summaryrefslogtreecommitdiff
path: root/drivers/md
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/md')
-rw-r--r--drivers/md/bcache/super.c46
-rw-r--r--drivers/md/dm-cache-metadata.c98
-rw-r--r--drivers/md/dm-cache-metadata.h4
-rw-r--r--drivers/md/dm-cache-target.c12
-rw-r--r--drivers/md/dm-snap.c9
-rw-r--r--drivers/md/dm-table.c36
-rw-r--r--drivers/md/dm-thin-metadata.c5
-rw-r--r--drivers/md/dm.c15
-rw-r--r--drivers/md/multipath.c4
-rw-r--r--drivers/md/raid1.c7
-rw-r--r--drivers/md/raid10.c7
-rw-r--r--drivers/md/raid5.c51
-rw-r--r--drivers/md/raid5.h4
13 files changed, 193 insertions, 105 deletions
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 8d0ead98e..a296425a7 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -1015,8 +1015,12 @@ 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);
@@ -1028,6 +1032,9 @@ 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);
@@ -1366,6 +1373,9 @@ 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);
@@ -1828,11 +1838,12 @@ 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;
@@ -1847,27 +1858,35 @@ 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 */
@@ -1965,7 +1984,8 @@ 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)
diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c
index f6543f3a9..27f2ef300 100644
--- a/drivers/md/dm-cache-metadata.c
+++ b/drivers/md/dm-cache-metadata.c
@@ -867,19 +867,40 @@ static int blocks_are_unmapped_or_clean(struct dm_cache_metadata *cmd,
return 0;
}
-#define WRITE_LOCK(cmd) \
- if (cmd->fail_io || dm_bm_is_read_only(cmd->bm)) \
+#define WRITE_LOCK(cmd) \
+ down_write(&cmd->root_lock); \
+ if (cmd->fail_io || dm_bm_is_read_only(cmd->bm)) { \
+ up_write(&cmd->root_lock); \
return -EINVAL; \
- down_write(&cmd->root_lock)
+ }
#define WRITE_LOCK_VOID(cmd) \
- if (cmd->fail_io || dm_bm_is_read_only(cmd->bm)) \
+ down_write(&cmd->root_lock); \
+ if (cmd->fail_io || dm_bm_is_read_only(cmd->bm)) { \
+ up_write(&cmd->root_lock); \
return; \
- down_write(&cmd->root_lock)
+ }
#define WRITE_UNLOCK(cmd) \
up_write(&cmd->root_lock)
+#define READ_LOCK(cmd) \
+ down_read(&cmd->root_lock); \
+ if (cmd->fail_io || dm_bm_is_read_only(cmd->bm)) { \
+ up_read(&cmd->root_lock); \
+ return -EINVAL; \
+ }
+
+#define READ_LOCK_VOID(cmd) \
+ down_read(&cmd->root_lock); \
+ if (cmd->fail_io || dm_bm_is_read_only(cmd->bm)) { \
+ up_read(&cmd->root_lock); \
+ return; \
+ }
+
+#define READ_UNLOCK(cmd) \
+ up_read(&cmd->root_lock)
+
int dm_cache_resize(struct dm_cache_metadata *cmd, dm_cblock_t new_cache_size)
{
int r;
@@ -1015,22 +1036,20 @@ int dm_cache_load_discards(struct dm_cache_metadata *cmd,
{
int r;
- down_read(&cmd->root_lock);
+ READ_LOCK(cmd);
r = __load_discards(cmd, fn, context);
- up_read(&cmd->root_lock);
+ READ_UNLOCK(cmd);
return r;
}
-dm_cblock_t dm_cache_size(struct dm_cache_metadata *cmd)
+int dm_cache_size(struct dm_cache_metadata *cmd, dm_cblock_t *result)
{
- dm_cblock_t r;
+ READ_LOCK(cmd);
+ *result = cmd->cache_blocks;
+ READ_UNLOCK(cmd);
- down_read(&cmd->root_lock);
- r = cmd->cache_blocks;
- up_read(&cmd->root_lock);
-
- return r;
+ return 0;
}
static int __remove(struct dm_cache_metadata *cmd, dm_cblock_t cblock)
@@ -1188,9 +1207,9 @@ int dm_cache_load_mappings(struct dm_cache_metadata *cmd,
{
