summaryrefslogtreecommitdiffstats
path: root/drivers/md
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/md')
-rw-r--r--drivers/md/dm-core.h12
-rw-r--r--drivers/md/dm-era-target.c8
-rw-r--r--drivers/md/dm-log.c5
-rw-r--r--drivers/md/dm-raid.c2
-rw-r--r--drivers/md/dm-rq.c2
-rw-r--r--drivers/md/dm-table.c11
-rw-r--r--drivers/md/dm.c149
-rw-r--r--drivers/md/dm.h2
-rw-r--r--drivers/md/md.c14
-rw-r--r--drivers/md/md.h2
-rw-r--r--drivers/md/raid5-ppl.c4
11 files changed, 92 insertions, 119 deletions
diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h
index d21648a923ea..c954ff91870e 100644
--- a/drivers/md/dm-core.h
+++ b/drivers/md/dm-core.h
@@ -33,6 +33,14 @@ struct dm_kobject_holder {
* access their members!
*/
+/*
+ * For mempools pre-allocation at the table loading time.
+ */
+struct dm_md_mempools {
+ struct bio_set bs;
+ struct bio_set io_bs;
+};
+
struct mapped_device {
struct mutex suspend_lock;
@@ -110,8 +118,7 @@ struct mapped_device {
/*
* io objects are allocated from here.
*/
- struct bio_set io_bs;
- struct bio_set bs;
+ struct dm_md_mempools *mempools;
/* kobject and completion */
struct dm_kobject_holder kobj_holder;
@@ -265,6 +272,7 @@ struct dm_io {
atomic_t io_count;
struct mapped_device *md;
+ struct bio *split_bio;
/* The three fields represent mapped part of original bio */
struct bio *orig_bio;
unsigned int sector_offset; /* offset to end of orig_bio */
diff --git a/drivers/md/dm-era-target.c b/drivers/md/dm-era-target.c
index 1f6bf152b3c7..e92c1afc3677 100644
--- a/drivers/md/dm-era-target.c
+++ b/drivers/md/dm-era-target.c
@@ -1400,7 +1400,7 @@ static void start_worker(struct era *era)
static void stop_worker(struct era *era)
{
atomic_set(&era->suspended, 1);
- flush_workqueue(era->wq);
+ drain_workqueue(era->wq);
}
/*----------------------------------------------------------------
@@ -1570,6 +1570,12 @@ static void era_postsuspend(struct dm_target *ti)
}
stop_worker(era);
+
+ r = metadata_commit(era->md);
+ if (r) {
+ DMERR("%s: metadata_commit failed", __func__);
+ /* FIXME: fail mode */
+ }
}
static int era_preresume(struct dm_target *ti)
diff --git a/drivers/md/dm-log.c b/drivers/md/dm-log.c
index 06f328928a7f..0c6620e7b7bf 100644
--- a/drivers/md/dm-log.c
+++ b/drivers/md/dm-log.c
@@ -415,8 +415,7 @@ static int create_log_context(struct dm_dirty_log *log, struct dm_target *ti,
/*
* Work out how many "unsigned long"s we need to hold the bitset.
