aboutsummaryrefslogtreecommitdiff
path: root/drivers/md
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/md')
-rw-r--r--drivers/md/bcache/btree.c5
-rw-r--r--drivers/md/bcache/super.c62
-rw-r--r--drivers/md/bcache/writeback.c37
-rw-r--r--drivers/md/bcache/writeback.h3
-rw-r--r--drivers/md/bitmap.c2
-rw-r--r--drivers/md/dm-cache-policy-cleaner.c2
-rw-r--r--drivers/md/dm-exception-store.h2
-rw-r--r--drivers/md/dm-raid.c3
-rw-r--r--drivers/md/dm-snap-persistent.c5
-rw-r--r--drivers/md/dm-snap-transient.c4
-rw-r--r--drivers/md/dm-snap.c20
-rw-r--r--drivers/md/dm-stats.c2
-rw-r--r--drivers/md/dm-thin-metadata.c4
-rw-r--r--drivers/md/dm-thin.c6
-rw-r--r--drivers/md/md.c12
-rw-r--r--drivers/md/multipath.c4
-rw-r--r--drivers/md/persistent-data/dm-btree-internal.h6
-rw-r--r--drivers/md/persistent-data/dm-btree-remove.c35
-rw-r--r--drivers/md/persistent-data/dm-btree-spine.c37
-rw-r--r--drivers/md/persistent-data/dm-btree.c11
-rw-r--r--drivers/md/persistent-data/dm-space-map-metadata.c50
-rw-r--r--drivers/md/raid1.c14
-rw-r--r--drivers/md/raid10.c7
-rw-r--r--drivers/md/raid5.c10
24 files changed, 231 insertions, 112 deletions
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index 00cde40db572..43829d9493f7 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -1741,6 +1741,7 @@ static void bch_btree_gc(struct cache_set *c)
do {
ret = btree_root(gc_root, c, &op, &writes, &stats);
closure_sync(&writes);
+ cond_resched();
if (ret && ret != -EAGAIN)
pr_warn("gc failed!");
@@ -2162,8 +2163,10 @@ int bch_btree_insert_check_key(struct btree *b, struct btree_op *op,
rw_lock(true, b, b->level);
if (b->key.ptr[0] != btree_ptr ||
- b->seq != seq + 1)
+ b->seq != seq + 1) {
+ op->lock = b->level;
goto out;
+ }
}
SET_KEY_PTRS(check_key, 1);
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 4dd2bb7167f0..2a102834c2ee 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -708,6 +708,8 @@ static void bcache_device_link(struct bcache_device *d, struct cache_set *c,
WARN(sysfs_create_link(&d->kobj, &c->kobj, "cache") ||
sysfs_create_link(&c->kobj, &d->kobj, d->name),
"Couldn't create device <-> cache set symlinks");
+
+ clear_bit(BCACHE_DEV_UNLINK_DONE, &d->flags);
}
static void bcache_device_detach(struct bcache_device *d)
@@ -878,8 +880,11 @@ void bch_cached_dev_run(struct cached_dev *dc)
buf[SB_LABEL_SIZE] = '\0';
env[2] = kasprintf(GFP_KERNEL, "CACHED_LABEL=%s", buf);
- if (atomic_xchg(&dc->running, 1))
+ if (atomic_xchg(&dc->running, 1)) {
+ kfree(env[1]);
+ kfree(env[2]);
return;
+ }
if (!d->c &&
BDEV_STATE(&dc->sb) != BDEV_STATE_NONE) {
@@ -1041,8 +1046,12 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c)
*/
atomic_set(&dc->count, 1);
- if (bch_cached_dev_writeback_start(dc))
+ /* Block writeback thread, but spawn it */
+ down_write(&dc->writeback_lock);
+ if (bch_cached_dev_writeback_start(dc)) {
+ up_write(&dc->writeback_lock);
return -ENOMEM;
+ }
if (BDEV_STATE(&dc->sb) == BDEV_STATE_DIRTY) {
bch_sectors_dirty_init(dc);
@@ -1054,6 +1063,9 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c)
bch_cached_dev_run(dc);
bcache_device_link(&dc->disk, c, "bdev");
+ /* Allow the writeback thread to proceed */
+ up_write(&dc->writeback_lock);
+
pr_info("Caching %s as %s on set %pU",
bdevname(dc->bdev, buf), dc->disk.disk->disk_name,
dc->disk.c->sb.set_uuid);
@@ -1392,6 +1404,9 @@ static void cache_set_flush(struct closure *cl)
struct btree *b;
unsigned i;
+ if (!c)
+ closure_return(cl);
+
bch_cache_accounting_destroy(&c->accounting);
