diff options
Diffstat (limited to 'drivers/md')
65 files changed, 1025 insertions, 780 deletions
diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig index 104aa5355090..239c1744a926 100644 --- a/drivers/md/Kconfig +++ b/drivers/md/Kconfig @@ -299,6 +299,7 @@ config DM_CRYPT select CRYPTO select CRYPTO_CBC select CRYPTO_ESSIV + select CRYPTO_LIB_MD5 # needed by lmk IV mode help This device-mapper target allows you to create a device that transparently encrypts the data on it. You'll need to activate @@ -546,6 +547,7 @@ config DM_VERITY depends on BLK_DEV_DM select CRYPTO select CRYPTO_HASH + select CRYPTO_LIB_SHA256 select DM_BUFIO help This device-mapper target creates a read-only device that diff --git a/drivers/md/bcache/alloc.c b/drivers/md/bcache/alloc.c index 48ce750bf70a..7708d92df23e 100644 --- a/drivers/md/bcache/alloc.c +++ b/drivers/md/bcache/alloc.c @@ -24,21 +24,18 @@ * Since the gens and priorities are all stored contiguously on disk, we can * batch this up: We fill up the free_inc list with freshly invalidated buckets, * call prio_write(), and when prio_write() finishes we pull buckets off the - * free_inc list and optionally discard them. + * free_inc list. * * free_inc isn't the only freelist - if it was, we'd often to sleep while * priorities and gens were being written before we could allocate. c->free is a * smaller freelist, and buckets on that list are always ready to be used. * - * If we've got discards enabled, that happens when a bucket moves from the - * free_inc list to the free list. - * * There is another freelist, because sometimes we have buckets that we know * have nothing pointing into them - these we can reuse without waiting for * priorities to be rewritten. These come from freed btree nodes and buckets * that garbage collection discovered no longer had valid keys pointing into * them (because they were overwritten). That's the unused list - buckets on the - * unused list move to the free list, optionally being discarded in the process. + * unused list move to the free list. * * It's also important to ensure that gens don't wrap around - with respect to * either the oldest gen in the btree or the gen on disk. This is quite @@ -118,8 +115,7 @@ void bch_rescale_priorities(struct cache_set *c, int sectors) /* * Background allocation thread: scans for buckets to be invalidated, * invalidates them, rewrites prios/gens (marking them as invalidated on disk), - * then optionally issues discard commands to the newly free buckets, then puts - * them on the various freelists. + * then puts them on the various freelists. */ static inline bool can_inc_bucket_gen(struct bucket *b) @@ -321,8 +317,7 @@ static int bch_allocator_thread(void *arg) while (1) { /* * First, we pull buckets off of the unused and free_inc lists, - * possibly issue discards to them, then we add the bucket to - * the free list: + * then we add the bucket to the free list: */ while (1) { long bucket; @@ -330,14 +325,6 @@ static int bch_allocator_thread(void *arg) if (!fifo_pop(&ca->free_inc, bucket)) break; - if (ca->discard) { - mutex_unlock(&ca->set->bucket_lock); - blkdev_issue_discard(ca->bdev, - bucket_to_sector(ca->set, bucket), - ca->sb.bucket_size, GFP_KERNEL); - mutex_lock(&ca->set->bucket_lock); - } - allocator_wait(ca, bch_allocator_push(ca, bucket)); wake_up(&ca->set->btree_cache_wait); wake_up(&ca->set->bucket_wait); @@ -412,7 +399,11 @@ long bch_bucket_alloc(struct cache *ca, unsigned int reserve, bool wait) TASK_UNINTERRUPTIBLE); mutex_unlock(&ca->set->bucket_lock); + + atomic_inc(&ca->set->bucket_wait_cnt); schedule(); + atomic_dec(&ca->set->bucket_wait_cnt); + mutex_lock(&ca->set->bucket_lock); } while (!fifo_pop(&ca->free[RESERVE_NONE], r) && !fifo_pop(&ca->free[reserve], r)); diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h index 1d33e40d26ea..8ccacba85547 100644 --- a/drivers/md/bcache/bcache.h +++ b/drivers/md/bcache/bcache.h @@ -447,8 +447,7 @@ struct cache { * free_inc: Incoming buckets - these are buckets that currently have * cached data in them, and we can't reuse them until after we write * their new gen to disk. After prio_write() finishes writing the new - * gens/prios, they'll be moved to the free list (and possibly discarded - * in the process) + * gens/prios, they'll be moved to the free list. */ DECLARE_FIFO(long, free)[RESERVE_NR]; DECLARE_FIFO(long, free_inc); @@ -467,8 +466,6 @@ struct cache { */ unsigned int invalidate_needs_gc; - bool discard; /* Get rid of? */ - struct journal_device journal; /* The rest of this all shows up in sysfs */ @@ -607,6 +604,7 @@ struct cache_set { */ atomic_t prio_blocked; wait_queue_head_t bucket_wait; + atomic_t bucket_wait_cnt; /* * For any bio we don't skip we subtract the number of sectors from diff --git a/drivers/md/bcache/bset.h b/drivers/md/bcache/bset.h index 011f6062c4c0..6ee2c6a506a2 100644 --- a/drivers/md/bcache/bset.h +++ b/drivers/md/bcache/bset.h @@ -327,9 +327,13 @@ struct btree_iter { /* Fixed-size btree_iter that can be allocated on the stack */ struct btree_iter_stack { - struct btree_iter iter; - struct btree_iter_set stack_data[MAX_BSETS]; + /* Must be last as it ends in a flexible-array member. */ + TRAILING_OVERLAP(struct btree_iter, iter, data, + struct btree_iter_set stack_data[MAX_BSETS]; + ); }; +static_assert(offsetof(struct btree_iter_stack, iter.data) == + offsetof(struct btree_iter_stack, stack_data)); typedef bool (*ptr_filter_fn)(struct btree_keys *b, const struct bkey *k); diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c index 210b59007d98..3ed39c823826 100644 --- a/drivers/md/bcache/btree.c +++ b/drivers/md/bcache/btree.c @@ -89,8 +89,9 @@ * Test module load/unload */ -#define MAX_GC_TIMES 100 -#define MIN_GC_NODES 100 +#define MAX_GC_TIMES_SHIFT 7 /* 128 loops */ +#define GC_NODES_MIN 10 +#define GC_SLEEP_MS_MIN 10 #define GC_SLEEP_MS 100 #define PTR_DIRTY_BIT (((uint64_t) 1 << 36)) @@ -371,7 +372,7 @@ static void do_btree_node_write(struct btree *b) SET_PTR_OFFSET(&k.key, 0, PTR_OFFSET(&k.key, 0) + bset_sector_offset(&b->keys, i)); - if (!bch_bio_alloc_pages(b->bio, __GFP_NOWARN|GFP_NOWAIT)) { + if (!bch_bio_alloc_pages(b->bio, GFP_NOWAIT)) { struct bio_vec *bv; void *addr = (void *) ((unsigned long) i & ~(PAGE_SIZE - 1)); struct bvec_iter_all iter_all; @@ -1578,29 +1579,29 @@ static unsigned int btree_gc_count_keys(struct btree *b) static size_t btree_gc_min_nodes(struct cache_set *c) { - size_t min_nodes; + size_t min_nodes = GC_NODES_MIN; - /* - * Since incremental GC would stop 100ms when front - * side I/O comes, so when there are many btree nodes, - * if GC only processes constant (100) nodes each time, - * GC would last a long time, and the front side I/Os - * would run out of the buckets (since no new bucket - * can be allocated during GC), and be blocked again. - * So GC should not process constant nodes, but varied - * nodes according to the number of btree nodes, which - * realized by dividing GC into constant(100) times, - * so when there are many btree nodes, GC can process - * more nodes each time, otherwise, GC will process less - * nodes each time (but no less than MIN_GC_NODES) - */ - min_nodes = c->gc_stats.nodes / MAX_GC_TIMES; - if (min_nodes < MIN_GC_NODES) - min_nodes = MIN_GC_NODES; + if (atomic_read(&c->search_inflight) == 0) { + size_t n = c->gc_stats.nodes >> MAX_GC_TIMES_SHIFT; + + if (min_nodes < n) + min_nodes = n; + } return min_nodes; } +static uint64_t btree_gc_sleep_ms(struct cache_set *c) +{ + uint64_t sleep_ms; + + if (atomic_read(&c->bucket_wait_cnt) > 0) + sleep_ms = GC_SLEEP_MS_MIN; + else + sleep_ms = GC_SLEEP_MS; + + return sleep_ms; +} static int btree_gc_recurse(struct btree *b, struct btree_op *op, struct closure *writes, struct gc_stat *gc) @@ -1668,8 +1669,7 @@ static int btree_gc_recurse(struct btree *b, struct btree_op *op, memmove(r + 1, r, sizeof(r[0]) * (GC_MERGE_NODES - 1)); r->b = NULL; - if (atomic_read(&b->c->search_inflight) && - gc->nodes >= gc->nodes_pre + btree_gc_min_nodes(b->c)) { + if (gc->nodes >= (gc->nodes_pre + btree_gc_min_nodes(b->c))) { gc->nodes_pre = gc->nodes; ret = -EAGAIN; break; @@ -1846,8 +1846,8 @@ static void bch_btree_gc(struct cache_set *c) cond_resched(); if (ret == -EAGAIN) - schedule_timeout_interruptible(msecs_to_jiffies - (GC_SLEEP_MS)); + schedule_timeout_interruptible( + msecs_to_jiffies(btree_gc_sleep_ms(c))); else if (ret) pr_warn("gc failed!\n"); } while (ret && !test_bit(CACHE_SET_IO_DISABLE, &c->flags)); @@ -2822,7 +2822,8 @@ void bch_btree_exit(void) int __init bch_btree_init(void) { - btree_io_wq = alloc_workqueue("bch_btree_io", WQ_MEM_RECLAIM, 0); + btree_io_wq = alloc_workqueue("bch_btree_io", + WQ_MEM_RECLAIM | WQ_PERCPU, 0); if (!btree_io_wq) return -ENOMEM; diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c index d50eb82ccb4f..144693b7c46a 100644 --- a/drivers/md/bcache/journal.c +++ b/drivers/md/bcache/journal.c @@ -275,8 +275,7 @@ bsearch: * ja->cur_idx */ ja->cur_idx = i; - ja->last_idx = ja->discard_idx = (i + 1) % - ca->sb.njournal_buckets; + ja->last_idx = (i + 1) % ca->sb.njournal_buckets; } @@ -336,16 +335,6 @@ void bch_journal_mark(struct cache_set *c, struct list_head *list) } } -static bool is_discard_enabled(struct cache_set *s) -{ - struct cache *ca = s->cache; - - if (ca->discard) - return true; - - return false; -} - int bch_journal_replay(struct cache_set *s, struct list_head *list) { int ret = 0, keys = 0, entries = 0; @@ -360,15 +349,10 @@ int bch_journal_replay(struct cache_set *s, struct list_head *list) BUG_ON(i->pin && atomic_read(i->pin) != 1); if (n != i->j.seq) { - if (n == start && is_discard_enabled(s)) - pr_info("journal entries %llu-%llu may be discarded! (replaying %llu-%llu)\n", - n, i->j.seq - 1, start, end); - else { - pr_err("journal entries %llu-%llu missing! (replaying %llu-%llu)\n", - n, i->j.seq - 1, start, end); - ret = -EIO; - goto err; - } + pr_err("journal entries %llu-%llu missing! (replaying %llu-%llu)\n", + n, i->j.seq - 1, start, end); + ret = -EIO; + goto err; } for (k = i->j.start; @@ -568,65 +552,6 @@ out: #define last_seq(j) ((j)->seq - fifo_used(&(j)->pin) + 1) -static void journal_discard_endio(struct bio *bio) -{ - struct journal_device *ja = - container_of(bio, struct journal_device, discard_bio); - struct cache *ca = container_of(ja, struct cache, journal); - - atomic_set(&ja->discard_in_flight, DISCARD_DONE); - - closure_wake_up(&ca->set->journal.wait); - closure_put(&ca->set->cl); -} - -static void journal_discard_work(struct work_struct *work) -{ - struct journal_device *ja = - container_of(work, struct journal_device, discard_work); - - submit_bio(&ja->discard_bio); -} - -static void do_journal_discard(struct cache *ca) -{ - struct journal_device *ja = &ca->journal; - struct bio *bio = &ja->discard_bio; - - if (!ca->discard) { - ja->discard_idx = ja->last_idx; - return; - } - - switch (atomic_read(&ja->discard_in_flight)) { - case DISCARD_IN_FLIGHT: - return; - - case DISCARD_DONE: - ja->discard_idx = (ja->discard_idx + 1) % - ca->sb.njournal_buckets; - - atomic_set(&ja->discard_in_flight, DISCARD_READY); - fallthrough; - - case DISCARD_READY: - if (ja->discard_idx == ja->last_idx) - return; - - atomic_set(&ja->discard_in_flight, DISCARD_IN_FLIGHT); - - bio_init_inline(bio, ca->bdev, 1, REQ_OP_DISCARD); - bio->bi_iter.bi_sector = bucket_to_sector(ca->set, - ca->sb.d[ja->discard_idx]); - bio->bi_iter.bi_size = bucket_bytes(ca); - bio->bi_end_io = journal_discard_endio; - - closure_get(&ca->set->cl); - INIT_WORK(&ja->discard_work, journal_discard_work); - queue_work(bch_journal_wq, &ja->discard_work); - } -} - static unsigned int free_journal_buckets(struct cache_set *c) { struct journal *j = &c->journal; @@ -635,10 +560,10 @@ static unsigned int free_journal_buckets(struct cache_set *c) unsigned int n; /* In case njournal_buckets is not power of 2 */ - if (ja->cur_idx >= ja->discard_idx) - n = ca->sb.njournal_buckets + ja->discard_idx - ja->cur_idx; + if (ja->cur_idx >= ja->last_idx) + n = ca->sb.njournal_buckets + ja->last_idx - ja->cur_idx; else - n = ja->discard_idx - ja->cur_idx; + n = ja->last_idx - ja->cur_idx; if (n > (1 + j->do_reserve)) return n - (1 + j->do_reserve); @@ -668,8 +593,6 @@ static void journal_reclaim(struct cache_set *c) ja->last_idx = (ja->last_idx + 1) % ca->sb.njournal_buckets; - do_journal_discard(ca); - if (c->journal.blocks_free) goto out; diff --git a/drivers/md/bcache/journal.h b/drivers/md/bcache/journal.h index cd316b4a1e95..9e9d1b3016a5 100644 --- a/drivers/md/bcache/journal.h +++ b/drivers/md/bcache/journal.h @@ -139,19 +139,6 @@ struct journal_device { /* Last journal bucket that still contains an open journal entry */ unsigned int last_idx; - /* Next journal bucket to be discarded */ - unsigned int discard_idx; - -#define DISCARD_READY 0 -#define DISCARD_IN_FLIGHT 1 -#define DISCARD_DONE 2 - /* 1 - discard in flight, -1 - discard completed */ - atomic_t discard_in_flight; - - struct work_struct discard_work; - struct bio discard_bio; - struct bio_vec discard_bv; - /* Bio for journal reads/writes to this device */ struct bio bio; struct bio_vec bv[8]; diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 6d250e366412..c17d4517af22 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -1388,7 +1388,7 @@ static CLOSURE_CALLBACK(cached_dev_flush) bch_cache_accounting_destroy(&dc->accounting); kobject_del(&d->kobj); - continue_at(cl, cached_dev_free, system_wq); + continue_at(cl, cached_dev_free, system_percpu_wq); } static int cached_dev_init(struct cached_dev *dc, unsigned int block_size) @@ -1400,7 +1400,7 @@ static int cached_dev_init(struct cached_dev *dc, unsigned int block_size) __module_get(THIS_MODULE); INIT_LIST_HEAD(&dc->list); closure_init(&dc->disk.cl, NULL); - set_closure_fn(&dc->disk.cl, cached_dev_flush, system_wq); + set_closure_fn(&dc->disk.cl, cached_dev_flush, system_percpu_wq); kobject_init(&dc->disk.kobj, &bch_cached_dev_ktype); INIT_WORK(&dc->detach, cached_dev_detach_finish); sema_init(&dc->sb_write_mutex, 1); @@ -1513,7 +1513,7 @@ static CLOSURE_CALLBACK(flash_dev_flush) bcache_device_unlink(d); mutex_unlock(&bch_register_lock); kobject_del(&d->kobj); - continue_at(cl, flash_dev_free, system_wq); + continue_at(cl, flash_dev_free, system_percpu_wq); } static int flash_dev_run(struct cache_set *c, struct uuid_entry *u) @@ -1525,7 +1525,7 @@ static int flash_dev_run(struct cache_set *c, struct uuid_entry *u) goto err_ret; closure_init(&d->cl, NULL); - set_closure_fn(&d->cl, flash_dev_flush, system_wq); + set_closure_fn(&d->cl, flash_dev_flush, system_percpu_wq); kobject_init(&d->kobj, &bch_flash_dev_ktype); @@ -1833,7 +1833,7 @@ static CLOSURE_CALLBACK(__cache_set_unregister) mutex_unlock(&bch_register_lock); - continue_at(cl, cache_set_flush, system_wq); + continue_at(cl, cache_set_flush, system_percpu_wq); } void bch_cache_set_stop(struct cache_set *c) @@ -1863,10 +1863,10 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb) __module_get(THIS_MODULE); closure_init(&c->cl, NULL); - set_closure_fn(&c->cl, cache_set_free, system_wq); + set_closure_fn(&c->cl, cache_set_free, system_percpu_wq); closure_init(&c->caching, &c->cl); - set_closure_fn(&c->caching, __cache_set_unregister, system_wq); + set_closure_fn(&c->caching, __cache_set_unregister, system_percpu_wq); /* Maybe create continue_at_noreturn() and use it here? */ closure_set_stopped(&c->cl); @@ -1939,7 +1939,8 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb) if (!c->uuids) goto err; - c->moving_gc_wq = alloc_workqueue("bcache_gc", WQ_MEM_RECLAIM, 0); + c->moving_gc_wq = alloc_workqueue("bcache_gc", + WQ_MEM_RECLAIM | WQ_PERCPU, 0); if (!c->moving_gc_wq) goto err; @@ -2382,9 +2383,6 @@ static int register_cache(struct cache_sb *sb, struct cache_sb_disk *sb_disk, ca->bdev = file_bdev(bdev_file); ca->sb_disk = sb_disk; - if (bdev_max_discard_sectors(file_bdev(bdev_file))) - ca->discard = CACHE_DISCARD(&ca->sb); - ret = cache_alloc(ca); if (ret != 0) { if (ret == -ENOMEM) @@ -2531,7 +2529,7 @@ static void register_device_async(struct async_reg_args *args) INIT_DELAYED_WORK(&args->reg_work, register_cache_worker); /* 10 jiffies is enough for a delay */ - queue_delayed_work(system_wq, &args->reg_work, 10); + queue_delayed_work(system_percpu_wq, &args->reg_work, 10); } static void *alloc_holder_object(struct cache_sb *sb) @@ -2905,24 +2903,25 @@ static int __init bcache_init(void) if (bch_btree_init()) goto err; - bcache_wq = alloc_workqueue("bcache", WQ_MEM_RECLAIM, 0); + bcache_wq = alloc_workqueue("bcache", WQ_MEM_RECLAIM | WQ_PERCPU, 0); if (!bcache_wq) goto err; /* * Let's not make this `WQ_MEM_RECLAIM` for the following reasons: * - * 1. It used `system_wq` before which also does no memory reclaim. + * 1. It used `system_percpu_wq` before which also does no memory reclaim. * 2. With `WQ_MEM_RECLAIM` desktop stalls, increased boot times, and * reduced throughput can be observed. * - * We still want to user our own queue to not congest the `system_wq`. + * We still want to user our own queue to not congest the `system_percpu_wq`. */ - bch_flush_wq = alloc_workqueue("bch_flush", 0, 0); + bch_flush_wq = alloc_workqueue("bch_flush", WQ_PERCPU, 0); if (!bch_flush_wq) goto err; - bch_journal_wq = alloc_workqueue("bch_journal", WQ_MEM_RECLAIM, 0); + bch_journal_wq = alloc_workqueue("bch_journal", + WQ_MEM_RECLAIM | WQ_PERCPU, 0); if (!bch_journal_wq) goto err; diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c index 826b14cae4e5..72f38e5b6f5c 100644 --- a/drivers/md/bcache/sysfs.c +++ b/drivers/md/bcache/sysfs.c @@ -134,7 +134,6 @@ read_attribute(partial_stripes_expensive); rw_attribute(synchronous); rw_attribute(journal_delay_ms); rw_attribute(io_disable); -rw_attribute(discard); rw_attribute(running); rw_attribute(label); rw_attribute(errors); @@ -1036,7 +1035,6 @@ SHOW(__bch_cache) sysfs_hprint(bucket_size, bucket_bytes(ca)); sysfs_hprint(block_size, block_bytes(ca)); sysfs_print(nbuckets, ca->sb.nbuckets); - sysfs_print(discard, ca->discard); sysfs_hprint(written, atomic_long_read(&ca->sectors_written) << 9); sysfs_hprint(btree_written, atomic_long_read(&ca->btree_sectors_written) << 9); @@ -1142,18 +1140,6 @@ STORE(__bch_cache) if (bcache_is_reboot) return -EBUSY; - if (attr == &sysfs_discard) { - bool v = strtoul_or_return(buf); - - if (bdev_max_discard_sectors(ca->bdev)) - ca->discard = v; - - if (v != CACHE_DISCARD(&ca->sb)) { - SET_CACHE_DISCARD(&ca->sb, v); - bcache_write_super(ca->set); - } - } - if (attr == &sysfs_cache_replacement_policy) { v = __sysfs_match_string(cache_replacement_policies, -1, buf); if (v < 0) @@ -1185,7 +1171,6 @@ static struct attribute *bch_cache_attrs[] = { &sysfs_block_size, &sysfs_nbuckets, &sysfs_priority_stats, - &sysfs_discard, &sysfs_written, &sysfs_btree_written, &sysfs_metadata_written, diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c index 6ba73dc1a3df..4b237074f453 100644 --- a/drivers/md/bcache/writeback.c +++ b/drivers/md/bcache/writeback.c @@ -805,8 +805,7 @@ static int bch_writeback_thread(void *arg) * may set BCH_ENABLE_AUTO_GC via sysfs, then when * BCH_DO_AUTO_GC is set, garbage collection thread * will be wake up here. After moving gc, the shrunk - * btree and discarded free buckets SSD space may be - * helpful for following write requests. + * btree may be helpful for following write requests. */ if (c->gc_after_writeback == (BCH_ENABLE_AUTO_GC|BCH_DO_AUTO_GC)) { @@ -1076,7 +1075,7 @@ void bch_cached_dev_writeback_init(struct cached_dev *dc) int bch_cached_dev_writeback_start(struct cached_dev *dc) { dc->writeback_write_wq = alloc_workqueue("bcache_writeback_wq", - WQ_MEM_RECLAIM, 0); + WQ_MEM_RECLAIM | WQ_PERCPU, 0); if (!dc->writeback_write_wq) return -ENOMEM; diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index e6d28be11c5c..5235f3e4924b 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -1374,7 +1374,7 @@ static void submit_io(struct dm_buffer *b, enum req_op op, unsigned short ioprio { unsigned int n_sectors; sector_t sector; - unsigned int offset, end; + unsigned int offset, end, align; b->end_io = end_io; @@ -1388,9 +1388,11 @@ static void submit_io(struct dm_buffer *b, enum req_op op, unsigned short ioprio b->c->write_callback(b); offset = b->write_start; end = b->write_end; - offset &= -DM_BUFIO_WRITE_ALIGN; - end += DM_BUFIO_WRITE_ALIGN - 1; - end &= -DM_BUFIO_WRITE_ALIGN; + align = max(DM_BUFIO_WRITE_ALIGN, + bdev_physical_block_size(b->c->bdev)); + offset &= -align; + end += align - 1; + end &= -align; if (unlikely(end > b->c->block_size)) end = b->c->block_size; diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h index a3c9f74fe2dc..1cda8618d74d 100644 --- a/drivers/md/dm-core.h +++ b/drivers/md/dm-core.h @@ -139,7 +139,6 @@ struct mapped_device { struct srcu_struct io_barrier; #ifdef CONFIG_BLK_DEV_ZONED - unsigned int nr_zones; void *zone_revalidate_map; struct task_struct *revalidate_map_task; #endif diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 5ef43231fe77..79704fbc523b 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -21,6 +21,7 @@ #include <linux/mempool.h> #include <linux/slab.h> #include <linux/crypto.h> +#include <linux/fips.h> #include <linux/workqueue.h> #include <linux/kthread.h> #include <linux/backing-dev.h> @@ -120,7 +121,6 @@ struct iv_benbi_private { #define LMK_SEED_SIZE 64 /* hash + 0 */ struct iv_lmk_private { - struct crypto_shash *hash_tfm; u8 *seed; }; @@ -254,22 +254,15 @@ static unsigned int max_write_size = 0; module_param(max_write_size, uint, 0644); MODULE_PARM_DESC(max_write_size, "Maximum size of a write request"); -static unsigned get_max_request_sectors(struct dm_target *ti, struct bio *bio) +static unsigned get_max_request_sectors(struct dm_target *ti, struct bio *bio, bool no_split) { struct crypt_config *cc = ti->private; unsigned val, sector_align; bool wrt = op_is_write(bio_op(bio)); - if (wrt) { - /* - * For zoned devices, splitting write operations creates the - * risk of deadlocking queue freeze operations with zone write - * plugging BIO work when the reminder of a split BIO is - * issued. So always allow the entire BIO to proceed. - */ - if (ti->emulate_zone_append) - return bio_sectors(bio); - + if (no_split) { + val = -1; + } else if (wrt) { val = min_not_zero(READ_ONCE(max_write_size), DM_CRYPT_DEFAULT_MAX_WRITE_SIZE); } else { @@ -465,10 +458,6 @@ static void crypt_iv_lmk_dtr(struct crypt_config *cc) { struct iv_lmk_private *lmk = &cc->iv_gen_private.lmk; - if (lmk->hash_tfm && !IS_ERR(lmk->hash_tfm)) - crypto_free_shash(lmk->hash_tfm); - lmk->hash_tfm = NULL; - kfree_sensitive(lmk->seed); lmk->seed = NULL; } @@ -483,11 +472,10 @@ static int crypt_iv_lmk_ctr(struct crypt_config *cc, struct dm_target *ti, return -EINVAL; } - lmk->hash_tfm = crypto_alloc_shash("md5", 0, - CRYPTO_ALG_ALLOCATES_MEMORY); - if (IS_ERR(lmk->hash_tfm)) { - ti->error = "Error initializing LMK hash"; - return PTR_ERR(lmk->hash_tfm); + if (fips_enabled) { + ti->error = "LMK support is disabled due to FIPS"; + /* ... because it uses MD5. */ + return -EINVAL; } /* No seed in LMK version 2 */ @@ -498,7 +486,6 @@ static int crypt_iv_lmk_ctr(struct crypt_config *cc, struct dm_target *ti, lmk->seed = kzalloc(LMK_SEED_SIZE, GFP_KERNEL); if (!lmk->seed) { - crypt_iv_lmk_dtr(cc); ti->error = "Error kmallocing seed storage in LMK"; return -ENOMEM; } @@ -514,7 +501,7 @@ static int crypt_iv_lmk_init(struct crypt_config *cc) /* LMK seed is on the position of LMK_KEYS + 1 key */ if (lmk->seed) memcpy(lmk->seed, cc->key + (cc->tfms_count * subkey_size), - crypto_shash_digestsize(lmk->hash_tfm)); + MD5_DIGEST_SIZE); return 0; } @@ -529,55 +516,31 @@ static int crypt_iv_lmk_wipe(struct crypt_config *cc) return 0; } -static int crypt_iv_lmk_one(struct crypt_config *cc, u8 *iv, - struct dm_crypt_request *dmreq, - u8 *data) +static void crypt_iv_lmk_one(struct crypt_config *cc, u8 *iv, + struct dm_crypt_request *dmreq, u8 *data) { struct iv_lmk_private *lmk = &cc->iv_gen_private.lmk; - SHASH_DESC_ON_STACK(desc, lmk->hash_tfm); - union { - struct md5_state md5state; - u8 state[CRYPTO_MD5_STATESIZE]; - } u; + struct md5_ctx ctx; __le32 buf[4]; - int i, r; - desc->tfm = lmk->hash_tfm; + md5_init(&ctx); - r = crypto_shash_init(desc); - if (r) - return r; - - if (lmk->seed) { - r = crypto_shash_update(desc, lmk->seed, LMK_SEED_SIZE); - if (r) - return r; - } + if (lmk->seed) + md5_update(&ctx, lmk->seed, LMK_SEED_SIZE); /* Sector is always 512B, block size 16, add data of blocks 1-31 */ - r = crypto_shash_update(desc, data + 16, 16 * 31); - if (r) - return r; + md5_update(&ctx, data + 16, 16 * 31); /* Sector is cropped to 56 bits here */ buf[0] = cpu_to_le32(dmreq->iv_sector & 0xFFFFFFFF); buf[1] = cpu_to_le32((((u64)dmreq->iv_sector >> 32) & 0x00FFFFFF) | 0x80000000); buf[2] = cpu_to_le32(4024); buf[3] = 0; - r = crypto_shash_update(desc, (u8 *)buf, sizeof(buf)); - if (r) - return r; + md5_update(&ctx, (u8 *)buf, sizeof(buf)); /* No MD5 padding here */ - r = crypto_shash_export(desc, &u.md5state); - if (r) - return r; - - for (i = 0; i < MD5_HASH_WORDS; i++) - __cpu_to_le32s(&u.md5state.hash[i]); - memcpy(iv, &u.md5state.hash, cc->iv_size); - - return 0; + cpu_to_le32_array(ctx.state.h, ARRAY_SIZE(ctx.state.h)); + memcpy(iv, ctx.state.h, cc->iv_size); } static int crypt_iv_lmk_gen(struct crypt_config *cc, u8 *iv, @@ -585,17 +548,15 @@ static int crypt_iv_lmk_gen(struct crypt_config *cc, u8 *iv, { struct scatterlist *sg; u8 *src; - int r = 0; if (bio_data_dir(dmreq->ctx->bio_in) == WRITE) { sg = crypt_get_sg_data(cc, dmreq->sg_in); src = kmap_local_page(sg_page(sg)); - r = crypt_iv_lmk_one(cc, iv, dmreq, src + sg->offset); + crypt_iv_lmk_one(cc, iv, dmreq, src + sg->offset); kunmap_local(src); } else memset(iv, 0, cc->iv_size); - - return r; + return 0; } static int crypt_iv_lmk_post(struct crypt_config *cc, u8 *iv, @@ -603,21 +564,19 @@ static int crypt_iv_lmk_post(struct crypt_config *cc, u8 *iv, { struct scatterlist *sg; u8 *dst; - int r; if (bio_data_dir(dmreq->ctx->bio_in) == WRITE) return 0; sg = crypt_get_sg_data(cc, dmreq->sg_out); dst = kmap_local_page(sg_page(sg)); - r = crypt_iv_lmk_one(cc, iv, dmreq, dst + sg->offset); + crypt_iv_lmk_one(cc, iv, dmreq, dst + sg->offset); /* Tweak the first block of plaintext sector */ - if (!r) - crypto_xor(dst + sg->offset, iv, cc->iv_size); + crypto_xor(dst + sg->offset, iv, cc->iv_size); kunmap_local(dst); - return r; + return 0; } static void crypt_iv_tcw_dtr(struct crypt_config *cc) @@ -1781,7 +1740,7 @@ static void crypt_free_buffer_pages(struct crypt_config *cc, struct bio *clone) bio_for_each_folio_all(fi, clone) { if (folio_test_large(fi.folio)) { percpu_counter_sub(&cc->n_allocated_pages, - 1 << folio_order(fi.folio)); + folio_nr_pages(fi.folio)); folio_put(fi.folio); } else { mempool_free(&fi.folio->page, &cc->page_pool); @@ -3496,6 +3455,7 @@ static int crypt_map(struct dm_target *ti, struct bio *bio) struct dm_crypt_io *io; struct crypt_config *cc = ti->private; unsigned max_sectors; + bool no_split; /* * If bio is REQ_PREFLUSH or REQ_OP_DISCARD, just bypass crypt queues. @@ -3513,10 +3473,20 @@ static int crypt_map(struct dm_target *ti, struct bio *bio) /* * Check if bio is too large, split as needed. + * + * For zoned devices, splitting write operations creates the + * risk of deadlocking queue freeze operations with zone write + * plugging BIO work when the reminder of a split BIO is + * issued. So always allow the entire BIO to proceed. */ - max_sectors = get_max_request_sectors(ti, bio); - if (unlikely(bio_sectors(bio) > max_sectors)) + no_split = (ti->emulate_zone_append && op_is_write(bio_op(bio))) || + (bio->bi_opf & REQ_ATOMIC); + max_sectors = get_max_request_sectors(ti, bio, no_split); + if (unlikely(bio_sectors(bio) > max_sectors)) { + if (unlikely(no_split)) + return DM_MAPIO_KILL; dm_accept_partial_bio(bio, max_sectors); + } /* * Ensure that bio is a multiple of internal sector encryption size @@ -3762,15 +3732,20 @@ static void crypt_io_hints(struct dm_target *ti, struct queue_limits *limits) if (ti->emulate_zone_append) limits->max_hw_sectors = min(limits->max_hw_sectors, BIO_MAX_VECS << PAGE_SECTORS_SHIFT); + + limits->atomic_write_hw_unit_max = min(limits->atomic_write_hw_unit_max, + BIO_MAX_VECS << PAGE_SHIFT); + limits->atomic_write_hw_max = min(limits->atomic_write_hw_max, + BIO_MAX_VECS << PAGE_SHIFT); } static struct target_type crypt_target = { .name = "crypt", - .version = {1, 28, 0}, + .version = {1, 29, 0}, .module = THIS_MODULE, .ctr = crypt_ctr, .dtr = crypt_dtr, - .features = DM_TARGET_ZONED_HM, + .features = DM_TARGET_ZONED_HM | DM_TARGET_ATOMIC_WRITES, .report_zones = crypt_report_zones, .map = crypt_map, .status = crypt_status, diff --git a/drivers/md/dm-ebs-target.c b/drivers/md/dm-ebs-target.c index 6abb31ca9662..b354e74a670e 100644 --- a/drivers/md/dm-ebs-target.c +++ b/drivers/md/dm-ebs-target.c @@ -103,7 +103,7 @@ static int __ebs_rw_bvec(struct ebs_c *ec, enum req_op op, struct bio_vec *bv, } else { flush_dcache_page(bv->bv_page); memcpy(ba, pa, cur_len); - dm_bufio_mark_partial_buffer_dirty(b, buf_off, buf_off + cur_len); + dm_bufio_mark_buffer_dirty(b); } dm_bufio_release(b); diff --git a/drivers/md/dm-exception-store.h b/drivers/md/dm-exception-store.h index b67976637538..061b4d310813 100644 --- a/drivers/md/dm-exception-store.h +++ b/drivers/md/dm-exception-store.h @@ -29,7 +29,7 @@ typedef sector_t chunk_t; * chunk within the device. */ struct dm_exception { - struct hlist_bl_node hash_list; + struct hlist_node hash_list; chunk_t old_chunk; chunk_t new_chunk; diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c index 7bb7174f8f4f..f0c84e7a5daa 100644 --- a/drivers/md/dm-log-writes.c +++ b/drivers/md/dm-log-writes.c @@ -432,6 +432,7 @@ static int log_writes_kthread(void *arg) struct log_writes_c *lc = arg; sector_t sector = 0; + set_freezable(); while (!kthread_should_stop()) { bool super = false; bool logging_enabled; diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index aaf4a0a4b0eb..c18358271618 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -131,7 +131,7 @@ static void queue_if_no_path_timeout_work(struct timer_list *t); #define MPATHF_QUEUE_IO 0 /* Must we queue all I/O? */ #define MPATHF_QUEUE_IF_NO_PATH 1 /* Queue I/O if last path fails? */ #define MPATHF_SAVED_QUEUE_IF_NO_PATH 2 /* Saved state during suspension */ -#define MPATHF_RETAIN_ATTACHED_HW_HANDLER 3 /* If there's already a hw_handler present, don't change it. */ +/* MPATHF_RETAIN_ATTACHED_HW_HANDLER no longer has any effect */ #define MPATHF_PG_INIT_DISABLED 4 /* pg_init is not currently allowed */ #define MPATHF_PG_INIT_REQUIRED 5 /* pg_init needs calling? */ #define MPATHF_PG_INIT_DELAY_RETRY 6 /* Delay pg_init retry? */ @@ -237,16 +237,10 @@ static struct multipath *alloc_multipath(struct dm_target *ti) static int alloc_multipath_stage2(struct dm_target *ti, struct multipath *m) { - if (m->queue_mode == DM_TYPE_NONE) { + if (m->queue_mode == DM_TYPE_NONE) m->queue_mode = DM_TYPE_REQUEST_BASED; - } else if (m->queue_mode == DM_TYPE_BIO_BASED) { + else if (m->queue_mode == DM_TYPE_BIO_BASED) INIT_WORK(&m->process_queued_bios, process_queued_bios); - /* - * bio-based doesn't support any direct scsi_dh management; - * it just discovers if a scsi_dh is attached. - */ - set_bit(MPATHF_RETAIN_ATTACHED_HW_HANDLER, &m->flags); - } dm_table_set_type(ti->table, m->queue_mode); @@ -887,36 +881,30 @@ static int setup_scsi_dh(struct block_device *bdev, struct multipath *m, struct request_queue *q = bdev_get_queue(bdev); int r; - if (mpath_double_check_test_bit(MPATHF_RETAIN_ATTACHED_HW_HANDLER, m)) { -retain: - if (*attached_handler_name) { - /* - * Clear any hw_handler_params associated with a - * handler that isn't already attached. - */ - if (m->hw_handler_name && strcmp(*attached_handler_name, m->hw_handler_name)) { - kfree(m->hw_handler_params); - m->hw_handler_params = NULL; - } - - /* - * Reset hw_handler_name to match the attached handler - * - * NB. This modifies the table line to show the actual - * handler instead of the original table passed in. - */ - kfree(m->hw_handler_name); - m->hw_handler_name = *attached_handler_name; - *attached_handler_name = NULL; + if (*attached_handler_name) { + /* + * Clear any hw_handler_params associated with a + * handler that isn't already attached. + */ + if (m->hw_handler_name && strcmp(*attached_handler_name, + m->hw_handler_name)) { + kfree(m->hw_handler_params); + m->hw_handler_params = NULL; } + + /* + * Reset hw_handler_name to match the attached handler + * + * NB. This modifies the table line to show the actual + * handler instead of the original table passed in. + */ + kfree(m->hw_handler_name); + m->hw_handler_name = *attached_handler_name; + *attached_handler_name = NULL; } if (m->hw_handler_name) { r = scsi_dh_attach(q, m->hw_handler_name); - if (r == -EBUSY) { - DMINFO("retaining handler on device %pg", bdev); - goto retain; - } if (r < 0) { *error = "error attaching hardware handler"; return r; @@ -1138,7 +1126,7 @@ static int parse_features(struct dm_arg_set *as, struct multipath *m) } if (!strcasecmp(arg_name, "retain_attached_hw_handler")) { - set_bit(MPATHF_RETAIN_ATTACHED_HW_HANDLER, &m->flags); + /* no longer has any effect */ continue; } @@ -1823,7 +1811,6 @@ static void multipath_status(struct dm_target *ti, status_type_t type, DMEMIT("%u ", test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags) + (m->pg_init_retries > 0) * 2 + (m->pg_init_delay_msecs != DM_PG_INIT_DELAY_DEFAULT) * 2 + - test_bit(MPATHF_RETAIN_ATTACHED_HW_HANDLER, &m->flags) + (m->queue_mode != DM_TYPE_REQUEST_BASED) * 2); if (test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags)) @@ -1832,8 +1819,6 @@ static void multipath_status(struct dm_target *ti, status_type_t type, DMEMIT("pg_init_retries %u ", m->pg_init_retries); if (m->pg_init_delay_msecs != DM_PG_INIT_DELAY_DEFAULT) DMEMIT("pg_init_delay_msecs %u ", m->pg_init_delay_msecs); - if (test_bit(MPATHF_RETAIN_ATTACHED_HW_HANDLER, &m->flags)) - DMEMIT("retain_attached_hw_handler "); if (m->queue_mode != DM_TYPE_REQUEST_BASED) { switch (m->queue_mode) { case DM_TYPE_BIO_BASED: @@ -2307,7 +2292,7 @@ static struct target_type multipath_target = { .name = "multipath", .version = {1, 15, 0}, .features = DM_TARGET_SINGLETON | DM_TARGET_IMMUTABLE | - DM_TARGET_PASSES_INTEGRITY, + DM_TARGET_PASSES_INTEGRITY | DM_TARGET_ATOMIC_WRITES, .module = THIS_MODULE, .ctr = multipath_ctr, .dtr = multipath_dtr, diff --git a/drivers/md/dm-pcache/Makefile b/drivers/md/dm-pcache/Makefile index 86776e4acad2..cedfd38854f6 100644 --- a/drivers/md/dm-pcache/Makefile +++ b/drivers/md/dm-pcache/Makefile @@ -1,3 +1,3 @@ dm-pcache-y := dm_pcache.o cache_dev.o segment.o backing_dev.o cache.o cache_gc.o cache_writeback.o cache_segment.o cache_key.o cache_req.o -obj-m += dm-pcache.o +obj-$(CONFIG_DM_PCACHE) += dm-pcache.o diff --git a/drivers/md/dm-pcache/cache.c b/drivers/md/dm-pcache/cache.c index d8e92367d947..534bf07b794f 100644 --- a/drivers/md/dm-pcache/cache.c +++ b/drivers/md/dm-pcache/cache.c @@ -10,7 +10,8 @@ struct kmem_cache *key_cache; static inline struct pcache_cache_info *get_cache_info_addr(struct pcache_cache *cache) { - return cache->cache_info_addr + cache->info_index; + return (struct pcache_cache_info *)((char *)cache->cache_info_addr + + (size_t)cache->info_index * PCACHE_CACHE_INFO_SIZE); } static void cache_info_write(struct pcache_cache *cache) @@ -21,10 +22,10 @@ static void cache_info_write(struct pcache_cache *cache) cache_info->header.crc = pcache_meta_crc(&cache_info->header, sizeof(struct pcache_cache_info)); + cache->info_index = (cache->info_index + 1) % PCACHE_META_INDEX_MAX; memcpy_flushcache(get_cache_info_addr(cache), cache_info, sizeof(struct pcache_cache_info)); - - cache->info_index = (cache->info_index + 1) % PCACHE_META_INDEX_MAX; + pmem_wmb(); } static void cache_info_init_default(struct pcache_cache *cache); @@ -49,6 +50,8 @@ static int cache_info_init(struct pcache_cache *cache, struct pcache_cache_optio return -EINVAL; } + cache->info_index = ((char *)cache_info_addr - (char *)cache->cache_info_addr) / PCACHE_CACHE_INFO_SIZE; + return 0; } @@ -93,10 +96,10 @@ void cache_pos_encode(struct pcache_cache *cache, pos_onmedia.header.seq = seq; pos_onmedia.header.crc = cache_pos_onmedia_crc(&pos_onmedia); + *index = (*index + 1) % PCACHE_META_INDEX_MAX; + memcpy_flushcache(pos_onmedia_addr, &pos_onmedia, sizeof(struct pcache_cache_pos_onmedia)); pmem_wmb(); - - *index = (*index + 1) % PCACHE_META_INDEX_MAX; } int cache_pos_decode(struct pcache_cache *cache, @@ -181,7 +184,7 @@ static void cache_info_init_default(struct pcache_cache *cache) { struct pcache_cache_info *cache_info = &cache->cache_info; - cache_info->header.seq = 0; + memset(cache_info, 0, sizeof(*cache_info)); cache_info->n_segs = cache->cache_dev->seg_num; cache_info_set_gc_percent(cache_info, PCACHE_CACHE_GC_PERCENT_DEFAULT); } @@ -411,7 +414,7 @@ void pcache_cache_stop(struct dm_pcache *pcache) { struct pcache_cache *cache = &pcache->cache; - cache_flush(cache); + pcache_cache_flush(cache); cancel_delayed_work_sync(&cache->gc_work); flush_work(&cache->clean_work); diff --git a/drivers/md/dm-pcache/cache.h b/drivers/md/dm-pcache/cache.h index 1136d86958c8..27613b56be54 100644 --- a/drivers/md/dm-pcache/cache.h +++ b/drivers/md/dm-pcache/cache.h @@ -339,7 +339,7 @@ void cache_seg_put(struct pcache_cache_segment *cache_seg); void cache_seg_set_next_seg(struct pcache_cache_segment *cache_seg, u32 seg_id); /* cache request*/ -int cache_flush(struct pcache_cache *cache); +int pcache_cache_flush(struct pcache_cache *cache); void miss_read_end_work_fn(struct work_struct *work); int pcache_cache_handle_req(struct pcache_cache *cache, struct pcache_request *pcache_req); diff --git a/drivers/md/dm-pcache/cache_req.c b/drivers/md/dm-pcache/cache_req.c index 27f94c1fa968..7854a30e07b7 100644 --- a/drivers/md/dm-pcache/cache_req.c +++ b/drivers/md/dm-pcache/cache_req.c @@ -790,7 +790,7 @@ err: } /** - * cache_flush - Flush all ksets to persist any pending cache data + * pcache_cache_flush - Flush all ksets to persist any pending cache data * @cache: Pointer to the cache structure * * This function iterates through all ksets associated with the provided `cache` @@ -802,7 +802,7 @@ err: * the respective error code, preventing the flush operation from proceeding to * subsequent ksets. */ -int cache_flush(struct pcache_cache *cache) +int pcache_cache_flush(struct pcache_cache *cache) { struct pcache_cache_kset *kset; int ret; @@ -827,7 +827,7 @@ int pcache_cache_handle_req(struct pcache_cache *cache, struct pcache_request *p struct bio *bio = pcache_req->bio; if (unlikely(bio->bi_opf & REQ_PREFLUSH)) - return cache_flush(cache); + return pcache_cache_flush(cache); if (bio_data_dir(bio) == READ) return cache_read(cache, pcache_req); diff --git a/drivers/md/dm-pcache/cache_segment.c b/drivers/md/dm-pcache/cache_segment.c index f0b58980806e..9d92e2b067ed 100644 --- a/drivers/md/dm-pcache/cache_segment.c +++ b/drivers/md/dm-pcache/cache_segment.c @@ -26,11 +26,11 @@ static void cache_seg_info_write(struct pcache_cache_segment *cache_seg) seg_info->header.seq++; seg_info->header.crc = pcache_meta_crc(&seg_info->header, sizeof(struct pcache_segment_info)); + cache_seg->info_index = (cache_seg->info_index + 1) % PCACHE_META_INDEX_MAX; + seg_info_addr = get_seg_info_addr(cache_seg); memcpy_flushcache(seg_info_addr, seg_info, sizeof(struct pcache_segment_info)); pmem_wmb(); - - cache_seg->info_index = (cache_seg->info_index + 1) % PCACHE_META_INDEX_MAX; mutex_unlock(&cache_seg->info_lock); } @@ -56,7 +56,10 @@ static int cache_seg_info_load(struct pcache_cache_segment *cache_seg) ret = -EIO; goto out; } - cache_seg->info_index = cache_seg_info_addr - cache_seg_info_addr_base; + + cache_seg->info_index = + ((char *)cache_seg_info_addr - (char *)cache_seg_info_addr_base) / + PCACHE_SEG_INFO_SIZE; out: mutex_unlock(&cache_seg->info_lock); @@ -129,10 +132,10 @@ static void cache_seg_ctrl_write(struct pcache_cache_segment *cache_seg) cache_seg_gen.header.crc = pcache_meta_crc(&cache_seg_gen.header, sizeof(struct pcache_cache_seg_gen)); + cache_seg->gen_index = (cache_seg->gen_index + 1) % PCACHE_META_INDEX_MAX; + memcpy_flushcache(get_cache_seg_gen_addr(cache_seg), &cache_seg_gen, sizeof(struct pcache_cache_seg_gen)); pmem_wmb(); - - cache_seg->gen_index = (cache_seg->gen_index + 1) % PCACHE_META_INDEX_MAX; } static void cache_seg_ctrl_init(struct pcache_cache_segment *cache_seg) diff --git a/drivers/md/dm-pcache/pcache_internal.h b/drivers/md/dm-pcache/pcache_internal.h index d427e534727c..b7a3319d2bd3 100644 --- a/drivers/md/dm-pcache/pcache_internal.h +++ b/drivers/md/dm-pcache/pcache_internal.h @@ -99,7 +99,7 @@ static inline void __must_check *pcache_meta_find_latest(struct pcache_meta_head /* Update latest if a more recent sequence is found */ if (!latest || pcache_meta_seq_after(meta->seq, seq_latest)) { seq_latest = meta->seq; - latest = (void *)header + (i * meta_max_size); + latest = meta_addr; } } diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index c6f7129e43d3..4bacdc499984 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -2287,6 +2287,8 @@ static int super_init_validation(struct raid_set *rs, struct md_rdev *rdev) mddev->reshape_position = le64_to_cpu(sb->reshape_position); rs->raid_type = get_raid_type_by_ll(mddev->level, mddev->layout); + if (!rs->raid_type) + return -EINVAL; } } else { diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c index f40c18da4000..dbd148967de4 100644 --- a/drivers/md/dm-snap.c +++ b/drivers/md/dm-snap.c @@ -40,10 +40,15 @@ static const char dm_snapshot_merge_target_name[] = "snapshot-merge"; #define DM_TRACKED_CHUNK_HASH(x) ((unsigned long)(x) & \ (DM_TRACKED_CHUNK_HASH_SIZE - 1)) +struct dm_hlist_head { + struct hlist_head head; + spinlock_t lock; +}; + struct dm_exception_table { uint32_t hash_mask; unsigned int hash_shift; - struct hlist_bl_head *table; + struct dm_hlist_head *table; }; struct dm_snapshot { @@ -628,8 +633,8 @@ static uint32_t exception_hash(struct dm_exception_table *et, chunk_t chunk); /* Lock to protect access to the completed and pending exception hash tables. */ struct dm_exception_table_lock { - struct hlist_bl_head *complete_slot; - struct hlist_bl_head *pending_slot; + spinlock_t *complete_slot; + spinlock_t *pending_slot; }; static void dm_exception_table_lock_init(struct dm_snapshot *s, chunk_t chunk, @@ -638,20 +643,20 @@ static void dm_exception_table_lock_init(struct dm_snapshot *s, chunk_t chunk, struct dm_exception_table *complete = &s->complete; struct dm_exception_table *pending = &s->pending; - lock->complete_slot = &complete->table[exception_hash(complete, chunk)]; - lock->pending_slot = &pending->table[exception_hash(pending, chunk)]; + lock->complete_slot = &complete->table[exception_hash(complete, chunk)].lock; + lock->pending_slot = &pending->table[exception_hash(pending, chunk)].lock; } static void dm_exception_table_lock(struct dm_exception_table_lock *lock) { - hlist_bl_lock(lock->complete_slot); - hlist_bl_lock(lock->pending_slot); + spin_lock_nested(lock->complete_slot, 1); + spin_lock_nested(lock->pending_slot, 2); } static void dm_exception_table_unlock(struct dm_exception_table_lock *lock) { - hlist_bl_unlock(lock->pending_slot); - hlist_bl_unlock(lock->complete_slot); + spin_unlock(lock->pending_slot); + spin_unlock(lock->complete_slot); } static int dm_exception_table_init(struct dm_exception_table *et, @@ -661,13 +666,15 @@ static int dm_exception_table_init(struct dm_exception_table *et, et->hash_shift = hash_shift; et->hash_mask = size - 1; - et->table = kvmalloc_array(size, sizeof(struct hlist_bl_head), + et->table = kvmalloc_array(size, sizeof(struct dm_hlist_head), GFP_KERNEL); if (!et->table) return -ENOMEM; - for (i = 0; i < size; i++) - INIT_HLIST_BL_HEAD(et->table + i); + for (i = 0; i < size; i++) { + INIT_HLIST_HEAD(&et->table[i].head); + spin_lock_init(&et->table[i].lock); + } return 0; } @@ -675,16 +682,17 @@ static int dm_exception_table_init(struct dm_exception_table *et, static void dm_exception_table_exit(struct dm_exception_table *et, struct kmem_cache *mem) { - struct hlist_bl_head *slot; + struct dm_hlist_head *slot; struct dm_exception *ex; - struct hlist_bl_node *pos, *n; + struct hlist_node *pos; int i, size; size = et->hash_mask + 1; for (i = 0; i < size; i++) { slot = et->table + i; - hlist_bl_for_each_entry_safe(ex, pos, n, slot, hash_list) { + hlist_for_each_entry_safe(ex, pos, &slot->head, hash_list) { + hlist_del(&ex->hash_list); kmem_cache_free(mem, ex); cond_resched(); } @@ -700,7 +708,7 @@ static uint32_t exception_hash(struct dm_exception_table *et, chunk_t chunk) static void dm_remove_exception(struct dm_exception *e) { - hlist_bl_del(&e->hash_list); + hlist_del(&e->hash_list); } /* @@ -710,12 +718,11 @@ static void dm_remove_exception(struct dm_exception *e) static struct dm_exception *dm_lookup_exception(struct dm_exception_table *et, chunk_t chunk) { - struct hlist_bl_head *slot; - struct hlist_bl_node *pos; + struct hlist_head *slot; struct dm_exception *e; - slot = &et->table[exception_hash(et, chunk)]; - hlist_bl_for_each_entry(e, pos, slot, hash_list) + slot = &et->table[exception_hash(et, chunk)].head; + hlist_for_each_entry(e, slot, hash_list) if (chunk >= e->old_chunk && chunk <= e->old_chunk + dm_consecutive_chunk_count(e)) return e; @@ -762,18 +769,17 @@ static void free_pending_exception(struct dm_snap_pending_exception *pe) static void dm_insert_exception(struct dm_exception_table *eh, struct dm_exception *new_e) { - struct hlist_bl_head *l; - struct hlist_bl_node *pos; + struct hlist_head *l; struct dm_exception *e = NULL; - l = &eh->table[exception_hash(eh, new_e->old_chunk)]; + l = &eh->table[exception_hash(eh, new_e->old_chunk)].head; /* Add immediately if this table doesn't support consecutive chunks */ if (!eh->hash_shift) goto out; /* List is ordered by old_chunk */ - hlist_bl_for_each_entry(e, pos, l, hash_list) { + hlist_for_each_entry(e, l, hash_list) { /* Insert after an existing chunk? */ if (new_e->old_chunk == (e->old_chunk + dm_consecutive_chunk_count(e) + 1) && @@ -804,13 +810,13 @@ out: * Either the table doesn't support consecutive chunks or slot * l is empty. */ - hlist_bl_add_head(&new_e->hash_list, l); + hlist_add_head(&new_e->hash_list, l); } else if (new_e->old_chunk < e->old_chunk) { /* Add before an existing exception */ - hlist_bl_add_before(&new_e->hash_list, &e->hash_list); + hlist_add_before(&new_e->hash_list, &e->hash_list); } else { /* Add to l's tail: e is the last exception in this slot */ - hlist_bl_add_behind(&new_e->hash_list, &e->hash_list); + hlist_add_behind(&new_e->hash_list, &e->hash_list); } } @@ -820,7 +826,6 @@ out: */ static int dm_add_exception(void *context, chunk_t old, chunk_t new) { - struct dm_exception_table_lock lock; struct dm_snapshot *s = context; struct dm_exception *e; @@ -833,17 +838,7 @@ static int dm_add_exception(void *context, chunk_t old, chunk_t new) /* Consecutive_count is implicitly initialised to zero */ e->new_chunk = new; - /* - * Although there is no need to lock access to the exception tables - * here, if we don't then hlist_bl_add_head(), called by - * dm_insert_exception(), will complain about accessing the - * corresponding list without locking it first. - */ - dm_exception_table_lock_init(s, old, &lock); - - dm_exception_table_lock(&lock); dm_insert_exception(&s->complete, e); - dm_exception_table_unlock(&lock); return 0; } @@ -873,7 +868,7 @@ static int calc_max_buckets(void) /* use a fixed size of 2MB */ unsigned long mem = 2 * 1024 * 1024; - mem /= sizeof(struct hlist_bl_head); + mem /= sizeof(struct dm_hlist_head); return mem; } diff --git a/drivers/md/dm-sysfs.c b/drivers/md/dm-sysfs.c index bfaef27ca79f..22bc70923a83 100644 --- a/drivers/md/dm-sysfs.c +++ b/drivers/md/dm-sysfs.c @@ -86,17 +86,13 @@ static ssize_t dm_attr_uuid_show(struct mapped_device *md, char *buf) static ssize_t dm_attr_suspended_show(struct mapped_device *md, char *buf) { - sprintf(buf, "%d\n", dm_suspended_md(md)); - - return strlen(buf); + return sysfs_emit(buf, "%d\n", dm_suspended_md(md)); } static ssize_t dm_attr_use_blk_mq_show(struct mapped_device *md, char *buf) { /* Purely for userspace compatibility */ - sprintf(buf, "%d\n", true); - - return strlen(buf); + return sysfs_emit(buf, "%d\n", true); } static DM_ATTR_RO(name); diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index ad0a60a07b93..0522cd700e0e 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -2043,6 +2043,10 @@ bool dm_table_supports_size_change(struct dm_table *t, sector_t old_size, return true; } +/* + * This function will be skipped by noflush reloads of immutable request + * based devices (dm-mpath). + */ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, struct queue_limits *limits) { diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index c84149ba4e38..52ffb495f5a8 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -395,13 +395,13 @@ static void begin_discard(struct discard_op *op, struct thin_c *tc, struct bio * op->bio = NULL; } -static int issue_discard(struct discard_op *op, dm_block_t data_b, dm_block_t data_e) +static void issue_discard(struct discard_op *op, dm_block_t data_b, dm_block_t data_e) { struct thin_c *tc = op->tc; sector_t s = block_to_sectors(tc->pool, data_b); sector_t len = block_to_sectors(tc->pool, data_e - data_b); - return __blkdev_issue_discard(tc->pool_dev->bdev, s, len, GFP_NOIO, &op->bio); + __blkdev_issue_discard(tc->pool_dev->bdev, s, len, GFP_NOIO, &op->bio); } static void end_discard(struct discard_op *op, int r) @@ -1113,9 +1113,7 @@ static void passdown_double_checking_shared_status(struct dm_thin_new_mapping *m break; } - r = issue_discard(&op, b, e); - if (r) - goto out; + issue_discard(&op, b, e); b = e; } @@ -1188,8 +1186,8 @@ static void process_prepared_discard_passdown_pt1(struct dm_thin_new_mapping *m) struct discard_op op; begin_discard(&op, tc, discard_parent); - r = issue_discard(&op, m->data_block, data_end); - end_discard(&op, r); + issue_discard(&op, m->data_block, data_end); + end_discard(&op, 0); } } @@ -4383,11 +4381,8 @@ static void thin_postsuspend(struct dm_target *ti) { struct thin_c *tc = ti->private; - /* - * The dm_noflush_suspending flag has been cleared by now, so - * unfortunately we must always run this. - */ - noflush_work(tc, do_noflush_stop); + if (dm_noflush_suspending(ti)) + noflush_work(tc, do_noflush_stop); } static int thin_preresume(struct dm_target *ti) diff --git a/drivers/md/dm-vdo/action-manager.c b/drivers/md/dm-vdo/action-manager.c index a0e5e7077d13..e3bba0b28aad 100644 --- a/drivers/md/dm-vdo/action-manager.c +++ b/drivers/md/dm-vdo/action-manager.c @@ -43,7 +43,7 @@ struct action { * @actions: The two action slots. * @current_action: The current action slot. * @zones: The number of zones in which an action is to be applied. - * @Scheduler: A function to schedule a default next action. + * @scheduler: A function to schedule a default next action. * @get_zone_thread_id: A function to get the id of the thread on which to apply an action to a * zone. * @initiator_thread_id: The ID of the thread on which actions may be initiated. diff --git a/drivers/md/dm-vdo/admin-state.c b/drivers/md/dm-vdo/admin-state.c index 3f9dba525154..da153fef085e 100644 --- a/drivers/md/dm-vdo/admin-state.c +++ b/drivers/md/dm-vdo/admin-state.c @@ -149,7 +149,8 @@ const struct admin_state_code *VDO_ADMIN_STATE_RESUMING = &VDO_CODE_RESUMING; /** * get_next_state() - Determine the state which should be set after a given operation completes * based on the operation and the current state. - * @operation The operation to be started. + * @state: The current admin state. + * @operation: The operation to be started. * * Return: The state to set when the operation completes or NULL if the operation can not be * started in the current state. @@ -187,6 +188,8 @@ static const struct admin_state_code *get_next_state(const struct admin_state *s /** * vdo_finish_operation() - Finish the current operation. + * @state: The current admin state. + * @result: The result of the operation. * * Will notify the operation waiter if there is one. This method should be used for operations * started with vdo_start_operation(). For operations which were started with vdo_start_draining(), @@ -214,8 +217,10 @@ bool vdo_finish_operation(struct admin_state *state, int result) /** * begin_operation() - Begin an operation if it may be started given the current state. - * @waiter A completion to notify when the operation is complete; may be NULL. - * @initiator The vdo_admin_initiator_fn to call if the operation may begin; may be NULL. + * @state: The current admin state. + * @operation: The operation to be started. + * @waiter: A completion to notify when the operation is complete; may be NULL. + * @initiator: The vdo_admin_initiator_fn to call if the operation may begin; may be NULL. * * Return: VDO_SUCCESS or an error. */ @@ -259,8 +264,10 @@ static int __must_check begin_operation(struct admin_state *state, /** * start_operation() - Start an operation if it may be started given the current state. - * @waiter A completion to notify when the operation is complete. - * @initiator The vdo_admin_initiator_fn to call if the operation may begin; may be NULL. + * @state: The current admin state. + * @operation: The operation to be started. + * @waiter: A completion to notify when the operation is complete; may be NULL. + * @initiator: The vdo_admin_initiator_fn to call if the operation may begin; may be NULL. * * Return: true if the operation was started. */ @@ -274,10 +281,10 @@ static inline bool __must_check start_operation(struct admin_state *state, /** * check_code() - Check the result of a state validation. - * @valid true if the code is of an appropriate type. - * @code The code which failed to be of the correct type. - * @what What the code failed to be, for logging. - * @waiter The completion to notify of the error; may be NULL. + * @valid: True if the code is of an appropriate type. + * @code: The code which failed to be of the correct type. + * @what: What the code failed to be, for logging. + * @waiter: The completion to notify of the error; may be NULL. * * If the result failed, log an invalid state error and, if there is a waiter, notify it. * @@ -301,7 +308,8 @@ static bool check_code(bool valid, const struct admin_state_code *code, const ch /** * assert_vdo_drain_operation() - Check that an operation is a drain. - * @waiter The completion to finish with an error if the operation is not a drain. + * @operation: The operation to check. + * @waiter: The completion to finish with an error if the operation is not a drain. * * Return: true if the specified operation is a drain. */ @@ -313,9 +321,10 @@ static bool __must_check assert_vdo_drain_operation(const struct admin_state_cod /** * vdo_start_draining() - Initiate a drain operation if the current state permits it. - * @operation The type of drain to initiate. - * @waiter The completion to notify when the drain is complete. - * @initiator The vdo_admin_initiator_fn to call if the operation may begin; may be NULL. + * @state: The current admin state. + * @operation: The type of drain to initiate. + * @waiter: The completion to notify when the drain is complete. + * @initiator: The vdo_admin_initiator_fn to call if the operation may begin; may be NULL. * * Return: true if the drain was initiated, if not the waiter will be notified. */ @@ -345,6 +354,7 @@ bool vdo_start_draining(struct admin_state *state, /** * vdo_finish_draining() - Finish a drain operation if one was in progress. + * @state: The current admin state. * * Return: true if the state was draining; will notify the waiter if so. */ @@ -355,6 +365,8 @@ bool vdo_finish_draining(struct admin_state *state) /** * vdo_finish_draining_with_result() - Finish a drain operation with a status code. + * @state: The current admin state. + * @result: The result of the drain operation. * * Return: true if the state was draining; will notify the waiter if so. */ @@ -365,7 +377,8 @@ bool vdo_finish_draining_with_result(struct admin_state *state, int result) /** * vdo_assert_load_operation() - Check that an operation is a load. - * @waiter The completion to finish with an error if the operation is not a load. + * @operation: The operation to check. + * @waiter: The completion to finish with an error if the operation is not a load. * * Return: true if the specified operation is a load. */ @@ -377,9 +390,10 @@ bool vdo_assert_load_operation(const struct admin_state_code *operation, /** * vdo_start_loading() - Initiate a load operation if the current state permits it. - * @operation The type of load to initiate. - * @waiter The completion to notify when the load is complete (may be NULL). - * @initiator The vdo_admin_initiator_fn to call if the operation may begin; may be NULL. + * @state: The current admin state. + * @operation: The type of load to initiate. + * @waiter: The completion to notify when the load is complete; may be NULL. + * @initiator: The vdo_admin_initiator_fn to call if the operation may begin; may be NULL. * * Return: true if the load was initiated, if not the waiter will be notified. */ @@ -393,6 +407,7 @@ bool vdo_start_loading(struct admin_state *state, /** * vdo_finish_loading() - Finish a load operation if one was in progress. + * @state: The current admin state. * * Return: true if the state was loading; will notify the waiter if so. */ @@ -403,7 +418,8 @@ bool vdo_finish_loading(struct admin_state *state) /** * vdo_finish_loading_with_result() - Finish a load operation with a status code. - * @result The result of the load operation. + * @state: The current admin state. + * @result: The result of the load operation. * * Return: true if the state was loading; will notify the waiter if so. */ @@ -414,7 +430,8 @@ bool vdo_finish_loading_with_result(struct admin_state *state, int result) /** * assert_vdo_resume_operation() - Check whether an admin_state_code is a resume operation. - * @waiter The completion to notify if the operation is not a resume operation; may be NULL. + * @operation: The operation to check. + * @waiter: The completion to notify if the operation is not a resume operation; may be NULL. * * Return: true if the code is a resume operation. */ @@ -427,9 +444,10 @@ static bool __must_check assert_vdo_resume_operation(const struct admin_state_co /** * vdo_start_resuming() - Initiate a resume operation if the current state permits it. - * @operation The type of resume to start. - * @waiter The completion to notify when the resume is complete (may be NULL). - * @initiator The vdo_admin_initiator_fn to call if the operation may begin; may be NULL. + * @state: The current admin state. + * @operation: The type of resume to start. + * @waiter: The completion to notify when the resume is complete; may be NULL. + * @initiator: The vdo_admin_initiator_fn to call if the operation may begin; may be NULL. * * Return: true if the resume was initiated, if not the waiter will be notified. */ @@ -443,6 +461,7 @@ bool vdo_start_resuming(struct admin_state *state, /** * vdo_finish_resuming() - Finish a resume operation if one was in progress. + * @state: The current admin state. * * Return: true if the state was resuming; will notify the waiter if so. */ @@ -453,7 +472,8 @@ bool vdo_finish_resuming(struct admin_state *state) /** * vdo_finish_resuming_with_result() - Finish a resume operation with a status code. - * @result The result of the resume operation. + * @state: The current admin state. + * @result: The result of the resume operation. * * Return: true if the state was resuming; will notify the waiter if so. */ @@ -465,6 +485,7 @@ bool vdo_finish_resuming_with_result(struct admin_state *state, int result) /** * vdo_resume_if_quiescent() - Change the state to normal operation if the current state is * quiescent. + * @state: The current admin state. * * Return: VDO_SUCCESS if the state resumed, VDO_INVALID_ADMIN_STATE otherwise. */ @@ -479,6 +500,8 @@ int vdo_resume_if_quiescent(struct admin_state *state) /** * vdo_start_operation() - Attempt to start an operation. + * @state: The current admin state. + * @operation: The operation to attempt to start. * * Return: VDO_SUCCESS if the operation was started, VDO_INVALID_ADMIN_STATE if not */ @@ -490,8 +513,10 @@ int vdo_start_operation(struct admin_state *state, /** * vdo_start_operation_with_waiter() - Attempt to start an operation. - * @waiter the completion to notify when the operation completes or fails to start; may be NULL. - * @initiator The vdo_admin_initiator_fn to call if the operation may begin; may be NULL. + * @state: The current admin state. + * @operation: The operation to attempt to start. + * @waiter: The completion to notify when the operation completes or fails to start; may be NULL. + * @initiator: The vdo_admin_initiator_fn to call if the operation may begin; may be NULL. * * Return: VDO_SUCCESS if the operation was started, VDO_INVALID_ADMIN_STATE if not */ diff --git a/drivers/md/dm-vdo/block-map.c b/drivers/md/dm-vdo/block-map.c index baf683cabb1b..a7db5b41155e 100644 --- a/drivers/md/dm-vdo/block-map.c +++ b/drivers/md/dm-vdo/block-map.c @@ -174,6 +174,7 @@ static inline struct vdo_page_completion *page_completion_from_waiter(struct vdo /** * initialize_info() - Initialize all page info structures and put them on the free list. + * @cache: The page cache. * * Return: VDO_SUCCESS or an error. */ @@ -209,6 +210,7 @@ static int initialize_info(struct vdo_page_cache *cache) /** * allocate_cache_components() - Allocate components of the cache which require their own * allocation. + * @cache: The page cache. * * The caller is responsible for all clean up on errors. * @@ -238,6 +240,8 @@ static int __must_check allocate_cache_components(struct vdo_page_cache *cache) /** * assert_on_cache_thread() - Assert that a function has been called on the VDO page cache's * thread. + * @cache: The page cache. + * @function_name: The funtion name to report if the assertion fails. */ static inline void assert_on_cache_thread(struct vdo_page_cache *cache, const char *function_name) @@ -271,6 +275,7 @@ static void report_cache_pressure(struct vdo_page_cache *cache) /** * get_page_state_name() - Return the name of a page state. + * @state: The page state to describe. * * If the page state is invalid a static string is returned and the invalid state is logged. * @@ -342,6 +347,8 @@ static void update_lru(struct page_info *info) /** * set_info_state() - Set the state of a page_info and put it on the right list, adjusting * counters. + * @info: The page info to update. + * @new_state: The new state to set. */ static void set_info_state(struct page_info *info, enum vdo_page_buffer_state new_state) { @@ -416,6 +423,7 @@ static int reset_page_info(struct page_info *info) /** * find_free_page() - Find a free page. + * @cache: The page cache. * * Return: A pointer to the page info structure (if found), NULL otherwise. */ @@ -433,6 +441,7 @@ static struct page_info * __must_check find_free_page(struct vdo_page_cache *cac /** * find_page() - Find the page info (if any) associated with a given pbn. + * @cache: The page cache. * @pbn: The absolute physical block number of the page. * * Return: The page info for the page if available, or NULL if not. @@ -449,6 +458,7 @@ static struct page_info * __must_check find_page(struct vdo_page_cache *cache, /** * select_lru_page() - Determine which page is least recently used. + * @cache: The page cache. * * Picks the least recently used from among the non-busy entries at the front of each of the lru * list. Since whenever we mark a page busy we also put it to the end of the list it is unlikely @@ -523,6 +533,8 @@ static void complete_waiter_with_page(struct vdo_waiter *waiter, void *page_info /** * distribute_page_over_waitq() - Complete a waitq of VDO page completions with a page result. + * @info: The loaded page info. + * @waitq: The list of waiting data_vios. * * Upon completion the waitq will be empty. * @@ -548,7 +560,9 @@ static unsigned int distribute_page_over_waitq(struct page_info *info, /** * set_persistent_error() - Set a persistent error which all requests will receive in the future. + * @cache: The page cache. * @context: A string describing what triggered the error. + * @result: The error result to set on the cache. * * Once triggered, all enqueued completions will get this error. Any future requests will result in * this error as well. @@ -581,6 +595,7 @@ static void set_persistent_error(struct vdo_page_cache *cache, const char *conte /** * validate_completed_page() - Check that a page completion which is being freed to the cache * referred to a valid page and is in a valid state. + * @completion: The page completion to check. * @writable: Whether a writable page is required. * * Return: VDO_SUCCESS if the page was valid, otherwise as error @@ -758,6 +773,8 @@ static void load_cache_page_endio(struct bio *bio) /** * launch_page_load() - Begin the process of loading a page. + * @info: The page info to launch. + * @pbn: The absolute physical block number of the page to load. * * Return: VDO_SUCCESS or an error code. */ @@ -836,6 +853,7 @@ static void save_pages(struct vdo_page_cache *cache) /** * schedule_page_save() - Add a page to the outgoing list of pages waiting to be saved. + * @info: The page info to save. * * Once in the list, a page may not be used until it has been written out. */ @@ -854,6 +872,7 @@ static void schedule_page_save(struct page_info *info) /** * launch_page_save() - Add a page to outgoing pages waiting to be saved, and then start saving * pages if another save is not in progress. + * @info: The page info to save. */ static void launch_page_save(struct page_info *info) { @@ -864,6 +883,7 @@ static void launch_page_save(struct page_info *info) /** * completion_needs_page() - Determine whether a given vdo_page_completion (as a waiter) is * requesting a given page number. + * @waiter: The page completion waiter to check. * @context: A pointer to the pbn of the desired page. * * Implements waiter_match_fn. @@ -880,6 +900,7 @@ static bool completion_needs_page(struct vdo_waiter *waiter, void *context) /** * allocate_free_page() - Allocate a free page to the first completion in the waiting queue, and * any other completions that match it in page number. + * @info: The page info to allocate a page for. */ static void allocate_free_page(struct page_info *info) { @@ -925,6 +946,7 @@ static void allocate_free_page(struct page_info *info) /** * discard_a_page() - Begin the process of discarding a page. + * @cache: The page cache. * * If no page is discardable, increments a count of deferred frees so that the next release of a * page which is no longer busy will kick off another discard cycle. This is an indication that the @@ -955,10 +977,6 @@ static void discard_a_page(struct vdo_page_cache *cache) launch_page_save(info); } -/** - * discard_page_for_completion() - Helper used to trigger a discard so that the completion can get - * a different page. - */ static void discard_page_for_completion(struct vdo_page_completion *vdo_page_comp) { struct vdo_page_cache *cache = vdo_page_comp->cache; @@ -1132,6 +1150,7 @@ static void write_pages(struct vdo_completion *flush_completion) /** * vdo_release_page_completion() - Release a VDO Page Completion. + * @completion: The page completion to release. * * The page referenced by this completion (if