[tip:perf/urgent] perf/core: Fix lock inversion between perf,trace,cpuhp

[tip-bot for Peter Zijlstra <tipbot@xxxxxxxxx>]

Commit-ID:  25695067c32e34047b5490436a90af507fda1c2e
Gitweb:     https://git.kernel.org/tip/25695067c32e34047b5490436a90af507fda1c2e
Author:     Peter Zijlstra <peterz@xxxxxxxxxxxxx>
AuthorDate: Tue, 9 Jan 2018 13:10:30 +0100
Committer:  Ingo Molnar <mingo@xxxxxxxxxx>
CommitDate: Wed, 24 Jan 2018 10:07:23 +0100

perf/core: Fix lock inversion between perf,trace,cpuhp

Lockdep gifted us with noticing the following race:

        perf_trace_init()
          perf_trace_event_init()
            perf_trace_event_reg()
              tp_event->class->reg() := tracepoint_probe_register
                  trace_point_add_func()

          perf_event_init_cpu()

        perf_event_task_disable()
          mutex_lock(&current->perf_event_mutex)

        do_exit()
          task_work_run()
            __fput()
              perf_release()
                perf_event_release_kernel()
                  free_event()
                    _free_event()
                      event->destroy() := perf_trace_destroy

Fix that by moving the free_event() out from under the locks.

Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Steven Rostedt (VMware) <rostedt@xxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
---
 kernel/events/core.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 4df5b69..2d80824 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1231,6 +1231,10 @@ static void put_ctx(struct perf_event_context *ctx)
  *	      perf_event_context::lock
  *	    perf_event::mmap_mutex
  *	    mmap_sem
+ *
+ *    cpu_hotplug_lock
+ *      pmus_lock
+ *	  cpuctx->mutex / perf_event_context::mutex
  */
 static struct perf_event_context *
 perf_event_ctx_lock_nested(struct perf_event *event, int nesting)
@@ -4196,6 +4200,7 @@ int perf_event_release_kernel(struct perf_event *event)
 {
 	struct perf_event_context *ctx = event->ctx;
 	struct perf_event *child, *tmp;
+	LIST_HEAD(free_list);
 
 	/*
 	 * If we got here through err_file: fput(event_file); we will not have
@@ -4268,8 +4273,7 @@ again:
 					       struct perf_event, child_list);
 		if (tmp == child) {
 			perf_remove_from_context(child, DETACH_GROUP);
-			list_del(&child->child_list);
-			free_event(child);
+			list_move(&child->child_list, &free_list);
 			/*
 			 * This matches the refcount bump in inherit_event();
 			 * this can't be the last reference.
@@ -4284,6 +4288,11 @@ again:
 	}
 	mutex_unlock(&event->child_mutex);
 
+	list_for_each_entry_safe(child, tmp, &free_list, child_list) {
+		list_del(&child->child_list);
+		free_event(child);
+	}
+
 no_ctx:
 	put_event(event); /* Must be the 'last' reference */
 	return 0;
--
To unsubscribe from this list: send the line "unsubscribe linux-tip-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html