diff options
Diffstat (limited to 'drivers/md/dm.c')
| -rw-r--r-- | drivers/md/dm.c | 1895 |
1 files changed, 1034 insertions, 861 deletions
diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 3167480b532..32b958dbc49 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -14,16 +14,26 @@ #include <linux/moduleparam.h> #include <linux/blkpg.h> #include <linux/bio.h> -#include <linux/buffer_head.h> #include <linux/mempool.h> #include <linux/slab.h> #include <linux/idr.h> #include <linux/hdreg.h> +#include <linux/delay.h> #include <trace/events/block.h> #define DM_MSG_PREFIX "core" +#ifdef CONFIG_PRINTK +/* + * ratelimit state to be used in DMXXX_LIMIT(). + */ +DEFINE_RATELIMIT_STATE(dm_ratelimit_state, + DEFAULT_RATELIMIT_INTERVAL, + DEFAULT_RATELIMIT_BURST); +EXPORT_SYMBOL(dm_ratelimit_state); +#endif + /* * Cookies are numeric values sent with CHANGE and REMOVE * uevents while resuming, removing or renaming the device. @@ -36,7 +46,16 @@ static const char *_name = DM_NAME; static unsigned int major = 0; static unsigned int _major = 0; +static DEFINE_IDR(_minor_idr); + static DEFINE_SPINLOCK(_minor_lock); + +static void do_deferred_remove(struct work_struct *w); + +static DECLARE_WORK(deferred_remove_work, do_deferred_remove); + +static struct workqueue_struct *deferred_remove_workqueue; + /* * For bio-based dm. * One of these is allocated per bio. @@ -48,17 +67,7 @@ struct dm_io { struct bio *bio; unsigned long start_time; spinlock_t endio_lock; -}; - -/* - * For bio-based dm. - * One of these is allocated per target within a bio. Hopefully - * this will be simplified out one day. - */ -struct dm_target_io { - struct dm_io *io; - struct dm_target *ti; - union map_info info; + struct dm_stats_aux stats_aux; }; /* @@ -74,21 +83,19 @@ struct dm_rq_target_io { }; /* - * For request-based dm. - * One of these is allocated per bio. + * For request-based dm - the bio clones we allocate are embedded in these + * structs. + * + * We allocate these with bio_alloc_bioset, using the front_pad parameter when + * the bioset is created - this means the bio has to come at the end of the + * struct. */ struct dm_rq_clone_bio_info { struct bio *orig; struct dm_rq_target_io *tio; + struct bio clone; }; -union map_info *dm_get_mapinfo(struct bio *bio) -{ - if (bio && bio->bi_private) - return &((struct dm_target_io *)bio->bi_private)->info; - return NULL; -} - union map_info *dm_get_rq_mapinfo(struct request *rq) { if (rq && rq->end_io_data) @@ -108,21 +115,42 @@ EXPORT_SYMBOL_GPL(dm_get_rq_mapinfo); #define DMF_FREEING 3 #define DMF_DELETING 4 #define DMF_NOFLUSH_SUSPENDING 5 -#define DMF_QUEUE_IO_TO_THREAD 6 +#define DMF_MERGE_IS_OPTIONAL 6 +#define DMF_DEFERRED_REMOVE 7 + +/* + * A dummy definition to make RCU happy. + * struct dm_table should never be dereferenced in this file. + */ +struct dm_table { + int undefined__; +}; /* * Work processed by per-device workqueue. */ struct mapped_device { - struct rw_semaphore io_lock; + struct srcu_struct io_barrier; struct mutex suspend_lock; - rwlock_t map_lock; atomic_t holders; atomic_t open_count; + /* + * The current mapping. + * Use dm_get_live_table{_fast} or take suspend_lock for + * dereference. + */ + struct dm_table *map; + unsigned long flags; struct request_queue *queue; + unsigned type; + /* Protect queue and type against concurrent access. */ + struct mutex type_lock; + + struct target_type *immutable_target_type; + struct gendisk *disk; char name[16]; @@ -138,35 +166,14 @@ struct mapped_device { spinlock_t deferred_lock; /* - * An error from the barrier request currently being processed. - */ - int barrier_error; - - /* - * Protect barrier_error from concurrent endio processing - * in request-based dm. - */ - spinlock_t barrier_error_lock; - - /* - * Processing queue (flush/barriers) + * Processing queue (flush) */ struct workqueue_struct *wq; - struct work_struct barrier_work; - - /* A pointer to the currently processing pre/post flush request */ - struct request *flush_request; - - /* - * The current mapping. - */ - struct dm_table *map; /* * io objects are allocated from here. */ mempool_t *io_pool; - mempool_t *tio_pool; struct bio_set *bs; @@ -188,14 +195,13 @@ struct mapped_device { /* forced geometry settings */ struct hd_geometry geometry; - /* For saving the address of __make_request for request based dm */ - make_request_fn *saved_make_request_fn; + /* kobject and completion */ + struct dm_kobject_holder kobj_holder; - /* sysfs handle */ - struct kobject kobj; + /* zero-length flush that will be cloned and submitted to targets */ + struct bio flush_bio; - /* zero-length barrier that will be cloned and submitted to targets */ - struct bio barrier_bio; + struct dm_stats stats; }; /* @@ -203,15 +209,57 @@ struct mapped_device { */ struct dm_md_mempools { mempool_t *io_pool; - mempool_t *tio_pool; struct bio_set *bs; }; -#define MIN_IOS 256 +#define RESERVED_BIO_BASED_IOS 16 +#define RESERVED_REQUEST_BASED_IOS 256 +#define RESERVED_MAX_IOS 1024 static struct kmem_cache *_io_cache; -static struct kmem_cache *_tio_cache; static struct kmem_cache *_rq_tio_cache; -static struct kmem_cache *_rq_bio_info_cache; + +/* + * Bio-based DM's mempools' reserved IOs set by the user. + */ +static unsigned reserved_bio_based_ios = RESERVED_BIO_BASED_IOS; + +/* + * Request-based DM's mempools' reserved IOs set by the user. + */ +static unsigned reserved_rq_based_ios = RESERVED_REQUEST_BASED_IOS; + +static unsigned __dm_get_reserved_ios(unsigned *reserved_ios, + unsigned def, unsigned max) +{ + unsigned ios = ACCESS_ONCE(*reserved_ios); + unsigned modified_ios = 0; + + if (!ios) + modified_ios = def; + else if (ios > max) + modified_ios = max; + + if (modified_ios) { + (void)cmpxchg(reserved_ios, ios, modified_ios); + ios = modified_ios; + } + + return ios; +} + +unsigned dm_get_reserved_bio_based_ios(void) +{ + return __dm_get_reserved_ios(&reserved_bio_based_ios, + RESERVED_BIO_BASED_IOS, RESERVED_MAX_IOS); +} +EXPORT_SYMBOL_GPL(dm_get_reserved_bio_based_ios); + +unsigned dm_get_reserved_rq_based_ios(void) +{ + return __dm_get_reserved_ios(&reserved_rq_based_ios, + RESERVED_REQUEST_BASED_IOS, RESERVED_MAX_IOS); +} +EXPORT_SYMBOL_GPL(dm_get_reserved_rq_based_ios); static int __init local_init(void) { @@ -222,41 +270,36 @@ static int __init local_init(void) if (!_io_cache) return r; - /* allocate a slab for the target ios */ - _tio_cache = KMEM_CACHE(dm_target_io, 0); - if (!_tio_cache) - goto out_free_io_cache; - _rq_tio_cache = KMEM_CACHE(dm_rq_target_io, 0); if (!_rq_tio_cache) - goto out_free_tio_cache; - - _rq_bio_info_cache = KMEM_CACHE(dm_rq_clone_bio_info, 0); - if (!_rq_bio_info_cache) - goto out_free_rq_tio_cache; + goto out_free_io_cache; r = dm_uevent_init(); if (r) - goto out_free_rq_bio_info_cache; + goto out_free_rq_tio_cache; + + deferred_remove_workqueue = alloc_workqueue("kdmremove", WQ_UNBOUND, 1); + if (!deferred_remove_workqueue) { + r = -ENOMEM; + goto out_uevent_exit; + } _major = major; r = register_blkdev(_major, _name); if (r < 0) - goto out_uevent_exit; + goto out_free_workqueue; if (!_major) _major = r; return 0; +out_free_workqueue: + destroy_workqueue(deferred_remove_workqueue); out_uevent_exit: dm_uevent_exit(); -out_free_rq_bio_info_cache: - kmem_cache_destroy(_rq_bio_info_cache); out_free_rq_tio_cache: kmem_cache_destroy(_rq_tio_cache); -out_free_tio_cache: - kmem_cache_destroy(_tio_cache); out_free_io_cache: kmem_cache_destroy(_io_cache); @@ -265,9 +308,10 @@ out_free_io_cache: static void local_exit(void) { - kmem_cache_destroy(_rq_bio_info_cache); + flush_scheduled_work(); + destroy_workqueue(deferred_remove_workqueue); + kmem_cache_destroy(_rq_tio_cache); - kmem_cache_destroy(_tio_cache); kmem_cache_destroy(_io_cache); unregister_blkdev(_major, _name); dm_uevent_exit(); @@ -285,6 +329,7 @@ static int (*_inits[])(void) __initdata = { dm_io_init, dm_kcopyd_init, dm_interface_init, + dm_statistics_init, }; static void (*_exits[])(void) = { @@ -295,6 +340,7 @@ static void (*_exits[])(void) = { dm_io_exit, dm_kcopyd_exit, dm_interface_exit, + dm_statistics_exit, }; static int __init dm_init(void) @@ -324,6 +370,11 @@ static void __exit dm_exit(void) while (i--) _exits[i](); + + /* + * Should be empty by this point. + */ + idr_destroy(&_minor_idr); } /* @@ -359,12 +410,19 @@ out: return md ? 0 : -ENXIO; } -static int dm_blk_close(struct gendisk *disk, fmode_t mode) +static void dm_blk_close(struct gendisk *disk, fmode_t mode) { struct mapped_device *md = disk->private_data; - atomic_dec(&md->open_count); + + spin_lock(&_minor_lock); + + if (atomic_dec_and_test(&md->open_count) && + (test_bit(DMF_DEFERRED_REMOVE, &md->flags))) + queue_work(deferred_remove_workqueue, &deferred_remove_work); + dm_put(md); - return 0; + + spin_unlock(&_minor_lock); } int dm_open_count(struct mapped_device *md) @@ -375,14 +433,18 @@ int dm_open_count(struct mapped_device *md) /* * Guarantees nothing is using the device before it's deleted. */ -int dm_lock_for_deletion(struct mapped_device *md) +int dm_lock_for_deletion(struct mapped_device *md, bool mark_deferred, bool only_deferred) { int r = 0; spin_lock(&_minor_lock); - if (dm_open_count(md)) + if (dm_open_count(md)) { r = -EBUSY; + if (mark_deferred) + set_bit(DMF_DEFERRED_REMOVE, &md->flags); + } else if (only_deferred && !test_bit(DMF_DEFERRED_REMOVE, &md->flags)) + r = -EEXIST; else set_bit(DMF_DELETING, &md->flags); @@ -391,6 +453,42 @@ int dm_lock_for_deletion(struct mapped_device *md) return r; } +int dm_cancel_deferred_remove(struct mapped_device *md) +{ + int r = 0; + + spin_lock(&_minor_lock); + + if (test_bit(DMF_DELETING, &md->flags)) + r = -EBUSY; + else + clear_bit(DMF_DEFERRED_REMOVE, &md->flags); + + spin_unlock(&_minor_lock); + + return r; +} + +static void do_deferred_remove(struct work_struct *w) +{ + dm_deferred_remove(); +} + +sector_t dm_get_size(struct mapped_device *md) +{ + return get_capacity(md->disk); +} + +struct request_queue *dm_get_md_queue(struct mapped_device *md) +{ + return md->queue; +} + +struct dm_stats *dm_get_stats(struct mapped_device *md) +{ + return &md->stats; +} + static int dm_blk_getgeo(struct block_device *bdev, struct hd_geometry *geo) { struct mapped_device *md = bdev->bd_disk->private_data; @@ -402,10 +500,14 @@ static int dm_blk_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) { struct mapped_device *md = bdev->bd_disk->private_data; - struct dm_table *map = dm_get_live_table(md); + int srcu_idx; + struct dm_table *map; struct dm_target *tgt; int r = -ENOTTY; +retry: + map = dm_get_live_table(md, &srcu_idx); + if (!map || !dm_table_get_size(map)) goto out; @@ -424,7 +526,12 @@ static int dm_blk_ioctl(struct block_device *bdev, fmode_t mode, r = tgt->type->ioctl(tgt, cmd, arg); out: - dm_table_put(map); + dm_put_live_table(md, srcu_idx); + + if (r == -ENOTCONN) { + msleep(10); + goto retry; + } return r; } @@ -441,28 +548,18 @@ static void free_io(struct mapped_device *md, struct dm_io *io) static void free_tio(struct mapped_device *md, struct dm_target_io *tio) { - mempool_free(tio, md->tio_pool); + bio_put(&tio->clone); } static struct dm_rq_target_io *alloc_rq_tio(struct mapped_device *md, gfp_t gfp_mask) { - return mempool_alloc(md->tio_pool, gfp_mask); + return mempool_alloc(md->io_pool, gfp_mask); } static void free_rq_tio(struct dm_rq_target_io *tio) { - mempool_free(tio, tio->md->tio_pool); -} - -static struct dm_rq_clone_bio_info *alloc_bio_info(struct mapped_device *md) -{ - return mempool_alloc(md->io_pool, GFP_ATOMIC); -} - -static void free_bio_info(struct dm_rq_clone_bio_info *info) -{ - mempool_free(info, info->tio->md->io_pool); + mempool_free(tio, tio->md->io_pool); } static int md_in_flight(struct mapped_device *md) @@ -474,15 +571,21 @@ static int md_in_flight(struct mapped_device *md) static void start_io_acct(struct dm_io *io) { struct mapped_device *md = io->md; + struct bio *bio = io->bio; int cpu; - int rw = bio_data_dir(io->bio); + int rw = bio_data_dir(bio); io->start_time = jiffies; cpu = part_stat_lock(); part_round_stats(cpu, &dm_disk(md)->part0); part_stat_unlock(); - dm_disk(md)->part0.in_flight[rw] = atomic_inc_return(&md->pending[rw]); + atomic_set(&dm_disk(md)->part0.in_flight[rw], + atomic_inc_return(&md->pending[rw])); + + if (unlikely(dm_stats_used(&md->stats))) + dm_stats_account_io(&md->stats, bio->bi_rw, bio->bi_iter.bi_sector, + bio_sectors(bio), false, 0, &io->stats_aux); } static void end_io_acct(struct dm_io *io) @@ -498,12 +601,16 @@ static void end_io_acct(struct dm_io *io) part_stat_add(cpu, &dm_disk(md)->part0, ticks[rw], duration); part_stat_unlock(); + if (unlikely(dm_stats_used(&md->stats))) + dm_stats_account_io(&md->stats, bio->bi_rw, bio->bi_iter.bi_sector, + bio_sectors(bio), true, duration, &io->stats_aux); + /* * After this is decremented the bio must not be touched if it is - * a barrier. + * a flush. */ - dm_disk(md)->part0.in_flight[rw] = pending = - atomic_dec_return(&md->pending[rw]); + pending = atomic_dec_return(&md->pending[rw]); + atomic_set(&dm_disk(md)->part0.in_flight[rw], pending); pending += atomic_read(&md->pending[rw^0x1]); /* nudge anyone waiting on suspend queue */ @@ -516,35 +623,50 @@ static void end_io_acct(struct dm_io *io) */ static void queue_io(struct mapped_device *md, struct bio *bio) { - down_write(&md->io_lock); + unsigned long flags; - spin_lock_irq(&md->deferred_lock); + spin_lock_irqsave(&md->deferred_lock, flags); bio_list_add(&md->deferred, bio); - spin_unlock_irq(&md->deferred_lock); - - if (!test_and_set_bit(DMF_QUEUE_IO_TO_THREAD, &md->flags)) - queue_work(md->wq, &md->work); - - up_write(&md->io_lock); + spin_unlock_irqrestore(&md->deferred_lock, flags); + queue_work(md->wq, &md->work); } /* * Everyone (including functions in this file), should use this * function to access the md->map field, and make sure they call - * dm_table_put() when finished. + * dm_put_live_table() when finished. */ -struct dm_table *dm_get_live_table(struct mapped_device *md) +struct dm_table *dm_get_live_table(struct mapped_device *md, int *srcu_idx) __acquires(md->io_barrier) { - struct dm_table *t; - unsigned long flags; + *srcu_idx = srcu_read_lock(&md->io_barrier); - read_lock_irqsave(&md->map_lock, flags); - t = md->map; - if (t) - dm_table_get(t); - read_unlock_irqrestore(&md->map_lock, flags); + return srcu_dereference(md->map, &md->io_barrier); +} - return t; +void dm_put_live_table(struct mapped_device *md, int srcu_idx) __releases(md->io_barrier) +{ + srcu_read_unlock(&md->io_barrier, srcu_idx); +} + +void dm_sync_table(struct mapped_device *md) +{ + synchronize_srcu(&md->io_barrier); + synchronize_rcu_expedited(); +} + +/* + * A fast alternative to dm_get_live_table/dm_put_live_table. + * The caller must not block between these two functions. + */ +static struct dm_table *dm_get_live_table_fast(struct mapped_device *md) __acquires(RCU) +{ + rcu_read_lock(); + return rcu_dereference(md->map); +} + +static void dm_put_live_table_fast(struct mapped_device *md) __releases(RCU) +{ + rcu_read_unlock(); } /* @@ -613,11 +735,9 @@ static void dec_pending(struct dm_io *io, int error) * Target requested pushing back the I/O. */ spin_lock_irqsave(&md->deferred_lock, flags); - if (__noflush_suspending(md)) { - if (!bio_rw_flagged(io->bio, BIO_RW_BARRIER)) - bio_list_add_head(&md->deferred, - io->bio); - } else + if (__noflush_suspending(md)) + bio_list_add_head(&md->deferred, io->bio); + else /* noflush suspend was interrupted. */ io->error = -EIO; spin_unlock_irqrestore(&md->deferred_lock, flags); @@ -625,34 +745,39 @@ static void dec_pending(struct dm_io *io, int error) io_error = io->error; bio = io->bio; + end_io_acct(io); + free_io(md, io); - if (bio_rw_flagged(bio, BIO_RW_BARRIER)) { + if (io_error == DM_ENDIO_REQUEUE) + return; + + if ((bio->bi_rw & REQ_FLUSH) && bio->bi_iter.bi_size) { /* - * There can be just one barrier request so we use - * a per-device variable for error reporting. - * Note that you can't touch the bio after end_io_acct + * Preflush done for flush with data, reissue + * without REQ_FLUSH. */ - if (!md->barrier_error && io_error != -EOPNOTSUPP) - md->barrier_error = io_error; - end_io_acct(io); + bio->bi_rw &= ~REQ_FLUSH; + queue_io(md, bio); } else { - end_io_acct(io); - - if (io_error != DM_ENDIO_REQUEUE) { - trace_block_bio_complete(md->queue, bio); - - bio_endio(bio, io_error); - } + /* done with normal IO or empty flush */ + trace_block_bio_complete(md->queue, bio, io_error); + bio_endio(bio, io_error); } - - free_io(md, io); } } +static void disable_write_same(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; +} + static void clone_endio(struct bio *bio, int error) { int r = 0; - struct dm_target_io *tio = bio->bi_private; + struct dm_target_io *tio = container_of(bio, struct dm_target_io, clone); struct dm_io *io = tio->io; struct mapped_device *md = tio->io->md; dm_endio_fn endio = tio->ti->type->end_io; @@ -661,7 +786,7 @@ static void clone_endio(struct bio *bio, int error) error = -EIO; if (endio) { - r = endio(tio->ti, bio, error, &tio->info); + r = endio(tio->ti, bio, error); if (r < 0 || r == DM_ENDIO_REQUEUE) /* * error and requeue request are handled @@ -677,13 +802,11 @@ static void clone_endio(struct bio *bio, int error) } } - /* - * Store md for cleanup instead of tio which is about to get freed. - */ - bio->bi_private = md->bs; + if (unlikely(r == -EREMOTEIO && (bio->bi_rw & REQ_WRITE_SAME) && + !bdev_get_queue(bio->bi_bdev)->limits.max_write_same_sectors)) + disable_write_same(md); free_tio(md, tio); - bio_put(bio); dec_pending(io, error); } @@ -692,10 +815,11 @@ static void clone_endio(struct bio *bio, int error) */ static void end_clone_bio(struct bio *clone, int error) { - struct dm_rq_clone_bio_info *info = clone->bi_private; + struct dm_rq_clone_bio_info *info = + container_of(clone, struct dm_rq_clone_bio_info, clone); struct dm_rq_target_io *tio = info->tio; struct bio *bio = info->orig; - unsigned int nr_bytes = info->orig->bi_size; + unsigned int nr_bytes = info->orig->bi_iter.bi_size; bio_put(clone); @@ -737,23 +861,6 @@ static void end_clone_bio(struct bio *clone, int error) blk_update_request(tio->orig, 0, nr_bytes); } -static void store_barrier_error(struct mapped_device *md, int error) -{ - unsigned long flags; - - spin_lock_irqsave(&md->barrier_error_lock, flags); - /* - * Basically, the first error is taken, but: - * -EOPNOTSUPP supersedes any I/O error. - * Requeue request supersedes any I/O error but -EOPNOTSUPP. - */ - if (!md->barrier_error || error == -EOPNOTSUPP || - (md->barrier_error != -EOPNOTSUPP && - error == DM_ENDIO_REQUEUE)) - md->barrier_error = error; - spin_unlock_irqrestore(&md->barrier_error_lock, flags); -} - /* * Don't touch any member of the md after calling this function because * the md may be freed in dm_put() at the end of this function. @@ -767,8 +874,14 @@ static void rq_completed(struct mapped_device *md, int rw, int run_queue) if (!md_in_flight(md)) wake_up(&md->wait); + /* + * Run this off this callpath, as drivers could invoke end_io while + * inside their request_fn (and holding the queue lock). Calling + * back into ->request_fn() could deadlock attempting to grab the + * queue lock again. + */ if (run_queue) - blk_run_queue(md->queue); + blk_run_queue_async(md->queue); /* * dm_put() must be at the end of this function. See the comment above @@ -791,13 +904,11 @@ static void free_rq_clone(struct request *clone) static void dm_end_request(struct request *clone, int error) { int rw = rq_data_dir(clone); - int run_queue = 1; - bool is_barrier = blk_barrier_rq(clone); struct dm_rq_target_io *tio = clone->end_io_data; struct mapped_device *md = tio->md; struct request *rq = tio->orig; - if (blk_pc_request(rq) && !is_barrier) { + if (rq->cmd_type == REQ_TYPE_BLOCK_PC) { rq->errors = clone->errors; rq->resid_len = clone->resid_len; @@ -811,15 +922,8 @@ static void dm_end_request(struct request *clone, int error) } free_rq_clone(clone); - - if (unlikely(is_barrier)) { - if (unlikely(error)) - store_barrier_error(md, error); - run_queue = 0; - } else - blk_end_request_all(rq, error); - - rq_completed(md, rw, run_queue); + blk_end_request_all(rq, error); + rq_completed(md, rw, true); } static void dm_unprep_request(struct request *rq) @@ -844,21 +948,9 @@ void dm_requeue_unmapped_request(struct request *clone) struct request_queue *q = rq->q; unsigned long flags; - if (unlikely(blk_barrier_rq(clone))) { - /* - * Barrier clones share an original request. - * Leave it to dm_end_request(), which handles this special - * case. - */ - dm_end_request(clone, DM_ENDIO_REQUEUE); - return; - } - dm_unprep_request(rq); spin_lock_irqsave(q->queue_lock, flags); - if (elv_queue_empty(q)) - blk_plug_device(q); blk_requeue_request(q, rq); spin_unlock_irqrestore(q->queue_lock, flags); @@ -899,10 +991,18 @@ static void dm_done(struct request *clone, int error, bool mapped) { int r = error; struct dm_rq_target_io *tio = clone->end_io_data; - dm_request_endio_fn rq_end_io = tio->ti->type->rq_end_io; + dm_request_endio_fn rq_end_io = NULL; - if (mapped && rq_end_io) - r = rq_end_io(tio->ti, clone, error, &tio->info); + if (tio->ti) { + rq_end_io = tio->ti->type->rq_end_io; + + if (mapped && rq_end_io) + r = rq_end_io(tio->ti, clone, error, &tio->info); + } + + if (unlikely(r == -EREMOTEIO && (clone->cmd_flags & REQ_WRITE_SAME) && + !clone->q->limits.max_write_same_sectors)) + disable_write_same(tio->md); if (r <= 0) /* The target wants to complete the I/O */ @@ -943,19 +1043,6 @@ static void dm_complete_request(struct request *clone, int error) struct dm_rq_target_io *tio = clone->end_io_data; struct request *rq = tio->orig; - if (unlikely(blk_barrier_rq(clone))) { - /* - * Barrier clones share an original request. So can't use - * softirq_done with the original. - * Pass the clone to dm_done() directly in this special case. - * It is safe (even if clone->q->queue_lock is held here) - * because there is no I/O dispatching during the completion - * of barrier clone. - */ - dm_done(clone, error, true); - return; - } - tio->error = error; rq->completion_data = clone; blk_complete_request(rq); @@ -972,17 +1059,6 @@ void dm_kill_unmapped_request(struct request *clone, int error) struct dm_rq_target_io *tio = clone->end_io_data; struct request *rq = tio->orig; - if (unlikely(blk_barrier_rq(clone))) { - /* - * Barrier clones share an original request. - * Leave it to dm_end_request(), which handles this special - * case. - */ - BUG_ON(error > 0); - dm_end_request(clone, error); - return; - } - rq->cmd_flags |= REQ_FAILED; dm_complete_request(clone, error); } @@ -1012,35 +1088,104 @@ static void end_clone_request(struct request *clone, int error) dm_complete_request(clone, error); } -static sector_t max_io_len(struct mapped_device *md, - sector_t sector, struct dm_target *ti) +/* + * Return maximum size of I/O possible at the supplied sector up to the current + * target boundary. + */ +static sector_t max_io_len_target_boundary(sector_t sector, struct dm_target *ti) { - sector_t offset = sector - ti->begin; - sector_t len = ti->len - offset; + sector_t target_offset = dm_target_offset(ti, sector); + + return ti->len - target_offset; +} + +static sector_t max_io_len(sector_t sector, struct dm_target *ti) +{ + sector_t len = max_io_len_target_boundary(sector, ti); + sector_t offset, max_len; /* - * Does the target need to split even further ? + * Does the target need to split even further? */ - if (ti->split_io) { - sector_t boundary; - boundary = ((offset + ti->split_io) & ~(ti->split_io - 1)) - - offset; - if (len > boundary) - len = boundary; + if (ti->max_io_len) { + offset = dm_target_offset(ti, sector); + if (unlikely(ti->max_io_len & (ti->max_io_len - 1))) + max_len = sector_div(offset, ti->max_io_len); + else + max_len = offset & (ti->max_io_len - 1); + max_len = ti->max_io_len - max_len; + + if (len > max_len) + len = max_len; } return len; } -static void __map_bio(struct dm_target *ti, struct bio *clone, - struct dm_target_io *tio) +int dm_set_target_max_io_len(struct dm_target *ti, sector_t len) +{ + if (len > UINT_MAX) { + DMERR("Specified maximum size of target IO (%llu) exceeds limit (%u)", + (unsigned long long)len, UINT_MAX); + ti->error = "Maximum size of target IO is too large"; + return -EINVAL; + } + + ti->max_io_len = (uint32_t) len; + + return 0; +} +EXPORT_SYMBOL_GPL(dm_set_target_max_io_len); + +/* + * A target may call dm_accept_partial_bio only from the map routine. It is + * allowed for all bio types except REQ_FLUSH. + * + * 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 + * sent in a next bio. + * + * A diagram that explains the arithmetics: + * +--------------------+---------------+-------+ + * | 1 | 2 | 3 | + * +--------------------+---------------+-------+ + * + * <-------------- *tio->len_ptr ---------------> + * <------- bi_size -------> + * <-- n_sectors --> + * + * Region 1 was already iterated over with bio_advance or similar function. + * (it may be empty if the target doesn't use bio_advance) + * Region 2 is the remaining bio size that the target wants to process. + * (it may be empty if region 1 is non-empty, although there is no reason + * to make it empty) + * The target requires that region 3 is to be sent in the next bio. + * + * If the target wants to receive multiple copies of the bio (via num_*bios, etc), + * the partially processed part (the sum of regions 1+2) must be the same for all + * copies of the bio. + */ +void dm_accept_partial_bio(struct bio *bio, unsigned n_sectors) +{ + struct dm_target_io *tio = container_of(bio, struct dm_target_io, clone); + unsigned bi_size = bio->bi_iter.bi_size >> SECTOR_SHIFT; + BUG_ON(bio->bi_rw & REQ_FLUSH); + BUG_ON(bi_size > *tio->len_ptr); + BUG_ON(n_sectors > bi_size); + *tio->len_ptr -= bi_size - n_sectors; + bio->bi_iter.bi_size = n_sectors << SECTOR_SHIFT; +} +EXPORT_SYMBOL_GPL(dm_accept_partial_bio); + +static void __map_bio(struct dm_target_io *tio) { int r; sector_t sector; struct mapped_device *md; + struct bio *clone = &tio->clone; + struct dm_target *ti = tio->ti; clone->bi_end_io = clone_endio; - clone->bi_private = tio; /* * Map the clone. If r == 0 we don't need to do @@ -1048,24 +1193,19 @@ static void __map_bio(struct dm_target *ti, struct bio *clone, * this io. */ atomic_inc(&tio->io->io_count); - sector = clone->bi_sector; - r = ti->type->map(ti, clone, &tio->info); + sector = clone->bi_iter.bi_sector; + r = ti->type->map(ti, clone); if (r == DM_MAPIO_REMAPPED) { /* the bio has been remapped so dispatch it */ - trace_block_remap(bdev_get_queue(clone->bi_bdev), clone, - tio->io->bio->bi_bdev->bd_dev, sector); + trace_block_bio_remap(bdev_get_queue(clone->bi_bdev), clone, + tio->io->bio->bi_bdev->bd_dev, sector); generic_make_request(clone); } else if (r < 0 || r == DM_MAPIO_REQUEUE) { /* error the io and bail out, or requeue it if needed */ md = tio->io->md; dec_pending(tio->io, r); - /* - * Store bio_set for cleanup. - */ - clone->bi_private = md->bs; - bio_put(clone); free_tio(md, tio); } else if (r) { DMWARN("unimplemented target map return value: %d", r); @@ -1079,257 +1219,250 @@ struct clone_info { struct bio *bio; struct dm_io *io; sector_t sector; - sector_t sector_count; - unsigned short idx; + unsigned sector_count; }; -static void dm_bio_destructor(struct bio *bio) +static void bio_setup_sector(struct bio *bio, sector_t sector, unsigned len) { - struct bio_set *bs = bio->bi_private; - - bio_free(bio, bs); + bio->bi_iter.bi_sector = sector; + bio->bi_iter.bi_size = to_bytes(len); } /* - * Creates a little bio that is just does part of a bvec. + * Creates a bio that consists of range of complete bvecs. */ -static struct bio *split_bvec(struct bio *bio, sector_t sector, - unsigned short idx, unsigned int offset, - unsigned int len, struct bio_set *bs) +static void clone_bio(struct dm_target_io *tio, struct bio *bio, + sector_t sector, unsigned len) { - struct bio *clone; - struct bio_vec *bv = bio->bi_io_vec + idx; - - clone = bio_alloc_bioset(GFP_NOIO, 1, bs); - clone->bi_destructor = dm_bio_destructor; - *clone->bi_io_vec = *bv; - - clone->bi_sector = sector; - clone->bi_bdev = bio->bi_bdev; - clone->bi_rw = bio->bi_rw & ~(1 << BIO_RW_BARRIER); - clone->bi_vcnt = 1; - clone->bi_size = to_bytes(len); - clone->bi_io_vec->bv_offset = offset; - clone->bi_io_vec->bv_len = clone->bi_size; - clone->bi_flags |= 1 << BIO_CLONED; - - if (bio_integrity(bio)) { - bio_integrity_clone(clone, bio, GFP_NOIO, bs); - bio_integrity_trim(clone, - bio_sector_offset(bio, idx, offset), len); - } + struct bio *clone = &tio->clone; - return clone; -} + __bio_clone_fast(clone, bio); -/* - * Creates a bio that consists of range of complete bvecs. - */ -static struct bio *clone_bio(struct bio *bio, sector_t sector, - unsigned short idx, unsigned short bv_count, - unsigned int len, struct bio_set *bs) -{ - struct bio *clone; + if (bio_integrity(bio)) + bio_integrity_clone(clone, bio, GFP_NOIO); - clone = bio_alloc_bioset(GFP_NOIO, bio->bi_max_vecs, bs); - __bio_clone(clone, bio); - clone->bi_rw &= ~(1 << BIO_RW_BARRIER); - clone->bi_destructor = dm_bio_destructor; - clone->bi_sector = sector; - clone->bi_idx = idx; - clone->bi_vcnt = idx + bv_count; - clone->bi_size = to_bytes(len); - clone->bi_flags &= ~(1 << BIO_SEG_VALID); - - if (bio_integrity(bio)) { - bio_integrity_clone(clone, bio, GFP_NOIO, bs); - - if (idx != bio->bi_idx || clone->bi_size < bio->bi_size) - bio_integrity_trim(clone, - bio_sector_offset(bio, idx, 0), len); - } + bio_advance(clone, to_bytes(sector - clone->bi_iter.bi_sector)); + clone->bi_iter.bi_size = to_bytes(len); - return clone; + if (bio_integrity(bio)) + bio_integrity_trim(clone, 0, len); } static struct dm_target_io *alloc_tio(struct clone_info *ci, - struct dm_target *ti) + struct dm_target *ti, int nr_iovecs, + unsigned target_bio_nr) { - struct dm_target_io *tio = mempool_alloc(ci->md->tio_pool, GFP_NOIO); + struct dm_target_io *tio; + struct bio *clone; + + clone = bio_alloc_bioset(GFP_NOIO, nr_iovecs, ci->md->bs); + tio = container_of(clone, struct dm_target_io, clone); tio->io = ci->io; tio->ti = ti; - memset(&tio->info, 0, sizeof(tio->info)); + tio->target_bio_nr = target_bio_nr; return tio; } -static void __flush_target(struct clone_info *ci, struct dm_target *ti, - unsigned flush_nr) +static void __clone_and_map_simple_bio(struct clone_info *ci, + struct dm_target *ti, + unsigned target_bio_nr, unsigned *len) { - struct dm_target_io *tio = alloc_tio(ci, ti); - struct bio *clone; + struct dm_target_io *tio = alloc_tio(ci, ti, ci->bio->bi_max_vecs, target_bio_nr); + struct bio *clone = &tio->clone; - tio->info.flush_request = flush_nr; + tio->len_ptr = len; - clone = bio_alloc_bioset(GFP_NOIO, 0, ci->md->bs); - __bio_clone(clone, ci->bio); - clone->bi_destructor = dm_bio_destructor; + /* + * Discard requests require the bio's inline iovecs be initialized. + * ci->bio->bi_max_vecs is BIO_INLINE_VECS anyway, for both flush + * and discard, so no need for concern about wasted bvec allocations. + */ + __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) +{ + unsigned target_bio_nr; - __map_bio(ti, clone, tio); + for (target_bio_nr = 0; target_bio_nr < num_bios; target_bio_nr++) + __clone_and_map_simple_bio(ci, ti, target_bio_nr, len); } -static int __clone_and_map_empty_barrier(struct clone_info *ci) +static int __send_empty_flush(struct clone_info *ci) { - unsigned target_nr = 0, flush_nr; + unsigned target_nr = 0; struct dm_target *ti; + BUG_ON(bio_has_data(ci->bio)); while ((ti = dm_table_get_target(ci->map, target_nr++))) - for (flush_nr = 0; flush_nr < ti->num_flush_requests; - flush_nr++) - __flush_target(ci, ti, flush_nr); - - ci->sector_count = 0; + __send_duplicate_bios(ci, ti, ti->num_flush_bios, NULL); return 0; } -static int __clone_and_map(struct clone_info *ci) +static void __clone_and_map_data_bio(struct clone_info *ci, struct dm_target *ti, + sector_t sector, unsigned *len) { - struct bio *clone, *bio = ci->bio; - struct dm_target *ti; - sector_t len = 0, max; + struct bio *bio = ci->bio; struct dm_target_io *tio; - - if (unlikely(bio_empty_barrier(bio))) - return __clone_and_map_empty_barrier(ci); - - ti = dm_table_find_target(ci->map, ci->sector); - if (!dm_target_is_valid(ti)) - return -EIO; - - max = max_io_len(ci->md, ci->sector, ti); + unsigned target_bio_nr; + unsigned num_target_bios = 1; /* - * Allocate a target io object. + * Does the target want to receive duplicate copies of the bio? */ - tio = alloc_tio(ci, ti); + if (bio_data_dir(bio) == WRITE && ti->num_write_bios) + num_target_bios = ti->num_write_bios(ti, bio); + + for (target_bio_nr = 0; target_bio_nr < num_target_bios; target_bio_nr++) { + tio = alloc_tio(ci, ti, 0, target_bio_nr); + tio->len_ptr = len; + clone_bio(tio, bio, sector, *len); + __map_bio(tio); + } +} - if (ci->sector_count <= max) { - /* - * Optimise for the simple case where we can do all of - * the remaining io with a single clone. - */ - clone = clone_bio(bio, ci->sector, ci->idx, - bio->bi_vcnt - ci->idx, ci->sector_count, - ci->md->bs); - __map_bio(ti, clone, tio); - ci->sector_count = 0; +typedef unsigned (*get_num_bios_fn)(struct dm_target *ti); - } else if (to_sector(bio->bi_io_vec[ci->idx].bv_len) <= max) { - /* - * There are some bvecs that don't span targets. - * Do as many of these as possible. - */ - int i; - sector_t remaining = max; - sector_t bv_len; +static unsigned get_num_discard_bios(struct dm_target *ti) +{ + return ti->num_discard_bios; +} - for (i = ci->idx; remaining && (i < bio->bi_vcnt); i++) { - bv_len = to_sector(bio->bi_io_vec[i].bv_len); +static unsigned get_num_write_same_bios(struct dm_target *ti) +{ + return ti->num_write_same_bios; +} - if (bv_len > remaining) - break; +typedef bool (*is_split_required_fn)(struct dm_target *ti); - remaining -= bv_len; - len += bv_len; - } +static bool is_split_required_for_discard(struct dm_target *ti) +{ + return ti->split_discard_bios; +} - clone = clone_bio(bio, ci->sector, ci->idx, i - ci->idx, len, - ci->md->bs); - __map_bio(ti, clone, tio); +static int __send_changing_extent_only(struct clone_info *ci, + get_num_bios_fn get_num_bios, + is_split_required_fn is_split_required) +{ + struct dm_target *ti; + unsigned len; + unsigned num_bios; - ci->sector += len; - ci->sector_count -= len; - ci->idx = i; + do { + ti = dm_table_find_target(ci->map, ci->sector); + if (!dm_target_is_valid(ti)) + return -EIO; - } else { /* - * Handle a bvec that must be split between two or more targets. + * 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. */ - struct bio_vec *bv = bio->bi_io_vec + ci->idx; - sector_t remaining = to_sector(bv->bv_len); - unsigned int offset = 0; + num_bios = get_num_bios ? get_num_bios(ti) : 0; + if (!num_bios) + return -EOPNOTSUPP; - do { - if (offset) { - ti = dm_table_find_target(ci->map, ci->sector); - if (!dm_target_is_valid(ti)) - return -EIO; + if (is_split_required && !is_split_required(ti)) + len = min((sector_t)ci->sector_count, max_io_len_target_boundary(ci->sector, ti)); + else + len = min((sector_t)ci->sector_count, max_io_len(ci->sector, ti)); - max = max_io_len(ci->md, ci->sector, ti); + __send_duplicate_bios(ci, ti, num_bios, &len); - tio = alloc_tio(ci, ti); - } + ci->sector += len; + } while (ci->sector_count -= len); - len = min(remaining, max); + return 0; +} - clone = split_bvec(bio, ci->sector, ci->idx, - bv->bv_offset + offset, len, - ci->md->bs); +static int __send_discard(struct clone_info *ci) +{ + return __send_changing_extent_only(ci, get_num_discard_bios, + is_split_required_for_discard); +} - __map_bio(ti, clone, tio); +static int __send_write_same(struct clone_info *ci) +{ + return __send_changing_extent_only(ci, get_num_write_same_bios, NULL); +} - ci->sector += len; - ci->sector_count -= len; - offset += to_bytes(len); - } while (remaining -= len); +/* + * Select the correct strategy for processing a non-flush bio. + */ +static int __split_and_process_non_flush(struct clone_info *ci) +{ + struct bio *bio = ci->bio; + struct dm_target *ti; + unsigned len; - ci->idx++; - } + if (unlikely(bio->bi_rw & REQ_DISCARD)) + return __send_discard(ci); + else if (unlikely(bio->bi_rw & REQ_WRITE_SAME)) + return __send_write_same(ci); + + ti = dm_table_find_target(ci->map, ci->sector); + if (!dm_target_is_valid(ti)) + return -EIO; + + len = min_t(sector_t, max_io_len(ci->sector, ti), ci->sector_count); + + __clone_and_map_data_bio(ci, ti, ci->sector, &len); + + ci->sector += len; + ci->sector_count -= len; return 0; } /* - * Split the bio into several clones and submit it to targets. + * 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 bio *bio) +static void __split_and_process_bio(struct mapped_device *md, + struct dm_table *map, struct bio *bio) { struct clone_info ci; int error = 0; - ci.map = dm_get_live_table(md); - if (unlikely(!ci.map)) { - if (!bio_rw_flagged(bio, BIO_RW_BARRIER)) - bio_io_error(bio); - else - if (!md->barrier_error) - md->barrier_error = -EIO; + if (unlikely(!map)) { + bio_io_error(bio); return; } + ci.map = map; ci.md = md; - ci.bio = bio; ci.io = alloc_io(md); ci.io->error = 0; atomic_set(&ci.io->io_count, 1); ci.io->bio = bio; ci.io->md = md; spin_lock_init(&ci.io->endio_lock); - ci.sector = bio->bi_sector; - ci.sector_count = bio_sectors(bio); - if (unlikely(bio_empty_barrier(bio))) - ci.sector_count = 1; - ci.idx = bio->bi_idx; + ci.sector = bio->bi_iter.bi_sector; start_io_acct(ci.io); - while (ci.sector_count && !error) - error = __clone_and_map(&ci); + + if (bio->bi_rw & REQ_FLUSH) { + ci.bio = &ci.md->flush_bio; + ci.sector_count = 0; + error = __send_empty_flush(&ci); + /* dec_pending submits any data associated with flush */ + } else { + ci.bio = bio; + ci.sector_count = bio_sectors(bio); + while (ci.sector_count && !error) + error = __split_and_process_non_flush(&ci); + } /* drop the extra reference count */ dec_pending(ci.io, error); - dm_table_put(ci.map); } /*----------------------------------------------------------------- * CRUD END @@ -1340,7 +1473,7 @@ static int dm_merge_bvec(struct request_queue *q, struct bio_vec *biovec) { struct mapped_device *md = q->queuedata; - struct dm_table *map = dm_get_live_table(md); + struct dm_table *map = dm_get_live_table_fast(md); struct dm_target *ti; sector_t max_sectors; int max_size = 0; @@ -1350,12 +1483,12 @@ static int dm_merge_bvec(struct request_queue *q, ti = dm_table_find_target(map, bvm->bi_sector); if (!dm_target_is_valid(ti)) - goto out_table; + goto out; /* * Find maximum amount of I/O that won't need splitting */ - max_sectors = min(max_io_len(md, bvm->bi_sector, ti), + max_sectors = min(max_io_len(bvm->bi_sector, ti), (sector_t) BIO_MAX_SECTORS); max_size = (max_sectors << SECTOR_SHIFT) - bvm->bi_size; if (max_size < 0) @@ -1376,13 +1509,10 @@ static int dm_merge_bvec(struct request_queue *q, * just one page. */ else if (queue_max_hw_sectors(q) <= PAGE_SIZE >> 9) - max_size = 0; -out_table: - dm_table_put(map); - out: + dm_put_live_table_fast(md); /* * Always allow an entire first page */ @@ -1396,82 +1526,50 @@ out: * The request function that just remaps the bio built up by * dm_merge_bvec. */ -static int _dm_request(struct request_queue *q, struct bio *bio) +static void _dm_request(struct request_queue *q, struct bio *bio) { int rw = bio_data_dir(bio); struct mapped_device *md = q->queuedata; int cpu; + int srcu_idx; + struct dm_table *map; - down_read(&md->io_lock); + map = dm_get_live_table(md, &srcu_idx); cpu = part_stat_lock(); part_stat_inc(cpu, &dm_disk(md)->part0, ios[rw]); part_stat_add(cpu, &dm_disk(md)->part0, sectors[rw], bio_sectors(bio)); part_stat_unlock(); - /* - * If we're suspended or the thread is processing barriers - * we have to queue this io for later. - */ - if (unlikely(test_bit(DMF_QUEUE_IO_TO_THREAD, &md->flags)) || - unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) { - up_read(&md->io_lock); + /* if we're suspended, we have to queue this io for later */ + if (unlikely(test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags))) { + dm_put_live_table(md, srcu_idx); - if (unlikely(test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags)) && - bio_rw(bio) == READA) { + if (bio_rw(bio) != READA) + queue_io(md, bio); + else bio_io_error(bio); - return 0; - } - - queue_io(md, bio); - - return 0; + return; } - __split_and_process_bio(md, bio); - up_read(&md->io_lock); - return 0; -} - -static int dm_make_request(struct request_queue *q, struct bio *bio) -{ - struct mapped_device *md = q->queuedata; - - return md->saved_make_request_fn(q, bio); /* call __make_request() */ + __split_and_process_bio(md, map, bio); + dm_put_live_table(md, srcu_idx); + return; } -static int dm_request_based(struct mapped_device *md) +int dm_request_based(struct mapped_device *md) { return blk_queue_stackable(md->queue); } -static int dm_request(struct request_queue *q, struct bio *bio) +static void dm_request(struct request_queue *q, struct bio *bio) { struct mapped_device *md = q->queuedata; if (dm_request_based(md)) - return dm_make_request(q, bio); - - return _dm_request(q, bio); -} - -/* - * Mark this request as flush request, so that dm_request_fn() can - * recognize. - */ -static void dm_rq_prepare_flush(struct request_queue *q, struct request *rq) -{ - rq->cmd_type = REQ_TYPE_LINUX_BLOCK; - rq->cmd[0] = REQ_LB_OP_FLUSH; -} - -static bool dm_rq_is_flush_request(struct request *rq) -{ - if (rq->cmd_type == REQ_TYPE_LINUX_BLOCK && - rq->cmd[0] == REQ_LB_OP_FLUSH) - return true; + blk_queue_bio(q, bio); else - return false; + _dm_request(q, bio); } void dm_dispatch_request(struct request *rq) @@ -1488,30 +1586,16 @@ void dm_dispatch_request(struct request *rq) } EXPORT_SYMBOL_GPL(dm_dispatch_request); -static void dm_rq_bio_destructor(struct bio *bio) -{ - struct dm_rq_clone_bio_info *info = bio->bi_private; - struct mapped_device *md = info->tio->md; - - free_bio_info(info); - bio_free(bio, md->bs); -} - static int dm_rq_bio_constructor(struct bio *bio, struct bio *bio_orig, void *data) { struct dm_rq_target_io *tio = data; - struct mapped_device *md = tio->md; - struct dm_rq_clone_bio_info *info = alloc_bio_info(md); - - if (!info) - return -ENOMEM; + struct dm_rq_clone_bio_info *info = + container_of(bio, struct dm_rq_clone_bio_info, clone); info->orig = bio_orig; info->tio = tio; bio->bi_end_io = end_clone_bio; - bio->bi_private = info; - bio->bi_destructor = dm_rq_bio_destructor; return 0; } @@ -1521,22 +1605,14 @@ static int setup_clone(struct request *clone, struct request *rq, { int r; - if (dm_rq_is_flush_request(rq)) { - blk_rq_init(NULL, clone); - clone->cmd_type = REQ_TYPE_FS; - clone->cmd_flags |= (REQ_HARDBARRIER | WRITE); - } else { - r = blk_rq_prep_clone(clone, rq, tio->md->bs, GFP_ATOMIC, - dm_rq_bio_constructor, tio); - if (r) - return r; - - clone->cmd = rq->cmd; - clone->cmd_len = rq->cmd_len; - clone->sense = rq->sense; - clone->buffer = rq->buffer; - } + r = blk_rq_prep_clone(clone, rq, tio->md->bs, GFP_ATOMIC, + dm_rq_bio_constructor, tio); + if (r) + return r; + clone->cmd = rq->cmd; + clone->cmd_len = rq->cmd_len; + clone->sense = rq->sense; clone->end_io = end_clone_request; clone->end_io_data = tio; @@ -1577,9 +1653,6 @@ static int dm_prep_fn(struct request_queue *q, struct request *rq) struct mapped_device *md = q->queuedata; struct request *clone; - if (unlikely(dm_rq_is_flush_request(rq))) - return BLKPREP_OK; - if (unlikely(rq->special)) { DMWARN("Already has something in rq->special."); return BLKPREP_KILL; @@ -1595,21 +1668,17 @@ static int dm_prep_fn(struct request_queue *q, struct request *rq) return BLKPREP_OK; } -static void map_request(struct dm_target *ti, struct request *clone, - struct mapped_device *md) +/* + * Returns: + * 0 : the request has been processed (not requeued) + * !0 : the request has been requeued + */ +static int map_request(struct dm_target *ti, struct request *clone, + struct mapped_device *md) { - int r; + int r, requeued = 0; struct dm_rq_target_io *tio = clone->end_io_data; - /* - * Hold the md reference here for the in-flight I/O. - * We can't rely on the reference count by device opener, - * because the device may be closed during the request completion - * when all bios are completed. - * See the comment in rq_completed() too. - */ - dm_get(md); - tio->ti = ti; r = ti->type->map_rq(ti, clone, &tio->info); switch (r) { @@ -1625,6 +1694,7 @@ static void map_request(struct dm_target *ti, struct request *clone, case DM_MAPIO_REQUEUE: /* The target wants to requeue the I/O */ dm_requeue_unmapped_request(clone); + requeued = 1; break; default: if (r > 0) { @@ -1636,6 +1706,28 @@ static void map_request(struct dm_target *ti, struct request *clone, dm_kill_unmapped_request(clone, r); break; } + + return requeued; +} + +static struct request *dm_start_request(struct mapped_device *md, struct request *orig) +{ + struct request *clone; + + blk_start_request(orig); + clone = orig->special; + atomic_inc(&md->pending[rq_data_dir(clone)]); + + /* + * Hold the md reference here for the in-flight I/O. + * We can't rely on the reference count by device opener, + * because the device may be closed during the request completion + * when all bios are completed. + * See the comment in rq_completed() too. + */ + dm_get(md); + + return clone; } /* @@ -1645,9 +1737,11 @@ static void map_request(struct dm_target *ti, struct request *clone, static void dm_request_fn(struct request_queue *q) { struct mapped_device *md = q->queuedata; - struct dm_table *map = dm_get_live_table(md); + int srcu_idx; + struct dm_table *map = dm_get_live_table(md, &srcu_idx); struct dm_target *ti; struct request *rq, *clone; + sector_t pos; /* * For suspend, check blk_queue_stopped() and increment @@ -1655,43 +1749,51 @@ static void dm_request_fn(struct request_queue *q) * number of in-flight I/Os after the queue is stopped in * dm_suspend(). */ - while (!blk_queue_plugged(q) && !blk_queue_stopped(q)) { + while (!blk_queue_stopped(q)) { rq = blk_peek_request(q); if (!rq) - goto plug_and_out; + goto delay_and_out; - if (unlikely(dm_rq_is_flush_request(rq))) { - BUG_ON(md->flush_request); - md->flush_request = rq; - blk_start_request(rq); - queue_work(md->wq, &md->barrier_work); - goto out; + /* always use block 0 to find the target for flushes for now */ + pos = 0; + if (!(rq->cmd_flags & REQ_FLUSH)) + pos = blk_rq_pos(rq); + + ti = dm_table_find_target(map, pos); + if (!dm_target_is_valid(ti)) { + /* + * Must perform setup, that dm_done() requires, + * before calling dm_kill_unmapped_request + */ + DMERR_LIMIT("request attempted access beyond the end of device"); + clone = dm_start_request(md, rq); + dm_kill_unmapped_request(clone, -EIO); + continue; } - ti = dm_table_find_target(map, blk_rq_pos(rq)); if (ti->type->busy && ti->type->busy(ti)) - goto plug_and_out; + goto delay_and_out; - blk_start_request(rq); - clone = rq->special; - atomic_inc(&md->pending[rq_data_dir(clone)]); + clone = dm_start_request(md, rq); spin_unlock(q->queue_lock); - map_request(ti, clone, md); - spin_lock_irq(q->queue_lock); + if (map_request(ti, clone, md)) + goto requeued; + + BUG_ON(!irqs_disabled()); + spin_lock(q->queue_lock); } goto out; -plug_and_out: - if (!elv_queue_empty(q)) - /* Some requests still remain, retry later */ - blk_plug_device(q); +requeued: + BUG_ON(!irqs_disabled()); + spin_lock(q->queue_lock); +delay_and_out: + blk_delay_queue(q, HZ / 10); out: - dm_table_put(map); - - return; + dm_put_live_table(md, srcu_idx); } int dm_underlying_device_busy(struct request_queue *q) @@ -1704,32 +1806,18 @@ static int dm_lld_busy(struct request_queue *q) { int r; struct mapped_device *md = q->queuedata; - struct dm_table *map = dm_get_live_table(md); + struct dm_table *map = dm_get_live_table_fast(md); if (!map || test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags)) r = 1; else r = dm_table_any_busy_target(map); - dm_table_put(map); + dm_put_live_table_fast(md); return r; } -static void dm_unplug_all(struct request_queue *q) -{ - struct mapped_device *md = q->queuedata; - struct dm_table *map = dm_get_live_table(md); - - if (map) { - if (dm_request_based(md)) - generic_unplug_device(q); - - dm_table_unplug_all(map); - dm_table_put(map); - } -} - static int dm_any_congested(void *congested_data, int bdi_bits) { int r = bdi_bits; @@ -1737,7 +1825,7 @@ static int dm_any_congested(void *congested_data, int bdi_bits) struct dm_table *map; if (!test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags)) { - map = dm_get_live_table(md); + map = dm_get_live_table_fast(md); if (map) { /* * Request-based dm cares about only own queue for @@ -1748,9 +1836,8 @@ static int dm_any_congested(void *congested_data, int bdi_bits) bdi_bits; else r = dm_table_any_congested(map, bdi_bits); - - dm_table_put(map); } + dm_put_live_table_fast(md); } return r; @@ -1759,8 +1846,6 @@ static int dm_any_congested(void *congested_data, int bdi_bits) /*----------------------------------------------------------------- * An IDR is used to