diff options
Diffstat (limited to 'drivers/md/dm.c')
-rw-r--r-- | drivers/md/dm.c | 356 |
1 files changed, 193 insertions, 163 deletions
diff --git a/drivers/md/dm.c b/drivers/md/dm.c index ab37ae114e94..32440ad5f684 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -24,6 +24,7 @@ #include <linux/ktime.h> #include <linux/elevator.h> /* for rq_end_sector() */ #include <linux/blk-mq.h> +#include <linux/pr.h> #include <trace/events/block.h> @@ -124,9 +125,8 @@ EXPORT_SYMBOL_GPL(dm_get_rq_mapinfo); #define DMF_FREEING 3 #define DMF_DELETING 4 #define DMF_NOFLUSH_SUSPENDING 5 -#define DMF_MERGE_IS_OPTIONAL 6 -#define DMF_DEFERRED_REMOVE 7 -#define DMF_SUSPENDED_INTERNALLY 8 +#define DMF_DEFERRED_REMOVE 6 +#define DMF_SUSPENDED_INTERNALLY 7 /* * A dummy definition to make RCU happy. @@ -556,18 +556,16 @@ static int dm_blk_getgeo(struct block_device *bdev, struct hd_geometry *geo) return dm_get_geometry(md, geo); } -static int dm_blk_ioctl(struct block_device *bdev, fmode_t mode, - unsigned int cmd, unsigned long arg) +static int dm_get_live_table_for_ioctl(struct mapped_device *md, + struct dm_target **tgt, struct block_device **bdev, + fmode_t *mode, int *srcu_idx) { - struct mapped_device *md = bdev->bd_disk->private_data; - int srcu_idx; struct dm_table *map; - struct dm_target *tgt; - int r = -ENOTTY; + int r; retry: - map = dm_get_live_table(md, &srcu_idx); - + r = -ENOTTY; + map = dm_get_live_table(md, srcu_idx); if (!map || !dm_table_get_size(map)) goto out; @@ -575,8 +573,9 @@ retry: if (dm_table_get_num_targets(map) != 1) goto out; - tgt = dm_table_get_target(map, 0); - if (!tgt->type->ioctl) + *tgt = dm_table_get_target(map, 0); + + if (!(*tgt)->type->prepare_ioctl) goto out; if (dm_suspended_md(md)) { @@ -584,16 +583,46 @@ retry: goto out; } - r = tgt->type->ioctl(tgt, cmd, arg); + r = (*tgt)->type->prepare_ioctl(*tgt, bdev, mode); + if (r < 0) + goto out; + + return r; out: - dm_put_live_table(md, srcu_idx); - + dm_put_live_table(md, *srcu_idx); if (r == -ENOTCONN) { msleep(10); goto retry; } + return r; +} +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_target *tgt; + int srcu_idx, r; + + r = dm_get_live_table_for_ioctl(md, &tgt, &bdev, &mode, &srcu_idx); + if (r < 0) + return r; + + if (r > 0) { + /* + * Target determined this ioctl is being issued against + * a logical partition of the parent bdev; so extra + * validation is needed. + */ + r = scsi_verify_blk_ioctl(NULL, cmd); + if (r) + goto out; + } + + r = __blkdev_driver_ioctl(bdev, mode, cmd, arg); +out: + dm_put_live_table(md, srcu_idx); return r; } @@ -944,7 +973,8 @@ static void dec_pending(struct dm_io *io, int error) } else { /* done with normal IO or empty flush */ trace_block_bio_complete(md->queue, bio, io_error); - bio_endio(bio, io_error); + bio->bi_error = io_error; + bio_endio(bio); } } } @@ -957,17 +987,15 @@ static void disable_write_same(struct mapped_device *md) limits->max_write_same_sectors = 0; } -static void clone_endio(struct bio *bio, int error) +static void clone_endio(struct bio *bio) { + int error = bio->bi_error; int r = error; 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; - if (!bio_flagged(bio, BIO_UPTODATE) && !error) - error = -EIO; - if (endio) { r = endio(tio->ti, bio, error); if (r < 0 || r == DM_ENDIO_REQUEUE) @@ -996,13 +1024,14 @@ static void clone_endio(struct bio *bio, int error) /* * Partial completion handling for request-based dm */ -static void end_clone_bio(struct bio *clone, int error) +static void end_clone_bio(struct bio *clone) { 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_iter.bi_size; + int error = clone->bi_error; bio_put(clone); @@ -1466,7 +1495,7 @@ static void __map_bio(struct dm_target_io *tio) md = tio->io->md; dec_pending(tio->io, r); free_tio(md, tio); - } else if (r) { + } else if (r != DM_MAPIO_SUBMITTED) { DMWARN("unimplemented target map return value: %d", r); BUG(); } @@ -1722,67 +1751,6 @@ static void __split_and_process_bio(struct mapped_device *md, * CRUD END *---------------------------------------------------------------*/ -static int dm_merge_bvec(struct request_queue *q, - struct bvec_merge_data *bvm, - struct bio_vec *biovec) -{ - struct mapped_device *md = q->queuedata; - struct dm_table *map = dm_get_live_table_fast(md); - struct dm_target *ti; - sector_t max_sectors, max_size = 0; - - if (unlikely(!map)) - goto out; - - ti = dm_table_find_target(map, bvm->bi_sector); - if (!dm_target_is_valid(ti)) - goto out; - - /* - * Find maximum amount of I/O that won't need splitting - */ - max_sectors = min(max_io_len(bvm->bi_sector, ti), - (sector_t) queue_max_sectors(q)); - max_size = (max_sectors << SECTOR_SHIFT) - bvm->bi_size; - - /* - * FIXME: this stop-gap fix _must_ be cleaned up (by passing a sector_t - * to the targets' merge function since it holds sectors not bytes). - * Just doing this as an interim fix for stable@ because the more - * comprehensive cleanup of switching to sector_t will impact every - * DM target that implements a ->merge hook. - */ - if (max_size > INT_MAX) - max_size = INT_MAX; - - /* - * merge_bvec_fn() returns number of bytes - * it can accept at this offset - * max is precomputed maximal io size - */ - if (max_size && ti->type->merge) - max_size = ti->type->merge(ti, bvm, biovec, (int) max_size); - /* - * If the target doesn't support merge method and some of the devices - * provided their merge_bvec method (we know this by looking for the - * max_hw_sectors that dm_set_device_limits may set), then we can't - * allow bios with multiple vector entries. So always set max_size - * to 0, and the code below allows just one page. - */ - else if (queue_max_hw_sectors(q) <= PAGE_SIZE >> 9) - max_size = 0; - -out: - dm_put_live_table_fast(md); - /* - * Always allow an entire first page - */ - if (max_size <= biovec->bv_len && !(bvm->bi_size >> SECTOR_SHIFT)) - max_size = biovec->bv_len; - - return max_size; -} - /* * The request function that just remaps the bio built up by * dm_merge_bvec. @@ -2258,6 +2226,13 @@ static void dm_init_md_queue(struct mapped_device *md) * This queue is new, so no concurrency on the queue_flags. */ queue_flag_clear_unlocked(QUEUE_FLAG_STACKABLE, md->queue); + + /* + * Initialize data that will only be used by a non-blk-mq DM queue + * - must do so here (in alloc_dev callchain) before queue is used + */ + md->queue->queuedata = md; + md->queue->backing_dev_info.congested_data = md; } static void dm_init_old_md_queue(struct mapped_device *md) @@ -2268,10 +2243,7 @@ static void dm_init_old_md_queue(struct mapped_device *md) /* * Initialize aspects of queue that aren't relevant for blk-mq */ - md->queue->queuedata = md; md->queue->backing_dev_info.congested_fn = dm_any_congested; - md->queue->backing_dev_info.congested_data = md; - blk_queue_bounce_limit(md->queue, BLK_BOUNCE_ANY); } @@ -2281,10 +2253,8 @@ static void cleanup_mapped_device(struct mapped_device *md) destroy_workqueue(md->wq); if (md->kworker_task) kthread_stop(md->kworker_task); - if (md->io_pool) - mempool_destroy(md->io_pool); - if (md->rq_pool) - mempool_destroy(md->rq_pool); + mempool_destroy(md->io_pool); + mempool_destroy(md->rq_pool); if (md->bs) bioset_free(md->bs); @@ -2294,8 +2264,6 @@ static void cleanup_mapped_device(struct mapped_device *md) spin_lock(&_minor_lock); md->disk->private_data = NULL; spin_unlock(&_minor_lock); - if (blk_get_integrity(md->disk)) - blk_integrity_unregister(md->disk); del_gendisk(md->disk); put_disk(md->disk); } @@ -2503,59 +2471,6 @@ static void __set_size(struct mapped_device *md, sector_t size) } /* - * 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_make_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; -} - -/* * Returns old map, which caller must destroy. */ static struct dm_table *__bind(struct mapped_device *md, struct dm_table *t, @@ -2564,7 +2479,6 @@ 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; - int merge_is_optional; size = dm_table_get_size(t); @@ -2590,17 +2504,11 @@ static struct dm_table *__bind(struct mapped_device *md, struct dm_table *t, __bind_mempools(md, t); - merge_is_optional = dm_table_merge_is_optional(t); - old_map = rcu_dereference_protected(md->map, lockdep_is_held(&md->suspend_lock)); rcu_assign_pointer(md->map, t); md->immutable_target_type = dm_table_get_immutable_target_type(t); dm_table_set_restrictions(t, q, limits); - if (merge_is_optional) - set_bit(DMF_MERGE_IS_OPTIONAL, &md->flags); - else - clear_bit(DMF_MERGE_IS_OPTIONAL, &md->flags); if (old_map) dm_sync_table(md); @@ -2881,7 +2789,12 @@ int dm_setup_md_queue(struct mapped_device *md) case DM_TYPE_BIO_BASED: dm_init_old_md_queue(md); blk_queue_make_request(md->queue, dm_make_request); - blk_queue_merge_bvec(md->queue, dm_merge_bvec); + /* + * DM handles splitting bios as needed. Free the bio_split bioset + * since it won't be used (saves 1 process per bio-based DM device). + */ + bioset_free(md->queue->bio_split); + md->queue->bio_split = NULL; break; } @@ -2959,8 +2872,6 @@ static void __dm_destroy(struct mapped_device *md, bool wait) might_sleep(); - map = dm_get_live_table(md, &srcu_idx); - spin_lock(&_minor_lock); idr_replace(&_minor_idr, MINOR_ALLOCED, MINOR(disk_devt(dm_disk(md)))); set_bit(DMF_FREEING, &md->flags); @@ -2974,14 +2885,14 @@ static void __dm_destroy(struct mapped_device *md, bool wait) * do not race with internal suspend. */ mutex_lock(&md->suspend_lock); + map = dm_get_live_table(md, &srcu_idx); if (!dm_suspended_md(md)) { dm_table_presuspend_targets(map); dm_table_postsuspend_targets(map); } - mutex_unlock(&md->suspend_lock); - /* dm_put_live_table must be before msleep, otherwise deadlock is possible */ dm_put_live_table(md, srcu_idx); + mutex_unlock(&md->suspend_lock); /* * Rare, but there may be I/O requests still going to complete, @@ -3630,11 +3541,8 @@ void dm_free_md_mempools(struct dm_md_mempools *pools) if (!pools) return; - if (pools->io_pool) - mempool_destroy(pools->io_pool); - - if (pools->rq_pool) - mempool_destroy(pools->rq_pool); + mempool_destroy(pools->io_pool); + mempool_destroy(pools->rq_pool); if (pools->bs) bioset_free(pools->bs); @@ -3642,11 +3550,133 @@ void dm_free_md_mempools(struct dm_md_mempools *pools) kfree(pools); } +static int dm_pr_register(struct block_device *bdev, u64 old_key, u64 new_key, + u32 flags) +{ + struct mapped_device *md = bdev->bd_disk->private_data; + const struct pr_ops *ops; + struct dm_target *tgt; + fmode_t mode; + int srcu_idx, r; + + r = dm_get_live_table_for_ioctl(md, &tgt, &bdev, &mode, &srcu_idx); + if (r < 0) + return r; + + ops = bdev->bd_disk->fops->pr_ops; + if (ops && ops->pr_register) + r = ops->pr_register(bdev, old_key, new_key, flags); + else + r = -EOPNOTSUPP; + + dm_put_live_table(md, srcu_idx); + return r; +} + +static int dm_pr_reserve(struct block_device *bdev, u64 key, enum pr_type type, + u32 flags) +{ + struct mapped_device *md = bdev->bd_disk->private_data; + const struct pr_ops *ops; + struct dm_target *tgt; + fmode_t mode; + int srcu_idx, r; + + r = dm_get_live_table_for_ioctl(md, &tgt, &bdev, &mode, &srcu_idx); + if (r < 0) + return r; + + ops = bdev->bd_disk->fops->pr_ops; + if (ops && ops->pr_reserve) + r = ops->pr_reserve(bdev, key, type, flags); + else + r = -EOPNOTSUPP; + + dm_put_live_table(md, srcu_idx); + return r; +} + +static int dm_pr_release(struct block_device *bdev, u64 key, enum pr_type type) +{ + struct mapped_device *md = bdev->bd_disk->private_data; + const struct pr_ops *ops; + struct dm_target *tgt; + fmode_t mode; + int srcu_idx, r; + + r = dm_get_live_table_for_ioctl(md, &tgt, &bdev, &mode, &srcu_idx); + if (r < 0) + return r; + + ops = bdev->bd_disk->fops->pr_ops; + if (ops && ops->pr_release) + r = ops->pr_release(bdev, key, type); + else + r = -EOPNOTSUPP; + + dm_put_live_table(md, srcu_idx); + return r; +} + +static int dm_pr_preempt(struct block_device *bdev, u64 old_key, u64 new_key, + enum pr_type type, bool abort) +{ + struct mapped_device *md = bdev->bd_disk->private_data; + const struct pr_ops *ops; + struct dm_target *tgt; + fmode_t mode; + int srcu_idx, r; + + r = dm_get_live_table_for_ioctl(md, &tgt, &bdev, &mode, &srcu_idx); + if (r < 0) + return r; + + ops = bdev->bd_disk->fops->pr_ops; + if (ops && ops->pr_preempt) + r = ops->pr_preempt(bdev, old_key, new_key, type, abort); + else + r = -EOPNOTSUPP; + + dm_put_live_table(md, srcu_idx); + return r; +} + +static int dm_pr_clear(struct block_device *bdev, u64 key) +{ + struct mapped_device *md = bdev->bd_disk->private_data; + const struct pr_ops *ops; + struct dm_target *tgt; + fmode_t mode; + int srcu_idx, r; + + r = dm_get_live_table_for_ioctl(md, &tgt, &bdev, &mode, &srcu_idx); + if (r < 0) + return r; + + ops = bdev->bd_disk->fops->pr_ops; + if (ops && ops->pr_clear) + r = ops->pr_clear(bdev, key); + else + r = -EOPNOTSUPP; + + dm_put_live_table(md, srcu_idx); + return r; +} + +static const struct pr_ops dm_pr_ops = { + .pr_register = dm_pr_register, + .pr_reserve = dm_pr_reserve, + .pr_release = dm_pr_release, + .pr_preempt = dm_pr_preempt, + .pr_clear = dm_pr_clear, +}; + static const struct block_device_operations dm_blk_dops = { .open = dm_blk_open, .release = dm_blk_close, .ioctl = dm_blk_ioctl, .getgeo = dm_blk_getgeo, + .pr_ops = &dm_pr_ops, .owner = THIS_MODULE }; |