diff options
Diffstat (limited to 'drivers/md')
52 files changed, 1077 insertions, 613 deletions
diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig index 1e9db8e4acdf..0b1870a09e1f 100644 --- a/drivers/md/Kconfig +++ b/drivers/md/Kconfig @@ -61,6 +61,19 @@ config MD_BITMAP_FILE various kernel APIs and can only work with files on a file system not actually sitting on the MD device. +config MD_LINEAR + tristate "Linear (append) mode" + depends on BLK_DEV_MD + help + If you say Y here, then your multiple devices driver will be able to + use the so-called linear mode, i.e. it will combine the hard disk + partitions by simply appending one to the other. + + To compile this as a module, choose M here: the module + will be called linear. + + If unsure, say Y. + config MD_RAID0 tristate "RAID-0 (striping) mode" depends on BLK_DEV_MD diff --git a/drivers/md/Makefile b/drivers/md/Makefile index 476a214e4bdc..87bdfc9fe14c 100644 --- a/drivers/md/Makefile +++ b/drivers/md/Makefile @@ -29,12 +29,14 @@ dm-zoned-y += dm-zoned-target.o dm-zoned-metadata.o dm-zoned-reclaim.o md-mod-y += md.o md-bitmap.o raid456-y += raid5.o raid5-cache.o raid5-ppl.o +linear-y += md-linear.o # Note: link order is important. All raid personalities # and must come before md.o, as they each initialise # themselves, and md.o may use the personalities when it # auto-initialised. +obj-$(CONFIG_MD_LINEAR) += linear.o obj-$(CONFIG_MD_RAID0) += raid0.o obj-$(CONFIG_MD_RAID1) += raid1.o obj-$(CONFIG_MD_RAID10) += raid10.o diff --git a/drivers/md/bcache/alloc.c b/drivers/md/bcache/alloc.c index da50f6661bae..48ce750bf70a 100644 --- a/drivers/md/bcache/alloc.c +++ b/drivers/md/bcache/alloc.c @@ -164,68 +164,40 @@ static void bch_invalidate_one_bucket(struct cache *ca, struct bucket *b) * prio is worth 1/8th of what INITIAL_PRIO is worth. */ -static inline unsigned int new_bucket_prio(struct cache *ca, struct bucket *b) -{ - unsigned int min_prio = (INITIAL_PRIO - ca->set->min_prio) / 8; - - return (b->prio - ca->set->min_prio + min_prio) * GC_SECTORS_USED(b); -} - -static inline bool new_bucket_max_cmp(const void *l, const void *r, void *args) -{ - struct bucket **lhs = (struct bucket **)l; - struct bucket **rhs = (struct bucket **)r; - struct cache *ca = args; - - return new_bucket_prio(ca, *lhs) > new_bucket_prio(ca, *rhs); -} - -static inline bool new_bucket_min_cmp(const void *l, const void *r, void *args) -{ - struct bucket **lhs = (struct bucket **)l; - struct bucket **rhs = (struct bucket **)r; - struct cache *ca = args; - - return new_bucket_prio(ca, *lhs) < new_bucket_prio(ca, *rhs); -} - -static inline void new_bucket_swap(void *l, void *r, void __always_unused *args) -{ - struct bucket **lhs = l, **rhs = r; +#define bucket_prio(b) \ +({ \ + unsigned int min_prio = (INITIAL_PRIO - ca->set->min_prio) / 8; \ + \ + (b->prio - ca->set->min_prio + min_prio) * GC_SECTORS_USED(b); \ +}) - swap(*lhs, *rhs); -} +#define bucket_max_cmp(l, r) (bucket_prio(l) < bucket_prio(r)) +#define bucket_min_cmp(l, r) (bucket_prio(l) > bucket_prio(r)) static void invalidate_buckets_lru(struct cache *ca) { struct bucket *b; - const struct min_heap_callbacks bucket_max_cmp_callback = { - .less = new_bucket_max_cmp, - .swp = new_bucket_swap, - }; - const struct min_heap_callbacks bucket_min_cmp_callback = { - .less = new_bucket_min_cmp, - .swp = new_bucket_swap, - }; + ssize_t i; - ca->heap.nr = 0; + ca->heap.used = 0; for_each_bucket(b, ca) { if (!bch_can_invalidate_bucket(ca, b)) continue; - if (!min_heap_full(&ca->heap)) - min_heap_push(&ca->heap, &b, &bucket_max_cmp_callback, ca); - else if (!new_bucket_max_cmp(&b, min_heap_peek(&ca->heap), ca)) { + if (!heap_full(&ca->heap)) + heap_add(&ca->heap, b, bucket_max_cmp); + else if (bucket_max_cmp(b, heap_peek(&ca->heap))) { ca->heap.data[0] = b; - min_heap_sift_down(&ca->heap, 0, &bucket_max_cmp_callback, ca); + heap_sift(&ca->heap, 0, bucket_max_cmp); } } - min_heapify_all(&ca->heap, &bucket_min_cmp_callback, ca); + for (i = ca->heap.used / 2 - 1; i >= 0; --i) + heap_sift(&ca->heap, i, bucket_min_cmp); while (!fifo_full(&ca->free_inc)) { - if (!ca->heap.nr) { + if (!heap_pop(&ca->heap, b, bucket_min_cmp)) { /* * We don't want to be calling invalidate_buckets() * multiple times when it can't do anything @@ -234,8 +206,6 @@ static void invalidate_buckets_lru(struct cache *ca) wake_up_gc(ca->set); return; } - b = min_heap_peek(&ca->heap)[0]; - min_heap_pop(&ca->heap, &bucket_min_cmp_callback, ca); bch_invalidate_one_bucket(ca, b); } diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h index 785b0d9008fa..1d33e40d26ea 100644 --- a/drivers/md/bcache/bcache.h +++ b/drivers/md/bcache/bcache.h @@ -458,7 +458,7 @@ struct cache { /* Allocation stuff: */ struct bucket *buckets; - DEFINE_MIN_HEAP(struct bucket *, cache_heap) heap; + DECLARE_HEAP(struct bucket *, heap); /* * If nonzero, we know we aren't going to find any buckets to invalidate diff --git a/drivers/md/bcache/bset.c b/drivers/md/bcache/bset.c index bd97d8626887..463eb13bd0b2 100644 --- a/drivers/md/bcache/bset.c +++ b/drivers/md/bcache/bset.c @@ -54,11 +54,9 @@ void bch_dump_bucket(struct btree_keys *b) int __bch_count_data(struct btree_keys *b) { unsigned int ret = 0; - struct btree_iter iter; + struct btree_iter_stack iter; struct bkey *k; - min_heap_init(&iter.heap, NULL, MAX_BSETS); - if (b->ops->is_extents) for_each_key(b, k, &iter) ret += KEY_SIZE(k); @@ -69,11 +67,9 @@ void __bch_check_keys(struct btree_keys *b, const char *fmt, ...) { va_list args; struct bkey *k, *p = NULL; - struct btree_iter iter; + struct btree_iter_stack iter; const char *err; - min_heap_init(&iter.heap, NULL, MAX_BSETS); - for_each_key(b, k, &iter) { if (b->ops->is_extents) { err = "Keys out of order"; @@ -114,9 +110,9 @@ bug: static void bch_btree_iter_next_check(struct btree_iter *iter) { - struct bkey *k = iter->heap.data->k, *next = bkey_next(k); + struct bkey *k = iter->data->k, *next = bkey_next(k); - if (next < iter->heap.data->end && + if (next < iter->data->end && bkey_cmp(k, iter->b->ops->is_extents ? &START_KEY(next) : next) > 0) { bch_dump_bucket(iter->b); @@ -883,14 +879,12 @@ unsigned int bch_btree_insert_key(struct btree_keys *b, struct bkey *k, unsigned int status = BTREE_INSERT_STATUS_NO_INSERT; struct bset *i = bset_tree_last(b)->data; struct bkey *m, *prev = NULL; - struct btree_iter iter; + struct btree_iter_stack iter; struct bkey preceding_key_on_stack = ZERO_KEY; struct bkey *preceding_key_p = &preceding_key_on_stack; BUG_ON(b->ops->is_extents && !KEY_SIZE(k)); - min_heap_init(&iter.heap, NULL, MAX_BSETS); - /* * If k has preceding key, preceding_key_p will be set to address * of k's preceding key; otherwise preceding_key_p will be set @@ -901,9 +895,9 @@ unsigned int bch_btree_insert_key(struct btree_keys *b, struct bkey *k, else preceding_key(k, &preceding_key_p); - m = bch_btree_iter_init(b, &iter, preceding_key_p); + m = bch_btree_iter_stack_init(b, &iter, preceding_key_p); - if (b->ops->insert_fixup(b, k, &iter, replace_key)) + if (b->ops->insert_fixup(b, k, &iter.iter, replace_key)) return status; status = BTREE_INSERT_STATUS_INSERT; @@ -1083,102 +1077,79 @@ struct bkey *__bch_bset_search(struct btree_keys *b, struct bset_tree *t, /* Btree iterator */ -typedef bool (new_btree_iter_cmp_fn)(const void *, const void *, void *); - -static inline bool new_btree_iter_cmp(const void *l, const void *r, void __always_unused *args) -{ - const struct btree_iter_set *_l = l; - const struct btree_iter_set *_r = r; - - return bkey_cmp(_l->k, _r->k) <= 0; -} +typedef bool (btree_iter_cmp_fn)(struct btree_iter_set, + struct btree_iter_set); -static inline void new_btree_iter_swap(void *iter1, void *iter2, void __always_unused *args) +static inline bool btree_iter_cmp(struct btree_iter_set l, + struct btree_iter_set r) { - struct btree_iter_set *_iter1 = iter1; - struct btree_iter_set *_iter2 = iter2; - - swap(*_iter1, *_iter2); + return bkey_cmp(l.k, r.k) > 0; } static inline bool btree_iter_end(struct btree_iter *iter) { - return !iter->heap.nr; + return !iter->used; } void bch_btree_iter_push(struct btree_iter *iter, struct bkey *k, struct bkey *end) { - const struct min_heap_callbacks callbacks = { - .less = new_btree_iter_cmp, - .swp = new_btree_iter_swap, - }; - if (k != end) - BUG_ON(!min_heap_push(&iter->heap, - &((struct btree_iter_set) { k, end }), - &callbacks, - NULL)); + BUG_ON(!heap_add(iter, + ((struct btree_iter_set) { k, end }), + btree_iter_cmp)); } -static struct bkey *__bch_btree_iter_init(struct btree_keys *b, - struct btree_iter *iter, - struct bkey *search, - struct bset_tree *start) +static struct bkey *__bch_btree_iter_stack_init(struct btree_keys *b, + struct btree_iter_stack *iter, + struct bkey *search, + struct bset_tree *start) { struct bkey *ret = NULL; - iter->heap.size = ARRAY_SIZE(iter->heap.preallocated); - iter->heap.nr = 0; + iter->iter.size = ARRAY_SIZE(iter->stack_data); + iter->iter.used = 0; #ifdef CONFIG_BCACHE_DEBUG - iter->b = b; + iter->iter.b = b; #endif for (; start <= bset_tree_last(b); start++) { ret = bch_bset_search(b, start, search); - bch_btree_iter_push(iter, ret, bset_bkey_last(start->data)); + bch_btree_iter_push(&iter->iter, ret, bset_bkey_last(start->data)); } return ret; } -struct bkey *bch_btree_iter_init(struct btree_keys *b, - struct btree_iter *iter, +struct bkey *bch_btree_iter_stack_init(struct btree_keys *b, + struct btree_iter_stack *iter, struct bkey *search) { - return __bch_btree_iter_init(b, iter, search, b->set); + return __bch_btree_iter_stack_init(b, iter, search, b->set); } static inline struct bkey *__bch_btree_iter_next(struct btree_iter *iter, - new_btree_iter_cmp_fn *cmp) + btree_iter_cmp_fn *cmp) { struct btree_iter_set b __maybe_unused; struct bkey *ret = NULL; - const struct min_heap_callbacks callbacks = { - .less = cmp, - .swp = new_btree_iter_swap, - }; if (!btree_iter_end(iter)) { bch_btree_iter_next_check(iter); - ret = iter->heap.data->k; - iter->heap.data->k = bkey_next(iter->heap.data->k); + ret = iter->data->k; + iter->data->k = bkey_next(iter->data->k); - if (iter->heap.data->k > iter->heap.data->end) { + if (iter->data->k > iter->data->end) { WARN_ONCE(1, "bset was corrupt!\n"); - iter->heap.data->k = iter->heap.data->end; + iter->data->k = iter->data->end; } - if (iter->heap.data->k == iter->heap.data->end) { - if (iter->heap.nr) { - b = min_heap_peek(&iter->heap)[0]; - min_heap_pop(&iter->heap, &callbacks, NULL); - } - } + if (iter->data->k == iter->data->end) + heap_pop(iter, b, cmp); else - min_heap_sift_down(&iter->heap, 0, &callbacks, NULL); + heap_sift(iter, 0, cmp); } return ret; @@ -1186,7 +1157,7 @@ static inline struct bkey *__bch_btree_iter_next(struct btree_iter *iter, struct bkey *bch_btree_iter_next(struct btree_iter *iter) { - return __bch_btree_iter_next(iter, new_btree_iter_cmp); + return __bch_btree_iter_next(iter, btree_iter_cmp); } @@ -1224,18 +1195,16 @@ static void btree_mergesort(struct btree_keys *b, struct bset *out, struct btree_iter *iter, bool fixup, bool remove_stale) { + int i; struct bkey *k, *last = NULL; BKEY_PADDED(k) tmp; bool (*bad)(struct btree_keys *, const struct bkey *) = remove_stale ? bch_ptr_bad : bch_ptr_invalid; - const struct min_heap_callbacks callbacks = { - .less = b->ops->sort_cmp, - .swp = new_btree_iter_swap, - }; /* Heapify the iterator, using our comparison function */ - min_heapify_all(&iter->heap, &callbacks, NULL); + for (i = iter->used / 2 - 1; i >= 0; --i) + heap_sift(iter, i, b->ops->sort_cmp); while (!btree_iter_end(iter)) { if (b->ops->sort_fixup && fixup) @@ -1324,11 +1293,10 @@ void bch_btree_sort_partial(struct btree_keys *b, unsigned int start, struct bset_sort_state *state) { size_t order = b->page_order, keys = 0; - struct btree_iter iter; + struct btree_iter_stack iter; int oldsize = bch_count_data(b); - min_heap_init(&iter.heap, NULL, MAX_BSETS); - __bch_btree_iter_init(b, &iter, NULL, &b->set[start]); + __bch_btree_iter_stack_init(b, &iter, NULL, &b->set[start]); if (start) { unsigned int i; @@ -1339,7 +1307,7 @@ void bch_btree_sort_partial(struct btree_keys *b, unsigned int start, order = get_order(__set_bytes(b->set->data, keys)); } - __btree_sort(b, &iter, start, order, false, state); + __btree_sort(b, &iter.iter, start, order, false, state); EBUG_ON(oldsize >= 0 && bch_count_data(b) != oldsize); } @@ -1355,13 +1323,11 @@ void bch_btree_sort_into(struct btree_keys *b, struct btree_keys *new, struct bset_sort_state *state) { uint64_t start_time = local_clock(); - struct btree_iter iter; - - min_heap_init(&iter.heap, NULL, MAX_BSETS); + struct btree_iter_stack iter; - bch_btree_iter_init(b, &iter, NULL); + bch_btree_iter_stack_init(b, &iter, NULL); - btree_mergesort(b, new->set->data, &iter, false, true); + btree_mergesort(b, new->set->data, &iter.iter, false, true); bch_time_stats_update(&state->time, start_time); diff --git a/drivers/md/bcache/bset.h b/drivers/md/bcache/bset.h index f79441acd4c1..011f6062c4c0 100644 --- a/drivers/md/bcache/bset.h +++ b/drivers/md/bcache/bset.h @@ -187,9 +187,8 @@ struct bset_tree { }; struct btree_keys_ops { - bool (*sort_cmp)(const void *l, - const void *r, - void *args); + bool (*sort_cmp)(struct btree_iter_set l, + struct btree_iter_set r); struct bkey *(*sort_fixup)(struct btree_iter *iter, struct bkey *tmp); bool (*insert_fixup)(struct btree_keys *b, @@ -313,17 +312,23 @@ enum { BTREE_INSERT_STATUS_FRONT_MERGE, }; -struct btree_iter_set { - struct bkey *k, *end; -}; - /* Btree key iteration */ struct btree_iter { + size_t size, used; #ifdef CONFIG_BCACHE_DEBUG struct btree_keys *b; #endif - MIN_HEAP_PREALLOCATED(struct btree_iter_set, btree_iter_heap, MAX_BSETS) heap; + struct btree_iter_set { + struct bkey *k, *end; + } data[]; +}; + +/* 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]; }; typedef bool (*ptr_filter_fn)(struct btree_keys *b, const struct bkey *k); @@ -335,9 +340,9 @@ struct bkey *bch_btree_iter_next_filter(struct btree_iter *iter, void bch_btree_iter_push(struct btree_iter *iter, struct bkey *k, struct bkey *end); -struct bkey *bch_btree_iter_init(struct btree_keys *b, - struct btree_iter *iter, - struct bkey *search); +struct bkey *bch_btree_iter_stack_init(struct btree_keys *b, + struct btree_iter_stack *iter, + struct bkey *search); struct bkey *__bch_bset_search(struct btree_keys *b, struct bset_tree *t, const struct bkey *search); @@ -352,13 +357,14 @@ static inline struct bkey *bch_bset_search(struct btree_keys *b, return search ? __bch_bset_search(b, t, search) : t->data->start; } -#define for_each_key_filter(b, k, iter, filter) \ - for (bch_btree_iter_init((b), (iter), NULL); \ - ((k) = bch_btree_iter_next_filter((iter), (b), filter));) +#define for_each_key_filter(b, k, stack_iter, filter) \ + for (bch_btree_iter_stack_init((b), (stack_iter), NULL); \ + ((k) = bch_btree_iter_next_filter(&((stack_iter)->iter), (b), \ + filter));) -#define for_each_key(b, k, iter) \ - for (bch_btree_iter_init((b), (iter), NULL); \ - ((k) = bch_btree_iter_next(iter));) +#define for_each_key(b, k, stack_iter) \ + for (bch_btree_iter_stack_init((b), (stack_iter), NULL); \ + ((k) = bch_btree_iter_next(&((stack_iter)->iter)));) /* Sorting */ diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c index ed40d8600656..4e6ccf2c8a0b 100644 --- a/drivers/md/bcache/btree.c +++ b/drivers/md/bcache/btree.c @@ -149,19 +149,19 @@ void bch_btree_node_read_done(struct btree *b) { const char *err = "bad btree header"; struct bset *i = btree_bset_first(b); - struct btree_iter iter; + struct btree_iter *iter; /* * c->fill_iter can allocate an iterator with more memory space * than static MAX_BSETS. * See the comment arount cache_set->fill_iter. */ - iter.heap.data = mempool_alloc(&b->c->fill_iter, GFP_NOIO); - iter.heap.size = b->c->cache->sb.bucket_size / b->c->cache->sb.block_size; - iter.heap.nr = 0; + iter = mempool_alloc(&b->c->fill_iter, GFP_NOIO); + iter->size = b->c->cache->sb.bucket_size / b->c->cache->sb.block_size; + iter->used = 0; #ifdef CONFIG_BCACHE_DEBUG - iter.b = &b->keys; + iter->b = &b->keys; #endif if (!i->seq) @@ -199,7 +199,7 @@ void bch_btree_node_read_done(struct btree *b) if (i != b->keys.set[0].data && !i->keys) goto err; - bch_btree_iter_push(&iter, i->start, bset_bkey_last(i)); + bch_btree_iter_push(iter, i->start, bset_bkey_last(i)); b->written += set_blocks(i, block_bytes(b->c->cache)); } @@ -211,7 +211,7 @@ void bch_btree_node_read_done(struct btree *b) if (i->seq == b->keys.set[0].data->seq) goto err; - bch_btree_sort_and_fix_extents(&b->keys, &iter, &b->c->sort); + bch_btree_sort_and_fix_extents(&b->keys, iter, &b->c->sort); i = b->keys.set[0].data; err = "short btree key"; @@ -223,7 +223,7 @@ void bch_btree_node_read_done(struct btree *b) bch_bset_init_next(&b->keys, write_block(b), bset_magic(&b->c->cache->sb)); out: - mempool_free(iter.heap.data, &b->c->fill_iter); + mempool_free(iter, &b->c->fill_iter); return; err: set_btree_node_io_error(b); @@ -1309,11 +1309,9 @@ static bool btree_gc_mark_node(struct btree *b, struct gc_stat *gc) uint8_t stale = 0; unsigned int keys = 0, good_keys = 0; struct bkey *k; - struct btree_iter iter; + struct btree_iter_stack iter; struct bset_tree *t; - min_heap_init(&iter.heap, NULL, MAX_BSETS); - gc->nodes++; for_each_key_filter(&b->keys, k, &iter, bch_ptr_invalid) { @@ -1572,11 +1570,9 @@ static int btree_gc_rewrite_node(struct btree *b, struct btree_op *op, static unsigned int btree_gc_count_keys(struct btree *b) { struct bkey *k; - struct btree_iter iter; + struct btree_iter_stack iter; unsigned int ret = 0; - min_heap_init(&iter.heap, NULL, MAX_BSETS); - for_each_key_filter(&b->keys, k, &iter, bch_ptr_bad) ret += bkey_u64s(k); @@ -1615,18 +1611,18 @@ static int btree_gc_recurse(struct btree *b, struct btree_op *op, int ret = 0; bool should_rewrite; struct bkey *k; - struct btree_iter iter; + struct btree_iter_stack iter; struct gc_merge_info r[GC_MERGE_NODES]; struct gc_merge_info *i, *last = r + ARRAY_SIZE(r) - 1; - min_heap_init(&iter.heap, NULL, MAX_BSETS); - bch_btree_iter_init(&b->keys, &iter, &b->c->gc_done); + bch_btree_iter_stack_init(&b->keys, &iter, &b->c->gc_done); for (i = r; i < r + ARRAY_SIZE(r); i++) i->b = ERR_PTR(-EINTR); while (1) { - k = bch_btree_iter_next_filter(&iter, &b->keys, bch_ptr_bad); + k = bch_btree_iter_next_filter(&iter.iter, &b->keys, + bch_ptr_bad); if (k) { r->b = bch_btree_node_get(b->c, op, k, b->level - 1, true, b); @@ -1921,9 +1917,7 @@ static int bch_btree_check_recurse(struct btree *b, struct btree_op *op) { int ret = 0; struct bkey *k, *p = NULL; - struct btree_iter iter; - - min_heap_init(&iter.heap, NULL, MAX_BSETS); + struct btree_iter_stack iter; for_each_key_filter(&b->keys, k, &iter, bch_ptr_invalid) bch_initial_mark_key(b->c, b->level, k); @@ -1931,10 +1925,10 @@ static int bch_btree_check_recurse(struct btree *b, struct btree_op *op) bch_initial_mark_key(b->c, b->level + 1, &b->key); if (b->level) { - bch_btree_iter_init(&b->keys, &iter, NULL); + bch_btree_iter_stack_init(&b->keys, &iter, NULL); do { - k = bch_btree_iter_next_filter(&iter, &b->keys, + k = bch_btree_iter_next_filter(&iter.iter, &b->keys, bch_ptr_bad); if (k) { btree_node_prefetch(b, k); @@ -1962,7 +1956,7 @@ static int bch_btree_check_thread(void *arg) struct btree_check_info *info = arg; struct btree_check_state *check_state = info->state; struct cache_set *c = check_state->c; - struct btree_iter iter; + struct btree_iter_stack iter; struct bkey *k, *p; int cur_idx, prev_idx, skip_nr; @@ -1970,11 +1964,9 @@ static int bch_btree_check_thread(void *arg) cur_idx = prev_idx = 0; ret = 0; - min_heap_init(&iter.heap, NULL, MAX_BSETS); - /* root node keys are checked before thread created */ - bch_btree_iter_init(&c->root->keys, &iter, NULL); - k = bch_btree_iter_next_filter(&iter, &c->root->keys, bch_ptr_bad); + bch_btree_iter_stack_init(&c->root->keys, &iter, NULL); + k = bch_btree_iter_next_filter(&iter.iter, &c->root->keys, bch_ptr_bad); BUG_ON(!k); p = k; @@ -1992,7 +1984,7 @@ static int bch_btree_check_thread(void *arg) skip_nr = cur_idx - prev_idx; while (skip_nr) { - k = bch_btree_iter_next_filter(&iter, + k = bch_btree_iter_next_filter(&iter.iter, &c->root->keys, bch_ptr_bad); if (k) @@ -2065,11 +2057,9 @@ int bch_btree_check(struct cache_set *c) int ret = 0; int i; struct bkey *k = NULL; - struct btree_iter iter; + struct btree_iter_stack iter; struct btree_check_state check_state; - min_heap_init(&iter.heap, NULL, MAX_BSETS); - /* check and mark root node keys */ for_each_key_filter(&c->root->keys, k, &iter, bch_ptr_invalid) bch_initial_mark_key(c, c->root->level, k); @@ -2563,12 +2553,11 @@ static int bch_btree_map_nodes_recurse(struct btree *b, struct btree_op *op, if (b->level) { struct bkey *k; - struct btree_iter iter; + struct btree_iter_stack iter; - min_heap_init(&iter.heap, NULL, MAX_BSETS); - bch_btree_iter_init(&b->keys, &iter, from); + bch_btree_iter_stack_init(&b->keys, &iter, from); - while ((k = bch_btree_iter_next_filter(&iter, &b->keys, + while ((k = bch_btree_iter_next_filter(&iter.iter, &b->keys, bch_ptr_bad))) { ret = bcache_btree(map_nodes_recurse, k, b, op, from, fn, flags); @@ -2597,12 +2586,12 @@ int bch_btree_map_keys_recurse(struct btree *b, struct btree_op *op, { int ret = MAP_CONTINUE; struct bkey *k; - struct btree_iter iter; + struct btree_iter_stack iter; - min_heap_init(&iter.heap, NULL, MAX_BSETS); - bch_btree_iter_init(&b->keys, &iter, from); + bch_btree_iter_stack_init(&b->keys, &iter, from); - while ((k = bch_btree_iter_next_filter(&iter, &b->keys, bch_ptr_bad))) { + while ((k = bch_btree_iter_next_filter(&iter.iter, &b->keys, + bch_ptr_bad))) { ret = !b->level ? fn(op, b, k) : bcache_btree(map_keys_recurse, k, diff --git a/drivers/md/bcache/extents.c b/drivers/md/bcache/extents.c index a7221e5dbe81..d626ffcbecb9 100644 --- a/drivers/md/bcache/extents.c +++ b/drivers/md/bcache/extents.c @@ -33,16 +33,15 @@ static void sort_key_next(struct btree_iter *iter, i->k = bkey_next(i->k); if (i->k == i->end) - *i = iter->heap.data[--iter->heap.nr]; + *i = iter->data[--iter->used]; } -static bool new_bch_key_sort_cmp(const void *l, const void *r, void *args) +static bool bch_key_sort_cmp(struct btree_iter_set l, + struct btree_iter_set r) { - struct btree_iter_set *_l = (struct btree_iter_set *)l; - struct btree_iter_set *_r = (struct btree_iter_set *)r; - int64_t c = bkey_cmp(_l->k, _r->k); + int64_t c = bkey_cmp(l.k, r.k); - return !(c ? c > 0 : _l->k < _r->k); + return c ? c > 0 : l.k < r.k; } static bool __ptr_invalid(struct cache_set *c, const struct bkey *k) @@ -239,7 +238,7 @@ static bool bch_btree_ptr_insert_fixup(struct btree_keys *bk, } const struct btree_keys_ops bch_btree_keys_ops = { - .sort_cmp = new_bch_key_sort_cmp, + .sort_cmp = bch_key_sort_cmp, .insert_fixup = bch_btree_ptr_insert_fixup, .key_invalid = bch_btree_ptr_invalid, .key_bad = bch_btree_ptr_bad, @@ -256,36 +255,22 @@ const struct btree_keys_ops bch_btree_keys_ops = { * Necessary for btree_sort_fixup() - if there are multiple keys that compare * equal in different sets, we have to process them newest to oldest. */ - -static bool new_bch_extent_sort_cmp(const void *l, const void *r, void __always_unused *args) -{ - struct btree_iter_set *_l = (struct btree_iter_set *)l; - struct btree_iter_set *_r = (struct btree_iter_set *)r; - int64_t c = bkey_cmp(&START_KEY(_l->k), &START_KEY(_r->k)); - - return !(c ? c > 0 : _l->k < _r->k); -} - -static inline void new_btree_iter_swap(void *iter1, void *iter2, void __always_unused *args) +static bool bch_extent_sort_cmp(struct btree_iter_set l, + struct btree_iter_set r) { - struct btree_iter_set *_iter1 = iter1; - struct btree_iter_set *_iter2 = iter2; + int64_t c = bkey_cmp(&START_KEY(l.k), &START_KEY(r.k)); - swap(*_iter1, *_iter2); + return c ? c > 0 : l.k < r.k; } static struct bkey *bch_extent_sort_fixup(struct btree_iter *iter, struct bkey *tmp) { - const struct min_heap_callbacks callbacks = { - .less = new_bch_extent_sort_cmp, - .swp = new_btree_iter_swap, - }; - while (iter->heap.nr > 1) { - struct btree_iter_set *top = iter->heap.data, *i = top + 1; - - if (iter->heap.nr > 2 && - !new_bch_extent_sort_cmp(&i[0], &i[1], NULL)) + while (iter->used > 1) { + struct btree_iter_set *top = iter->data, *i = top + 1; + + if (iter->used > 2 && + bch_extent_sort_cmp(i[0], i[1])) i++; if (bkey_cmp(top->k, &START_KEY(i->k)) <= 0) @@ -293,7 +278,7 @@ static struct bkey *bch_extent_sort_fixup(struct btree_iter *iter, if (!KEY_SIZE(i->k)) { sort_key_next(iter, i); - min_heap_sift_down(&iter->heap, i - top, &callbacks, NULL); + heap_sift(iter, i - top, bch_extent_sort_cmp); continue; } @@ -303,7 +288,7 @@ static struct bkey *bch_extent_sort_fixup(struct btree_iter *iter, else bch_cut_front(top->k, i->k); - min_heap_sift_down(&iter->heap, i - top, &callbacks, NULL); + heap_sift(iter, i - top, bch_extent_sort_cmp); } else { /* can't happen because of comparison func */ BUG_ON(!bkey_cmp(&START_KEY(top->k), &START_KEY(i->k))); @@ -313,7 +298,7 @@ static struct bkey *bch_extent_sort_fixup(struct btree_iter *iter, bch_cut_back(&START_KEY(i->k), tmp); bch_cut_front(i->k, top->k); - min_heap_sift_down(&iter->heap, 0, &callbacks, NULL); + heap_sift(iter, 0, bch_extent_sort_cmp); return tmp; } else { @@ -633,7 +618,7 @@ static bool bch_extent_merge(struct btree_keys *bk, } const struct btree_keys_ops bch_extent_keys_ops = { - .sort_cmp = new_bch_extent_sort_cmp, + .sort_cmp = bch_extent_sort_cmp, .sort_fixup = bch_extent_sort_fixup, .insert_fixup = bch_extent_insert_fixup, .key_invalid = bch_extent_invalid, diff --git a/drivers/md/bcache/movinggc.c b/drivers/md/bcache/movinggc.c index 7f482729c56d..ebd500bdf0b2 100644 --- a/drivers/md/bcache/movinggc.c +++ b/drivers/md/bcache/movinggc.c @@ -182,27 +182,16 @@ err: if (!IS_ERR_OR_NULL(w->private)) closure_sync(&cl); } -static bool new_bucket_cmp(const void *l, const void *r, void __always_unused *args) +static bool bucket_cmp(struct bucket *l, struct bucket *r) { - struct bucket **_l = (struct bucket **)l; - struct bucket **_r = (struct bucket **)r; - - return GC_SECTORS_USED(*_l) >= GC_SECTORS_USED(*_r); -} - -static void new_bucket_swap(void *l, void *r, void __always_unused *args) -{ - struct bucket **_l = l; - struct bucket **_r = r; - - swap(*_l, *_r); + return GC_SECTORS_USED(l) < GC_SECTORS_USED(r); } static unsigned int bucket_heap_top(struct cache *ca) { struct bucket *b; - return (b = min_heap_peek(&ca->heap)[0]) ? GC_SECTORS_USED(b) : 0; + return (b = heap_peek(&ca->heap)) ? GC_SECTORS_USED(b) : 0; } void bch_moving_gc(struct cache_set *c) @@ -210,10 +199,6 @@ void bch_moving_gc(struct cache_set *c) struct cache *ca = c->cache; struct bucket *b; unsigned long sectors_to_move, reserve_sectors; - const struct min_heap_callbacks callbacks = { - .less = new_bucket_cmp, - .swp = new_bucket_swap, - }; if (!c->copy_gc_enabled) return; @@ -224,7 +209,7 @@ void bch_moving_gc(struct cache_set *c) reserve_sectors = ca->sb.bucket_size * fifo_used(&ca->free[RESERVE_MOVINGGC]); - ca->heap.nr = 0; + ca->heap.used = 0; for_each_bucket(b, ca) { if (GC_MARK(b) == GC_MARK_METADATA || @@ -233,31 +218,25 @@ void bch_moving_gc(struct cache_set *c) atomic_read(&b->pin)) continue; - if (!min_heap_full(&ca->heap)) { + if (!heap_full(&ca->heap)) { sectors_to_move += GC_SECTORS_USED(b); - min_heap_push(&ca->heap, &b, &callbacks, NULL); - } else if (!new_bucket_cmp(&b, min_heap_peek(&ca->heap), ca)) { + heap_add(&ca->heap, b, bucket_cmp); + } else if (bucket_cmp(b, heap_peek(&ca->heap))) { sectors_to_move -= bucket_heap_top(ca); sectors_to_move += GC_SECTORS_USED(b); ca->heap.data[0] = b; - min_heap_sift_down(&ca->heap, 0, &callbacks, NULL); + heap_sift(&ca->heap, 0, bucket_cmp); } } while (sectors_to_move > reserve_sectors) { - if (ca->heap.nr) { - b = min_heap_peek(&ca->heap)[0]; - min_heap_pop(&ca->heap, &callbacks, NULL); - } + heap_pop(&ca->heap, b, bucket_cmp); sectors_to_move -= GC_SECTORS_USED(b); } - while (ca->heap.nr) { - b = min_heap_peek(&ca->heap)[0]; - min_heap_pop(&ca->heap, &callbacks, NULL); + while (heap_pop(&ca->heap, b, bucket_cmp)) SET_GC_MOVE(b, 1); - } mutex_unlock(&c->bucket_lock); diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index e42f1400cea9..1084b3f0dfe7 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -1733,7 +1733,12 @@ static CLOSURE_CALLBACK(cache_set_flush) mutex_unlock(&b->write_lock); } - if (ca->alloc_thread) + /* + * If the register_cache_set() call to bch_cache_set_alloc() failed, + * ca has not been assigned a value and return error. + * So we need check ca is not NULL during bch_cache_set_unregister(). + */ + if (ca && ca->alloc_thread) kthread_stop(ca->alloc_thread); if (c->journal.cur) { @@ -1907,7 +1912,8 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb) INIT_LIST_HEAD(&c->btree_cache_freed); INIT_LIST_HEAD(&c->data_buckets); - iter_size = ((meta_bucket_pages(sb) * PAGE_SECTORS) / sb->block_size) * + iter_size = sizeof(struct btree_iter) + + ((meta_bucket_pages(sb) * PAGE_SECTORS) / sb->block_size) * sizeof(struct btree_iter_set); c->devices = kcalloc(c->nr_uuids, sizeof(void *), GFP_KERNEL); diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c index e8f696cb58c0..826b14cae4e5 100644 --- a/drivers/md/bcache/sysfs.c +++ b/drivers/md/bcache/sysfs.c @@ -660,9 +660,7 @@ static unsigned