summaryrefslogtreecommitdiff
path: root/drivers/md
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/md')
-rw-r--r--drivers/md/bcache/alloc.c2
-rw-r--r--drivers/md/bcache/btree.c5
-rw-r--r--drivers/md/bcache/extents.c2
-rw-r--r--drivers/md/bcache/journal.c7
-rw-r--r--drivers/md/bcache/request.c13
-rw-r--r--drivers/md/dm-bufio.c8
-rw-r--r--drivers/md/dm-cache-target.c12
-rw-r--r--drivers/md/dm-mpath.c67
-rw-r--r--drivers/md/dm-snap.c48
-rw-r--r--drivers/md/dm-table.c5
-rw-r--r--drivers/md/dm-thin.c22
-rw-r--r--drivers/md/md.c4
-rw-r--r--drivers/md/raid1.c4
-rw-r--r--drivers/md/raid10.c4
-rw-r--r--drivers/md/raid5-cache.c22
-rw-r--r--drivers/md/raid5.c2
16 files changed, 139 insertions, 88 deletions
diff --git a/drivers/md/bcache/alloc.c b/drivers/md/bcache/alloc.c
index a27d85232ce1..a0cc1bc6d884 100644
--- a/drivers/md/bcache/alloc.c
+++ b/drivers/md/bcache/alloc.c
@@ -490,7 +490,7 @@ int __bch_bucket_alloc_set(struct cache_set *c, unsigned reserve,
if (b == -1)
goto err;
- k->ptr[i] = PTR(ca->buckets[b].gen,
+ k->ptr[i] = MAKE_PTR(ca->buckets[b].gen,
bucket_to_sector(c, b),
ca->sb.nr_this_dev);
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index 11c5503d31dc..81e8dc3dbe5e 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -807,7 +807,10 @@ 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/extents.c b/drivers/md/bcache/extents.c
index 41c238fc3733..f9d391711595 100644
--- a/drivers/md/bcache/extents.c
+++ b/drivers/md/bcache/extents.c
@@ -585,7 +585,7 @@ static bool bch_extent_merge(struct btree_keys *bk, struct bkey *l, struct bkey
return false;
for (i = 0; i < KEY_PTRS(l); i++)
- if (l->ptr[i] + PTR(0, KEY_SIZE(l), 0) != r->ptr[i] ||
+ if (l->ptr[i] + MAKE_PTR(0, KEY_SIZE(l), 0) != r->ptr[i] ||
PTR_BUCKET_NR(b->c, l, i) != PTR_BUCKET_NR(b->c, r, i))
return false;
diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c
index 02a98ddb592d..a87165c1d8e5 100644
--- a/drivers/md/bcache/journal.c
+++ b/drivers/md/bcache/journal.c
@@ -170,6 +170,11 @@ int bch_journal_read(struct cache_set *c, struct list_head *list)
* find a sequence of buckets with valid journal entries
*/
for (i = 0; i < ca->sb.njournal_buckets; i++) {
+ /*
+ * We must try the index l with ZERO first for
+ * correctness due to the scenario that the journal
+ * bucket is circular buffer which might have wrapped
+ */
l = (i * 2654435769U) % ca->sb.njournal_buckets;
if (test_bit(l, bitmap))
@@ -507,7 +512,7 @@ static void journal_reclaim(struct cache_set *c)
continue;
ja->cur_idx = next;
- k->ptr[n++] = PTR(0,
+ k->ptr[n++] = MAKE_PTR(0,
bucket_to_sector(c, ca->sb.d[ja->cur_idx]),
ca->sb.nr_this_dev);
}
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index 3a7aed7282b2..643c3021624f 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -708,16 +708,15 @@ static void cached_dev_read_error(struct closure *cl)
{
struct search *s = container_of(cl, struct search, cl);
struct bio *bio = &s->bio.bio;
- struct cached_dev *dc = container_of(s->d, struct cached_dev, disk);
/*
- * If cache device is dirty (dc->has_dirty is non-zero), then
- * recovery a failed read request from cached device may get a
- * stale data back. So read failure recovery is only permitted
- * when cache device is clean.
