From: Darrick J. Wong <[email protected]>
Currently, if the loop device receives a WRITE_ZEROES request, it asks
the underlying filesystem to punch out the range. This behavior is
correct if unmapping is allowed. However, a NOUNMAP request means that
the caller forbids us from freeing the storage backing the range, so
punching out the range is incorrect behavior.
To satisfy a NOUNMAP | WRITE_ZEROES request, loop should ask the
underlying filesystem to FALLOC_FL_ZERO_RANGE, which is (according to
the fallocate documentation) required to ensure that the entire range is
backed by real storage, which suffices for our purposes.
Fixes: 19372e2769179dd ("loop: implement REQ_OP_WRITE_ZEROES")
Signed-off-by: Darrick J. Wong <[email protected]>
---
drivers/block/loop.c | 32 +++++++++++++++++++++++++++++++-
1 file changed, 31 insertions(+), 1 deletion(-)
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index f6f77eaa7217..0dc981e94bf0 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -441,6 +441,35 @@ static int lo_discard(struct loop_device *lo, struct
request *rq, loff_t pos)
return ret;
}
+static int lo_zeroout(struct loop_device *lo, struct request *rq, loff_t pos)
+{
+ struct file *file = lo->lo_backing_file;
+ int mode = FALLOC_FL_ZERO_RANGE | FALLOC_FL_KEEP_SIZE;
+ int ret;
+
+ /* If we're allowed to unmap the blocks, ask the fs to punch them. */
+ if (!(rq->cmd_flags & REQ_NOUNMAP)) {
+ ret = lo_discard(lo, rq, pos);
+ if (!ret)
+ return 0;
+ }
+
+ /*
+ * Otherwise, ask the fs to zero out the blocks, which will result in
+ * space being allocated to the file.
+ */
+ if (!file->f_op->fallocate) {
+ ret = -EOPNOTSUPP;
+ goto out;
+ }
+
+ ret = file->f_op->fallocate(file, mode, pos, blk_rq_bytes(rq));
+ if (unlikely(ret && ret != -EINVAL && ret != -EOPNOTSUPP))
+ ret = -EIO;
+ out:
+ return ret;
+}
+
static int lo_req_flush(struct loop_device *lo, struct request *rq)
{
struct file *file = lo->lo_backing_file;
@@ -597,8 +626,9 @@ static int do_req_filebacked(struct loop_device *lo, struct
request *rq)
case REQ_OP_FLUSH:
return lo_req_flush(lo, rq);
case REQ_OP_DISCARD:
- case REQ_OP_WRITE_ZEROES:
return lo_discard(lo, rq, pos);
+ case REQ_OP_WRITE_ZEROES:
+ return lo_zeroout(lo, rq, pos);
case REQ_OP_WRITE:
if (lo->transfer)
return lo_write_transfer(lo, rq, pos);
