diff options
Diffstat (limited to 'drivers/md')
-rw-r--r-- | drivers/md/Kconfig | 16 | ||||
-rw-r--r-- | drivers/md/bcache/super.c | 8 | ||||
-rw-r--r-- | drivers/md/bcache/util.h | 12 | ||||
-rw-r--r-- | drivers/md/dm-bufio.c | 18 | ||||
-rw-r--r-- | drivers/md/dm-cache-background-tracker.c | 5 | ||||
-rw-r--r-- | drivers/md/dm-cache-metadata.c | 12 | ||||
-rw-r--r-- | drivers/md/dm-cache-policy-smq.c | 47 | ||||
-rw-r--r-- | drivers/md/dm-cache-target.c | 27 | ||||
-rw-r--r-- | drivers/md/dm-core.h | 1 | ||||
-rw-r--r-- | drivers/md/dm-ioctl.c | 13 | ||||
-rw-r--r-- | drivers/md/dm-linear.c | 27 | ||||
-rw-r--r-- | drivers/md/dm-mpath.c | 19 | ||||
-rw-r--r-- | drivers/md/dm-rq.c | 8 | ||||
-rw-r--r-- | drivers/md/dm-snap.c | 6 | ||||
-rw-r--r-- | drivers/md/dm-stats.c | 7 | ||||
-rw-r--r-- | drivers/md/dm-stripe.c | 29 | ||||
-rw-r--r-- | drivers/md/dm-target.c | 6 | ||||
-rw-r--r-- | drivers/md/dm-thin-metadata.c | 4 | ||||
-rw-r--r-- | drivers/md/dm.c | 67 | ||||
-rw-r--r-- | drivers/md/persistent-data/dm-space-map-disk.c | 15 |
20 files changed, 199 insertions, 148 deletions
diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig index 7468a22f9d10..906103c168ea 100644 --- a/drivers/md/Kconfig +++ b/drivers/md/Kconfig @@ -200,6 +200,7 @@ config BLK_DEV_DM_BUILTIN config BLK_DEV_DM tristate "Device mapper support" select BLK_DEV_DM_BUILTIN + select DAX ---help--- Device-mapper is a low level volume manager. It works by allowing people to specify mappings for ranges of logical sectors. Various @@ -502,13 +503,24 @@ config DM_LOG_WRITES If unsure, say N. config DM_INTEGRITY - tristate "Integrity target" + tristate "Integrity target support" depends on BLK_DEV_DM select BLK_DEV_INTEGRITY select DM_BUFIO select CRYPTO select ASYNC_XOR ---help--- - This is the integrity target. + This device-mapper target emulates a block device that has + additional per-sector tags that can be used for storing + integrity information. + + This integrity target is used with the dm-crypt target to + provide authenticated disk encryption or it can be used + standalone. + + To compile this code as a module, choose M here: the module will + be called dm-integrity. + + If unsure, say N. endif # MD diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 85e3f21c2514..e57353e39168 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -767,16 +767,12 @@ static int bcache_device_init(struct bcache_device *d, unsigned block_size, } n = d->nr_stripes * sizeof(atomic_t); - d->stripe_sectors_dirty = n < PAGE_SIZE << 6 - ? kzalloc(n, GFP_KERNEL) - : vzalloc(n); + d->stripe_sectors_dirty = kvzalloc(n, GFP_KERNEL); if (!d->stripe_sectors_dirty) return -ENOMEM; n = BITS_TO_LONGS(d->nr_stripes) * sizeof(unsigned long); - d->full_dirty_stripes = n < PAGE_SIZE << 6 - ? kzalloc(n, GFP_KERNEL) - : vzalloc(n); + d->full_dirty_stripes = kvzalloc(n, GFP_KERNEL); if (!d->full_dirty_stripes) return -ENOMEM; diff --git a/drivers/md/bcache/util.h b/drivers/md/bcache/util.h index 5d13930f0f22..cb8d2ccbb6c6 100644 --- a/drivers/md/bcache/util.h +++ b/drivers/md/bcache/util.h @@ -43,11 +43,7 @@ struct closure; (heap)->used = 0; \ (heap)->size = (_size); \ _bytes = (heap)->size * sizeof(*(heap)->data); \ - (heap)->data = NULL; \ - if (_bytes < KMALLOC_MAX_SIZE) \ - (heap)->data = kmalloc(_bytes, (gfp)); \ - if ((!(heap)->data) && ((gfp) & GFP_KERNEL)) \ - (heap)->data = vmalloc(_bytes); \ + (heap)->data = kvmalloc(_bytes, (gfp) & GFP_KERNEL); \ (heap)->data; \ }) @@ -136,12 +132,8 @@ do { \ \ (fifo)->mask = _allocated_size - 1; \ (fifo)->front = (fifo)->back = 0; \ - (fifo)->data = NULL; \ \ - if (_bytes < KMALLOC_MAX_SIZE) \ - (fifo)->data = kmalloc(_bytes, (gfp)); \ - if ((!