kobject_put(&c->internal);
@@ -1857,11 +1872,12 @@ static int cache_alloc(struct cache_sb *sb, struct cache *ca)
return 0;
}
-static void register_cache(struct cache_sb *sb, struct page *sb_page,
+static int register_cache(struct cache_sb *sb, struct page *sb_page,
struct block_device *bdev, struct cache *ca)
{
char name[BDEVNAME_SIZE];
- const char *err = "cannot allocate memory";
+ const char *err = NULL;
+ int ret = 0;
memcpy(&ca->sb, sb, sizeof(struct cache_sb));
ca->bdev = bdev;
@@ -1876,27 +1892,35 @@ static void register_cache(struct cache_sb *sb, struct page *sb_page,
if (blk_queue_discard(bdev_get_queue(ca->bdev)))
ca->discard = CACHE_DISCARD(&ca->sb);
- if (cache_alloc(sb, ca) != 0)
+ ret = cache_alloc(sb, ca);
+ if (ret != 0)
goto err;
- err = "error creating kobject";
- if (kobject_add(&ca->kobj, &part_to_dev(bdev->bd_part)->kobj, "bcache"))
- goto err;
+ if (kobject_add(&ca->kobj, &part_to_dev(bdev->bd_part)->kobj, "bcache")) {
+ err = "error calling kobject_add";
+ ret = -ENOMEM;
+ goto out;
+ }
mutex_lock(&bch_register_lock);
err = register_cache_set(ca);
mutex_unlock(&bch_register_lock);
- if (err)
- goto err;
+ if (err) {
+ ret = -ENODEV;
+ goto out;
+ }
pr_info("registered cache device %s", bdevname(bdev, name));
+
out:
kobject_put(&ca->kobj);
- return;
+
err:
- pr_notice("error opening %s: %s", bdevname(bdev, name), err);
- goto out;
+ if (err)
+ pr_notice("error opening %s: %s", bdevname(bdev, name), err);
+
+ return ret;
}
/* Global interfaces/init */
@@ -1967,6 +1991,8 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
else
err = "device busy";
mutex_unlock(&bch_register_lock);
+ if (attr == &ksysfs_register_quiet)
+ goto out;
}
goto err;
}
@@ -1992,7 +2018,8 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
if (!ca)
goto err_close;
- register_cache(sb, sb_page, bdev, ca);
+ if (register_cache(sb, sb_page, bdev, ca) != 0)
+ goto err_close;
}
out:
if (sb_page)
@@ -2005,8 +2032,7 @@ out:
err_close:
blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
err:
- if (attr != &ksysfs_register_quiet)
- pr_info("error opening %s: %s", path, err);
+ pr_info("error opening %s: %s", path, err);
ret = -EINVAL;
goto out;
}
@@ -2100,8 +2126,10 @@ static int __init bcache_init(void)
closure_debug_init();
bcache_major = register_blkdev(0, "bcache");
- if (bcache_major < 0)
+ if (bcache_major < 0) {
+ unregister_reboot_notifier(&reboot);
return bcache_major;
+ }
if (!(bcache_wq = create_workqueue("bcache")) ||
!(bcache_kobj = kobject_create_and_add("bcache", fs_kobj)) ||
diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index f1986bcd1bf0..540256a0df4f 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -323,6 +323,10 @@ void bcache_dev_sectors_dirty_add(struct cache_set *c, unsigned inode,
static bool dirty_pred(struct keybuf *buf, struct bkey *k)
{
+ struct cached_dev *dc = container_of(buf, struct cached_dev, writeback_keys);
+
+ BUG_ON(KEY_INODE(k) != dc->disk.id);
+
return KEY_DIRTY(k);
}
@@ -372,11 +376,24 @@ next:
}
}
+/*
+ * Returns true if we scanned the entire disk
+ */
static bool refill_dirty(struct cached_dev *dc)
{
struct keybuf *buf = &dc->writeback_keys;
+ struct bkey start = KEY(dc->disk.id, 0, 0);
struct bkey end = KEY(dc->disk.id, MAX_KEY_OFFSET, 0);
- bool searched_from_start = false;
+ struct bkey start_pos;
+
+ /*
+ * make sure keybuf pos is inside the range for this disk - at bringup
+ * we might not be attached yet so this disk's inode nr isn't
+ * initialized then
+ */
