1 files changed, 30 insertions, 2 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index b0c95f0f06fd..6b17ac1b0c2a 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7458,7 +7458,19 @@ __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
@@ -7474,7 +7486,7 @@ __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])) {
@@ -7499,6 +7511,15 @@ 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
@@ -7509,6 +7530,13 @@ 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.