*/
- bitset_size = dm_round_up(region_count,
- sizeof(*lc->clean_bits) << BYTE_SHIFT);
+ bitset_size = dm_round_up(region_count, BITS_PER_LONG);
bitset_size >>= BYTE_SHIFT;
lc->bitset_uint32_count = bitset_size / sizeof(*lc->clean_bits);
@@ -616,7 +615,7 @@ static int disk_resume(struct dm_dirty_log *log)
log_clear_bit(lc, lc->clean_bits, i);
/* clear any old bits -- device has shrunk */
- for (i = lc->region_count; i % (sizeof(*lc->clean_bits) << BYTE_SHIFT); i++)
+ for (i = lc->region_count; i % BITS_PER_LONG; i++)
log_clear_bit(lc, lc->clean_bits, i);
/* copy clean across to sync */
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 5e41fbae3f6b..9526ccbedafb 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -3725,7 +3725,7 @@ static int raid_message(struct dm_target *ti, unsigned int argc, char **argv,
if (!strcasecmp(argv[0], "idle") || !strcasecmp(argv[0], "frozen")) {
if (mddev->sync_thread) {
set_bit(MD_RECOVERY_INTR, &mddev->recovery);
- md_reap_sync_thread(mddev, false);
+ md_reap_sync_thread(mddev);
}
} else if (decipher_sync_action(mddev, mddev->recovery) != st_idle)
return -EBUSY;
diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c
index 6087cdcaad46..a83b98a8d2a9 100644
--- a/drivers/md/dm-rq.c
+++ b/drivers/md/dm-rq.c
@@ -319,7 +319,7 @@ static int setup_clone(struct request *clone, struct request *rq,
{
int r;
- r = blk_rq_prep_clone(clone, rq, &tio->md->bs, gfp_mask,
+ r = blk_rq_prep_clone(clone, rq, &tio->md->mempools->bs, gfp_mask,
dm_rq_bio_constructor, tio);
if (r)
return r;
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 0e833a154b31..bd539afbfe88 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -1038,17 +1038,6 @@ static int dm_table_alloc_md_mempools(struct dm_table *t, struct mapped_device *
return 0;
}
-void dm_table_free_md_mempools(struct dm_table *t)
-{
- dm_free_md_mempools(t->mempools);
- t->mempools = NULL;
-}
-
-struct dm_md_mempools *dm_table_get_md_mempools(struct dm_table *t)
-{
- return t->mempools;
-}
-
static int setup_indexes(struct dm_table *t)
{
int i;
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index dfb0a551bd88..2b75f1ef7386 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -136,14 +136,6 @@ static int get_swap_bios(void)
return latch;
}
-/*
- * For mempools pre-allocation at the table loading time.
- */
-struct dm_md_mempools {
- struct bio_set bs;
- struct bio_set io_bs;
-};
-
struct table_device {
struct list_head list;
refcount_t count;
@@ -563,6 +555,10 @@ static void dm_start_io_acct(struct dm_io *io, struct bio *clone)
unsigned long flags;
/* Can afford locking given DM_TIO_IS_DUPLICATE_BIO */
spin_lock_irqsave(&io->lock, flags);
+ if (dm_io_flagged(io, DM_IO_ACCOUNTED)) {
+ spin_unlock_irqrestore(&io->lock, flags);
+ return;
+ }
dm_io_set_flag(io, DM_IO_ACCOUNTED);
spin_unlock_irqrestore(&io->lock, flags);
}
@@ -581,7 +577,7 @@ static struct dm_io *alloc_io(struct mapped_device *md, struct bio *bio)
struct dm_target_io *tio;
struct bio *clone;
- clone = bio_alloc_clone(NULL, bio, GFP_NOIO, &md->io_bs);
+ clone = bio_alloc_clone(NULL, bio, GFP_NOIO, &md->mempools->io_bs);
/* Set default bdev, but target must bio_set_dev() before issuing IO */
clone->bi_bdev = md->disk->part0;
@@ -598,6 +594,7 @@ static struct dm_io *alloc_io(struct mapped_device *md, struct bio *bio)
atomic_set(&io->io_count, 2);
