diff options
Diffstat (limited to 'drivers/md')
29 files changed, 1897 insertions, 959 deletions
diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig index 3e01e6fb3424..0a2e7273db9e 100644 --- a/drivers/md/Kconfig +++ b/drivers/md/Kconfig @@ -123,6 +123,7 @@ config MD_RAID456 tristate "RAID-4/RAID-5/RAID-6 mode" depends on BLK_DEV_MD select RAID6_PQ + select LIBCRC32C select ASYNC_MEMCPY select ASYNC_XOR select ASYNC_PQ @@ -239,6 +240,15 @@ config DM_BUFIO as a cache, holding recently-read blocks in memory and performing delayed writes. +config DM_DEBUG_BLOCK_STACK_TRACING + bool "Keep stack trace of persistent data block lock holders" + depends on STACKTRACE_SUPPORT && DM_BUFIO + select STACKTRACE + ---help--- + Enable this for messages that may help debug problems with the + block manager locking used by thin provisioning and caching. + + If unsure, say N. config DM_BIO_PRISON tristate depends on BLK_DEV_DM @@ -457,6 +467,18 @@ config DM_VERITY If unsure, say N. +config DM_VERITY_FEC + bool "Verity forward error correction support" + depends on DM_VERITY + select REED_SOLOMON + select REED_SOLOMON_DEC8 + ---help--- + Add forward error correction support to dm-verity. This option + makes it possible to use pre-generated error correction data to + recover from corrupted blocks. + + If unsure, say N. + config DM_SWITCH tristate "Switch target support (EXPERIMENTAL)" depends on BLK_DEV_DM diff --git a/drivers/md/Makefile b/drivers/md/Makefile index f34979cd141a..62a65764e8e0 100644 --- a/drivers/md/Makefile +++ b/drivers/md/Makefile @@ -16,6 +16,7 @@ dm-cache-mq-y += dm-cache-policy-mq.o dm-cache-smq-y += dm-cache-policy-smq.o dm-cache-cleaner-y += dm-cache-policy-cleaner.o dm-era-y += dm-era-target.o +dm-verity-y += dm-verity-target.o md-mod-y += md.o bitmap.o raid456-y += raid5.o raid5-cache.o @@ -63,3 +64,7 @@ obj-$(CONFIG_DM_LOG_WRITES) += dm-log-writes.o ifeq ($(CONFIG_DM_UEVENT),y) dm-mod-objs += dm-uevent.o endif + +ifeq ($(CONFIG_DM_VERITY_FEC),y) +dm-verity-objs += dm-verity-fec.o +endif diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c index 8e9877b04637..25fa8445bb24 100644 --- a/drivers/md/bcache/request.c +++ b/drivers/md/bcache/request.c @@ -958,7 +958,8 @@ static void cached_dev_nodata(struct closure *cl) /* Cached devices - read & write stuff */ -static void cached_dev_make_request(struct request_queue *q, struct bio *bio) +static blk_qc_t cached_dev_make_request(struct request_queue *q, + struct bio *bio) { struct search *s; struct bcache_device *d = bio->bi_bdev->bd_disk->private_data; @@ -997,6 +998,8 @@ static void cached_dev_make_request(struct request_queue *q, struct bio *bio) else generic_make_request(bio); } + + return BLK_QC_T_NONE; } static int cached_dev_ioctl(struct bcache_device *d, fmode_t mode, @@ -1070,7 +1073,8 @@ static void flash_dev_nodata(struct closure *cl) continue_at(cl, search_free, NULL); } -static void flash_dev_make_request(struct request_queue *q, struct bio *bio) +static blk_qc_t flash_dev_make_request(struct request_queue *q, + struct bio *bio) { struct search *s; struct closure *cl; @@ -1093,7 +1097,7 @@ static void flash_dev_make_request(struct request_queue *q, struct bio *bio) continue_at_nobarrier(&s->cl, flash_dev_nodata, bcache_wq); - return; + return BLK_QC_T_NONE; } else if (rw) { bch_keybuf_check_overlapping(&s->iop.c->moving_gc_keys, &KEY(d->id, bio->bi_iter.bi_sector, 0), @@ -1109,6 +1113,7 @@ static void flash_dev_make_request(struct request_queue *q, struct bio *bio) } continue_at(cl, search_free, NULL); + return BLK_QC_T_NONE; } static int flash_dev_ioctl(struct bcache_device *d, fmode_t mode, diff --git a/drivers/md/bcache/util.c b/drivers/md/bcache/util.c index db3ae4c2b223..dde6172f3f10 100644 --- a/drivers/md/bcache/util.c +++ b/drivers/md/bcache/util.c @@ -230,7 +230,7 @@ void bch_bio_map(struct bio *bio, void *base) BUG_ON(!bio->bi_iter.bi_size); BUG_ON(bio->bi_vcnt); - bv->bv_offset = base ? ((unsigned long) base) % PAGE_SIZE : 0; + bv->bv_offset = base ? offset_in_page(base) : 0; goto start; for (; size; bio->bi_vcnt++, bv++) { diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index 2dd33085b331..cd77216beff1 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -16,6 +16,7 @@ #include <linux/shrinker.h> #include <linux/module.h> #include <linux/rbtree.h> +#include <linux/stacktrace.h> #define DM_MSG_PREFIX "bufio" @@ -149,6 +150,11 @@ struct dm_buffer { struct list_head write_list; struct bio bio; struct bio_vec bio_vec[DM_BUFIO_INLINE_VECS]; +#ifdef CONFIG_DM_DEBUG_BLOCK_STACK_TRACING +#define MAX_STACK 10 + struct stack_trace stack_trace; + unsigned long stack_entries[MAX_STACK]; +#endif }; /*----------------------------------------------------------------*/ @@ -253,6 +259,17 @@ static LIST_HEAD(dm_bufio_all_clients); */ static DEFINE_MUTEX(dm_bufio_clients_lock); +#ifdef CONFIG_DM_DEBUG_BLOCK_STACK_TRACING +static void buffer_record_stack(struct dm_buffer *b) +{ + b->stack_trace.nr_entries = 0; + b->stack_trace.max_entries = MAX_STACK; + b->stack_trace.entries = b->stack_entries; + b->stack_trace.skip = 2; + save_stack_trace(&b->stack_trace); +} +#endif + /*---------------------------------------------------------------- * A red/black tree acts as an index for all the buffers. *--------------------------------------------------------------*/ @@ -454,6 +471,9 @@ static struct dm_buffer *alloc_buffer(struct dm_bufio_client *c, gfp_t gfp_mask) adjust_total_allocated(b->data_mode, (long)c->block_size); +#ifdef CONFIG_DM_DEBUG_BLOCK_STACK_TRACING + memset(&b->stack_trace, 0, sizeof(b->stack_trace)); +#endif return b; } @@ -630,7 +650,7 @@ static void use_inline_bio(struct dm_buffer *b, int rw, sector_t block, do { if (!bio_add_page(&b->bio, virt_to_page(ptr), len < PAGE_SIZE ? len : PAGE_SIZE, - virt_to_phys(ptr) & (PAGE_SIZE - 1))) { + offset_in_page(ptr))) { BUG_ON(b->c->block_size <= PAGE_SIZE); use_dmio(b, rw, block, end_io); return; @@ -1063,12 +1083,16 @@ static void *new_read(struct dm_bufio_client *c, sector_t block, dm_bufio_lock(c); b = __bufio_new(c, block, nf, &need_submit, &write_list); +#ifdef CONFIG_DM_DEBUG_BLOCK_STACK_TRACING + if (b && b->hold_count == 1) + buffer_record_stack(b); +#endif dm_bufio_unlock(c); __flush_write_list(&write_list); if (!b) - return b; + return NULL; if (need_submit) submit_io(b, READ, b->block, read_endio); @@ -1462,6 +1486,7 @@ static void drop_buffers(struct dm_bufio_client *c) { struct dm_buffer *b; int i; + bool warned = false; BUG_ON(dm_bufio_in_request()); @@ -1476,9 +1501,21 @@ static void drop_buffers(struct dm_bufio_client *c) __free_buffer_wake(b); for (i = 0; i < LIST_SIZE; i++) - list_for_each_entry(b, &c->lru[i], lru_list) + list_for_each_entry(b, &c->lru[i], lru_list) { + WARN_ON(!warned); + warned = true; DMERR("leaked buffer %llx, hold count %u, list %d", (unsigned long long)b->block, b->hold_count, i); +#ifdef CONFIG_DM_DEBUG_BLOCK_STACK_TRACING + print_stack_trace(&b->stack_trace, 1); + b->hold_count = 0; /* mark unclaimed to avoid BUG_ON below */ +#endif + } + +#ifdef CONFIG_DM_DEBUG_BLOCK_STACK_TRACING + while ((b = __get_unclaimed_buffer(c))) + __free_buffer_wake(b); +#endif for (i = 0; i < LIST_SIZE; i++) BUG_ON(!list_empty(&c->lru[i])); @@ -1891,8 +1928,7 @@ static void __exit dm_bufio_exit(void) bug = 1; } - if (bug) - BUG(); + BUG_ON(bug); } module_init(dm_bufio_init) diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index 2fd4c8296144..5780accffa30 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -118,14 +118,12 @@ static void iot_io_end(struct io_tracker *iot, sector_t len) */ struct dm_hook_info { bio_end_io_t *bi_end_io; - void *bi_private; }; static void dm_hook_bio(struct dm_hook_info *h, struct bio *bio, bio_end_io_t *bi_end_io, void *bi_private) { h->bi_end_io = bio->bi_end_io; - h->bi_private = bio->bi_private; bio->bi_end_io = bi_end_io; bio->bi_private = bi_private; @@ -134,7 +132,6 @@ static void dm_hook_bio(struct dm_hook_info *h, struct bio *bio, static void dm_unhook_bio(struct dm_hook_info *h, struct bio *bio) { bio->bi_end_io = h->bi_end_io; - bio->bi_private = h->bi_private; } /*----------------------------------------------------------------*/ diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 3729b394432c..3147c8d09ea8 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -112,7 +112,8 @@ struct iv_tcw_private { * and encrypts / decrypts at the same time. */ enum flags { DM_CRYPT_SUSPENDED, DM_CRYPT_KEY_VALID, - DM_CRYPT_SAME_CPU, DM_CRYPT_NO_OFFLOAD }; + DM_CRYPT_SAME_CPU, DM_CRYPT_NO_OFFLOAD, + DM_CRYPT_EXIT_THREAD}; /* * The fields in here must be read only after initialization. @@ -994,7 +995,7 @@ static struct bio *crypt_alloc_buffer(struct dm_crypt_io *io, unsigned size) struct bio_vec *bvec; retry: - if (unlikely(gfp_mask & __GFP_WAIT)) + if (unlikely(gfp_mask & __GFP_DIRECT_RECLAIM)) mutex_lock(&cc->bio_alloc_lock); clone = bio_alloc_bioset(GFP_NOIO, nr_iovecs, cc->bs); @@ -1010,7 +1011,7 @@ retry: if (!page) { crypt_free_buffer_pages(cc, clone); bio_put(clone); - gfp_mask |= __GFP_WAIT; + gfp_mask |= __GFP_DIRECT_RECLAIM; goto retry; } @@ -1027,7 +1028,7 @@ retry: } return_clone: - if (unlikely(gfp_mask & __GFP_WAIT)) + if (unlikely(gfp_mask & __GFP_DIRECT_RECLAIM)) mutex_unlock(&cc->bio_alloc_lock); return clone; @@ -1203,20 +1204,18 @@ continue_locked: if (!RB_EMPTY_ROOT(&cc->write_tree)) goto pop_from_list; + if (unlikely(test_bit(DM_CRYPT_EXIT_THREAD, &cc->flags))) { + spin_unlock_irq(&cc->write_thread_wait.lock); + break; + } + __set_current_state(TASK_INTERRUPTIBLE); __add_wait_queue(&cc->write_thread_wait, &wait); spin_unlock_irq(&cc->write_thread_wait.lock); - if (unlikely(kthread_should_stop())) { - set_task_state(current, TASK_RUNNING); - remove_wait_queue(&cc->write_thread_wait, &wait); - break; - } - schedule(); - set_task_state(current, TASK_RUNNING); spin_lock_irq(&cc->write_thread_wait.lock); __remove_wait_queue(&cc->write_thread_wait, &wait); goto continue_locked; @@ -1531,8 +1530,13 @@ static void crypt_dtr(struct dm_target *ti) if (!cc) return; - if (cc->write_thread) + if (cc->write_thread) { + spin_lock_irq(&cc->write_thread_wait.lock); + set_bit(DM_CRYPT_EXIT_THREAD, &cc->flags); + wake_up_locked(&cc->write_thread_wait); + spin_unlock_irq(&cc->write_thread_wait.lock); kthread_stop(cc->write_thread); + } if (cc->io_queue) destroy_workqueue(cc->io_queue); diff --git a/drivers/md/dm-exception-store.h b/drivers/md/dm-exception-store.h index fae34e7a0b1e..12b5216c2cfe 100644 --- a/drivers/md/dm-exception-store.h +++ b/drivers/md/dm-exception-store.h @@ -69,7 +69,7 @@ struct dm_exception_store_type { * Update the metadata with this exception. */ void (*commit_exception) (struct dm_exception_store *store, - struct dm_exception *e, + struct dm_exception *e, int valid, void (*callback) (void *, int success), void *callback_context); diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c index 81c5e1a1f363..06d426eb5a30 100644 --- a/drivers/md/dm-io.c +++ b/drivers/md/dm-io.c @@ -246,7 +246,7 @@ static void vm_dp_init(struct dpages *dp, void *data) { dp->get_page = vm_get_page; dp->next_page = vm_next_page; - dp->context_u = ((unsigned long) data) & (PAGE_SIZE - 1); + dp->context_u = offset_in_page(data); dp->context_ptr = data; } @@ -271,7 +271,7 @@ static void km_dp_init(struct dpages *dp, void *data) { dp->get_page = km_get_page; dp->next_page = km_next_page; - dp->context_u = ((unsigned long) data) & (PAGE_SIZE - 1); + dp->context_u = offset_in_page(data); dp->context_ptr = data; } diff --git a/drivers/md/dm-kcopyd.c b/drivers/md/dm-kcopyd.c index 3a7cade5e27d..1452ed9aacb4 100644 --- a/drivers/md/dm-kcopyd.c +++ b/drivers/md/dm-kcopyd.c @@ -244,7 +244,7 @@ static int kcopyd_get_pages(struct dm_kcopyd_client *kc, *pages = NULL; do { - pl = alloc_pl(__GFP_NOWARN | __GFP_NORETRY); + pl = alloc_pl(__GFP_NOWARN | __GFP_NORETRY | __GFP_KSWAPD_RECLAIM); if (unlikely(!pl)) { /* Use reserved pages */ pl = kc->pages; diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index aaa6caa46a9f..cfa29f574c2a 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -1537,32 +1537,34 @@ static int multipath_prepare_ioctl(struct dm_target *ti, struct block_device **bdev, fmode_t *mode) { struct multipath *m = ti->private; - struct pgpath *pgpath; unsigned long flags; int r; - r = 0; - spin_lock_irqsave(&m->lock, flags); if (!m->current_pgpath) __choose_pgpath(m, 0); - pgpath = m->current_pgpath; - - if (pgpath) { - *bdev = pgpath->path.dev->bdev; - *mode = pgpath->path.dev->mode; + if (m->current_pgpath) { + if (!m->queue_io) { + *bdev = m->current_pgpath->path.dev->bdev; + *mode = m->current_pgpath->path.dev->mode; + r = 0; + } else { + /* pg_init has not started or completed */ + r = -ENOTCONN; + } + } else { + /* No path is available */ + if (m->queue_if_no_path) + r = -ENOTCONN; + else + r = -EIO; } - if ((pgpath && m->queue_io) || (!pgpath && m->queue_if_no_path)) - r = -ENOTCONN; - else if (!