summaryrefslogtreecommitdiffstats
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/debug.c10
-rw-r--r--drivers/md/bcache/journal.c2
-rw-r--r--drivers/md/bcache/request.c6
-rw-r--r--drivers/md/bcache/super.c3
-rw-r--r--drivers/md/bcache/sysfs.c2
-rw-r--r--drivers/md/dm-bufio.c9
-rw-r--r--drivers/md/dm-cache-target.c9
-rw-r--r--drivers/md/dm-clone-target.c9
-rw-r--r--drivers/md/dm-integrity.c7
-rw-r--r--drivers/md/dm-io.c2
-rw-r--r--drivers/md/dm-log-writes.c3
-rw-r--r--drivers/md/dm-ps-historical-service-time.c11
-rw-r--r--drivers/md/dm-raid.c9
-rw-r--r--drivers/md/dm-table.c25
-rw-r--r--drivers/md/dm-thin.c15
-rw-r--r--drivers/md/dm-zone.c49
-rw-r--r--drivers/md/dm-zoned-target.c2
-rw-r--r--drivers/md/dm.c21
-rw-r--r--drivers/md/md-bitmap.c45
-rw-r--r--drivers/md/md-cluster.c2
-rw-r--r--drivers/md/md-linear.c11
-rw-r--r--drivers/md/md.c67
-rw-r--r--drivers/md/md.h62
-rw-r--r--drivers/md/raid0.c38
-rw-r--r--drivers/md/raid1.c73
-rw-r--r--drivers/md/raid10.c81
-rw-r--r--drivers/md/raid5-cache.c8
-rw-r--r--drivers/md/raid5-ppl.c13
-rw-r--r--drivers/md/raid5.c241
-rw-r--r--drivers/md/raid5.h23
31 files changed, 440 insertions, 420 deletions
diff --git a/drivers/md/bcache/alloc.c b/drivers/md/bcache/alloc.c
index 097577ae3c47..ce13c272c387 100644
--- a/drivers/md/bcache/alloc.c
+++ b/drivers/md/bcache/alloc.c
@@ -336,7 +336,7 @@ static int bch_allocator_thread(void *arg)
mutex_unlock(&ca->set->bucket_lock);
blkdev_issue_discard(ca->bdev,
bucket_to_sector(ca->set, bucket),
- ca->sb.bucket_size, GFP_KERNEL, 0);
+ ca->sb.bucket_size, GFP_KERNEL);
mutex_lock(&ca->set->bucket_lock);
}
diff --git a/drivers/md/bcache/debug.c b/drivers/md/bcache/debug.c
index 6230dfdd9286..7510d1c983a5 100644
--- a/drivers/md/bcache/debug.c
+++ b/drivers/md/bcache/debug.c
@@ -107,15 +107,16 @@ void bch_btree_verify(struct btree *b)
void bch_data_verify(struct cached_dev *dc, struct bio *bio)
{
+ unsigned int nr_segs = bio_segments(bio);
struct bio *check;
struct bio_vec bv, cbv;
struct bvec_iter iter, citer = { 0 };
- check = bio_kmalloc(GFP_NOIO, bio_segments(bio));
+ check = bio_kmalloc(nr_segs, GFP_NOIO);
if (!check)
return;
- bio_set_dev(check, bio->bi_bdev);
- check->bi_opf = REQ_OP_READ;
+ bio_init(check, bio->bi_bdev, check->bi_inline_vecs, nr_segs,
+ REQ_OP_READ);
check->bi_iter.bi_sector = bio->bi_iter.bi_sector;
check->bi_iter.bi_size = bio->bi_iter.bi_size;
@@ -146,7 +147,8 @@ void bch_data_verify(struct cached_dev *dc, struct bio *bio)
bio_free_pages(check);
out_put:
- bio_put(check);
+ bio_uninit(check);
+ kfree(check);
}
#endif
diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c
index 7c2ca52ca3e4..df5347ea450b 100644
--- a/drivers/md/bcache/journal.c
+++ b/drivers/md/bcache/journal.c
@@ -771,12 +771,12 @@ static void journal_write_unlocked(struct closure *cl)
bio_reset(bio, ca->bdev, REQ_OP_WRITE |
REQ_SYNC | REQ_META | REQ_PREFLUSH | REQ_FUA);
- bch_bio_map(bio, w->data);
bio->bi_iter.bi_sector = PTR_OFFSET(k, i);
bio->bi_iter.bi_size = sectors << 9;
bio->bi_end_io = journal_write_endio;
bio->bi_private = w;
+ bch_bio_map(bio, w->data);
trace_bcache_journal_write(bio, w->data->keys);
bio_list_add(&list, bio);
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index fdd0194f84dd..9c5dde73da88 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -685,7 +685,7 @@ static void do_bio_hook(struct search *s,
{
struct bio *bio = &s->bio.bio;
- bio_init_clone(bio->bi_bdev, bio, orig_bio, GFP_NOIO);
+ bio_init_clone(orig_bio->bi_bdev, bio, orig_bio, GFP_NOIO);
/*
* bi_end_io can be set separately somewhere else, e.g. the
* variants in,
@@ -1005,7 +1005,7 @@ static void cached_dev_write(struct cached_dev *dc, struct search *s)
bio_get(s->iop.bio);
if (bio_op(bio) == REQ_OP_DISCARD &&
- !blk_queue_discard(bdev_get_queue(dc->bdev)))
+ !bdev_max_discard_sectors(dc->bdev))
goto insert_data;
/* I/O request sent to backing device */
@@ -1115,7 +1115,7 @@ static void detached_dev_do_request(struct bcache_device *d, struct bio *bio,
bio->bi_private = ddip;
if ((bio_op(bio) == REQ_OP_DISCARD) &&
- !blk_queue_discard(bdev_get_queue(dc->bdev)))
+ !bdev_max_discard_sectors(dc->bdev))
bio->bi_end_io(bio);
else
submit_bio_noacct(bio);
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index bf3de149d3c9..2f49e31142f6 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -973,7 +973,6 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size,
blk_queue_flag_set(QUEUE_FLAG_NONROT, d->disk->queue);
blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, d->disk->queue);
- blk_queue_flag_set(QUEUE_FLAG_DISCARD, d->disk->queue);
blk_queue_write_cache(q, true, true);
@@ -2350,7 +2349,7 @@ static int register_cache(struct cache_sb *sb, struct cache_sb_disk *sb_disk,
ca->bdev->bd_holder = ca;
ca->sb_disk = sb_disk;
- if (blk_queue_discard(bdev_get_queue(bdev)))
+ if (bdev_max_discard_sectors((bdev)))
ca->discard = CACHE_DISCARD(&ca->sb);
ret = cache_alloc(ca);
diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c
index d1029d71ff3b..c6f677059214 100644
--- a/drivers/md/bcache/sysfs.c
+++ b/drivers/md/bcache/sysfs.c
@@ -1151,7 +1151,7 @@ STORE(__bch_cache)
if (attr == &sysfs_discard) {
bool v = strtoul_or_return(buf);
- if (blk_queue_discard(bdev_get_queue(ca->bdev)))
+ if (bdev_max_discard_sectors(ca->bdev))
ca->discard = v;
if (v != CACHE_DISCARD(&ca->sb)) {
diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index e9cbc70d5a0e..5ffa1dcf84cf 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -611,7 +611,8 @@ static void bio_complete(struct bio *bio)
{
struct dm_buffer *b = bio->bi_private;
blk_status_t status = bio->bi_status;
- bio_put(bio);
+ bio_uninit(bio);
+ kfree(bio);
b->end_io(b, status);
}
@@ -626,16 +627,14 @@ static void use_bio(struct dm_buffer *b, int rw, sector_t sector,
if (unlikely(b->c->sectors_per_block_bits < PAGE_SHIFT - SECTOR_SHIFT))
vec_size += 2;
- bio = bio_kmalloc(GFP_NOWAIT | __GFP_NORETRY | __GFP_NOWARN, vec_size);
+ bio = bio_kmalloc(vec_size, GFP_NOWAIT | __GFP_NORETRY | __GFP_NOWARN);
if (!bio) {
dmio:
use_dmio(b, rw, sector, n_sectors, offset);
return;
}
-
+ bio_init(bio, b->c->bdev, bio->bi_inline_vecs, vec_size, rw);
bio->bi_iter.bi_sector = sector;
- bio_set_dev(bio, b->c->bdev);
- bio_set_op_attrs(bio, rw, 0);
bio->bi_end_io = bio_complete;
bio->bi_private = b;
diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index 780a61bc6cc0..28c5de8eca4a 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -3329,13 +3329,6 @@ static int cache_iterate_devices(struct dm_target *ti,
return r;
}
-static bool origin_dev_supports_discard(struct block_device *origin_bdev)
-{
- struct request_queue *q = bdev_get_queue(origin_bdev);
-
- return blk_queue_discard(q);
-}
-
/*
* If discard_passdown was enabled verify that the origin device
* supports discards. Disable discard_passdown if not.
@@ -3349,7 +3342,7 @@ static void disable_passdown_if_not_supported(struct cache *cache)
if (!cache->features.discard_passdown)
return;
- if (!origin_dev_supports_discard(origin_bdev))
+ if (!bdev_max_discard_sectors(origin_bdev))
reason = "discard unsupported";
else if (origin_limits->max_discard_sectors < cache->sectors_per_block)
diff --git a/drivers/md/dm-clone-target.c b/drivers/md/dm-clone-target.c
index 128316a73d01..811b0a5379d0 100644
--- a/drivers/md/dm-clone-target.c
+++ b/drivers/md/dm-clone-target.c
@@ -2016,13 +2016,6 @@ static void clone_resume(struct dm_target *ti)
do_waker(&clone->waker.work);
}
-static bool bdev_supports_discards(struct block_device *bdev)
-{
- struct request_queue *q = bdev_get_queue(bdev);
-
- return (q && blk_queue_discard(q));
-}
-
/*
* If discard_passdown was enabled verify that the destination device supports
* discards. Disable discard_passdown if not.
@@ -2036,7 +2029,7 @@ static void disable_passdown_if_not_supported(struct clone *clone)
if (!test_bit(DM_CLONE_DISCARD_PASSDOWN, &clone->flags))
return;
- if (!bdev_supports_discards(dest_dev))
+ if (!bdev_max_discard_sectors(dest_dev))
reason = "discard unsupported";
else if (dest_limits->max_discard_sectors < clone->region_size)
reason = "max discard sectors smaller than a region";
diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c
index ad2d5faa2ebb..36ae30b73a6e 100644
--- a/drivers/md/dm-integrity.c
+++ b/drivers/md/dm-integrity.c
@@ -4399,6 +4399,7 @@ try_smaller_buffer:
}
if (ic->internal_hash) {
+ size_t recalc_tags_size;
ic->recalc_wq = alloc_workqueue("dm-integrity-recalc", WQ_MEM_RECLAIM, 1);
if (!ic->recalc_wq ) {
ti->error = "Cannot allocate workqueue";
@@ -4412,8 +4413,10 @@ try_smaller_buffer:
r = -ENOMEM;
goto bad;
}
- ic->recalc_tags = kvmalloc_array(RECALC_SECTORS >> ic->sb->log2_sectors_per_block,
- ic->tag_size, GFP_KERNEL);
+ recalc_tags_size = (RECALC_SECTORS >> ic->sb->log2_sectors_per_block) * ic->tag_size;
+ if (crypto_shash_digestsize(ic->internal_hash) > ic->tag_size)
+ recalc_tags_size += crypto_shash_digestsize(ic->internal_hash) - ic->tag_size;
+ ic->recalc_tags = kvmalloc(recalc_tags_size, GFP_KERNEL);
if (!ic->recalc_tags) {
ti->error = "Cannot allocate tags for recalculating";
r = -ENOMEM;
diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c
index 5762366333a2..e4b95eaeec8c 100644
--- a/drivers/md/dm-io.c
+++ b/drivers/md/dm-io.c
@@ -311,7 +311,7 @@ static void do_region(int op, int op_flags, unsigned region,
* Reject unsupported discard and write same requests.
