[PATCH] tools/liblockdep: Fix debug_check thinko in mutex destroy

* [PATCH] tools/liblockdep: Fix debug_check thinko in mutex destroy
@ 2014-12-08 11:07 Kirill Smelkov
  2014-12-08 14:59 ` Sasha Levin
  0 siblings, 1 reply; 4+ messages in thread
From: Kirill Smelkov @ 2014-12-08 11:07 UTC (permalink / raw)
  To: Sasha Levin; +Cc: Ingo Molnar, linux-kernel, Kirill Smelkov

In mutex destroy code currently we pass to debug_check_no_locks_freed()

    [mem_from, mem_end)

address region. But debug_check_no_locks_freed() accepts

    mem_from, mem_*len*

i.e. second parameter is region length, not end address. And it was
always so, starting from 2006 (fbb9ce95 "lockdep: core").

Fix it, or else on a mutex destroy we wrongly check
much-wider-than-mutex region and can find not-yet-released other locks
there and wrongly report BUGs on them.

Signed-off-by: Kirill Smelkov <kirr@nexedi.com>
---
 tools/lib/lockdep/preload.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/lib/lockdep/preload.c b/tools/lib/lockdep/preload.c
index 6f80360..0b0112c 100644
--- a/tools/lib/lockdep/preload.c
+++ b/tools/lib/lockdep/preload.c
@@ -317,7 +317,7 @@ int pthread_mutex_destroy(pthread_mutex_t *mutex)
 	 *
 	 * TODO: Hook into free() and add that check there as well.
 	 */
-	debug_check_no_locks_freed(mutex, mutex + sizeof(*mutex));
+	debug_check_no_locks_freed(mutex, sizeof(*mutex));
 	__del_lock(__get_lock(mutex));
 	return ll_pthread_mutex_destroy(mutex);
 }
@@ -341,7 +341,7 @@ int pthread_rwlock_destroy(pthread_rwlock_t *rwlock)
 {
 	try_init_preload();
 
-	debug_check_no_locks_freed(rwlock, rwlock + sizeof(*rwlock));
+	debug_check_no_locks_freed(rwlock, sizeof(*rwlock));
 	__del_lock(__get_lock(rwlock));
 	return ll_pthread_rwlock_destroy(rwlock);
 }
-- 
2.2.0.309.gc3c329f

^ permalink raw reply related	[flat|nested] 4+ messages in thread