*bdev) - r = -EIO; - spin_unlock_irqrestore(&m->lock, flags); - if (r == -ENOTCONN && !fatal_signal_pending(current)) { + if (r == -ENOTCONN) { spin_lock_irqsave(&m->lock, flags); if (!m->current_pg) { /* Path status changed, redo selection */ diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c index 3164b8bce294..4d3909393f2c 100644 --- a/drivers/md/dm-snap-persistent.c +++ b/drivers/md/dm-snap-persistent.c @@ -695,7 +695,7 @@ static int persistent_prepare_exception(struct dm_exception_store *store, } static void persistent_commit_exception(struct dm_exception_store *store, - struct dm_exception *e, + struct dm_exception *e, int valid, void (*callback) (void *, int success), void *callback_context) { @@ -704,6 +704,9 @@ static void persistent_commit_exception(struct dm_exception_store *store, struct core_exception ce; struct commit_callback *cb; + if (!valid) + ps->valid = 0; + ce.old_chunk = e->old_chunk; ce.new_chunk = e->new_chunk; write_exception(ps, ps->current_committed++, &ce); diff --git a/drivers/md/dm-snap-transient.c b/drivers/md/dm-snap-transient.c index 9b7c8c8049d6..4d50a12cf00c 100644 --- a/drivers/md/dm-snap-transient.c +++ b/drivers/md/dm-snap-transient.c @@ -52,12 +52,12 @@ static int transient_prepare_exception(struct dm_exception_store *store, } static void transient_commit_exception(struct dm_exception_store *store, - struct dm_exception *e, + struct dm_exception *e, int valid, void (*callback) (void *, int success), void *callback_context) { /* Just succeed */ - callback(callback_context, 1); + callback(callback_context, valid); } static void transient_usage(struct dm_exception_store *store, diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c index c06b74e91cd6..3766386080a4 100644 --- a/drivers/md/dm-snap.c +++ b/drivers/md/dm-snap.c @@ -207,7 +207,6 @@ struct dm_snap_pending_exception { */ struct bio *full_bio; bio_end_io_t *full_bio_end_io; - void *full_bio_private; }; /* @@ -1438,8 +1437,9 @@ static void __invalidate_snapshot(struct dm_snapshot *s, int err) dm_table_event(s->ti->table); } -static void pending_complete(struct dm_snap_pending_exception *pe, int success) +static void pending_complete(void *context, int success) { + struct dm_snap_pending_exception *pe = context; struct dm_exception *e; struct dm_snapshot *s = pe->snap; struct bio *origin_bios = NULL; @@ -1485,10 +1485,8 @@ out: snapshot_bios = bio_list_get(&pe->snapshot_bios); origin_bios = bio_list_get(&pe->origin_bios); full_bio = pe->full_bio; - if (full_bio) { + if (full_bio) full_bio->bi_end_io = pe->full_bio_end_io; - full_bio->bi_private = pe->full_bio_private; - } increment_pending_exceptions_done_count(); up_write(&s->lock); @@ -1509,24 +1507,13 @@ out: free_pending_exception(pe); } -static void commit_callback(void *context, int success) -{ - struct dm_snap_pending_exception *pe = context; - - pending_complete(pe, success); -} - static void complete_exception(struct dm_snap_pending_exception *pe) { struct dm_snapshot *s = pe->snap; - if (unlikely(pe->copy_error)) - pending_complete(pe, 0); - - else - /* Update the metadata if we are persistent */ - s->store->type->commit_exception(s->store, &pe->e, - commit_callback, pe); + /* Update the metadata if we are persistent */ + s->store->type->commit_exception(s->store, &pe->e, !pe->copy_error, + pending_complete, pe); } /* @@ -1605,7 +1592,6 @@ static void start_full_bio(struct dm_snap_pending_exception *pe, pe->full_bio = bio; pe->full_bio_end_io = bio->bi_end_io; - pe->full_bio_private = bio->bi_private; callback_data = dm_kcopyd_prepare_callback(s->kcopyd_client, copy_callback, pe); diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c index 1fa45695b68a..f962d6453afd 100644 --- a/drivers/md/dm-thin-metadata.c +++ b/drivers/md/dm-thin-metadata.c @@ -1207,6 +1207,12 @@ static int __reserve_metadata_snap(struct dm_pool_metadata *pmd) dm_block_t held_root; /* + * We commit to ensure the btree roots which we increment in a + * moment are up to date. + */ + __commit_transaction(pmd); + + /* * Copy the superblock. */ dm_sm_inc_block(pmd->metadata_sm, THIN_SUPERBLOCK_LOCATION); @@ -1389,8 +1395,21 @@ static bool __snapshotted_since(struct dm_thin_device *td, uint32_t time) return td->snapshotted_time > time; } -int dm_thin_find_block(struct dm_thin_device *td, dm_block_t block, - int can_issue_io, struct dm_thin_lookup_result *result) +static void unpack_lookup_result(struct dm_thin_device *td, __le64 value, + struct dm_thin_lookup_result *result) +{ + uint64_t block_time = 0; + dm_block_t exception_block; + uint32_t exception_time; + + block_time = le64_to_cpu(value); + unpack_block_time(block_time, &exception_block, &exception_time); + result->block = exception_block; + result->shared = __snapshotted_since(td, exception_time); +} + +static int __find_block(struct dm_thin_device *td, dm_block_t block, + int can_issue_io, struct dm_thin_lookup_result *result) { int r; __le64 value; @@ -1398,39 +1417,56 @@ int dm_thin_find_block(struct dm_thin_device *td, dm_block_t block, dm_block_t keys[2] = { td->id, block }; struct dm_btree_info *info; - down_read(&pmd->root_lock); - if (pmd->fail_io) { - up_read(&pmd->root_lock); - return -EINVAL; - } - if (can_issue_io) { info = &pmd->info; } else info = &pmd->nb_info; r = dm_btree_lookup(info, pmd->root, keys, &value); - if (!r) { - uint64_t block_time = 0; - dm_block_t exception_block; - uint32_t exception_time; - - block_time = le64_to_cpu(value); - unpack_block_time(block_time, &exception_block, - &exception_time); - result->block = exception_block; - result->shared = __snapshotted_since(td, exception_time); + if (!r) + unpack_lookup_result(td, value, result); + + return r; +} + +int dm_thin_find_block(struct dm_thin_device *td, dm_block_t block, + int can_issue_io, struct dm_thin_lookup_result *result) +{ + int r; + struct dm_pool_metadata *pmd = td->pmd; + + down_read(&pmd->root_lock); + if (pmd->fail_io) { + up_read(&pmd->root_lock); + return -EINVAL; } + r = __find_block(td, block, can_issue_io, result); + up_read(&pmd->root_lock); return r; } -/* FIXME: write a more efficient one in btree */ -int dm_thin_find_mapped_range(struct dm_thin_device *td, - dm_block_t begin, dm_block_t end, - dm_block_t *thin_begin, dm_block_t *thin_end, - dm_block_t *pool_begin, bool *maybe_shared) +static int __find_next_mapped_block(struct dm_thin_device *td, dm_block_t block, + dm_block_t *vblock, + struct dm_thin_lookup_result *result) +{ + int r; + __le64 value; + struct dm_pool_metadata *pmd = td->pmd; + dm_block_t keys[2] = { td->id, block }; + + r = dm_btree_lookup_next(&pmd->info, pmd->root, keys, vblock, &value); + if (!r) + unpack_lookup_result(td, value, result); + + return r; +} + +static int __find_mapped_range(struct dm_thin_device *td, + dm_block_t begin, dm_block_t end, + dm_block_t *thin_begin, dm_block_t *thin_end, + dm_block_t *pool_begin, bool *maybe_shared) { int r; dm_block_t pool_end; @@ -1439,21 +1475,11 @@ int dm_thin_find_mapped_range(struct dm_thin_device *td, if (end < begin) return -ENODATA; - /* - * Find first mapped block. - */ - while (begin < end) { - r = dm_thin_find_block(td, begin, true, &lookup); - if (r) { - if (r != -ENODATA) - return r; - } else - break; - - begin++; - } + r = __find_next_mapped_block(td, begin, &begin, &lookup); + if (r) + return r; - if (begin == end) + if (begin >= end) return -ENODATA; *thin_begin = begin; @@ -1463,7 +1489,7 @@ int dm_thin_find_mapped_range(struct dm_thin_device *td, begin++; pool_end = *pool_begin + 1; while (begin != end) { - r = dm_thin_find_block(td, begin, true, &lookup); + r = __find_block(td, begin, true, &lookup); if (r) { if (r == -ENODATA) break; @@ -1483,6 +1509,24 @@ int dm_thin_find_mapped_range(struct dm_thin_device *td, return 0; } +int dm_thin_find_mapped_range(struct dm_thin_device *td, + dm_block_t begin, dm_block_t end, + dm_block_t *thin_begin, dm_block_t *thin_end, + dm_block_t *pool_begin, bool *maybe_shared) +{ + int r = -EINVAL; + struct dm_pool_metadata *pmd = td->pmd; + + down_read(&pmd->root_lock); + if (!pmd->fail_io) { + r = __find_mapped_range(td, begin, end, thin_begin, thin_end, + pool_begin, maybe_shared); + } + up_read(&pmd->root_lock); + + return r; +} + static int __insert(struct dm_thin_device *td, dm_block_t block, dm_block_t data_block) { @@ -1538,7 +1582,7 @@ static int __remove(struct dm_thin_device *td, dm_block_t block) static int __remove_range(struct dm_thin_device *td, dm_block_t begin, dm_block_t end) { int r; - unsigned count; + unsigned count, total_count = 0; struct dm_pool_metadata *pmd = td->pmd; dm_block_t keys[1] = { td->id }; __le64 value; @@ -1561,11 +1605,29 @@ static int __remove_range(struct dm_thin_device *td, dm_block_t begin, dm_block_ if (r) return r; - r = dm_btree_remove_leaves(&pmd->bl_info, mapping_root, &begin, end, &mapping_root, &count); - if (r) - return r; + /* + * Remove leaves stops at the first unmapped entry, so we have to + * loop round finding mapped ranges. + */ + while (begin < end) { + r = dm_btree_lookup_next(&pmd->bl_info, mapping_root, &begin, &begin, &value); + if (r == -ENODATA) + break; + + if (r) + return r; + + if (begin >= end) + break; + + r = dm_btree_remove_leaves(&pmd->bl_info, mapping_root, &begin, end, &mapping_root, &count); + if (r) + return r; + + total_count += count; + } - td->mapped_blocks -= count; + td->mapped_blocks -= total_count; td->changed = 1; /* diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index 3897b90bd462..72d91f477683 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -2432,6 +2432,7 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode) case PM_WRITE: if (old_mode != new_mode) notify_of_pool_mode_change(pool, "write"); + pool->pf.error_if_no_space = pt->requested_pf.error_if_no_space; dm_pool_metadata_read_write(pool->pmd); pool->process_bio = process_bio; pool->process_discard = process_discard_bio; @@ -3452,8 +3453,8 @@ static void pool_postsuspend(struct dm_target *ti) struct pool_c *pt = ti->private; struct pool *pool = pt->pool; - cancel_delayed_work(&pool->waker); - cancel_delayed_work(&pool->no_space_timeout); + cancel_delayed_work_sync(&pool->waker); + cancel_delayed_work_sync(&pool->no_space_timeout); flush_workqueue(pool->wq); (void) commit(pool); } @@ -3885,7 +3886,7 @@ static struct target_type pool_target = { .name = "thin-pool", .features = DM_TARGET_SINGLETON | DM_TARGET_ALWAYS_WRITEABLE | DM_TARGET_IMMUTABLE, - .version = {1, 16, 0}, + .version = {1, 17, 0}, .module = THIS_MODULE, .ctr = pool_ctr, .dtr = pool_dtr, @@ -4249,10 +4250,9 @@ static void thin_io_hints(struct dm_target *ti, struct queue_limits *limits) { struct thin_c *tc = ti->private; struct pool *pool = tc->pool; - struct queue_limits *pool_limits = dm_get_queue_limits(pool->pool_md); - if (!pool_limits->discard_granularity) - return; /* pool's discard support is disabled */ + if (!pool->pf.discard_enabled) + return; limits->discard_granularity = pool->sectors_per_block << SECTOR_SHIFT; limits->max_discard_sectors = 2048 * 1024 * 16; /* 16G */ @@ -4260,7 +4260,7 @@ static void thin_io_hints(struct dm_target *ti, struct queue_limits *limits) static struct target_type thin_target = { .name = "thin", - .version = {1, 16, 0}, + .version = {1, 17, 0}, .module = THIS_MODULE, .ctr = thin_ctr, .dtr = thin_dtr, diff --git a/drivers/md/dm-verity-fec.c b/drivers/md/dm-verity-fec.c new file mode 100644 index 000000000000..1cc10c4de701 --- /dev/null +++ b/drivers/md/dm-verity-fec.c @@ -0,0 +1,818 @@ +/* + * Copyright (C) 2015 Google, Inc. + * + * Author: Sami Tolvanen <samitolvanen@google.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the Free + * Software Foundation; either version 2 of the License, or (at your option) + * any later version. + */ + +#include "dm-verity-fec.h" +#include <linux/math64.h> + +#define DM_MSG_PREFIX "verity-fec" + +/* + * If error correction has been configured, returns true. + */ +bool verity_fec_is_enabled(struct dm_verity *v) +{ + return v->fec && v->fec->dev; +} + +/* + * Return a pointer to dm_verity_fec_io after dm_verity_io and its variable + * length fields. + */ +static inline struct dm_verity_fec_io *fec_io(struct dm_verity_io *io) +{ + return (struct dm_verity_fec_io *) verity_io_digest_end(io->v, io); +} + +/* + * Return an interleaved offset for a byte in RS block. + */ +static inline u64 fec_interleave(struct dm_verity *v, u64 offset) +{ + u32 mod; + + mod = do_div(offset, v->fec->rsn); + return offset + mod * (v->fec->rounds << v->data_dev_block_bits); +} + +/* + * Decode an RS block using Reed-Solomon. + */ +static int fec_decode_rs8(struct dm_verity *v, struct dm_verity_fec_io *fio, + u8 *data, u8 *fec, int neras) +{ + int i; + uint16_t par[DM_VERITY_FEC_RSM - DM_VERITY_FEC_MIN_RSN]; + + for (i = 0; i < v->fec->roots; i++) + par[i] = fec[i]; + + return decode_rs8(fio->rs, data, par, v->fec->rsn, NULL, neras, + fio->erasures, 0, NULL); +} + +/* + * Read error-correcting codes for the requested RS block. Returns a pointer + * to the data block. Caller is responsible for releasing buf. + */ +static u8 *fec_read_parity(struct dm_verity *v, u64 rsb, int index, + unsigned *offset, struct dm_buffer **buf) +{ + u64 position, block; + u8 *res; + + position = (index + rsb) * v->fec->roots; + block = position >> v->data_dev_block_bits; + *offset = (unsigned)(position - (block << v->data_dev_block_bits)); + + res = dm_bufio_read(v->fec->bufio, v->fec->start + block, buf); + if (unlikely(IS_ERR(res))) { + DMERR("%s: FEC %llu: parity read failed (block %llu): %ld", + v->data_dev->name, (unsigned long long)rsb, + (unsigned long long)(v->fec->start + block), + PTR_ERR(res)); + *buf = NULL; + } + + return res; +} + +/* Loop over each preallocated buffer slot. */ +#define fec_for_each_prealloc_buffer(__i) \ + for (__i = 0; __i < DM_VERITY_FEC_BUF_PREALLOC; __i++) + +/* Loop over each extra buffer slot. */ +#define fec_for_each_extra_buffer(io, __i) \ + for (__i = DM_VERITY_FEC_BUF_PREALLOC; __i < DM_VERITY_FEC_BUF_MAX; __i++) + +/* Loop over each allocated buffer. */ +#define fec_for_each_buffer(io, __i) \ + for (__i = 0; __i < (io)->nbufs; __i++) + +/* Loop over each RS block in each allocated buffer. */ +#define fec_for_each_buffer_rs_block(io, __i, __j) \ + fec_for_each_buffer(io, __i) \ + for (__j = 0; __j < 1 << DM_VERITY_FEC_BUF_RS_BITS; __j++) + +/* + * Return a pointer to the current RS block when called inside + * fec_for_each_buffer_rs_block. + */ +static inline u8 *fec_buffer_rs_block(struct dm_verity *v, + struct dm_verity_fec_io *fio, + unsigned i, unsigned j) +{ + return &fio->bufs[i][j * v->fec->rsn]; +} + +/* + * Return