+ * If read request hit dirty data (s->read_dirty_data is true),
+ * then recovery a failed read request from cached device may
+ * get a stale data back. So read failure recovery is only
+ * permitted when read request hit clean data in cache device,
+ * or when cache read race happened.
*/
- if (s->recoverable &&
- (dc && !atomic_read(&dc->has_dirty))) {
+ if (s->recoverable && !s->read_dirty_data) {
/* Retry from the backing device: */
trace_bcache_read_retry(s->orig_bio);
diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index b8ac591aaaa7..c546b567f3b5 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -1611,7 +1611,8 @@ 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++) {
@@ -1647,8 +1648,11 @@ static unsigned long
dm_bufio_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
{
struct dm_bufio_client *c = container_of(shrink, struct dm_bufio_client, shrinker);
+ unsigned long count = READ_ONCE(c->n_buffers[LIST_CLEAN]) +
+ READ_ONCE(c->n_buffers[LIST_DIRTY]);
+ unsigned long retain_target = get_retain_buffers(c);
- return READ_ONCE(c->n_buffers[LIST_CLEAN]) + READ_ONCE(c->n_buffers[LIST_DIRTY]);
+ return (count < retain_target) ? 0 : (count - retain_target);
}
/*
diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index cf23a14f9c6a..47407e43b96a 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -3472,18 +3472,18 @@ static int __init dm_cache_init(void)
{
int r;
- r = dm_register_target(&cache_target);
- if (r) {
- DMERR("cache target registration failed: %d", r);
- return r;
- }
-
migration_cache = KMEM_CACHE(dm_cache_migration, 0);
if (!migration_cache) {
dm_unregister_target(&cache_target);
return -ENOMEM;
}
+ r = dm_register_target(&cache_target);
+ if (r) {
+ DMERR("cache target registration failed: %d", r);
+ return r;
+ }
+
return 0;
}
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index c8faa2b85842..f7810cc869ac 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -458,6 +458,38 @@ do { \
} while (0)
/*
+ * Check whether bios must be queued in the device-mapper core rather
+ * than here in the target.
+ *
+ * If MPATHF_QUEUE_IF_NO_PATH and MPATHF_SAVED_QUEUE_IF_NO_PATH hold
+ * the same value then we are not between multipath_presuspend()
+ * and multipath_resume() calls and we have no need to check
+ * for the DMF_NOFLUSH_SUSPENDING flag.
+ */
+static bool __must_push_back(struct multipath *m, unsigned long flags)
+{
+ return ((test_bit(MPATHF_QUEUE_IF_NO_PATH, &flags) !=
+ test_bit(MPATHF_SAVED_QUEUE_IF_NO_PATH, &flags)) &&
+ dm_noflush_suspending(m->ti));
+}
+
+/*
+ * Following functions use READ_ONCE to get atomic access to
+ * all m->flags to avoid taking spinlock
+ */
+static bool must_push_back_rq(struct multipath *m)
+{
+ unsigned long flags = READ_ONCE(m->flags);
+ return test_bit(MPATHF_QUEUE_IF_NO_PATH, &flags) || __must_push_back(m, flags);
+}
+
+static bool must_push_back_bio(struct multipath *m)
+{
+ unsigned long flags = READ_ONCE(m->flags);
+ return __must_push_back(m, flags);
+}
+
+/*
* Map cloned requests (request-based multipath)
*/
static int multipath_clone_and_map(struct dm_target *ti, struct request *rq,
@@ -478,7 +510,7 @@ static int multipath_clone_and_map(struct dm_target *ti, struct request *rq,
pgpath = choose_pgpath(m, nr_bytes);
if (!pgpath) {