keep track of allocated minor numbers. *---------------------------------------------------------------*/ -static DEFINE_IDR(_minor_idr); - static void free_minor(int minor) { spin_lock(&_minor_lock); @@ -1773,68 +1858,64 @@ static void free_minor(int minor) */ static int specific_minor(int minor) { - int r, m; + int r; if (minor >= (1 << MINORBITS)) return -EINVAL; - r = idr_pre_get(&_minor_idr, GFP_KERNEL); - if (!r) - return -ENOMEM; - + idr_preload(GFP_KERNEL); spin_lock(&_minor_lock); - if (idr_find(&_minor_idr, minor)) { - r = -EBUSY; - goto out; - } - - r = idr_get_new_above(&_minor_idr, MINOR_ALLOCED, minor, &m); - if (r) - goto out; + r = idr_alloc(&_minor_idr, MINOR_ALLOCED, minor, minor + 1, GFP_NOWAIT); - if (m != minor) { - idr_remove(&_minor_idr, m); - r = -EBUSY; - goto out; - } - -out: spin_unlock(&_minor_lock); - return r; + idr_preload_end(); + if (r < 0) + return r == -ENOSPC ? -EBUSY : r; + return 0; } static int next_free_minor(int *minor) { - int r, m; - - r = idr_pre_get(&_minor_idr, GFP_KERNEL); - if (!r) - return -ENOMEM; + int r; + idr_preload(GFP_KERNEL); spin_lock(&_minor_lock); - r = idr_get_new(&_minor_idr, MINOR_ALLOCED, &m); - if (r) - goto out; - - if (m >= (1 << MINORBITS)) { - idr_remove(&_minor_idr, m); - r = -ENOSPC; - goto out; - } + r = idr_alloc(&_minor_idr, MINOR_ALLOCED, 0, 1 << MINORBITS, GFP_NOWAIT); - *minor = m; - -out: spin_unlock(&_minor_lock); - return r; + idr_preload_end(); + if (r < 0) + return r; + *minor = r; + return 0; } static const struct block_device_operations dm_blk_dops; static void dm_wq_work(struct work_struct *work); -static void dm_rq_barrier_work(struct work_struct *work); + +static void dm_init_md_queue(struct mapped_device *md) +{ + /* + * Request-based dm devices cannot be stacked on top of bio-based dm + * devices. The type of this dm device has not been decided yet. + * The type is decided at the first table loading time. + * To prevent problematic device stacking, clear the queue flag + * for request stacking support until then. + * + * This queue is new, so no concurrency on the queue_flags. + */ + queue_flag_clear_unlocked(QUEUE_FLAG_STACKABLE, md->queue); + + md->queue->queuedata = md; + md->queue->backing_dev_info.congested_fn = dm_any_congested; + md->queue->backing_dev_info.congested_data = md; + blk_queue_make_request(md->queue, dm_request); + blk_queue_bounce_limit(md->queue, BLK_BOUNCE_ANY); + blk_queue_merge_bvec(md->queue, dm_merge_bvec); +} /* * Allocate and initialise a blank device with a given minor. @@ -1861,11 +1942,14 @@ static struct mapped_device *alloc_dev(int minor) if (r < 0) goto bad_minor; - init_rwsem(&md->io_lock); + r = init_srcu_struct(&md->io_barrier); + if (r < 0) + goto bad_io_barrier; + + md->type = DM_TYPE_NONE; mutex_init(&md->suspend_lock); + mutex_init(&md->type_lock); spin_lock_init(&md->deferred_lock); - spin_lock_init(&md->barrier_error_lock); - rwlock_init(&md->map_lock); atomic_set(&md->holders, 1); atomic_set(&md->open_count, 0); atomic_set(&md->event_nr, 0); @@ -1873,34 +1957,11 @@ static struct mapped_device *alloc_dev(int minor) INIT_LIST_HEAD(&md->uevent_list); spin_lock_init(&md->uevent_lock); - md->queue = blk_init_queue(dm_request_fn, NULL); + md->queue = blk_alloc_queue(GFP_KERNEL); if (!md->queue) goto bad_queue; - /* - * Request-based dm devices cannot be stacked on top of bio-based dm - * devices. The type of this dm device has not been decided yet, - * although we initialized the queue using blk_init_queue(). - * The type is decided at the first table loading time. - * To prevent problematic device stacking, clear the queue flag - * for request stacking support until then. - * - * This queue is new, so no concurrency on the queue_flags. - */ - queue_flag_clear_unlocked(QUEUE_FLAG_STACKABLE, md->queue); - md->saved_make_request_fn = md->queue->make_request_fn; - md->queue->queuedata = md; - md->queue->backing_dev_info.congested_fn = dm_any_congested; - md->queue->backing_dev_info.congested_data = md; - blk_queue_make_request(md->queue, dm_request); - blk_queue_bounce_limit(md->queue, BLK_BOUNCE_ANY); - md->queue->unplug_fn = dm_unplug_all; - blk_queue_merge_bvec(md->queue, dm_merge_bvec); - blk_queue_softirq_done(md->queue, dm_softirq_done); - blk_queue_prep_rq(md->queue, dm_prep_fn); - blk_queue_lld_busy(md->queue, dm_lld_busy); - blk_queue_ordered(md->queue, QUEUE_ORDERED_DRAIN_FLUSH, - dm_rq_prepare_flush); + dm_init_md_queue(md); md->disk = alloc_disk(1); if (!md->disk) @@ -1910,8 +1971,8 @@ static struct mapped_device *alloc_dev(int minor) atomic_set(&md->pending[1], 0); init_waitqueue_head(&md->wait); INIT_WORK(&md->work, dm_wq_work); - INIT_WORK(&md->barrier_work, dm_rq_barrier_work); init_waitqueue_head(&md->eventq); + init_completion(&md->kobj_holder.completion); md->disk->major = _major; md->disk->first_minor = minor; @@ -1922,7 +1983,7 @@ static struct mapped_device *alloc_dev(int minor) add_disk(md->disk); format_dev_t(md->name, MKDEV(_major, minor)); - md->wq = create_singlethread_workqueue("kdmflush"); + md->wq = alloc_workqueue("kdmflush", WQ_MEM_RECLAIM, 0); if (!md->wq) goto bad_thread; @@ -1930,6 +1991,12 @@ static struct mapped_device *alloc_dev(int minor) if (!md->bdev) goto bad_bdev; + bio_init(&md->flush_bio); + md->flush_bio.bi_bdev = md->bdev; + md->flush_bio.bi_rw = WRITE_FLUSH; + + dm_stats_init(&md->stats); + /* Populate the mapping, nobody knows we exist yet */ spin_lock(&_minor_lock); old_md = idr_replace(&_minor_idr, md, minor); @@ -1947,6 +2014,8 @@ bad_thread: bad_disk: blk_cleanup_queue(md->queue); bad_queue: + cleanup_srcu_struct(&md->io_barrier); +bad_io_barrier: free_minor(minor); bad_minor: module_put(THIS_MODULE); @@ -1964,14 +2033,13 @@ static void free_dev(struct mapped_device *md) unlock_fs(md); bdput(md->bdev); destroy_workqueue(md->wq); - if (md->tio_pool) - mempool_destroy(md->tio_pool); if (md->io_pool) mempool_destroy(md->io_pool); if (md->bs) bioset_free(md->bs); blk_integrity_unregister(md->disk); del_gendisk(md->disk); + cleanup_srcu_struct(&md->io_barrier); free_minor(minor); spin_lock(&_minor_lock); @@ -1980,25 +2048,42 @@ static void free_dev(struct mapped_device *md) put_disk(md->disk); blk_cleanup_queue(md->queue); + dm_stats_cleanup(&md->stats); module_put(THIS_MODULE); kfree(md); } static void __bind_mempools(struct mapped_device *md, struct dm_table *t) { - struct dm_md_mempools *p; + struct dm_md_mempools *p = dm_table_get_md_mempools(t); - if (md->io_pool && md->tio_pool && md->bs) - /* the md already has necessary mempools */ + if (md->io_pool && md->bs) { + /* The md already has necessary mempools. */ + if (dm_table_get_type(t) == DM_TYPE_BIO_BASED) { + /* + * Reload bioset because front_pad may have changed + * because a different table was loaded. + */ + bioset_free(md->bs); + md->bs = p->bs; + p->bs = NULL; + } else if (dm_table_get_type(t) == DM_TYPE_REQUEST_BASED) { + /* + * There's no need to reload with request-based dm + * because the size of front_pad doesn't change. + * Note for future: If you are to reload bioset, + * prep-ed requests in the queue may refer + * to bio from the old bioset, so you must walk + * through the queue to unprep. + */ + } goto out; + } - p = dm_table_get_md_mempools(t); - BUG_ON(!p || md->io_pool || md->tio_pool || md->bs); + BUG_ON(!p || md->io_pool || md->bs); md->io_pool = p->io_pool; p->io_pool = NULL; - md->tio_pool = p->tio_pool; - p->tio_pool = NULL; md->bs = p->bs; p->bs = NULL; @@ -2026,13 +2111,67 @@ static void event_callback(void *context) wake_up(&md->eventq); } +/* + * Protected by md->suspend_lock obtained by dm_swap_table(). + */ static void __set_size(struct mapped_device *md, sector_t size) { set_capacity(md->disk, size); - mutex_lock(&md->bdev->bd_inode->i_mutex); i_size_write(md->bdev->bd_inode, (loff_t)size << SECTOR_SHIFT); - mutex_unlock(&md->bdev->bd_inode->i_mutex); +} + +/* + * Return 1 if the queue has a compulsory merge_bvec_fn function. + * + * If this function returns 0, then the device is either a non-dm + * device without a merge_bvec_fn, or it is a dm device that is + * able to split any bios it receives that are too big. + */ +int dm_queue_merge_is_compulsory(struct request_queue *q) +{ + struct mapped_device *dev_md; + + if (!q->merge_bvec_fn) + return 0; + + if (q->make_request_fn == dm_request) { + dev_md = q->queuedata; + if (test_bit(DMF_MERGE_IS_OPTIONAL, &dev_md->flags)) + return 0; + } + + return 1; +} + +static int dm_device_merge_is_compulsory(struct dm_target *ti, + struct dm_dev *dev, sector_t start, + sector_t len, void *data) +{ + struct block_device *bdev = dev->bdev; + struct request_queue *q = bdev_get_queue(bdev); + + return dm_queue_merge_is_compulsory(q); +} + +/* + * Return 1 if it is acceptable to ignore merge_bvec_fn based + * on the properties of the underlying devices. + */ +static int dm_table_merge_is_optional(struct dm_table *table) +{ + unsigned i = 0; + struct dm_target *ti; + + while (i < dm_table_get_num_targets(table)) { + ti = dm_table_get_target(table, i++); + + if (ti->type->iterate_devices && + ti->type->iterate_devices(ti, dm_device_merge_is_compulsory, NULL)) + return 0; + } + + return 1; } /* @@ -2044,14 +2183,14 @@ static struct dm_table *__bind(struct mapped_device *md, struct dm_table *t, struct dm_table *old_map; struct request_queue *q = md->queue; sector_t size; - unsigned long flags; + int merge_is_optional; size = dm_table_get_size(t); /* * Wipe any geometry if the size of the table changed. */ - if (size != get_capacity(md->disk)) + if (size != dm_get_size(md)) memset(&md->geometry, 0, sizeof(md->geometry)); __set_size(md, size); @@ -2070,11 +2209,18 @@ static struct dm_table *__bind(struct mapped_device *md, struct dm_table *t, __bind_mempools(md, t); - write_lock_irqsave(&md->map_lock, flags); + merge_is_optional = dm_table_merge_is_optional(t); + old_map = md->map; - md->map = t; + rcu_assign_pointer(md->map, t); + md->immutable_target_type = dm_table_get_immutable_target_type(t); + dm_table_set_restrictions(t, q, limits); - write_unlock_irqrestore(&md->map_lock, flags); + if (merge_is_optional) + set_bit(DMF_MERGE_IS_OPTIONAL, &md->flags); + else + clear_bit(DMF_MERGE_IS_OPTIONAL, &md->flags); + dm_sync_table(md); return old_map; } @@ -2085,15 +2231,13 @@ static struct dm_table *__bind(struct mapped_device *md, struct dm_table *t, static struct dm_table *__unbind(struct mapped_device *md) { struct dm_table *map = md->map; - unsigned long flags; if (!map) return NULL; dm_table_event_callback(map, NULL, NULL); - write_lock_irqsave(&md->map_lock, flags); - md->map = NULL; - write_unlock_irqrestore(&md->map_lock, flags); + RCU_INIT_POINTER(md->map, NULL); + dm_sync_table(md); return map; } @@ -2115,6 +2259,88 @@ int dm_create(int minor, struct mapped_device **result) return 0; } +/* + * Functions to manage md->type. + * All are required to hold md->type_lock. + */ +void dm_lock_md_type(struct mapped_device *md) +{ + mutex_lock(&md->type_lock); +} + +void dm_unlock_md_type(struct mapped_device *md) +{ + mutex_unlock(&md->type_lock); +} + +void dm_set_md_type(struct mapped_device *md, unsigned type) +{ + BUG_ON(!mutex_is_locked(&md->type_lock)); + md->type = type; +} + +unsigned dm_get_md_type(struct mapped_device *md) +{ + BUG_ON(!mutex_is_locked(&md->type_lock)); + return md->type; +} + +struct target_type *dm_get_immutable_target_type(struct mapped_device *md) +{ + return md->immutable_target_type; +} + +/* + * The queue_limits are only valid as long as you have a reference + * count on 'md'. + */ +struct queue_limits *dm_get_queue_limits(struct mapped_device *md) +{ + BUG_ON(!atomic_read(&md->holders)); + return &md->queue->limits; +} +EXPORT_SYMBOL_GPL(dm_get_queue_limits); + +/* + * Fully initialize a request-based queue (->elevator, ->request_fn, etc). + */ +static int dm_init_request_based_queue(struct mapped_device *md) +{ + struct request_queue *q = NULL; + + if (md->queue->elevator) + return 1; + + /* Fully initialize the queue */ + q = blk_init_allocated_queue(md->queue, dm_request_fn, NULL); + if (!q) + return 0; + + md->queue = q; + dm_init_md_queue(md); + blk_queue_softirq_done(md->queue, dm_softirq_done); + blk_queue_prep_rq(md->queue, dm_prep_fn); + blk_queue_lld_busy(md->queue, dm_lld_busy); + + elv_register_queue(md->queue); + + return 1; +} + +/* + * Setup the DM device's queue based on md's type + */ +int dm_setup_md_queue(struct mapped_device *md) +{ + if ((dm_get_md_type(md) == DM_TYPE_REQUEST_BASED) && + !dm_init_request_based_queue(md)) { + DMWARN("Cannot initialize queue for request-based mapped device"); + return -EINVAL; + } + + return 0; +} + static struct mapped_device *dm_find_md(dev_t dev) { struct mapped_device *md; @@ -2128,6 +2354,7 @@ static struct mapped_device *dm_find_md(dev_t dev) md = idr_find(&_minor_idr, minor); if (md && (md == MINOR_ALLOCED || (MINOR(disk_devt(dm_disk(md))) != minor) || + dm_deleting_md(md) || test_bit(DMF_FREEING, &md->flags))) { md = NULL; goto out; @@ -2148,6 +2375,7 @@ struct mapped_device *dm_get_md(dev_t dev) return md; } +EXPORT_SYMBOL_GPL(dm_get_md); void *dm_get_mdptr(struct mapped_device *md) { @@ -2162,6 +2390,7 @@ void dm_set_mdptr(struct mapped_device *md, void *ptr) void dm_get(struct mapped_device *md) { atomic_inc(&md->holders); + BUG_ON(test_bit(DMF_FREEING, &md->flags)); } const char *dm_device_name(struct mapped_device *md) @@ -2170,27 +2399,58 @@ const char *dm_device_name(struct mapped_device *md) } EXPORT_SYMBOL_GPL(dm_device_name); -void dm_put(struct mapped_device *md) +static void __dm_destroy(struct mapped_device *md, bool wait) { struct dm_table *map; + int srcu_idx; - BUG_ON(test_bit(DMF_FREEING, &md->flags)); + might_sleep(); - if (atomic_dec_and_lock(&md->holders, &_minor_lock)) { - map = dm_get_live_table(md); - idr_replace(&_minor_idr, MINOR_ALLOCED, - MINOR(disk_devt(dm_disk(md)))); - set_bit(DMF_FREEING, &md->flags); - spin_unlock(&_minor_lock); - if (!dm_suspended_md(md)) { - dm_table_presuspend_targets(map); - dm_table_postsuspend_targets(map); - } - dm_sysfs_exit(md); - dm_table_put(map); - dm_table_destroy(__unbind(md)); - free_dev(md); + spin_lock(&_minor_lock); + map = dm_get_live_table(md, &srcu_idx); + idr_replace(&_minor_idr, MINOR_ALLOCED, MINOR(disk_devt(dm_disk(md)))); + set_bit(DMF_FREEING, &md->flags); + spin_unlock(&_minor_lock); + + if (!dm_suspended_md(md)) { + dm_table_presuspend_targets(map); + dm_table_postsuspend_targets(map); } + + /* dm_put_live_table must be before msleep, otherwise deadlock is possible */ + dm_put_live_table(md, srcu_idx); + + /* + * Rare, but there may be I/O requests still going to complete, + * for example. Wait for all references to disappear. + * No one should increment the reference count of the mapped_device, + * after the mapped_device state becomes DMF_FREEING. + */ + if (wait) + while (atomic_read(&md->holders)) + msleep(1); + else if (atomic_read(&md->holders)) + DMWARN("%s: Forcibly removing mapped_device still in use! (%d users)", + dm_device_name(md), atomic_read(&md->holders)); + + dm_sysfs_exit(md); + dm_table_destroy(__unbind(md)); + free_dev(md); +} + +void dm_destroy(struct mapped_device *md) +{ + __dm_destroy(md, true); +} + +void dm_destroy_immediate(struct mapped_device *md) +{ + __dm_destroy(md, false); +} + +void dm_put(struct mapped_device *md) +{ + atomic_dec(&md->holders); } EXPORT_SYMBOL_GPL(dm_put); @@ -2199,14 +2459,11 @@ static int dm_wait_for_completion(struct mapped_device *md, int interruptible) int r = 0; DECLARE_WAITQUEUE(wait, current); - dm_unplug_all(md->queue); - add_wait_queue(&md->wait, &wait); while (1) { set_current_state(interruptible); - smp_mb(); if (!md_in_flight(md)) break; @@ -2225,38 +2482,6 @@ static int dm_wait_for_completion(struct mapped_device *md, int interruptible) return r; } -static void dm_flush(struct mapped_device *md) -{ - dm_wait_for_completion(md, TASK_UNINTERRUPTIBLE); - - bio_init(&md->barrier_bio); - md->barrier_bio.bi_bdev = md->bdev; - md->barrier_bio.bi_rw = WRITE_BARRIER; - __split_and_process_bio(md, &md->barrier_bio); - - dm_wait_for_completion(md, TASK_UNINTERRUPTIBLE); -} - -static void process_barrier(struct mapped_device *md, struct bio *bio) -{ - md->barrier_error = 0; - - dm_flush(md); - - if (!bio_empty_barrier(bio)) { - __split_and_process_bio(md, bio); - dm_flush(md); - } - - if (md->barrier_error != DM_ENDIO_REQUEUE) - bio_endio(bio, md->barrier_error); - else { - spin_lock_irq(&md->deferred_lock); - bio_list_add_head(&md->deferred, bio); - spin_unlock_irq(&md->deferred_lock); - } -} - /* * Process the deferred bios */ @@ -2265,116 +2490,41 @@ static void dm_wq_work(struct work_struct *work) struct mapped_device *md = container_of(work, struct mapped_device, work); struct bio *c; + int srcu_idx; + struct dm_table *map; - down_write(&md->io_lock); + map = dm_get_live_table(md, &srcu_idx); while (!test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags)) { spin_lock_irq(&md->deferred_lock); c = bio_list_pop(&md->deferred); spin_unlock_irq(&md->deferred_lock); - if (!c) { - clear_bit(DMF_QUEUE_IO_TO_THREAD, &md->flags); + if (!c) break; - } - - up_write(&md->io_lock); if (dm_request_based(md)) generic_make_request(c); - else { - if (bio_rw_flagged(c, BIO_RW_BARRIER)) - process_barrier(md, c); - else - __split_and_process_bio(md, c); - } - - down_write(&md->io_lock); + else + __split_and_process_bio(md, map, c); } - up_write(&md->io_lock); + dm_put_live_table(md, srcu_idx); } static void dm_queue_flush(struct mapped_device *md) { clear_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags); - smp_mb__after_clear_bit(); + smp_mb__after_atomic(); queue_work(md->wq, &md->work); } -static void dm_rq_set_flush_nr(struct request *clone, unsigned flush_nr) -{ - struct dm_rq_target_io *tio = clone->end_io_data; - - tio->info.flush_request = flush_nr; -} - -/* Issue barrier requests to targets and wait for their completion. */ -static int dm_rq_barrier(struct mapped_device *md) -{ - int i, j; - struct dm_table *map = dm_get_live_table(md); - unsigned num_targets = dm_table_get_num_targets(map); - struct dm_target *ti; - struct request *clone; - - md->barrier_error = 0; - - for (i = 0; i < num_targets; i++) { - ti = dm_table_get_target(map, i); - for (j = 0; j < ti->num_flush_requests; j++) { - clone = clone_rq(md->flush_request, md, GFP_NOIO); - dm_rq_set_flush_nr(clone, j); - atomic_inc(&md->pending[rq_data_dir(clone)]); - map_request(ti, clone, md); - } - } - - dm_wait_for_completion(md, TASK_UNINTERRUPTIBLE); - dm_table_put(map); - - return md->barrier_error; -} - -static void dm_rq_barrier_work(struct work_struct *work) -{ - int error; - struct mapped_device *md = container_of(work, struct mapped_device, - barrier_work); - struct request_queue *q = md->queue; - struct request *rq; - unsigned long flags; - - /* - * Hold the md reference here and leave it at the last part so that - * the md can't be deleted by device opener when the barrier request - * completes. - */ - dm_get(md); - - error = dm_rq_barrier(md); - - rq = md->flush_request; - md->flush_request = NULL; - - if (error == DM_ENDIO_REQUEUE) { - spin_lock_irqsave(q->queue_lock, flags); - blk_requeue_request(q, rq); - spin_unlock_irqrestore(q->queue_lock, flags); - } else - blk_end_request_all(rq, error); - - blk_run_queue(q); - - dm_put(md); -} - /* * Swap in a new table, returning the old one for the caller to destroy. */ struct dm_table *dm_swap_table(struct mapped_device *md, struct dm_table *table) { - struct dm_table *map = ERR_PTR(-EINVAL); + struct dm_table *live_map = NULL, *map = ERR_PTR(-EINVAL); struct queue_limits