diff options
Diffstat (limited to 'drivers/md')
-rw-r--r-- | drivers/md/dm-crypt.c | 43 | ||||
-rw-r--r-- | drivers/md/dm-io.c | 4 | ||||
-rw-r--r-- | drivers/md/dm-ioctl.c | 7 | ||||
-rw-r--r-- | drivers/md/dm-kcopyd.c | 2 | ||||
-rw-r--r-- | drivers/md/dm.c | 32 | ||||
-rw-r--r-- | drivers/md/linear.c | 6 | ||||
-rw-r--r-- | drivers/md/md.c | 58 | ||||
-rw-r--r-- | drivers/md/raid1.c | 6 | ||||
-rw-r--r-- | drivers/md/raid10.c | 19 |
9 files changed, 109 insertions, 68 deletions
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 35bda49796f..bfefd079a95 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -60,6 +60,7 @@ struct dm_crypt_io { }; struct dm_crypt_request { + struct convert_context *ctx; struct scatterlist sg_in; struct scatterlist sg_out; }; @@ -335,6 +336,18 @@ static void crypt_convert_init(struct crypt_config *cc, init_completion(&ctx->restart); } +static struct dm_crypt_request *dmreq_of_req(struct crypt_config *cc, + struct ablkcipher_request *req) +{ + return (struct dm_crypt_request *)((char *)req + cc->dmreq_start); +} + +static struct ablkcipher_request *req_of_dmreq(struct crypt_config *cc, + struct dm_crypt_request *dmreq) +{ + return (struct ablkcipher_request *)((char *)dmreq - cc->dmreq_start); +} + static int crypt_convert_block(struct crypt_config *cc, struct convert_context *ctx, struct ablkcipher_request *req) @@ -345,10 +358,11 @@ static int crypt_convert_block(struct crypt_config *cc, u8 *iv; int r = 0; - dmreq = (struct dm_crypt_request *)((char *)req + cc->dmreq_start); + dmreq = dmreq_of_req(cc, req); iv = (u8 *)ALIGN((unsigned long)(dmreq + 1), crypto_ablkcipher_alignmask(cc->tfm) + 1); + dmreq->ctx = ctx; sg_init_table(&dmreq->sg_in, 1); sg_set_page(&dmreq->sg_in, bv_in->bv_page, 1 << SECTOR_SHIFT, bv_in->bv_offset + ctx->offset_in); @@ -395,8 +409,9 @@ static void crypt_alloc_req(struct crypt_config *cc, cc->req = mempool_alloc(cc->req_pool, GFP_NOIO); ablkcipher_request_set_tfm(cc->req, cc->tfm); ablkcipher_request_set_callback(cc->req, CRYPTO_TFM_REQ_MAY_BACKLOG | - CRYPTO_TFM_REQ_MAY_SLEEP, - kcryptd_async_done, ctx); + CRYPTO_TFM_REQ_MAY_SLEEP, + kcryptd_async_done, + dmreq_of_req(cc, cc->req)); } /* @@ -553,19 +568,22 @@ static void crypt_inc_pending(struct dm_crypt_io *io) static void crypt_dec_pending(struct dm_crypt_io *io) { struct crypt_config *cc = io->target->private; + struct bio *base_bio = io->base_bio; + struct dm_crypt_io *base_io = io->base_io; + int error = io->error; if (!atomic_dec_and_test(&io->pending)) return; - if (likely(!io->base_io)) - bio_endio(io->base_bio, io->error); + mempool_free(io, cc->io_pool); + + if (likely(!base_io)) + bio_endio(base_bio, error); else { - if (io->error && !io->base_io->error) - io->base_io->error = io->error; - crypt_dec_pending(io->base_io); + if (error && !base_io->error) + base_io->error = error; + crypt_dec_pending(base_io); } - - mempool_free(io, cc->io_pool); } /* @@ -821,7 +839,8 @@ static void kcryptd_crypt_read_convert(struct dm_crypt_io *io) static void kcryptd_async_done(struct crypto_async_request *async_req, int error) { - struct convert_context *ctx = async_req->data; + struct dm_crypt_request *dmreq = async_req->data; + struct convert_context *ctx = dmreq->ctx; struct dm_crypt_io *io = container_of(ctx, struct dm_crypt_io, ctx); struct crypt_config *cc = io->target->private; @@ -830,7 +849,7 @@ static void kcryptd_async_done(struct crypto_async_request *async_req, return; } - mempool_free(ablkcipher_request_cast(async_req), cc->req_pool); + mempool_free(req_of_dmreq(cc, dmreq), cc->req_pool); if (!atomic_dec_and_test(&ctx->pending)) return; diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c index a34338567a2..36e2b5e46a6 100644 --- a/drivers/md/dm-io.c +++ b/drivers/md/dm-io.c @@ -292,6 +292,8 @@ static void do_region(int rw, unsigned region, struct dm_io_region *where, (PAGE_SIZE >> SECTOR_SHIFT)); num_bvecs = 1 + min_t(int, bio_get_nr_vecs(where->bdev), num_bvecs); + if (unlikely(num_bvecs > BIO_MAX_PAGES)) + num_bvecs = BIO_MAX_PAGES; bio = bio_alloc_bioset(GFP_NOIO, num_bvecs, io->client->bios); bio->bi_sector = where->sector + (where->count - remaining); bio->bi_bdev = where->bdev; @@ -328,7 +330,7 @@ static void dispatch_io(int rw, unsigned int num_regions, struct dpages old_pages = *dp; if (sync) - rw |= (1 << BIO_RW_SYNC); + rw |= (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_UNPLUG); /* * For multiple regions we need to be careful to rewind diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c index 54d0588fc1f..f01096549a9 100644 --- a/drivers/md/dm-ioctl.c +++ b/drivers/md/dm-ioctl.c @@ -704,7 +704,8 @@ static int dev_rename(struct dm_ioctl *param, size_t param_size) char *new_name = (char *) param + param->data_start; if (new_name < param->data || - invalid_str(new_name, (void *) param + param_size)) { + invalid_str(new_name, (void *) param + param_size) || + strlen(new_name) > DM_NAME_LEN - 1) { DMWARN("Invalid new logical volume name supplied."); return -EINVAL; } @@ -1063,7 +1064,7 @@ static int table_load(struct dm_ioctl *param, size_t param_size) r = populate_table(t, param, param_size); if (r) { - dm_table_put(t); + dm_table_destroy(t); goto out; } @@ -1071,7 +1072,7 @@ static int table_load(struct dm_ioctl *param, size_t param_size) hc = dm_get_mdptr(md); if (!hc || hc->md != md) { DMWARN("device has been removed from the dev hash table."); - dm_table_put(t); + dm_table_destroy(t); up_write(&_hash_lock); r = -ENXIO; goto out; diff --git a/drivers/md/dm-kcopyd.c b/drivers/md/dm-kcopyd.c index 3073618269e..0a225da2127 100644 --- a/drivers/md/dm-kcopyd.c +++ b/drivers/md/dm-kcopyd.c @@ -344,7 +344,7 @@ static int run_io_job(struct kcopyd_job *job) { int r; struct dm_io_request io_req = { - .bi_rw = job->rw | (1 << BIO_RW_SYNC), + .bi_rw = job->rw | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_UNPLUG), .mem.type = DM_IO_PAGE_LIST, .mem.ptr.pl = job->pages, .mem.offset = job->offset, diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 51ba1db4b3e..8d40f27cce8 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -525,9 +525,12 @@ static int __noflush_suspending(struct mapped_device *md) static void dec_pending(struct dm_io *io, int error) { unsigned long flags; + int io_error; + struct bio *bio; + struct mapped_device *md = io->md; /* Push-back supersedes any I/O errors */ - if (error && !(io->error > 0 && __noflush_suspending(io->md))) + if (error && !(io->error > 0 && __noflush_suspending(md))) io->error = error; if (atomic_dec_and_test(&io->io_count)) { @@ -537,24 +540,27 @@ static void dec_pending(struct dm_io *io, int error) * This must be handled before the sleeper on * suspend queue merges the pushback list. */ - spin_lock_irqsave(&io->md->pushback_lock, flags); - if (__noflush_suspending(io->md)) - bio_list_add(&io->md->pushback, io->bio); + spin_lock_irqsave(&md->pushback_lock, flags); + if (__noflush_suspending(md)) + bio_list_add(&md->pushback, io->bio); else /* noflush suspend was interrupted. */ io->error = -EIO; - spin_unlock_irqrestore(&io->md->pushback_lock, flags); + spin_unlock_irqrestore(&md->pushback_lock, flags); } end_io_acct(io); - if (io->error != DM_ENDIO_REQUEUE) { - trace_block_bio_complete(io->md->queue, io->bio); + io_error = io->error; + bio = io->bio; - bio_endio(io->bio, io->error); - } + free_io(md, io); + + if (io_error != DM_ENDIO_REQUEUE) { + trace_block_bio_complete(md->queue, bio); - free_io(io->md, io); + bio_endio(bio, io_error); + } } } @@ -562,6 +568,7 @@ static void clone_endio(struct bio *bio, int error) { int r = 0; struct dm_target_io *tio = bio->bi_private; + struct dm_io *io = tio->io; struct mapped_device *md = tio->io->md; dm_endio_fn endio = tio->ti->type->end_io; @@ -585,15 +592,14 @@ static void clone_endio(struct bio *bio, int error) } } - dec_pending(tio->io, error); - /* * Store md for cleanup instead of tio which is about to get freed. */ bio->bi_private = md->bs; - bio_put(bio); free_tio(md, tio); + bio_put(bio); + dec_pending(io, error); } static sector_t max_io_len(struct mapped_device *md, diff --git a/drivers/md/linear.c b/drivers/md/linear.c index 1e3aea9eecf..09658b21847 100644 --- a/drivers/md/linear.c +++ b/drivers/md/linear.c @@ -25,13 +25,13 @@ static inline dev_info_t *which_dev(mddev_t *mddev, sector_t sector) { dev_info_t *hash; linear_conf_t *conf = mddev_to_conf(mddev); + sector_t idx = sector >> conf->sector_shift; /* * sector_div(a,b) returns the remainer and sets a to a/b */ - sector >>= conf->sector_shift; - (void)sector_div(sector, conf->spacing); - hash = conf->hash_table[sector]; + (void)sector_div(idx, conf->spacing); + hash = conf->hash_table[idx]; while (sector >= hash->num_sectors + hash->start_sector) hash++; diff --git a/drivers/md/md.c b/drivers/md/md.c index 41e2509bf89..a307f87eb90 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -214,12 +214,7 @@ static inline mddev_t *mddev_get(mddev_t *mddev) return mddev; } -static void mddev_delayed_delete(struct work_struct *ws) -{ - mddev_t *mddev = container_of(ws, mddev_t, del_work); - kobject_del(&mddev->kobj); - kobject_put(&mddev->kobj); -} +static void mddev_delayed_delete(struct work_struct *ws); static void mddev_put(mddev_t *mddev) { @@ -474,7 +469,7 @@ void md_super_write(mddev_t *mddev, mdk_rdev_t *rdev, * causes ENOTSUPP, we allocate a spare bio... */ struct bio *bio = bio_alloc(GFP_NOIO, 1); - int rw = (1<<BIO_RW) | (1<<BIO_RW_SYNC); + int rw = (1<<BIO_RW) | (1<<BIO_RW_SYNCIO) | (1<<BIO_RW_UNPLUG); bio->bi_bdev = rdev->bdev; bio->bi_sector = sector; @@ -531,7 +526,7 @@ int sync_page_io(struct block_device *bdev, sector_t sector, int size, struct completion event; int ret; - rw |= (1 << BIO_RW_SYNC); + rw |= (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_UNPLUG); bio->bi_bdev = bdev; bio->bi_sector = sector; @@ -1481,6 +1476,11 @@ static int bind_rdev_to_array(mdk_rdev_t * rdev, mddev_t * mddev) if (find_rdev_nr(mddev, rdev->desc_nr)) return -EBUSY; } + if (mddev->max_disks && rdev->desc_nr >= mddev->max_disks) { + printk(KERN_WARNING "md: %s: array is limited to %d devices\n", + mdname(mddev), mddev->max_disks); + return -EBUSY; + } bdevname(rdev->bdev,b); while ( (s=strchr(b, '/')) != NULL) *s = '!'; @@ -2441,6 +2441,15 @@ static void analyze_sbs(mddev_t * mddev) i = 0; rdev_for_each(rdev, tmp, mddev) { + if (rdev->desc_nr >= mddev->max_disks || + i > mddev->max_disks) { + printk(KERN_WARNING + "md: %s: %s: only %d devices permitted\n", + mdname(mddev), bdevname(rdev->bdev, b), + mddev->max_disks); + kick_rdev_from_array(rdev); + continue; + } if (rdev != freshest) if (super_types[mddev->major_version]. validate_super(mddev, rdev)) { @@ -3528,6 +3537,21 @@ static struct kobj_type md_ktype = { int mdp_major = 0; +static void mddev_delayed_delete(struct work_struct *ws) +{ + mddev_t *mddev = container_of(ws, mddev_t, del_work); + + if (mddev->private == &md_redundancy_group) { + sysfs_remove_group(&mddev->kobj, &md_redundancy_group); + if (mddev->sysfs_action) + sysfs_put(mddev->sysfs_action); + mddev->sysfs_action = NULL; + mddev->private = NULL; + } + kobject_del(&mddev->kobj); + kobject_put(&mddev->kobj); +} + static int md_alloc(dev_t dev, char *name) { static DEFINE_MUTEX(disks_mutex); @@ -4019,13 +4043,9 @@ static int do_md_stop(mddev_t * mddev, int mode, int is_open) mddev->queue->merge_bvec_fn = NULL; mddev->queue->unplug_fn = NULL; mddev->queue->backing_dev_info.congested_fn = NULL; - if (mddev->pers->sync_request) { - sysfs_remove_group(&mddev->kobj, &md_redundancy_group); - if (mddev->sysfs_action) - sysfs_put(mddev->sysfs_action); - mddev->sysfs_action = NULL; - } module_put(mddev->pers->owner); + if (mddev->pers->sync_request) + mddev->private = &md_redundancy_group; mddev->pers = NULL; /* tell userspace to handle 'inactive' */ sysfs_notify_dirent(mddev->sysfs_state); @@ -4614,13 +4634,6 @@ static int hot_add_disk(mddev_t * mddev, dev_t dev) * noticed in interrupt contexts ... */ - if (rdev->desc_nr == mddev->max_disks) { - printk(KERN_WARNING "%s: can not hot-add to full array!