tools/liblockdep: Fix debug_check thinko in mutex destroy

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>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
This commit is contained in:
Kirill Smelkov 2014-12-08 14:07:59 +03:00 committed by Sasha Levin
parent b2776bf714
commit 95bfdf23e4

View File

@ -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);
}