aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/md
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/md')
-rw-r--r--drivers/md/bcache/alloc.c19
-rw-r--r--drivers/md/bcache/btree.c5
-rw-r--r--drivers/md/bcache/super.c17
-rw-r--r--drivers/md/dm-bufio.c7
-rw-r--r--drivers/md/dm-io.c1
-rw-r--r--drivers/md/dm-ioctl.c4
-rw-r--r--drivers/md/dm-thin-metadata.c6
-rw-r--r--drivers/md/md-cluster.c4
-rw-r--r--drivers/md/md.c10
-rw-r--r--drivers/md/persistent-data/dm-btree.c19
-rw-r--r--drivers/md/raid10.c2
-rw-r--r--drivers/md/raid5.c30
12 files changed, 80 insertions, 44 deletions
diff --git a/drivers/md/bcache/alloc.c b/drivers/md/bcache/alloc.c
index 4d46f2ce606f..aa84fcfd59fc 100644
--- a/drivers/md/bcache/alloc.c
+++ b/drivers/md/bcache/alloc.c
@@ -514,15 +514,21 @@ struct open_bucket {
/*
* We keep multiple buckets open for writes, and try to segregate different
- * write streams for better cache utilization: first we look for a bucket where
- * the last write to it was sequential with the current write, and failing that
- * we look for a bucket that was last used by the same task.
+ * write streams for better cache utilization: first we try to segregate flash
+ * only volume write streams from cached devices, secondly we look for a bucket
+ * where the last write to it was sequential with the current write, and
+ * failing that we look for a bucket that was last used by the same task.
*
* The ideas is if you've got multiple tasks pulling data into the cache at the
* same time, you'll get better cache utilization if you try to segregate their
* data and preserve locality.
*
- * For example, say you've starting Firefox at the same time you're copying a
+ * For example, dirty sectors of flash only volume is not reclaimable, if their
+ * dirty sectors mixed with dirty sectors of cached device, such buckets will
+ * be marked as dirty and won't be reclaimed, though the dirty data of cached
+ * device have been written back to backend device.
+ *
+ * And say you've starting Firefox at the same time you're copying a
* bunch of files. Firefox will likely end up being fairly hot and stay in the
* cache awhile, but the data you copied might not be; if you wrote all that
* data to the same buckets it'd get invalidated at the same time.
@@ -539,7 +545,10 @@ static struct open_bucket *pick_data_bucket(struct cache_set *c,
struct open_bucket *ret, *ret_task = NULL;
list_for_each_entry_reverse(ret, &c->data_buckets, list)
- if (!bkey_cmp(&ret->key, search))
+ if (UUID_FLASH_ONLY(&c->uuids[KEY_INODE(&ret->key)]) !=
+ UUID_FLASH_ONLY(&c->uuids[KEY_INODE(search)]))
+ continue;
+ else if (!bkey_cmp(&ret->key, search))
goto found;
else if (ret->last_write_point == write_point)
ret_task = ret;
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index f0b75d54951a..ee2927b460c9 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -808,7 +808,10 @@ int bch_btree_cache_alloc(struct cache_set *c)
c->shrink.scan_objects = bch_mca_scan;
c->shrink.seeks = 4;
c->shrink.batch = c->btree_pages * 2;
- register_shrinker(&c->shrink);
+
+ if (register_shrinker(&c->shrink))
+ pr_warn("bcache: %s: could not register shrinker",
+ __func__);
