summaryrefslogtreecommitdiff
path: root/drivers/md
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/md')
-rw-r--r--drivers/md/bcache/bcache.h9
-rw-r--r--drivers/md/bcache/request.c79
-rw-r--r--drivers/md/bcache/super.c12
-rw-r--r--drivers/md/md.c61
-rw-r--r--drivers/md/raid5.c10
5 files changed, 110 insertions, 61 deletions
diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index 8ccacba85547..ec9ff9715081 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -273,6 +273,8 @@ struct bcache_device {
struct bio_set bio_split;
+ struct bio_set bio_detached;
+
unsigned int data_csum:1;
int (*cache_miss)(struct btree *b, struct search *s,
@@ -753,6 +755,13 @@ struct bbio {
struct bio bio;
};
+struct detached_dev_io_private {
+ struct bcache_device *d;
+ unsigned long start_time;
+ struct bio *orig_bio;
+ struct bio bio;
+};
+
#define BTREE_PRIO USHRT_MAX
#define INITIAL_PRIO 32768U
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index 82fdea7dea7a..a02aecac05cd 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -1077,68 +1077,58 @@ static CLOSURE_CALLBACK(cached_dev_nodata)
continue_at(cl, cached_dev_bio_complete, NULL);
}
-struct detached_dev_io_private {
- struct bcache_device *d;
- unsigned long start_time;
- bio_end_io_t *bi_end_io;
- void *bi_private;
- struct block_device *orig_bdev;
-};
-
static void detached_dev_end_io(struct bio *bio)
{
- struct detached_dev_io_private *ddip;
-
- ddip = bio->bi_private;
- bio->bi_end_io = ddip->bi_end_io;
- bio->bi_private = ddip->bi_private;
+ struct detached_dev_io_private *ddip =
+ container_of(bio, struct detached_dev_io_private, bio);
+ struct bio *orig_bio = ddip->orig_bio;
/* Count on the bcache device */
- bio_end_io_acct_remapped(bio, ddip->start_time, ddip->orig_bdev);
+ bio_end_io_acct(orig_bio, ddip->start_time);
if (bio->bi_status) {
- struct cached_dev *dc = container_of(ddip->d,
- struct cached_dev, disk);
+ struct cached_dev *dc = bio->bi_private;
+
/* should count I/O error for backing device here */
bch_count_backing_io_errors(dc, bio);
+ orig_bio->bi_status = bio->bi_status;
}
- kfree(ddip);
- bio_endio(bio);
+ bio_put(bio);
+ bio_endio(orig_bio);
}
-static void detached_dev_do_request(struct bcache_device *d, struct bio *bio,
- struct block_device *orig_bdev, unsigned long start_time)
+static void detached_dev_do_request(struct bcache_device *d,
+ struct bio *orig_bio, unsigned long start_time)
{
struct detached_dev_io_private *ddip;
struct cached_dev *dc = container_of(d, struct cached_dev, disk);
+ struct bio *clone_bio;
- /*
- * no need to call closure_get(&dc->disk.cl),
- * because upper layer had already opened bcache device,
- * which would call closure_get(&dc->disk.cl)
- */
- ddip = kzalloc(sizeof(struct detached_dev_io_private), GFP_NOIO);
- if (!ddip) {
- bio->bi_status = BLK_STS_RESOURCE;
- bio_endio(bio);
+ if (bio_op(orig_bio) == REQ_OP_DISCARD &&
+ !bdev_max_discard_sectors(dc->bdev)) {
+ bio_endio(orig_bio);
return;
}
- ddip->d = d;
+ clone_bio = bio_alloc_clone(dc->bdev, orig_bio, GFP_NOIO,
+ &d->bio_detached);
+ if (!clone_bio) {
+ orig_bio->bi_status = BLK_STS_RESOURCE;
+ bio_endio(orig_bio);
+ return;
+ }
+
+ ddip = container_of(clone_bio, struct detached_dev_io_private, bio);
/* Count on the bcache device */
- ddip->orig_bdev = orig_bdev;
+ ddip->d = d;
ddip->start_time = start_time;
- ddip->bi_end_io = bio->bi_end_io;
- ddip->bi_private = bio->bi_private;
- bio->bi_end_io = detached_dev_end_io;
- bio->bi_private = ddip;