an index to the current RS block when called inside + * fec_for_each_buffer_rs_block. + */ +static inline unsigned fec_buffer_rs_index(unsigned i, unsigned j) +{ + return (i << DM_VERITY_FEC_BUF_RS_BITS) + j; +} + +/* + * Decode all RS blocks from buffers and copy corrected bytes into fio->output + * starting from block_offset. + */ +static int fec_decode_bufs(struct dm_verity *v, struct dm_verity_fec_io *fio, + u64 rsb, int byte_index, unsigned block_offset, + int neras) +{ + int r, corrected = 0, res; + struct dm_buffer *buf; + unsigned n, i, offset; + u8 *par, *block; + + par = fec_read_parity(v, rsb, block_offset, &offset, &buf); + if (IS_ERR(par)) + return PTR_ERR(par); + + /* + * Decode the RS blocks we have in bufs. Each RS block results in + * one corrected target byte and consumes fec->roots parity bytes. + */ + fec_for_each_buffer_rs_block(fio, n, i) { + block = fec_buffer_rs_block(v, fio, n, i); + res = fec_decode_rs8(v, fio, block, &par[offset], neras); + if (res < 0) { + dm_bufio_release(buf); + + r = res; + goto error; + } + + corrected += res; + fio->output[block_offset] = block[byte_index]; + + block_offset++; + if (block_offset >= 1 << v->data_dev_block_bits) + goto done; + + /* read the next block when we run out of parity bytes */ + offset += v->fec->roots; + if (offset >= 1 << v->data_dev_block_bits) { + dm_bufio_release(buf); + + par = fec_read_parity(v, rsb, block_offset, &offset, &buf); + if (unlikely(IS_ERR(par))) + return PTR_ERR(par); + } + } +done: + r = corrected; +error: + if (r < 0 && neras) + DMERR_LIMIT("%s: FEC %llu: failed to correct: %d", + v->data_dev->name, (unsigned long long)rsb, r); + else if (r > 0) + DMWARN_LIMIT("%s: FEC %llu: corrected %d errors", + v->data_dev->name, (unsigned long long)rsb, r); + + return r; +} + +/* + * Locate data block erasures using verity hashes. + */ +static int fec_is_erasure(struct dm_verity *v, struct dm_verity_io *io, + u8 *want_digest, u8 *data) +{ + if (unlikely(verity_hash(v, verity_io_hash_desc(v, io), + data, 1 << v->data_dev_block_bits, + verity_io_real_digest(v, io)))) + return 0; + + return memcmp(verity_io_real_digest(v, io), want_digest, + v->digest_size) != 0; +} + +/* + * Read data blocks that are part of the RS block and deinterleave as much as + * fits into buffers. Check for erasure locations if @neras is non-NULL. + */ +static int fec_read_bufs(struct dm_verity *v, struct dm_verity_io *io, + u64 rsb, u64 target, unsigned block_offset, + int *neras) +{ + bool is_zero; + int i, j, target_index = -1; + struct dm_buffer *buf; + struct dm_bufio_client *bufio; + struct dm_verity_fec_io *fio = fec_io(io); + u64 block, ileaved; + u8 *bbuf, *rs_block; + u8 want_digest[v->digest_size]; + unsigned n, k; + + if (neras) + *neras = 0; + + /* + * read each of the rsn data blocks that are part of the RS block, and + * interleave contents to available bufs + */ + for (i = 0; i < v->fec->rsn; i++) { + ileaved = fec_interleave(v, rsb * v->fec->rsn + i); + + /* + * target is the data block we want to correct, target_index is + * the index of this block within the rsn RS blocks + */ + if (ileaved == target) + target_index = i; + + block = ileaved >> v->data_dev_block_bits; + bufio = v->fec->data_bufio; + + if (block >= v->data_blocks) { + block -= v->data_blocks; + + /* + * blocks outside the area were assumed to contain + * zeros when encoding data was generated + */ + if (unlikely(block >= v->fec->hash_blocks)) + continue; + + block += v->hash_start; + bufio = v->bufio; + } + + bbuf = dm_bufio_read(bufio, block, &buf); + if (unlikely(IS_ERR(bbuf))) { + DMWARN_LIMIT("%s: FEC %llu: read failed (%llu): %ld", + v->data_dev->name, + (unsigned long long)rsb, + (unsigned long long)block, PTR_ERR(bbuf)); + + /* assume the block is corrupted */ + if (neras && *neras <= v->fec->roots) + fio->erasures[(*neras)++] = i; + + continue; + } + + /* locate erasures if the block is on the data device */ + if (bufio == v->fec->data_bufio && + verity_hash_for_block(v, io, block, want_digest, + &is_zero) == 0) { + /* skip known zero blocks entirely */ + if (is_zero) + continue; + + /* + * skip if we have already found the theoretical + * maximum number (i.e. fec->roots) of erasures + */ + if (neras && *neras <= v->fec->roots && + fec_is_erasure(v, io, want_digest, bbuf)) + fio->erasures[(*neras)++] = i; + } + + /* + * deinterleave and copy the bytes that fit into bufs, + * starting from block_offset + */ + fec_for_each_buffer_rs_block(fio, n, j) { + k = fec_buffer_rs_index(n, j) + block_offset; + + if (k >= 1 << v->data_dev_block_bits) + goto done; + + rs_block = fec_buffer_rs_block(v, fio, n, j); + rs_block[i] = bbuf[k]; + } +done: + dm_bufio_release(buf); + } + + return target_index; +} + +/* + * Allocate RS control structure and FEC buffers from preallocated mempools, + * and attempt to allocate as many extra buffers as available. + */ +static int fec_alloc_bufs(struct dm_verity *v, struct dm_verity_fec_io *fio) +{ + unsigned n; + + if (!fio->rs) { + fio->rs = mempool_alloc(v->fec->rs_pool, 0); + if (unlikely(!fio->rs)) { + DMERR("failed to allocate RS"); + return -ENOMEM; + } + } + + fec_for_each_prealloc_buffer(n) { + if (fio->bufs[n]) + continue; + + fio->bufs[n] = mempool_alloc(v->fec->prealloc_pool, GFP_NOIO); + if (unlikely(!fio->bufs[n])) { + DMERR("failed to allocate FEC buffer"); + return -ENOMEM; + } + } + + /* try to allocate the maximum number of buffers */ + fec_for_each_extra_buffer(fio, n) { + if (fio->bufs[n]) + continue; + + fio->bufs[n] = mempool_alloc(v->fec->extra_pool, GFP_NOIO); + /* we can manage with even one buffer if necessary */ + if (unlikely(!fio->bufs[n])) + break; + } + fio->nbufs = n; + + if (!fio->output) { + fio->output = mempool_alloc(v->fec->output_pool, GFP_NOIO); + + if (!fio->output) { + DMERR("failed to allocate FEC page"); + return -ENOMEM; + } + } + + return 0; +} + +/* + * Initialize buffers and clear erasures. fec_read_bufs() assumes buffers are + * zeroed before deinterleaving. + */ +static void fec_init_bufs(struct dm_verity *v, struct dm_verity_fec_io *fio) +{ + unsigned n; + + fec_for_each_buffer(fio, n) + memset(fio->bufs[n], 0, v->fec->rsn << DM_VERITY_FEC_BUF_RS_BITS); + + memset(fio->erasures, 0, sizeof(fio->erasures)); +} + +/* + * Decode all RS blocks in a single data block and return the target block + * (indicated by @offset) in fio->output. If @use_erasures is non-zero, uses + * hashes to locate erasures. + */ +static int fec_decode_rsb(struct dm_verity *v, struct dm_verity_io *io, + struct dm_verity_fec_io *fio, u64 rsb, u64 offset, + bool use_erasures) +{ + int r, neras = 0; + unsigned pos; + + r = fec_alloc_bufs(v, fio); + if (unlikely(r < 0)) + return r; + + for (pos = 0; pos < 1 << v->data_dev_block_bits; ) { + fec_init_bufs(v, fio); + + r = fec_read_bufs(v, io, rsb, offset, pos, + use_erasures ? &neras : NULL); + if (unlikely(r < 0)) + return r; + + r = fec_decode_bufs(v, fio, rsb, r, pos, neras); + if (r < 0) + return r; + + pos += fio->nbufs << DM_VERITY_FEC_BUF_RS_BITS; + } + + /* Always re-validate the corrected block against the expected hash */ + r = verity_hash(v, verity_io_hash_desc(v, io), fio->output, + 1 << v->data_dev_block_bits, + verity_io_real_digest(v, io)); + if (unlikely(r < 0)) + return r; + + if (memcmp(verity_io_real_digest(v, io), verity_io_want_digest(v, io), + v->digest_size)) { + DMERR_LIMIT("%s: FEC %llu: failed to correct (%d erasures)", + v->data_dev->name, (unsigned long long)rsb, neras); + return -EILSEQ; + } + + return 0; +} + +static int fec_bv_copy(struct dm_verity *v, struct dm_verity_io *io, u8 *data, + size_t len) +{ + struct dm_verity_fec_io *fio = fec_io(io); + + memcpy(data, &fio->output[fio->output_pos], len); + fio->output_pos += len; + + return 0; +} + +/* + * Correct errors in a block. Copies corrected block to dest if non-NULL, + * otherwise to a bio_vec starting from iter. + */ +int verity_fec_decode(struct dm_verity *v, struct dm_verity_io *io, + enum verity_block_type type, sector_t block, u8 *dest, + struct bvec_iter *iter) +{ + int r; + struct dm_verity_fec_io *fio = fec_io(io); + u64 offset, res, rsb; + + if (!verity_fec_is_enabled(v)) + return -EOPNOTSUPP; + + if (type == DM_VERITY_BLOCK_TYPE_METADATA) + block += v->data_blocks; + + /* + * For RS(M, N), the continuous FEC data is divided into blocks of N + * bytes. Since block size may not be divisible by N, the last block + * is zero padded when decoding. + * + * Each byte of the block is covered by a different RS(M, N) code, + * and each code is interleaved over N blocks to make it less likely + * that bursty corruption will leave us in unrecoverable state. + */ + + offset = block << v->data_dev_block_bits; + + res = offset; + div64_u64(res, v->fec->rounds << v->data_dev_block_bits); + + /* + * The base RS block we can feed to the interleaver to find out all + * blocks required for decoding. + */ + rsb = offset - res * (v->fec->rounds << v->data_dev_block_bits); + + /* + * Locating erasures is slow, so attempt to recover the block without + * them first. Do a second attempt with erasures if the corruption is + * bad enough. + */ + r = fec_decode_rsb(v, io, fio, rsb, offset, false); + if (r < 0) { + r = fec_decode_rsb(v, io, fio, rsb, offset, true); + if (r < 0) + return r; + } + + if (dest) + memcpy(dest, fio->output, 1 << v->data_dev_block_bits); + else if (iter) { + fio->output_pos = 0; + r = verity_for_bv_block(v, io, iter, fec_bv_copy); + } + + return r; +} + +/* + * Clean up per-bio data. + */ +void verity_fec_finish_io(struct dm_verity_io *io) +{ + unsigned n; + struct dm_verity_fec *f = io->v->fec; + struct dm_verity_fec_io *fio = fec_io(io); + + if (!verity_fec_is_enabled(io->v)) + return; + + mempool_free(fio->rs, f->rs_pool); + + fec_for_each_prealloc_buffer(n) + mempool_free(fio->bufs[n], f->prealloc_pool); + + fec_for_each_extra_buffer(fio, n) + mempool_free(fio->bufs[n], f->extra_pool); + + mempool_free(fio->output, f->output_pool); +} + +/* + * Initialize per-bio data. + */ +void verity_fec_init_io(struct dm_verity_io *io) +{ + struct dm_verity_fec_io *fio = fec_io(io); + + if (!verity_fec_is_enabled(io->v)) + return; + + fio->rs = NULL; + memset(fio->bufs, 0, sizeof(fio->bufs)); + fio->nbufs = 0; + fio->output = NULL; +} + +/* + * Append feature arguments and values to the status table. + */ +unsigned verity_fec_status_table(struct dm_verity *v, unsigned sz, + char *result, unsigned maxlen) +{ + if (!verity_fec_is_enabled(v)) + return sz; + + DMEMIT(" " DM_VERITY_OPT_FEC_DEV " %s " + DM_VERITY_OPT_FEC_BLOCKS " %llu " + DM_VERITY_OPT_FEC_START " %llu " + DM_VERITY_OPT_FEC_ROOTS " %d", + v->fec->dev->name, + (unsigned long long)v->fec->blocks, + (unsigned long long)v->fec->start, + v->fec->roots); + + return sz; +} + +void verity_fec_dtr(struct dm_verity *v) +{ + struct dm_verity_fec *f = v->fec; + + if (!verity_fec_is_enabled(v)) + goto out; + + mempool_destroy(f->rs_pool); + mempool_destroy(f->prealloc_pool); + mempool_destroy(f->extra_pool); + kmem_cache_destroy(f->cache); + + if (f->data_bufio) + dm_bufio_client_destroy(f->data_bufio); + if (f->bufio) + dm_bufio_client_destroy(f->bufio); + + if (f->dev) + dm_put_device(v->ti, f->dev); +out: + kfree(f); + v->fec = NULL; +} + +static void *fec_rs_alloc(gfp_t gfp_mask, void *pool_data) +{ + struct dm_verity *v = (struct dm_verity *)pool_data; + + return init_rs(8, 0x11d, 0, 1, v->fec->roots); +} + +static void fec_rs_free(void *element, void *pool_data) +{ + struct rs_control *rs = (struct rs_control *)element; + + if (rs) + free_rs(rs); +} + +bool verity_is_fec_opt_arg(const char *arg_name) +{ + return (!strcasecmp(arg_name, DM_VERITY_OPT_FEC_DEV) || + !strcasecmp(arg_name, DM_VERITY_OPT_FEC_BLOCKS) || + !strcasecmp(arg_name, DM_VERITY_OPT_FEC_START) || + !strcasecmp(arg_name, DM_VERITY_OPT_FEC_ROOTS)); +} + +int verity_fec_parse_opt_args(struct dm_arg_set *as, struct dm_verity *v, + unsigned *argc, const char *arg_name) +{ + int r; + struct dm_target *ti = v->ti; + const char *arg_value; + unsigned long long num_ll; + unsigned char num_c; + char dummy; + + if (!