistic_spin_queue *next, *prev;
+struct optimistic_spin_node {
+	struct optimistic_spin_node *next, *prev;
 	int locked; /* 1 if lock acquired */
+	int cpu; /* encoded CPU # value */
 };
 
-extern bool osq_lock(struct optimistic_spin_queue **lock);
-extern void osq_unlock(struct optimistic_spin_queue **lock);
+extern bool osq_lock(struct optimistic_spin_queue *lock);
+extern void osq_unlock(struct optimistic_spin_queue *lock);
 
 #endif /* __LINUX_MCS_SPINLOCK_H */
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index bc73d33c676..acca2c1a3c5 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -60,7 +60,7 @@ __mutex_init(struct mutex *lock, const char *name, struct lock_class_key *key)
 	INIT_LIST_HEAD(&lock->wait_list);
 	mutex_clear_owner(lock);
 #ifdef CONFIG_MUTEX_SPIN_ON_OWNER
-	lock->osq = NULL;
+	osq_lock_init(&lock->osq);
 #endif
 
 	debug_mutex_init(lock, name, key);
diff --git a/kernel/locking/rwsem-spinlock.c b/kernel/locking/rwsem-spinlock.c
index 9be8a914497..2c93571162c 100644
--- a/kernel/locking/rwsem-spinlock.c
+++ b/kernel/locking/rwsem-spinlock.c
@@ -26,7 +26,7 @@ int rwsem_is_locked(struct rw_semaphore *sem)
 	unsigned long flags;
 
 	if (raw_spin_trylock_irqsave(&sem->wait_lock, flags)) {
-		ret = (sem->activity != 0);
+		ret = (sem->count != 0);
 		raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
 	}
 	return ret;
@@ -46,7 +46,7 @@ void __init_rwsem(struct rw_semaphore *sem, const char *name,
 	debug_check_no_locks_freed((void *)sem, sizeof(*sem));
 	lockdep_init_map(&sem->dep_map, name, key, 0);
 #endif
-	sem->activity = 0;
+	sem->count = 0;
 	raw_spin_lock_init(&sem->wait_lock);
 	INIT_LIST_HEAD(&sem->wait_list);
 }
@@ -95,7 +95,7 @@ __rwsem_do_wake(struct rw_semaphore *sem, int wakewrite)
 		waiter = list_entry(next, struct rwsem_waiter, list);
 	} while (waiter->type != RWSEM_WAITING_FOR_WRITE);
 
-	sem->activity += woken;
+	sem->count += woken;
 
  out:
 	return sem;
@@ -126,9 +126,9 @@ void __sched __down_read(struct rw_semaphore *sem)
 
 	raw_spin_lock_irqsave(&sem->wait_lock, flags);
 
-	if (sem->activity >= 0 && list_empty(&sem->wait_list)) {
+	if (sem->count >= 0 && list_empty(&sem->wait_list)) {
 		/* granted */
-		sem->activity++;
+		sem->count++;
 		raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
 		goto out;
 	}
@@ -170,9 +170,9 @@ int __down_read_trylock(struct rw_semaphore *sem)
 
 	raw_spin_lock_irqsave(&sem->wait_lock, flags);
 
-	if (sem->activity >= 0 && list_empty(&sem->wait_list)) {
+	if (sem->count >= 0 && list_empty(&sem->wait_list)) {
 		/* granted */
-		sem->activity++;
+		sem->count++;
 		ret = 1;
 	}
 
@@ -206,7 +206,7 @@ void __sched __down_write_nested(struct rw_semaphore *sem, int subclass)
 		 * itself into sleep and waiting for system woke it or someone
 		 * else in the head of the wait list up.
 		 */
-		if (sem->activity == 0)
+		if (sem->count == 0)
 			break;
 		set_task_state(tsk, TASK_UNINTERRUPTIBLE);
 		raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
@@ -214,7 +214,7 @@ void __sched __down_write_nested(struct rw_semaphore *sem, int subclass)
 		raw_spin_lock_irqsave(&sem->wait_lock, flags);
 	}
 	/* got the lock */
-	sem->activity = -1;
+	sem->count = -1;
 	list_del(&waiter.list);
 
 	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
@@ -235,9 +235,9 @@ int __down_write_trylock(struct rw_semaphore *sem)
 
 	raw_spin_lock_irqsave(&sem->wait_lock, flags);
 
-	if (sem->activity == 0) {
+	if (sem->count == 0) {
 		/* got the lock */
-		sem->activity = -1;
+		sem->count = -1;
 		ret = 1;
 	}
 
@@ -255,7 +255,7 @@ void __up_read(struct rw_semaphore *sem)
 
 	raw_spin_lock_irqsave(&sem->wait_lock, flags);
 
-	if (--sem->activity == 0 && !list_empty(&sem->wait_list))
+	if (--sem->count == 0 && !list_empty(&sem->wait_list))
 		sem = __rwsem_wake_one_writer(sem);
 
 	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
@@ -270,7 +270,7 @@ void __up_write(struct rw_semaphore *sem)
 
 	raw_spin_lock_irqsave(&sem->wait_lock, flags);
 
-	sem->activity = 0;
+	sem->count = 0;
 	if (!list_empty(&sem->wait_list))
 		sem = __rwsem_do_wake(sem, 1);
 
@@ -287,7 +287,7 @@ void __downgrade_write(struct rw_semaphore *sem)
 
 	raw_spin_lock_irqsave(&sem->wait_lock, flags);
 
-	sem->activity = 1;
+	sem->count = 1;
 	if (!list_empty(&sem->wait_list))
 		sem = __rwsem_do_wake(sem, 0);
 
diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
index dacc32142fc..a2391ac135c 100644
--- a/kernel/locking/rwsem-xadd.c
+++ b/kernel/locking/rwsem-xadd.c
@@ -82,9 +82,9 @@ void __init_rwsem(struct rw_semaphore *sem, const char *name,
 	sem->count = RWSEM_UNLOCKED_VALUE;
 	raw_spin_lock_init(&sem->wait_lock);
 	INIT_LIST_HEAD(&sem->wait_list);
-#ifdef CONFIG_SMP
+#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
 	sem->owner = NULL;
-	sem->osq = NULL;
+	osq_lock_init(&sem->osq);
 #endif
 }
 
