In theory, almost every user of task->child->perf_event_ctxp[] is wrong. find_get_context() can install the new context at any moment, we need read_barrier_depends(). dbe08d82ce3967ccdf459f7951d02589cf967300 "perf: Fix find_get_context() vs perf_event_exit_task() race" added rcu_dereference() into perf_event_exit_task_context() to make the precedent, but this makes __rcu_dereference_check() unhappy. Use rcu_dereference_raw() to shut up the warning. Reported-by: Ingo Molnar <mingo@xxxxxxx> Signed-off-by: Oleg Nesterov <oleg@xxxxxxxxxx> --- kernel/perf_event.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) --- git/kernel/perf_event.c~6_rcu_check 2011-01-19 18:49:23.000000000 +0100 +++ git/kernel/perf_event.c 2011-01-21 18:41:02.000000000 +0100 @@ -6133,7 +6133,7 @@ static void perf_event_exit_task_context * scheduled, so we are now safe from rescheduling changing * our context. */ - child_ctx = rcu_dereference(child->perf_event_ctxp[ctxn]); + child_ctx = rcu_dereference_raw(child->perf_event_ctxp[ctxn]); task_ctx_sched_out(child_ctx, EVENT_ALL); /* -- 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
|