*/
if (op == REQ_OP_DISCARD)
- special_cmd_max_sectors = q->limits.max_discard_sectors;
+ special_cmd_max_sectors = bdev_max_discard_sectors(where->bdev);
else if (op == REQ_OP_WRITE_ZEROES)
special_cmd_max_sectors = q->limits.max_write_zeroes_sectors;
if ((op == REQ_OP_DISCARD || op == REQ_OP_WRITE_ZEROES) &&
diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c
index c9d036d6bb2e..e194226c89e5 100644
--- a/drivers/md/dm-log-writes.c
+++ b/drivers/md/dm-log-writes.c
@@ -866,9 +866,8 @@ static int log_writes_message(struct dm_target *ti, unsigned argc, char **argv,
static void log_writes_io_hints(struct dm_target *ti, struct queue_limits *limits)
{
struct log_writes_c *lc = ti->private;
- struct request_queue *q = bdev_get_queue(lc->dev->bdev);
- if (!q || !blk_queue_discard(q)) {
+ if (!bdev_max_discard_sectors(lc->dev->bdev)) {
lc->device_supports_discard = false;
limits->discard_granularity = lc->sectorsize;
limits->max_discard_sectors = (UINT_MAX >> SECTOR_SHIFT);
diff --git a/drivers/md/dm-ps-historical-service-time.c b/drivers/md/dm-ps-historical-service-time.c
index 875bca30a0dd..82f2a06153dc 100644
--- a/drivers/md/dm-ps-historical-service-time.c
+++ b/drivers/md/dm-ps-historical-service-time.c
@@ -27,7 +27,6 @@
#include <linux/blkdev.h>
#include <linux/slab.h>
#include <linux/module.h>
-#include <linux/sched/clock.h>
#define DM_MSG_PREFIX "multipath historical-service-time"
@@ -433,7 +432,7 @@ static struct dm_path *hst_select_path(struct path_selector *ps,
{
struct selector *s = ps->context;
struct path_info *pi = NULL, *best = NULL;
- u64 time_now = sched_clock();
+ u64 time_now = ktime_get_ns();
struct dm_path *ret = NULL;
unsigned long flags;
@@ -474,7 +473,7 @@ static int hst_start_io(struct path_selector *ps, struct dm_path *path,
static u64 path_service_time(struct path_info *pi, u64 start_time)
{
- u64 sched_now = ktime_get_ns();
+ u64 now = ktime_get_ns();
/* if a previous disk request has finished after this IO was
* sent to the hardware, pretend the submission happened
@@ -483,11 +482,11 @@ static u64 path_service_time(struct path_info *pi, u64 start_time)
if (time_after64(pi->last_finish, start_time))
start_time = pi->last_finish;
- pi->last_finish = sched_now;
- if (time_before64(sched_now, start_time))
+ pi->last_finish = now;
+ if (time_before64(now, start_time))
return 0;
- return sched_now - start_time;
+ return now - start_time;
}
static int hst_end_io(struct path_selector *ps, struct dm_path *path,
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 2b26435a6946..9526ccbedafb 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -2963,13 +2963,8 @@ static void configure_discard_support(struct raid_set *rs)
raid456 = rs_is_raid456(rs);
for (i = 0; i < rs->raid_disks; i++) {
- struct request_queue *q;
-
- if (!rs->dev[i].rdev.bdev)
- continue;
-
- q = bdev_get_queue(rs->dev[i].rdev.bdev);
- if (!q || !blk_queue_discard(q))
+ if (!rs->dev[i].rdev.bdev ||
+ !bdev_max_discard_sectors(rs->dev[i].rdev.bdev))
return;
if (raid456) {
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 03541cfc2317..e7d42f6335a2 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -1820,9 +1820,7 @@ static int device_dax_write_cache_enabled(struct dm_target *ti,
static int device_is_rotational(struct dm_target *ti, struct dm_dev *dev,
sector_t start, sector_t len, void *data)
{
- struct request_queue *q = bdev_get_queue(dev->bdev);
-
- return !blk_queue_nonrot(q);
+ return !bdev_nonrot(dev->bdev);
}
static int device_is_not_random(struct dm_target *ti, struct dm_dev *dev,
@@ -1890,9 +1888,7 @@ static bool dm_table_supports_nowait(struct dm_table *t)
static int device_not_discard_capable(struct dm_target *ti, struct dm_dev *dev,
sector_t start, sector_t len, void *data)
{
- struct request_queue *q = bdev_get_queue(dev->bdev);
-
- return !blk_queue_discard(q);
+ return !bdev_max_discard_sectors(dev->bdev);
}
static bool dm_table_supports_discards(struct dm_table *t)
@@ -1924,9 +1920,7 @@ static int device_not_secure_erase_capable(struct dm_target *ti,
struct dm_dev *dev, sector_t start,
sector_t len, void *data)
{
- struct request_queue *q = bdev_get_queue(dev->bdev);
-
- return !blk_queue_secure_erase(q);
+ return !bdev_max_secure_erase_sectors(dev->bdev);
}
static bool dm_table_supports_secure_erase(struct dm_table *t)
@@ -1952,9 +1946,7 @@ static int device_requires_stable_pages(struct dm_target *ti,
struct dm_dev *dev, sector_t start,
sector_t len, void *data)
{
- struct request_queue *q = bdev_get_queue(dev->bdev);
-
- return blk_queue_stable_writes(q);
+ return bdev_stable_writes(dev->bdev);
}
int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
@@ -1974,18 +1966,15 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
blk_queue_flag_clear(QUEUE_FLAG_NOWAIT, q);
if (!dm_table_supports_discards(t)) {
- blk_queue_flag_clear(QUEUE_FLAG_DISCARD, q);
- /* Must also clear discard limits... */
q->limits.max_discard_sectors = 0;
q->limits.max_hw_discard_sectors = 0;
q->limits.discard_granularity = 0;
q->limits.discard_alignment = 0;
q->limits.discard_misaligned = 0;
- } else
- blk_queue_flag_set(QUEUE_FLAG_DISCARD, q);
+ }
- if (dm_table_supports_secure_erase(t))
- blk_queue_flag_set(QUEUE_FLAG_SECERASE, q);
+ if (!dm_table_supports_secure_erase(t))
+ q->limits.max_secure_erase_sectors = 0;
if (dm_table_supports_flush(t, (1UL << QUEUE_FLAG_WC))) {
wc = true;
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index 4d25d0e27031..84c083f76673 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -398,8 +398,8 @@ static int issue_discard(struct discard_op *op, dm_block_t data_b, dm_block_t da
sector_t s = block_to_sectors(tc->pool, data_b);
sector_t len = block_to_sectors(tc->pool, data_e - data_b);
- return __blkdev_issue_discard(tc->pool_dev->bdev, s, len,
- GFP_NOWAIT, 0, &op->bio);
+ return __blkdev_issue_discard(tc->pool_dev->bdev, s, len, GFP_NOWAIT,
+ &op->bio);
}
static void end_discard(struct discard_op *op, int r)
@@ -2802,13 +2802,6 @@ static void requeue_bios(struct pool *pool)
/*----------------------------------------------------------------
* Binding of control targets to a pool object
*--------------------------------------------------------------*/
-static bool data_dev_supports_discard(struct pool_c *pt)
-{
- struct request_queue *q = bdev_get_queue(pt->data_dev->bdev);
-
- return blk_queue_discard(q);
-}
-
static bool is_factor(sector_t block_size, uint32_t n)
{
return !sector_div(block_size, n);
@@ -2828,7 +2821,7 @@ static void disable_passdown_if_not_supported(struct pool_c *pt)
if (!pt->adjusted_pf.discard_passdown)
return;
- if (!data_dev_supports_discard(pt))
+ if (!bdev_max_discard_sectors(pt->data_dev->bdev))
reason = "discard unsupported";
else if (data_limits->max_discard_sectors < pool->sectors_per_block)
@@ -4057,8 +4050,6 @@ static void pool_io_hints(struct dm_target *ti, struct queue_limits *limits)
/*
* Must explicitly disallow stacking discard limits otherwise the
* block layer will stack them if pool's data device has support.
- * QUEUE_FLAG_DISCARD wouldn't be set but there is no way for the
- * user to see that, so make sure to set all discard limits to 0.
*/
limits->discard_granularity = 0;
return;
diff --git a/drivers/md/dm-zone.c b/drivers/md/dm-zone.c
index c1ca9be4b79e..57daa86c19cf 100644
--- a/drivers/md/dm-zone.c
+++ b/drivers/md/dm-zone.c
@@ -360,16 +360,20 @@ static int dm_update_zone_wp_offset(struct mapped_device *md, unsigned int zno,
return 0;
}
+struct orig_bio_details {
+ unsigned int op;
+ unsigned int nr_sectors;
+};
+
/*
* First phase of BIO mapping for targets with zone append emulation:
* check all BIO that change a zone writer pointer and change zone
* append operations into regular write operations.
*/
static bool dm_zone_map_bio_begin(struct mapped_device *md,
- struct bio *orig_bio, struct bio *clone)
+ unsigned int zno, struct bio *clone)
{
sector_t zsectors = blk_queue_zone_sectors(md->queue);
- unsigned int zno = bio_zone_no(orig_bio);
unsigned int zwp_offset = READ_ONCE(md->zwp_offset[zno]);
/*
@@ -384,7 +388,7 @@ static bool dm_zone_map_bio_begin(struct mapped_device *md,
WRITE_ONCE(md->zwp_offset[zno], zwp_offset);
}
- switch (bio_op(orig_bio)) {
+ switch (bio_op(clone)) {
case REQ_OP_ZONE_RESET:
case REQ_OP_ZONE_FINISH:
return true;
@@ -401,9 +405,8 @@ static bool dm_zone_map_bio_begin(struct mapped_device *md,
* target zone.
*/
clone->bi_opf = REQ_OP_WRITE | REQ_NOMERGE |
- (orig_bio->bi_opf & (~REQ_OP_MASK));
- clone->bi_iter.bi_sector =
- orig_bio->bi_iter.bi_sector + zwp_offset;
+ (clone->bi_opf & (~REQ_OP_MASK));
+ clone->bi_iter.bi_sector += zwp_offset;
break;
default:
DMWARN_LIMIT("Invalid BIO operation");
@@ -423,11 +426,10 @@ static bool dm_zone_map_bio_begin(struct mapped_device *md,
* data written to a zone. Note that at this point, the remapped clone BIO
* may already have completed, so we do not touch it.
*/
-static blk_status_t dm_zone_map_bio_end(struct mapped_device *md,
- struct bio *orig_bio,
+static blk_status_t dm_zone_map_bio_end(struct mapped_device *md, unsigned int zno,
+ struct orig_bio_details *orig_bio_details,
unsigned int nr_sectors)
{
- unsigned int zno = bio_zone_no(orig_bio);
unsigned int zwp_offset = READ_ONCE(md->zwp_offset[zno]);
/* The clone BIO may already have been completed and failed */
@@ -435,7 +437,7 @@ static blk_status_t dm_zone_map_bio_end(struct mapped_device *md,
return BLK_STS_IOERR;
/* Update the zone wp offset */
- switch (bio_op(orig_bio)) {
+ switch (orig_bio_details->op) {
case REQ_OP_ZONE_RESET:
WRITE_ONCE(md->zwp_offset[zno], 0);
return BLK_STS_OK;
@@ -452,7 +454,7 @@ static blk_status_t dm_zone_map_bio_end(struct mapped_device *md,
* Check that the target did not truncate the write operation
* emulating a zone append.
