drbd: fix potential kernel BUG (NULL deref)

BUG trace would look like:
 lc_find
 drbd_rs_complete_io
 got_OVResult
 drbd_asender

Could be triggered by explicit, or IO-error policy based,
detach during online-verify.

We may only dereference mdev->resync, if we first get_ldev(), as the
disk may break any time, causing mdev->resync to disappear once all
ldev references have been returned.
Already in flight online-verify requests or replies may still come in,
which we then need to ignore.

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

2 files changed, 19 insertions, 6 deletions

diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index 2c3edf0ac5ca..e4e4eddf04f2 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -4241,10 +4241,13 @@ static int got_IsInSync(struct drbd_conf *mdev, struct p_header80 *h)
 
         update_peer_seq(mdev, be32_to_cpu(p->seq_num));
 
-        drbd_rs_complete_io(mdev, sector);
-        drbd_set_in_sync(mdev, sector, blksize);
-        /* rs_same_csums is supposed to count in units of BM_BLOCK_SIZE */
-        mdev->rs_same_csum += (blksize >> BM_BLOCK_SHIFT);
+        if (get_ldev(mdev)) {
+                drbd_rs_complete_io(mdev, sector);
+                drbd_set_in_sync(mdev, sector, blksize);
+                /* rs_same_csums is supposed to count in units of BM_BLOCK_SIZE */
+                mdev->rs_same_csum += (blksize >> BM_BLOCK_SHIFT);
+                put_ldev(mdev);
+        }
         dec_rs_pending(mdev);
         atomic_add(blksize >> 9, &mdev->rs_sect_in);
 
@@ -4423,6 +4426,9 @@ static int got_OVResult(struct drbd_conf *mdev, struct p_header80 *h)
         else
                 ov_oos_print(mdev);
 
+        if (!get_ldev(mdev))
+                return TRUE;
+
         drbd_rs_complete_io(mdev, sector);
         dec_rs_pending(mdev);
 
@@ -4437,6 +4443,7 @@ static int got_OVResult(struct drbd_conf *mdev, struct p_header80 *h)
                         drbd_resync_finished(mdev);
                 }
         }
+        put_ldev(mdev);
         return TRUE;
 }
 
diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c
index 01743193f321..c72a5fc1c88e 100644
--- a/drivers/block/drbd/drbd_worker.c
+++ b/drivers/block/drbd/drbd_worker.c
@@ -1027,7 +1027,10 @@ int w_e_end_csum_rs_req(struct drbd_conf *mdev, struct drbd_work *w, int cancel)
                 return 1;
         }
 
-        drbd_rs_complete_io(mdev, e->sector);
+        if (get_ldev(mdev)) {
+                drbd_rs_complete_io(mdev, e->sector);
+                put_ldev(mdev);
+        }
 
         di = e->digest;
 
@@ -1134,7 +1137,10 @@ int w_e_end_ov_reply(struct drbd_conf *mdev, struct drbd_work *w, int cancel)
 
         /* after "cancel", because after drbd_disconnect/drbd_rs_cancel_all
          * the resync lru has been cleaned up already */
-        drbd_rs_complete_io(mdev, e->sector);
+        if (get_ldev(mdev)) {
+                drbd_rs_complete_io(mdev, e->sector);
+                put_ldev(mdev);
+        }
 
         di = e->digest;