int bch_root_usage(struct cache_set *c) unsigned int bytes = 0; struct bkey *k; struct btree *b; - struct btree_iter iter; - - min_heap_init(&iter.heap, NULL, MAX_BSETS); + struct btree_iter_stack iter; goto lock_root; diff --git a/drivers/md/bcache/util.h b/drivers/md/bcache/util.h index 539454d8e2d0..f61ab1bada6c 100644 --- a/drivers/md/bcache/util.h +++ b/drivers/md/bcache/util.h @@ -9,7 +9,6 @@ #include <linux/kernel.h> #include <linux/sched/clock.h> #include <linux/llist.h> -#include <linux/min_heap.h> #include <linux/ratelimit.h> #include <linux/vmalloc.h> #include <linux/workqueue.h> @@ -31,10 +30,16 @@ struct closure; #endif +#define DECLARE_HEAP(type, name) \ + struct { \ + size_t size, used; \ + type *data; \ + } name + #define init_heap(heap, _size, gfp) \ ({ \ size_t _bytes; \ - (heap)->nr = 0; \ + (heap)->used = 0; \ (heap)->size = (_size); \ _bytes = (heap)->size * sizeof(*(heap)->data); \ (heap)->data = kvmalloc(_bytes, (gfp) & GFP_KERNEL); \ @@ -47,6 +52,64 @@ do { \ (heap)->data = NULL; \ } while (0) +#define heap_swap(h, i, j) swap((h)->data[i], (h)->data[j]) + +#define heap_sift(h, i, cmp) \ +do { \ + size_t _r, _j = i; \ + \ + for (; _j * 2 + 1 < (h)->used; _j = _r) { \ + _r = _j * 2 + 1; \ + if (_r + 1 < (h)->used && \ + cmp((h)->data[_r], (h)->data[_r + 1])) \ + _r++; \ + \ + if (cmp((h)->data[_r], (h)->data[_j])) \ + break; \ + heap_swap(h, _r, _j); \ + } \ +} while (0) + +#define heap_sift_down(h, i, cmp) \ +do { \ + while (i) { \ + size_t p = (i - 1) / 2; \ + if (cmp((h)->data[i], (h)->data[p])) \ + break; \ + heap_swap(h, i, p); \ + i = p; \ + } \ +} while (0) + +#define heap_add(h, d, cmp) \ +({ \ + bool _r = !heap_full(h); \ + if (_r) { \ + size_t _i = (h)->used++; \ + (h)->data[_i] = d; \ + \ + heap_sift_down(h, _i, cmp); \ + heap_sift(h, _i, cmp); \ + } \ + _r; \ +}) + +#define heap_pop(h, d, cmp) \ +({ \ + bool _r = (h)->used; \ + if (_r) { \ + (d) = (h)->data[0]; \ + (h)->used--; \ + heap_swap(h, 0, (h)->used); \ + heap_sift(h, 0, cmp); \ + } \ + _r; \ +}) + +#define heap_peek(h) ((h)->used ? (h)->data[0] : NULL) + +#define heap_full(h) ((h)->used == (h)->size) + #define DECLARE_FIFO(type, name) \ struct { \ size_t front, back, size, mask; \ diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c index c1d28e365910..792e070ccf38 100644 --- a/drivers/md/bcache/writeback.c +++ b/drivers/md/bcache/writeback.c @@ -908,16 +908,15 @@ static int bch_dirty_init_thread(void *arg) struct dirty_init_thrd_info *info = arg; struct bch_dirty_init_state *state = info->state; struct cache_set *c = state->c; - struct btree_iter iter; + struct btree_iter_stack iter; struct bkey *k, *p; int cur_idx, prev_idx, skip_nr; k = p = NULL; prev_idx = 0; - min_heap_init(&iter.heap, NULL, MAX_BSETS); - bch_btree_iter_init(&c->root->keys, &iter, NULL); - k = bch_btree_iter_next_filter(&iter, &c->root->keys, bch_ptr_bad); + bch_btree_iter_stack_init(&c->root->keys, &iter, NULL); + k = bch_btree_iter_next_filter(&iter.iter, &c->root->keys, bch_ptr_bad); BUG_ON(!k); p = k; @@ -931,7 +930,7 @@ static int bch_dirty_init_thread(void *arg) skip_nr = cur_idx - prev_idx; while (skip_nr) { - k = bch_btree_iter_next_filter(&iter, + k = bch_btree_iter_next_filter(&iter.iter, &c->root->keys, bch_ptr_bad); if (k) @@ -980,13 +979,11 @@ void bch_sectors_dirty_init(struct bcache_device *d) int i; struct btree *b = NULL; struct bkey *k = NULL; - struct btree_iter iter; + struct btree_iter_stack iter; struct sectors_dirty_init op; struct cache_set *c = d->c; struct bch_dirty_init_state state; - min_heap_init(&iter.heap, NULL, MAX_BSETS); - retry_lock: b = c->root; rw_lock(0, b, b->level); diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index 23e0b71b991e..aaa21fe295f2 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -68,6 +68,8 @@ #define LIST_DIRTY 1 #define LIST_SIZE 2 +#define SCAN_RESCHED_CYCLE 16 + /*--------------------------------------------------------------*/ /* @@ -2414,7 +2416,12 @@ static void __scan(struct dm_bufio_client *c) atomic_long_dec(&c->need_shrink); freed++; - cond_resched(); + + if (unlikely(freed % SCAN_RESCHED_CYCLE == 0)) { + dm_bufio_unlock(c); + cond_resched(); + dm_bufio_lock(c); + } } } } @@ -2734,7 +2741,11 @@ static unsigned long __evict_many(struct dm_bufio_client *c, __make_buffer_clean(b); __free_buffer_wake(b); - cond_resched(); + if (need_resched()) { + dm_bufio_unlock(c); + cond_resched(); + dm_bufio_lock(c); + } } return count; diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index 849eb6333e98..6aa4095dc587 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -2899,6 +2899,27 @@ static dm_cblock_t get_cache_dev_size(struct cache *cache) return to_cblock(size); } +static bool can_resume(struct cache *cache) +{ + /* + * Disallow retrying the resume operation for devices that failed the + * first resume attempt, as the failure leaves the policy object partially + * initialized. Retrying could trigger BUG_ON when loading cache mappings + * into the incomplete policy object. + */ + if (cache->sized && !cache->loaded_mappings) { + if (get_cache_mode(cache) != CM_WRITE) + DMERR("%s: unable to resume a failed-loaded cache, please check metadata.", + cache_device_name(cache)); + else + DMERR("%s: unable to resume cache due to missing proper cache table reload", + cache_device_name(cache)); + return false; + } + + return true; +} + static bool can_resize(struct cache *cache, dm_cblock_t new_size) { if (from_cblock(new_size) > from_cblock(cache->cache_size)) { @@ -2947,6 +2968,9 @@ static int cache_preresume(struct dm_target *ti) struct cache *cache = ti->private; dm_cblock_t csize = get_cache_dev_size(cache); + if (!can_resume(cache)) + return -EINVAL; + /* * Check to see if the cache has resized. */ diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h index 3637761f3585..f3a3f2ef6322 100644 --- a/drivers/md/dm-core.h +++ b/drivers/md/dm-core.h @@ -141,6 +141,7 @@ struct mapped_device { #ifdef CONFIG_BLK_DEV_ZONED unsigned int nr_zones; void *zone_revalidate_map; + struct task_struct *revalidate_map_task; #endif #ifdef CONFIG_IMA diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 1ae2c71bb383..78c975d7cd5f 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -59,6 +59,7 @@ struct convert_context { struct bio *bio_out; struct bvec_iter iter_out; atomic_t cc_pending; + unsigned int tag_offset; u64 cc_sector; union { struct skcipher_request *req; @@ -1256,6 +1257,7 @@ static void crypt_convert_init(struct crypt_config *cc, if (bio_out) ctx->iter_out = bio_out->bi_iter; ctx->cc_sector = sector + cc->iv_offset; + ctx->tag_offset = 0; init_completion(&ctx->restart); } @@ -1588,7 +1590,6 @@ static void crypt_free_req(struct crypt_config *cc, void *req, struct bio *base_ static blk_status_t crypt_convert(struct crypt_config *cc, struct convert_context *ctx, bool atomic, bool reset_pending) { - unsigned int tag_offset = 0; unsigned int sector_step = cc->sector_size >> SECTOR_SHIFT; int r; @@ -1611,9 +1612,9 @@ static blk_status_t crypt_convert(struct crypt_config *cc, atomic_inc(&ctx->cc_pending); if (crypt_integrity_aead(cc)) - r = crypt_convert_block_aead(cc, ctx, ctx->r.req_aead, tag_offset); + r = crypt_convert_block_aead(cc, ctx, ctx->r.req_aead, ctx->tag_offset); else - r = crypt_convert_block_skcipher(cc, ctx, ctx->r.req, tag_offset); + r = crypt_convert_block_skcipher(cc, ctx, ctx->r.req, ctx->tag_offset); switch (r) { /* @@ -1633,8 +1634,8 @@ static blk_status_t crypt_convert(struct crypt_config *cc, * exit and continue processing in a workqueue */ ctx->r.req = NULL; + ctx->tag_offset++; ctx->cc_sector += sector_step; - tag_offset++; return BLK_STS_DEV_RESOURCE; } } else { @@ -1648,8 +1649,8 @@ static blk_status_t crypt_convert(struct crypt_config *cc, */ case -EINPROGRESS: ctx->r.req = NULL; + ctx->tag_offset++; ctx->cc_sector += sector_step; - tag_offset++; continue; /* * The request was already processed (synchronously). @@ -1657,7 +1658,7 @@ static blk_status_t crypt_convert(struct crypt_config *cc, case 0: atomic_dec(&ctx->cc_pending); ctx->cc_sector += sector_step; - tag_offset++; + ctx->tag_offset++; if (!atomic) cond_resched(); continue; @@ -2092,7 +2093,6 @@ static void kcryptd_crypt_write_continue(struct work_struct *work) struct crypt_config *cc = io->cc; struct convert_context *ctx = &io->ctx; int crypt_finished; - sector_t sector = io->sector; blk_status_t r; wait_for_completion(&ctx->restart); @@ -2109,10 +2109,8 @@ static void kcryptd_crypt_write_continue(struct work_struct *work) } /* Encryption was already finished, submit io now */ - if (crypt_finished) { + if (crypt_finished) kcryptd_crypt_write_io_submit(io, 0); - io->sector = sector; - } crypt_dec_pending(io); } @@ -2123,14 +2121,13 @@ static void kcryptd_crypt_write_convert(struct dm_crypt_io *io) struct convert_context *ctx = &io->ctx; struct bio *clone; int crypt_finished; - sector_t sector = io->sector; blk_status_t r; /* * Prevent io from disappearing until this function completes. */ crypt_inc_pending(io); - crypt_convert_init(cc, ctx, NULL, io->base_bio, sector); + crypt_convert_init(cc, ctx, NULL, io->base_bio, io->sector); clone = crypt_alloc_buffer(io, io->base_bio->bi_iter.bi_size); if (unlikely(!clone)) { @@ -2147,8 +2144,6 @@ static void kcryptd_crypt_write_convert(struct dm_crypt_io *io) io->ctx.iter_in = clone->bi_iter; } - sector += bio_sectors(clone); - crypt_inc_pending(io); r = crypt_convert(cc, ctx, test_bit(DM_CRYPT_NO_WRITE_WORKQUEUE, &cc->flags), true); @@ -2172,10 +2167,8 @@ static void kcryptd_crypt_write_convert(struct dm_crypt_io *io) } /* Encryption was already finished, submit io now */ - if (crypt_finished) { + if (crypt_finished) kcryptd_crypt_write_io_submit(io, 0); - io->sector = sector; - } dec: crypt_dec_pending(io); diff --git a/drivers/md/dm-ebs-target.c b/drivers/md/dm-ebs-target.c index 18ae45dcbfb2..b19b0142a690 100644 --- a/drivers/md/dm-ebs-target.c +++ b/drivers/md/dm-ebs-target.c @@ -390,6 +390,12 @@ static int ebs_map(struct dm_target *ti, struct bio *bio) return DM_MAPIO_REMAPPED; } +static void ebs_postsuspend(struct dm_target *ti) +{ + struct ebs_c *ec = ti->private; + dm_bufio_client_reset(ec->bufio); +} + static void ebs_status(struct dm_target *ti, status_type_t type, unsigned int status_flags, char *result, unsigned int maxlen) { @@ -447,6 +453,7 @@ static struct target_type ebs_target = { .ctr = ebs_ctr, .dtr = ebs_dtr, .map = ebs_map, + .postsuspend = ebs_postsuspend, .status = ebs_status, .io_hints = ebs_io_hints, .prepare_ioctl = ebs_prepare_ioctl, diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c index 731467d4ed10..347881f323d5 100644 --- a/drivers/md/dm-flakey.c +++ b/drivers/md/dm-flakey.c @@ -47,14 +47,15 @@ enum feature_flag_bits { }; struct per_bio_data { - bool bio_submitted; + bool bio_can_corrupt; + struct bvec_iter saved_iter; }; static int parse_features(struct dm_arg_set *as, struct flakey_c *fc, struct dm_target *ti) { - int r; - unsigned int argc; + int r = 0; + unsigned int argc = 0; const char *arg_name; static const struct dm_arg _args[] = { @@ -65,14 +66,13 @@ static int parse_features(struct dm_arg_set *as, struct flakey_c *fc, {0, PROBABILITY_BASE, "Invalid random corrupt argument"}, }; - /* No feature arguments supplied. */ - if (!as->argc) - return 0; - - r = dm_read_arg_group(_args, as, &argc, &ti->error); - if (r) + if (as->argc && (r = dm_read_arg_group(_args, as, &argc, &ti->error))) return r; + /* No feature arguments supplied. */ + if (!argc) + goto error_all_io; + while (argc) { arg_name = dm_shift_arg(as); argc--; @@ -217,6 +217,7 @@ static int parse_features(struct dm_arg_set *as, struct flakey_c *fc, if (!fc->corrupt_bio_byte && !test_bit(ERROR_READS, &fc->flags) && !test_bit(DROP_WRITES, &fc->flags) && !test_bit(ERROR_WRITES, &fc->flags) && !fc->random_read_corrupt && !fc->random_write_corrupt) { +error_all_io: set_bit(ERROR_WRITES, &fc->flags); set_bit(ERROR_READS, &fc->flags); } @@ -339,7 +340,8 @@ static void flakey_map_bio(struct dm_target *ti, struct bio *bio) } static void corrupt_bio_common(struct bio *bio, unsigned int corrupt_bio_byte, - unsigned char corrupt_bio_value) + unsigned char corrupt_bio_value, + struct bvec_iter start) { struct bvec_iter iter; struct bio_vec bvec; @@ -348,7 +350,7 @@ static void corrupt_bio_common(struct bio *bio, unsigned int corrupt_bio_byte, * Overwrite the Nth byte of the bio's data, on whichever page * it falls. */ - bio_for_each_segment(bvec, bio, iter) { + __bio_for_each_segment(bvec, bio, iter, start) { if (bio_iter_len(bio, iter) > corrupt_bio_byte) { unsigned char *segment = bvec_kmap_local(&bvec); segment[corrupt_bio_byte] = corrupt_bio_value; @@ -357,36 +359,31 @@ static void corrupt_bio_common(struct bio *bio, unsigned int corrupt_bio_byte, "(rw=%c bi_opf=%u bi_sector=%llu size=%u)\n", bio, corrupt_bio_value, corrupt_bio_byte, (bio_data_dir(bio) == WRITE) ? 'w' : 'r', bio->bi_opf, - (unsigned long long)bio->bi_iter.bi_sector, - bio->bi_iter.bi_size); + (unsigned long long)start.bi_sector, + start.bi_size); break; } corrupt_bio_byte -= bio_iter_len(bio, iter); } } -static void corrupt_bio_data(struct bio *bio, struct flakey_c *fc) +static void corrupt_bio_data(struct bio *bio, struct flakey_c *fc, + struct bvec_iter start) { unsigned int corrupt_bio_byte = fc->corrupt_bio_byte - 1; - if (!bio_has_data(bio)) - return; - - corrupt_bio_common(bio, corrupt_bio_byte, fc->corrupt_bio_value); + corrupt_bio_common(bio, corrupt_bio_byte, fc->corrupt_bio_value, start); } -static void corrupt_bio_random(struct bio *bio) +static void corrupt_bio_random(struct bio *bio, struct bvec_iter start) { unsigned int corrupt_byte; unsigned char corrupt_value; - if (!bio_has_data(bio)) - return; - - corrupt_byte = get_random_u32() % bio->bi_iter.bi_size; + corrupt_byte = get_random_u32() % start.bi_size; corrupt_value = get_random_u8(); - corrupt_bio_common(bio, corrupt_byte, corrupt_value); + corrupt_bio_common(bio, corrupt_byte, corrupt_value, start); } static void clone_free(struct bio *clone) @@ -426,7 +423,7 @@ static struct bio *clone_bio(struct dm_target *ti, struct flakey_c *fc, struct b if (!clone) return NULL; - bio_init(clone, fc->dev->bdev, bio->bi_inline_vecs, nr_iovecs, bio->bi_opf); + bio_init(clone, fc->dev->bdev, clone->bi_inline_vecs, nr_iovecs, bio->bi_opf); clone->bi_iter.bi_sector = flakey_map_sector(ti, bio->bi_iter.bi_sector); clone->bi_private = bio; @@ -481,7 +478,7 @@ static int flakey_map(struct dm_target *ti, struct bio *bio) unsigned int elapsed; struct per_bio_data *pb = dm_per_bio_data(bio, sizeof(struct per_bio_data)); - pb->bio_submitted = false; + pb->bio_can_corrupt = false; if (op_is_zone_mgmt(bio_op(bio))) goto map_bio; @@ -490,10 +487,11 @@ static int flakey_map(struct dm_target *ti, struct bio *bio) elapsed = (jiffies - fc->start_time) / HZ; if (elapsed % (fc->up_interval + fc->down_interval) >= fc->up_interval) { bool corrupt_fixed, corrupt_random; - /* - * Flag this bio as submitted while down. - */ - pb->bio_submitted = true; + + if (bio_has_data(bio)) { + pb->bio_can_corrupt = true; + pb->saved_iter = bio->bi_iter; + } /* * Error reads if neither corrupt_bio_byte or drop_writes or error_writes are set. @@ -516,6 +514,8 @@ static int flakey_map(struct dm_target *ti, struct bio *bio) return DM_MAPIO_SUBMITTED; } + if (!pb->bio_can_corrupt) + goto map_bio; /* * Corrupt matching writes. */ @@ -535,9 +535,11 @@ static int flakey_map(struct dm_target *ti, struct bio *bio) struct bio *clone = clone_bio(ti, fc, bio); if (clone) { if (corrupt_fixed) - corrupt_bio_data(clone, fc); + corrupt_bio_data(clone, fc, + clone->bi_iter); if (corrupt_random) - corrupt_bio_random(clone); + corrupt_bio_random(clone, + clone->bi_iter); submit_bio(clone); return DM_MAPIO_SUBMITTED; } @@ -559,21 +561,21 @@ static int flakey_end_io(struct dm_target *ti, struct bio *bio, if (op_is_zone_mgmt(bio_op(bio))) return DM_ENDIO_DONE; - if (!