(fifo)->data) && ((gfp) & GFP_KERNEL)) \ - (fifo)->data = vmalloc(_bytes); \ + (fifo)->data = kvmalloc(_bytes, (gfp) & GFP_KERNEL); \ (fifo)->data; \ }) diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index c92c31b23e54..cd8139593ccd 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -218,7 +218,7 @@ static DEFINE_SPINLOCK(param_spinlock); * Buffers are freed after this timeout */ static unsigned dm_bufio_max_age = DM_BUFIO_DEFAULT_AGE_SECS; -static unsigned dm_bufio_retain_bytes = DM_BUFIO_DEFAULT_RETAIN_BYTES; +static unsigned long dm_bufio_retain_bytes = DM_BUFIO_DEFAULT_RETAIN_BYTES; static unsigned long dm_bufio_peak_allocated; static unsigned long dm_bufio_allocated_kmem_cache; @@ -406,7 +406,7 @@ static void *alloc_buffer_data(struct dm_bufio_client *c, gfp_t gfp_mask, if (gfp_mask & __GFP_NORETRY) noio_flag = memalloc_noio_save(); - ptr = __vmalloc(c->block_size, gfp_mask | __GFP_HIGHMEM, PAGE_KERNEL); + ptr = __vmalloc(c->block_size, gfp_mask, PAGE_KERNEL); if (gfp_mask & __GFP_NORETRY) memalloc_noio_restore(noio_flag); @@ -1558,10 +1558,10 @@ static bool __try_evict_buffer(struct dm_buffer *b, gfp_t gfp) return true; } -static unsigned get_retain_buffers(struct dm_bufio_client *c) +static unsigned long get_retain_buffers(struct dm_bufio_client *c) { - unsigned retain_bytes = ACCESS_ONCE(dm_bufio_retain_bytes); - return retain_bytes / c->block_size; + unsigned long retain_bytes = ACCESS_ONCE(dm_bufio_retain_bytes); + return retain_bytes >> (c->sectors_per_block_bits + SECTOR_SHIFT); } static unsigned long __scan(struct dm_bufio_client *c, unsigned long nr_to_scan, @@ -1571,7 +1571,7 @@ static unsigned long __scan(struct dm_bufio_client *c, unsigned long nr_to_scan, struct dm_buffer *b, *tmp; unsigned long freed = 0; unsigned long count = nr_to_scan; - unsigned retain_target = get_retain_buffers(c); + unsigned long retain_target = get_retain_buffers(c); for (l = 0; l < LIST_SIZE; l++) { list_for_each_entry_safe_reverse(b, tmp, &c->lru[l], lru_list) { @@ -1794,8 +1794,8 @@ static bool older_than(struct dm_buffer *b, unsigned long age_hz) static void __evict_old_buffers(struct dm_bufio_client *c, unsigned long age_hz) { struct dm_buffer *b, *tmp; - unsigned retain_target = get_retain_buffers(c); - unsigned count; + unsigned long retain_target = get_retain_buffers(c); + unsigned long count; LIST_HEAD(write_list); dm_bufio_lock(c); @@ -1955,7 +1955,7 @@ MODULE_PARM_DESC(max_cache_size_bytes, "Size of metadata cache"); module_param_named(max_age_seconds, dm_bufio_max_age, uint, S_IRUGO | S_IWUSR); MODULE_PARM_DESC(max_age_seconds, "Max age of a buffer in seconds"); -module_param_named(retain_bytes, dm_bufio_retain_bytes, uint, S_IRUGO | S_IWUSR); +module_param_named(retain_bytes, dm_bufio_retain_bytes, ulong, S_IRUGO | S_IWUSR); MODULE_PARM_DESC(retain_bytes, "Try to keep at least this many bytes cached in memory"); module_param_named(peak_allocated_bytes, dm_bufio_peak_allocated, ulong, S_IRUGO | S_IWUSR); diff --git a/drivers/md/dm-cache-background-tracker.c b/drivers/md/dm-cache-background-tracker.c index 9b1afdfb13f0..707233891291 100644 --- a/drivers/md/dm-cache-background-tracker.c +++ b/drivers/md/dm-cache-background-tracker.c @@ -33,6 +33,11 @@ struct background_tracker *btracker_create(unsigned max_work) { struct background_tracker *b = kmalloc(sizeof(*b), GFP_KERNEL); + if (!b) { + DMERR("couldn't create background_tracker"); + return NULL; + } + b->max_work = max_work; atomic_set(&b->pending_promotes, 0); atomic_set(&b->pending_writebacks, 0); diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c index 8568dbd50ba4..4a4e9c75fc4c 100644 --- a/drivers/md/dm-cache-metadata.c +++ b/drivers/md/dm-cache-metadata.c @@ -1624,17 +1624,19 @@ void dm_cache_metadata_set_stats(struct dm_cache_metadata *cmd, int dm_cache_commit(struct dm_cache_metadata *cmd, bool clean_shutdown) { - int r; + int r = -EINVAL; flags_mutator mutator = (clean_shutdown ? set_clean_shutdown : clear_clean_shutdown); WRITE_LOCK(cmd); + if (cmd->fail_io) + goto out; + r = __commit_transaction(cmd, mutator); if (r) goto out; r = __begin_transaction(cmd); - out: WRITE_UNLOCK(cmd); return r; @@ -1646,7 +1648,8 @@ int dm_cache_get_free_metadata_block_count(struct dm_cache_metadata *cmd, int r = -EINVAL; READ_LOCK(cmd); - r = dm_sm_get_nr_free(cmd->metadata_sm, result); + if (!cmd->fail_io) + r = dm_sm_get_nr_free(cmd->metadata_sm, result); READ_UNLOCK(cmd); return r; @@ -1658,7 +1661,8 @@ int dm_cache_get_metadata_dev_size(struct dm_cache_metadata *cmd, int r = -EINVAL; READ_LOCK(cmd); - r = dm_sm_get_nr_blocks(cmd->metadata_sm, result); + if (!cmd->fail_io) + r = dm_sm_get_nr_blocks(cmd->metadata_sm, result); READ_UNLOCK(cmd); return r; diff --git a/drivers/md/dm-cache-policy-smq.c b/drivers/md/dm-cache-policy-smq.c index e0c40aec5e96..e5eb9c9b4bc8 100644 --- a/drivers/md/dm-cache-policy-smq.c +++ b/drivers/md/dm-cache-policy-smq.c @@ -1120,28 +1120,26 @@ static bool clean_target_met(struct smq_policy *mq, bool idle) * Cache entries may not be populated. So we cannot rely on the * size of the clean queue. */ - unsigned nr_clean = from_cblock(mq->cache_size) - q_size(&mq->dirty); - - if (idle) + if (idle) { /* * We'd like to clean everything. */ return q_size(&mq->dirty) == 0u; - else - return (nr_clean + btracker_nr_writebacks_queued(mq->bg_work)) >= - percent_to_target(mq, CLEAN_TARGET); + } + + /* + * If we're busy we don't worry about cleaning at all. + */ + return true; } -static bool free_target_met(struct smq_policy *mq, bool idle) +static bool free_target_met(struct smq_policy *mq) { - unsigned nr_free = from_cblock(mq->cache_size) - - mq->cache_alloc.nr_allocated; + unsigned nr_free; - if (idle) - return (nr_free + btracker_nr_demotions_queued(mq->bg_work)) >= - percent_to_target(mq, FREE_TARGET); - else - return true; + nr_free = from_cblock(mq->cache_size) - mq->cache_alloc.nr_allocated; + return (nr_free + btracker_nr_demotions_queued(mq->bg_work)) >= + percent_to_target(mq, FREE_TARGET); } /*----------------------------------------------------------------*/ @@ -1188,9 +1186,9 @@ static void queue_demotion(struct smq_policy *mq) if (unlikely(WARN_ON_ONCE(!mq->migrations_allowed))) return; - e = q_peek(&mq->clean, mq->clean.nr_levels, true); + e = q_peek(&mq->clean, mq->clean.nr_levels / 2, true); if (!e) { - if (!clean_target_met(mq, false)) + if (!clean_target_met(mq, true)) queue_writeback(mq); return; } @@ -1214,7 +1212,11 @@ static void queue_promotion(struct smq_policy *mq, dm_oblock_t oblock, return; if (allocator_empty(&mq->cache_alloc)) { - if (!free_target_met(mq, false)) + /* + * We always claim to be 'idle' to ensure some demotions happen + * with continuous loads. + */ + if (!free_target_met(mq)) queue_demotion(mq); return; } @@ -1415,14 +1417,10 @@ static int smq_get_background_work(struct dm_cache_policy *p, bool idle, spin_lock_irqsave(&mq->lock, flags); r = btracker_issue(mq->bg_work, result); if (r == -ENODATA) { - /* find some writeback work to do */ - if (mq->migrations_allowed && !free_target_met(mq, idle)) - queue_demotion(mq); - - else if (!clean_target_met(mq, idle)) + if (!clean_target_met(mq, idle)) { queue_writeback(mq); - - r = btracker_issue(mq->bg_work, result); + r = btracker_issue(mq->bg_work, result); + } } spin_unlock_irqrestore(&mq->lock, flags); @@ -1446,6 +1444,7 @@ static void __complete_background_work(struct smq_policy *mq, clear_pending(mq, e); if (success) { e->oblock = work->oblock; + e->level = NR_CACHE_LEVELS - 1; push(mq, e); // h, q, a } else { diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index 1db375f50a13..d682a0511381 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -94,6 +94,9 @@ static void iot_io_begin(struct io_tracker *iot, sector_t len) static void __iot_io_end(struct io_tracker *iot, sector_t len) { + if (!len) + return; + iot->in_flight -= len; if (!iot->in_flight) iot->idle_time = jiffies; @@ -474,7 +477,7 @@ struct cache { spinlock_t invalidation_lock; struct list_head invalidation_requests; - struct io_tracker origin_tracker; + struct io_tracker tracker; struct work_struct commit_ws; struct batcher committer; @@ -901,8 +904,7 @@ static dm_oblock_t get_bio_block(struct cache *cache, struct bio *bio) static bool accountable_bio(struct cache *cache, struct bio *bio) { - return ((bio->bi_bdev == cache->origin_dev->bdev) && - bio_op(bio) != REQ_OP_DISCARD); + return bio_op(bio) != REQ_OP_DISCARD; } static void accounted_begin(struct cache *cache, struct bio *bio) @@ -912,7 +914,7 @@ static void accounted_begin(struct cache *cache, struct bio *bio) if (accountable_bio(cache, bio)) { pb->len = bio_sectors(bio); - iot_io_begin(&cache->origin_tracker, pb->len); + iot_io_begin(&cache->tracker, pb->len); } } @@ -921,7 +923,7 @@ static void accounted_complete(struct cache *cache, struct bio *bio) size_t pb_data_size = get_per_bio_data_size(cache); struct per_bio_data *pb = get_per_bio_data(bio, pb_data_size); - iot_io_end(&cache->origin_tracker, pb->len); + iot_io_end(&cache->tracker, pb->len); } static void accounted_request(struct cache *cache, struct bio *bio) @@ -1716,20 +1718,19 @@ static int invalidate_start(struct cache *cache, dm_cblock_t cblock, enum busy { IDLE, - MODERATE, BUSY }; static enum busy spare_migration_bandwidth(struct cache *cache) { - bool idle = iot_idle_for(&cache->origin_tracker, HZ); + bool idle = iot_idle_for(&cache->tracker, HZ); sector_t current_volume = (atomic_read(&cache->nr_io_migrations) + 1) * cache->sectors_per_block; - if (current_volume <= cache->migration_threshold) - return idle ? IDLE : MODERATE; + if (idle && current_volume <= cache->migration_threshold) + return IDLE; else - return idle ? MODERATE : BUSY; + return BUSY; } static void inc_hit_counter(struct cache *cache, struct bio *bio) @@ -2045,8 +2046,6 @@ static void check_migrations(struct work_struct *ws) for (;;) { b = spare_migration_bandwidth(cache); - if (b == BUSY) - break; r = policy_get_background_work(cache->policy, b == IDLE, &op); if (r == -ENODATA) @@ -2717,7 +2716,7 @@ static int cache_create(struct cache_args *ca, struct cache **result) batcher_init(&cache->committer, commit_op, cache, issue_op, cache, cache->wq); - iot_init(&cache->origin_tracker); + iot_init(&cache->tracker); init_rwsem(&cache->background_work_lock); prevent_background_work(cache); @@ -2941,7 +2940,7 @@ static void cache_postsuspend(struct dm_target *ti) cancel_delayed_work(&cache->waker); flush_workqueue(cache->wq); - WARN_ON(cache->origin_tracker.in_flight); + WARN_ON(cache->tracker.in_flight); /* * If it's a flush suspend there won't be any deferred bios, so this diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h index 97db4d11c05a..52ca8d059e82 100644 --- a/drivers/md/dm-core.h +++ b/drivers/md/dm-core.h @@ -58,6 +58,7 @@ struct mapped_device { struct target_type *immutable_target_type; struct gendisk *disk; + struct dax_device *dax_dev; char name[16]; void *interface_ptr; diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c index 2d5d7064acbf..0555b4410e05 100644 --- a/drivers/md/dm-ioctl.c +++ b/drivers/md/dm-ioctl.c @@ -1691,6 +1691,7 @@ static int copy_params(struct dm_ioctl __user *user, struct dm_ioctl *param_kern struct dm_ioctl *dmi; int secure_data; const size_t minimum_data_size = offsetof(struct dm_ioctl, data); + unsigned noio_flag; if (copy_from_user(param_kernel, user, minimum_data_size)) return -EFAULT; @@ -1713,15 +1714,9 @@ static int copy_params(struct dm_ioctl __user *user, struct dm_ioctl *param_kern * Use kmalloc() rather than vmalloc() when we can. */ dmi = NULL; - if (param_kernel->data_size <= KMALLOC_MAX_SIZE) - dmi = kmalloc(param_kernel->data_size, GFP_NOIO | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN); - - if (!dmi) { - unsigned noio_flag; - noio_flag = memalloc_noio_save(); - dmi = __vmalloc(param_kernel->data_size, GFP_NOIO | __GFP_HIGH | __GFP_HIGHMEM, PAGE_KERNEL); - memalloc_noio_restore(noio_flag); - } + noio_flag = memalloc_noio_save(); + dmi = kvmalloc(param_kernel->data_size, GFP_KERNEL); + memalloc_noio_restore(noio_flag); if (!dmi) { if (secure_data && clear_user(user, param_kernel->data_size)) diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c index a5120961632a..7d42a9d9f406 100644 --- a/drivers/md/dm-linear.c +++ b/drivers/md/dm-linear.c @@ -9,6 +9,7 @@ #include <linux/init.h> #include <linux/blkdev.h> #include <linux/bio.h> +#include <linux/dax.h> #include <linux/slab.h> #include <linux/device-mapper.h> @@ -142,22 +143,20 @@ static int linear_iterate_devices(struct dm_target *ti, return fn(ti, lc->dev, lc->start, ti->len, data); } -static long linear_direct_access(struct dm_target *ti, sector_t sector, - void **kaddr, pfn_t *pfn, long size) +static long linear_dax_direct_access(struct dm_target *ti, pgoff_t pgoff, + long nr_pages, void **kaddr, pfn_t *pfn) { + long ret; struct linear_c *lc = ti->private; struct block_device *bdev = lc->dev->bdev; - struct blk_dax_ctl dax = { - .sector = linear_map_sector(ti, sector), - .size = size, - }; - long ret; - - ret = bdev_direct_access(bdev, &dax); - *kaddr = dax.addr; - *pfn = dax.pfn; - - return ret; + struct dax_device *dax_dev = lc->dev->dax_dev; + sector_t dev_sector, sector = pgoff * PAGE_SECTORS; + + dev_sector = linear_map_sector(ti, sector); + ret = bdev_dax_pgoff(bdev, dev_sector, nr_pages * PAGE_SIZE, &pgoff); + if (ret) + return ret; + return dax_direct_access(dax_dev, pgoff, nr_pages, kaddr, pfn); } static struct target_type linear_target = { @@ -171,7 +170,7 @@ static struct target_type linear_target = { .status = linear_status, .prepare_ioctl = linear_prepare_ioctl, .iterate_devices = linear_iterate_devices, - .direct_access = linear_direct_access, + .direct_access = linear_dax_direct_access, }; int __init dm_linear_init(void) diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index 926a6bcb32c8..3df056b73b66 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -447,7 +447,7 @@ failed: * it has