bcache: use bio cloning for detached device requests

Previously, bcache hijacked the bi_end_io and bi_private fields of
the incoming bio when the backing device was in a detached state.
This is fragile and breaks if the bio is needed to be processed by
other layers.

This patch transitions to using a cloned bio embedded within a private
structure. This ensures the original bio's metadata remains untouched.

Fixes: 53280e3984 ("bcache: fix improper use of bi_end_io")
Co-developed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Shida Zhang <zhangshida@kylinos.cn>
Acked-by: Coly Li <colyli@fnnas.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
master
Shida Zhang 2026-01-22 14:13:21 +08:00 committed by Jens Axboe
parent 046be7e596
commit 3ef825dfd4
3 changed files with 55 additions and 47 deletions

View File

@ -273,6 +273,8 @@ struct bcache_device {
struct bio_set bio_split;
struct bio_set bio_detached;
unsigned int data_csum:1;
int (*cache_miss)(struct btree *b, struct search *s,
@ -753,6 +755,13 @@ struct bbio {
struct bio bio;
};
struct detached_dev_io_private {
struct bcache_device *d;
unsigned long start_time;
struct bio *orig_bio;
struct bio bio;
};
#define BTREE_PRIO USHRT_MAX
#define INITIAL_PRIO 32768U

View File

@ -1077,68 +1077,58 @@ static CLOSURE_CALLBACK(cached_dev_nodata)
continue_at(cl, cached_dev_bio_complete, NULL);
}
struct detached_dev_io_private {
struct bcache_device *d;
unsigned long start_time;
bio_end_io_t *bi_end_io;
void *bi_private;
struct block_device *orig_bdev;
};
static void detached_dev_end_io(struct bio *bio)
{
struct detached_dev_io_private *ddip;
ddip = bio->bi_private;
bio->bi_end_io = ddip->bi_end_io;
bio->bi_private = ddip->bi_private;
struct detached_dev_io_private *ddip =
container_of(bio, struct detached_dev_io_private, bio);
struct bio *orig_bio = ddip->orig_bio;
/* Count on the bcache device */
bio_end_io_acct_remapped(bio, ddip->start_time, ddip->orig_bdev);
bio_end_io_acct(orig_bio, ddip->start_time);
if (bio->bi_status) {
struct cached_dev *dc = container_of(ddip->d,
struct cached_dev, disk);
struct cached_dev *dc = bio->bi_private;
/* should count I/O error for backing device here */
bch_count_backing_io_errors(dc, bio);
orig_bio->bi_status = bio->bi_status;
}
kfree(ddip);
bio_endio(bio);
bio_put(bio);
bio_endio(orig_bio);
}
static void detached_dev_do_request(struct bcache_device *d, struct bio *bio,
struct block_device *orig_bdev, unsigned long start_time)
static void detached_dev_do_request(struct bcache_device *d,
struct bio *orig_bio, unsigned long start_time)
{
struct detached_dev_io_private *ddip;
struct cached_dev *dc = container_of(d, struct cached_dev, disk);
struct bio *clone_bio;
/*
* no need to call closure_get(&dc->disk.cl),
* because upper layer had already opened bcache device,
* which would call closure_get(&dc->disk.cl)
*/
ddip = kzalloc(sizeof(struct detached_dev_io_private), GFP_NOIO);
if (!ddip) {
bio->bi_status = BLK_STS_RESOURCE;
bio_endio(bio);
if (bio_op(orig_bio) == REQ_OP_DISCARD &&
!bdev_max_discard_sectors(dc->bdev)) {
bio_endio(orig_bio);
return;
}
ddip->d = d;
/* Count on the bcache device */
ddip->orig_bdev = orig_bdev;
ddip->start_time = start_time;
ddip->bi_end_io = bio->bi_end_io;
ddip->bi_private = bio->bi_private;
bio->bi_end_io = detached_dev_end_io;
bio->bi_private = ddip;
clone_bio = bio_alloc_clone(dc->bdev, orig_bio, GFP_NOIO,
&d->bio_detached);
if (!clone_bio) {
orig_bio->bi_status = BLK_STS_RESOURCE;
bio_endio(orig_bio);
return;
}
if ((bio_op(bio) == REQ_OP_DISCARD) &&
!bdev_max_discard_sectors(dc->bdev))
detached_dev_end_io(bio);
else
submit_bio_noacct(bio);
ddip = container_of(clone_bio, struct detached_dev_io_private, bio);
/* Count on the bcache device */
ddip->d = d;
ddip->start_time = start_time;
ddip->orig_bio = orig_bio;
clone_bio->bi_end_io = detached_dev_end_io;
clone_bio->bi_private = dc;
submit_bio_noacct(clone_bio);
}
static void quit_max_writeback_rate(struct cache_set *c,
@ -1214,10 +1204,10 @@ void cached_dev_submit_bio(struct bio *bio)
start_time = bio_start_io_acct(bio);
bio_set_dev(bio, dc->bdev);
bio->bi_iter.bi_sector += dc->sb.data_offset;
if (cached_dev_get(dc)) {
bio_set_dev(bio, dc->bdev);
s = search_alloc(bio, d, orig_bdev, start_time);
trace_bcache_request_start(s->d, bio);
@ -1237,9 +1227,10 @@ void cached_dev_submit_bio(struct bio *bio)
else
cached_dev_read(dc, s);
}
} else
} else {
/* I/O request sent to backing device */
detached_dev_do_request(d, bio, orig_bdev, start_time);
detached_dev_do_request(d, bio, start_time);
}
}
static int cached_dev_ioctl(struct bcache_device *d, blk_mode_t mode,

View File

@ -887,6 +887,7 @@ static void bcache_device_free(struct bcache_device *d)
}
bioset_exit(&d->bio_split);
bioset_exit(&d->bio_detached);
kvfree(d->full_dirty_stripes);
kvfree(d->stripe_sectors_dirty);
@ -949,6 +950,11 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size,
BIOSET_NEED_BVECS|BIOSET_NEED_RESCUER))
goto out_ida_remove;
if (bioset_init(&d->bio_detached, 4,
offsetof(struct detached_dev_io_private, bio),
BIOSET_NEED_BVECS|BIOSET_NEED_RESCUER))
goto out_bioset_split_exit;
if (lim.logical_block_size > PAGE_SIZE && cached_bdev) {
/*
* This should only happen with BCACHE_SB_VERSION_BDEV.
@ -964,7 +970,7 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size,
d->disk = blk_alloc_disk(&lim, NUMA_NO_NODE);
if (IS_ERR(d->disk))
goto out_bioset_exit;
goto out_bioset_detach_exit;
set_capacity(d->disk, sectors);
snprintf(d->disk->disk_name, DISK_NAME_LEN, "bcache%i", idx);
@ -976,7 +982,9 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size,
d->disk->private_data = d;
return 0;
out_bioset_exit:
out_bioset_detach_exit:
bioset_exit(&d->bio_detached);
out_bioset_split_exit:
bioset_exit(&d->bio_split);
out_ida_remove:
ida_free(&bcache_device_idx, idx);