-
- if ((bio_op(bio) == REQ_OP_DISCARD) &&
- !bdev_max_discard_sectors(dc->bdev))
- detached_dev_end_io(bio);
- else
- submit_bio_noacct(bio);
+ ddip->orig_bio = orig_bio;
+
+ clone_bio->bi_end_io = detached_dev_end_io;
+ clone_bio->bi_private = dc;
+
+ submit_bio_noacct(clone_bio);
}
static void quit_max_writeback_rate(struct cache_set *c,
@@ -1214,10 +1204,10 @@ void cached_dev_submit_bio(struct bio *bio)
start_time = bio_start_io_acct(bio);
- bio_set_dev(bio, dc->bdev);
bio->bi_iter.bi_sector += dc->sb.data_offset;
if (cached_dev_get(dc)) {
+ bio_set_dev(bio, dc->bdev);
s = search_alloc(bio, d, orig_bdev, start_time);
trace_bcache_request_start(s->d, bio);
@@ -1237,9 +1227,10 @@ void cached_dev_submit_bio(struct bio *bio)
else
cached_dev_read(dc, s);
}
- } else
+ } else {
/* I/O request sent to backing device */
- detached_dev_do_request(d, bio, orig_bdev, start_time);
+ detached_dev_do_request(d, bio, start_time);
+ }
}
static int cached_dev_ioctl(struct bcache_device *d, blk_mode_t mode,
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index c17d4517af22..238d12ffdae8 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -887,6 +887,7 @@ static void bcache_device_free(struct bcache_device *d)
}
bioset_exit(&d->bio_split);
+ bioset_exit(&d->bio_detached);
kvfree(d->full_dirty_stripes);
kvfree(d->stripe_sectors_dirty);
@@ -949,6 +950,11 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size,
BIOSET_NEED_BVECS|BIOSET_NEED_RESCUER))
goto out_ida_remove;
+ if (bioset_init(&d->bio_detached, 4,
+ offsetof(struct detached_dev_io_private, bio),
+ BIOSET_NEED_BVECS|BIOSET_NEED_RESCUER))
+ goto out_bioset_split_exit;
+
if (lim.logical_block_size > PAGE_SIZE && cached_bdev) {
/*
* This should only happen with BCACHE_SB_VERSION_BDEV.
@@ -964,7 +970,7 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size,
d->disk = blk_alloc_disk(&lim, NUMA_NO_NODE);
if (IS_ERR(d->disk))
- goto out_bioset_exit;
+ goto out_bioset_detach_exit;
set_capacity(d->disk, sectors);
snprintf(d->disk->disk_name, DISK_NAME_LEN, "bcache%i", idx);
@@ -976,7 +982,9 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size,
d->disk->private_data = d;
return 0;
-out_bioset_exit:
+out_bioset_detach_exit:
+ bioset_exit(&d->bio_detached);
+out_bioset_split_exit:
bioset_exit(&d->bio_split);
out_ida_remove:
ida_free(&bcache_device_idx, idx);
diff --git a/drivers/md/md.c b/drivers/md/md.c
index e5922a682953..6d73f6e196a9 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -1999,7 +1999,6 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *freshest, struc
mddev->layout = le32_to_cpu(sb->layout);
mddev->raid_disks = le32_to_cpu(sb->raid_disks);
mddev->dev_sectors = le64_to_cpu(sb->size);
- mddev->logical_block_size = le32_to_cpu(sb->logical_block_size);
mddev->events = ev1;
mddev->bitmap_info.offset = 0;
mddev->bitmap_info.space = 0;
@@ -2015,6 +2014,9 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *freshest, struc
mddev->max_disks = (4096-256)/2;
+ if (!mddev->logical_block_size)
+ mddev->logical_block_size = le32_to_cpu(sb->logical_block_size);
+
if ((le32_to_cpu(sb->feature_map) & MD_FEATURE_BITMAP_OFFSET) &&
mddev->bitmap_info.file == NULL) {
mddev->bitmap_info.offset =
@@ -3882,7 +3884,6 @@ out_free_rdev:
static int analyze_sbs(struct mddev *mddev)
{
- int i;
struct md_rdev *rdev, *freshest, *tmp;
freshest = NULL;
@@ -3909,11 +3910,9 @@ static int analyze_sbs(struct mddev *mddev)
super_types[mddev->major_version].