*argc) { + ti->error = "FEC feature arguments require a value"; + return -EINVAL; + } + + arg_value = dm_shift_arg(as); + (*argc)--; + + if (!strcasecmp(arg_name, DM_VERITY_OPT_FEC_DEV)) { + r = dm_get_device(ti, arg_value, FMODE_READ, &v->fec->dev); + if (r) { + ti->error = "FEC device lookup failed"; + return r; + } + + } else if (!strcasecmp(arg_name, DM_VERITY_OPT_FEC_BLOCKS)) { + if (sscanf(arg_value, "%llu%c", &num_ll, &dummy) != 1 || + ((sector_t)(num_ll << (v->data_dev_block_bits - SECTOR_SHIFT)) + >> (v->data_dev_block_bits - SECTOR_SHIFT) != num_ll)) { + ti->error = "Invalid " DM_VERITY_OPT_FEC_BLOCKS; + return -EINVAL; + } + v->fec->blocks = num_ll; + + } else if (!strcasecmp(arg_name, DM_VERITY_OPT_FEC_START)) { + if (sscanf(arg_value, "%llu%c", &num_ll, &dummy) != 1 || + ((sector_t)(num_ll << (v->data_dev_block_bits - SECTOR_SHIFT)) >> + (v->data_dev_block_bits - SECTOR_SHIFT) != num_ll)) { + ti->error = "Invalid " DM_VERITY_OPT_FEC_START; + return -EINVAL; + } + v->fec->start = num_ll; + + } else if (!strcasecmp(arg_name, DM_VERITY_OPT_FEC_ROOTS)) { + if (sscanf(arg_value, "%hhu%c", &num_c, &dummy) != 1 || !num_c || + num_c < (DM_VERITY_FEC_RSM - DM_VERITY_FEC_MAX_RSN) || + num_c > (DM_VERITY_FEC_RSM - DM_VERITY_FEC_MIN_RSN)) { + ti->error = "Invalid " DM_VERITY_OPT_FEC_ROOTS; + return -EINVAL; + } + v->fec->roots = num_c; + + } else { + ti->error = "Unrecognized verity FEC feature request"; + return -EINVAL; + } + + return 0; +} + +/* + * Allocate dm_verity_fec for v->fec. Must be called before verity_fec_ctr. + */ +int verity_fec_ctr_alloc(struct dm_verity *v) +{ + struct dm_verity_fec *f; + + f = kzalloc(sizeof(struct dm_verity_fec), GFP_KERNEL); + if (!f) { + v->ti->error = "Cannot allocate FEC structure"; + return -ENOMEM; + } + v->fec = f; + + return 0; +} + +/* + * Validate arguments and preallocate memory. Must be called after arguments + * have been parsed using verity_fec_parse_opt_args. + */ +int verity_fec_ctr(struct dm_verity *v) +{ + struct dm_verity_fec *f = v->fec; + struct dm_target *ti = v->ti; + u64 hash_blocks; + + if (!verity_fec_is_enabled(v)) { + verity_fec_dtr(v); + return 0; + } + + /* + * FEC is computed over data blocks, possible metadata, and + * hash blocks. In other words, FEC covers total of fec_blocks + * blocks consisting of the following: + * + * data blocks | hash blocks | metadata (optional) + * + * We allow metadata after hash blocks to support a use case + * where all data is stored on the same device and FEC covers + * the entire area. + * + * If metadata is included, we require it to be available on the + * hash device after the hash blocks. + */ + + hash_blocks = v->hash_blocks - v->hash_start; + + /* + * Require matching block sizes for data and hash devices for + * simplicity. + */ + if (v->data_dev_block_bits != v->hash_dev_block_bits) { + ti->error = "Block sizes must match to use FEC"; + return -EINVAL; + } + + if (!f->roots) { + ti->error = "Missing " DM_VERITY_OPT_FEC_ROOTS; + return -EINVAL; + } + f->rsn = DM_VERITY_FEC_RSM - f->roots; + + if (!f->blocks) { + ti->error = "Missing " DM_VERITY_OPT_FEC_BLOCKS; + return -EINVAL; + } + + f->rounds = f->blocks; + if (sector_div(f->rounds, f->rsn)) + f->rounds++; + + /* + * Due to optional metadata, f->blocks can be larger than + * data_blocks and hash_blocks combined. + */ + if (f->blocks < v->data_blocks + hash_blocks || !f->rounds) { + ti->error = "Invalid " DM_VERITY_OPT_FEC_BLOCKS; + return -EINVAL; + } + + /* + * Metadata is accessed through the hash device, so we require + * it to be large enough. + */ + f->hash_blocks = f->blocks - v->data_blocks; + if (dm_bufio_get_device_size(v->bufio) < f->hash_blocks) { + ti->error = "Hash device is too small for " + DM_VERITY_OPT_FEC_BLOCKS; + return -E2BIG; + } + + f->bufio = dm_bufio_client_create(f->dev->bdev, + 1 << v->data_dev_block_bits, + 1, 0, NULL, NULL); + if (IS_ERR(f->bufio)) { + ti->error = "Cannot initialize FEC bufio client"; + return PTR_ERR(f->bufio); + } + + if (dm_bufio_get_device_size(f->bufio) < + ((f->start + f->rounds * f->roots) >> v->data_dev_block_bits)) { + ti->error = "FEC device is too small"; + return -E2BIG; + } + + f->data_bufio = dm_bufio_client_create(v->data_dev->bdev, + 1 << v->data_dev_block_bits, + 1, 0, NULL, NULL); + if (IS_ERR(f->data_bufio)) { + ti->error = "Cannot initialize FEC data bufio client"; + return PTR_ERR(f->data_bufio); + } + + if (dm_bufio_get_device_size(f->data_bufio) < v->data_blocks) { + ti->error = "Data device is too small"; + return -E2BIG; + } + + /* Preallocate an rs_control structure for each worker thread */ + f->rs_pool = mempool_create(num_online_cpus(), fec_rs_alloc, + fec_rs_free, (void *) v); + if (!f->rs_pool) { + ti->error = "Cannot allocate RS pool"; + return -ENOMEM; + } + + f->cache = kmem_cache_create("dm_verity_fec_buffers", + f->rsn << DM_VERITY_FEC_BUF_RS_BITS, + 0, 0, NULL); + if (!f->cache) { + ti->error = "Cannot create FEC buffer cache"; + return -ENOMEM; + } + + /* Preallocate DM_VERITY_FEC_BUF_PREALLOC buffers for each thread */ + f->prealloc_pool = mempool_create_slab_pool(num_online_cpus() * + DM_VERITY_FEC_BUF_PREALLOC, + f->cache); + if (!f->prealloc_pool) { + ti->error = "Cannot allocate FEC buffer prealloc pool"; + return -ENOMEM; + } + + f->extra_pool = mempool_create_slab_pool(0, f->cache); + if (!f->extra_pool) { + ti->error = "Cannot allocate FEC buffer extra pool"; + return -ENOMEM; + } + + /* Preallocate an output buffer for each thread */ + f->output_pool = mempool_create_kmalloc_pool(num_online_cpus(), + 1 << v->data_dev_block_bits); + if (!f->output_pool) { + ti->error = "Cannot allocate FEC output pool"; + return -ENOMEM; + } + + /* Reserve space for our per-bio data */ + ti->per_bio_data_size += sizeof(struct dm_verity_fec_io); + + return 0; +} diff --git a/drivers/md/dm-verity-fec.h b/drivers/md/dm-verity-fec.h new file mode 100644 index 000000000000..7fa0298b995e --- /dev/null +++ b/drivers/md/dm-verity-fec.h @@ -0,0 +1,152 @@ +/* + * Copyright (C) 2015 Google, Inc. + * + * Author: Sami Tolvanen <samitolvanen@google.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the Free + * Software Foundation; either version 2 of the License, or (at your option) + * any later version. + */ + +#ifndef DM_VERITY_FEC_H +#define DM_VERITY_FEC_H + +#include "dm-verity.h" +#include <linux/rslib.h> + +/* Reed-Solomon(M, N) parameters */ +#define DM_VERITY_FEC_RSM 255 +#define DM_VERITY_FEC_MAX_RSN 253 +#define DM_VERITY_FEC_MIN_RSN 231 /* ~10% space overhead */ + +/* buffers for deinterleaving and decoding */ +#define DM_VERITY_FEC_BUF_PREALLOC 1 /* buffers to preallocate */ +#define DM_VERITY_FEC_BUF_RS_BITS 4 /* 1 << RS blocks per buffer */ +/* we need buffers for at most 1 << block size RS blocks */ +#define DM_VERITY_FEC_BUF_MAX \ + (1 << (PAGE_SHIFT - DM_VERITY_FEC_BUF_RS_BITS)) + +#define DM_VERITY_OPT_FEC_DEV "use_fec_from_device" +#define DM_VERITY_OPT_FEC_BLOCKS "fec_blocks" +#define DM_VERITY_OPT_FEC_START "fec_start" +#define DM_VERITY_OPT_FEC_ROOTS "fec_roots" + +/* configuration */ +struct dm_verity_fec { + struct dm_dev *dev; /* parity data device */ + struct dm_bufio_client *data_bufio; /* for data dev access */ + struct dm_bufio_client *bufio; /* for parity data access */ + sector_t start; /* parity data start in blocks */ + sector_t blocks; /* number of blocks covered */ + sector_t rounds; /* number of interleaving rounds */ + sector_t hash_blocks; /* blocks covered after v->hash_start */ + unsigned char roots; /* number of parity bytes, M-N of RS(M, N) */ + unsigned char rsn; /* N of RS(M, N) */ + mempool_t *rs_pool; /* mempool for fio->rs */ + mempool_t *prealloc_pool; /* mempool for preallocated buffers */ + mempool_t *extra_pool; /* mempool for extra buffers */ + mempool_t *output_pool; /* mempool for output */ + struct kmem_cache *cache; /* cache for buffers */ +}; + +/* per-bio data */ +struct dm_verity_fec_io { + struct rs_control *rs; /* Reed-Solomon state */ + int erasures[DM_VERITY_FEC_MAX_RSN]; /* erasures for decode_rs8 */ + u8 *bufs[DM_VERITY_FEC_BUF_MAX]; /* bufs for deinterleaving */ + unsigned nbufs; /* number of buffers allocated */ + u8 *output; /* buffer for corrected output */ + size_t output_pos; +}; + +#ifdef CONFIG_DM_VERITY_FEC + +/* each feature parameter requires a value */ +#define DM_VERITY_OPTS_FEC 8 + +extern bool verity_fec_is_enabled(struct dm_verity *v); + +extern int verity_fec_decode(struct dm_verity *v, struct dm_verity_io *io, + enum verity_block_type type, sector_t block, + u8 *dest, struct bvec_iter *iter); + +extern unsigned verity_fec_status_table(struct dm_verity *v, unsigned sz, + char *result, unsigned maxlen); + +extern void verity_fec_finish_io(struct dm_verity_io *io); +extern void verity_fec_init_io(struct dm_verity_io *io); + +extern bool verity_is_fec_opt_arg(const char *arg_name); +extern int verity_fec_parse_opt_args(struct dm_arg_set *as, + struct dm_verity *v, unsigned *argc, + const char *arg_name); + +extern void verity_fec_dtr(struct dm_verity *v); + +extern int verity_fec_ctr_alloc(struct dm_verity *v); +extern int verity_fec_ctr(struct dm_verity *v); + +#else /* !CONFIG_DM_VERITY_FEC */ + +#define DM_VERITY_OPTS_FEC 0 + +static inline bool verity_fec_is_enabled(struct dm_verity *v) +{ + return false; +} + +static inline int verity_fec_decode(struct dm_verity *v, + struct dm_verity_io *io, + enum verity_block_type type, + sector_t block, u8 *dest, + struct bvec_iter *iter) +{ + return -EOPNOTSUPP; +} + +static inline unsigned verity_fec_status_table(struct dm_verity *v, + unsigned sz, char *result, + unsigned maxlen) +{ + return sz; +} + +static inline void verity_fec_finish_io(struct dm_verity_io *io) +{ +} + +static inline void verity_fec_init_io(struct dm_verity_io *io) +{ +} + +static inline bool verity_is_fec_opt_arg(const char *arg_name) +{ + return false; +} + +static inline int verity_fec_parse_opt_args(struct dm_arg_set *as, + struct dm_verity *v, + unsigned *argc, + const char *arg_name) +{ + return -EINVAL; +} + +static inline void verity_fec_dtr(struct dm_verity *v) +{ +} + +static inline int verity_fec_ctr_alloc(struct dm_verity *v) +{ + return 0; +} + +static inline int verity_fec_ctr(struct dm_verity *v) +{ + return 0; +} + +#endif /* CONFIG_DM_VERITY_FEC */ + +#endif /* DM_VERITY_FEC_H */ diff --git a/drivers/md/dm-verity.c b/drivers/md/dm-verity-target.c index ccf41886ebcf..5c5d30cb6ec5 100644 --- a/drivers/md/dm-verity.c +++ b/drivers/md/dm-verity-target.c @@ -14,12 +14,11 @@ * access behavior. */ -#include "dm-bufio.h" +#include "dm-verity.h" +#include "dm-verity-fec.h" #include <linux/module.h> -#include <linux/device-mapper.h> #include <linux/reboot.h> -#include <crypto/hash.h> #define DM_MSG_PREFIX "verity" @@ -28,83 +27,18 @@ #define DM_VERITY_DEFAULT_PREFETCH_SIZE 262144 -#define DM_VERITY_MAX_LEVELS 63 #define DM_VERITY_MAX_CORRUPTED_ERRS 100 #define DM_VERITY_OPT_LOGGING "ignore_corruption" #define DM_VERITY_OPT_RESTART "restart_on_corruption" +#define DM_VERITY_OPT_IGN_ZEROES "ignore_zero_blocks" + +#define DM_VERITY_OPTS_MAX (2 + DM_VERITY_OPTS_FEC) static unsigned dm_verity_prefetch_cluster = DM_VERITY_DEFAULT_PREFETCH_SIZE; module_param_named(prefetch_cluster, dm_verity_prefetch_cluster, uint, S_IRUGO | S_IWUSR); -enum verity_mode { - DM_VERITY_MODE_EIO, - DM_VERITY_MODE_LOGGING, - DM_VERITY_MODE_RESTART -}; - -enum verity_block_type { - DM_VERITY_BLOCK_TYPE_DATA, - DM_VERITY_BLOCK_TYPE_METADATA -}; - -struct dm_verity { - struct dm_dev *data_dev; - struct dm_dev *hash_dev; - struct dm_target *ti; - struct dm_bufio_client *bufio; - char *alg_name; - struct crypto_shash *tfm; - u8 *root_digest; /* digest of the root block */ - u8 *salt; /* salt: its size is salt_size */ - unsigned salt_size; - sector_t data_start; /* data offset in 512-byte sectors */ - sector_t hash_start; /* hash start in blocks */ - sector_t data_blocks; /* the number of data blocks */ - sector_t hash_blocks; /* the number of hash blocks */ - unsigned char data_dev_block_bits; /* log2(data blocksize) */ - unsigned char hash_dev_block_bits; /* log2(hash blocksize) */ - unsigned char hash_per_block_bits; /* log2(hashes in hash block) */ - unsigned char levels; /* the number of tree levels */ - unsigned char version; - unsigned digest_size; /* digest size for the current hash algorithm */ - unsigned shash_descsize;/* the size of temporary space for crypto */ - int hash_failed; /* set to 1 if hash of any block failed */ - enum verity_mode mode; /* mode for handling verification errors */ - unsigned corrupted_errs;/* Number of errors for corrupted blocks */ - - struct workqueue_struct *verify_wq; - - /* starting blocks for each tree level. 0 is the lowest level. */ - sector_t hash_level_block[DM_VERITY_MAX_LEVELS]; -}; - -struct dm_verity_io { - struct dm_verity *v; - - /* original values of bio->bi_end_io and bio->bi_private */ - bio_end_io_t *orig_bi_end_io; - void *orig_bi_private; - - sector_t block; - unsigned n_blocks; - - struct bvec_iter iter; - - struct work_struct work; - - /* - * Three variably-size fields follow this struct: - * - * u8 hash_desc[v->shash_descsize]; - * u8 real_digest[v->digest_size]; - * u8 want_digest[v->digest_size]; - * - * To access them use: io_hash_desc(), io_real_digest() and io_want_digest(). - */ -}; - struct dm_verity_prefetch_work { struct work_struct work; struct dm_verity *v; @@ -112,21 +46,6 @@ struct dm_verity_prefetch_work { unsigned n_blocks; }; -static struct shash_desc *io_hash_desc(struct dm_verity *v, struct dm_verity_io *io) -{ - return (struct shash_desc *)(io + 1); -} - -static u8 *io_real_digest(struct dm_verity *v, struct dm_verity_io *io) -{ - return (u8 *)(io + 1) + v->shash_descsize; -} - -static u8 *io_want_digest(struct dm_verity *v, struct dm_verity_io *io) -{ - return (u8 *)(io + 1) + v->shash_descsize + v->digest_size; -} - /* * Auxiliary structure appended to each dm-bufio buffer. If the value * hash_verified is nonzero, hash of the block has been verified. @@ -173,6 +92,84 @@ static sector_t verity_position_at_level(struct dm_verity *v, sector_t block, return block >> (level * v->hash_per_block_bits); } +/* + * Wrapper for crypto_shash_init, which handles verity salting. + */ +static int verity_hash_init(struct dm_verity *v, struct shash_desc *desc) +{ + int r; + + desc->tfm = v->tfm; + desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP; + + r = crypto_shash_init(desc); + + if (unlikely(r < 0)) { + DMERR("crypto_shash_init failed: %d", r); + return r; + } + + if (likely(v->version >= 1)) { + r = crypto_shash_update(desc, v->salt, v->salt_size); + + if (unlikely(r < 0)) { + DMERR("crypto_shash_update failed: %d", r); + return r; + } + } + + return 0; +} + +static int verity_hash_update(struct dm_verity *v, struct shash_desc *desc, + const u8 *data, size_t len) +{ + int r = crypto_shash_update(desc, data, len); + + if (unlikely(r < 0)) + DMERR("crypto_shash_update failed: %d", r); + + return r; +} + +static int verity_hash_final(struct dm_verity *v, struct shash_desc *desc, + u8 *digest) +{ + int r; + + if (unlikely(!v->version)) { + r = crypto_shash_update(desc, v->salt, v->salt_size); + + if (r < 0) { + DMERR("crypto_shash_update failed: %d", r); + return r; + } + } + + r = crypto_shash_final(desc, digest); + + if (unlikely(r < 0)) + DMERR("crypto_shash_final failed: %d", r); + + return r; +} + +int verity_hash(struct dm_verity *v, struct shash_desc *desc, + const