1 files changed, 81 insertions, 66 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 5129b120105..ed50b094321 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1444,6 +1444,11 @@ group_sched_out(struct perf_event *group_event,
 		cpuctx->exclusive = 0;
 }
 
+struct remove_event {
+	struct perf_event *event;
+	bool detach_group;
+};
+
 /*
  * Cross CPU call to remove a performance event
  *
@@ -1452,12 +1457,15 @@ group_sched_out(struct perf_event *group_event,
  */
 static int __perf_remove_from_context(void *info)
 {
-	struct perf_event *event = info;
+	struct remove_event *re = info;
+	struct perf_event *event = re->event;
 	struct perf_event_context *ctx = event->ctx;
 	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
 
 	raw_spin_lock(&ctx->lock);
 	event_sched_out(event, cpuctx, ctx);
+	if (re->detach_group)
+		perf_group_detach(event);
 	list_del_event(event, ctx);
 	if (!ctx->nr_events && cpuctx->task_ctx == ctx) {
 		ctx->is_active = 0;
@@ -1482,10 +1490,14 @@ static int __perf_remove_from_context(void *info)
  * When called from perf_event_exit_task, it's OK because the
  * context has been detached from its task.
  */
-static void perf_remove_from_context(struct perf_event *event)
+static void perf_remove_from_context(struct perf_event *event, bool detach_group)
 {
 	struct perf_event_context *ctx = event->ctx;
 	struct task_struct *task = ctx->task;
+	struct remove_event re = {
+		.event = event,
+		.detach_group = detach_group,
+	};
 
 	lockdep_assert_held(&ctx->mutex);
 
@@ -1494,12 +1506,12 @@ static void perf_remove_from_context(struct perf_event *event)
 		 * Per cpu events are removed via an smp call and
 		 * the removal is always successful.
 		 */
-		cpu_function_call(event->cpu, __perf_remove_from_context, event);
+		cpu_function_call(event->cpu, __perf_remove_from_context, &re);
 		return;
 	}
 
 retry:
-	if (!task_function_call(task, __perf_remove_from_context, event))
+	if (!task_function_call(task, __perf_remove_from_context, &re))
 		return;
 
 	raw_spin_lock_irq(&ctx->lock);
@@ -1516,6 +1528,8 @@ retry:
 	 * Since the task isn't running, its safe to remove the event, us
 	 * holding the ctx->lock ensures the task won't get scheduled in.
 	 */
+	if (detach_group)
+		perf_group_detach(event);
 	list_del_event(event, ctx);
 	raw_spin_unlock_irq(&ctx->lock);
 }
@@ -1664,6 +1678,8 @@ event_sched_in(struct perf_event *event,
 	u64 tstamp = perf_event_time(event);
 	int ret = 0;
 
+	lockdep_assert_held(&ctx->lock);
+
 	if (event->state <= PERF_EVENT_STATE_OFF)
 		return 0;
 
@@ -3235,7 +3251,8 @@ static void __free_event(struct perf_event *event)
 
 	call_rcu(&event->rcu_head, free_event_rcu);
 }
-static void free_event(struct perf_event *event)
+
+static void _free_event(struct perf_event *event)
 {
 	irq_work_sync(&event->pending);
 
@@ -3263,45 +3280,31 @@ static void free_event(struct perf_event *event)
 	if (is_cgroup_event(event))
 		perf_detach_cgroup(event);
 
