mirror of
git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
synced 2025-09-04 20:19:47 +08:00
block-6.17-20250822
-----BEGIN PGP SIGNATURE-----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=mbqK
-----END PGP SIGNATURE-----
Merge tag 'block-6.17-20250822' of git://git.kernel.dk/linux
Pull block fixes from Jens Axboe:
"A set of fixes for block that should go into this tree. A bit larger
than what I usually have at this point in time, a lot of that is the
continued fixing of the lockdep annotation for queue freezing that we
recently added, which has highlighted a number of little issues here
and there. This contains:
- MD pull request via Yu:
- Add a legacy_async_del_gendisk mode, to prevent a user tools
regression. New user tools releases will not use such a mode,
the old release with a new kernel now will have warning about
deprecated behavior, and we prepare to remove this legacy mode
after about a year later
- The rename in kernel causing user tools build failure, revert
the rename in mdp_superblock_s
- Fix a regression that interrupted resync can be shown as
recover from mdstat or sysfs
- Improve file size detection for loop, particularly for networked
file systems, by using getattr to get the size rather than the
cached inode size.
- Hotplug CPU lock vs queue freeze fix
- Lockdep fix while updating the number of hardware queues
- Fix stacking for PI devices
- Silence bio_check_eod() for the known case of device removal where
the size is truncated to 0 sectors"
* tag 'block-6.17-20250822' of git://git.kernel.dk/linux:
block: avoid cpu_hotplug_lock depedency on freeze_lock
block: decrement block_rq_qos static key in rq_qos_del()
block: skip q->rq_qos check in rq_qos_done_bio()
blk-mq: fix lockdep warning in __blk_mq_update_nr_hw_queues
block: tone down bio_check_eod
loop: use vfs_getattr_nosec for accurate file size
loop: Consolidate size calculation logic into lo_calculate_size()
block: remove newlines from the warnings in blk_validate_integrity_limits
block: handle pi_tuple_size in queue_limits_stack_integrity
selftests: ublk: Use ARRAY_SIZE() macro to improve code
md: fix sync_action incorrect display during resync
md: add helper rdev_needs_recovery()
md: keep recovery_cp in mdp_superblock_s
md: add legacy_async_del_gendisk mode
This commit is contained in:
Linus Torvalds
commit
a2e94e8079
@ -557,7 +557,7 @@ static inline int bio_check_eod(struct bio *bio)
|
||||
sector_t maxsector = bdev_nr_sectors(bio->bi_bdev);
|
||||
unsigned int nr_sectors = bio_sectors(bio);
|
||||
|
||||
if (nr_sectors &&
|
||||
if (nr_sectors && maxsector &&
|
||||
(nr_sectors > maxsector ||
|
||||
bio->bi_iter.bi_sector > maxsector - nr_sectors)) {
|
||||
pr_info_ratelimited("%s: attempt to access beyond end of device\n"
|
||||
|
||||
@ -95,6 +95,7 @@ static const char *const blk_queue_flag_name[] = {
|
||||
QUEUE_FLAG_NAME(SQ_SCHED),
|
||||
QUEUE_FLAG_NAME(DISABLE_WBT_DEF),
|
||||
QUEUE_FLAG_NAME(NO_ELV_SWITCH),
|
||||
QUEUE_FLAG_NAME(QOS_ENABLED),
|
||||
};
|
||||
#undef QUEUE_FLAG_NAME
|
||||
|
||||
|
||||
@ -5033,6 +5033,7 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
|
||||
unsigned int memflags;
|
||||
int i;
|
||||
struct xarray elv_tbl, et_tbl;
|
||||
bool queues_frozen = false;
|
||||
|
||||
lockdep_assert_held(&set->tag_list_lock);
|
