diff options
Diffstat (limited to 'drivers/md/dm.c')
| -rw-r--r-- | drivers/md/dm.c | 189 |
1 files changed, 102 insertions, 87 deletions
diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 109e81f33edb..87cf45f619fd 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -12,6 +12,7 @@ #include <linux/init.h> #include <linux/module.h> #include <linux/mutex.h> +#include <linux/sched/mm.h> #include <linux/sched/signal.h> #include <linux/blkpg.h> #include <linux/bio.h> @@ -142,6 +143,7 @@ EXPORT_SYMBOL_GPL(dm_bio_get_target_bio_nr); #define DMF_NOFLUSH_SUSPENDING 5 #define DMF_DEFERRED_REMOVE 6 #define DMF_SUSPENDED_INTERNALLY 7 +#define DMF_POST_SUSPENDING 8 #define DM_NUMA_NODE NUMA_NO_NODE static int dm_numa_node = DM_NUMA_NODE; @@ -654,28 +656,6 @@ static void free_tio(struct dm_target_io *tio) bio_put(&tio->clone); } -static bool md_in_flight_bios(struct mapped_device *md) -{ - int cpu; - struct hd_struct *part = &dm_disk(md)->part0; - long sum = 0; - - for_each_possible_cpu(cpu) { - sum += part_stat_local_read_cpu(part, in_flight[0], cpu); - sum += part_stat_local_read_cpu(part, in_flight[1], cpu); - } - - return sum != 0; -} - -static bool md_in_flight(struct mapped_device *md) -{ - if (queue_is_mq(md->queue)) - return blk_mq_queue_inflight(md->queue); - else - return md_in_flight_bios(md); -} - u64 dm_start_time_ns_from_clone(struct bio *bio) { struct dm_target_io *tio = container_of(bio, struct dm_target_io, clone); @@ -1009,6 +989,7 @@ static void clone_endio(struct bio *bio) struct dm_io *io = tio->io; struct mapped_device *md = tio->io->md; dm_endio_fn endio = tio->ti->type->end_io; + struct bio *orig_bio = io->orig_bio; if (unlikely(error == BLK_STS_TARGET) && md->type != DM_TYPE_NVME_BIO_BASED) { if (bio_op(bio) == REQ_OP_DISCARD && @@ -1022,6 +1003,18 @@ static void clone_endio(struct bio *bio) disable_write_zeroes(md); } + /* + * For zone-append bios get offset in zone of the written + * sector and add that to the original bio sector pos. + */ + if (bio_op(orig_bio) == REQ_OP_ZONE_APPEND) { + sector_t written_sector = bio->bi_iter.bi_sector; + struct request_queue *q = orig_bio->bi_disk->queue; + u64 mask = (u64)blk_queue_zone_sectors(q) - 1; + + orig_bio->bi_iter.bi_sector += written_sector & mask; + } + if (endio) { int r = endio(tio->ti, bio, &error); switch (r) { @@ -1280,7 +1273,6 @@ static blk_qc_t __map_bio(struct dm_target_io *tio) sector_t sector; struct bio *clone = &tio->clone; struct dm_io *io = tio->io; - struct mapped_device *md = io->md; struct dm_target *ti = tio->ti; blk_qc_t ret = BLK_QC_T_NONE; @@ -1302,10 +1294,7 @@ static blk_qc_t __map_bio(struct dm_target_io *tio) /* the bio has been remapped so dispatch it */ trace_block_bio_remap(clone->bi_disk->queue, clone, bio_dev(io->orig_bio), sector); - if (md->type == DM_TYPE_NVME_BIO_BASED) - ret = direct_make_request(clone); - else - ret = generic_make_request(clone); + ret = submit_bio_noacct(clone); break; case DM_MAPIO_KILL: free_tio(tio); @@ -1452,9 +1441,6 @@ static int __send_empty_flush(struct clone_info *ci) BUG_ON(bio_has_data(ci->bio)); while ((ti = dm_table_get_target(ci->map, target_nr++))) __send_duplicate_bios(ci, ti, ti->num_flush_bios, NULL); - - bio_disassociate_blkg(ci->bio); - return 