+ if (bkey_cmp(&buf->last_scanned, &start) < 0 ||
+ bkey_cmp(&buf->last_scanned, &end) > 0)
+ buf->last_scanned = start;
if (dc->partial_stripes_expensive) {
refill_full_stripes(dc);
@@ -384,14 +401,20 @@ static bool refill_dirty(struct cached_dev *dc)
return false;
}
- if (bkey_cmp(&buf->last_scanned, &end) >= 0) {
- buf->last_scanned = KEY(dc->disk.id, 0, 0);
- searched_from_start = true;
- }
-
+ start_pos = buf->last_scanned;
bch_refill_keybuf(dc->disk.c, buf, &end, dirty_pred);
- return bkey_cmp(&buf->last_scanned, &end) >= 0 && searched_from_start;
+ if (bkey_cmp(&buf->last_scanned, &end) < 0)
+ return false;
+
+ /*
+ * If we get to the end start scanning again from the beginning, and
+ * only scan up to where we initially started scanning from:
+ */
+ buf->last_scanned = start;
+ bch_refill_keybuf(dc->disk.c, buf, &start_pos, dirty_pred);
+
+ return bkey_cmp(&buf->last_scanned, &start_pos) >= 0;
}
static int bch_writeback_thread(void *arg)
diff --git a/drivers/md/bcache/writeback.h b/drivers/md/bcache/writeback.h
index 0a9dab187b79..073a042aed24 100644
--- a/drivers/md/bcache/writeback.h
+++ b/drivers/md/bcache/writeback.h
@@ -63,7 +63,8 @@ static inline bool should_writeback(struct cached_dev *dc, struct bio *bio,
static inline void bch_writeback_queue(struct cached_dev *dc)
{
- wake_up_process(dc->writeback_thread);
+ if (!IS_ERR_OR_NULL(dc->writeback_thread))
+ wake_up_process(dc->writeback_thread);
}
static inline void bch_writeback_add(struct cached_dev *dc)
diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index da3604e73e8a..cced062cab4b 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -564,6 +564,8 @@ static int bitmap_read_sb(struct bitmap *bitmap)
if (err)
return err;
+ err = -EINVAL;
+
sb = kmap_atomic(sb_page);
chunksize = le32_to_cpu(sb->chunksize);
diff --git a/drivers/md/dm-cache-policy-cleaner.c b/drivers/md/dm-cache-policy-cleaner.c
index b04d1f904d07..2eca9084defe 100644
--- a/drivers/md/dm-cache-policy-cleaner.c
+++ b/drivers/md/dm-cache-policy-cleaner.c
@@ -434,7 +434,7 @@ static struct dm_cache_policy *wb_create(dm_cblock_t cache_size,
static struct dm_cache_policy_type wb_policy_type = {
.name = "cleaner",
.version = {1, 0, 0},
- .hint_size = 0,
+ .hint_size = 4,
.owner = THIS_MODULE,
.create = wb_create
};
diff --git a/drivers/md/dm-exception-store.h b/drivers/md/dm-exception-store.h
index 0b2536247cf5..84e27708ad97 100644
--- a/drivers/md/dm-exception-store.h
+++ b/drivers/md/dm-exception-store.h
@@ -70,7 +70,7 @@ 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-raid.c b/drivers/md/dm-raid.c
index 07c0fa0fa284..e5d97da5f41e 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -327,8 +327,7 @@ static int validate_region_size(struct raid_set *rs, unsigned long region_size)
*/
if (min_region_size > (1 << 13)) {
/* If not a power of 2, make it the next power of 2 */
- if (min_region_size & (min_region_size - 1))
- region_size = 1 << fls(region_size);
+ region_size = roundup_pow_of_two(min_region_size);
DMINFO("Choosing default region size of %lu sectors",
region_size);
} else {
diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c
index d6e88178d22c..d3272acc0f0e 100644
--- a/drivers/md/dm-snap-persistent.c
+++ b/drivers/md/dm-snap-persistent.c
@@ -700,7 +700,7 @@ 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)
{
@@ -709,6 +709,9 @@ 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 1ce9a2586e41..31439d53cf7e 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 33de9f7a7180..b91b39caf7a9 100644