*error && pb->bio_submitted && (bio_data_dir(bio) == READ)) { + if (!*error && pb->bio_can_corrupt && (bio_data_dir(bio) == READ)) { if (fc->corrupt_bio_byte) { if ((fc->corrupt_bio_rw == READ) && all_corrupt_bio_flags_match(bio, fc)) { /* * Corrupt successful matching READs while in down state. */ - corrupt_bio_data(bio, fc); + corrupt_bio_data(bio, fc, pb->saved_iter); } } if (fc->random_read_corrupt) { u64 rnd = get_random_u64(); u32 rem = do_div(rnd, PROBABILITY_BASE); if (rem < fc->random_read_corrupt) - corrupt_bio_random(bio); + corrupt_bio_random(bio, pb->saved_iter); } if (test_bit(ERROR_READS, &fc->flags)) { /* diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index ee9f7cecd78e..450e1a7e7bac 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -21,6 +21,7 @@ #include <linux/reboot.h> #include <crypto/hash.h> #include <crypto/skcipher.h> +#include <crypto/utils.h> #include <linux/async_tx.h> #include <linux/dm-bufio.h> @@ -516,7 +517,7 @@ static int sb_mac(struct dm_integrity_c *ic, bool wr) dm_integrity_io_error(ic, "crypto_shash_digest", r); return r; } - if (memcmp(mac, actual_mac, mac_size)) { + if (crypto_memneq(mac, actual_mac, mac_size)) { dm_integrity_io_error(ic, "superblock mac", -EILSEQ); dm_audit_log_target(DM_MSG_PREFIX, "mac-superblock", ic->ti, 0); return -EILSEQ; @@ -859,7 +860,7 @@ static void rw_section_mac(struct dm_integrity_c *ic, unsigned int section, bool if (likely(wr)) memcpy(&js->mac, result + (j * JOURNAL_MAC_PER_SECTOR), JOURNAL_MAC_PER_SECTOR); else { - if (memcmp(&js->mac, result + (j * JOURNAL_MAC_PER_SECTOR), JOURNAL_MAC_PER_SECTOR)) { + if (crypto_memneq(&js->mac, result + (j * JOURNAL_MAC_PER_SECTOR), JOURNAL_MAC_PER_SECTOR)) { dm_integrity_io_error(ic, "journal mac", -EILSEQ); dm_audit_log_target(DM_MSG_PREFIX, "mac-journal", ic->ti, 0); } @@ -1401,10 +1402,9 @@ static bool find_newer_committed_node(struct dm_integrity_c *ic, struct journal_ static int dm_integrity_rw_tag(struct dm_integrity_c *ic, unsigned char *tag, sector_t *metadata_block, unsigned int *metadata_offset, unsigned int total_size, int op) { -#define MAY_BE_FILLER 1 -#define MAY_BE_HASH 2 unsigned int hash_offset = 0; - unsigned int may_be = MAY_BE_HASH | (ic->discard ? MAY_BE_FILLER : 0); + unsigned char mismatch_hash = 0; + unsigned char mismatch_filler = !ic->discard; do { unsigned char *data, *dp; @@ -1425,7 +1425,7 @@ static int dm_integrity_rw_tag(struct dm_integrity_c *ic, unsigned char *tag, se if (op == TAG_READ) { memcpy(tag, dp, to_copy); } else if (op == TAG_WRITE) { - if (memcmp(dp, tag, to_copy)) { + if (crypto_memneq(dp, tag, to_copy)) { memcpy(dp, tag, to_copy); dm_bufio_mark_partial_buffer_dirty(b, *metadata_offset, *metadata_offset + to_copy); } @@ -1433,29 +1433,30 @@ static int dm_integrity_rw_tag(struct dm_integrity_c *ic, unsigned char *tag, se /* e.g.: op == TAG_CMP */ if (likely(is_power_of_2(ic->tag_size))) { - if (unlikely(memcmp(dp, tag, to_copy))) - if (unlikely(!ic->discard) || - unlikely(memchr_inv(dp, DISCARD_FILLER, to_copy) != NULL)) { - goto thorough_test; - } + if (unlikely(crypto_memneq(dp, tag, to_copy))) + goto thorough_test; } else { unsigned int i, ts; thorough_test: ts = total_size; for (i = 0; i < to_copy; i++, ts--) { - if (unlikely(dp[i] != tag[i])) - may_be &= ~MAY_BE_HASH; - if (likely(dp[i] != DISCARD_FILLER)) - may_be &= ~MAY_BE_FILLER; + /* + * Warning: the control flow must not be + * dependent on match/mismatch of + * individual bytes. + */ + mismatch_hash |= dp[i] ^ tag[i]; + mismatch_filler |= dp[i] ^ DISCARD_FILLER; hash_offset++; if (unlikely(hash_offset == ic->tag_size)) { - if (unlikely(!may_be)) { + if (unlikely(mismatch_hash) && unlikely(mismatch_filler)) { dm_bufio_release(b); return ts; } hash_offset = 0; - may_be = MAY_BE_HASH | (ic->discard ? MAY_BE_FILLER : 0); + mismatch_hash = 0; + mismatch_filler = !ic->discard; } } } @@ -1476,8 +1477,6 @@ thorough_test: } while (unlikely(total_size)); return 0; -#undef MAY_BE_FILLER -#undef MAY_BE_HASH } struct flush_request { @@ -2076,7 +2075,7 @@ retry_kmap: char checksums_onstack[MAX_T(size_t, HASH_MAX_DIGESTSIZE, MAX_TAG_SIZE)]; integrity_sector_checksum(ic, logical_sector, mem + bv.bv_offset, checksums_onstack); - if (unlikely(memcmp(checksums_onstack, journal_entry_tag(ic, je), ic->tag_size))) { + if (unlikely(crypto_memneq(checksums_onstack, journal_entry_tag(ic, je), ic->tag_size))) { DMERR_LIMIT("Checksum failed when reading from journal, at sector 0x%llx", logical_sector); dm_audit_log_bio(DM_MSG_PREFIX, "journal-checksum", @@ -2595,7 +2594,7 @@ static void dm_integrity_inline_recheck(struct work_struct *w) bio_put(outgoing_bio); integrity_sector_checksum(ic, dio->bio_details.bi_iter.bi_sector, outgoing_data, digest); - if (unlikely(memcmp(digest, dio->integrity_payload, min(crypto_shash_digestsize(ic->internal_hash), ic->tag_size)))) { + if (unlikely(crypto_memneq(digest, dio->integrity_payload, min(crypto_shash_digestsize(ic->internal_hash), ic->tag_size)))) { DMERR_LIMIT("%pg: Checksum failed at sector 0x%llx", ic->dev->bdev, dio->bio_details.bi_iter.bi_sector); atomic64_inc(&ic->number_of_mismatches); @@ -2634,7 +2633,7 @@ static int dm_integrity_end_io(struct dm_target *ti, struct bio *bio, blk_status char *mem = bvec_kmap_local(&bv); //memset(mem, 0xff, ic->sectors_per_block << SECTOR_SHIFT); integrity_sector_checksum(ic, dio->bio_details.bi_iter.bi_sector, mem, digest); - if (unlikely(memcmp(digest, dio->integrity_payload + pos, + if (unlikely(crypto_memneq(digest, dio->integrity_payload + pos, min(crypto_shash_digestsize(ic->internal_hash), ic->tag_size)))) { kunmap_local(mem); dm_integrity_free_payload(dio); @@ -2911,7 +2910,7 @@ static void do_journal_write(struct dm_integrity_c *ic, unsigned int write_start integrity_sector_checksum(ic, sec + ((l - j) << ic->sb->log2_sectors_per_block), (char *)access_journal_data(ic, i, l), test_tag); - if (unlikely(memcmp(test_tag, journal_entry_tag(ic, je2), ic->tag_size))) { + if (unlikely(crypto_memneq(test_tag, journal_entry_tag(ic, je2), ic->tag_size))) { dm_integrity_io_error(ic, "tag mismatch when replaying journal", -EILSEQ); dm_audit_log_target(DM_MSG_PREFIX, "integrity-replay-journal", ic->ti, 0); } @@ -3790,10 +3789,6 @@ static void dm_integrity_status(struct dm_target *ti, status_type_t type, break; case STATUSTYPE_TABLE: { - __u64 watermark_percentage = (__u64)(ic->journal_entries - ic->free_sectors_threshold) * 100; - - watermark_percentage += ic->journal_entries / 2; - do_div(watermark_percentage, ic->journal_entries); arg_count = 3; arg_count += !!ic->meta_dev; arg_count += ic->sectors_per_block != 1; @@ -3826,6 +3821,10 @@ static void dm_integrity_status(struct dm_target *ti, status_type_t type, DMEMIT(" interleave_sectors:%u", 1U << ic->sb->log2_interleave_sectors); DMEMIT(" buffer_sectors:%u", 1U << ic->log2_buffer_sectors); if (ic->mode == 'J') { + __u64 watermark_percentage = (__u64)(ic->journal_entries - ic->free_sectors_threshold) * 100; + + watermark_percentage += ic->journal_entries / 2; + do_div(watermark_percentage, ic->journal_entries); DMEMIT(" journal_watermark:%u", (unsigned int)watermark_percentage); DMEMIT(" commit_time:%u", ic->autocommit_msec); } @@ -5081,16 +5080,19 @@ try_smaller_buffer: ic->recalc_bitmap = dm_integrity_alloc_page_list(n_bitmap_pages); if (!ic->recalc_bitmap) { + ti->error = "Could not allocate memory for bitmap"; r = -ENOMEM; goto bad; } ic->may_write_bitmap = dm_integrity_alloc_page_list(n_bitmap_pages); if (!ic->may_write_bitmap) { + ti->error = "Could not allocate memory for bitmap"; r = -ENOMEM; goto bad; } ic->bbs = kvmalloc_array(ic->n_bitmap_blocks, sizeof(struct bitmap_block_status), GFP_KERNEL); if (!ic->bbs) { + ti->error = "Could not allocate memory for bitmap"; r = -ENOMEM; goto bad; } @@ -5171,7 +5173,7 @@ static void dm_integrity_dtr(struct dm_target *ti) BUG_ON(!RB_EMPTY_ROOT(&ic->in_progress)); BUG_ON(!list_empty(&ic->wait_list)); - if (ic->mode == 'B') + if (ic->mode == 'B' && ic->bitmap_flush_work.work.func) cancel_delayed_work_sync(&ic->bitmap_flush_work); if (ic->metadata_wq) destroy_workqueue(ic->metadata_wq); diff --git a/drivers/md/dm-ps-historical-service-time.c b/drivers/md/dm-ps-historical-service-time.c index b49e10d76d03..2c8626a83de4 100644 --- a/drivers/md/dm-ps-historical-service-time.c +++ b/drivers/md/dm-ps-historical-service-time.c @@ -541,8 +541,10 @@ static int __init dm_hst_init(void) { int r = dm_register_path_selector(&hst_ps); - if (r < 0) + if (r < 0) { DMERR("register failed %d", r); + return r; + } DMINFO("version " HST_VERSION " loaded"); diff --git a/drivers/md/dm-ps-queue-length.c b/drivers/md/dm-ps-queue-length.c index e305f05ad1e5..eb543e6431e0 100644 --- a/drivers/md/dm-ps-queue-length.c +++ b/drivers/md/dm-ps-queue-length.c @@ -260,8 +260,10 @@ static int __init dm_ql_init(void) { int r = dm_register_path_selector(&ql_ps); - if (r < 0) + if (r < 0) { DMERR("register failed %d", r); + return r; + } DMINFO("version " QL_VERSION " loaded"); diff --git a/drivers/md/dm-ps-round-robin.c b/drivers/md/dm-ps-round-robin.c index d1745b123dc1..66a15ac0c22c 100644 --- a/drivers/md/dm-ps-round-robin.c +++ b/drivers/md/dm-ps-round-robin.c @@ -220,8 +220,10 @@ static int __init dm_rr_init(void) { int r = dm_register_path_selector(&rr_ps); - if (r < 0) + if (r < 0) { DMERR("register failed %d", r); + return r; + } DMINFO("version " RR_VERSION " loaded"); diff --git a/drivers/md/dm-ps-service-time.c b/drivers/md/dm-ps-service-time.c index 969d31c40272..f8c43aecdb27 100644 --- a/drivers/md/dm-ps-service-time.c +++ b/drivers/md/dm-ps-service-time.c @@ -341,8 +341,10 @@ static int __init dm_st_init(void) { int r = dm_register_path_selector(&st_ps); - if (r < 0) + if (r < 0) { DMERR("register failed %d", r); + return r; + } DMINFO("version " ST_VERSION " loaded"); diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index 1e0d3b9b75d6..163a5bbd485f 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -2410,7 +2410,7 @@ static int super_init_validation(struct raid_set *rs, struct md_rdev *rdev) */ sb_retrieve_failed_devices(sb, failed_devices); rdev_for_each(r, mddev) { - if (test_bit(Journal, &rdev->flags) || + if (test_bit(Journal, &r->flags) || !r->sb_page) continue; sb2 = page_address(r->sb_page); diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c index 9511dae5b556..94b6c43dfa5c 100644 --- a/drivers/md/dm-raid1.c +++ b/drivers/md/dm-raid1.c @@ -133,10 +133,9 @@ static void queue_bio(struct mirror_set *ms, struct bio *bio, int rw) spin_lock_irqsave(&ms->lock, flags); should_wake = !(bl->head); bio_list_add(bl, bio); - spin_unlock_irqrestore(&ms->lock, flags); - if (should_wake) wakeup_mirrord(ms); + spin_unlock_irqrestore(&ms->lock, flags); } static void dispatch_bios(void *context, struct bio_list *bio_list) @@ -646,9 +645,9 @@ static void write_callback(unsigned long error, void *context) if (!ms->failures.head) should_wake = 1; bio_list_add(&ms->failures, bio); - spin_unlock_irqrestore(&ms->lock, flags); if (should_wake) wakeup_mirrord(ms); + spin_unlock_irqrestore(&ms->lock, flags); } static void do_write(struct mirror_set *ms, struct bio *bio) diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c index 4112071de0be..c68dc1653cfd 100644 --- a/drivers/md/dm-stripe.c +++ b/drivers/md/dm-stripe.c @@ -459,6 +459,7 @@ static void stripe_io_hints(struct dm_target *ti, struct stripe_c *sc = ti->private; unsigned int chunk_size = sc->chunk_size << SECTOR_SHIFT; + limits->chunk_sectors = sc->chunk_size; limits->io_min = chunk_size; limits->io_opt = chunk_size * sc->stripes; } diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index dbd39b9722b9..20b8f560a2da 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -431,6 +431,7 @@ static int dm_set_device_limits(struct dm_target *ti, struct dm_dev *dev, return 0; } + mutex_lock(&q->limits_lock); if (blk_stack_limits(limits, &q->limits, get_start_sect(bdev) + start) < 0) DMWARN("%s: adding target device %pg caused an alignment inconsistency: " @@ -448,6 +449,7 @@ static int dm_set_device_limits(struct dm_target *ti, struct dm_dev *dev, */ if (!dm_target_has_integrity(ti->type)) queue_limits_stack_integrity_bdev(limits, bdev); + mutex_unlock(&q->limits_lock); return 0; } @@ -523,8 +525,9 @@ static char **realloc_argv(unsigned int *size, char **old_argv) gfp = GFP_NOIO; } argv = kmalloc_array(new_size, sizeof(*argv), gfp); - if (argv && old_argv) { - memcpy(argv, old_argv, *size * sizeof(*argv)); + if (argv) { + if (old_argv) + memcpy(argv, old_argv, *size * sizeof(*argv)); *size = new_size; } @@ -697,6 +700,10 @@ int dm_table_add_target(struct dm_table *t, const char *type, DMERR("%s: zero-length target", dm_device_name(t->md)); return -EINVAL; } + if (start + len < start || start + len > LLONG_MAX >> SECTOR_SHIFT) { + DMERR("%s: too large device", dm_device_name(t->md)); + return -EINVAL; + } ti->type = dm_get_target_type(type); if (!ti->type) { @@ -887,17 +894,17 @@ static bool dm_table_supports_dax(struct dm_table *t, return true; } -static int device_is_rq_stackable(struct dm_target *ti, struct dm_dev *dev, - sector_t start, sector_t len, void *data) +static int device_is_not_rq_stackable(struct dm_target *ti, struct dm_dev *dev, + sector_t start, sector_t len, void *data) { struct block_device *bdev = dev->bdev; struct request_queue *q = bdev_get_queue(bdev); /* request-based cannot stack on partitions! */ if (bdev_is_partition(bdev)) - return