this_cpu_inc(*md->pending_io);
io->orig_bio = bio;
+ io->split_bio = NULL;
io->md = md;
spin_lock_init(&io->lock);
io->start_time = jiffies;
@@ -628,7 +625,8 @@ static struct bio *alloc_tio(struct clone_info *ci, struct dm_target *ti,
} else {
struct mapped_device *md = ci->io->md;
- clone = bio_alloc_clone(NULL, ci->bio, gfp_mask, &md->bs);
+ clone = bio_alloc_clone(NULL, ci->bio, gfp_mask,
+ &md->mempools->bs);
if (!clone)
return NULL;
/* Set default bdev, but target must bio_set_dev() before issuing IO */
@@ -718,18 +716,18 @@ static void dm_put_live_table_fast(struct mapped_device *md) __releases(RCU)
}
static inline struct dm_table *dm_get_live_table_bio(struct mapped_device *md,
- int *srcu_idx, struct bio *bio)
+ int *srcu_idx, unsigned bio_opf)
{
- if (bio->bi_opf & REQ_NOWAIT)
+ if (bio_opf & REQ_NOWAIT)
return dm_get_live_table_fast(md);
else
return dm_get_live_table(md, srcu_idx);
}
static inline void dm_put_live_table_bio(struct mapped_device *md, int srcu_idx,
- struct bio *bio)
+ unsigned bio_opf)
{
- if (bio->bi_opf & REQ_NOWAIT)
+ if (bio_opf & REQ_NOWAIT)
dm_put_live_table_fast(md);
else
dm_put_live_table(md, srcu_idx);
@@ -890,7 +888,7 @@ static void dm_io_complete(struct dm_io *io)
{
blk_status_t io_error;
struct mapped_device *md = io->md;
- struct bio *bio = io->orig_bio;
+ struct bio *bio = io->split_bio ? io->split_bio : io->orig_bio;
if (io->status == BLK_STS_DM_REQUEUE) {
unsigned long flags;
@@ -942,9 +940,11 @@ static void dm_io_complete(struct dm_io *io)
if (io_error == BLK_STS_AGAIN) {
/* io_uring doesn't handle BLK_STS_AGAIN (yet) */
queue_io(md, bio);
+ return;
}
}
- return;
+ if (io_error == BLK_STS_DM_REQUEUE)
+ return;
}
if (bio_is_flush_with_data(bio)) {
@@ -1023,23 +1023,19 @@ static void clone_endio(struct bio *bio)
struct dm_io *io = tio->io;
struct mapped_device *md = io->md;
- if (likely(bio->bi_bdev != md->disk->part0)) {
- struct request_queue *q = bdev_get_queue(bio->bi_bdev);
-
- if (unlikely(error == BLK_STS_TARGET)) {
- if (bio_op(bio) == REQ_OP_DISCARD &&
- !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)
- disable_write_zeroes(md);
- }
-
- if (static_branch_unlikely(&zoned_enabled) &&
- unlikely(blk_queue_is_zoned(q)))
- dm_zone_endio(io, bio);
+ if (unlikely(error == BLK_STS_TARGET)) {
+ if (bio_op(bio) == REQ_OP_DISCARD &&
+ !bdev_max_discard_sectors(bio->bi_bdev))
+ disable_discard(md);
+ else if (bio_op(bio) == REQ_OP_WRITE_ZEROES &&
+ !bdev_write_zeroes_sectors(bio->bi_bdev))
+ disable_write_zeroes(md);
}
+ if (static_branch_unlikely(&zoned_enabled) &&
+ unlikely(blk_queue_is_zoned(bdev_get_queue(bio->bi_bdev))))
+ dm_zone_endio(io, bio);
+
if (endio) {
int r = endio(ti, bio, &error);
switch (r) {
@@ -1620,7 +1616,12 @@ static blk_status_t __split_and_process_bio(struct clone_info *ci)
ti = dm_table_find_target(ci->map, ci->sector);
if (unlikely(!ti))
return BLK_STS_IOERR;
- else if (unlikely(ci->is_abnormal_io))
+
+ if (unlikely((ci->bio->bi_opf & REQ_NOWAIT) != 0) &&
+ unlikely(!dm_target_supports_nowait(ti->type)))
+ return BLK_STS_NOTSUPP;
+
+ if (unlikely(ci->is_abnormal_io))
return __process_abnormal_io(ci, ti);
/*
@@ -1693,9 +1694,11 @@ static void dm_split_and_process_bio(struct mapped_device *md,
* Remainder must be passed to submit_bio_noacct() so it gets handled
* *after* bios already submitted have been completely processed.
