Merge branch 'linux-3.4.57' into rel-17

Bug 1348440

Change-Id: If25c49f027dc2a69642f7ed4733e965962b2a5a2
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>

30 files changed, 617 insertions, 265 deletions

diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index 31fdc480b5c6..0caf1f8de0fb 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -608,9 +608,9 @@ void audit_trim_trees(void)
 		}
 		spin_unlock(&hash_lock);
 		trim_marked(tree);
-		put_tree(tree);
 		drop_collected_mounts(root_mnt);
 skip_it:
+		put_tree(tree);
 		mutex_lock(&audit_filter_mutex);
 	}
 	list_del(&cursor);
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index ad447684aa47..9e4e81bc0d3f 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -2050,7 +2050,7 @@ static int cgroup_attach_proc(struct cgroup *cgrp, struct task_struct *leader)
 	if (!group)
 		return -ENOMEM;
 	/* pre-allocate to guarantee space while iterating in rcu read-side. */
-	retval = flex_array_prealloc(group, 0, group_size - 1, GFP_KERNEL);
+	retval = flex_array_prealloc(group, 0, group_size, GFP_KERNEL);
 	if (retval)
 		goto out_free_group_list;
 
diff --git a/kernel/cpu.c b/kernel/cpu.c
index acf5d8047458..ae08fe970529 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -125,6 +125,27 @@ static void cpu_hotplug_done(void)
 	mutex_unlock(&cpu_hotplug.lock);
 }
 
+/*
+ * Wait for currently running CPU hotplug operations to complete (if any) and
+ * disable future CPU hotplug (from sysfs). The 'cpu_add_remove_lock' protects
+ * the 'cpu_hotplug_disabled' flag. The same lock is also acquired by the
+ * hotplug path before performing hotplug operations. So acquiring that lock
+ * guarantees mutual exclusion from any currently running hotplug operations.
+ */
+void cpu_hotplug_disable(void)
+{
+	cpu_maps_update_begin();
+	cpu_hotplug_disabled = 1;
+	cpu_maps_update_done();
+}
+
+void cpu_hotplug_enable(void)
+{
+	cpu_maps_update_begin();
+	cpu_hotplug_disabled = 0;
+	cpu_maps_update_done();
+}
+
 #else /* #if CONFIG_HOTPLUG_CPU */
 static void cpu_hotplug_begin(void) {}
 static void cpu_hotplug_done(void) {}
@@ -486,36 +507,6 @@ static int __init alloc_frozen_cpus(void)
 core_initcall(alloc_frozen_cpus);
 
 /*
- * Prevent regular CPU hotplug from racing with the freezer, by disabling CPU
- * hotplug when tasks are about to be frozen. Also, don't allow the freezer
- * to continue until any currently running CPU hotplug operation gets
- * completed.
- * To modify the 'cpu_hotplug_disabled' flag, we need to acquire the
- * 'cpu_add_remove_lock'. And this same lock is also taken by the regular
- * CPU hotplug path and released only after it is complete. Thus, we
- * (and hence the freezer) will block here until any currently running CPU
- * hotplug operation gets completed.
- */
-void cpu_hotplug_disable_before_freeze(void)
-{
-	cpu_maps_update_begin();
-	cpu_hotplug_disabled = 1;
-	cpu_maps_update_done();
-}
-
-
-/*
- * When tasks have been thawed, re-enable regular CPU hotplug (which had been
- * disabled while beginning to freeze tasks).
- */
-void cpu_hotplug_enable_after_thaw(void)
-{
-	cpu_maps_update_begin();
-	cpu_hotplug_disabled = 0;
-	cpu_maps_update_done();
-}
-
-/*
  * When callbacks for CPU hotplug notifications are being executed, we must
  * ensure that the state of the system with respect to the tasks being frozen
  * or not, as reported by the notification, remains unchanged *throughout the
@@ -534,12 +525,12 @@ cpu_hotplug_pm_callback(struct notifier_block *nb,
 
 	case PM_SUSPEND_PREPARE:
 	case PM_HIBERNATION_PREPARE:
-		cpu_hotplug_disable_before_freeze();
+		cpu_hotplug_disable();
 		break;
 
 	case PM_POST_SUSPEND:
 	case PM_POST_HIBERNATION:
-		cpu_hotplug_enable_after_thaw();
+		cpu_hotplug_enable();
 		break;
 
 	default:
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 839a24f1ddeb..8e810bab9ca8 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -193,9 +193,6 @@ static void cpu_ctx_sched_in(struct perf_cpu_context *cpuctx,
 static void update_context_time(struct perf_event_context *ctx);
 static u64 perf_event_time(struct perf_event *event);
 
-static void ring_buffer_attach(struct perf_event *event,
-			       struct ring_buffer *rb);
-
 void __weak perf_event_print_debug(void)	{ }
 
 extern __weak const char *perf_pmu_name(void)
@@ -253,9 +250,9 @@ perf_cgroup_match(struct perf_event *event)
 	return !event->cgrp || event->cgrp == cpuctx->cgrp;
 }
 
-static inline void perf_get_cgroup(struct perf_event *event)
+static inline bool perf_tryget_cgroup(struct perf_event *event)
 {
-	css_get(&event->cgrp->css);
+	return css_tryget(&event->cgrp->css);
 }
 
 static inline void perf_put_cgroup(struct perf_event *event)
@@ -484,7 +481,11 @@ static inline int perf_cgroup_connect(int fd, struct perf_event *event,
 	event->cgrp = cgrp;
 
 	/* must be done before we fput() the file */
-	perf_get_cgroup(event);
+	if (!perf_tryget_cgroup(event)) {
+		event->cgrp = NULL;
+		ret = -ENOENT;
+		goto out;
+	}
 
 	/*
 	 * all events in a group must monitor
@@ -722,8 +723,18 @@ perf_lock_task_context(struct task_struct *task, int ctxn, unsigned long *flags)
 {
 	struct perf_event_context *ctx;
 
-	rcu_read_lock();
 retry:
+	/*
+	 * One of the few rules of preemptible RCU is that one cannot do
+	 * rcu_read_unlock() while holding a scheduler (or nested) lock when
+	 * part of the read side critical section was preemptible -- see
+	 * rcu_read_unlock_special().
+	 *
+	 * Since ctx->lock nests under rq->lock we must ensure the entire read
+	 * side critical section is non-preemptible.
+	 */
+	preempt_disable();
+	rcu_read_lock();
 	ctx = rcu_dereference(task->perf_event_ctxp[ctxn]);
 	if (ctx) {
 		/*
@@ -739,6 +750,8 @@ retry:
 		raw_spin_lock_irqsave(&ctx->lock, *flags);
 		if (ctx != rcu_dereference(task->perf_event_ctxp[ctxn])) {
 			raw_spin_unlock_irqrestore(&ctx->lock, *flags);
+			rcu_read_unlock();
+			preempt_enable();
 			goto retry;
 		}
 
@@ -748,6 +761,7 @@ retry:
 		}
 	}
 	rcu_read_unlock();
+	preempt_enable();
 	return ctx;
 }
 
@@ -901,6 +915,15 @@ list_add_event(struct perf_event *event, struct perf_event_context *ctx)
 }
 
 /*
+ * Initialize event state based on the perf_event_attr::disabled.
+ */
+static inline void perf_event__state_init(struct perf_event *event)
+{
+	event->state = event->attr.disabled ? PERF_EVENT_STATE_OFF :
+					      PERF_EVENT_STATE_INACTIVE;
+}
+
+/*
  * Called at perf_event creation and when events are attached/detached from a
  * group.
  */
@@ -1705,7 +1728,16 @@ static int __perf_event_enable(void *info)
 	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
 	int err;
 
-	if (WARN_ON_ONCE(!ctx->is_active))
+	/*
+	 * There's a time window between 'ctx->is_active' check
+	 * in perf_event_enable function and this place having:
+	 *   - IRQs on
+	 *   - ctx->lock unlocked
+	 *
+	 * where the task could be killed and 'ctx' deactivated
+	 * by perf_event_exit_task.
+	 */
+	if (!ctx->is_active)
 		return -EINVAL;
 
 	raw_spin_lock(&ctx->lock);
@@ -2849,6 +2881,7 @@ 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 free_event(struct perf_event *event)
 {
@@ -2873,15 +2906,30 @@ static void free_event(struct perf_event *event)
 		if (has_branch_stack(event)) {
 			static_key_slow_dec_deferred(&perf_sched_events);
 			/* is system-wide event */
-			if (!(event->attach_state & PERF_ATTACH_TASK))
+			if (!(event->attach_state & PERF_ATTACH_TASK)) {
 				atomic_dec(&per_cpu(perf_branch_stack_events,
 						    event->cpu));
+			}
 		}
 	}
 
 	if (event->rb) {
-		ring_buffer_put(event->rb);
-		event->rb = NULL;
+		struct ring_buffer *rb;
+
+		/*
+		 * Can happen when we close an event with re-directed output.
+		 *
+		 * Since we have a 0 refcount, perf_mmap_close() will skip
+		 * 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 */
+		}
+		mutex_unlock(&event->mmap_mutex);
 	}
 
 	if (is_cgroup_event(event))
@@ -3119,30 +3167,13 @@ static unsigned int perf_poll(struct file *file, poll_table *wait)
 	unsigned int events = POLL_HUP;
 