int r;
- down_read(&cmd->root_lock);
+ READ_LOCK(cmd);
r = __load_mappings(cmd, policy, fn, context);
- up_read(&cmd->root_lock);
+ READ_UNLOCK(cmd);
return r;
}
@@ -1215,18 +1234,18 @@ static int __dump_mappings(struct dm_cache_metadata *cmd)
void dm_cache_dump(struct dm_cache_metadata *cmd)
{
- down_read(&cmd->root_lock);
+ READ_LOCK_VOID(cmd);
__dump_mappings(cmd);
- up_read(&cmd->root_lock);
+ READ_UNLOCK(cmd);
}
int dm_cache_changed_this_transaction(struct dm_cache_metadata *cmd)
{
int r;
- down_read(&cmd->root_lock);
+ READ_LOCK(cmd);
r = cmd->changed;
- up_read(&cmd->root_lock);
+ READ_UNLOCK(cmd);
return r;
}
@@ -1276,9 +1295,9 @@ int dm_cache_set_dirty(struct dm_cache_metadata *cmd,
void dm_cache_metadata_get_stats(struct dm_cache_metadata *cmd,
struct dm_cache_statistics *stats)
{
- down_read(&cmd->root_lock);
+ READ_LOCK_VOID(cmd);
*stats = cmd->stats;
- up_read(&cmd->root_lock);
+ READ_UNLOCK(cmd);
}
void dm_cache_metadata_set_stats(struct dm_cache_metadata *cmd,
@@ -1312,9 +1331,9 @@ int dm_cache_get_free_metadata_block_count(struct dm_cache_metadata *cmd,
{
int r = -EINVAL;
- down_read(&cmd->root_lock);
+ READ_LOCK(cmd);
r = dm_sm_get_nr_free(cmd->metadata_sm, result);
- up_read(&cmd->root_lock);
+ READ_UNLOCK(cmd);
return r;
}
@@ -1324,9 +1343,9 @@ int dm_cache_get_metadata_dev_size(struct dm_cache_metadata *cmd,
{
int r = -EINVAL;
- down_read(&cmd->root_lock);
+ READ_LOCK(cmd);
r = dm_sm_get_nr_blocks(cmd->metadata_sm, result);
- up_read(&cmd->root_lock);
+ READ_UNLOCK(cmd);
return r;
}
@@ -1417,7 +1436,13 @@ int dm_cache_write_hints(struct dm_cache_metadata *cmd, struct dm_cache_policy *
int dm_cache_metadata_all_clean(struct dm_cache_metadata *cmd, bool *result)
{
- return blocks_are_unmapped_or_clean(cmd, 0, cmd->cache_blocks, result);
+ int r;
+
+ READ_LOCK(cmd);
+ r = blocks_are_unmapped_or_clean(cmd, 0, cmd->cache_blocks, result);
+ READ_UNLOCK(cmd);
+
+ return r;
}
void dm_cache_metadata_set_read_only(struct dm_cache_metadata *cmd)
@@ -1440,10 +1465,7 @@ int dm_cache_metadata_set_needs_check(struct dm_cache_metadata *cmd)
struct dm_block *sblock;
struct cache_disk_superblock *disk_super;
- /*
- * We ignore fail_io for this function.
- */
- down_write(&cmd->root_lock);
+ WRITE_LOCK(cmd);
set_bit(NEEDS_CHECK, &cmd->flags);
r = superblock_lock(cmd, &sblock);
@@ -1458,19 +1480,17 @@ int dm_cache_metadata_set_needs_check(struct dm_cache_metadata *cmd)
dm_bm_unlock(sblock);
out:
- up_write(&cmd->root_lock);
+ WRITE_UNLOCK(cmd);
return r;
}
-bool dm_cache_metadata_needs_check(struct dm_cache_metadata *cmd)
+int dm_cache_metadata_needs_check(struct dm_cache_metadata *cmd, bool *result)
{
- bool needs_check;
+ READ_LOCK(cmd);
+ *result = !!test_bit(NEEDS_CHECK, &cmd->flags);
+ READ_UNLOCK(cmd);
- down_read(&cmd->root_lock);
- needs_check = !!test_bit(NEEDS_CHECK, &cmd->flags);
- up_read(&cmd->root_lock);
-
- return needs_check;
+ return 0;
}
int dm_cache_metadata_abort(struct dm_cache_metadata *cmd)
diff --git a/drivers/md/dm-cache-metadata.h b/drivers/md/dm-cache-metadata.h
index 2ffee21f3..852874419 100644
--- a/drivers/md/dm-cache-metadata.h
+++ b/drivers/md/dm-cache-metadata.h
@@ -66,7 +66,7 @@ void dm_cache_metadata_close(struct dm_cache_metadata *cmd);
* origin blocks to map to.
