ipc/sem.c: use READ_ONCE()/WRITE_ONCE() for use_global_lock

The patch solves three weaknesses in ipc/sem.c:

1) The initial read of use_global_lock in sem_lock() is an intentional
   race.  KCSAN detects these accesses and prints a warning.

2) The code assumes that plain C read/writes are not mangled by the CPU
   or the compiler.

3) The comment it sysvipc_sem_proc_show() was hard to understand: The
   rest of the comments in ipc/sem.c speaks about sem_perm.lock, and
   suddenly this function speaks about ipc_lock_object().

To solve 1) and 2), use READ_ONCE()/WRITE_ONCE().  Plain C reads are used
in code that owns sma->sem_perm.lock.

The comment is updated to solve 3)

[[email protected]: use READ_ONCE()/WRITE_ONCE() for use_global_lock]
  Link: https://lkml.kernel.org/r/[email protected]

Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Manfred Spraul <[email protected]>
Reviewed-by: Paul E. McKenney <[email protected]>
Reviewed-by: Davidlohr Bueso <[email protected]>
Cc: <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

ipc/sem.c

@@ -217,6 +217,8 @@ static int sysvipc_sem_proc_show(struct seq_file *s, void *it);
  * this smp_load_acquire(), this is guaranteed because the smp_load_acquire()
  * is inside a spin_lock() and after a write from 0 to non-zero a
  * spin_lock()+spin_unlock() is done.
+ * To prevent the compiler/cpu temporarily writing 0 to use_global_lock,
+ * READ_ONCE()/WRITE_ONCE() is used.
  *
  * 2) queue.status: (SEM_BARRIER_2)
  * Initialization is done while holding sem_lock(), so no further barrier is
@@ -342,10 +344,10 @@ static void complexmode_enter(struct sem_array *sma)
 		 * Nothing to do, just reset the
 		 * counter until we return to simple mode.
 		 */
-		sma->use_global_lock = USE_GLOBAL_LOCK_HYSTERESIS;
+		WRITE_ONCE(sma->use_global_lock, USE_GLOBAL_LOCK_HYSTERESIS);
 		return;
 	}
-	sma->use_global_lock = USE_GLOBAL_LOCK_HYSTERESIS;
+	WRITE_ONCE(sma->use_global_lock, USE_GLOBAL_LOCK_HYSTERESIS);
 
 	for (i = 0; i < sma->sem_nsems; i++) {
 		sem = &sma->sems[i];
@@ -371,7 +373,8 @@ static void complexmode_tryleave(struct sem_array *sma)
 		/* See SEM_BARRIER_1 for purpose/pairing */
 		smp_store_release(&sma->use_global_lock, 0);
 	} else {
-		sma->use_global_lock--;
+		WRITE_ONCE(sma->use_global_lock,
+				sma->use_global_lock-1);
 	}
 }
 
@@ -412,7 +415,7 @@ static inline int sem_lock(struct sem_array *sma, struct sembuf *sops,
 	 * Initial check for use_global_lock. Just an optimization,
 	 * no locking, no memory barrier.
 	 */
-	if (!sma->use_global_lock) {
+	if (!READ_ONCE(sma->use_global_lock)) {
 		/*
 		 * It appears that no complex operation is around.
 		 * Acquire the per-semaphore lock.
@@ -2436,7 +2439,8 @@ static int sysvipc_sem_proc_show(struct seq_file *s, void *it)
 
 	/*
 	 * The proc interface isn't aware of sem_lock(), it calls
-	 * ipc_lock_object() directly (in sysvipc_find_ipc).
+	 * ipc_lock_object(), i.e. spin_lock(&sma->sem_perm.lock).
+	 * (in sysvipc_find_ipc)
 	 * In order to stay compatible with sem_lock(), we must
 	 * enter / leave complex_mode.
 	 */