u8 *data, size_t len, u8 *digest) +{ + int r; + + r = verity_hash_init(v, desc); + if (unlikely(r < 0)) + return r; + + r = verity_hash_update(v, desc, data, len); + if (unlikely(r < 0)) + return r; + + return verity_hash_final(v, desc, digest); +} + static void verity_hash_at_level(struct dm_verity *v, sector_t block, int level, sector_t *hash_block, unsigned *offset) { @@ -246,17 +243,17 @@ out: * Verify hash of a metadata block pertaining to the specified data block * ("block" argument) at a specified level ("level" argument). * - * On successful return, io_want_digest(v, io) contains the hash value for - * a lower tree level or for the data block (if we're at the lowest leve). + * On successful return, verity_io_want_digest(v, io) contains the hash value + * for a lower tree level or for the data block (if we're at the lowest level). * * If "skip_unverified" is true, unverified buffer is skipped and 1 is returned. * If "skip_unverified" is false, unverified buffer is hashed and verified - * against current value of io_want_digest(v, io). + * against current value of verity_io_want_digest(v, io). */ -static int verity_verify_level(struct dm_verity_io *io, sector_t block, - int level, bool skip_unverified) +static int verity_verify_level(struct dm_verity *v, struct dm_verity_io *io, + sector_t block, int level, bool skip_unverified, + u8 *want_digest) { - struct dm_verity *v = io->v; struct dm_buffer *buf; struct buffer_aux *aux; u8 *data; @@ -273,72 +270,128 @@ static int verity_verify_level(struct dm_verity_io *io, sector_t block, aux = dm_bufio_get_aux_data(buf); if (!aux->hash_verified) { - struct shash_desc *desc; - u8 *result; - if (skip_unverified) { r = 1; goto release_ret_r; } - desc = io_hash_desc(v, io); - desc->tfm = v->tfm; - desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP; - r = crypto_shash_init(desc); - if (r < 0) { - DMERR("crypto_shash_init failed: %d", r); + r = verity_hash(v, verity_io_hash_desc(v, io), + data, 1 << v->hash_dev_block_bits, + verity_io_real_digest(v, io)); + if (unlikely(r < 0)) goto release_ret_r; - } - - if (likely(v->version >= 1)) { - r = crypto_shash_update(desc, v->salt, v->salt_size); - if (r < 0) { - DMERR("crypto_shash_update failed: %d", r); - goto release_ret_r; - } - } - r = crypto_shash_update(desc, data, 1 << v->hash_dev_block_bits); - if (r < 0) { - DMERR("crypto_shash_update failed: %d", r); + if (likely(memcmp(verity_io_real_digest(v, io), want_digest, + v->digest_size) == 0)) + aux->hash_verified = 1; + else if (verity_fec_decode(v, io, + DM_VERITY_BLOCK_TYPE_METADATA, + hash_block, data, NULL) == 0) + aux->hash_verified = 1; + else if (verity_handle_err(v, + DM_VERITY_BLOCK_TYPE_METADATA, + hash_block)) { + r = -EIO; goto release_ret_r; } + } - if (!v->version) { - r = crypto_shash_update(desc, v->salt, v->salt_size); - if (r < 0) { - DMERR("crypto_shash_update failed: %d", r); - goto release_ret_r; - } - } + data += offset; + memcpy(want_digest, data, v->digest_size); + r = 0; - result = io_real_digest(v, io); - r = crypto_shash_final(desc, result); - if (r < 0) { - DMERR("crypto_shash_final failed: %d", r); - goto release_ret_r; - } - if (unlikely(memcmp(result, io_want_digest(v, io), v->digest_size))) { - if (verity_handle_err(v, DM_VERITY_BLOCK_TYPE_METADATA, - hash_block)) { - r = -EIO; - goto release_ret_r; - } - } else - aux->hash_verified = 1; +release_ret_r: + dm_bufio_release(buf); + return r; +} + +/* + * Find a hash for a given block, write it to digest and verify the integrity + * of the hash tree if necessary. + */ +int verity_hash_for_block(struct dm_verity *v, struct dm_verity_io *io, + sector_t block, u8 *digest, bool *is_zero) +{ + int r = 0, i; + + if (likely(v->levels)) { + /* + * First, we try to get the requested hash for + * the current block. If the hash block itself is + * verified, zero is returned. If it isn't, this + * function returns 1 and we fall back to whole + * chain verification. + */ + r = verity_verify_level(v, io, block, 0, true, digest); + if (likely(r <= 0)) + goto out; } - data += offset; + memcpy(digest, v->root_digest, v->digest_size); - memcpy(io_want_digest(v, io), data, v->digest_size); + for (i = v->levels - 1; i >= 0; i--) { + r = verity_verify_level(v, io, block, i, false, digest); + if (unlikely(r)) + goto out; + } +out: + if (!r && v->zero_digest) + *is_zero = !memcmp(v->zero_digest, digest, v->digest_size); + else + *is_zero = false; + + return r; +} + +/* + * Calls function process for 1 << v->data_dev_block_bits bytes in the bio_vec + * starting from iter. + */ +int verity_for_bv_block(struct dm_verity *v, struct dm_verity_io *io, + struct bvec_iter *iter, + int (*process)(struct dm_verity *v, + struct dm_verity_io *io, u8 *data, + size_t len)) +{ + unsigned todo = 1 << v->data_dev_block_bits; + struct bio *bio = dm_bio_from_per_bio_data(io, v->ti->per_bio_data_size); + + do { + int r; + u8 *page; + unsigned len; + struct bio_vec bv = bio_iter_iovec(bio, *iter); + + page = kmap_atomic(bv.bv_page); + len = bv.bv_len; + + if (likely(len >= todo)) + len = todo; + + r = process(v, io, page + bv.bv_offset, len); + kunmap_atomic(page); + + if (r < 0) + return r; + + bio_advance_iter(bio, iter, len); + todo -= len; + } while (todo); - dm_bufio_release(buf); return 0; +} -release_ret_r: - dm_bufio_release(buf); +static int verity_bv_hash_update(struct dm_verity *v, struct dm_verity_io *io, + u8 *data, size_t len) +{ + return verity_hash_update(v, verity_io_hash_desc(v, io), data, len); +} - return r; +static int verity_bv_zero(struct dm_verity *v, struct dm_verity_io *io, + u8 *data, size_t len) +{ + memset(data, 0, len); + return 0; } /* @@ -346,99 +399,56 @@ release_ret_r: */ static int verity_verify_io(struct dm_verity_io *io) { + bool is_zero; struct dm_verity *v = io->v; - struct bio *bio = dm_bio_from_per_bio_data(io, - v->ti->per_bio_data_size); + struct bvec_iter start; unsigned b; - int i; for (b = 0; b < io->n_blocks; b++) { - struct shash_desc *desc; - u8 *result; int r; - unsigned todo; + struct shash_desc *desc = verity_io_hash_desc(v, io); + + r = verity_hash_for_block(v, io, io->block + b, + verity_io_want_digest(v, io), + &is_zero); + if (unlikely(r < 0)) + return r; - if (likely(v->levels)) { + if (is_zero) { /* - * First, we try to get the requested hash for - * the current block. If the hash block itself is - * verified, zero is returned. If it isn't, this - * function returns 0 and we fall back to whole - * chain verification. + * If we expect a zero block, don't validate, just + * return zeros. */ - int r = verity_verify_level(io, io->block + b, 0, true); - if (likely(!r)) - goto test_block_hash; - if (r < 0) + r = verity_for_bv_block(v, io, &io->iter, + verity_bv_zero); + if (unlikely(r < 0)) return r; - } - memcpy(io_want_digest(v, io), v->root_digest, v->digest_size); - - for (i = v->levels - 1; i >= 0; i--) { - int r = verity_verify_level(io, io->block + b, i, false); - if (unlikely(r)) - return r; + continue; } -test_block_hash: - desc = io_hash_desc(v, io); - desc->tfm = v->tfm; - desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP; - r = crypto_shash_init(desc); - if (r < 0) { - DMERR("crypto_shash_init failed: %d", r); + r = verity_hash_init(v, desc); + if (unlikely(r < 0)) return r; - } - - if (likely(v->version >= 1)) { - r = crypto_shash_update(desc, v->salt, v->salt_size); - if (r < 0) { - DMERR("crypto_shash_update failed: %d", r); - return r; - } - } - todo = 1 << v->data_dev_block_bits; - do { - u8 *page; - unsigned len; - struct bio_vec bv = bio_iter_iovec(bio, io->iter); - - page = kmap_atomic(bv.bv_page); - len = bv.bv_len; - if (likely(len >= todo)) - len = todo; - r = crypto_shash_update(desc, page + bv.bv_offset, len); - kunmap_atomic(page); - - if (r < 0) { - DMERR("crypto_shash_update failed: %d", r); - return r; - } - - bio_advance_iter(bio, &io->iter, len); - todo -= len; - } while (todo); - if (!v->version) { - r = crypto_shash_update(desc, v->salt, v->salt_size); - if (r < 0) { - DMERR("crypto_shash_update failed: %d", r); - return r; - } - } + start = io->iter; + r = verity_for_bv_block(v, io, &io->iter, verity_bv_hash_update); + if (unlikely(r < 0)) + return r; - result = io_real_digest(v, io); - r = crypto_shash_final(desc, result); - if (r < 0) { - DMERR("crypto_shash_final failed: %d", r); + r = verity_hash_final(v, desc, verity_io_real_digest(v, io)); + if (unlikely(r < 0)) return r; - } - if (unlikely(memcmp(result, io_want_digest(v, io), v->digest_size))) { - if (verity_handle_err(v, DM_VERITY_BLOCK_TYPE_DATA, - io->block + b)) - return -EIO; - } + + if (likely(memcmp(verity_io_real_digest(v, io), + verity_io_want_digest(v, io), v->digest_size) == 0)) + continue; + else if (verity_fec_decode(v, io, DM_VERITY_BLOCK_TYPE_DATA, + io->block + b, NULL, &start) == 0) + continue; + else if (verity_handle_err(v, DM_VERITY_BLOCK_TYPE_DATA, + io->block + b)) + return -EIO; } return 0; @@ -453,9 +463,10 @@ static void verity_finish_io(struct dm_verity_io *io, int error) struct bio *bio = dm_bio_from_per_bio_data(io, v->ti->per_bio_data_size); bio->bi_end_io = io->orig_bi_end_io; - bio->bi_private = io->orig_bi_private; bio->bi_error = error; + verity_fec_finish_io(io); + bio_endio(bio); } @@ -470,7 +481,7 @@ static void verity_end_io(struct bio *bio) { struct dm_verity_io *io = bio->bi_private; - if (bio->bi_error) { + if (bio->bi_error && !verity_fec_is_enabled(io->v)) { verity_finish_io(io, bio->bi_error); return; } @@ -566,7 +577,6 @@ static int verity_map(struct dm_target *ti, struct bio *bio) io = dm_per_bio_data(bio, ti->per_bio_data_size); io->v = v; io->orig_bi_end_io = bio->bi_end_io; - io->orig_bi_private = bio->bi_private; io->block = bio->bi_iter.bi_sector >> (v->data_dev_block_bits - SECTOR_SHIFT); io->n_blocks = bio->bi_iter.bi_size >> v->data_dev_block_bits; @@ -574,6 +584,8 @@ static int verity_map(struct dm_target *ti, struct bio *bio) bio->bi_private = io; io->iter = bio->bi_iter; + verity_fec_init_io(io); + verity_submit_prefetch(v, io); generic_make_request(bio); @@ -588,6 +600,7 @@ static void verity_status(struct dm_target *ti, status_type_t type, unsigned status_flags, char *result, unsigned maxlen) { struct dm_verity *v = ti->private; + unsigned args = 0; unsigned sz = 0; unsigned x; @@ -614,8 +627,17 @@ static void verity_status(struct dm_target *ti, status_type_t type, else for (x = 0; x < v->salt_size; x++) DMEMIT("%02x", v->salt[x]); + if (v->mode != DM_VERITY_MODE_EIO) + args++; + if (verity_fec_is_enabled(v)) + args += DM_VERITY_OPTS_FEC; + if (v->zero_digest) + args++; + if (!args) + return; + DMEMIT(" %u", args); if (v->mode != DM_VERITY_MODE_EIO) { - DMEMIT(" 1 "); + DMEMIT(" "); switch (v->mode) { case DM_VERITY_MODE_LOGGING: DMEMIT(DM_VERITY_OPT_LOGGING); @@ -627,6 +649,9 @@ static void verity_status(struct dm_target *ti, status_type_t type, BUG(); } } + if (v->zero_digest) + DMEMIT(" " DM_VERITY_OPT_IGN_ZEROES); + sz = verity_fec_status_table(v, sz, result, maxlen); break; } } @@ -677,6 +702,7 @@ static void verity_dtr(struct dm_target *ti) kfree(v->salt); kfree(v->root_digest); + kfree(v->zero_digest); if (v->tfm) crypto_free_shash(v->tfm); @@ -689,9 +715,94 @@ static void verity_dtr(struct dm_target *ti) if (v->data_dev) dm_put_device(ti, v->data_dev); + verity_fec_dtr(v); + kfree(v); } +static int verity_alloc_zero_digest(struct dm_verity *v) +{ + int r = -ENOMEM; + struct shash_desc *desc; + u8 *zero_data; + + v->zero_digest = kmalloc(v->digest_size, GFP_KERNEL); + + if (!v->zero_digest) + return r; + + desc = kmalloc(v->shash_descsize, GFP_KERNEL); + + if (!desc) + return r; /* verity_dtr will free zero_digest */ + + zero_data = kzalloc(1 << v->data_dev_block_bits, GFP_KERNEL); + + if (!zero_data) + goto out; + + r = verity_hash(v, desc, zero_data, 1 << v->data_dev_block_bits, + v->zero_digest); + +out: + kfree(desc); + kfree(zero_data); + + return r; +} + +static int verity_parse_opt_args(struct dm_arg_set *as, struct dm_verity *v) +{ + int r; + unsigned argc; + struct dm_target *ti = v->ti; + const char *arg_name; + + static struct dm_arg _args[] = { + {0, DM_VERITY_OPTS_MAX, "Invalid number of feature args"}, + }; + + r = dm_read_arg_group(_args, as, &argc, &ti->error); + if (r) + return -EINVAL; + + if (!argc) + return 0; + + do { + arg_name = dm_shift_arg(as); + argc--; + + if (!strcasecmp(arg_name, DM_VERITY_OPT_LOGGING)) { + v->mode = DM_VERITY_MODE_LOGGING; + continue; + + } else if (!strcasecmp(arg_name, DM_VERITY_OPT_RESTART)) { + v->mode = DM_VERITY_MODE_RESTART; + continue; + + } else if (!strcasecmp(arg_name, DM_VERITY_OPT_IGN_ZEROES)) { + r = verity_alloc_zero_digest(v); + if (r) { + ti->error = "Cannot allocate zero digest"; + return r; + } + continue; + + } else if (verity_is_fec_opt_arg(arg_name)) { + r = verity_fec_parse_opt_args(as, v, &argc, arg_name); + if (r) + return r; + continue; + } + + ti->error = "Unrecognized verity feature request"; + return -EINVAL; + } while (argc && !r); + + return r; +} + /* * Target parameters: * <version> The current format is version 1. @@ -710,18 +821,13 @@ static int verity_ctr(struct dm_target *ti, unsigned argc, char **argv) { struct dm_verity *v; struct dm_arg_set as; - const char *opt_string; - unsigned int num, opt_params; + unsigned int num; unsigned long long num_ll; int r; int i; sector_t hash_position; char dummy; - static struct dm_arg _args[] = { - {0, 1, "Invalid number of feature args"}, - }; - v = kzalloc(sizeof(struct dm_verity), GFP_KERNEL); if (!v) { ti->error = "Cannot allocate verity structure"; @@ -730,6 +836,10 @@ static int verity_ctr(struct dm_target *ti, unsigned argc, char **argv) ti->private = v; v->ti = ti; + r = verity_fec_ctr_alloc(v); + if (r) + goto bad; + if ((dm_table_get_mode(ti->table) & ~FMODE_READ)) { ti->error = "Device must be readonly"; r = -EINVAL; @@ -866,29 +976,9 @@ static int verity_ctr(struct dm_target *ti, unsigned argc, char **argv) as.argc = argc; as.argv = argv; - r = dm_read_arg_group(_args, &as, &opt_params, &ti->error); - if (r) + r = verity_parse_opt_args(&as, v); + if (r < 0) goto bad; - - while (opt_params) { - opt_params--; - opt_string = dm_shift_arg(&as); - if (!opt_string) { - ti->error = "Not enough feature arguments"; - r = -EINVAL; - goto bad; - } - - if (!strcasecmp(opt_string, DM_VERITY_OPT_LOGGING)) - v->mode = DM_VERITY_MODE_LOGGING; - else if (!strcasecmp(opt_string, DM_VERITY_OPT_RESTART)) - v->mode = DM_VERITY_MODE_RESTART; - else { - ti->error = "Invalid feature arguments"; - r = -EINVAL; - goto bad; - } - } } v->hash_per_block_bits = @@ -938,8 +1028,6 @@ static int verity_ctr(struct dm_target *ti, unsigned argc, char **argv) goto bad; } - ti->per_bio_data_size = roundup(sizeof(struct dm_verity_io) + v->shash_descsize + v->digest_size * 2, __alignof__(struct dm_verity_io)); - /* WQ_UNBOUND greatly improves performance when running on ramdisk */ v->verify_wq = alloc_workqueue("kverityd", WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM | WQ_UNBOUND, num_online_cpus()); if (!v->verify_wq) { @@ -948,6 +1036,16 @@ static int verity_ctr(struct dm_target *ti, unsigned argc, char **argv) goto bad; } + ti->per_bio_data_size = sizeof(struct dm_verity_io) + + v->shash_descsize + v->digest_size * 2; + + r = verity_fec_ctr(v); + if (r) + goto bad; + + ti->per_bio_data_size = roundup(ti->per_bio_data_size, + __alignof__(struct dm_verity_io)); + return 0; bad: @@ -958,7 +1056,7 @@ bad: static struct target_type verity_target = { .name = "verity", - .version = {1, 2, 0}, + .version = {1, 3, 0}, .module = THIS_MODULE, .ctr = verity_ctr, .dtr = verity_dtr, diff --git a/drivers/md/dm-verity.h b/drivers/md/dm-verity.h new file mode 100644 index 000000000000..fb419f422d73 --- /dev/null +++ b/drivers/md/dm-verity.h @@ -0,0 +1,129 @@ +/* + * Copyright (C) 2012 Red Hat, Inc. + * Copyright (C) 2015 Google, Inc. + * + * Author: Mikulas Patocka <mpatocka@redhat.com> + * + * Based on Chromium dm-verity driver (C) 2011 The Chromium OS Authors + * + * This file is released under the GPLv2. + */ + +#ifndef DM_VERITY_H +#define DM_VERITY_H + +#include "dm-bufio.h" +#include <linux/device-mapper.h> +#include <crypto/hash.h> + +#define DM_VERITY_MAX_LEVELS 63 + +enum verity_mode { + DM_VERITY_MODE_EIO, + DM_VERITY_MODE_LOGGING, + DM_VERITY_MODE_RESTART +}; + +enum verity_block_type { + DM_VERITY_BLOCK_TYPE_DATA, + DM_VERITY_BLOCK_TYPE_METADATA +}; + +struct dm_verity_fec; + +struct dm_verity { + struct dm_dev *data_dev; + struct dm_dev *hash_dev; + struct dm_target *ti; + struct dm_bufio_client *bufio; + char *alg_name; + struct crypto_shash *tfm; + u8 *root_digest; /* digest of the root block */ + u8 *salt; /* salt: its size is salt_size */ + u8 *zero_digest; /* digest for a zero block */ + unsigned salt_size; + sector_t data_start; /* data offset in 512-byte sectors */ + sector_t hash_start; /* hash start in blocks */ + sector_t data_blocks; /* the number of data blocks */ + sector_t hash_blocks; /* the number of hash blocks */ + unsigned char data_dev_block_bits; /* log2(data blocksize) */ + unsigned char hash_dev_block_bits; /* log2(hash blocksize) */ + unsigned char hash_per_block_bits; /* log2(hashes in hash block) */ + unsigned char levels; /* the number of tree levels */ + unsigned char version; + unsigned digest_size; /* digest size for the current hash algorithm */ + unsigned shash_descsize;/* the size of temporary space for crypto */ + int hash_failed; /* set to 1 if hash of any block failed */ + enum verity_mode mode; /* mode for handling verification errors */ + unsigned corrupted_errs;/* Number of errors for corrupted blocks */ + + struct workqueue_struct *verify_wq; + + /* starting blocks for each tree level. 0 is the lowest level. */ + sector_t hash_level_block[DM_VERITY_MAX_LEVELS]; + + struct dm_verity_fec *fec; /* forward error correction */ +}; + +struct dm_verity_io { + struct dm_verity *v; + + /* original value of bio->bi_end_io */ + bio_end_io_t *orig_bi_end_io; + + sector_t block; + unsigned n_blocks; + + struct bvec_iter iter; + + struct work_struct work; + + /* + * Three variably-size fields follow this struct: + * + * u8 hash_desc[v->shash_descsize]; + * u8 real_digest[v->digest_size]; + * u8 want_digest[v->digest_size]; + * + * To access them use: verity_io_hash_desc(), verity_io_real_digest() + * and verity_io_want_digest(). + */ +}; + +static inline struct shash_desc *verity_io_hash_desc(struct dm_verity *v, + struct dm_verity_io *io) +{ + return (struct shash_desc *)(io + 1); +} + +static inline u8 *verity_io_real_digest(struct dm_verity *v, + struct dm_verity_io *io) +{ + return (u8 *)(io + 1) + v->shash_descsize; +} + +static inline u8 *verity_io_want_digest(struct dm_verity *v, + struct dm_verity_io *io) +{ + return (u8 *)(io + 1) + v->shash_descsize + v->digest_size; +} + +static inline u8 *verity_io_digest_end(struct dm_verity *v, + struct dm_verity_io *io) +{ + return verity_io_want_digest(v, io) + v->digest_size; +} + +extern int verity_for_bv_block(struct dm_verity *v, struct dm_verity_io *io, + struct bvec_iter *iter, + int (*process)(struct dm_verity *v, + struct dm_verity_io *io, + u8 *data, size_t len)); + +extern int verity_hash(struct dm_verity *v, struct shash_desc *desc, + const u8 *data, size_t len, u8 *digest); + +extern int verity_hash_for_block(struct dm_verity *v, struct dm_verity_io *io, + sector_t block, u8 *digest, bool *is_zero); + +#endif /* DM_VERITY_H */ diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 32440ad5f684..5df40480228b 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -591,7 +591,7 @@ retry: out: dm_put_live_table(md, *srcu_idx); - if (r == -ENOTCONN) { + if (r == -ENOTCONN && !fatal_signal_pending(current)) { msleep(10); goto retry; } @@ -603,9 +603,10 @@ static int dm_blk_ioctl(struct block_device *bdev, fmode_t mode, { struct mapped_device *md = bdev->bd_disk->private_data; struct dm_target *tgt; + struct block_device *tgt_bdev = NULL; int srcu_idx, r; - r = dm_get_live_table_for_ioctl(md, &tgt, &bdev, &mode, &srcu_idx); + r = dm_get_live_table_for_ioctl(md, &tgt, &tgt_bdev, &mode, &srcu_idx); if (r < 0) return r; @@ -620,7 +621,7 @@ static int dm_blk_ioctl(struct block_device *bdev, fmode_t mode, goto out; } - r = __blkdev_driver_ioctl(bdev, mode, cmd, arg); + r = __blkdev_driver_ioctl(tgt_bdev, mode, cmd, arg); out: dm_put_live_table(md, srcu_idx); return r; @@ -1755,7 +1756,7 @@ static void __split_and_process_bio(struct mapped_device *md, * The request function that just remaps the bio built up by * dm_merge_bvec. */ -static void dm_make_request(struct request_queue *q, struct bio *bio) +static blk_qc_t dm_make_request(struct request_queue *q, struct bio *bio) { int rw = bio_data_dir(bio); struct mapped_device *md = q->queuedata; @@ -1774,12 +1775,12 @@ static void dm_make_request(struct request_queue *q, struct bio *bio) queue_io(md, bio); else bio_io_error(bio); - return; + return BLK_QC_T_NONE; } __split_and_process_bio(md, map, bio); dm_put_live_table(md, srcu_idx); - return; + return BLK_QC_T_NONE; } int dm_request_based(struct mapped_device *md) diff --git a/drivers/md/md.c b/drivers/md/md.c index 3f9a514b5b9d..31b595479aa5 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -34,6 +34,7 @@ #include <linux/kthread.h> #include <linux/blkdev.h> +#include <linux/badblocks.h> #include <linux/sysctl.h> #include <linux/seq_file.h> #include <linux/fs.h> @@ -250,7 +251,7 @@ static DEFINE_SPINLOCK(all_mddevs_lock); * call has finished, the bio has been linked into some internal structure * and so is visible to ->quiesce(), so we don't need the refcount any more. */ -static void md_make_request(struct request_queue *q, struct bio *bio) +static blk_qc_t md_make_request(struct request_queue *q, struct bio *bio) { const int rw = bio_data_dir(bio); struct mddev *mddev = q->queuedata; @@ -262,13 +263,13 @@ static void md_make_request(struct request_queue *q, struct bio *bio) if (mddev == NULL || mddev->pers == NULL || !mddev->ready) { bio_io_error(bio); - return; + return BLK_QC_T_NONE; } if (mddev->ro == 1 && unlikely(rw == WRITE)) { if (bio_sectors(bio) != 0) bio->bi_error = -EROFS; bio_endio(bio); - return; + return BLK_QC_T_NONE; } smp_rmb(); /* Ensure implications of 'active' are visible */ rcu_read_lock(); @@ -302,6 +303,8 @@ static void md_make_request(struct request_queue *q, struct bio *bio) if (atomic_dec_and_test(&mddev->active_io) && mddev->suspended) wake_up(&mddev->sb_wait); + + return BLK_QC_T_NONE; } /* mddev_suspend makes sure no new requests are submitted @@ -312,8 +315,8 @@ static void md_make_request(struct request_queue *q, struct bio *bio) */ void mddev_suspend(struct mddev *mddev) { - BUG_ON(mddev->suspended); - mddev->suspended = 1; + if (mddev->suspended++) + return; synchronize_rcu(); wait_event(mddev->sb_wait, atomic_read(&mddev->active_io) == 0); mddev->pers->quiesce(mddev, 1); @@ -324,7 +327,8 @@ EXPORT_SYMBOL_GPL(mddev_suspend); void mddev_resume(struct mddev *mddev) { - mddev->suspended = 0; + if (--mddev->suspended) + return; wake_up(&mddev->sb_wait); mddev->pers->quiesce(mddev, 0); @@ -707,8 +711,7 @@ void md_rdev_clear(struct md_rdev *rdev) put_page(rdev->bb_page); rdev->bb_page = NULL; } - kfree(rdev->badblocks.page); - rdev->badblocks.page = NULL; + badblocks_exit(&rdev->badblocks); } EXPORT_SYMBOL_GPL(md_rdev_clear); @@ -1358,8 +1361,6 @@ static __le32 calc_sb_1_csum(struct mdp_superblock_1 *sb) return cpu_to_le32(csum); } -static int md_set_badblocks(struct badblocks *bb, sector_t s, int sectors, - int acknowledged); static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_version) { struct mdp_superblock_1 *sb; @@ -1484,8 +1485,7 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_ count <<= sb->bblog_shift; if (bb + 1 == 0) break; - if (md_set_badblocks(&rdev->badblocks, - sector, count, 1) == 0) + if (badblocks_set(&rdev->badblocks, sector, count, 1)) return -EINVAL; } } else if (sb->bblog_offset != 0) @@ -1650,7 +1650,7 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev) rdev->journal_tail = le64_to_cpu(sb->journal_tail); if (mddev->recovery_cp == MaxSector) set_bit(MD_JOURNAL_CLEAN, &mddev->flags); - rdev->raid_disk = mddev->raid_disks; + rdev->raid_disk = 0; break; default: rdev->saved_raid_disk = role; @@ -2317,7 +2317,7 @@ repeat: rdev_for_each(rdev, mddev) { if (rdev->badblocks.changed) { rdev->badblocks.changed = 0; - md_ack_all_badblocks(&rdev->badblocks); + ack_all_badblocks(&rdev->badblocks); md_error(mddev, rdev); } clear_bit(Blocked, &rdev->flags); @@ -2443,7 +2443,7 @@ repeat: clear_bit(Blocked, &rdev->flags); if (any_badblocks_changed) - md_ack_all_badblocks(&rdev->badblocks); + ack_all_badblocks(&rdev->badblocks); clear_bit(BlockedBadBlocks, &rdev->flags); wake_up(&rdev->blocked_wait); } @@ -2771,6 +2771,7 @@ slot_store(struct md_rdev *rdev, const char *buf, size_t len) /* Activating a spare .. or possibly reactivating * if we ever get bitmaps working here. */ + int err; if (rdev->raid_disk != -1) return -EBUSY; @@ -2792,9 +2793,15 @@ slot_store(struct md_rdev *rdev, const char *buf, size_t len) rdev->saved_raid_disk = -1; clear_bit(In_sync, &rdev->flags); clear_bit(Bitmap_sync, &rdev->flags); - remove_and_add_spares(rdev->mddev, rdev); - if (rdev->raid_disk == -1) - return -EBUSY; + err = rdev->mddev->pers-> + hot_add_disk(rdev->mddev, rdev); + if (err) { + rdev->raid_disk = -1; + return err; + } else + sysfs_notify_dirent_safe(rdev->sysfs_state); + if (sysfs_link_rdev(rdev->mddev, rdev)) + /* failure here is OK */; /* don't wakeup anyone, leave that to userspace. */ } else { if (slot >= rdev->mddev->raid_disks && @@ -3044,11 +3051,17 @@ static ssize_t recovery_start_store(struct md_rdev *rdev, const char *buf, size_ static struct rdev_sysfs_entry rdev_recovery_start = __ATTR(recovery_start, S_IRUGO|S_IWUSR, recovery_start_show, recovery_start_store); -static ssize_t -badblocks_show(struct badblocks *bb, char *page, int unack); -static ssize_t -badblocks_store(struct badblocks *bb, const char *page, size_t len, int unack); - +/* sysfs access to bad-blocks list. + * We present two files. + * 'bad-blocks' lists sector numbers and lengths of ranges that + * are recorded as bad. The list is truncated to fit within + * the one-page limit of sysfs. + * Writing "sector length" to this file adds an acknowledged + * bad block list. + * 'unacknowledged-bad-blocks' lists bad blocks that have not yet + * been acknowledged. Writing to this file adds bad blocks + * without acknowledging them. This is largely for testing. + */ static ssize_t bb_show(struct md_rdev *rdev, char *page) { return badblocks_show(&rdev->badblocks, page, 0); @@ -3163,14 +3176,7 @@ int md_rdev_init(struct md_rdev *rdev) * This reserves the space even on arrays where it cannot * be used - I wonder if that matters */ - rdev->badblocks.count = 0; - rdev->badblocks.shift = -1; /* disabled until explicitly enabled */ - rdev->badblocks.page = kmalloc(PAGE_SIZE, GFP_KERNEL); - seqlock_init(&rdev->badblocks.lock); - if (rdev->badblocks.page == NULL) - return -ENOMEM; - - return 0; + return badblocks_init(&rdev->badblocks, 0); } EXPORT_SYMBOL_GPL(md_rdev_init); /* @@ -4316,8 +4322,7 @@ action_store(struct mddev *mddev, const char *page, size_t len) } mddev_unlock(mddev); } - } else if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) || - test_bit(MD_RECOVERY_NEEDED, &mddev->recovery)) + } else if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) return -EBUSY; else if (cmd_match(page, "resync")) clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); @@ -4330,8 +4335,12 @@ action_store(struct mddev *mddev, const char *page, size_t len) return -EINVAL; err = mddev_lock(mddev); if (!err) { - clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); - err = mddev->pers->start_reshape(mddev); + if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) + err = -EBUSY; + else { + clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); + err = mddev->pers->start_reshape(mddev); + } mddev_unlock(mddev); } if (err) @@ -8476,254 +8485,9 @@ void md_finish_reshape(struct mddev *mddev) } EXPORT_SYMBOL(md_finish_reshape); -/* Bad block management. - * We can record which blocks on each device are 'bad' and so just - * fail those blocks, or that stripe, rather than the whole device. - * Entries in the bad-block table are 64bits wide. This comprises: - * Length of bad-range, in sectors: 0-511 for lengths 1-512 - * Start of bad-range, sector offset, 54 bits (allows 8 exbibytes) - * A 'shift' can be set so that larger blocks are tracked and - * consequently larger devices can be covered. - * 'Acknowledged' flag - 1 bit. - the most significant bit. - * - * Locking of the bad-block table uses a seqlock so md_is_badblock - * might need to retry if it is very unlucky. - * We will sometimes want to check for bad blocks in a bi_end_io function, - * so we use the write_seqlock_irq variant. - * - * When looking for a bad block we specify a range and want to - * know if any block in the range is bad. So we binary-search - * to the last range that starts at-or-before the given endpoint, - * (or "before the sector after the target range") - * then see if it ends after the given start. - * We return - * 0 if there are no known bad blocks in the range - * 1 if there are known bad block which are all acknowledged - * -1 if there are bad blocks which have not yet been acknowledged in metadata. - * plus the start/length of the first bad section we overlap. - */ -int md_is_badblock(struct badblocks *bb, sector_t s, int sectors, - sector_t *first_bad, int *bad_sectors) -{ - int hi; - int lo; - u64 *p = bb->page; - int rv; - sector_t target = s + sectors; - unsigned seq; - - if (bb->shift > 0) { - /* round the start down, and the end up */ - s >>= bb->shift; - target += (1<<bb->shift) - 1; - target >>= bb->shift; - sectors = target - s; - } - /* 'target' is now the first block after the bad range */ - -retry: - seq = read_seqbegin(&bb->lock); - lo = 0; - rv = 0; - hi = bb->count; - - /* Binary search between lo and hi for 'target' - * i.e. for the last range that starts before 'target' - */ - /* INVARIANT: ranges before 'lo' and at-or-after 'hi' - * are known not to be the last range before target. - * VARIANT: hi-lo is the number of possible - * ranges, and decreases until it reaches 1 - */ - while (hi - lo > 1) { - int mid = (lo + hi) / 2; - sector_t a = BB_OFFSET(p[mid]); - if (a < target) - /* This could still be the one, earlier ranges - * could not. */ - lo = mid; - else - /* This and later ranges are definitely out. */ - hi = mid; - } - /* 'lo' might be the last that started before target, but 'hi' isn't */ - if (hi > lo) { - /* need to check all range that end after 's' to see if - * any are unacknowledged. - */ - while (lo >= 0 && - BB_OFFSET(p[lo]) + BB_LEN(p[lo]) > s) { - if (BB_OFFSET(p[lo]) < target) { - /* starts before the end, and finishes after - * the start, so they must overlap - */ - if (rv != -1 && BB_ACK(p[lo])) - rv = 1; - else - rv = -1; - *first_bad = BB_OFFSET(p[lo]); - *bad_sectors = BB_LEN(p[lo]); - } - lo--; - } - } - - if (read_seqretry(&bb->lock, seq)) - goto retry; - - return rv; -} -EXPORT_SYMBOL_GPL(md_is_badblock); - -/* - * Add a range of bad blocks to the table. - * This might extend the table, or might contract it - * if two adjacent ranges can be merged. - * We binary-search to find the 'insertion' point, then - * decide how best to handle it. - */ -static int md_set_badblocks(struct badblocks *bb, sector_t s, int sectors, - int acknowledged) -{ - u64 *p; - int lo, hi; - int rv = 1; - unsigned long flags; - - if (bb->shift < 0) - /* badblocks are disabled */ - return 0; - - if (bb->shift) { - /* round the start down, and the end up */ - sector_t next = s + sectors; - s >>= bb->shift; - next += (1<<bb->shift) - 1; - next >>= bb->shift; - sectors = next - s; - } - - write_seqlock_irqsave(&bb->lock, flags); - - p = bb->page; - lo = 0; - hi = bb->count; - /* Find the last range that starts at-or-before 's' */ - while (hi - lo > 1) { - int mid = (lo + hi) / 2; - sector_t a = BB_OFFSET(p[mid]); - if (a <= s) - lo = mid; - else - hi = mid; - } - if (hi > lo && BB_OFFSET(p[lo]) > s) - hi = lo; - - if (hi > lo) { - /* we found a range that might merge with the start - * of our new range - */ - sector_t a = BB_OFFSET(p[lo]); - sector_t e = a + BB_LEN(p[lo]); - int ack = BB_ACK(p[lo]); - if (e >= s) { - /* Yes, we can merge with a previous range */ - if (s == a && s + sectors >= e) - /* new range covers old */ - ack = acknowledged; - else - ack = ack && acknowledged; - - if (e < s + sectors) - e = s + sectors; - if (e - a <= BB_MAX_LEN) { - p[lo] = BB_MAKE(a, e-a, ack); - s = e; - } else { - /* does not all fit in one range, - * make p[lo] maximal - */ - if (BB_LEN(p[lo]) != BB_MAX_LEN) - p[lo] = BB_MAKE(a, BB_MAX_LEN, ack); - s = a + BB_MAX_LEN; - } - sectors = e - s; - } - } - if (sectors && hi < bb->count) { - /* 'hi' points to the first range that starts after 's'. - * Maybe we can merge with the start of that range */ - sector_t a = BB_OFFSET(p[hi]); - sector_t e = a + BB_LEN(p[hi]); - int ack = BB_ACK(p[hi]); - if (a <= s + sectors) { - /* merging is possible */ - if (e <= s + sectors) { - /* full overlap */ - e = s + sectors; - ack = acknowledged; - } else - ack = ack && acknowledged; - - a = s; - if (e - a <= BB_MAX_LEN) { - p[hi] = BB_MAKE(a, e-a, ack); - s = e; - } else { - p[hi] = BB_MAKE(a, BB_MAX_LEN, ack); - s = a + BB_MAX_LEN; - } - sectors = e - s; - lo = hi; - hi++; - } - } - if (sectors == 0 && hi < bb->count) { - /* we might be able to combine lo and hi */ - /* Note: 's' is at the end of 'lo' */ - sector_t a = BB_OFFSET(p[hi]); - int lolen = BB_LEN(p[lo]); - int hilen = BB_LEN(p[hi]); - int newlen = lolen + hilen - (s - a); - if (s >= a && newlen < BB_MAX_LEN) { - /* yes, we can combine them */ - int ack = BB_ACK(p[lo]) && BB_ACK(p[hi]); - p[lo] = BB_MAKE(BB_OFFSET(p[lo]), newlen, ack); - memmove(p + hi, p + hi + 1, - (bb->count - hi - 1) * 8); - bb->count--; - } - } - while (sectors) { - /* didn't merge (it all). - * Need to add a range just before 'hi' */ - if (bb->count >= MD_MAX_BADBLOCKS) { - /* No room for more */ - rv = 0; - break; - } else { - int this_sectors = sectors; - memmove(p + hi + 1, p + hi, - (bb->count - hi) * 8); - bb->count++; - - if (this_sectors > BB_MAX_LEN) - this_sectors = BB_MAX_LEN; - p[hi] = BB_MAKE(s, this_sectors, acknowledged); - sectors -= this_sectors; - s += this_sectors; - } - } - - bb->changed = 1; - if (!acknowledged) - bb->unacked_exist = 1; - write_sequnlock_irqrestore(&bb->lock, flags); - - return rv; -} +/* Bad block management */ +/* Returns 1 on success, 0 on failure */ int rdev_set_badblocks(struct md_rdev *rdev, sector_t s, int sectors, int is_new) { @@ -8732,114 +8496,19 @@ int rdev_set_badblocks(struct md_rdev *rdev, sector_t s, int sectors, s += rdev->new_data_offset; else s += rdev->data_offset; - rv = md_set_badblocks(&rdev->badblocks, - s, sectors, 0); - if (rv) { + rv = badblocks_set(&rdev->badblocks, s, sectors, 0); + if (rv == 0) { /* Make sure they get written out promptly */ sysfs_notify_dirent_safe(rdev->sysfs_state); set_bit(MD_CHANGE_CLEAN, &rdev->mddev->flags); set_bit(MD_CHANGE_PENDING, &rdev->mddev->flags); md_wakeup_thread(rdev->mddev->thread); - } - return rv; + return 1; + } else + return 0; } EXPORT_SYMBOL_GPL(rdev_set_badblocks); -/* - * Remove a range of bad blocks from the table. - * This may involve extending the table if we spilt a region, - * but it must not fail. So if the table becomes full, we just - * drop the remove request. - */ -static int md_clear_badblocks(struct badblocks *bb, sector_t s, int sectors) -{ - u64 *p; - int lo, hi; - sector_t target = s + sectors; - int rv = 0; - - if (bb->shift > 0) { - /* When clearing we round the start up and the end down. - * This should not matter as the shift should align with - * the block size and no rounding should ever be needed. - * However it is better the think a block is bad when it - * isn't than to think a block is not bad when it is. - */ - s += (1<<bb->shift) - 1; - s >>= bb->shift; - target >>= bb->shift; - sectors = target - s; - } - - write_seqlock_irq(&bb->lock); - - p = bb->page; - lo = 0; - hi = bb->count; - /* Find the last range that starts before 'target' */ - while (hi - lo > 1) { - int mid = (lo + hi) / 2; - sector_t a = BB_OFFSET(p[mid]); - if (a < target) - lo = mid; - else - hi = mid; - } - if (hi > lo) { - /* p[lo] is the last range that could overlap the - * current range. Earlier ranges could also overlap, - * but only this one can overlap the end of the range. - */ - if (BB_OFFSET(p[lo]) + BB_LEN(p[lo]) > target) { - /* Partial overlap, leave the tail of this range */ - int ack = BB_ACK(p[lo]); - sector_t a = BB_OFFSET(p[lo]); - sector_t end = a + BB_LEN(p[lo]); - - if (a < s) { - /* we need to split this range */ - if (bb->count >= MD_MAX_BADBLOCKS) { - rv = -ENOSPC; - goto out; - } - memmove(p+lo+1, p+lo, (bb->count - lo) * 8); - bb->count++; - p[lo] = BB_MAKE(a, s-a, ack); - lo++; - } - p[lo] = BB_MAKE(target, end - target, ack); - /* there is no longer an overlap */ - hi = lo; - lo--; - } - while (lo >= 0 && - BB_OFFSET(p[lo]) + BB_LEN(p[lo]) > s) { - /* This range does overlap */ - if (BB_OFFSET(p[lo]) < s) { - /* Keep the early parts of this range. */ - int ack = BB_ACK(p[lo]); - sector_t start = BB_OFFSET(p[lo]); - p[lo] = BB_MAKE(start, s - start, ack); - /* now low doesn't overlap, so.. */ - break; - } - lo--; - } - /* 'lo' is strictly before, 'hi' is strictly after, - * anything between needs to be discarded - */ - if (hi - lo > 1) { - memmove(p+lo+1, p+hi, (bb->count - hi) * 8); - bb->count -= (hi - lo - 1); - } - } - - bb->changed = 1; -out: - write_sequnlock_irq(&bb->lock); - return rv; -} - int rdev_clear_badblocks(struct md_rdev *rdev, sector_t s, int sectors, int is_new) { @@ -8847,133 +8516,11 @@ int rdev_clear_badblocks(struct md_rdev *rdev, sector_t s, int sectors, s += rdev->new_data_offset; else s += rdev->data_offset; - return md_clear_badblocks(&rdev->badblocks, + return badblocks_clear(&rdev->badblocks, s, sectors); } EXPORT_SYMBOL_GPL(rdev_clear_badblocks); -/* - * Acknowledge all bad blocks in a list. - * This only succeeds if ->changed is clear. It is used by - * in-kernel metadata updates - */ -void md_ack_all_badblocks(struct badblocks *bb) -{ - if (bb->page == NULL || bb->changed) - /* no point even trying */ - return; - write_seqlock_irq(&bb->lock); - - if (bb->changed == 0 && bb->unacked_exist) { - u64 *p = bb->page; - int i; - for (i = 0; i < bb->count ; i++) { - if (!BB_ACK(p[i])) { - sector_t start = BB_OFFSET(p[i]); - int len = BB_LEN(p[i]); - p[i] = BB_MAKE(start, len, 1); - } - } - bb->unacked_exist = 0; - } - write_sequnlock_irq(&bb->lock); -} -EXPORT_SYMBOL_GPL(md_ack_all_badblocks); - -/* sysfs access to bad-blocks list. - * We present two files. - * 'bad-blocks' lists sector numbers and lengths of ranges that - * are recorded as bad. The list is truncated to fit within - * the one-page limit of sysfs. - * Writing "sector length" to this file adds an acknowledged - * bad block list. - * 'unacknowledged-bad-blocks' lists bad blocks that have not yet - * been acknowledged. Writing to this file adds bad blocks - * without acknowledging them. This is largely for testing. - */ - -static ssize_t -badblocks_show(struct badblocks *bb, char *page, int unack) -{ - size_t len; - int i; - u64 *p = bb->page; - unsigned seq; - - if (bb->shift < 0) - return 0; - -retry: - seq = read_seqbegin(&bb->lock); - - len = 0; - i = 0; - - while (len < PAGE_SIZE && i < bb->count) { - sector_t s = BB_OFFSET(p[i]); - unsigned int length = BB_LEN(p[i]); - int ack = BB_ACK(p[i]); - i++; - - if (unack && ack) - continue; - - len += snprintf(page+len, PAGE_SIZE-len, "%llu %u\n", - (unsigned long long)s << bb->shift, - length << bb->shift); - } - if (unack && len == 0) - bb->unacked_exist = 0; - - if (read_seqretry(&bb->lock, seq)) - goto retry; - - return len; -} - -#define DO_DEBUG 1 - -static ssize_t -badblocks_store(struct badblocks *bb, const char *page, size_t len, int unack) -{ - unsigned long long sector; - int length; - char newline; -#ifdef DO_DEBUG - /* Allow clearing via sysfs *only* for testing/debugging. - * Normally only a successful write may clear a badblock - */ - int clear = 0; - if (page[0] == '-') { - clear = 1; - page++; - } -#endif /* DO_DEBUG */ - - switch (sscanf(page, "%llu %d%c", §or, &length, &newline)) { - case 3: - if (newline != '\n') - return -EINVAL; - case 2: - if (length <= 0) - return -EINVAL; - break; - default: - return -EINVAL; - } - -#ifdef DO_DEBUG - if (clear) { - md_clear_badblocks(bb, sector, length); - return len; - } -#endif /* DO_DEBUG */ - if (md_set_badblocks(bb, sector, length, !unack)) - return len; - else - return -ENOSPC; -} - static int md_notify_reboot(struct notifier_block *this, unsigned long code, void *x) { diff --git a/drivers/md/md.h b/drivers/md/md.h index 2bea51edfab7..75b9aaacb03f 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -17,6 +17,7 @@ #include <linux/blkdev.h> #include <linux/backing-dev.h> +#include <linux/badblocks.h> #include <linux/kobject.h> #include <linux/list.h> #include <linux/mm.h> @@ -28,13 +29,6 @@ #define MaxSector (~(sector_t)0) -/* Bad block numbers are stored sorted in a single page. - * 64bits is used for each block or extent. - * 54 bits are sector number, 9 bits are extent size, - * 1 bit is an 'acknowledged' flag. - */ -#define MD_MAX_BADBLOCKS (PAGE_SIZE/8) - /* * MD's 'extended' device */ @@ -117,22 +111,7 @@ struct md_rdev { struct kernfs_node *sysfs_state; /* handle for 'state' * sysfs entry */ - struct badblocks { - int count; /* count of bad blocks */ - int unacked_exist; /* there probably are unacknowledged - * bad blocks. This is only cleared - * when a read discovers none - */ - int shift; /* shift from sectors to block size - * a -ve shift means badblocks are - * disabled.