--- a/drivers/md/dm-snap.c
+++ b/drivers/md/dm-snap.c
@@ -1428,8 +1428,9 @@ 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;
@@ -1500,24 +1501,13 @@ 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);
}
/*
diff --git a/drivers/md/dm-stats.c b/drivers/md/dm-stats.c
index 87f86c77b094..6f2a4ce413f7 100644
--- a/drivers/md/dm-stats.c
+++ b/drivers/md/dm-stats.c
@@ -795,6 +795,8 @@ static int message_stats_create(struct mapped_device *md,
return -EINVAL;
if (sscanf(argv[2], "/%u%c", &divisor, &dummy) == 1) {
+ if (!divisor)
+ return -EINVAL;
step = end - start;
if (do_div(step, divisor))
step++;
diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c
index e9d33ad59df5..3412b86e79fd 100644
--- a/drivers/md/dm-thin-metadata.c
+++ b/drivers/md/dm-thin-metadata.c
@@ -1295,8 +1295,8 @@ static int __release_metadata_snap(struct dm_pool_metadata *pmd)
return r;
disk_super = dm_block_data(copy);
- dm_sm_dec_block(pmd->metadata_sm, le64_to_cpu(disk_super->data_mapping_root));
- dm_sm_dec_block(pmd->metadata_sm, le64_to_cpu(disk_super->device_details_root));
+ dm_btree_del(&pmd->info, le64_to_cpu(disk_super->data_mapping_root));
+ dm_btree_del(&pmd->details_info, le64_to_cpu(disk_super->device_details_root));
dm_sm_dec_block(pmd->metadata_sm, held_root);
return dm_tm_unlock(pmd->tm, copy);
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index 0801e35b9940..9dfe2bb713c5 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -2596,7 +2596,7 @@ static int pool_ctr(struct dm_target *ti, unsigned argc, char **argv)
metadata_low_callback,
pool);
if (r)
- goto out_free_pt;
+ goto out_flags_changed;
pt->callbacks.congested_fn = pool_is_congested;
dm_table_add_target_callbacks(ti->table, &pt->callbacks);
@@ -2790,8 +2790,8 @@ 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);
}
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 9233c71138f1..3d2cc7453ec1 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -282,6 +282,8 @@ static void md_make_request(struct request_queue *q, struct bio *bio)
* go away inside make_request
*/
sectors = bio_sectors(bio);
+ /* bio could be mergeable after passing to underlayer */
+ bio->bi_rw &= ~REQ_NOMERGE;
mddev->pers->make_request(mddev, bio);
cpu = part_stat_lock();
@@ -5073,6 +5075,8 @@ EXPORT_SYMBOL_GPL(md_stop_writes);
static void __md_stop(struct mddev *mddev)
{
mddev->ready = 0;
+ /* Ensure ->event_work is done */
+ flush_workqueue(md_misc_wq);
mddev->pers->stop(mddev);
if (mddev->pers->sync_request && mddev->to_remove == NULL)
mddev->to_remove = &md_redundancy_group;
@@ -5432,8 +5436,7 @@ static int get_bitmap_file(struct mddev *mddev, void __user * arg)
char *ptr, *buf = NULL;
int err = -ENOMEM;
- file = kmalloc(sizeof(*file), GFP_NOIO);
-
+ file = kzalloc(sizeof(*file), GFP_NOIO);
if (!file)
goto out;
@@ -6031,7 +6034,7 @@ static int update_array_info(struct mddev *mddev, mdu_array_info_t *info)
mddev->ctime != info->ctime ||
mddev->level != info->level ||
/* mddev->layout != info->layout || */
- !mddev->persistent != info->not_persistent||
+ mddev->persistent != !info->not_persistent ||
mddev->chunk_sectors != info->chunk_size >> 9 ||
/* ignore bottom 8 bits of state, and allow SB_BITMAP_PRESENT to change */
((state^info->state) & 0xfffffe00)
@@ -7559,8 +7562,7 @@ static int remove_and_add_spares(struct mddev *mddev,
!test_bit(Bitmap_sync, &rdev->flags)))
continue;
- if (rdev->saved_raid_disk < 0)
- rdev->recovery_offset = 0;
+ rdev->recovery_offset = 0;
if (mddev->pers->
hot_add_disk(mddev, rdev) == 0) {
