[DCCP]: fix theoretical ccids_{read,write}_lock() race
Make sure that spin_unlock_wait() is properly ordered wrt atomic_inc(). (akpm: can't we convert this code to use rwlocks?) Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
parent
b5890d8ba4
commit
d725fdc802
@ -40,6 +40,7 @@ static inline void ccids_write_unlock(void)
|
|||||||
static inline void ccids_read_lock(void)
|
static inline void ccids_read_lock(void)
|
||||||
{
|
{
|
||||||
atomic_inc(&ccids_lockct);
|
atomic_inc(&ccids_lockct);
|
||||||
|
smp_mb__after_atomic_inc();
|
||||||
spin_unlock_wait(&ccids_lock);
|
spin_unlock_wait(&ccids_lock);
|
||||||
}
|
}
|
||||||
|
|
||||||
|
Loading…
Reference in New Issue
Block a user