lkml.org 
[lkml]   [2009]   [Oct]   [3]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[PATCH 1/2] tracing: Check total refcount before releasing bufs in profile_enable failure
Date
When we call the profile_enable() callback of an event, we release the
shared perf event tracing buffers unconditionnaly in the failure path.
This is wrong because there may be other users of these. Then check the
total refcount before doing this.

Reported-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Li Zefan <lizf@cn.fujitsu.com>
---
kernel/trace/trace_event_profile.c | 15 ++++++++++-----
1 files changed, 10 insertions(+), 5 deletions(-)

diff --git a/kernel/trace/trace_event_profile.c b/kernel/trace/trace_event_profile.c
index dd44b87..e52784b 100644
--- a/kernel/trace/trace_event_profile.c
+++ b/kernel/trace/trace_event_profile.c
@@ -31,7 +31,7 @@ static int ftrace_profile_enable_event(struct ftrace_event_call *event)
if (atomic_inc_return(&event->profile_count))
return 0;

- if (!total_profile_count++) {
+ if (!total_profile_count) {
buf = (char *)alloc_percpu(profile_buf_t);
if (!buf)
goto fail_buf;
@@ -46,14 +46,19 @@ static int ftrace_profile_enable_event(struct ftrace_event_call *event)
}

ret = event->profile_enable();
- if (!ret)
+ if (!ret) {
+ total_profile_count++;
return 0;
+ }

- kfree(trace_profile_buf_nmi);
fail_buf_nmi:
- kfree(trace_profile_buf);
+ if (!total_profile_count) {
+ kfree(trace_profile_buf_nmi);
+ kfree(trace_profile_buf);
+ trace_profile_buf_nmi = NULL;
+ trace_profile_buf = NULL;
+ }
fail_buf:
- total_profile_count--;
atomic_dec(&event->profile_count);

return ret;
--
1.6.2.3


\
 
 \ /
  Last update: 2009-10-03 15:49    [W:0.125 / U:0.240 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site