if (sysfs_link_rdev(mddev, rdev))
diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c
index 399272f9c042..2df218da1791 100644
--- a/drivers/md/multipath.c
+++ b/drivers/md/multipath.c
@@ -129,7 +129,9 @@ static void multipath_make_request(struct mddev *mddev, struct bio * bio)
}
multipath = conf->multipaths + mp_bh->path;
- mp_bh->bio = *bio;
+ bio_init(&mp_bh->bio);
+ __bio_clone_fast(&mp_bh->bio, bio);
+
mp_bh->bio.bi_iter.bi_sector += multipath->rdev->data_offset;
mp_bh->bio.bi_bdev = multipath->rdev->bdev;
mp_bh->bio.bi_rw |= REQ_FAILFAST_TRANSPORT;
diff --git a/drivers/md/persistent-data/dm-btree-internal.h b/drivers/md/persistent-data/dm-btree-internal.h
index bf2b80d5c470..8731b6ea026b 100644
--- a/drivers/md/persistent-data/dm-btree-internal.h
+++ b/drivers/md/persistent-data/dm-btree-internal.h
@@ -138,4 +138,10 @@ int lower_bound(struct btree_node *n, uint64_t key);
extern struct dm_block_validator btree_node_validator;
+/*
+ * Value type for upper levels of multi-level btrees.
+ */
+extern void init_le64_type(struct dm_transaction_manager *tm,
+ struct dm_btree_value_type *vt);
+
#endif /* DM_BTREE_INTERNAL_H */
diff --git a/drivers/md/persistent-data/dm-btree-remove.c b/drivers/md/persistent-data/dm-btree-remove.c
index b88757cd0d1d..92cd09f3c69b 100644
--- a/drivers/md/persistent-data/dm-btree-remove.c
+++ b/drivers/md/persistent-data/dm-btree-remove.c
@@ -301,35 +301,40 @@ static void redistribute3(struct dm_btree_info *info, struct btree_node *parent,
{
int s;
uint32_t max_entries = le32_to_cpu(left->header.max_entries);
- unsigned target = (nr_left + nr_center + nr_right) / 3;
- BUG_ON(target > max_entries);
+ unsigned total = nr_left + nr_center + nr_right;
+ unsigned target_right = total / 3;
+ unsigned remainder = (target_right * 3) != total;
+ unsigned target_left = target_right + remainder;
+
+ BUG_ON(target_left > max_entries);
+ BUG_ON(target_right > max_entries);
if (nr_left < nr_right) {
- s = nr_left - target;
+ s = nr_left - target_left;
if (s < 0 && nr_center < -s) {
/* not enough in central node */
- shift(left, center, nr_center);
- s = nr_center - target;
+ shift(left, center, -nr_center);
+ s += nr_center;
shift(left, right, s);
nr_right += s;
} else
shift(left, center, s);
- shift(center, right, target - nr_right);
+ shift(center, right, target_right - nr_right);
} else {
- s = target - nr_right;
+ s = target_right - nr_right;
if (s > 0 && nr_center < s) {
/* not enough in central node */
shift(center, right, nr_center);
- s = target - nr_center;
+ s -= nr_center;
shift(left, right, s);
nr_left -= s;
} else
shift(center, right, s);
- shift(left, center, nr_left - target);
+ shift(left, center, nr_left - target_left);
}
*key_ptr(parent, c->index) = center->keys[0];
@@ -544,14 +549,6 @@ static int remove_raw(struct shadow_spine *s, struct dm_btree_info *info,
return r;
}
-static struct dm_btree_value_type le64_type = {
- .context = NULL,
- .size = sizeof(__le64),
- .inc = NULL,
- .dec = NULL,
- .equal = NULL
-};
-
int dm_btree_remove(struct dm_btree_info *info, dm_block_t root,
uint64_t *keys, dm_block_t *new_root)
{
@@ -559,12 +556,14 @@ int dm_btree_remove(struct dm_btree_info *info, dm_block_t root,
int index = 0, r = 0;
struct shadow_spine spine;
struct btree_node *n;
+ struct dm_btree_value_type le64_vt;
+ init_le64_type(info->tm, &le64_vt);
init_shadow_spine(&spine, info);
for (level = 0; level < info->levels; level++) {
r = remove_raw(&spine, info,
(level == last_level ?