*/
- if (nr_sectors != bio_sectors(orig_bio)) {
+ if (nr_sectors != orig_bio_details->nr_sectors) {
DMWARN_LIMIT("Truncated write for zone append");
return BLK_STS_IOERR;
}
@@ -488,7 +490,7 @@ static inline void dm_zone_unlock(struct request_queue *q,
bio_clear_flag(clone, BIO_ZONE_WRITE_LOCKED);
}
-static bool dm_need_zone_wp_tracking(struct bio *orig_bio)
+static bool dm_need_zone_wp_tracking(struct bio *bio)
{
/*
* Special processing is not needed for operations that do not need the
@@ -496,15 +498,15 @@ static bool dm_need_zone_wp_tracking(struct bio *orig_bio)
* zones and all operations that do not modify directly a sequential
* zone write pointer.
*/
- if (op_is_flush(orig_bio->bi_opf) && !bio_sectors(orig_bio))
+ if (op_is_flush(bio->bi_opf) && !bio_sectors(bio))
return false;
- switch (bio_op(orig_bio)) {
+ switch (bio_op(bio)) {
case REQ_OP_WRITE_ZEROES:
case REQ_OP_WRITE:
case REQ_OP_ZONE_RESET:
case REQ_OP_ZONE_FINISH:
case REQ_OP_ZONE_APPEND:
- return bio_zone_is_seq(orig_bio);
+ return bio_zone_is_seq(bio);
default:
return false;
}
@@ -519,8 +521,8 @@ int dm_zone_map_bio(struct dm_target_io *tio)
struct dm_target *ti = tio->ti;
struct mapped_device *md = io->md;
struct request_queue *q = md->queue;
- struct bio *orig_bio = io->orig_bio;
struct bio *clone = &tio->clone;
+ struct orig_bio_details orig_bio_details;
unsigned int zno;
blk_status_t sts;
int r;
@@ -529,18 +531,21 @@ int dm_zone_map_bio(struct dm_target_io *tio)
* IOs that do not change a zone write pointer do not need
* any additional special processing.
*/
- if (!dm_need_zone_wp_tracking(orig_bio))
+ if (!dm_need_zone_wp_tracking(clone))
return ti->type->map(ti, clone);
/* Lock the target zone */
- zno = bio_zone_no(orig_bio);
+ zno = bio_zone_no(clone);
dm_zone_lock(q, zno, clone);
+ orig_bio_details.nr_sectors = bio_sectors(clone);
+ orig_bio_details.op = bio_op(clone);
+
/*
* Check that the bio and the target zone write pointer offset are
* both valid, and if the bio is a zone append, remap it to a write.
*/
- if (!dm_zone_map_bio_begin(md, orig_bio, clone)) {
+ if (!dm_zone_map_bio_begin(md, zno, clone)) {
dm_zone_unlock(q, zno, clone);
return DM_MAPIO_KILL;
}
@@ -560,7 +565,8 @@ int dm_zone_map_bio(struct dm_target_io *tio)
* The target submitted the clone BIO. The target zone will
* be unlocked on completion of the clone.
*/
- sts = dm_zone_map_bio_end(md, orig_bio, *tio->len_ptr);
+ sts = dm_zone_map_bio_end(md, zno, &orig_bio_details,
+ *tio->len_ptr);
break;
case DM_MAPIO_REMAPPED:
/*
@@ -568,7 +574,8 @@ int dm_zone_map_bio(struct dm_target_io *tio)
* unlock the target zone here as the clone will not be
* submitted.
*/
- sts = dm_zone_map_bio_end(md, orig_bio, *tio->len_ptr);
+ sts = dm_zone_map_bio_end(md, zno, &orig_bio_details,
+ *tio->len_ptr);
if (sts != BLK_STS_OK)
dm_zone_unlock(q, zno, clone);
break;
diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c
index cac295cc8840..0ec5d8b9b1a4 100644
--- a/drivers/md/dm-zoned-target.c
+++ b/drivers/md/dm-zoned-target.c
@@ -1001,7 +1001,7 @@ static void dmz_io_hints(struct dm_target *ti, struct queue_limits *limits)
blk_limits_io_min(limits, DMZ_BLOCK_SIZE);
blk_limits_io_opt(limits, DMZ_BLOCK_SIZE);
- limits->discard_alignment = DMZ_BLOCK_SIZE;
+ limits->discard_alignment = 0;
limits->discard_granularity = DMZ_BLOCK_SIZE;
limits->max_discard_sectors = chunk_sectors;
limits->max_hw_discard_sectors = chunk_sectors;
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 3c5fad7c4ee6..39081338ca61 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -955,7 +955,6 @@ void disable_discard(struct mapped_device *md)
/* device doesn't really support DISCARD, disable it */
limits->max_discard_sectors = 0;
- blk_queue_flag_clear(QUEUE_FLAG_DISCARD, md->queue);
}
void disable_write_zeroes(struct mapped_device *md)
@@ -982,7 +981,7 @@ static void clone_endio(struct bio *bio)
if (unlikely(error == BLK_STS_TARGET)) {
if (bio_op(bio) == REQ_OP_DISCARD &&
- !q->limits.max_discard_sectors)
+ !bdev_max_discard_sectors(bio->bi_bdev))
disable_discard(md);
else if (bio_op(bio) == REQ_OP_WRITE_ZEROES &&
!q->limits.max_write_zeroes_sectors)
@@ -1323,8 +1322,7 @@ static void __map_bio(struct bio *clone)
}
static void alloc_multiple_bios(struct bio_list *blist, struct clone_info *ci,
- struct dm_target *ti, unsigned num_bios,
- unsigned *len)
+ struct dm_target *ti, unsigned num_bios)
{
struct bio *bio;
int try;
@@ -1335,7 +1333,7 @@ static void alloc_multiple_bios(struct bio_list *blist, struct clone_info *ci,
if (try)
mutex_lock(&ci->io->md->table_devices_lock);
for (bio_nr = 0; bio_nr < num_bios; bio_nr++) {
- bio = alloc_tio(ci, ti, bio_nr, len,
+ bio = alloc_tio(ci, ti, bio_nr, NULL,
try ? GFP_NOIO : GFP_NOWAIT);
if (!bio)
break;
@@ -1363,11 +1361,11 @@ static void __send_duplicate_bios(struct clone_info *ci, struct dm_target *ti,
break;
case 1:
clone = alloc_tio(ci, ti, 0, len, GFP_NOIO);
- dm_tio_set_flag(clone_to_tio(clone), DM_TIO_IS_DUPLICATE_BIO);
__map_bio(clone);
break;
default:
- alloc_multiple_bios(&blist, ci, ti, num_bios, len);
+ /* dm_accept_partial_bio() is not supported with shared tio->len_ptr */
+ alloc_multiple_bios(&blist, ci, ti, num_bios);
while ((clone = bio_list_pop(&blist))) {
dm_tio_set_flag(clone_to_tio(clone), DM_TIO_IS_DUPLICATE_BIO);
__map_bio(clone);
@@ -1392,6 +1390,7 @@ static void __send_empty_flush(struct clone_info *ci)
ci->bio = &flush_bio;
ci->sector_count = 0;
+ ci->io->tio.clone.bi_iter.bi_size = 0;
while ((ti = dm_table_get_target(ci->map, target_nr++)))
__send_duplicate_bios(ci, ti, ti->num_flush_bios, NULL);
@@ -1407,14 +1406,10 @@ static void __send_changing_extent_only(struct clone_info *ci, struct dm_target
len = min_t(sector_t, ci->sector_count,
max_io_len_target_boundary(ti, dm_target_offset(ti, ci->sector)));
- /*
- * dm_accept_partial_bio cannot be used with duplicate bios,
- * so update clone_info cursor before __send_duplicate_bios().
- */
+ __send_duplicate_bios(ci, ti, num_bios, &len);
+
ci->sector += len;
ci->sector_count -= len;
-
- __send_duplicate_bios(ci, ti, num_bios, &len);
}
static bool is_abnormal_io(struct bio *bio)
diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c
index bfd6026d7809..d87f674ab762 100644
--- a/drivers/md/md-bitmap.c
+++ b/drivers/md/md-bitmap.c
@@ -639,14 +639,6 @@ re_read:
daemon_sleep = le32_to_cpu(sb->daemon_sleep) * HZ;
write_behind = le32_to_cpu(sb->write_behind);
sectors_reserved = le32_to_cpu(sb->sectors_reserved);
- /* Setup nodes/clustername only if bitmap version is
- * cluster-compatible
- */
- if (sb->version == cpu_to_le32(BITMAP_MAJOR_CLUSTERED)) {
- nodes = le32_to_cpu(sb->nodes);
- strlcpy(bitmap->mddev->bitmap_info.cluster_name,
- sb->cluster_name, 64);
- }
/* verify that the bitmap-specific fields are valid */
if (sb->magic != cpu_to_le32(BITMAP_MAGIC))
@@ -668,6 +660,16 @@ re_read:
goto out;
}
+ /*
+ * Setup nodes/clustername only if bitmap version is
+ * cluster-compatible
+ */
+ if (sb->version == cpu_to_le32(BITMAP_MAJOR_CLUSTERED)) {
+ nodes = le32_to_cpu(sb->nodes);
+ strscpy(bitmap->mddev->bitmap_info.cluster_name,
+ sb->cluster_name, 64);
+ }
+
/* keep the array size field of the bitmap superblock up to date */
sb->sync_size = cpu_to_le64(bitmap->mddev->resync_max_sectors);
@@ -695,14 +697,13 @@ re_read:
if (le32_to_cpu(sb->version) == BITMAP_MAJOR_HOSTENDIAN)
set_bit(BITMAP_HOSTENDIAN, &bitmap->flags);
bitmap->events_cleared = le64_to_cpu(sb->events_cleared);
- strlcpy(bitmap->mddev->bitmap_info.cluster_name, sb->cluster_name, 64);
err = 0;
out:
kunmap_atomic(sb);
- /* Assigning chunksize is required for "re_read" */
- bitmap->mddev->bitmap_info.chunksize = chunksize;
if (err == 0 && nodes && (bitmap->cluster_slot < 0)) {
+ /* Assigning chunksize is required for "re_read" */
+ bitmap->mddev->bitmap_info.chunksize = chunksize;
err = md_setup_cluster(bitmap->mddev, nodes);
if (err) {
pr_warn("%s: Could not setup cluster service (%d)\n",
@@ -713,18 +714,18 @@ out:
goto re_read;
}
-
out_no_sb:
- if (test_bit(BITMAP_STALE, &bitmap->flags))
- bitmap->events_cleared = bitmap->mddev->events;
- bitmap->mddev->bitmap_info.chunksize = chunksize;
- bitmap->mddev->bitmap_info.daemon_sleep = daemon_sleep;
- bitmap->mddev->bitmap_info.max_write_behind = write_behind;
- bitmap->mddev->bitmap_info.nodes = nodes;
- if (bitmap->mddev->bitmap_info.space == 0 ||
- bitmap->mddev->bitmap_info.space > sectors_reserved)
- bitmap->mddev->bitmap_info.space = sectors_reserved;
- if (err) {
+ if (err == 0) {
+ if (test_bit(BITMAP_STALE, &bitmap->flags))
+ bitmap->events_cleared = bitmap->mddev->events;
+ bitmap->mddev->bitmap_info.chunksize = chunksize;
+ bitmap->mddev->bitmap_info.daemon_sleep = daemon_sleep;
+ bitmap->mddev->bitmap_info.max_write_behind = write_behind;
+ bitmap->mddev->bitmap_info.nodes = nodes;
+ if (bitmap->mddev->bitmap_info.space == 0 ||
+ bitmap->mddev->bitmap_info.space > sectors_reserved)
+ bitmap->mddev->bitmap_info.space = sectors_reserved;
+ } else {
md_bitmap_print_sb(bitmap);
if (bitmap->cluster_slot < 0)
md_cluster_stop(bitmap->mddev);
diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c
index 1c8a06b77c85..37cbcce3cc66 100644
--- a/drivers/md/md-cluster.c
+++ b/drivers/md/md-cluster.c
@@ -201,7 +201,7 @@ static struct dlm_lock_resource *lockres_init(struct mddev *mddev,
pr_err("md-cluster: Unable to allocate resource name for resource %s\n", name);
goto out_err;
}
- strlcpy(res->name, name, namelen + 1);
+ strscpy(res->name, name, namelen + 1);
if (with_lvb) {
res->lksb.sb_lvbptr = kzalloc(LVB_SIZE, GFP_KERNEL);
if (!res->lksb.sb_lvbptr) {
diff --git a/drivers/md/md-linear.c b/drivers/md/md-linear.c
index 0f55b079371b..138a3b25c5c8 100644
--- a/drivers/md/md-linear.c
+++ b/drivers/md/md-linear.c
@@ -64,7 +64,6 @@ static struct linear_conf *linear_conf(struct mddev *mddev, int raid_disks)
struct linear_conf *conf;
struct md_rdev *rdev;
int i, cnt;
- bool discard_supported = false;
conf = kzalloc(struct_size(conf, disks, raid_disks), GFP_KERNEL);
if (!conf)
@@ -96,9 +95,6 @@ static struct linear_conf *linear_conf(struct mddev *mddev, int raid_disks)
conf->array_sectors += rdev->sectors;
cnt++;
-
- if (blk_queue_discard(bdev_get_queue(rdev->bdev)))
- discard_supported = true;
}
if (cnt != raid_disks) {
pr_warn("md/linear:%s: not enough drives present. Aborting!\n",
@@ -106,11 +102,6 @@ static struct linear_conf *linear_conf(struct mddev *mddev, int raid_disks)
goto out;
}
- if (!discard_supported)
- blk_queue_flag_clear(QUEUE_FLAG_DISCARD, mddev->queue);
- else
- blk_queue_flag_set(QUEUE_FLAG_DISCARD, mddev->queue);
-
/*
* Here we calculate the device offsets.