validate_super(mddev, NULL/*freshest*/, freshest);
- i = 0;
rdev_for_each_safe(rdev, tmp, mddev) {
if (mddev->max_disks &&
- (rdev->desc_nr >= mddev->max_disks ||
- i > mddev->max_disks)) {
+ rdev->desc_nr >= mddev->max_disks) {
pr_warn("md: %s: %pg: only %d devices permitted\n",
mdname(mddev), rdev->bdev,
mddev->max_disks);
@@ -4407,7 +4406,7 @@ raid_disks_store(struct mddev *mddev, const char *buf, size_t len)
if (err < 0)
return err;
- err = mddev_lock(mddev);
+ err = mddev_suspend_and_lock(mddev);
if (err)
return err;
if (mddev->pers)
@@ -4432,7 +4431,7 @@ raid_disks_store(struct mddev *mddev, const char *buf, size_t len)
} else
mddev->raid_disks = n;
out_unlock:
- mddev_unlock(mddev);
+ mddev_unlock_and_resume(mddev);
return err ? err : len;
}
static struct md_sysfs_entry md_raid_disks =
@@ -5981,13 +5980,33 @@ lbs_store(struct mddev *mddev, const char *buf, size_t len)
if (mddev->major_version == 0)
return -EINVAL;
- if (mddev->pers)
- return -EBUSY;
-
err = kstrtouint(buf, 10, &lbs);
if (err < 0)
return -EINVAL;
+ if (mddev->pers) {
+ unsigned int curr_lbs;
+
+ if (mddev->logical_block_size)
+ return -EBUSY;
+ /*
+ * To fix forward compatibility issues, LBS is not
+ * configured for arrays from old kernels (<=6.18) by default.
+ * If the user confirms no rollback to old kernels,
+ * enable LBS by writing current LBS — to prevent data
+ * loss from LBS changes.
+ */
+ curr_lbs = queue_logical_block_size(mddev->gendisk->queue);
+ if (lbs != curr_lbs)
+ return -EINVAL;
+
+ mddev->logical_block_size = curr_lbs;
+ set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
+ pr_info("%s: logical block size configured successfully, array will not be assembled in old kernels (<= 6.18)\n",
+ mdname(mddev));
+ return len;
+ }
+
err = mddev_lock(mddev);
if (err)
goto unlock;
@@ -6163,7 +6182,27 @@ int mddev_stack_rdev_limits(struct mddev *mddev, struct queue_limits *lim,
mdname(mddev));
return -EINVAL;
}
- mddev->logical_block_size = lim->logical_block_size;
+
+ /* Only 1.x meta needs to set logical block size */
+ if (mddev->major_version == 0)
+ return 0;
+
+ /*
+ * Fix forward compatibility issue. Only set LBS by default for
+ * new arrays, mddev->events == 0 indicates the array was just
+ * created. When assembling an array, read LBS from the superblock
+ * instead — LBS is 0 in superblocks created by old kernels.
+ */
+ if (!mddev->events) {
+ pr_info("%s: array will not be assembled in old kernels that lack configurable LBS support (<= 6.18)\n",
+ mdname(mddev));
+ mddev->logical_block_size = lim->logical_block_size;
+ }
+
+ if (!mddev->logical_block_size)
+ pr_warn("%s: echo current LBS to md/logical_block_size to prevent data loss issues from LBS changes.\n"
+ "\tNote: After setting, array will not be assembled in old kernels (<= 6.18)\n",
+ mdname(mddev));
return 0;
}
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index e57ce3295292..8dc98f545969 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -7187,12 +7187,14 @@ raid5_store_group_thread_cnt(struct mddev *mddev, const char *page, size_t len)
err = mddev_suspend_and_lock(mddev);
if (err)
return err;
+ conf = mddev->private;
+ if (!conf) {
+ mddev_unlock_and_resume(mddev);
+ return -ENODEV;
+ }
raid5_quiesce(mddev, true);
- conf = mddev->private;
- if (!conf)
- err = -ENODEV;
- else if (new != conf->worker_cnt_per_group) {
+ if (new != conf->worker_cnt_per_group) {
old_groups = conf->worker_groups;
if (old_groups)
flush_workqueue(raid5_wq);
generated by cgit v1.2.3 (git 2.0.4) at 2026-01-28 14:44:19 +0000