been invoked. */ #define dm_report_EIO(m) \ -({ \ +do { \ struct mapped_device *md = dm_table_get_md((m)->ti->table); \ \ pr_debug("%s: returning EIO; QIFNP = %d; SQIFNP = %d; DNFS = %d\n", \ @@ -455,8 +455,7 @@ failed: test_bit(MPATHF_QUEUE_IF_NO_PATH, &(m)->flags), \ test_bit(MPATHF_SAVED_QUEUE_IF_NO_PATH, &(m)->flags), \ dm_noflush_suspending((m)->ti)); \ - -EIO; \ -}) +} while (0) /* * Map cloned requests (request-based multipath) @@ -481,7 +480,8 @@ static int multipath_clone_and_map(struct dm_target *ti, struct request *rq, if (!pgpath) { if (test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags)) return DM_MAPIO_DELAY_REQUEUE; - return dm_report_EIO(m); /* Failed */ + dm_report_EIO(m); /* Failed */ + return DM_MAPIO_KILL; } else if (test_bit(MPATHF_QUEUE_IO, &m->flags) || test_bit(MPATHF_PG_INIT_REQUIRED, &m->flags)) { if (pg_init_all_paths(m)) @@ -558,7 +558,8 @@ static int __multipath_map_bio(struct multipath *m, struct bio *bio, struct dm_m if (!pgpath) { if (test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags)) return DM_MAPIO_REQUEUE; - return dm_report_EIO(m); + dm_report_EIO(m); + return -EIO; } mpio->pgpath = pgpath; @@ -1493,7 +1494,7 @@ static int multipath_end_io(struct dm_target *ti, struct request *clone, if (atomic_read(&m->nr_valid_paths) == 0 && !test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags)) { if (error == -EIO) - error = dm_report_EIO(m); + dm_report_EIO(m); /* complete with the original error */ r = DM_ENDIO_DONE; } @@ -1524,8 +1525,10 @@ static int do_end_io_bio(struct multipath *m, struct bio *clone, fail_path(mpio->pgpath); if (atomic_read(&m->nr_valid_paths) == 0 && - !test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags)) - return dm_report_EIO(m); + !test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags)) { + dm_report_EIO(m); + return -EIO; + } /* Queue for the daemon to resubmit */ dm_bio_restore(get_bio_details_from_bio(clone), clone); diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c index a48130b90157..b639fa7246ee 100644 --- a/drivers/md/dm-rq.c +++ b/drivers/md/dm-rq.c @@ -507,6 +507,7 @@ static int map_request(struct dm_rq_target_io *tio) case DM_MAPIO_KILL: /* The target wants to complete the I/O */ dm_kill_unmapped_request(rq, -EIO); + break; default: DMWARN("unimplemented target map return value: %d", r); BUG(); @@ -720,11 +721,10 @@ int dm_old_init_request_queue(struct mapped_device *md, struct dm_table *t) return 0; } -static int dm_mq_init_request(void *data, struct request *rq, - unsigned int hctx_idx, unsigned int request_idx, - unsigned int numa_node) +static int dm_mq_init_request(struct blk_mq_tag_set *set, struct request *rq, + unsigned int hctx_idx, unsigned int numa_node) { - return __dm_rq_init_rq(data, rq); + return __dm_rq_init_rq(set->driver_data, rq); } static int dm_mq_queue_rq(struct blk_mq_hw_ctx *hctx, diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c index c65feeada864..e152d9817c81 100644 --- a/drivers/md/dm-snap.c +++ b/drivers/md/dm-snap.c @@ -2302,8 +2302,8 @@ static int origin_map(struct dm_target *ti, struct bio *bio) return do_origin(o->dev, bio); } -static long origin_direct_access(struct dm_target *ti, sector_t sector, - void **kaddr, pfn_t *pfn, long size) +static long origin_dax_direct_access(struct dm_target *ti, pgoff_t pgoff, + long nr_pages, void **kaddr, pfn_t *pfn) { DMWARN("device does not support dax."); return -EIO; @@ -2368,7 +2368,7 @@ static struct target_type origin_target = { .postsuspend = origin_postsuspend, .status = origin_status, .iterate_devices = origin_iterate_devices, - .direct_access = origin_direct_access, + .direct_access = origin_dax_direct_access, }; static struct target_type snapshot_target = { diff --git a/drivers/md/dm-stats.c b/drivers/md/dm-stats.c index 0250e7e521ab..6028d8247f58 100644 --- a/drivers/md/dm-stats.c +++ b/drivers/md/dm-stats.c @@ -146,12 +146,7 @@ static void *dm_kvzalloc(size_t alloc_size, int node) if (!claim_shared_memory(alloc_size)) return NULL; - if (alloc_size <= KMALLOC_MAX_SIZE) { - p = kzalloc_node(alloc_size, GFP_KERNEL | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN, node); - if (p) - return p; - } - p = vzalloc_node(alloc_size, node); + p = kvzalloc_node(alloc_size, GFP_KERNEL | __GFP_NOMEMALLOC, node); if (p) return p; diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c index 4b50ae115c6d..75152482f3ad 100644 --- a/drivers/md/dm-stripe.c +++ b/drivers/md/dm-stripe.c @@ -11,6 +11,7 @@ #include <linux/init.h> #include <linux/blkdev.h> #include <linux/bio.h> +#include <linux/dax.h> #include <linux/slab.h> #include <linux/log2.h> @@ -310,27 +311,25 @@ static int stripe_map(struct dm_target *ti, struct bio *bio) return DM_MAPIO_REMAPPED; } -static long stripe_direct_access(struct dm_target *ti, sector_t sector, - void **kaddr, pfn_t *pfn, long size) +static long stripe_dax_direct_access(struct dm_target *ti, pgoff_t pgoff, + long nr_pages, void **kaddr, pfn_t *pfn) { + sector_t dev_sector, sector = pgoff * PAGE_SECTORS; struct stripe_c *sc = ti->private; - uint32_t stripe; + struct dax_device *dax_dev; struct block_device *bdev; - struct blk_dax_ctl dax = { - .size = size, - }; + uint32_t stripe; long ret; - stripe_map_sector(sc, sector, &stripe, &dax.sector); - - dax.sector += sc->stripe[stripe].physical_start; + stripe_map_sector(sc, sector, &stripe, &dev_sector); + dev_sector += sc->stripe[stripe].physical_start; + dax_dev = sc->stripe[stripe].dev->dax_dev; bdev = sc->stripe[stripe].dev->bdev; - ret = bdev_direct_access(bdev, &dax); - *kaddr = dax.addr; - *pfn = dax.pfn; - - return ret; + ret = bdev_dax_pgoff(bdev, dev_sector, nr_pages * PAGE_SIZE, &pgoff); + if (ret) + return ret; + return dax_direct_access(dax_dev, pgoff, nr_pages, kaddr, pfn); } /* @@ -451,7 +450,7 @@ static struct target_type stripe_target = { .status = stripe_status, .iterate_devices = stripe_iterate_devices, .io_hints = stripe_io_hints, - .direct_access = stripe_direct_access, + .direct_access = stripe_dax_direct_access, }; int __init dm_stripe_init(void) diff --git a/drivers/md/dm-target.c b/drivers/md/dm-target.c index 6264ff00dcf0..b242b750542f 100644 --- a/drivers/md/dm-target.c +++ b/drivers/md/dm-target.c @@ -142,8 +142,8 @@ static void io_err_release_clone_rq(struct request *clone) { } -static long io_err_direct_access(struct dm_target *ti, sector_t sector, - void **kaddr, pfn_t *pfn, long size) +static long io_err_dax_direct_access(struct dm_target *ti, pgoff_t pgoff, + long nr_pages, void **kaddr, pfn_t *pfn) { return -EIO; } @@ -157,7 +157,7 @@ static struct target_type error_target = { .map = io_err_map, .clone_and_map_rq = io_err_clone_and_map_rq, .release_clone_rq = io_err_release_clone_rq, - .direct_access = io_err_direct_access, + .direct_access = io_err_dax_direct_access, }; int __init dm_target_init(void) diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c index 0f0251d0d337..d31d18d9727c 100644 --- a/drivers/md/dm-thin-metadata.c +++ b/drivers/md/dm-thin-metadata.c @@ -484,11 +484,11 @@ static int __write_initial_superblock(struct