*/
@@ -252,7 +243,7 @@ static bool linear_make_request(struct mddev *mddev, struct bio *bio)
start_sector + data_offset;
if (unlikely((bio_op(bio) == REQ_OP_DISCARD) &&
- !blk_queue_discard(bio->bi_bdev->bd_disk->queue))) {
+ !bdev_max_discard_sectors(bio->bi_bdev))) {
/* Just ignore it */
bio_endio(bio);
} else {
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 309b3af906ad..707e802d0082 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -2627,14 +2627,16 @@ static void sync_sbs(struct mddev *mddev, int nospares)
static bool does_sb_need_changing(struct mddev *mddev)
{
- struct md_rdev *rdev;
+ struct md_rdev *rdev = NULL, *iter;
struct mdp_superblock_1 *sb;
int role;
/* Find a good rdev */
- rdev_for_each(rdev, mddev)
- if ((rdev->raid_disk >= 0) && !test_bit(Faulty, &rdev->flags))
+ rdev_for_each(iter, mddev)
+ if ((iter->raid_disk >= 0) && !test_bit(Faulty, &iter->flags)) {
+ rdev = iter;
break;
+ }
/* No good device found. */
if (!rdev)
@@ -2645,11 +2647,11 @@ static bool does_sb_need_changing(struct mddev *mddev)
rdev_for_each(rdev, mddev) {
role = le16_to_cpu(sb->dev_roles[rdev->desc_nr]);
/* Device activated? */
- if (role == 0xffff && rdev->raid_disk >=0 &&
+ if (role == MD_DISK_ROLE_SPARE && rdev->raid_disk >= 0 &&
!test_bit(Faulty, &rdev->flags))
return true;
/* Device turned faulty? */
- if (test_bit(Faulty, &rdev->flags) && (role < 0xfffd))
+ if (test_bit(Faulty, &rdev->flags) && (role < MD_DISK_ROLE_MAX))
return true;
}
@@ -2984,10 +2986,11 @@ state_store(struct md_rdev *rdev, const char *buf, size_t len)
if (cmd_match(buf, "faulty") && rdev->mddev->pers) {
md_error(rdev->mddev, rdev);
- if (test_bit(Faulty, &rdev->flags))
- err = 0;
- else
+
+ if (test_bit(MD_BROKEN, &rdev->mddev->flags))
err = -EBUSY;
+ else
+ err = 0;
} else if (cmd_match(buf, "remove")) {
if (rdev->mddev->pers) {
clear_bit(Blocked, &rdev->flags);
@@ -4028,7 +4031,7 @@ level_store(struct mddev *mddev, const char *buf, size_t len)
oldpriv = mddev->private;
mddev->pers = pers;
mddev->private = priv;
- strlcpy(mddev->clevel, pers->name, sizeof(mddev->clevel));
+ strscpy(mddev->clevel, pers->name, sizeof(mddev->clevel));
mddev->level = mddev->new_level;
mddev->layout = mddev->new_layout;
mddev->chunk_sectors = mddev->new_chunk_sectors;
@@ -4353,10 +4356,9 @@ __ATTR_PREALLOC(resync_start, S_IRUGO|S_IWUSR,
* like active, but no writes have been seen for a while (100msec).
*
* broken
- * RAID0/LINEAR-only: same as clean, but array is missing a member.
- * It's useful because RAID0/LINEAR mounted-arrays aren't stopped
- * when a member is gone, so this state will at least alert the
- * user that something is wrong.
+* Array is failed. It's useful because mounted-arrays aren't stopped
+* when array is failed, so this state will at least alert the user that
+* something is wrong.
*/
enum array_state { clear, inactive, suspended, readonly, read_auto, clean, active,
write_pending, active_idle, broken, bad_word};
@@ -5763,7 +5765,7 @@ static int add_named_array(const char *val, const struct kernel_param *kp)
len--;
if (len >= DISK_NAME_LEN)
return -E2BIG;
- strlcpy(buf, val, len+1);
+ strscpy(buf, val, len+1);
if (strncmp(buf, "md_", 3) == 0)
return md_alloc(0, buf);
if (strncmp(buf, "md", 2) == 0 &&
@@ -5896,7 +5898,7 @@ int md_run(struct mddev *mddev)
mddev->level = pers->level;
mddev->new_level = pers->level;
}
- strlcpy(mddev->clevel, pers->name, sizeof(mddev->clevel));
+ strscpy(mddev->clevel, pers->name, sizeof(mddev->clevel));
if (mddev->reshape_position != MaxSector &&
pers->start_reshape == NULL) {
@@ -5991,8 +5993,7 @@ int md_run(struct mddev *mddev)
bool nonrot = true;
rdev_for_each(rdev, mddev) {
- if (rdev->raid_disk >= 0 &&
- !blk_queue_nonrot(bdev_get_queue(rdev->bdev))) {
+ if (rdev->raid_disk >= 0 && !bdev_nonrot(rdev->bdev)) {
nonrot = false;
break;
}
@@ -7444,7 +7445,7 @@ static int set_disk_faulty(struct mddev *mddev, dev_t dev)
err = -ENODEV;
else {
md_error(mddev, rdev);
- if (!test_bit(Faulty, &rdev->flags))
+ if (test_bit(MD_BROKEN, &mddev->flags))
err = -EBUSY;
}
rcu_read_unlock();
@@ -7985,13 +7986,16 @@ void md_error(struct mddev *mddev, struct md_rdev *rdev)
if (!mddev->pers || !mddev->pers->error_handler)
return;
- mddev->pers->error_handler(mddev,rdev);
- if (mddev->degraded)
+ mddev->pers->error_handler(mddev, rdev);
+
+ if (mddev->degraded && !test_bit(MD_BROKEN, &mddev->flags))
set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
sysfs_notify_dirent_safe(rdev->sysfs_state);
set_bit(MD_RECOVERY_INTR, &mddev->recovery);
- set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
- md_wakeup_thread(mddev->thread);
+ if (!test_bit(MD_BROKEN, &mddev->flags)) {
+ set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+ md_wakeup_thread(mddev->thread);
+ }
if (mddev->event_work.func)
queue_work(md_misc_wq, &mddev->event_work);
md_new_event();
@@ -8585,7 +8589,7 @@ void md_submit_discard_bio(struct mddev *mddev, struct md_rdev *rdev,
{
struct bio *discard_bio = NULL;
- if (__blkdev_issue_discard(rdev->bdev, start, size, GFP_NOIO, 0,
+ if (__blkdev_issue_discard(rdev->bdev, start, size, GFP_NOIO,
&discard_bio) || !discard_bio)
return;
@@ -9671,7 +9675,7 @@ static void check_sb_changes(struct mddev *mddev, struct md_rdev *rdev)
role = le16_to_cpu(sb->dev_roles[rdev2->desc_nr]);
if (test_bit(Candidate, &rdev2->flags)) {
- if (role == 0xfffe) {
+ if (role == MD_DISK_ROLE_FAULTY) {
pr_info("md: Removing Candidate device %s because add failed\n", bdevname(rdev2->bdev,b));
md_kick_rdev_from_array(rdev2);
continue;
@@ -9684,7 +9688,7 @@ static void check_sb_changes(struct mddev *mddev, struct md_rdev *rdev)
/*
* got activated except reshape is happening.
*/
- if (rdev2->raid_disk == -1 && role != 0xffff &&
+ if (rdev2->raid_disk == -1 && role != MD_DISK_ROLE_SPARE &&
!(le32_to_cpu(sb->feature_map) &
MD_FEATURE_RESHAPE_ACTIVE)) {
rdev2->saved_raid_disk = role;
@@ -9701,7 +9705,8 @@ static void check_sb_changes(struct mddev *mddev, struct md_rdev *rdev)
* as faulty. The recovery is performed by the
* one who initiated the error.
*/
- if ((role == 0xfffe) || (role == 0xfffd)) {
+ if (role == MD_DISK_ROLE_FAULTY ||
+ role == MD_DISK_ROLE_JOURNAL) {
md_error(mddev, rdev2);
clear_bit(Blocked, &rdev2->flags);
}
@@ -9791,16 +9796,18 @@ static int read_rdev(struct mddev *mddev, struct md_rdev *rdev)
void md_reload_sb(struct mddev *mddev, int nr)
{
- struct md_rdev *rdev;
+ struct md_rdev *rdev = NULL, *iter;
int err;
/* Find the rdev */
- rdev_for_each_rcu(rdev, mddev) {
- if (rdev->desc_nr == nr)
+ rdev_for_each_rcu(iter, mddev) {
+ if (iter->desc_nr == nr) {
+ rdev = iter;
break;
+ }
}
- if (!rdev || rdev->desc_nr != nr) {
+ if (!rdev) {
pr_warn("%s: %d Could not find rdev with nr %d\n", __func__, __LINE__, nr);
return;
}
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 6ac283864533..cf2cbb17acbd 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -234,34 +234,42 @@ extern int rdev_clear_badblocks(struct md_rdev *rdev, sector_t s, int sectors,
int is_new);
struct md_cluster_info;
-/* change UNSUPPORTED_MDDEV_FLAGS for each array type if new flag is added */
+/**
+ * enum mddev_flags - md device flags.
+ * @MD_ARRAY_FIRST_USE: First use of array, needs initialization.
+ * @MD_CLOSING: If set, we are closing the array, do not open it then.
+ * @MD_JOURNAL_CLEAN: A raid with journal is already clean.
+ * @MD_HAS_JOURNAL: The raid array has journal feature set.
+ * @MD_CLUSTER_RESYNC_LOCKED: cluster raid only, which means node, already took
+ * resync lock, need to release the lock.
+ * @MD_FAILFAST_SUPPORTED: Using MD_FAILFAST on metadata writes is supported as
+ * calls to md_error() will never cause the array to
+ * become failed.
+ * @MD_HAS_PPL: The raid array has PPL feature set.
+ * @MD_HAS_MULTIPLE_PPLS: The raid array has multiple PPLs feature set.
+ * @MD_ALLOW_SB_UPDATE: md_check_recovery is allowed to update the metadata
+ * without taking reconfig_mutex.
+ * @MD_UPDATING_SB: md_check_recovery is updating the metadata without
+ * explicitly holding reconfig_mutex.
+ * @MD_NOT_READY: do_md_run() is active, so 'array_state', ust not report that
+ * array is ready yet.