||||
|
||||
@ -5056,9 +5057,6 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
|
||||
blk_mq_sysfs_unregister_hctxs(q);
|
||||
}
|
||||
|
||||
list_for_each_entry(q, &set->tag_list, tag_set_list)
|
||||
blk_mq_freeze_queue_nomemsave(q);
|
||||
|
||||
/*
|
||||
* Switch IO scheduler to 'none', cleaning up the data associated
|
||||
* with the previous scheduler. We will switch back once we are done
|
||||
@ -5068,6 +5066,9 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
|
||||
if (blk_mq_elv_switch_none(q, &elv_tbl))
|
||||
goto switch_back;
|
||||
|
||||
list_for_each_entry(q, &set->tag_list, tag_set_list)
|
||||
blk_mq_freeze_queue_nomemsave(q);
|
||||
queues_frozen = true;
|
||||
if (blk_mq_realloc_tag_set_tags(set, nr_hw_queues) < 0)
|
||||
goto switch_back;
|
||||
|
||||
@ -5091,8 +5092,12 @@ fallback:
|
||||
}
|
||||
switch_back:
|
||||
/* The blk_mq_elv_switch_back unfreezes queue for us. */
|
||||
list_for_each_entry(q, &set->tag_list, tag_set_list)
|
||||
list_for_each_entry(q, &set->tag_list, tag_set_list) {
|
||||
/* switch_back expects queue to be frozen */
|
||||
if (!queues_frozen)
|
||||
blk_mq_freeze_queue_nomemsave(q);
|
||||
blk_mq_elv_switch_back(q, &elv_tbl, &et_tbl);
|
||||
}
|
||||
|
||||
list_for_each_entry(q, &set->tag_list, tag_set_list) {
|
||||
blk_mq_sysfs_register_hctxs(q);
|
||||
|
||||
@ -2,8 +2,6 @@
|
||||
|
||||
#include "blk-rq-qos.h"
|
||||
|
||||
__read_mostly DEFINE_STATIC_KEY_FALSE(block_rq_qos);
|
||||
|
||||
/*
|
||||
* Increment 'v', if 'v' is below 'below'. Returns true if we succeeded,
|
||||
* false if 'v' + 1 would be bigger than 'below'.
|
||||
@ -319,8 +317,8 @@ void rq_qos_exit(struct request_queue *q)
|
||||
struct rq_qos *rqos = q->rq_qos;
|
||||
q->rq_qos = rqos->next;
|
||||
rqos->ops->exit(rqos);
|
||||
static_branch_dec(&block_rq_qos);
|
||||
}
|
||||
blk_queue_flag_clear(QUEUE_FLAG_QOS_ENABLED, q);
|
||||
mutex_unlock(&q->rq_qos_mutex);
|
||||
}
|
||||
|
||||
@ -346,7 +344,7 @@ int rq_qos_add(struct rq_qos *rqos, struct gendisk *disk, enum rq_qos_id id,
|
||||
goto ebusy;
|
||||
rqos->next = q->rq_qos;
|
||||
q->rq_qos = rqos;
|
||||
static_branch_inc(&block_rq_qos);
|
||||
blk_queue_flag_set(QUEUE_FLAG_QOS_ENABLED, q);
|
||||
|
||||
blk_mq_unfreeze_queue(q, memflags);
|
||||
|
||||
@ -377,6 +375,8 @@ void rq_qos_del(struct rq_qos *rqos)
|
||||
break;
|
||||
}
|
||||
}
|
||||
if (!q->rq_qos)
|
||||
blk_queue_flag_clear(QUEUE_FLAG_QOS_ENABLED, q);
|
||||
blk_mq_unfreeze_queue(q, memflags);
|
||||
|
||||
mutex_lock(&q->debugfs_mutex);
|
||||
|
||||
@ -12,7 +12,6 @@
|
||||
#include "blk-mq-debugfs.h"
|
||||
|
||||
struct blk_mq_debugfs_attr;
|
||||
extern struct static_key_false block_rq_qos;
|
||||
|
||||
enum rq_qos_id {
|
||||
RQ_QOS_WBT,
|
||||
@ -113,43 +112,55 @@ void __rq_qos_queue_depth_changed(struct rq_qos *rqos);
|
||||
|
||||
static inline void rq_qos_cleanup(struct request_queue *q, struct bio *bio)
|
||||
{
|
||||
if (static_branch_unlikely(&block_rq_qos) && q->rq_qos)
|
||||
if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) &&
|
||||
q->rq_qos)
|
||||
__rq_qos_cleanup(q->rq_qos, bio);
|
||||
}
|
||||
|
||||
static inline void rq_qos_done(struct request_queue *q, struct request *rq)
|
||||
{
|
||||
if (static_branch_unlikely(&block_rq_qos) && q->rq_qos &&
|
||||
