block: add a bi_error field to struct bio
Currently we have two different ways to signal an I/O error on a BIO:
(1) by clearing the BIO_UPTODATE flag
(2) by returning a Linux errno value to the bi_end_io callback
The first one has the drawback of only communicating a single possible
error (-EIO), and the second one has the drawback of not beeing persistent
when bios are queued up, and are not passed along from child to parent
bio in the ever more popular chaining scenario. Having both mechanisms
available has the additional drawback of utterly confusing driver authors
and introducing bugs where various I/O submitters only deal with one of
them, and the others have to add boilerplate code to deal with both kinds
of error returns.
So add a new bi_error field to store an errno value directly in struct
bio and remove the existing mechanisms to clean all this up.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: NeilBrown <neilb@suse.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index f80f1af..9aa7d1f 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -255,9 +255,10 @@
done = 1;
if (!test_bit(R1BIO_Uptodate, &r1_bio->state))
- clear_bit(BIO_UPTODATE, &bio->bi_flags);
+ bio->bi_error = -EIO;
+
if (done) {
- bio_endio(bio, 0);
+ bio_endio(bio);
/*
* Wake up any possible resync thread that waits for the device
* to go idle.
@@ -312,9 +313,9 @@
return mirror;
}
-static void raid1_end_read_request(struct bio *bio, int error)
+static void raid1_end_read_request(struct bio *bio)
{
- int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
+ int uptodate = !bio->bi_error;
struct r1bio *r1_bio = bio->bi_private;
int mirror;
struct r1conf *conf = r1_bio->mddev->private;
@@ -397,9 +398,8 @@
}
}
-static void raid1_end_write_request(struct bio *bio, int error)
+static void raid1_end_write_request(struct bio *bio)
{
- int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
struct r1bio *r1_bio = bio->bi_private;
int mirror, behind = test_bit(R1BIO_BehindIO, &r1_bio->state);
struct r1conf *conf = r1_bio->mddev->private;
@@ -410,7 +410,7 @@
/*
* 'one mirror IO has finished' event handler:
*/
- if (!uptodate) {
+ if (bio->bi_error) {
set_bit(WriteErrorSeen,
&conf->mirrors[mirror].rdev->flags);
if (!test_and_set_bit(WantReplacement,
@@ -793,7 +793,7 @@
if (unlikely((bio->bi_rw & REQ_DISCARD) &&
!blk_queue_discard(bdev_get_queue(bio->bi_bdev))))
/* Just ignore it */
- bio_endio(bio, 0);
+ bio_endio(bio);
else
generic_make_request(bio);
bio = next;
@@ -1068,7 +1068,7 @@
if (unlikely((bio->bi_rw & REQ_DISCARD) &&
!blk_queue_discard(bdev_get_queue(bio->bi_bdev))))
/* Just ignore it */
- bio_endio(bio, 0);
+ bio_endio(bio);
else
generic_make_request(bio);
bio = next;
@@ -1734,7 +1734,7 @@
return err;
}
-static void end_sync_read(struct bio *bio, int error)
+static void end_sync_read(struct bio *bio)
{
struct r1bio *r1_bio = bio->bi_private;
@@ -1745,16 +1745,16 @@
* or re-read if the read failed.
* We don't do much here, just schedule handling by raid1d
*/
- if (test_bit(BIO_UPTODATE, &bio->bi_flags))
+ if (!bio->bi_error)
set_bit(R1BIO_Uptodate, &r1_bio->state);
if (atomic_dec_and_test(&r1_bio->remaining))
reschedule_retry(r1_bio);
}
-static void end_sync_write(struct bio *bio, int error)
+static void end_sync_write(struct bio *bio)
{
- int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
+ int uptodate = !bio->bi_error;
struct r1bio *r1_bio = bio->bi_private;
struct mddev *mddev = r1_bio->mddev;
struct r1conf *conf = mddev->private;
@@ -1941,7 +1941,7 @@
idx ++;
}
set_bit(R1BIO_Uptodate, &r1_bio->state);
- set_bit(BIO_UPTODATE, &bio->bi_flags);
+ bio->bi_error = 0;
return 1;
}
@@ -1965,15 +1965,14 @@
for (i = 0; i < conf->raid_disks * 2; i++) {
int j;
int size;
- int uptodate;
+ int error;
struct bio *b = r1_bio->bios[i];
if (b->bi_end_io != end_sync_read)
continue;
- /* fixup the bio for reuse, but preserve BIO_UPTODATE */
- uptodate = test_bit(BIO_UPTODATE, &b->bi_flags);
+ /* fixup the bio for reuse, but preserve errno */
+ error = b->bi_error;
bio_reset(b);
- if (!uptodate)
- clear_bit(BIO_UPTODATE, &b->bi_flags);
+ b->bi_error = error;
b->bi_vcnt = vcnt;
b->bi_iter.bi_size = r1_bio->sectors << 9;
b->bi_iter.bi_sector = r1_bio->sector +
@@ -1996,7 +1995,7 @@
}
for (primary = 0; primary < conf->raid_disks * 2; primary++)
if (r1_bio->bios[primary]->bi_end_io == end_sync_read &&
- test_bit(BIO_UPTODATE, &r1_bio->bios[primary]->bi_flags)) {
+ !r1_bio->bios[primary]->bi_error) {
r1_bio->bios[primary]->bi_end_io = NULL;
rdev_dec_pending(conf->mirrors[primary].rdev, mddev);
break;
@@ -2006,14 +2005,14 @@
int j;
struct bio *pbio = r1_bio->bios[primary];
struct bio *sbio = r1_bio->bios[i];
- int uptodate = test_bit(BIO_UPTODATE, &sbio->bi_flags);
+ int error = sbio->bi_error;
if (sbio->bi_end_io != end_sync_read)
continue;
- /* Now we can 'fixup' the BIO_UPTODATE flag */
- set_bit(BIO_UPTODATE, &sbio->bi_flags);
+ /* Now we can 'fixup' the error value */
+ sbio->bi_error = 0;
- if (uptodate) {
+ if (!error) {
for (j = vcnt; j-- ; ) {
struct page *p, *s;
p = pbio->bi_io_vec[j].bv_page;
@@ -2028,7 +2027,7 @@
if (j >= 0)
atomic64_add(r1_bio->sectors, &mddev->resync_mismatches);
if (j < 0 || (test_bit(MD_RECOVERY_CHECK, &mddev->recovery)
- && uptodate)) {
+ && !error)) {
/* No need to write to this device. */
sbio->bi_end_io = NULL;
rdev_dec_pending(conf->mirrors[i].rdev, mddev);
@@ -2269,11 +2268,11 @@
struct bio *bio = r1_bio->bios[m];
if (bio->bi_end_io == NULL)
continue;
- if (test_bit(BIO_UPTODATE, &bio->bi_flags) &&
+ if (!bio->bi_error &&
test_bit(R1BIO_MadeGood, &r1_bio->state)) {
rdev_clear_badblocks(rdev, r1_bio->sector, s, 0);
}
- if (!test_bit(BIO_UPTODATE, &bio->bi_flags) &&
+ if (bio->bi_error &&
test_bit(R1BIO_WriteError, &r1_bio->state)) {
if (!rdev_set_badblocks(rdev, r1_bio->sector, s, 0))
md_error(conf->mddev, rdev);