+ * @MD_BROKEN: This is used to stop writes and mark array as failed.
+ *
+ * change UNSUPPORTED_MDDEV_FLAGS for each array type if new flag is added
+ */
enum mddev_flags {
- MD_ARRAY_FIRST_USE, /* First use of array, needs initialization */
- MD_CLOSING, /* If set, we are closing the array, do not open
- * it then */
- MD_JOURNAL_CLEAN, /* A raid with journal is already clean */
- MD_HAS_JOURNAL, /* The raid array has journal feature set */
- MD_CLUSTER_RESYNC_LOCKED, /* cluster raid only, which means node
- * already took resync lock, need to
- * release the lock */
- MD_FAILFAST_SUPPORTED, /* Using MD_FAILFAST on metadata writes is
- * supported as calls to md_error() will
- * never cause the array to become failed.
- */
- MD_HAS_PPL, /* The raid array has PPL feature set */
- MD_HAS_MULTIPLE_PPLS, /* The raid array has multiple PPLs feature set */
- MD_ALLOW_SB_UPDATE, /* md_check_recovery is allowed to update
- * the metadata without taking reconfig_mutex.
- */
- MD_UPDATING_SB, /* md_check_recovery is updating the metadata
- * without explicitly holding reconfig_mutex.
- */
- MD_NOT_READY, /* do_md_run() is active, so 'array_state'
- * must not report that array is ready yet
- */
- MD_BROKEN, /* This is used in RAID-0/LINEAR only, to stop
- * I/O in case an array member is gone/failed.
- */
+ MD_ARRAY_FIRST_USE,
+ MD_CLOSING,
+ MD_JOURNAL_CLEAN,
+ MD_HAS_JOURNAL,
+ MD_CLUSTER_RESYNC_LOCKED,
+ MD_FAILFAST_SUPPORTED,
+ MD_HAS_PPL,
+ MD_HAS_MULTIPLE_PPLS,
+ MD_ALLOW_SB_UPDATE,
+ MD_UPDATING_SB,
+ MD_NOT_READY,
+ MD_BROKEN,
};
enum mddev_sb_flags {
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index b21e101183f4..e11701e394ca 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -128,21 +128,6 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf)
pr_debug("md/raid0:%s: FINAL %d zones\n",
mdname(mddev), conf->nr_strip_zones);
- if (conf->nr_strip_zones == 1) {
- conf->layout = RAID0_ORIG_LAYOUT;
- } else if (mddev->layout == RAID0_ORIG_LAYOUT ||
- mddev->layout == RAID0_ALT_MULTIZONE_LAYOUT) {
- conf->layout = mddev->layout;
- } else if (default_layout == RAID0_ORIG_LAYOUT ||
- default_layout == RAID0_ALT_MULTIZONE_LAYOUT) {
- conf->layout = default_layout;
- } else {
- pr_err("md/raid0:%s: cannot assemble multi-zone RAID0 with default_layout setting\n",
- mdname(mddev));
- pr_err("md/raid0: please set raid0.default_layout to 1 or 2\n");
- err = -ENOTSUPP;
- goto abort;
- }
/*
* now since we have the hard sector sizes, we can make sure
* chunk size is a multiple of that sector size
@@ -273,6 +258,22 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf)
(unsigned long long)smallest->sectors);
}
+ if (conf->nr_strip_zones == 1 || conf->strip_zone[1].nb_dev == 1) {
+ conf->layout = RAID0_ORIG_LAYOUT;
+ } else if (mddev->layout == RAID0_ORIG_LAYOUT ||
+ mddev->layout == RAID0_ALT_MULTIZONE_LAYOUT) {
+ conf->layout = mddev->layout;
+ } else if (default_layout == RAID0_ORIG_LAYOUT ||
+ default_layout == RAID0_ALT_MULTIZONE_LAYOUT) {
+ conf->layout = default_layout;
+ } else {
+ pr_err("md/raid0:%s: cannot assemble multi-zone RAID0 with default_layout setting\n",
+ mdname(mddev));
+ pr_err("md/raid0: please set raid0.default_layout to 1 or 2\n");
+ err = -EOPNOTSUPP;
+ goto abort;
+ }
+
pr_debug("md/raid0:%s: done.\n", mdname(mddev));
*private_conf = conf;
@@ -399,7 +400,6 @@ static int raid0_run(struct mddev *mddev)
conf = mddev->private;
if (mddev->queue) {
struct md_rdev *rdev;
- bool discard_supported = false;
blk_queue_max_hw_sectors(mddev->queue, mddev->chunk_sectors);
blk_queue_max_write_zeroes_sectors(mddev->queue, mddev->chunk_sectors);
@@ -412,13 +412,7 @@ static int raid0_run(struct mddev *mddev)
rdev_for_each(rdev, mddev) {
disk_stack_limits(mddev->gendisk, rdev->bdev,
rdev->data_offset << 9);
- if (blk_queue_discard(bdev_get_queue(rdev->bdev)))
- discard_supported = true;
}
- if (!discard_supported)
- blk_queue_flag_clear(QUEUE_FLAG_DISCARD, mddev->queue);
- else
- blk_queue_flag_set(QUEUE_FLAG_DISCARD, mddev->queue);
}
/* calculate array device size */
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 99d5464a51f8..99d5af1362d7 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -165,9 +165,10 @@ static void * r1buf_pool_alloc(gfp_t gfp_flags, void *data)
* Allocate bios : 1 for reading, n-1 for writing
*/
for (j = pi->raid_disks ; j-- ; ) {
- bio = bio_kmalloc(gfp_flags, RESYNC_PAGES);
+ bio = bio_kmalloc(RESYNC_PAGES, gfp_flags);
if (!bio)
goto out_free_bio;
+ bio_init(bio, NULL, bio->bi_inline_vecs, RESYNC_PAGES, 0);
r1_bio->bios[j] = bio;
}
/*
@@ -206,8 +207,10 @@ out_free_pages:
resync_free_pages(&rps[j]);
out_free_bio:
- while (++j < pi->raid_disks)
- bio_put(r1_bio->bios[j]);
+ while (++j < pi->raid_disks) {
+ bio_uninit(r1_bio->bios[j]);
+ kfree(r1_bio->bios[j]);
+ }
kfree(rps);
out_free_r1bio:
@@ -225,7 +228,8 @@ static void r1buf_pool_free(void *__r1_bio, void *data)
for (i = pi->raid_disks; i--; ) {
rp = get_resync_pages(r1bio->bios[i]);
resync_free_pages(rp);
- bio_put(r1bio->bios[i]);
+ bio_uninit(r1bio->bios[i]);
+ kfree(r1bio->bios[i]);
}
/* resync pages array stored in the 1st bio's .bi_private */
@@ -704,7 +708,7 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
/* At least two disks to choose from so failfast is OK */
set_bit(R1BIO_FailFast, &r1_bio->state);
- nonrot = blk_queue_nonrot(bdev_get_queue(rdev->bdev));
+ nonrot = bdev_nonrot(rdev->bdev);
has_nonrot_disk |= nonrot;
pending = atomic_read(&rdev->nr_pending);
dist = abs(this_sector - conf->mirrors[disk].head_position);
@@ -802,7 +806,7 @@ static void flush_bio_list(struct r1conf *conf, struct bio *bio)
if (test_bit(Faulty, &rdev->flags)) {
bio_io_error(bio);
} else if (unlikely((bio_op(bio) == REQ_OP_DISCARD) &&
- !blk_queue_discard(bio->bi_bdev->bd_disk->queue)))
+ !bdev_max_discard_sectors(bio->bi_bdev)))
/* Just ignore it */
bio_endio(bio);
else
@@ -1637,30 +1641,39 @@ static void raid1_status(struct seq_file *seq, struct mddev *mddev)
seq_printf(seq, "]");
}
+/**
+ * raid1_error() - RAID1 error handler.
+ * @mddev: affected md device.
+ * @rdev: member device to fail.
+ *
+ * The routine acknowledges &rdev failure and determines new @mddev state.
+ * If it failed, then:
+ * - &MD_BROKEN flag is set in &mddev->flags.
+ * - recovery is disabled.
+ * Otherwise, it must be degraded:
+ * - recovery is interrupted.
+ * - &mddev->degraded is bumped.
+ *
+ * @rdev is marked as &Faulty excluding case when array is failed and
+ * &mddev->fail_last_dev is off.
+ */
static void raid1_error(struct mddev *mddev, struct md_rdev *rdev)
{
char b[BDEVNAME_SIZE];
struct r1conf *conf = mddev->private;
unsigned long flags;
- /*
- * If it is not operational, then we have already marked it as dead
- * else if it is the last working disks with "fail_last_dev == false",
- * ignore the error, let the next level up know.
- * else mark the drive as failed
- */
spin_lock_irqsave(&conf->device_lock, flags);
- if (test_bit(In_sync, &rdev->flags) && !mddev->fail_last_dev
- && (conf->raid_disks - mddev->degraded) == 1) {
- /*
- * Don't fail the drive, act as though we were just a
- * normal single drive.
- * However don't try a recovery from this drive as
- * it is very likely to fail.
- */
- conf->recovery_disabled = mddev->recovery_disabled;
- spin_unlock_irqrestore(&conf->device_lock, flags);
- return;
+
+ if (test_bit(In_sync, &rdev->flags) &&
+ (conf->raid_disks - mddev->degraded) == 1) {
+ set_bit(MD_BROKEN, &mddev->flags);
+
+ if (!mddev->fail_last_dev) {
+ conf->recovery_disabled = mddev->recovery_disabled;
+ spin_unlock_irqrestore(&conf->device_lock, flags);
+ return;
+ }
}
set_bit(Blocked, &rdev->flags);
if (test_and_clear_bit(In_sync, &rdev->flags))
@@ -1826,8 +1839,6 @@ static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev)
break;
}
}
- if (mddev->queue && blk_queue_discard(bdev_get_queue(rdev->bdev)))
- blk_queue_flag_set(QUEUE_FLAG_DISCARD, mddev->queue);
print_conf(conf);
return err;
}
@@ -3106,7 +3117,6 @@ static int raid1_run(struct mddev *mddev)
int i;
struct md_rdev *rdev;
int ret;
- bool discard_supported = false;
if (mddev->level != 1) {
pr_warn("md/raid1:%s: raid level not set to mirroring (%d)\n",
@@ -3141,8 +3151,6 @@ static int raid1_run(struct mddev *mddev)
continue;
disk_stack_limits(mddev->gendisk, rdev->bdev,
rdev->data_offset << 9);
- if (blk_queue_discard(bdev_get_queue(rdev->bdev)))
- discard_supported = true;
}
mddev->degraded = 0;
@@ -3179,15 +3187,6 @@ static int raid1_run(struct mddev *mddev)
md_set_array_sectors(mddev, raid1_size(mddev, 0, 0));
- if (mddev->queue) {
- if (discard_supported)
- blk_queue_flag_set(QUEUE_FLAG_DISCARD,
- mddev->queue);
- else
- blk_queue_flag_clear(QUEUE_FLAG_DISCARD,
- mddev->queue);
- }
-
ret = md_integrity_register(mddev);
if (ret) {
md_unregister_thread(&mddev->thread);
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index dfe7d62d3fbd..dfa576cdf11c 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -145,15 +145,17 @@ static void * r10buf_pool_alloc(gfp_t gfp_flags, void *data)
* Allocate bios.