!blk_rq_is_passthrough(rq))
|
||||
if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) &&
|
||||
q->rq_qos && !blk_rq_is_passthrough(rq))
|
||||
__rq_qos_done(q->rq_qos, rq);
|
||||
}
|
||||
|
||||
static inline void rq_qos_issue(struct request_queue *q, struct request *rq)
|
||||
{
|
||||
if (static_branch_unlikely(&block_rq_qos) && q->rq_qos)
|
||||
if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) &&
|
||||
q->rq_qos)
|
||||
__rq_qos_issue(q->rq_qos, rq);
|
||||
}
|
||||
|
||||
static inline void rq_qos_requeue(struct request_queue *q, struct request *rq)
|
||||
{
|
||||
if (static_branch_unlikely(&block_rq_qos) && q->rq_qos)
|
||||
if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) &&
|
||||
q->rq_qos)
|
||||
__rq_qos_requeue(q->rq_qos, rq);
|
||||
}
|
||||
|
||||
static inline void rq_qos_done_bio(struct bio *bio)
|
||||
{
|
||||
if (static_branch_unlikely(&block_rq_qos) &&
|
||||
bio->bi_bdev && (bio_flagged(bio, BIO_QOS_THROTTLED) ||
|
||||
bio_flagged(bio, BIO_QOS_MERGED))) {
|
||||
struct request_queue *q = bdev_get_queue(bio->bi_bdev);
|
||||
if (q->rq_qos)
|
||||
__rq_qos_done_bio(q->rq_qos, bio);
|
||||
}
|
||||
struct request_queue *q;
|
||||
|
||||
if (!bio->bi_bdev || (!bio_flagged(bio, BIO_QOS_THROTTLED) &&
|
||||
!bio_flagged(bio, BIO_QOS_MERGED)))
|
||||
return;
|
||||
|
||||
q = bdev_get_queue(bio->bi_bdev);
|
||||
|
||||
/*
|
||||
* If a bio has BIO_QOS_xxx set, it implicitly implies that
|
||||
* q->rq_qos is present. So, we skip re-checking q->rq_qos
|
||||
* here as an extra optimization and directly call
|
||||
* __rq_qos_done_bio().
|
||||
*/
|
||||
__rq_qos_done_bio(q->rq_qos, bio);
|
||||
}
|
||||
|
||||
static inline void rq_qos_throttle(struct request_queue *q, struct bio *bio)
|
||||
{
|
||||
if (static_branch_unlikely(&block_rq_qos) && q->rq_qos) {
|
||||
if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) &&
|
||||
q->rq_qos) {
|
||||
bio_set_flag(bio, BIO_QOS_THROTTLED);
|
||||
__rq_qos_throttle(q->rq_qos, bio);
|
||||
}
|
||||
@ -158,14 +169,16 @@ static inline void rq_qos_throttle(struct request_queue *q, struct bio *bio)
|
||||
static inline void rq_qos_track(struct request_queue *q, struct request *rq,
|
||||
struct bio *bio)
|
||||
{
|
||||
if (static_branch_unlikely(&block_rq_qos) && q->rq_qos)
|
||||
if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) &&
|
||||
q->rq_qos)
|
||||
__rq_qos_track(q->rq_qos, rq, bio);
|
||||
}
|
||||
|
||||
static inline void rq_qos_merge(struct request_queue *q, struct request *rq,
|
||||
struct bio *bio)
|
||||
{
|
||||
if (static_branch_unlikely(&block_rq_qos) && q->rq_qos) {
|
||||
if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) &&
|
||||
q->rq_qos) {
|
||||
bio_set_flag(bio, BIO_QOS_MERGED);
|
||||
__rq_qos_merge(q->rq_qos, rq, bio);
|
||||
}
|
||||
@ -173,7 +186,8 @@ static inline void rq_qos_merge(struct request_queue *q, struct request *rq,
|
||||
|
||||
static inline void rq_qos_queue_depth_changed(struct request_queue *q)
|
||||
{
|
||||
if (static_branch_unlikely(&block_rq_qos) && q->rq_qos)
|
||||
if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) &&
|
||||
q->rq_qos)
|
||||
__rq_qos_queue_depth_changed(q->rq_qos);
|
||||
}
|
||||
|
||||
|
||||
@ -157,16 +157,14 @@ static int blk_validate_integrity_limits(struct queue_limits *lim)
