1 files changed, 152 insertions, 70 deletions

diff --git a/ipc/sem.c b/ipc/sem.c
index 19c8b980d1f..db9d241af13 100644
--- a/ipc/sem.c
+++ b/ipc/sem.c
@@ -253,70 +253,112 @@ static void sem_rcu_free(struct rcu_head *head)
 }
 
 /*
+ * 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
+ * that sem_perm.lock is free.
+ * that a) sem_perm.lock is free and b) complex_count is 0.
+ */
+static void sem_wait_array(struct sem_array *sma)
+{
+	int i;
+	struct sem *sem;
+
+	if (sma->complex_count)  {
+		/* The thread that increased sma->complex_count waited on
+		 * all sem->lock locks. Thus we don't need to wait again.
+		 */
+		return;
+	}
+
+	for (i = 0; i < sma->sem_nsems; i++) {
+		sem = sma->sem_base + i;
+		spin_unlock_wait(&sem->lock);
+	}
+}
+
+/*
  * If the request contains only one semaphore operation, and there are
  * no complex transactions pending, lock only the semaphore involved.
  * Otherwise, lock the entire semaphore array, since we either have
  * multiple semaphores in our own semops, or we need to look at
  * semaphores from other pending complex operations.
- *
- * Carefully guard against sma->complex_count changing between zero
- * and non-zero while we are spinning for the lock. The value of
- * sma->complex_count cannot change while we are holding the lock,
- * so sem_unlock should be fine.
- *
- * The global lock path checks that all the local locks have been released,
- * checking each local lock once. This means that the local lock paths
- * cannot start their critical sections while the global lock is held.
  */
 static inline int sem_lock(struct sem_array *sma, struct sembuf *sops,
 			      int nsops)
 {
-	int locknum;
- again:
-	if (nsops == 1 && !sma->complex_count) {
-		struct sem *sem = sma->sem_base + sops->sem_num;
+	struct sem *sem;
 
-		/* Lock just the semaphore we are interested in. */
-		spin_lock(&sem->lock);
+	if (nsops != 1) {
+		/* Complex operation - acquire a full lock */
+		ipc_lock_object(&sma->sem_perm);
 
-		/*
-		 * If sma->complex_count was set while we were spinning,
-		 * we may need to look at things we did not lock here.
+		/* And wait until all simple ops that are processed
+		 * right now have dropped their locks.
 		 */
-		if (unlikely(sma->complex_count)) {
-			spin_unlock(&sem->lock);
-			goto lock_array;
-		}
+		sem_wait_array(sma);
+		return -1;
+	}
+
+	/*
+	 * Only one semaphore affected - try to optimize locking.
+	 * The rules are:
+	 * - optimized locking is possible if no complex operation
+	 *   is either enqueued or processed right now.
+	 * - The test for enqueued complex ops is simple:
+	 *      sma->complex_count != 0
+	 * - Testing for complex ops that are processed right now is
+	 *   a bit more difficult. Complex ops acquire the full lock
+	 *   and first wait that the running simple ops have completed.
+	 *   (see above)
+	 *   Thus: If we own a simple lock and the global lock is free
+	 *	and complex_count is now 0, then it will stay 0 and
+	 *	thus just locking sem->lock is sufficient.
+	 */
+	sem = sma->sem_base + sops->sem_num;
 
+	if (sma->complex_count == 0) {
 		/*
-		 * Another process is holding the global lock on the
-		 * sem_array; we cannot enter our critical section,
-		 * but have to wait for the global lock to be released.
+		 * It appears that no complex operation is around.
+		 * Acquire the per-semaphore lock.
 		 */
-		if (unlikely(spin_is_locked(&sma->sem_perm.lock))) {
-			spin_unlock(&sem->lock);
-			spin_unlock_wait(&sma->sem_perm.lock);
-			goto again;
+		spin_lock(&sem->lock);
+
+		/* Then check that the global lock is free */
+		if (!spin_is_locked(&sma->sem_perm.lock)) {
+			/* spin_is_locked() is not a memory barrier */
+			smp_mb();
+
+			/* Now repeat the test of complex_count:
+			 * It can't change anymore until we drop sem->lock.
+			 * Thus: if is now 0, then it will stay 0.
+			 */
+			if (sma->complex_count == 0) {
+				/* fast path successful! */
+				return sops->sem_num;
+			}
 		}
+		spin_unlock(&sem->lock);
+	}
+
+	/* slow path: acquire the full lock */
+	ipc_lock_object(&sma->sem_perm);
 
