dm snapshot: suspend merging snapshot when doing exception handover

The "dm snapshot: suspend origin when doing exception handover" commit
fixed a exception store handover bug associated with pending exceptions
to the "snapshot-origin" target.

However, a similar problem exists in snapshot merging. When snapshot
merging is in progress, we use the target "snapshot-merge" instead of
"snapshot-origin". Consequently, during exception store handover, we
must find the snapshot-merge target and suspend its associated
mapped_device.

To avoid lockdep warnings, the target must be suspended and resumed
without holding _origins_lock.

Introduce a dm_hold() function that grabs a reference on a
mapped_device, but unlike dm_get(), it doesn't crash if the device has
the DMF_FREEING flag set, it returns an error in this case.

In snapshot_resume() we grab the reference to the origin device using
dm_hold() while holding _origins_lock (_origins_lock guarantees that the
device won't disappear). Then we release _origins_lock, suspend the
device and grab _origins_lock again.

NOTE to stable@ people:
When backporting to kernels 3.18 and older, use dm_internal_suspend and
dm_internal_resume instead of dm_internal_suspend_fast and
dm_internal_resume_fast.

Signed-off-by: Mikulas Patocka <[e-mail]>
Signed-off-by: Mike Snitzer <[e-mail]>
Cc: [e-mail]

drivers/md/dm-snap.c

···
 static void snapshot_resume(struct dm_target *ti)
 {
 	struct dm_snapshot *s = ti->private;
-	struct dm_snapshot *snap_src = NULL, *snap_dest = NULL;
+	struct dm_snapshot *snap_src = NULL, *snap_dest = NULL, *snap_merging = NULL;
 	struct dm_origin *o;
 	struct mapped_device *origin_md = NULL;
+	bool must_restart_merging = false;
 
 	down_read(&_origins_lock);
 
 	o = __lookup_dm_origin(s->origin->bdev);
 	if (o)
 		origin_md = dm_table_get_md(o->ti->table);
+	if (!origin_md) {
+		(void) __find_snapshots_sharing_cow(s, NULL, NULL, &snap_merging);
+		if (snap_merging)
+			origin_md = dm_table_get_md(snap_merging->ti->table);
+	}
 	if (origin_md == dm_table_get_md(ti->table))
 		origin_md = NULL;
+	if (origin_md) {
+		if (dm_hold(origin_md))
+			origin_md = NULL;
+	}
 
-	if (origin_md)
+	up_read(&_origins_lock);
+
+	if (origin_md) {
 		dm_internal_suspend_fast(origin_md);
+		if (snap_merging && test_bit(RUNNING_MERGE, &snap_merging->state_bits)) {
+			must_restart_merging = true;
+			stop_merge(snap_merging);
+		}
+	}
+
+	down_read(&_origins_lock);
 
 	(void) __find_snapshots_sharing_cow(s, &snap_src, &snap_dest, NULL);
 	if (snap_src && snap_dest) {
···
 		up_write(&snap_src->lock);
 	}
 
-	if (origin_md)
-		dm_internal_resume_fast(origin_md);
-
 	up_read(&_origins_lock);
+
+	if (origin_md) {
+		if (must_restart_merging)
+			start_merge(snap_merging);
+		dm_internal_resume_fast(origin_md);
+		dm_put(origin_md);
+	}
 
 	/* Now we have correct chunk size, reregister */
 	reregister_snapshot(s);
···
 
 static struct target_type merge_target = {
 	.name    = dm_snapshot_merge_target_name,
-	.version = {1, 2, 0},
+	.version = {1, 3, 0},
 	.module  = THIS_MODULE,
 	.ctr     = snapshot_ctr,
 	.dtr     = snapshot_dtr,

drivers/md/dm.c

···
 	BUG_ON(test_bit(DMF_FREEING, &md->flags));
 }
 
+int dm_hold(struct mapped_device *md)
+{
+	spin_lock(&_minor_lock);
+	if (test_bit(DMF_FREEING, &md->flags)) {
+		spin_unlock(&_minor_lock);
+		return -EBUSY;
+	}
+	dm_get(md);
+	spin_unlock(&_minor_lock);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dm_hold);
+
 const char *dm_device_name(struct mapped_device *md)
 {
 	return md->name;

include/linux/device-mapper.h

···
  */
 struct mapped_device *dm_get_md(dev_t dev);
 void dm_get(struct mapped_device *md);
+int dm_hold(struct mapped_device *md);
 void dm_put(struct mapped_device *md);
 
 /*