false; + return true; - return queue_is_mq(q); + return !queue_is_mq(q); } static int dm_table_determine_type(struct dm_table *t) @@ -993,7 +1000,7 @@ verify_rq_based: /* Non-request-stackable devices can't be used for request-based dm */ if (!ti->type->iterate_devices || - !ti->type->iterate_devices(ti, device_is_rq_stackable, NULL)) { + ti->type->iterate_devices(ti, device_is_not_rq_stackable, NULL)) { DMERR("table load rejected: including non-request-stackable devices"); return -EINVAL; } @@ -1182,7 +1189,7 @@ static int dm_keyslot_evict(struct blk_crypto_profile *profile, t = dm_get_live_table(md, &srcu_idx); if (!t) - return 0; + goto put_live_table; for (unsigned int i = 0; i < t->num_targets; i++) { struct dm_target *ti = dm_table_get_target(t, i); @@ -1193,6 +1200,7 @@ static int dm_keyslot_evict(struct blk_crypto_profile *profile, (void *)key); } +put_live_table: dm_put_live_table(md, srcu_idx); return 0; } @@ -1728,8 +1736,12 @@ static int device_not_write_zeroes_capable(struct dm_target *ti, struct dm_dev * sector_t start, sector_t len, void *data) { struct request_queue *q = bdev_get_queue(dev->bdev); + int b; - return !q->limits.max_write_zeroes_sectors; + mutex_lock(&q->limits_lock); + b = !q->limits.max_write_zeroes_sectors; + mutex_unlock(&q->limits_lock); + return b; } static bool dm_table_supports_write_zeroes(struct dm_table *t) diff --git a/drivers/md/dm-vdo/dedupe.c b/drivers/md/dm-vdo/dedupe.c index 80628ae93fba..5a74b3a85ec4 100644 --- a/drivers/md/dm-vdo/dedupe.c +++ b/drivers/md/dm-vdo/dedupe.c @@ -2178,6 +2178,7 @@ static int initialize_index(struct vdo *vdo, struct hash_zones *zones) vdo_set_dedupe_index_timeout_interval(vdo_dedupe_index_timeout_interval); vdo_set_dedupe_index_min_timer_interval(vdo_dedupe_index_min_timer_interval); + spin_lock_init(&zones->lock); /* * Since we will save up the timeouts that would have been reported but were ratelimited, diff --git a/drivers/md/dm-vdo/indexer/index-layout.c b/drivers/md/dm-vdo/indexer/index-layout.c index 627adc24af3b..053b7845d1f3 100644 --- a/drivers/md/dm-vdo/indexer/index-layout.c +++ b/drivers/md/dm-vdo/indexer/index-layout.c @@ -54,7 +54,6 @@ * Each save also has a unique nonce. */ -#define MAGIC_SIZE 32 #define NONCE_INFO_SIZE 32 #define MAX_SAVES 2 @@ -98,9 +97,11 @@ enum region_type { #define SUPER_VERSION_CURRENT 3 #define SUPER_VERSION_MAXIMUM 7 -static const u8 LAYOUT_MAGIC[MAGIC_SIZE] = "*ALBIREO*SINGLE*FILE*LAYOUT*001*"; +static const u8 LAYOUT_MAGIC[] = "*ALBIREO*SINGLE*FILE*LAYOUT*001*"; static const u64 REGION_MAGIC = 0x416c6252676e3031; /* 'AlbRgn01' */ +#define MAGIC_SIZE (sizeof(LAYOUT_MAGIC) - 1) + struct region_header { u64 magic; u64 region_blocks; diff --git a/drivers/md/dm-vdo/indexer/volume.c b/drivers/md/dm-vdo/indexer/volume.c index 655453bb276b..425b3a74f4db 100644 --- a/drivers/md/dm-vdo/indexer/volume.c +++ b/drivers/md/dm-vdo/indexer/volume.c @@ -754,10 +754,11 @@ static int get_volume_page_protected(struct volume *volume, struct uds_request * u32 physical_page, struct cached_page **page_ptr) { struct cached_page *page; + unsigned int zone_number = request->zone_number; get_page_from_cache(&volume->page_cache, physical_page, &page); if (page != NULL) { - if (request->zone_number == 0) { + if (zone_number == 0) { /* Only one zone is allowed to update the LRU. */ make_page_most_recent(&volume->page_cache, page); } @@ -767,7 +768,7 @@ static int get_volume_page_protected(struct volume *volume, struct uds_request * } /* Prepare to enqueue a read for the page. */ - end_pending_search(&volume->page_cache, request->zone_number); + end_pending_search(&volume->page_cache, zone_number); mutex_lock(&volume->read_threads_mutex); /* @@ -787,8 +788,7 @@ static int get_volume_page_protected(struct volume *volume, struct uds_request * * the order does not matter for correctness as it does below. */ mutex_unlock(&volume->read_threads_mutex); - begin_pending_search(&volume->page_cache, physical_page, - request->zone_number); + begin_pending_search(&volume->page_cache, physical_page, zone_number); return UDS_QUEUED; } @@ -797,7 +797,7 @@ static int get_volume_page_protected(struct volume *volume, struct uds_request * * "search pending" state in careful order so no other thread can mess with the data before * the caller gets to look at it. */ - begin_pending_search(&volume->page_cache, physical_page, request->zone_number); + begin_pending_search(&volume->page_cache, physical_page, zone_number); mutex_unlock(&volume->read_threads_mutex); *page_ptr = page; return UDS_SUCCESS; @@ -849,6 +849,7 @@ static int search_cached_index_page(struct volume *volume, struct uds_request *r { int result; struct cached_page *page = NULL; + unsigned int zone_number = request->zone_number; u32 physical_page = map_to_physical_page(volume->geometry, chapter, index_page_number); @@ -858,18 +859,18 @@ static int search_cached_index_page(struct volume *volume, struct uds_request *r * invalidation by the reader thread, before the reader thread has noticed that the * invalidate_counter has been incremented. */ - begin_pending_search(&volume->page_cache, physical_page, request->zone_number); + begin_pending_search(&volume->page_cache, physical_page, zone_number); result = get_volume_page_protected(volume, request, physical_page, &page); if (result != UDS_SUCCESS) { - end_pending_search(&volume->page_cache, request->zone_number); + end_pending_search(&volume->page_cache, zone_number); return result; } result = uds_search_chapter_index_page(&page->index_page, volume->geometry, &request->record_name, record_page_number); - end_pending_search(&volume->page_cache, request->zone_number); + end_pending_search(&volume->page_cache, zone_number); return result; } @@ -882,6 +883,7 @@ int uds_search_cached_record_page(struct volume *volume, struct uds_request *req { struct cached_page *record_page; struct index_geometry *geometry = volume->geometry; + unsigned int zone_number = request->zone_number; int result; u32 physical_page, page_number; @@ -905,11 +907,11 @@ int uds_search_cached_record_page(struct volume *volume, struct uds_request *req * invalidation by the reader thread, before the reader thread has noticed that the * invalidate_counter has been incremented. */ - begin_pending_search(&volume->page_cache, physical_page, request->zone_number); + begin_pending_search(&volume->page_cache, physical_page, zone_number); result = get_volume_page_protected(volume, request, physical_page, &record_page); if (result != UDS_SUCCESS) { - end_pending_search(&volume->page_cache, request->zone_number); + end_pending_search(&volume->page_cache, zone_number); return result; } @@ -917,7 +919,7 @@ int uds_search_cached_record_page(struct volume *volume, struct uds_request *req &request->record_name, geometry, &request->old_metadata)) *found = true; - end_pending_search(&volume->page_cache, request->zone_number); + end_pending_search(&volume->page_cache, zone_number); return UDS_SUCCESS; } diff --git a/drivers/md/dm-vdo/vdo.c b/drivers/md/dm-vdo/vdo.c index fff847767755..b897f88250d2 100644 --- a/drivers/md/dm-vdo/vdo.c +++ b/drivers/md/dm-vdo/vdo.c @@ -31,9 +31,7 @@ #include <linux/completion.h> #include <linux/device-mapper.h> -#include <linux/kernel.h> #include <linux/lz4.h> -#include <linux/module.h> #include <linux/mutex.h> #include <linux/spinlock.h> #include <linux/types.h> @@ -142,12 +140,6 @@ static void finish_vdo_request_queue(void *ptr) vdo_unregister_allocating_thread(); } -#ifdef MODULE -#define MODULE_NAME THIS_MODULE->name -#else -#define MODULE_NAME "dm-vdo" -#endif /* MODULE */ - static const struct vdo_work_queue_type default_queue_type = { .start = start_vdo_request_queue, .finish = finish_vdo_request_queue, @@ -559,8 +551,7 @@ int vdo_make(unsigned int instance, struct device_config *config, char **reason, *vdo_ptr = vdo; snprintf(vdo->thread_name_prefix, sizeof(vdo->thread_name_prefix), - "%s%u", MODULE_NAME, instance); - BUG_ON(vdo->thread_name_prefix[0] == '\0'); + "vdo%u", instance); result = vdo_allocate(vdo->thread_config.thread_count, struct vdo_thread, __func__, &vdo->threads); if (result != VDO_SUCCESS) { diff --git a/drivers/md/dm-verity-fec.c b/drivers/md/dm-verity-fec.c index 6bd9848518d4..559b8179ac50 100644 --- a/drivers/md/dm-verity-fec.c +++ b/drivers/md/dm-verity-fec.c @@ -604,6 +604,10 @@ int verity_fec_parse_opt_args(struct dm_arg_set *as, struct dm_verity *v, (*argc)--; if (!strcasecmp(arg_name, DM_VERITY_OPT_FEC_DEV)) { + if (v->fec->dev) { + ti->error = "FEC device already specified"; + return -EINVAL; + } r = dm_get_device(ti, arg_value, BLK_OPEN_READ, &v->fec->dev); if (r) { ti->error = "FEC device lookup failed"; diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c index c142ec5458b7..ce0462e751a6 100644 --- a/drivers/md/dm-verity-target.c +++ b/drivers/md/dm-verity-target.c @@ -796,6 +796,13 @@ static int verity_map(struct dm_target *ti, struct bio *bio) return DM_MAPIO_SUBMITTED; } +static void verity_postsuspend(struct dm_target *ti) +{ + struct dm_verity *v = ti->private; + flush_workqueue(v->verify_wq); + dm_bufio_client_reset(v->bufio); +} + /* * Status: V (valid) or C (corruption found) */ @@ -1073,6 +1080,9 @@ static int verity_alloc_most_once(struct dm_verity *v) { struct dm_target *ti = v->ti; + if (v->validated_blocks) + return 0; + /* the bitset can only handle INT_MAX blocks */ if (v->data_blocks > INT_MAX) { ti->error = "device too large to use check_at_most_once"; @@ -1096,6 +1106,9 @@ static int verity_alloc_zero_digest(struct dm_verity *v) struct dm_verity_io *io; u8 *zero_data; + if (v->zero_digest) + return 0; + v->zero_digest = kmalloc(v->digest_size, GFP_KERNEL); if (!v->zero_digest) @@ -1530,7 +1543,7 @@ static int verity_ctr(struct dm_target *ti, unsigned int argc, char **argv) goto bad; } - /* Root hash signature is a optional parameter*/ + /* Root hash signature is an optional parameter */ r = verity_verify_root_hash(root_hash_digest_to_validate, strlen(root_hash_digest_to_validate), verify_args.sig, @@ -1766,6 +1779,7 @@ static struct target_type verity_target = { .ctr = verity_ctr, .dtr = verity_dtr, .map = verity_map, + .postsuspend = verity_postsuspend, .status = verity_status, .prepare_ioctl = verity_prepare_ioctl, .iterate_devices = verity_iterate_devices, diff --git a/drivers/md/dm-verity-verify-sig.c b/drivers/md/dm-verity-verify-sig.c index a9e2c6c0a33c..d5261a0e4232 100644 --- a/drivers/md/dm-verity-verify-sig.c +++ b/drivers/md/dm-verity-verify-sig.c @@ -71,9 +71,14 @@ int verity_verify_sig_parse_opt_args(struct dm_arg_set *as, const char *arg_name) { struct dm_target *ti = v->ti; - int ret = 0; + int ret; const char *sig_key = NULL; + if (v->signature_key_desc) { + ti->error = DM_VERITY_VERIFY_ERR("root_hash_sig_key_desc already specified"); + return -EINVAL; + } + if (!*argc) { ti->error = DM_VERITY_VERIFY_ERR("Signature key not specified"); return -EINVAL; @@ -83,14 +88,18 @@ int verity_verify_sig_parse_opt_args(struct dm_arg_set *as, (*argc)--; ret = verity_verify_get_sig_from_key(sig_key, sig_opts); - if (ret < 0) + if (ret < 0) { ti->error = DM_VERITY_VERIFY_ERR("Invalid key specified"); + return ret; + } v->signature_key_desc = kstrdup(sig_key, GFP_KERNEL); - if (!v->signature_key_desc) + if (!v->signature_key_desc) { + ti->error = DM_VERITY_VERIFY_ERR("Could not allocate memory for signature key"); return -ENOMEM; + } - return ret; + return 0; } /* diff --git a/drivers/md/dm-zone.c b/drivers/md/dm-zone.c index c0d41c36e06e..04cc36a9d5ca 100644 --- a/drivers/md/dm-zone.c +++ b/drivers/md/dm-zone.c @@ -56,24 +56,31 @@ int dm_blk_report_zones(struct gendisk *disk, sector_t sector, { struct mapped_device *md = disk->private_data; struct dm_table *map; - int srcu_idx, ret; + struct dm_table *zone_revalidate_map = md->zone_revalidate_map; + int srcu_idx, ret = -EIO; + bool put_table = false; - if (!md->zone_revalidate_map) { - /* Regular user context */ + if (!zone_revalidate_map || md->revalidate_map_task != current) { + /* + * Regular user context or + * Zone revalidation during __bind() is in progress, but this + * call is from a different process + */ if (dm_suspended_md(md)) return -EAGAIN; map = dm_get_live_table(md, &srcu_idx); - if (!map) - return -EIO; + put_table = true; } else { /* Zone revalidation during __bind() */ - map = md->zone_revalidate_map; + map = zone_revalidate_map; } - ret = dm_blk_do_report_zones(md, map, sector, nr_zones, cb, data); + if (map) + ret = dm_blk_do_report_zones(md, map, sector, nr_zones, cb, + data); - if (!md->zone_revalidate_map) + if (put_table) dm_put_live_table(md, srcu_idx); return ret; @@ -175,7 +182,9 @@ int dm_revalidate_zones(struct dm_table *t, struct request_queue *q) * our table for dm_blk_report_zones() to use directly. */ md->zone_revalidate_map = t; + md->revalidate_map_task = current; ret = blk_revalidate_disk_zones(disk); + md->revalidate_map_task = NULL; md->zone_revalidate_map = NULL; if (ret) { diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c index 6141fc25d842..c38bd6e4c273 100644 --- a/drivers/md/dm-zoned-target.c +++ b/drivers/md/dm-zoned-target.c @@ -1061,7 +1061,7 @@ static int dmz_iterate_devices(struct dm_target *ti, struct dmz_target *dmz = ti->private; unsigned int zone_nr_sectors = dmz_zone_nr_sectors(dmz->metadata); sector_t capacity; - int i, r; + int i, r = 0; for (i = 0; i < dmz->nr_ddevs; i++) { capacity = dmz->dev[i].capacity & ~(zone_nr_sectors - 1); diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 19230404d8c2..c5dcd632404c 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1541,14 +1541,18 @@ static void __send_empty_flush(struct clone_info *ci) { struct dm_table *t = ci->map; struct bio flush_bio; + blk_opf_t opf = REQ_OP_WRITE | REQ_PREFLUSH | REQ_SYNC; + + if ((ci->io->orig_bio->bi_opf & (REQ_IDLE | REQ_SYNC)) == + (REQ_IDLE | REQ_SYNC)) + opf |= REQ_IDLE; /* * Use an on-stack bio for this, it's safe since we don't * need to reference it after submit. It's just used as * the basis for the clone(s). */ - bio_init(&flush_bio, ci->io->md->disk->part0, NULL, 0, - REQ_OP_WRITE | REQ_PREFLUSH | REQ_SYNC); + bio_init(&flush_bio, ci->io->md->disk->part0, NULL, 0, opf); ci->bio = &flush_bio; ci->sector_count = 0; @@ -1784,19 +1788,35 @@ static void init_clone_info(struct clone_info *ci, struct dm_io *io, } #ifdef CONFIG_BLK_DEV_ZONED -static inline bool dm_zone_bio_needs_split(struct mapped_device *md, - struct bio *bio) +static inline bool dm_zone_bio_needs_split(struct bio *bio) { /* - * For mapped device that need zone append emulation, we must - * split any large BIO that straddles zone boundaries. + * Special case the zone operations that cannot or