0; } @@ -1642,6 +1628,7 @@ static blk_qc_t __split_and_process_bio(struct mapped_device *md, ci.bio = &flush_bio; ci.sector_count = 0; error = __send_empty_flush(&ci); + bio_uninit(ci.bio); /* dec_pending submits any data associated with flush */ } else if (op_is_zone_mgmt(bio_op(bio))) { ci.bio = bio; @@ -1654,7 +1641,7 @@ static blk_qc_t __split_and_process_bio(struct mapped_device *md, error = __split_and_process_non_flush(&ci); if (current->bio_list && ci.sector_count && !error) { /* - * Remainder must be passed to generic_make_request() + * Remainder must be passed to submit_bio_noacct() * so that it gets handled *after* bios already submitted * have been completely processed. * We take a clone of the original to store in @@ -1679,7 +1666,7 @@ static blk_qc_t __split_and_process_bio(struct mapped_device *md, bio_chain(b, bio); trace_block_split(md->queue, b, bio->bi_iter.bi_sector); - ret = generic_make_request(bio); + ret = submit_bio_noacct(bio); break; } } @@ -1716,6 +1703,7 @@ static blk_qc_t __process_bio(struct mapped_device *md, struct dm_table *map, ci.bio = &flush_bio; ci.sector_count = 0; error = __send_empty_flush(&ci); + bio_uninit(ci.bio); /* dec_pending submits any data associated with flush */ } else { struct dm_target_io *tio; @@ -1746,7 +1734,7 @@ static void dm_queue_split(struct mapped_device *md, struct dm_target *ti, struc bio_chain(split, *bio); trace_block_split(md->queue, split, (*bio)->bi_iter.bi_sector); - generic_make_request(*bio); + submit_bio_noacct(*bio); *bio = split; } } @@ -1771,13 +1759,13 @@ static blk_qc_t dm_process_bio(struct mapped_device *md, } /* - * If in ->make_request_fn we need to use blk_queue_split(), otherwise + * If in ->queue_bio we need to use blk_queue_split(), otherwise * queue_limits for abnormal requests (e.g. discard, writesame, etc) * won't be imposed. */ if (current->bio_list) { if (is_abnormal_io(bio)) - blk_queue_split(md->queue, &bio); + blk_queue_split(&bio); else dm_queue_split(md, ti, &bio); } @@ -1788,9 +1776,9 @@ static blk_qc_t dm_process_bio(struct mapped_device *md, return __split_and_process_bio(md, map, bio); } -static blk_qc_t dm_make_request(struct request_queue *q, struct bio *bio) +static blk_qc_t dm_submit_bio(struct bio *bio) { - struct mapped_device *md = q->queuedata; + struct mapped_device *md = bio->bi_disk->private_data; blk_qc_t ret = BLK_QC_T_NONE; int srcu_idx; struct dm_table *map; @@ -1799,12 +1787,12 @@ static blk_qc_t dm_make_request(struct request_queue *q, struct bio *bio) /* * We are called with a live reference on q_usage_counter, but * that one will be released as soon as we return. Grab an - * extra one as blk_mq_make_request expects to be able to - * consume a reference (which lives until the request is freed - * in case a request is allocated). + * extra one as blk_mq_submit_bio expects to be able to consume + * a reference (which lives until the request is freed in case a + * request is allocated). */ - percpu_ref_get(&q->q_usage_counter); - return blk_mq_make_request(q, bio); + percpu_ref_get(&bio->bi_disk->queue->q_usage_counter); + return blk_mq_submit_bio(bio); } map = dm_get_live_table(md, &srcu_idx); @@ -1826,31 +1814,6 @@ static blk_qc_t dm_make_request(struct