1 files changed, 97 insertions, 102 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index d1a1bee3522..58690af323e 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -25,11 +25,11 @@
 #include <linux/reboot.h>
 #include <linux/vmstat.h>
 #include <linux/device.h>
+#include <linux/export.h>
 #include <linux/vmalloc.h>
 #include <linux/hardirq.h>
 #include <linux/rculist.h>
 #include <linux/uaccess.h>
-#include <linux/suspend.h>
 #include <linux/syscalls.h>
 #include <linux/anon_inodes.h>
 #include <linux/kernel_stat.h>
@@ -185,6 +185,9 @@ 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)
@@ -2171,9 +2174,10 @@ static void perf_event_context_sched_in(struct perf_event_context *ctx,
 	 */
 	cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE);
 
-	perf_event_sched_in(cpuctx, ctx, task);
+	if (ctx->nr_events)
+		cpuctx->task_ctx = ctx;
 
-	cpuctx->task_ctx = ctx;
+	perf_event_sched_in(cpuctx, cpuctx->task_ctx, task);
 
 	perf_pmu_enable(ctx->pmu);
 	perf_ctx_unlock(cpuctx, ctx);
@@ -3190,12 +3194,33 @@ static unsigned int perf_poll(struct file *file, poll_table *wait)
 	struct ring_buffer *rb;
 	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()
+	 */
+	mutex_lock(&event->mmap_mutex);
+
 	rcu_read_lock();
 	rb = rcu_dereference(event->rb);
-	if (rb)
+	if (rb) {
+		ring_buffer_attach(event, rb);
 		events = atomic_xchg(&rb->poll, 0);
+	}
 	rcu_read_unlock();
 
+	mutex_unlock(&event->mmap_mutex);
+
 	poll_wait(file, &event->waitq, wait);
 
 	return events;
@@ -3496,6 +3521,53 @@ unlock:
 	return ret;
 }
 
+static void ring_buffer_attach(struct perf_event *event,
+			       struct ring_buffer *rb)
+{
+	unsigned long flags;
+
+	if (!list_empty(&event->rb_entry))
+		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:
+	spin_unlock_irqrestore(&rb->event_lock, flags);
+}
+
+static void ring_buffer_detach(struct perf_event *event,
+			       struct ring_buffer *rb)
+{
+	unsigned long flags;
+
+	if (list_empty(&event->rb_entry))
+		return;
+
+	spin_lock_irqsave(&rb->event_lock, flags);
+	list_del_init(&event->rb_entry);
+	wake_up_all(&event->waitq);
+	spin_unlock_irqrestore(&rb->event_lock, flags);
+}
+
+static void ring_buffer_wakeup(struct perf_event *event)
+{
+	struct ring_buffer *rb;
+
+	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:
+	rcu_read_unlock();
+}
+
 static void rb_free_rcu(struct rcu_head *rcu_head)
 {
 	struct ring_buffer *rb;
@@ -3521,9 +3593,19 @@ 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);
+
 	call_rcu(&rb->rcu_head, rb_free_rcu);
 }
 
@@ -3544,8 +3626,9 @@ static void perf_mmap_close(struct vm_area_struct *vma)
 		struct ring_buffer *rb = event->rb;
 
 		atomic_long_sub((size >> PAGE_SHIFT) + 1, &user->locked_vm);
-		vma->vm_mm->locked_vm -= event->mmap_locked;
+		vma->vm_mm->pinned_vm -= event->mmap_locked;
 		rcu_assign_pointer(event->rb, NULL);
+		ring_buffer_detach(event, rb);
 		mutex_unlock(&event->mmap_mutex);
 
 		ring_buffer_put(rb);
@@ -3625,7 +3708,7 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 
 	lock_limit = rlimit(RLIMIT_MEMLOCK);
 	lock_limit >>= PAGE_SHIFT;
-	locked = vma->vm_mm->locked_vm + extra;
+	locked = vma->vm_mm->pinned_vm + extra;
 
 	if ((locked > lock_limit) && perf_paranoid_tracepoint_raw() &&
 		!capable(CAP_IPC_LOCK)) {
@@ -3651,7 +3734,7 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 	atomic_long_add(user_extra, &user->locked_vm);
 	event->mmap_locked = extra;
 	event->mmap_user = get_current_user();
-	vma->vm_mm->locked_vm += event->mmap_locked;
+	vma->vm_mm->pinned_vm += event->mmap_locked;
 
 unlock:
 	if (!ret)
@@ -3700,7 +3783,7 @@ static const struct file_operations perf_fops = {
 
 void perf_event_wakeup(struct perf_event *event)
 {
-	wake_up_all(&event->waitq);
+	ring_buffer_wakeup(event);
 
 	if (event->pending_kill) {
 		kill_fasync(&event->fasync, SIGIO, event->pending_kill);
@@ -5822,6 +5905,8 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 	INIT_LIST_HEAD(&event->group_entry);
 	INIT_LIST_HEAD(&event->event_entry);
 	INIT_LIST_HEAD(&event->sibling_list);
+	INIT_LIST_HEAD(&event->rb_entry);
+
 	init_waitqueue_head(&event->waitq);
 	init_irq_work(&event->pending, perf_pending_event);
 