 	/*
-	 * Race between perf_event_set_output() and perf_poll(): perf_poll()
-	 * grabs the rb reference but perf_event_set_output() overrides it.
-	 * Here is the timeline for two threads T1, T2:
-	 * t0: T1, rb = rcu_dereference(event->rb)
-	 * t1: T2, old_rb = event->rb
-	 * t2: T2, event->rb = new rb
-	 * t3: T2, ring_buffer_detach(old_rb)
-	 * t4: T1, ring_buffer_attach(rb1)
-	 * t5: T1, poll_wait(event->waitq)
-	 *
-	 * To avoid this problem, we grab mmap_mutex in perf_poll()
-	 * thereby ensuring that the assignment of the new ring buffer
-	 * and the detachment of the old buffer appear atomic to perf_poll()
+	 * Pin the event->rb by taking event->mmap_mutex; otherwise
+	 * perf_event_set_output() can swizzle our rb and make us miss wakeups.
 	 */
 	mutex_lock(&event->mmap_mutex);
-
-	rcu_read_lock();
-	rb = rcu_dereference(event->rb);
-	if (rb) {
-		ring_buffer_attach(event, rb);
+	rb = event->rb;
+	if (rb)
 		events = atomic_xchg(&rb->poll, 0);
-	}
-	rcu_read_unlock();
-
 	mutex_unlock(&event->mmap_mutex);
 
 	poll_wait(file, &event->waitq, wait);
@@ -3459,16 +3490,12 @@ static void ring_buffer_attach(struct perf_event *event,
 		return;
 
 	spin_lock_irqsave(&rb->event_lock, flags);
-	if (!list_empty(&event->rb_entry))
-		goto unlock;
-
-	list_add(&event->rb_entry, &rb->event_list);
-unlock:
+	if (list_empty(&event->rb_entry))
+		list_add(&event->rb_entry, &rb->event_list);
 	spin_unlock_irqrestore(&rb->event_lock, flags);
 }
 
-static void ring_buffer_detach(struct perf_event *event,
-			       struct ring_buffer *rb)
+static void ring_buffer_detach(struct perf_event *event, struct ring_buffer *rb)
 {
 	unsigned long flags;
 
@@ -3487,13 +3514,10 @@ static void ring_buffer_wakeup(struct perf_event *event)
 
 	rcu_read_lock();
 	rb = rcu_dereference(event->rb);
-	if (!rb)
-		goto unlock;
-
-	list_for_each_entry_rcu(event, &rb->event_list, rb_entry)
-		wake_up_all(&event->waitq);
-
-unlock:
+	if (rb) {
+		list_for_each_entry_rcu(event, &rb->event_list, rb_entry)
+			wake_up_all(&event->waitq);
+	}
 	rcu_read_unlock();
 }
 
@@ -3522,18 +3546,10 @@ static struct ring_buffer *ring_buffer_get(struct perf_event *event)
 
 static void ring_buffer_put(struct ring_buffer *rb)
 {
-	struct perf_event *event, *n;
-	unsigned long flags;
-
 	if (!atomic_dec_and_test(&rb->refcount))
 		return;
 
-	spin_lock_irqsave(&rb->event_lock, flags);
-	list_for_each_entry_safe(event, n, &rb->event_list, rb_entry) {
-		list_del_init(&event->rb_entry);
-		wake_up_all(&event->waitq);
-	}
-	spin_unlock_irqrestore(&rb->event_lock, flags);
+	WARN_ON_ONCE(!list_empty(&rb->event_list));
 
 	call_rcu(&rb->rcu_head, rb_free_rcu);
 }
@@ -3543,26 +3559,100 @@ static void perf_mmap_open(struct vm_area_struct *vma)
 	struct perf_event *event = vma->vm_file->private_data;
 
 	atomic_inc(&event->mmap_count);
+	atomic_inc(&event->rb->mmap_count);
 }
 
+/*
+ * A buffer can be mmap()ed multiple times; either directly through the same
+ * event, or through other events by use of perf_event_set_output().
+ *
+ * In order to undo the VM accounting done by perf_mmap() we need to destroy
+ * the buffer here, where we still have a VM context. This means we need
+ * to detach all events redirecting to us.
+ */
 static void perf_mmap_close(struct vm_area_struct *vma)
 {
 	struct perf_event *event = vma->vm_file->private_data;
 
-	if (atomic_dec_and_mutex_lock(&event->mmap_count, &event->mmap_mutex)) {
-		unsigned long size = perf_data_size(event->rb);
-		struct user_struct *user = event->mmap_user;
-		struct ring_buffer *rb = event->rb;
+	struct ring_buffer *rb = event->rb;
+	struct user_struct *mmap_user = rb->mmap_user;
+	int mmap_locked = rb->mmap_locked;
+	unsigned long size = perf_data_size(rb);
+
+	atomic_dec(&rb->mmap_count);
+
+	if (!atomic_dec_and_mutex_lock(&event->mmap_count, &event->mmap_mutex))
+		return;
+
+	/* Detach current event from the buffer. */
+	rcu_assign_pointer(event->rb, NULL);
+	ring_buffer_detach(event, rb);
+	mutex_unlock(&event->mmap_mutex);
 
-		atomic_long_sub((size >> PAGE_SHIFT) + 1, &user->locked_vm);
-		vma->vm_mm->pinned_vm -= event->mmap_locked;
-		rcu_assign_pointer(event->rb, NULL);
-		ring_buffer_detach(event, rb);
+	/* 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;
+	}
+
+	/*
+	 * No other mmap()s, detach from all other events that might redirect
+	 * into the now unreachable buffer. Somewhat complicated by the
+	 * fact that rb::event_lock otherwise nests inside mmap_mutex.
+	 */
+again:
+	rcu_read_lock();
+	list_for_each_entry_rcu(event, &rb->event_list, rb_entry) {
+		if (!atomic_long_inc_not_zero(&event->refcount)) {
+			/*
+			 * This event is en-route to free_event() which will
+			 * detach it and remove it from the list.
+			 */
+			continue;
+		}
+		rcu_read_unlock();
+
+		mutex_lock(&event->mmap_mutex);
+		/*
+		 * Check we didn't race with perf_event_set_output() which can
+		 * swizzle the rb from under us while we were waiting to
+		 * acquire mmap_mutex.
+		 *
+		 * If we find a different rb; ignore this event, a next
+		 * iteration will no longer find it on the list. We have to
+		 * 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 */
+		}
 		mutex_unlock(&event->mmap_mutex);
+		put_event(event);
 
-		ring_buffer_put(rb);
-		free_uid(user);
+		/*
+		 * Restart the iteration; either we're on the wrong list or
+		 * destroyed its integrity by doing a deletion.
+		 */
+		goto again;
 	}
+	rcu_read_unlock();
+
+	/*
+	 * It could be there's still a few 0-ref events on the list; they'll
+	 * get cleaned up by free_event() -- they'll also still have their
+	 * ref on the rb and will free it whenever they are done with it.
+	 *
+	 * Aside from that, this buffer is 'fully' detached and unmapped,
+	 * undo the VM accounting.
+	 */
+
+	atomic_long_sub((size >> PAGE_SHIFT) + 1, &mmap_user->locked_vm);
+	vma->vm_mm->pinned_vm -= mmap_locked;
+	free_uid(mmap_user);
+
+	ring_buffer_put(rb); /* could be last */
 }
 
 static const struct vm_operations_struct perf_mmap_vmops = {
@@ -3612,12 +3702,24 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 		return -EINVAL;
 
 	WARN_ON_ONCE(event->ctx->parent_ctx);
+again:
 	mutex_lock(&event->mmap_mutex);
 	if (event->rb) {
-		if (event->rb->nr_pages == nr_pages)
-			atomic_inc(&event->rb->refcount);
-		else
+		if (event->rb->nr_pages != nr_pages) {
 			ret = -EINVAL;
+			goto unlock;
+		}
+
+		if (!atomic_inc_not_zero(&event->rb->mmap_count)) {
+			/*
+			 * Raced against perf_mmap_close() through
+			 * perf_event_set_output(). Try again, hope for better
+			 * luck.
+			 */
+			mutex_unlock(&event->mmap_mutex);
+			goto again;
+		}
+
 		goto unlock;
 	}
 