limits; int r; @@ -2384,17 +2534,25 @@ struct dm_table *dm_swap_table(struct mapped_device *md, struct dm_table *table) if (!dm_suspended_md(md)) goto out; - r = dm_calculate_queue_limits(table, &limits); - if (r) { - map = ERR_PTR(r); - goto out; + /* + * If the new table has no data devices, retain the existing limits. + * This helps multipath with queue_if_no_path if all paths disappear, + * then new I/O is queued based on these limits, and then some paths + * reappear. + */ + if (dm_table_has_no_data_devices(table)) { + live_map = dm_get_live_table_fast(md); + if (live_map) + limits = md->queue->limits; + dm_put_live_table_fast(md); } - /* cannot change the device type, once a table is bound */ - if (md->map && - (dm_table_get_type(md->map) != dm_table_get_type(table))) { - DMWARN("can't change the device type after a table is bound"); - goto out; + if (!live_map) { + r = dm_calculate_queue_limits(table, &limits); + if (r) { + map = ERR_PTR(r); + goto out; + } } map = __bind(md, table, &limits); @@ -2466,7 +2624,7 @@ int dm_suspend(struct mapped_device *md, unsigned suspend_flags) goto out_unlock; } - map = dm_get_live_table(md); + map = md->map; /* * DMF_NOFLUSH_SUSPENDING must be set before presuspend. @@ -2487,7 +2645,7 @@ int dm_suspend(struct mapped_device *md, unsigned suspend_flags) if (!noflush && do_lockfs) { r = lock_fs(md); if (r) - goto out; + goto out_unlock; } /* @@ -2498,23 +2656,16 @@ int dm_suspend(struct mapped_device *md, unsigned suspend_flags) * * To get all processes out of __split_and_process_bio in dm_request, * we take the write lock. To prevent any process from reentering - * __split_and_process_bio from dm_request, we set - * DMF_QUEUE_IO_TO_THREAD. - * - * To quiesce the thread (dm_wq_work), we set DMF_BLOCK_IO_FOR_SUSPEND - * and call flush_workqueue(md->wq). flush_workqueue will wait until - * dm_wq_work exits and DMF_BLOCK_IO_FOR_SUSPEND will prevent any - * further calls to __split_and_process_bio from dm_wq_work. + * __split_and_process_bio from dm_request and quiesce the thread + * (dm_wq_work), we set BMF_BLOCK_IO_FOR_SUSPEND and call + * flush_workqueue(md->wq). */ - down_write(&md->io_lock); set_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags); - set_bit(DMF_QUEUE_IO_TO_THREAD, &md->flags); - up_write(&md->io_lock); + synchronize_srcu(&md->io_barrier); /* - * Request-based dm uses md->wq for barrier (dm_rq_barrier_work) which - * can be kicked until md->queue is stopped. So stop md->queue before - * flushing md->wq. + * Stop md->queue before flushing md->wq in case request-based + * dm defers requests to md->wq from md->queue. */ if (dm_request_based(md)) stop_queue(md->queue); @@ -2528,10 +2679,9 @@ int dm_suspend(struct mapped_device *md, unsigned suspend_flags) */ r = dm_wait_for_completion(md, TASK_INTERRUPTIBLE); - down_write(&md->io_lock); if (noflush) clear_bit(DMF_NOFLUSH_SUSPENDING, &md->flags); - up_write(&md->io_lock); + synchronize_srcu(&md->io_barrier); /* were we interrupted ? */ if (r < 0) { @@ -2541,7 +2691,7 @@ int dm_suspend(struct mapped_device *md, unsigned suspend_flags) start_queue(md->queue); unlock_fs(md); - goto out; /* pushback list is already flushed, so skip flush */ + goto out_unlock; /* pushback list is already flushed, so skip flush */ } /* @@ -2554,9 +2704,6 @@ int dm_suspend(struct mapped_device *md, unsigned suspend_flags) dm_table_postsuspend_targets(map); -out: - dm_table_put(map); - out_unlock: mutex_unlock(&md->suspend_lock); return r; @@ -2571,7 +2718,7 @@ int dm_resume(struct mapped_device *md) if (!dm_suspended_md(md)) goto out; - map = dm_get_live_table(md); + map = md->map; if (!map || !dm_table_get_size(map)) goto out; @@ -2593,30 +2740,61 @@ int dm_resume(struct mapped_device *md) clear_bit(DMF_SUSPENDED, &md->flags); - dm_table_unplug_all(map); r = 0; out: - dm_table_put(map); mutex_unlock(&md->suspend_lock); return r; } +/* + * Internal suspend/resume works like userspace-driven suspend. It waits + * until all bios finish and prevents issuing new bios to the target drivers. + * It may be used only from the kernel. + * + * Internal suspend holds md->suspend_lock, which prevents interaction with + * userspace-driven suspend. + */ + +void dm_internal_suspend(struct mapped_device *md) +{ + mutex_lock(&md->suspend_lock); + if (dm_suspended_md(md)) + return; + + set_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags); + synchronize_srcu(&md->io_barrier); + flush_workqueue(md->wq); + dm_wait_for_completion(md, TASK_UNINTERRUPTIBLE); +} + +void dm_internal_resume(struct mapped_device *md) +{ + if (dm_suspended_md(md)) + goto done; + + dm_queue_flush(md); + +done: + mutex_unlock(&md->suspend_lock); +} + /*----------------------------------------------------------------- * Event notification. *---------------------------------------------------------------*/ -void dm_kobject_uevent(struct mapped_device *md, enum kobject_action action, +int dm_kobject_uevent(struct mapped_device *md, enum kobject_action action, unsigned cookie) { char udev_cookie[DM_COOKIE_LENGTH]; char *envp[] = { udev_cookie, NULL }; if (!cookie) - kobject_uevent(&disk_to_dev(md->disk)->kobj, action); + return kobject_uevent(&disk_to_dev(md->disk)->kobj, action); else { snprintf(udev_cookie, DM_COOKIE_LENGTH, "%s=%u", DM_COOKIE_ENV_VAR_NAME, cookie); - kobject_uevent_env(&disk_to_dev(md->disk)->kobj, action, envp); + return kobject_uevent_env(&disk_to_dev(md->disk)->kobj, + action, envp); } } @@ -2656,20 +2834,14 @@ struct gendisk *dm_disk(struct mapped_device *md) struct kobject *dm_kobject(struct mapped_device *md) { - return &md->kobj; + return &md->kobj_holder.kobj; } -/* - * struct mapped_device should not be exported outside of dm.c - * so use this check to verify that kobj is part of md structure - */ struct mapped_device *dm_get_from_kobject(struct kobject *kobj) { struct mapped_device *md; - md = container_of(kobj, struct mapped_device, kobj); - if (&md->kobj != kobj) - return NULL; + md = container_of(kobj, struct mapped_device, kobj_holder.kobj); if (test_bit(DMF_FREEING, &md->flags) || dm_deleting_md(md)) @@ -2684,62 +2856,61 @@ int dm_suspended_md(struct mapped_device *md) return test_bit(DMF_SUSPENDED, &md->flags); } -int dm_suspended(struct dm_target *ti) +int dm_test_deferred_remove_flag(struct mapped_device *md) { - struct mapped_device *md = dm_table_get_md(ti->table); - int r = dm_suspended_md(md); - - dm_put(md); + return test_bit(DMF_DEFERRED_REMOVE, &md->flags); +} - return r; +int dm_suspended(struct dm_target *ti) +{ + return dm_suspended_md(dm_table_get_md(ti->table)); } EXPORT_SYMBOL_GPL(dm_suspended); int dm_noflush_suspending(struct dm_target *ti) { - struct mapped_device *md = dm_table_get_md(ti->table); - int r = __noflush_suspending(md); - - dm_put(md); - - return r; + return __noflush_suspending(dm_table_get_md(ti->table)); } EXPORT_SYMBOL_GPL(dm_noflush_suspending); -struct dm_md_mempools *dm_alloc_md_mempools(unsigned type) +struct dm_md_mempools *dm_alloc_md_mempools(unsigned type, unsigned integrity, unsigned per_bio_data_size) { - struct dm_md_mempools *pools = kmalloc(sizeof(*pools), GFP_KERNEL); + struct dm_md_mempools *pools = kzalloc(sizeof(*pools), GFP_KERNEL); + struct kmem_cache *cachep; + unsigned int pool_size; + unsigned int front_pad; if (!pools) return NULL; - pools->io_pool = (type == DM_TYPE_BIO_BASED) ? - mempool_create_slab_pool(MIN_IOS, _io_cache) : - mempool_create_slab_pool(MIN_IOS, _rq_bio_info_cache); - if (!pools->io_pool) - goto free_pools_and_out; + if (type == DM_TYPE_BIO_BASED) { + cachep = _io_cache; + pool_size = dm_get_reserved_bio_based_ios(); + front_pad = roundup(per_bio_data_size, __alignof__(struct dm_target_io)) + offsetof(struct dm_target_io, clone); + } else if (type == DM_TYPE_REQUEST_BASED) { + cachep = _rq_tio_cache; + pool_size = dm_get_reserved_rq_based_ios(); + front_pad = offsetof(struct dm_rq_clone_bio_info, clone); + /* per_bio_data_size is not used. See __bind_mempools(). */ + WARN_ON(per_bio_data_size != 0); + } else + goto out; - pools->tio_pool = (type == DM_TYPE_BIO_BASED) ? - mempool_create_slab_pool(MIN_IOS, _tio_cache) : - mempool_create_slab_pool(MIN_IOS, _rq_tio_cache); - if (!pools->tio_pool) - goto free_io_pool_and_out; + pools->io_pool = mempool_create_slab_pool(pool_size, cachep); + if (!pools->io_pool) + goto out; - pools->bs = (type == DM_TYPE_BIO_BASED) ? - bioset_create(16, 0) : bioset_create(MIN_IOS, 0); + pools->bs = bioset_create(pool_size, front_pad); if (!pools->bs) - goto free_tio_pool_and_out; - - return pools; + goto out; -free_tio_pool_and_out: - mempool_destroy(pools->tio_pool); + if (integrity && bioset_integrity_create(pools->bs, pool_size)) + goto out; -free_io_pool_and_out: - mempool_destroy(pools->io_pool); + return pools; -free_pools_and_out: - kfree(pools); +out: + dm_free_md_mempools(pools); return NULL; } @@ -2752,9 +2923,6 @@ void dm_free_md_mempools(struct dm_md_mempools *pools) if (pools->io_pool) mempool_destroy(pools->io_pool); - if (pools->tio_pool) - mempool_destroy(pools->tio_pool); - if (pools->bs) bioset_free(pools->bs); @@ -2769,8 +2937,6 @@ static const struct block_device_operations dm_blk_dops = { .owner = THIS_MODULE }; -EXPORT_SYMBOL(dm_get_mapinfo); - /* * module hooks */ @@ -2779,6 +2945,13 @@ module_exit(dm_exit); module_param(major, uint, 0); MODULE_PARM_DESC(major, "The major number of the device mapper"); + +module_param(reserved_bio_based_ios, uint, S_IRUGO | S_IWUSR); +MODULE_PARM_DESC(reserved_bio_based_ios, "Reserved IOs in bio-based mempools"); + +module_param(reserved_rq_based_ios, uint, S_IRUGO | S_IWUSR); +MODULE_PARM_DESC(reserved_rq_based_ios, "Reserved IOs in request-based mempools"); + MODULE_DESCRIPTION(DM_NAME " driver"); MODULE_AUTHOR("Joe Thornber <dm-devel@redhat.com>"); MODULE_LICENSE("GPL"); |