|
||||
switch (bi->csum_type) {
|
||||
case BLK_INTEGRITY_CSUM_NONE:
|
||||
if (bi->pi_tuple_size) {
|
||||
pr_warn("pi_tuple_size must be 0 when checksum type \
|
||||
is none\n");
|
||||
pr_warn("pi_tuple_size must be 0 when checksum type is none\n");
|
||||
return -EINVAL;
|
||||
}
|
||||
break;
|
||||
case BLK_INTEGRITY_CSUM_CRC:
|
||||
case BLK_INTEGRITY_CSUM_IP:
|
||||
if (bi->pi_tuple_size != sizeof(struct t10_pi_tuple)) {
|
||||
pr_warn("pi_tuple_size mismatch for T10 PI: expected \
|
||||
%zu, got %u\n",
|
||||
pr_warn("pi_tuple_size mismatch for T10 PI: expected %zu, got %u\n",
|
||||
sizeof(struct t10_pi_tuple),
|
||||
bi->pi_tuple_size);
|
||||
return -EINVAL;
|
||||
@ -174,8 +172,7 @@ static int blk_validate_integrity_limits(struct queue_limits *lim)
|
||||
break;
|
||||
case BLK_INTEGRITY_CSUM_CRC64:
|
||||
if (bi->pi_tuple_size != sizeof(struct crc64_pi_tuple)) {
|
||||
pr_warn("pi_tuple_size mismatch for CRC64 PI: \
|
||||
expected %zu, got %u\n",
|
||||
pr_warn("pi_tuple_size mismatch for CRC64 PI: expected %zu, got %u\n",
|
||||
sizeof(struct crc64_pi_tuple),
|
||||
bi->pi_tuple_size);
|
||||
return -EINVAL;
|
||||
@ -972,6 +969,8 @@ bool queue_limits_stack_integrity(struct queue_limits *t,
|
||||
goto incompatible;
|
||||
if (ti->csum_type != bi->csum_type)
|
||||
goto incompatible;
|
||||
if (ti->pi_tuple_size != bi->pi_tuple_size)
|
||||
goto incompatible;
|
||||
if ((ti->flags & BLK_INTEGRITY_REF_TAG) !=
|
||||
(bi->flags & BLK_INTEGRITY_REF_TAG))
|
||||
goto incompatible;
|
||||
@ -980,6 +979,7 @@ bool queue_limits_stack_integrity(struct queue_limits *t,
|
||||
ti->flags |= (bi->flags & BLK_INTEGRITY_DEVICE_CAPABLE) |
|
||||
(bi->flags & BLK_INTEGRITY_REF_TAG);
|
||||
ti->csum_type = bi->csum_type;
|
||||
ti->pi_tuple_size = bi->pi_tuple_size;
|
||||
ti->metadata_size = bi->metadata_size;
|
||||
ti->pi_offset = bi->pi_offset;
|
||||
ti->interval_exp = bi->interval_exp;
|
||||
|
||||
@ -137,20 +137,29 @@ static void loop_global_unlock(struct loop_device *lo, bool global)
|
||||
static int max_part;
|
||||
static int part_shift;
|
||||
|
||||
static loff_t get_size(loff_t offset, loff_t sizelimit, struct file *file)
|
||||
static loff_t lo_calculate_size(struct loop_device *lo, struct file *file)
|
||||
{
|
||||
struct kstat stat;
|
||||
loff_t loopsize;
|
||||
int ret;
|
||||
|
||||
/* Compute loopsize in bytes */
|
||||
loopsize = i_size_read(file->f_mapping->host);
|
||||
if (offset > 0)
|
||||
loopsize -= offset;
|
||||
/*
|
||||
* Get the accurate file size. This provides better results than
|
||||
* cached inode data, particularly for network filesystems where
|
||||
* metadata may be stale.
|
||||
*/
|
||||
ret = vfs_getattr_nosec(&file->f_path, &stat, STATX_SIZE, 0);
|
||||
if (ret)
|
||||
return 0;
|
||||
|
||||
loopsize = stat.size;
|
||||
if (lo->lo_offset > 0)
|
||||
loopsize -= lo->lo_offset;
|
||||
/* offset is beyond i_size, weird but possible */
|
||||
if (loopsize < 0)
|
||||
return 0;
|
||||
|
||||
if (sizelimit > 0 && sizelimit < loopsize)
|
||||
loopsize = sizelimit;
|
||||
if (lo->lo_sizelimit > 0 && lo->lo_sizelimit < loopsize)
|
||||
loopsize = lo->lo_sizelimit;
|
||||
/*
|
||||
* Unfortunately, if we want to do I/O on the device,
|
||||
* the number of 512-byte sectors has to fit into a sector_t.