@@ -262,7 +262,7 @@ static inline bool rwsem_try_write_lock(long count, struct rw_semaphore *sem)
 	return false;
 }
 
-#ifdef CONFIG_SMP
+#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
 /*
  * Try to acquire write lock before the writer has been put on wait queue.
  */
@@ -285,10 +285,10 @@ static inline bool rwsem_try_write_lock_unqueued(struct rw_semaphore *sem)
 static inline bool rwsem_can_spin_on_owner(struct rw_semaphore *sem)
 {
 	struct task_struct *owner;
-	bool on_cpu = true;
+	bool on_cpu = false;
 
 	if (need_resched())
-		return 0;
+		return false;
 
 	rcu_read_lock();
 	owner = ACCESS_ONCE(sem->owner);
@@ -297,9 +297,9 @@ static inline bool rwsem_can_spin_on_owner(struct rw_semaphore *sem)
 	rcu_read_unlock();
 
 	/*
-	 * If sem->owner is not set, the rwsem owner may have
-	 * just acquired it and not set the owner yet or the rwsem
-	 * has been released.
+	 * If sem->owner is not set, yet we have just recently entered the
+	 * slowpath, then there is a possibility reader(s) may have the lock.
+	 * To be safe, avoid spinning in these situations.
 	 */
 	return on_cpu;
 }
diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index 42f806de49d..e2d3bc7f03b 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -12,7 +12,7 @@
 
 #include <linux/atomic.h>
 
-#if defined(CONFIG_SMP) && defined(CONFIG_RWSEM_XCHGADD_ALGORITHM)
+#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
 static inline void rwsem_set_owner(struct rw_semaphore *sem)
 {
 	sem->owner = current;
diff --git a/kernel/power/process.c b/kernel/power/process.c
index 0ca8d83e236..4ee194eb524 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -186,6 +186,7 @@ void thaw_processes(void)
 
 	printk("Restarting tasks ... ");
 
+	__usermodehelper_set_disable_depth(UMH_FREEZING);
 	thaw_workqueues();
 
 	read_lock(&tasklist_lock);
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 4dd8822f732..ed35a4790af 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -306,7 +306,7 @@ int suspend_devices_and_enter(suspend_state_t state)
 		error = suspend_ops->begin(state);
 		if (error)
 			goto Close;
-	} else if (state == PM_SUSPEND_FREEZE && freeze_ops->begin) {
+	} else if (state == PM_SUSPEND_FREEZE && freeze_ops && freeze_ops->begin) {
 		error = freeze_ops->begin();
 		if (error)
 			goto Close;
@@ -335,7 +335,7 @@ int suspend_devices_and_enter(suspend_state_t state)
  Close:
 	if (need_suspend_ops(state) && suspend_ops->end)
 		suspend_ops->end();
-	else if (state == PM_SUSPEND_FREEZE && freeze_ops->end)
+	else if (state == PM_SUSPEND_FREEZE && freeze_ops && freeze_ops->end)
 		freeze_ops->end();
 
 	return error;
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index ea2d5f6962e..13e839dbca0 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -1416,9 +1416,10 @@ static int have_callable_console(void)
 /*
  * Can we actually use the console at this time on this cpu?
  *
- * Console drivers may assume that per-cpu resources have been allocated. So
- * unless they're explicitly marked as being able to cope (CON_ANYTIME) don't
- * call them until this CPU is officially up.
+ * Console drivers may assume that per-cpu resources have
+ * been allocated. So unless they're explicitly marked as
+ * being able to cope (CON_ANYTIME) don't call them until
+ * this CPU is officially up.
  */
 static inline int can_use_console(unsigned int cpu)
 {
@@ -1431,10 +1432,8 @@ static inline int can_use_console(unsigned int cpu)
  * console_lock held, and 'console_locked' set) if it
  * is successful, false otherwise.
  */
-static int console_trylock_for_printk(void)
+static int console_trylock_for_printk(unsigned int cpu)
 {
-	unsigned int cpu = smp_processor_id();
-
 	if (!console_trylock())
 		return 0;
 	/*
@@ -1609,8 +1608,7 @@ asmlinkage int vprintk_emit(int facility, int level,
 		 */
 		if (!oops_in_progress && !lockdep_recursing(current)) {
 			recursion_bug = 1;
-			local_irq_restore(flags);
-			return 0;
+			goto out_restore_irqs;
 		}
 		zap_locks();
 	}
@@ -1718,27 +1716,21 @@ asmlinkage int vprintk_emit(int facility, int level,
 
 	logbuf_cpu = UINT_MAX;
 	raw_spin_unlock(&logbuf_lock);
-	lockdep_on();
-	local_irq_restore(flags);
 
 	/* If called from the scheduler, we can not call up(). */
-	if (in_sched)
-		return printed_len;
-
-	/*
-	 * Disable preemption to avoid being preempted while holding
-	 * console_sem which would prevent anyone from printing to console
-	 */
-	preempt_disable();
-	/*
-	 * Try to acquire and then immediately release the console semaphore.
-	 * The release will print out buffers and wake up /dev/kmsg and syslog()
-	 * users.
-	 */
-	if (console_trylock_for_printk())
-		console_unlock();
-	preempt_enable();
+	if (!in_sched) {
+		/*
+		 * Try to acquire and then immediately release the console
+		 * semaphore.  The release will print out buffers and wake up
+		 * /dev/kmsg and syslog() users.
+		 */
+		if (console_trylock_for_printk(this_cpu))
+			console_unlock();
+	}
 
+	lockdep_on();
+out_restore_irqs:
+	local_irq_restore(flags);
 	return printed_len;
 }
 EXPORT_SYMBOL(vprintk_emit);
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index f1ba77363fb..625d0b0cd75 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -206,6 +206,70 @@ void rcu_bh_qs(int cpu)
 	rdp->passed_quiesce = 1;
 }
 