-
 	__free_event(event);
 }
 
-int perf_event_release_kernel(struct perf_event *event)
+/*
+ * Used to free events which have a known refcount of 1, such as in error paths
+ * where the event isn't exposed yet and inherited events.
+ */
+static void free_event(struct perf_event *event)
 {
-	struct perf_event_context *ctx = event->ctx;
-
-	WARN_ON_ONCE(ctx->parent_ctx);
-	/*
-	 * There are two ways this annotation is useful:
-	 *
-	 *  1) there is a lock recursion from perf_event_exit_task
-	 *     see the comment there.
-	 *
-	 *  2) there is a lock-inversion with mmap_sem through
-	 *     perf_event_read_group(), which takes faults while
-	 *     holding ctx->mutex, however this is called after
-	 *     the last filedesc died, so there is no possibility
-	 *     to trigger the AB-BA case.
-	 */
-	mutex_lock_nested(&ctx->mutex, SINGLE_DEPTH_NESTING);
-	raw_spin_lock_irq(&ctx->lock);
-	perf_group_detach(event);
-	raw_spin_unlock_irq(&ctx->lock);
-	perf_remove_from_context(event);
-	mutex_unlock(&ctx->mutex);
-
-	free_event(event);
+	if (WARN(atomic_long_cmpxchg(&event->refcount, 1, 0) != 1,
+				"unexpected event refcount: %ld; ptr=%p\n",
+				atomic_long_read(&event->refcount), event)) {
+		/* leak to avoid use-after-free */
+		return;
+	}
 
-	return 0;
+	_free_event(event);
 }
-EXPORT_SYMBOL_GPL(perf_event_release_kernel);
 
 /*
  * Called when the last reference to the file is gone.
  */
 static void put_event(struct perf_event *event)
 {
+	struct perf_event_context *ctx = event->ctx;
 	struct task_struct *owner;
 
 	if (!atomic_long_dec_and_test(&event->refcount))
@@ -3340,8 +3343,32 @@ static void put_event(struct perf_event *event)
 		put_task_struct(owner);
 	}
 
-	perf_event_release_kernel(event);
+	WARN_ON_ONCE(ctx->parent_ctx);
+	/*
+	 * There are two ways this annotation is useful:
+	 *
+	 *  1) there is a lock recursion from perf_event_exit_task
+	 *     see the comment there.
+	 *
+	 *  2) there is a lock-inversion with mmap_sem through
+	 *     perf_event_read_group(), which takes faults while
+	 *     holding ctx->mutex, however this is called after
+	 *     the last filedesc died, so there is no possibility
+	 *     to trigger the AB-BA case.
+	 */
+	mutex_lock_nested(&ctx->mutex, SINGLE_DEPTH_NESTING);
+	perf_remove_from_context(event, true);
+	mutex_unlock(&ctx->mutex);
+
+	_free_event(event);
+}
+
+int perf_event_release_kernel(struct perf_event *event)
+{
+	put_event(event);
+	return 0;
 }
+EXPORT_SYMBOL_GPL(perf_event_release_kernel);
 
 static int perf_release(struct inode *inode, struct file *file)
 {
@@ -7070,20 +7097,26 @@ SYSCALL_DEFINE5(perf_event_open,
 		}
 	}
 
+	if (task && group_leader &&
+	    group_leader->attr.inherit != attr.inherit) {
+		err = -EINVAL;
+		goto err_task;
+	}
+
 	get_online_cpus();
 
 	event = perf_event_alloc(&attr, cpu, task, group_leader, NULL,
 				 NULL, NULL);
 	if (IS_ERR(event)) {
 		err = PTR_ERR(event);
-		goto err_task;
+		goto err_cpus;
 	}
 
 	if (flags & PERF_FLAG_PID_CGROUP) {
 		err = perf_cgroup_connect(pid, event, &attr, group_leader);
 		if (err) {
 			__free_event(event);
-			goto err_task;
+			goto err_cpus;
 		}
 	}
 
@@ -7180,7 +7213,7 @@ SYSCALL_DEFINE5(perf_event_open,
 		struct perf_event_context *gctx = group_leader->ctx;
 
 		mutex_lock(&gctx->mutex);
-		perf_remove_from_context(group_leader);
+		perf_remove_from_context(group_leader, false);
 