@@ -3658,12 +3760,16 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 		ret = -ENOMEM;
 		goto unlock;
 	}
-	rcu_assign_pointer(event->rb, rb);
+
+	atomic_set(&rb->mmap_count, 1);
+	rb->mmap_locked = extra;
+	rb->mmap_user = get_current_user();
 
 	atomic_long_add(user_extra, &user->locked_vm);
-	event->mmap_locked = extra;
-	event->mmap_user = get_current_user();
-	vma->vm_mm->pinned_vm += event->mmap_locked;
+	vma->vm_mm->pinned_vm += extra;
+
+	ring_buffer_attach(event, rb);
+	rcu_assign_pointer(event->rb, rb);
 
 	perf_event_update_userpage(event);
 
@@ -3672,7 +3778,11 @@ unlock:
 		atomic_inc(&event->mmap_count);
 	mutex_unlock(&event->mmap_mutex);
 
-	vma->vm_flags |= VM_RESERVED;
+	/*
+	 * Since pinned accounting is per vm we cannot allow fork() to copy our
+	 * vma.
+	 */
+	vma->vm_flags |= VM_DONTCOPY | VM_RESERVED;
 	vma->vm_ops = &perf_mmap_vmops;
 
 	return ret;
@@ -5961,8 +6071,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 	event->overflow_handler	= overflow_handler;
 	event->overflow_handler_context = context;
 
-	if (attr->disabled)
-		event->state = PERF_EVENT_STATE_OFF;
+	perf_event__state_init(event);
 
 	pmu = NULL;
 
@@ -6161,6 +6270,8 @@ 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);
@@ -6168,16 +6279,28 @@ set:
 			goto unlock;
 	}
 
-	old_rb = event->rb;
-	rcu_assign_pointer(event->rb, rb);
 	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);
+	}
+
 	ret = 0;
 unlock:
 	mutex_unlock(&event->mmap_mutex);
 
-	if (old_rb)
-		ring_buffer_put(old_rb);
 out:
 	return ret;
 }
@@ -6370,9 +6493,17 @@ SYSCALL_DEFINE5(perf_event_open,
 
 		mutex_lock(&gctx->mutex);
 		perf_remove_from_context(group_leader);
+
+		/*
+		 * Removing from the context ends up with disabled
+		 * event. What we want here is event in the initial
+		 * startup state, ready to be add into new context.
+		 */
+		perf_event__state_init(group_leader);
 		list_for_each_entry(sibling, &group_leader->sibling_list,
 				    group_entry) {
 			perf_remove_from_context(sibling);
+			perf_event__state_init(sibling);
 			put_ctx(gctx);
 		}
 		mutex_unlock(&gctx->mutex);
@@ -6844,7 +6975,7 @@ inherit_task_group(struct perf_event *event, struct task_struct *parent,
 		 * child.
 		 */
 
-		child_ctx = alloc_perf_context(event->pmu, child);
+		child_ctx = alloc_perf_context(parent_ctx->pmu, child);
 		if (!child_ctx)
 			return -ENOMEM;
 
diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c
index bb38c4d3ee12..fc8bfcf3a3da 100644
--- a/kernel/events/hw_breakpoint.c
+++ b/kernel/events/hw_breakpoint.c
@@ -147,7 +147,7 @@ fetch_bp_busy_slots(struct bp_busy_slots *slots, struct perf_event *bp,
 		return;
 	}
 
-	for_each_online_cpu(cpu) {
+	for_each_possible_cpu(cpu) {
 		unsigned int nr;
 
 		nr = per_cpu(nr_cpu_bp_pinned[type], cpu);
@@ -233,7 +233,7 @@ toggle_bp_slot(struct perf_event *bp, bool enable, enum bp_type_idx type,
 	if (cpu >= 0) {
 		toggle_bp_task_slot(bp, cpu, enable, type, weight);
 	} else {
-		for_each_online_cpu(cpu)
+		for_each_possible_cpu(cpu)
 			toggle_bp_task_slot(bp, cpu, enable, type, weight);
 	}
 
diff --git a/kernel/events/internal.h b/kernel/events/internal.h
index b0b107f90afc..b400e6429c02 100644
--- a/kernel/events/internal.h
+++ b/kernel/events/internal.h
@@ -30,6 +30,10 @@ struct ring_buffer {
 	spinlock_t			event_lock;
 	struct list_head		event_list;
 
+	atomic_t			mmap_count;
+	unsigned long			mmap_locked;
+	struct user_struct		*mmap_user;
+
 	struct perf_event_mmap_page	*user_page;
 	void				*data_pages[0];
 };
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index cdd5607c0ceb..a57ef25867e3 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -61,6 +61,7 @@
 DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
 {
 
+	.lock = __RAW_SPIN_LOCK_UNLOCKED(hrtimer_bases.lock),
 	.clock_base =
 	{
 		{
@@ -297,6 +298,10 @@ ktime_t ktime_sub_ns(const ktime_t kt, u64 nsec)
 	} else {
 		unsigned long rem = do_div(nsec, NSEC_PER_SEC);
 
+		/* Make sure nsec fits into long */
+		if (unlikely(nsec > KTIME_SEC_MAX))
+			return (ktime_t){ .tv64 = KTIME_MAX };
+
 		tmp = ktime_set((long)nsec, rem);
 	}
 
@@ -702,17 +707,20 @@ static int hrtimer_switch_to_hres(void)
 	return 1;
 }
 
+static void clock_was_set_work(struct work_struct *work)
+{
+	clock_was_set();
+}
+
+static DECLARE_WORK(hrtimer_work, clock_was_set_work);
+
 /*
- * Called from timekeeping code to reprogramm the hrtimer interrupt
- * device. If called from the timer interrupt context we defer it to
- * softirq context.
+ * Called from timekeeping and resume code to reprogramm the hrtimer
+ * interrupt device on all cpus.
  */
 void clock_was_set_delayed(void)
 {
-	struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
-
-	cpu_base->clock_was_set = 1;
-	__raise_softirq_irqoff(HRTIMER_SOFTIRQ);
+	schedule_work(&hrtimer_work);
 }
 
 #else
@@ -761,8 +769,10 @@ void hrtimers_resume(void)
 	WARN_ONCE(!irqs_disabled(),
 		  KERN_INFO "hrtimers_resume() called with IRQs enabled!");
 
+	/* Retrigger on the local CPU */
 	retrigger_next_event(NULL);
-	timerfd_clock_was_set();
+	/* And schedule a retrigger for all others */
+	clock_was_set_delayed();
 }
 
 static inline void timer_stats_hrtimer_set_start_info(struct hrtimer *timer)
@@ -1307,6 +1317,8 @@ retry:
 
 				expires = ktime_sub(hrtimer_get_expires(timer),
 						    base->offset);
+				if (expires.tv64 < 0)
+					expires.tv64 = KTIME_MAX;
 				if (expires.tv64 < expires_next.tv64)
 					expires_next = expires;
 				break;
@@ -1409,13 +1421,6 @@ void hrtimer_peek_ahead_timers(void)
 
 static void run_hrtimer_softirq(struct softirq_action *h)
 {
-	struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
-
-	if (cpu_base->clock_was_set) {
-		cpu_base->clock_was_set = 0;
-		clock_was_set();
-	}
-
 	hrtimer_peek_ahead_timers();
 }
 
@@ -1640,8 +1645,6 @@ static void __cpuinit init_hrtimers_cpu(int cpu)
 	struct hrtimer_cpu_base *cpu_base = &per_cpu(hrtimer_bases, cpu);
 	int i;
 
-	raw_spin_lock_init(&cpu_base->lock);
-
 	for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
 		cpu_base->clock_base[i].cpu_base = cpu_base;
 		timerqueue_init_head(&cpu_base->clock_base[i].active);
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 7684920f4f66..86a500d7ea59 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -546,9 +546,9 @@ int can_request_irq(unsigned int irq, unsigned long irqflags)
 		return 0;
 
 	if (irq_settings_can_request(desc)) {
-		if (desc->action)
-			if (irqflags & desc->action->flags & IRQF_SHARED)
-				canrequest =1;
+		if (!desc->action ||
+		    irqflags & desc->action->flags & IRQF_SHARED)
+			canrequest = 1;
 	}
 	irq_put_desc_unlock(desc, flags);
 	return canrequest;
diff --git a/kernel/kmod.c b/kernel/kmod.c
index 05698a7415fe..f2490e1dd51f 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -541,6 +541,11 @@ int call_usermodehelper_exec(struct subprocess_info *sub_info, int wait)
 	int retval = 0;
 
 	helper_lock();
+	if (!sub_info->path) {
+		retval = -EINVAL;
+		goto out;
+	}
+
 	if (sub_info->path[0] == '\0')
 		goto out;
 
diff --git a/kernel/panic.c b/kernel/panic.c
index 90fd443165df..9ce61102c01e 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -81,6 +81,14 @@ void panic(const char *fmt, ...)
 	int state = 0;
 