+static DEFINE_PER_CPU(int, rcu_sched_qs_mask);
+
+static DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = {
+	.dynticks_nesting = DYNTICK_TASK_EXIT_IDLE,
+	.dynticks = ATOMIC_INIT(1),
+#ifdef CONFIG_NO_HZ_FULL_SYSIDLE
+	.dynticks_idle_nesting = DYNTICK_TASK_NEST_VALUE,
+	.dynticks_idle = ATOMIC_INIT(1),
+#endif /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */
+};
+
+/*
+ * Let the RCU core know that this CPU has gone through the scheduler,
+ * which is a quiescent state.  This is called when the need for a
+ * quiescent state is urgent, so we burn an atomic operation and full
+ * memory barriers to let the RCU core know about it, regardless of what
+ * this CPU might (or might not) do in the near future.
+ *
+ * We inform the RCU core by emulating a zero-duration dyntick-idle
+ * period, which we in turn do by incrementing the ->dynticks counter
+ * by two.
+ */
+static void rcu_momentary_dyntick_idle(void)
+{
+	unsigned long flags;
+	struct rcu_data *rdp;
+	struct rcu_dynticks *rdtp;
+	int resched_mask;
+	struct rcu_state *rsp;
+
+	local_irq_save(flags);
+
+	/*
+	 * Yes, we can lose flag-setting operations.  This is OK, because
+	 * the flag will be set again after some delay.
+	 */
+	resched_mask = raw_cpu_read(rcu_sched_qs_mask);
+	raw_cpu_write(rcu_sched_qs_mask, 0);
+
+	/* Find the flavor that needs a quiescent state. */
+	for_each_rcu_flavor(rsp) {
+		rdp = raw_cpu_ptr(rsp->rda);
+		if (!(resched_mask & rsp->flavor_mask))
+			continue;
+		smp_mb(); /* rcu_sched_qs_mask before cond_resched_completed. */
+		if (ACCESS_ONCE(rdp->mynode->completed) !=
+		    ACCESS_ONCE(rdp->cond_resched_completed))
+			continue;
+
+		/*
+		 * Pretend to be momentarily idle for the quiescent state.
+		 * This allows the grace-period kthread to record the
+		 * quiescent state, with no need for this CPU to do anything
+		 * further.
+		 */
+		rdtp = this_cpu_ptr(&rcu_dynticks);
+		smp_mb__before_atomic(); /* Earlier stuff before QS. */
+		atomic_add(2, &rdtp->dynticks);  /* QS. */
+		smp_mb__after_atomic(); /* Later stuff after QS. */
+		break;
+	}
+	local_irq_restore(flags);
+}
+
 /*
  * Note a context switch.  This is a quiescent state for RCU-sched,
  * and requires special handling for preemptible RCU.
@@ -216,19 +280,12 @@ void rcu_note_context_switch(int cpu)
 	trace_rcu_utilization(TPS("Start context switch"));
 	rcu_sched_qs(cpu);
 	rcu_preempt_note_context_switch(cpu);
+	if (unlikely(raw_cpu_read(rcu_sched_qs_mask)))
+		rcu_momentary_dyntick_idle();
 	trace_rcu_utilization(TPS("End context switch"));
 }
 EXPORT_SYMBOL_GPL(rcu_note_context_switch);
 
-static DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = {
-	.dynticks_nesting = DYNTICK_TASK_EXIT_IDLE,
-	.dynticks = ATOMIC_INIT(1),
-#ifdef CONFIG_NO_HZ_FULL_SYSIDLE
-	.dynticks_idle_nesting = DYNTICK_TASK_NEST_VALUE,
-	.dynticks_idle = ATOMIC_INIT(1),
-#endif /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */
-};
-
 static long blimit = 10;	/* Maximum callbacks per rcu_do_batch. */
 static long qhimark = 10000;	/* If this many pending, ignore blimit. */
 static long qlowmark = 100;	/* Once only this many pending, use blimit. */
@@ -243,6 +300,13 @@ static ulong jiffies_till_next_fqs = ULONG_MAX;
 module_param(jiffies_till_first_fqs, ulong, 0644);
 module_param(jiffies_till_next_fqs, ulong, 0644);
 
+/*
+ * How long the grace period must be before we start recruiting
+ * quiescent-state help from rcu_note_context_switch().
+ */
+static ulong jiffies_till_sched_qs = HZ / 20;
+module_param(jiffies_till_sched_qs, ulong, 0644);
+
 static bool rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp,
 				  struct rcu_data *rdp);
 static void force_qs_rnp(struct rcu_state *rsp,
@@ -853,6 +917,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp,
 				    bool *isidle, unsigned long *maxj)
 {
 	unsigned int curr;
+	int *rcrmp;
 	unsigned int snap;
 
 	curr = (unsigned int)atomic_add_return(0, &rdp->dynticks->dynticks);
@@ -893,27 +958,43 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp,
 	}
 