 		/*
 		 * Removing from the context ends up with disabled
@@ -7190,7 +7223,7 @@ SYSCALL_DEFINE5(perf_event_open,
 		perf_event__state_init(group_leader);
 		list_for_each_entry(sibling, &group_leader->sibling_list,
 				    group_entry) {
-			perf_remove_from_context(sibling);
+			perf_remove_from_context(sibling, false);
 			perf_event__state_init(sibling);
 			put_ctx(gctx);
 		}
@@ -7245,8 +7278,9 @@ err_context:
 	put_ctx(ctx);
 err_alloc:
 	free_event(event);
-err_task:
+err_cpus:
 	put_online_cpus();
+err_task:
 	if (task)
 		put_task_struct(task);
 err_group_fd:
@@ -7320,7 +7354,7 @@ void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu)
 	mutex_lock(&src_ctx->mutex);
 	list_for_each_entry_safe(event, tmp, &src_ctx->event_list,
 				 event_entry) {
-		perf_remove_from_context(event);
+		perf_remove_from_context(event, false);
 		unaccount_event_cpu(event, src_cpu);
 		put_ctx(src_ctx);
 		list_add(&event->migrate_entry, &events);
@@ -7382,13 +7416,7 @@ __perf_event_exit_task(struct perf_event *child_event,
 			 struct perf_event_context *child_ctx,
 			 struct task_struct *child)
 {
-	if (child_event->parent) {
-		raw_spin_lock_irq(&child_ctx->lock);
-		perf_group_detach(child_event);
-		raw_spin_unlock_irq(&child_ctx->lock);
-	}
-
-	perf_remove_from_context(child_event);
+	perf_remove_from_context(child_event, true);
 
 	/*
 	 * It can happen that the parent exits first, and has events
@@ -7403,7 +7431,7 @@ __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, *tmp;
+	struct perf_event *child_event;
 	struct perf_event_context *child_ctx;
 	unsigned long flags;
 
@@ -7457,24 +7485,9 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn)
 	 */
 	mutex_lock(&child_ctx->mutex);
 
-again:
-	list_for_each_entry_safe(child_event, tmp, &child_ctx->pinned_groups,
-				 group_entry)
+	list_for_each_entry_rcu(child_event, &child_ctx->event_list, event_entry)
 		__perf_event_exit_task(child_event, child_ctx, child);
 
-	list_for_each_entry_safe(child_event, tmp, &child_ctx->flexible_groups,
-				 group_entry)
-		__perf_event_exit_task(child_event, child_ctx, child);
-
-	/*
-	 * If the last event was a group event, it will have appended all
-	 * its siblings to the list, but we obtained 'tmp' before that which
-	 * will still point to the list head terminating the iteration.
-	 */
-	if (!list_empty(&child_ctx->pinned_groups) ||
-	    !list_empty(&child_ctx->flexible_groups))
-		goto again;
-
 	mutex_unlock(&child_ctx->mutex);
 
 	put_ctx(child_ctx);
@@ -7739,6 +7752,8 @@ int perf_event_init_context(struct task_struct *child, int ctxn)
 	 * swapped under us.
 	 */
 	parent_ctx = perf_pin_task_context(parent, ctxn);
+	if (!parent_ctx)
+		return 0;
 
 	/*
 	 * No need to check if parent_ctx != NULL here; since we saw
@@ -7872,14 +7887,14 @@ static void perf_pmu_rotate_stop(struct pmu *pmu)
 
 static void __perf_event_exit_context(void *__info)
 {
+	struct remove_event re = { .detach_group = false };
 	struct perf_event_context *ctx = __info;
-	struct perf_event *event;
 
 	perf_pmu_rotate_stop(ctx->pmu);
 
 	rcu_read_lock();
-	list_for_each_entry_rcu(event, &ctx->event_list, event_entry)
-		__perf_remove_from_context(event);
+	list_for_each_entry_rcu(re.event, &ctx->event_list, event_entry)
+		__perf_remove_from_context(&re);
 	rcu_read_unlock();
 }