diff options
Diffstat (limited to 'drivers/md')
51 files changed, 929 insertions, 947 deletions
diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig index b5ea378e66cb..998a5cfdbc4e 100644 --- a/drivers/md/Kconfig +++ b/drivers/md/Kconfig @@ -204,6 +204,7 @@ config BLK_DEV_DM tristate "Device mapper support" select BLOCK_HOLDER_DEPRECATED if SYSFS select BLK_DEV_DM_BUILTIN + select BLK_MQ_STACKING depends on DAX || DAX=n help Device-mapper is a low level volume manager. It works by allowing diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c index 88c573eeb598..ad9f16689419 100644 --- a/drivers/md/bcache/btree.c +++ b/drivers/md/bcache/btree.c @@ -2060,9 +2060,11 @@ int bch_btree_check(struct cache_set *c) } } + /* + * Must wait for all threads to stop. + */ wait_event_interruptible(check_state->wait, - atomic_read(&check_state->started) == 0 || - test_bit(CACHE_SET_IO_DISABLE, &c->flags)); + atomic_read(&check_state->started) == 0); for (i = 0; i < check_state->total_threads; i++) { if (check_state->infos[i].result) { diff --git a/drivers/md/bcache/io.c b/drivers/md/bcache/io.c index 9c6f9ec55b72..020712c5203f 100644 --- a/drivers/md/bcache/io.c +++ b/drivers/md/bcache/io.c @@ -26,7 +26,8 @@ struct bio *bch_bbio_alloc(struct cache_set *c) struct bbio *b = mempool_alloc(&c->bio_meta, GFP_NOIO); struct bio *bio = &b->bio; - bio_init(bio, bio->bi_inline_vecs, meta_bucket_pages(&c->cache->sb)); + bio_init(bio, NULL, bio->bi_inline_vecs, + meta_bucket_pages(&c->cache->sb), 0); return bio; } diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c index 61bd79babf7a..7c2ca52ca3e4 100644 --- a/drivers/md/bcache/journal.c +++ b/drivers/md/bcache/journal.c @@ -53,14 +53,12 @@ static int journal_read_bucket(struct cache *ca, struct list_head *list, reread: left = ca->sb.bucket_size - offset; len = min_t(unsigned int, left, PAGE_SECTORS << JSET_BITS); - bio_reset(bio); + bio_reset(bio, ca->bdev, REQ_OP_READ); bio->bi_iter.bi_sector = bucket + offset; - bio_set_dev(bio, ca->bdev); bio->bi_iter.bi_size = len << 9; bio->bi_end_io = journal_read_endio; bio->bi_private = &cl; - bio_set_op_attrs(bio, REQ_OP_READ, 0); bch_bio_map(bio, data); closure_bio_submit(ca->set, bio, &cl); @@ -611,11 +609,9 @@ static void do_journal_discard(struct cache *ca) atomic_set(&ja->discard_in_flight, DISCARD_IN_FLIGHT); - bio_init(bio, bio->bi_inline_vecs, 1); - bio_set_op_attrs(bio, REQ_OP_DISCARD, 0); + bio_init(bio, ca->bdev, bio->bi_inline_vecs, 1, REQ_OP_DISCARD); bio->bi_iter.bi_sector = bucket_to_sector(ca->set, ca->sb.d[ja->discard_idx]); - bio_set_dev(bio, ca->bdev); bio->bi_iter.bi_size = bucket_bytes(ca); bio->bi_end_io = journal_discard_endio; @@ -773,16 +769,14 @@ static void journal_write_unlocked(struct closure *cl) atomic_long_add(sectors, &ca->meta_sectors_written); - bio_reset(bio); + bio_reset(bio, ca->bdev, REQ_OP_WRITE | + REQ_SYNC | REQ_META | REQ_PREFLUSH | REQ_FUA); + bch_bio_map(bio, w->data); bio->bi_iter.bi_sector = PTR_OFFSET(k, i); - bio_set_dev(bio, ca->bdev); bio->bi_iter.bi_size = sectors << 9; bio->bi_end_io = journal_write_endio; bio->bi_private = w; - bio_set_op_attrs(bio, REQ_OP_WRITE, - REQ_SYNC|REQ_META|REQ_PREFLUSH|REQ_FUA); - bch_bio_map(bio, w->data); trace_bcache_journal_write(bio, w->data->keys); bio_list_add(&list, bio); diff --git a/drivers/md/bcache/movinggc.c b/drivers/md/bcache/movinggc.c index b9c3d27ec093..99499d1f6e66 100644 --- a/drivers/md/bcache/movinggc.c +++ b/drivers/md/bcache/movinggc.c @@ -79,8 +79,8 @@ static void moving_init(struct moving_io *io) { struct bio *bio = &io->bio.bio; - bio_init(bio, bio->bi_inline_vecs, - DIV_ROUND_UP(KEY_SIZE(&io->w->key), PAGE_SECTORS)); + bio_init(bio, NULL, bio->bi_inline_vecs, + DIV_ROUND_UP(KEY_SIZE(&io->w->key), PAGE_SECTORS), 0); bio_get(bio); bio_set_prio(bio, IOPRIO_PRIO_VALUE(IOPRIO_CLASS_IDLE, 0)); diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c index d15aae6c51c1..fdd0194f84dd 100644 --- a/drivers/md/bcache/request.c +++ b/drivers/md/bcache/request.c @@ -44,10 +44,10 @@ static void bio_csum(struct bio *bio, struct bkey *k) uint64_t csum = 0; bio_for_each_segment(bv, bio, iter) { - void *d = kmap(bv.bv_page) + bv.bv_offset; + void *d = bvec_kmap_local(&bv); csum = crc64_be(csum, d, bv.bv_len); - kunmap(bv.bv_page); + kunmap_local(d); } k->ptr[KEY_PTRS(k)] = csum & (~0ULL >> 1); @@ -685,8 +685,7 @@ static void do_bio_hook(struct search *s, { struct bio *bio = &s->bio.bio; - bio_init(bio, NULL, 0); - __bio_clone_fast(bio, orig_bio); + bio_init_clone(bio->bi_bdev, bio, orig_bio, GFP_NOIO); /* * bi_end_io can be set separately somewhere else, e.g. the * variants in, @@ -831,11 +830,11 @@ static void cached_dev_read_done(struct closure *cl) */ if (s->iop.bio) { - bio_reset(s->iop.bio); + bio_reset(s->iop.bio, s->cache_miss->bi_bdev, REQ_OP_READ); s->iop.bio->bi_iter.bi_sector = s->cache_miss->bi_iter.bi_sector; - bio_copy_dev(s->iop.bio, s->cache_miss); s->iop.bio->bi_iter.bi_size = s->insert_bio_sectors << 9; + bio_clone_blkg_association(s->iop.bio, s->cache_miss); bch_bio_map(s->iop.bio, NULL); bio_copy_data(s->cache_miss, s->iop.bio); @@ -913,14 +912,13 @@ static int cached_dev_cache_miss(struct btree *b, struct search *s, /* btree_search_recurse()'s btree iterator is no good anymore */ ret = miss == bio ? MAP_DONE : -EINTR; - cache_bio = bio_alloc_bioset(GFP_NOWAIT, + cache_bio = bio_alloc_bioset(miss->bi_bdev, DIV_ROUND_UP(s->insert_bio_sectors, PAGE_SECTORS), - &dc->disk.bio_split); + 0, GFP_NOWAIT, &dc->disk.bio_split); if (!cache_bio) goto out_submit; cache_bio->bi_iter.bi_sector = miss->bi_iter.bi_sector; - bio_copy_dev(cache_bio, miss); cache_bio->bi_iter.bi_size = s->insert_bio_sectors << 9; cache_bio->bi_end_io = backing_request_endio; @@ -1025,21 +1023,21 @@ static void cached_dev_write(struct cached_dev *dc, struct search *s) */ struct bio *flush; - flush = bio_alloc_bioset(GFP_NOIO, 0, - &dc->disk.bio_split); + flush = bio_alloc_bioset(bio->bi_bdev, 0, + REQ_OP_WRITE | REQ_PREFLUSH, + GFP_NOIO, &dc->disk.bio_split); if (!flush) { s->iop.status = BLK_STS_RESOURCE; goto insert_data; } - bio_copy_dev(flush, bio); flush->bi_end_io = backing_request_endio; flush->bi_private = cl; - flush->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH; /* I/O request sent to backing device */ closure_bio_submit(s->iop.c, flush, cl); } } else { - s->iop.bio = bio_clone_fast(bio, GFP_NOIO, &dc->disk.bio_split); + s->iop.bio = bio_alloc_clone(bio->bi_bdev, bio, GFP_NOIO, + &dc->disk.bio_split); /* I/O request sent to backing device */ bio->bi_end_io = backing_request_endio; closure_bio_submit(s->iop.c, bio, cl); diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 140f35dc0c45..bf3de149d3c9 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -18,7 +18,6 @@ #include <linux/blkdev.h> #include <linux/pagemap.h> #include <linux/debugfs.h> -#include <linux/genhd.h> #include <linux/idr.h> #include <linux/kthread.h> #include <linux/workqueue.h> @@ -343,8 +342,7 @@ void bch_write_bdev_super(struct cached_dev *dc, struct closure *parent) down(&dc->sb_write_mutex); closure_init(cl, parent); - bio_init(bio, dc->sb_bv, 1); - bio_set_dev(bio, dc->bdev); + bio_init(bio, dc->bdev, dc->sb_bv, 1, 0); bio->bi_end_io = write_bdev_super_endio; bio->bi_private = dc; @@ -387,8 +385,7 @@ void bcache_write_super(struct cache_set *c) if (ca->sb.version < version) ca->sb.version = version; - bio_init(bio, ca->sb_bv, 1); - bio_set_dev(bio, ca->bdev); + bio_init(bio, ca->bdev, ca->sb_bv, 1, 0); bio->bi_end_io = write_super_endio; bio->bi_private = ca; @@ -2240,7 +2237,7 @@ static int cache_alloc(struct cache *ca) __module_get(THIS_MODULE); kobject_init(&ca->kobj, &bch_cache_ktype); - bio_init(&ca->journal.bio, ca->journal.bio.bi_inline_vecs, 8); + bio_init(&ca->journal.bio, NULL, ca->journal.bio.bi_inline_vecs, 8, 0); /* * when ca->sb.njournal_buckets is not zero, journal exists, diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c index c7560f66dca8..9ee0005874cd 100644 --- a/drivers/md/bcache/writeback.c +++ b/drivers/md/bcache/writeback.c @@ -292,8 +292,8 @@ static void dirty_init(struct keybuf_key *w) struct dirty_io *io = w->private; struct bio *bio = &io->bio; - bio_init(bio, bio->bi_inline_vecs, - DIV_ROUND_UP(KEY_SIZE(&w->key), PAGE_SECTORS)); + bio_init(bio, NULL, bio->bi_inline_vecs, + DIV_ROUND_UP(KEY_SIZE(&w->key), PAGE_SECTORS), 0); if (!io->dc->writeback_percent) bio_set_prio(bio, IOPRIO_PRIO_VALUE(IOPRIO_CLASS_IDLE, 0)); @@ -585,10 +585,13 @@ void bcache_dev_sectors_dirty_add(struct cache_set *c, unsigned int inode, sectors_dirty = atomic_add_return(s, d->stripe_sectors_dirty + stripe); - if (sectors_dirty == d->stripe_size) - set_bit(stripe, d->full_dirty_stripes); - else - clear_bit(stripe, d->full_dirty_stripes); + if (sectors_dirty == d->stripe_size) { + if (!test_bit(stripe, d->full_dirty_stripes)) + set_bit(stripe, d->full_dirty_stripes); + } else { + if (test_bit(stripe, d->full_dirty_stripes)) + clear_bit(stripe, d->full_dirty_stripes); + } nr_sectors -= s; stripe_offset = 0; @@ -998,9 +1001,11 @@ void bch_sectors_dirty_init(struct bcache_device *d) } } + /* + * Must wait for all threads to stop. + */ wait_event_interruptible(state->wait, - atomic_read(&state->started) == 0 || - test_bit(CACHE_SET_IO_DISABLE, &c->flags)); + atomic_read(&state->started) == 0); out: kfree(state); diff --git a/drivers/md/dm-cache-policy-smq.c b/drivers/md/dm-cache-policy-smq.c index b61aac00ff40..a3d281fc14c3 100644 --- a/drivers/md/dm-cache-policy-smq.c +++ b/drivers/md/dm-cache-policy-smq.c @@ -1026,7 +1026,9 @@ static unsigned default_promote_level(struct smq_policy *mq) * This scheme reminds me of a graph of entropy vs probability of a * binary variable. */ - static unsigned table[] = {1, 1, 1, 2, 4, 6, 7, 8, 7, 6, 4, 4, 3, 3, 2, 2, 1}; + static const unsigned int table[] = { + 1, 1, 1, 2, 4, 6, 7, 8, 7, 6, 4, 4, 3, 3, 2, 2, 1 + }; unsigned hits = mq->cache_stats.hits; unsigned misses = mq->cache_stats.misses; diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index 447d030036d1..780a61bc6cc0 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -744,21 +744,14 @@ static void check_if_tick_bio_needed(struct cache *cache, struct bio *bio) spin_unlock_irq(&cache->lock); } -static void __remap_to_origin_clear_discard(struct cache *cache, struct bio *bio, - dm_oblock_t oblock, bool bio_has_pbd) -{ - if (bio_has_pbd) - check_if_tick_bio_needed(cache, bio); - remap_to_origin(cache, bio); - if (bio_data_dir(bio) == WRITE) - clear_discard(cache, oblock_to_dblock(cache, oblock)); -} - static void remap_to_origin_clear_discard(struct cache *cache, struct bio *bio, dm_oblock_t oblock) { // FIXME: check_if_tick_bio_needed() is called way too much through this interface - __remap_to_origin_clear_discard(cache, bio, oblock, true); + check_if_tick_bio_needed(cache, bio); + remap_to_origin(cache, bio); + if (bio_data_dir(bio) == WRITE) + clear_discard(cache, oblock_to_dblock(cache, oblock)); } static void remap_to_cache_dirty(struct cache *cache, struct bio *bio, @@ -810,7 +803,7 @@ static void accounted_complete(struct cache *cache, struct bio *bio) static void accounted_request(struct cache *cache, struct bio *bio) { accounted_begin(cache, bio); - submit_bio_noacct(bio); + dm_submit_bio_remap(bio, NULL); } static void issue_op(struct bio *bio, void *context) @@ -826,16 +819,15 @@ static void issue_op(struct bio *bio, void *context) static void remap_to_origin_and_cache(struct cache *cache, struct bio *bio, dm_oblock_t oblock, dm_cblock_t cblock) { - struct bio *origin_bio = bio_clone_fast(bio, GFP_NOIO, &cache->bs); + struct bio *origin_bio = bio_alloc_clone(cache->origin_dev->bdev, bio, + GFP_NOIO, &cache->bs); BUG_ON(!origin_bio); bio_chain(origin_bio, bio); - /* - * Passing false to __remap_to_origin_clear_discard() skips - * all code that might use per_bio_data (since clone doesn't have it) - */ - __remap_to_origin_clear_discard(cache, origin_bio, oblock, false); + + if (bio_data_dir(origin_bio) == WRITE) + clear_discard(cache, oblock_to_dblock(cache, oblock)); submit_bio(origin_bio); remap_to_cache(cache, bio, cblock); @@ -1716,7 +1708,7 @@ static bool process_bio(struct cache *cache, struct bio *bio) bool commit_needed; if (map_bio(cache, bio, get_bio_block(cache, bio), &commit_needed) == DM_MAPIO_REMAPPED) - submit_bio_noacct(bio); + dm_submit_bio_remap(bio, NULL); return commit_needed; } @@ -1782,7 +1774,7 @@ static bool process_discard_bio(struct cache *cache, struct bio *bio) if (cache->features.discard_passdown) { remap_to_origin(cache, bio); - submit_bio_noacct(bio); + dm_submit_bio_remap(bio, NULL); } else bio_endio(bio); @@ -2023,7 +2015,6 @@ static int parse_metadata_dev(struct cache_args *ca, struct dm_arg_set *as, { int r; sector_t metadata_dev_size; - char b[BDEVNAME_SIZE]; if (!at_least_one_arg(as, error)) return -EINVAL; @@ -2037,8 +2028,8 @@ static int parse_metadata_dev(struct cache_args *ca, struct dm_arg_set *as, metadata_dev_size = get_dev_size(ca->metadata_dev); if (metadata_dev_size > DM_CACHE_METADATA_MAX_SECTORS_WARNING) - DMWARN("Metadata device %s is larger than %u sectors: excess space will not be used.", - bdevname(ca->metadata_dev->bdev, b), THIN_METADATA_MAX_SECTORS); + DMWARN("Metadata device %pg is larger than %u sectors: excess space will not be used.", + ca->metadata_dev->bdev, THIN_METADATA_MAX_SECTORS); return 0; } @@ -2365,6 +2356,7 @@ static int cache_create(struct cache_args *ca, struct cache **result) cache->ti = ca->ti; ti->private = cache; + ti->accounts_remapped_io = true; ti->num_flush_bios = 2; ti->flush_supported = true; @@ -3353,7 +3345,6 @@ static void disable_passdown_if_not_supported(struct cache *cache) struct block_device *origin_bdev = cache->origin_dev->bdev; struct queue_limits *origin_limits = &bdev_get_queue(origin_bdev)->limits; const char *reason = NULL; - char buf[BDEVNAME_SIZE]; if (!cache->features.discard_passdown) return; @@ -3365,8 +3356,8 @@ static void disable_passdown_if_not_supported(struct cache *cache) reason = "max discard sectors smaller than a block"; if (reason) { - DMWARN("Origin device (%s) %s: Disabling discard passdown.", - bdevname(origin_bdev, buf), reason); + DMWARN("Origin device (%pg) %s: Disabling discard passdown.", + origin_bdev, reason); cache->features.discard_passdown = false; } } diff --git a/drivers/md/dm-clone-target.c b/drivers/md/dm-clone-target.c index 4599632d7a84..128316a73d01 100644 --- a/drivers/md/dm-clone-target.c +++ b/drivers/md/dm-clone-target.c @@ -1682,7 +1682,6 @@ static int parse_metadata_dev(struct clone *clone, struct dm_arg_set *as, char * { int r; sector_t metadata_dev_size; - char b[BDEVNAME_SIZE]; r = dm_get_device(clone->ti, dm_shift_arg(as), FMODE_READ | FMODE_WRITE, &clone->metadata_dev); @@ -1693,8 +1692,8 @@ static int parse_metadata_dev(struct clone *clone, struct dm_arg_set *as, char * metadata_dev_size = get_dev_size(clone->metadata_dev); if (metadata_dev_size > DM_CLONE_METADATA_MAX_SECTORS_WARNING) - DMWARN("Metadata device %s is larger than %u sectors: excess space will not be used.", - bdevname(clone->metadata_dev->bdev, b), DM_CLONE_METADATA_MAX_SECTORS); + DMWARN("Metadata device %pg is larger than %u sectors: excess space will not be used.", + clone->metadata_dev->bdev, DM_CLONE_METADATA_MAX_SECTORS); return 0; } @@ -2033,7 +2032,6 @@ static void disable_passdown_if_not_supported(struct clone *clone) struct block_device *dest_dev = clone->dest_dev->bdev; struct queue_limits *dest_limits = &bdev_get_queue(dest_dev)->limits; const char *reason = NULL; - char buf[BDEVNAME_SIZE]; if (!test_bit(DM_CLONE_DISCARD_PASSDOWN, &clone->flags)) return; @@ -2044,8 +2042,8 @@ static void disable_passdown_if_not_supported(struct clone *clone) reason = "max discard sectors smaller than a region"; if (reason) { - DMWARN("Destination device (%s) %s: Disabling discard passdown.", - bdevname(dest_dev, buf), reason); + DMWARN("Destination device (%pd) %s: Disabling discard passdown.", + dest_dev, reason); clear_bit(DM_CLONE_DISCARD_PASSDOWN, &clone->flags); } } diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h index b855fef4f38a..4081cb6cf7b3 100644 --- a/drivers/md/dm-core.h +++ b/drivers/md/dm-core.h @@ -11,7 +11,6 @@ #include <linux/kthread.h> #include <linux/ktime.h> -#include <linux/genhd.h> #include <linux/blk-mq.h> #include <linux/blk-crypto-profile.h> @@ -65,11 +64,21 @@ struct mapped_device { struct gendisk *disk; struct dax_device *dax_dev; + wait_queue_head_t wait; + unsigned long __percpu *pending_io; + + /* forced geometry settings */ + struct hd_geometry geometry; + + /* + * Processing queue (flush) + */ + struct workqueue_struct *wq; + /* * A list of ios that arrived while we were suspended. */ struct work_struct work; - wait_queue_head_t wait; spinlock_t deferred_lock; struct bio_list