ipc: move locking out of ipcctl_pre_down_nolock

This function currently acquires both the rw_mutex and the rcu lock on
successful lookups, leaving the callers to explicitly unlock them,
creating another two level locking situation.

Make the callers (including those that still use ipcctl_pre_down())
explicitly lock and unlock the rwsem and rcu lock.

Signed-off-by: Davidlohr Bueso <davidlohr.bueso@hp.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

ipc/msg.c

@@ -407,31 +407,38 @@ static int msgctl_down(struct ipc_namespace *ns, int msqid, int cmd,
 			return -EFAULT;
 	}
 
+	down_write(&msg_ids(ns).rw_mutex);
+	rcu_read_lock();
+
 	ipcp = ipcctl_pre_down(ns, &msg_ids(ns), msqid, cmd,
 			       &msqid64.msg_perm, msqid64.msg_qbytes);
-	if (IS_ERR(ipcp))
-		return PTR_ERR(ipcp);
+	if (IS_ERR(ipcp)) {
+		err = PTR_ERR(ipcp);
+		/* the ipc lock is not held upon failure */
+		goto out_unlock1;
+	}
 
 	msq = container_of(ipcp, struct msg_queue, q_perm);
 
 	err = security_msg_queue_msgctl(msq, cmd);
 	if (err)
-		goto out_unlock;
+		goto out_unlock0;
 
 	switch (cmd) {
 	case IPC_RMID:
+		/* freeque unlocks the ipc object and rcu */
 		freeque(ns, ipcp);
 		goto out_up;
 	case IPC_SET:
 		if (msqid64.msg_qbytes > ns->msg_ctlmnb &&
 		    !capable(CAP_SYS_RESOURCE)) {
 			err = -EPERM;
-			goto out_unlock;
+			goto out_unlock0;
 		}
 
 		err = ipc_update_perm(&msqid64.msg_perm, ipcp);
 		if (err)
-			goto out_unlock;
+			goto out_unlock0;
 
 		msq->q_qbytes = msqid64.msg_qbytes;
 
@@ -448,8 +455,11 @@ static int msgctl_down(struct ipc_namespace *ns, int msqid, int cmd,
 	default:
 		err = -EINVAL;
 	}
-out_unlock:
-	msg_unlock(msq);
+
+out_unlock0:
+	ipc_unlock_object(&msq->q_perm);
+out_unlock1:
+	rcu_read_unlock();
 out_up:
 	up_write(&msg_ids(ns).rw_mutex);
 	return err;

ipc/sem.c

@@ -1289,39 +1289,44 @@ static int semctl_down(struct ipc_namespace *ns, int semid,
 			return -EFAULT;
 	}
 
+	down_write(&sem_ids(ns).rw_mutex);
+	rcu_read_lock();
+
 	ipcp = ipcctl_pre_down_nolock(ns, &sem_ids(ns), semid, cmd,
 				      &semid64.sem_perm, 0);
-	if (IS_ERR(ipcp))
-		return PTR_ERR(ipcp);
+	if (IS_ERR(ipcp)) {
+		err = PTR_ERR(ipcp);
+		/* the ipc lock is not held upon failure */
+		goto out_unlock1;
+	}
 
 	sma = container_of(ipcp, struct sem_array, sem_perm);
 
 	err = security_sem_semctl(sma, cmd);
-	if (err) {
-		rcu_read_unlock();
-		goto out_up;
-	}
+	if (err)
+		goto out_unlock1;
 
-	switch(cmd){
+	switch (cmd) {
 	case IPC_RMID:
 		sem_lock(sma, NULL, -1);
+		/* freeary unlocks the ipc object and rcu */
 		freeary(ns, ipcp);
 		goto out_up;
 	case IPC_SET:
 		sem_lock(sma, NULL, -1);
 		err = ipc_update_perm(&semid64.sem_perm, ipcp);
 		if (err)
-			goto out_unlock;
+			goto out_unlock0;
 		sma->sem_ctime = get_seconds();
 		break;
 	default:
-		rcu_read_unlock();
 		err = -EINVAL;
-		goto out_up;
+		goto out_unlock1;
 	}
 