*/
for (j = nalloc ; j-- ; ) {
- bio = bio_kmalloc(gfp_flags, RESYNC_PAGES);
+ bio = bio_kmalloc(RESYNC_PAGES, gfp_flags);
if (!bio)
goto out_free_bio;
+ bio_init(bio, NULL, bio->bi_inline_vecs, RESYNC_PAGES, 0);
r10_bio->devs[j].bio = bio;
if (!conf->have_replacement)
continue;
- bio = bio_kmalloc(gfp_flags, RESYNC_PAGES);
+ bio = bio_kmalloc(RESYNC_PAGES, gfp_flags);
if (!bio)
goto out_free_bio;
+ bio_init(bio, NULL, bio->bi_inline_vecs, RESYNC_PAGES, 0);
r10_bio->devs[j].repl_bio = bio;
}
/*
@@ -197,9 +199,11 @@ out_free_pages:
out_free_bio:
for ( ; j < nalloc; j++) {
if (r10_bio->devs[j].bio)
- bio_put(r10_bio->devs[j].bio);
+ bio_uninit(r10_bio->devs[j].bio);
+ kfree(r10_bio->devs[j].bio);
if (r10_bio->devs[j].repl_bio)
- bio_put(r10_bio->devs[j].repl_bio);
+ bio_uninit(r10_bio->devs[j].repl_bio);
+ kfree(r10_bio->devs[j].repl_bio);
}
kfree(rps);
out_free_r10bio:
@@ -220,12 +224,15 @@ static void r10buf_pool_free(void *__r10_bio, void *data)
if (bio) {
rp = get_resync_pages(bio);
resync_free_pages(rp);
- bio_put(bio);
+ bio_uninit(bio);
+ kfree(bio);
}
bio = r10bio->devs[j].repl_bio;
- if (bio)
- bio_put(bio);
+ if (bio) {
+ bio_uninit(bio);
+ kfree(bio);
+ }
}
/* resync pages array stored in the 1st bio's .bi_private */
@@ -796,7 +803,7 @@ static struct md_rdev *read_balance(struct r10conf *conf,
if (!do_balance)
break;
- nonrot = blk_queue_nonrot(bdev_get_queue(rdev->bdev));
+ nonrot = bdev_nonrot(rdev->bdev);
has_nonrot_disk |= nonrot;
pending = atomic_read(&rdev->nr_pending);
if (min_pending > pending && nonrot) {
@@ -888,7 +895,7 @@ static void flush_pending_writes(struct r10conf *conf)
if (test_bit(Faulty, &rdev->flags)) {
bio_io_error(bio);
} else if (unlikely((bio_op(bio) == REQ_OP_DISCARD) &&
- !blk_queue_discard(bio->bi_bdev->bd_disk->queue)))
+ !bdev_max_discard_sectors(bio->bi_bdev)))
/* Just ignore it */
bio_endio(bio);
else
@@ -1083,7 +1090,7 @@ static void raid10_unplug(struct blk_plug_cb *cb, bool from_schedule)
if (test_bit(Faulty, &rdev->flags)) {
bio_io_error(bio);
} else if (unlikely((bio_op(bio) == REQ_OP_DISCARD) &&
- !blk_queue_discard(bio->bi_bdev->bd_disk->queue)))
+ !bdev_max_discard_sectors(bio->bi_bdev)))
/* Just ignore it */
bio_endio(bio);
else
@@ -1963,32 +1970,40 @@ static int enough(struct r10conf *conf, int ignore)
_enough(conf, 1, ignore);
}
+/**
+ * raid10_error() - RAID10 error handler.
+ * @mddev: affected md device.
+ * @rdev: member device to fail.
+ *
+ * The routine acknowledges &rdev failure and determines new @mddev state.
+ * If it failed, then:
+ * - &MD_BROKEN flag is set in &mddev->flags.
+ * Otherwise, it must be degraded:
+ * - recovery is interrupted.
+ * - &mddev->degraded is bumped.
+
+ * @rdev is marked as &Faulty excluding case when array is failed and
+ * &mddev->fail_last_dev is off.
+ */
static void raid10_error(struct mddev *mddev, struct md_rdev *rdev)
{
char b[BDEVNAME_SIZE];
struct r10conf *conf = mddev->private;
unsigned long flags;
- /*
- * If it is not operational, then we have already marked it as dead
- * else if it is the last working disks with "fail_last_dev == false",
- * ignore the error, let the next level up know.
- * else mark the drive as failed
- */
spin_lock_irqsave(&conf->device_lock, flags);
- if (test_bit(In_sync, &rdev->flags) && !mddev->fail_last_dev
- && !enough(conf, rdev->raid_disk)) {
- /*
- * Don't fail the drive, just return an IO error.
- */
- spin_unlock_irqrestore(&conf->device_lock, flags);
- return;
+
+ if (test_bit(In_sync, &rdev->flags) && !enough(conf, rdev->raid_disk)) {
+ set_bit(MD_BROKEN, &mddev->flags);
+
+ if (!mddev->fail_last_dev) {
+ spin_unlock_irqrestore(&conf->device_lock, flags);
+ return;
+ }
}
if (test_and_clear_bit(In_sync, &rdev->flags))
mddev->degraded++;
- /*
- * If recovery is running, make sure it aborts.
- */
+
set_bit(MD_RECOVERY_INTR, &mddev->recovery);
set_bit(Blocked, &rdev->flags);
set_bit(Faulty, &rdev->flags);
@@ -2144,8 +2159,6 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
rcu_assign_pointer(p->rdev, rdev);
break;
}
- if (mddev->queue && blk_queue_discard(bdev_get_queue(rdev->bdev)))
- blk_queue_flag_set(QUEUE_FLAG_DISCARD, mddev->queue);
print_conf(conf);
return err;
@@ -4069,7 +4082,6 @@ static int raid10_run(struct mddev *mddev)
sector_t size;
sector_t min_offset_diff = 0;
int first = 1;
- bool discard_supported = false;
if (mddev_init_writes_pending(mddev) < 0)
return -ENOMEM;
@@ -4140,20 +4152,9 @@ static int raid10_run(struct mddev *mddev)
rdev->data_offset << 9);
disk->head_position = 0;
-
- if (blk_queue_discard(bdev_get_queue(rdev->bdev)))
- discard_supported = true;
first = 0;
}
- if (mddev->queue) {
- if (discard_supported)
- blk_queue_flag_set(QUEUE_FLAG_DISCARD,
- mddev->queue);
- else
- blk_queue_flag_clear(QUEUE_FLAG_DISCARD,
- mddev->queue);
- }
/* need to check that every block has at least one working mirror */
if (!enough(conf, -1)) {
pr_err("md/raid10:%s: not enough operational mirrors.\n",
diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c
index a7d50ff9020a..094a4042589e 100644
--- a/drivers/md/raid5-cache.c
+++ b/drivers/md/raid5-cache.c
@@ -1318,7 +1318,7 @@ static void r5l_write_super_and_discard_space(struct r5l_log *log,
r5l_write_super(log, end);
- if (!blk_queue_discard(bdev_get_queue(bdev)))
+ if (!bdev_max_discard_sectors(bdev))
return;
mddev = log->rdev->mddev;
@@ -1344,14 +1344,14 @@ static void r5l_write_super_and_discard_space(struct r5l_log *log,
if (log->last_checkpoint < end) {
blkdev_issue_discard(bdev,
log->last_checkpoint + log->rdev->data_offset,
- end - log->last_checkpoint, GFP_NOIO, 0);
+ end - log->last_checkpoint, GFP_NOIO);
} else {
blkdev_issue_discard(bdev,
log->last_checkpoint + log->rdev->data_offset,
log->device_size - log->last_checkpoint,
- GFP_NOIO, 0);
+ GFP_NOIO);
blkdev_issue_discard(bdev, log->rdev->data_offset, end,
- GFP_NOIO, 0);
+ GFP_NOIO);
}
}
diff --git a/drivers/md/raid5-ppl.c b/drivers/md/raid5-ppl.c
index d3962d92df18..55d065a87b89 100644
--- a/drivers/md/raid5-ppl.c
+++ b/drivers/md/raid5-ppl.c
@@ -883,7 +883,9 @@ static int ppl_recover_entry(struct ppl_log *log, struct ppl_header_entry *e,
(unsigned long long)r_sector, dd_idx,
(unsigned long long)sector);
- rdev = conf->disks[dd_idx].rdev;
+ /* Array has not started so rcu dereference is safe */
+ rdev = rcu_dereference_protected(
+ conf->disks[dd_idx].rdev, 1);
if (!rdev || (!test_bit(In_sync, &rdev->flags) &&
sector >= rdev->recovery_offset)) {
pr_debug("%s:%*s data member disk %d missing\n",
@@ -934,7 +936,10 @@ static int ppl_recover_entry(struct ppl_log *log, struct ppl_header_entry *e,
parity_sector = raid5_compute_sector(conf, r_sector_first + i,
0, &disk, &sh);
BUG_ON(sh.pd_idx != le32_to_cpu(e->parity_disk));
- parity_rdev = conf->disks[sh.pd_idx].rdev;
+
+ /* Array has not started so rcu dereference is safe */
+ parity_rdev = rcu_dereference_protected(
+ conf->disks[sh.pd_idx].rdev, 1);
BUG_ON(parity_rdev->bdev->bd_dev != log->rdev->bdev->bd_dev);
pr_debug("%s:%*s write parity at sector %llu, disk %s\n",
@@ -1404,7 +1409,9 @@ int ppl_init_log(struct r5conf *conf)
for (i = 0; i < ppl_conf->count; i++) {
struct ppl_log *log = &ppl_conf->child_logs[i];
- struct md_rdev *rdev = conf->disks[i].rdev;
+ /* Array has not started so rcu dereference is safe */
+ struct md_rdev *rdev =
+ rcu_dereference_protected(conf->disks[i].rdev, 1);
mutex_init(&log->io_mutex);
spin_lock_init(&log->io_list_lock);
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 351d341a1ffa..39038fa8b1c8 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -79,18 +79,21 @@ static inline int stripe_hash_locks_hash(struct r5conf *conf, sector_t sect)
}
static inline void lock_device_hash_lock(struct r5conf *conf, int hash)
+ __acquires(&conf->device_lock)
{
spin_lock_irq(conf->hash_locks + hash);
spin_lock(&conf->device_lock);
}
static inline void unlock_device_hash_lock(struct r5conf *conf, int hash)
+ __releases(&conf->device_lock)
{
spin_unlock(&conf->device_lock);
spin_unlock_irq(conf->hash_locks + hash);
}
static inline void lock_all_device_hash_locks_irq(struct r5conf *conf)
+ __acquires(&conf->device_lock)
{
int i;
spin_lock_irq(conf->hash_locks);
@@ -100,6 +103,7 @@ static inline void lock_all_device_hash_locks_irq(struct r5conf *conf)
}
static inline void unlock_all_device_hash_locks_irq(struct r5conf *conf)
+ __releases(&conf->device_lock)
{
int i;
spin_unlock(&conf->device_lock);
@@ -164,6 +168,7 @@ static bool stripe_is_lowprio(struct stripe_head *sh)
}
static void raid5_wakeup_stripe_thread(struct stripe_head *sh)
+ __must_hold(&sh->raid_conf->device_lock)
{
struct r5conf *conf = sh->raid_conf;
struct r5worker_group *group;
@@ -211,6 +216,7 @@ static void raid5_wakeup_stripe_thread(struct stripe_head *sh)
static void do_release_stripe(struct r5conf *conf, struct stripe_head *sh,
struct list_head *temp_inactive_list)
+ __must_hold(&conf->device_lock)
{
int i;
int injournal = 0; /* number of date pages with R5_InJournal */
@@ -296,6 +302,7 @@ static void do_release_stripe(struct r5conf *conf, struct stripe_head *sh,
static void __release_stripe(struct r5conf *conf, struct stripe_head *sh,
struct list_head *temp_inactive_list)
+ __must_hold(&conf->device_lock)
{
if (atomic_dec_and_test(&sh->count))
do_release_stripe(conf, sh, temp_inactive_list);
@@ -350,9 +357,9 @@ static void release_inactive_stripe_list(struct r5conf *conf,
}
}
-/* should hold conf->device_lock already */
static int release_stripe_list(struct r5conf *conf,
struct list_head *temp_inactive_list)
+ __must_hold(&conf->device_lock)
{
struct stripe_head *sh, *t;
int count = 0;
@@ -629,6 +636,10 @@ static struct stripe_head *__find_stripe(struct r5conf *conf, sector_t sector,
* This is because some failed devices may only affect one
* of the two sections, and some non-in_sync devices may
* be insync in the section most affected by failed devices.
