[PATCH 3.16.y-ckt 079/180] dm snapshot: fix hung bios when copy error occurs

[Luis Henriques]

3.16.7-ckt24 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Mikulas Patocka <mpatocka at redhat.com>

commit 385277bfb57faac44e92497104ba542cdd82d5fe upstream.

When there is an error copying a chunk dm-snapshot can incorrectly hold
associated bios indefinitely, resulting in hung IO.

The function copy_callback sets pe->error if there was error copying the
chunk, and then calls complete_exception.  complete_exception calls
pending_complete on error, otherwise it calls commit_exception with
commit_callback (and commit_callback calls complete_exception).

The persistent exception store (dm-snap-persistent.c) assumes that calls
to prepare_exception and commit_exception are paired.
persistent_prepare_exception increases ps->pending_count and
persistent_commit_exception decreases it.

If there is a copy error, persistent_prepare_exception is called but
persistent_commit_exception is not.  This results in the variable
ps->pending_count never returning to zero and that causes some pending
exceptions (and their associated bios) to be held forever.

Fix this by unconditionally calling commit_exception regardless of
whether the copy was successful.  A new "valid" parameter is added to
commit_exception -- when the copy fails this parameter is set to zero so
that the chunk that failed to copy (and all following chunks) is not
recorded in the snapshot store.  Also, remove commit_callback now that
it is merely a wrapper around pending_complete.

Signed-off-by: Mikulas Patocka <mpatocka at redhat.com>
Signed-off-by: Mike Snitzer <snitzer at redhat.com>
Signed-off-by: Luis Henriques <luis.henriques at canonical.com>
---
 drivers/md/dm-exception-store.h |  2 +-
 drivers/md/dm-snap-persistent.c |  5 ++++-
 drivers/md/dm-snap-transient.c  |  4 ++--
 drivers/md/dm-snap.c            | 20 +++++---------------
 4 files changed, 12 insertions(+), 19 deletions(-)

diff --git a/drivers/md/dm-exception-store.h b/drivers/md/dm-exception-store.h
index 0b2536247cf5..84e27708ad97 100644
--- a/drivers/md/dm-exception-store.h
+++ b/drivers/md/dm-exception-store.h
@@ -70,7 +70,7 @@ struct dm_exception_store_type {
 	 * Update the metadata with this exception.
 	 */
 	void (*commit_exception) (struct dm_exception_store *store,
-				  struct dm_exception *e,
+				  struct dm_exception *e, int valid,
 				  void (*callback) (void *, int success),
 				  void *callback_context);
 
diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c
index d6e88178d22c..d3272acc0f0e 100644
--- a/drivers/md/dm-snap-persistent.c
+++ b/drivers/md/dm-snap-persistent.c
@@ -700,7 +700,7 @@ static int persistent_prepare_exception(struct dm_exception_store *store,
 }
 
 static void persistent_commit_exception(struct dm_exception_store *store,
-					struct dm_exception *e,
+					struct dm_exception *e, int valid,
 					void (*callback) (void *, int success),
 					void *callback_context)
 {
@@ -709,6 +709,9 @@ static void persistent_commit_exception(struct dm_exception_store *store,
 	struct core_exception ce;
 	struct commit_callback *cb;
 
+	if (!valid)
+		ps->valid = 0;
+
 	ce.old_chunk = e->old_chunk;
 	ce.new_chunk = e->new_chunk;
 	write_exception(ps, ps->current_committed++, &ce);
diff --git a/drivers/md/dm-snap-transient.c b/drivers/md/dm-snap-transient.c
index 1ce9a2586e41..31439d53cf7e 100644
--- a/drivers/md/dm-snap-transient.c
+++ b/drivers/md/dm-snap-transient.c
@@ -52,12 +52,12 @@ static int transient_prepare_exception(struct dm_exception_store *store,
 }
 
 static void transient_commit_exception(struct dm_exception_store *store,
-				       struct dm_exception *e,
+				       struct dm_exception *e, int valid,
 				       void (*callback) (void *, int success),
 				       void *callback_context)
 {
 	/* Just succeed */
-	callback(callback_context, 1);
+	callback(callback_context, valid);
 }
 
 static void transient_usage(struct dm_exception_store *store,
diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c
index 3363fa199a19..057237277854 100644
--- a/drivers/md/dm-snap.c
+++ b/drivers/md/dm-snap.c
@@ -1436,8 +1436,9 @@ static void __invalidate_snapshot(struct dm_snapshot *s, int err)
 	dm_table_event(s->ti->table);
 }
 
-static void pending_complete(struct dm_snap_pending_exception *pe, int success)
+static void pending_complete(void *context, int success)
 {
+	struct dm_snap_pending_exception *pe = context;
 	struct dm_exception *e;
 	struct dm_snapshot *s = pe->snap;
 	struct bio *origin_bios = NULL;
@@ -1508,24 +1509,13 @@ out:
 	free_pending_exception(pe);
 }
 
-static void commit_callback(void *context, int success)
-{
-	struct dm_snap_pending_exception *pe = context;
-
-	pending_complete(pe, success);
-}
-
 static void complete_exception(struct dm_snap_pending_exception *pe)
 {
 	struct dm_snapshot *s = pe->snap;
 
-	if (unlikely(pe->copy_error))
-		pending_complete(pe, 0);
-
-	else
-		/* Update the metadata if we are persistent */
-		s->store->type->commit_exception(s->store, &pe->e,
-						 commit_callback, pe);
+	/* Update the metadata if we are persistent */
+	s->store->type->commit_exception(s->store, &pe->e, !pe->copy_error,
+					 pending_complete, pe);
 }
 
 /*