diff options
Diffstat (limited to 'drivers/md')
-rw-r--r-- | drivers/md/dm-bufio.c | 43 | ||||
-rw-r--r-- | drivers/md/dm-cache-metadata.c | 9 | ||||
-rw-r--r-- | drivers/md/dm-cache-target.c | 13 | ||||
-rw-r--r-- | drivers/md/dm-crypt.c | 4 | ||||
-rw-r--r-- | drivers/md/dm-io.c | 22 | ||||
-rw-r--r-- | drivers/md/dm-mpath.c | 5 | ||||
-rw-r--r-- | drivers/md/dm-snap.c | 10 | ||||
-rw-r--r-- | drivers/md/dm-thin-metadata.c | 9 | ||||
-rw-r--r-- | drivers/md/dm-zero.c | 4 | ||||
-rw-r--r-- | drivers/md/dm.c | 15 | ||||
-rw-r--r-- | drivers/md/md.c | 28 | ||||
-rw-r--r-- | drivers/md/raid0.c | 6 | ||||
-rw-r--r-- | drivers/md/raid1.c | 8 | ||||
-rw-r--r-- | drivers/md/raid10.c | 11 |
14 files changed, 104 insertions, 83 deletions
diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index 4e84095833db..ab472c557d18 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -615,16 +615,6 @@ static void write_endio(struct bio *bio, int error) } /* - * This function is called when wait_on_bit is actually waiting. - */ -static int do_io_schedule(void *word) -{ - io_schedule(); - - return 0; -} - -/* * Initiate a write on a dirty buffer, but don't wait for it. * * - If the buffer is not dirty, exit. @@ -640,8 +630,7 @@ static void __write_dirty_buffer(struct dm_buffer *b, return; clear_bit(B_DIRTY, &b->state); - wait_on_bit_lock(&b->state, B_WRITING, - do_io_schedule, TASK_UNINTERRUPTIBLE); + wait_on_bit_lock_io(&b->state, B_WRITING, TASK_UNINTERRUPTIBLE); if (!write_list) submit_io(b, WRITE, b->block, write_endio); @@ -675,9 +664,9 @@ static void __make_buffer_clean(struct dm_buffer *b) if (!b->state) /* fast case */ return; - wait_on_bit(&b->state, B_READING, do_io_schedule, TASK_UNINTERRUPTIBLE); + wait_on_bit_io(&b->state, B_READING, TASK_UNINTERRUPTIBLE); __write_dirty_buffer(b, NULL); - wait_on_bit(&b->state, B_WRITING, do_io_schedule, TASK_UNINTERRUPTIBLE); + wait_on_bit_io(&b->state, B_WRITING, TASK_UNINTERRUPTIBLE); } /* @@ -1030,7 +1019,7 @@ static void *new_read(struct dm_bufio_client *c, sector_t block, if (need_submit) submit_io(b, READ, b->block, read_endio); - wait_on_bit(&b->state, B_READING, do_io_schedule, TASK_UNINTERRUPTIBLE); + wait_on_bit_io(&b->state, B_READING, TASK_UNINTERRUPTIBLE); if (b->read_error) { int error = b->read_error; @@ -1209,15 +1198,13 @@ again: dropped_lock = 1; b->hold_count++; dm_bufio_unlock(c); - wait_on_bit(&b->state, B_WRITING, - do_io_schedule, - TASK_UNINTERRUPTIBLE); + wait_on_bit_io(&b->state, B_WRITING, + TASK_UNINTERRUPTIBLE); dm_bufio_lock(c); b->hold_count--; } else - wait_on_bit(&b->state, B_WRITING, - do_io_schedule, - TASK_UNINTERRUPTIBLE); + wait_on_bit_io(&b->state, B_WRITING, + TASK_UNINTERRUPTIBLE); } if (!test_bit(B_DIRTY, &b->state) && @@ -1321,15 +1308,15 @@ retry: __write_dirty_buffer(b, NULL); if (b->hold_count == 1) { - wait_on_bit(&b->state, B_WRITING, - do_io_schedule, TASK_UNINTERRUPTIBLE); + wait_on_bit_io(&b->state, B_WRITING, + TASK_UNINTERRUPTIBLE); set_bit(B_DIRTY, &b->state); __unlink_buffer(b); __link_buffer(b, new_block, LIST_DIRTY); } else { sector_t old_block; - wait_on_bit_lock(&b->state, B_WRITING, - do_io_schedule, TASK_UNINTERRUPTIBLE); + wait_on_bit_lock_io(&b->state, B_WRITING, + TASK_UNINTERRUPTIBLE); /* * Relink buffer to "new_block" so that write_callback * sees "new_block" as a block number. @@ -1341,8 +1328,8 @@ retry: __unlink_buffer(b); __link_buffer(b, new_block, b->list_mode); submit_io(b, WRITE, new_block, write_endio); - wait_on_bit(&b->state, B_WRITING, - do_io_schedule, TASK_UNINTERRUPTIBLE); + wait_on_bit_io(&b->state, B_WRITING, + TASK_UNINTERRUPTIBLE); __unlink_buffer(b); __link_buffer(b, old_block, b->list_mode); } @@ -1541,7 +1528,7 @@ struct dm_bufio_client *dm_bufio_client_create(struct block_device *bdev, unsign BUG_ON(block_size < 1 << SECTOR_SHIFT || (block_size & (block_size - 1))); - c = kmalloc(sizeof(*c), GFP_KERNEL); + c = kzalloc(sizeof(*c), GFP_KERNEL); if (!c) { r = -ENOMEM; goto bad_client; diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c index 4ead4ba60656..d2899e7eb3aa 100644 --- a/drivers/md/dm-cache-metadata.c +++ b/drivers/md/dm-cache-metadata.c @@ -425,6 +425,15 @@ static int __open_metadata(struct dm_cache_metadata *cmd) disk_super = dm_block_data(sblock); + /* Verify the data block size hasn't changed */ + if (le32_to_cpu(disk_super->data_block_size) != cmd->data_block_size) { + DMERR("changing the data block size (from %u to %llu) is not supported", + le32_to_cpu(disk_super->data_block_size), + (unsigned long long)cmd->data_block_size); + r = -EINVAL; + goto bad; + } + r = __check_incompat_features(disk_super, cmd); if (r < 0) goto bad; diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index 5f054c44b485..2c63326638b6 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -231,7 +231,7 @@ struct cache { /* * cache_size entries, dirty if set */ - dm_cblock_t nr_dirty; + atomic_t nr_dirty; unsigned long *dirty_bitset; /* @@ -492,7 +492,7 @@ static bool is_dirty(struct cache *cache, dm_cblock_t b) static void set_dirty(struct cache *cache, dm_oblock_t oblock, dm_cblock_t cblock) { if (!test_and_set_bit(from_cblock(cblock), cache->dirty_bitset)) { - cache->nr_dirty = to_cblock(from_cblock(cache->nr_dirty) + 1); + atomic_inc(&cache->nr_dirty); policy_set_dirty(cache->policy, oblock); } } @@ -501,8 +501,7 @@ static void clear_dirty(struct cache *cache, dm_oblock_t oblock, dm_cblock_t cbl { if (test_and_clear_bit(from_cblock(cblock), cache->dirty_bitset)) { policy_clear_dirty(cache->policy, oblock); - cache->nr_dirty = to_cblock(from_cblock(cache->nr_dirty) - 1); - if (!from_cblock(cache->nr_dirty)) + if (atomic_dec_return(&cache->nr_dirty) == 0) dm_table_event(cache->ti->table); } } @@ -2269,7 +2268,7 @@ static int cache_create(struct cache_args *ca, struct cache **result) atomic_set(&cache->quiescing_ack, 0); r = -ENOMEM; - cache->nr_dirty = 0; + atomic_set(&cache->nr_dirty, 0); cache->dirty_bitset = alloc_bitset(from_cblock(cache->cache_size)); if (!cache->dirty_bitset) { *error = "could not allocate dirty bitset"; @@ -2808,7 +2807,7 @@ static void cache_status(struct dm_target *ti, status_type_t type, residency = policy_residency(cache->policy); - DMEMIT("%u %llu/%llu %u %llu/%llu %u %u %u %u %u %u %llu ", + DMEMIT("%u %llu/%llu %u %llu/%llu %u %u %u %u %u %u %lu ", (unsigned)(DM_CACHE_METADATA_BLOCK_SIZE >> SECTOR_SHIFT), (unsigned long long)(nr_blocks_metadata - nr_free_blocks_metadata), (unsigned long long)nr_blocks_metadata, @@ -2821,7 +2820,7 @@ static void cache_status(struct dm_target *ti, status_type_t type, (unsigned) atomic_read(&cache->stats.write_miss), (unsigned) atomic_read(&cache->stats.demotion), (unsigned) atomic_read(&cache->stats.promotion), - (unsigned long long) from_cblock(cache->nr_dirty)); + (unsigned long) atomic_read(&cache->nr_dirty)); if (writethrough_mode(&cache->features)) DMEMIT("1 writethrough "); diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 53b213226c01..4cba2d808afb 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2003 Christophe Saout <christophe@saout.de> + * Copyright (C) 2003 Jana Saout <jana@saout.de> * Copyright (C) 2004 Clemens Fruhwirth <clemens@endorphin.org> * Copyright (C) 2006-2009 Red Hat, Inc. All rights reserved. * Copyright (C) 2013 Milan Broz <gmazyland@gmail.com> @@ -1996,6 +1996,6 @@ static void __exit dm_crypt_exit(void) module_init(dm_crypt_init); module_exit(dm_crypt_exit); -MODULE_AUTHOR("Christophe Saout <christophe@saout.de>"); +MODULE_AUTHOR("Jana Saout <jana@saout.de>"); MODULE_DESCRIPTION(DM_NAME " target for transparent encryption / decryption"); MODULE_LICENSE("GPL"); diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c index 3842ac738f98..db404a0f7e2c 100644 --- a/drivers/md/dm-io.c +++ b/drivers/md/dm-io.c @@ -10,6 +10,7 @@ #include <linux/device-mapper.h> #include <linux/bio.h> +#include <linux/completion.h> #include <linux/mempool.h> #include <linux/module.h> #include <linux/sched.h> @@ -32,7 +33,7 @@ struct dm_io_client { struct io { unsigned long error_bits; atomic_t count; - struct task_struct *sleeper; + struct completion *wait; struct dm_io_client *client; io_notify_fn callback; void *context; @@ -121,8 +122,8 @@ static void dec_count(struct io *io, unsigned int region, int error) invalidate_kernel_vmap_range(io->vma_invalidate_address, io->vma_invalidate_size); - if (io->sleeper) - wake_up_process(io->sleeper); + if (io->wait) + complete(io->wait); else { unsigned long r = io->error_bits; @@ -387,6 +388,7 @@ static int sync_io(struct dm_io_client *client, unsigned int num_regions, */ volatile char io_[sizeof(struct io) + __alignof__(struct io) - 1]; struct io *io = (struct io *)PTR_ALIGN(&io_, __alignof__(struct io)); + DECLARE_COMPLETION_ONSTACK(wait); if (num_regions > 1 && (rw & RW_MASK) != WRITE) { WARN_ON(1); @@ -395,7 +397,7 @@ static int sync_io(struct dm_io_client *client, unsigned int num_regions, io->error_bits = 0; atomic_set(&io->count, 1); /* see dispatch_io() */ - io->sleeper = current; + io->wait = &wait; io->client = client; io->vma_invalidate_address = dp->vma_invalidate_address; @@ -403,15 +405,7 @@ static int sync_io(struct dm_io_client *client, unsigned int num_regions, dispatch_io(rw, num_regions, where, dp, io, 1); - while (1) { - set_current_state(TASK_UNINTERRUPTIBLE); - - if (!atomic_read(&io->count)) - break; - - io_schedule(); - } - set_current_state(TASK_RUNNING); + wait_for_completion_io(&wait); if (error_bits) *error_bits = io->error_bits; @@ -434,7 +428,7 @@ static int async_io(struct dm_io_client *client, unsigned int num_regions, io = mempool_alloc(client->pool, GFP_NOIO); io->error_bits = 0; atomic_set(&io->count, 1); /* see dispatch_io() */ - io->sleeper = NULL; + io->wait = NULL; io->client = client; io->callback = fn; io->context = context; diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index 3f6fd9d33ba3..f4167b013d99 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -1611,8 +1611,9 @@ static int multipath_busy(struct dm_target *ti) spin_lock_irqsave(&m->lock, flags); - /* pg_init in progress, requeue until done */ - if (!pg_ready(m)) { + /* pg_init in progress or no paths available */ + if (m->pg_init_in_progress || + (!m->nr_valid_paths && m->queue_if_no_path)) { busy = 1; goto out; } diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c index 5bd2290cfb1e..864b03f47727 100644 --- a/drivers/md/dm-snap.c +++ b/drivers/md/dm-snap.c @@ -1032,21 +1032,13 @@ static void start_merge(struct dm_snapshot *s) snapshot_merge_next_chunks(s); } -static int wait_schedule(void *ptr) -{ - schedule(); - - return 0; -} - /* * Stop the merging process and wait until it finishes. */ static void stop_merge(struct dm_snapshot *s) { set_bit(SHUTDOWN_MERGE, &s->state_bits); - wait_on_bit(&s->state_bits, RUNNING_MERGE, wait_schedule, - TASK_UNINTERRUPTIBLE); + wait_on_bit(&s->state_bits, RUNNING_MERGE, TASK_UNINTERRUPTIBLE); clear_bit(SHUTDOWN_MERGE, &s->state_bits); } diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c index b086a945edcb..e9d33ad59df5 100644 --- a/drivers/md/dm-thin-metadata.c +++ b/drivers/md/dm-thin-metadata.c @@ -613,6 +613,15 @@ static int __open_metadata(struct dm_pool_metadata *pmd) disk_super = dm_block_data(sblock); + /* Verify the data block size hasn't changed */ + if (le32_to_cpu(disk_super->data_block_size) != pmd->data_block_size) { + DMERR("changing the data block size (from %u to %llu) is not supported", + le32_to_cpu(disk_super->data_block_size), + (unsigned long long)pmd->data_block_size); + r = -EINVAL; + goto bad_unlock_sblock; + } + r = __check_incompat_features(disk_super, pmd); if (r < 0) goto bad_unlock_sblock; diff --git a/drivers/md/dm-zero.c b/drivers/md/dm-zero.c index c99003e0d47a..b9a64bbce304 100644 --- a/drivers/md/dm-zero.c +++ b/drivers/md/dm-zero.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2003 Christophe Saout <christophe@saout.de> + * Copyright (C) 2003 Jana Saout <jana@saout.de> * * This file is released under the GPL. */ @@ -79,6 +79,6 @@ static void __exit dm_zero_exit(void) module_init(dm_zero_init) module_exit(dm_zero_exit) -MODULE_AUTHOR("Christophe Saout <christophe@saout.de>"); +MODULE_AUTHOR("Jana Saout <jana@saout.de>"); MODULE_DESCRIPTION(DM_NAME " dummy target returning zeros"); MODULE_LICENSE("GPL"); diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 437d99045ef2..32b958dbc499 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -54,6 +54,8 @@ static void do_deferred_remove(struct work_struct *w); static DECLARE_WORK(deferred_remove_work, do_deferred_remove); +static struct workqueue_struct *deferred_remove_workqueue; + /* * For bio-based dm. * One of these is allocated per bio. @@ -276,16 +278,24 @@ static int __init local_init(void) if (r) goto out_free_rq_tio_cache; + deferred_remove_workqueue = alloc_workqueue("kdmremove", WQ_UNBOUND, 1); + if (!deferred_remove_workqueue) { + r = -ENOMEM; + goto out_uevent_exit; + } + _major = major; r = register_blkdev(_major, _name); if (r < 0) - goto out_uevent_exit; + goto out_free_workqueue; if (!_major) _major = r; return 0; +out_free_workqueue: + destroy_workqueue(deferred_remove_workqueue); out_uevent_exit: dm_uevent_exit(); out_free_rq_tio_cache: @@ -299,6 +309,7 @@ out_free_io_cache: static void local_exit(void) { flush_scheduled_work(); + destroy_workqueue(deferred_remove_workqueue); kmem_cache_destroy(_rq_tio_cache); kmem_cache_destroy(_io_cache); @@ -407,7 +418,7 @@ static void dm_blk_close(struct gendisk *disk, fmode_t mode) if (atomic_dec_and_test(&md->open_count) && (test_bit(DMF_DEFERRED_REMOVE, &md->flags))) - schedule_work(&deferred_remove_work); + queue_work(deferred_remove_workqueue, &deferred_remove_work); dm_put(md); diff --git a/drivers/md/md.c b/drivers/md/md.c index 34846856dbc6..1294238610df 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -5599,7 +5599,7 @@ static int get_array_info(struct mddev * mddev, void __user * arg) if (mddev->in_sync) info.state = (1<<MD_SB_CLEAN); if (mddev->bitmap && mddev->bitmap_info.offset) - info.state = (1<<MD_SB_BITMAP_PRESENT); + info.state |= (1<<MD_SB_BITMAP_PRESENT); info.active_disks = insync; info.working_disks = working; info.failed_disks = failed; @@ -5961,7 +5961,7 @@ static int set_bitmap_file(struct mddev *mddev, int fd) int err = 0; if (mddev->pers) { - if (!mddev->pers->quiesce) + if (!mddev->pers->quiesce || !mddev->thread) return -EBUSY; if (mddev->recovery || mddev->sync_thread) return -EBUSY; @@ -6263,7 +6263,7 @@ static int update_array_info(struct mddev *mddev, mdu_array_info_t *info) rv = update_raid_disks(mddev, info->raid_disks); if ((state ^ info->state) & (1<<MD_SB_BITMAP_PRESENT)) { - if (mddev->pers->quiesce == NULL) + if (mddev->pers->quiesce == NULL || mddev->thread == NULL) return -EINVAL; if (mddev->recovery || mddev->sync_thread) return -EBUSY; @@ -7376,7 +7376,7 @@ void md_do_sync(struct md_thread *thread) struct mddev *mddev2; unsigned int currspeed = 