summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorManfred Spraul <manfred@colorfullife.com>2015-08-15 01:35:10 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2015-08-15 01:56:32 +0300
commit3ed1f8a99d70ea1cd1508910eb107d0edcae5009 (patch)
treee969912641af3d1095025d90d55dc33d9af2a10b
parent7f6bf39bbdd1dcccd103ba7dce8496a8e72e7df4 (diff)
downloadlinux-3ed1f8a99d70ea1cd1508910eb107d0edcae5009.tar.xz
ipc/sem.c: update/correct memory barriers
sem_lock() did not properly pair memory barriers: !spin_is_locked() and spin_unlock_wait() are both only control barriers. The code needs an acquire barrier, otherwise the cpu might perform read operations before the lock test. As no primitive exists inside <include/spinlock.h> and since it seems noone wants another primitive, the code creates a local primitive within ipc/sem.c. With regards to -stable: The change of sem_wait_array() is a bugfix, the change to sem_lock() is a nop (just a preprocessor redefinition to improve the readability). The bugfix is necessary for all kernels that use sem_wait_array() (i.e.: starting from 3.10). Signed-off-by: Manfred Spraul <manfred@colorfullife.com> Reported-by: Oleg Nesterov <oleg@redhat.com> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Kirill Tkhai <ktkhai@parallels.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: <stable@vger.kernel.org> [3.10+] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-rw-r--r--ipc/sem.c18
1 files changed, 14 insertions, 4 deletions
diff --git a/ipc/sem.c b/ipc/sem.c
index 178f303deea5..b471e5a3863d 100644
--- a/ipc/sem.c
+++ b/ipc/sem.c
@@ -253,6 +253,16 @@ static void sem_rcu_free(struct rcu_head *head)
}
/*
+ * spin_unlock_wait() and !spin_is_locked() are not memory barriers, they
+ * are only control barriers.
+ * The code must pair with spin_unlock(&sem->lock) or
+ * spin_unlock(&sem_perm.lock), thus just the control barrier is insufficient.
+ *
+ * smp_rmb() is sufficient, as writes cannot pass the control barrier.
+ */
+#define ipc_smp_acquire__after_spin_is_unlocked() smp_rmb()
+
+/*
* Wait until all currently ongoing simple ops have completed.
* Caller must own sem_perm.lock.
* New simple ops cannot start, because simple ops first check
@@ -275,6 +285,7 @@ static void sem_wait_array(struct sem_array *sma)
sem = sma->sem_base + i;
spin_unlock_wait(&sem->lock);
}
+ ipc_smp_acquire__after_spin_is_unlocked();
}
/*
@@ -327,13 +338,12 @@ static inline int sem_lock(struct sem_array *sma, struct sembuf *sops,
/* Then check that the global lock is free */
if (!spin_is_locked(&sma->sem_perm.lock)) {
/*
- * The ipc object lock check must be visible on all
- * cores before rechecking the complex count. Otherwise
- * we can race with another thread that does:
+ * We need a memory barrier with acquire semantics,
+ * otherwise we can race with another thread that does:
* complex_count++;
* spin_unlock(sem_perm.lock);
*/
- smp_rmb();
+ ipc_smp_acquire__after_spin_is_unlocked();
/*
* Now repeat the test of complex_count: