diff options
author | Greg Kroah-Hartman <gregkh@linuxfoundation.org> | 2021-01-25 11:19:46 +0100 |
---|---|---|
committer | Greg Kroah-Hartman <gregkh@linuxfoundation.org> | 2021-01-25 11:19:46 +0100 |
commit | 0f8b29fabacbcf0e617896c7ea832b7ea2ef2406 (patch) | |
tree | 0187f2baef24b5d78d94aecc7057356a36c58b5d /drivers/md | |
parent | tty: fix up iterate_tty_read() EOVERFLOW handling (diff) | |
parent | Linux 5.11-rc5 (diff) | |
download | linux-0f8b29fabacbcf0e617896c7ea832b7ea2ef2406.tar.xz linux-0f8b29fabacbcf0e617896c7ea832b7ea2ef2406.zip |
Merge 5.11-rc5 into tty-next
We need the fixes in here and this resolves a merge issue in
drivers/tty/tty_io.c
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Diffstat (limited to 'drivers/md')
-rw-r--r-- | drivers/md/Kconfig | 2 | ||||
-rw-r--r-- | drivers/md/bcache/features.c | 2 | ||||
-rw-r--r-- | drivers/md/bcache/features.h | 30 | ||||
-rw-r--r-- | drivers/md/bcache/super.c | 53 | ||||
-rw-r--r-- | drivers/md/dm-bufio.c | 6 | ||||
-rw-r--r-- | drivers/md/dm-crypt.c | 177 | ||||
-rw-r--r-- | drivers/md/dm-integrity.c | 92 | ||||
-rw-r--r-- | drivers/md/dm-raid.c | 6 | ||||
-rw-r--r-- | drivers/md/dm-snap.c | 24 | ||||
-rw-r--r-- | drivers/md/dm-table.c | 15 | ||||
-rw-r--r-- | drivers/md/dm.c | 2 | ||||
-rw-r--r-- | drivers/md/md.c | 2 |
12 files changed, 359 insertions, 52 deletions
diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig index b7e2d9666614..9e44c09f6410 100644 --- a/drivers/md/Kconfig +++ b/drivers/md/Kconfig @@ -605,6 +605,7 @@ config DM_INTEGRITY select BLK_DEV_INTEGRITY select DM_BUFIO select CRYPTO + select CRYPTO_SKCIPHER select ASYNC_XOR help This device-mapper target emulates a block device that has @@ -622,6 +623,7 @@ config DM_ZONED tristate "Drive-managed zoned block device target support" depends on BLK_DEV_DM depends on BLK_DEV_ZONED + select CRC32 help This device-mapper target takes a host-managed or host-aware zoned block device and exposes most of its capacity as a regular block diff --git a/drivers/md/bcache/features.c b/drivers/md/bcache/features.c index 6469223f0b77..d636b7b2d070 100644 --- a/drivers/md/bcache/features.c +++ b/drivers/md/bcache/features.c @@ -17,7 +17,7 @@ struct feature { }; static struct feature feature_list[] = { - {BCH_FEATURE_INCOMPAT, BCH_FEATURE_INCOMPAT_LARGE_BUCKET, + {BCH_FEATURE_INCOMPAT, BCH_FEATURE_INCOMPAT_LOG_LARGE_BUCKET_SIZE, "large_bucket"}, {0, 0, 0 }, }; diff --git a/drivers/md/bcache/features.h b/drivers/md/bcache/features.h index a1653c478041..84fc2c0f0101 100644 --- a/drivers/md/bcache/features.h +++ b/drivers/md/bcache/features.h @@ -13,11 +13,15 @@ /* Feature set definition */ /* Incompat feature set */ -#define BCH_FEATURE_INCOMPAT_LARGE_BUCKET 0x0001 /* 32bit bucket size */ +/* 32bit bucket size, obsoleted */ +#define BCH_FEATURE_INCOMPAT_OBSO_LARGE_BUCKET 0x0001 +/* real bucket size is (1 << bucket_size) */ +#define BCH_FEATURE_INCOMPAT_LOG_LARGE_BUCKET_SIZE 0x0002 -#define BCH_FEATURE_COMPAT_SUUP 0 -#define BCH_FEATURE_RO_COMPAT_SUUP 0 -#define BCH_FEATURE_INCOMPAT_SUUP BCH_FEATURE_INCOMPAT_LARGE_BUCKET +#define BCH_FEATURE_COMPAT_SUPP 0 +#define BCH_FEATURE_RO_COMPAT_SUPP 0 +#define BCH_FEATURE_INCOMPAT_SUPP (BCH_FEATURE_INCOMPAT_OBSO_LARGE_BUCKET| \ + BCH_FEATURE_INCOMPAT_LOG_LARGE_BUCKET_SIZE) #define BCH_HAS_COMPAT_FEATURE(sb, mask) \ ((sb)->feature_compat & (mask)) @@ -77,7 +81,23 @@ static inline void bch_clear_feature_##name(struct cache_sb *sb) \ ~BCH##_FEATURE_INCOMPAT_##flagname; \ } -BCH_FEATURE_INCOMPAT_FUNCS(large_bucket, LARGE_BUCKET); +BCH_FEATURE_INCOMPAT_FUNCS(obso_large_bucket, OBSO_LARGE_BUCKET); +BCH_FEATURE_INCOMPAT_FUNCS(large_bucket, LOG_LARGE_BUCKET_SIZE); + +static inline bool bch_has_unknown_compat_features(struct cache_sb *sb) +{ + return ((sb->feature_compat & ~BCH_FEATURE_COMPAT_SUPP) != 0); +} + +static inline bool bch_has_unknown_ro_compat_features(struct cache_sb *sb) +{ + return ((sb->feature_ro_compat & ~BCH_FEATURE_RO_COMPAT_SUPP) != 0); +} + +static inline bool bch_has_unknown_incompat_features(struct cache_sb *sb) +{ + return ((sb->feature_incompat & ~BCH_FEATURE_INCOMPAT_SUPP) != 0); +} int bch_print_cache_set_feature_compat(struct cache_set *c, char *buf, int size); int bch_print_cache_set_feature_ro_compat(struct cache_set *c, char *buf, int size); diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index a4752ac410dc..2047a9cccdb5 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -64,9 +64,25 @@ static unsigned int get_bucket_size(struct cache_sb *sb, struct cache_sb_disk *s { unsigned int bucket_size = le16_to_cpu(s->bucket_size); - if (sb->version >= BCACHE_SB_VERSION_CDEV_WITH_FEATURES && - bch_has_feature_large_bucket(sb)) - bucket_size |= le16_to_cpu(s->bucket_size_hi) << 16; + if (sb->version >= BCACHE_SB_VERSION_CDEV_WITH_FEATURES) { + if (bch_has_feature_large_bucket(sb)) { + unsigned int max, order; + + max = sizeof(unsigned int) * BITS_PER_BYTE - 1; + order = le16_to_cpu(s->bucket_size); + /* + * bcache tool will make sure the overflow won't + * happen, an error message here is enough. + */ + if (order > max) + pr_err("Bucket size (1 << %u) overflows\n", + order); + bucket_size = 1 << order; + } else if (bch_has_feature_obso_large_bucket(sb)) { + bucket_size += + le16_to_cpu(s->obso_bucket_size_hi) << 16; + } + } return bucket_size; } @@ -228,6 +244,20 @@ static const char *read_super(struct cache_sb *sb, struct block_device *bdev, sb->feature_compat = le64_to_cpu(s->feature_compat); sb->feature_incompat = le64_to_cpu(s->feature_incompat); sb->feature_ro_compat = le64_to_cpu(s->feature_ro_compat); + + /* Check incompatible features */ + err = "Unsupported compatible feature found"; + if (bch_has_unknown_compat_features(sb)) + goto err; + + err = "Unsupported read-only compatible feature found"; + if (bch_has_unknown_ro_compat_features(sb)) + goto err; + + err = "Unsupported incompatible feature found"; + if (bch_has_unknown_incompat_features(sb)) + goto err; + err = read_super_common(sb, bdev, s); if (err) goto err; @@ -1302,6 +1332,12 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c, bcache_device_link(&dc->disk, c, "bdev"); atomic_inc(&c->attached_dev_nr); + if (bch_has_feature_obso_large_bucket(&(c->cache->sb))) { + pr_err("The obsoleted large bucket layout is unsupported, set the bcache device into read-only\n"); + pr_err("Please update to the latest bcache-tools to create the cache device\n"); + set_disk_ro(dc->disk.disk, 1); + } + /* Allow the writeback thread to proceed */ up_write(&dc->writeback_lock); @@ -1524,6 +1560,12 @@ static int flash_dev_run(struct cache_set *c, struct uuid_entry *u) bcache_device_link(d, c, "volume"); + if (bch_has_feature_obso_large_bucket(&c->cache->sb)) { + pr_err("The obsoleted large bucket layout is unsupported, set the bcache device into read-only\n"); + pr_err("Please update to the latest bcache-tools to create the cache device\n"); + set_disk_ro(d->disk, 1); + } + return 0; err: kobject_put(&d->kobj); @@ -2083,6 +2125,9 @@ static int run_cache_set(struct cache_set *c) c->cache->sb.last_mount = (u32)ktime_get_real_seconds(); bcache_write_super(c); + if (bch_has_feature_obso_large_bucket(&c->cache->sb)) + pr_err("Detect obsoleted large bucket layout, all attached bcache device will be read-only\n"); + list_for_each_entry_safe(dc, t, &uncached_devices, list) bch_cached_dev_attach(dc, c, NULL); @@ -2644,8 +2689,8 @@ static ssize_t bch_pending_bdevs_cleanup(struct kobject *k, } list_for_each_entry_safe(pdev, tpdev, &pending_devs, list) { + char *pdev_set_uuid = pdev->dc->sb.set_uuid; list_for_each_entry_safe(c, tc, &bch_cache_sets, list) { - char *pdev_set_uuid = pdev->dc->sb.set_uuid; char *set_uuid = c->set_uuid; if (!memcmp(pdev_set_uuid, set_uuid, 16)) { diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index 9c1a86bde658..fce4cbf9529d 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -1534,6 +1534,12 @@ sector_t dm_bufio_get_device_size(struct dm_bufio_client *c) } EXPORT_SYMBOL_GPL(dm_bufio_get_device_size); +struct dm_io_client *dm_bufio_get_dm_io_client(struct dm_bufio_client *c) +{ + return c->dm_io; +} +EXPORT_SYMBOL_GPL(dm_bufio_get_dm_io_client); + sector_t dm_bufio_get_block_number(struct dm_buffer *b) { return b->block; diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 5f9f9b3a226d..5a55617a08e6 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -1454,13 +1454,16 @@ static int crypt_convert_block_skcipher(struct crypt_config *cc, static void kcryptd_async_done(struct crypto_async_request *async_req, int error); -static void crypt_alloc_req_skcipher(struct crypt_config *cc, +static int crypt_alloc_req_skcipher(struct crypt_config *cc, struct convert_context *ctx) { unsigned key_index = ctx->cc_sector & (cc->tfms_count - 1); - if (!ctx->r.req) - ctx->r.req = mempool_alloc(&cc->req_pool, GFP_NOIO); + if (!ctx->r.req) { + ctx->r.req = mempool_alloc(&cc->req_pool, in_interrupt() ? GFP_ATOMIC : GFP_NOIO); + if (!ctx->r.req) + return -ENOMEM; + } skcipher_request_set_tfm(ctx->r.req, cc->cipher_tfm.tfms[key_index]); @@ -1471,13 +1474,18 @@ static void crypt_alloc_req_skcipher(struct crypt_config *cc, skcipher_request_set_callback(ctx->r.req, CRYPTO_TFM_REQ_MAY_BACKLOG, kcryptd_async_done, dmreq_of_req(cc, ctx->r.req)); + + return 0; } -static void crypt_alloc_req_aead(struct crypt_config *cc, +static int crypt_alloc_req_aead(struct crypt_config *cc, struct convert_context *ctx) { - if (!ctx->r.req_aead) - ctx->r.req_aead = mempool_alloc(&cc->req_pool, GFP_NOIO); + if (!ctx->r.req_aead) { + ctx->r.req_aead = mempool_alloc(&cc->req_pool, in_interrupt() ? GFP_ATOMIC : GFP_NOIO); + if (!ctx->r.req_aead) + return -ENOMEM; + } aead_request_set_tfm(ctx->r.req_aead, cc->cipher_tfm.tfms_aead[0]); @@ -1488,15 +1496,17 @@ static void crypt_alloc_req_aead(struct crypt_config *cc, aead_request_set_callback(ctx->r.req_aead, CRYPTO_TFM_REQ_MAY_BACKLOG, kcryptd_async_done, dmreq_of_req(cc, ctx->r.req_aead)); + + return 0; } -static void crypt_alloc_req(struct crypt_config *cc, +static int crypt_alloc_req(struct crypt_config *cc, struct convert_context *ctx) { if (crypt_integrity_aead(cc)) - crypt_alloc_req_aead(cc, ctx); + return crypt_alloc_req_aead(cc, ctx); else - crypt_alloc_req_skcipher(cc, ctx); + return crypt_alloc_req_skcipher(cc, ctx); } static void crypt_free_req_skcipher(struct crypt_config *cc, @@ -1529,17 +1539,28 @@ static void crypt_free_req(struct crypt_config *cc, void *req, struct bio *base_ * Encrypt / decrypt data from