0, window; - sector_t max_sectors,j, io_sectors; + sector_t max_sectors,j, io_sectors, recovery_done; unsigned long mark[SYNC_MARKS]; unsigned long update_time; sector_t mark_cnt[SYNC_MARKS]; @@ -7501,6 +7501,19 @@ void md_do_sync(struct md_thread *thread) rdev->recovery_offset < j) j = rdev->recovery_offset; rcu_read_unlock(); + + /* If there is a bitmap, we need to make sure all + * writes that started before we added a spare + * complete before we start doing a recovery. + * Otherwise the write might complete and (via + * bitmap_endwrite) set a bit in the bitmap after the + * recovery has checked that bit and skipped that + * region. + */ + if (mddev->bitmap) { + mddev->pers->quiesce(mddev, 1); + mddev->pers->quiesce(mddev, 0); + } } printk(KERN_INFO "md: %s of RAID array %s\n", desc, mdname(mddev)); @@ -7639,7 +7652,8 @@ void md_do_sync(struct md_thread *thread) */ cond_resched(); - currspeed = ((unsigned long)(io_sectors-mddev->resync_mark_cnt))/2 + recovery_done = io_sectors - atomic_read(&mddev->recovery_active); + currspeed = ((unsigned long)(recovery_done - mddev->resync_mark_cnt))/2 /((jiffies-mddev->resync_mark)/HZ +1) +1; if (currspeed > speed_min(mddev)) { @@ -8579,7 +8593,7 @@ static int __init md_init(void) goto err_mdp; mdp_major = ret; - blk_register_region(MKDEV(MD_MAJOR, 0), 1UL<<MINORBITS, THIS_MODULE, + blk_register_region(MKDEV(MD_MAJOR, 0), 512, THIS_MODULE, md_probe, NULL, NULL); blk_register_region(MKDEV(mdp_major, 0), 1UL<<MINORBITS, THIS_MODULE, md_probe, NULL, NULL); @@ -8674,7 +8688,7 @@ static __exit void md_exit(void) struct list_head *tmp; int delay = 1; - blk_unregister_region(MKDEV(MD_MAJOR,0), 1U << MINORBITS); + blk_unregister_region(MKDEV(MD_MAJOR,0), 512); blk_unregister_region(MKDEV(mdp_major,0), 1U << MINORBITS); unregister_blkdev(MD_MAJOR,"md"); diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index 407a99e46f69..cf91f5910c7c 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -685,6 +685,12 @@ static void *raid0_takeover(struct mddev *mddev) * raid10 - assuming we have all necessary active disks * raid1 - with (N -1) mirror drives faulty */ + + if (mddev->bitmap) { + printk(KERN_ERR "md/raid0: %s: cannot takeover array with bitmap\n", + mdname(mddev)); + return ERR_PTR(-EBUSY); + } if (mddev->level == 4) return raid0_takeover_raid45(mddev); diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 56e24c072b62..d7690f86fdb9 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1501,12 +1501,12 @@ static void error(struct mddev *mddev, struct md_rdev *rdev) mddev->degraded++; set_bit(Faulty, &rdev->flags); spin_unlock_irqrestore(&conf->device_lock, flags); - /* - * if recovery is running, make sure it aborts. - */ - set_bit(MD_RECOVERY_INTR, &mddev->recovery); } else set_bit(Faulty, &rdev->flags); + /* + * if recovery is running, make sure it aborts. + */ + set_bit(MD_RECOVERY_INTR, &mddev->recovery); set_bit(MD_CHANGE_DEVS, &mddev->flags); printk(KERN_ALERT "md/raid1:%s: Disk failure on %s, disabling device.\n" diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index cb882aae9e20..b08c18871323 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -1684,13 +1684,12 @@ static void error(struct mddev *mddev, struct md_rdev *rdev) spin_unlock_irqrestore(&conf->device_lock, flags); return; } - if (test_and_clear_bit(In_sync, &rdev->flags)) { + if (test_and_clear_bit(In_sync, &rdev->flags)) mddev->degraded++; - /* - * if recovery is running, make sure it aborts. - */ - set_bit(MD_RECOVERY_INTR, &mddev->recovery); - } + /* + * If recovery is running, make sure it aborts. + */ + set_bit(MD_RECOVERY_INTR, &mddev->recovery); set_bit(Blocked, &rdev->flags); set_bit(Faulty, &rdev->flags); set_bit(MD_CHANGE_DEVS, &mddev->flags); |