request_queue *q, struct bio *bio) return ret; } -static int dm_any_congested(void *congested_data, int bdi_bits) -{ - int r = bdi_bits; - struct mapped_device *md = congested_data; - struct dm_table *map; - - if (!test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags)) { - if (dm_request_based(md)) { - /* - * With request-based DM we only need to check the - * top-level queue for congestion. - */ - struct backing_dev_info *bdi = md->queue->backing_dev_info; - r = bdi->wb.congested->state & bdi_bits; - } else { - map = dm_get_live_table_fast(md); - if (map) - r = dm_table_any_congested(map, bdi_bits); - dm_put_live_table_fast(md); - } - } - - return r; -} - /*----------------------------------------------------------------- * An IDR is used to keep track of allocated minor numbers. *---------------------------------------------------------------*/ @@ -1989,14 +1952,13 @@ static struct mapped_device *alloc_dev(int minor) spin_lock_init(&md->uevent_lock); /* - * default to bio-based required ->make_request_fn until DM - * table is loaded and md->type established. If request-based - * table is loaded: blk-mq will override accordingly. + * default to bio-based until DM table is loaded and md->type + * established. If request-based table is loaded: blk-mq will + * override accordingly. */ - md->queue = blk_alloc_queue(dm_make_request, numa_node_id); + md->queue = blk_alloc_queue(numa_node_id); if (!md->queue) goto bad; - md->queue->queuedata = md; md->disk = alloc_disk_node(1, md->numa_node_id); if (!md->disk) @@ -2290,12 +2252,6 @@ struct queue_limits *dm_get_queue_limits(struct mapped_device *md) } EXPORT_SYMBOL_GPL(dm_get_queue_limits); -static void dm_init_congested_fn(struct mapped_device *md) -{ - md->queue->backing_dev_info->congested_data = md; - md->queue->backing_dev_info->congested_fn = dm_any_congested; -} - /* * Setup the DM device's queue based on md's type */ @@ -2312,12 +2268,10 @@ int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t) DMERR("Cannot initialize queue for request-based dm-mq mapped device"); return r; } - dm_init_congested_fn(md); break; case DM_TYPE_BIO_BASED: case DM_TYPE_DAX_BIO_BASED: case DM_TYPE_NVME_BIO_BASED: - dm_init_congested_fn(md); break; case DM_TYPE_NONE: WARN_ON_ONCE(true); @@ -2417,6 +2371,7 @@ static void __dm_destroy(struct mapped_device *md, bool wait) if (!dm_suspended_md(md)) { dm_table_presuspend_targets(map); set_bit(DMF_SUSPENDED, &md->flags); + set_bit(DMF_POST_SUSPENDING, &md->flags); dm_table_postsuspend_targets(map); } /* dm_put_live_table must be before msleep, otherwise deadlock is possible */ @@ -2457,15 +2412,29 @@ void dm_put(struct mapped_device *md) } EXPORT_SYMBOL_GPL(dm_put); -static int dm_wait_for_completion(struct mapped_device *md, long task_state) +static bool md_in_flight_bios(struct mapped_device *md) +{ + int cpu; + struct hd_struct *part = &dm_disk(md)->part0; + long sum = 0; + + for_each_possible_cpu(cpu) { + sum += part_stat_local_read_cpu(part, in_flight[0], cpu); + sum += part_stat_local_read_cpu(part, in_flight[1], cpu); + } + + return sum != 0; +} + +static int dm_wait_for_bios_completion(struct mapped_device *md, long task_state) { int r = 0; DEFINE_WAIT(wait); - while (1) { + while (true) { prepare_to_wait(&md->wait, &wait, task_state); - if (!md_in_flight(md)) + if (!md_in_flight_bios(md)) break; if (signal_pending_state(task_state, current)) { @@ -2480,6 +2449,28 @@ static int dm_wait_for_completion(struct mapped_device *md, long task_state) return r; } +static int dm_wait_for_completion(struct mapped_device *md, long task_state) +{ + int r = 0; + + if (!queue_is_mq(md->queue)) + return dm_wait_for_bios_completion(md, task_state); + + while (true) { + if (!blk_mq_queue_inflight(md->queue)) + break; + + if (signal_pending_state(task_state, current)) { + r = -EINTR; + break; + } + + msleep(5); + } + + return r; +} + /* * Process the deferred bios */ @@ -2502,7 +2493,7 @@ static void dm_wq_work(struct work_struct *work) break; if (dm_request_based(md)) - (void) generic_make_request(c); + (void) submit_bio_noacct(c); else (void) dm_process_bio(md, map, c); } @@ -2739,7 +2730,9 @@ retry: if (r) goto out_unlock; + set_bit(DMF_POST_SUSPENDING, &md->flags); dm_table_postsuspend_targets(map); + clear_bit(DMF_POST_SUSPENDING, &md->flags); out_unlock: mutex_unlock(&md->suspend_lock); @@ -2836,7 +2829,9 @@ static void __dm_internal_suspend(struct mapped_device *md, unsigned suspend_fla (void) __dm_suspend(md, map, suspend_flags, TASK_UNINTERRUPTIBLE, DMF_SUSPENDED_INTERNALLY); + set_bit(DMF_POST_SUSPENDING, &md->flags); dm_table_postsuspend_targets(map); + clear_bit(DMF_POST_SUSPENDING, &md->flags); } static void __dm_internal_resume(struct mapped_device *md) @@ -2913,17 +2908,25 @@ EXPORT_SYMBOL_GPL(dm_internal_resume_fast); int dm_kobject_uevent(struct mapped_device *md, enum kobject_action action, unsigned cookie) { + int r; + unsigned noio_flag; char udev_cookie[DM_COOKIE_LENGTH]; char *envp[] = { udev_cookie, NULL }; + noio_flag = memalloc_noio_save(); + if (!cookie) - return kobject_uevent(&disk_to_dev(md->disk)->kobj, action); + r = kobject_uevent(&disk_to_dev(md->disk)->kobj, action); else { snprintf(udev_cookie, DM_COOKIE_LENGTH, "%s=%u", DM_COOKIE_ENV_VAR_NAME, cookie); - return kobject_uevent_env(&disk_to_dev(md->disk)->kobj, - action, envp); + r = kobject_uevent_env(&disk_to_dev(md->disk)->kobj, + action, envp); } + + memalloc_noio_restore(noio_flag); + + return r; } uint32_t dm_next_uevent_seq(struct mapped_device *md) @@ -2989,6 +2992,11 @@ int dm_suspended_md(struct mapped_device *md) return test_bit(DMF_SUSPENDED, &md->flags); } +static int dm_post_suspending_md(struct mapped_device *md) +{ + return test_bit(DMF_POST_SUSPENDING, &md->flags); +} + int dm_suspended_internally_md(struct mapped_device *md) { return test_bit(DMF_SUSPENDED_INTERNALLY, &md->flags); @@ -3005,6 +3013,12 @@ int dm_suspended(struct dm_target *ti) } EXPORT_SYMBOL_GPL(dm_suspended); +int dm_post_suspending(struct dm_target *ti) +{ + return dm_post_suspending_md(dm_table_get_md(ti->table)); +} +EXPORT_SYMBOL_GPL(dm_post_suspending); + int dm_noflush_suspending(struct dm_target *ti) { return __noflush_suspending(dm_table_get_md(ti->table)); @@ -3234,6 +3248,7 @@ static const struct pr_ops dm_pr_ops = { }; static const struct block_device_operations dm_blk_dops = { + .submit_bio = dm_submit_bio, .open = dm_blk_open, .release = dm_blk_close, .ioctl = dm_blk_ioctl, |