any) will no longer be held busy by this completion. * If a page becomes discardable and there are completions awaiting free pages then a new round of @@ -1172,10 +1191,6 @@ void vdo_release_page_completion(struct vdo_completion *completion) } } -/** - * load_page_for_completion() - Helper function to load a page as described by a VDO Page - * Completion. - */ static void load_page_for_completion(struct page_info *info, struct vdo_page_completion *vdo_page_comp) { @@ -1319,6 +1334,7 @@ int vdo_get_cached_page(struct vdo_completion *completion, /** * vdo_invalidate_page_cache() - Invalidate all entries in the VDO page cache. + * @cache: The page cache. * * There must not be any dirty pages in the cache. * @@ -1345,6 +1361,10 @@ int vdo_invalidate_page_cache(struct vdo_page_cache *cache) /** * get_tree_page_by_index() - Get the tree page for a given height and page index. + * @forest: The block map forest. + * @root_index: The root index of the tree to search. + * @height: The height in the tree. + * @page_index: The page index. * * Return: The requested page. */ @@ -2211,6 +2231,7 @@ static void allocate_block_map_page(struct block_map_zone *zone, /** * vdo_find_block_map_slot() - Find the block map slot in which the block map entry for a data_vio * resides and cache that result in the data_vio. + * @data_vio: The data vio. * * All ancestors in the tree will be allocated or loaded, as needed. */ @@ -2435,6 +2456,7 @@ static void deforest(struct forest *forest, size_t first_page_segment) /** * make_forest() - Make a collection of trees for a block_map, expanding the existing forest if * there is one. + * @map: The block map. * @entries: The number of entries the block map will hold. * * Return: VDO_SUCCESS or an error. @@ -2476,6 +2498,7 @@ static int make_forest(struct block_map *map, block_count_t entries) /** * replace_forest() - Replace a block_map's forest with the already-prepared larger forest. + * @map: The block map. */ static void replace_forest(struct block_map *map) { @@ -2492,6 +2515,7 @@ static void replace_forest(struct block_map *map) /** * finish_cursor() - Finish the traversal of a single tree. If it was the last cursor, finish the * traversal. + * @cursor: The cursor to complete. */ static void finish_cursor(struct cursor *cursor) { @@ -2549,6 +2573,7 @@ static void traversal_endio(struct bio *bio) /** * traverse() - Traverse a single block map tree. + * @cursor: A cursor tracking traversal progress. * * This is the recursive heart of the traversal process. */ @@ -2619,6 +2644,7 @@ static void traverse(struct cursor *cursor) /** * launch_cursor() - Start traversing a single block map tree now that the cursor has a VIO with * which to load pages. + * @waiter: The parent of the cursor to launch. * @context: The pooled_vio just acquired. * * Implements waiter_callback_fn. @@ -2636,6 +2662,8 @@ static void launch_cursor(struct vdo_waiter *waiter, void *context) /** * compute_boundary() - Compute the number of pages used at each level of the given root's tree. + * @map: The block map. + * @root_index: The tree root index. * * Return: The list of page counts as a boundary structure. */ @@ -2668,6 +2696,7 @@ static struct boundary compute_boundary(struct block_map *map, root_count_t root /** * vdo_traverse_forest() - Walk the entire forest of a block map. + * @map: The block map. * @callback: A function to call with the pbn of each allocated node in the forest. * @completion: The completion to notify on each traversed PBN, and when traversal completes. */ @@ -2707,6 +2736,9 @@ void vdo_traverse_forest(struct block_map *map, vdo_entry_callback_fn callback, /** * initialize_block_map_zone() - Initialize the per-zone portions of the block map. + * @map: The block map. + * @zone_number: The zone to initialize. + * @cache_size: The total block map cache size. * @maximum_age: The number of journal blocks before a dirtied page is considered old and must be * written out. */ @@ -3091,6 +3123,7 @@ static void fetch_mapping_page(struct data_vio *data_vio, bool modifiable, /** * clear_mapped_location() - Clear a data_vio's mapped block location, setting it to be unmapped. + * @data_vio: The data vio. * * This indicates the block map entry for the logical block is either unmapped or corrupted. */ @@ -3104,6 +3137,8 @@ static void clear_mapped_location(struct data_vio *data_vio) /** * set_mapped_location() - Decode and validate a block map entry, and set the mapped location of a * data_vio. + * @data_vio: The data vio. + * @entry: The new mapped entry to set. * * Return: VDO_SUCCESS or VDO_BAD_MAPPING if the map entry is invalid or an error code for any * other failure diff --git a/drivers/md/dm-vdo/completion.c b/drivers/md/dm-vdo/completion.c index 5ad85334632d..2f00acbb3b2b 100644 --- a/drivers/md/dm-vdo/completion.c +++ b/drivers/md/dm-vdo/completion.c @@ -65,6 +65,8 @@ static inline void assert_incomplete(struct vdo_completion *completion) /** * vdo_set_completion_result() - Set the result of a completion. + * @completion: The completion to update. + * @result: The result to set. * * Older errors will not be masked. */ @@ -77,6 +79,7 @@ void vdo_set_completion_result(struct vdo_completion *completion, int result) /** * vdo_launch_completion_with_priority() - Run or enqueue a completion. + * @completion: The completion to launch. * @priority: The priority at which to enqueue the completion. * * If called on the correct thread (i.e. the one specified in the completion's callback_thread_id @@ -125,6 +128,8 @@ void vdo_enqueue_completion(struct vdo_completion *completion, /** * vdo_requeue_completion_if_needed() - Requeue a completion if not called on the specified thread. + * @completion: The completion to requeue. + * @callback_thread_id: The thread on which to requeue the completion. * * Return: True if the completion was requeued; callers may not access the completion in this case. */ diff --git a/drivers/md/dm-vdo/data-vio.c b/drivers/md/dm-vdo/data-vio.c index 262e11581f2d..3333e1e5b02e 100644 --- a/drivers/md/dm-vdo/data-vio.c +++ b/drivers/md/dm-vdo/data-vio.c @@ -227,6 +227,7 @@ static inline u64 get_arrival_time(struct bio *bio) /** * check_for_drain_complete_locked() - Check whether a data_vio_pool has no outstanding data_vios * or waiters while holding the pool's lock. + * @pool: The data_vio pool. */ static bool check_for_drain_complete_locked(struct data_vio_pool *pool) { @@ -387,6 +388,7 @@ struct data_vio_compression_status advance_data_vio_compression_stage(struct dat /** * cancel_data_vio_compression() - Prevent this data_vio from being compressed or packed. + * @data_vio: The data_vio. * * Return: true if the data_vio is in the packer and the caller was the first caller to cancel it. */ @@ -483,6 +485,8 @@ static void attempt_logical_block_lock(struct vdo_completion *completion) /** * launch_data_vio() - (Re)initialize a data_vio to have a new logical block number, keeping the * same parent and other state and send it on its way. + * @data_vio: The data_vio to launch. + * @lbn: The logical block number. */ static void launch_data_vio(struct data_vio *data_vio, logical_block_number_t lbn) { @@ -641,6 +645,7 @@ static void update_limiter(struct limiter *limiter) /** * schedule_releases() - Ensure that release processing is scheduled. + * @pool: The data_vio pool. * * If this call switches the state to processing, enqueue. Otherwise, some other thread has already * done so. @@ -768,6 +773,8 @@ static void initialize_limiter(struct limiter *limiter, struct data_vio_pool *po /** * initialize_data_vio() - Allocate the components of a data_vio. + * @data_vio: The data_vio to initialize. + * @vdo: The vdo containing the data_vio. * * The caller is responsible for cleaning up the data_vio on error. * @@ -880,6 +887,7 @@ int make_data_vio_pool(struct vdo *vdo, data_vio_count_t pool_size, /** * free_data_vio_pool() - Free a data_vio_pool and the data_vios in it. + * @pool: The data_vio pool to free. * * All data_vios must be returned to the pool before calling this function. */ @@ -944,6 +952,8 @@ static void wait_permit(struct limiter *limiter, struct bio *bio) /** * vdo_launch_bio() - Acquire a data_vio from the pool, assign the bio to it, and launch it. + * @pool: The data_vio pool. + * @bio: The bio to launch. * * This will block if data_vios or discard permits are not available. */ @@ -994,6 +1004,7 @@ static void assert_on_vdo_cpu_thread(const struct vdo *vdo, const char *name) /** * drain_data_vio_pool() - Wait asynchronously for all data_vios to be returned to the pool. + * @pool: The data_vio pool. * @completion: The completion to notify when the pool has drained. */ void drain_data_vio_pool(struct data_vio_pool *pool, struct vdo_completion *completion) @@ -1005,6 +1016,7 @@ void drain_data_vio_pool(struct data_vio_pool *pool, struct vdo_completion *comp /** * resume_data_vio_pool() - Resume a data_vio pool. + * @pool: The data_vio pool. * @completion: The completion to notify when the pool has resumed. */ void resume_data_vio_pool(struct data_vio_pool *pool, struct vdo_completion *completion) @@ -1024,6 +1036,7 @@ static void dump_limiter(const char *name, struct limiter *limiter) /** * dump_data_vio_pool() - Dump a data_vio pool to the log. + * @pool: The data_vio pool. * @dump_vios: Whether to dump the details of each busy data_vio as well. */ void dump_data_vio_pool(struct data_vio_pool *pool, bool dump_vios) @@ -1114,6 +1127,7 @@ static void perform_cleanup_stage(struct data_vio *data_vio, /** * release_allocated_lock() - Release the PBN lock and/or the reference on the allocated block at * the end of processing a data_vio. + * @completion: The data_vio holding the lock. */ static void release_allocated_lock(struct vdo_completion *completion) { @@ -1194,6 +1208,7 @@ static void transfer_lock(struct data_vio *data_vio, struct lbn_lock *lock) /** * release_logical_lock() - Release the logical block lock and flush generation lock at the end of * processing a data_vio. + * @completion: The data_vio holding the lock. */ static void release_logical_lock(struct vdo_completion *completion) { @@ -1228,6 +1243,7 @@ static void clean_hash_lock(struct vdo_completion *completion) /** * finish_cleanup() - Make some assertions about a data_vio which has finished cleaning up. + * @data_vio: The data_vio. * * If it is part of a multi-block discard, starts on the next block, otherwise, returns it to the * pool. @@ -1342,6 +1358,7 @@ void handle_data_vio_error(struct vdo_completion *completion) /** * get_data_vio_operation_name() - Get the name of the last asynchronous operation performed on a * data_vio. + * @data_vio: The data_vio. */ const char *get_data_vio_operation_name(struct data_vio *data_vio) { @@ -1355,7 +1372,7 @@ const char *get_data_vio_operation_name(struct data_vio *data_vio) /** * data_vio_allocate_data_block() - Allocate a data block. - * + * @data_vio: The data_vio. * @write_lock_type: The type of write lock to obtain on the block. * @callback: The callback which will attempt an allocation in the current zone and continue if it * succeeds. @@ -1379,6 +1396,7 @@ void data_vio_allocate_data_block(struct data_vio *data_vio, /** * release_data_vio_allocation_lock() - Release the PBN lock on a data_vio's allocated block. + * @data_vio: The data_vio. * @reset: If true, the allocation will be reset (i.e. any allocated pbn will be forgotten). * * If the reference to the locked block is still provisional, it will be released as well. @@ -1399,6 +1417,7 @@ void release_data_vio_allocation_lock(struct data_vio *data_vio, bool reset) /** * uncompress_data_vio() - Uncompress the data a data_vio has just read. + * @data_vio: The data_vio. * @mapping_state: The mapping state indicating which fragment to decompress. * @buffer: The buffer to receive the uncompressed data. */ @@ -1519,6 +1538,7 @@ static void complete_zero_read(struct vdo_completion *completion) /** * read_block() - Read a block asynchronously. + * @completion: The data_vio doing the read. * * This is the callback registered in read_block_mapping(). */ @@ -1675,6 +1695,7 @@ static void journal_remapping(struct vdo_completion *completion) /** * read_old_block_mapping() - Get the previous PBN/LBN mapping of an in-progress write. + * @completion: The data_vio doing the read. * * Gets the previous PBN mapped to this LBN from the block map, so as to make an appropriate * journal entry referencing the removal of this LBN->PBN mapping. @@ -1704,6 +1725,7 @@ void update_metadata_for_data_vio_write(struct data_vio *data_vio, struct pbn_lo /** * pack_compressed_data() - Attempt to pack the compressed data_vio into a block. + * @completion: The data_vio. * * This is the callback registered in launch_compress_data_vio(). */ @@ -1725,6 +1747,7 @@ static void pack_compressed_data(struct vdo_completion *completion) /** * compress_data_vio() - Do the actual work of compressing the data on a CPU queue. + * @completion: The data_vio. * * This callback is registered in launch_compress_data_vio(). */ @@ -1754,6 +1777,7 @@ static void compress_data_vio(struct vdo_completion *completion) /** * launch_compress_data_vio() - Continue a write by attempting to compress the data. + * @data_vio: The data_vio. * * This is a re-entry point to vio_write used by hash locks. */ @@ -1796,7 +1820,8 @@ void launch_compress_data_vio(struct data_vio *data_vio) /** * hash_data_vio() - Hash the data in a data_vio and set the hash zone (which also flags the record * name as set). - + * @completion: The data_vio. + * * This callback is registered in prepare_for_dedupe(). */ static void hash_data_vio(struct vdo_completion *completion) @@ -1832,6 +1857,7 @@ static void prepare_for_dedupe(struct data_vio *data_vio) /** * write_bio_finished() - This is the bio_end_io function registered in write_block() to be called * when a data_vio's write to the underlying storage has completed. + * @bio: The bio to update. */ static void write_bio_finished(struct bio *bio) { @@ -1884,6 +1910,7 @@ void write_data_vio(struct data_vio *data_vio) /** * acknowledge_write_callback() - Acknowledge a write to the requestor. + * @completion: The data_vio. * * This callback is registered in allocate_block() and continue_write_with_block_map_slot(). */ @@ -1909,6 +1936,7 @@ static void acknowledge_write_callback(struct vdo_completion *completion) /** * allocate_block() - Attempt to allocate a block in the current allocation zone. + * @completion: The data_vio. * * This callback is registered in continue_write_with_block_map_slot(). */ @@ -1941,6 +1969,7 @@ static void allocate_block(struct vdo_completion *completion) /** * handle_allocation_error() - Handle an error attempting to allocate a block. + * @completion: The data_vio. * * This error handler is registered in continue_write_with_block_map_slot(). */ @@ -1970,6 +1999,7 @@ static int assert_is_discard(struct data_vio *data_vio) /** * continue_data_vio_with_block_map_slot() - Read the data_vio's mapping from the block map. + * @completion: The data_vio to continue. * * This callback is registered in launch_read_data_vio(). */ diff --git a/drivers/md/dm-vdo/dedupe.c b/drivers/md/dm-vdo/dedupe.c index 4d983092a152..75a26f3f4461 100644 --- a/drivers/md/dm-vdo/dedupe.c +++ b/drivers/md/dm-vdo/dedupe.c @@ -917,6 +917,8 @@ static int __must_check acquire_lock(struct hash_zone *zone, /** * enter_forked_lock() - Bind the data_vio to a new hash lock. + * @waiter: The data_vio's waiter link. + * @context: The new hash lock. * * Implements waiter_callback_fn. Binds the data_vio that was waiting to a new hash lock and waits * on that lock. @@ -971,7 +973,7 @@ static void fork_hash_lock(struct hash_lock *old_lock, struct data_vio *new_agen * path. * @lock: The hash lock. * @data_vio: The data_vio to deduplicate using the hash lock. - * @has_claim: true if the data_vio already has claimed an increment from the duplicate lock. + * @has_claim: True if the data_vio already has claimed an increment from the duplicate lock. * * If no increments are available, this will roll over to a new hash lock and launch the data_vio * as the writing agent for that lock. @@ -996,7 +998,7 @@ static void launch_dedupe(struct hash_lock *lock, struct data_vio *data_vio, * true copy of their data on disk. * @lock: The hash lock. * @agent: The data_vio acting as the agent for the lock. - * @agent_is_done: true only if the agent has already written or deduplicated against its data. + * @agent_is_done: True only if the agent has already written or deduplicated against its data. * * If the agent itself needs to deduplicate, an increment for it must already have been claimed * from the duplicate lock, ensuring the hash lock will still have a data_vio holding it. @@ -2146,8 +2148,8 @@ static void start_expiration_timer(struct dedupe_context *context) /** * report_dedupe_timeouts() - Record and eventually report that some dedupe requests reached their * expiration time without getting answers, so we timed them out. - * @zones: the hash zones. - * @timeouts: the number of newly timed out requests. + * @zones: The hash zones. + * @timeouts: The number of newly timed out requests. */ static void report_dedupe_timeouts(struct hash_zones *zones, unsigned int timeouts) { @@ -2509,6 +2511,8 @@ static void initiate_suspend_index(struct admin_state *state) /** * suspend_index() - Suspend the UDS index prior to draining hash zones. + * @context: Not used. + * @completion: The completion for the suspend operation. * * Implements vdo_action_preamble_fn */ @@ -2521,21 +2525,13 @@ static void suspend_index(void *context, struct vdo_completion *completion) initiate_suspend_index); } -/** - * initiate_drain() - Initiate a drain. - * - * Implements vdo_admin_initiator_fn. - */ +/** Implements vdo_admin_initiator_fn. */ static void initiate_drain(struct admin_state *state) { check_for_drain_complete(container_of(state, struct hash_zone, state)); } -/** - * drain_hash_zone() - Drain a hash zone. - * - * Implements vdo_zone_action_fn. - */ +/** Implements vdo_zone_action_fn. */ static void drain_hash_zone(void *context, zone_count_t zone_number, struct vdo_completion *parent) { @@ -2572,6 +2568,8 @@ static void launch_dedupe_state_change(struct hash_zones *zones) /** * resume_index() - Resume the UDS index prior to resuming hash zones. + * @context: Not used. + * @parent: The completion for the resume operation. * * Implements vdo_action_preamble_fn */ @@ -2602,11 +2600,7 @@ static void resume_index(void *context, struct vdo_completion *parent) vdo_finish_completion(parent); } -/** - * resume_hash_zone() - Resume a hash zone. - * - * Implements vdo_zone_action_fn. - */ +/** Implements vdo_zone_action_fn. */ static void resume_hash_zone(void *context, zone_count_t zone_number, struct vdo_completion *parent) { @@ -2634,7 +2628,7 @@ void vdo_resume_hash_zones(struct hash_zones *zones, struct vdo_completion *pare /** * get_hash_zone_statistics() - Add the statistics for this hash zone to the tally for all zones. * @zone: The hash zone to query. - * @tally: The tally + * @tally: The tally. */ static void get_hash_zone_statistics(const struct hash_zone *zone, struct hash_lock_statistics *tally) @@ -2680,8 +2674,8 @@ static void get_index_statistics(struct hash_zones *zones, /** * vdo_get_dedupe_statistics() - Tally the statistics from all the hash zones and the UDS index. - * @zones: The hash zones to query - * @stats: A structure to store the statistics + * @zones: The hash zones to query. + * @stats: A structure to store the statistics. * * Return: The sum of the hash lock statistics from all hash zones plus the statistics from the UDS * index @@ -2856,9 +2850,9 @@ void vdo_set_dedupe_index_min_timer_interval(unsigned int value) /** * acquire_context() - Acquire a dedupe context from a hash_zone if any are available. - * @zone: the hash zone + * @zone: The hash zone. * - * Return: A dedupe_context or NULL if none are available + * Return: A dedupe_context or NULL if none are available. */ static struct dedupe_context * __must_check acquire_context(struct hash_zone *zone) { diff --git a/drivers/md/dm-vdo/dm-vdo-target.c b/drivers/md/dm-vdo/dm-vdo-target.c index 0e04c2021682..6af40d40f255 100644 --- a/drivers/md/dm-vdo/dm-vdo-target.c +++ b/drivers/md/dm-vdo/dm-vdo-target.c @@ -1144,6 +1144,7 @@ static bool vdo_uses_device(struct vdo *vdo, const void *context) /** * get_thread_id_for_phase() - Get the thread id for the current phase of the admin operation in * progress. + * @vdo: The vdo. */ static thread_id_t __must_check get_thread_id_for_phase(struct vdo *vdo) { @@ -1188,9 +1189,9 @@ static struct vdo_completion *prepare_admin_completion(struct vdo *vdo, /** * advance_phase() - Increment the phase of the current admin operation and prepare the admin * completion to run on the thread for the next phase. - * @vdo: The on which an admin operation is being performed + * @vdo: The vdo on which an admin operation is being performed. * - * Return: The current phase + * Return: The current phase. */ static u32 advance_phase(struct vdo *vdo) { diff --git a/drivers/md/dm-vdo/encodings.c b/drivers/md/dm-vdo/encodings.c index b7cc0f41caca..dd59691be840 100644 --- a/drivers/md/dm-vdo/encodings.c +++ b/drivers/md/dm-vdo/encodings.c @@ -432,7 +432,10 @@ static void encode_block_map_state_2_0(u8 *buffer, size_t *offset, /** * vdo_compute_new_forest_pages() - Compute the number of pages which must be allocated at each * level in order to grow the forest to a new number of entries. + * @root_count: The number of block map roots. + * @old_sizes: The sizes of the old tree segments. * @entries: The new number of entries the block map must address. + * @new_sizes: The sizes of the new tree segments. * * Return: The total number of non-leaf pages required. */ @@ -462,6 +465,9 @@ block_count_t vdo_compute_new_forest_pages(root_count_t root_count, /** * encode_recovery_journal_state_7_0() - Encode the state of a recovery journal. + * @buffer: A buffer to store the encoding. + * @offset: The offset in the buffer at which to encode. + * @state: The recovery journal state to encode. * * Return: VDO_SUCCESS or an error code. */ @@ -484,6 +490,7 @@ static void encode_recovery_journal_state_7_0(u8 *buffer, size_t *offset, /** * decode_recovery_journal_state_7_0() - Decode the state of a recovery journal saved in a buffer. * @buffer: The buffer containing the saved state. + * @offset: The offset to start decoding from. * @state: A pointer to a recovery journal state to hold the result of a successful decode. * * Return: VDO_SUCCESS or an error code. @@ -544,6 +551,9 @@ const char *vdo_get_journal_operation_name(enum journal_operation operation) /** * encode_slab_depot_state_2_0() - Encode the state of a slab depot into a buffer. + * @buffer: A buffer to store the encoding. + * @offset: The offset in the buffer at which to encode. + * @state: The slab depot state to encode. */ static void encode_slab_depot_state_2_0(u8 *buffer, size_t *offset, struct slab_depot_state_2_0 state) @@ -570,6 +580,9 @@ static void encode_slab_depot_state_2_0(u8 *buffer, size_t *offset, /** * decode_slab_depot_state_2_0() - Decode slab depot component state version 2.0 from a buffer. + * @buffer: The buffer being decoded. + * @offset: The offset to start decoding from. + * @state: A pointer to a slab depot state to hold the decoded result. * * Return: VDO_SUCCESS or an error code. */ @@ -1156,6 +1169,9 @@ static struct vdo_component unpack_vdo_component_41_0(struct packed_vdo_componen /** * decode_vdo_component() - Decode the component data for the vdo itself out of the super block. + * @buffer: The buffer being decoded. + * @offset: The offset to start decoding from. + * @component: The vdo component structure to decode into. * * Return: VDO_SUCCESS or an error. */ @@ -1290,7 +1306,7 @@ void vdo_destroy_component_states(struct vdo_component_states *states) * understand. * @buffer: The buffer being decoded. * @offset: The offset to start decoding from. - * @geometry: The vdo geometry + * @geometry: The vdo geometry. * @states: An object to hold the successfully decoded state. * * Return: VDO_SUCCESS or an error. @@ -1329,7 +1345,7 @@ static int __must_check decode_components(u8 *buffer, size_t *offset, /** * vdo_decode_component_states() - Decode the payload of a super block. * @buffer: The buffer containing the encoded super block contents. - * @geometry: The vdo geometry + * @geometry: The vdo geometry. * @states: A pointer to hold the decoded states. * * Return: VDO_SUCCESS or an error. @@ -1383,6 +1399,9 @@ int vdo_validate_component_states(struct vdo_component_states *states, /** * vdo_encode_component_states() - Encode the state of all vdo components in the super block. + * @buffer: A buffer to store the encoding. + * @offset: The offset into the buffer to start the encoding. + * @states: The component states to encode. */ static void vdo_encode_component_states(u8 *buffer, size_t *offset, const struct vdo_component_states *states) @@ -1402,6 +1421,8 @@ static void vdo_encode_component_states(u8 *buffer, size_t *offset, /** * vdo_encode_super_block() - Encode a super block into its on-disk representation. + * @buffer: A buffer to store the encoding. + * @states: The component states to encode. */ void vdo_encode_super_block(u8 *buffer, struct vdo_component_states *states) { @@ -1426,6 +1447,7 @@ void vdo_encode_super_block(u8 *buffer, struct vdo_component_states *states) /** * vdo_decode_super_block() - Decode a super block from its on-disk representation. + * @buffer: The buffer to decode from. */ int vdo_decode_super_block(u8 *buffer) { diff --git a/drivers/md/dm-vdo/flush.c b/drivers/md/dm-vdo/flush.c index dd4fdee2ca0c..82a259ef1601 100644 --- a/drivers/md/dm-vdo/flush.c +++ b/drivers/md/dm-vdo/flush.c @@ -522,11 +522,7 @@ static void vdo_complete_flush(struct vdo_flush *flush) vdo_enqueue_completion(completion, BIO_Q_FLUSH_PRIORITY); } -/** - * initiate_drain() - Initiate a drain. - * - * Implements vdo_admin_initiator_fn. - */ +/** Implements vdo_admin_initiator_fn. */ static void initiate_drain(struct admin_state *state) { check_for_drain_complete(container_of(state, struct flusher, state)); diff --git a/drivers/md/dm-vdo/funnel-workqueue.c b/drivers/md/dm-vdo/funnel-workqueue.c index 0613c82bbe8e..8a79b33b8b09 100644 --- a/drivers/md/dm-vdo/funnel-workqueue.c +++ b/drivers/md/dm-vdo/funnel-workqueue.c @@ -372,6 +372,13 @@ static int make_simple_work_queue(const char *thread_name_prefix, const char *na /** * vdo_make_work_queue() - Create a work queue; if multiple threads are requested, completions will * be distributed to them in round-robin fashion. + * @thread_name_prefix: A prefix for the thread names to identify them as a vdo thread. + * @name: A base name to identify this queue. + * @owner: The vdo_thread structure to manage this queue. + * @type: The type of queue to create. + * @thread_count: The number of actual threads handling this queue. + * @thread_privates: An array of private contexts, one for each thread; may be NULL. + * @queue_ptr: A pointer to return the new work queue. * * Each queue is associated with a struct vdo_thread which has a single vdo thread id. Regardless * of the actual number of queues and threads allocated here, code outside of the queue diff --git a/drivers/md/dm-vdo/io-submitter.c b/drivers/md/dm-vdo/io-submitter.c index 11d47770b54d..e26d75f8366d 100644 --- a/drivers/md/dm-vdo/io-submitter.c +++ b/drivers/md/dm-vdo/io-submitter.c @@ -118,6 +118,7 @@ static void send_bio_to_device(struct vio *vio, struct bio *bio) /** * vdo_submit_vio() - Submits a vio's bio to the underlying block device. May block if the device * is busy. This callback should be used by vios which did not attempt to merge. + * @completion: The vio to submit. */ void vdo_submit_vio(struct vdo_completion *completion) { @@ -133,7 +134,7 @@ void vdo_submit_vio(struct vdo_completion *completion) * The list will always contain at least one entry (the bio for the vio on which it is called), but * other bios may have been merged with it as well. * - * Return: bio The head of the bio list to submit. + * Return: The head of the bio list to submit. */ static struct bio *get_bio_list(struct vio *vio) { @@ -158,6 +159,7 @@ static struct bio *get_bio_list(struct vio *vio) /** * submit_data_vio() - Submit a data_vio's bio to the storage below along with * any bios that have been merged with it. + * @completion: The vio to submit. * * Context: This call may block and so should only be called from a bio thread. */ @@ -184,7 +186,7 @@ static void submit_data_vio(struct vdo_completion *completion) * There are two types of merging possible, forward and backward, which are distinguished by a flag * that uses kernel elevator terminology. * - * Return: the vio to merge to, NULL if no merging is possible. + * Return: The vio to merge to, NULL if no merging is possible. */ static struct vio *get_mergeable_locked(struct int_map *map, struct vio *vio, bool back_merge) @@ -262,7 +264,7 @@ static int merge_to_next_head(struct int_map *bio_map, struct vio *vio, * * Currently this is only used for data_vios, but is broken out for future use with metadata vios. * - * Return: whether or not the vio was merged. + * Return: Whether or not the vio was merged. */ static bool try_bio_map_merge(struct vio *vio) { @@ -306,7 +308,7 @@ static bool try_bio_map_merge(struct vio *vio) /** * vdo_submit_data_vio() - Submit I/O for a data_vio. - * @data_vio: the data_vio for which to issue I/O. + * @data_vio: The data_vio for which to issue I/O. * * If possible, this I/O will be merged other pending I/Os. Otherwise, the data_vio will be sent to * the appropriate bio zone directly. @@ -321,13 +323,13 @@ void vdo_submit_data_vio(struct data_vio *data_vio) /** * __submit_metadata_vio() - Submit I/O for a metadata vio. - * @vio: the vio for which to issue I/O - * @physical: the physical block number to read or write - * @callback: the bio endio function which will be called after the I/O completes - * @error_handler: the handler for submission or I/O errors (may be NULL) - * @operation: the type of I/O to perform - * @data: the buffer to read or write (may be NULL) - * @size: the I/O amount in bytes + * @vio: The vio for which to issue I/O. + * @physical: The physical block number to read or write. + * @callback: The bio endio function which will be called after the I/O completes. + * @error_handler: The handler for submission or I/O errors; may be NULL. + * @operation: The type of I/O to perform. + * @data: The buffer to read or write; may be NULL. + * @size: The I/O amount in bytes. * * The vio is enqueued on a vdo bio queue so that bio submission (which may block) does not block * other vdo threads. @@ -441,7 +443,7 @@ int vdo_make_io_submitter(unsigned int thread_count, unsigned int rotation_inter /** * vdo_cleanup_io_submitter() - Tear down the io_submitter fields as needed for a physical layer. - * @io_submitter: The I/O submitter data to tear down (may be NULL). + * @io_submitter: The I/O submitter data to tear down; may be NULL. */ void vdo_cleanup_io_submitter(struct io_submitter *io_submitter) { diff --git a/drivers/md/dm-vdo/logger.c b/drivers/md/dm-vdo/logger.c index 3f7dc2cb6b98..76a987ccf926 100644 --- a/drivers/md/dm-vdo/logger.c +++ b/drivers/md/dm-vdo/logger.c @@ -34,7 +34,7 @@ static const char *get_current_interrupt_type(void) if (in_nmi()) return "NMI"; - if (in_irq()) + if (in_hardirq()) return "HI"; if (in_softirq()) diff --git a/drivers/md/dm-vdo/logical-zone.c b/drivers/md/dm-vdo/logical-zone.c index 026f031ffc9e..0a27e60a9dfd 100644 --- a/drivers/md/dm-vdo/logical-zone.c +++ b/drivers/md/dm-vdo/logical-zone.c @@ -159,21 +159,13 @@ static void check_for_drain_complete(struct logical_zone *zone) vdo_finish_draining(&zone->state); } -/** - * initiate_drain() - Initiate a drain. - * - * Implements vdo_admin_initiator_fn. - */ +/** Implements vdo_admin_initiator_fn. */ static void initiate_drain(struct admin_state *state) { check_for_drain_complete(container_of(state, struct logical_zone, state)); } -/** - * drain_logical_zone() - Drain a logical zone. - * - * Implements vdo_zone_action_fn. - */ +/** Implements vdo_zone_action_fn. */ static void drain_logical_zone(void *context, zone_count_t zone_number, struct vdo_completion *parent) { @@ -192,11 +184,7 @@ void vdo_drain_logical_zones(struct logical_zones *zones, parent); } -/** - * resume_logical_zone() - Resume a logical zone. - * - * Implements vdo_zone_action_fn. - */ +/** Implements vdo_zone_action_fn. */ static void resume_logical_zone(void *context, zone_count_t zone_number, struct vdo_completion *parent) { @@ -356,7 +344,7 @@ struct physical_zone *vdo_get_next_allocation_zone(struct logical_zone *zone) /** * vdo_dump_logical_zone() - Dump information about a logical zone to the log for debugging. - * @zone: The zone to dump + * @zone: The zone to dump. * * Context: the information is dumped in a thread-unsafe fashion. * diff --git a/drivers/md/dm-vdo/packer.c b/drivers/md/dm-vdo/packer.c index f70f5edabc10..666be6d557e1 100644 --- a/drivers/md/dm-vdo/packer.c +++ b/drivers/md/dm-vdo/packer.c @@ -35,10 +35,10 @@ static const struct version_number COMPRESSED_BLOCK_1_0 = { /** * vdo_get_compressed_block_fragment() - Get a reference to a compressed fragment from a compressed * block. - * @mapping_state [in] The mapping state for the look up. - * @compressed_block [in] The compressed block that was read from disk. - * @fragment_offset [out] The offset of the fragment within a compressed block. - * @fragment_size [out] The size of the fragment. + * @mapping_state: The mapping state describing the fragment. + * @block: The compressed block that was read from disk. + * @fragment_offset: The offset of the fragment within the compressed block. + * @fragment_size: The size of the fragment. * * Return: If a valid compressed fragment is found, VDO_SUCCESS; otherwise, VDO_INVALID_FRAGMENT if * the fragment is invalid. @@ -382,6 +382,7 @@ static void initialize_compressed_block(struct compressed_block *block, u16 size * @compression: The agent's compression_state to pack in to. * @data_vio: The data_vio to pack. * @offset: The offset into the compressed block at which to pack the fragment. + * @slot: The slot number in the compressed block. * @block: The compressed block which will be written out when batch is fully packed. * * Return: The new amount of space used. @@ -705,11 +706,7 @@ void vdo_increment_packer_flush_generation(struct packer *packer) vdo_flush_packer(packer); } -/** - * initiate_drain() - Initiate a drain. - * - * Implements vdo_admin_initiator_fn. - */ +/** Implements vdo_admin_initiator_fn. */ static void initiate_drain(struct admin_state *state) { struct packer *packer = container_of(state, struct packer, state); diff --git a/drivers/md/dm-vdo/physical-zone.c b/drivers/md/dm-vdo/physical-zone.c index a43b5c45fab7..686eb7d714e6 100644 --- a/drivers/md/dm-vdo/physical-zone.c +++ b/drivers/md/dm-vdo/physical-zone.c @@ -60,7 +60,7 @@ static inline bool has_lock_type(const struct pbn_lock *lock, enum pbn_lock_type * vdo_is_pbn_read_lock() - Check whether a pbn_lock is a read lock. * @lock: The lock to check. * - * Return: true if the lock is a read lock. + * Return: True if the lock is a read lock. */ bool vdo_is_pbn_read_lock(const struct pbn_lock *lock) { @@ -75,6 +75,7 @@ static inline void set_pbn_lock_type(struct pbn_lock *lock, enum pbn_lock_type t /** * vdo_downgrade_pbn_write_lock() - Downgrade a PBN write lock to a PBN read lock. * @lock: The PBN write lock to downgrade. + * @compressed_write: True if the written block was a compressed block. * * The lock holder count is cleared and the caller is responsible for setting the new count. */ @@ -582,7 +583,7 @@ static bool continue_allocating(struct data_vio *data_vio) * that fails try the next if possible. * @data_vio: The data_vio needing an allocation. * - * Return: true if a block was allocated, if not the data_vio will have been dispatched so the + * Return: True if a block was allocated, if not the data_vio will have been dispatched so the * caller must not touch it. */ bool vdo_allocate_block_in_zone(struct data_vio *data_vio) diff --git a/drivers/md/dm-vdo/recovery-journal.c b/drivers/md/dm-vdo/recovery-journal.c index de58184f538f..9cc0f0ff1664 100644 --- a/drivers/md/dm-vdo/recovery-journal.c +++ b/drivers/md/dm-vdo/recovery-journal.c @@ -109,7 +109,7 @@ static atomic_t *get_decrement_counter(struct recovery_journal *journal, * @journal: The recovery journal. * @lock_number: The lock to check. * - * Return: true if the journal zone is locked. + * Return: True if the journal zone is locked. */ static bool is_journal_zone_locked(struct recovery_journal *journal, block_count_t lock_number) @@ -217,7 +217,7 @@ static struct recovery_journal_block * __must_check pop_free_list(struct recover * Indicates it has any uncommitted entries, which includes both entries not written and entries * written but not yet acknowledged. * - * Return: true if the block has any uncommitted entries. + * Return: True if the block has any uncommitted entries. */ static inline bool __must_check is_block_dirty(const struct recovery_journal_block *block) { @@ -228,7 +228,7 @@ static inline bool __must_check is_block_dirty(const struct recovery_journal_blo * is_block_empty() - Check whether a journal block is empty. * @block: The block to check. * - * Return: true if the block has no entries. + * Return: True if the block has no entries. */ static inline bool __must_check is_block_empty(const struct recovery_journal_block *block) { @@ -239,7 +239,7 @@ static inline bool __must_check is_block_empty(const struct recovery_journal_blo * is_block_full() - Check whether a journal block is full. * @block: The block to check. * - * Return: true if the block is full. + * Return: True if the block is full. */ static inline bool __must_check is_block_full(const struct recovery_journal_block *block) { @@ -260,6 +260,8 @@ static void assert_on_journal_thread(struct recovery_journal *journal, /** * continue_waiter() - Release a data_vio from the journal. + * @waiter: The data_vio waiting on journal activity. + * @context: The result of the journal operation. * * Invoked whenever a data_vio is to be released from the journal, either because its entry was * committed to disk, or because there was an error. Implements waiter_callback_fn. @@ -273,7 +275,7 @@ static void continue_waiter(struct vdo_waiter *waiter, void *context) * has_block_waiters() - Check whether the journal has any waiters on any blocks. * @journal: The journal in question. * - * Return: true if any block has a waiter. + * Return: True if any block has a waiter. */ static inline bool has_block_waiters(struct recovery_journal *journal) { @@ -296,7 +298,7 @@ static void notify_commit_waiters(struct recovery_journal *journal); * suspend_lock_counter() - Prevent the lock counter from notifying. * @counter: The counter. * - * Return: true if the lock counter was not notifying and hence the suspend was efficacious. + * Return: True if the lock counter was not notifying and hence the suspend was efficacious. */ static bool suspend_lock_counter(struct lock_counter *counter) { @@ -416,7 +418,7 @@ sequence_number_t vdo_get_recovery_journal_current_sequence_number(struct recove * * The head is the lowest sequence number of the block map head and the slab journal head. * - * Return: the head of the journal. + * Return: The head of the journal. */ static inline sequence_number_t get_recovery_journal_head(const struct recovery_journal *journal) { @@ -535,7 +537,7 @@ static void initialize_journal_state(struct recovery_journal *journal) * vdo_get_recovery_journal_length() - Get the number of usable recovery journal blocks. * @journal_size: The size of the recovery journal in blocks. * - * Return: the number of recovery journal blocks usable for entries. + * Return: The number of recovery journal blocks usable for entries. */ block_count_t vdo_get_recovery_journal_length(block_count_t journal_size) { @@ -1078,6 +1080,8 @@ static void update_usages(struct recovery_journal *journal, struct data_vio *dat /** * assign_entry() - Assign an entry waiter to the active block. + * @waiter: The data_vio. + * @context: The recovery journal block. * * Implements waiter_callback_fn. */ @@ -1165,6 +1169,8 @@ static void recycle_journal_block(struct recovery_journal_block *block) /** * continue_committed_waiter() - invoked whenever a VIO is to be released from the journal because * its entry was committed to disk. + * @waiter: The data_vio waiting on a journal write. + * @context: A pointer to the recovery journal. * * Implements waiter_callback_fn. */ @@ -1362,6 +1368,8 @@ static void add_queued_recovery_entries(struct recovery_journal_block *block) /** * write_block() - Issue a block for writing. + * @waiter: The recovery journal block to write. + * @context: Not used. * * Implements waiter_callback_fn. */ @@ -1611,11 +1619,7 @@ void vdo_release_journal_entry_lock(struct recovery_journal *journal, smp_mb__after_atomic(); } -/** - * initiate_drain() - Initiate a drain. - * - * Implements vdo_admin_initiator_fn. - */ +/** Implements vdo_admin_initiator_fn. */ static void initiate_drain(struct admin_state *state) { check_for_drain_complete(container_of(state, struct recovery_journal, state)); diff --git a/drivers/md/dm-vdo/slab-depot.c b/drivers/md/dm-vdo/slab-depot.c index f3d80ff7bef5..034ecaa51f48 100644 --- a/drivers/md/dm-vdo/slab-depot.c +++ b/drivers/md/dm-vdo/slab-depot.c @@ -40,7 +40,7 @@ static const bool NORMAL_OPERATION = true; /** * get_lock() - Get the lock object for a slab journal block by sequence number. - * @journal: vdo_slab journal to retrieve from. + * @journal: The vdo_slab journal to retrieve from. * @sequence_number: Sequence number of the block. * * Return: The lock object for the given sequence number. @@ -110,7 +110,7 @@ static void initialize_journal_state(struct slab_journal *journal) * block_is_full() - Check whether a journal block is full. * @journal: The slab journal for the block. * - * Return: true if the tail block is full. + * Return: True if the tail block is full. */ static bool __must_check block_is_full(struct slab_journal *journal) { @@ -127,10 +127,11 @@ static void release_journal_locks(struct vdo_waiter *waiter, void *context); /** * is_slab_journal_blank() - Check whether a slab's journal is blank. + * @slab: The slab to check. * * A slab journal is blank if it has never had any entries recorded in it. * - * Return: true if the slab's journal has never been modified. + * Return: True if the slab's journal has never been modified. */ static bool is_slab_journal_blank(const struct vdo_slab *slab) { @@ -227,6 +228,7 @@ static u8 __must_check compute_fullness_hint(struct slab_depot *depot, /** * check_summary_drain_complete() - Check whether an allocators summary has finished draining. + * @allocator: The allocator to check. */ static void check_summary_drain_complete(struct block_allocator *allocator) { @@ -349,7 +351,7 @@ static void launch_write(struct slab_summary_block *block) /** * update_slab_summary_entry() - Update the entry for a slab. - * @slab: The slab whose entry is to be updated + * @slab: The slab whose entry is to be updated. * @waiter: The waiter that is updating the summary. * @tail_block_offset: The offset of the slab journal's tail block. * @load_ref_counts: Whether the reference counts must be loaded from disk on the vdo load. @@ -654,6 +656,7 @@ static void update_tail_block_location(struct slab_journal *journal) /** * reopen_slab_journal() - Reopen a slab's journal by emptying it and then adding pending entries. + * @slab: The slab to reopen. */ static void reopen_slab_journal(struct vdo_slab *slab) { @@ -839,8 +842,6 @@ static void commit_tail(struct slab_journal *journal) * @sbn: The slab block number of the entry to encode. * @operation: The type of the entry. * @increment: True if this is an increment. - * - * Exposed for unit tests. */ static void encode_slab_journal_entry(struct slab_journal_block_header *tail_header, slab_journal_payload *payload, @@ -951,7 +952,7 @@ static inline block_count_t journal_length(const struct slab_journal *journal) * @parent: The completion to notify when there is space to add the entry if the entry could not be * added immediately. * - * Return: true if the entry was added immediately. + * Return: True if the entry was added immediately. */ bool vdo_attempt_replay_into_slab(struct vdo_slab *slab, physical_block_number_t pbn, enum journal_operation operation, bool increment, @@ -1003,7 +1004,7 @@ bool vdo_attempt_replay_into_slab(struct vdo_slab *slab, physical_block_number_t * requires_reaping() - Check whether the journal must be reaped before adding new entries. * @journal: The journal to check. * - * Return: true if the journal must be reaped. + * Return: True if the journal must be reaped. */ static bool requires_reaping(const struct slab_journal *journal) { @@ -1275,6 +1276,8 @@ static void