Don't decrement bi_size in bio_endio

The only caller of bio_endio that does not pass the full bi_size
is end_that_request_first.  Also, no ->bi_end_io method is really
interested in bi_size being decremented.

So move the decrement and related code into ll_rw_blk and merge it
with order_bio_endio to form req_bio_endio which does endio functionality
specific to request completion.

As some ->bi_end_io methods do check bi_size of 0, we set it thus for
now, but that will go in the next patch.

Signed-off-by: Neil Brown <neilb@suse.de>
### Diffstat output
 ./block/ll_rw_blk.c |   42 +++++++++++++++++++++++++++---------------
 ./fs/bio.c          |   23 +++++++++++------------
 2 files changed, 38 insertions(+), 27 deletions(-)

diff .prev/block/ll_rw_blk.c ./block/ll_rw_blk.c
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>

diff --git a/block/ll_rw_blk.c b/block/ll_rw_blk.c
index dfe0948ec8b26c1f89f393e66e9022ad6a4c395f..b55ed0df33f06f3ed87ebb63ce7a7d8195f8b110 100644 (file)
--- a/block/ll_rw_blk.c
+++ b/block/ll_rw_blk.c
@@ -527,22 +527,36 @@ int blk_do_ordered(struct request_queue *q, struct request **rqp)
        return 1;
 }
 
-static int ordered_bio_endio(struct request *rq, struct bio *bio,
-                            unsigned int nbytes, int error)
+static void req_bio_endio(struct request *rq, struct bio *bio,
+                         unsigned int nbytes, int error)
 {
        struct request_queue *q = rq->q;
 
-       if (&q->bar_rq != rq)
-               return 0;
+       if (&q->bar_rq != rq) {
+               if (error)
+                       clear_bit(BIO_UPTODATE, &bio->bi_flags);
+               else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
+                       error = -EIO;
 
-       /*
-        * Okay, this is the barrier request in progress, just
-        * record the error;
-        */
-       if (error && !q->orderr)
-               q->orderr = error;
+               if (unlikely(nbytes > bio->bi_size)) {
+                       printk("%s: want %u bytes done, only %u left\n",
+                              __FUNCTION__, nbytes, bio->bi_size);
+                       nbytes = bio->bi_size;
+               }
 
-       return 1;
+               bio->bi_size -= nbytes;
+               bio->bi_sector += (nbytes >> 9);
+               if (bio->bi_size == 0)
+                       bio_endio(bio, bio->bi_size, error);
+       } else {
+
+               /*
+                * Okay, this is the barrier request in progress, just
+                * record the error;
+                */
+               if (error && !q->orderr)
+                       q->orderr = error;
+       }
 }
 
 /**
@@ -3388,8 +3402,7 @@ static int __end_that_request_first(struct request *req, int uptodate,
                if (nr_bytes >= bio->bi_size) {
                        req->bio = bio->bi_next;
                        nbytes = bio->bi_size;
-                       if (!ordered_bio_endio(req, bio, nbytes, error))
-                               bio_endio(bio, nbytes, error);
+                       req_bio_endio(req, bio, nbytes, error);
                        next_idx = 0;
                        bio_nbytes = 0;
                } else {
@@ -3444,8 +3457,7 @@ static int __end_that_request_first(struct request *req, int uptodate,
         * if the request wasn't completed, update state
         */
        if (bio_nbytes) {
-               if (!ordered_bio_endio(req, bio, bio_nbytes, error))
-                       bio_endio(bio, bio_nbytes, error);
+               req_bio_endio(req, bio, bio_nbytes, error);
                bio->bi_idx += next_idx;
                bio_iovec(bio)->bv_offset += nr_bytes;
                bio_iovec(bio)->bv_len -= nr_bytes;

diff --git a/fs/bio.c b/fs/bio.c
index 5720b940bb5fc4e53b0a03a9723339113c69ac5b..3adecd64ff6e592f7857f82d042e72648caa2661 100644 (file)
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -1006,13 +1006,14 @@ void bio_check_pages_dirty(struct bio *bio)
  * @error:     error, if any
  *
  * Description:
- *   bio_endio() will end I/O on @bytes_done number of bytes. This may be
- *   just a partial part of the bio, or it may be the whole bio. bio_endio()
- *   is the preferred way to end I/O on a bio, it takes care of decrementing
- *   bi_size and clearing BIO_UPTODATE on error. @error is 0 on success, and
- *   and one of the established -Exxxx (-EIO, for instance) error values in
- *   case something went wrong. Noone should call bi_end_io() directly on
- *   a bio unless they own it and thus know that it has an end_io function.
+ *   bio_endio() will end I/O on @bytes_done number of bytes. This
+ *   must always be the whole (remaining) bio. bio_endio() is the
+ *   preferred way to end I/O on a bio, it takes care of clearing
+ *   BIO_UPTODATE on error. @error is 0 on success, and and one of the
+ *   established -Exxxx (-EIO, for instance) error values in case
+ *   something went wrong. Noone should call bi_end_io() directly on a
+ *   bio unless they own it and thus know that it has an end_io
+ *   function.
  **/
 void bio_endio(struct bio *bio, unsigned int bytes_done, int error)
 {
@@ -1021,16 +1022,14 @@ void bio_endio(struct bio *bio, unsigned int bytes_done, int error)
        else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
                error = -EIO;
 
-       if (unlikely(bytes_done > bio->bi_size)) {
+       if (unlikely(bytes_done != bio->bi_size)) {
                printk("%s: want %u bytes done, only %u left\n", __FUNCTION__,
                                                bytes_done, bio->bi_size);
                bytes_done = bio->bi_size;
        }
 
-       bio->bi_size -= bytes_done;
-       bio->bi_sector += (bytes_done >> 9);
-
-       if (bio->bi_size && bio->bi_end_io)
+       bio->bi_size = 0; /* expected by some callees - will be removed */
+       if (bio->bi_end_io)
                bio->bi_end_io(bio, bytes_done, error);
 }