summaryrefslogtreecommitdiff
path: root/drivers/md
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/md')
-rw-r--r--drivers/md/bitmap.c8
-rw-r--r--drivers/md/bitmap.h3
-rw-r--r--drivers/md/dm-log-userspace-transfer.c2
-rw-r--r--drivers/md/dm-mpath.c4
-rw-r--r--drivers/md/dm-raid.c4
-rw-r--r--drivers/md/dm-thin.c16
-rw-r--r--drivers/md/linear.c9
-rw-r--r--drivers/md/md.c7
-rw-r--r--drivers/md/raid0.c27
-rw-r--r--drivers/md/raid1.c16
-rw-r--r--drivers/md/raid10.c6
-rw-r--r--drivers/md/raid5.c59
12 files changed, 103 insertions, 58 deletions
diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index 3d0dfa7a89a..17e2b472e16 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -539,9 +539,6 @@ static int bitmap_new_disk_sb(struct bitmap *bitmap)
bitmap->events_cleared = bitmap->mddev->events;
sb->events_cleared = cpu_to_le64(bitmap->mddev->events);
- bitmap->flags |= BITMAP_HOSTENDIAN;
- sb->version = cpu_to_le32(BITMAP_MAJOR_HOSTENDIAN);
-
kunmap_atomic(sb);
return 0;
@@ -1730,8 +1727,7 @@ int bitmap_create(struct mddev *mddev)
bitmap->chunkshift = (ffz(~mddev->bitmap_info.chunksize)
- BITMAP_BLOCK_SHIFT);
- /* now that chunksize and chunkshift are set, we can use these macros */
- chunks = (blocks + bitmap->chunkshift - 1) >>
+ chunks = (blocks + (1 << bitmap->chunkshift) - 1) >>
bitmap->chunkshift;
pages = (chunks + PAGE_COUNTER_RATIO - 1) / PAGE_COUNTER_RATIO;
@@ -1788,7 +1784,9 @@ int bitmap_load(struct mddev *mddev)
* re-add of a missing device */
start = mddev->recovery_cp;
+ mutex_lock(&mddev->bitmap_info.mutex);
err = bitmap_init_from_disk(bitmap, start);
+ mutex_unlock(&mddev->bitmap_info.mutex);
if (err)
goto out;
diff --git a/drivers/md/bitmap.h b/drivers/md/bitmap.h
index 55ca5aec84e..b44b0aba2d4 100644
--- a/drivers/md/bitmap.h
+++ b/drivers/md/bitmap.h
@@ -101,9 +101,6 @@ typedef __u16 bitmap_counter_t;
#define BITMAP_BLOCK_SHIFT 9
-/* how many blocks per chunk? (this is variable) */
-#define CHUNK_BLOCK_RATIO(bitmap) ((bitmap)->mddev->bitmap_info.chunksize >> BITMAP_BLOCK_SHIFT)
-
#endif
/*
diff --git a/drivers/md/dm-log-userspace-transfer.c b/drivers/md/dm-log-userspace-transfer.c
index 1f23e048f07..08d9a207259 100644
--- a/drivers/md/dm-log-userspace-transfer.c
+++ b/drivers/md/dm-log-userspace-transfer.c
@@ -134,7 +134,7 @@ static void cn_ulog_callback(struct cn_msg *msg, struct netlink_skb_parms *nsp)
{
struct dm_ulog_request *tfr = (struct dm_ulog_request *)(msg + 1);
- if (!cap_raised(current_cap(), CAP_SYS_ADMIN))
+ if (!capable(CAP_SYS_ADMIN))
return;
spin_lock(&receiving_list_lock);
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index 922a3385eea..754f38f8a69 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -718,8 +718,8 @@ static int parse_hw_handler(struct dm_arg_set *as, struct multipath *m)
return 0;
m->hw_handler_name = kstrdup(dm_shift_arg(as), GFP_KERNEL);
- request_module("scsi_dh_%s", m->hw_handler_name);
- if (scsi_dh_handler_exist(m->hw_handler_name) == 0) {
+ if (!try_then_request_module(scsi_dh_handler_exist(m->hw_handler_name),
+ "scsi_dh_%s", m->hw_handler_name)) {
ti->error = "unknown hardware handler type";
ret = -EINVAL;
goto fail;
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index b0ba52459ed..68965e66324 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -859,7 +859,7 @@ static int analyse_superblocks(struct dm_target *ti, struct raid_set *rs)
int ret;
unsigned redundancy = 0;
struct raid_dev *dev;
