We need to check if the exception was completed after dropping the lock.
After regaining the lock, __find_pending_exception checks if the exception
was already placed into &s->pending hash.
But we don't check if the exception was already completed and placed into
&s->complete hash. If the process waiting in alloc_pending_exception was
delayed at this point because of a scheduling latency and the exception
was meanwhile completed, we'd miss that and allocate another pending
exception for already completed chunk.
It will lead to a situation when two records for the same chunk exist and
it could lead to data corruption because multiple snapshot I/Os to the
affected chunk could be redirected to different locations in the snapshot.
Signed-off-by: Mikulas Patocka <mpatocka@xxxxxxxxxx>
---
drivers/md/dm-snap.c | 13 +++++++++++++
1 file changed, 13 insertions(+)
Index: linux-2.6.29-rc6-devel/drivers/md/dm-snap.c
===================================================================
--- linux-2.6.29-rc6-devel.orig/drivers/md/dm-snap.c 2009-02-25 18:30:30.000000000 +0100
+++ linux-2.6.29-rc6-devel/drivers/md/dm-snap.c 2009-02-25 18:36:36.000000000 +0100
@@ -1080,6 +1080,13 @@ static int snapshot_map(struct dm_target
goto out_unlock;
}
+ e = lookup_exception(&s->complete, chunk);
+ if (e) {
+ free_pending_exception(pe);
+ remap_exception(s, e, bio, chunk);
+ goto out_unlock;
+ }
+
pe = __find_pending_exception(s, pe, chunk);
if (!pe) {
__invalidate_snapshot(s, -ENOMEM);
@@ -1226,6 +1233,12 @@ static int __origin_write(struct list_he
goto next_snapshot;
}
+ e = lookup_exception(&snap->complete, chunk);
+ if (e) {
+ free_pending_exception(pe);
+ goto next_snapshot;
+ }
+
pe = __find_pending_exception(snap, pe, chunk);
if (!pe) {
__invalidate_snapshot(snap, -ENOMEM);
--
dm-devel mailing list
dm-devel@xxxxxxxxxx
https://www.redhat.com/mailman/listinfo/dm-devel