- if (test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags))
+ if (must_push_back_rq(m))
return DM_MAPIO_DELAY_REQUEUE;
dm_report_EIO(m); /* Failed */
return DM_MAPIO_KILL;
@@ -553,7 +585,7 @@ static int __multipath_map_bio(struct multipath *m, struct bio *bio, struct dm_m
}
if (!pgpath) {
- if (test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags))
+ if (must_push_back_bio(m))
return DM_MAPIO_REQUEUE;
dm_report_EIO(m);
return DM_MAPIO_KILL;
@@ -651,8 +683,7 @@ static int queue_if_no_path(struct multipath *m, bool queue_if_no_path,
assign_bit(MPATHF_SAVED_QUEUE_IF_NO_PATH, &m->flags,
(save_old_value && test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags)) ||
(!save_old_value && queue_if_no_path));
- assign_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags,
- queue_if_no_path || dm_noflush_suspending(m->ti));
+ assign_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags, queue_if_no_path);
spin_unlock_irqrestore(&m->lock, flags);
if (!queue_if_no_path) {
@@ -1486,7 +1517,7 @@ static int multipath_end_io(struct dm_target *ti, struct request *clone,
fail_path(pgpath);
if (atomic_read(&m->nr_valid_paths) == 0 &&
- !test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags)) {
+ !must_push_back_rq(m)) {
if (error == BLK_STS_IOERR)
dm_report_EIO(m);
/* complete with the original error */
@@ -1521,8 +1552,12 @@ static int multipath_end_io_bio(struct dm_target *ti, struct bio *clone,
if (atomic_read(&m->nr_valid_paths) == 0 &&
!test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags)) {
- dm_report_EIO(m);
- *error = BLK_STS_IOERR;
+ if (must_push_back_bio(m)) {
+ r = DM_ENDIO_REQUEUE;
+ } else {
+ dm_report_EIO(m);
+ *error = BLK_STS_IOERR;
+ }
goto done;
}
@@ -1957,13 +1992,6 @@ static int __init dm_multipath_init(void)
{
int r;
- r = dm_register_target(&multipath_target);
- if (r < 0) {
- DMERR("request-based register failed %d", r);
- r = -EINVAL;
- goto bad_register_target;
- }
-
kmultipathd = alloc_workqueue("kmpathd", WQ_MEM_RECLAIM, 0);
if (!kmultipathd) {
DMERR("failed to create workqueue kmpathd");
@@ -1985,13 +2013,20 @@ static int __init dm_multipath_init(void)
goto bad_alloc_kmpath_handlerd;
}
+ r = dm_register_target(&multipath_target);
+ if (r < 0) {
+ DMERR("request-based register failed %d", r);
+ r = -EINVAL;
+ goto bad_register_target;
+ }
+
return 0;
+bad_register_target:
+ destroy_workqueue(kmpath_handlerd);
bad_alloc_kmpath_handlerd:
destroy_workqueue(kmultipathd);
bad_alloc_kmultipathd:
- dm_unregister_target(&multipath_target);
-bad_register_target:
return r;
}
diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c
index 1113b42e1eda..a0613bd8ed00 100644
--- a/drivers/md/dm-snap.c
+++ b/drivers/md/dm-snap.c
@@ -2411,24 +2411,6 @@ static int __init dm_snapshot_init(void)
return r;
}
- r = dm_register_target(&snapshot_target);
- if (r < 0) {
- DMERR("snapshot target register failed %d", r);
- goto bad_register_snapshot_target;
- }
-
- r = dm_register_target(&origin_target);
- if (r < 0) {
- DMERR("Origin target register failed %d", r);
- goto bad_register_origin_target;
- }
-
- r = dm_register_target(&merge_target);
- if (r < 0) {
- DMERR("Merge target register failed %d", r);
- goto bad_register_merge_target;
- }
-
r = init_origin_hash();
if (r) {
DMERR("init_origin_hash failed.");
@@ -2449,19 +2431,37 @@ static int __init dm_snapshot_init(void)
