block: improve flush bio completion

bio's for flush are completed twice - once during the data phase and
one more time after the whole sequence is complete.  The first
completion shouldn't notify completion to the issuer.

This was achieved by skipping all bio completion steps in
req_bio_endio() for the first completion; however, this has two
drawbacks.

* Error is not recorded in bio and must be tracked somewhere else.

* Partial completion is not supported.

Both don't cause problems for the current users; however, they make
further improvements difficult.  Change req_bio_endio() such that it
only skips the actual notification part for the first completion.  bio
completion is implemented with partial completions on mind anyway so
this is as simple as moving the REQ_FLUSH_SEQ conditional such that
only calling of bio_endio() is skipped.

Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>

diff --git a/block/blk-core.c b/block/blk-core.c
index fc7d8ad76f440916e1fa2c00ebd9550d51833829..617bb9e40927dd4e669f576d0b4b0cd52d067022 100644 (file)
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -136,37 +136,31 @@ static void req_bio_endio(struct request *rq, struct bio *bio,
 {
        struct request_queue *q = rq->q;
 
-       if (!(rq->cmd_flags & REQ_FLUSH_SEQ)) {
-               if (error)
-                       clear_bit(BIO_UPTODATE, &bio->bi_flags);
-               else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
-                       error = -EIO;
-
-               if (unlikely(nbytes > bio->bi_size)) {
-                       printk(KERN_ERR "%s: want %u bytes done, %u left\n",
-                              __func__, nbytes, bio->bi_size);
-                       nbytes = bio->bi_size;
-               }
+       if (error)
+               clear_bit(BIO_UPTODATE, &bio->bi_flags);
+       else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
+               error = -EIO;
+
+       if (unlikely(nbytes > bio->bi_size)) {
+               printk(KERN_ERR "%s: want %u bytes done, %u left\n",
+                      __func__, nbytes, bio->bi_size);
+               nbytes = bio->bi_size;
+       }
 
-               if (unlikely(rq->cmd_flags & REQ_QUIET))
-                       set_bit(BIO_QUIET, &bio->bi_flags);
+       if (unlikely(rq->cmd_flags & REQ_QUIET))
+               set_bit(BIO_QUIET, &bio->bi_flags);
 
-               bio->bi_size -= nbytes;
-               bio->bi_sector += (nbytes >> 9);
+       bio->bi_size -= nbytes;
+       bio->bi_sector += (nbytes >> 9);
 
-               if (bio_integrity(bio))
-                       bio_integrity_advance(bio, nbytes);
+       if (bio_integrity(bio))
+               bio_integrity_advance(bio, nbytes);
 
-               if (bio->bi_size == 0)
-                       bio_endio(bio, error);
-       } else {
-               /*
-                * Okay, this is the sequenced flush request in
-                * progress, just record the error;
-                */
-               if (error && !q->flush_err)
-                       q->flush_err = error;
-       }
+       /* don't actually finish bio if it's part of flush sequence */
+       if (bio->bi_size == 0 && !(rq->cmd_flags & REQ_FLUSH_SEQ))
+               bio_endio(bio, error);
+       else if (error && !q->flush_err)
+               q->flush_err = error;
 }
 
 void blk_dump_rq_flags(struct request *rq, char *msg)