- &info->value_type : &le64_type),
+ &info->value_type : &le64_vt),
root, keys[level], (unsigned *)&index);
if (r < 0)
break;
diff --git a/drivers/md/persistent-data/dm-btree-spine.c b/drivers/md/persistent-data/dm-btree-spine.c
index 1b5e13ec7f96..0dee514ba4c5 100644
--- a/drivers/md/persistent-data/dm-btree-spine.c
+++ b/drivers/md/persistent-data/dm-btree-spine.c
@@ -249,3 +249,40 @@ int shadow_root(struct shadow_spine *s)
{
return s->root;
}
+
+static void le64_inc(void *context, const void *value_le)
+{
+ struct dm_transaction_manager *tm = context;
+ __le64 v_le;
+
+ memcpy(&v_le, value_le, sizeof(v_le));
+ dm_tm_inc(tm, le64_to_cpu(v_le));
+}
+
+static void le64_dec(void *context, const void *value_le)
+{
+ struct dm_transaction_manager *tm = context;
+ __le64 v_le;
+
+ memcpy(&v_le, value_le, sizeof(v_le));
+ dm_tm_dec(tm, le64_to_cpu(v_le));
+}
+
+static int le64_equal(void *context, const void *value1_le, const void *value2_le)
+{
+ __le64 v1_le, v2_le;
+
+ memcpy(&v1_le, value1_le, sizeof(v1_le));
+ memcpy(&v2_le, value2_le, sizeof(v2_le));
+ return v1_le == v2_le;
+}
+
+void init_le64_type(struct dm_transaction_manager *tm,
+ struct dm_btree_value_type *vt)
+{
+ vt->context = tm;
+ vt->size = sizeof(__le64);
+ vt->inc = le64_inc;
+ vt->dec = le64_dec;
+ vt->equal = le64_equal;
+}
diff --git a/drivers/md/persistent-data/dm-btree.c b/drivers/md/persistent-data/dm-btree.c
index 200ac12a1d40..d6e47033b5e0 100644
--- a/drivers/md/persistent-data/dm-btree.c
+++ b/drivers/md/persistent-data/dm-btree.c
@@ -255,7 +255,7 @@ int dm_btree_del(struct dm_btree_info *info, dm_block_t root)
int r;
struct del_stack *s;
- s = kmalloc(sizeof(*s), GFP_KERNEL);
+ s = kmalloc(sizeof(*s), GFP_NOIO);
if (!s)
return -ENOMEM;
s->info = info;
@@ -523,7 +523,7 @@ static int btree_split_beneath(struct shadow_spine *s, uint64_t key)
r = new_block(s->info, &right);
if (r < 0) {
- /* FIXME: put left */
+ unlock_block(s->info, left);
return r;
}
@@ -667,12 +667,7 @@ static int insert(struct dm_btree_info *info, dm_block_t root,
struct btree_node *n;
struct dm_btree_value_type le64_type;
- le64_type.context = NULL;
- le64_type.size = sizeof(__le64);
- le64_type.inc = NULL;
- le64_type.dec = NULL;
- le64_type.equal = NULL;
-
+ init_le64_type(info->tm, &le64_type);
init_shadow_spine(&spine, info);
for (level = 0; level < (info->levels - 1); level++) {
diff --git a/drivers/md/persistent-data/dm-space-map-metadata.c b/drivers/md/persistent-data/dm-space-map-metadata.c
index f4e22bcc7fb8..199c9ccd1f5d 100644
--- a/drivers/md/persistent-data/dm-space-map-metadata.c
+++ b/drivers/md/persistent-data/dm-space-map-metadata.c
@@ -204,6 +204,27 @@ static void in(struct sm_metadata *smm)
smm->recursion_count++;
}
+static int apply_bops(struct sm_metadata *smm)
+{
+ int r = 0;
+
+ while (!brb_empty(&smm->uncommitted)) {