|
||||
@ -158,11 +167,6 @@ static loff_t get_size(loff_t offset, loff_t sizelimit, struct file *file)
|
||||
return loopsize >> 9;
|
||||
}
|
||||
|
||||
static loff_t get_loop_size(struct loop_device *lo, struct file *file)
|
||||
{
|
||||
return get_size(lo->lo_offset, lo->lo_sizelimit, file);
|
||||
}
|
||||
|
||||
/*
|
||||
* We support direct I/O only if lo_offset is aligned with the logical I/O size
|
||||
* of backing device, and the logical block size of loop is bigger than that of
|
||||
@ -569,7 +573,7 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
|
||||
error = -EINVAL;
|
||||
|
||||
/* size of the new backing store needs to be the same */
|
||||
if (get_loop_size(lo, file) != get_loop_size(lo, old_file))
|
||||
if (lo_calculate_size(lo, file) != lo_calculate_size(lo, old_file))
|
||||
goto out_err;
|
||||
|
||||
/*
|
||||
@ -1063,7 +1067,7 @@ static int loop_configure(struct loop_device *lo, blk_mode_t mode,
|
||||
loop_update_dio(lo);
|
||||
loop_sysfs_init(lo);
|
||||
|
||||
size = get_loop_size(lo, file);
|
||||
size = lo_calculate_size(lo, file);
|
||||
loop_set_size(lo, size);
|
||||
|
||||
/* Order wrt reading lo_state in loop_validate_file(). */
|
||||
@ -1255,8 +1259,7 @@ out_unfreeze:
|
||||
if (partscan)
|
||||
clear_bit(GD_SUPPRESS_PART_SCAN, &lo->lo_disk->state);
|
||||
if (!err && size_changed) {
|
||||
loff_t new_size = get_size(lo->lo_offset, lo->lo_sizelimit,
|
||||
lo->lo_backing_file);
|
||||
loff_t new_size = lo_calculate_size(lo, lo->lo_backing_file);
|
||||
loop_set_size(lo, new_size);
|
||||
}
|
||||
out_unlock:
|
||||
@ -1399,7 +1402,7 @@ static int loop_set_capacity(struct loop_device *lo)
|
||||
if (unlikely(lo->lo_state != Lo_bound))
|
||||
return -ENXIO;
|
||||
|
||||
size = get_loop_size(lo, lo->lo_backing_file);
|
||||
size = lo_calculate_size(lo, lo->lo_backing_file);
|
||||
loop_set_size(lo, size);
|
||||
|
||||
return 0;
|
||||
|
||||
122
drivers/md/md.c
122
drivers/md/md.c
@ -339,6 +339,7 @@ static int start_readonly;
|
||||
* so all the races disappear.