 	/*
-	 * There is a possibility that a CPU in adaptive-ticks state
-	 * might run in the kernel with the scheduling-clock tick disabled
-	 * for an extended time period.  Invoke rcu_kick_nohz_cpu() to
-	 * force the CPU to restart the scheduling-clock tick in this
-	 * CPU is in this state.
-	 */
-	rcu_kick_nohz_cpu(rdp->cpu);
-
-	/*
-	 * Alternatively, the CPU might be running in the kernel
-	 * for an extended period of time without a quiescent state.
-	 * Attempt to force the CPU through the scheduler to gain the
-	 * needed quiescent state, but only if the grace period has gone
-	 * on for an uncommonly long time.  If there are many stuck CPUs,
-	 * we will beat on the first one until it gets unstuck, then move
-	 * to the next.  Only do this for the primary flavor of RCU.
+	 * A CPU running for an extended time within the kernel can
+	 * delay RCU grace periods.  When the CPU is in NO_HZ_FULL mode,
+	 * even context-switching back and forth between a pair of
+	 * in-kernel CPU-bound tasks cannot advance grace periods.
+	 * So if the grace period is old enough, make the CPU pay attention.
+	 * Note that the unsynchronized assignments to the per-CPU
+	 * rcu_sched_qs_mask variable are safe.  Yes, setting of
+	 * bits can be lost, but they will be set again on the next
+	 * force-quiescent-state pass.  So lost bit sets do not result
+	 * in incorrect behavior, merely in a grace period lasting
+	 * a few jiffies longer than it might otherwise.  Because
+	 * there are at most four threads involved, and because the
+	 * updates are only once every few jiffies, the probability of
+	 * lossage (and thus of slight grace-period extension) is
+	 * quite low.
+	 *
+	 * Note that if the jiffies_till_sched_qs boot/sysfs parameter
+	 * is set too high, we override with half of the RCU CPU stall
+	 * warning delay.
 	 */
-	if (rdp->rsp == rcu_state_p &&
+	rcrmp = &per_cpu(rcu_sched_qs_mask, rdp->cpu);
+	if (ULONG_CMP_GE(jiffies,
+			 rdp->rsp->gp_start + jiffies_till_sched_qs) ||
 	    ULONG_CMP_GE(jiffies, rdp->rsp->jiffies_resched)) {
-		rdp->rsp->jiffies_resched += 5;
-		resched_cpu(rdp->cpu);
+		if (!(ACCESS_ONCE(*rcrmp) & rdp->rsp->flavor_mask)) {
+			ACCESS_ONCE(rdp->cond_resched_completed) =
+				ACCESS_ONCE(rdp->mynode->completed);
+			smp_mb(); /* ->cond_resched_completed before *rcrmp. */
+			ACCESS_ONCE(*rcrmp) =
+				ACCESS_ONCE(*rcrmp) + rdp->rsp->flavor_mask;
+			resched_cpu(rdp->cpu);  /* Force CPU into scheduler. */
+			rdp->rsp->jiffies_resched += 5; /* Enable beating. */
+		} else if (ULONG_CMP_GE(jiffies, rdp->rsp->jiffies_resched)) {
+			/* Time to beat on that CPU again! */
+			resched_cpu(rdp->cpu);  /* Force CPU into scheduler. */
+			rdp->rsp->jiffies_resched += 5; /* Re-enable beating. */
+		}
 	}
 
 	return 0;
@@ -3491,6 +3572,7 @@ static void __init rcu_init_one(struct rcu_state *rsp,
 			       "rcu_node_fqs_1",
 			       "rcu_node_fqs_2",
 			       "rcu_node_fqs_3" };  /* Match MAX_RCU_LVLS */
+	static u8 fl_mask = 0x1;
 	int cpustride = 1;
 	int i;
 	int j;
@@ -3509,6 +3591,8 @@ static void __init rcu_init_one(struct rcu_state *rsp,
 	for (i = 1; i < rcu_num_lvls; i++)
 		rsp->level[i] = rsp->level[i - 1] + rsp->levelcnt[i - 1];
 	rcu_init_levelspread(rsp);
+	rsp->flavor_mask = fl_mask;
+	fl_mask <<= 1;
 
 	/* Initialize the elements themselves, starting from the leaves. */
 
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index bf2c1e66969..0f69a79c5b7 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -307,6 +307,9 @@ struct rcu_data {
 	/* 4) reasons this CPU needed to be kicked by force_quiescent_state */
 	unsigned long dynticks_fqs;	/* Kicked due to dynticks idle. */
 	unsigned long offline_fqs;	/* Kicked due to being offline. */
+	unsigned long cond_resched_completed;
+					/* Grace period that needs help */
+					/*  from cond_resched(). */
 
 	/* 5) __rcu_pending() statistics. */
 	unsigned long n_rcu_pending;	/* rcu_pending() calls since boot. */
@@ -392,6 +395,7 @@ struct rcu_state {
 	struct rcu_node *level[RCU_NUM_LVLS];	/* Hierarchy levels. */
 	u32 levelcnt[MAX_RCU_LVLS + 1];		/* # nodes in each level. */
 	u8 levelspread[RCU_NUM_LVLS];		/* kids/node in each level. */
+	u8 flavor_mask;				/* bit in flavor mask. */
 	struct rcu_data __percpu *rda;		/* pointer of percu rcu_data. */
 	void (*call)(struct rcu_head *head,	/* call_rcu() flavor. */
 		     void (*func)(struct rcu_head *head));
@@ -563,7 +567,7 @@ static bool rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp);
 static void do_nocb_deferred_wakeup(struct rcu_data *rdp);
 static void rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp);
 static void rcu_spawn_nocb_kthreads(struct rcu_state *rsp);
-static void rcu_kick_nohz_cpu(int cpu);
+static void __maybe_unused rcu_kick_nohz_cpu(int cpu);
 static bool init_nocb_callback_list(struct rcu_data *rdp);
 static void rcu_sysidle_enter(struct rcu_dynticks *rdtp, int irq);
 static void rcu_sysidle_exit(struct rcu_dynticks *rdtp, int irq);
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index cbc2c45265e..02ac0fb186b 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -2404,7 +2404,7 @@ static bool init_nocb_callback_list(struct rcu_data *rdp)
  * if an adaptive-ticks CPU is failing to respond to the current grace
  * period and has not be idle from an RCU perspective, kick it.
  */
-static void rcu_kick_nohz_cpu(int cpu)
+static void __maybe_unused rcu_kick_nohz_cpu(int cpu)
 {
 #ifdef CONFIG_NO_HZ_FULL
 	if (tick_nohz_full_cpu(cpu))
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index a2aeb4df0f6..bc788357053 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -200,12 +200,12 @@ void wait_rcu_gp(call_rcu_func_t crf)
 EXPORT_SYMBOL_GPL(wait_rcu_gp);
 