-		locknum = sops->sem_num;
+	if (sma->complex_count == 0) {
+		/* False alarm:
+		 * There is no complex operation, thus we can switch
+		 * back to the fast path.
+		 */
+		spin_lock(&sem->lock);
+		ipc_unlock_object(&sma->sem_perm);
+		return sops->sem_num;
 	} else {
-		int i;
-		/*
-		 * Lock the semaphore array, and wait for all of the
-		 * individual semaphore locks to go away.  The code
-		 * above ensures no new single-lock holders will enter
-		 * their critical section while the array lock is held.
+		/* Not a false alarm, thus complete the sequence for a
+		 * full lock.
 		 */
- lock_array:
-		ipc_lock_object(&sma->sem_perm);
-		for (i = 0; i < sma->sem_nsems; i++) {
-			struct sem *sem = sma->sem_base + i;
-			spin_unlock_wait(&sem->lock);
-		}
-		locknum = -1;
+		sem_wait_array(sma);
+		return -1;
 	}
-	return locknum;
 }
 
 static inline void sem_unlock(struct sem_array *sma, int locknum)
@@ -876,6 +918,24 @@ again:
 }
 
 /**
+ * set_semotime(sma, sops) - set sem_otime
+ * @sma: semaphore array
+ * @sops: operations that modified the array, may be NULL
+ *
+ * sem_otime is replicated to avoid cache line trashing.
+ * This function sets one instance to the current time.
+ */
+static void set_semotime(struct sem_array *sma, struct sembuf *sops)
+{
+	if (sops == NULL) {
+		sma->sem_base[0].sem_otime = get_seconds();
+	} else {
+		sma->sem_base[sops[0].sem_num].sem_otime =
+							get_seconds();
+	}
+}
+
+/**
  * do_smart_update(sma, sops, nsops, otime, pt) - optimized update_queue
  * @sma: semaphore array
  * @sops: operations that were performed
@@ -925,17 +985,10 @@ static void do_smart_update(struct sem_array *sma, struct sembuf *sops, int nsop
 			}
 		}
 	}
-	if (otime) {
-		if (sops == NULL) {
-			sma->sem_base[0].sem_otime = get_seconds();
-		} else {
-			sma->sem_base[sops[0].sem_num].sem_otime =
-								get_seconds();
-		}
-	}
+	if (otime)
+		set_semotime(sma, sops);
 }
 
-
 /* The following counts are associated to each semaphore:
  *   semncnt        number of tasks waiting on semval being nonzero
  *   semzcnt        number of tasks waiting on semval being zero
@@ -1229,6 +1282,12 @@ static int semctl_setval(struct ipc_namespace *ns, int semid, int semnum,
 
 	sem_lock(sma, NULL, -1);
 
+	if (sma->sem_perm.deleted) {
+		sem_unlock(sma, -1);
+		rcu_read_unlock();
+		return -EIDRM;
+	}
+
 	curr = &sma->sem_base[semnum];
 
 	ipc_assert_locked_object(&sma->sem_perm);
@@ -1283,12 +1342,14 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum,
 		int i;
 
 		sem_lock(sma, NULL, -1);
+		if (sma->sem_perm.deleted) {
+			err = -EIDRM;
+			goto out_unlock;
+		}
 		if(nsems > SEMMSL_FAST) {
 			if (!ipc_rcu_getref(sma)) {
-				sem_unlock(sma, -1);
-				rcu_read_unlock();
 				err = -EIDRM;
-				goto out_free;
+				goto out_unlock;
 			}
 			sem_unlock(sma, -1);
 			rcu_read_unlock();
@@ -1301,10 +1362,8 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum,
 			rcu_read_lock();
 			sem_lock_and_putref(sma);
 			if (sma->sem_perm.deleted) {
-				sem_unlock(sma, -1);
-				rcu_read_unlock();
 				err = -EIDRM;
-				goto out_free;
+				goto out_unlock;
 			}
 		}
 		for (i = 0; i < sma->sem_nsems; i++)
@@ -1322,8 +1381,8 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum,
 		struct sem_undo *un;
 