|
||||
*/
|
||||
static bool create_on_open = true;
|
||||
static bool legacy_async_del_gendisk = true;
|
||||
|
||||
/*
|
||||
* We have a system wide 'event count' that is incremented
|
||||
@ -877,15 +878,18 @@ void mddev_unlock(struct mddev *mddev)
|
||||
export_rdev(rdev, mddev);
|
||||
}
|
||||
|
||||
/* Call del_gendisk after release reconfig_mutex to avoid
|
||||
* deadlock (e.g. call del_gendisk under the lock and an
|
||||
* access to sysfs files waits the lock)
|
||||
* And MD_DELETED is only used for md raid which is set in
|
||||
* do_md_stop. dm raid only uses md_stop to stop. So dm raid
|
||||
* doesn't need to check MD_DELETED when getting reconfig lock
|
||||
*/
|
||||
if (test_bit(MD_DELETED, &mddev->flags))
|
||||
del_gendisk(mddev->gendisk);
|
||||
if (!legacy_async_del_gendisk) {
|
||||
/*
|
||||
* Call del_gendisk after release reconfig_mutex to avoid
|
||||
* deadlock (e.g. call del_gendisk under the lock and an
|
||||
* access to sysfs files waits the lock)
|
||||
* And MD_DELETED is only used for md raid which is set in
|
||||
* do_md_stop. dm raid only uses md_stop to stop. So dm raid
|
||||
* doesn't need to check MD_DELETED when getting reconfig lock
|
||||
*/
|
||||
if (test_bit(MD_DELETED, &mddev->flags))
|
||||
del_gendisk(mddev->gendisk);
|
||||
}
|
||||
}
|
||||
EXPORT_SYMBOL_GPL(mddev_unlock);
|
||||
|
||||
@ -1419,7 +1423,7 @@ static int super_90_validate(struct mddev *mddev, struct md_rdev *freshest, stru
|
||||
else {
|
||||
if (sb->events_hi == sb->cp_events_hi &&
|
||||
sb->events_lo == sb->cp_events_lo) {
|
||||
mddev->resync_offset = sb->resync_offset;
|
||||
mddev->resync_offset = sb->recovery_cp;
|
||||
} else
|
||||
mddev->resync_offset = 0;
|
||||
}
|
||||
@ -1547,13 +1551,13 @@ static void super_90_sync(struct mddev *mddev, struct md_rdev *rdev)
|
||||
mddev->minor_version = sb->minor_version;
|
||||
if (mddev->in_sync)
|
||||
{
|
||||
sb->resync_offset = mddev->resync_offset;
|
||||
sb->recovery_cp = mddev->resync_offset;
|
||||
sb->cp_events_hi = (mddev->events>>32);
|
||||
sb->cp_events_lo = (u32)mddev->events;
|
||||
if (mddev->resync_offset == MaxSector)
|
||||
sb->state = (1<< MD_SB_CLEAN);
|
||||
} else
|
||||
sb->resync_offset = 0;
|
||||
sb->recovery_cp = 0;
|
||||
|
||||
sb->layout = mddev->layout;
|
||||
sb->chunk_size = mddev->chunk_sectors << 9;
|
||||
@ -4835,9 +4839,42 @@ out_unlock:
|
||||
static struct md_sysfs_entry md_metadata =
|
||||
__ATTR_PREALLOC(metadata_version, S_IRUGO|S_IWUSR, metadata_show, metadata_store);
|
||||
|
||||
static bool rdev_needs_recovery(struct md_rdev *rdev, sector_t sectors)
|
||||
{
|
||||
return rdev->raid_disk >= 0 &&
|
||||
!test_bit(Journal, &rdev->flags) &&
|
||||
!test_bit(Faulty, &rdev->flags) &&
|
||||
!test_bit(In_sync, &rdev->flags) &&
|
||||
rdev->recovery_offset < sectors;
|
||||
}
|
||||
|
||||
static enum sync_action md_get_active_sync_action(struct mddev *mddev)
|
||||
{
|
||||
struct md_rdev *rdev;
|
||||
bool is_recover = false;
|
||||
|
||||
if (mddev->resync_offset < MaxSector)
|
||||
return ACTION_RESYNC;
|
||||
|
||||
if (mddev->reshape_position != MaxSector)
|
||||
return ACTION_RESHAPE;
|
||||
|
||||
rcu_read_lock();
|
||||
rdev_for_each_rcu(rdev, mddev) {
|
||||
if (rdev_needs_recovery(rdev, MaxSector)) {
|
||||
is_recover = true;
|
||||
break;
|
||||
}
|
||||
}
|
||||
rcu_read_unlock();
|
||||
|
||||
return is_recover ? ACTION_RECOVER : ACTION_IDLE;
|
||||
}
|
||||
|
||||
enum sync_action md_sync_action(struct mddev *mddev)
|
||||
{
|
||||
unsigned long recovery = mddev->recovery;
|
||||
enum sync_action active_action;
|
||||
|
||||
/*
|
||||
* frozen has the highest priority, means running sync_thread will be
|
||||
@ -4861,8 +4898,17 @@ enum sync_action md_sync_action(struct mddev *mddev)
|
||||
!test_bit(MD_RECOVERY_NEEDED, &recovery))
|
||||
return ACTION_IDLE;
|
||||
|
||||
if (test_bit(MD_RECOVERY_RESHAPE, &recovery) ||
|
||||
mddev->reshape_position != MaxSector)
|
||||
/*
|
||||
* Check if any sync operation (resync/recover/reshape) is
|
||||
* currently active. This ensures that only one sync operation
|
||||
* can run at a time. Returns the type of active operation, or
|
||||
* ACTION_IDLE if none are active.
