Skip to contentSkip to conversation

perf, trace: Remove superfluous rcu_read_lock()

tip:perf/core tip-bot for Peter Zijlstra 1 participant 1 message Jun 9, 2010

lore
Share & tools
lore
#0 lore raw
Commit-ID:  8ed92280be013180e24c84456ab6babcb07037cc
Gitweb:     http://git.kernel.org/tip/8ed92280be013180e24c84456ab6babcb07037cc
Author:     Peter Zijlstra <[email protected]>
AuthorDate: Fri, 21 May 2010 15:13:59 +0200
Committer:  Ingo Molnar <[email protected]>
CommitDate: Wed, 9 Jun 2010 11:12:33 +0200

perf, trace: Remove superfluous rcu_read_lock()

__DO_TRACE() already calls the callbacks under rcu_read_lock_sched(), which is sufficient for our needs, avoid doing it again.

Cc Steven Rostedt <[email protected]>
Cc Frederic Weisbecker <[email protected]>

LKML-Reference: <new-submission>

---
 kernel/perf_event.c |    2 --
 1 files changed, 0 insertions(+), 2 deletions(-)
kernel/perf_event.c +0 -2
index 4bd3b59..b39bec3 100644
@@ -4613,12 +4613,10 @@ void perf_tp_event(u64 addr, u64 count, void *record, int entry_size,
 	perf_sample_data_init(&data, addr);
 	data.raw = &raw;
 
-	rcu_read_lock();
 	hlist_for_each_entry_rcu(event, node, head, hlist_entry) {
 		if (perf_tp_event_match(event, &data, regs))
 			perf_swevent_add(event, count, 1, &data, regs);
 	}
-	rcu_read_unlock();
 
 	perf_swevent_put_recursion_context(rctx);
 }