return 0;
}
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 6f7bc8a8674b..80812d05b3e2 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -921,6 +921,12 @@ static void cached_dev_detach_finish(struct work_struct *w)
mutex_lock(&bch_register_lock);
+ cancel_delayed_work_sync(&dc->writeback_rate_update);
+ if (!IS_ERR_OR_NULL(dc->writeback_thread)) {
+ kthread_stop(dc->writeback_thread);
+ dc->writeback_thread = NULL;
+ }
+
memset(&dc->sb.set_uuid, 0, 16);
SET_BDEV_STATE(&dc->sb, BDEV_STATE_NONE);
@@ -966,6 +972,7 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c)
uint32_t rtime = cpu_to_le32(get_seconds());
struct uuid_entry *u;
char buf[BDEVNAME_SIZE];
+ struct cached_dev *exist_dc, *t;
bdevname(dc->bdev, buf);
@@ -989,6 +996,16 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c)
return -EINVAL;
}
+ /* Check whether already attached */
+ list_for_each_entry_safe(exist_dc, t, &c->cached_devs, list) {
+ if (!memcmp(dc->sb.uuid, exist_dc->sb.uuid, 16)) {
+ pr_err("Tried to attach %s but duplicate UUID already attached",
+ buf);
+
+ return -EINVAL;
+ }
+ }
+
u = uuid_find(c, dc->sb.uuid);
if (u &&
diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index 51dc353f7962..657b8f763754 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -1521,7 +1521,8 @@ static unsigned long __scan(struct dm_bufio_client *c, unsigned long nr_to_scan,
int l;
struct dm_buffer *b, *tmp;
unsigned long freed = 0;
- unsigned long count = nr_to_scan;
+ unsigned long count = c->n_buffers[LIST_CLEAN] +
+ c->n_buffers[LIST_DIRTY];
unsigned long retain_target = get_retain_buffers(c);
for (l = 0; l < LIST_SIZE; l++) {
@@ -1558,6 +1559,7 @@ dm_bufio_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
{
struct dm_bufio_client *c;
unsigned long count;
+ unsigned long retain_target;
c = container_of(shrink, struct dm_bufio_client, shrinker);
if (sc->gfp_mask & __GFP_FS)
@@ -1566,8 +1568,9 @@ dm_bufio_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
return 0;
count = c->n_buffers[LIST_CLEAN] + c->n_buffers[LIST_DIRTY];
+ retain_target = get_retain_buffers(c);
dm_bufio_unlock(c);
- return count;
+ return (count < retain_target) ? 0 : (count - retain_target);
}
/*
diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c
index 74adcd2c967e..01d7b5785b8e 100644
--- a/drivers/md/dm-io.c
+++ b/drivers/md/dm-io.c
@@ -299,6 +299,7 @@ static void do_region(int rw, unsigned region, struct dm_io_region *where,
else if (rw & REQ_WRITE_SAME)
special_cmd_max_sectors = q->limits.max_write_same_sectors;
if ((rw & (REQ_DISCARD | REQ_WRITE_SAME)) && special_cmd_max_sectors == 0) {
+ atomic_inc(&io->count);
dec_count(io, region, -EOPNOTSUPP);
return;
}
diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c
index df060fd016f6..e8200892ed41 100644
--- a/drivers/md/dm-ioctl.c
+++ b/drivers/md/dm-ioctl.c
@@ -1773,12 +1773,12 @@ static int validate_params(uint cmd, struct dm_ioctl *param)
cmd == DM_LIST_VERSIONS_CMD)
return 0;
- if ((cmd == DM_DEV_CREATE_CMD)) {
+ if (cmd == DM_DEV_CREATE_CMD) {
if (!*param->name) {
DMWARN("name not supplied when creating device");
return -EINVAL;
}
- } else if ((*param->uuid && *param->name)) {