- struct md_rdev *rdev, *freshest;
+ struct md_rdev *rdev, *tmp, *freshest;
struct mddev *mddev = &rs->md;
switch (rs->raid_type->level) {
@@ -877,7 +877,7 @@ static int analyse_superblocks(struct dm_target *ti, struct raid_set *rs)
}
freshest = NULL;
- rdev_for_each(rdev, mddev) {
+ rdev_for_each_safe(rdev, tmp, mddev) {
if (!rdev->meta_bdev)
continue;
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index 213ae32a0fc..2fd87b544a9 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -279,8 +279,10 @@ static void __cell_release(struct cell *cell, struct bio_list *inmates)
hlist_del(&cell->list);
- bio_list_add(inmates, cell->holder);
- bio_list_merge(inmates, &cell->bios);
+ if (inmates) {
+ bio_list_add(inmates, cell->holder);
+ bio_list_merge(inmates, &cell->bios);
+ }
mempool_free(cell, prison->cell_pool);
}
@@ -303,9 +305,10 @@ static void cell_release(struct cell *cell, struct bio_list *bios)
*/
static void __cell_release_singleton(struct cell *cell, struct bio *bio)
{
- hlist_del(&cell->list);
BUG_ON(cell->holder != bio);
BUG_ON(!bio_list_empty(&cell->bios));
+
+ __cell_release(cell, NULL);
}
static void cell_release_singleton(struct cell *cell, struct bio *bio)
@@ -1177,6 +1180,7 @@ static void no_space(struct cell *cell)
static void process_discard(struct thin_c *tc, struct bio *bio)
{
int r;
+ unsigned long flags;
struct pool *pool = tc->pool;
struct cell *cell, *cell2;
struct cell_key key, key2;
@@ -1218,7 +1222,9 @@ static void process_discard(struct thin_c *tc, struct bio *bio)
m->bio = bio;
if (!ds_add_work(&pool->all_io_ds, &m->list)) {
+ spin_lock_irqsave(&pool->lock, flags);
list_add(&m->list, &pool->prepared_discards);
+ spin_unlock_irqrestore(&pool->lock, flags);
wake_worker(pool);
}
} else {
@@ -2626,8 +2632,10 @@ static int thin_endio(struct dm_target *ti,
if (h->all_io_entry) {
INIT_LIST_HEAD(&work);
ds_dec(h->all_io_entry, &work);
+ spin_lock_irqsave(&pool->lock, flags);
list_for_each_entry_safe(m, tmp, &work, list)
list_add(&m->list, &pool->prepared_discards);
+ spin_unlock_irqrestore(&pool->lock, flags);
}
mempool_free(h, pool->endio_hook_pool);
@@ -2759,6 +2767,6 @@ static void dm_thin_exit(void)
module_init(dm_thin_init);
module_exit(dm_thin_exit);
-MODULE_DESCRIPTION(DM_NAME "device-mapper thin provisioning target");
+MODULE_DESCRIPTION(DM_NAME " thin provisioning target");
MODULE_AUTHOR("Joe Thornber <dm-devel@redhat.com>");
MODULE_LICENSE("GPL");
diff --git a/drivers/md/linear.c b/drivers/md/linear.c
index b0fcc7d02ad..fa211d80fc0 100644
--- a/drivers/md/linear.c
+++ b/drivers/md/linear.c
@@ -198,6 +198,7 @@ out:
static int linear_run (struct mddev *mddev)
{
struct linear_conf *conf;
+ int ret;
if (md_check_no_bitmap(mddev))
return -EINVAL;
@@ -211,7 +212,13 @@ static int linear_run (struct mddev *mddev)
blk_queue_merge_bvec(mddev->queue, linear_mergeable_bvec);
mddev->queue->backing_dev_info.congested_fn = linear_congested;
mddev->queue->backing_dev_info.congested_data = mddev;
- return md_integrity_register(mddev);
+
+ ret = md_integrity_register(mddev);
+ if (ret) {
+ kfree(conf);
+ mddev->private = NULL;
+ }
+ return ret;
}
static int linear_add(struct mddev *mddev, struct md_rdev *rdev)
diff --git a/drivers/md/md.c b/drivers/md/md.c
index b572e1e386c..477eb2e180c 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -7560,14 +7560,14 @@ void md_check_recovery(struct mddev *mddev)
* any transients in the value of "sync_action".