@@ -6028,6 +6113,8 @@ set:
 
 	old_rb = event->rb;
 	rcu_assign_pointer(event->rb, rb);
+	if (old_rb)
+		ring_buffer_detach(event, old_rb);
 	ret = 0;
 unlock:
 	mutex_unlock(&event->mmap_mutex);
@@ -6853,7 +6940,7 @@ static void __cpuinit perf_event_init_cpu(int cpu)
 	struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu);
 
 	mutex_lock(&swhash->hlist_mutex);
-	if (swhash->hlist_refcount > 0 && !swhash->swevent_hlist) {
+	if (swhash->hlist_refcount > 0) {
 		struct swevent_hlist *hlist;
 
 		hlist = kzalloc_node(sizeof(*hlist), GFP_KERNEL, cpu_to_node(cpu));
@@ -6942,14 +7029,7 @@ perf_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu)
 {
 	unsigned int cpu = (long)hcpu;
 
-	/*
-	 * Ignore suspend/resume action, the perf_pm_notifier will
-	 * take care of that.
-	 */
-	if (action & CPU_TASKS_FROZEN)
-		return NOTIFY_OK;
-
-	switch (action) {
+	switch (action & ~CPU_TASKS_FROZEN) {
 
 	case CPU_UP_PREPARE:
 	case CPU_DOWN_FAILED:
@@ -6968,90 +7048,6 @@ perf_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu)
 	return NOTIFY_OK;
 }
 
-static void perf_pm_resume_cpu(void *unused)
-{
-	struct perf_cpu_context *cpuctx;
-	struct perf_event_context *ctx;
-	struct pmu *pmu;
-	int idx;
-
-	idx = srcu_read_lock(&pmus_srcu);
-	list_for_each_entry_rcu(pmu, &pmus, entry) {
-		cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
-		ctx = cpuctx->task_ctx;
-
-		perf_ctx_lock(cpuctx, ctx);
-		perf_pmu_disable(cpuctx->ctx.pmu);
-
-		cpu_ctx_sched_out(cpuctx, EVENT_ALL);
-		if (ctx)
-			ctx_sched_out(ctx, cpuctx, EVENT_ALL);
-
-		perf_pmu_enable(cpuctx->ctx.pmu);
-		perf_ctx_unlock(cpuctx, ctx);
-	}
-	srcu_read_unlock(&pmus_srcu, idx);
-}
-
-static void perf_pm_suspend_cpu(void *unused)
-{
-	struct perf_cpu_context *cpuctx;
-	struct perf_event_context *ctx;
-	struct pmu *pmu;
-	int idx;
-
-	idx = srcu_read_lock(&pmus_srcu);
-	list_for_each_entry_rcu(pmu, &pmus, entry) {
-		cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
-		ctx = cpuctx->task_ctx;
-
-		perf_ctx_lock(cpuctx, ctx);
-		perf_pmu_disable(cpuctx->ctx.pmu);
-
-		perf_event_sched_in(cpuctx, ctx, current);
-
-		perf_pmu_enable(cpuctx->ctx.pmu);
-		perf_ctx_unlock(cpuctx, ctx);
-	}
-	srcu_read_unlock(&pmus_srcu, idx);
-}
-
-static int perf_resume(void)
-{
-	get_online_cpus();
-	smp_call_function(perf_pm_resume_cpu, NULL, 1);
-	put_online_cpus();
-
-	return NOTIFY_OK;
-}
-
-static int perf_suspend(void)
-{
-	get_online_cpus();
-	smp_call_function(perf_pm_suspend_cpu, NULL, 1);
-	put_online_cpus();
-
-	return NOTIFY_OK;
-}
-
-static int perf_pm(struct notifier_block *self, unsigned long action, void *ptr)
-{
-	switch (action) {
-	case PM_POST_HIBERNATION:
-	case PM_POST_SUSPEND:
-		return perf_resume();
-	case PM_HIBERNATION_PREPARE:
-	case PM_SUSPEND_PREPARE:
-		return perf_suspend();
-	default:
-		return NOTIFY_DONE;
-	}
-}
-
-static struct notifier_block perf_pm_notifier = {
-	.notifier_call = perf_pm,
-};
-
 void __init perf_event_init(void)
 {
 	int ret;
@@ -7066,7 +7062,6 @@ void __init perf_event_init(void)
 	perf_tp_register();
 	perf_cpu_notifier(perf_cpu_notify);
 	register_reboot_notifier(&perf_reboot_notifier);
-	register_pm_notifier(&perf_pm_notifier);
 
 	ret = init_hw_breakpoint();
 	WARN(ret, "hw_breakpoint initialization failed with: %d", ret);