 	/*
+	 * Disable local interrupts. This will prevent panic_smp_self_stop
+	 * from deadlocking the first cpu that invokes the panic, since
+	 * there is nothing to prevent an interrupt handler (that runs
+	 * after the panic_lock is acquired) from invoking panic again.
+	 */
+	local_irq_disable();
+
+	/*
 	 * It's possible to come here directly from a panic-assertion and
 	 * not have preempt disabled. Some functions called from here want
 	 * preempt to be disabled. No point enabling it later though...
diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index c685e31492df..c3ae1446461c 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -176,10 +176,36 @@ static u64 sched_clock_remote(struct sched_clock_data *scd)
 	u64 this_clock, remote_clock;
 	u64 *ptr, old_val, val;
 
+#if BITS_PER_LONG != 64
+again:
+	/*
+	 * Careful here: The local and the remote clock values need to
+	 * be read out atomic as we need to compare the values and
+	 * then update either the local or the remote side. So the
+	 * cmpxchg64 below only protects one readout.
+	 *
+	 * We must reread via sched_clock_local() in the retry case on
+	 * 32bit as an NMI could use sched_clock_local() via the
+	 * tracer and hit between the readout of
+	 * the low32bit and the high 32bit portion.
+	 */
+	this_clock = sched_clock_local(my_scd);
+	/*
+	 * We must enforce atomic readout on 32bit, otherwise the
+	 * update on the remote cpu can hit inbetween the readout of
+	 * the low32bit and the high 32bit portion.
+	 */
+	remote_clock = cmpxchg64(&scd->clock, 0, 0);
+#else
+	/*
+	 * On 64bit the read of [my]scd->clock is atomic versus the
+	 * update, so we can avoid the above 32bit dance.
+	 */
 	sched_clock_local(my_scd);
 again:
 	this_clock = my_scd->clock;
 	remote_clock = scd->clock;
+#endif
 
 	/*
 	 * Use the opportunity that we have both locks
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 9b20f3e88bd0..99d701ee206c 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1653,8 +1653,10 @@ static void try_to_wake_up_local(struct task_struct *p)
 {
 	struct rq *rq = task_rq(p);
 
-	BUG_ON(rq != this_rq());
-	BUG_ON(p == current);
+	if (WARN_ON_ONCE(rq != this_rq()) ||
+	    WARN_ON_ONCE(p == current))
+		return;
+
 	lockdep_assert_held(&rq->lock);
 
 	if (!raw_spin_trylock(&p->pi_lock)) {
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index e9553640c1c3..da4512f578bf 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5511,7 +5511,7 @@ static unsigned int get_rr_interval_fair(struct rq *rq, struct task_struct *task
 	 * idle runqueue:
 	 */
 	if (rq->cfs.load.weight)
-		rr_interval = NS_TO_JIFFIES(sched_slice(&rq->cfs, se));
+		rr_interval = NS_TO_JIFFIES(sched_slice(cfs_rq_of(se), se));
 
 	return rr_interval;
 }
diff --git a/kernel/signal.c b/kernel/signal.c
index 563b7711d234..ee44fc784d73 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -482,6 +482,9 @@ flush_signal_handlers(struct task_struct *t, int force_default)
 		if (force_default || ka->sa.sa_handler != SIG_IGN)
 			ka->sa.sa_handler = SIG_DFL;
 		ka->sa.sa_flags = 0;
+#ifdef __ARCH_HAS_SA_RESTORER
+		ka->sa.sa_restorer = NULL;
+#endif
 		sigemptyset(&ka->sa.sa_mask);
 		ka++;
 	}
@@ -2864,7 +2867,7 @@ do_send_specific(pid_t tgid, pid_t pid, int sig, struct siginfo *info)
 
 static int do_tkill(pid_t tgid, pid_t pid, int sig)
 {
-	struct siginfo info;
+	struct siginfo info = {};
 
 	info.si_signo = sig;
 	info.si_errno = 0;
diff --git a/kernel/sys.c b/kernel/sys.c
index b0003db7fea0..3449d262ea44 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -320,7 +320,6 @@ void kernel_restart_prepare(char *cmd)
 	system_state = SYSTEM_RESTART;
 	usermodehelper_disable();
 	device_shutdown();
-	syscore_shutdown();
 }
 
 /**
@@ -354,6 +353,29 @@ int unregister_reboot_notifier(struct notifier_block *nb)
 }
 EXPORT_SYMBOL(unregister_reboot_notifier);
 
+/* Add backwards compatibility for stable trees. */
+#ifndef PF_NO_SETAFFINITY
+#define PF_NO_SETAFFINITY		PF_THREAD_BOUND
+#endif
+
+static void migrate_to_reboot_cpu(void)
+{
+	/* The boot cpu is always logical cpu 0 */
+	int cpu = 0;
+
+	cpu_hotplug_disable();
+
+	/* Make certain the cpu I'm about to reboot on is online */
+	if (!cpu_online(cpu))
+		cpu = cpumask_first(cpu_online_mask);
+
+	/* Prevent races with other tasks migrating this task */
+	current->flags |= PF_NO_SETAFFINITY;
+
+	/* Make certain I only run on the appropriate processor */
+	set_cpus_allowed_ptr(current, cpumask_of(cpu));
+}
+
 /**
  *	kernel_restart - reboot the system
  *	@cmd: pointer to buffer containing command to execute for restart
@@ -365,7 +387,8 @@ EXPORT_SYMBOL(unregister_reboot_notifier);
 void kernel_restart(char *cmd)
 {
 	kernel_restart_prepare(cmd);
-	disable_nonboot_cpus();
+	migrate_to_reboot_cpu();
+	syscore_shutdown();
 	if (!cmd)
 		printk(KERN_EMERG "Restarting system.\n");
 	else
@@ -391,6 +414,7 @@ static void kernel_shutdown_prepare(enum system_states state)
 void kernel_halt(void)
 {
 	kernel_shutdown_prepare(SYSTEM_HALT);
+	migrate_to_reboot_cpu();
 	syscore_shutdown();
 	printk(KERN_EMERG "System halted.\n");
 	kmsg_dump(KMSG_DUMP_HALT);
@@ -409,7 +433,7 @@ void kernel_power_off(void)
 	kernel_shutdown_prepare(SYSTEM_POWER_OFF);
 	if (pm_power_off_prepare)
 		pm_power_off_prepare();
-	disable_nonboot_cpus();
+	migrate_to_reboot_cpu();
 	syscore_shutdown();
 	printk(KERN_EMERG "Power down.\n");
 	kmsg_dump(KMSG_DUMP_POWEROFF);
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index f113755695e2..f8961bf97362 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -66,12 +66,17 @@ static void tick_broadcast_start_periodic(struct clock_event_device *bc)
  */
 int tick_check_broadcast_device(struct clock_event_device *dev)
 {
-	if ((tick_broadcast_device.evtdev &&
+	struct clock_event_device *cur = tick_broadcast_device.evtdev;
+
+	if ((dev->features & CLOCK_EVT_FEAT_DUMMY) ||
+	    (tick_broadcast_device.evtdev &&
 	     tick_broadcast_device.evtdev->rating >= dev->rating) ||
 	     (dev->features & CLOCK_EVT_FEAT_C3STOP))
 		return 0;
 
 	clockevents_exchange_device(tick_broadcast_device.evtdev, dev);
+	if (cur)
+		cur->event_handler = clockevents_handle_noop;
 	tick_broadcast_device.evtdev = dev;
 	if (!cpumask_empty(tick_get_broadcast_mask()))
 		tick_broadcast_start_periodic(dev);
@@ -395,7 +400,15 @@ void tick_check_oneshot_broadcast(int cpu)
 	if (cpumask_test_cpu(cpu, to_cpumask(tick_broadcast_oneshot_mask))) {
 		struct tick_device *td = &per_cpu(tick_cpu_device, cpu);
 
-		clockevents_set_mode(td->evtdev, CLOCK_EVT_MODE_ONESHOT);
+		/*
+		 * We might be in the middle of switching over from
+		 * periodic to oneshot. If the CPU has not yet
+		 * switched over, leave the device alone.
+		 */
+		if (td->mode == TICKDEV_MODE_ONESHOT) {
+			clockevents_set_mode(td->evtdev,
+					     CLOCK_EVT_MODE_ONESHOT);
+		}
 	}
 }
 