 #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD
-static inline void debug_init_rcu_head(struct rcu_head *head)
+void init_rcu_head(struct rcu_head *head)
 {
 	debug_object_init(head, &rcuhead_debug_descr);
 }
 
-static inline void debug_rcu_head_free(struct rcu_head *head)
+void destroy_rcu_head(struct rcu_head *head)
 {
 	debug_object_free(head, &rcuhead_debug_descr);
 }
@@ -350,21 +350,3 @@ static int __init check_cpu_stall_init(void)
 early_initcall(check_cpu_stall_init);
 
 #endif /* #ifdef CONFIG_RCU_STALL_COMMON */
-
-/*
- * Hooks for cond_resched() and friends to avoid RCU CPU stall warnings.
- */
-
-DEFINE_PER_CPU(int, rcu_cond_resched_count);
-
-/*
- * Report a set of RCU quiescent states, for use by cond_resched()
- * and friends.  Out of line due to being called infrequently.
- */
-void rcu_resched(void)
-{
-	preempt_disable();
-	__this_cpu_write(rcu_cond_resched_count, 0);
-	rcu_note_context_switch(smp_processor_id());
-	preempt_enable();
-}
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 3bdf01b494f..bc1638b3344 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4147,7 +4147,6 @@ static void __cond_resched(void)
 
 int __sched _cond_resched(void)
 {
-	rcu_cond_resched();
 	if (should_resched()) {
 		__cond_resched();
 		return 1;
@@ -4166,18 +4165,15 @@ EXPORT_SYMBOL(_cond_resched);
  */
 int __cond_resched_lock(spinlock_t *lock)
 {
-	bool need_rcu_resched = rcu_should_resched();
 	int resched = should_resched();
 	int ret = 0;
 
 	lockdep_assert_held(lock);
 
-	if (spin_needbreak(lock) || resched || need_rcu_resched) {
+	if (spin_needbreak(lock) || resched) {
 		spin_unlock(lock);
 		if (resched)
 			__cond_resched();
-		else if (unlikely(need_rcu_resched))
-			rcu_resched();
 		else
 			cpu_relax();
 		ret = 1;
@@ -4191,7 +4187,6 @@ int __sched __cond_resched_softirq(void)
 {
 	BUG_ON(!in_softirq());
 
-	rcu_cond_resched();  /* BH disabled OK, just recording QSes. */
 	if (should_resched()) {
 		local_bh_enable();
 		__cond_resched();
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 695f9773bb6..627b3c34b82 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -608,7 +608,7 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
 
 		avg_atom = p->se.sum_exec_runtime;
 		if (nr_switches)
-			do_div(avg_atom, nr_switches);
+			avg_atom = div64_ul(avg_atom, nr_switches);
 		else
 			avg_atom = -1LL;
 
diff --git a/kernel/smp.c b/kernel/smp.c
index 306f8180b0d..80c33f8de14 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -29,6 +29,8 @@ static DEFINE_PER_CPU_SHARED_ALIGNED(struct call_function_data, cfd_data);
 
 static DEFINE_PER_CPU_SHARED_ALIGNED(struct llist_head, call_single_queue);
 
+static void flush_smp_call_function_queue(bool warn_cpu_offline);
+
 static int
 hotplug_cfd(struct notifier_block *nfb, unsigned long action, void *hcpu)
 {
@@ -51,12 +53,27 @@ hotplug_cfd(struct notifier_block *nfb, unsigned long action, void *hcpu)
 #ifdef CONFIG_HOTPLUG_CPU
 	case CPU_UP_CANCELED:
 	case CPU_UP_CANCELED_FROZEN:
+		/* Fall-through to the CPU_DEAD[_FROZEN] case. */
 
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN:
 		free_cpumask_var(cfd->cpumask);
 		free_percpu(cfd->csd);
 		break;
+
+	case CPU_DYING:
+	case CPU_DYING_FROZEN:
+		/*
+		 * The IPIs for the smp-call-function callbacks queued by other
+		 * CPUs might arrive late, either due to hardware latencies or
+		 * because this CPU disabled interrupts (inside stop-machine)
+		 * before the IPIs were sent. So flush out any pending callbacks
+		 * explicitly (without waiting for the IPIs to arrive), to
+		 * ensure that the outgoing CPU doesn't go offline with work
+		 * still pending.
+		 */
+		flush_smp_call_function_queue(false);
+		break;
 #endif
 	};
 
@@ -177,23 +194,47 @@ static int generic_exec_single(int cpu, struct call_single_data *csd,
 	return 0;
 }
 
-/*
- * Invoked by arch to handle an IPI for call function single. Must be
- * called from the arch with interrupts disabled.
+/**
+ * generic_smp_call_function_single_interrupt - Execute SMP IPI callbacks
+ *
+ * Invoked by arch to handle an IPI for call function single.
+ * Must be called with interrupts disabled.
  */
 void generic_smp_call_function_single_interrupt(void)
 {
+	flush_smp_call_function_queue(true);
+}
+
+/**
+ * flush_smp_call_function_queue - Flush pending smp-call-function callbacks
+ *
+ * @warn_cpu_offline: If set to 'true', warn if callbacks were queued on an
+ *		      offline CPU. Skip this check if set to 'false'.
+ *
+ * Flush any pending smp-call-function callbacks queued on this CPU. This is
+ * invoked by the generic IPI handler, as well as by a CPU about to go offline,
+ * to ensure that all pending IPI callbacks are run before it goes completely
+ * offline.
+ *
+ * Loop through the call_single_queue and run all the queued callbacks.
+ * Must be called with interrupts disabled.
+ */
+static void flush_smp_call_function_queue(bool warn_cpu_offline)
+{
+	struct llist_head *head;
 	struct llist_node *entry;
 	struct call_single_data *csd, *csd_next;
 	static bool warned;
 
-	entry = llist_del_all(&__get_cpu_var(call_single_queue));
+	WARN_ON(!irqs_disabled());
+
+	head = &__get_cpu_var(call_single_queue);
+	entry = llist_del_all(head);
 	entry = llist_reverse_order(entry);
 