*/
set_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
- clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
/* Clear some bits that don't mean anything, but
* might be left set
*/
clear_bit(MD_RECOVERY_INTR, &mddev->recovery);
clear_bit(MD_RECOVERY_DONE, &mddev->recovery);
- if (test_bit(MD_RECOVERY_FROZEN, &mddev->recovery))
+ if (!test_and_clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery) ||
+ test_bit(MD_RECOVERY_FROZEN, &mddev->recovery))
goto unlock;
/* no recovery is running.
* remove any failed drives, then
@@ -8140,7 +8140,8 @@ static int md_notify_reboot(struct notifier_block *this,
for_each_mddev(mddev, tmp) {
if (mddev_trylock(mddev)) {
- __md_stop_writes(mddev);
+ if (mddev->pers)
+ __md_stop_writes(mddev);
mddev->safemode = 2;
mddev_unlock(mddev);
}
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index 6f31f5596e0..de63a1fc373 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -407,6 +407,8 @@ static sector_t raid0_size(struct mddev *mddev, sector_t sectors, int raid_disks
return array_sectors;
}
+static int raid0_stop(struct mddev *mddev);
+
static int raid0_run(struct mddev *mddev)
{
struct r0conf *conf;
@@ -454,7 +456,12 @@ static int raid0_run(struct mddev *mddev)
blk_queue_merge_bvec(mddev->queue, raid0_mergeable_bvec);
dump_zones(mddev);
- return md_integrity_register(mddev);
+
+ ret = md_integrity_register(mddev);
+ if (ret)
+ raid0_stop(mddev);
+
+ return ret;
}
static int raid0_stop(struct mddev *mddev)
@@ -625,6 +632,7 @@ static void *raid0_takeover_raid10(struct mddev *mddev)
static void *raid0_takeover_raid1(struct mddev *mddev)
{
struct r0conf *priv_conf;
+ int chunksect;
/* Check layout:
* - (N - 1) mirror drives must be already faulty
@@ -635,10 +643,25 @@ static void *raid0_takeover_raid1(struct mddev *mddev)
return ERR_PTR(-EINVAL);
}
+ /*
+ * a raid1 doesn't have the notion of chunk size, so
+ * figure out the largest suitable size we can use.
