perf: Fix race in removing an event

[pandora-kernel.git] / kernel / events / core.c

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 1d1edcb..14c111c 100644 (file)
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1180,6 +1180,11 @@ 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
  *
@@ -1188,12 +1193,15 @@ 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;
@@ -1218,10 +1226,14 @@ 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);
 
@@ -1230,12 +1242,12 @@ 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);
@@ -1252,6 +1264,8 @@ 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);
 }
@@ -3046,10 +3060,7 @@ int perf_event_release_kernel(struct perf_event *event)
         *     to trigger the AB-BA case.
         */
        mutex_lock_nested(&ctx->mutex, SINGLE_DEPTH_NESTING);
-       raw_spin_lock_irq(&ctx->lock);
-       perf_group_detach(event);
-       raw_spin_unlock_irq(&ctx->lock);
-       perf_remove_from_context(event);
+       perf_remove_from_context(event, true);
        mutex_unlock(&ctx->mutex);
 
        free_event(event);
@@ -6459,7 +6470,7 @@ 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
@@ -6469,7 +6480,7 @@ 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);
                }
@@ -6622,13 +6633,7 @@ __perf_event_exit_task(struct perf_event *child_event,
                         struct perf_event_context *child_ctx,
                         struct task_struct *child)
 {
-       if (child_event->parent) {
-               raw_spin_lock_irq(&child_ctx->lock);
-               perf_group_detach(child_event);
-               raw_spin_unlock_irq(&child_ctx->lock);
-       }
-
-       perf_remove_from_context(child_event);
+       perf_remove_from_context(child_event, !!child_event->parent);
 
        /*
         * It can happen that the parent exits first, and has events
@@ -7113,14 +7118,14 @@ 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();
 }