*/
int dm_cache_resize(struct dm_cache_metadata *cmd, dm_cblock_t new_cache_size);
-dm_cblock_t dm_cache_size(struct dm_cache_metadata *cmd);
+int dm_cache_size(struct dm_cache_metadata *cmd, dm_cblock_t *result);
int dm_cache_discard_bitset_resize(struct dm_cache_metadata *cmd,
sector_t discard_block_size,
@@ -137,7 +137,7 @@ int dm_cache_write_hints(struct dm_cache_metadata *cmd, struct dm_cache_policy *
*/
int dm_cache_metadata_all_clean(struct dm_cache_metadata *cmd, bool *result);
-bool dm_cache_metadata_needs_check(struct dm_cache_metadata *cmd);
+int dm_cache_metadata_needs_check(struct dm_cache_metadata *cmd, bool *result);
int dm_cache_metadata_set_needs_check(struct dm_cache_metadata *cmd);
void dm_cache_metadata_set_read_only(struct dm_cache_metadata *cmd);
void dm_cache_metadata_set_read_write(struct dm_cache_metadata *cmd);
diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index 5780accff..bb9b92ebb 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -984,9 +984,14 @@ static void notify_mode_switch(struct cache *cache, enum cache_metadata_mode mod
static void set_cache_mode(struct cache *cache, enum cache_metadata_mode new_mode)
{
- bool needs_check = dm_cache_metadata_needs_check(cache->cmd);
+ bool needs_check;
enum cache_metadata_mode old_mode = get_cache_mode(cache);
+ if (dm_cache_metadata_needs_check(cache->cmd, &needs_check)) {
+ DMERR("unable to read needs_check flag, setting failure mode");
+ new_mode = CM_FAIL;
+ }
+
if (new_mode == CM_WRITE && needs_check) {
DMERR("%s: unable to switch cache to write mode until repaired.",
cache_device_name(cache));
@@ -3510,6 +3515,7 @@ static void cache_status(struct dm_target *ti, status_type_t type,
char buf[BDEVNAME_SIZE];
struct cache *cache = ti->private;
dm_cblock_t residency;
+ bool needs_check;
switch (type) {
case STATUSTYPE_INFO:
@@ -3583,7 +3589,9 @@ static void cache_status(struct dm_target *ti, status_type_t type,
else
DMEMIT("rw ");
- if (dm_cache_metadata_needs_check(cache->cmd))
+ r = dm_cache_metadata_needs_check(cache->cmd, &needs_check);
+
+ if (r || needs_check)
DMEMIT("needs_check ");
else
DMEMIT("- ");
diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c
index 376638608..e4d1bafe7 100644
--- a/drivers/md/dm-snap.c
+++ b/drivers/md/dm-snap.c
@@ -1105,6 +1105,7 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv)
int i;
int r = -EINVAL;
char *origin_path, *cow_path;
+ dev_t origin_dev, cow_dev;
unsigned args_used, num_flush_bios = 1;
fmode_t origin_mode = FMODE_READ;
@@ -1135,11 +1136,19 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv)
ti->error = "Cannot get origin device";
goto bad_origin;
}
+ origin_dev = s->origin->bdev->bd_dev;
cow_path = argv[0];
argv++;
argc--;
+ cow_dev = dm_get_dev_t(cow_path);
+ if (cow_dev && cow_dev == origin_dev) {
+ ti->error = "COW device cannot be the same as origin device";
+ r = -EINVAL;
+ goto bad_cow;
+ }
+
r = dm_get_device(ti, cow_path, dm_table_get_mode(ti->table), &s->cow);
if (r) {
ti->error = "Cannot get COW device";
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 061152a43..cb5d0daf5 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -365,6 +365,26 @@ static int upgrade_mode(struct dm_dev_internal *dd, fmode_t new_mode,
}
/*
+ * Convert the path to a device
+ */
+dev_t dm_get_dev_t(const char *path)
+{
+ dev_t uninitialized_var(dev);
+ struct block_device *bdev;
+
+ bdev = lookup_bdev(path);
+ if (IS_ERR(bdev))
+ dev = name_to_dev_t(path);
+ else {
+ dev = bdev->bd_dev;
+ bdput(bdev);
+ }
+
+ return dev;
+}
+EXPORT_SYMBOL_GPL(dm_get_dev_t);
+
+/*
* Add a device to the list, or just increment the usage count if
* it's already present.