deferred; @@ -84,36 +93,28 @@ struct mapped_device { struct list_head uevent_list; spinlock_t uevent_lock; /* Protect access to uevent_list */ + /* for blk-mq request-based DM support */ + bool init_tio_pdu:1; + struct blk_mq_tag_set *tag_set; + + struct dm_stats stats; + /* the number of internal suspends */ unsigned internal_suspend_count; + int swap_bios; + struct semaphore swap_bios_semaphore; + struct mutex swap_bios_lock; + /* * io objects are allocated from here. */ struct bio_set io_bs; struct bio_set bs; - /* - * Processing queue (flush) - */ - struct workqueue_struct *wq; - - /* forced geometry settings */ - struct hd_geometry geometry; - /* kobject and completion */ struct dm_kobject_holder kobj_holder; - int swap_bios; - struct semaphore swap_bios_semaphore; - struct mutex swap_bios_lock; - - struct dm_stats stats; - - /* for blk-mq request-based DM support */ - struct blk_mq_tag_set *tag_set; - bool init_tio_pdu:1; - struct srcu_struct io_barrier; #ifdef CONFIG_BLK_DEV_ZONED @@ -141,7 +142,6 @@ struct mapped_device { #define DMF_EMULATE_ZONE_APPEND 9 void disable_discard(struct mapped_device *md); -void disable_write_same(struct mapped_device *md); void disable_write_zeroes(struct mapped_device *md); static inline sector_t dm_get_size(struct mapped_device *md) @@ -207,35 +207,76 @@ struct dm_table { /* * One of these is allocated per clone bio. */ -#define DM_TIO_MAGIC 7282014 +#define DM_TIO_MAGIC 28714 struct dm_target_io { - unsigned int magic; + unsigned short magic; + unsigned short flags; + unsigned int target_bio_nr; struct dm_io *io; struct dm_target *ti; - unsigned int target_bio_nr; unsigned int *len_ptr; - bool inside_dm_io; + sector_t old_sector; struct bio clone; }; /* + * dm_target_io flags + */ +enum { + DM_TIO_INSIDE_DM_IO, + DM_TIO_IS_DUPLICATE_BIO +}; + +static inline bool dm_tio_flagged(struct dm_target_io *tio, unsigned int bit) +{ + return (tio->flags & (1U << bit)) != 0; +} + +static inline void dm_tio_set_flag(struct dm_target_io *tio, unsigned int bit) +{ + tio->flags |= (1U << bit); +} + +/* * One of these is allocated per original bio. * It contains the first clone used for that original. */ -#define DM_IO_MAGIC 5191977 +#define DM_IO_MAGIC 19577 struct dm_io { - unsigned int magic; - struct mapped_device *md; - blk_status_t status; + unsigned short magic; + unsigned short flags; atomic_t io_count; + struct mapped_device *md; struct bio *orig_bio; + blk_status_t status; + spinlock_t lock; unsigned long start_time; - spinlock_t endio_lock; + void *data; + struct hlist_node node; + struct task_struct *map_task; struct dm_stats_aux stats_aux; /* last member of dm_target_io is 'struct bio' */ struct dm_target_io tio; }; +/* + * dm_io flags + */ +enum { + DM_IO_START_ACCT, + DM_IO_ACCOUNTED +}; + +static inline bool dm_io_flagged(struct dm_io *io, unsigned int bit) +{ + return (io->flags & (1U << bit)) != 0; +} + +static inline void dm_io_set_flag(struct dm_io *io, unsigned int bit) +{ + io->flags |= (1U << bit); +} + static inline void dm_io_inc_pending(struct dm_io *io) { atomic_inc(&io->io_count); diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index d4ae31558826..fb80539865d7 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -234,7 +234,7 @@ static volatile unsigned long dm_crypt_pages_per_client; #define DM_CRYPT_MEMORY_PERCENT 2 #define DM_CRYPT_MIN_PAGES_PER_CLIENT (BIO_MAX_VECS * 16) -static void clone_init(struct dm_crypt_io *, struct bio *); +static void crypt_endio(struct bio *clone); static void kcryptd_queue_crypt(struct dm_crypt_io *io); static struct scatterlist *crypt_get_sg_data(struct crypt_config *cc, struct scatterlist *sg); @@ -1364,11 +1364,10 @@ static int crypt_convert_block_aead(struct crypt_config *cc, } if (r == -EBADMSG) { - char b[BDEVNAME_SIZE]; sector_t s = le64_to_cpu(*sector); - DMERR_LIMIT("%s: INTEGRITY AEAD ERROR, sector %llu", - bio_devname(ctx->bio_in, b), s); + DMERR_LIMIT("%pg: INTEGRITY AEAD ERROR, sector %llu", + ctx->bio_in->bi_bdev, s); dm_audit_log_bio(DM_MSG_PREFIX, "integrity-aead", ctx->bio_in, s, 0); } @@ -1672,11 +1671,10 @@ retry: if (unlikely(gfp_mask & __GFP_DIRECT_RECLAIM)) mutex_lock(&cc->bio_alloc_lock); - clone = bio_alloc_bioset(GFP_NOIO, nr_iovecs, &cc->bs); - if (!clone) - goto out; - - clone_init(io, clone); + clone = bio_alloc_bioset(cc->dev->bdev, nr_iovecs, io->base_bio->bi_opf, + GFP_NOIO, &cc->bs); + clone->bi_private = io; + clone->bi_end_io = crypt_endio; remaining_size = size; @@ -1702,7 +1700,7 @@ retry: bio_put(clone); clone = NULL; } -out: + if (unlikely(gfp_mask & __GFP_DIRECT_RECLAIM)) mutex_unlock(&cc->bio_alloc_lock); @@ -1829,15 +1827,7 @@ static void crypt_endio(struct bio *clone) crypt_dec_pending(io); } -static void clone_init(struct dm_crypt_io *io, struct bio *clone) -{ - struct crypt_config *cc = io->cc; - - clone->bi_private = io; - clone->bi_end_io = crypt_endio; - bio_set_dev(clone, cc->dev->bdev); - clone->bi_opf = io->base_bio->bi_opf; -} +#define CRYPT_MAP_READ_GFP GFP_NOWAIT static int kcryptd_io_read(struct dm_crypt_io *io, gfp_t gfp) { @@ -1845,18 +1835,19 @@ static int kcryptd_io_read(struct dm_crypt_io *io, gfp_t gfp) struct bio *clone; /* - * We need the original biovec array in order to decrypt - * the whole bio data *afterwards* -- thanks to immutable - * biovecs we don't need to worry about the block layer - * modifying the biovec array; so leverage bio_clone_fast(). + * We need the original biovec array in order to decrypt the whole bio + * data *afterwards* -- thanks to immutable biovecs we don't need to + * worry about the block layer modifying the biovec array; so leverage + * bio_alloc_clone(). */ - clone = bio_clone_fast(io->base_bio, gfp, &cc->bs); + clone = bio_alloc_clone(cc->dev->bdev, io->base_bio, gfp, &cc->bs); if (!clone) return 1; + clone->bi_private = io; + clone->bi_end_io = crypt_endio; crypt_inc_pending(io); - clone_init(io, clone); clone->bi_iter.bi_sector = cc->start + io->sector; if (dm_crypt_integrity_io_alloc(io, clone)) { @@ -1865,7 +1856,7 @@ static int kcryptd_io_read(struct dm_crypt_io *io, gfp_t gfp) return 1; } - submit_bio_noacct(clone); + dm_submit_bio_remap(io->base_bio, clone); return 0; } @@ -1891,7 +1882,7 @@ static void kcryptd_io_write(struct dm_crypt_io *io) { struct bio *clone = io->ctx.bio_out; - submit_bio_noacct(clone); + dm_submit_bio_remap(io->base_bio, clone); } #define crypt_io_from_node(node) rb_entry((node), struct dm_crypt_io, rb_node) @@ -1970,7 +1961,7 @@ static void kcryptd_crypt_write_io_submit(struct dm_crypt_io *io, int async) if ((likely(!async) && test_bit(DM_CRYPT_NO_OFFLOAD, &cc->flags)) || test_bit(DM_CRYPT_NO_WRITE_WORKQUEUE, &cc->flags)) { - submit_bio_noacct(clone); + dm_submit_bio_remap(io->base_bio, clone); return; } @@ -2006,7 +1997,6 @@ static bool kcryptd_crypt_write_inline(struct crypt_config *cc, */ switch (bio_op(ctx->bio_in)) { case REQ_OP_WRITE: - case REQ_OP_WRITE_SAME: case REQ_OP_WRITE_ZEROES: return true; default: @@ -2179,11 +2169,10 @@ static void kcryptd_async_done(struct crypto_async_request *async_req, error = cc->iv_gen_ops->post(cc, org_iv_of_dmreq(cc, dmreq), dmreq); if (error == -EBADMSG) { - char b[BDEVNAME_SIZE]; sector_t s = le64_to_cpu(*org_sector_of_dmreq(cc, dmreq)); - DMERR_LIMIT("%s: INTEGRITY AEAD ERROR, sector %llu", - bio_devname(ctx->bio_in, b), s); + DMERR_LIMIT("%pg: INTEGRITY AEAD ERROR, sector %llu", + ctx->bio_in->bi_bdev, s); dm_audit_log_bio(DM_MSG_PREFIX, "integrity-aead", ctx->bio_in, s, 0); io->error = BLK_STS_PROTECTION; @@ -2590,7 +2579,7 @@ static int crypt_set_keyring_key(struct crypt_config *cc, const char *key_string static int get_key_size(char **key_string) { - return (*key_string[0] == ':') ? -EINVAL : strlen(*key_string) >> 1; + return (*key_string[0] == ':') ? -EINVAL : (int)(strlen(*key_string) >> 1); } #endif /* CONFIG_KEYS */ @@ -3373,6 +3362,7 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv) ti->num_flush_bios = 1; ti->limit_swap_bios = true; + ti->accounts_remapped_io = true; dm_audit_log_ctr(DM_MSG_PREFIX, ti, 1); return 0; @@ -3441,7 +3431,7 @@ static int crypt_map(struct dm_target *ti, struct bio *bio) io->ctx.r.req = (struct skcipher_request *)(io + 1); if (bio_data_dir(io->base_bio) == READ) { - if (kcryptd_io_read(io, GFP_NOWAIT)) + if (kcryptd_io_read(io, CRYPT_MAP_READ_GFP)) kcryptd_queue_read(io); } else kcryptd_queue_crypt(io); @@ -3636,7 +3626,7 @@ static void crypt_io_hints(struct dm_target *ti, struct queue_limits *limits) static struct target_type crypt_target = { .name = "crypt", - .version = {1, 23, 0}, + .version = {1, 24, 0}, .module = THIS_MODULE, .ctr = crypt_ctr, .dtr = crypt_dtr, diff --git a/drivers/md/dm-delay.c b/drivers/md/dm-delay.c index 59e51d285b0e..9a51bf51a859 100644 --- a/drivers/md/dm-delay.c +++ b/drivers/md/dm-delay.c @@ -72,7 +72,7 @@ static void flush_bios(struct bio *bio) while (bio) { n = bio->bi_next; bio->bi_next = NULL; - submit_bio_noacct(bio); + dm_submit_bio_remap(bio, NULL); bio = n; } } @@ -232,6 +232,7 @@ out: ti->num_flush_bios = 1; ti->num_discard_bios = 1; + ti->accounts_remapped_io = true; ti->per_io_data_size = sizeof(struct dm_delay_info); return 0; @@ -355,7 +356,7 @@ out: static struct target_type delay_target = { .name = "delay", - .version = {1, 2, 1}, + .version = {1, 3, 0}, .features = DM_TARGET_PASSES_INTEGRITY, .module = THIS_MODULE, .ctr = delay_ctr, diff --git a/drivers/md/dm-ebs-target.c b/drivers/md/dm-ebs-target.c index 7ce5d509b940..0221fa63f888 100644 --- a/drivers/md/dm-ebs-target.c +++ b/drivers/md/dm-ebs-target.c @@ -335,7 +335,6 @@ static int ebs_ctr(struct dm_target *ti, unsigned int argc, char **argv) ti->num_flush_bios = 1; ti->num_discard_bios = 1; ti->num_secure_erase_bios = 0; - ti->num_write_same_bios = 0; ti->num_write_zeroes_bios = 0; return 0; bad: diff --git a/drivers/md/dm-ima.c b/drivers/md/dm-ima.c index 957999998d70..1842d3a958ef 100644 --- a/drivers/md/dm-ima.c +++ b/drivers/md/dm-ima.c @@ -455,7 +455,7 @@ void dm_ima_measure_on_device_resume(struct mapped_device *md, bool swap) scnprintf(device_table_data, DM_IMA_DEVICE_BUF_LEN, "%sname=%s,uuid=%s;device_resume=no_data;", DM_IMA_VERSION_STR, dev_name, dev_uuid); - l += strlen(device_table_data); + l = strlen(device_table_data); } @@ -568,7 +568,7 @@ void dm_ima_measure_on_device_remove(struct mapped_device *md, bool remove_all) scnprintf(device_table_data, DM_IMA_DEVICE_BUF_LEN, "%sname=%s,uuid=%s;device_remove=no_data;", DM_IMA_VERSION_STR, dev_name, dev_uuid); - l += strlen(device_table_data); + l = strlen(device_table_data); } memcpy(device_table_data + l, remove_all_str, remove_all_len); @@ -654,7 +654,7 @@ void dm_ima_measure_on_table_clear(struct mapped_device *md, bool new_map) scnprintf(device_table_data, DM_IMA_DEVICE_BUF_LEN, "%sname=%s,uuid=%s;table_clear=no_data;", DM_IMA_VERSION_STR, dev_name, dev_uuid); - l += strlen(device_table_data); + l = strlen(device_table_data); } capacity_len = strlen(capacity_str); diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index eb4b5e52bd6f..c58a5111cb57 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -1788,12 +1788,11 @@ again: checksums_ptr - checksums, dio->op == REQ_OP_READ ? TAG_CMP : TAG_WRITE); if (unlikely(r)) { if (r > 0) { - char b[BDEVNAME_SIZE]; sector_t s; s = sector - ((r + ic->tag_size - 1) / ic->tag_size); - DMERR_LIMIT("%s: Checksum failed at sector 0x%llx", - bio_devname(bio, b), s); + DMERR_LIMIT("%pg: Checksum failed at sector 0x%llx", + bio->bi_bdev, s); r = -EILSEQ; atomic64_inc(&ic->number_of_mismatches); dm_audit_log_bio(DM_MSG_PREFIX, "integrity-checksum", diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c index 2d3cda0acacb..5762366333a2 100644 --- a/drivers/md/dm-io.c +++ b/drivers/md/dm-io.c @@ -304,7 +304,6 @@ static void do_region(int op, int op_flags, unsigned region, unsigned num_bvecs; sector_t remaining = where->count; struct request_queue *q = bdev_get_queue(where->bdev); - unsigned short logical_block_size = queue_logical_block_size(q); sector_t num_sectors; unsigned int special_cmd_max_sectors; @@ -315,10 +314,8 @@ static void do_region(int op, int op_flags, unsigned region, special_cmd_max_sectors = q->limits.max_discard_sectors; else if (op == REQ_OP_WRITE_ZEROES) special_cmd_max_sectors = q->limits.max_write_zeroes_sectors; - else if (op == REQ_OP_WRITE_SAME) - special_cmd_max_sectors = q->limits.max_write_same_sectors; - if ((op == REQ_OP_DISCARD || op == REQ_OP_WRITE_ZEROES || - op == REQ_OP_WRITE_SAME) && special_cmd_max_sectors == 0) { + if ((op == REQ_OP_DISCARD || op == REQ_OP_WRITE_ZEROES) && + special_cmd_max_sectors == 0) { atomic_inc(&io->count); dec_count(io, region, BLK_STS_NOTSUPP); return; @@ -337,37 +334,21 @@ static void do_region(int op, int op_flags, unsigned region, case REQ_OP_WRITE_ZEROES: num_bvecs = 0; break; - case REQ_OP_WRITE_SAME: - num_bvecs = 1; - break; default: num_bvecs = bio_max_segs(dm_sector_div_up(remaining, (PAGE_SIZE >> SECTOR_SHIFT))); } - bio = bio_alloc_bioset(GFP_NOIO, num_bvecs, &io->client->bios); + bio = bio_alloc_bioset(where->bdev, num_bvecs, op | op_flags, + GFP_NOIO, &io->client->bios); bio->bi_iter.bi_sector = where->sector + (where->count - remaining); - bio_set_dev(bio, where->bdev); bio->bi_end_io = endio; - bio_set_op_attrs(bio, op, op_flags); store_io_and_region_in_bio(bio, io, region); if (op == REQ_OP_DISCARD || op == REQ_OP_WRITE_ZEROES) { num_sectors = min_t(sector_t, special_cmd_max_sectors, remaining); bio->bi_iter.bi_size = num_sectors << SECTOR_SHIFT; remaining -= num_sectors; - } else if (op == REQ_OP_WRITE_SAME) { - /* - * WRITE SAME only uses a single page. - */ - dp->get_page(dp, &page, &len, &offset); - bio_add_page(bio, page, logical_block_size, offset); - num_sectors = min_t(sector_t, special_cmd_max_sectors, remaining); - bio->bi_iter.bi_size = num_sectors << SECTOR_SHIFT; - - offset = 0; - remaining -= num_sectors; - dp->next_page(dp); } else while (remaining) { /* * Try and add as many pages as possible. @@ -526,14 +507,6 @@ static int dp_init(struct dm_io_request *io_req, struct dpages *dp, return 0; } -/* - * New collapsed (a)synchronous interface. - * - * If the IO is asynchronous (i.e. it has notify.fn), you must either unplug - * the queue with blk_unplug() some time later or set REQ_SYNC in - * io_req->bi_opf. If you fail to do one of these, the IO will be submitted to - * the disk after q->unplug_delay, which defaults to 3ms in blk-settings.c. - */ int dm_io(struct dm_io_request *io_req, unsigned num_regions, struct dm_io_region *where, unsigned long *sync_error_bits) { diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c index 21fe8652b095..901abd6dea41 100644 --- a/drivers/md/dm-ioctl.c +++ b/drivers/md/dm-ioctl.c @@ -18,6 +18,7 @@ #include <linux/dm-ioctl.h> #include <linux/hdreg.h> #include <linux/compat.h> +#include <linux/nospec.h> #include <linux/uaccess.h> #include <linux/ima.h> @@ -1788,6 +1789,7 @@ static ioctl_fn lookup_ioctl(unsigned int cmd, int *ioctl_flags) if (unlikely(cmd >= ARRAY_SIZE(_ioctls))) return NULL; + cmd = array_index_nospec(cmd, ARRAY_SIZE(_ioctls)); *ioctl_flags = _ioctls[cmd].flags; return _ioctls[cmd].fn; } diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c index 1b97a11d7151..76b486e4d2be 100644 --- a/drivers/md/dm-linear.c +++ b/drivers/md/dm-linear.c @@ -60,7 +60,6 @@ static int linear_ctr(struct dm_target *ti, unsigned int argc, char **argv) ti->num_flush_bios = 1; ti->num_discard_bios = 1; ti->num_secure_erase_bios = 1; - ti->num_write_same_bios = 1; ti->num_write_zeroes_bios = 1; ti->private = lc; return 0; diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c index 139b09b06eda..c9d036d6bb2e 100644 --- a/drivers/md/dm-log-writes.c +++ b/drivers/md/dm-log-writes.c @@ -217,18 +217,12 @@ static int write_metadata(struct log_writes_c *lc, void *entry, void *ptr; size_t ret; - bio = bio_alloc(GFP_KERNEL, 1); - if (!bio) { - DMERR("Couldn't alloc log bio"); - goto error; - } + bio = bio_alloc(lc->logdev->bdev, 1, REQ_OP_WRITE, GFP_KERNEL); bio->bi_iter.bi_size = 0; bio->bi_iter.bi_sector = sector; - bio_set_dev(bio, lc->logdev->bdev); bio->bi_end_io = (sector == WRITE_LOG_SUPER_SECTOR) ? log_end_super : log_end_io; bio->bi_private = lc; - bio_set_op_attrs(bio, REQ_OP_WRITE, 0); page = alloc_page(GFP_KERNEL); if (!page) { @@ -275,18 +269,12 @@ static int write_inline_data(struct log_writes_c *lc, void *entry, atomic_inc(&lc->io_blocks); - bio = bio_alloc(GFP_KERNEL, bio_pages); - if (!bio) { - DMERR("Couldn't alloc inline data bio"); - goto error; - } - + bio = bio_alloc(lc->logdev->bdev, bio_pages, REQ_OP_WRITE, + GFP_KERNEL); bio->bi_iter.bi_size = 0; bio->bi_iter.bi_sector = sector; - bio_set_dev(bio, lc->logdev->bdev); bio->bi_end_io = log_end_io; bio->bi_private = lc; - bio_set_op_attrs(bio, REQ_OP_WRITE, 0); for (i = 0; i < bio_pages; i++) { pg_datalen = min_t(int, datalen, PAGE_SIZE); @@ -322,7 +310,6 @@ static int write_inline_data(struct log_writes_c *lc, void *entry, error_bio: bio_free_pages(bio); bio_put(bio); -error: put_io_block(lc); return -1; } @@ -363,17 +350,12 @@ static int log_one_block(struct log_writes_c *lc, goto out; atomic_inc(&lc->io_blocks); - bio = bio_alloc(GFP_KERNEL, bio_max_segs(block->vec_cnt)); - if (!bio) { - DMERR("Couldn't alloc log bio"); - goto error; - } + bio = bio_alloc(lc->logdev->bdev, bio_max_segs(block->vec_cnt), + REQ_OP_WRITE, GFP_KERNEL); bio->bi_iter.bi_size = 0; bio->bi_iter.bi_sector = sector; - bio_set_dev(bio, lc->logdev->bdev); bio->bi_end_io = log_end_io; bio->bi_private = lc; - bio_set_op_attrs(bio, REQ_OP_WRITE, 0); for (i = 0; i < block->vec_cnt; i++) { /* @@ -385,18 +367,13 @@ static int log_one_block(struct log_writes_c *lc, if (ret != block->vecs[i].bv_len) { atomic_inc(&lc->io_blocks); submit_bio(bio); - bio = bio_alloc(GFP_KERNEL, - bio_max_segs(block->vec_cnt - i)); - if (!bio) { - DMERR("Couldn't alloc log bio"); - goto error; - } + bio = bio_alloc(lc->logdev->bdev, + bio_max_segs(block->vec_cnt - i), + REQ_OP_WRITE, GFP_KERNEL); bio->bi_iter.bi_size = 0; bio->bi_iter.bi_sector = sector; - bio_set_dev(bio, lc->logdev->bdev); bio->bi_end_io = log_end_io; bio->bi_private = lc; - bio_set_op_attrs(bio, REQ_OP_WRITE, 0); ret = bio_add_page(bio, block->vecs[i].bv_page, block->vecs[i].bv_len, 0); diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index f4719b65e5e3..6ed9d2731254 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -899,10 +899,7 @@ retain: if (m->hw_handler_name) { r = scsi_dh_attach(q, m->hw_handler_name); if (r == -EBUSY) { - char b[BDEVNAME_SIZE]; - - printk(KERN_INFO "dm-mpath: retaining handler on device %s\n", - bdevname(bdev, b)); + DMINFO("retaining handler on device %pg", bdev); goto retain; } if (r < 0) { @@ -1252,7 +1249,6 @@ static int multipath_ctr(struct dm_target *ti, unsigned argc, char **argv) ti->num_flush_bios = 1; ti->num_discard_bios = 1; - ti->num_write_same_bios = 1; ti->num_write_zeroes_bios = 1; if (m->queue_mode == DM_TYPE_BIO_BASED) ti->per_io_data_size = multipath_per_bio_data_size(); diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c index 579ab6183d4d..6087cdcaad46 100644 --- a/drivers/md/dm-rq.c +++ b/drivers/md/dm-rq.c @@ -217,9 +217,6 @@ static void dm_done(struct request *clone, blk_status_t error, bool mapped) if (req_op(clone) == REQ_OP_DISCARD && !clone->q->limits.max_discard_sectors) disable_discard(tio->md); - else if (req_op(clone) == REQ_OP_WRITE_SAME && - !clone->q->limits.max_write_same_sectors) - disable_write_same(tio->md); else if (req_op(clone) == REQ_OP_WRITE_ZEROES && !clone->q->limits.max_write_zeroes_sectors) disable_write_zeroes(tio->md); @@ -303,21 +300,6 @@ static void end_clone_request(struct request *clone, blk_status_t error) dm_complete_request(tio->orig, error); } -static blk_status_t dm_dispatch_clone_request(struct request *clone, struct request *rq) -{ - blk_status_t r; - - if (blk_queue_io_stat(clone->q)) - clone->rq_flags |= RQF_IO_STAT; - - clone->start_time_ns = ktime_get_ns(); - r = blk_insert_cloned_request(clone->q, clone); - if (r != BLK_STS_OK && r != BLK_STS_RESOURCE && r != BLK_STS_DEV_RESOURCE) - /* must complete clone in terms of original request */ - dm_complete_request(rq, r); - return r; -} - static int dm_rq_bio_constructor(struct bio *bio, struct bio *bio_orig, void *data) { @@ -398,13 +380,20 @@ static int map_request(struct dm_rq_target_io *tio) /* The target has remapped the I/O so dispatch it */ trace_block_rq_remap(clone, disk_devt(dm_disk(md)), blk_rq_pos(rq)); - ret = dm_dispatch_clone_request(clone, rq); - if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE) { + ret = blk_insert_cloned_request(clone); + switch (ret) { + case BLK_STS_OK: + break; + case BLK_STS_RESOURCE: + case BLK_STS_DEV_RESOURCE: blk_rq_unprep_clone(clone); blk_mq_cleanup_rq(clone); tio->ti->type->release_clone_rq(clone, &tio->info); tio->clone = NULL; return DM_MAPIO_REQUEUE; + default: + /* must complete clone in terms of original request */ + dm_complete_request(rq, ret); } break; case DM_MAPIO_REQUEUE: @@ -499,8 +488,13 @@ static blk_status_t dm_mq_queue_rq(struct blk_mq_hw_ctx *hctx, if (unlikely(!ti)) { int srcu_idx; - struct dm_table *map = dm_get_live_table(md, &srcu_idx); + struct dm_table *map; + map = dm_get_live_table(md, &srcu_idx); + if (unlikely(!map)) { + dm_put_live_table(md, srcu_idx); + return BLK_STS_RESOURCE; + } ti = dm_table_find_target(map, 0); dm_put_live_table(md, srcu_idx); } diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c index dcf34c6b05ad..0d336b5ec571 100644 --- a/drivers/md/dm-snap.c +++ b/drivers/md/dm-snap.c @@ -141,11 +141,6 @@ struct dm_snapshot { * for them to be committed. */ struct bio_list bios_queued_during_merge; - - /* - * Flush data after merge. - */ - struct bio flush_bio; }; /* @@ -1127,17 +1122,6 @@ shut: static void error_bios(struct bio *bio); -static int flush_data(struct dm_snapshot *s) -{ - struct bio *flush_bio = &s->flush_bio; - - bio_reset(flush_bio); - bio_set_dev(flush_bio, s->origin->bdev); - flush_bio->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH; - - return submit_bio_wait(flush_bio); -} - static void merge_callback(int read_err, unsigned long write_err, void *context) { struct dm_snapshot *s = context; @@ -1151,7 +1135,7 @@ static void merge_callback(int read_err, unsigned long write_err, void *context) goto shut; } - if (flush_data(s) < 0) { + if (blkdev_issue_flush(s->origin->bdev) < 0) { DMERR("Flush after merge failed: shutting down merge"); goto shut; } @@ -1340,7 +1324,6 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv) s->first_merging_chunk = 0; s->num_merging_chunks = 0; bio_list_init(&s->bios_queued_during_merge); - bio_init(&s->flush_bio, NULL, 0); /* Allocate hash table for COW data */ if (init_hash_tables(s)) { @@ -1528,8 +1511,6 @@ static void snapshot_dtr(struct dm_target *ti) dm_exception_store_destroy(s->store); - bio_uninit(&s->flush_bio); - dm_put_device(ti, s->cow); dm_put_device(ti, s->origin); diff --git a/drivers/md/dm-stats.c b/drivers/md/dm-stats.c index 35d368c418d0..0e039a8c0bf2 100644 --- a/drivers/md/dm-stats.c +++ b/drivers/md/dm-stats.c @@ -195,6 +195,7 @@ void dm_stats_init(struct dm_stats *stats) mutex_init(&stats->mutex); INIT_LIST_HEAD(&stats->list); + stats->precise_timestamps = false; stats->last = alloc_percpu(struct dm_stats_last_position); for_each_possible_cpu(cpu) { last = per_cpu_ptr(stats->last, cpu); @@ -231,6 +232,22 @@ void dm_stats_cleanup(struct dm_stats *stats) mutex_destroy(&stats->mutex); } +static void dm_stats_recalc_precise_timestamps(struct dm_stats *stats) +{ + struct list_head *l; + struct dm_stat *tmp_s; + bool precise_timestamps = false; + + list_for_each(l, &stats->list) { + tmp_s = container_of(l, struct dm_stat, list_entry); + if (tmp_s->stat_flags & STAT_PRECISE_TIMESTAMPS) { + precise_timestamps = true; + break; + } + } + stats->precise_timestamps = precise_timestamps; +} + static int dm_stats_create(struct dm_stats *stats, sector_t start, sector_t end, sector_t step, unsigned stat_flags, unsigned n_histogram_entries, @@ -376,6 +393,9 @@ static int dm_stats_create(struct dm_stats *stats, sector_t start, sector_t end, } ret_id = s->id; list_add_tail_rcu(&s->list_entry, l); + + dm_stats_recalc_precise_timestamps(stats); + mutex_unlock(&stats->mutex); resume_callback(md); @@ -418,6 +438,9 @@ static int dm_stats_delete(struct dm_stats *stats, int id) } list_del_rcu(&s->list_entry); + + dm_stats_recalc_precise_timestamps(stats); + mutex_unlock(&stats->mutex); /* @@ -621,13 +644,14 @@ static void __dm_stat_bio(struct dm_stat *s, int bi_rw, void dm_stats_account_io(struct dm_stats *stats, unsigned long bi_rw, sector_t bi_sector, unsigned bi_sectors, bool end, - unsigned long duration_jiffies, + unsigned long start_time, struct dm_stats_aux *stats_aux) { struct dm_stat *s; sector_t end_sector; struct dm_stats_last_position *last; bool got_precise_time; + unsigned long duration_jiffies = 0; if (unlikely(!bi_sectors)) return; @@ -647,16 +671,16 @@ void dm_stats_account_io(struct dm_stats *stats, unsigned long bi_rw, )); WRITE_ONCE(last->last_sector, end_sector); WRITE_ONCE(last->last_rw, bi_rw); - } + } else + duration_jiffies = jiffies - start_time; rcu_read_lock(); got_precise_time = false; list_for_each_entry_rcu(s, &stats->list, list_entry) { if (s->stat_flags & STAT_PRECISE_TIMESTAMPS && !got_precise_time) { - if (!end) - stats_aux->duration_ns = ktime_to_ns(ktime_get()); - else + /* start (!end) duration_ns is set by DM core's alloc_io() */ + if (end) stats_aux->duration_ns = ktime_to_ns(ktime_get()) - stats_aux->duration_ns; got_precise_time = true; } diff --git a/drivers/md/dm-stats.h b/drivers/md/dm-stats.h index 2ddfae678f32..09c81a1ec057 100644 --- a/drivers/md/dm-stats.h +++ b/drivers/md/dm-stats.h @@ -13,8 +13,7 @@ struct dm_stats { struct mutex mutex; struct list_head list; /* list of struct dm_stat */ struct dm_stats_last_position __percpu *last; - sector_t last_sector; - unsigned last_rw; + bool precise_timestamps; }; struct dm_stats_aux { @@ -32,7 +31,7 @@ int dm_stats_message(struct mapped_device *md, unsigned argc, char **argv, void dm_stats_account_io(struct dm_stats *stats, unsigned long bi_rw, sector_t bi_sector, unsigned bi_sectors, bool end, - unsigned long duration_jiffies, + unsigned long start_time, struct dm_stats_aux *aux); static inline bool dm_stats_used(struct dm_stats *st) @@ -40,4 +39,10 @@ static inline bool dm_stats_used(struct dm_stats *st) return !list_empty(&st->list); } +static inline void dm_stats_record_start(struct dm_stats *stats, struct dm_stats_aux *aux) +{ + if (unlikely(stats->precise_timestamps)) + aux->duration_ns = ktime_to_ns(ktime_get()); +} + #endif diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c index e566115ec0bb..c81d331d1afe 100644 --- a/drivers/md/dm-stripe.c +++ b/drivers/md/dm-stripe.c @@ -157,7 +157,6 @@ static int stripe_ctr(struct dm_target *ti, unsigned int argc, char **argv) ti->num_flush_bios = stripes; ti->num_discard_bios = stripes; ti->num_secure_erase_bios = stripes; - ti->num_write_same_bios = stripes; ti->num_write_zeroes_bios = stripes; sc->chunk_size = chunk_size; @@ -284,8 +283,7 @@ static int stripe_map(struct dm_target *ti, struct bio *bio) } if (unlikely(bio_op(bio) == REQ_OP_DISCARD) || unlikely(bio_op(bio) == REQ_OP_SECURE_ERASE) || - unlikely(bio_op(bio) == REQ_OP_WRITE_ZEROES) || - unlikely(bio_op(bio) == REQ_OP_WRITE_SAME)) { + unlikely(bio_op(bio) == REQ_OP_WRITE_ZEROES)) { target_bio_nr = dm_bio_get_target_bio_nr(bio); BUG_ON(target_bio_nr >= sc->stripes); return stripe_map_range(sc, bio, target_bio_nr); diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index e43096cfe9e2..03541cfc2317 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -230,15 +230,14 @@ static int device_area_is_invalid(struct dm_target *ti, struct dm_dev *dev, sector_t dev_size = bdev_nr_sectors(bdev); unsigned short logical_block_size_sectors = limits->logical_block_size >> SECTOR_SHIFT; - char b[BDEVNAME_SIZE]; if (!dev_size) return 0; if ((start >= dev_size) || (start + len > dev_size)) { - DMWARN("%s: %s too small for target: " + DMWARN("%s: %pg too small for target: " "start=%llu, len=%llu, dev_size=%llu", - dm_device_name(ti->table->md), bdevname(bdev, b), + dm_device_name(ti->table->md), bdev, (unsigned long long)start, (unsigned long long)len, (unsigned long long)dev_size); @@ -253,10 +252,10 @@ static int device_area_is_invalid(struct dm_target *ti, struct dm_dev *dev, unsigned int zone_sectors = bdev_zone_sectors(bdev); if (start & (zone_sectors - 1)) { - DMWARN("%s: start=%llu not aligned to h/w zone size %u of %s", + DMWARN("%s: start=%llu not aligned to h/w zone size %u of %pg", dm_device_name(ti->table->md), (unsigned long long)start, - zone_sectors, bdevname(bdev, b)); + zone_sectors, bdev); return 1; } @@ -270,10 +269,10 @@ static int device_area_is_invalid(struct dm_target *ti, struct dm_dev *dev, * the sector range. */ if (len & (zone_sectors - 1)) { - DMWARN("%s: len=%llu not aligned to h/w zone size %u of %s", + DMWARN("%s: len=%llu not aligned to h/w zone size %u of %pg", dm_device_name(ti->table->md), (unsigned long long)len, - zone_sectors, bdevname(bdev, b)); + zone_sectors, bdev); return 1; } } @@ -283,19 +282,19 @@ static int device_area_is_invalid(struct dm_target *ti, struct dm_dev *dev, if (start & (logical_block_size_sectors - 1)) { DMWARN("%s: start=%llu not aligned to h/w " - "logical block size %u of %s", + "logical block size %u of %pg", dm_device_name(ti->table->md), (unsigned long long)start, - limits->logical_block_size, bdevname(bdev, b)); + limits->logical_block_size, bdev); return 1; } if (len & (logical_block_size_sectors - 1)) { DMWARN("%s: len=%llu not aligned to h/w " - "logical block size %u of %s", + "logical block size %u of %pg", dm_device_name(ti->table->md), (unsigned long long)len, - limits->logical_block_size, bdevname(bdev, b)); + limits->logical_block_size, bdev); return 1; } @@ -400,20 +399,19 @@ static int dm_set_device_limits(struct dm_target *ti, struct dm_dev *dev, struct queue_limits *limits = data; struct block_device *bdev = dev->bdev; struct request_queue *q = bdev_get_queue(bdev); - char b[BDEVNAME_SIZE]; if (unlikely(!q)) { - DMWARN("%s: Cannot set limits for nonexistent device %s", - dm_device_name(ti->table->md), bdevname(bdev, b)); + DMWARN("%s: Cannot set limits for nonexistent device %pg", + dm_device_name(ti->table->md), bdev); return 0; } if (blk_stack_limits(limits, &q->limits, get_start_sect(bdev) + start) < 0) - DMWARN("%s: adding target device %s caused an alignment inconsistency: " + DMWARN("%s: adding target device %pg caused an alignment inconsistency: " "physical_block_size=%u, logical_block_size=%u, " "alignment_offset=%u, start=%llu", - dm_device_name(ti->table->md), bdevname(bdev, b), + dm_device_name(ti->table->md), bdev, q->limits.physical_block_size, q->limits.logical_block_size, q->limits.alignment_offset, @@ -1483,6 +1481,14 @@ struct dm_target *dm_table_find_target(struct dm_table *t, sector_t sector) return &t->targets[(KEYS_PER_NODE * n) + k]; } +static int device_not_poll_capable(struct dm_target *ti, struct dm_dev *dev, + sector_t start, sector_t len, void *data) +{ + struct request_queue *q = bdev_get_queue(dev->bdev); + + return !test_bit(QUEUE_FLAG_POLL, &q->queue_flags); +} + /* * type->iterate_devices() should be called when the sanity check needs to * iterate and check all underlying data devices. iterate_devices() will @@ -1533,6 +1539,11 @@ static int count_device(struct dm_target *ti, struct dm_dev *dev, return 0; } +static int dm_table_supports_poll(struct dm_table *t) +{ + return !dm_table_any_dev_attr(t, device_not_poll_capable, NULL); +} + /* * Check whether a table has no data devices attached using each * target's iterate_devices method. @@ -1822,33 +1833,6 @@ static int device_is_not_random(struct dm_target *ti, struct dm_dev *dev, return !blk_queue_add_random(q); } -static int device_not_write_same_capable(struct dm_target *ti, struct dm_dev *dev, - sector_t start, sector_t len, void *data) -{ - struct request_queue *q = bdev_get_queue(dev->bdev); - - return !q->limits.max_write_same_sectors; -} - -static bool dm_table_supports_write_same(struct dm_table *t) -{ - struct dm_target *ti; - unsigned i; - - for (i = 0; i < dm_table_get_num_targets(t); i++) { - ti = dm_table_get_target(t, i); - - if (!ti->num_write_same_bios) - return false; - - if (!ti->type->iterate_devices || - ti->type->iterate_devices(ti, device_not_write_same_capable, NULL)) - return false; - } - - return true; -} - static int device_not_write_zeroes_capable(struct dm_target *ti, struct dm_dev *dev, sector_t start, sector_t len, void *data) { @@ -2027,8 +2011,6 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, else blk_queue_flag_set(QUEUE_FLAG_NONROT, q); - if (!dm_table_supports_write_same(t)) - q->limits.max_write_same_sectors = 0; if (!dm_table_supports_write_zeroes(t)) q->limits.max_write_zeroes_sectors = 0; @@ -2069,6 +2051,20 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, dm_update_crypto_profile(q, t); disk_update_readahead(t->md->disk); + /* + * Check for request-based device is left to + * dm_mq_init_request_queue()->blk_mq_init_allocated_queue(). + * + * For bio-based device, only set QUEUE_FLAG_POLL when all + * underlying devices supporting polling. + */ + if (__table_type_bio_based(t->type)) { + if (dm_table_supports_poll(t)) + blk_queue_flag_set(QUEUE_FLAG_POLL, q); + else + blk_queue_flag_clear(QUEUE_FLAG_POLL, q); + } + return 0; } diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c index 1a96a07cbf44..2db7030aba00 100644 --- a/drivers/md/dm-thin-metadata.c +++ b/drivers/md/dm-thin-metadata.c @@ -1665,22 +1665,6 @@ int dm_thin_insert_block(struct dm_thin_device *td, dm_block_t block, return r; } -static int __remove(struct dm_thin_device *td, dm_block_t block) -{ - int r; - struct dm_pool_metadata *pmd = td->pmd; - dm_block_t keys[2] = { td->id, block }; - - r = dm_btree_remove(&pmd->info, pmd->root, keys, &pmd->root); - if (r) - return r; - - td->mapped_blocks--; - td->changed = true; - - return 0; -} - static int __remove_range(struct dm_thin_device *td, dm_block_t begin, dm_block_t end) { int r; @@ -1740,18 +1724,6 @@ static int __remove_range(struct dm_thin_device *td, dm_block_t begin, dm_block_ return dm_btree_insert(&pmd->tl_info, pmd->root, keys, &value, &pmd->root); } -int dm_thin_remove_block(struct dm_thin_device *td, dm_block_t block) -{ - int r = -EINVAL; - - pmd_write_lock(td->pmd); - if (!td->pmd->fail_io) - r = __remove(td, block); - pmd_write_unlock(td->pmd); - - return r; -} - int dm_thin_remove_range(struct dm_thin_device *td, dm_block_t begin, dm_block_t end) { diff --git a/drivers/md/dm-thin-metadata.h b/drivers/md/dm-thin-metadata.h index 7ef56bd2a7e3..4d7a2caf21d9 100644 --- a/drivers/md/dm-thin-metadata.h +++ b/drivers/md/dm-thin-metadata.h @@ -166,7 +166,6 @@ int dm_pool_alloc_data_block(struct dm_pool_metadata *pmd, dm_block_t *result); int dm_thin_insert_block(struct dm_thin_device *td, dm_block_t block, dm_block_t data_block); -int dm_thin_remove_block(struct dm_thin_device *td, dm_block_t block); int dm_thin_remove_range(struct dm_thin_device *td, dm_block_t begin, dm_block_t end); diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index ec119d2422d5..4d25d0e27031 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -161,7 +161,7 @@ static void throttle_work_start(struct throttle *t) static void throttle_work_update(struct throttle *t) { - if (!t->throttle_applied && jiffies > t->threshold) { + if (!t->throttle_applied && time_is_before_jiffies(t->threshold)) { down_write(&t->lock); t->throttle_applied = true; } @@ -282,8 +282,6 @@ struct pool { struct dm_bio_prison_cell **cell_sort_array; mempool_t mapping_pool; - - struct bio flush_bio; }; static void metadata_operation_failed(struct pool *pool, const char *op, int r); @@ -757,7 +755,7 @@ static void issue(struct thin_c *tc, struct bio *bio) struct pool *pool = tc->pool; if (!bio_triggers_commit(tc, bio)) { - submit_bio_noacct(bio); + dm_submit_bio_remap(bio, NULL); return; } @@ -1179,25 +1177,17 @@ static void process_prepared_discard_passdown_pt1(struct dm_thin_new_mapping *m) return; } - discard_parent = bio_alloc(GFP_NOIO, 1); - if (!discard_parent) { - DMWARN("%s: unable to allocate top level discard bio for passdown. Skipping passdown.", - dm_device_name(tc->pool->pool_md)); - queue_passdown_pt2(m); - - } else { - discard_parent->bi_end_io = passdown_endio; - discard_parent->bi_private = m; - - if (m->maybe_shared) - passdown_double_checking_shared_status(m, discard_parent); - else { - struct discard_op op; - - begin_discard(&op, tc, discard_parent); - r = issue_discard(&op, m->data_block, data_end); - end_discard(&op, r); - } + discard_parent = bio_alloc(NULL, 1, 0, GFP_NOIO); + discard_parent->bi_end_io = passdown_endio; + discard_parent->bi_private = m; + if (m->maybe_shared) + passdown_double_checking_shared_status(m, discard_parent); + else { + struct discard_op op; + + begin_discard(&op, tc, discard_parent); + r = issue_discard(&op, m->data_block, data_end); + end_discard(&op, r); } } @@ -2393,7 +2383,7 @@ static void process_deferred_bios(struct pool *pool) if (bio->bi_opf & REQ_PREFLUSH) bio_endio(bio); else - submit_bio_noacct(bio); + dm_submit_bio_remap(bio, NULL); } } @@ -2834,7 +2824,6 @@ static void disable_passdown_if_not_supported(struct pool_c *pt) struct block_device *data_bdev = pt->data_dev->bdev; struct queue_limits *data_limits = &bdev_get_queue(data_bdev)->limits; const char *reason = NULL; - char buf[BDEVNAME_SIZE]; if (!pt->adjusted_pf.discard_passdown) return; @@ -2846,7 +2835,7 @@ static void disable_passdown_if_not_supported(struct pool_c *pt) reason = "max discard sectors smaller than a block"; if (reason) { - DMWARN("Data device (%s) %s: Disabling discard passdown.", bdevname(data_bdev, buf), reason); + DMWARN("Data device (%pg) %s: Disabling discard passdown.", data_bdev, reason); pt->adjusted_pf.discard_passdown = false; } } @@ -2913,7 +2902,6 @@ static void __pool_destroy(struct pool *pool) if (pool->next_mapping) mempool_free(pool->next_mapping, &pool->mapping_pool); mempool_exit(&pool->mapping_pool); - bio_uninit(&pool->flush_bio); dm_deferred_set_destroy(pool->shared_read_ds); dm_deferred_set_destroy(pool->all_io_ds); kfree(pool); @@ -2994,7 +2982,6 @@ static struct pool *pool_create(struct mapped_device *pool_md, pool->low_water_triggered = false; pool->suspended = true; pool->out_of_data_space = false; - bio_init(&pool->flush_bio, NULL, 0); pool->shared_read_ds = dm_deferred_set_create(); if (!pool->shared_read_ds) { @@ -3201,13 +3188,8 @@ static void metadata_low_callback(void *context) static int metadata_pre_commit_callback(void *context) { struct pool *pool = context; - struct bio *flush_bio = &pool->flush_bio; - - bio_reset(flush_bio); - bio_set_dev(flush_bio, pool->data_dev); - flush_bio->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH; - return submit_bio_wait(flush_bio); + return blkdev_issue_flush(pool->data_dev); } static sector_t get_dev_size(struct block_device *bdev) @@ -3218,11 +3200,10 @@ static sector_t get_dev_size(struct block_device *bdev) static void warn_if_metadata_device_too_big(struct block_device *bdev) { sector_t metadata_dev_size = get_dev_size(bdev); - char buffer[BDEVNAME_SIZE]; if (metadata_dev_size > THIN_METADATA_MAX_SECTORS_WARNING) - DMWARN("Metadata device %s is larger than %u sectors: excess space will not be used.", - bdevname(bdev, buffer), THIN_METADATA_MAX_SECTORS); + DMWARN("Metadata device %pg is larger than %u sectors: excess space will not be used.", + bdev, THIN_METADATA_MAX_SECTORS); } static sector_t get_metadata_dev_size(struct block_device *bdev) @@ -4250,6 +4231,7 @@ static int thin_ctr(struct dm_target *ti, unsigned argc, char **argv) ti->num_flush_bios = 1; ti->flush_supported = true; + ti->accounts_remapped_io = true; ti->per_io_data_size = sizeof(struct dm_thin_endio_hook); /* In case the pool supports discards, pass them on. */ diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c index 4f31591d2d25..5630b470ba42 100644 --- a/drivers/md/dm-writecache.c +++ b/drivers/md/dm-writecache.c @@ -1821,11 +1821,11 @@ static void __writecache_writeback_pmem(struct dm_writecache *wc, struct writeba max_pages = e->wc_list_contiguous; - bio = bio_alloc_bioset(GFP_NOIO, max_pages, &wc->bio_set); + bio = bio_alloc_bioset(wc->dev->bdev, max_pages, REQ_OP_WRITE, + GFP_NOIO, &wc->bio_set); wb = container_of(bio, struct writeback_struct, bio); wb->wc = wc; bio->bi_end_io = writecache_writeback_endio; - bio_set_dev(bio, wc->dev->bdev); bio->bi_iter.bi_sector = read_original_sector(wc, e); if (max_pages <= WB_LIST_INLINE || unlikely(!(wb->wc_list = kmalloc_array(max_pages, sizeof(struct wc_entry *), @@ -1852,7 +1852,8 @@ static void __writecache_writeback_pmem(struct dm_writecache *wc, struct writeba wb->wc_list[wb->wc_list_n++] = f; e = f; } - bio_set_op_attrs(bio, REQ_OP_WRITE, WC_MODE_FUA(wc) * REQ_FUA); + if (WC_MODE_FUA(wc)) + bio->bi_opf |= REQ_FUA; if (writecache_has_error(wc)) { bio->bi_status = BLK_STS_IOERR; bio_endio(bio); diff --git a/drivers/md/dm-zone.c b/drivers/md/dm-zone.c index 6d82a34438c8..c1ca9be4b79e 100644 --- a/drivers/md/dm-zone.c +++ b/drivers/md/dm-zone.c @@ -130,7 +130,6 @@ bool dm_is_zone_write(struct mapped_device *md, struct bio *bio) switch (bio_op(bio)) { case REQ_OP_WRITE_ZEROES: - case REQ_OP_WRITE_SAME: case REQ_OP_WRITE: return !op_is_flush(bio->bi_opf) && bio_sectors(bio); default: @@ -390,7 +389,6 @@ static bool dm_zone_map_bio_begin(struct mapped_device *md, case REQ_OP_ZONE_FINISH: return true; case REQ_OP_WRITE_ZEROES: - case REQ_OP_WRITE_SAME: case REQ_OP_WRITE: /* Writes must be aligned to the zone write pointer */ if ((clone->bi_iter.bi_sector & (zsectors - 1)) != zwp_offset) @@ -446,7 +444,6 @@ static blk_status_t dm_zone_map_bio_end(struct mapped_device *md, blk_queue_zone_sectors(md->queue)); return BLK_STS_OK; case REQ_OP_WRITE_ZEROES: - case REQ_OP_WRITE_SAME: case REQ_OP_WRITE: WRITE_ONCE(md->zwp_offset[zno], zwp_offset + nr_sectors); return BLK_STS_OK; @@ -503,7 +500,6 @@ static bool dm_need_zone_wp_tracking(struct bio *orig_bio) return false; switch (bio_op(orig_bio)) { case REQ_OP_WRITE_ZEROES: - case REQ_OP_WRITE_SAME: case REQ_OP_WRITE: case REQ_OP_ZONE_RESET: case REQ_OP_ZONE_FINISH: diff --git a/drivers/md/dm-zoned-metadata.c b/drivers/md/dm-zoned-metadata.c index ee4626d08557..d1ea66114d14 100644 --- a/drivers/md/dm-zoned-metadata.c +++ b/drivers/md/dm-zoned-metadata.c @@ -550,11 +550,8 @@ static struct dmz_mblock *dmz_get_mblock_slow(struct dmz_metadata *zmd, if (!mblk) return ERR_PTR(-ENOMEM); - bio = bio_alloc(GFP_NOIO, 1); - if (!bio) { - dmz_free_mblock(zmd, mblk); - return ERR_PTR(-ENOMEM); - } + bio = bio_alloc(dev->bdev, 1, REQ_OP_READ | REQ_META | REQ_PRIO, + GFP_NOIO); spin_lock(&zmd->mblk_lock); @@ -578,10 +575,8 @@ static struct dmz_mblock *dmz_get_mblock_slow(struct dmz_metadata *zmd, /* Submit read BIO */ bio->bi_iter.bi_sector = dmz_blk2sect(block); - bio_set_dev(bio, dev->bdev); bio->bi_private = mblk; bio->bi_end_io = dmz_mblock_bio_end_io; - bio_set_op_attrs(bio, REQ_OP_READ, REQ_META | REQ_PRIO); bio_add_page(bio, mblk->page, DMZ_BLOCK_SIZE, 0); submit_bio(bio); @@ -725,19 +720,14 @@ static int dmz_write_mblock(struct dmz_metadata *zmd, struct dmz_mblock *mblk, if (dmz_bdev_is_dying(dev)) return -EIO; - bio = bio_alloc(GFP_NOIO, 1); - if (!bio) { - set_bit(DMZ_META_ERROR, &mblk->state); - return -ENOMEM; - } + bio = bio_alloc(dev->bdev, 1, REQ_OP_WRITE | REQ_META | REQ_PRIO, + GFP_NOIO); set_bit(DMZ_META_WRITING, &mblk->state); bio->bi_iter.bi_sector = dmz_blk2sect(block); - bio_set_dev(bio, dev->bdev); bio->bi_private = mblk; bio->bi_end_io = dmz_mblock_bio_end_io; - bio_set_op_attrs(bio, REQ_OP_WRITE, REQ_META | REQ_PRIO); bio_add_page(bio, mblk->page, DMZ_BLOCK_SIZE, 0); submit_bio(bio); @@ -759,13 +749,9 @@ static int dmz_rdwr_block(struct dmz_dev *dev, int op, if (dmz_bdev_is_dying(dev)) return -EIO; - bio = bio_alloc(GFP_NOIO, 1); - if (!bio) - return -ENOMEM; - + bio = bio_alloc(dev->bdev, 1, op | REQ_SYNC | REQ_META | REQ_PRIO, + GFP_NOIO); bio->bi_iter.bi_sector = dmz_blk2sect(block); - bio_set_dev(bio, dev->bdev); - bio_set_op_attrs(bio, op, REQ_SYNC | REQ_META | REQ_PRIO); bio_add_page(bio, page, DMZ_BLOCK_SIZE, 0); ret = submit_bio_wait(bio); bio_put(bio); @@ -1115,8 +1101,8 @@ static int dmz_check_sb(struct dmz_metadata *zmd, struct dmz_sb *dsb, */ static int dmz_read_sb(struct dmz_metadata *zmd, struct dmz_sb *sb, int set) { - dmz_zmd_debug(zmd, "read superblock set %d dev %s block %llu", - set, sb->dev->name, sb->block); + dmz_zmd_debug(zmd, "read superblock set %d dev %pg block %llu", + set, sb->dev->bdev, sb->block); return dmz_rdwr_block(sb->dev, REQ_OP_READ, sb->block, sb->mblk->page); diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c index 166c4e9d99c9..cac295cc8840 100644 --- a/drivers/md/dm-zoned-target.c +++ b/drivers/md/dm-zoned-target.c @@ -125,11 +125,10 @@ static int dmz_submit_bio(struct dmz_target *dmz, struct dm_zone *zone, if (dev->flags & DMZ_BDEV_DYING) return -EIO; - clone = bio_clone_fast(bio, GFP_NOIO, &dmz->bio_set); + clone = bio_alloc_clone(dev->bdev, bio, GFP_NOIO, &dmz->bio_set); if (!clone) return -ENOMEM; - bio_set_dev(clone, dev->bdev); bioctx->dev = dev; clone->bi_iter.bi_sector = dmz_start_sect(dmz->metadata, zone) + dmz_blk2sect(chunk_block); @@ -731,7 +730,6 @@ static int dmz_get_zoned_device(struct dm_target *ti, char *path, } dev->bdev = bdev; dev->dev_idx = idx; - (void)bdevname(dev->bdev, dev->name); dev->capacity = bdev_nr_sectors(bdev); if (ti->begin) { diff --git a/drivers/md/dm-zoned.h b/drivers/md/dm-zoned.h index 22f11440b423..a02744a0846c 100644 --- a/drivers/md/dm-zoned.h +++ b/drivers/md/dm-zoned.h @@ -56,7 +56,6 @@ struct dmz_dev { struct dmz_metadata *metadata; struct dmz_reclaim *reclaim; - char name[BDEVNAME_SIZE]; uuid_t uuid; sector_t capacity; @@ -176,16 +175,16 @@ enum { * Message functions. */ #define dmz_dev_info(dev, format, args...) \ - DMINFO("(%s): " format, (dev)->name, ## args) + DMINFO("(%pg): " format, (dev)->bdev, ## args) #define dmz_dev_err(dev, format, args...) \ - DMERR("(%s): " format, (dev)->name, ## args) + DMERR("(%pg): " format, (dev)->bdev, ## args) #define dmz_dev_warn(dev, format, args...) \ - DMWARN("(%s): " format, (dev)->name, ## args) + DMWARN("(%pg): " format, (dev)->bdev, ## args) #define dmz_dev_debug(dev, format, args...) \ - DMDEBUG("(%s): " format, (dev)->name, ## args) + DMDEBUG("(%pg): " format, (dev)->bdev, ## args) /* * Functions defined in dm-zoned-metadata.c diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 997ace47bbd5..ad2e0bbeb559 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -40,6 +40,13 @@ #define DM_COOKIE_ENV_VAR_NAME "DM_COOKIE" #define DM_COOKIE_LENGTH 24 +/* + * For REQ_POLLED fs bio, this flag is set if we link mapped underlying + * dm_io into one list, and reuse bio->bi_private as the list head. Before + * ending this fs bio, we will recover its ->bi_private. + */ +#define REQ_DM_POLL_LIST REQ_DRV + static const char *_name = DM_NAME; static unsigned int major = 0; @@ -73,16 +80,21 @@ struct clone_info { struct dm_io *io; sector_t sector; unsigned sector_count; + bool submit_as_polled; }; #define DM_TARGET_IO_BIO_OFFSET (offsetof(struct dm_target_io, clone)) #define DM_IO_BIO_OFFSET \ (offsetof(struct dm_target_io, clone) + offsetof(struct dm_io, tio)) +static inline struct dm_target_io *clone_to_tio(struct bio *clone) +{ + return container_of(clone, struct dm_target_io, clone); +} + void *dm_per_bio_data(struct bio *bio, size_t data_size) { - struct dm_target_io *tio = container_of(bio, struct dm_target_io, clone); - if (!tio->inside_dm_io) + if (!dm_tio_flagged(clone_to_tio(bio), DM_TIO_INSIDE_DM_IO)) return (char *)bio - DM_TARGET_IO_BIO_OFFSET - data_size; return (char *)bio - DM_IO_BIO_OFFSET - data_size; } @@ -477,40 +489,78 @@ out: u64 dm_start_time_ns_from_clone(struct bio *bio) { - struct dm_target_io *tio = container_of(bio, struct dm_target_io, clone); - struct dm_io *io = tio->io; - - return jiffies_to_nsecs(io->start_time); + return jiffies_to_nsecs(clone_to_tio(bio)->io->start_time); } EXPORT_SYMBOL_GPL(dm_start_time_ns_from_clone); -static void start_io_acct(struct dm_io *io) +static bool bio_is_flush_with_data(struct bio *bio) { - struct mapped_device *md = io->md; - struct bio *bio = io->orig_bio; + return ((bio->bi_opf & REQ_PREFLUSH) && bio->bi_iter.bi_size); +} + +static void dm_io_acct(bool end, struct mapped_device *md, struct bio *bio, + unsigned long start_time, struct dm_stats_aux *stats_aux) +{ + bool is_flush_with_data; + unsigned int bi_size; + + /* If REQ_PREFLUSH set save any payload but do not account it */ + is_flush_with_data = bio_is_flush_with_data(bio); + if (is_flush_with_data) { + bi_size = bio->bi_iter.bi_size; + bio->bi_iter.bi_size = 0; + } + + if (!end) + bio_start_io_acct_time(bio, start_time); + else + bio_end_io_acct(bio, start_time); - bio_start_io_acct_time(bio, io->start_time); if (unlikely(dm_stats_used(&md->stats))) dm_stats_account_io(&md->stats, bio_data_dir(bio), bio->bi_iter.bi_sector, bio_sectors(bio), - false, 0, &io->stats_aux); + end, start_time, stats_aux); + + /* Restore bio's payload so it does get accounted upon requeue */ + if (is_flush_with_data) + bio->bi_iter.bi_size = bi_size; } -static void end_io_acct(struct mapped_device *md, struct bio *bio, - unsigned long start_time, struct dm_stats_aux *stats_aux) +static void __dm_start_io_acct(struct dm_io *io, struct bio *bio) { - unsigned long duration = jiffies - start_time; + dm_io_acct(false, io->md, bio, io->start_time, &io->stats_aux); +} - bio_end_io_acct(bio, start_time); +static void dm_start_io_acct(struct dm_io *io, struct bio *clone) +{ + /* Must account IO to DM device in terms of orig_bio */ + struct bio *bio = io->orig_bio; - if (unlikely(dm_stats_used(&md->stats))) - dm_stats_account_io(&md->stats, bio_data_dir(bio), - bio->bi_iter.bi_sector, bio_sectors(bio), - true, duration, stats_aux); + /* + * Ensure IO accounting is only ever started once. + * Expect no possibility for race unless DM_TIO_IS_DUPLICATE_BIO. + */ + if (!clone || + likely(!dm_tio_flagged(clone_to_tio(clone), DM_TIO_IS_DUPLICATE_BIO))) { + if (WARN_ON_ONCE(dm_io_flagged(io, DM_IO_ACCOUNTED))) + return; + dm_io_set_flag(io, DM_IO_ACCOUNTED); + } else { + unsigned long flags; + if (dm_io_flagged(io, DM_IO_ACCOUNTED)) + return; + /* Can afford locking given DM_TIO_IS_DUPLICATE_BIO */ + spin_lock_irqsave(&io->lock, flags); + dm_io_set_flag(io, DM_IO_ACCOUNTED); + spin_unlock_irqrestore(&io->lock, flags); + } - /* nudge anyone waiting on suspend queue */ - if (unlikely(wq_has_sleeper(&md->wait))) - wake_up(&md->wait); + __dm_start_io_acct(io, bio); +} + +static void dm_end_io_acct(struct dm_io *io, struct bio *bio) +{ + dm_io_acct(true, io->md, bio, io->start_time, &io->stats_aux); } static struct dm_io *alloc_io(struct mapped_device *md, struct bio *bio) @@ -519,62 +569,80 @@ static struct dm_io *alloc_io(struct mapped_device *md, struct bio *bio) struct dm_target_io *tio; struct bio *clone; - clone = bio_alloc_bioset(GFP_NOIO, 0, &md->io_bs); - if (!clone) - return NULL; + clone = bio_alloc_clone(bio->bi_bdev, bio, GFP_NOIO, &md->io_bs); - tio = container_of(clone, struct dm_target_io, clone); - tio->inside_dm_io = true; + tio = clone_to_tio(clone); + tio->flags = 0; + dm_tio_set_flag(tio, DM_TIO_INSIDE_DM_IO); tio->io = NULL; io = container_of(tio, struct dm_io, tio); io->magic = DM_IO_MAGIC; io->status = 0; atomic_set(&io->io_count, 1); - io->orig_bio = bio; + this_cpu_inc(*md->pending_io); + io->orig_bio = NULL; io->md = md; - spin_lock_init(&io->endio_lock); - + io->map_task = current; + spin_lock_init(&io->lock); io->start_time = jiffies; + io->flags = 0; + + dm_stats_record_start(&md->stats, &io->stats_aux); return io; } -static void free_io(struct mapped_device *md, struct dm_io *io) +static void free_io(struct dm_io *io) { bio_put(&io->tio.clone); } -static struct dm_target_io *alloc_tio(struct clone_info *ci, struct dm_target *ti, - unsigned target_bio_nr, gfp_t gfp_mask) +static struct bio *alloc_tio(struct clone_info *ci, struct dm_target *ti, + unsigned target_bio_nr, unsigned *len, gfp_t gfp_mask) { struct dm_target_io *tio; + struct bio *clone; if (!ci->io->tio.io) { /* the dm_target_io embedded in ci->io is available */ tio = &ci->io->tio; + /* alloc_io() already initialized embedded clone */ + clone = &tio->clone; } else { - struct bio *clone = bio_alloc_bioset(gfp_mask, 0, &ci->io->md->bs); + clone = bio_alloc_clone(ci->bio->bi_bdev, ci->bio, + gfp_mask, &ci->io->md->bs); if (!clone) return NULL; - tio = container_of(clone, struct dm_target_io, clone); - tio->inside_dm_io = false; + /* REQ_DM_POLL_LIST shouldn't be inherited */ + clone->bi_opf &= ~REQ_DM_POLL_LIST; + + tio = clone_to_tio(clone); + tio->flags = 0; /* also clears DM_TIO_INSIDE_DM_IO */ } tio->magic = DM_TIO_MAGIC; tio->io = ci->io; tio->ti = ti; tio->target_bio_nr = target_bio_nr; + tio->len_ptr = len; + tio->old_sector = 0; - return tio; + if (len) { + clone->bi_iter.bi_size = to_bytes(*len); + if (bio_integrity(clone)) + bio_integrity_trim(clone); + } + + return clone; } -static void free_tio(struct dm_target_io *tio) +static void free_tio(struct bio *clone) { - if (tio->inside_dm_io) + if (dm_tio_flagged(clone_to_tio(clone), DM_TIO_INSIDE_DM_IO)) return; - bio_put(&tio->clone); + bio_put(clone); } /* @@ -779,88 +847,109 @@ static int __noflush_suspending(struct mapped_device *md) return test_bit(DMF_NOFLUSH_SUSPENDING, &md->flags); } -/* - * Decrements the number of outstanding ios that a bio has been - * cloned into, completing the original io if necc. - */ -void dm_io_dec_pending(struct dm_io *io, blk_status_t error) +static void dm_io_complete(struct dm_io *io) { - unsigned long flags; blk_status_t io_error; - struct bio *bio; struct mapped_device *md = io->md; - unsigned long start_time = 0; - struct dm_stats_aux stats_aux; - - /* Push-back supersedes any I/O errors */ - if (unlikely(error)) { - spin_lock_irqsave(&io->endio_lock, flags); - if (!(io->status == BLK_STS_DM_REQUEUE && __noflush_suspending(md))) - io->status = error; - spin_unlock_irqrestore(&io->endio_lock, flags); - } + struct bio *bio = io->orig_bio; - if (atomic_dec_and_test(&io->io_count)) { - bio = io->orig_bio; - if (io->status == BLK_STS_DM_REQUEUE) { + if (io->status == BLK_STS_DM_REQUEUE) { + unsigned long flags; + /* + * Target requested pushing back the I/O. + */ + spin_lock_irqsave(&md->deferred_lock, flags); + if (__noflush_suspending(md) && + !WARN_ON_ONCE(dm_is_zone_write(md, bio))) { + /* NOTE early return due to BLK_STS_DM_REQUEUE below */ + bio_list_add_head(&md->deferred, bio); + } else { /* - * Target requested pushing back the I/O. + * noflush suspend was interrupted or this is + * a write to a zoned target. */ - spin_lock_irqsave(&md->deferred_lock, flags); - if (__noflush_suspending(md) && - !WARN_ON_ONCE(dm_is_zone_write(md, bio))) { - /* NOTE early return due to BLK_STS_DM_REQUEUE below */ - bio_list_add_head(&md->deferred, bio); - } else { - /* - * noflush suspend was interrupted or this is - * a write to a zoned target. - */ - io->status = BLK_STS_IOERR; - } - spin_unlock_irqrestore(&md->deferred_lock, flags); + io->status = BLK_STS_IOERR; } + spin_unlock_irqrestore(&md->deferred_lock, flags); + } - io_error = io->status; - start_time = io->start_time; - stats_aux = io->stats_aux; - free_io(md, io); - end_io_acct(md, bio, start_time, &stats_aux); + io_error = io->status; + if (dm_io_flagged(io, DM_IO_ACCOUNTED)) + dm_end_io_acct(io, bio); + else if (!io_error) { + /* + * Must handle target that DM_MAPIO_SUBMITTED only to + * then bio_endio() rather than dm_submit_bio_remap() + */ + __dm_start_io_acct(io, bio); + dm_end_io_acct(io, bio); + } + free_io(io); + smp_wmb(); + this_cpu_dec(*md->pending_io); - if (io_error == BLK_STS_DM_REQUEUE) - return; + /* nudge anyone waiting on suspend queue */ + if (unlikely(wq_has_sleeper(&md->wait))) + wake_up(&md->wait); - if ((bio->bi_opf & REQ_PREFLUSH) && bio->bi_iter.bi_size) { - /* - * Preflush done for flush with data, reissue - * without REQ_PREFLUSH. - */ - bio->bi_opf &= ~REQ_PREFLUSH; - queue_io(md, bio); - } else { - /* done with normal IO or empty flush */ - if (io_error) - bio->bi_status = io_error; - bio_endio(bio); - } + if (io_error == BLK_STS_DM_REQUEUE) { + /* + * Upper layer won't help us poll split bio, io->orig_bio + * may only reflect a subset of the pre-split original, + * so clear REQ_POLLED in case of requeue + */ + bio->bi_opf &= ~REQ_POLLED; + return; + } + + if (bio_is_flush_with_data(bio)) { + /* + * Preflush done for flush with data, reissue + * without REQ_PREFLUSH. + */ + bio->bi_opf &= ~REQ_PREFLUSH; + queue_io(md, bio); + } else { + /* done with normal IO or empty flush */ + if (io_error) + bio->bi_status = io_error; + bio_endio(bio); } } -void disable_discard(struct mapped_device *md) +static inline bool dm_tio_is_normal(struct dm_target_io *tio) { - struct queue_limits *limits = dm_get_queue_limits(md); + return (dm_tio_flagged(tio, DM_TIO_INSIDE_DM_IO) && + !dm_tio_flagged(tio, DM_TIO_IS_DUPLICATE_BIO)); +} - /* device doesn't really support DISCARD, disable it */ - limits->max_discard_sectors = 0; - blk_queue_flag_clear(QUEUE_FLAG_DISCARD, md->queue); +/* + * Decrements the number of outstanding ios that a bio has been + * cloned into, completing the original io if necc. + */ +void dm_io_dec_pending(struct dm_io *io, blk_status_t error) +{ + /* Push-back supersedes any I/O errors */ + if (unlikely(error)) { + unsigned long flags; + spin_lock_irqsave(&io->lock, flags); + if (!(io->status == BLK_STS_DM_REQUEUE && + __noflush_suspending(io->md))) + io->status = error; + spin_unlock_irqrestore(&io->lock, flags); + } + + if (atomic_dec_and_test(&io->io_count)) + dm_io_complete(io); } -void disable_write_same(struct mapped_device *md) +void disable_discard(struct mapped_device *md) { struct queue_limits *limits = dm_get_queue_limits(md); - /* device doesn't really support WRITE SAME, disable it */ - limits->max_write_same_sectors = 0; + /* device doesn't really support DISCARD, disable it */ + limits->max_discard_sectors = 0; + blk_queue_flag_clear(QUEUE_FLAG_DISCARD, md->queue); } void disable_write_zeroes(struct mapped_device *md) @@ -879,7 +968,7 @@ static bool swap_bios_limit(struct dm_target *ti, struct bio *bio) static void clone_endio(struct bio *bio) { blk_status_t error = bio->bi_status; - struct dm_target_io *tio = container_of(bio, struct dm_target_io, clone); + struct dm_target_io *tio = clone_to_tio(bio); struct dm_io *io = tio->io; struct mapped_device *md = tio->io->md; dm_endio_fn endio = tio->ti->type->end_io; @@ -889,9 +978,6 @@ static void clone_endio(struct bio *bio) if (bio_op(bio) == REQ_OP_DISCARD && !q->limits.max_discard_sectors) disable_discard(md); - else if (bio_op(bio) == REQ_OP_WRITE_SAME && - !q->limits.max_write_same_sectors) - disable_write_same(md); else if (bio_op(bio) == REQ_OP_WRITE_ZEROES && !q->limits.max_write_zeroes_sectors) disable_write_zeroes(md); @@ -930,7 +1016,7 @@ static void clone_endio(struct bio *bio) up(&md->swap_bios_semaphore); } - free_tio(tio); + free_tio(bio); dm_io_dec_pending(io, error); } @@ -1057,7 +1143,8 @@ static int dm_dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff, /* * A target may call dm_accept_partial_bio only from the map routine. It is * allowed for all bio types except REQ_PREFLUSH, REQ_OP_ZONE_* zone management - * operations and REQ_OP_ZONE_APPEND (zone append writes). + * operations, REQ_OP_ZONE_APPEND (zone append writes) and any bio serviced by + * __send_duplicate_bios(). * * dm_accept_partial_bio informs the dm that the target only wants to process * additional n_sectors sectors of the bio and the rest of the data should be @@ -1085,10 +1172,10 @@ static int dm_dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff, */ void dm_accept_partial_bio(struct bio *bio, unsigned n_sectors) { - struct dm_target_io *tio = container_of(bio, struct dm_target_io, clone); + struct dm_target_io *tio = clone_to_tio(bio); unsigned bi_size = bio->bi_iter.bi_size >> SECTOR_SHIFT; - BUG_ON(bio->bi_opf & REQ_PREFLUSH); + BUG_ON(dm_tio_flagged(tio, DM_TIO_IS_DUPLICATE_BIO)); BUG_ON(op_is_zone_mgmt(bio_op(bio))); BUG_ON(bio_op(bio) == REQ_OP_ZONE_APPEND); BUG_ON(bi_size > *tio->len_ptr); @@ -1099,6 +1186,56 @@ void dm_accept_partial_bio(struct bio *bio, unsigned n_sectors) } EXPORT_SYMBOL_GPL(dm_accept_partial_bio); +static inline void __dm_submit_bio_remap(struct bio *clone, + dev_t dev, sector_t old_sector) +{ + trace_block_bio_remap(clone, dev, old_sector); + submit_bio_noacct(clone); +} + +/* + * @clone: clone bio that DM core passed to target's .map function + * @tgt_clone: clone of @clone bio that target needs submitted + * + * Targets should use this interface to submit bios they take + * ownership of when returning DM_MAPIO_SUBMITTED. + * + * Target should also enable ti->accounts_remapped_io + */ +void dm_submit_bio_remap(struct bio *clone, struct bio *tgt_clone) +{ + struct dm_target_io *tio = clone_to_tio(clone); + struct dm_io *io = tio->io; + + WARN_ON_ONCE(!tio->ti->accounts_remapped_io); + + /* establish bio that will get submitted */ + if (!tgt_clone) + tgt_clone = clone; + + /* + * Account io->origin_bio to DM dev on behalf of target + * that took ownership of IO with DM_MAPIO_SUBMITTED. + */ + if (io->map_task == current) { + /* Still in target's map function */ + dm_io_set_flag(io, DM_IO_START_ACCT); + } else { + /* + * Called by another thread, managed by DM target, + * wait for dm_split_and_process_bio() to store + * io->orig_bio + */ + while (unlikely(!smp_load_acquire(&io->orig_bio))) + msleep(1); + dm_start_io_acct(io, clone); + } + + __dm_submit_bio_remap(tgt_clone, disk_devt(io->md->disk), + tio->old_sector); +} +EXPORT_SYMBOL_GPL(dm_submit_bio_remap); + static noinline void __set_swap_bios_limit(struct mapped_device *md, int latch) { mutex_lock(&md->swap_bios_lock); @@ -1115,23 +1252,20 @@ static noinline void __set_swap_bios_limit(struct mapped_device *md, int latch) mutex_unlock(&md->swap_bios_lock); } -static void __map_bio(struct dm_target_io *tio) +static void __map_bio(struct bio *clone) { + struct dm_target_io *tio = clone_to_tio(clone); int r; - sector_t sector; - struct bio *clone = &tio->clone; struct dm_io *io = tio->io; struct dm_target *ti = tio->ti; clone->bi_end_io = clone_endio; /* - * Map the clone. If r == 0 we don't need to do - * anything, the target has assumed ownership of - * this io. + * Map the clone. */ dm_io_inc_pending(io); - sector = clone->bi_iter.bi_sector; + tio->old_sector = clone->bi_iter.bi_sector; if (unlikely(swap_bios_limit(ti, clone))) { struct mapped_device *md = io->md; @@ -1153,27 +1287,28 @@ static void __map_bio(struct dm_target_io *tio) switch (r) { case DM_MAPIO_SUBMITTED: + /* target has assumed ownership of this io */ + if (!ti->accounts_remapped_io) + dm_io_set_flag(io, DM_IO_START_ACCT); break; case DM_MAPIO_REMAPPED: - /* the bio has been remapped so dispatch it */ - trace_block_bio_remap(clone, bio_dev(io->orig_bio), sector); - submit_bio_noacct(clone); + /* + * the bio has been remapped so dispatch it, but defer + * dm_start_io_acct() until after possible bio_split(). + */ + __dm_submit_bio_remap(clone, disk_devt(io->md->disk), + tio->old_sector); + dm_io_set_flag(io, DM_IO_START_ACCT); break; case DM_MAPIO_KILL: - if (unlikely(swap_bios_limit(ti, clone))) { - struct mapped_device *md = io->md; - up(&md->swap_bios_semaphore); - } - free_tio(tio); - dm_io_dec_pending(io, BLK_STS_IOERR); - break; case DM_MAPIO_REQUEUE: - if (unlikely(swap_bios_limit(ti, clone))) { - struct mapped_device *md = io->md; - up(&md->swap_bios_semaphore); - } - free_tio(tio); - dm_io_dec_pending(io, BLK_STS_DM_REQUEUE); + if (unlikely(swap_bios_limit(ti, clone))) + up(&io->md->swap_bios_semaphore); + free_tio(clone); + if (r == DM_MAPIO_KILL) + dm_io_dec_pending(io, BLK_STS_IOERR); + else + dm_io_dec_pending(io, BLK_STS_DM_REQUEUE); break; default: DMWARN("unimplemented target map return value: %d", r); @@ -1181,119 +1316,61 @@ static void __map_bio(struct dm_target_io *tio) } } -static void bio_setup_sector(struct bio *bio, sector_t sector, unsigned len) -{ - bio->bi_iter.bi_sector = sector; - bio->bi_iter.bi_size = to_bytes(len); -} - -/* - * Creates a bio that consists of range of complete bvecs. - */ -static int clone_bio(struct dm_target_io *tio, struct bio *bio, - sector_t sector, unsigned len) -{ - struct bio *clone = &tio->clone; - int r; - - __bio_clone_fast(clone, bio); - - r = bio_crypt_clone(clone, bio, GFP_NOIO); - if (r < 0) - return r; - - if (bio_integrity(bio)) { - if (unlikely(!dm_target_has_integrity(tio->ti->type) && - !dm_target_passes_integrity(tio->ti->type))) { - DMWARN("%s: the target %s doesn't support integrity data.", - dm_device_name(tio->io->md), - tio->ti->type->name); - return -EIO; - } - - r = bio_integrity_clone(clone, bio, GFP_NOIO); - if (r < 0) - return r; - } - - bio_advance(clone, to_bytes(sector - clone->bi_iter.bi_sector)); - clone->bi_iter.bi_size = to_bytes(len); - - if (bio_integrity(bio)) - bio_integrity_trim(clone); - - return 0; -} - static void alloc_multiple_bios(struct bio_list *blist, struct clone_info *ci, - struct dm_target *ti, unsigned num_bios) + struct dm_target *ti, unsigned num_bios, + unsigned *len) { - struct dm_target_io *tio; + struct bio *bio; int try; - if (!num_bios) - return; - - if (num_bios == 1) { - tio = alloc_tio(ci, ti, 0, GFP_NOIO); - bio_list_add(blist, &tio->clone); - return; - } - for (try = 0; try < 2; try++) { int bio_nr; - struct bio *bio; if (try) mutex_lock(&ci->io->md->table_devices_lock); for (bio_nr = 0; bio_nr < num_bios; bio_nr++) { - tio = alloc_tio(ci, ti, bio_nr, try ? GFP_NOIO : GFP_NOWAIT); - if (!tio) + bio = alloc_tio(ci, ti, bio_nr, len, + try ? GFP_NOIO : GFP_NOWAIT); + if (!bio) break; - bio_list_add(blist, &tio->clone); + bio_list_add(blist, bio); } if (try) mutex_unlock(&ci->io->md->table_devices_lock); if (bio_nr == num_bios) return; - while ((bio = bio_list_pop(blist))) { - tio = container_of(bio, struct dm_target_io, clone); - free_tio(tio); - } + while ((bio = bio_list_pop(blist))) + free_tio(bio); } } -static void __clone_and_map_simple_bio(struct clone_info *ci, - struct dm_target_io *tio, unsigned *len) -{ - struct bio *clone = &tio->clone; - - tio->len_ptr = len; - - __bio_clone_fast(clone, ci->bio); - if (len) - bio_setup_sector(clone, ci->sector, *len); - __map_bio(tio); -} - static void __send_duplicate_bios(struct clone_info *ci, struct dm_target *ti, unsigned num_bios, unsigned *len) { struct bio_list blist = BIO_EMPTY_LIST; - struct bio *bio; - struct dm_target_io *tio; - - alloc_multiple_bios(&blist, ci, ti, num_bios); + struct bio *clone; - while ((bio = bio_list_pop(&blist))) { - tio = container_of(bio, struct dm_target_io, clone); - __clone_and_map_simple_bio(ci, tio, len); + switch (num_bios) { + case 0: + break; + case 1: + clone = alloc_tio(ci, ti, 0, len, GFP_NOIO); + dm_tio_set_flag(clone_to_tio(clone), DM_TIO_IS_DUPLICATE_BIO); + __map_bio(clone); + break; + default: + alloc_multiple_bios(&blist, ci, ti, num_bios, len); + while ((clone = bio_list_pop(&blist))) { + dm_tio_set_flag(clone_to_tio(clone), DM_TIO_IS_DUPLICATE_BIO); + __map_bio(clone); + } + break; } } -static int __send_empty_flush(struct clone_info *ci) +static void __send_empty_flush(struct clone_info *ci) { unsigned target_nr = 0; struct dm_target *ti; @@ -1304,63 +1381,34 @@ static int __send_empty_flush(struct clone_info *ci) * need to reference it after submit. It's just used as * the basis for the clone(s). */ - bio_init(&flush_bio, NULL, 0); - flush_bio.bi_opf = REQ_OP_WRITE | REQ_PREFLUSH | REQ_SYNC; - bio_set_dev(&flush_bio, ci->io->md->disk->part0); + bio_init(&flush_bio, ci->io->md->disk->part0, NULL, 0, + REQ_OP_WRITE | REQ_PREFLUSH | REQ_SYNC); ci->bio = &flush_bio; ci->sector_count = 0; - BUG_ON(bio_has_data(ci->bio)); while ((ti = dm_table_get_target(ci->map, target_nr++))) __send_duplicate_bios(ci, ti, ti->num_flush_bios, NULL); bio_uninit(ci->bio); - return 0; } -static int __clone_and_map_data_bio(struct clone_info *ci, struct dm_target *ti, - sector_t sector, unsigned *len) -{ - struct bio *bio = ci->bio; - struct dm_target_io *tio; - int r; - - tio = alloc_tio(ci, ti, 0, GFP_NOIO); - tio->len_ptr = len; - r = clone_bio(tio, bio, sector, *len); - if (r < 0) { - free_tio(tio); - return r; - } - __map_bio(tio); - - return 0; -} - -static int __send_changing_extent_only(struct clone_info *ci, struct dm_target *ti, - unsigned num_bios) +static void __send_changing_extent_only(struct clone_info *ci, struct dm_target *ti, + unsigned num_bios) { unsigned len; - /* - * Even though the device advertised support for this type of - * request, that does not mean every target supports it, and - * reconfiguration might also have changed that since the - * check was performed. - */ - if (!num_bios) - return -EOPNOTSUPP; - len = min_t(sector_t, ci->sector_count, max_io_len_target_boundary(ti, dm_target_offset(ti, ci->sector))); - __send_duplicate_bios(ci, ti, num_bios, &len); - + /* + * dm_accept_partial_bio cannot be used with duplicate bios, + * so update clone_info cursor before __send_duplicate_bios(). + */ ci->sector += len; ci->sector_count -= len; - return 0; + __send_duplicate_bios(ci, ti, num_bios, &len); } static bool is_abnormal_io(struct bio *bio) @@ -1370,7 +1418,6 @@ static bool is_abnormal_io(struct bio *bio) switch (bio_op(bio)) { case REQ_OP_DISCARD: case REQ_OP_SECURE_ERASE: - case REQ_OP_WRITE_SAME: case REQ_OP_WRITE_ZEROES: r = true; break; @@ -1382,19 +1429,15 @@ static bool is_abnormal_io(struct bio *bio) static bool __process_abnormal_io(struct clone_info *ci, struct dm_target *ti, int *result) { - struct bio *bio = ci->bio; unsigned num_bios = 0; - switch (bio_op(bio)) { + switch (bio_op(ci->bio)) { case REQ_OP_DISCARD: num_bios = ti->num_discard_bios; break; case REQ_OP_SECURE_ERASE: num_bios = ti->num_secure_erase_bios; break; - case REQ_OP_WRITE_SAME: - num_bios = ti->num_write_same_bios; - break; case REQ_OP_WRITE_ZEROES: num_bios = ti->num_write_zeroes_bios; break; @@ -1402,15 +1445,68 @@ static bool __process_abnormal_io(struct clone_info *ci, struct dm_target *ti, return false; } - *result = __send_changing_extent_only(ci, ti, num_bios); + /* + * Even though the device advertised support for this type of + * request, that does not mean every target supports it, and + * reconfiguration might also have changed that since the + * check was performed. + */ + if (!num_bios) + *result = -EOPNOTSUPP; + else { + __send_changing_extent_only(ci, ti, num_bios); + *result = 0; + } return true; } /* + * Reuse ->bi_private as hlist head for storing all dm_io instances + * associated with this bio, and this bio's bi_private needs to be + * stored in dm_io->data before the reuse. + * + * bio->bi_private is owned by fs or upper layer, so block layer won't + * touch it after splitting. Meantime it won't be changed by anyone after + * bio is submitted. So this reuse is safe. + */ +static inline struct hlist_head *dm_get_bio_hlist_head(struct bio *bio) +{ + return (struct hlist_head *)&bio->bi_private; +} + +static void dm_queue_poll_io(struct bio *bio, struct dm_io *io) +{ + struct hlist_head *head = dm_get_bio_hlist_head(bio); + + if (!(bio->bi_opf & REQ_DM_POLL_LIST)) { + bio->bi_opf |= REQ_DM_POLL_LIST; + /* + * Save .bi_private into dm_io, so that we can reuse + * .bi_private as hlist head for storing dm_io list + */ + io->data = bio->bi_private; + + INIT_HLIST_HEAD(head); + + /* tell block layer to poll for completion */ + bio->bi_cookie = ~BLK_QC_T_NONE; + } else { + /* + * bio recursed due to split, reuse original poll list, + * and save bio->bi_private too. + */ + io->data = hlist_entry(head->first, struct dm_io, node)->data; + } + + hlist_add_head(&io->node, head); +} + +/* * Select the correct strategy for processing a non-flush bio. */ -static int __split_and_process_non_flush(struct clone_info *ci) +static int __split_and_process_bio(struct clone_info *ci) { + struct bio *clone; struct dm_target *ti; unsigned len; int r; @@ -1422,11 +1518,15 @@ static int __split_and_process_non_flush(struct clone_info *ci) if (__process_abnormal_io(ci, ti, &r)) return r; - len = min_t(sector_t, max_io_len(ti, ci->sector), ci->sector_count); + /* + * Only support bio polling for normal IO, and the target io is + * exactly inside the dm_io instance (verified in dm_poll_dm_io) + */ + ci->submit_as_polled = ci->bio->bi_opf & REQ_POLLED; - r = __clone_and_map_data_bio(ci, ti, ci->sector, &len); - if (r < 0) - return r; + len = min_t(sector_t, max_io_len(ti, ci->sector), ci->sector_count); + clone = alloc_tio(ci, ti, 0, &len, GFP_NOIO); + __map_bio(clone); ci->sector += len; ci->sector_count -= len; @@ -1439,53 +1539,69 @@ static void init_clone_info(struct clone_info *ci, struct mapped_device *md, { ci->map = map; ci->io = alloc_io(md, bio); + ci->bio = bio; + ci->submit_as_polled = false; ci->sector = bio->bi_iter.bi_sector; + ci->sector_count = bio_sectors(bio); + + /* Shouldn't happen but sector_count was being set to 0 so... */ + if (WARN_ON_ONCE(op_is_zone_mgmt(bio_op(bio)) && ci->sector_count)) + ci->sector_count = 0; } /* * Entry point to split a bio into clones and submit them to the targets. */ -static void __split_and_process_bio(struct mapped_device *md, - struct dm_table *map, struct bio *bio) +static void dm_split_and_process_bio(struct mapped_device *md, + struct dm_table *map, struct bio *bio) { struct clone_info ci; + struct bio *orig_bio = NULL; int error = 0; init_clone_info(&ci, md, map, bio); if (bio->bi_opf & REQ_PREFLUSH) { - error = __send_empty_flush(&ci); - /* dm_io_dec_pending submits any data associated with flush */ - } else if (op_is_zone_mgmt(bio_op(bio))) { - ci.bio = bio; - ci.sector_count = 0; - error = __split_and_process_non_flush(&ci); - } else { - ci.bio = bio; - ci.sector_count = bio_sectors(bio); - error = __split_and_process_non_flush(&ci); - if (ci.sector_count && !error) { - /* - * Remainder must be passed to submit_bio_noacct() - * so that it gets handled *after* bios already submitted - * have been completely processed. - * We take a clone of the original to store in - * ci.io->orig_bio to be used by end_io_acct() and - * for dec_pending to use for completion handling. - */ - struct bio *b = bio_split(bio, bio_sectors(bio) - ci.sector_count, - GFP_NOIO, &md->queue->bio_split); - ci.io->orig_bio = b; - - bio_chain(b, bio); - trace_block_split(b, bio->bi_iter.bi_sector); - submit_bio_noacct(bio); - } + __send_empty_flush(&ci); + /* dm_io_complete submits any data associated with flush */ + goto out; } - start_io_acct(ci.io); - /* drop the extra reference count */ - dm_io_dec_pending(ci.io, errno_to_blk_status(error)); + error = __split_and_process_bio(&ci); + ci.io->map_task = NULL; + if (error || !ci.sector_count) + goto out; + + /* + * Remainder must be passed to submit_bio_noacct() so it gets handled + * *after* bios already submitted have been completely processed. + * We take a clone of the original to store in ci.io->orig_bio to be + * used by dm_end_io_acct() and for dm_io_complete() to use for + * completion handling. + */ + orig_bio = bio_split(bio, bio_sectors(bio) - ci.sector_count, + GFP_NOIO, &md->queue->bio_split); + bio_chain(orig_bio, bio); + trace_block_split(orig_bio, bio->bi_iter.bi_sector); + submit_bio_noacct(bio); +out: + if (!orig_bio) + orig_bio = bio; + smp_store_release(&ci.io->orig_bio, orig_bio); + if (dm_io_flagged(ci.io, DM_IO_START_ACCT)) + dm_start_io_acct(ci.io, NULL); + + /* + * Drop the extra reference count for non-POLLED bio, and hold one + * reference for POLLED bio, which will be released in dm_poll_bio + * + * Add every dm_io instance into the hlist_head which is stored in + * bio->bi_private, so that dm_poll_bio can poll them all. + */ + if (error || !ci.submit_as_polled) + dm_io_dec_pending(ci.io, errno_to_blk_status(error)); + else + dm_queue_poll_io(bio, ci.io); } static void dm_submit_bio(struct bio *bio) @@ -1495,15 +1611,10 @@ static void dm_submit_bio(struct bio *bio) struct dm_table *map; map = dm_get_live_table(md, &srcu_idx); - if (unlikely(!map)) { - DMERR_LIMIT("%s: mapping table unavailable, erroring io", - dm_device_name(md)); - bio_io_error(bio); - goto out; - } - /* If suspended, queue this IO for later */ - if (unlikely(test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags))) { + /* If suspended, or map not yet available, queue this IO for later */ + if (unlikely(test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags)) || + unlikely(!map)) { if (bio->bi_opf & REQ_NOWAIT) bio_wouldblock_error(bio); else if (bio->bi_opf & REQ_RAHEAD) @@ -1520,11 +1631,72 @@ static void dm_submit_bio(struct bio *bio) if (is_abnormal_io(bio)) blk_queue_split(&bio); - __split_and_process_bio(md, map, bio); + dm_split_and_process_bio(md, map, bio); out: dm_put_live_table(md, srcu_idx); } +static bool dm_poll_dm_io(struct dm_io *io, struct io_comp_batch *iob, + unsigned int flags) +{ + WARN_ON_ONCE(!dm_tio_is_normal(&io->tio)); + + /* don't poll if the mapped io is done */ + if (atomic_read(&io->io_count) > 1) + bio_poll(&io->tio.clone, iob, flags); + + /* bio_poll holds the last reference */ + return atomic_read(&io->io_count) == 1; +} + +static int dm_poll_bio(struct bio *bio, struct io_comp_batch *iob, + unsigned int flags) +{ + struct hlist_head *head = dm_get_bio_hlist_head(bio); + struct hlist_head tmp = HLIST_HEAD_INIT; + struct hlist_node *next; + struct dm_io *io; + + /* Only poll normal bio which was marked as REQ_DM_POLL_LIST */ + if (!(bio->bi_opf & REQ_DM_POLL_LIST)) + return 0; + + WARN_ON_ONCE(hlist_empty(head)); + + hlist_move_list(head, &tmp); + + /* + * Restore .bi_private before possibly completing dm_io. + * + * bio_poll() is only possible once @bio has been completely + * submitted via submit_bio_noacct()'s depth-first submission. + * So there is no dm_queue_poll_io() race associated with + * clearing REQ_DM_POLL_LIST here. + */ + bio->bi_opf &= ~REQ_DM_POLL_LIST; + bio->bi_private = hlist_entry(tmp.first, struct dm_io, node)->data; + + hlist_for_each_entry_safe(io, next, &tmp, node) { + if (dm_poll_dm_io(io, iob, flags)) { + hlist_del_init(&io->node); + /* + * clone_endio() has already occurred, so passing + * error as 0 here doesn't override io->status + */ + dm_io_dec_pending(io, 0); + } + } + + /* Not done? */ + if (!hlist_empty(&tmp)) { + bio->bi_opf |= REQ_DM_POLL_LIST; + /* Reset bio->bi_private to dm_io list head */ + hlist_move_list(&tmp, head); + return 0; + } + return 1; +} + /*----------------------------------------------------------------- * An IDR is used to keep track of allocated minor numbers. *---------------------------------------------------------------*/ @@ -1607,6 +1779,7 @@ static void cleanup_mapped_device(struct mapped_device *md) md->dax_dev = NULL; } + dm_cleanup_zoned_dev(md); if (md->disk) { spin_lock(&_minor_lock); md->disk->private_data = NULL; @@ -1619,6 +1792,11 @@ static void cleanup_mapped_device(struct mapped_device *md) blk_cleanup_disk(md->disk); } + if (md->pending_io) { + free_percpu(md->pending_io); + md->pending_io = NULL; + } + cleanup_srcu_struct(&md->io_barrier); mutex_destroy(&md->suspend_lock); @@ -1627,7 +1805,6 @@ static void cleanup_mapped_device(struct mapped_device *md) mutex_destroy(&md->swap_bios_lock); dm_mq_cleanup_mapped_device(md); - dm_cleanup_zoned_dev(md); } /* @@ -1721,6 +1898,10 @@ static struct mapped_device *alloc_dev(int minor) if (!md->wq) goto bad; + md->pending_io = alloc_percpu(unsigned long); + if (!md->pending_io) + goto bad; + dm_stats_init(&md->stats); /* Populate the mapping, nobody knows we exist yet */ @@ -1830,8 +2011,6 @@ static struct dm_table *__bind(struct mapped_device *md, struct dm_table *t, struct queue_limits *limits) { struct dm_table *old_map; - struct request_queue *q = md->queue; - bool request_based = dm_table_request_based(t); sector_t size; int ret; @@ -1852,7 +2031,7 @@ static struct dm_table *__bind(struct mapped_device *md, struct dm_table *t, dm_table_event_callback(t, event_callback, md); - if (request_based) { + if (dm_table_request_based(t)) { /* * Leverage the fact that request-based DM targets are * immutable singletons - used to optimize dm_mq_queue_rq. @@ -1866,7 +2045,7 @@ static struct dm_table *__bind(struct mapped_device *md, struct dm_table *t, goto out; } - ret = dm_table_set_restrictions(t, q, limits); + ret = dm_table_set_restrictions(t, md->queue, limits); if (ret) { old_map = ERR_PTR(ret); goto out; @@ -1878,7 +2057,6 @@ static struct dm_table *__bind(struct mapped_device *md, struct dm_table *t, if (old_map) dm_sync_table(md); - out: return old_map; } @@ -2128,16 +2306,13 @@ void dm_put(struct mapped_device *md) } EXPORT_SYMBOL_GPL(dm_put); -static bool md_in_flight_bios(struct mapped_device *md) +static bool dm_in_flight_bios(struct mapped_device *md) { int cpu; - struct block_device *part = dm_disk(md)->part0; - long sum = 0; + unsigned long sum = 0; - for_each_possible_cpu(cpu) { - sum += part_stat_local_read_cpu(part, in_flight[0], cpu); - sum += part_stat_local_read_cpu(part, in_flight[1], cpu); - } + for_each_possible_cpu(cpu) + sum += *per_cpu_ptr(md->pending_io, cpu); return sum != 0; } @@ -2150,7 +2325,7 @@ static int dm_wait_for_bios_completion(struct mapped_device *md, unsigned int ta while (true) { prepare_to_wait(&md->wait, &wait, task_state); - if (!md_in_flight_bios(md)) + if (!dm_in_flight_bios(md)) break; if (signal_pending_state(task_state, current)) { @@ -2162,6 +2337,8 @@ static int dm_wait_for_bios_completion(struct mapped_device *md, unsigned int ta } finish_wait(&md->wait, &wait); + smp_rmb(); + return r; } @@ -2333,11 +2510,11 @@ static int __dm_suspend(struct mapped_device *md, struct dm_table *map, /* * Here we must make sure that no processes are submitting requests * to target drivers i.e. no one may be executing - * __split_and_process_bio from dm_submit_bio. + * dm_split_and_process_bio from dm_submit_bio. * - * To get all processes out of __split_and_process_bio in dm_submit_bio, + * To get all processes out of dm_split_and_process_bio in dm_submit_bio, * we take the write lock. To prevent any process from reentering - * __split_and_process_bio from dm_submit_bio and quiesce the thread + * dm_split_and_process_bio from dm_submit_bio and quiesce the thread * (dm_wq_work), we set DMF_BLOCK_IO_FOR_SUSPEND and call * flush_workqueue(md->wq). */ @@ -2945,6 +3122,7 @@ static const struct pr_ops dm_pr_ops = { static const struct block_device_operations dm_blk_dops = { .submit_bio = dm_submit_bio, + .poll_bio = dm_poll_bio, .open = dm_blk_open, .release = dm_blk_close, .ioctl = dm_blk_ioctl, diff --git a/drivers/md/md-faulty.c b/drivers/md/md-faulty.c index c0dc6f2ef4a3..50ad818978a4 100644 --- a/drivers/md/md-faulty.c +++ b/drivers/md/md-faulty.c @@ -205,9 +205,9 @@ static bool faulty_make_request(struct mddev *mddev, struct bio *bio) } } if (failit) { - struct bio *b = bio_clone_fast(bio, GFP_NOIO, &mddev->bio_set); + struct bio *b = bio_alloc_clone(conf->rdev->bdev, bio, GFP_NOIO, + &mddev->bio_set); - bio_set_dev(b, conf->rdev->bdev); b->bi_private = bio; b->bi_end_io = faulty_fail; bio = b; diff --git a/drivers/md/md-linear.c b/drivers/md/md-linear.c index 1ff51647a682..0f55b079371b 100644 --- a/drivers/md/md-linear.c +++ b/drivers/md/md-linear.c @@ -259,7 +259,6 @@ static bool linear_make_request(struct mddev *mddev, struct bio *bio) if (mddev->gendisk) trace_block_bio_remap(bio, disk_devt(mddev->gendisk), bio_sector); - mddev_check_writesame(mddev, bio); mddev_check_write_zeroes(mddev, bio); submit_bio_noacct(bio); } diff --git a/drivers/md/md-multipath.c b/drivers/md/md-multipath.c index e7d6486f090f..1c6dbf92c136 100644 --- a/drivers/md/md-multipath.c +++ b/drivers/md/md-multipath.c @@ -121,15 +121,12 @@ static bool multipath_make_request(struct mddev *mddev, struct bio * bio) } multipath = conf->multipaths + mp_bh->path; - bio_init(&mp_bh->bio, NULL, 0); - __bio_clone_fast(&mp_bh->bio, bio); + bio_init_clone(multipath->rdev->bdev, &mp_bh->bio, bio, GFP_NOIO); mp_bh->bio.bi_iter.bi_sector += multipath->rdev->data_offset; - bio_set_dev(&mp_bh->bio, multipath->rdev->bdev); mp_bh->bio.bi_opf |= REQ_FAILFAST_TRANSPORT; mp_bh->bio.bi_end_io = multipath_end_request; mp_bh->bio.bi_private = mp_bh; - mddev_check_writesame(mddev, &mp_bh->bio); mddev_check_write_zeroes(mddev, &mp_bh->bio); submit_bio_noacct(&mp_bh->bio); return true; @@ -299,7 +296,6 @@ static void multipathd(struct md_thread *thread) md_check_recovery(mddev); for (;;) { - char b[BDEVNAME_SIZE]; spin_lock_irqsave(&conf->device_lock, flags); if (list_empty(head)) break; @@ -311,13 +307,13 @@ static void multipathd(struct md_thread *thread) bio->bi_iter.bi_sector = mp_bh->master_bio->bi_iter.bi_sector; if ((mp_bh->path = multipath_map (conf))<0) { - pr_err("multipath: %s: unrecoverable IO read error for block %llu\n", - bio_devname(bio, b), + pr_err("multipath: %pg: unrecoverable IO read error for block %llu\n", + bio->bi_bdev, (unsigned long long)bio->bi_iter.bi_sector); multipath_end_bh_io(mp_bh, BLK_STS_IOERR); } else { - pr_err("multipath: %s: redirecting sector %llu to another IO path\n", - bio_devname(bio, b), + pr_err("multipath: %pg: redirecting sector %llu to another IO path\n", + bio->bi_bdev, (unsigned long long)bio->bi_iter.bi_sector); *bio = *(mp_bh->master_bio); bio->bi_iter.bi_sector += diff --git a/drivers/md/md.c b/drivers/md/md.c index 4d38bd7dadd6..309b3af906ad 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -562,11 +562,11 @@ static void submit_flushes(struct work_struct *ws) atomic_inc(&rdev->nr_pending); atomic_inc(&rdev->nr_pending); rcu_read_unlock(); - bi = bio_alloc_bioset(GFP_NOIO, 0, &mddev->bio_set); + bi = bio_alloc_bioset(rdev->bdev, 0, + REQ_OP_WRITE | REQ_PREFLUSH, + GFP_NOIO, &mddev->bio_set); bi->bi_end_io = md_end_flush; bi->bi_private = rdev; - bio_set_dev(bi, rdev->bdev); - bi->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH; atomic_inc(&mddev->flush_pending); submit_bio(bi); rcu_read_lock(); @@ -955,7 +955,6 @@ void md_super_write(struct mddev *mddev, struct md_rdev *rdev, * If an error occurred, call md_error */ struct bio *bio; - int ff = 0; if (!page) return; @@ -963,11 +962,13 @@ void md_super_write(struct mddev *mddev, struct md_rdev *rdev, if (test_bit(Faulty, &rdev->flags)) return; - bio = bio_alloc_bioset(GFP_NOIO, 1, &mddev->sync_set); + bio = bio_alloc_bioset(rdev->meta_bdev ? rdev->meta_bdev : rdev->bdev, + 1, + REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH | REQ_FUA, + GFP_NOIO, &mddev->sync_set); atomic_inc(&rdev->nr_pending); - bio_set_dev(bio, rdev->meta_bdev ? rdev->meta_bdev : rdev->bdev); bio->bi_iter.bi_sector = sector; bio_add_page(bio, page, size, 0); bio->bi_private = rdev; @@ -976,8 +977,7 @@ void md_super_write(struct mddev *mddev, struct md_rdev *rdev, if (test_bit(MD_FAILFAST_SUPPORTED, &mddev->flags) && test_bit(FailFast, &rdev->flags) && !test_bit(LastDev, &rdev->flags)) - ff = MD_FAILFAST; - bio->bi_opf = REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH | REQ_FUA | ff; + bio->bi_opf |= MD_FAILFAST; atomic_inc(&mddev->pending_writes); submit_bio(bio); @@ -998,13 +998,11 @@ int sync_page_io(struct md_rdev *rdev, sector_t sector, int size, struct bio bio; struct bio_vec bvec; - bio_init(&bio, &bvec, 1); - if (metadata_op && rdev->meta_bdev) - bio_set_dev(&bio, rdev->meta_bdev); + bio_init(&bio, rdev->meta_bdev, &bvec, 1, op | op_flags); else - bio_set_dev(&bio, rdev->bdev); - bio.bi_opf = op | op_flags; + bio_init(&bio, rdev->bdev, &bvec, 1, op | op_flags); + if (metadata_op) bio.bi_iter.bi_sector = sector + rdev->sb_start; else if (rdev->mddev->reshape_position != MaxSector && @@ -8636,13 +8634,14 @@ static void md_end_io_acct(struct bio *bio) */ void md_account_bio(struct mddev *mddev, struct bio **bio) { + struct block_device *bdev = (*bio)->bi_bdev; struct md_io_acct *md_io_acct; struct bio *clone; - if (!blk_queue_io_stat((*bio)->bi_bdev->bd_disk->queue)) + if (!blk_queue_io_stat(bdev->bd_disk->queue)) return; - clone = bio_clone_fast(*bio, GFP_NOIO, &mddev->io_acct_set); + clone = bio_alloc_clone(bdev, *bio, GFP_NOIO, &mddev->io_acct_set); md_io_acct = container_of(clone, struct md_io_acct, bio_clone); md_io_acct->orig_bio = *bio; md_io_acct->start_time = bio_start_io_acct(*bio); @@ -9583,7 +9582,7 @@ static int md_notify_reboot(struct notifier_block *this, * driver, we do want to have a safe RAID driver ... */ if (need_delay) - mdelay(1000*1); + msleep(1000); return NOTIFY_DONE; } diff --git a/drivers/md/md.h b/drivers/md/md.h index f1bf3625ef4c..6ac283864533 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -797,13 +797,6 @@ static inline void mddev_clear_unsupported_flags(struct mddev *mddev, mddev->flags &= ~unsupported_flags; } -static inline void mddev_check_writesame(struct mddev *mddev, struct bio *bio) -{ - if (bio_op(bio) == REQ_OP_WRITE_SAME && - !bio->bi_bdev->bd_disk->queue->limits.max_write_same_sectors) - mddev->queue->limits.max_write_same_sectors = 0; -} - static inline void mddev_check_write_zeroes(struct mddev *mddev, struct bio *bio) { if (bio_op(bio) == REQ_OP_WRITE_ZEROES && diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index b59a77b31b90..b21e101183f4 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -402,7 +402,6 @@ static int raid0_run(struct mddev *mddev) bool discard_supported = false; blk_queue_max_hw_sectors(mddev->queue, mddev->chunk_sectors); - blk_queue_max_write_same_sectors(mddev->queue, mddev->chunk_sectors); blk_queue_max_write_zeroes_sectors(mddev->queue, mddev->chunk_sectors); blk_queue_max_discard_sectors(mddev->queue, UINT_MAX); @@ -594,7 +593,6 @@ static bool raid0_make_request(struct mddev *mddev, struct bio *bio) if (mddev->gendisk) trace_block_bio_remap(bio, disk_devt(mddev->gendisk), bio_sector); - mddev_check_writesame(mddev, bio); mddev_check_write_zeroes(mddev, bio); submit_bio_noacct(bio); return true; diff --git a/drivers/md/raid1-10.c b/drivers/md/raid1-10.c index 83f9a4f3d82e..e61f6cad4e08 100644 --- a/drivers/md/raid1-10.c +++ b/drivers/md/raid1-10.c @@ -28,6 +28,11 @@ struct resync_pages { struct page *pages[RESYNC_PAGES]; }; +struct raid1_plug_cb { + struct blk_plug_cb cb; + struct bio_list pending; +}; + static void rbio_pool_free(void *rbio, void *data) { kfree(rbio); diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index e2d8acb1e988..99d5464a51f8 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -824,7 +824,6 @@ static void flush_pending_writes(struct r1conf *conf) struct bio *bio; bio = bio_list_get(&conf->pending_bio_list); - conf->pending_count = 0; spin_unlock_irq(&conf->device_lock); /* @@ -1126,7 +1125,8 @@ static void alloc_behind_master_bio(struct r1bio *r1_bio, int i = 0; struct bio *behind_bio = NULL; - behind_bio = bio_alloc_bioset(GFP_NOIO, vcnt, &r1_bio->mddev->bio_set); + behind_bio = bio_alloc_bioset(NULL, vcnt, 0, GFP_NOIO, + &r1_bio->mddev->bio_set); if (!behind_bio) return; @@ -1136,8 +1136,6 @@ static void alloc_behind_master_bio(struct r1bio *r1_bio, goto skip_copy; } - behind_bio->bi_write_hint = bio->bi_write_hint; - while (i < vcnt && size) { struct page *page; int len = min_t(int, PAGE_SIZE, size); @@ -1166,12 +1164,6 @@ free_pages: bio_put(behind_bio); } -struct raid1_plug_cb { - struct blk_plug_cb cb; - struct bio_list pending; - int pending_cnt; -}; - static void raid1_unplug(struct blk_plug_cb *cb, bool from_schedule) { struct raid1_plug_cb *plug = container_of(cb, struct raid1_plug_cb, @@ -1183,7 +1175,6 @@ static void raid1_unplug(struct blk_plug_cb *cb, bool from_schedule) if (from_schedule || current->bio_list) { spin_lock_irq(&conf->device_lock); bio_list_merge(&conf->pending_bio_list, &plug->pending); - conf->pending_count += plug->pending_cnt; spin_unlock_irq(&conf->device_lock); wake_up(&conf->wait_barrier); md_wakeup_thread(mddev->thread); @@ -1319,13 +1310,13 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio, if (!r1bio_existed && blk_queue_io_stat(bio->bi_bdev->bd_disk->queue)) r1_bio->start_time = bio_start_io_acct(bio); - read_bio = bio_clone_fast(bio, gfp, &mddev->bio_set); + read_bio = bio_alloc_clone(mirror->rdev->bdev, bio, gfp, + &mddev->bio_set); r1_bio->bios[rdisk] = read_bio; read_bio->bi_iter.bi_sector = r1_bio->sector + mirror->rdev->data_offset; - bio_set_dev(read_bio, mirror->rdev->bdev); read_bio->bi_end_io = raid1_end_read_request; bio_set_op_attrs(read_bio, op, do_sync); if (test_bit(FailFast, &mirror->rdev->flags) && @@ -1545,24 +1536,25 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio, first_clone = 0; } - if (r1_bio->behind_master_bio) - mbio = bio_clone_fast(r1_bio->behind_master_bio, - GFP_NOIO, &mddev->bio_set); - else - mbio = bio_clone_fast(bio, GFP_NOIO, &mddev->bio_set); - if (r1_bio->behind_master_bio) { + mbio = bio_alloc_clone(rdev->bdev, + r1_bio->behind_master_bio, + GFP_NOIO, &mddev->bio_set); if (test_bit(CollisionCheck, &rdev->flags)) wait_for_serialization(rdev, r1_bio); if (test_bit(WriteMostly, &rdev->flags)) atomic_inc(&r1_bio->behind_remaining); - } else if (mddev->serialize_policy) - wait_for_serialization(rdev, r1_bio); + } else { + mbio = bio_alloc_clone(rdev->bdev, bio, GFP_NOIO, + &mddev->bio_set); + + if (mddev->serialize_policy) + wait_for_serialization(rdev, r1_bio); + } r1_bio->bios[i] = mbio; mbio->bi_iter.bi_sector = (r1_bio->sector + rdev->data_offset); - bio_set_dev(mbio, rdev->bdev); mbio->bi_end_io = raid1_end_write_request; mbio->bi_opf = bio_op(bio) | (bio->bi_opf & (REQ_SYNC | REQ_FUA)); if (test_bit(FailFast, &rdev->flags) && @@ -1586,11 +1578,9 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio, plug = NULL; if (plug) { bio_list_add(&plug->pending, mbio); - plug->pending_cnt++; } else { spin_lock_irqsave(&conf->device_lock, flags); bio_list_add(&conf->pending_bio_list, mbio); - conf->pending_count++; spin_unlock_irqrestore(&conf->device_lock, flags); md_wakeup_thread(mddev->thread); } @@ -2070,15 +2060,14 @@ static int fix_sync_read_error(struct r1bio *r1_bio) } while (!success && d != r1_bio->read_disk); if (!success) { - char b[BDEVNAME_SIZE]; int abort = 0; /* Cannot read from anywhere, this block is lost. * Record a bad block on each device. If that doesn't * work just disable and interrupt the recovery. * Don't fail devices as that won't really help. */ - pr_crit_ratelimited("md/raid1:%s: %s: unrecoverable I/O read error for block %llu\n", - mdname(mddev), bio_devname(bio, b), + pr_crit_ratelimited("md/raid1:%s: %pg: unrecoverable I/O read error for block %llu\n", + mdname(mddev), bio->bi_bdev, (unsigned long long)r1_bio->sector); for (d = 0; d < conf->raid_disks * 2; d++) { rdev = conf->mirrors[d].rdev; @@ -2165,11 +2154,10 @@ static void process_checks(struct r1bio *r1_bio) continue; /* fixup the bio for reuse, but preserve errno */ status = b->bi_status; - bio_reset(b); + bio_reset(b, conf->mirrors[i].rdev->bdev, REQ_OP_READ); b->bi_status = status; b->bi_iter.bi_sector = r1_bio->sector + conf->mirrors[i].rdev->data_offset; - bio_set_dev(b, conf->mirrors[i].rdev->bdev); b->bi_end_io = end_sync_read; rp->raid_bio = r1_bio; b->bi_private = rp; @@ -2416,12 +2404,12 @@ static int narrow_write_error(struct r1bio *r1_bio, int i) /* Write at 'sector' for 'sectors'*/ if (test_bit(R1BIO_BehindIO, &r1_bio->state)) { - wbio = bio_clone_fast(r1_bio->behind_master_bio, - GFP_NOIO, - &mddev->bio_set); + wbio = bio_alloc_clone(rdev->bdev, + r1_bio->behind_master_bio, + GFP_NOIO, &mddev->bio_set); } else { - wbio = bio_clone_fast(r1_bio->master_bio, GFP_NOIO, - &mddev->bio_set); + wbio = bio_alloc_clone(rdev->bdev, r1_bio->master_bio, + GFP_NOIO, &mddev->bio_set); } bio_set_op_attrs(wbio, REQ_OP_WRITE, 0); @@ -2430,7 +2418,6 @@ static int narrow_write_error(struct r1bio *r1_bio, int i) bio_trim(wbio, sector - r1_bio->sector, sectors); wbio->bi_iter.bi_sector += rdev->data_offset; - bio_set_dev(wbio, rdev->bdev); if (submit_bio_wait(wbio) < 0) /* failure! */ @@ -2650,7 +2637,7 @@ static struct r1bio *raid1_alloc_init_r1buf(struct r1conf *conf) for (i = conf->poolinfo->raid_disks; i--; ) { bio = r1bio->bios[i]; rps = bio->bi_private; - bio_reset(bio); + bio_reset(bio, NULL, 0); bio->bi_private = rps; } r1bio->master_bio = NULL; @@ -3058,7 +3045,6 @@ static struct r1conf *setup_conf(struct mddev *mddev) init_waitqueue_head(&conf->wait_barrier); bio_list_init(&conf->pending_bio_list); - conf->pending_count = 0; conf->recovery_disabled = mddev->recovery_disabled - 1; err = -EIO; @@ -3147,10 +3133,8 @@ static int raid1_run(struct mddev *mddev) if (IS_ERR(conf)) return PTR_ERR(conf); - if (mddev->queue) { - blk_queue_max_write_same_sectors(mddev->queue, 0); + if (mddev->queue) blk_queue_max_write_zeroes_sectors(mddev->queue, 0); - } rdev_for_each(rdev, mddev) { if (!mddev->gendisk) diff --git a/drivers/md/raid1.h b/drivers/md/raid1.h index ccf10e59b116..ebb6788820e7 100644 --- a/drivers/md/raid1.h +++ b/drivers/md/raid1.h @@ -87,7 +87,6 @@ struct r1conf { /* queue pending writes to be submitted on unplug */ struct bio_list pending_bio_list; - int pending_count; /* for use when syncing mirrors: * We don't allow both normal IO and resync/recovery IO at diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 2b969f70a31f..dfe7d62d3fbd 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -861,7 +861,6 @@ static void flush_pending_writes(struct r10conf *conf) struct bio *bio; bio = bio_list_get(&conf->pending_bio_list); - conf->pending_count = 0; spin_unlock_irq(&conf->device_lock); /* @@ -1054,16 +1053,9 @@ static sector_t choose_data_offset(struct r10bio *r10_bio, return rdev->new_data_offset; } -struct raid10_plug_cb { - struct blk_plug_cb cb; - struct bio_list pending; - int pending_cnt; -}; - static void raid10_unplug(struct blk_plug_cb *cb, bool from_schedule) { - struct raid10_plug_cb *plug = container_of(cb, struct raid10_plug_cb, - cb); + struct raid1_plug_cb *plug = container_of(cb, struct raid1_plug_cb, cb); struct mddev *mddev = plug->cb.data; struct r10conf *conf = mddev->private; struct bio *bio; @@ -1071,7 +1063,6 @@ static void raid10_unplug(struct blk_plug_cb *cb, bool from_schedule) if (from_schedule || current->bio_list) { spin_lock_irq(&conf->device_lock); bio_list_merge(&conf->pending_bio_list, &plug->pending); - conf->pending_count += plug->pending_cnt; spin_unlock_irq(&conf->device_lock); wake_up(&conf->wait_barrier); md_wakeup_thread(mddev->thread); @@ -1208,14 +1199,13 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio, if (blk_queue_io_stat(bio->bi_bdev->bd_disk->queue)) r10_bio->start_time = bio_start_io_acct(bio); - read_bio = bio_clone_fast(bio, gfp, &mddev->bio_set); + read_bio = bio_alloc_clone(rdev->bdev, bio, gfp, &mddev->bio_set); r10_bio->devs[slot].bio = read_bio; r10_bio->devs[slot].rdev = rdev; read_bio->bi_iter.bi_sector = r10_bio->devs[slot].addr + choose_data_offset(r10_bio, rdev); - bio_set_dev(read_bio, rdev->bdev); read_bio->bi_end_io = raid10_end_read_request; bio_set_op_attrs(read_bio, op, do_sync); if (test_bit(FailFast, &rdev->flags) && @@ -1239,7 +1229,7 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio, const unsigned long do_fua = (bio->bi_opf & REQ_FUA); unsigned long flags; struct blk_plug_cb *cb; - struct raid10_plug_cb *plug = NULL; + struct raid1_plug_cb *plug = NULL; struct r10conf *conf = mddev->private; struct md_rdev *rdev; int devnum = r10_bio->devs[n_copy].devnum; @@ -1255,7 +1245,7 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio, } else rdev = conf->mirrors[devnum].rdev; - mbio = bio_clone_fast(bio, GFP_NOIO, &mddev->bio_set); + mbio = bio_alloc_clone(rdev->bdev, bio, GFP_NOIO, &mddev->bio_set); if (replacement) r10_bio->devs[n_copy].repl_bio = mbio; else @@ -1263,7 +1253,6 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio, mbio->bi_iter.bi_sector = (r10_bio->devs[n_copy].addr + choose_data_offset(r10_bio, rdev)); - bio_set_dev(mbio, rdev->bdev); mbio->bi_end_io = raid10_end_write_request; bio_set_op_attrs(mbio, op, do_sync | do_fua); if (!replacement && test_bit(FailFast, @@ -1282,16 +1271,14 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio, cb = blk_check_plugged(raid10_unplug, mddev, sizeof(*plug)); if (cb) - plug = container_of(cb, struct raid10_plug_cb, cb); + plug = container_of(cb, struct raid1_plug_cb, cb); else plug = NULL; if (plug) { bio_list_add(&plug->pending, mbio); - plug->pending_cnt++; } else { spin_lock_irqsave(&conf->device_lock, flags); bio_list_add(&conf->pending_bio_list, mbio); - conf->pending_count++; spin_unlock_irqrestore(&conf->device_lock, flags); md_wakeup_thread(mddev->thread); } @@ -1812,7 +1799,8 @@ retry_discard: */ if (r10_bio->devs[disk].bio) { struct md_rdev *rdev = conf->mirrors[disk].rdev; - mbio = bio_clone_fast(bio, GFP_NOIO, &mddev->bio_set); + mbio = bio_alloc_clone(bio->bi_bdev, bio, GFP_NOIO, + &mddev->bio_set); mbio->bi_end_io = raid10_end_discard_request; mbio->bi_private = r10_bio; r10_bio->devs[disk].bio = mbio; @@ -1825,7 +1813,8 @@ retry_discard: } if (r10_bio->devs[disk].repl_bio) { struct md_rdev *rrdev = conf->mirrors[disk].replacement; - rbio = bio_clone_fast(bio, GFP_NOIO, &mddev->bio_set); + rbio = bio_alloc_clone(bio->bi_bdev, bio, GFP_NOIO, + &mddev->bio_set); rbio->bi_end_io = raid10_end_discard_request; rbio->bi_private = r10_bio; r10_bio->devs[disk].repl_bio = rbio; @@ -2422,7 +2411,7 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio) * bi_vecs, as the read request might have corrupted these */ rp = get_resync_pages(tbio); - bio_reset(tbio); + bio_reset(tbio, conf->mirrors[d].rdev->bdev, REQ_OP_WRITE); md_bio_reset_resync_pages(tbio, rp, fbio->bi_iter.bi_size); @@ -2430,7 +2419,6 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio) tbio->bi_private = rp; tbio->bi_iter.bi_sector = r10_bio->devs[i].addr; tbio->bi_end_io = end_sync_write; - bio_set_op_attrs(tbio, REQ_OP_WRITE, 0); bio_copy_data(tbio, fbio); @@ -2441,7 +2429,6 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio) if (test_bit(FailFast, &conf->mirrors[d].rdev->flags)) tbio->bi_opf |= MD_FAILFAST; tbio->bi_iter.bi_sector += conf->mirrors[d].rdev->data_offset; - bio_set_dev(tbio, conf->mirrors[d].rdev->bdev); submit_bio_noacct(tbio); } @@ -2894,12 +2881,12 @@ static int narrow_write_error(struct r10bio *r10_bio, int i) if (sectors > sect_to_write) sectors = sect_to_write; /* Write at 'sector' for 'sectors' */ - wbio = bio_clone_fast(bio, GFP_NOIO, &mddev->bio_set); + wbio = bio_alloc_clone(rdev->bdev, bio, GFP_NOIO, + &mddev->bio_set); bio_trim(wbio, sector - bio->bi_iter.bi_sector, sectors); wsector = r10_bio->devs[i].addr + (sector - r10_bio->sector); wbio->bi_iter.bi_sector = wsector + choose_data_offset(r10_bio, rdev); - bio_set_dev(wbio, rdev->bdev); bio_set_op_attrs(wbio, REQ_OP_WRITE, 0); if (submit_bio_wait(wbio) < 0) @@ -3160,12 +3147,12 @@ static struct r10bio *raid10_alloc_init_r10buf(struct r10conf *conf) for (i = 0; i < nalloc; i++) { bio = r10bio->devs[i].bio; rp = bio->bi_private; - bio_reset(bio); + bio_reset(bio, NULL, 0); bio->bi_private = rp; bio = r10bio->devs[i].repl_bio; if (bio) { rp = bio->bi_private; - bio_reset(bio); + bio_reset(bio, NULL, 0); bio->bi_private = rp; } } @@ -4115,7 +4102,6 @@ static int raid10_run(struct mddev *mddev) if (mddev->queue) { blk_queue_max_discard_sectors(mddev->queue, UINT_MAX); - blk_queue_max_write_same_sectors(mddev->queue, 0); blk_queue_max_write_zeroes_sectors(mddev->queue, 0); blk_queue_io_min(mddev->queue, mddev->chunk_sectors << 9); raid10_set_io_opt(conf); @@ -4892,14 +4878,12 @@ read_more: return sectors_done; } - read_bio = bio_alloc_bioset(GFP_KERNEL, RESYNC_PAGES, &mddev->bio_set); - - bio_set_dev(read_bio, rdev->bdev); + read_bio = bio_alloc_bioset(rdev->bdev, RESYNC_PAGES, REQ_OP_READ, + GFP_KERNEL, &mddev->bio_set); read_bio->bi_iter.bi_sector = (r10_bio->devs[r10_bio->read_slot].addr + rdev->data_offset); read_bio->bi_private = r10_bio; read_bio->bi_end_io = end_reshape_read; - bio_set_op_attrs(read_bio, REQ_OP_READ, 0); r10_bio->master_bio = read_bio; r10_bio->read_slot = r10_bio->devs[r10_bio->read_slot].devnum; diff --git a/drivers/md/raid10.h b/drivers/md/raid10.h index c34bb196790e..5c0804d8bb1f 100644 --- a/drivers/md/raid10.h +++ b/drivers/md/raid10.h @@ -75,7 +75,6 @@ struct r10conf { /* queue pending writes and submit them on unplug */ struct bio_list pending_bio_list; - int pending_count; spinlock_t resync_lock; atomic_t nr_pending; diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c index 0b5dcaabbc15..a7d50ff9020a 100644 --- a/drivers/md/raid5-cache.c +++ b/drivers/md/raid5-cache.c @@ -735,10 +735,9 @@ static void r5l_submit_current_io(struct r5l_log *log) static struct bio *r5l_bio_alloc(struct r5l_log *log) { - struct bio *bio = bio_alloc_bioset(GFP_NOIO, BIO_MAX_VECS, &log->bs); + struct bio *bio = bio_alloc_bioset(log->rdev->bdev, BIO_MAX_VECS, + REQ_OP_WRITE, GFP_NOIO, &log->bs); - bio_set_op_attrs(bio, REQ_OP_WRITE, 0); - bio_set_dev(bio, log->rdev->bdev); bio->bi_iter.bi_sector = log->rdev->data_offset + log->log_start; return bio; @@ -1267,6 +1266,8 @@ static void r5l_log_flush_endio(struct bio *bio) r5l_io_run_stripes(io); list_splice_tail_init(&log->flushing_ios, &log->finished_ios); spin_unlock_irqrestore(&log->io_list_lock, flags); + + bio_uninit(bio); } /* @@ -1302,10 +1303,9 @@ void r5l_flush_stripe_to_raid(struct r5l_log *log) if (!do_flush) return; - bio_reset(&log->flush_bio); - bio_set_dev(&log->flush_bio, log->rdev->bdev); + bio_init(&log->flush_bio, log->rdev->bdev, NULL, 0, + REQ_OP_WRITE | REQ_PREFLUSH); log->flush_bio.bi_end_io = r5l_log_flush_endio; - log->flush_bio.bi_opf = REQ_OP_WRITE | REQ_PREFLUSH; submit_bio(&log->flush_bio); } @@ -1623,10 +1623,10 @@ struct r5l_recovery_ctx { * just copy data from the pool. */ struct page *ra_pool[R5L_RECOVERY_PAGE_POOL_SIZE]; + struct bio_vec ra_bvec[R5L_RECOVERY_PAGE_POOL_SIZE]; sector_t pool_offset; /* offset of first page in the pool */ int total_pages; /* total allocated pages */ int valid_pages; /* pages with valid data */ - struct bio *ra_bio; /* bio to do the read ahead */ }; static int r5l_recovery_allocate_ra_pool(struct r5l_log *log, @@ -1634,10 +1634,6 @@ static int r5l_recovery_allocate_ra_pool(struct r5l_log *log, { struct page *page; - ctx->ra_bio = bio_alloc_bioset(GFP_KERNEL, BIO_MAX_VECS, &log->bs); - if (!ctx->ra_bio) - return -ENOMEM; - ctx->valid_pages = 0; ctx->total_pages = 0; while (ctx->total_pages < R5L_RECOVERY_PAGE_POOL_SIZE) { @@ -1649,10 +1645,8 @@ static int r5l_recovery_allocate_ra_pool(struct r5l_log *log, ctx->total_pages += 1; } - if (ctx->total_pages == 0) { - bio_put(ctx->ra_bio); + if (ctx->total_pages == 0) return -ENOMEM; - } ctx->pool_offset = 0; return 0; @@ -1665,7 +1659,6 @@ static void r5l_recovery_free_ra_pool(struct r5l_log *log, for (i = 0; i < ctx->total_pages; ++i) put_page(ctx->ra_pool[i]); - bio_put(ctx->ra_bio); } /* @@ -1678,17 +1671,19 @@ static int r5l_recovery_fetch_ra_pool(struct r5l_log *log, struct r5l_recovery_ctx *ctx, sector_t offset) { - bio_reset(ctx->ra_bio); - bio_set_dev(ctx->ra_bio, log->rdev->bdev); - bio_set_op_attrs(ctx->ra_bio, REQ_OP_READ, 0); - ctx->ra_bio->bi_iter.bi_sector = log->rdev->data_offset + offset; + struct bio bio; + int ret; + + bio_init(&bio, log->rdev->bdev, ctx->ra_bvec, + R5L_RECOVERY_PAGE_POOL_SIZE, REQ_OP_READ); + bio.bi_iter.bi_sector = log->rdev->data_offset + offset; ctx->valid_pages = 0; ctx->pool_offset = offset; while (ctx->valid_pages < ctx->total_pages) { - bio_add_page(ctx->ra_bio, - ctx->ra_pool[ctx->valid_pages], PAGE_SIZE, 0); + __bio_add_page(&bio, ctx->ra_pool[ctx->valid_pages], PAGE_SIZE, + 0); ctx->valid_pages += 1; offset = r5l_ring_add(log, offset, BLOCK_SECTORS); @@ -1697,7 +1692,9 @@ static int r5l_recovery_fetch_ra_pool(struct r5l_log *log, break; } - return submit_bio_wait(ctx->ra_bio); + ret = submit_bio_wait(&bio); + bio_uninit(&bio); + return ret; } /* @@ -3108,7 +3105,6 @@ int r5l_init_log(struct r5conf *conf, struct md_rdev *rdev) INIT_LIST_HEAD(&log->io_end_ios); INIT_LIST_HEAD(&log->flushing_ios); INIT_LIST_HEAD(&log->finished_ios); - bio_init(&log->flush_bio, NULL, 0); log->io_kc = KMEM_CACHE(r5l_io_unit, 0); if (!log->io_kc) diff --git a/drivers/md/raid5-ppl.c b/drivers/md/raid5-ppl.c index 4ab417915d7f..d3962d92df18 100644 --- a/drivers/md/raid5-ppl.c +++ b/drivers/md/raid5-ppl.c @@ -250,7 +250,8 @@ static struct ppl_io_unit *ppl_new_iounit(struct ppl_log *log, INIT_LIST_HEAD(&io->stripe_list); atomic_set(&io->pending_stripes, 0); atomic_set(&io->pending_flushes, 0); - bio_init(&io->bio, io->biovec, PPL_IO_INLINE_BVECS); + bio_init(&io->bio, log->rdev->bdev, io->biovec, PPL_IO_INLINE_BVECS, + REQ_OP_WRITE | REQ_FUA); pplhdr = page_address(io->header_page); clear_page(pplhdr); @@ -416,12 +417,10 @@ static void ppl_log_endio(struct bio *bio) static void ppl_submit_iounit_bio(struct ppl_io_unit *io, struct bio *bio) { - char b[BDEVNAME_SIZE]; - - pr_debug("%s: seq: %llu size: %u sector: %llu dev: %s\n", + pr_debug("%s: seq: %llu size: %u sector: %llu dev: %pg\n", __func__, io->seq, bio->bi_iter.bi_size, (unsigned long long)bio->bi_iter.bi_sector, - bio_devname(bio, b)); + bio->bi_bdev); submit_bio(bio); } @@ -465,11 +464,8 @@ static void ppl_submit_iounit(struct ppl_io_unit *io) bio->bi_end_io = ppl_log_endio; - bio->bi_opf = REQ_OP_WRITE | REQ_FUA; - bio_set_dev(bio, log->rdev->bdev); bio->bi_iter.bi_sector = log->next_io_sector; bio_add_page(bio, io->header_page, PAGE_SIZE, 0); - bio->bi_write_hint = ppl_conf->write_hint; pr_debug("%s: log->current_io_sector: %llu\n", __func__, (unsigned long long)log->next_io_sector); @@ -496,11 +492,9 @@ static void ppl_submit_iounit(struct ppl_io_unit *io) if (!bio_add_page(bio, sh->ppl_page, PAGE_SIZE, 0)) { struct bio *prev = bio; - bio = bio_alloc_bioset(GFP_NOIO, BIO_MAX_VECS, + bio = bio_alloc_bioset(prev->bi_bdev, BIO_MAX_VECS, + prev->bi_opf, GFP_NOIO, &ppl_conf->bs); - bio->bi_opf = prev->bi_opf; - bio->bi_write_hint = prev->bi_write_hint; - bio_copy_dev(bio, prev); bio->bi_iter.bi_sector = bio_end_sector(prev); bio_add_page(bio, sh->ppl_page, PAGE_SIZE, 0); @@ -590,9 +584,8 @@ static void ppl_flush_endio(struct bio *bio) struct ppl_log *log = io->log; struct ppl_conf *ppl_conf = log->ppl_conf; struct r5conf *conf = ppl_conf->mddev->private; - char b[BDEVNAME_SIZE]; - pr_debug("%s: dev: %s\n", __func__, bio_devname(bio, b)); + pr_debug("%s: dev: %pg\n", __func__, bio->bi_bdev); if (bio->bi_status) { struct md_rdev *rdev; @@ -635,16 +628,14 @@ static void ppl_do_flush(struct ppl_io_unit *io) if (bdev) { struct bio *bio; - char b[BDEVNAME_SIZE]; - bio = bio_alloc_bioset(GFP_NOIO, 0, &ppl_conf->flush_bs); - bio_set_dev(bio, bdev); + bio = bio_alloc_bioset(bdev, 0, GFP_NOIO, + REQ_OP_WRITE | REQ_PREFLUSH, + &ppl_conf->flush_bs); bio->bi_private = io; - bio->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH; bio->bi_end_io = ppl_flush_endio; - pr_debug("%s: dev: %s\n", __func__, - bio_devname(bio, b)); + pr_debug("%s: dev: %ps\n", __func__, bio->bi_bdev); submit_bio(bio); flushed_disks++; @@ -1403,7 +1394,6 @@ int ppl_init_log(struct r5conf *conf) atomic64_set(&ppl_conf->seq, 0); INIT_LIST_HEAD(&ppl_conf->no_mem_stripes); spin_lock_init(&ppl_conf->no_mem_stripes_lock); - ppl_conf->write_hint = RWH_WRITE_LIFE_NOT_SET; if (!mddev->external) { ppl_conf->signature = ~crc32c_le(~0, mddev->uuid, sizeof(mddev->uuid)); @@ -1502,25 +1492,13 @@ int ppl_modify_log(struct r5conf *conf, struct md_rdev *rdev, bool add) static ssize_t ppl_write_hint_show(struct mddev *mddev, char *buf) { - size_t ret = 0; - struct r5conf *conf; - struct ppl_conf *ppl_conf = NULL; - - spin_lock(&mddev->lock); - conf = mddev->private; - if (conf && raid5_has_ppl(conf)) - ppl_conf = conf->log_private; - ret = sprintf(buf, "%d\n", ppl_conf ? ppl_conf->write_hint : 0); - spin_unlock(&mddev->lock); - - return ret; + return sprintf(buf, "%d\n", 0); } static ssize_t ppl_write_hint_store(struct mddev *mddev, const char *page, size_t len) { struct r5conf *conf; - struct ppl_conf *ppl_conf; int err = 0; unsigned short new; @@ -1534,17 +1512,10 @@ ppl_write_hint_store(struct mddev *mddev, const char *page, size_t len) return err; conf = mddev->private; - if (!conf) { + if (!conf) err = -ENODEV; - } else if (raid5_has_ppl(conf)) { - ppl_conf = conf->log_private; - if (!ppl_conf) - err = -EINVAL; - else - ppl_conf->write_hint = new; - } else { + else if (!raid5_has_ppl(conf) || !conf->log_private) err = -EINVAL; - } mddev_unlock(mddev); diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index ffe720c73b0a..351d341a1ffa 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -1060,6 +1060,7 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s) int i, disks = sh->disks; struct stripe_head *head_sh = sh; struct bio_list pending_bios = BIO_EMPTY_LIST; + struct r5dev *dev; bool should_defer; might_sleep(); @@ -1094,8 +1095,9 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s) op_flags |= REQ_SYNC; again: - bi = &sh->dev[i].req; - rbi = &sh->dev[i].rreq; /* For writing to replacement */ + dev = &sh->dev[i]; + bi = &dev->req; + rbi = &dev->rreq; /* For writing to replacement */ rcu_read_lock(); rrdev = rcu_dereference(conf->disks[i].replacement); @@ -1171,8 +1173,7 @@ again: set_bit(STRIPE_IO_STARTED, &sh->state); - bio_set_dev(bi, rdev->bdev); - bio_set_op_attrs(bi, op, op_flags); + bio_init(bi, rdev->bdev, &dev->vec, 1, op | op_flags); bi->bi_end_io = op_is_write(op) ? raid5_end_write_request : raid5_end_read_request; @@ -1210,9 +1211,6 @@ again: bi->bi_io_vec[0].bv_len = RAID5_STRIPE_SIZE(conf); bi->bi_io_vec[0].bv_offset = sh->dev[i].offset; bi->bi_iter.bi_size = RAID5_STRIPE_SIZE(conf); - bi->bi_write_hint = sh->dev[i].write_hint; - if (!rrdev) - sh->dev[i].write_hint = RWH_WRITE_LIFE_NOT_SET; /* * If this is discard request, set bi_vcnt 0. We don't * want to confuse SCSI because SCSI will replace payload @@ -1238,8 +1236,7 @@ again: set_bit(STRIPE_IO_STARTED, &sh->state); - bio_set_dev(rbi, rrdev->bdev); - bio_set_op_attrs(rbi, op, op_flags); + bio_init(rbi, rrdev->bdev, &dev->rvec, 1, op | op_flags); BUG_ON(!op_is_write(op)); rbi->bi_end_io = raid5_end_write_request; rbi->bi_private = sh; @@ -1264,8 +1261,6 @@ again: rbi->bi_io_vec[0].bv_len = RAID5_STRIPE_SIZE(conf); rbi->bi_io_vec[0].bv_offset = sh->dev[i].offset; rbi->bi_iter.bi_size = RAID5_STRIPE_SIZE(conf); - rbi->bi_write_hint = sh->dev[i].write_hint; - sh->dev[i].write_hint = RWH_WRITE_LIFE_NOT_SET; /* * If this is discard request, set bi_vcnt 0. We don't * want to confuse SCSI because SCSI will replace payload @@ -2294,7 +2289,6 @@ static struct stripe_head *alloc_stripe(struct kmem_cache *sc, gfp_t gfp, int disks, struct r5conf *conf) { struct stripe_head *sh; - int i; sh = kmem_cache_zalloc(sc, gfp); if (sh) { @@ -2307,12 +2301,6 @@ static struct stripe_head *alloc_stripe(struct kmem_cache *sc, gfp_t gfp, atomic_set(&sh->count, 1); sh->raid_conf = conf; sh->log_start = MaxSector; - for (i = 0; i < disks; i++) { - struct r5dev *dev = &sh->dev[i]; - - bio_init(&dev->req, &dev->vec, 1); - bio_init(&dev->rreq, &dev->rvec, 1); - } if (raid5_has_ppl(conf)) { sh->ppl_page = alloc_page(gfp); @@ -2677,7 +2665,6 @@ static void raid5_end_read_request(struct bio * bi) (unsigned long long)sh->sector, i, atomic_read(&sh->count), bi->bi_status); if (i == disks) { - bio_reset(bi); BUG(); return; } @@ -2785,7 +2772,7 @@ static void raid5_end_read_request(struct bio * bi) } } rdev_dec_pending(rdev, conf->mddev); - bio_reset(bi); + bio_uninit(bi); clear_bit(R5_LOCKED, &sh->dev[i].flags); set_bit(STRIPE_HANDLE, &sh->state); raid5_release_stripe(sh); @@ -2823,7 +2810,6 @@ static void raid5_end_write_request(struct bio *bi) (unsigned long long)sh->sector, i, atomic_read(&sh->count), bi->bi_status); if (i == disks) { - bio_reset(bi); BUG(); return; } @@ -2860,7 +2846,7 @@ static void raid5_end_write_request(struct bio *bi) if (sh->batch_head && bi->bi_status && !replacement) set_bit(STRIPE_BATCH_ERR, &sh->batch_head->state); - bio_reset(bi); + bio_uninit(bi); if (!test_and_clear_bit(R5_DOUBLE_LOCKED, &sh->dev[i].flags)) clear_bit(R5_LOCKED, &sh->dev[i].flags); set_bit(STRIPE_HANDLE, &sh->state); @@ -3416,7 +3402,6 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, (unsigned long long)sh->sector); spin_lock_irq(&sh->stripe_lock); - sh->dev[dd_idx].write_hint = bi->bi_write_hint; /* Don't allow new IO added to stripes in batch list */ if (sh->batch_head) goto overlap; @@ -5438,14 +5423,14 @@ static int raid5_read_one_chunk(struct mddev *mddev, struct bio *raid_bio) return 0; } - align_bio = bio_clone_fast(raid_bio, GFP_NOIO, &mddev->io_acct_set); + align_bio = bio_alloc_clone(rdev->bdev, raid_bio, GFP_NOIO, + &mddev->io_acct_set); md_io_acct = container_of(align_bio, struct md_io_acct, bio_clone); raid_bio->bi_next = (void *)rdev; if (blk_queue_io_stat(raid_bio->bi_bdev->bd_disk->queue)) md_io_acct->start_time = bio_start_io_acct(raid_bio); md_io_acct->orig_bio = raid_bio; - bio_set_dev(align_bio, rdev->bdev); align_bio->bi_end_io = raid5_align_endio; align_bio->bi_private = md_io_acct; align_bio->bi_iter.bi_sector = sector; @@ -7767,7 +7752,6 @@ static int raid5_run(struct mddev *mddev) mddev->queue->limits.discard_alignment = stripe; mddev->queue->limits.discard_granularity = stripe; - blk_queue_max_write_same_sectors(mddev->queue, 0); blk_queue_max_write_zeroes_sectors(mddev->queue, 0); rdev_for_each(rdev, mddev) { |