-	/*
-	 * Shouldn't receive this interrupt on a cpu that is not yet online.
-	 */
-	if (unlikely(!cpu_online(smp_processor_id()) && !warned)) {
+	/* There shouldn't be any pending callbacks on an offline CPU. */
+	if (unlikely(warn_cpu_offline && !cpu_online(smp_processor_id()) &&
+		     !warned && !llist_empty(head))) {
 		warned = true;
 		WARN(1, "IPI on offline CPU %d\n", smp_processor_id());
 
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 7de6555cfea..75b22e22a72 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -136,7 +136,6 @@ static unsigned long dirty_bytes_min = 2 * PAGE_SIZE;
 /* this is needed for the proc_dointvec_minmax for [fs_]overflow UID and GID */
 static int maxolduid = 65535;
 static int minolduid;
-static int min_percpu_pagelist_fract = 8;
 
 static int ngroups_max = NGROUPS_MAX;
 static const int cap_last_cap = CAP_LAST_CAP;
@@ -861,6 +860,17 @@ static struct ctl_table kern_table[] = {
 		.extra1		= &zero,
 		.extra2		= &one,
 	},
+#ifdef CONFIG_SMP
+	{
+		.procname	= "softlockup_all_cpu_backtrace",
+		.data		= &sysctl_softlockup_all_cpu_backtrace,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &one,
+	},
+#endif /* CONFIG_SMP */
 	{
 		.procname       = "nmi_watchdog",
 		.data           = &watchdog_user_enabled,
@@ -1317,7 +1327,7 @@ static struct ctl_table vm_table[] = {
 		.maxlen		= sizeof(percpu_pagelist_fraction),
 		.mode		= 0644,
 		.proc_handler	= percpu_pagelist_fraction_sysctl_handler,
-		.extra1		= &min_percpu_pagelist_fract,
+		.extra1		= &zero,
 	},
 #ifdef CONFIG_MMU
 	{
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index 88c9c65a430..fe75444ae7e 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -585,9 +585,14 @@ static int alarm_timer_set(struct k_itimer *timr, int flags,
 				struct itimerspec *new_setting,
 				struct itimerspec *old_setting)
 {
+	ktime_t exp;
+
 	if (!rtcdev)
 		return -ENOTSUPP;
 
+	if (flags & ~TIMER_ABSTIME)
+		return -EINVAL;
+
 	if (old_setting)
 		alarm_timer_get(timr, old_setting);
 
@@ -597,8 +602,16 @@ static int alarm_timer_set(struct k_itimer *timr, int flags,
 
 	/* start the timer */
 	timr->it.alarm.interval = timespec_to_ktime(new_setting->it_interval);
-	alarm_start(&timr->it.alarm.alarmtimer,
-			timespec_to_ktime(new_setting->it_value));
+	exp = timespec_to_ktime(new_setting->it_value);
+	/* Convert (if necessary) to absolute time */
+	if (flags != TIMER_ABSTIME) {
+		ktime_t now;
+
+		now = alarm_bases[timr->it.alarm.alarmtimer.type].gettime();
+		exp = ktime_add(now, exp);
+	}
+
+	alarm_start(&timr->it.alarm.alarmtimer, exp);
 	return 0;
 }
 
@@ -730,6 +743,9 @@ static int alarm_timer_nsleep(const clockid_t which_clock, int flags,
 	if (!alarmtimer_get_rtcdev())
 		return -ENOTSUPP;
 
+	if (flags & ~TIMER_ABSTIME)
+		return -EINVAL;
+
 	if (!capable(CAP_WAKE_ALARM))
 		return -EPERM;
 
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 5b372e3ed67..ac9d1dad630 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -265,12 +265,12 @@ static void update_ftrace_function(void)
 		func = ftrace_ops_list_func;
 	}
 
+	update_function_graph_func();
+
 	/* If there's no change, then do nothing more here */
 	if (ftrace_trace_function == func)
 		return;
 
-	update_function_graph_func();
-
 	/*
 	 * If we are using the list function, it doesn't care
 	 * about the function_trace_ops.
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 7c56c3d0694..ff7027199a9 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -616,10 +616,6 @@ int ring_buffer_poll_wait(struct ring_buffer *buffer, int cpu,
 	struct ring_buffer_per_cpu *cpu_buffer;
 	struct rb_irq_work *work;
 
-	if ((cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer)) ||
-	    (cpu != RING_BUFFER_ALL_CPUS && !ring_buffer_empty_cpu(buffer, cpu)))
-		return POLLIN | POLLRDNORM;
-
 	if (cpu == RING_BUFFER_ALL_CPUS)
 		work = &buffer->irq_work;
 	else {
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 384ede31171..291397e6666 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -466,6 +466,12 @@ int __trace_puts(unsigned long ip, const char *str, int size)
 	struct print_entry *entry;
 	unsigned long irq_flags;
 	int alloc;
+	int pc;
+
+	if (!(trace_flags & TRACE_ITER_PRINTK))
+		return 0;
+
+	pc = preempt_count();
 
 	if (unlikely(tracing_selftest_running || tracing_disabled))
 		return 0;
@@ -475,7 +481,7 @@ int __trace_puts(unsigned long ip, const char *str, int size)
 	local_save_flags(irq_flags);
 	buffer = global_trace.trace_buffer.buffer;
 	event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, alloc, 
-					  irq_flags, preempt_count());
+					  irq_flags, pc);
 	if (!event)
 		return 0;
 
@@ -492,6 +498,7 @@ int __trace_puts(unsigned long ip, const char *str, int size)
 		entry->buf[size] = '\0';
 