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index da6c9ecad4e4..ead79bce1258 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -323,6 +323,7 @@ static void tick_shutdown(unsigned int *cpup)
 		 */
 		dev->mode = CLOCK_EVT_MODE_UNUSED;
 		clockevents_exchange_device(dev, NULL);
+		dev->event_handler = clockevents_handle_noop;
 		td->evtdev = NULL;
 	}
 	raw_spin_unlock_irqrestore(&tick_device_lock, flags);
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index cd0e5a7d1632..2196248dabba 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -145,7 +145,6 @@ static void tick_nohz_update_jiffies(ktime_t now)
 	tick_do_update_jiffies64(now);
 	local_irq_restore(flags);
 
-	calc_load_exit_idle();
 	touch_softlockup_watchdog();
 }
 
@@ -497,12 +496,17 @@ void tick_nohz_idle_enter(void)
  */
 void tick_nohz_irq_exit(void)
 {
+	unsigned long flags;
 	struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
 
 	if (!ts->inidle)
 		return;
 
+	local_irq_save(flags);
+
 	tick_nohz_stop_sched_tick(ts);
+
+	local_irq_restore(flags);
 }
 
 /**
@@ -862,7 +866,7 @@ void tick_cancel_sched_timer(int cpu)
 		hrtimer_cancel(&ts->sched_timer);
 # endif
 
-	ts->nohz_mode = NOHZ_MODE_INACTIVE;
+	memset(ts, 0, sizeof(*ts));
 }
 #endif
 
diff --git a/kernel/timer.c b/kernel/timer.c
index 6dfdb72828ff..7e0a770be489 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -145,9 +145,11 @@ static unsigned long round_jiffies_common(unsigned long j, int cpu,
 	/* now that we have rounded, subtract the extra skew again */
 	j -= cpu * 3;
 
-	if (j <= jiffies) /* rounding ate our timeout entirely; */
-		return original;
-	return j;
+	/*
+	 * Make sure j is still in the future. Otherwise return the
+	 * unmodified value.
+	 */
+	return time_is_after_jiffies(j) ? j : original;
 }
 
 /**
@@ -1680,12 +1682,12 @@ static int __cpuinit init_timers_cpu(int cpu)
 			boot_done = 1;
 			base = &boot_tvec_bases;
 		}
+		spin_lock_init(&base->lock);
 		tvec_base_done[cpu] = 1;
 	} else {
 		base = per_cpu(tvec_bases, cpu);
 	}
 
-	spin_lock_init(&base->lock);
 
 	for (j = 0; j < TVN_SIZE; j++) {
 		INIT_LIST_HEAD(base->tv5.vec + j);
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index e2a3f7207cca..eddb2876f7b9 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -386,24 +386,28 @@ config KPROBE_EVENT
 	  If you want to use perf tools, this option is strongly recommended.
 
 config DYNAMIC_FTRACE
-	bool "enable/disable ftrace tracepoints dynamically"
+	bool "enable/disable function tracing dynamically"
 	depends on FUNCTION_TRACER
 	depends on HAVE_DYNAMIC_FTRACE
 	default y
 	help
-          This option will modify all the calls to ftrace dynamically
-	  (will patch them out of the binary image and replace them
-	  with a No-Op instruction) as they are called. A table is
-	  created to dynamically enable them again.
+	  This option will modify all the calls to function tracing
+	  dynamically (will patch them out of the binary image and
+	  replace them with a No-Op instruction) on boot up. During
+	  compile time, a table is made of all the locations that ftrace
+	  can function trace, and this table is linked into the kernel
+	  image. When this is enabled, functions can be individually
+	  enabled, and the functions not enabled will not affect
+	  performance of the system.
+
+	  See the files in /sys/kernel/debug/tracing:
+	    available_filter_functions
+	    set_ftrace_filter
+	    set_ftrace_notrace
 
 	  This way a CONFIG_FUNCTION_TRACER kernel is slightly larger, but
 	  otherwise has native performance as long as no tracing is active.
 
-	  The changes to the code are done by a kernel thread that
-	  wakes up once a second and checks to see if any ftrace calls
-	  were made. If so, it runs stop_machine (stops all CPUS)
-	  and modifies the code to jump over the call to ftrace.
-
 config FUNCTION_PROFILER
 	bool "Kernel function profiler"
 	depends on FUNCTION_TRACER
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 4a86e6404085..e101cf9acc06 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -624,7 +624,7 @@ int ftrace_profile_pages_init(struct ftrace_profile_stat *stat)
 
 	pages = DIV_ROUND_UP(functions, PROFILES_PER_PAGE);
 
-	for (i = 0; i < pages; i++) {
+	for (i = 1; i < pages; i++) {
 		pg->next = (void *)get_zeroed_page(GFP_KERNEL);
 		if (!pg->next)
 			goto out_free;
@@ -642,7 +642,6 @@ int ftrace_profile_pages_init(struct ftrace_profile_stat *stat)
 		free_page(tmp);
 	}
 
-	free_page((unsigned long)stat->pages);
 	stat->pages = NULL;
 	stat->start = NULL;
 
@@ -1000,6 +999,19 @@ static __init void ftrace_profile_debugfs(struct dentry *d_tracer)
 
 static struct pid * const ftrace_swapper_pid = &init_struct_pid;
 
+loff_t
+ftrace_filter_lseek(struct file *file, loff_t offset, int whence)
+{
+	loff_t ret;
+
+	if (file->f_mode & FMODE_READ)
+		ret = seq_lseek(file, offset, whence);
+	else
+		file->f_pos = ret = 1;
+
+	return ret;
+}
+
 #ifdef CONFIG_DYNAMIC_FTRACE
 
 #ifndef CONFIG_FTRACE_MCOUNT_RECORD
@@ -2542,7 +2554,7 @@ static void ftrace_filter_reset(struct ftrace_hash *hash)
  * routine, you can use ftrace_filter_write() for the write
  * routine if @flag has FTRACE_ITER_FILTER set, or
  * ftrace_notrace_write() if @flag has FTRACE_ITER_NOTRACE set.
- * ftrace_regex_lseek() should be used as the lseek routine, and
+ * ftrace_filter_lseek() should be used as the lseek routine, and
  * release must call ftrace_regex_release().
  */
 int
@@ -2626,19 +2638,6 @@ ftrace_notrace_open(struct inode *inode, struct file *file)
 				 inode, file);
 }
 
-loff_t
-ftrace_regex_lseek(struct file *file, loff_t offset, int origin)
-{
-	loff_t ret;
-
-	if (file->f_mode & FMODE_READ)
-		ret = seq_lseek(file, offset, origin);
-	else
-		file->f_pos = ret = 1;
-
-	return ret;
-}
-
 static int ftrace_match(char *str, char *regex, int len, int type)
 {
 	int matched = 0;
@@ -3034,8 +3033,8 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 					continue;
 			}
 
-			hlist_del(&entry->node);
-			call_rcu(&entry->rcu, ftrace_free_entry_rcu);
+			hlist_del_rcu(&entry->node);
+			call_rcu_sched(&entry->rcu, ftrace_free_entry_rcu);
 		}
 	}
 	__disable_ftrace_function_probe();
@@ -3446,7 +3445,7 @@ static const struct file_operations ftrace_filter_fops = {
 	.open = ftrace_filter_open,
 	.read = seq_read,
 	.write = ftrace_filter_write,
-	.llseek = ftrace_regex_lseek,
+	.llseek = ftrace_filter_lseek,
 	.release = ftrace_regex_release,
 };
 
@@ -3454,7 +3453,7 @@ static const struct file_operations ftrace_notrace_fops = {
 	.open = ftrace_notrace_open,
 	.read = seq_read,
 	.write = ftrace_notrace_write,
-	.llseek = ftrace_regex_lseek,
+	.llseek = ftrace_filter_lseek,
 	.release = ftrace_regex_release,
 };
 
@@ -3612,7 +3611,8 @@ out:
 	if (fail)
 		return -EINVAL;
 
-	ftrace_graph_filter_enabled = 1;
+	ftrace_graph_filter_enabled = !!(*idx);
+
 	return 0;
 }
 
@@ -3659,8 +3659,8 @@ static const struct file_operations ftrace_graph_fops = {
 	.open		= ftrace_graph_open,
 	.read		= seq_read,
 	.write		= ftrace_graph_write,
+	.llseek		= ftrace_filter_lseek,
 	.release	= ftrace_graph_release,
-	.llseek		= seq_lseek,
 };
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
 
@@ -4261,7 +4261,7 @@ static const struct file_operations ftrace_pid_fops = {
 	.open		= ftrace_pid_open,
 	.write		= ftrace_pid_write,
 	.read		= seq_read,
-	.llseek		= seq_lseek,
+	.llseek		= ftrace_filter_lseek,
 	.release	= ftrace_pid_release,
 };
 