+ struct block_op bop;
+
+ r = brb_pop(&smm->uncommitted, &bop);
+ if (r) {
+ DMERR("bug in bop ring buffer");
+ break;
+ }
+
+ r = commit_bop(smm, &bop);
+ if (r)
+ break;
+ }
+
+ return r;
+}
+
static int out(struct sm_metadata *smm)
{
int r = 0;
@@ -216,21 +237,8 @@ static int out(struct sm_metadata *smm)
return -ENOMEM;
}
- if (smm->recursion_count == 1) {
- while (!brb_empty(&smm->uncommitted)) {
- struct block_op bop;
-
- r = brb_pop(&smm->uncommitted, &bop);
- if (r) {
- DMERR("bug in bop ring buffer");
- break;
- }
-
- r = commit_bop(smm, &bop);
- if (r)
- break;
- }
- }
+ if (smm->recursion_count == 1)
+ apply_bops(smm);
smm->recursion_count--;
@@ -702,6 +710,12 @@ static int sm_metadata_extend(struct dm_space_map *sm, dm_block_t extra_blocks)
}
old_len = smm->begin;
+ r = apply_bops(smm);
+ if (r) {
+ DMERR("%s: apply_bops failed", __func__);
+ goto out;
+ }
+
r = sm_ll_commit(&smm->ll);
if (r)
goto out;
@@ -771,6 +785,12 @@ int dm_sm_metadata_create(struct dm_space_map *sm,
if (r)
return r;
+ r = apply_bops(smm);
+ if (r) {
+ DMERR("%s: apply_bops failed", __func__);
+ return r;
+ }
+
return sm_metadata_commit(sm);
}
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 2f2f38f4d83c..3c8ada48ca76 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -336,7 +336,7 @@ static void raid1_end_read_request(struct bio *bio, int error)
spin_lock_irqsave(&conf->device_lock, flags);
if (r1_bio->mddev->degraded == conf->raid_disks ||
(r1_bio->mddev->degraded == conf->raid_disks-1 &&
- !test_bit(Faulty, &conf->mirrors[mirror].rdev->flags)))
+ test_bit(In_sync, &conf->mirrors[mirror].rdev->flags)))
uptodate = 1;
spin_unlock_irqrestore(&conf->device_lock, flags);
}
@@ -1474,6 +1474,7 @@ static void error(struct mddev *mddev, struct md_rdev *rdev)
{
char b[BDEVNAME_SIZE];
struct r1conf *conf = mddev->private;
+ unsigned long flags;
/*
* If it is not operational, then we have already marked it as dead
@@ -1493,14 +1494,13 @@ static void error(struct mddev *mddev, struct md_rdev *rdev)
return;
}
set_bit(Blocked, &rdev->flags);
+ spin_lock_irqsave(&conf->device_lock, flags);
if (test_and_clear_bit(In_sync, &rdev->flags)) {
- unsigned long flags;
- spin_lock_irqsave(&conf->device_lock, flags);
mddev->degraded++;
set_bit(Faulty, &rdev->flags);
- spin_unlock_irqrestore(&conf->device_lock, flags);
} else
set_bit(Faulty, &rdev->flags);
+ spin_unlock_irqrestore(&conf->device_lock, flags);
/*
* if recovery is running, make sure it aborts.
*/
@@ -1566,7 +1566,10 @@ static int raid1_spare_active(struct mddev *mddev)
* Find all failed disks within the RAID1 configuration
* and mark them readable.
* Called under mddev lock, so rcu protection not needed.
+ * device_lock used to avoid races with raid1_end_read_request
+ * which expects 'In_sync' flags and ->degraded to be consistent.
