1/ When aligned requests fail (read error) they need to be retried
via the normal method (stripe cache). As we cannot be sure that
we can process a single read in one go (we may not be able to
allocate all the stripes needed) we store a bio-being-retried
and a list of bioes-that-still-need-to-be-retried.
When find a bio that needs to be retried, we should add it to
the list, not to single-bio...
2/ The cloned bio is being used-after-free (to test BIO_UPTODATE).
3/ We forgot to add rdev->data_offset when submitting
a bio for aligned-read
4/ clone_bio calls blk_recount_segments and then we change bi_bdev,
so we need to invalidate the segment counts.
5/ We were never incrementing 'scnt' when resubmitting failed
aligned requests.
Signed-off-by: Neil Brown <neilb@xxxxxxx>
### Diffstat output
./drivers/md/raid5.c | 14 +++++++++-----
1 file changed, 9 insertions(+), 5 deletions(-)
diff .prev/drivers/md/raid5.c ./drivers/md/raid5.c
--- .prev/drivers/md/raid5.c 2006-11-14 10:34:17.000000000 +1100
+++ ./drivers/md/raid5.c 2006-11-14 10:34:33.000000000 +1100
@@ -2658,8 +2658,8 @@ static void add_bio_to_retry(struct bio
spin_lock_irqsave(&conf->device_lock, flags);
- bi->bi_next = conf->retry_read_aligned;
- conf->retry_read_aligned = bi;
+ bi->bi_next = conf->retry_read_aligned_list;
+ conf->retry_read_aligned_list = bi;
spin_unlock_irqrestore(&conf->device_lock, flags);
md_wakeup_thread(conf->mddev->thread);
@@ -2698,6 +2698,7 @@ static int raid5_align_endio(struct bio
struct bio* raid_bi = bi->bi_private;
mddev_t *mddev;
raid5_conf_t *conf;
+ int uptodate = test_bit(BIO_UPTODATE, &bi->bi_flags);
if (bi->bi_size)
return 1;
@@ -2706,7 +2707,7 @@ static int raid5_align_endio(struct bio
mddev = raid_bi->bi_bdev->bd_disk->queue->queuedata;
conf = mddev_to_conf(mddev);
- if (!error && test_bit(BIO_UPTODATE, &bi->bi_flags)) {
+ if (!error && uptodate) {
bio_endio(raid_bi, bytes, 0);
if (atomic_dec_and_test(&conf->active_aligned_reads))
wake_up(&conf->wait_for_stripe);
@@ -2759,9 +2760,11 @@ static int chunk_aligned_read(request_qu
rcu_read_lock();
rdev = rcu_dereference(conf->disks[dd_idx].rdev);
if (rdev && test_bit(In_sync, &rdev->flags)) {
- align_bi->bi_bdev = rdev->bdev;
atomic_inc(&rdev->nr_pending);
rcu_read_unlock();
+ align_bi->bi_bdev = rdev->bdev;
+ align_bi->bi_flags &= ~(1 << BIO_SEG_VALID);
+ align_bi->bi_sector += rdev->data_offset;
spin_lock_irq(&conf->device_lock);
wait_event_lock_irq(conf->wait_for_stripe,
@@ -3151,7 +3154,8 @@ static int retry_aligned_read(raid5_con
conf);
last_sector = raid_bio->bi_sector + (raid_bio->bi_size>>9);
- for (; logical_sector < last_sector; logical_sector += STRIPE_SECTORS) {
+ for (; logical_sector < last_sector;
+ logical_sector += STRIPE_SECTORS, scnt++) {
if (scnt < raid_bio->bi_hw_segments)
/* already done this stripe */
-
To unsubscribe from this list: send the line "unsubscribe linux-raid" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