+ *
+ * Most calls to this function hold &conf->device_lock. Calls
+ * in raid5_run() do not require the lock as no other threads
+ * have been started yet.
*/
int raid5_calc_degraded(struct r5conf *conf)
{
@@ -686,17 +697,17 @@ int raid5_calc_degraded(struct r5conf *conf)
return degraded;
}
-static int has_failed(struct r5conf *conf)
+static bool has_failed(struct r5conf *conf)
{
- int degraded;
+ int degraded = conf->mddev->degraded;
- if (conf->mddev->reshape_position == MaxSector)
- return conf->mddev->degraded > conf->max_degraded;
+ if (test_bit(MD_BROKEN, &conf->mddev->flags))
+ return true;
- degraded = raid5_calc_degraded(conf);
- if (degraded > conf->max_degraded)
- return 1;
- return 0;
+ if (conf->mddev->reshape_position != MaxSector)
+ degraded = raid5_calc_degraded(conf);
+
+ return degraded > conf->max_degraded;
}
struct stripe_head *
@@ -2648,6 +2659,28 @@ static void shrink_stripes(struct r5conf *conf)
conf->slab_cache = NULL;
}
+/*
+ * This helper wraps rcu_dereference_protected() and can be used when
+ * it is known that the nr_pending of the rdev is elevated.
+ */
+static struct md_rdev *rdev_pend_deref(struct md_rdev __rcu *rdev)
+{
+ return rcu_dereference_protected(rdev,
+ atomic_read(&rcu_access_pointer(rdev)->nr_pending));
+}
+
+/*
+ * This helper wraps rcu_dereference_protected() and should be used
+ * when it is known that the mddev_lock() is held. This is safe
+ * seeing raid5_remove_disk() has the same lock held.
+ */
+static struct md_rdev *rdev_mdlock_deref(struct mddev *mddev,
+ struct md_rdev __rcu *rdev)
+{
+ return rcu_dereference_protected(rdev,
+ lockdep_is_held(&mddev->reconfig_mutex));
+}
+
static void raid5_end_read_request(struct bio * bi)
{
struct stripe_head *sh = bi->bi_private;
@@ -2674,9 +2707,9 @@ static void raid5_end_read_request(struct bio * bi)
* In that case it moved down to 'rdev'.
* rdev is not removed until all requests are finished.
*/
- rdev = conf->disks[i].replacement;
+ rdev = rdev_pend_deref(conf->disks[i].replacement);
if (!rdev)
- rdev = conf->disks[i].rdev;
+ rdev = rdev_pend_deref(conf->disks[i].rdev);
if (use_new_offset(conf, sh))
s = sh->sector + rdev->new_data_offset;
@@ -2790,11 +2823,11 @@ static void raid5_end_write_request(struct bio *bi)
for (i = 0 ; i < disks; i++) {
if (bi == &sh->dev[i].req) {
- rdev = conf->disks[i].rdev;
+ rdev = rdev_pend_deref(conf->disks[i].rdev);
break;
}
if (bi == &sh->dev[i].rreq) {
- rdev = conf->disks[i].replacement;
+ rdev = rdev_pend_deref(conf->disks[i].replacement);
if (rdev)
replacement = 1;
else
@@ -2802,7 +2835,7 @@ static void raid5_end_write_request(struct bio *bi)
* replaced it. rdev is not removed
* until all requests are finished.
*/
- rdev = conf->disks[i].rdev;
+ rdev = rdev_pend_deref(conf->disks[i].rdev);
break;
}
}
@@ -2863,34 +2896,31 @@ static void raid5_error(struct mddev *mddev, struct md_rdev *rdev)
unsigned long flags;
pr_debug("raid456: error called\n");
+ pr_crit("md/raid:%s: Disk failure on %s, disabling device.\n",
+ mdname(mddev), bdevname(rdev->bdev, b));
+
spin_lock_irqsave(&conf->device_lock, flags);
+ set_bit(Faulty, &rdev->flags);
+ clear_bit(In_sync, &rdev->flags);
+ mddev->degraded = raid5_calc_degraded(conf);
- if (test_bit(In_sync, &rdev->flags) &&
- mddev->degraded == conf->max_degraded) {
- /*
- * Don't allow to achieve failed state
- * Don't try to recover this device
- */
+ if (has_failed(conf)) {
+ set_bit(MD_BROKEN, &conf->mddev->flags);
conf->recovery_disabled = mddev->recovery_disabled;
- spin_unlock_irqrestore(&conf->device_lock, flags);
- return;
+
+ pr_crit("md/raid:%s: Cannot continue operation (%d/%d failed).\n",
+ mdname(mddev), mddev->degraded, conf->raid_disks);
+ } else {
+ pr_crit("md/raid:%s: Operation continuing on %d devices.\n",
+ mdname(mddev), conf->raid_disks - mddev->degraded);
}
- 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_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"
- "md/raid:%s: Operation continuing on %d devices.\n",
- mdname(mddev),
- bdevname(rdev->bdev, b),
- mdname(mddev),
- conf->raid_disks - mddev->degraded);
r5c_update_on_rdev_error(mddev, rdev);
}
@@ -5213,23 +5243,23 @@ finish:
struct r5dev *dev = &sh->dev[i];
if (test_and_clear_bit(R5_WriteError, &dev->flags)) {
/* We own a safe reference to the rdev */
- rdev = conf->disks[i].rdev;
+ rdev = rdev_pend_deref(conf->disks[i].rdev);
if (!rdev_set_badblocks(rdev, sh->sector,
RAID5_STRIPE_SECTORS(conf), 0))
md_error(conf->mddev, rdev);
rdev_dec_pending(rdev, conf->mddev);
}
if (test_and_clear_bit(R5_MadeGood, &dev->flags)) {
- rdev = conf->disks[i].rdev;
+ rdev = rdev_pend_deref(conf->disks[i].rdev);
rdev_clear_badblocks(rdev, sh->sector,
RAID5_STRIPE_SECTORS(conf), 0);
rdev_dec_pending(rdev, conf->mddev);
}
if (test_and_clear_bit(R5_MadeGoodRepl, &dev->flags)) {
- rdev = conf->disks[i].replacement;
+ rdev = rdev_pend_deref(conf->disks[i].replacement);
if (!rdev)
/* rdev have been moved down */
- rdev = conf->disks[i].rdev;
+ rdev = rdev_pend_deref(conf->disks[i].rdev);
rdev_clear_badblocks(rdev, sh->sector,
RAID5_STRIPE_SECTORS(conf), 0);
rdev_dec_pending(rdev, conf->mddev);
@@ -5256,6 +5286,7 @@ finish:
}
static void raid5_activate_delayed(struct r5conf *conf)
+ __must_hold(&conf->device_lock)
{
if (atomic_read(&conf->preread_active_stripes) < IO_THRESHOLD) {
while (!list_empty(&conf->delayed_list)) {
@@ -5273,9 +5304,9 @@ static void raid5_activate_delayed(struct r5conf *conf)
}
static void activate_bit_delay(struct r5conf *conf,
- struct list_head *temp_inactive_list)
+ struct list_head *temp_inactive_list)
+ __must_hold(&conf->device_lock)
{
- /* device_lock is held */
struct list_head head;
list_add(&head, &conf->bitmap_list);
list_del_init(&conf->bitmap_list);
@@ -5500,6 +5531,7 @@ static struct bio *chunk_aligned_read(struct mddev *mddev, struct bio *raid_bio)
* handle_list.
*/
static struct stripe_head *__get_priority_stripe(struct r5conf *conf, int group)
+ __must_hold(&conf->device_lock)
{
struct stripe_head *sh, *tmp;
struct list_head *handle_list = NULL;
@@ -6288,7 +6320,7 @@ static inline sector_t raid5_sync_request(struct mddev *mddev, sector_t sector_n
*/
rcu_read_lock();
for (i = 0; i < conf->raid_disks; i++) {
- struct md_rdev *rdev = READ_ONCE(conf->disks[i].rdev);
+ struct md_rdev *rdev = rcu_dereference(conf->disks[i].rdev);
if (rdev == NULL || test_bit(Faulty, &rdev->flags))
still_degraded = 1;
@@ -6371,8 +6403,7 @@ static int retry_aligned_read(struct r5conf *conf, struct bio *raid_bio,
static int handle_active_stripes(struct r5conf *conf, int group,
struct r5worker *worker,
struct list_head *temp_inactive_list)
- __releases(&conf->device_lock)
- __acquires(&conf->device_lock)
+ __must_hold(&conf->device_lock)
{
struct stripe_head *batch[MAX_STRIPE_BATCH], *sh;
int i, batch_size = 0, hash;
@@ -7166,7 +7197,7 @@ static struct r5conf *setup_conf(struct mddev *mddev)
int i;
int group_cnt;
struct r5worker_group *new_group;
- int ret;
+ int ret = -ENOMEM;
if (mddev->new_level != 5
&& mddev->new_level != 4
@@ -7225,6 +7256,7 @@ static struct r5conf *setup_conf(struct mddev *mddev)
spin_lock_init(&conf->device_lock);
seqcount_spinlock_init(&conf->gen_lock, &conf->device_lock);
mutex_init(&conf->cache_size_mutex);
+
init_waitqueue_head(&conf->wait_for_quiescent);
init_waitqueue_head(&conf->wait_for_stripe);
init_waitqueue_head(&conf->wait_for_overlap);
@@ -7242,7 +7274,7 @@ static struct r5conf *setup_conf(struct mddev *mddev)
rdev_for_each(rdev, mddev) {
if (test_bit(Journal, &rdev->flags))
continue;
- if (blk_queue_nonrot(bdev_get_queue(rdev->bdev))) {
+ if (bdev_nonrot(rdev->bdev)) {
conf->batch_bio_dispatch = false;
break;
}
@@ -7302,11 +7334,13 @@ static struct r5conf *setup_conf(struct mddev *mddev)
conf->level = mddev->new_level;
conf->chunk_sectors = mddev->new_chunk_sectors;
- if (raid5_alloc_percpu(conf) != 0)
+ ret = raid5_alloc_percpu(conf);
+ if (ret)
goto abort;
pr_debug("raid456: run(%s) called.\n", mdname(mddev));
+ ret = -EIO;
rdev_for_each(rdev, mddev) {
raid_disk = rdev->raid_disk;
if (raid_disk >= max_disks
@@ -7317,11 +7351,11 @@ static struct r5conf *setup_conf(struct mddev *mddev)
if (test_bit(Replacement, &rdev->flags)) {
if (disk->replacement)
goto abort;
- disk->replacement = rdev;
+ RCU_INIT_POINTER(disk->replacement, rdev);
} else {
if (disk->rdev)
goto abort;
- disk->rdev = rdev;
+ RCU_INIT_POINTER(disk->rdev, rdev);
}
if (test_bit(In_sync, &rdev->flags)) {
@@ -7370,6 +7404,7 @@ static struct r5conf *setup_conf(struct mddev *mddev)
if (grow_stripes(conf, conf->min_nr_stripes)) {
pr_warn("md/raid:%s: couldn't allocate %dkB for buffers\n",
mdname(mddev), memory);
+ ret = -ENOMEM;
goto abort;
} else
pr_debug("md/raid:%s: allocated %dkB\n", mdname(mddev), memory);
@@ -7383,7 +7418,8 @@ static struct r5conf *setup_conf(struct mddev *mddev)
conf->shrinker.count_objects = raid5_cache_count;
conf->shrinker.batch = 128;
conf->shrinker.flags = 0;
- if (register_shrinker(&conf->shrinker)) {
+ ret = register_shrinker(&conf->shrinker);
+ if (ret) {
pr_warn("md/raid:%s: couldn't register shrinker.\n",
mdname(mddev));
goto abort;
@@ -7394,17 +7430,16 @@ static struct r5conf *setup_conf(struct mddev *mddev)
if (!conf->thread) {
pr_warn("md/raid:%s: couldn't allocate thread.\n",
mdname(mddev));
+ ret = -ENOMEM;
goto abort;
}
return conf;
abort:
- if (conf) {
+ if (conf)
free_conf(conf);
- return ERR_PTR(-EIO);
- } else
- return ERR_PTR(-ENOMEM);
+ return ERR_PTR(ret);
}
static int only_parity(int raid_disk, int algo, int raid_disks, int max_degraded)
@@ -7621,17 +7656,18 @@ static int raid5_run(struct mddev *mddev)
for (i = 0; i < conf->raid_disks && conf->previous_raid_disks;
i++) {
- rdev = conf->disks[i].rdev;
+ rdev = rdev_mdlock_deref(mddev, conf->disks[i].rdev);
if (!rdev && conf->disks[i].replacement) {
/* The replacement is all we have yet */
- rdev = conf->disks[i].replacement;
+ rdev = rdev_mdlock_deref(mddev,
+ conf->disks[i].replacement);
conf->disks[i].replacement = NULL;
clear_bit(Replacement, &rdev->flags);
- conf->disks[i].rdev = rdev;
+ rcu_assign_pointer(conf->disks[i].rdev, rdev);
}
if (!rdev)
continue;
- if (conf->disks[i].replacement &&
+ if (rcu_access_pointer(conf->disks[i].replacement) &&
conf->reshape_progress != MaxSector) {
/* replacements and reshape simply do not mix. */
pr_warn("md: cannot handle concurrent replacement and reshape.\n");
@@ -7749,7 +7785,6 @@ static int raid5_run(struct mddev *mddev)
*/
stripe = stripe * PAGE_SIZE;
stripe = roundup_pow_of_two(stripe);
- mddev->queue->limits.discard_alignment = stripe;
mddev->queue->limits.discard_granularity = stripe;
blk_queue_max_write_zeroes_sectors(mddev->queue, 0);
@@ -7776,14 +7811,10 @@ static int raid5_run(struct mddev *mddev)
* A better idea might be to turn DISCARD into WRITE_ZEROES
* requests, as that is required to be safe.