+ */
+ chunksect = 64 * 2; /* 64K by default */
+
+ /* The array must be an exact multiple of chunksize */
+ while (chunksect && (mddev->array_sectors & (chunksect - 1)))
+ chunksect >>= 1;
+
+ if ((chunksect << 9) < PAGE_SIZE)
+ /* array size does not allow a suitable chunk size */
+ return ERR_PTR(-EINVAL);
+
/* Set new parameters */
mddev->new_level = 0;
mddev->new_layout = 0;
- mddev->new_chunk_sectors = 128; /* by default set chunk size to 64k */
+ mddev->new_chunk_sectors = chunksect;
+ mddev->chunk_sectors = chunksect;
mddev->delta_disks = 1 - mddev->raid_disks;
mddev->raid_disks = 1;
/* make sure it will be not marked as dirty */
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 4a40a200d76..15dd59b84e9 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1712,6 +1712,7 @@ static int process_checks(struct r1bio *r1_bio)
struct r1conf *conf = mddev->private;
int primary;
int i;
+ int vcnt;
for (primary = 0; primary < conf->raid_disks * 2; primary++)
if (r1_bio->bios[primary]->bi_end_io == end_sync_read &&
@@ -1721,9 +1722,9 @@ static int process_checks(struct r1bio *r1_bio)
break;
}
r1_bio->read_disk = primary;
+ vcnt = (r1_bio->sectors + PAGE_SIZE / 512 - 1) >> (PAGE_SHIFT - 9);
for (i = 0; i < conf->raid_disks * 2; i++) {
int j;
- int vcnt = r1_bio->sectors >> (PAGE_SHIFT- 9);
struct bio *pbio = r1_bio->bios[primary];
struct bio *sbio = r1_bio->bios[i];
int size;
@@ -1738,7 +1739,7 @@ static int process_checks(struct r1bio *r1_bio)
s = sbio->bi_io_vec[j].bv_page;
if (memcmp(page_address(p),
page_address(s),
- PAGE_SIZE))
+ sbio->bi_io_vec[j].bv_len))
break;
}
} else
@@ -2386,8 +2387,7 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int *skipp
int ok = 1;
for (i = 0 ; i < conf->raid_disks * 2 ; i++)
if (r1_bio->bios[i]->bi_end_io == end_sync_write) {
- struct md_rdev *rdev =
- rcu_dereference(conf->mirrors[i].rdev);
+ struct md_rdev *rdev = conf->mirrors[i].rdev;
ok = rdev_set_badblocks(rdev, sector_nr,
min_bad, 0
) && ok;
@@ -2636,11 +2636,13 @@ static struct r1conf *setup_conf(struct mddev *mddev)
return ERR_PTR(err);
}
+static int stop(struct mddev *mddev);
static int run(struct mddev *mddev)
{
struct r1conf *conf;
int i;
struct md_rdev *rdev;
+ int ret;
if (mddev->level != 1) {
printk(KERN_ERR "md/raid1:%s: raid level not set to mirroring (%d)\n",
@@ -2705,7 +2707,11 @@ static int run(struct mddev *mddev)
mddev->queue->backing_dev_info.congested_data = mddev;
blk_queue_merge_bvec(mddev->queue, raid1_mergeable_bvec);
}
- return md_integrity_register(mddev);
+
+ ret = md_integrity_register(mddev);
+ if (ret)
+ stop(mddev);
+ return ret;
}
static int stop(struct mddev *mddev)
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 3540316886f..c8dbb84d535 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -1788,6 +1788,7 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio)
struct r10conf *conf = mddev->private;
int i, first;
struct bio *tbio, *fbio;
+ int vcnt;
atomic_set(&r10_bio->remaining, 1);
@@ -1802,10 +1803,10 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio)
first = i;
fbio = r10_bio->devs[i].bio;
+ vcnt = (r10_bio->sectors + (PAGE_SIZE >> 9) - 1) >> (PAGE_SHIFT - 9);
/* now find blocks with errors */
for (i=0 ; i < conf->copies ; i++) {
int j, d;
- int vcnt = r10_bio->sectors >> (PAGE_SHIFT-9);
tbio = r10_bio->devs[i].bio;
@@ -1821,7 +1822,7 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio)
for (j = 0; j < vcnt; j++)
if (memcmp(page_address(fbio->bi_io_vec[j].bv_page),
page_address(tbio->bi_io_vec[j].bv_page),
- PAGE_SIZE))
+ fbio->bi_io_vec[j].bv_len))
break;
if (j == vcnt)
continue;
@@ -1871,7 +1872,6 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio)
*/
for (i = 0; i < conf->copies; i++) {
int j, d;
- int vcnt = r10_bio->sectors >> (PAGE_SHIFT-9);
tbio = r10_bio->devs[i].repl_bio;
if (!tbio || !tbio->bi_end_io)
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 23ac880bba9..f351422938e 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -2471,39 +2471,41 @@ handle_failed_sync(struct r5conf *conf, struct stripe_head *sh,
int abort = 0;
int i;
- md_done_sync(conf->mddev, STRIPE_SECTORS, 0);
clear_bit(STRIPE_SYNCING, &sh->state);
s->syncing = 0;
s->replacing = 0;
/* There is nothing more to do for sync/check/repair.