dm_pool_metadata *pmd) if (r < 0) return r; - r = save_sm_roots(pmd); + r = dm_tm_pre_commit(pmd->tm); if (r < 0) return r; - r = dm_tm_pre_commit(pmd->tm); + r = save_sm_roots(pmd); if (r < 0) return r; diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 268edf402bbb..6ef9500226c0 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -16,6 +16,7 @@ #include <linux/blkpg.h> #include <linux/bio.h> #include <linux/mempool.h> +#include <linux/dax.h> #include <linux/slab.h> #include <linux/idr.h> #include <linux/hdreg.h> @@ -629,6 +630,7 @@ static int open_table_device(struct table_device *td, dev_t dev, } td->dm_dev.bdev = bdev; + td->dm_dev.dax_dev = dax_get_by_host(bdev->bd_disk->disk_name); return 0; } @@ -642,7 +644,9 @@ static void close_table_device(struct table_device *td, struct mapped_device *md bd_unlink_disk_holder(td->dm_dev.bdev, dm_disk(md)); blkdev_put(td->dm_dev.bdev, td->dm_dev.mode | FMODE_EXCL); + put_dax(td->dm_dev.dax_dev); td->dm_dev.bdev = NULL; + td->dm_dev.dax_dev = NULL; } static struct table_device *find_table_device(struct list_head *l, dev_t dev, @@ -920,31 +924,49 @@ int dm_set_target_max_io_len(struct dm_target *ti, sector_t len) } EXPORT_SYMBOL_GPL(dm_set_target_max_io_len); -static long dm_blk_direct_access(struct block_device *bdev, sector_t sector, - void **kaddr, pfn_t *pfn, long size) +static struct dm_target *dm_dax_get_live_target(struct mapped_device *md, + sector_t sector, int *srcu_idx) { - struct mapped_device *md = bdev->bd_disk->private_data; struct dm_table *map; struct dm_target *ti; - int srcu_idx; - long len, ret = -EIO; - map = dm_get_live_table(md, &srcu_idx); + map = dm_get_live_table(md, srcu_idx); if (!map) - goto out; + return NULL; ti = dm_table_find_target(map, sector); if (!dm_target_is_valid(ti)) - goto out; + return NULL; + + return ti; +} + +static long dm_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, + long nr_pages, void **kaddr, pfn_t *pfn) +{ + struct mapped_device *md = dax_get_private(dax_dev); + sector_t sector = pgoff * PAGE_SECTORS; + struct dm_target *ti; + long len, ret = -EIO; + int srcu_idx; - len = max_io_len(sector, ti) << SECTOR_SHIFT; - size = min(len, size); + ti = dm_dax_get_live_target(md, sector, &srcu_idx); + if (!ti) + goto out; + if (!ti->type->direct_access) + goto out; + len = max_io_len(sector, ti) / PAGE_SECTORS; + if (len < 1) + goto out; + nr_pages = min(len, nr_pages); if (ti->type->direct_access) - ret = ti->type->direct_access(ti, sector, kaddr, pfn, size); -out: + ret = ti->type->direct_access(ti, pgoff, nr_pages, kaddr, pfn); + + out: dm_put_live_table(md, srcu_idx); - return min(ret, size); + + return ret; } /* @@ -1471,6 +1493,7 @@ static int next_free_minor(int *minor) } static const struct block_device_operations dm_blk_dops; +static const struct dax_operations dm_dax_ops; static void dm_wq_work(struct work_struct *work); @@ -1517,6 +1540,12 @@ static void cleanup_mapped_device(struct mapped_device *md) if (md->bs) bioset_free(md->bs); + if (md->dax_dev) { + kill_dax(md->dax_dev); + put_dax(md->dax_dev); + md->dax_dev = NULL; + } + if (md->disk) { spin_lock(&_minor_lock); md->disk->private_data = NULL; @@ -1544,6 +1573,7 @@ static void cleanup_mapped_device(struct mapped_device *md) static struct mapped_device *alloc_dev(int minor) { int r, numa_node_id = dm_get_numa_node(); + struct dax_device *dax_dev; struct mapped_device *md; void *old_md; @@ -1608,6 +1638,12 @@ static struct mapped_device *alloc_dev(int minor) md->disk->queue = md->q |