*/ - u64 *page; /* badblock list */ - int changed; - seqlock_t lock; - - sector_t sector; - sector_t size; /* in sectors */ - } badblocks; + struct badblocks badblocks; }; enum flag_bits { Faulty, /* device is known to have a fault */ @@ -185,22 +164,11 @@ enum flag_bits { */ }; -#define BB_LEN_MASK (0x00000000000001FFULL) -#define BB_OFFSET_MASK (0x7FFFFFFFFFFFFE00ULL) -#define BB_ACK_MASK (0x8000000000000000ULL) -#define BB_MAX_LEN 512 -#define BB_OFFSET(x) (((x) & BB_OFFSET_MASK) >> 9) -#define BB_LEN(x) (((x) & BB_LEN_MASK) + 1) -#define BB_ACK(x) (!!((x) & BB_ACK_MASK)) -#define BB_MAKE(a, l, ack) (((a)<<9) | ((l)-1) | ((u64)(!!(ack)) << 63)) - -extern int md_is_badblock(struct badblocks *bb, sector_t s, int sectors, - sector_t *first_bad, int *bad_sectors); static inline int is_badblock(struct md_rdev *rdev, sector_t s, int sectors, sector_t *first_bad, int *bad_sectors) { if (unlikely(rdev->badblocks.count)) { - int rv = md_is_badblock(&rdev->badblocks, rdev->data_offset + s, + int rv = badblocks_check(&rdev->badblocks, rdev->data_offset + s, sectors, first_bad, bad_sectors); if (rv) @@ -213,8 +181,6 @@ extern int rdev_set_badblocks(struct md_rdev *rdev, sector_t s, int sectors, int is_new); extern int rdev_clear_badblocks(struct md_rdev *rdev, sector_t s, int sectors, int is_new); -extern void md_ack_all_badblocks(struct badblocks *bb); - struct md_cluster_info; struct mddev { @@ -566,7 +532,9 @@ static inline char * mdname (struct mddev * mddev) static inline int sysfs_link_rdev(struct mddev *mddev, struct md_rdev *rdev) { char nm[20]; - if (!test_bit(Replacement, &rdev->flags) && mddev->kobj.sd) { + if (!test_bit(Replacement, &rdev->flags) && + !test_bit(Journal, &rdev->flags) && + mddev->kobj.sd) { sprintf(nm, "rd%d", rdev->raid_disk); return sysfs_create_link(&mddev->kobj, &rdev->kobj, nm); } else @@ -576,7 +544,9 @@ static inline int sysfs_link_rdev(struct mddev *mddev, struct md_rdev *rdev) static inline void sysfs_unlink_rdev(struct mddev *mddev, struct md_rdev *rdev) { char nm[20]; - if (!test_bit(Replacement, &rdev->flags) && mddev->kobj.sd) { + if (!test_bit(Replacement, &rdev->flags) && + !test_bit(Journal, &rdev->flags) && + mddev->kobj.sd) { sprintf(nm, "rd%d", rdev->raid_disk); sysfs_remove_link(&mddev->kobj, nm); } diff --git a/drivers/md/persistent-data/Kconfig b/drivers/md/persistent-data/Kconfig index 78c74bb71ba4..a53cbc928af1 100644 --- a/drivers/md/persistent-data/Kconfig +++ b/drivers/md/persistent-data/Kconfig @@ -7,12 +7,3 @@ config DM_PERSISTENT_DATA Library providing immutable on-disk data structure support for device-mapper targets such as the thin provisioning target. -config DM_DEBUG_BLOCK_STACK_TRACING - bool "Keep stack trace of persistent data block lock holders" - depends on STACKTRACE_SUPPORT && DM_PERSISTENT_DATA - select STACKTRACE - ---help--- - Enable this for messages that may help debug problems with the - block manager locking used by thin provisioning and caching. - - If unsure, say N. diff --git a/drivers/md/persistent-data/dm-block-manager.c b/drivers/md/persistent-data/dm-block-manager.c index f2393ba838eb..1e33dd51c21f 100644 --- a/drivers/md/persistent-data/dm-block-manager.c +++ b/drivers/md/persistent-data/dm-block-manager.c @@ -97,10 +97,6 @@ static void __del_holder(struct block_lock *lock, struct task_struct *task) static int __check_holder(struct block_lock *lock) { unsigned i; -#ifdef CONFIG_DM_DEBUG_BLOCK_STACK_TRACING - static struct stack_trace t; - static stack_entries entries; -#endif for (i = 0; i < MAX_HOLDERS; i++) { if (lock->holders[i] == current) { @@ -110,12 +106,7 @@ static int __check_holder(struct block_lock *lock) print_stack_trace(lock->traces + i, 4); DMERR("subsequent acquisition attempted here:"); - t.nr_entries = 0; - t.max_entries = MAX_STACK; - t.entries = entries; - t.skip = 3; - save_stack_trace(&t); - print_stack_trace(&t, 4); + dump_stack(); #endif return -EINVAL; } diff --git a/drivers/md/persistent-data/dm-btree.c b/drivers/md/persistent-data/dm-btree.c index c573402033b2..ea3d3b656fd0 100644 --- a/drivers/md/persistent-data/dm-btree.c +++ b/drivers/md/persistent-data/dm-btree.c @@ -63,6 +63,11 @@ int lower_bound(struct btree_node *n, uint64_t key) return bsearch(n, key, 0); } +static int upper_bound(struct btree_node *n, uint64_t key) +{ + return bsearch(n, key, 1); +} + void inc_children(struct dm_transaction_manager *tm, struct btree_node *n, struct dm_btree_value_type *vt) { @@ -252,6 +257,16 @@ static void pop_frame(struct del_stack *s) dm_tm_unlock(s->tm, f->b); } +static void unlock_all_frames(struct del_stack *s) +{ + struct frame *f; + + while (unprocessed_frames(s)) { + f = s->spine + s->top--; + dm_tm_unlock(s->tm, f->b); + } +} + int dm_btree_del(struct dm_btree_info *info, dm_block_t root) { int r; @@ -308,9 +323,13 @@ int dm_btree_del(struct dm_btree_info *info, dm_block_t root) pop_frame(s); } } - out: + if (r) { + /* cleanup all frames of del_stack */ + unlock_all_frames(s); + } kfree(s); + return r; } EXPORT_SYMBOL_GPL(dm_btree_del); @@ -392,6 +411,82 @@ int dm_btree_lookup(struct dm_btree_info *info, dm_block_t root, } EXPORT_SYMBOL_GPL(dm_btree_lookup); +static int dm_btree_lookup_next_single(struct dm_btree_info *info, dm_block_t root, + uint64_t key, uint64_t *rkey, void *value_le) +{ + int r, i; + uint32_t flags, nr_entries; + struct dm_block *node; + struct btree_node *n; + + r = bn_read_lock(info, root, &node); + if (r) + return r; + + n = dm_block_data(node); + flags = le32_to_cpu(n->header.flags); + nr_entries = le32_to_cpu(n->header.nr_entries); + + if (flags & INTERNAL_NODE) { + i = lower_bound(n, key); + if (i < 0 || i >= nr_entries) { + r = -ENODATA; + goto out; + } + + r = dm_btree_lookup_next_single(info, value64(n, i), key, rkey, value_le); + if (r == -ENODATA && i < (nr_entries - 1)) { + i++; + r = dm_btree_lookup_next_single(info, value64(n, i), key, rkey, value_le); + } + + } else { + i = upper_bound(n, key); + if (i < 0 || i >= nr_entries) { + r = -ENODATA; + goto out; + } + + *rkey = le64_to_cpu(n->keys[i]); + memcpy(value_le, value_ptr(n, i), info->value_type.size); + } +out: + dm_tm_unlock(info->tm, node); + return r; +} + +int dm_btree_lookup_next(struct dm_btree_info *info, dm_block_t root, + uint64_t *keys, uint64_t *rkey, void *value_le) +{ + unsigned level; + int r = -ENODATA; + __le64 internal_value_le; + struct ro_spine spine; + + init_ro_spine(&spine, info); + for (level = 0; level < info->levels - 1u; level++) { + r = btree_lookup_raw(&spine, root, keys[level], + lower_bound, rkey, + &internal_value_le, sizeof(uint64_t)); + if (r) + goto out; + + if (*rkey != keys[level]) { + r = -ENODATA; + goto out; + } + + root = le64_to_cpu(internal_value_le); + } + + r = dm_btree_lookup_next_single(info, root, keys[level], rkey, value_le); +out: + exit_ro_spine(&spine); + return r; +} + +EXPORT_SYMBOL_GPL(dm_btree_lookup_next); + /* * Splits a node by creating a sibling node and shifting half the nodes * contents across. Assumes there is a parent node, and it has room for @@ -473,8 +568,10 @@ static int btree_split_sibling(struct shadow_spine *s, unsigned parent_index, r = insert_at(sizeof(__le64), pn, parent_index + 1, le64_to_cpu(rn->keys[0]), &location); - if (r) + if (r) { + unlock_block(s->info, right); return r; + } if (key < le64_to_cpu(rn->keys[0])) { unlock_block(s->info, right); @@ -657,12 +754,19 @@ static int btree_insert_raw(struct shadow_spine *s, dm_block_t root, return 0; } +static bool need_insert(struct btree_node *node, uint64_t *keys, + unsigned level, unsigned index) +{ + return ((index >= le32_to_cpu(node->header.nr_entries)) || + (le64_to_cpu(node->keys[index]) != keys[level])); +} + static int insert(struct dm_btree_info *info, dm_block_t root, uint64_t *keys, void *value, dm_block_t *new_root, int *inserted) __dm_written_to_disk(value) { - int r, need_insert; + int r; unsigned level, index = -1, last_level = info->levels - 1; dm_block_t block = root; struct shadow_spine spine; @@ -678,10 +782,8 @@ static int insert(struct dm_btree_info *info, dm_block_t root, goto bad; n = dm_block_data(shadow_current(&spine)); - need_insert = ((index >= le32_to_cpu(n->header.nr_entries)) || - (le64_to_cpu(n->keys[index]) != keys[level])); - if (need_insert) { + if (need_insert(n, keys, level, index)) { dm_block_t new_tree; __le64 new_le; @@ -708,10 +810,8 @@ static int insert(struct dm_btree_info *info, dm_block_t root, goto bad; n = dm_block_data(shadow_current(&spine)); - need_insert = ((index >= le32_to_cpu(n->header.nr_entries)) || - (le64_to_cpu(n->keys[index]) != keys[level])); - if (need_insert) { + if (need_insert(n, keys, level, index)) { if (inserted) *inserted = 1; diff --git a/drivers/md/persistent-data/dm-btree.h b/drivers/md/persistent-data/dm-btree.h index 11d8cf78621d..c74301fa5a37 100644 --- a/drivers/md/persistent-data/dm-btree.h +++ b/drivers/md/persistent-data/dm-btree.h @@ -110,6 +110,13 @@ int dm_btree_lookup(struct dm_btree_info *info, dm_block_t root, uint64_t *keys, void *value_le); /* + * Tries to find the first key where the bottom level key is >= to that + * given. Useful for skipping empty sections of the btree. + */ +int dm_btree_lookup_next(struct dm_btree_info *info, dm_block_t root, + uint64_t *keys, uint64_t *rkey, void *value_le); + +/* * Insertion (or overwrite an existing value). O(ln(n)) */ int dm_btree_insert(struct dm_btree_info *info, dm_block_t root, @@ -135,9 +142,10 @@ int dm_btree_remove(struct dm_btree_info *info, dm_block_t root, uint64_t *keys, dm_block_t *new_root); /* - * Removes values between 'keys' and keys2, where keys2 is keys with the - * final key replaced with 'end_key'. 'end_key' is the one-past-the-end - * value. 'keys' may be altered. + * Removes a _contiguous_ run of values starting from 'keys' and not + * reaching keys2 (where keys2 is keys with the final key replaced with + * 'end_key'). 'end_key' is the one-past-the-end value. 'keys' may be + * altered. */ int dm_btree_remove_leaves(struct dm_btree_info *info, dm_block_t root, uint64_t *keys, uint64_t end_key, diff --git a/drivers/md/persistent-data/dm-space-map-metadata.c b/drivers/md/persistent-data/dm-space-map-metadata.c index 53091295fce9..7e44005595c1 100644 --- a/drivers/md/persistent-data/dm-space-map-metadata.c +++ b/drivers/md/persistent-data/dm-space-map-metadata.c @@ -136,7 +136,7 @@ static int brb_push(struct bop_ring_buffer *brb, return 0; } -static int brb_pop(struct bop_ring_buffer *brb, struct block_op *result) +static int brb_peek(struct bop_ring_buffer *brb, struct block_op *result) { struct block_op *bop; @@ -147,6 +147,14 @@ static int brb_pop(struct bop_ring_buffer *brb, struct block_op *result) result->type = bop->type; result->block = bop->block; + return 0; +} + +static int brb_pop(struct bop_ring_buffer *brb) +{ + if (brb_empty(brb)) + return -ENODATA; + brb->begin = brb_next(brb, brb->begin); return 0; @@ -211,7 +219,7 @@ static int apply_bops(struct sm_metadata *smm) while (!brb_empty(&smm->uncommitted)) { struct block_op bop; - r = brb_pop(&smm->uncommitted, &bop); + r = brb_peek(&smm->uncommitted, &bop); if (r) { DMERR("bug in bop ring buffer"); break; @@ -220,6 +228,8 @@ static int apply_bops(struct sm_metadata *smm) r = commit_bop(smm, &bop); if (r) break; + + brb_pop(&smm->uncommitted); } return r; @@ -683,7 +693,6 @@ static struct dm_space_map bootstrap_ops = { static int sm_metadata_extend(struct dm_space_map *sm, dm_block_t extra_blocks) { int r, i; - enum allocation_event ev; struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm); dm_block_t old_len = smm->ll.nr_blocks; @@ -705,11 +714,12 @@ static int sm_metadata_extend(struct dm_space_map *sm, dm_block_t extra_blocks) * allocate any new blocks. */ do { - for (i = old_len; !r && i < smm->begin; i++) { - r = sm_ll_inc(&smm->ll, i, &ev); - if (r) - goto out; - } + for (i = old_len; !r && i < smm->begin; i++) + r = add_bop(smm, BOP_INC, i); + + if (r) + goto out; + old_len = smm->begin; r = apply_bops(smm); @@ -754,7 +764,6 @@ int dm_sm_metadata_create(struct dm_space_map *sm, { int r; dm_block_t i; - enum allocation_event ev; struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm); smm->begin = superblock + 1; @@ -782,7 +791,7 @@ int dm_sm_metadata_create(struct dm_space_map *sm, * allocated blocks that they were built from. */ for (i = superblock; !r && i < smm->begin; i++) - r = sm_ll_inc(&smm->ll, i, &ev); + r = add_bop(smm, BOP_INC, i); if (r) return r; diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 41d70bc9ba2f..84e597e1c489 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -1946,6 +1946,8 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio) first = i; fbio = r10_bio->devs[i].bio; + fbio->bi_iter.bi_size = r10_bio->sectors << 9; + fbio->bi_iter.bi_idx = 0; vcnt = (r10_bio->sectors + (PAGE_SIZE >> 9) - 1) >> (PAGE_SHIFT - 9); /* now find blocks with errors */ @@ -1989,7 +1991,7 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio) bio_reset(tbio); tbio->bi_vcnt = vcnt; - tbio->bi_iter.bi_size = r10_bio->sectors << 9; + tbio->bi_iter.bi_size = fbio->bi_iter.bi_size; tbio->bi_rw = WRITE; tbio->bi_private = r10_bio; tbio->bi_iter.bi_sector = r10_bio->devs[i].addr; |