one bio to another one (can be the same one) */ static blk_status_t crypt_convert(struct crypt_config *cc, - struct convert_context *ctx, bool atomic) + struct convert_context *ctx, bool atomic, bool reset_pending) { unsigned int tag_offset = 0; unsigned int sector_step = cc->sector_size >> SECTOR_SHIFT; int r; - atomic_set(&ctx->cc_pending, 1); + /* + * if reset_pending is set we are dealing with the bio for the first time, + * else we're continuing to work on the previous bio, so don't mess with + * the cc_pending counter + */ + if (reset_pending) + atomic_set(&ctx->cc_pending, 1); while (ctx->iter_in.bi_size && ctx->iter_out.bi_size) { - crypt_alloc_req(cc, ctx); + r = crypt_alloc_req(cc, ctx); + if (r) { + complete(&ctx->restart); + return BLK_STS_DEV_RESOURCE; + } + atomic_inc(&ctx->cc_pending); if (crypt_integrity_aead(cc)) @@ -1553,7 +1574,25 @@ static blk_status_t crypt_convert(struct crypt_config *cc, * but the driver request queue is full, let's wait. */ case -EBUSY: - wait_for_completion(&ctx->restart); + if (in_interrupt()) { + if (try_wait_for_completion(&ctx->restart)) { + /* + * we don't have to block to wait for completion, + * so proceed + */ + } else { + /* + * we can't wait for completion without blocking + * exit and continue processing in a workqueue + */ + ctx->r.req = NULL; + ctx->cc_sector += sector_step; + tag_offset++; + return BLK_STS_DEV_RESOURCE; + } + } else { + wait_for_completion(&ctx->restart); + } reinit_completion(&ctx->restart); fallthrough; /* @@ -1691,6 +1730,12 @@ static void crypt_inc_pending(struct dm_crypt_io *io) atomic_inc(&io->io_pending); } +static void kcryptd_io_bio_endio(struct work_struct *work) +{ + struct dm_crypt_io *io = container_of(work, struct dm_crypt_io, work); + bio_endio(io->base_bio); +} + /* * One of the bios was finished. Check for completion of * the whole request and correctly clean up the buffer. @@ -1713,7 +1758,23 @@ static void crypt_dec_pending(struct dm_crypt_io *io) kfree(io->integrity_metadata); base_bio->bi_status = error; - bio_endio(base_bio); + + /* + * If we are running this function from our tasklet, + * we can't call bio_endio() here, because it will call + * clone_endio() from dm.c, which in turn will + * free the current struct dm_crypt_io structure with + * our tasklet. In this case we need to delay bio_endio() + * execution to after the tasklet is done and dequeued. + */ + if (tasklet_trylock(&io->tasklet)) { + tasklet_unlock(&io->tasklet); + bio_endio(base_bio); + return; + } + + INIT_WORK(&io->work, kcryptd_io_bio_endio); + queue_work(cc->io_queue, &io->work); } /* @@ -1945,6 +2006,37 @@ static bool kcryptd_crypt_write_inline(struct crypt_config *cc, } } +static void kcryptd_crypt_write_continue(struct work_struct *work) +{ + struct dm_crypt_io *io = container_of(work, struct dm_crypt_io, work); + struct crypt_config *cc = io->cc; + struct convert_context *ctx = &io->ctx; + int crypt_finished; + sector_t sector = io->sector; + blk_status_t r; + + wait_for_completion(&ctx->restart); + reinit_completion(&ctx->restart); + + r = crypt_convert(cc, &io->ctx, true, false); + if (r) + io->error = r; + crypt_finished = atomic_dec_and_test(&ctx->cc_pending); + if (!crypt_finished && kcryptd_crypt_write_inline(cc, ctx)) { + /* Wait for completion signaled by kcryptd_async_done() */ + wait_for_completion(&ctx->restart); + crypt_finished = 1; + } + + /* Encryption was already finished, submit io now */ + if (crypt_finished) { + kcryptd_crypt_write_io_submit(io, 