+ } else if (*param->uuid && *param->name) {
DMWARN("only supply one of name or uuid, cmd(%u)", cmd);
return -EINVAL;
}
diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c
index a178134abbe8..c9f51f7c1063 100644
--- a/drivers/md/dm-thin-metadata.c
+++ b/drivers/md/dm-thin-metadata.c
@@ -81,10 +81,14 @@
#define SECTOR_TO_BLOCK_SHIFT 3
/*
+ * For btree insert:
* 3 for btree insert +
* 2 for btree lookup used within space map
+ * For btree remove:
+ * 2 for shadow spine +
+ * 4 for rebalance 3 child node
*/
-#define THIN_MAX_CONCURRENT_LOCKS 5
+#define THIN_MAX_CONCURRENT_LOCKS 6
/* This should be plenty */
#define SPACE_MAP_ROOT_SIZE 128
diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c
index 4eb5cb18f98d..f490382173b6 100644
--- a/drivers/md/md-cluster.c
+++ b/drivers/md/md-cluster.c
@@ -850,8 +850,10 @@ static int add_new_disk_start(struct mddev *mddev, struct md_rdev *rdev)
cmsg.raid_slot = rdev->desc_nr;
lock_comm(cinfo);
ret = __sendmsg(cinfo, &cmsg);
- if (ret)
+ if (ret) {
+ unlock_comm(cinfo);
return ret;
+ }
cinfo->no_new_dev_lockres->flags |= DLM_LKF_NOQUEUE;
ret = dlm_lock_sync(cinfo->no_new_dev_lockres, DLM_LOCK_EX);
cinfo->no_new_dev_lockres->flags &= ~DLM_LKF_NOQUEUE;
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 1fdcd5735418..03bcc1ab2e9d 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -1043,8 +1043,9 @@ static int super_90_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor
* (not needed for Linear and RAID0 as metadata doesn't
* record this size)
*/
- if (rdev->sectors >= (2ULL << 32) && sb->level >= 1)
- rdev->sectors = (2ULL << 32) - 2;
+ if (IS_ENABLED(CONFIG_LBDAF) && (u64)rdev->sectors >= (2ULL << 32) &&
+ sb->level >= 1)
+ rdev->sectors = (sector_t)(2ULL << 32) - 2;
if (rdev->sectors < ((sector_t)sb->size) * 2 && sb->level >= 1)
/* "this cannot possibly happen" ... */
@@ -1337,8 +1338,9 @@ super_90_rdev_size_change(struct md_rdev *rdev, sector_t num_sectors)
/* Limit to 4TB as metadata cannot record more than that.
* 4TB == 2^32 KB, or 2*2^32 sectors.
*/
- if (num_sectors >= (2ULL << 32) && rdev->mddev->level >= 1)
- num_sectors = (2ULL << 32) - 2;
+ if (IS_ENABLED(CONFIG_LBDAF) && (u64)num_sectors >= (2ULL << 32) &&
+ rdev->mddev->level >= 1)
+ num_sectors = (sector_t)(2ULL << 32) - 2;
md_super_write(rdev->mddev, rdev, rdev->sb_start, rdev->sb_size,
rdev->sb_page);
md_super_wait(rdev->mddev);
diff --git a/drivers/md/persistent-data/dm-btree.c b/drivers/md/persistent-data/dm-btree.c
index 360c22d44647..f2a8e4c69d9f 100644
--- a/drivers/md/persistent-data/dm-btree.c
+++ b/drivers/md/persistent-data/dm-btree.c
@@ -572,23 +572,8 @@ static int btree_split_beneath(struct shadow_spine *s, uint64_t key)
pn->keys[1] = rn->keys[0];
memcpy_disk(value_ptr(pn, 1), &val, sizeof(__le64));
- /*
- * rejig the spine. This is ugly, since it knows too
- * much about the spine
- */
- if (s->nodes[0] != new_parent) {
- unlock_block(s->info, s->nodes[0]);
- s->nodes[0] = new_parent;
- }
- if (key < le64_to_cpu(rn->keys[0])) {
- unlock_block(s->info, right);
- s->nodes[1] = left;
- } else {
- unlock_block(s->info, left);
- s->nodes[1] = right;
- }
- s->count = 2;
-
+ unlock_block(s->info, left);