*/
- bio_trim(bio, io->sectors, ci.sector_count);
- trace_block_split(bio, bio->bi_iter.bi_sector);
- bio_inc_remaining(bio);
+ WARN_ON_ONCE(!dm_io_flagged(io, DM_IO_WAS_SPLIT));
+ io->split_bio = bio_split(bio, io->sectors, GFP_NOIO,
+ &md->queue->bio_split);
+ bio_chain(io->split_bio, bio);
+ trace_block_split(io->split_bio, bio->bi_iter.bi_sector);
submit_bio_noacct(bio);
out:
/*
@@ -1722,8 +1725,9 @@ static void dm_submit_bio(struct bio *bio)
struct mapped_device *md = bio->bi_bdev->bd_disk->private_data;
int srcu_idx;
struct dm_table *map;
+ unsigned bio_opf = bio->bi_opf;
- map = dm_get_live_table_bio(md, &srcu_idx, bio);
+ map = dm_get_live_table_bio(md, &srcu_idx, bio_opf);
/* If suspended, or map not yet available, queue this IO for later */
if (unlikely(test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags)) ||
@@ -1739,7 +1743,7 @@ static void dm_submit_bio(struct bio *bio)
dm_split_and_process_bio(md, map, bio);
out:
- dm_put_live_table_bio(md, srcu_idx, bio);
+ dm_put_live_table_bio(md, srcu_idx, bio_opf);
}
static bool dm_poll_dm_io(struct dm_io *io, struct io_comp_batch *iob,
@@ -1876,8 +1880,7 @@ static void cleanup_mapped_device(struct mapped_device *md)
{
if (md->wq)
destroy_workqueue(md->wq);
- bioset_exit(&md->bs);
- bioset_exit(&md->io_bs);
+ dm_free_md_mempools(md->mempools);
if (md->dax_dev) {
dax_remove_host(md->disk);
@@ -2049,48 +2052,6 @@ static void free_dev(struct mapped_device *md)
kvfree(md);
}
-static int __bind_mempools(struct mapped_device *md, struct dm_table *t)
-{
- struct dm_md_mempools *p = dm_table_get_md_mempools(t);
- int ret = 0;
-
- if (dm_table_bio_based(t)) {
- /*
- * The md may already have mempools that need changing.
- * If so, reload bioset because front_pad may have changed
- * because a different table was loaded.
- */
- bioset_exit(&md->bs);
- bioset_exit(&md->io_bs);
-
- } else if (bioset_initialized(&md->bs)) {
- /*
- * There's no need to reload with request-based dm
- * because the size of front_pad doesn't change.
- * Note for future: If you are to reload bioset,
- * prep-ed requests in the queue may refer
- * to bio from the old bioset, so you must walk
- * through the queue to unprep.
- */
- goto out;
- }
-
- BUG_ON(!p ||
- bioset_initialized(&md->bs) ||
- bioset_initialized(&md->io_bs));
-
- ret = bioset_init_from_src(&md->bs, &p->bs);
- if (ret)
- goto out;
- ret = bioset_init_from_src(&md->io_bs, &p->io_bs);
- if (ret)
- bioset_exit(&md->bs);
-out:
- /* mempool bind completed, no longer need any mempools in the table */
- dm_table_free_md_mempools(t);
- return ret;
-}
-
/*
* Bind a table to the device.
*/
@@ -2144,12 +2105,28 @@ static struct dm_table *__bind(struct mapped_device *md, struct dm_table *t,
* immutable singletons - used to optimize dm_mq_queue_rq.
*/
md->immutable_target = dm_table_get_immutable_target(t);
- }
- ret = __bind_mempools(md, t);
- if (ret) {
- old_map = ERR_PTR(ret);
- goto out;
+ /*
+ * There is no need to reload with request-based dm because the
+ * size of front_pad doesn't change.
+ *
+ * Note for future: If you are to reload bioset, prep-ed
+ * requests in the queue may refer to bio from the old bioset,
+ * so you must walk through the queue to unprep.
+ */
+ if (!md->mempools) {
+ md->mempools = t->mempools;
+ t->mempools = NULL;
+ }
+ } else {
+ /*
+ * The md may already have mempools that need changing.
+ * If so, reload bioset because front_pad may have changed
+ * because a different table was loaded.
