summaryrefslogtreecommitdiff
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/super.c17
-rw-r--r--drivers/md/dm-io.c1
-rw-r--r--drivers/md/dm-ioctl.c4
-rw-r--r--drivers/md/md-cluster.c4
-rw-r--r--drivers/md/raid10.c7
-rw-r--r--drivers/md/raid5.c30
7 files changed, 63 insertions, 19 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/super.c b/drivers/md/bcache/super.c
index c2248b75f2da..b9a526271f02 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -890,6 +890,12 @@ 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);
@@ -935,6 +941,7 @@ 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);
@@ -958,6 +965,16 @@ 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-io.c b/drivers/md/dm-io.c
index 81c5e1a1f363..1b84d2890fbf 100644
--- a/drivers/md/dm-io.c
+++ b/drivers/md/dm-io.c
@@ -300,6 +300,7 @@ 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 7baeeafa059d..065d7cee0d21 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/md-cluster.c b/drivers/md/md-cluster.c
index 494d01d0e92a..a7a561af05c9 100644
--- a/drivers/md/md-cluster.c
+++ b/drivers/md/md-cluster.c
@@ -945,8 +945,10 @@ static int add_new_disk(struct mddev *mddev, struct md_rdev *rdev)
cmsg.raid_slot = cpu_to_le32(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/raid10.c b/drivers/md/raid10.c
index a67e1a36733f..45e7a47e5f7b 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -2698,6 +2698,11 @@ static void handle_write_completed(struct r10conf *conf, struct r10bio *r10_bio)
list_add(&r10_bio->retry_list, &conf->bio_end_io_list);
conf->nr_queued++;
spin_unlock_irq(&conf->device_lock);
+ /*
+ * In case freeze_array() is waiting for condition
+ * nr_pending == nr_queued + extra to be true.
+ */
+ wake_up(&conf->wait_barrier);
md_wakeup_thread(conf->mddev->thread);
} else {
if (test_bit(R10BIO_WriteError,
@@ -3633,6 +3638,7 @@ static int run(struct mddev *mddev)
if (blk_queue_discard(bdev_get_queue(rdev->bdev)))
discard_supported = true;
+ first = 0;
}
if (mddev->queue) {
@@ -4039,6 +4045,7 @@ 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 77403228e098..9284acea4f7b 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
@@ -726,12 +725,11 @@ 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);
}
}
@@ -739,8 +737,7 @@ 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 */
@@ -3372,9 +3369,20 @@ 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 v1.2.3 (git 2.25.1) at 2025-12-25 19:35:51 +0000