 	__buffer_unlock_commit(buffer, event);
+	ftrace_trace_stack(buffer, irq_flags, 4, pc);
 
 	return size;
 }
@@ -509,6 +516,12 @@ int __trace_bputs(unsigned long ip, const char *str)
 	struct bputs_entry *entry;
 	unsigned long irq_flags;
 	int size = sizeof(struct bputs_entry);
+	int pc;
+
+	if (!(trace_flags & TRACE_ITER_PRINTK))
+		return 0;
+
+	pc = preempt_count();
 
 	if (unlikely(tracing_selftest_running || tracing_disabled))
 		return 0;
@@ -516,7 +529,7 @@ int __trace_bputs(unsigned long ip, const char *str)
 	local_save_flags(irq_flags);
 	buffer = global_trace.trace_buffer.buffer;
 	event = trace_buffer_lock_reserve(buffer, TRACE_BPUTS, size,
-					  irq_flags, preempt_count());
+					  irq_flags, pc);
 	if (!event)
 		return 0;
 
@@ -525,6 +538,7 @@ int __trace_bputs(unsigned long ip, const char *str)
 	entry->str			= str;
 
 	__buffer_unlock_commit(buffer, event);
+	ftrace_trace_stack(buffer, irq_flags, 4, pc);
 
 	return 1;
 }
@@ -809,7 +823,7 @@ static struct {
 	{ trace_clock_local,	"local",	1 },
 	{ trace_clock_global,	"global",	1 },
 	{ trace_clock_counter,	"counter",	0 },
-	{ trace_clock_jiffies,	"uptime",	1 },
+	{ trace_clock_jiffies,	"uptime",	0 },
 	{ trace_clock,		"perf",		1 },
 	ARCH_TRACE_CLOCKS
 };
@@ -1396,7 +1410,6 @@ void tracing_start(void)
 
 	arch_spin_unlock(&global_trace.max_lock);
 
-	ftrace_start();
  out:
 	raw_spin_unlock_irqrestore(&global_trace.start_lock, flags);
 }
@@ -1443,7 +1456,6 @@ void tracing_stop(void)
 	struct ring_buffer *buffer;
 	unsigned long flags;
 
-	ftrace_stop();
 	raw_spin_lock_irqsave(&global_trace.start_lock, flags);
 	if (global_trace.stop_count++)
 		goto out;
diff --git a/kernel/trace/trace_clock.c b/kernel/trace/trace_clock.c
index 26dc348332b..57b67b1f24d 100644
--- a/kernel/trace/trace_clock.c
+++ b/kernel/trace/trace_clock.c
@@ -59,13 +59,14 @@ u64 notrace trace_clock(void)
 
 /*
  * trace_jiffy_clock(): Simply use jiffies as a clock counter.
+ * Note that this use of jiffies_64 is not completely safe on
+ * 32-bit systems. But the window is tiny, and the effect if
+ * we are affected is that we will have an obviously bogus
+ * timestamp on a trace event - i.e. not life threatening.
  */
 u64 notrace trace_clock_jiffies(void)
 {
-	u64 jiffy = jiffies - INITIAL_JIFFIES;
-
-	/* Return nsecs */
-	return (u64)jiffies_to_usecs(jiffy) * 1000ULL;
+	return jiffies_64_to_clock_t(jiffies_64 - INITIAL_JIFFIES);
 }
 
 /*
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index f99e0b3bca8..2de53628689 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -470,6 +470,7 @@ static void remove_event_file_dir(struct ftrace_event_file *file)
 
 	list_del(&file->list);
 	remove_subsystem(file->system);
+	free_event_filter(file->filter);
 	kmem_cache_free(file_cachep, file);
 }
 
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 04fdb5de823..3c9b97e6b1f 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -893,6 +893,9 @@ probe_event_enable(struct trace_uprobe *tu, struct ftrace_event_file *file,
 	int ret;
 
 	if (file) {
+		if (tu->tp.flags & TP_FLAG_PROFILE)
+			return -EINTR;
+
 		link = kmalloc(sizeof(*link), GFP_KERNEL);
 		if (!link)
 			return -ENOMEM;
@@ -901,29 +904,40 @@ probe_event_enable(struct trace_uprobe *tu, struct ftrace_event_file *file,
 		list_add_tail_rcu(&link->list, &tu->tp.files);
 
 		tu->tp.flags |= TP_FLAG_TRACE;
-	} else
-		tu->tp.flags |= TP_FLAG_PROFILE;
+	} else {
+		if (tu->tp.flags & TP_FLAG_TRACE)
+			return -EINTR;
 
-	ret = uprobe_buffer_enable();
-	if (ret < 0)
-		return ret;
+		tu->tp.flags |= TP_FLAG_PROFILE;
+	}
 
 	WARN_ON(!uprobe_filter_is_empty(&tu->filter));
 
 	if (enabled)
 		return 0;
 
+	ret = uprobe_buffer_enable();
+	if (ret)
+		goto err_flags;
+
 	tu->consumer.filter = filter;
 	ret = uprobe_register(tu->inode, tu->offset, &tu->consumer);
-	if (ret) {
-		if (file) {
-			list_del(&link->list);
-			kfree(link);
-			tu->tp.flags &= ~TP_FLAG_TRACE;
-		} else
-			tu->tp.flags &= ~TP_FLAG_PROFILE;
-	}
+	if (ret)
+		goto err_buffer;
 
+	return 0;
+
+ err_buffer:
+	uprobe_buffer_disable();
+
+ err_flags:
+	if (file) {
+		list_del(&link->list);
+		kfree(link);
+		tu->tp.flags &= ~TP_FLAG_TRACE;
+	} else {
+		tu->tp.flags &= ~TP_FLAG_PROFILE;
+	}
 	return ret;
 }
 
@@ -1201,12 +1215,6 @@ static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs)
 
 	current->utask->vaddr = (unsigned long) &udd;
 
-#ifdef CONFIG_PERF_EVENTS
-	if ((tu->tp.flags & TP_FLAG_TRACE) == 0 &&
-	    !uprobe_perf_filter(&tu->consumer, 0, current->mm))
-		return UPROBE_HANDLER_REMOVE;
-#endif
-
 	if (WARN_ON_ONCE(!uprobe_cpu_buffer))
 		return 0;
 