*/
@@ -372,23 +392,15 @@ int dm_get_device(struct dm_target *ti, const char *path, fmode_t mode,
struct dm_dev **result)
{
int r;
- dev_t uninitialized_var(dev);
+ dev_t dev;
struct dm_dev_internal *dd;
struct dm_table *t = ti->table;
- struct block_device *bdev;
BUG_ON(!t);
- /* convert the path to a device */
- bdev = lookup_bdev(path);
- if (IS_ERR(bdev)) {
- dev = name_to_dev_t(path);
- if (!dev)
- return -ENODEV;
- } else {
- dev = bdev->bd_dev;
- bdput(bdev);
- }
+ dev = dm_get_dev_t(path);
+ if (!dev)
+ return -ENODEV;
dd = find_device(&t->devices, dev);
if (!dd) {
diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c
index f962d6453..185010d9c 100644
--- a/drivers/md/dm-thin-metadata.c
+++ b/drivers/md/dm-thin-metadata.c
@@ -1981,5 +1981,8 @@ bool dm_pool_metadata_needs_check(struct dm_pool_metadata *pmd)
void dm_pool_issue_prefetches(struct dm_pool_metadata *pmd)
{
- dm_tm_issue_prefetches(pmd->tm);
+ down_read(&pmd->root_lock);
+ if (!pmd->fail_io)
+ dm_tm_issue_prefetches(pmd->tm);
+ up_read(&pmd->root_lock);
}
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index dd834927b..c338aebb4 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1109,12 +1109,8 @@ static void rq_completed(struct mapped_device *md, int rw, bool run_queue)
* back into ->request_fn() could deadlock attempting to grab the
* queue lock again.
*/
- if (run_queue) {
- if (md->queue->mq_ops)
- blk_mq_run_hw_queues(md->queue, true);
- else
- blk_run_queue_async(md->queue);
- }
+ if (!md->queue->mq_ops && run_queue)
+ blk_run_queue_async(md->queue);
/*
* dm_put() must be at the end of this function. See the comment above
@@ -1214,9 +1210,9 @@ static void dm_requeue_original_request(struct mapped_device *md,
{
int rw = rq_data_dir(rq);
+ rq_end_stats(md, rq);
dm_unprep_request(rq);
- rq_end_stats(md, rq);
if (!rq->q->mq_ops)
old_requeue_request(rq);
else {
@@ -1336,7 +1332,10 @@ static void dm_complete_request(struct request *rq, int error)
struct dm_rq_target_io *tio = tio_from_request(rq);
tio->error = error;
- blk_complete_request(rq);
+ if (!rq->q->mq_ops)
+ blk_complete_request(rq);
+ else
+ blk_mq_complete_request(rq, error);
}
/*
diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c
index 0a72ab6e6..dd483bb2e 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/raid1.c b/drivers/md/raid1.c
index 4e3843f7d..bb5bce059 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -2274,6 +2274,7 @@ static void handle_write_finished(struct r1conf *conf, struct r1bio *r1_bio)
if (fail) {
spin_lock_irq(&conf->device_lock);
list_add(&r1_bio->retry_list, &conf->bio_end_io_list);
+ conf->nr_queued++;
spin_unlock_irq(&conf->device_lock);
md_wakeup_thread(conf->mddev->thread);
} else {
@@ -2391,8 +2392,10 @@ static void raid1d(struct md_thread *thread)
LIST_HEAD(tmp);
spin_lock_irqsave(&conf->device_lock, flags);
if (!test_bit(MD_CHANGE_PENDING, &mddev->flags)) {
- list_add(&tmp, &conf->bio_end_io_list);
- list_del_init(&conf->bio_end_io_list);
+ while (!list_empty(&conf->bio_end_io_list)) {
+ list_move(conf->bio_end_io_list.prev, &tmp);