@@ -4381,12 +4381,8 @@ ftrace_enable_sysctl(struct ctl_table *table, int write,
 		ftrace_startup_sysctl();
 
 		/* we are starting ftrace again */
-		if (ftrace_ops_list != &ftrace_list_end) {
-			if (ftrace_ops_list->next == &ftrace_list_end)
-				ftrace_trace_function = ftrace_ops_list->func;
-			else
-				ftrace_trace_function = ftrace_ops_list_func;
-		}
+		if (ftrace_ops_list != &ftrace_list_end)
+			update_ftrace_function();
 
 	} else {
 		/* stopping ftrace calls (just send to ftrace_stub) */
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 55e4d4c5313d..13cd224c7e81 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -687,7 +687,15 @@ __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 
 	memcpy(max_data->comm, tsk->comm, TASK_COMM_LEN);
 	max_data->pid = tsk->pid;
-	max_data->uid = task_uid(tsk);
+	/*
+	 * If tsk == current, then use current_uid(), as that does not use
+	 * RCU. The irq tracer can be called out of RCU scope.
+	 */
+	if (tsk == current)
+		max_data->uid = current_uid();
+	else
+		max_data->uid = task_uid(tsk);
+
 	max_data->nice = tsk->static_prio - 20 - MAX_RT_PRIO;
 	max_data->policy = tsk->policy;
 	max_data->rt_priority = tsk->rt_priority;
@@ -708,7 +716,7 @@ __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 void
 update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 {
-	struct ring_buffer *buf = tr->buffer;
+	struct ring_buffer *buf;
 
 	if (trace_stop_count)
 		return;
@@ -720,6 +728,7 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 	}
 	arch_spin_lock(&ftrace_max_lock);
 
+	buf = tr->buffer;
 	tr->buffer = max_tr.buffer;
 	max_tr.buffer = buf;
 
@@ -2742,11 +2751,25 @@ static int set_tracer_option(struct tracer *trace, char *cmp, int neg)
 	return -EINVAL;
 }
 
-static void set_tracer_flags(unsigned int mask, int enabled)
+/* Some tracers require overwrite to stay enabled */
+int trace_keep_overwrite(struct tracer *tracer, u32 mask, int set)
+{
+	if (tracer->enabled && (mask & TRACE_ITER_OVERWRITE) && !set)
+		return -1;
+
+	return 0;
+}
+
+int set_tracer_flag(unsigned int mask, int enabled)
 {
 	/* do nothing if flag is already set */
 	if (!!(trace_flags & mask) == !!enabled)
-		return;
+		return 0;
+
+	/* Give the tracer a chance to approve the change */
+	if (current_trace->flag_changed)
+		if (current_trace->flag_changed(current_trace, mask, !!enabled))
+			return -EINVAL;
 
 	if (enabled)
 		trace_flags |= mask;
@@ -2758,6 +2781,8 @@ static void set_tracer_flags(unsigned int mask, int enabled)
 
 	if (mask == TRACE_ITER_OVERWRITE)
 		ring_buffer_change_overwrite(global_trace.buffer, enabled);
+
+	return 0;
 }
 
 static ssize_t
@@ -2767,7 +2792,7 @@ tracing_trace_options_write(struct file *filp, const char __user *ubuf,
 	char buf[64];
 	char *cmp;
 	int neg = 0;
-	int ret;
+	int ret = -ENODEV;
 	int i;
 
 	if (cnt >= sizeof(buf))
@@ -2784,21 +2809,23 @@ tracing_trace_options_write(struct file *filp, const char __user *ubuf,
 		cmp += 2;
 	}
 
+	mutex_lock(&trace_types_lock);
+
 	for (i = 0; trace_options[i]; i++) {
 		if (strcmp(cmp, trace_options[i]) == 0) {
-			set_tracer_flags(1 << i, !neg);
+			ret = set_tracer_flag(1 << i, !neg);
 			break;
 		}
 	}
 
 	/* If no option could be set, test the specific tracer options */
-	if (!trace_options[i]) {
-		mutex_lock(&trace_types_lock);
+	if (!trace_options[i])
 		ret = set_tracer_option(current_trace, cmp, neg);
-		mutex_unlock(&trace_types_lock);
-		if (ret)
-			return ret;
-	}
+
+	mutex_unlock(&trace_types_lock);
+
+	if (ret < 0)
+		return ret;
 
 	*ppos += cnt;
 
@@ -3122,6 +3149,9 @@ static int tracing_set_tracer(const char *buf)
 		goto out;
 
 	trace_branch_disable();
+
+	current_trace->enabled = false;
+
 	if (current_trace && current_trace->reset)
 		current_trace->reset(tr);
 	if (current_trace && current_trace->use_max_tr) {
@@ -3151,6 +3181,7 @@ static int tracing_set_tracer(const char *buf)
 			goto out;
 	}
 
+	current_trace->enabled = true;
 	trace_branch_enable(tr);
  out:
 	mutex_unlock(&trace_types_lock);
@@ -4485,7 +4516,13 @@ trace_options_core_write(struct file *filp, const char __user *ubuf, size_t cnt,
 
 	if (val != 0 && val != 1)
 		return -EINVAL;
-	set_tracer_flags(1 << index, val);
+
+	mutex_lock(&trace_types_lock);
+	ret = set_tracer_flag(1 << index, val);
+	mutex_unlock(&trace_types_lock);
+
+	if (ret < 0)
+		return ret;
 
 	*ppos += cnt;
 
@@ -4688,6 +4725,8 @@ static __init int tracer_init_debugfs(void)
 	trace_access_lock_init();
 
 	d_tracer = tracing_init_dentry();
+	if (!d_tracer)
+		return 0;
 
 	trace_create_file("tracing_enabled", 0644, d_tracer,
 			&global_trace, &tracing_ctrl_fops);
@@ -4824,36 +4863,32 @@ void trace_init_global_iter(struct trace_iterator *iter)
 	iter->cpu_file = TRACE_PIPE_ALL_CPU;
 }
 
-static void
-__ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode)
+void ftrace_dump(enum ftrace_dump_mode oops_dump_mode)
 {
-	static arch_spinlock_t ftrace_dump_lock =
-		(arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
 	/* use static because iter can be a bit big for the stack */
 	static struct trace_iterator iter;
+	static atomic_t dump_running;
 	unsigned int old_userobj;
-	static int dump_ran;
 	unsigned long flags;
 	int cnt = 0, cpu;
 
-	/* only one dump */
-	local_irq_save(flags);
-	arch_spin_lock(&ftrace_dump_lock);
-	if (dump_ran)
-		goto out;
-
-	dump_ran = 1;
+	/* Only allow one dump user at a time. */
+	if (atomic_inc_return(&dump_running) != 1) {
+		atomic_dec(&dump_running);
+		return;
+	}
 
+	/*
+	 * Always turn off tracing when we dump.
+	 * We don't need to show trace output of what happens
+	 * between multiple crashes.
+	 *
+	 * If the user does a sysrq-z, then they can re-enable
+	 * tracing with echo 1 > tracing_on.
+	 */
 	tracing_off();
 
-	/* Did function tracer already get disabled? */
-	if (ftrace_is_dead()) {
-		printk("# WARNING: FUNCTION TRACING IS CORRUPTED\n");
-		printk("#          MAY BE MISSING FUNCTION EVENTS\n");
-	}
-
-	if (disable_tracing)
-		ftrace_kill();
+	local_irq_save(flags);
 
 	trace_init_global_iter(&iter);
 
@@ -4886,6 +4921,12 @@ __ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode)
 
 	printk(KERN_TRACE "Dumping ftrace buffer:\n");
 
+	/* Did function tracer already get disabled? */
+	if (ftrace_is_dead()) {
+		printk("# WARNING: FUNCTION TRACING IS CORRUPTED\n");
+		printk("#          MAY BE MISSING FUNCTION EVENTS\n");
+	}
+
 	/*
 	 * We need to stop all tracing on all CPUS to read the
 	 * the next buffer. This is a bit expensive, but is
@@ -4925,26 +4966,14 @@ __ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode)
 		printk(KERN_TRACE "---------------------------------\n");
 
  out_enable:
-	/* Re-enable tracing if requested */
-	if (!disable_tracing) {
-		trace_flags |= old_userobj;
+	trace_flags |= old_userobj;
 