dirty_block(struct reference_block *block) /** * get_reference_block() - Get the reference block that covers the given block index. + * @slab: The slab containing the references. + * @index: The index of the physical block. */ static struct reference_block * __must_check get_reference_block(struct vdo_slab *slab, slab_block_number index) @@ -1379,7 +1382,8 @@ static void prioritize_slab(struct vdo_slab *slab) /** * adjust_free_block_count() - Adjust the free block count and (if needed) reprioritize the slab. - * @incremented: true if the free block count went up. + * @slab: The slab. + * @incremented: True if the free block count went up. */ static void adjust_free_block_count(struct vdo_slab *slab, bool incremented) { @@ -1885,6 +1889,7 @@ static void add_entries(struct slab_journal *journal) /** * reset_search_cursor() - Reset the free block search back to the first reference counter in the * first reference block of a slab. + * @slab: The slab. */ static void reset_search_cursor(struct vdo_slab *slab) { @@ -1892,17 +1897,17 @@ static void reset_search_cursor(struct vdo_slab *slab) cursor->block = cursor->first_block; cursor->index = 0; - /* Unit tests have slabs with only one reference block (and it's a runt). */ cursor->end_index = min_t(u32, COUNTS_PER_BLOCK, slab->block_count); } /** * advance_search_cursor() - Advance the search cursor to the start of the next reference block in - * a slab, + * a slab. + * @slab: The slab. * * Wraps around to the first reference block if the current block is the last reference block. * - * Return: true unless the cursor was at the last reference block. + * Return: True unless the cursor was at the last reference block. */ static bool advance_search_cursor(struct vdo_slab *slab) { @@ -1933,6 +1938,9 @@ static bool advance_search_cursor(struct vdo_slab *slab) /** * vdo_adjust_reference_count_for_rebuild() - Adjust the reference count of a block during rebuild. + * @depot: The slab depot. + * @pbn: The physical block number to adjust. + * @operation: The type opf operation. * * Return: VDO_SUCCESS or an error. */ @@ -2038,9 +2046,7 @@ static inline slab_block_number find_zero_byte_in_word(const u8 *word_ptr, * @slab: The slab counters to scan. * @index_ptr: A pointer to hold the array index of the free block. * - * Exposed for unit testing. - * - * Return: true if a free block was found in the specified range. + * Return: True if a free block was found in the specified range. */ static bool find_free_block(const struct vdo_slab *slab, slab_block_number *index_ptr) { @@ -2097,7 +2103,7 @@ static bool find_free_block(const struct vdo_slab *slab, slab_block_number *inde * @slab: The slab to search. * @free_index_ptr: A pointer to receive the array index of the zero reference count. * - * Return: true if an unreferenced counter was found. + * Return: True if an unreferenced counter was found. */ static bool search_current_reference_block(const struct vdo_slab *slab, slab_block_number *free_index_ptr) @@ -2116,7 +2122,7 @@ static bool search_current_reference_block(const struct vdo_slab *slab, * counter index saved in the search cursor and searching up to the end of the last reference * block. The search does not wrap. * - * Return: true if an unreferenced counter was found. + * Return: True if an unreferenced counter was found. */ static bool search_reference_blocks(struct vdo_slab *slab, slab_block_number *free_index_ptr) @@ -2136,6 +2142,8 @@ static bool search_reference_blocks(struct vdo_slab *slab, /** * make_provisional_reference() - Do the bookkeeping for making a provisional reference. + * @slab: The slab. + * @block_number: The index for the physical block to reference. */ static void make_provisional_reference(struct vdo_slab *slab, slab_block_number block_number) @@ -2155,6 +2163,7 @@ static void make_provisional_reference(struct vdo_slab *slab, /** * dirty_all_reference_blocks() - Mark all reference count blocks in a slab as dirty. + * @slab: The slab. */ static void dirty_all_reference_blocks(struct vdo_slab *slab) { @@ -2173,10 +2182,10 @@ static inline bool journal_points_equal(struct journal_point first, /** * match_bytes() - Check an 8-byte word for bytes matching the value specified - * @input: A word to examine the bytes of - * @match: The byte value sought + * @input: A word to examine the bytes of. + * @match: The byte value sought. * - * Return: 1 in each byte when the corresponding input byte matched, 0 otherwise + * Return: 1 in each byte when the corresponding input byte matched, 0 otherwise. */ static inline u64 match_bytes(u64 input, u8 match) { @@ -2191,12 +2200,12 @@ static inline u64 match_bytes(u64 input, u8 match) /** * count_valid_references() - Process a newly loaded refcount array - * @counters: the array of counters from a metadata block + * @counters: The array of counters from a metadata block. * - * Scan a 8-byte-aligned array of counters, fixing up any "provisional" values that weren't - * cleaned up at shutdown, changing them internally to "empty". + * Scan an 8-byte-aligned array of counters, fixing up any provisional values that + * weren't cleaned up at shutdown, changing them internally to zero. * - * Return: the number of blocks that are referenced (counters not "empty") + * Return: The number of blocks with a non-zero reference count. */ static unsigned int count_valid_references(vdo_refcount_t *counters) { @@ -2351,6 +2360,7 @@ static void load_reference_block_group(struct vdo_waiter *waiter, void *context) /** * load_reference_blocks() - Load a slab's reference blocks from the underlying storage into a * pre-allocated reference counter. + * @slab: The slab. */ static void load_reference_blocks(struct vdo_slab *slab) { @@ -2375,6 +2385,7 @@ static void load_reference_blocks(struct vdo_slab *slab) /** * drain_slab() - Drain all reference count I/O. + * @slab: The slab. * * Depending upon the type of drain being performed (as recorded in the ref_count's vdo_slab), the * reference blocks may be loaded from disk or dirty reference blocks may be written out. @@ -2564,6 +2575,7 @@ static void read_slab_journal_tail(struct vdo_waiter *waiter, void *context) /** * load_slab_journal() - Load a slab's journal by reading the journal's tail. + * @slab: The slab. */ static void load_slab_journal(struct vdo_slab *slab) { @@ -2663,11 +2675,7 @@ static void queue_slab(struct vdo_slab *slab) prioritize_slab(slab); } -/** - * initiate_slab_action() - Initiate a slab action. - * - * Implements vdo_admin_initiator_fn. - */ +/** Implements vdo_admin_initiator_fn. */ static void initiate_slab_action(struct admin_state *state) { struct vdo_slab *slab = container_of(state, struct vdo_slab, state); @@ -2720,7 +2728,7 @@ static struct vdo_slab *get_next_slab(struct slab_scrubber *scrubber) * has_slabs_to_scrub() - Check whether a scrubber has slabs to scrub. * @scrubber: The scrubber to check. * - * Return: true if the scrubber has slabs to scrub. + * Return: True if the scrubber has slabs to scrub. */ static inline bool __must_check has_slabs_to_scrub(struct slab_scrubber *scrubber) { @@ -2741,6 +2749,7 @@ static void uninitialize_scrubber_vio(struct slab_scrubber *scrubber) * finish_scrubbing() - Stop scrubbing, either because there are no more slabs to scrub or because * there's been an error. * @scrubber: The scrubber. + * @result: The result of the scrubbing operation. */ static void finish_scrubbing(struct slab_scrubber *scrubber, int result) { @@ -3132,11 +3141,13 @@ static struct vdo_slab *next_slab(struct slab_iterator *iterator) /** * abort_waiter() - Abort vios waiting to make journal entries when read-only. + * @waiter: A waiting data_vio. + * @context: Not used. * * This callback is invoked on all vios waiting to make slab journal entries after the VDO has gone * into read-only mode. Implements waiter_callback_fn. */ -static void abort_waiter(struct vdo_waiter *waiter, void *context __always_unused) +static void abort_waiter(struct vdo_waiter *waiter, void __always_unused *context) { struct reference_updater *updater = container_of(waiter, struct reference_updater, waiter); @@ -3536,7 +3547,7 @@ static void initiate_load(struct admin_state *state) /** * vdo_notify_slab_journals_are_recovered() - Inform a block allocator that its slab journals have * been recovered from the recovery journal. - * @completion The allocator completion + * @completion: The allocator completion. */ void vdo_notify_slab_journals_are_recovered(struct vdo_completion *completion) { @@ -3775,7 +3786,7 @@ static int initialize_slab_journal(struct vdo_slab *slab) * in the slab. * @allocator: The block allocator to which the slab belongs. * @slab_number: The slab number of the slab. - * @is_new: true if this slab is being allocated as part of a resize. + * @is_new: True if this slab is being allocated as part of a resize. * @slab_ptr: A pointer to receive the new slab. * * Return: VDO_SUCCESS or an error code. @@ -3894,11 +3905,7 @@ void vdo_abandon_new_slabs(struct slab_depot *depot) vdo_free(vdo_forget(depot->new_slabs)); } -/** - * get_allocator_thread_id() - Get the ID of the thread on which a given allocator operates. - * - * Implements vdo_zone_thread_getter_fn. - */ +/** Implements vdo_zone_thread_getter_fn. */ static thread_id_t get_allocator_thread_id(void *context, zone_count_t zone_number) { return ((struct slab_depot *) context)->allocators[zone_number].thread_id; @@ -3911,7 +3918,7 @@ static thread_id_t get_allocator_thread_id(void *context, zone_count_t zone_numb * @recovery_lock: The sequence number of the recovery journal block whose locks should be * released. * - * Return: true if the journal does hold a lock on the specified block (which it will release). + * Return: True if the journal released a lock on the specified block. */ static bool __must_check release_recovery_journal_lock(struct slab_journal *journal, sequence_number_t recovery_lock) @@ -3955,6 +3962,8 @@ static void release_tail_block_locks(void *context, zone_count_t zone_number, /** * prepare_for_tail_block_commit() - Prepare to commit oldest tail blocks. + * @context: The slab depot. + * @parent: The parent operation. * * Implements vdo_action_preamble_fn. */ @@ -3968,6 +3977,7 @@ static void prepare_for_tail_block_commit(void *context, struct vdo_completion * /** * schedule_tail_block_commit() - Schedule a tail block commit if necessary. + * @context: The slab depot. * * This method should not be called directly. Rather, call vdo_schedule_default_action() on the * depot's action manager. @@ -4361,6 +4371,7 @@ struct slab_depot_state_2_0 vdo_record_slab_depot(const struct slab_depot *depot /** * vdo_allocate_reference_counters() - Allocate the reference counters for all slabs in the depot. + * @depot: The slab depot. * * Context: This method may be called only before entering normal operation from the load thread. * @@ -4615,7 +4626,9 @@ static void load_summary_endio(struct bio *bio) } /** - * load_slab_summary() - The preamble of a load operation. + * load_slab_summary() - Load the slab summary before the slab data. + * @context: The slab depot. + * @parent: The load operation. * * Implements vdo_action_preamble_fn. */ @@ -4731,7 +4744,7 @@ void vdo_update_slab_depot_size(struct slab_depot *depot) * vdo_prepare_to_grow_slab_depot() - Allocate new memory needed for a resize of a slab depot to * the given size. * @depot: The depot to prepare to resize. - * @partition: The new depot partition + * @partition: The new depot partition. * * Return: VDO_SUCCESS or an error. */ @@ -4781,6 +4794,7 @@ int vdo_prepare_to_grow_slab_depot(struct slab_depot *depot, /** * finish_registration() - Finish registering new slabs now that all of the allocators have * received their new slabs. + * @context: The slab depot. * * Implements vdo_action_conclusion_fn. */ diff --git a/drivers/md/dm-vdo/vdo.c b/drivers/md/dm-vdo/vdo.c index 80b608674022..09fd0628d18c 100644 --- a/drivers/md/dm-vdo/vdo.c +++ b/drivers/md/dm-vdo/vdo.c @@ -181,6 +181,8 @@ static void assign_thread_ids(struct thread_config *config, /** * initialize_thread_config() - Initialize the thread mapping + * @counts: The number and types of threads to create. + * @config: The thread_config to initialize. * * If the logical, physical, and hash zone counts are all 0, a single thread will be shared by all * three plus the packer and recovery journal. Otherwise, there must be at least one of each type, @@ -884,6 +886,7 @@ const struct admin_state_code *vdo_get_admin_state(const struct vdo *vdo) /** * record_vdo() - Record the state of the VDO for encoding in the super block. + * @vdo: The vdo. */ static void record_vdo(struct vdo *vdo) { @@ -1277,7 +1280,7 @@ void vdo_enter_read_only_mode(struct vdo *vdo, int error_code) * vdo_is_read_only() - Check whether the VDO is read-only. * @vdo: The vdo. * - * Return: true if the vdo is read-only. + * Return: True if the vdo is read-only. * * This method may be called from any thread, as opposed to examining the VDO's state field which * is only safe to check from the admin thread. @@ -1291,7 +1294,7 @@ bool vdo_is_read_only(struct vdo *vdo) * vdo_in_read_only_mode() - Check whether a vdo is in read-only mode. * @vdo: The vdo to query. * - * Return: true if the vdo is in read-only mode. + * Return: True if the vdo is in read-only mode. */ bool vdo_in_read_only_mode(const struct vdo *vdo) { @@ -1302,7 +1305,7 @@ bool vdo_in_read_only_mode(const struct vdo *vdo) * vdo_in_recovery_mode() - Check whether the vdo is in recovery mode. * @vdo: The vdo to query. * - * Return: true if the vdo is in recovery mode. + * Return: True if the vdo is in recovery mode. */ bool vdo_in_recovery_mode(const struct vdo *vdo) { diff --git a/drivers/md/dm-vdo/vdo.h b/drivers/md/dm-vdo/vdo.h index 483ae873e002..1aaba73997b7 100644 --- a/drivers/md/dm-vdo/vdo.h +++ b/drivers/md/dm-vdo/vdo.h @@ -279,8 +279,10 @@ static inline bool vdo_uses_bio_ack_queue(struct vdo *vdo) /** * typedef vdo_filter_fn - Method type for vdo matching methods. + * @vdo: The vdo to match. + * @context: A parameter for the filter to use. * - * A filter function returns false if the vdo doesn't match. + * Return: True if the vdo matches the filter criteria, false if it doesn't. */ typedef bool (*vdo_filter_fn)(struct vdo *vdo, const void *context); diff --git a/drivers/md/dm-vdo/vio.c b/drivers/md/dm-vdo/vio.c index 8fc22fb14196..5ffc867d9c5e 100644 --- a/drivers/md/dm-vdo/vio.c +++ b/drivers/md/dm-vdo/vio.c @@ -398,8 +398,9 @@ void free_vio_pool(struct vio_pool *pool) /** * is_vio_pool_busy() - Check whether an vio pool has outstanding entries. + * @pool: The vio pool. * - * Return: true if the pool is busy. + * Return: True if the pool is busy. */ bool is_vio_pool_busy(struct vio_pool *pool) { diff --git a/drivers/md/dm-vdo/vio.h b/drivers/md/dm-vdo/vio.h index 4bfcb21901f1..7a8a6819aec4 100644 --- a/drivers/md/dm-vdo/vio.h +++ b/drivers/md/dm-vdo/vio.h @@ -156,8 +156,7 @@ static inline enum vdo_completion_priority get_metadata_priority(struct vio *vio /** * continue_vio() - Enqueue a vio to run its next callback. * @vio: The vio to continue. - * - * Return: The result of the current operation. + * @result: The result of the current operation. */ static inline void continue_vio(struct vio *vio, int result) { @@ -172,6 +171,9 @@ void vdo_count_completed_bios(struct bio *bio); /** * continue_vio_after_io() - Continue a vio now that its I/O has returned. + * @vio: The vio to continue. + * @callback: The next operation for this vio. + * @thread: Which thread to run the next operation on. */ static inline void continue_vio_after_io(struct vio *vio, vdo_action_fn callback, thread_id_t thread) diff --git a/drivers/md/dm-verity-fec.c b/drivers/md/dm-verity-fec.c index d382a390d39a..c79de517afee 100644 --- a/drivers/md/dm-verity-fec.c +++ b/drivers/md/dm-verity-fec.c @@ -177,9 +177,11 @@ error: if (r < 0 && neras) DMERR_LIMIT("%s: FEC %llu: failed to correct: %d", v->data_dev->name, (unsigned long long)rsb, r); - else if (r > 0) + else if (r > 0) { DMWARN_LIMIT("%s: FEC %llu: corrected %d errors", v->data_dev->name, (unsigned long long)rsb, r); + atomic64_inc(&v->fec->corrected); + } return r; } @@ -188,14 +190,13 @@ error: * Locate data block erasures using verity hashes. */ static int fec_is_erasure(struct dm_verity *v, struct dm_verity_io *io, - u8 *want_digest, u8 *data) + const u8 *want_digest, const u8 *data) { if (unlikely(verity_hash(v, io, data, 1 << v->data_dev_block_bits, - verity_io_real_digest(v, io)))) + io->tmp_digest))) return 0; - return memcmp(verity_io_real_digest(v, io), want_digest, - v->digest_size) != 0; + return memcmp(io->tmp_digest, want_digest, v->digest_size) != 0; } /* @@ -320,11 +321,7 @@ static int fec_alloc_bufs(struct dm_verity *v, struct dm_verity_fec_io *fio) if (fio->bufs[n]) continue; - fio->bufs[n] = mempool_alloc(&v->fec->prealloc_pool, GFP_NOWAIT); - if (unlikely(!fio->bufs[n])) { - DMERR("failed to allocate FEC buffer"); - return -ENOMEM; - } + fio->bufs[n] = mempool_alloc(&v->fec->prealloc_pool, GFP_NOIO); } /* try to allocate the maximum number of buffers */ @@ -332,7 +329,7 @@ static int fec_alloc_bufs(struct dm_verity *v, struct dm_verity_fec_io *fio) if (fio->bufs[n]) continue; - fio->bufs[n] = mempool_alloc(&v->fec->extra_pool, GFP_NOWAIT); + fio->bufs[n] = kmem_cache_alloc(v->fec->cache, GFP_NOWAIT); /* we can manage with even one buffer if necessary */ if (unlikely(!fio->bufs[n])) break; @@ -366,7 +363,7 @@ static void fec_init_bufs(struct dm_verity *v, struct dm_verity_fec_io *fio) */ static int fec_decode_rsb(struct dm_verity *v, struct dm_verity_io *io, struct dm_verity_fec_io *fio, u64 rsb, u64 offset, - bool use_erasures) + const u8 *want_digest, bool use_erasures) { int r, neras = 0; unsigned int pos; @@ -392,12 +389,11 @@ static int fec_decode_rsb(struct dm_verity *v, struct dm_verity_io *io, /* Always re-validate the corrected block against the expected hash */ r = verity_hash(v, io, fio->output, 1 << v->data_dev_block_bits, - verity_io_real_digest(v, io)); + io->tmp_digest); if (unlikely(r < 0)) return r; - if (memcmp(verity_io_real_digest(v, io), verity_io_want_digest(v, io), - v->digest_size)) { + if (memcmp(io->tmp_digest, want_digest, v->digest_size)) { DMERR_LIMIT("%s: FEC %llu: failed to correct (%d erasures)", v->data_dev->name, (unsigned long long)rsb, neras); return -EILSEQ; @@ -408,7 +404,8 @@ static int fec_decode_rsb(struct dm_verity *v, struct dm_verity_io *io, /* Correct errors in a block. Copies corrected block to dest. */ int verity_fec_decode(struct dm_verity *v, struct dm_verity_io *io, - enum verity_block_type type, sector_t block, u8 *dest) + enum verity_block_type type, const u8 *want_digest, + sector_t block, u8 *dest) { int r; struct dm_verity_fec_io *fio = fec_io(io); @@ -417,10 +414,8 @@ int verity_fec_decode(struct dm_verity *v, struct dm_verity_io *io, if (!verity_fec_is_enabled(v)) return -EOPNOTSUPP; - if (fio->level >= DM_VERITY_FEC_MAX_RECURSION) { - DMWARN_LIMIT("%s: FEC: recursion too deep", v->data_dev->name); + if (fio->level) return -EIO; - } fio->level++; @@ -451,9 +446,9 @@ int verity_fec_decode(struct dm_verity *v, struct dm_verity_io *io, * them first. Do a second attempt with erasures if the corruption is * bad enough. */ - r = fec_decode_rsb(v, io, fio, rsb, offset, false); + r = fec_decode_rsb(v, io, fio, rsb, offset, want_digest, false); if (r < 0) { - r = fec_decode_rsb(v, io, fio, rsb, offset, true); + r = fec_decode_rsb(v, io, fio, rsb, offset, want_digest, true); if (r < 0) goto done; } @@ -483,7 +478,8 @@ void verity_fec_finish_io(struct dm_verity_io *io) mempool_free(fio->bufs[n], &f->prealloc_pool); fec_for_each_extra_buffer(fio, n) - mempool_free(fio->bufs[n], &f->extra_pool); + if (fio->bufs[n]) + kmem_cache_free(f->cache, fio->bufs[n]); mempool_free(fio->output, &f->output_pool); } @@ -535,7 +531,6 @@ void verity_fec_dtr(struct dm_verity *v) mempool_exit(&f->rs_pool); mempool_exit(&f->prealloc_pool); - mempool_exit(&f->extra_pool); mempool_exit(&f->output_pool); kmem_cache_destroy(f->cache); @@ -788,12 +783,6 @@ int verity_fec_ctr(struct dm_verity *v) return ret; } - ret = mempool_init_slab_pool(&f->extra_pool, 0, f->cache); - if (ret) { - ti->error = "Cannot allocate FEC buffer extra pool"; - return ret; - } - /* Preallocate an output buffer for each thread */ ret = mempool_init_kmalloc_pool(&f->output_pool, num_online_cpus(), 1 << v->data_dev_block_bits); diff --git a/drivers/md/dm-verity-fec.h b/drivers/md/dm-verity-fec.h index 09123a612953..5fd267873812 100644 --- a/drivers/md/dm-verity-fec.h +++ b/drivers/md/dm-verity-fec.h @@ -23,9 +23,6 @@ #define DM_VERITY_FEC_BUF_MAX \ (1 << (PAGE_SHIFT - DM_VERITY_FEC_BUF_RS_BITS)) -/* maximum recursion level for verity_fec_decode */ -#define DM_VERITY_FEC_MAX_RECURSION 4 - #define DM_VERITY_OPT_FEC_DEV "use_fec_from_device" #define DM_VERITY_OPT_FEC_BLOCKS "fec_blocks" #define DM_VERITY_OPT_FEC_START "fec_start" @@ -45,9 +42,9 @@ struct dm_verity_fec { unsigned char rsn; /* N of RS(M, N) */ mempool_t rs_pool; /* mempool for fio->rs */ mempool_t prealloc_pool; /* mempool for preallocated buffers */ - mempool_t extra_pool; /* mempool for extra buffers */ mempool_t output_pool; /* mempool for output */ struct kmem_cache *cache; /* cache for buffers */ + atomic64_t corrected; /* corrected errors */ }; /* per-bio data */ @@ -68,8 +65,8 @@ struct dm_verity_fec_io { extern bool verity_fec_is_enabled(struct dm_verity *v); extern int verity_fec_decode(struct dm_verity *v, struct dm_verity_io *io, - enum verity_block_type type, sector_t block, - u8 *dest); + enum verity_block_type type, const u8 *want_digest, + sector_t block, u8 *dest); extern unsigned int verity_fec_status_table(struct dm_verity *v, unsigned int sz, char *result, unsigned int maxlen); @@ -99,6 +96,7 @@ static inline bool verity_fec_is_enabled(struct dm_verity *v) static inline int verity_fec_decode(struct dm_verity *v, struct dm_verity_io *io, enum verity_block_type type, + const u8 *want_digest, sector_t block, u8 *dest) { return -EOPNOTSUPP; diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c index 66a00a8ccb39..5c17472d7896 100644 --- a/drivers/md/dm-verity-target.c +++ b/drivers/md/dm-verity-target.c @@ -117,11 +117,25 @@ static sector_t verity_position_at_level(struct dm_verity *v, sector_t block, int verity_hash(struct dm_verity *v, struct dm_verity_io *io, const u8 *data, size_t len, u8 *digest) { - struct shash_desc *desc = &io->hash_desc; + struct shash_desc *desc; int r; + if (likely(v->use_sha256_lib)) { + struct