should not be split. */ - return dm_emulate_zone_append(md) && bio_straddles_zones(bio) && - !bio_flagged(bio, BIO_ZONE_WRITE_PLUGGING); + switch (bio_op(bio)) { + case REQ_OP_ZONE_APPEND: + case REQ_OP_ZONE_FINISH: + case REQ_OP_ZONE_RESET: + case REQ_OP_ZONE_RESET_ALL: + return false; + default: + break; + } + + /* + * When mapped devices use the block layer zone write plugging, we must + * split any large BIO to the mapped device limits to not submit BIOs + * that span zone boundaries and to avoid potential deadlocks with + * queue freeze operations. + */ + return bio_needs_zone_write_plugging(bio) || bio_straddles_zones(bio); } + static inline bool dm_zone_plug_bio(struct mapped_device *md, struct bio *bio) { - return dm_emulate_zone_append(md) && blk_zone_plug_bio(bio, 0); + if (!bio_needs_zone_write_plugging(bio)) + return false; + return blk_zone_plug_bio(bio, 0); } static blk_status_t __send_zone_reset_all_emulated(struct clone_info *ci, @@ -1912,8 +1932,7 @@ static blk_status_t __send_zone_reset_all(struct clone_info *ci) } #else -static inline bool dm_zone_bio_needs_split(struct mapped_device *md, - struct bio *bio) +static inline bool dm_zone_bio_needs_split(struct bio *bio) { return false; } @@ -1940,9 +1959,7 @@ static void dm_split_and_process_bio(struct mapped_device *md, is_abnormal = is_abnormal_io(bio); if (static_branch_unlikely(&zoned_enabled)) { - /* Special case REQ_OP_ZONE_RESET_ALL as it cannot be split. */ - need_split = (bio_op(bio) != REQ_OP_ZONE_RESET_ALL) && - (is_abnormal || dm_zone_bio_needs_split(md, bio)); + need_split = is_abnormal || dm_zone_bio_needs_split(bio); } else { need_split = is_abnormal; } @@ -2406,21 +2423,29 @@ static struct dm_table *__bind(struct mapped_device *md, struct dm_table *t, struct queue_limits *limits) { struct dm_table *old_map; - sector_t size; + sector_t size, old_size; int ret; lockdep_assert_held(&md->suspend_lock); size = dm_table_get_size(t); + old_size = dm_get_size(md); + 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; + } + /* * Wipe any geometry if the size of the table changed. */ - if (size != dm_get_size(md)) + if (size != old_size) memset(&md->geometry, 0, sizeof(md->geometry)); - set_capacity(md->disk, size); - dm_table_event_callback(t, event_callback, md); if (dm_table_request_based(t)) { @@ -2438,10 +2463,10 @@ static struct dm_table *__bind(struct mapped_device *md, struct dm_table *t, * requests in the queue may refer to bio from the old bioset, * so you must walk through the queue to unprep. */ - if (!md->mempools) { + if (!md->mempools) md->mempools = t->mempools; - t->mempools = NULL; - } + else + dm_free_md_mempools(t->mempools); } else { /* * The md may already have mempools that need changing. @@ -2450,14 +2475,8 @@ static struct dm_table *__bind(struct mapped_device *md, struct dm_table *t, */ dm_free_md_mempools(md->mempools); md->mempools = t->mempools; - t->mempools = NULL; - } - - ret = dm_table_set_restrictions(t, md->queue, limits); - if (ret) { - old_map = ERR_PTR(ret); - goto out; } + t->mempools = NULL; old_map = rcu_dereference_protected(md->map, lockdep_is_held(&md->suspend_lock)); rcu_assign_pointer(md->map, (void *)t); diff --git a/drivers/md/md-autodetect.c b/drivers/md/md-autodetect.c index b2a00f213c2c..4b80165afd23 100644 --- a/drivers/md/md-autodetect.c +++ b/drivers/md/md-autodetect.c @@ -49,6 +49,7 @@ static int md_setup_ents __initdata; * instead of just one. -- KTK * 18May2000: Added support for persistent-superblock arrays: * md=n,0,factor,fault,device-list uses RAID0 for device n + * md=n,-1,factor,fault,device-list uses LINEAR for device n * md=n,device-list reads a RAID superblock from the devices * elements in device-list are read by name_to_kdev_t so can be * a hex number or something like /dev/hda1 /dev/sdb @@ -87,7 +88,7 @@ static int __init md_setup(char *str) md_setup_ents++; switch (get_option(&str, &level)) { /* RAID level */ case 2: /* could be 0 or -1.. */ - if (level == 0) { + if (level == 0 || level == LEVEL_LINEAR) { if (get_option(&str, &factor) != 2 || /* Chunk Size */ get_option(&str, &fault) != 2) { printk(KERN_WARNING "md: Too few arguments supplied to md=.\n"); @@ -95,7 +96,10 @@ static int __init md_setup(char *str) } md_setup_args[ent].level = level; md_setup_args[ent].chunk = 1 << (factor+12); - pername = "raid0"; + if (level == LEVEL_LINEAR) + pername = "linear"; + else + pername = "raid0"; break; } fallthrough; diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c index c3a42dd66ce5..0da1d0723f88 100644 --- a/drivers/md/md-bitmap.c +++ b/drivers/md/md-bitmap.c @@ -787,7 +787,7 @@ static int md_bitmap_new_disk_sb(struct bitmap *bitmap) * is a good choice? We choose COUNTER_MAX / 2 arbitrarily. */ write_behind = bitmap->mddev->bitmap_info.max_write_behind; - if (write_behind > COUNTER_MAX) + if (write_behind > COUNTER_MAX / 2) write_behind = COUNTER_MAX / 2; sb->write_behind = cpu_to_le32(write_behind); bitmap->mddev->bitmap_info.max_write_behind = write_behind; @@ -1671,24 +1671,13 @@ __acquires(bitmap->lock) } static int bitmap_startwrite(struct mddev *mddev, sector_t offset, - unsigned long sectors, bool behind) + unsigned long sectors) { struct bitmap *bitmap = mddev->bitmap; if (!bitmap) return 0; - if (behind) { - int bw; - atomic_inc(&bitmap->behind_writes); - bw = atomic_read(&bitmap->behind_writes); - if (bw > bitmap->behind_writes_used) - bitmap->behind_writes_used = bw; - - pr_debug("inc write-behind count %d/%lu\n", - bw, bitmap->mddev->bitmap_info.max_write_behind); - } - while (sectors) { sector_t blocks; bitmap_counter_t *bmc; @@ -1737,21 +1726,13 @@ static int bitmap_startwrite(struct mddev *mddev, sector_t offset, } static void bitmap_endwrite(struct mddev *mddev, sector_t offset, - unsigned long sectors, bool success, bool behind) + unsigned long sectors) { struct bitmap *bitmap = mddev->bitmap; if (!bitmap) return; - if (behind) { - if (atomic_dec_and_test(&bitmap->behind_writes)) - wake_up(&bitmap->behind_wait); - pr_debug("dec write-behind count %d/%lu\n", - atomic_read(&bitmap->behind_writes), - bitmap->mddev->bitmap_info.max_write_behind); - } - while (sectors) { sector_t blocks; unsigned long flags; @@ -1764,15 +1745,16 @@ static void bitmap_endwrite(struct mddev *mddev, sector_t offset, return; } - if (success && !bitmap->mddev->degraded && - bitmap->events_cleared < bitmap->mddev->events) { - bitmap->events_cleared = bitmap->mddev->events; - bitmap->need_sync = 1; - sysfs_notify_dirent_safe(bitmap->sysfs_can_clear); - } - - if (!success && !NEEDED(*bmc)) + if (!bitmap->mddev->degraded) { + if (bitmap->events_cleared < bitmap->mddev->events) { + bitmap->events_cleared = bitmap->mddev->events; + bitmap->need_sync = 1; + sysfs_notify_dirent_safe( + bitmap->sysfs_can_clear); + } + } else if (!NEEDED(*bmc)) { *bmc |= NEEDED_MASK; + } if (COUNTER(*bmc) == COUNTER_MAX) wake_up(&bitmap->overflow_wait); @@ -2062,6 +2044,37 @@ static void md_bitmap_free(void *data) kfree(bitmap); } +static void bitmap_start_behind_write(struct mddev *mddev) +{ + struct bitmap *bitmap = mddev->bitmap; + int bw; + + if (!bitmap) + return; + + atomic_inc(&bitmap->behind_writes); + bw = atomic_read(&bitmap->behind_writes); + if (bw > bitmap->behind_writes_used) + bitmap->behind_writes_used = bw; + + pr_debug("inc write-behind count %d/%lu\n", + bw, bitmap->mddev->bitmap_info.max_write_behind); +} + +static void bitmap_end_behind_write(struct mddev *mddev) +{ + struct bitmap *bitmap = mddev->bitmap; + + if (!bitmap) + return; + + if (atomic_dec_and_test(&bitmap->behind_writes)) + wake_up(&bitmap->behind_wait); + pr_debug("dec write-behind count %d/%lu\n", + atomic_read(&bitmap->behind_writes), + bitmap->mddev->bitmap_info.max_write_behind); +} + static void bitmap_wait_behind_writes(struct mddev *mddev) { struct bitmap *bitmap = mddev->bitmap; @@ -2342,7 +2355,8 @@ static int bitmap_get_stats(void *data, struct md_bitmap_stats *stats) if (!bitmap) return -ENOENT; - + if (!bitmap->storage.sb_page) + return -EINVAL; sb = kmap_local_page(bitmap->storage.sb_page); stats->sync_size = le64_to_cpu(sb->sync_size); kunmap_local(sb); @@ -2981,6 +2995,9 @@ static struct bitmap_operations bitmap_ops = { .dirty_bits = bitmap_dirty_bits, .unplug = bitmap_unplug, .daemon_work = bitmap_daemon_work, + + .start_behind_write = bitmap_start_behind_write, + .end_behind_write = bitmap_end_behind_write, .wait_behind_writes = bitmap_wait_behind_writes, .startwrite = bitmap_startwrite, diff --git a/drivers/md/md-bitmap.h b/drivers/md/md-bitmap.h index 662e6fc141a7..31c93019c76b 100644 --- a/drivers/md/md-bitmap.h +++ b/drivers/md/md-bitmap.h @@ -84,12 +84,15 @@ struct bitmap_operations { unsigned long e); void (*unplug)(struct mddev *mddev, bool sync); void (*daemon_work)(struct mddev *mddev); + + void (*start_behind_write)(struct mddev *mddev); + void (*end_behind_write)(struct mddev *mddev); void (*wait_behind_writes)(struct mddev *mddev); int (*startwrite)(struct mddev *mddev, sector_t offset, - unsigned long sectors, bool behind); + unsigned long sectors); void (*endwrite)(struct mddev *mddev, sector_t offset, - unsigned long sectors, bool success, bool behind); + unsigned long sectors); bool (*start_sync)(struct mddev *mddev, sector_t offset, sector_t *blocks, bool degraded); void (*end_sync)(struct mddev *mddev, sector_t offset, sector_t *blocks); diff --git a/drivers/md/md-linear.c b/drivers/md/md-linear.c new file mode 100644 index 000000000000..369aed044b40 --- /dev/null +++ b/drivers/md/md-linear.c @@ -0,0 +1,352 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * linear.c : Multiple Devices driver for Linux Copyright (C) 1994-96 Marc + * ZYNGIER <zyngier@ufr-info-p7.ibp.fr> or <maz@gloups.fdn.fr> + */ + +#include <linux/blkdev.h> +#include <linux/raid/md_u.h> +#include <linux/seq_file.h> +#include <linux/module.h> +#include <linux/slab.h> +#include <trace/events/block.h> +#include "md.h" + +struct dev_info { + struct md_rdev *rdev; + sector_t end_sector; +}; + +struct linear_conf { + struct rcu_head rcu; + sector_t array_sectors; + /* a copy of mddev->raid_disks */ + int raid_disks; + struct dev_info disks[] __counted_by(raid_disks); +}; + +/* + * find which device holds a particular offset + */ +static inline struct dev_info *which_dev(struct mddev *mddev, sector_t sector) +{ + int lo, mid, hi; + struct linear_conf *conf; + + lo = 0; + hi = mddev->raid_disks - 1; + conf = mddev->private; + + /* + * Binary Search + */ + + while (hi > lo) { + + mid = (hi + lo) / 2; + if (sector < conf->disks[mid].end_sector) + hi = mid; + else + lo = mid + 1; + } + + return conf->disks + lo; +} + +static sector_t linear_size(struct mddev *mddev, sector_t sectors, int raid_disks) +{ + struct linear_conf *conf; + sector_t array_sectors; + + conf = mddev->private; + WARN_ONCE(sectors || raid_disks, + "%s does not support generic reshape\n", __func__); + array_sectors = conf->array_sectors; + + return array_sectors; +} + +static int linear_set_limits(struct mddev *mddev) +{ + struct queue_limits lim; + int err; + + md_init_stacking_limits(&lim); + lim.max_hw_sectors = mddev->chunk_sectors; + lim.max_write_zeroes_sectors = mddev->chunk_sectors; + lim.io_min = mddev->chunk_sectors << 9; + err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY); + if (err) + return err; + + return queue_limits_set(mddev->gendisk->queue, &lim); +} + +static struct linear_conf *linear_conf(struct mddev *mddev, int raid_disks) +{ + struct linear_conf *conf; + struct md_rdev *rdev; + int ret = -EINVAL; + int cnt; + int i; + + conf = kzalloc(struct_size(conf, disks, raid_disks), GFP_KERNEL); + if (!conf) + return ERR_PTR(-ENOMEM); + + /* + * conf->raid_disks is copy of mddev->raid_disks. The reason to + * keep a copy of mddev->raid_disks in struct linear_conf is, + * mddev->raid_disks may not be consistent with pointers number of + * conf->disks[] when it is updated in linear_add() and used to + * iterate old conf->disks[] earray in linear_congested(). + * Here conf->raid_disks is always consitent with number of + * pointers in conf->disks[] array, and mddev->private is updated + * with rcu_assign_pointer() in linear_addr(), such race can be + * avoided. + */ + conf->raid_disks = raid_disks; + + cnt = 0; + conf->array_sectors = 0; + + rdev_for_each(rdev, mddev) { + int j = rdev->raid_disk; + struct dev_info *disk = conf->disks + j; + sector_t sectors; + + if (j < 0 || j >= raid_disks || disk->rdev) { + pr_warn("md/linear:%s: disk numbering problem. Aborting!\n", + mdname(mddev)); + goto out; + } + + disk->rdev = rdev; + if (mddev->chunk_sectors) { + sectors = rdev->sectors; + sector_div(sectors, mddev->chunk_sectors); + rdev->sectors = sectors * mddev->chunk_sectors; + } + + conf->array_sectors += rdev->sectors; + cnt++; + } + if (cnt != raid_disks) { + pr_warn("md/linear:%s: not enough drives present. Aborting!