*/
+ spin_lock_irqsave(&conf->device_lock, flags);
for (i = 0; i < conf->raid_disks; i++) {
struct md_rdev *rdev = conf->mirrors[i].rdev;
struct md_rdev *repl = conf->mirrors[conf->raid_disks + i].rdev;
@@ -1596,7 +1599,6 @@ static int raid1_spare_active(struct mddev *mddev)
sysfs_notify_dirent_safe(rdev->sysfs_state);
}
}
- spin_lock_irqsave(&conf->device_lock, flags);
mddev->degraded -= count;
spin_unlock_irqrestore(&conf->device_lock, flags);
@@ -2243,7 +2245,7 @@ static int narrow_write_error(struct r1bio *r1_bio, int i)
bio_trim(wbio, sector - r1_bio->sector, sectors);
wbio->bi_iter.bi_sector += rdev->data_offset;
wbio->bi_bdev = rdev->bdev;
- if (submit_bio_wait(WRITE, wbio) == 0)
+ if (submit_bio_wait(WRITE, wbio) < 0)
/* failure! */
ok = rdev_set_badblocks(rdev, sector,
sectors, 0)
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 32e282f4c83c..644f9e576736 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -2599,7 +2599,7 @@ static int narrow_write_error(struct r10bio *r10_bio, int i)
choose_data_offset(r10_bio, rdev) +
(sector - r10_bio->sector));
wbio->bi_bdev = rdev->bdev;
- if (submit_bio_wait(WRITE, wbio) == 0)
+ if (submit_bio_wait(WRITE, wbio) < 0)
/* Failure! */
ok = rdev_set_badblocks(rdev, sector,
sectors, 0)
@@ -3581,6 +3581,7 @@ static struct r10conf *setup_conf(struct mddev *mddev)
/* far_copies must be 1 */
conf->prev.stride = conf->dev_sectors;
}
+ conf->reshape_safe = conf->reshape_progress;
spin_lock_init(&conf->device_lock);
INIT_LIST_HEAD(&conf->retry_list);
@@ -3788,7 +3789,6 @@ static int run(struct mddev *mddev)
}
conf->offset_diff = min_offset_diff;
- conf->reshape_safe = conf->reshape_progress;
clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
@@ -4135,6 +4135,7 @@ static int raid10_start_reshape(struct mddev *mddev)
conf->reshape_progress = size;
} else
conf->reshape_progress = 0;
+ conf->reshape_safe = conf->reshape_progress;
spin_unlock_irq(&conf->device_lock);
if (mddev->delta_disks && mddev->bitmap) {
@@ -4201,6 +4202,7 @@ abort:
rdev->new_data_offset = rdev->data_offset;
smp_wmb();
conf->reshape_progress = MaxSector;
+ conf->reshape_safe = MaxSector;
mddev->reshape_position = MaxSector;
spin_unlock_irq(&conf->device_lock);
return ret;
@@ -4555,6 +4557,7 @@ static void end_reshape(struct r10conf *conf)
md_finish_reshape(conf->mddev);
smp_wmb();
conf->reshape_progress = MaxSector;
+ conf->reshape_safe = MaxSector;
spin_unlock_irq(&conf->device_lock);
/* read-ahead size must cover two whole stripes, which is
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 1e92630fcf75..ec8cd8b31909 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -3062,6 +3062,8 @@ static void handle_stripe_clean_event(struct r5conf *conf,
}
if (!discard_pending &&
test_bit(R5_Discard, &sh->dev[sh->pd_idx].flags)) {
+ int hash = sh->hash_lock_index;
+
clear_bit(R5_Discard, &sh->dev[sh->pd_idx].flags);
clear_bit(R5_UPTODATE, &sh->dev[sh->pd_idx].flags);
if (sh->qd_idx >= 0) {
@@ -3075,9 +3077,9 @@ static void handle_stripe_clean_event(struct r5conf *conf,
* no updated data, so remove it from hash list and the stripe
* will be reinitialized
*/
- spin_lock_irq(&conf->device_lock);
+ spin_lock_irq(conf->hash_locks + hash);
remove_hash(sh);
- spin_unlock_irq(&conf->device_lock);
+ spin_unlock_irq(conf->hash_locks + hash);
if (test_bit(STRIPE_SYNC_REQUESTED, &sh->state))
set_bit(STRIPE_HANDLE, &sh->state);
@@ -6246,8 +6248,8 @@ static int run(struct mddev *mddev)
}
if (discard_supported &&
- mddev->queue->limits.max_discard_sectors >= stripe &&
- mddev->queue->limits.discard_granularity >= stripe)
+ mddev->queue->limits.max_discard_sectors >= (stripe >> 9) &&
+ mddev->queue->limits.discard_granularity >= stripe)
queue_flag_set_unlocked(QUEUE_FLAG_DISCARD,
mddev->queue);
else
generated by cgit v1.2.3 (git 2.25.1) at 2024-06-05 18:18:55 +0000