+ */
+ dm_free_md_mempools(md->mempools);
+ md->mempools = t->mempools;
+ t->mempools = NULL;
}
ret = dm_table_set_restrictions(t, md->queue, limits);
diff --git a/drivers/md/dm.h b/drivers/md/dm.h
index 3f89664fea01..a8405ce305a9 100644
--- a/drivers/md/dm.h
+++ b/drivers/md/dm.h
@@ -71,8 +71,6 @@ struct dm_target *dm_table_get_immutable_target(struct dm_table *t);
struct dm_target *dm_table_get_wildcard_target(struct dm_table *t);
bool dm_table_bio_based(struct dm_table *t);
bool dm_table_request_based(struct dm_table *t);
-void dm_table_free_md_mempools(struct dm_table *t);
-struct dm_md_mempools *dm_table_get_md_mempools(struct dm_table *t);
void dm_lock_md_type(struct mapped_device *md);
void dm_unlock_md_type(struct mapped_device *md);
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 8273ac5eef06..c7ecb0bffda0 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -4831,7 +4831,7 @@ action_store(struct mddev *mddev, const char *page, size_t len)
flush_workqueue(md_misc_wq);
if (mddev->sync_thread) {
set_bit(MD_RECOVERY_INTR, &mddev->recovery);
- md_reap_sync_thread(mddev, true);
+ md_reap_sync_thread(mddev);
}
mddev_unlock(mddev);
}
@@ -6197,7 +6197,7 @@ static void __md_stop_writes(struct mddev *mddev)
flush_workqueue(md_misc_wq);
if (mddev->sync_thread) {
set_bit(MD_RECOVERY_INTR, &mddev->recovery);
- md_reap_sync_thread(mddev, true);
+ md_reap_sync_thread(mddev);
}
del_timer_sync(&mddev->safemode_timer);
@@ -9303,7 +9303,7 @@ void md_check_recovery(struct mddev *mddev)
* ->spare_active and clear saved_raid_disk
*/
set_bit(MD_RECOVERY_INTR, &mddev->recovery);
- md_reap_sync_thread(mddev, true);
+ md_reap_sync_thread(mddev);
clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
clear_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags);
@@ -9338,7 +9338,7 @@ void md_check_recovery(struct mddev *mddev)
goto unlock;
}
if (mddev->sync_thread) {
- md_reap_sync_thread(mddev, true);
+ md_reap_sync_thread(mddev);
goto unlock;
}
/* Set RUNNING before clearing NEEDED to avoid
@@ -9411,18 +9411,14 @@ void md_check_recovery(struct mddev *mddev)
}
EXPORT_SYMBOL(md_check_recovery);
-void md_reap_sync_thread(struct mddev *mddev, bool reconfig_mutex_held)
+void md_reap_sync_thread(struct mddev *mddev)
{
struct md_rdev *rdev;
sector_t old_dev_sectors = mddev->dev_sectors;
bool is_reshaped = false;
- if (reconfig_mutex_held)
- mddev_unlock(mddev);
/* resync has finished, collect result */
md_unregister_thread(&mddev->sync_thread);
- if (reconfig_mutex_held)
- mddev_lock_nointr(mddev);
if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery) &&
!test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery) &&
mddev->degraded != mddev->raid_disks) {
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 5f62c46ac2d3..cf2cbb17acbd 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -719,7 +719,7 @@ extern struct md_thread *md_register_thread(
extern void md_unregister_thread(struct md_thread **threadp);
extern void md_wakeup_thread(struct md_thread *thread);
extern void md_check_recovery(struct mddev *mddev);
-extern void md_reap_sync_thread(struct mddev *mddev, bool reconfig_mutex_held);
+extern void md_reap_sync_thread(struct mddev *mddev);
extern int mddev_init_writes_pending(struct mddev *mddev);
extern bool md_write_start(struct mddev *mddev, struct bio *bi);
extern void md_write_inc(struct mddev *mddev, struct bio *bi);
diff --git a/drivers/md/raid5-ppl.c b/drivers/md/raid5-ppl.c
index 973e2e06f19c..0a2e4806b1ec 100644
--- a/drivers/md/raid5-ppl.c
+++ b/drivers/md/raid5-ppl.c
@@ -629,9 +629,9 @@ static void ppl_do_flush(struct ppl_io_unit *io)
if (bdev) {
struct bio *bio;
- bio = bio_alloc_bioset(bdev, 0, GFP_NOIO,
+ bio = bio_alloc_bioset(bdev, 0,
REQ_OP_WRITE | REQ_PREFLUSH,
- &ppl_conf->flush_bs);
+ GFP_NOIO, &ppl_conf->flush_bs);
bio->bi_private = io;
bio->bi_end_io = ppl_flush_endio;
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-24 12:44:02 +0100