|
||||
*/
|
||||
active_action = md_get_active_sync_action(mddev);
|
||||
if (active_action != ACTION_IDLE)
|
||||
return active_action;
|
||||
|
||||
if (test_bit(MD_RECOVERY_RESHAPE, &recovery))
|
||||
return ACTION_RESHAPE;
|
||||
|
||||
if (test_bit(MD_RECOVERY_RECOVER, &recovery))
|
||||
@ -5818,6 +5864,13 @@ static void md_kobj_release(struct kobject *ko)
|
||||
{
|
||||
struct mddev *mddev = container_of(ko, struct mddev, kobj);
|
||||
|
||||
if (legacy_async_del_gendisk) {
|
||||
if (mddev->sysfs_state)
|
||||
sysfs_put(mddev->sysfs_state);
|
||||
if (mddev->sysfs_level)
|
||||
sysfs_put(mddev->sysfs_level);
|
||||
del_gendisk(mddev->gendisk);
|
||||
}
|
||||
put_disk(mddev->gendisk);
|
||||
}
|
||||
|
||||
@ -6021,6 +6074,9 @@ static int md_alloc_and_put(dev_t dev, char *name)
|
||||
{
|
||||
struct mddev *mddev = md_alloc(dev, name);
|
||||
|
||||
if (legacy_async_del_gendisk)
|
||||
pr_warn("md: async del_gendisk mode will be removed in future, please upgrade to mdadm-4.5+\n");
|
||||
|
||||
if (IS_ERR(mddev))
|
||||
return PTR_ERR(mddev);
|
||||
mddev_put(mddev);
|
||||
@ -6431,10 +6487,22 @@ static void md_clean(struct mddev *mddev)
|
||||
mddev->persistent = 0;
|
||||
mddev->level = LEVEL_NONE;
|
||||
mddev->clevel[0] = 0;
|
||||
/* if UNTIL_STOP is set, it's cleared here */
|
||||
mddev->hold_active = 0;
|
||||
/* Don't clear MD_CLOSING, or mddev can be opened again. */
|
||||
mddev->flags &= BIT_ULL_MASK(MD_CLOSING);
|
||||
|
||||
/*
|
||||
* For legacy_async_del_gendisk mode, it can stop the array in the
|
||||
* middle of assembling it, then it still can access the array. So
|
||||
* it needs to clear MD_CLOSING. If not legacy_async_del_gendisk,
|
||||
* it can't open the array again after stopping it. So it doesn't
|
||||
* clear MD_CLOSING.
|
||||
*/
|
||||
if (legacy_async_del_gendisk && mddev->hold_active) {
|
||||
clear_bit(MD_CLOSING, &mddev->flags);
|
||||
} else {
|
||||
/* if UNTIL_STOP is set, it's cleared here */
|
||||
mddev->hold_active = 0;
|
||||
/* Don't clear MD_CLOSING, or mddev can be opened again. */
|
||||
mddev->flags &= BIT_ULL_MASK(MD_CLOSING);
|
||||
}
|
||||
mddev->sb_flags = 0;
|
||||
mddev->ro = MD_RDWR;
|
||||
mddev->metadata_type[0] = 0;
|
||||
@ -6658,7 +6726,8 @@ static int do_md_stop(struct mddev *mddev, int mode)
|
||||
|
||||
export_array(mddev);
|
||||
md_clean(mddev);
|
||||
set_bit(MD_DELETED, &mddev->flags);
|
||||
if (!legacy_async_del_gendisk)
|
||||
set_bit(MD_DELETED, &mddev->flags);
|
||||
}
|
||||
md_new_event();
|
||||
sysfs_notify_dirent_safe(mddev->sysfs_state);
|
||||
@ -8968,11 +9037,7 @@ static sector_t md_sync_position(struct mddev *mddev, enum sync_action action)
|
||||
start = MaxSector;
|
||||
rcu_read_lock();
|
||||
rdev_for_each_rcu(rdev, mddev)
|
||||
if (rdev->raid_disk >= 0 &&
|
||||
!test_bit(Journal, &rdev->flags) &&
|
||||
!test_bit(Faulty, &rdev->flags) &&