-out_unlock:
+out_unlock0:
 	sem_unlock(sma, -1);
+out_unlock1:
 	rcu_read_unlock();
 out_up:
 	up_write(&sem_ids(ns).rw_mutex);

ipc/shm.c

@@ -757,31 +757,42 @@ static int shmctl_down(struct ipc_namespace *ns, int shmid, int cmd,
 			return -EFAULT;
 	}
 
+	down_write(&shm_ids(ns).rw_mutex);
+	rcu_read_lock();
+
 	ipcp = ipcctl_pre_down(ns, &shm_ids(ns), shmid, cmd,
 			       &shmid64.shm_perm, 0);
-	if (IS_ERR(ipcp))
-		return PTR_ERR(ipcp);
+	if (IS_ERR(ipcp)) {
+		err = PTR_ERR(ipcp);
+		/* the ipc lock is not held upon failure */
+		goto out_unlock1;
+	}
 
 	shp = container_of(ipcp, struct shmid_kernel, shm_perm);
 
 	err = security_shm_shmctl(shp, cmd);
 	if (err)
-		goto out_unlock;
+		goto out_unlock0;
+
 	switch (cmd) {
 	case IPC_RMID:
+		/* do_shm_rmid unlocks the ipc object and rcu */
 		do_shm_rmid(ns, ipcp);
 		goto out_up;
 	case IPC_SET:
 		err = ipc_update_perm(&shmid64.shm_perm, ipcp);
 		if (err)
-			goto out_unlock;
+			goto out_unlock0;
 		shp->shm_ctim = get_seconds();
 		break;
 	default:
 		err = -EINVAL;
 	}
-out_unlock:
-	shm_unlock(shp);
+
+out_unlock0:
+	ipc_unlock_object(&shp->shm_perm);
+out_unlock1:
+	rcu_read_unlock();
 out_up:
 	up_write(&shm_ids(ns).rw_mutex);
 	return err;

ipc/util.c

@@ -746,8 +746,10 @@ int ipc_update_perm(struct ipc64_perm *in, struct kern_ipc_perm *out)
  * It must be called without any lock held and
  *  - retrieves the ipc with the given id in the given table.
  *  - performs some audit and permission check, depending on the given cmd
- *  - returns the ipc with both ipc and rw_mutex locks held in case of success
+ *  - returns the ipc with the ipc lock held in case of success
  *    or an err-code without any lock held otherwise.
+ *
+ * Call holding the both the rw_mutex and the rcu read lock.
  */
 struct kern_ipc_perm *ipcctl_pre_down(struct ipc_namespace *ns,
 				      struct ipc_ids *ids, int id, int cmd,
@@ -772,13 +774,10 @@ struct kern_ipc_perm *ipcctl_pre_down_nolock(struct ipc_namespace *ns,
 	int err = -EPERM;
 	struct kern_ipc_perm *ipcp;
 
-	down_write(&ids->rw_mutex);
-	rcu_read_lock();
-
 	ipcp = ipc_obtain_object_check(ids, id);
 	if (IS_ERR(ipcp)) {
 		err = PTR_ERR(ipcp);
-		goto out_up;
+		goto err;
 	}
 
 	audit_ipc_obj(ipcp);
@@ -789,16 +788,8 @@ struct kern_ipc_perm *ipcctl_pre_down_nolock(struct ipc_namespace *ns,
 	euid = current_euid();
 	if (uid_eq(euid, ipcp->cuid) || uid_eq(euid, ipcp->uid)  ||
 	    ns_capable(ns->user_ns, CAP_SYS_ADMIN))
-		return ipcp;
-
-out_up:
-	/*
-	 * Unsuccessful lookup, unlock and return
-	 * the corresponding error.
-	 */
-	rcu_read_unlock();
-	up_write(&ids->rw_mutex);
-
+		return ipcp; /* successful lookup */
+err:
 	return ERR_PTR(err);
 }