goto bad_pending_cache;
}
+ r = dm_register_target(&snapshot_target);
+ if (r < 0) {
+ DMERR("snapshot target register failed %d", r);
+ goto bad_register_snapshot_target;
+ }
+
+ r = dm_register_target(&origin_target);
+ if (r < 0) {
+ DMERR("Origin target register failed %d", r);
+ goto bad_register_origin_target;
+ }
+
+ r = dm_register_target(&merge_target);
+ if (r < 0) {
+ DMERR("Merge target register failed %d", r);
+ goto bad_register_merge_target;
+ }
+
return 0;
-bad_pending_cache:
- kmem_cache_destroy(exception_cache);
-bad_exception_cache:
- exit_origin_hash();
-bad_origin_hash:
- dm_unregister_target(&merge_target);
bad_register_merge_target:
dm_unregister_target(&origin_target);
bad_register_origin_target:
dm_unregister_target(&snapshot_target);
bad_register_snapshot_target:
+ kmem_cache_destroy(pending_cache);
+bad_pending_cache:
+ kmem_cache_destroy(exception_cache);
+bad_exception_cache:
+ exit_origin_hash();
+bad_origin_hash:
dm_exception_store_exit();
return r;
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 88130b5d95f9..aaffd0c0ee9a 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -453,14 +453,15 @@ int dm_get_device(struct dm_target *ti, const char *path, fmode_t mode,
refcount_set(&dd->count, 1);
list_add(&dd->list, &t->devices);
+ goto out;
} else if (dd->dm_dev->mode != (mode | dd->dm_dev->mode)) {
r = upgrade_mode(dd, mode, t->md);
if (r)
return r;
- refcount_inc(&dd->count);
}
-
+ refcount_inc(&dd->count);
+out:
*result = dd->dm_dev;
return 0;
}
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index 89e5dff9b4cf..f91d771fff4b 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -4355,30 +4355,28 @@ static struct target_type thin_target = {
static int __init dm_thin_init(void)
{
- int r;
+ int r = -ENOMEM;
pool_table_init();
+ _new_mapping_cache = KMEM_CACHE(dm_thin_new_mapping, 0);
+ if (!_new_mapping_cache)
+ return r;
+
r = dm_register_target(&thin_target);
if (r)
- return r;
+ goto bad_new_mapping_cache;
r = dm_register_target(&pool_target);
if (r)
- goto bad_pool_target;
-
- r = -ENOMEM;
-
- _new_mapping_cache = KMEM_CACHE(dm_thin_new_mapping, 0);
- if (!_new_mapping_cache)
- goto bad_new_mapping_cache;
+ goto bad_thin_target;
return 0;
-bad_new_mapping_cache:
- dm_unregister_target(&pool_target);
-bad_pool_target:
+bad_thin_target:
dm_unregister_target(&thin_target);
+bad_new_mapping_cache:
+ kmem_cache_destroy(_new_mapping_cache);
return r;
}
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 41c050b59ec4..4e4dee0ec2de 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -7605,7 +7605,9 @@ static int status_resync(struct seq_file *seq, struct mddev *mddev)
if (test_bit(MD_RECOVERY_DONE, &mddev->recovery))
/* Still cleaning up */
resync = max_sectors;
- } else
+ } else if (resync > max_sectors)
+ resync = max_sectors;
+ else
resync -= atomic_read(&mddev->recovery_active);
if (resync == 0) {
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index cc9d337a1ed3..6df398e3a008 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -809,11 +809,15 @@ static void flush_pending_writes(struct r1conf *conf)
spin_lock_irq(&conf->device_lock);
if (conf->pending_bio_list.head) {
+ struct blk_plug plug;
struct bio *bio;
+
bio = bio_list_get(&conf->pending_bio_list);
conf->pending_count = 0;