|
||||
!test_bit(In_sync, &rdev->flags) &&
|
||||
rdev->recovery_offset < start)
|
||||
if (rdev_needs_recovery(rdev, start))
|
||||
start = rdev->recovery_offset;
|
||||
rcu_read_unlock();
|
||||
|
||||
@ -9331,12 +9396,8 @@ void md_do_sync(struct md_thread *thread)
|
||||
test_bit(MD_RECOVERY_RECOVER, &mddev->recovery)) {
|
||||
rcu_read_lock();
|
||||
rdev_for_each_rcu(rdev, mddev)
|
||||
if (rdev->raid_disk >= 0 &&
|
||||
mddev->delta_disks >= 0 &&
|
||||
!test_bit(Journal, &rdev->flags) &&
|
||||
!test_bit(Faulty, &rdev->flags) &&
|
||||
!test_bit(In_sync, &rdev->flags) &&
|
||||
rdev->recovery_offset < mddev->curr_resync)
|
||||
if (mddev->delta_disks >= 0 &&
|
||||
rdev_needs_recovery(rdev, mddev->curr_resync))
|
||||
rdev->recovery_offset = mddev->curr_resync;
|
||||
rcu_read_unlock();
|
||||
}
|
||||
@ -10392,6 +10453,7 @@ module_param_call(start_ro, set_ro, get_ro, NULL, S_IRUSR|S_IWUSR);
|
||||
module_param(start_dirty_degraded, int, S_IRUGO|S_IWUSR);
|
||||
module_param_call(new_array, add_named_array, NULL, NULL, S_IWUSR);
|
||||
module_param(create_on_open, bool, S_IRUSR|S_IWUSR);
|
||||
module_param(legacy_async_del_gendisk, bool, 0600);
|
||||
|
||||
MODULE_LICENSE("GPL");
|
||||
MODULE_DESCRIPTION("MD RAID framework");
|
||||
|
||||
@ -656,6 +656,7 @@ enum {
|
||||
QUEUE_FLAG_SQ_SCHED, /* single queue style io dispatch */
|
||||
QUEUE_FLAG_DISABLE_WBT_DEF, /* for sched to disable/enable wbt */
|
||||
QUEUE_FLAG_NO_ELV_SWITCH, /* can't switch elevator any more */
|
||||
QUEUE_FLAG_QOS_ENABLED, /* qos is enabled */
|
||||
QUEUE_FLAG_MAX
|
||||
};
|
||||
|
||||
|
||||
@ -173,7 +173,7 @@ typedef struct mdp_superblock_s {
|
||||
#else
|
||||
#error unspecified endianness
|
||||
#endif
|
||||
__u32 resync_offset; /* 11 resync checkpoint sector count */
|
||||
__u32 recovery_cp; /* 11 resync checkpoint sector count */
|
||||
/* There are only valid for minor_version > 90 */
|
||||
__u64 reshape_position; /* 12,13 next address in array-space for reshape */
|
||||
__u32 new_level; /* 14 new level we are reshaping to */
|
||||
|
||||
@ -1400,7 +1400,7 @@ static int cmd_dev_get_features(void)
|
||||
|
||||
if (!((1ULL << i) & features))
|
||||
continue;
|
||||
if (i < sizeof(feat_map) / sizeof(feat_map[0]))
|
||||
if (i < ARRAY_SIZE(feat_map))
|
||||
feat = feat_map[i];
|
||||
else
|
||||
feat = "unknown";
|
||||
@ -1477,7 +1477,7 @@ static void __cmd_create_help(char *exe, bool recovery)
|
||||
printf("\tdefault: nr_queues=2(max 32), depth=128(max 1024), dev_id=-1(auto allocation)\n");
|
||||
printf("\tdefault: nthreads=nr_queues");
|
||||
|
||||
for (i = 0; i < sizeof(tgt_ops_list) / sizeof(tgt_ops_list[0]); i++) {
|
||||
for (i = 0; i < ARRAY_SIZE(tgt_ops_list); i++) {
|
||||
const struct ublk_tgt_ops *ops = tgt_ops_list[i];
|
||||
|
||||
if (ops->usage)
|
||||
|
||||
Loading…
Reference in New Issue
Block a user