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index 33cbd8c203f..3490407dc7b 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -492,33 +492,29 @@ static int sys_tracepoint_refcount;
 
 void syscall_regfunc(void)
 {
-	unsigned long flags;
-	struct task_struct *g, *t;
+	struct task_struct *p, *t;
 
 	if (!sys_tracepoint_refcount) {
-		read_lock_irqsave(&tasklist_lock, flags);
-		do_each_thread(g, t) {
-			/* Skip kernel threads. */
-			if (t->mm)
-				set_tsk_thread_flag(t, TIF_SYSCALL_TRACEPOINT);
-		} while_each_thread(g, t);
-		read_unlock_irqrestore(&tasklist_lock, flags);
+		read_lock(&tasklist_lock);
+		for_each_process_thread(p, t) {
+			set_tsk_thread_flag(t, TIF_SYSCALL_TRACEPOINT);
+		}
+		read_unlock(&tasklist_lock);
 	}
 	sys_tracepoint_refcount++;
 }
 
 void syscall_unregfunc(void)
 {
-	unsigned long flags;
-	struct task_struct *g, *t;
+	struct task_struct *p, *t;
 
 	sys_tracepoint_refcount--;
 	if (!sys_tracepoint_refcount) {
-		read_lock_irqsave(&tasklist_lock, flags);
-		do_each_thread(g, t) {
+		read_lock(&tasklist_lock);
+		for_each_process_thread(p, t) {
 			clear_tsk_thread_flag(t, TIF_SYSCALL_TRACEPOINT);
-		} while_each_thread(g, t);
-		read_unlock_irqrestore(&tasklist_lock, flags);
+		}
+		read_unlock(&tasklist_lock);
 	}
 }
 #endif
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 516203e665f..c3319bd1b04 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -31,6 +31,12 @@
 
 int watchdog_user_enabled = 1;
 int __read_mostly watchdog_thresh = 10;
+#ifdef CONFIG_SMP
+int __read_mostly sysctl_softlockup_all_cpu_backtrace;
+#else
+#define sysctl_softlockup_all_cpu_backtrace 0
+#endif
+
 static int __read_mostly watchdog_running;
 static u64 __read_mostly sample_period;
 
@@ -47,6 +53,7 @@ static DEFINE_PER_CPU(bool, watchdog_nmi_touch);
 static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts_saved);
 static DEFINE_PER_CPU(struct perf_event *, watchdog_ev);
 #endif
+static unsigned long soft_lockup_nmi_warn;
 
 /* boot commands */
 /*
@@ -95,6 +102,15 @@ static int __init nosoftlockup_setup(char *str)
 }
 __setup("nosoftlockup", nosoftlockup_setup);
 /*  */
+#ifdef CONFIG_SMP
+static int __init softlockup_all_cpu_backtrace_setup(char *str)
+{
+	sysctl_softlockup_all_cpu_backtrace =
+		!!simple_strtol(str, NULL, 0);
+	return 1;
+}
+__setup("softlockup_all_cpu_backtrace=", softlockup_all_cpu_backtrace_setup);
+#endif
 
 /*
  * Hard-lockup warnings should be triggered after just a few seconds. Soft-
@@ -271,6 +287,7 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 	unsigned long touch_ts = __this_cpu_read(watchdog_touch_ts);
 	struct pt_regs *regs = get_irq_regs();
 	int duration;
+	int softlockup_all_cpu_backtrace = sysctl_softlockup_all_cpu_backtrace;
 
 	/* kick the hardlockup detector */
 	watchdog_interrupt_count();
@@ -317,6 +334,17 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 		if (__this_cpu_read(soft_watchdog_warn) == true)
 			return HRTIMER_RESTART;
 
+		if (softlockup_all_cpu_backtrace) {
+			/* Prevent multiple soft-lockup reports if one cpu is already
+			 * engaged in dumping cpu back traces
+			 */
+			if (test_and_set_bit(0, &soft_lockup_nmi_warn)) {
+				/* Someone else will report us. Let's give up */
+				__this_cpu_write(soft_watchdog_warn, true);
+				return HRTIMER_RESTART;
+			}
+		}
+
 		printk(KERN_EMERG "BUG: soft lockup - CPU#%d stuck for %us! [%s:%d]\n",
 			smp_processor_id(), duration,
 			current->comm, task_pid_nr(current));
@@ -327,6 +355,17 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 		else
 			dump_stack();
 
+		if (softlockup_all_cpu_backtrace) {
+			/* Avoid generating two back traces for current
+			 * given that one is already made above
+			 */
+			trigger_allbutself_cpu_backtrace();
+
+			clear_bit(0, &soft_lockup_nmi_warn);
+			/* Barrier to sync with other cpus */
+			smp_mb__after_atomic();
+		}
+
 		if (softlockup_panic)
 			panic("softlockup: hung tasks");
 		__this_cpu_write(soft_watchdog_warn, true);
@@ -527,10 +566,8 @@ static void update_timers_all_cpus(void)
 	int cpu;
 
 	get_online_cpus();
-	preempt_disable();
 	for_each_online_cpu(cpu)
 		update_timers(cpu);
-	preempt_enable();
 	put_online_cpus();
 }
 
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 6203d290087..35974ac6960 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -3284,6 +3284,7 @@ int workqueue_sysfs_register(struct workqueue_struct *wq)
 		}
 	}
 
+	dev_set_uevent_suppress(&wq_dev->dev, false);
 	kobject_uevent(&wq_dev->dev.kobj, KOBJ_ADD);
 	return 0;
 }
@@ -4879,7 +4880,7 @@ static void __init wq_numa_init(void)
 	BUG_ON(!tbl);
 
 	for_each_node(node)
-		BUG_ON(!alloc_cpumask_var_node(&tbl[node], GFP_KERNEL,
+		BUG_ON(!zalloc_cpumask_var_node(&tbl[node], GFP_KERNEL,
 				node_online(node) ? node : NUMA_NO_NODE));
 
 	for_each_possible_cpu(cpu) {