sha256_ctx *ctx = &io->hash_ctx.sha256; + + /* + * Fast path using SHA-256 library. This is enabled only for + * verity version 1, where the salt is at the beginning. + */ + *ctx = *v->initial_hashstate.sha256; + sha256_update(ctx, data, len); + sha256_final(ctx, digest); + return 0; + } + + desc = &io->hash_ctx.shash; desc->tfm = v->shash_tfm; - if (unlikely(v->initial_hashstate == NULL)) { + if (unlikely(v->initial_hashstate.shash == NULL)) { /* Version 0: salt at end */ r = crypto_shash_init(desc) ?: crypto_shash_update(desc, data, len) ?: @@ -129,7 +143,7 @@ int verity_hash(struct dm_verity *v, struct dm_verity_io *io, crypto_shash_final(desc, digest); } else { /* Version 1: salt at beginning */ - r = crypto_shash_import(desc, v->initial_hashstate) ?: + r = crypto_shash_import(desc, v->initial_hashstate.shash) ?: crypto_shash_finup(desc, data, len, digest); } if (unlikely(r)) @@ -215,12 +229,12 @@ out: * Verify hash of a metadata block pertaining to the specified data block * ("block" argument) at a specified level ("level" argument). * - * On successful return, verity_io_want_digest(v, io) contains the hash value - * for a lower tree level or for the data block (if we're at the lowest level). + * On successful return, want_digest contains the hash value for a lower tree + * level or for the data block (if we're at the lowest level). * * If "skip_unverified" is true, unverified buffer is skipped and 1 is returned. * If "skip_unverified" is false, unverified buffer is hashed and verified - * against current value of verity_io_want_digest(v, io). + * against current value of want_digest. */ static int verity_verify_level(struct dm_verity *v, struct dm_verity_io *io, sector_t block, int level, bool skip_unverified, @@ -259,7 +273,7 @@ static int verity_verify_level(struct dm_verity *v, struct dm_verity_io *io, if (IS_ERR(data)) return r; if (verity_fec_decode(v, io, DM_VERITY_BLOCK_TYPE_METADATA, - hash_block, data) == 0) { + want_digest, hash_block, data) == 0) { aux = dm_bufio_get_aux_data(buf); aux->hash_verified = 1; goto release_ok; @@ -279,11 +293,11 @@ static int verity_verify_level(struct dm_verity *v, struct dm_verity_io *io, } r = verity_hash(v, io, data, 1 << v->hash_dev_block_bits, - verity_io_real_digest(v, io)); + io->tmp_digest); if (unlikely(r < 0)) goto release_ret_r; - if (likely(memcmp(verity_io_real_digest(v, io), want_digest, + if (likely(memcmp(io->tmp_digest, want_digest, v->digest_size) == 0)) aux->hash_verified = 1; else if (static_branch_unlikely(&use_bh_wq_enabled) && io->in_bh) { @@ -294,7 +308,7 @@ static int verity_verify_level(struct dm_verity *v, struct dm_verity_io *io, r = -EAGAIN; goto release_ret_r; } else if (verity_fec_decode(v, io, DM_VERITY_BLOCK_TYPE_METADATA, - hash_block, data) == 0) + want_digest, hash_block, data) == 0) aux->hash_verified = 1; else if (verity_handle_err(v, DM_VERITY_BLOCK_TYPE_METADATA, @@ -358,7 +372,8 @@ out: } static noinline int verity_recheck(struct dm_verity *v, struct dm_verity_io *io, - sector_t cur_block, u8 *dest) + const u8 *want_digest, sector_t cur_block, + u8 *dest) { struct page *page; void *buffer; @@ -382,12 +397,11 @@ static noinline int verity_recheck(struct dm_verity *v, struct dm_verity_io *io, goto free_ret; r = verity_hash(v, io, buffer, 1 << v->data_dev_block_bits, - verity_io_real_digest(v, io)); + io->tmp_digest); if (unlikely(r)) goto free_ret; - if (memcmp(verity_io_real_digest(v, io), - verity_io_want_digest(v, io), v->digest_size)) { + if (memcmp(io->tmp_digest, want_digest, v->digest_size)) { r = -EIO; goto free_ret; } @@ -402,9 +416,13 @@ free_ret: static int verity_handle_data_hash_mismatch(struct dm_verity *v, struct dm_verity_io *io, - struct bio *bio, sector_t blkno, - u8 *data) + struct bio *bio, + struct pending_block *block) { + const u8 *want_digest = block->want_digest; + sector_t blkno = block->blkno; + u8 *data = block->data; + if (static_branch_unlikely(&use_bh_wq_enabled) && io->in_bh) { /* * Error handling code (FEC included) cannot be run in the @@ -412,14 +430,14 @@ static int verity_handle_data_hash_mismatch(struct dm_verity *v, */ return -EAGAIN; } - if (verity_recheck(v, io, blkno, data) == 0) { + if (verity_recheck(v, io, want_digest, blkno, data) == 0) { if (v->validated_blocks) set_bit(blkno, v->validated_blocks); return 0; } #if defined(CONFIG_DM_VERITY_FEC) - if (verity_fec_decode(v, io, DM_VERITY_BLOCK_TYPE_DATA, blkno, - data) == 0) + if (verity_fec_decode(v, io, DM_VERITY_BLOCK_TYPE_DATA, want_digest, + blkno, data) == 0) return 0; #endif if (bio->bi_status) @@ -433,6 +451,58 @@ static int verity_handle_data_hash_mismatch(struct dm_verity *v, return 0; } +static void verity_clear_pending_blocks(struct dm_verity_io *io) +{ + int i; + + for (i = io->num_pending - 1; i >= 0; i--) { + kunmap_local(io->pending_blocks[i].data); + io->pending_blocks[i].data = NULL; + } + io->num_pending = 0; +} + +static int verity_verify_pending_blocks(struct dm_verity *v, + struct dm_verity_io *io, + struct bio *bio) +{ + const unsigned int block_size = 1 << v->data_dev_block_bits; + int i, r; + + if (io->num_pending == 2) { + /* num_pending == 2 implies that the algorithm is SHA-256 */ + sha256_finup_2x(v->initial_hashstate.sha256, + io->pending_blocks[0].data, + io->pending_blocks[1].data, block_size, + io->pending_blocks[0].real_digest, + io->pending_blocks[1].real_digest); + } else { + for (i = 0; i < io->num_pending; i++) { + r = verity_hash(v, io, io->pending_blocks[i].data, + block_size, + io->pending_blocks[i].real_digest); + if (unlikely(r)) + return r; + } + } + + for (i = 0; i < io->num_pending; i++) { + struct pending_block *block = &io->pending_blocks[i]; + + if (likely(memcmp(block->real_digest, block->want_digest, + v->digest_size) == 0)) { + if (v->validated_blocks) + set_bit(block->blkno, v->validated_blocks); + } else { + r = verity_handle_data_hash_mismatch(v, io, bio, block); + if (unlikely(r)) + return r; + } + } + verity_clear_pending_blocks(io); + return 0; +} + /* * Verify one "dm_verity_io" structure. */ @@ -440,10 +510,14 @@ static int verity_verify_io(struct dm_verity_io *io) { struct dm_verity *v = io->v; const unsigned int block_size = 1 << v->data_dev_block_bits; + const int max_pending = v->use_sha256_finup_2x ? 2 : 1; struct bvec_iter iter_copy; struct bvec_iter *iter; struct bio *bio = dm_bio_from_per_bio_data(io, v->ti->per_io_data_size); unsigned int b; + int r; + + io->num_pending = 0; if (static_branch_unlikely(&use_bh_wq_enabled) && io->in_bh) { /* @@ -457,21 +531,22 @@ static int verity_verify_io(struct dm_verity_io *io) for (b = 0; b < io->n_blocks; b++, bio_advance_iter(bio, iter, block_size)) { - int r; - sector_t cur_block = io->block + b; + sector_t blkno = io->block + b; + struct pending_block *block; bool is_zero; struct bio_vec bv; void *data; if (v->validated_blocks && bio->bi_status == BLK_STS_OK && - likely(test_bit(cur_block, v->validated_blocks))) + likely(test_bit(blkno, v->validated_blocks))) continue; - r = verity_hash_for_block(v, io, cur_block, - verity_io_want_digest(v, io), + block = &io->pending_blocks[io->num_pending]; + + r = verity_hash_for_block(v, io, blkno, block->want_digest, &is_zero); if (unlikely(r < 0)) - return r; + goto error; bv = bio_iter_iovec(bio, *iter); if (unlikely(bv.bv_len < block_size)) { @@ -482,7 +557,8 @@ static int verity_verify_io(struct dm_verity_io *io) * data block size to be greater than PAGE_SIZE. */ DMERR_LIMIT("unaligned io (data block spans pages)"); - return -EIO; + r = -EIO; + goto error; } data = bvec_kmap_local(&bv); @@ -496,29 +572,26 @@ static int verity_verify_io(struct dm_verity_io *io) kunmap_local(data); continue; } - - r = verity_hash(v, io, data, block_size, - verity_io_real_digest(v, io)); - if (unlikely(r < 0)) { - kunmap_local(data); - return r; + block->data = data; + block->blkno = blkno; + if (++io->num_pending == max_pending) { + r = verity_verify_pending_blocks(v, io, bio); + if (unlikely(r)) + goto error; } + } - if (likely(memcmp(verity_io_real_digest(v, io), - verity_io_want_digest(v, io), v->digest_size) == 0)) { - if (v->validated_blocks) - set_bit(cur_block, v->validated_blocks); - kunmap_local(data); - continue; - } - r = verity_handle_data_hash_mismatch(v, io, bio, cur_block, - data); - kunmap_local(data); + if (io->num_pending) { + r = verity_verify_pending_blocks(v, io, bio); if (unlikely(r)) - return r; + goto error; } return 0; + +error: + verity_clear_pending_blocks(io); + return r; } /* @@ -775,6 +848,10 @@ static void verity_status(struct dm_target *ti, status_type_t type, switch (type) { case STATUSTYPE_INFO: DMEMIT("%c", v->hash_failed ? 'C' : 'V'); + if (verity_fec_is_enabled(v)) + DMEMIT(" %lld", atomic64_read(&v->fec->corrected)); + else + DMEMIT(" -"); break; case STATUSTYPE_TABLE: DMEMIT("%u %s %s %u %u %llu %llu %s ", @@ -1004,7 +1081,7 @@ static void verity_dtr(struct dm_target *ti) kvfree(v->validated_blocks); kfree(v->salt); - kfree(v->initial_hashstate); + kfree(v->initial_hashstate.shash); kfree(v->root_digest); kfree(v->zero_digest); verity_free_sig(v); @@ -1069,8 +1146,7 @@ static int verity_alloc_zero_digest(struct dm_verity *v) if (!v->zero_digest) return r; - io = kmalloc(sizeof(*io) + crypto_shash_descsize(v->shash_tfm), - GFP_KERNEL); + io = kmalloc(v->ti->per_io_data_size, GFP_KERNEL); if (!io) return r; /* verity_dtr will free zero_digest */ @@ -1252,11 +1328,26 @@ static int verity_setup_hash_alg(struct dm_verity *v, const char *alg_name) } v->shash_tfm = shash; v->digest_size = crypto_shash_digestsize(shash); - DMINFO("%s using \"%s\"", alg_name, crypto_shash_driver_name(shash)); if ((1 << v->hash_dev_block_bits) < v->digest_size * 2) { ti->error = "Digest size too big"; return -EINVAL; } + if (likely(v->version && strcmp(alg_name, "sha256") == 0)) { + /* + * Fast path: use the library API for reduced overhead and + * interleaved hashing support. + */ + v->use_sha256_lib = true; + if (sha256_finup_2x_is_optimized()) + v->use_sha256_finup_2x = true; + ti->per_io_data_size = + offsetofend(struct dm_verity_io, hash_ctx.sha256); + } else { + /* Fallback case: use the generic crypto API. */ + ti->per_io_data_size = + offsetofend(struct dm_verity_io, hash_ctx.shash) + + crypto_shash_descsize(shash); + } return 0; } @@ -1277,7 +1368,18 @@ static int verity_setup_salt_and_hashstate(struct dm_verity *v, const char *arg) return -EINVAL; } } - if (v->version) { /* Version 1: salt at beginning */ + if (likely(v->use_sha256_lib)) { + /* Implies version 1: salt at beginning */ + v->initial_hashstate.sha256 = + kmalloc(sizeof(struct sha256_ctx), GFP_KERNEL); + if (!v->initial_hashstate.sha256) { + ti->error = "Cannot allocate initial hash state"; + return -ENOMEM; + } + sha256_init(v->initial_hashstate.sha256); + sha256_update(v->initial_hashstate.sha256, + v->salt, v->salt_size); + } else if (v->version) { /* Version 1: salt at beginning */ SHASH_DESC_ON_STACK(desc, v->shash_tfm); int r; @@ -1285,16 +1387,16 @@ static int verity_setup_salt_and_hashstate(struct dm_verity *v, const char *arg) * Compute the pre-salted hash state that can be passed to * crypto_shash_import() for each block later. */ - v->initial_hashstate = kmalloc( + v->initial_hashstate.shash = kmalloc( crypto_shash_statesize(v->shash_tfm), GFP_KERNEL); - if (!v->initial_hashstate) { + if (!v->initial_hashstate.shash) { ti->error = "Cannot allocate initial hash state"; return -ENOMEM; } desc->tfm = v->shash_tfm; r = crypto_shash_init(desc) ?: crypto_shash_update(desc, v->salt, v->salt_size) ?: - crypto_shash_export(desc, v->initial_hashstate); + crypto_shash_export(desc, v->initial_hashstate.shash); if (r) { ti->error = "Cannot set up initial hash state"; return r; @@ -1556,9 +1658,6 @@ static int verity_ctr(struct dm_target *ti, unsigned int argc, char **argv) goto bad; } - ti->per_io_data_size = sizeof(struct dm_verity_io) + - crypto_shash_descsize(v->shash_tfm); - r = verity_fec_ctr(v); if (r) goto bad; @@ -1690,7 +1789,7 @@ static struct target_type verity_target = { .name = "verity", /* Note: the LSMs depend on the singleton and immutable features */ .features = DM_TARGET_SINGLETON | DM_TARGET_IMMUTABLE, - .version = {1, 12, 0}, + .version = {1, 13, 0}, .module = THIS_MODULE, .ctr = verity_ctr, .dtr = verity_dtr, diff --git a/drivers/md/dm-verity.h b/drivers/md/dm-verity.h index 6d141abd965c..f975a9e5c5d6 100644 --- a/drivers/md/dm-verity.h +++ b/drivers/md/dm-verity.h @@ -16,6 +16,7 @@ #include <linux/device-mapper.h> #include <linux/interrupt.h> #include <crypto/hash.h> +#include <crypto/sha2.h> #define DM_VERITY_MAX_LEVELS 63 @@ -42,7 +43,10 @@ struct dm_verity { struct crypto_shash *shash_tfm; u8 *root_digest; /* digest of the root block */ u8 *salt; /* salt: its size is salt_size */ - u8 *initial_hashstate; /* salted initial state, if version >= 1 */ + union { + struct sha256_ctx *sha256; /* for use_sha256_lib=1 */ + u8 *shash; /* for use_sha256_lib=0 */ + } initial_hashstate; /* salted initial state, if version >= 1 */ u8 *zero_digest; /* digest for a zero block */ #ifdef CONFIG_SECURITY u8 *root_digest_sig; /* signature of the root digest */ @@ -59,6 +63,8 @@ struct dm_verity { unsigned char version; bool hash_failed:1; /* set if hash of any block failed */ bool use_bh_wq:1; /* try to verify in BH wq before normal work-queue */ + bool use_sha256_lib:1; /* use SHA-256 library instead of generic crypto API */ + bool use_sha256_finup_2x:1; /* use interleaved hashing optimization */ unsigned int digest_size; /* digest size for the current hash algorithm */ enum verity_mode mode; /* mode for handling verification errors */ enum verity_mode error_mode;/* mode for handling I/O errors */ @@ -78,6 +84,13 @@ struct dm_verity { mempool_t recheck_pool; }; +struct pending_block { + void *data; + sector_t blkno; + u8 want_digest[HASH_MAX_DIGESTSIZE]; + u8 real_digest[HASH_MAX_DIGESTSIZE]; +}; + struct dm_verity_io { struct dm_verity *v; @@ -94,28 +107,29 @@ struct dm_verity_io { struct work_struct work; struct work_struct bh_work; - u8 real_digest[HASH_MAX_DIGESTSIZE]; - u8 want_digest[HASH_MAX_DIGESTSIZE]; + u8 tmp_digest[HASH_MAX_DIGESTSIZE]; /* - * Temporary space for hashing. This is variable-length and must be at - * the end of the struct. struct shash_desc is just the fixed part; - * it's followed by a context of size crypto_shash_descsize(shash_tfm). + * This is the queue of data blocks that are pending verification. When + * the crypto layer supports interleaved hashing, we allow multiple + * blocks to be queued up in order to utilize it. This can improve + * performance significantly vs. sequential hashing of each block. */ - struct shash_desc hash_desc; -}; + int num_pending; + struct pending_block pending_blocks[2]; -static inline u8 *verity_io_real_digest(struct dm_verity *v, - struct dm_verity_io *io) -{ - return io->real_digest; -} - -static inline u8 *verity_io_want_digest(struct dm_verity *v, - struct dm_verity_io *io) -{ - return io->want_digest; -} + /* + * Temporary space for hashing. Either sha256 or shash is used, + * depending on the value of use_sha256_lib. If shash is used, + * then this field is variable-length, with total size + * sizeof(struct shash_desc) + crypto_shash_descsize(shash_tfm). + * For this reason, this field must be the end of the struct. + */ + union { + struct sha256_ctx sha256; + struct shash_desc shash; + } hash_ctx; +}; extern int verity_hash(struct dm_verity *v, struct dm_verity_io *io, const u8 *data, size_t len, u8 *digest); diff --git a/drivers/md/dm-zone.c b/drivers/md/dm-zone.c index 78e17dd4d01b..c95e417194b3 100644 --- a/drivers/md/dm-zone.c +++ b/drivers/md/dm-zone.c @@ -17,33 +17,26 @@ * For internal zone reports bypassing the top BIO submission path. */ static int dm_blk_do_report_zones(struct mapped_device *md, struct dm_table *t, - sector_t sector, unsigned int nr_zones, - report_zones_cb cb, void *data) + unsigned int nr_zones, + struct dm_report_zones_args *args) { - struct gendisk *disk = md->disk; - int ret; - struct dm_report_zones_args args = { - .next_sector = sector, - .orig_data = data, - .orig_cb = cb, - }; - do { struct dm_target *tgt; + int ret; - tgt = dm_table_find_target(t, args.next_sector); + tgt = dm_table_find_target(t, args->next_sector); if (WARN_ON_ONCE(!tgt->type->report_zones)) return -EIO; - args.tgt = tgt; - ret = tgt->type->report_zones(tgt, &args, - nr_zones - args.zone_idx); + args->tgt = tgt; + ret = tgt->type->report_zones(tgt, args, + nr_zones - args->zone_idx); if (ret < 0) return ret; - } while (args.zone_idx < nr_zones && - args.next_sector < get_capacity(disk)); + } while (args->zone_idx < nr_zones && + args->next_sector < get_capacity(md->disk)); - return args.zone_idx; + return args->zone_idx; } /* @@ -52,7 +45,8 @@ static int dm_blk_do_report_zones(struct mapped_device *md, struct dm_table *t, * generally implemented by targets using dm_report_zones(). */ int dm_blk_report_zones(struct gendisk *disk, sector_t sector, - unsigned int nr_zones, report_zones_cb cb, void *data) + unsigned int nr_zones, + struct blk_report_zones_args *args) { struct mapped_device *md = disk->private_data; struct dm_table *map; @@ -76,9 +70,14 @@ int dm_blk_report_zones(struct gendisk *disk, sector_t sector, map = zone_revalidate_map; } - if (map) - ret = dm_blk_do_report_zones(md, map, sector, nr_zones, cb, - data); + if (map) { + struct dm_report_zones_args dm_args = { + .disk = md->disk, + .next_sector = sector, + .rep_args = args, + }; + ret = dm_blk_do_report_zones(md, map, nr_zones, &dm_args); + } if (put_table) dm_put_live_table(md, srcu_idx); @@ -113,7 +112,18 @@ static int dm_report_zones_cb(struct blk_zone *zone, unsigned int idx, } args->next_sector = zone->start + zone->len; - return args->orig_cb(zone, args->zone_idx++, args->orig_data); + + /* If we have an internal callback, call it first. */ + if (args->cb) { + int ret; + + ret = args->cb(zone, args->zone_idx, args->data); + if (ret) + return ret; + } + + return disk_report_zone(args->disk, zone, args->zone_idx++, + args->rep_args); } /* @@ -193,8 +203,6 @@ int dm_revalidate_zones(struct dm_table *t, struct request_queue *q) return ret; } - md->nr_zones = disk->nr_zones; - return 0; } @@ -442,7 +450,6 @@ void dm_finalize_zone_settings(struct dm_table *t, struct queue_limits *lim) set_bit(DMF_EMULATE_ZONE_APPEND, &md->flags); } else { clear_bit(DMF_EMULATE_ZONE_APPEND, &md->flags); - md->nr_zones = 0; md->disk->nr_zones = 0; } } @@ -492,10 +499,15 @@ int dm_zone_get_reset_bitmap(struct mapped_device *md, struct dm_table *t, sector_t sector, unsigned int nr_zones, unsigned long *need_reset) { + struct dm_report_zones_args args = { + .disk = md->disk, + .next_sector = sector, + .cb = dm_zone_need_reset_cb, + .data = need_reset, + }; int ret; - ret = dm_blk_do_report_zones(md, t, sector, nr_zones, - dm_zone_need_reset_cb, need_reset); + ret = dm_blk_do_report_zones(md, t, nr_zones, &args); if (ret != nr_zones) { DMERR("Get %s zone reset bitmap failed\n", md->disk->disk_name); diff --git a/drivers/md/dm.c b/drivers/md/dm.c index f5e5e59b232b..b63279202260 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -272,7 +272,7 @@ static int __init dm_init(void) int r, i; #if (IS_ENABLED(CONFIG_IMA) && !IS_ENABLED(CONFIG_IMA_DISABLE_HTABLE)) - DMWARN("CONFIG_IMA_DISABLE_HTABLE is disabled." + DMINFO("CONFIG_IMA_DISABLE_HTABLE is disabled." " Duplicate IMA measurements will not be recorded in the IMA log."); #endif @@ -1321,6 +1321,7 @@ void dm_accept_partial_bio(struct bio *bio, unsigned int n_sectors) BUG_ON(dm_tio_flagged(tio, DM_TIO_IS_DUPLICATE_BIO)); BUG_ON(bio_sectors > *tio->len_ptr); BUG_ON(n_sectors > bio_sectors); + BUG_ON(bio->bi_opf & REQ_ATOMIC); if (static_branch_unlikely(&zoned_enabled) && unlikely(bdev_is_zoned(bio->bi_bdev))) { @@ -1735,8 +1736,12 @@ static blk_status_t __split_and_process_bio(struct clone_info *ci) ci->submit_as_polled = !!