 		if (!ipc_rcu_getref(sma)) {
-			rcu_read_unlock();
-			return -EIDRM;
+			err = -EIDRM;
+			goto out_rcu_wakeup;
 		}
 		rcu_read_unlock();
 
@@ -1351,10 +1410,8 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum,
 		rcu_read_lock();
 		sem_lock_and_putref(sma);
 		if (sma->sem_perm.deleted) {
-			sem_unlock(sma, -1);
-			rcu_read_unlock();
 			err = -EIDRM;
-			goto out_free;
+			goto out_unlock;
 		}
 
 		for (i = 0; i < nsems; i++)
@@ -1378,6 +1435,10 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum,
 		goto out_rcu_wakeup;
 
 	sem_lock(sma, NULL, -1);
+	if (sma->sem_perm.deleted) {
+		err = -EIDRM;
+		goto out_unlock;
+	}
 	curr = &sma->sem_base[semnum];
 
 	switch (cmd) {
@@ -1783,6 +1844,10 @@ SYSCALL_DEFINE4(semtimedop, int, semid, struct sembuf __user *, tsops,
 	if (error)
 		goto out_rcu_wakeup;
 
+	error = -EIDRM;
+	locknum = sem_lock(sma, sops, nsops);
+	if (sma->sem_perm.deleted)
+		goto out_unlock_free;
 	/*
 	 * semid identifiers are not unique - find_alloc_undo may have
 	 * allocated an undo structure, it was invalidated by an RMID
@@ -1790,19 +1855,22 @@ SYSCALL_DEFINE4(semtimedop, int, semid, struct sembuf __user *, tsops,
 	 * This case can be detected checking un->semid. The existence of
 	 * "un" itself is guaranteed by rcu.
 	 */
-	error = -EIDRM;
-	locknum = sem_lock(sma, sops, nsops);
 	if (un && un->semid == -1)
 		goto out_unlock_free;
 
 	error = perform_atomic_semop(sma, sops, nsops, un,
 					task_tgid_vnr(current));
-	if (error <= 0) {
-		if (alter && error == 0)
+	if (error == 0) {
+		/* If the operation was successful, then do
+		 * the required updates.
+		 */
+		if (alter)
 			do_smart_update(sma, sops, nsops, 1, &tasks);
-
-		goto out_unlock_free;
+		else
+			set_semotime(sma, sops);
 	}
+	if (error <= 0)
+		goto out_unlock_free;
 
 	/* We need to sleep on this operation, so we put the current
 	 * task into the pending queue and go to sleep.
@@ -1999,6 +2067,12 @@ void exit_sem(struct task_struct *tsk)
 		}
 
 		sem_lock(sma, NULL, -1);
+		/* exit_sem raced with IPC_RMID, nothing to do */
+		if (sma->sem_perm.deleted) {
+			sem_unlock(sma, -1);
+			rcu_read_unlock();
+			continue;
+		}
 		un = __lookup_undo(ulp, semid);
 		if (un == NULL) {
 			/* exit_sem raced with IPC_RMID+semget() that created
@@ -2061,6 +2135,14 @@ static int sysvipc_sem_proc_show(struct seq_file *s, void *it)
 	struct sem_array *sma = it;
 	time_t sem_otime;
 
+	/*
+	 * The proc interface isn't aware of sem_lock(), it calls
+	 * ipc_lock_object() directly (in sysvipc_find_ipc).
+	 * In order to stay compatible with sem_lock(), we must wait until
+	 * all simple semop() calls have left their critical regions.
+	 */
+	sem_wait_array(sma);
+
 	sem_otime = get_semotime(sma);
 
 	return seq_printf(s,