*/
- if (devices_handle_discard_safely &&
- mddev->queue->limits.max_discard_sectors >= (stripe >> 9) &&
- mddev->queue->limits.discard_granularity >= stripe)
- blk_queue_flag_set(QUEUE_FLAG_DISCARD,
- mddev->queue);
- else
- blk_queue_flag_clear(QUEUE_FLAG_DISCARD,
- mddev->queue);
+ if (!devices_handle_discard_safely ||
+ mddev->queue->limits.max_discard_sectors < (stripe >> 9) ||
+ mddev->queue->limits.discard_granularity < stripe)
+ blk_queue_max_discard_sectors(mddev->queue, 0);
blk_queue_max_hw_sectors(mddev->queue, UINT_MAX);
}
@@ -7832,8 +7863,8 @@ static void raid5_status(struct seq_file *seq, struct mddev *mddev)
static void print_raid5_conf (struct r5conf *conf)
{
+ struct md_rdev *rdev;
int i;
- struct disk_info *tmp;
pr_debug("RAID conf printout:\n");
if (!conf) {
@@ -7844,50 +7875,54 @@ static void print_raid5_conf (struct r5conf *conf)
conf->raid_disks,
conf->raid_disks - conf->mddev->degraded);
+ rcu_read_lock();
for (i = 0; i < conf->raid_disks; i++) {
char b[BDEVNAME_SIZE];
- tmp = conf->disks + i;
- if (tmp->rdev)
+ rdev = rcu_dereference(conf->disks[i].rdev);
+ if (rdev)
pr_debug(" disk %d, o:%d, dev:%s\n",
- i, !test_bit(Faulty, &tmp->rdev->flags),
- bdevname(tmp->rdev->bdev, b));
+ i, !test_bit(Faulty, &rdev->flags),
+ bdevname(rdev->bdev, b));
}
+ rcu_read_unlock();
}
static int raid5_spare_active(struct mddev *mddev)
{
int i;
struct r5conf *conf = mddev->private;
- struct disk_info *tmp;
+ struct md_rdev *rdev, *replacement;
int count = 0;
unsigned long flags;
for (i = 0; i < conf->raid_disks; i++) {
- tmp = conf->disks + i;
- if (tmp->replacement
- && tmp->replacement->recovery_offset == MaxSector
- && !test_bit(Faulty, &tmp->replacement->flags)
- && !test_and_set_bit(In_sync, &tmp->replacement->flags)) {
+ rdev = rdev_mdlock_deref(mddev, conf->disks[i].rdev);
+ replacement = rdev_mdlock_deref(mddev,
+ conf->disks[i].replacement);
+ if (replacement
+ && replacement->recovery_offset == MaxSector
+ && !test_bit(Faulty, &replacement->flags)
+ && !test_and_set_bit(In_sync, &replacement->flags)) {
/* Replacement has just become active. */
- if (!tmp->rdev
- || !test_and_clear_bit(In_sync, &tmp->rdev->flags))
+ if (!rdev
+ || !test_and_clear_bit(In_sync, &rdev->flags))
count++;
- if (tmp->rdev) {
+ if (rdev) {
/* Replaced device not technically faulty,
* but we need to be sure it gets removed
* and never re-added.
*/
- set_bit(Faulty, &tmp->rdev->flags);
+ set_bit(Faulty, &rdev->flags);
sysfs_notify_dirent_safe(
- tmp->rdev->sysfs_state);
+ rdev->sysfs_state);
}
- sysfs_notify_dirent_safe(tmp->replacement->sysfs_state);
- } else if (tmp->rdev
- && tmp->rdev->recovery_offset == MaxSector
- && !test_bit(Faulty, &tmp->rdev->flags)
- && !test_and_set_bit(In_sync, &tmp->rdev->flags)) {
+ sysfs_notify_dirent_safe(replacement->sysfs_state);
+ } else if (rdev
+ && rdev->recovery_offset == MaxSector
+ && !test_bit(Faulty, &rdev->flags)
+ && !test_and_set_bit(In_sync, &rdev->flags)) {
count++;
- sysfs_notify_dirent_safe(tmp->rdev->sysfs_state);
+ sysfs_notify_dirent_safe(rdev->sysfs_state);
}
}
spin_lock_irqsave(&conf->device_lock, flags);
@@ -7902,8 +7937,9 @@ static int raid5_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
struct r5conf *conf = mddev->private;
int err = 0;
int number = rdev->raid_disk;
- struct md_rdev **rdevp;
+ struct md_rdev __rcu **rdevp;
struct disk_info *p = conf->disks + number;
+ struct md_rdev *tmp;
print_raid5_conf(conf);
if (test_bit(Journal, &rdev->flags) && conf->log) {
@@ -7921,9 +7957,9 @@ static int raid5_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
log_exit(conf);
return 0;
}
- if (rdev == p->rdev)
+ if (rdev == rcu_access_pointer(p->rdev))
rdevp = &p->rdev;
- else if (rdev == p->replacement)
+ else if (rdev == rcu_access_pointer(p->replacement))
rdevp = &p->replacement;
else
return 0;
@@ -7943,18 +7979,20 @@ static int raid5_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
if (!test_bit(Faulty, &rdev->flags) &&
mddev->recovery_disabled != conf->recovery_disabled &&
!has_failed(conf) &&
- (!p->replacement || p->replacement == rdev) &&
+ (!rcu_access_pointer(p->replacement) ||
+ rcu_access_pointer(p->replacement) == rdev) &&
number < conf->raid_disks) {
err = -EBUSY;
goto abort;
}
*rdevp = NULL;
if (!test_bit(RemoveSynchronized, &rdev->flags)) {
+ lockdep_assert_held(&mddev->reconfig_mutex);
synchronize_rcu();
if (atomic_read(&rdev->nr_pending)) {
/* lost the race, try later */
err = -EBUSY;
- *rdevp = rdev;
+ rcu_assign_pointer(*rdevp, rdev);
}
}
if (!err) {
@@ -7962,17 +8000,19 @@ static int raid5_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
if (err)
goto abort;
}
- if (p->replacement) {
+
+ tmp = rcu_access_pointer(p->replacement);
+ if (tmp) {
/* We must have just cleared 'rdev' */
- p->rdev = p->replacement;
- clear_bit(Replacement, &p->replacement->flags);
+ rcu_assign_pointer(p->rdev, tmp);
+ clear_bit(Replacement, &tmp->flags);
smp_mb(); /* Make sure other CPUs may see both as identical
* but will never see neither - if they are careful
*/
- p->replacement = NULL;
+ rcu_assign_pointer(p->replacement, NULL);
if (!err)
- err = log_modify(conf, p->rdev, true);
+ err = log_modify(conf, tmp, true);
}
clear_bit(WantReplacement, &rdev->flags);
@@ -7988,6 +8028,7 @@ static int raid5_add_disk(struct mddev *mddev, struct md_rdev *rdev)
int ret, err = -EEXIST;
int disk;
struct disk_info *p;
+ struct md_rdev *tmp;
int first = 0;
int last = conf->raid_disks - 1;
@@ -8045,7 +8086,8 @@ static int raid5_add_disk(struct mddev *mddev, struct md_rdev *rdev)
}
for (disk = first; disk <= last; disk++) {
p = conf->disks + disk;
- if (test_bit(WantReplacement, &p->rdev->flags) &&
+ tmp = rdev_mdlock_deref(mddev, p->rdev);
+ if (test_bit(WantReplacement, &tmp->flags) &&
p->replacement == NULL) {
clear_bit(In_sync, &rdev->flags);
set_bit(Replacement, &rdev->flags);
@@ -8336,6 +8378,7 @@ static void end_reshape(struct r5conf *conf)
static void raid5_finish_reshape(struct mddev *mddev)
{
struct r5conf *conf = mddev->private;
+ struct md_rdev *rdev;
if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery)) {
@@ -8347,10 +8390,12 @@ static void raid5_finish_reshape(struct mddev *mddev)
for (d = conf->raid_disks ;
d < conf->raid_disks - mddev->delta_disks;
d++) {
- struct md_rdev *rdev = conf->disks[d].rdev;
+ rdev = rdev_mdlock_deref(mddev,
+ conf->disks[d].rdev);
if (rdev)
clear_bit(In_sync, &rdev->flags);
- rdev = conf->disks[d].replacement;
+ rdev = rdev_mdlock_deref(mddev,
+ conf->disks[d].replacement);
if (rdev)
clear_bit(In_sync, &rdev->flags);
}
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index 9e8486a9e445..638d29863503 100644
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -473,7 +473,8 @@ enum {
*/
struct disk_info {
- struct md_rdev *rdev, *replacement;
+ struct md_rdev __rcu *rdev;
+ struct md_rdev __rcu *replacement;
struct page *extra_page; /* extra page to use in prexor */
};
@@ -560,6 +561,16 @@ struct r5pending_data {
struct bio_list bios;
};
+struct raid5_percpu {
+ struct page *spare_page; /* Used when checking P/Q in raid6 */
+ void *scribble; /* space for constructing buffer
+ * lists and performing address
+ * conversions
+ */
+ int scribble_obj_size;
+ local_lock_t lock;
+};
+
struct r5conf {
struct hlist_head *stripe_hashtbl;
/* only protect corresponding hash list and inactive_list */
@@ -635,15 +646,7 @@ struct r5conf {
*/
int recovery_disabled;
/* per cpu variables */
- struct raid5_percpu {
- struct page *spare_page; /* Used when checking P/Q in raid6 */
- void *scribble; /* space for constructing buffer
- * lists and performing address
- * conversions
- */
- int scribble_obj_size;
- local_lock_t lock;
- } __percpu *percpu;
+ struct raid5_percpu __percpu *percpu;
int scribble_disks;
int scribble_sectors;
struct hlist_node node;
generated by cgit v1.2.3 (git 2.39.1) at 2025-01-07 18:24:06 +0100