-		for_each_tracing_cpu(cpu) {
-			atomic_dec(&iter.tr->data[cpu]->disabled);
-		}
-		tracing_on();
+	for_each_tracing_cpu(cpu) {
+		atomic_dec(&iter.tr->data[cpu]->disabled);
 	}
-
- out:
-	arch_spin_unlock(&ftrace_dump_lock);
+ 	atomic_dec(&dump_running);
 	local_irq_restore(flags);
 }
-
-/* By default: disable tracing after the dump */
-void ftrace_dump(enum ftrace_dump_mode oops_dump_mode)
-{
-	__ftrace_dump(true, oops_dump_mode);
-}
 EXPORT_SYMBOL_GPL(ftrace_dump);
 
 __init static int tracer_alloc_buffers(void)
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index f95d65da6db8..7360674ea049 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -278,10 +278,14 @@ struct tracer {
 	enum print_line_t	(*print_line)(struct trace_iterator *iter);
 	/* If you handled the flag setting, return 0 */
 	int			(*set_flag)(u32 old_flags, u32 bit, int set);
+	/* Return 0 if OK with change, else return non-zero */
+	int			(*flag_changed)(struct tracer *tracer,
+						u32 mask, int set);
 	struct tracer		*next;
 	struct tracer_flags	*flags;
 	int			print_max;
 	int			use_max_tr;
+	bool			enabled;
 };
 
 
@@ -826,6 +830,9 @@ extern struct list_head ftrace_events;
 extern const char *__start___trace_bprintk_fmt[];
 extern const char *__stop___trace_bprintk_fmt[];
 
+int trace_keep_overwrite(struct tracer *tracer, u32 mask, int set);
+int set_tracer_flag(unsigned int mask, int enabled);
+
 #undef FTRACE_ENTRY
 #define FTRACE_ENTRY(call, struct_name, id, tstruct, print, filter)	\
 	extern struct ftrace_event_call					\
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 006d5c9b2615..4d7cd25aeece 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -777,7 +777,11 @@ static int filter_set_pred(struct event_filter *filter,
 
 static void __free_preds(struct event_filter *filter)
 {
+	int i;
+
 	if (filter->preds) {
+		for (i = 0; i < filter->n_preds; i++)
+			kfree(filter->preds[i].ops);
 		kfree(filter->preds);
 		filter->preds = NULL;
 	}
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index 99d20e920368..8dd139a3f6c7 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -32,7 +32,7 @@ enum {
 
 static int trace_type __read_mostly;
 
-static int save_lat_flag;
+static int save_flags;
 
 static void stop_irqsoff_tracer(struct trace_array *tr, int graph);
 static int start_irqsoff_tracer(struct trace_array *tr, int graph);
@@ -557,8 +557,11 @@ static void stop_irqsoff_tracer(struct trace_array *tr, int graph)
 
 static void __irqsoff_tracer_init(struct trace_array *tr)
 {
-	save_lat_flag = trace_flags & TRACE_ITER_LATENCY_FMT;
-	trace_flags |= TRACE_ITER_LATENCY_FMT;
+	save_flags = trace_flags;
+
+	/* non overwrite screws up the latency tracers */
+	set_tracer_flag(TRACE_ITER_OVERWRITE, 1);
+	set_tracer_flag(TRACE_ITER_LATENCY_FMT, 1);
 
 	tracing_max_latency = 0;
 	irqsoff_trace = tr;
@@ -572,10 +575,13 @@ static void __irqsoff_tracer_init(struct trace_array *tr)
 
 static void irqsoff_tracer_reset(struct trace_array *tr)
 {
+	int lat_flag = save_flags & TRACE_ITER_LATENCY_FMT;
+	int overwrite_flag = save_flags & TRACE_ITER_OVERWRITE;
+
 	stop_irqsoff_tracer(tr, is_graph());
 
-	if (!save_lat_flag)
-		trace_flags &= ~TRACE_ITER_LATENCY_FMT;
+	set_tracer_flag(TRACE_ITER_LATENCY_FMT, lat_flag);
+	set_tracer_flag(TRACE_ITER_OVERWRITE, overwrite_flag);
 }
 
 static void irqsoff_tracer_start(struct trace_array *tr)
@@ -608,6 +614,7 @@ static struct tracer irqsoff_tracer __read_mostly =
 	.print_line     = irqsoff_print_line,
 	.flags		= &tracer_flags,
 	.set_flag	= irqsoff_set_flag,
+	.flag_changed	= trace_keep_overwrite,
 #ifdef CONFIG_FTRACE_SELFTEST
 	.selftest    = trace_selftest_startup_irqsoff,
 #endif
@@ -641,6 +648,7 @@ static struct tracer preemptoff_tracer __read_mostly =
 	.print_line     = irqsoff_print_line,
 	.flags		= &tracer_flags,
 	.set_flag	= irqsoff_set_flag,
+	.flag_changed	= trace_keep_overwrite,
 #ifdef CONFIG_FTRACE_SELFTEST
 	.selftest    = trace_selftest_startup_preemptoff,
 #endif
@@ -676,6 +684,7 @@ static struct tracer preemptirqsoff_tracer __read_mostly =
 	.print_line     = irqsoff_print_line,
 	.flags		= &tracer_flags,
 	.set_flag	= irqsoff_set_flag,
+	.flag_changed	= trace_keep_overwrite,
 #ifdef CONFIG_FTRACE_SELFTEST
 	.selftest    = trace_selftest_startup_preemptirqsoff,
 #endif
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index ff791ea48b57..9eadedc9b4a8 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -36,7 +36,7 @@ static void __wakeup_reset(struct trace_array *tr);
 static int wakeup_graph_entry(struct ftrace_graph_ent *trace);
 static void wakeup_graph_return(struct ftrace_graph_ret *trace);
 
-static int save_lat_flag;
+static int save_flags;
 
 #define TRACE_DISPLAY_GRAPH     1
 
@@ -539,8 +539,11 @@ static void stop_wakeup_tracer(struct trace_array *tr)
 
 static int __wakeup_tracer_init(struct trace_array *tr)
 {
-	save_lat_flag = trace_flags & TRACE_ITER_LATENCY_FMT;
-	trace_flags |= TRACE_ITER_LATENCY_FMT;
+	save_flags = trace_flags;
+
+	/* non overwrite screws up the latency tracers */
+	set_tracer_flag(TRACE_ITER_OVERWRITE, 1);
+	set_tracer_flag(TRACE_ITER_LATENCY_FMT, 1);
 
 	tracing_max_latency = 0;
 	wakeup_trace = tr;
@@ -562,12 +565,15 @@ static int wakeup_rt_tracer_init(struct trace_array *tr)
 
 static void wakeup_tracer_reset(struct trace_array *tr)
 {
+	int lat_flag = save_flags & TRACE_ITER_LATENCY_FMT;
+	int overwrite_flag = save_flags & TRACE_ITER_OVERWRITE;
+
 	stop_wakeup_tracer(tr);
 	/* make sure we put back any tasks we are tracing */
 	wakeup_reset(tr);
 
-	if (!save_lat_flag)
-		trace_flags &= ~TRACE_ITER_LATENCY_FMT;
+	set_tracer_flag(TRACE_ITER_LATENCY_FMT, lat_flag);
+	set_tracer_flag(TRACE_ITER_OVERWRITE, overwrite_flag);
 }
 
 static void wakeup_tracer_start(struct trace_array *tr)
@@ -593,6 +599,7 @@ static struct tracer wakeup_tracer __read_mostly =
 	.print_line	= wakeup_print_line,
 	.flags		= &tracer_flags,
 	.set_flag	= wakeup_set_flag,
+	.flag_changed	= trace_keep_overwrite,
 #ifdef CONFIG_FTRACE_SELFTEST
 	.selftest    = trace_selftest_startup_wakeup,
 #endif
@@ -614,6 +621,7 @@ static struct tracer wakeup_rt_tracer __read_mostly =
 	.print_line	= wakeup_print_line,
 	.flags		= &tracer_flags,
 	.set_flag	= wakeup_set_flag,
+	.flag_changed	= trace_keep_overwrite,
 #ifdef CONFIG_FTRACE_SELFTEST
 	.selftest    = trace_selftest_startup_wakeup,
 #endif
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index 288541f977fb..09fd98afd266 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -461,8 +461,6 @@ trace_selftest_startup_function(struct tracer *trace, struct trace_array *tr)
 /* Maximum number of functions to trace before diagnosing a hang */
 #define GRAPH_MAX_FUNC_TEST	100000000
 
-static void
-__ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode);
 static unsigned int graph_hang_thresh;
 