+ * Don't even need to abort as that is handled elsewhere
+ * if needed, and not always wanted e.g. if there is a known
+ * bad block here.
* For recover/replace we need to record a bad block on all
* non-sync devices, or abort the recovery
*/
- if (!test_bit(MD_RECOVERY_RECOVER, &conf->mddev->recovery))
- return;
- /* During recovery devices cannot be removed, so locking and
- * refcounting of rdevs is not needed
- */
- for (i = 0; i < conf->raid_disks; i++) {
- struct md_rdev *rdev = conf->disks[i].rdev;
- if (rdev
- && !test_bit(Faulty, &rdev->flags)
- && !test_bit(In_sync, &rdev->flags)
- && !rdev_set_badblocks(rdev, sh->sector,
- STRIPE_SECTORS, 0))
- abort = 1;
- rdev = conf->disks[i].replacement;
- if (rdev
- && !test_bit(Faulty, &rdev->flags)
- && !test_bit(In_sync, &rdev->flags)
- && !rdev_set_badblocks(rdev, sh->sector,
- STRIPE_SECTORS, 0))
- abort = 1;
- }
- if (abort) {
- conf->recovery_disabled = conf->mddev->recovery_disabled;
- set_bit(MD_RECOVERY_INTR, &conf->mddev->recovery);
+ if (test_bit(MD_RECOVERY_RECOVER, &conf->mddev->recovery)) {
+ /* During recovery devices cannot be removed, so
+ * locking and refcounting of rdevs is not needed
+ */
+ for (i = 0; i < conf->raid_disks; i++) {
+ struct md_rdev *rdev = conf->disks[i].rdev;
+ if (rdev
+ && !test_bit(Faulty, &rdev->flags)
+ && !test_bit(In_sync, &rdev->flags)
+ && !rdev_set_badblocks(rdev, sh->sector,
+ STRIPE_SECTORS, 0))
+ abort = 1;
+ rdev = conf->disks[i].replacement;
+ if (rdev
+ && !test_bit(Faulty, &rdev->flags)
+ && !test_bit(In_sync, &rdev->flags)
+ && !rdev_set_badblocks(rdev, sh->sector,
+ STRIPE_SECTORS, 0))
+ abort = 1;
+ }
+ if (abort)
+ conf->recovery_disabled =
+ conf->mddev->recovery_disabled;
}
+ md_done_sync(conf->mddev, STRIPE_SECTORS, !abort);
}
static int want_replace(struct stripe_head *sh, int disk_idx)
@@ -3203,7 +3205,8 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s)
/* Not in-sync */;
else if (is_bad) {
/* also not in-sync */
- if (!test_bit(WriteErrorSeen, &rdev->flags)) {
+ if (!test_bit(WriteErrorSeen, &rdev->flags) &&
+ test_bit(R5_UPTODATE, &dev->flags)) {
/* treat as in-sync, but with a read error
* which we can now try to correct
*/
@@ -3276,12 +3279,14 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s)
/* If there is a failed device being replaced,
* we must be recovering.
* else if we are after recovery_cp, we must be syncing
+ * else if MD_RECOVERY_REQUESTED is set, we also are syncing.
* else we can only be replacing
* sync and recovery both need to read all devices, and so
* use the same flag.
*/
if (do_recovery ||
- sh->sector >= conf->mddev->recovery_cp)
+ sh->sector >= conf->mddev->recovery_cp ||
+ test_bit(MD_RECOVERY_REQUESTED, &(conf->mddev->recovery)))
s->syncing = 1;
else
s->replacing = 1;
generated by cgit v1.2.3-70-g09d2 (git 2.51.2) at 2025-11-03 09:25:40 +0000