\n", + mdname(mddev)); + goto out; + } + + /* + * Here we calculate the device offsets. + */ + conf->disks[0].end_sector = conf->disks[0].rdev->sectors; + + for (i = 1; i < raid_disks; i++) + conf->disks[i].end_sector = + conf->disks[i-1].end_sector + + conf->disks[i].rdev->sectors; + + if (!mddev_is_dm(mddev)) { + ret = linear_set_limits(mddev); + if (ret) + goto out; + } + + return conf; + +out: + kfree(conf); + return ERR_PTR(ret); +} + +static int linear_run(struct mddev *mddev) +{ + struct linear_conf *conf; + int ret; + + if (md_check_no_bitmap(mddev)) + return -EINVAL; + + conf = linear_conf(mddev, mddev->raid_disks); + if (IS_ERR(conf)) + return PTR_ERR(conf); + + mddev->private = conf; + md_set_array_sectors(mddev, linear_size(mddev, 0, 0)); + + ret = md_integrity_register(mddev); + if (ret) { + kfree(conf); + mddev->private = NULL; + } + return ret; +} + +static int linear_add(struct mddev *mddev, struct md_rdev *rdev) +{ + /* Adding a drive to a linear array allows the array to grow. + * It is permitted if the new drive has a matching superblock + * already on it, with raid_disk equal to raid_disks. + * It is achieved by creating a new linear_private_data structure + * and swapping it in in-place of the current one. + * The current one is never freed until the array is stopped. + * This avoids races. + */ + struct linear_conf *newconf, *oldconf; + + if (rdev->saved_raid_disk != mddev->raid_disks) + return -EINVAL; + + rdev->raid_disk = rdev->saved_raid_disk; + rdev->saved_raid_disk = -1; + + newconf = linear_conf(mddev, mddev->raid_disks + 1); + if (IS_ERR(newconf)) + return PTR_ERR(newconf); + + /* newconf->raid_disks already keeps a copy of * the increased + * value of mddev->raid_disks, WARN_ONCE() is just used to make + * sure of this. It is possible that oldconf is still referenced + * in linear_congested(), therefore kfree_rcu() is used to free + * oldconf until no one uses it anymore. + */ + oldconf = rcu_dereference_protected(mddev->private, + lockdep_is_held(&mddev->reconfig_mutex)); + mddev->raid_disks++; + WARN_ONCE(mddev->raid_disks != newconf->raid_disks, + "copied raid_disks doesn't match mddev->raid_disks"); + rcu_assign_pointer(mddev->private, newconf); + md_set_array_sectors(mddev, linear_size(mddev, 0, 0)); + set_capacity_and_notify(mddev->gendisk, mddev->array_sectors); + kfree_rcu(oldconf, rcu); + return 0; +} + +static void linear_free(struct mddev *mddev, void *priv) +{ + struct linear_conf *conf = priv; + + kfree(conf); +} + +static bool linear_make_request(struct mddev *mddev, struct bio *bio) +{ + struct dev_info *tmp_dev; + sector_t start_sector, end_sector, data_offset; + sector_t bio_sector = bio->bi_iter.bi_sector; + + if (unlikely(bio->bi_opf & REQ_PREFLUSH) + && md_flush_request(mddev, bio)) + return true; + + tmp_dev = which_dev(mddev, bio_sector); + start_sector = tmp_dev->end_sector - tmp_dev->rdev->sectors; + end_sector = tmp_dev->end_sector; + data_offset = tmp_dev->rdev->data_offset; + + if (unlikely(bio_sector >= end_sector || + bio_sector < start_sector)) + goto out_of_bounds; + + if (unlikely(is_rdev_broken(tmp_dev->rdev))) { + md_error(mddev, tmp_dev->rdev); + bio_io_error(bio); + return true; + } + + if (unlikely(bio_end_sector(bio) > end_sector)) { + /* This bio crosses a device boundary, so we have to split it */ + struct bio *split = bio_split(bio, end_sector - bio_sector, + GFP_NOIO, &mddev->bio_set); + + if (IS_ERR(split)) { + bio->bi_status = errno_to_blk_status(PTR_ERR(split)); + bio_endio(bio); + return true; + } + + bio_chain(split, bio); + submit_bio_noacct(bio); + bio = split; + } + + md_account_bio(mddev, &bio); + bio_set_dev(bio, tmp_dev->rdev->bdev); + bio->bi_iter.bi_sector = bio->bi_iter.bi_sector - + start_sector + data_offset; + + if (unlikely((bio_op(bio) == REQ_OP_DISCARD) && + !bdev_max_discard_sectors(bio->bi_bdev))) { + /* Just ignore it */ + bio_endio(bio); + } else { + if (mddev->gendisk) + trace_block_bio_remap(bio, disk_devt(mddev->gendisk), + bio_sector); + mddev_check_write_zeroes(mddev, bio); + submit_bio_noacct(bio); + } + return true; + +out_of_bounds: + pr_err("md/linear:%s: make_request: Sector %llu out of bounds on dev %pg: %llu sectors, offset %llu\n", + mdname(mddev), + (unsigned long long)bio->bi_iter.bi_sector, + tmp_dev->rdev->bdev, + (unsigned long long)tmp_dev->rdev->sectors, + (unsigned long long)start_sector); + bio_io_error(bio); + return true; +} + +static void linear_status(struct seq_file *seq, struct mddev *mddev) +{ + seq_printf(seq, " %dk rounding", mddev->chunk_sectors / 2); +} + +static void linear_error(struct mddev *mddev, struct md_rdev *rdev) +{ + if (!test_and_set_bit(MD_BROKEN, &mddev->flags)) { + char *md_name = mdname(mddev); + + pr_crit("md/linear%s: Disk failure on %pg detected, failing array.\n", + md_name, rdev->bdev); + } +} + +static void linear_quiesce(struct mddev *mddev, int state) +{ +} + +static struct md_personality linear_personality = { + .name = "linear", + .level = LEVEL_LINEAR, + .owner = THIS_MODULE, + .make_request = linear_make_request, + .run = linear_run, + .free = linear_free, + .status = linear_status, + .hot_add_disk = linear_add, + .size = linear_size, + .quiesce = linear_quiesce, + .error_handler = linear_error, +}; + +static int __init linear_init(void) +{ + return register_md_personality(&linear_personality); +} + +static void linear_exit(void) +{ + unregister_md_personality(&linear_personality); +} + +module_init(linear_init); +module_exit(linear_exit); +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Linear device concatenation personality for MD (deprecated)"); +MODULE_ALIAS("md-personality-1"); /* LINEAR - deprecated*/ +MODULE_ALIAS("md-linear"); +MODULE_ALIAS("md-level--1"); diff --git a/drivers/md/md.c b/drivers/md/md.c index 67108c397c5a..4b3291723670 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -629,6 +629,12 @@ static void __mddev_put(struct mddev *mddev) queue_work(md_misc_wq, &mddev->del_work); } +static void mddev_put_locked(struct mddev *mddev) +{ + if (atomic_dec_and_test(&mddev->active)) + __mddev_put(mddev); +} + void mddev_put(struct mddev *mddev) { if (!atomic_dec_and_lock(&mddev->active, &all_mddevs_lock)) @@ -8124,7 +8130,7 @@ void md_error(struct mddev *mddev, struct md_rdev *rdev) return; mddev->pers->error_handler(mddev, rdev); - if (mddev->pers->level == 0) + if (mddev->pers->level == 0 || mddev->pers->level == LEVEL_LINEAR) return; if (mddev->degraded && !test_bit(MD_BROKEN, &mddev->flags)) @@ -8376,6 +8382,10 @@ static int md_seq_show(struct seq_file *seq, void *v) return 0; spin_unlock(&all_mddevs_lock); + + /* prevent bitmap to be freed after checking */ + mutex_lock(&mddev->bitmap_info.mutex); + spin_lock(&mddev->lock); if (mddev->pers || mddev->raid_disks || !list_empty(&mddev->disks)) { seq_printf(seq, "%s : ", mdname(mddev)); @@ -8451,14 +8461,13 @@ static int md_seq_show(struct seq_file *seq, void *v) seq_printf(seq, "\n"); } spin_unlock(&mddev->lock); + mutex_unlock(&mddev->bitmap_info.mutex); spin_lock(&all_mddevs_lock); if (mddev == list_last_entry(&all_mddevs, struct mddev, all_mddevs)) status_unused(seq); - if (atomic_dec_and_test(&mddev->active)) - __mddev_put(mddev); - + mddev_put_locked(mddev); return 0; } @@ -8745,12 +8754,32 @@ void md_submit_discard_bio(struct mddev *mddev, struct md_rdev *rdev, } EXPORT_SYMBOL_GPL(md_submit_discard_bio); +static void md_bitmap_start(struct mddev *mddev, + struct md_io_clone *md_io_clone) +{ + if (mddev->pers->bitmap_sector) + mddev->pers->bitmap_sector(mddev, &md_io_clone->offset, + &md_io_clone->sectors); + + mddev->bitmap_ops->startwrite(mddev, md_io_clone->offset, + md_io_clone->sectors); +} + +static void md_bitmap_end(struct mddev *mddev, struct md_io_clone *md_io_clone) +{ + mddev->bitmap_ops->endwrite(mddev, md_io_clone->offset, + md_io_clone->sectors); +} + static void md_end_clone_io(struct bio *bio) { struct md_io_clone *md_io_clone = bio->bi_private; struct bio *orig_bio = md_io_clone->orig_bio; struct mddev *mddev = md_io_clone->mddev; + if (bio_data_dir(orig_bio) == WRITE && mddev->bitmap) + md_bitmap_end(mddev, md_io_clone); + if (bio->bi_status && !orig_bio->bi_status) orig_bio->bi_status = bio->bi_status; @@ -8775,6 +8804,12 @@ static void md_clone_bio(struct mddev *mddev, struct bio **bio) if (blk_queue_io_stat(bdev->bd_disk->queue)) md_io_clone->start_time = bio_start_io_acct(*bio); + if (bio_data_dir(*bio) == WRITE && mddev->bitmap) { + md_io_clone->offset = (*bio)->bi_iter.bi_sector; + md_io_clone->sectors = bio_sectors(*bio); + md_bitmap_start(mddev, md_io_clone); + } + clone->bi_end_io = md_end_clone_io; clone->bi_private = md_io_clone; *bio = clone; @@ -8793,6 +8828,9 @@ void md_free_cloned_bio(struct bio *bio) struct bio *orig_bio = md_io_clone->orig_bio; struct mddev *mddev = md_io_clone->mddev; + if (bio_data_dir(orig_bio) == WRITE && mddev->bitmap) + md_bitmap_end(mddev, md_io_clone); + if (bio->bi_status && !orig_bio->bi_status) orig_bio->bi_status = bio->bi_status; @@ -9664,8 +9702,8 @@ void md_check_recovery(struct mddev *mddev) * remove disk. */ rdev_for_each_safe(rdev, tmp, mddev) { - if (test_and_clear_bit(ClusterRemove, &rdev->flags) && - rdev->raid_disk < 0) + if (rdev->raid_disk < 0 && + test_and_clear_bit(ClusterRemove, &rdev->flags)) md_kick_rdev_from_array(rdev); } } @@ -9852,11 +9890,11 @@ EXPORT_SYMBOL_GPL(rdev_clear_badblocks); static int md_notify_reboot(struct notifier_block *this, unsigned long code, void *x) { - struct mddev *mddev, *n; + struct mddev *mddev; int need_delay = 0; spin_lock(&all_mddevs_lock); - list_for_each_entry_safe(mddev, n, &all_mddevs, all_mddevs) { + list_for_each_entry(mddev, &all_mddevs, all_mddevs) { if (!mddev_get(mddev)) continue; spin_unlock(&all_mddevs_lock); @@ -9868,8 +9906,8 @@ static int md_notify_reboot(struct notifier_block *this, mddev_unlock(mddev); } need_delay = 1; - mddev_put(mddev); spin_lock(&all_mddevs_lock); + mddev_put_locked(mddev); } spin_unlock(&all_mddevs_lock); @@ -9962,8 +10000,11 @@ static void check_sb_changes(struct mddev *mddev, struct md_rdev *rdev) /* Check for change of roles in the active devices */ rdev_for_each_safe(rdev2, tmp, mddev) { - if (test_bit(Faulty, &rdev2->flags)) + if (test_bit(Faulty, &rdev2->flags)) { + if (test_bit(ClusterRemove, &rdev2->flags)) + set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); continue; + } /* Check if the roles changed */ role = le16_to_cpu(sb->dev_roles[rdev2->desc_nr]); @@ -10202,7 +10243,7 @@ void md_autostart_arrays(int part) static __exit void md_exit(void) { - struct mddev *mddev, *n; + struct mddev *mddev; int delay = 1; unregister_blkdev(MD_MAJOR,"md"); @@ -10223,7 +10264,7 @@ static __exit void md_exit(void) remove_proc_entry("mdstat", NULL); spin_lock(&all_mddevs_lock); - list_for_each_entry_safe(mddev, n, &all_mddevs, all_mddevs) { + list_for_each_entry(mddev, &all_mddevs, all_mddevs) { if (!mddev_get(mddev)) continue; spin_unlock(&all_mddevs_lock); @@ -10235,8 +10276,8 @@ static __exit void md_exit(void) * the mddev for destruction by a workqueue, and the * destroy_workqueue() below will wait for that to complete. */ - mddev_put(mddev); spin_lock(&all_mddevs_lock); + mddev_put_locked(mddev); } spin_unlock(&all_mddevs_lock); diff --git a/drivers/md/md.h b/drivers/md/md.h index 5d2e6bd58e4d..8826dce9717d 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -746,6 +746,9 @@ struct md_personality void *(*takeover) (struct mddev *mddev); /* Changes the consistency policy of an active array. */ int (*change_consistency_policy)(struct mddev *mddev, const char *buf); + /* convert io ranges from array to bitmap */ + void (*bitmap_sector)(struct mddev *mddev, sector_t *offset, + unsigned long *sectors); }; struct md_sysfs_entry { @@ -828,6 +831,8 @@ struct md_io_clone { struct mddev *mddev; struct bio *orig_bio; unsigned long start_time; + sector_t offset; + unsigned long sectors; struct bio bio_clone; }; diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index 32d587524778..31bea72bcb01 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -385,10 +385,8 @@ static int raid0_set_limits(struct mddev *mddev) lim.io_min = mddev->chunk_sectors << 9; lim.io_opt = lim.io_min * mddev->raid_disks; err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY); - if (err) { - queue_limits_cancel_update(mddev->gendisk->queue); + if (err) return err; - } return queue_limits_set(mddev->gendisk->queue, &lim); } diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 6c9d24203f39..fe1599db69c8 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -420,10 +420,8 @@ static void close_write(struct r1bio *r1_bio) r1_bio->behind_master_bio = NULL; } - /* clear the bitmap if all writes complete successfully */ - mddev->bitmap_ops->endwrite(mddev, r1_bio->sector, r1_bio->sectors, - !test_bit(R1BIO_Degraded, &r1_bio->state), - test_bit(R1BIO_BehindIO, &r1_bio->state)); + if (test_bit(R1BIO_BehindIO, &r1_bio->state)) + mddev->bitmap_ops->end_behind_write(mddev); md_write_end(mddev); } @@ -480,8 +478,6 @@ static void raid1_end_write_request(struct bio *bio) if (!test_bit(Faulty, &rdev->flags)) set_bit(R1BIO_WriteError, &r1_bio->state); else { - /* Fail the request */ - set_bit(R1BIO_Degraded, &r1_bio->state); /* Finished with this branch */ r1_bio->bios[mirror] = NULL; to_put = bio; @@ -1492,11 +1488,8 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio, break; } r1_bio->bios[i] = NULL; - if (!rdev || test_bit(Faulty, &rdev->flags)) { - if (i < conf->raid_disks) - set_bit(R1BIO_Degraded, &r1_bio->state); + if (!rdev || test_bit(Faulty, &rdev->flags)) continue; - } atomic_inc(&rdev->nr_pending); if (test_bit(WriteErrorSeen, &rdev->flags)) { @@ -1522,16 +1515,6 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio, */ max_sectors = bad_sectors; rdev_dec_pending(rdev, mddev); - /* We don't set R1BIO_Degraded as that - * only applies if the disk is - * missing, so it might be re-added, - * and we want to know to recover this - * chunk. - * In this case the device is here, - * and the fact that this chunk is not - * in-sync is recorded in the bad - * block log - */ continue; } if (is_bad) { @@ -1611,9 +1594,8 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio, stats.behind_writes < max_write_behind) alloc_behind_master_bio(r1_bio, bio); - mddev->bitmap_ops->startwrite( - mddev, r1_bio->sector, r1_bio->sectors, - test_bit(R1BIO_BehindIO, &r1_bio->state)); + if (test_bit(R1BIO_BehindIO, &r1_bio->state)) + mddev->bitmap_ops->start_behind_write(mddev); first_clone = 0; } @@ -2174,14 +2156,9 @@ static int fix_sync_read_error(struct r1bio *r1_bio) if (!rdev_set_badblocks(rdev, sect, s, 0)) abort = 1; } - if (abort) { - conf->recovery_disabled = - mddev->recovery_disabled; - set_bit(MD_RECOVERY_INTR, &mddev->recovery); - md_done_sync(mddev, r1_bio->sectors, 0); - put_buf(r1_bio); + if (abort) return 0; - } + /* Try next page */ sectors -= s; sect += s; @@ -2320,10 +2297,21 @@ static void sync_request_write(struct mddev *mddev, struct r1bio *r1_bio) int disks = conf->raid_disks * 2; struct bio *wbio; - if (!test_bit(R1BIO_Uptodate, &r1_bio->state)) - /* ouch - failed to read all of that. */ - if (!fix_sync_read_error(r1_bio)) + if (!test_bit(R1BIO_Uptodate, &r1_bio->state)) { + /* + * ouch - failed to read all of that. + * No need to fix read error for check/repair + * because all member disks are read. + */ + if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery) || + !fix_sync_read_error(r1_bio)) { + conf->recovery_disabled = mddev->recovery_disabled; + set_bit(MD_RECOVERY_INTR, &mddev->recovery); + md_done_sync(mddev, r1_bio->sectors, 0); + put_buf(r1_bio); return; + } + } if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) process_checks(r1_bio); @@ -2567,12 +2555,10 @@ static void handle_write_finished(struct r1conf *conf, struct r1bio *r1_bio) * errors. */ fail = true; - if (!narrow_write_error(r1_bio, m)) { + if (!narrow_write_error(r1_bio, m)) md_error(conf->mddev, conf->mirrors[m].rdev); /* an I/O failed, we can't clear the bitmap */ - set_bit(R1BIO_Degraded, &r1_bio->state); - } rdev_dec_pending(conf->mirrors[m].rdev, conf->mddev); } @@ -2663,8 +2649,6 @@ static void raid1d(struct md_thread *thread) list_del(&r1_bio->retry_list); idx = sector_to_idx(r1_bio->sector); atomic_dec(&conf->nr_queued[idx]); - if (mddev->degraded) - set_bit(R1BIO_Degraded, &r1_bio->state); if (test_bit(R1BIO_WriteError, &r1_bio->state)) close_write(r1_bio); raid_end_bio_io(r1_bio); @@ -3193,10 +3177,8 @@ static int raid1_set_limits(struct mddev *mddev) md_init_stacking_limits(&lim); lim.max_write_zeroes_sectors = 0; err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY); - if (err) { - queue_limits_cancel_update(mddev->gendisk->queue); + if (err) return err; - } return queue_limits_set(mddev->gendisk->queue, &lim); } @@ -3398,6 +3380,7 @@ static int raid1_reshape(struct mddev *mddev) /* ok, everything is stopped */ oldpool = conf->r1bio_pool; conf->r1bio_pool = newpool; + init_waitqueue_head(&conf->r1bio_pool.wait); for (d = d2 = 0; d < conf->raid_disks; d++) { struct md_rdev *rdev = conf->mirrors[d].rdev; diff --git a/drivers/md/raid1.h b/drivers/md/raid1.h index 5300cbaa58a4..33f318fcc268 100644 --- a/drivers/md/raid1.h +++ b/drivers/md/raid1.h @@ -188,7 +188,6 @@ struct r1bio { enum r1bio_state { R1BIO_Uptodate, R1BIO_IsSync, - R1BIO_Degraded, R1BIO_BehindIO, /* Set ReadError on bios that experience a readerror so that * raid1d knows what to do with them. diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 862b1fb71d86..7515a98001ca 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -428,10 +428,6 @@ static void close_write(struct r10bio *r10_bio) { struct mddev *mddev = r10_bio->mddev; - /* clear the bitmap if all writes complete successfully */ - mddev->bitmap_ops->endwrite(mddev, r10_bio->sector, r10_bio->sectors, - !test_bit(R10BIO_Degraded, &r10_bio->state), - false); md_write_end(mddev); } @@ -501,7 +497,6 @@ static void raid10_end_write_request(struct bio *bio) set_bit(R10BIO_WriteError, &r10_bio->state); else { /* Fail the request */ - set_bit(R10BIO_Degraded, &r10_bio->state); r10_bio->devs[slot].bio = NULL; to_put = bio; dec_rdev = 1; @@ -1186,8 +1181,11 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio, } } - if (!regular_request_wait(mddev, conf, bio, r10_bio->sectors)) + if (!regular_request_wait(mddev, conf, bio, r10_bio->sectors)) { + raid_end_bio_io(r10_bio); return; + } + rdev = read_balance(conf, r10_bio, &max_sectors); if (!rdev) { if (err_rdev) { @@ -1373,8 +1371,11 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio, } sectors = r10_bio->sectors; - if (!regular_request_wait(mddev, conf, bio, sectors)) + if (!regular_request_wait(mddev, conf, bio, sectors)) { + raid_end_bio_io(r10_bio); return; + } + if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) && (mddev->reshape_backwards ? (bio->bi_iter.bi_sector < conf->reshape_safe && @@ -1430,10 +1431,8 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio, r10_bio->devs[i].bio = NULL; r10_bio->devs[i].repl_bio = NULL; - if (!rdev && !rrdev) { - set_bit(R10BIO_Degraded, &r10_bio->state); + if (!rdev && !rrdev) continue; - } if (rdev && test_bit(WriteErrorSeen, &rdev->flags)) { sector_t first_bad; sector_t dev_sector = r10_bio->devs[i].addr; @@ -1450,14 +1449,6 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio, * to other devices yet */ max_sectors = bad_sectors; - /* We don't set R10BIO_Degraded as that - * only applies if the disk is missing, - * so it might be re-added, and we want to - * know to recover this chunk. - * In this case the device is here, and the - * fact that this chunk is not in-sync is - * recorded in the bad block log. - */ continue; } if (is_bad) { @@ -1493,8 +1484,6 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio, md_account_bio(mddev, &bio); r10_bio->master_bio = bio; atomic_set(&r10_bio->remaining, 1); - mddev->bitmap_ops->startwrite(mddev, r10_bio->sector, r10_bio->sectors, - false); for (i = 0; i < conf->copies; i++) { if (r10_bio->devs[i].bio) @@ -1704,6 +1693,7 @@ retry_discard: * The discard bio returns only first r10bio finishes */ if (first_copy) { + md_account_bio(mddev, &bio); r10_bio->master_bio = bio; set_bit(R10BIO_Discard, &r10_bio->state); first_copy = false; @@ -2910,11 +2900,8 @@ static void handle_write_completed(struct r10conf *conf, struct r10bio *r10_bio) rdev_dec_pending(rdev, conf->mddev); } else if (bio != NULL && bio->bi_status) { fail = true; - if (!narrow_write_error(r10_bio, m)) { + if (!narrow_write_error(r10_bio, m)) md_error(conf->mddev, rdev); - set_bit(R10BIO_Degraded, - &r10_bio->state); - } rdev_dec_pending(rdev, conf->mddev); } bio = r10_bio->devs[m].repl_bio; @@ -2973,8 +2960,6 @@ static void raid10d(struct md_thread *thread) r10_bio = list_first_entry(&tmp, struct r10bio, retry_list); list_del(&r10_bio->retry_list); - if (mddev->degraded) - set_bit(R10BIO_Degraded, &r10_bio->state); if (test_bit(R10BIO_WriteError, &r10_bio->state)) @@ -3983,12 +3968,11 @@ static int raid10_set_queue_limits(struct mddev *mddev) md_init_stacking_limits(&lim); lim.max_write_zeroes_sectors = 0; lim.io_min = mddev->chunk_sectors << 9; + lim.chunk_sectors = mddev->chunk_sectors; lim.io_opt = lim.io_min * raid10_nr_stripes(conf); err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY); - if (err) { - queue_limits_cancel_update(mddev->gendisk->queue); + if (err) return err; - } return queue_limits_set(mddev->gendisk->queue, &lim); } diff --git a/drivers/md/raid10.h b/drivers/md/raid10.h index 2e75e88d0802..3f16ad6904a9 100644 --- a/drivers/md/raid10.h +++ b/drivers/md/raid10.h @@ -161,7 +161,6 @@ enum r10bio_state { R10BIO_IsSync, R10BIO_IsRecover, R10BIO_IsReshape, - R10BIO_Degraded, /* Set ReadError on bios that experience a read error * so that raid10d knows what to do with them. */ diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c index b4f7b79fd187..011246e16a99 100644 --- a/drivers/md/raid5-cache.c +++ b/drivers/md/raid5-cache.c @@ -313,10 +313,6 @@ void r5c_handle_cached_data_endio(struct r5conf *conf, if (sh->dev[i].written) { set_bit(R5_UPTODATE, &sh->dev[i].flags); r5c_return_dev_pending_writes(conf, &sh->dev[i]); - conf->mddev->bitmap_ops->endwrite(conf->mddev, - sh->sector, RAID5_STRIPE_SECTORS(conf), - !test_bit(STRIPE_DEGRADED, &sh->state), - false); } } } diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 2fa1f270fb1d..39e7596e78c0 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -906,8 +906,7 @@ static bool stripe_can_batch(struct stripe_head *sh) if (raid5_has_log(conf) || raid5_has_ppl(conf)) return false; return test_bit(STRIPE_BATCH_READY, &sh->state) && - !test_bit(STRIPE_BITMAP_PENDING, &sh->state) && - is_full_stripe_write(sh); + is_full_stripe_write(sh); } /* we only do back search */ @@ -1345,8 +1344,6 @@ again: submit_bio_noacct(rbi); } if (!rdev && !rrdev) { - if (op_is_write(op)) - set_bit(STRIPE_DEGRADED, &sh->state); pr_debug("skip op %d on disc %d for sector %llu\n", bi->bi_opf, i, (unsigned long long)sh->sector); clear_bit(R5_LOCKED, &sh->dev[i].flags); @@ -2884,7 +2881,6 @@ static void raid5_end_write_request(struct bio *bi) set_bit(R5_MadeGoodRepl, &sh->dev[i].flags); } else { if (bi->bi_status) { - set_bit(STRIPE_DEGRADED, &sh->state); set_bit(WriteErrorSeen, &rdev->flags); set_bit(R5_WriteError, &sh->dev[i].flags); if (!test_and_set_bit(WantReplacement, &rdev->flags)) @@ -3548,29 +3544,9 @@ static void __add_stripe_bio(struct stripe_head *sh, struct bio *bi, (*bip)->bi_iter.bi_sector, sh->sector, dd_idx, sh->dev[dd_idx].sector); - if (conf->mddev->bitmap && firstwrite) { - /* Cannot hold spinlock over bitmap_startwrite, - * but must ensure this isn't added to a batch until - * we have added to the bitmap and set bm_seq. - * So set STRIPE_BITMAP_PENDING to prevent - * batching. - * If multiple __add_stripe_bio() calls race here they - * much all set STRIPE_BITMAP_PENDING. So only the first one - * to complete "bitmap_startwrite" gets to set - * STRIPE_BIT_DELAY. This is important as once a stripe - * is added to a batch, STRIPE_BIT_DELAY cannot be changed - * any more. - */ - set_bit(STRIPE_BITMAP_PENDING, &sh->state); - spin_unlock_irq(&sh->stripe_lock); - conf->mddev->bitmap_ops->startwrite(conf->mddev, sh->sector, - RAID5_STRIPE_SECTORS(conf), false); - spin_lock_irq(&sh->stripe_lock); - clear_bit(STRIPE_BITMAP_PENDING, &sh->state); - if (!sh->batch_head) { - sh->bm_seq = conf->seq_flush+1; - set_bit(STRIPE_BIT_DELAY, &sh->state); - } + if (conf->mddev->bitmap && firstwrite && !sh->batch_head) { + sh->bm_seq = conf->seq_flush+1; + set_bit(STRIPE_BIT_DELAY, &sh->state); } } @@ -3621,7 +3597,6 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh, BUG_ON(sh->batch_head); for (i = disks; i--; ) { struct bio *bi; - int bitmap_end = 0; if (test_bit(R5_ReadError, &sh->dev[i].flags)) { struct md_rdev *rdev = conf->disks[i].rdev; @@ -3646,8 +3621,6 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh, sh->dev[i].towrite = NULL; sh->overwrite_disks = 0; spin_unlock_irq(&sh->stripe_lock); - if (bi) - bitmap_end = 1; log_stripe_write_finished(sh); @@ -3662,11 +3635,6 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh, bio_io_error(bi); bi = nextbi; } - if (bitmap_end) - conf->mddev->bitmap_ops->endwrite(conf->mddev, - sh->sector, RAID5_STRIPE_SECTORS(conf), - false, false); - bitmap_end = 0; /* and fail all 'written' */ bi = sh->dev[i].written; sh->dev[i].written = NULL; @@ -3675,7 +3643,6 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh, sh->dev[i].page = sh->dev[i].orig_page; } - if (bi) bitmap_end = 1; while (bi && bi->bi_iter.bi_sector < sh->dev[i].sector + RAID5_STRIPE_SECTORS(conf)) { struct bio *bi2 = r5_next_bio(conf, bi, sh->dev[i].sector); @@ -3709,10 +3676,6 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh, bi = nextbi; } } - if (bitmap_end) - conf->mddev->bitmap_ops->endwrite(conf->mddev, - sh->sector, RAID5_STRIPE_SECTORS(conf), - false, false); /* If we were in the middle of a write the parity block might * still be locked - so just clear all R5_LOCKED flags */ @@ -4061,10 +4024,7 @@ returnbi: bio_endio(wbi); wbi = wbi2; } - conf->mddev->bitmap_ops->endwrite(conf->mddev, - sh->sector, RAID5_STRIPE_SECTORS(conf), - !test_bit(STRIPE_DEGRADED, &sh->state), - false); + if (head_sh->batch_head) { sh = list_first_entry(&sh->batch_list, struct stripe_head, @@ -4341,7 +4301,6 @@ static void handle_parity_checks5(struct r5conf *conf, struct stripe_head *sh, s->locked++; set_bit(R5_Wantwrite, &dev->flags); - clear_bit(STRIPE_DEGRADED, &sh->state); set_bit(STRIPE_INSYNC, &sh->state); break; case check_state_run: @@ -4498,7 +4457,6 @@ static void handle_parity_checks6(struct r5conf *conf, struct stripe_head *sh, clear_bit(R5_Wantwrite, &dev->flags); s->locked--; } - clear_bit(STRIPE_DEGRADED, &sh->state); set_bit(STRIPE_INSYNC, &sh->state); break; @@ -4892,8 +4850,7 @@ static void break_stripe_batch_list(struct stripe_head *head_sh, (1 << STRIPE_COMPUTE_RUN) | (1 << STRIPE_DISCARD) | (1 << STRIPE_BATCH_READY) | - (1 << STRIPE_BATCH_ERR) | - (1 << STRIPE_BITMAP_PENDING)), + (1 << STRIPE_BATCH_ERR)), "stripe state: %lx\n", sh->state); WARN_ONCE(head_sh->state & ((1 << STRIPE_DISCARD) | (1 << STRIPE_REPLACED)), @@ -4901,7 +4858,6 @@ static void break_stripe_batch_list(struct stripe_head *head_sh, set_mask_bits(&sh->state, ~(STRIPE_EXPAND_SYNC_FLAGS | (1 << STRIPE_PREREAD_ACTIVE) | - (1 << STRIPE_DEGRADED) | (1 << STRIPE_ON_UNPLUG_LIST)), head_sh->state & (1 << STRIPE_INSYNC)); @@ -5785,10 +5741,6 @@ static void make_discard_request(struct mddev *mddev, struct bio *bi) } spin_unlock_irq(&sh->stripe_lock); if (conf->mddev->bitmap) { - for (d = 0; d < conf->raid_disks - conf->max_degraded; - d++) - mddev->bitmap_ops->startwrite(mddev, sh->sector, - RAID5_STRIPE_SECTORS(conf), false); sh->bm_seq = conf->seq_flush + 1; set_bit(STRIPE_BIT_DELAY, &sh->state); } @@ -5929,6 +5881,54 @@ static enum reshape_loc get_reshape_loc(struct mddev *mddev, return LOC_BEHIND_RESHAPE; } +static void raid5_bitmap_sector(struct mddev *mddev, sector_t *offset, + unsigned long *sectors) +{ + struct r5conf *conf = mddev->private; + sector_t start = *offset; + sector_t end = start + *sectors; + sector_t prev_start = start; + sector_t prev_end = end; + int sectors_per_chunk; + enum reshape_loc loc; + int dd_idx; + + sectors_per_chunk = conf->chunk_sectors * + (conf->raid_disks - conf->max_degraded); + start = round_down(start, sectors_per_chunk); + end = round_up(end, sectors_per_chunk); + + start = raid5_compute_sector(conf, start, 0, &dd_idx, NULL); + end = raid5_compute_sector(conf, end, 0, &dd_idx, NULL); + + /* + * For LOC_INSIDE_RESHAPE, this IO will wait for reshape to make + * progress, hence it's the same as LOC_BEHIND_RESHAPE. + */ + loc = get_reshape_loc(mddev, conf, prev_start); + if (likely(loc != LOC_AHEAD_OF_RESHAPE)) { + *offset = start; + *sectors = end - start; + return; + } + + sectors_per_chunk = conf->prev_chunk_sectors * + (conf->previous_raid_disks - conf->max_degraded); + prev_start = round_down(prev_start, sectors_per_chunk); + prev_end = round_down(prev_end, sectors_per_chunk); + + prev_start = raid5_compute_sector(conf, prev_start, 1, &dd_idx, NULL); + prev_end = raid5_compute_sector(conf, prev_end, 1, &dd_idx, NULL); + + /* + * for LOC_AHEAD_OF_RESHAPE, reshape can make progress before this IO + * is handled in make_stripe_request(), we can't know this here hence + * we set bits for both. + */ + *offset = min(start, prev_start); + *sectors = max(end, prev_end) - *offset; +} + static enum stripe_result make_stripe_request(struct mddev *mddev, struct r5conf *conf, struct stripe_request_ctx *ctx, sector_t logical_sector, struct bio *bi) @@ -8977,6 +8977,7 @@ static struct md_personality raid6_personality = .takeover = raid6_takeover, .change_consistency_policy = raid5_change_consistency_policy, .prepare_suspend = raid5_prepare_suspend, + .bitmap_sector = raid5_bitmap_sector, }; static struct md_personality raid5_personality = { @@ -9002,6 +9003,7 @@ static struct md_personality raid5_personality = .takeover = raid5_takeover, .change_consistency_policy = raid5_change_consistency_policy, .prepare_suspend = raid5_prepare_suspend, + .bitmap_sector = raid5_bitmap_sector, }; static struct md_personality raid4_personality = @@ -9028,6 +9030,7 @@ static struct md_personality raid4_personality = .takeover = raid4_takeover, .change_consistency_policy = raid5_change_consistency_policy, .prepare_suspend = raid5_prepare_suspend, + .bitmap_sector = raid5_bitmap_sector, }; static int __init raid5_init(void) diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h index 896ecfc4afa6..2e42c1641049 100644 --- a/drivers/md/raid5.h +++ b/drivers/md/raid5.h @@ -358,7 +358,6 @@ enum { STRIPE_REPLACED, STRIPE_PREREAD_ACTIVE, STRIPE_DELAYED, - STRIPE_DEGRADED, STRIPE_BIT_DELAY, STRIPE_EXPANDING, STRIPE_EXPAND_SOURCE, @@ -372,9 +371,6 @@ enum { STRIPE_ON_RELEASE_LIST, STRIPE_BATCH_READY, STRIPE_BATCH_ERR, - STRIPE_BITMAP_PENDING, /* Being added to bitmap, don't add - * to batch yet. - */ STRIPE_LOG_TRAPPED, /* trapped into log (see raid5-cache.c) * this bit is used in two scenarios: * |