+ unlock_block(s->info, right);
return 0;
}
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 4cbc3df79a2a..641259fe891b 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -3702,6 +3702,7 @@ static int run(struct mddev *mddev)
if (blk_queue_discard(bdev_get_queue(rdev->bdev)))
discard_supported = true;
+ first = 0;
}
if (mddev->queue) {
@@ -4110,6 +4111,7 @@ static int raid10_start_reshape(struct mddev *mddev)
diff = 0;
if (first || diff < min_offset_diff)
min_offset_diff = diff;
+ first = 0;
}
}
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 52019434e193..0cc1ccc056ac 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -110,8 +110,7 @@ static inline void unlock_device_hash_lock(struct r5conf *conf, int hash)
static inline void lock_all_device_hash_locks_irq(struct r5conf *conf)
{
int i;
- local_irq_disable();
- spin_lock(conf->hash_locks);
+ spin_lock_irq(conf->hash_locks);
for (i = 1; i < NR_STRIPE_HASH_LOCKS; i++)
spin_lock_nest_lock(conf->hash_locks + i, conf->hash_locks);
spin_lock(&conf->device_lock);
@@ -121,9 +120,9 @@ static inline void unlock_all_device_hash_locks_irq(struct r5conf *conf)
{
int i;
spin_unlock(&conf->device_lock);
- for (i = NR_STRIPE_HASH_LOCKS; i; i--)
- spin_unlock(conf->hash_locks + i - 1);
- local_irq_enable();
+ for (i = NR_STRIPE_HASH_LOCKS - 1; i; i--)
+ spin_unlock(conf->hash_locks + i);
+ spin_unlock_irq(conf->hash_locks);
}
/* bio's attached to a stripe+device for I/O are linked together in bi_sector
@@ -728,12 +727,11 @@ static bool is_full_stripe_write(struct stripe_head *sh)
static void lock_two_stripes(struct stripe_head *sh1, struct stripe_head *sh2)
{
- local_irq_disable();
if (sh1 > sh2) {
- spin_lock(&sh2->stripe_lock);
+ spin_lock_irq(&sh2->stripe_lock);
spin_lock_nested(&sh1->stripe_lock, 1);
} else {
- spin_lock(&sh1->stripe_lock);
+ spin_lock_irq(&sh1->stripe_lock);
spin_lock_nested(&sh2->stripe_lock, 1);
}
}
@@ -741,8 +739,7 @@ static void lock_two_stripes(struct stripe_head *sh1, struct stripe_head *sh2)
static void unlock_two_stripes(struct stripe_head *sh1, struct stripe_head *sh2)
{
spin_unlock(&sh1->stripe_lock);
- spin_unlock(&sh2->stripe_lock);
- local_irq_enable();
+ spin_unlock_irq(&sh2->stripe_lock);
}
/* Only freshly new full stripe normal write stripe can be added to a batch list */
@@ -3370,9 +3367,20 @@ static int fetch_block(struct stripe_head *sh, struct stripe_head_state *s,
BUG_ON(test_bit(R5_Wantcompute, &dev->flags));
BUG_ON(test_bit(R5_Wantread, &dev->flags));
BUG_ON(sh->batch_head);
+
+ /*
+ * In the raid6 case if the only non-uptodate disk is P
+ * then we already trusted P to compute the other failed
+ * drives. It is safe to compute rather than re-read P.
+ * In other cases we only compute blocks from failed
+ * devices, otherwise check/repair might fail to detect
+ * a real inconsistency.
+ */
+
if ((s->uptodate == disks - 1) &&
+ ((sh->qd_idx >= 0 && sh->pd_idx == disk_idx) ||
(s->failed && (disk_idx == s->failed_num[0] ||
- disk_idx == s->failed_num[1]))) {
+ disk_idx == s->failed_num[1])))) {
/* have disk failed, and we're requested to fetch it;
* do compute it
*/
generated by cgit 1.2.3-korg (git 2.39.0) at 2024-06-14 20:42:56 +0000