+ conf->nr_queued--;
+ }
}
spin_unlock_irqrestore(&conf->device_lock, flags);
while (!list_empty(&tmp)) {
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 1c1447dd3..e3fd725d5 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -2664,6 +2664,7 @@ static void handle_write_completed(struct r10conf *conf, struct r10bio *r10_bio)
if (fail) {
spin_lock_irq(&conf->device_lock);
list_add(&r10_bio->retry_list, &conf->bio_end_io_list);
+ conf->nr_queued++;
spin_unlock_irq(&conf->device_lock);
md_wakeup_thread(conf->mddev->thread);
} else {
@@ -2691,8 +2692,10 @@ static void raid10d(struct md_thread *thread)
LIST_HEAD(tmp);
spin_lock_irqsave(&conf->device_lock, flags);
if (!test_bit(MD_CHANGE_PENDING, &mddev->flags)) {
- list_add(&tmp, &conf->bio_end_io_list);
- list_del_init(&conf->bio_end_io_list);
+ while (!list_empty(&conf->bio_end_io_list)) {
+ list_move(conf->bio_end_io_list.prev, &tmp);
+ conf->nr_queued--;
+ }
}
spin_unlock_irqrestore(&conf->device_lock, flags);
while (!list_empty(&tmp)) {
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index b4f02c995..32d52878f 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -340,8 +340,7 @@ static void release_inactive_stripe_list(struct r5conf *conf,
int hash)
{
int size;
- unsigned long do_wakeup = 0;
- int i = 0;
+ bool do_wakeup = false;
unsigned long flags;
if (hash == NR_STRIPE_HASH_LOCKS) {
@@ -362,19 +361,15 @@ static void release_inactive_stripe_list(struct r5conf *conf,
!list_empty(list))
atomic_dec(&conf->empty_inactive_list_nr);
list_splice_tail_init(list, conf->inactive_list + hash);
- do_wakeup |= 1 << hash;
+ do_wakeup = true;
spin_unlock_irqrestore(conf->hash_locks + hash, flags);
}
size--;
hash--;
}
- for (i = 0; i < NR_STRIPE_HASH_LOCKS; i++) {
- if (do_wakeup & (1 << i))
- wake_up(&conf->wait_for_stripe[i]);
- }
-
if (do_wakeup) {
+ wake_up(&conf->wait_for_stripe);
if (atomic_read(&conf->active_stripes) == 0)
wake_up(&conf->wait_for_quiescent);
if (conf->retry_read_aligned)
@@ -687,15 +682,14 @@ raid5_get_active_stripe(struct r5conf *conf, sector_t sector,
if (!sh) {
set_bit(R5_INACTIVE_BLOCKED,
&conf->cache_state);
- wait_event_exclusive_cmd(
- conf->wait_for_stripe[hash],
+ wait_event_lock_irq(
+ conf->wait_for_stripe,
!list_empty(conf->inactive_list + hash) &&
(atomic_read(&conf->active_stripes)
< (conf->max_nr_stripes * 3 / 4)
|| !test_bit(R5_INACTIVE_BLOCKED,
&conf->cache_state)),
- spin_unlock_irq(conf->hash_locks + hash),
- spin_lock_irq(conf->hash_locks + hash));
+ *(conf->hash_locks + hash));
clear_bit(R5_INACTIVE_BLOCKED,
&conf->cache_state);
} else {
@@ -720,9 +714,6 @@ raid5_get_active_stripe(struct r5conf *conf, sector_t sector,
}
} while (sh == NULL);
- if (!list_empty(conf->inactive_list + hash))
- wake_up(&conf->wait_for_stripe[hash]);
-
spin_unlock_irq(conf->hash_locks + hash);
return sh;
}
@@ -2089,6 +2080,14 @@ static int resize_chunks(struct r5conf *conf, int new_disks, int new_sectors)
unsigned long cpu;
int err = 0;
+ /*
+ * Never shrink. And mddev_suspend() could deadlock if this is called