\n", - mdname(mddev)); - err = -EBUSY; - goto abort_unbind_export; - } - rdev->raid_disk = -1; md_update_sb(mddev, 1); @@ -4634,9 +4647,6 @@ static int hot_add_disk(mddev_t * mddev, dev_t dev) md_new_event(mddev); return 0; -abort_unbind_export: - unbind_rdev_from_array(rdev); - abort_export: export_rdev(rdev); return err; diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 7b4f5f7155d..e2466425d9c 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1237,8 +1237,9 @@ static void end_sync_write(struct bio *bio, int error) update_head_pos(mirror, r1_bio); if (atomic_dec_and_test(&r1_bio->remaining)) { - md_done_sync(mddev, r1_bio->sectors, uptodate); + sector_t s = r1_bio->sectors; put_buf(r1_bio); + md_done_sync(mddev, s, uptodate); } } @@ -1640,7 +1641,8 @@ static void raid1d(mddev_t *mddev) } bio = r1_bio->bios[r1_bio->read_disk]; - if ((disk=read_balance(conf, r1_bio)) == -1) { + if ((disk=read_balance(conf, r1_bio)) == -1 || + disk == r1_bio->read_disk) { printk(KERN_ALERT "raid1: %s: unrecoverable I/O" " read error for block %llu\n", bdevname(bio->bi_bdev,b), diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 6736d6dff98..7301631abe0 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -1236,6 +1236,7 @@ static void end_sync_read(struct bio *bio, int error) /* for reconstruct, we always reschedule after a read. * for resync, only after all reads */ + rdev_dec_pending(conf->mirrors[d].rdev, conf->mddev); if (test_bit(R10BIO_IsRecover, &r10_bio->state) || atomic_dec_and_test(&r10_bio->remaining)) { /* we have read all the blocks, @@ -1243,7 +1244,6 @@ static void end_sync_read(struct bio *bio, int error) */ reschedule_retry(r10_bio); } - rdev_dec_pending(conf->mirrors[d].rdev, conf->mddev); } static void end_sync_write(struct bio *bio, int error) @@ -1264,11 +1264,13 @@ static void end_sync_write(struct bio *bio, int error) update_head_pos(i, r10_bio); + rdev_dec_pending(conf->mirrors[d].rdev, mddev); while (atomic_dec_and_test(&r10_bio->remaining)) { if (r10_bio->master_bio == NULL) { /* the primary of several recovery bios */ - md_done_sync(mddev, r10_bio->sectors, 1); + sector_t s = r10_bio->sectors; put_buf(r10_bio); + md_done_sync(mddev, s, 1); break; } else { r10bio_t *r10_bio2 = (r10bio_t *)r10_bio->master_bio; @@ -1276,7 +1278,6 @@ static void end_sync_write(struct bio *bio, int error) r10_bio = r10_bio2; } } - rdev_dec_pending(conf->mirrors[d].rdev, mddev); } /* @@ -1749,8 +1750,6 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i if (!go_faster && conf->nr_waiting) msleep_interruptible(1000); - bitmap_cond_end_sync(mddev->bitmap, sector_nr); - /* Again, very different code for resync and recovery. * Both must result in an r10bio with a list of bios that * have bi_end_io, bi_sector, bi_bdev set, @@ -1886,6 +1885,8 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i /* resync. Schedule a read for every block at this virt offset */ int count = 0; + bitmap_cond_end_sync(mddev->bitmap, sector_nr); + if (!bitmap_start_sync(mddev->bitmap, sector_nr, &sync_blocks, mddev->degraded) && !conf->fullsync && !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) { @@ -2010,13 +2011,13 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i /* There is nowhere to write, so all non-sync * drives must be failed, so try the next chunk... */ - { - sector_t sec = max_sector - sector_nr; - sectors_skipped += sec; + if (sector_nr + max_sync < max_sector) + max_sector = sector_nr + max_sync; + + sectors_skipped += (max_sector - sector_nr); chunks_skipped ++; sector_nr = max_sector; goto skipped; - } } static int run(mddev_t *mddev) |