 /* Wrap the real function entry probe to avoid possible hanging */
@@ -472,8 +470,11 @@ static int trace_graph_entry_watchdog(struct ftrace_graph_ent *trace)
 	if (unlikely(++graph_hang_thresh > GRAPH_MAX_FUNC_TEST)) {
 		ftrace_graph_stop();
 		printk(KERN_WARNING "BUG: Function graph tracer hang!\n");
-		if (ftrace_dump_on_oops)
-			__ftrace_dump(false, DUMP_ALL);
+		if (ftrace_dump_on_oops) {
+			ftrace_dump(DUMP_ALL);
+			/* ftrace_dump() disables tracing */
+			tracing_on();
+		}
 		return 0;
 	}
 
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index d4545f49242e..8298997c2486 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -20,13 +20,24 @@
 
 #define STACK_TRACE_ENTRIES 500
 
+#ifdef CC_USING_FENTRY
+# define fentry		1
+#else
+# define fentry		0
+#endif
+
 static unsigned long stack_dump_trace[STACK_TRACE_ENTRIES+1] =
 	 { [0 ... (STACK_TRACE_ENTRIES)] = ULONG_MAX };
 static unsigned stack_dump_index[STACK_TRACE_ENTRIES];
 
+/*
+ * Reserve one entry for the passed in ip. This will allow
+ * us to remove most or all of the stack size overhead
+ * added by the stack tracer itself.
+ */
 static struct stack_trace max_stack_trace = {
-	.max_entries		= STACK_TRACE_ENTRIES,
-	.entries		= stack_dump_trace,
+	.max_entries		= STACK_TRACE_ENTRIES - 1,
+	.entries		= &stack_dump_trace[1],
 };
 
 static unsigned long max_stack_size;
@@ -40,25 +51,34 @@ static DEFINE_MUTEX(stack_sysctl_mutex);
 int stack_tracer_enabled;
 static int last_stack_tracer_enabled;
 
-static inline void check_stack(void)
+static inline void
+check_stack(unsigned long ip, unsigned long *stack)
 {
 	unsigned long this_size, flags;
 	unsigned long *p, *top, *start;
+	static int tracer_frame;
+	int frame_size = ACCESS_ONCE(tracer_frame);
 	int i;
 
-	this_size = ((unsigned long)&this_size) & (THREAD_SIZE-1);
+	this_size = ((unsigned long)stack) & (THREAD_SIZE-1);
 	this_size = THREAD_SIZE - this_size;
+	/* Remove the frame of the tracer */
+	this_size -= frame_size;
 
 	if (this_size <= max_stack_size)
 		return;
 
 	/* we do not handle interrupt stacks yet */
-	if (!object_is_on_stack(&this_size))
+	if (!object_is_on_stack(stack))
 		return;
 
 	local_irq_save(flags);
 	arch_spin_lock(&max_stack_lock);
 
+	/* In case another CPU set the tracer_frame on us */
+	if (unlikely(!frame_size))
+		this_size -= tracer_frame;
+
 	/* a race could have already updated it */
 	if (this_size <= max_stack_size)
 		goto out;
@@ -71,10 +91,18 @@ static inline void check_stack(void)
 	save_stack_trace(&max_stack_trace);
 
 	/*
+	 * Add the passed in ip from the function tracer.
+	 * Searching for this on the stack will skip over
+	 * most of the overhead from the stack tracer itself.
+	 */
+	stack_dump_trace[0] = ip;
+	max_stack_trace.nr_entries++;
+
+	/*
 	 * Now find where in the stack these are.
 	 */
 	i = 0;
-	start = &this_size;
+	start = stack;
 	top = (unsigned long *)
 		(((unsigned long)start & ~(THREAD_SIZE-1)) + THREAD_SIZE);
 
@@ -98,6 +126,18 @@ static inline void check_stack(void)
 				found = 1;
 				/* Start the search from here */
 				start = p + 1;
+				/*
+				 * We do not want to show the overhead
+				 * of the stack tracer stack in the
+				 * max stack. If we haven't figured
+				 * out what that is, then figure it out
+				 * now.
+				 */
+				if (unlikely(!tracer_frame) && i == 1) {
+					tracer_frame = (p - stack) *
+						sizeof(unsigned long);
+					max_stack_size -= tracer_frame;
+				}
 			}
 		}
 
@@ -113,6 +153,7 @@ static inline void check_stack(void)
 static void
 stack_trace_call(unsigned long ip, unsigned long parent_ip)
 {
+	unsigned long stack;
 	int cpu;
 
 	if (unlikely(!ftrace_enabled || stack_trace_disabled))
@@ -125,7 +166,26 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip)
 	if (per_cpu(trace_active, cpu)++ != 0)
 		goto out;
 
-	check_stack();
+	/*
+	 * When fentry is used, the traced function does not get
+	 * its stack frame set up, and we lose the parent.
+	 * The ip is pretty useless because the function tracer
+	 * was called before that function set up its stack frame.
+	 * In this case, we use the parent ip.
+	 *
+	 * By adding the return address of either the parent ip
+	 * or the current ip we can disregard most of the stack usage
+	 * caused by the stack tracer itself.
+	 *
+	 * The function tracer always reports the address of where the
+	 * mcount call was, but the stack will hold the return address.
+	 */
+	if (fentry)
+		ip = parent_ip;
+	else
+		ip += MCOUNT_INSN_SIZE;
+
+	check_stack(ip, &stack);
 
  out:
 	per_cpu(trace_active, cpu)--;
@@ -324,7 +384,7 @@ static const struct file_operations stack_trace_filter_fops = {
 	.open = stack_trace_filter_open,
 	.read = seq_read,
 	.write = ftrace_filter_write,
-	.llseek = ftrace_regex_lseek,
+	.llseek = ftrace_filter_lseek,
 	.release = ftrace_regex_release,
 };
 
@@ -373,6 +433,8 @@ static __init int stack_trace_init(void)
 	struct dentry *d_tracer;
 
 	d_tracer = tracing_init_dentry();
+	if (!d_tracer)
+		return 0;
 
 	trace_create_file("stack_max_size", 0644, d_tracer,
 			&max_stack_size, &stack_max_size_fops);
diff --git a/kernel/trace/trace_stat.c b/kernel/trace/trace_stat.c
index 96cffb269e73..847f88a6194b 100644
--- a/kernel/trace/trace_stat.c
+++ b/kernel/trace/trace_stat.c
@@ -307,6 +307,8 @@ static int tracing_stat_init(void)
 	struct dentry *d_tracing;
 
 	d_tracing = tracing_init_dentry();
+	if (!d_tracing)
+		return 0;
 
 	stat_dir = debugfs_create_dir("trace_stat", d_tracing);
 	if (!stat_dir)
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 96fc73369099..c9ce09addacd 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -305,6 +305,8 @@ void ftrace_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 	struct ring_buffer *buffer;
 	int size;
 	int syscall_nr;
+	unsigned long irq_flags;
+	int pc;
 
 	syscall_nr = syscall_get_nr(current, regs);
 	if (syscall_nr < 0)
@@ -318,8 +320,11 @@ void ftrace_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 
 	size = sizeof(*entry) + sizeof(unsigned long) * sys_data->nb_args;
 
+	local_save_flags(irq_flags);
+	pc = preempt_count();
+
 	event = trace_current_buffer_lock_reserve(&buffer,
-			sys_data->enter_event->event.type, size, 0, 0);
+			sys_data->enter_event->event.type, size, irq_flags, pc);
 	if (!event)
 		return;
 
@@ -329,7 +334,8 @@ void ftrace_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 
 	if (!filter_current_check_discard(buffer, sys_data->enter_event,
 					  entry, event))
-		trace_current_buffer_unlock_commit(buffer, event, 0, 0);
+		trace_current_buffer_unlock_commit(buffer, event,
+						   irq_flags, pc);
 }
 
 void ftrace_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
@@ -339,6 +345,8 @@ void ftrace_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 	struct ring_buffer_event *event;
 	struct ring_buffer *buffer;
 	int syscall_nr;
+	unsigned long irq_flags;
+	int pc;
 
 	syscall_nr = syscall_get_nr(current, regs);
 	if (syscall_nr < 0)
@@ -350,8 +358,12 @@ void ftrace_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 	if (!sys_data)
 		return;
 
+	local_save_flags(irq_flags);
+	pc = preempt_count();
+
 	event = trace_current_buffer_lock_reserve(&buffer,
-			sys_data->exit_event->event.type, sizeof(*entry), 0, 0);
+			sys_data->exit_event->event.type, sizeof(*entry),
+			irq_flags, pc);
 	if (!event)
 		return;
 
@@ -361,7 +373,8 @@ void ftrace_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 
 	if (!filter_current_check_discard(buffer, sys_data->exit_event,
 					  entry, event))
-		trace_current_buffer_unlock_commit(buffer, event, 0, 0);
+		trace_current_buffer_unlock_commit(buffer, event,
+						   irq_flags, pc);
 }
 
 int reg_event_syscall_enter(struct ftrace_event_call *call)