+ * from raid5d. In that case, scribble_disks and scribble_sectors
+ * should equal to new_disks and new_sectors
+ */
+ if (conf->scribble_disks >= new_disks &&
+ conf->scribble_sectors >= new_sectors)
+ return 0;
mddev_suspend(conf->mddev);
get_online_cpus();
for_each_present_cpu(cpu) {
@@ -2110,6 +2109,10 @@ static int resize_chunks(struct r5conf *conf, int new_disks, int new_sectors)
}
put_online_cpus();
mddev_resume(conf->mddev);
+ if (!err) {
+ conf->scribble_disks = new_disks;
+ conf->scribble_sectors = new_sectors;
+ }
return err;
}
@@ -2190,7 +2193,7 @@ static int resize_stripes(struct r5conf *conf, int newsize)
cnt = 0;
list_for_each_entry(nsh, &newstripes, lru) {
lock_device_hash_lock(conf, hash);
- wait_event_exclusive_cmd(conf->wait_for_stripe[hash],
+ wait_event_cmd(conf->wait_for_stripe,
!list_empty(conf->inactive_list + hash),
unlock_device_hash_lock(conf, hash),
lock_device_hash_lock(conf, hash));
@@ -4236,7 +4239,6 @@ static void break_stripe_batch_list(struct stripe_head *head_sh,
WARN_ON_ONCE(sh->state & ((1 << STRIPE_ACTIVE) |
(1 << STRIPE_SYNCING) |
(1 << STRIPE_REPLACED) |
- (1 << STRIPE_PREREAD_ACTIVE) |
(1 << STRIPE_DELAYED) |
(1 << STRIPE_BIT_DELAY) |
(1 << STRIPE_FULL_WRITE) |
@@ -4251,6 +4253,7 @@ static void break_stripe_batch_list(struct stripe_head *head_sh,
(1 << STRIPE_REPLACED)));
set_mask_bits(&sh->state, ~(STRIPE_EXPAND_SYNC_FLAGS |
+ (1 << STRIPE_PREREAD_ACTIVE) |
(1 << STRIPE_DEGRADED)),
head_sh->state & (1 << STRIPE_INSYNC));
@@ -6413,6 +6416,12 @@ static int raid5_alloc_percpu(struct r5conf *conf)
}
put_online_cpus();
+ if (!err) {
+ conf->scribble_disks = max(conf->raid_disks,
+ conf->previous_raid_disks);
+ conf->scribble_sectors = max(conf->chunk_sectors,
+ conf->prev_chunk_sectors);
+ }
return err;
}
@@ -6503,9 +6512,7 @@ static struct r5conf *setup_conf(struct mddev *mddev)
seqcount_init(&conf->gen_lock);
mutex_init(&conf->cache_size_mutex);
init_waitqueue_head(&conf->wait_for_quiescent);
- for (i = 0; i < NR_STRIPE_HASH_LOCKS; i++) {
- init_waitqueue_head(&conf->wait_for_stripe[i]);
- }
+ init_waitqueue_head(&conf->wait_for_stripe);
init_waitqueue_head(&conf->wait_for_overlap);
INIT_LIST_HEAD(&conf->handle_list);
INIT_LIST_HEAD(&conf->hold_list);
@@ -7014,8 +7021,8 @@ static int raid5_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
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index a415e1cd3..517d4b68a 100644
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -510,6 +510,8 @@ struct r5conf {
* conversions
*/
} __percpu *percpu;
+ int scribble_disks;
+ int scribble_sectors;
#ifdef CONFIG_HOTPLUG_CPU
struct notifier_block cpu_notify;
#endif
@@ -522,7 +524,7 @@ struct r5conf {
atomic_t empty_inactive_list_nr;
struct llist_head released_stripes;
wait_queue_head_t wait_for_quiescent;
- wait_queue_head_t wait_for_stripe[NR_STRIPE_HASH_LOCKS];
+ wait_queue_head_t wait_for_stripe;
wait_queue_head_t wait_for_overlap;
unsigned long cache_state;
#define R5_INACTIVE_BLOCKED 1 /* release of inactive stripes blocked,
generated by cgit v1.2.3 (git 2.25.1) at 2024-05-23 16:40:53 +0000