spin_unlock_irq(&conf->device_lock);
+ blk_start_plug(&plug);
flush_bio_list(conf, bio);
+ blk_finish_plug(&plug);
} else
spin_unlock_irq(&conf->device_lock);
}
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index b9edbc747a95..c131835cf008 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -894,10 +894,13 @@ static void flush_pending_writes(struct r10conf *conf)
spin_lock_irq(&conf->device_lock);
if (conf->pending_bio_list.head) {
+ struct blk_plug plug;
struct bio *bio;
+
bio = bio_list_get(&conf->pending_bio_list);
conf->pending_count = 0;
spin_unlock_irq(&conf->device_lock);
+ blk_start_plug(&plug);
/* flush any pending bitmap writes to disk
* before proceeding w/ I/O */
bitmap_unplug(conf->mddev->bitmap);
@@ -918,6 +921,7 @@ static void flush_pending_writes(struct r10conf *conf)
generic_make_request(bio);
bio = next;
}
+ blk_finish_plug(&plug);
} else
spin_unlock_irq(&conf->device_lock);
}
diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c
index f1c86d938502..39f31f07ffe9 100644
--- a/drivers/md/raid5-cache.c
+++ b/drivers/md/raid5-cache.c
@@ -2577,31 +2577,22 @@ static ssize_t r5c_journal_mode_show(struct mddev *mddev, char *page)
int r5c_journal_mode_set(struct mddev *mddev, int mode)
{
struct r5conf *conf;
- int err;
if (mode < R5C_JOURNAL_MODE_WRITE_THROUGH ||
mode > R5C_JOURNAL_MODE_WRITE_BACK)
return -EINVAL;
- err = mddev_lock(mddev);
- if (err)
- return err;
conf = mddev->private;
- if (!conf || !conf->log) {
- mddev_unlock(mddev);
+ if (!conf || !conf->log)
return -ENODEV;
- }
if (raid5_calc_degraded(conf) > 0 &&
- mode == R5C_JOURNAL_MODE_WRITE_BACK) {
- mddev_unlock(mddev);
+ mode == R5C_JOURNAL_MODE_WRITE_BACK)
return -EINVAL;
- }
mddev_suspend(mddev);
conf->log->r5c_journal_mode = mode;
mddev_resume(mddev);
- mddev_unlock(mddev);
pr_debug("md/raid:%s: setting r5c cache mode to %d: %s\n",
mdname(mddev), mode, r5c_journal_mode_str[mode]);
@@ -2614,6 +2605,7 @@ static ssize_t r5c_journal_mode_store(struct mddev *mddev,
{
int mode = ARRAY_SIZE(r5c_journal_mode_str);
size_t len = length;
+ int ret;
if (len < 2)
return -EINVAL;
@@ -2625,8 +2617,12 @@ static ssize_t r5c_journal_mode_store(struct mddev *mddev,
if (strlen(r5c_journal_mode_str[mode]) == len &&
!strncmp(page, r5c_journal_mode_str[mode], len))
break;
-
- return r5c_journal_mode_set(mddev, mode) ?: length;
+ ret = mddev_lock(mddev);
+ if (ret)
+ return ret;
+ ret = r5c_journal_mode_set(mddev, mode);
+ mddev_unlock(mddev);
+ return ret ?: length;
}
struct md_sysfs_entry
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 31dc25e2871a..98ce4272ace9 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -2677,13 +2677,13 @@ static void raid5_error(struct mddev *mddev, struct md_rdev *rdev)
pr_debug("raid456: error called\n");
spin_lock_irqsave(&conf->device_lock, flags);
+ set_bit(Faulty, &rdev->flags);
clear_bit(In_sync, &rdev->flags);
mddev->degraded = raid5_calc_degraded(conf);
spin_unlock_irqrestore(&conf->device_lock, flags);
set_bit(MD_RECOVERY_INTR, &mddev->recovery);
set_bit(Blocked, &rdev->flags);
- set_bit(Faulty, &rdev->flags);
set_mask_bits(&mddev->sb_flags, 0,
BIT(MD_SB_CHANGE_DEVS) | BIT(MD_SB_CHANGE_PENDING));
pr_crit("md/raid:%s: Disk failure on %s, disabling device.\n"
generated by cgit v1.2.3 (git 2.39.0) at 2025-01-17 09:39:36 +0300