X-Git-Url: http://git.monstr.eu/?a=blobdiff_plain;f=ipc%2Fmqueue.c;h=49a05ba3000dbab9f6821e3deb3a5223c29a528a;hb=b27a939e8376a3f1ed09b9c33ef44d20f18ec3d0;hp=3d920ff15c80dd26532c72c0c3dea77ef6557a9e;hpb=8a86b00a437ec06b298477463c7a9b8774570507;p=linux-2.6-microblaze.git

diff --git a/ipc/mqueue.c b/ipc/mqueue.c
index 3d920ff15c80..49a05ba3000d 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -63,6 +63,66 @@ struct posix_msg_tree_node {
 	int			priority;
 };
 
+/*
+ * Locking:
+ *
+ * Accesses to a message queue are synchronized by acquiring info->lock.
+ *
+ * There are two notable exceptions:
+ * - The actual wakeup of a sleeping task is performed using the wake_q
+ *   framework. info->lock is already released when wake_up_q is called.
+ * - The exit codepaths after sleeping check ext_wait_queue->state without
+ *   any locks. If it is STATE_READY, then the syscall is completed without
+ *   acquiring info->lock.
+ *
+ * MQ_BARRIER:
+ * To achieve proper release/acquire memory barrier pairing, the state is set to
+ * STATE_READY with smp_store_release(), and it is read with READ_ONCE followed
+ * by smp_acquire__after_ctrl_dep(). In addition, wake_q_add_safe() is used.
+ *
+ * This prevents the following races:
+ *
+ * 1) With the simple wake_q_add(), the task could be gone already before
+ *    the increase of the reference happens
+ * Thread A
+ *				Thread B
+ * WRITE_ONCE(wait.state, STATE_NONE);
+ * schedule_hrtimeout()
+ *				wake_q_add(A)
+ *				if (cmpxchg()) // success
+ *				   ->state = STATE_READY (reordered)
+ * <timeout returns>
+ * if (wait.state == STATE_READY) return;
+ * sysret to user space
+ * sys_exit()
+ *				get_task_struct() // UaF
+ *
+ * Solution: Use wake_q_add_safe() and perform the get_task_struct() before
+ * the smp_store_release() that does ->state = STATE_READY.
+ *
+ * 2) Without proper _release/_acquire barriers, the woken up task
+ *    could read stale data
+ *
+ * Thread A
+ *				Thread B
+ * do_mq_timedreceive
+ * WRITE_ONCE(wait.state, STATE_NONE);
+ * schedule_hrtimeout()
+ *				state = STATE_READY;
+ * <timeout returns>
+ * if (wait.state == STATE_READY) return;
+ * msg_ptr = wait.msg;		// Access to stale data!
+ *				receiver->msg = message; (reordered)
+ *
+ * Solution: use _release and _acquire barriers.
+ *
+ * 3) There is intentionally no barrier when setting current->state
+ *    to TASK_INTERRUPTIBLE: spin_unlock(&info->lock) provides the
+ *    release memory barrier, and the wakeup is triggered when holding
+ *    info->lock, i.e. spin_lock(&info->lock) provided a pairing
+ *    acquire memory barrier.
+ */
+
 struct ext_wait_queue {		/* queue of sleeping tasks */
 	struct task_struct *task;
 	struct list_head list;
@@ -646,18 +706,23 @@ static int wq_sleep(struct mqueue_inode_info *info, int sr,
 	wq_add(info, sr, ewp);
 
 	for (;;) {
+		/* memory barrier not required, we hold info->lock */
 		__set_current_state(TASK_INTERRUPTIBLE);
 
 		spin_unlock(&info->lock);
 		time = schedule_hrtimeout_range_clock(timeout, 0,
 			HRTIMER_MODE_ABS, CLOCK_REALTIME);
 
-		if (ewp->state == STATE_READY) {
+		if (READ_ONCE(ewp->state) == STATE_READY) {
+			/* see MQ_BARRIER for purpose/pairing */
+			smp_acquire__after_ctrl_dep();
 			retval = 0;
 			goto out;
 		}
 		spin_lock(&info->lock);
-		if (ewp->state == STATE_READY) {
+
+		/* we hold info->lock, so no memory barrier required */
+		if (READ_ONCE(ewp->state) == STATE_READY) {
 			retval = 0;
 			goto out_unlock;
 		}
@@ -918,6 +983,18 @@ out_name:
  * The same algorithm is used for senders.
  */
 
+static inline void __pipelined_op(struct wake_q_head *wake_q,
+				  struct mqueue_inode_info *info,
+				  struct ext_wait_queue *this)
+{
+	list_del(&this->list);
+	get_task_struct(this->task);
+
+	/* see MQ_BARRIER for purpose/pairing */
+	smp_store_release(&this->state, STATE_READY);
+	wake_q_add_safe(wake_q, this->task);
+}
+
 /* pipelined_send() - send a message directly to the task waiting in
  * sys_mq_timedreceive() (without inserting message into a queue).
  */
@@ -927,17 +1004,7 @@ static inline void pipelined_send(struct wake_q_head *wake_q,
 				  struct ext_wait_queue *receiver)
 {
 	receiver->msg = message;
-	list_del(&receiver->list);
-	wake_q_add(wake_q, receiver->task);
-	/*
-	 * Rely on the implicit cmpxchg barrier from wake_q_add such
-	 * that we can ensure that updating receiver->state is the last
-	 * write operation: As once set, the receiver can continue,
-	 * and if we don't have the reference count from the wake_q,
-	 * yet, at that point we can later have a use-after-free
-	 * condition and bogus wakeup.
-	 */
-	receiver->state = STATE_READY;
+	__pipelined_op(wake_q, info, receiver);
 }
 
 /* pipelined_receive() - if there is task waiting in sys_mq_timedsend()
@@ -955,9 +1022,7 @@ static inline void pipelined_receive(struct wake_q_head *wake_q,
 	if (msg_insert(sender->msg, info))
 		return;
 
-	list_del(&sender->list);
-	wake_q_add(wake_q, sender->task);
-	sender->state = STATE_READY;
+	__pipelined_op(wake_q, info, sender);
 }
 
 static int do_mq_timedsend(mqd_t mqdes, const char __user *u_msg_ptr,
@@ -1044,7 +1109,9 @@ static int do_mq_timedsend(mqd_t mqdes, const char __user *u_msg_ptr,
 		} else {
 			wait.task = current;
 			wait.msg = (void *) msg_ptr;
-			wait.state = STATE_NONE;
+
+			/* memory barrier not required, we hold info->lock */
+			WRITE_ONCE(wait.state, STATE_NONE);
 			ret = wq_sleep(info, SEND, timeout, &wait);
 			/*
 			 * wq_sleep must be called with info->lock held, and
@@ -1147,7 +1214,9 @@ static int do_mq_timedreceive(mqd_t mqdes, char __user *u_msg_ptr,
 			ret = -EAGAIN;
 		} else {
 			wait.task = current;
-			wait.state = STATE_NONE;
+
+			/* memory barrier not required, we hold info->lock */
+			WRITE_ONCE(wait.state, STATE_NONE);
 			ret = wq_sleep(info, RECV, timeout, &wait);
 			msg_ptr = wait.msg;
 		}