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/raid5.c b/drivers/md/raid5.c
index 59e44e9..84d6eec 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -233,7 +233,7 @@
bi->bi_iter.bi_size = 0;
trace_block_bio_complete(bdev_get_queue(bi->bi_bdev),
bi, 0);
- bio_endio(bi, 0);
+ bio_endio(bi);
bi = return_bi;
}
}
@@ -887,9 +887,9 @@
}
static void
-raid5_end_read_request(struct bio *bi, int error);
+raid5_end_read_request(struct bio *bi);
static void
-raid5_end_write_request(struct bio *bi, int error);
+raid5_end_write_request(struct bio *bi);
static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
{
@@ -2277,12 +2277,11 @@
conf->slab_cache = NULL;
}
-static void raid5_end_read_request(struct bio * bi, int error)
+static void raid5_end_read_request(struct bio * bi)
{
struct stripe_head *sh = bi->bi_private;
struct r5conf *conf = sh->raid_conf;
int disks = sh->disks, i;
- int uptodate = test_bit(BIO_UPTODATE, &bi->bi_flags);
char b[BDEVNAME_SIZE];
struct md_rdev *rdev = NULL;
sector_t s;
@@ -2291,9 +2290,9 @@
if (bi == &sh->dev[i].req)
break;
- pr_debug("end_read_request %llu/%d, count: %d, uptodate %d.\n",
+ pr_debug("end_read_request %llu/%d, count: %d, error %d.\n",
(unsigned long long)sh->sector, i, atomic_read(&sh->count),
- uptodate);
+ bi->bi_error);
if (i == disks) {
BUG();
return;
@@ -2312,7 +2311,7 @@
s = sh->sector + rdev->new_data_offset;
else
s = sh->sector + rdev->data_offset;
- if (uptodate) {
+ if (!bi->bi_error) {
set_bit(R5_UPTODATE, &sh->dev[i].flags);
if (test_bit(R5_ReadError, &sh->dev[i].flags)) {
/* Note that this cannot happen on a
@@ -2400,13 +2399,12 @@
release_stripe(sh);
}
-static void raid5_end_write_request(struct bio *bi, int error)
+static void raid5_end_write_request(struct bio *bi)
{
struct stripe_head *sh = bi->bi_private;
struct r5conf *conf = sh->raid_conf;
int disks = sh->disks, i;
struct md_rdev *uninitialized_var(rdev);
- int uptodate = test_bit(BIO_UPTODATE, &bi->bi_flags);
sector_t first_bad;
int bad_sectors;
int replacement = 0;
@@ -2429,23 +2427,23 @@
break;
}
}
- pr_debug("end_write_request %llu/%d, count %d, uptodate: %d.\n",
+ pr_debug("end_write_request %llu/%d, count %d, error: %d.\n",
(unsigned long long)sh->sector, i, atomic_read(&sh->count),
- uptodate);
+ bi->bi_error);
if (i == disks) {
BUG();
return;
}
if (replacement) {
- if (!uptodate)
+ if (bi->bi_error)
md_error(conf->mddev, rdev);
else if (is_badblock(rdev, sh->sector,
STRIPE_SECTORS,
&first_bad, &bad_sectors))
set_bit(R5_MadeGoodRepl, &sh->dev[i].flags);
} else {
- if (!uptodate) {
+ if (bi->bi_error) {
set_bit(STRIPE_DEGRADED, &sh->state);
set_bit(WriteErrorSeen, &rdev->flags);
set_bit(R5_WriteError, &sh->dev[i].flags);
@@ -2466,7 +2464,7 @@
}
rdev_dec_pending(rdev, conf->mddev);
- if (sh->batch_head && !uptodate && !replacement)
+ if (sh->batch_head && bi->bi_error && !replacement)
set_bit(STRIPE_BATCH_ERR, &sh->batch_head->state);
if (!test_and_clear_bit(R5_DOUBLE_LOCKED, &sh->dev[i].flags))
@@ -3107,7 +3105,8 @@
while (bi && bi->bi_iter.bi_sector <
sh->dev[i].sector + STRIPE_SECTORS) {
struct bio *nextbi = r5_next_bio(bi, sh->dev[i].sector);
- clear_bit(BIO_UPTODATE, &bi->bi_flags);
+
+ bi->bi_error = -EIO;
if (!raid5_dec_bi_active_stripes(bi)) {
md_write_end(conf->mddev);
bi->bi_next = *return_bi;
@@ -3131,7 +3130,8 @@
while (bi && bi->bi_iter.bi_sector <
sh->dev[i].sector + STRIPE_SECTORS) {
struct bio *bi2 = r5_next_bio(bi, sh->dev[i].sector);
- clear_bit(BIO_UPTODATE, &bi->bi_flags);
+
+ bi->bi_error = -EIO;
if (!raid5_dec_bi_active_stripes(bi)) {
md_write_end(conf->mddev);
bi->bi_next = *return_bi;
@@ -3156,7 +3156,8 @@
sh->dev[i].sector + STRIPE_SECTORS) {
struct bio *nextbi =
r5_next_bio(bi, sh->dev[i].sector);
- clear_bit(BIO_UPTODATE, &bi->bi_flags);
+
+ bi->bi_error = -EIO;
if (!raid5_dec_bi_active_stripes(bi)) {
bi->bi_next = *return_bi;
*return_bi = bi;
@@ -4749,12 +4750,11 @@
* first).
* If the read failed..
*/
-static void raid5_align_endio(struct bio *bi, int error)
+static void raid5_align_endio(struct bio *bi)
{
struct bio* raid_bi = bi->bi_private;
struct mddev *mddev;
struct r5conf *conf;
- int uptodate = test_bit(BIO_UPTODATE, &bi->bi_flags);
struct md_rdev *rdev;
bio_put(bi);
@@ -4766,10 +4766,10 @@
rdev_dec_pending(rdev, conf->mddev);
- if (!error && uptodate) {
+ if (!bi->bi_error) {
trace_block_bio_complete(bdev_get_queue(raid_bi->bi_bdev),
raid_bi, 0);
- bio_endio(raid_bi, 0);
+ bio_endio(raid_bi);
if (atomic_dec_and_test(&conf->active_aligned_reads))
wake_up(&conf->wait_for_quiescent);
return;
@@ -5133,7 +5133,7 @@
remaining = raid5_dec_bi_active_stripes(bi);
if (remaining == 0) {
md_write_end(mddev);
- bio_endio(bi, 0);
+ bio_endio(bi);
}
}
@@ -5297,7 +5297,7 @@
release_stripe_plug(mddev, sh);
} else {
/* cannot get stripe for read-ahead, just give-up */
- clear_bit(BIO_UPTODATE, &bi->bi_flags);
+ bi->bi_error = -EIO;
break;
}
}
@@ -5311,7 +5311,7 @@
trace_block_bio_complete(bdev_get_queue(bi->bi_bdev),
bi, 0);
- bio_endio(bi, 0);
+ bio_endio(bi);
}
}
@@ -5707,7 +5707,7 @@
if (remaining == 0) {
trace_block_bio_complete(bdev_get_queue(raid_bio->bi_bdev),
raid_bio, 0);
- bio_endio(raid_bio, 0);
+ bio_endio(raid_bio);
}
if (atomic_dec_and_test(&conf->active_aligned_reads))
wake_up(&conf->wait_for_quiescent);