drbd: Fixed a race between disk-attach and unexpected state changes

This was a very hard to trigger race condition.

If we got a state packet from the peer, after drbd_nl_disk() has
already changed the disk state to D_NEGOTIATING but
after_state_ch() was not yet run by the worker, then receive_state()
might called drbd_sync_handshake(), which in turn crashed
when accessing p_uuid.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>

drivers/block/drbd/drbd_main.c

@@ -1236,8 +1236,6 @@ static void after_state_ch(struct drbd_conf *mdev, union drbd_state os,
 	/* Last part of the attaching process ... */
 	if (ns.conn >= C_CONNECTED &&
 	    os.disk == D_ATTACHING && ns.disk == D_NEGOTIATING) {
-		kfree(mdev->p_uuid); /* We expect to receive up-to-date UUIDs soon. */
-		mdev->p_uuid = NULL; /* ...to not use the old ones in the mean time */
 		drbd_send_sizes(mdev, 0, 0);  /* to start sync... */
 		drbd_send_uuids(mdev);
 		drbd_send_state(mdev);

drivers/block/drbd/drbd_nl.c

@@ -1114,6 +1114,12 @@ static int drbd_nl_disk_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp
 		mdev->new_state_tmp.i = ns.i;
 		ns.i = os.i;
 		ns.disk = D_NEGOTIATING;
+
+		/* We expect to receive up-to-date UUIDs soon.
+		   To avoid a race in receive_state, free p_uuid while
+		   holding req_lock. I.e. atomic with the state change */
+		kfree(mdev->p_uuid);
+		mdev->p_uuid = NULL;
 	}
 
 	rv = _drbd_set_state(mdev, ns, CS_VERBOSE, NULL);

include/linux/drbd.h

@@ -53,7 +53,7 @@
 
 
 extern const char *drbd_buildtag(void);
-#define REL_VERSION "8.3.8rc2"
+#define REL_VERSION "8.3.8"
 #define API_VERSION 88
 #define PRO_VERSION_MIN 86
 #define PRO_VERSION_MAX 94