(ci->bio->bi_opf & REQ_POLLED); len = min_t(sector_t, max_io_len(ti, ci->sector), ci->sector_count); - if (ci->bio->bi_opf & REQ_ATOMIC && len != ci->sector_count) - return BLK_STS_IOERR; + if (ci->bio->bi_opf & REQ_ATOMIC) { + if (unlikely(!dm_target_supports_atomic_writes(ti->type))) + return BLK_STS_IOERR; + if (unlikely(len != ci->sector_count)) + return BLK_STS_IOERR; + } setup_split_accounting(ci, len); @@ -2005,7 +2010,7 @@ static void dm_split_and_process_bio(struct mapped_device *md, * linear target or multiple linear targets pointing to the same * device), we can send the flush with data directly to it. */ - if (map->flush_bypasses_map) { + if (bio->bi_iter.bi_size && map->flush_bypasses_map) { struct list_head *devices = dm_table_get_devices(map); if (devices->next == devices->prev) goto send_preflush_with_data; @@ -2439,7 +2444,6 @@ static struct dm_table *__bind(struct mapped_device *md, struct dm_table *t, { struct dm_table *old_map; sector_t size, old_size; - int ret; lockdep_assert_held(&md->suspend_lock); @@ -2454,11 +2458,13 @@ static struct dm_table *__bind(struct mapped_device *md, struct dm_table *t, set_capacity(md->disk, size); - ret = dm_table_set_restrictions(t, md->queue, limits); - if (ret) { - set_capacity(md->disk, old_size); - old_map = ERR_PTR(ret); - goto out; + if (limits) { + int ret = dm_table_set_restrictions(t, md->queue, limits); + if (ret) { + set_capacity(md->disk, old_size); + old_map = ERR_PTR(ret); + goto out; + } } /* @@ -2836,6 +2842,7 @@ static void dm_wq_work(struct work_struct *work) static void dm_queue_flush(struct mapped_device *md) { + clear_bit(DMF_NOFLUSH_SUSPENDING, &md->flags); clear_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags); smp_mb__after_atomic(); queue_work(md->wq, &md->work); @@ -2848,6 +2855,7 @@ struct dm_table *dm_swap_table(struct mapped_device *md, struct dm_table *table) { struct dm_table *live_map = NULL, *map = ERR_PTR(-EINVAL); struct queue_limits limits; + bool update_limits = true; int r; mutex_lock(&md->suspend_lock); @@ -2857,19 +2865,30 @@ struct dm_table *dm_swap_table(struct mapped_device *md, struct dm_table *table) goto out; /* + * To avoid a potential deadlock locking the queue limits, disallow + * updating the queue limits during a table swap, when updating an + * immutable request-based dm device (dm-multipath) during a noflush + * suspend. It is userspace's responsibility to make sure that the new + * table uses the same limits as the existing table, if it asks for a + * noflush suspend. + */ + if (dm_request_based(md) && md->immutable_target && + __noflush_suspending(md)) + update_limits = false; + /* * 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)) { + else 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); } - if (!live_map) { + if (update_limits && !live_map) { r = dm_calculate_queue_limits(table, &limits); if (r) { map = ERR_PTR(r); @@ -2877,7 +2896,7 @@ struct dm_table *dm_swap_table(struct mapped_device *md, struct dm_table *table) } } - map = __bind(md, table, &limits); + map = __bind(md, table, update_limits ? &limits : NULL); dm_issue_global_event(); out: @@ -2930,7 +2949,6 @@ static int __dm_suspend(struct mapped_device *md, struct dm_table *map, /* * DMF_NOFLUSH_SUSPENDING must be set before presuspend. - * This flag is cleared before dm_suspend returns. */ if (noflush) set_bit(DMF_NOFLUSH_SUSPENDING, &md->flags); @@ -2993,8 +3011,6 @@ static int __dm_suspend(struct mapped_device *md, struct dm_table *map, if (!r) set_bit(dmf_suspended_flag, &md->flags); - if (noflush) - clear_bit(DMF_NOFLUSH_SUSPENDING, &md->flags); if (map) synchronize_srcu(&md->io_barrier); diff --git a/drivers/md/dm.h b/drivers/md/dm.h index 245f52b59215..7a795979ec72 100644 --- a/drivers/md/dm.h +++ b/drivers/md/dm.h @@ -109,7 +109,8 @@ void dm_finalize_zone_settings(struct dm_table *t, struct queue_limits *lim); void dm_zone_endio(struct dm_io *io, struct bio *clone); #ifdef CONFIG_BLK_DEV_ZONED int dm_blk_report_zones(struct gendisk *disk, sector_t sector, - unsigned int nr_zones, report_zones_cb cb, void *data); + unsigned int nr_zones, + struct blk_report_zones_args *args); bool dm_is_zone_write(struct mapped_device *md, struct bio *bio); int dm_zone_get_reset_bitmap(struct mapped_device *md, struct dm_table *t, sector_t sector, unsigned int nr_zones, diff --git a/drivers/md/md-linear.c b/drivers/md/md-linear.c index 7033d982d377..8d7b82c4a723 100644 --- a/drivers/md/md-linear.c +++ b/drivers/md/md-linear.c @@ -72,9 +72,11 @@ static int linear_set_limits(struct mddev *mddev) md_init_stacking_limits(&lim); lim.max_hw_sectors = mddev->chunk_sectors; + lim.logical_block_size = mddev->logical_block_size; lim.max_write_zeroes_sectors = mddev->chunk_sectors; lim.max_hw_wzeroes_unmap_sectors = mddev->chunk_sectors; lim.io_min = mddev->chunk_sectors << 9; + lim.features |= BLK_FEAT_ATOMIC_WRITES; err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY); if (err) return err; diff --git a/drivers/md/md-llbitmap.c b/drivers/md/md-llbitmap.c index 1eb434306162..9c1ade19b774 100644 --- a/drivers/md/md-llbitmap.c +++ b/drivers/md/md-llbitmap.c @@ -378,7 +378,7 @@ static void llbitmap_infect_dirty_bits(struct llbitmap *llbitmap, case BitClean: pctl->state[pos] = BitDirty; break; - }; + } } } diff --git a/drivers/md/md.c b/drivers/md/md.c index 41c476b40c7a..e5922a682953 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -99,7 +99,7 @@ static int remove_and_add_spares(struct mddev *mddev, struct md_rdev *this); static void mddev_detach(struct mddev *mddev); static void export_rdev(struct md_rdev *rdev, struct mddev *mddev); -static void md_wakeup_thread_directly(struct md_thread __rcu *thread); +static void md_wakeup_thread_directly(struct md_thread __rcu **thread); /* * Default number of read corrections we'll attempt on an rdev @@ -339,6 +339,7 @@ static int start_readonly; */ static bool create_on_open = true; static bool legacy_async_del_gendisk = true; +static bool check_new_feature = true; /* * We have a system wide 'event count' that is incremented @@ -730,6 +731,8 @@ static void mddev_clear_bitmap_ops(struct mddev *mddev) int mddev_init(struct mddev *mddev) { + int err = 0; + if (!IS_ENABLED(CONFIG_MD_BITMAP)) mddev->bitmap_id = ID_BITMAP_NONE; else @@ -741,10 +744,23 @@ int mddev_init(struct mddev *mddev) if (percpu_ref_init(&mddev->writes_pending, no_op, PERCPU_REF_ALLOW_REINIT, GFP_KERNEL)) { - percpu_ref_exit(&mddev->active_io); - return -ENOMEM; + err = -ENOMEM; + goto exit_acitve_io; } + err = bioset_init(&mddev->bio_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS); + if (err) + goto exit_writes_pending; + + err = bioset_init(&mddev->sync_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS); + if (err) + goto exit_bio_set; + + err = bioset_init(&mddev->io_clone_set, BIO_POOL_SIZE, + offsetof(struct md_io_clone, bio_clone), 0); + if (err) + goto exit_sync_set; + /* We want to start with the refcount at zero */ percpu_ref_put(&mddev->writes_pending); @@ -773,11 +789,24 @@ int mddev_init(struct mddev *mddev) INIT_WORK(&mddev->del_work, mddev_delayed_delete); return 0; + +exit_sync_set: + bioset_exit(&mddev->sync_set); +exit_bio_set: + bioset_exit(&mddev->bio_set); +exit_writes_pending: + percpu_ref_exit(&mddev->writes_pending); +exit_acitve_io: + percpu_ref_exit(&mddev->active_io); + return err; } EXPORT_SYMBOL_GPL(mddev_init); void mddev_destroy(struct mddev *mddev) { + bioset_exit(&mddev->bio_set); + bioset_exit(&mddev->sync_set); + bioset_exit(&mddev->io_clone_set); percpu_ref_exit(&mddev->active_io); percpu_ref_exit(&mddev->writes_pending); } @@ -941,8 +970,11 @@ void mddev_unlock(struct mddev *mddev) * do_md_stop. dm raid only uses md_stop to stop. So dm raid * doesn't need to check MD_DELETED when getting reconfig lock */ - if (test_bit(MD_DELETED, &mddev->flags)) + if (test_bit(MD_DELETED, &mddev->flags) && + !test_and_set_bit(MD_DO_DELETE, &mddev->flags)) { + kobject_del(&mddev->kobj); del_gendisk(mddev->gendisk); + } } } EXPORT_SYMBOL_GPL(mddev_unlock); @@ -1820,9 +1852,13 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_ } if (sb->pad0 || sb->pad3[0] || - memcmp(sb->pad3, sb->pad3+1, sizeof(sb->pad3) - sizeof(sb->pad3[1]))) - /* Some padding is non-zero, might be a new feature */ - return -EINVAL; + memcmp(sb->pad3, sb->pad3+1, sizeof(sb->pad3) - sizeof(sb->pad3[1]))) { + pr_warn("Some padding is non-zero on %pg, might be a new feature\n", + rdev->bdev); + if (check_new_feature) + return -EINVAL; + pr_warn("check_new_feature is disabled, data corruption possible\n"); + } rdev->preferred_minor = 0xffff; rdev->data_offset = le64_to_cpu(sb->data_offset); @@ -1963,6 +1999,7 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *freshest, struc mddev->layout = le32_to_cpu(sb->layout); mddev->raid_disks = le32_to_cpu(sb->raid_disks); mddev->dev_sectors = le64_to_cpu(sb->size); + mddev->logical_block_size = le32_to_cpu(sb->logical_block_size); mddev->events = ev1; mddev->bitmap_info.offset = 0; mddev->bitmap_info.space = 0; @@ -2172,6 +2209,7 @@ static void super_1_sync(struct mddev *mddev, struct md_rdev *rdev) sb->chunksize = cpu_to_le32(mddev->chunk_sectors); sb->level = cpu_to_le32(mddev->level); sb->layout = cpu_to_le32(mddev->layout); + sb->logical_block_size = cpu_to_le32(mddev->logical_block_size); if (test_bit(FailFast, &rdev->flags)) sb->devflags |= FailFast1; else @@ -2750,6 +2788,7 @@ void md_update_sb(struct mddev *mddev, int force_change) if (!md_is_rdwr(mddev)) { if (force_change) set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags); + pr_err("%s: can't update sb for read-only array %s\n", __func__, mdname(mddev)); return; } @@ -5134,7 +5173,7 @@ static void stop_sync_thread(struct mddev *mddev, bool locked) * Thread might be blocked waiting for metadata update which will now * never happen */ - md_wakeup_thread_directly(mddev->sync_thread); + md_wakeup_thread_directly(&mddev->sync_thread); if (work_pending(&mddev->sync_work)) flush_work(&mddev->sync_work); @@ -5900,6 +5939,68 @@ static struct md_sysfs_entry md_serialize_policy = __ATTR(serialize_policy, S_IRUGO | S_IWUSR, serialize_policy_show, serialize_policy_store); +static int mddev_set_logical_block_size(struct mddev *mddev, + unsigned int lbs) +{ + int err = 0; + struct queue_limits lim; + + if (queue_logical_block_size(mddev->gendisk->queue) >= lbs) { + pr_err("%s: Cannot set LBS smaller than mddev LBS %u\n", + mdname(mddev), lbs); + return -EINVAL; + } + + lim = queue_limits_start_update(mddev->gendisk->queue); + lim.logical_block_size = lbs; + pr_info("%s: logical_block_size is changed, data may be lost\n", + mdname(mddev)); + err = queue_limits_commit_update(mddev->gendisk->queue, &lim); + if (err) + return err; + + mddev->logical_block_size = lbs; + /* New lbs will be written to superblock after array is running */ + set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags); + return 0; +} + +static ssize_t +lbs_show(struct mddev *mddev, char *page) +{ + return sprintf(page, "%u\n", mddev->logical_block_size); +} + +static ssize_t +lbs_store(struct mddev *mddev, const char *buf, size_t len) +{ + unsigned int lbs; + int err = -EBUSY; + + /* Only 1.x meta supports configurable LBS */ + if (mddev->major_version == 0) + return -EINVAL; + + if (mddev->pers) + return -EBUSY; + + err = kstrtouint(buf, 10, &lbs); + if (err < 0) + return -EINVAL; + + err = mddev_lock(mddev); + if (err) + goto unlock; + + err = mddev_set_logical_block_size(mddev, lbs); + +unlock: + mddev_unlock(mddev); + return err ?: len; +} + +static struct md_sysfs_entry md_logical_block_size = +__ATTR(logical_block_size, 0644, lbs_show, lbs_store); static struct attribute *md_default_attrs[] = { &md_level.attr, @@ -5922,6 +6023,7 @@ static struct attribute *md_default_attrs[] = { &md_consistency_policy.attr, &md_fail_last_dev.attr, &md_serialize_policy.attr, + &md_logical_block_size.attr, NULL, }; @@ -6052,6 +6154,17 @@ int mddev_stack_rdev_limits(struct mddev *mddev, struct queue_limits *lim, return -EINVAL; } + /* + * Before RAID adding folio support, the logical_block_size + * should be smaller than the page size. + */ + if (lim->logical_block_size > PAGE_SIZE) { + pr_err("%s: logical_block_size must not larger than PAGE_SIZE\n", + mdname(mddev)); + return -EINVAL; + } + mddev->logical_block_size = lim->logical_block_size; + return 0; } EXPORT_SYMBOL_GPL(mddev_stack_rdev_limits); @@ -6064,6 +6177,13 @@ int mddev_stack_new_rdev(struct mddev *mddev, struct md_rdev *rdev) if (mddev_is_dm(mddev)) return 0; + if (queue_logical_block_size(rdev->bdev->bd_disk->queue) > + queue_logical_block_size(mddev->gendisk->queue)) { + pr_err("%s: incompatible logical_block_size, can not add\n", + mdname(mddev)); + return -EINVAL; + } + lim = queue_limits_start_update(mddev->gendisk->queue); queue_limits_stack_bdev(&lim, rdev->bdev, rdev->data_offset, mddev->gendisk->disk_name); @@ -6384,29 +6504,9 @@ int md_run(struct mddev *mddev) nowait = nowait && bdev_nowait(rdev->bdev); } - if (!bioset_initialized(&mddev->bio_set)) { - err = bioset_init(&mddev->bio_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS); - if (err) - return err; - } - if (!bioset_initialized(&mddev->sync_set)) { - err = bioset_init(&mddev->sync_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS); - if (err) - goto exit_bio_set; - } - - if (!bioset_initialized(&mddev->io_clone_set)) { - err = bioset_init(&mddev->io_clone_set, BIO_POOL_SIZE, - offsetof(struct md_io_clone, bio_clone), 0); - if (err) - goto exit_sync_set; - } - pers = get_pers(mddev->level, mddev->clevel); - if (!pers) { - err = -EINVAL; - goto abort; - } + if (!pers) + return -EINVAL; if (mddev->level != pers->head.id) { mddev->level = pers->head.id; mddev->new_level = pers->head.id; @@ -6417,8 +6517,7 @@ int md_run(struct mddev *mddev) pers->start_reshape == NULL) { /* This personality cannot handle reshaping... */ put_pers(pers); - err = -EINVAL; - goto abort; + return -EINVAL; } if (pers->sync_request) { @@ -6545,12 +6644,6 @@ bitmap_abort: mddev->private = NULL; put_pers(pers); md_bitmap_destroy(mddev); -abort: - bioset_exit(&mddev->io_clone_set); -exit_sync_set: - bioset_exit(&mddev->sync_set); -exit_bio_set: - bioset_exit(&mddev->bio_set); return err; } EXPORT_SYMBOL_GPL(md_run); @@ -6683,6 +6776,7 @@ static void md_clean(struct mddev *mddev) mddev->chunk_sectors = 0; mddev->ctime = mddev->utime = 0; mddev->layout = 0; + mddev->logical_block_size = 0; mddev->max_disks = 0; mddev->events = 0; mddev->can_decrease_events = 0; @@ -6775,10 +6869,6 @@ static void __md_stop(struct mddev *mddev) mddev->private = NULL; put_pers(pers); clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); - - bioset_exit(&mddev->bio_set); - bioset_exit(&mddev->sync_set); - bioset_exit(&mddev->io_clone_set); } void md_stop(struct mddev *mddev) @@ -6869,6 +6959,10 @@ static int do_md_stop(struct mddev *mddev, int mode) if (!md_is_rdwr(mddev)) set_disk_ro(disk, 0); + if (mode == 2 && mddev->pers->sync_request && + mddev->to_remove == NULL) + mddev->to_remove = &md_redundancy_group; + __md_stop_writes(mddev); __md_stop(mddev); @@ -8373,22 +8467,21 @@ static int md_thread(void *arg) return 0; } -static void md_wakeup_thread_directly(struct md_thread __rcu *thread) +static void md_wakeup_thread_directly(struct md_thread __rcu **thread) { struct md_thread *t; rcu_read_lock(); - t = rcu_dereference(thread); + t = rcu_dereference(*thread); if (t) wake_up_process(t->tsk); rcu_read_unlock(); } -void md_wakeup_thread(struct md_thread __rcu *thread) +void __md_wakeup_thread(struct md_thread __rcu *thread) { struct md_thread *t; - rcu_read_lock(); t = rcu_dereference(thread); if (t) { pr_debug("md: waking up MD thread %s.\n", t->tsk->comm); @@ -8396,9 +8489,8 @@ void md_wakeup_thread(struct md_thread __rcu *thread) if (wq_has_sleeper(&t->wqueue)) wake_up(&t->wqueue); } - rcu_read_unlock(); } -EXPORT_SYMBOL(md_wakeup_thread); +EXPORT_SYMBOL(__md_wakeup_thread); struct md_thread *md_register_thread(void (*run) (struct md_thread *), struct mddev *mddev, const char *name) @@ -9978,6 +10070,52 @@ static void unregister_sync_thread(struct mddev *mddev) md_reap_sync_thread(mddev); } +static bool md_should_do_recovery(struct mddev *mddev) +{ + /* + * As long as one of the following flags is set, + * recovery needs to do or cleanup. + */ + if (test_bit(MD_RECOVERY_NEEDED, &mddev->recovery) || + test_bit(MD_RECOVERY_DONE, &mddev->recovery)) + return true; + + /* + * If no flags are set and it is in read-only status, + * there is nothing to do. + */ + if (!md_is_rdwr(mddev)) + return false; + + /* + * MD_SB_CHANGE_PENDING indicates that the array is switching from clean to + * active, and no action is needed for now. + * All other MD_SB_* flags require to update the superblock. + */ + if (mddev->sb_flags & ~ (1<<MD_SB_CHANGE_PENDING)) + return true; + + /* + * If the array is not using external metadata and there has been no data + * written for some time, then the array's status needs to be set to + * in_sync. + */ + if (mddev->external == 0 && mddev->safemode == 1) + return true; + + /* + * When the system is about to restart or the process receives an signal, + * the array needs to be synchronized as soon as possible. + * Once the data synchronization is completed, need to change the array + * status to in_sync. + */ + if (mddev->safemode == 2 && !mddev->in_sync && + mddev->resync_offset == MaxSector) + return true; + + return false; +} + /* * This routine is regularly called by all per-raid-array threads to * deal with generic issues like resync and super-block update. @@ -10014,18 +10152,7 @@ void md_check_recovery(struct mddev *mddev) flush_signals(current); } - if (!md_is_rdwr(mddev) && - !test_bit(MD_RECOVERY_NEEDED, &mddev->recovery) && - !test_bit(MD_RECOVERY_DONE, &mddev->recovery)) - return; - if ( ! ( - (mddev->sb_flags & ~ (1<<MD_SB_CHANGE_PENDING)) || - test_bit(MD_RECOVERY_NEEDED, &mddev->recovery) || - test_bit(MD_RECOVERY_DONE, &mddev->recovery) || - (mddev->external == 0 && mddev->safemode == 1) || - (mddev->safemode == 2 - && !mddev->in_sync && mddev->resync_offset == MaxSector) - )) + if (!md_should_do_recovery(mddev)) return; if (mddev_trylock(mddev)) { @@ -10281,7 +10408,6 @@ static int md_notify_reboot(struct notifier_block *this, unsigned long code, void *x) { struct mddev *mddev; - int need_delay = 0; spin_lock(&all_mddevs_lock); list_for_each_entry(mddev, &all_mddevs, all_mddevs) { @@ -10295,21 +10421,11 @@ static int md_notify_reboot(struct notifier_block *this, mddev->safemode = 2; mddev_unlock(mddev); } - need_delay = 1; spin_lock(&all_mddevs_lock); mddev_put_locked(mddev); } spin_unlock(&all_mddevs_lock); - /* - * certain more exotic SCSI devices are known to be - * volatile wrt too early system reboots. While the - * right place to handle this issue is the given - * driver, we do want to have a safe RAID driver ... - */ - if (need_delay) - msleep(1000); - return NOTIFY_DONE; } @@ -10697,6 +10813,7 @@ module_param(start_dirty_degraded, int, S_IRUGO|S_IWUSR); module_param_call(new_array, add_named_array, NULL, NULL, S_IWUSR); module_param(create_on_open, bool, S_IRUSR|S_IWUSR); module_param(legacy_async_del_gendisk, bool, 0600); +module_param(check_new_feature, bool, 0600); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("MD RAID framework"); diff --git a/drivers/md/md.h b/drivers/md/md.h index 1979c2d4fe89..6985f2829bbd 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -354,6 +354,7 @@ enum mddev_flags { MD_HAS_MULTIPLE_PPLS, MD_NOT_READY, MD_BROKEN, + MD_DO_DELETE, MD_DELETED, }; @@ -432,6 +433,7 @@ struct mddev { sector_t array_sectors; /* exported array size */ int external_size; /* size managed * externally */ + unsigned int logical_block_size; __u64 events; /* If the last 'event' was simply a clean->dirty transition, and * we didn't write it to the spares, then it is safe and simple @@ -882,6 +884,12 @@ struct md_io_clone { #define THREAD_WAKEUP 0 +#define md_wakeup_thread(thread) do { \ + rcu_read_lock(); \ + __md_wakeup_thread(thread); \ + rcu_read_unlock(); \ +} while (0) + static inline void safe_put_page(struct page *p) { if (p) put_page(p); @@ -895,7 +903,7 @@ extern struct md_thread *md_register_thread( struct mddev *mddev, const char *name); extern void md_unregister_thread(struct mddev *mddev, struct md_thread __rcu **threadp); -extern void md_wakeup_thread(struct md_thread __rcu *thread); +extern void __md_wakeup_thread(struct md_thread __rcu *thread); extern void md_check_recovery(struct mddev *mddev); extern void md_reap_sync_thread(struct mddev *mddev); extern enum sync_action md_sync_action(struct mddev *mddev); diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index e443e478645a..985c377356eb 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -68,7 +68,10 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf) struct strip_zone *zone; int cnt; struct r0conf *conf = kzalloc(sizeof(*conf), GFP_KERNEL); - unsigned blksize = 512; + unsigned int blksize = 512; + + if (!mddev_is_dm(mddev)) + blksize = queue_logical_block_size(mddev->gendisk->queue); *private_conf = ERR_PTR(-ENOMEM); if (!conf) @@ -84,7 +87,8 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf) sector_div(sectors, mddev->chunk_sectors); rdev1->sectors = sectors * mddev->chunk_sectors; - blksize = max(blksize, queue_logical_block_size( + if (mddev_is_dm(mddev)) + blksize = max(blksize, queue_logical_block_size( rdev1->bdev->bd_disk->queue)); rdev_for_each(rdev2, mddev) { @@ -383,6 +387,7 @@ static int raid0_set_limits(struct mddev *mddev) lim.max_hw_sectors = mddev->chunk_sectors; lim.max_write_zeroes_sectors = mddev->chunk_sectors; lim.max_hw_wzeroes_unmap_sectors = mddev->chunk_sectors; + lim.logical_block_size = mddev->logical_block_size; lim.io_min = mddev->chunk_sectors << 9; lim.io_opt = lim.io_min * mddev->raid_disks; lim.chunk_sectors = mddev->chunk_sectors; @@ -405,6 +410,12 @@ static int raid0_run(struct mddev *mddev) if (md_check_no_bitmap(mddev)) return -EINVAL; + if (!mddev_is_dm(mddev)) { + ret = raid0_set_limits(mddev); + if (ret) + return ret; + } + /* if private is not null, we are here after takeover */ if (mddev->private == NULL) { ret = create_strip_zones(mddev, &conf); @@ -413,11 +424,6 @@ static int raid0_run(struct mddev *mddev) mddev->private = conf; } conf = mddev->private; - if (!mddev_is_dm(mddev)) { - ret = raid0_set_limits(mddev); - if (ret) - return ret; - } /* calculate array device size */ md_set_array_sectors(mddev, raid0_size(mddev, 0, 0)); diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 592a40233004..57d50465eed1 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -3213,6 +3213,7 @@ static int raid1_set_limits(struct mddev *mddev) md_init_stacking_limits(&lim); lim.max_write_zeroes_sectors = 0; lim.max_hw_wzeroes_unmap_sectors = 0; + lim.logical_block_size = mddev->logical_block_size; lim.features |= BLK_FEAT_ATOMIC_WRITES; err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY); if (err) diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 14dcd5142eb4..84be4cc7e873 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -4000,6 +4000,7 @@ static int raid10_set_queue_limits(struct mddev *mddev) md_init_stacking_limits(&lim); lim.max_write_zeroes_sectors = 0; lim.max_hw_wzeroes_unmap_sectors = 0; + lim.logical_block_size = mddev->logical_block_size; lim.io_min = mddev->chunk_sectors << 9; lim.chunk_sectors = mddev->chunk_sectors; lim.io_opt = lim.io_min * raid10_nr_stripes(conf); diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c index ba768ca7f422..e29e69335c69 100644 --- a/drivers/md/raid5-cache.c +++ b/drivers/md/raid5-cache.c @@ -3104,7 +3104,7 @@ int r5l_init_log(struct r5conf *conf, struct md_rdev *rdev) goto out_mempool; spin_lock_init(&log->tree_lock); - INIT_RADIX_TREE(&log->big_stripe_tree, GFP_NOWAIT | __GFP_NOWARN); + INIT_RADIX_TREE(&log->big_stripe_tree, GFP_NOWAIT); thread = md_register_thread(r5l_reclaim_thread, log->rdev->mddev, "reclaim"); diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 24b32a0c95b4..e57ce3295292 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -4956,7 +4956,8 @@ static void handle_stripe(struct stripe_head *sh) goto finish; if (s.handle_bad_blocks || - test_bit(MD_SB_CHANGE_PENDING, &conf->mddev->sb_flags)) { + (md_is_rdwr(conf->mddev) && + test_bit(MD_SB_CHANGE_PENDING, &conf->mddev->sb_flags))) { set_bit(STRIPE_HANDLE, &sh->state); goto finish; } @@ -6768,7 +6769,8 @@ static void raid5d(struct md_thread *thread) int batch_size, released; unsigned int offset; - if (test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags)) + if (md_is_rdwr(mddev) && + test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags)) break; released = release_stripe_list(conf, conf->temp_inactive_list); @@ -7745,6 +7747,7 @@ static int raid5_set_limits(struct mddev *mddev) stripe = roundup_pow_of_two(data_disks * (mddev->chunk_sectors << 9)); md_init_stacking_limits(&lim); + lim.logical_block_size = mddev->logical_block_size; lim.io_min = mddev->chunk_sectors << 9; lim.io_opt = lim.io_min * (conf->raid_disks - conf->max_degraded); lim.features |= BLK_FEAT_RAID_PARTIAL_STRIPES_EXPENSIVE; |