0); + io->sector = sector; + } + + crypt_dec_pending(io); +} + static void kcryptd_crypt_write_convert(struct dm_crypt_io *io) { struct crypt_config *cc = io->cc; @@ -1973,7 +2065,17 @@ static void kcryptd_crypt_write_convert(struct dm_crypt_io *io) crypt_inc_pending(io); r = crypt_convert(cc, ctx, - test_bit(DM_CRYPT_NO_WRITE_WORKQUEUE, &cc->flags)); + test_bit(DM_CRYPT_NO_WRITE_WORKQUEUE, &cc->flags), true); + /* + * Crypto API backlogged the request, because its queue was full + * and we're in softirq context, so continue from a workqueue + * (TODO: is it actually possible to be in softirq in the write path?) + */ + if (r == BLK_STS_DEV_RESOURCE) { + INIT_WORK(&io->work, kcryptd_crypt_write_continue); + queue_work(cc->crypt_queue, &io->work); + return; + } if (r) io->error = r; crypt_finished = atomic_dec_and_test(&ctx->cc_pending); @@ -1998,6 +2100,25 @@ static void kcryptd_crypt_read_done(struct dm_crypt_io *io) crypt_dec_pending(io); } +static void kcryptd_crypt_read_continue(struct work_struct *work) +{ + struct dm_crypt_io *io = container_of(work, struct dm_crypt_io, work); + struct crypt_config *cc = io->cc; + blk_status_t r; + + wait_for_completion(&io->ctx.restart); + reinit_completion(&io->ctx.restart); + + r = crypt_convert(cc, &io->ctx, true, false); + if (r) + io->error = r; + + if (atomic_dec_and_test(&io->ctx.cc_pending)) + kcryptd_crypt_read_done(io); + + crypt_dec_pending(io); +} + static void kcryptd_crypt_read_convert(struct dm_crypt_io *io) { struct crypt_config *cc = io->cc; @@ -2009,7 +2130,16 @@ static void kcryptd_crypt_read_convert(struct dm_crypt_io *io) io->sector); r = crypt_convert(cc, &io->ctx, - test_bit(DM_CRYPT_NO_READ_WORKQUEUE, &cc->flags)); + test_bit(DM_CRYPT_NO_READ_WORKQUEUE, &cc->flags), true); + /* + * Crypto API backlogged the request, because its queue was full + * and we're in softirq context, so continue from a workqueue + */ + if (r == BLK_STS_DEV_RESOURCE) { + INIT_WORK(&io->work, kcryptd_crypt_read_continue); + queue_work(cc->crypt_queue, &io->work); + return; + } if (r) io->error = r; @@ -2091,8 +2221,12 @@ static void kcryptd_queue_crypt(struct dm_crypt_io *io) if ((bio_data_dir(io->base_bio) == READ && test_bit(DM_CRYPT_NO_READ_WORKQUEUE, &cc->flags)) || (bio_data_dir(io->base_bio) == WRITE && test_bit(DM_CRYPT_NO_WRITE_WORKQUEUE, &cc->flags))) { - if (in_irq()) { - /* Crypto API's "skcipher_walk_first() refuses to work in hard IRQ context */ + /* + * in_irq(): Crypto API's skcipher_walk_first() refuses to work in hard IRQ context. + * irqs_disabled(): the kernel may run some IO completion from the idle thread, but + * it is being executed with irqs disabled. + */ + if (in_irq() || irqs_disabled()) { tasklet_init(&io->tasklet, kcryptd_crypt_tasklet, (unsigned long)&io->work); tasklet_schedule(&io->tasklet); return; @@ -3166,12 +3300,11 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv) } if (test_bit(DM_CRYPT_SAME_CPU, &cc->flags)) - cc->crypt_queue = alloc_workqueue("kcryptd-%s", WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM, + cc->crypt_queue = alloc_workqueue("kcryptd/%s", WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM, 1, devname); else - cc->crypt_queue = alloc_workqueue("kcryptd-%s", - WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM | - WQ_UNBOUND | WQ_SYSFS, + cc->crypt_queue = alloc_workqueue("kcryptd/%s", + WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM | WQ_UNBOUND, num_online_cpus(), devname); if (!cc->crypt_queue) { ti->error = "Couldn't create kcryptd queue"; diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index 5a7a1b90e671..b64fede032dc 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -257,8 +257,9 @@ struct dm_integrity_c { bool journal_uptodate; bool just_formatted; bool recalculate_flag; - bool fix_padding; bool discard; + bool fix_padding; + bool legacy_recalculate; struct alg_spec internal_hash_alg; struct alg_spec journal_crypt_alg; @@ -386,6 +387,14 @@ static int dm_integrity_failed(struct dm_integrity_c *ic) return READ_ONCE(ic->failed); } +static bool dm_integrity_disable_recalculate(struct dm_integrity_c *ic) +{ + if ((ic->internal_hash_alg.key || ic->journal_mac_alg.key) && + !ic->legacy_recalculate) + return true; + return false; +} + static commit_id_t dm_integrity_commit_id(struct dm_integrity_c *ic, unsigned i, unsigned j, unsigned char seq) { @@ -1379,12 +1388,52 @@ thorough_test: #undef MAY_BE_HASH } -static void dm_integrity_flush_buffers(struct dm_integrity_c *ic) +struct flush_request { + struct dm_io_request io_req; + struct dm_io_region io_reg; + struct dm_integrity_c *ic; + struct completion comp; +}; + +static void flush_notify(unsigned long error, void *fr_) +{ + struct flush_request *fr = fr_; + if (unlikely(error != 0)) + dm_integrity_io_error(fr->ic, "flusing disk cache", -EIO); + complete(&fr->comp); +} + +static void dm_integrity_flush_buffers(struct dm_integrity_c *ic, bool flush_data) { int r; + + struct flush_request fr; + + if (!ic->meta_dev) + flush_data = false; + if (flush_data) { + fr.io_req.bi_op = REQ_OP_WRITE, + fr.io_req.bi_op_flags = REQ_PREFLUSH | REQ_SYNC, + fr.io_req.mem.type = DM_IO_KMEM, + fr.io_req.mem.ptr.addr = NULL, + fr.io_req.notify.fn = flush_notify, + fr.io_req.notify.context = &fr; + fr.io_req.client = dm_bufio_get_dm_io_client(ic->bufio), + fr.io_reg.bdev = ic->dev->bdev, + fr.io_reg.sector = 0, + fr.io_reg.count = 0, + fr.ic = ic; + init_completion(&fr.comp); + r = dm_io(&fr.io_req, 1, &fr.io_reg, NULL); + BUG_ON(r); + } + r = dm_bufio_write_dirty_buffers(ic->bufio); if (unlikely(r)) dm_integrity_io_error(ic, "writing tags", r); + + if (flush_data) + wait_for_completion(&fr.comp); } static void sleep_on_endio_wait(struct dm_integrity_c *ic) @@ -2110,7 +2159,7 @@ offload_to_thread: if (unlikely(dio->op == REQ_OP_DISCARD) && likely(ic->mode != 'D')) { integrity_metadata(&dio->work); - dm_integrity_flush_buffers(ic); + dm_integrity_flush_buffers(ic, false); dio->in_flight = (atomic_t)ATOMIC_INIT(1); dio->completion = NULL; @@ -2195,7 +2244,7 @@ static void integrity_commit(struct work_struct *w) flushes = bio_list_get(&ic->flush_bio_list); if (unlikely(ic->mode != 'J')) { spin_unlock_irq(&ic->endio_wait.lock); - dm_integrity_flush_buffers(ic); + dm_integrity_flush_buffers(ic, true); goto release_flush_bios; } @@ -2409,7 +2458,7 @@ skip_io: complete_journal_op(&comp); wait_for_completion_io(&comp.comp); - dm_integrity_flush_buffers(ic); + dm_integrity_flush_buffers(ic, true); } static void integrity_writer(struct work_struct *w) @@ -2451,7 +2500,7 @@ static void recalc_write_super(struct dm_integrity_c *ic) { int r; - dm_integrity_flush_buffers(ic); + dm_integrity_flush_buffers(ic, false); if (dm_integrity_failed(ic)) return; @@ -2654,7 +2703,7 @@ static void bitmap_flush_work(struct work_struct *work) unsigned long limit; struct bio *bio; - dm_integrity_flush_buffers(ic); + dm_integrity_flush_buffers(ic, false); range.logical_sector = 0; range.n_sectors = ic->provided_data_sectors; @@ -2663,9 +2712,7 @@ static void bitmap_flush_work(struct work_struct *work) add_new_range_and_wait(ic, &range); spin_unlock_irq(&ic->endio_wait.lock); - dm_integrity_flush_buffers(ic); - if (ic->meta_dev) - blkdev_issue_flush(ic->dev->bdev, GFP_NOIO); + dm_integrity_flush_buffers(ic, true); limit = ic->provided_data_sectors; if (ic->sb->flags & cpu_to_le32(SB_FLAG_RECALCULATING)) { @@ -2934,11 +2981,11 @@ static void dm_integrity_postsuspend(struct dm_target *ti) if (ic->meta_dev) queue_work(ic->writer_wq, &ic->writer_work); drain_workqueue(ic->writer_wq); - dm_integrity_flush_buffers(ic); + dm_integrity_flush_buffers(ic, true); } if (ic->mode == 'B') { - dm_integrity_flush_buffers(ic); + dm_integrity_flush_buffers(ic, true); #if 1 /* set to 0 to test bitmap replay code */ init_journal(ic, 0, ic->journal_sections, 0); @@ -3102,6 +3149,7 @@ static void dm_integrity_status(struct dm_target *ti, status_type_t type, arg_count += !!ic->journal_crypt_alg.alg_string; arg_count += !!ic->journal_mac_alg.alg_string; arg_count += (ic->sb->flags & cpu_to_le32(SB_FLAG_FIXED_PADDING)) != 0; + arg_count += ic->legacy_recalculate; DMEMIT("%s %llu %u %c %u", ic->dev->name, ic->start, ic->tag_size, ic->mode, arg_count); if (ic->meta_dev) @@ -3125,6 +3173,8 @@ static void dm_integrity_status(struct dm_target *ti, status_type_t type, } if ((ic->sb->flags & cpu_to_le32(SB_FLAG_FIXED_PADDING)) != 0) DMEMIT(" fix_padding"); + if (ic->legacy_recalculate) + DMEMIT(" legacy_recalculate"); #define EMIT_ALG(a, n) \ do { \ @@ -3754,7 +3804,7 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned argc, char **argv) unsigned extra_args; struct dm_arg_set as; static const struct dm_arg _args[] = { - {0, 9, "Invalid number of feature args"}, + {0, 16, "Invalid number of feature args"}, }; unsigned journal_sectors, interleave_sectors, buffer_sectors, journal_watermark, sync_msec; bool should_write_sb; @@ -3902,6 +3952,8 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned argc, char **argv) ic->discard = true; } else if (!strcmp(opt_string, "fix_padding")) { ic->fix_padding = true; + } else if (!strcmp(opt_string, "legacy_recalculate")) { + ic->legacy_recalculate = true; } else { r = -EINVAL; ti->error = "Invalid argument"; @@ -4197,6 +4249,20 @@ try_smaller_buffer: r = -ENOMEM; goto bad; } + } else { + if (ic->sb->flags & cpu_to_le32(SB_FLAG_RECALCULATING)) { + ti->error = "Recalculate can only be specified with internal_hash"; + r = -EINVAL; + goto bad; + } + } + + if (ic->sb->flags & cpu_to_le32(SB_FLAG_RECALCULATING) && + le64_to_cpu(ic->sb->recalc_sector) < ic->provided_data_sectors && + dm_integrity_disable_recalculate(ic)) { + ti->error = "Recalculating with HMAC is disabled for security reasons - if you really need it, use the argument \"legacy_recalculate\""; + r = -EOPNOTSUPP; + goto bad; } ic->bufio = dm_bufio_client_create(ic->meta_dev ? ic->meta_dev->bdev : ic->dev->bdev, diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index 23c38777e8f6..cab12b2251ba 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -3729,10 +3729,10 @@ static void raid_io_hints(struct dm_target *ti, struct queue_limits *limits) blk_limits_io_opt(limits, chunk_size_bytes * mddev_data_stripes(rs)); /* - * RAID1 and RAID10 personalities require bio splitting, - * RAID0/4/5/6 don't and process large discard bios properly. + * RAID0 and RAID10 personalities require bio splitting, + * RAID1/4/5/6 don't and process large discard bios properly. */ - if (rs_is_raid1(rs) || rs_is_raid10(rs)) { + if (rs_is_raid0(rs) || rs_is_raid10(rs)) { limits->discard_granularity = chunk_size_bytes; limits->max_discard_sectors = rs->md.chunk_sectors; } diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c index 4668b2cd98f4..11890db71f3f 100644 --- a/drivers/md/dm-snap.c +++ b/drivers/md/dm-snap.c @@ -141,6 +141,11 @@ struct dm_snapshot { * for them to be committed. */ struct bio_list bios_queued_during_merge; + + /* + * Flush data after merge. + */ + struct bio flush_bio; }; /* @@ -1121,6 +1126,17 @@ shut: static void error_bios(struct bio *bio); +static int flush_data(struct dm_snapshot *s) +{ + struct bio *flush_bio = &s->flush_bio; + + bio_reset(flush_bio); + bio_set_dev(flush_bio, s->origin->bdev); + flush_bio->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH; + + return submit_bio_wait(flush_bio); +} + static void merge_callback(int read_err, unsigned long write_err, void *context) { struct dm_snapshot *s = context; @@ -1134,6 +1150,11 @@ static void merge_callback(int read_err, unsigned long write_err, void *context) goto shut; } + if (flush_data(s) < 0) { + DMERR("Flush after merge failed: shutting down merge"); + goto shut; + } + if (s->store->type->commit_merge(s->store, s->num_merging_chunks) < 0) { DMERR("Write error in exception store: shutting down merge"); @@ -1318,6 +1339,7 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv) s->first_merging_chunk = 0; s->num_merging_chunks = 0; bio_list_init(&s->bios_queued_during_merge); + bio_init(&s->flush_bio, NULL, 0); /* Allocate hash table for COW data */ if (init_hash_tables(s)) { @@ -1504,6 +1526,8 @@ static void snapshot_dtr(struct dm_target *ti) dm_exception_store_destroy(s->store); + bio_uninit(&s->flush_bio); + dm_put_device(ti, s->cow); dm_put_device(ti, s->origin); diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 188f41287f18..4acf2342f7ad 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -363,14 +363,23 @@ int dm_get_device(struct dm_target *ti, const char *path, fmode_t mode, { int r; dev_t dev; + unsigned int major, minor; + char dummy; struct dm_dev_internal *dd; struct dm_table *t = ti->table; BUG_ON(!t); - dev = dm_get_dev_t(path); - if (!dev) - return -ENODEV; + if (sscanf(path, "%u:%u%c", &major, &minor, &dummy) == 2) { + /* Extract the major/minor numbers */ + dev = MKDEV(major, minor); + if (MAJOR(dev) != major || MINOR(dev) != minor) + return -EOVERFLOW; + } else { + dev = dm_get_dev_t(path); + if (!dev) + return -ENODEV; + } dd = find_device(&t->devices, dev); if (!dd) { diff --git a/drivers/md/dm.c b/drivers/md/dm.c index b3c3c8b4cb42..7bac564f3faa 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -562,7 +562,7 @@ static int dm_blk_ioctl(struct block_device *bdev, fmode_t mode, * subset of the parent bdev; require extra privileges. */ if (!capable(CAP_SYS_RAWIO)) { - DMWARN_LIMIT( + DMDEBUG_LIMIT( "%s: sending ioctl %x to DM device without required privilege.", current->comm, cmd); r = -ENOIOCTLCMD; diff --git a/drivers/md/md.c b/drivers/md/md.c index ca409428b4fc..04384452a7ab 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -639,8 +639,10 @@ static void md_submit_flush_data(struct work_struct *ws) * could wait for this and below md_handle_request could wait for those * bios because of suspend check */ + spin_lock_irq(&mddev->lock); mddev->prev_flush_start = mddev->start_flush; mddev->flush_bio = NULL; + spin_unlock_irq(&mddev->lock); wake_up(&mddev->sb_wait); if (bio->bi_iter.bi_size == 0) { |