Merge tag 'for-6.19/block-20251201' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux

Pull block updates from Jens Axboe:

 - Fix head insertion for mq-deadline, a regression from when priority
   support was added

 - Series simplifying and improving the ublk user copy code

 - Various ublk related cleanups

 - Fixup REQ_NOWAIT handling in loop/zloop, clearing NOWAIT when the
   request is punted to a thread for handling

 - Merge and then later revert loop dio nowait support, as it ended up
   causing excessive stack usage for when the inline issue code needs to
   dip back into the full file system code

 - Improve auto integrity code, making it less deadlock prone

 - Speedup polled IO handling, but manually managing the hctx lookups

 - Fixes for blk-throttle for SSD devices

 - Small series with fixes for the S390 dasd driver

 - Add support for caching zones, avoiding unnecessary report zone
   queries

 - MD pull requests via Yu:
      - fix null-ptr-dereference regression for dm-raid0
      - fix IO hang for raid5 when array is broken with IO inflight
      - remove legacy 1s delay to speed up system shutdown
      - change maintainer's email address
      - data can be lost if array is created with different lbs devices,
        fix this problem and record lbs of the array in metadata
      - fix rcu protection for md_thread
      - fix mddev kobject lifetime regression
      - enable atomic writes for md-linear
      - some cleanups

 - bcache updates via Coly
      - remove useless discard and cache device code
      - improve usage of per-cpu workqueues

 - Reorganize the IO scheduler switching code, fixing some lockdep
   reports as well

 - Improve the block layer P2P DMA support

 - Add support to the block tracing code for zoned devices

 - Segment calculation improves, and memory alignment flexibility
   improvements

 - Set of prep and cleanups patches for ublk batching support. The
   actual batching hasn't been added yet, but helps shrink down the
   workload of getting that patchset ready for 6.20

 - Fix for how the ps3 block driver handles segments offsets

 - Improve how block plugging handles batch tag allocations

 - nbd fixes for use-after-free of the configuration on device clear/put

 - Set of improvements and fixes for zloop

 - Add Damien as maintainer of the block zoned device code handling

 - Various other fixes and cleanups

* tag 'for-6.19/block-20251201' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux: (162 commits)
  block/rnbd: correct all kernel-doc complaints
  blk-mq: use queue_hctx in blk_mq_map_queue_type
  md: remove legacy 1s delay in md_notify_reboot
  md/raid5: fix IO hang when array is broken with IO inflight
  md: warn about updating super block failure
  md/raid0: fix NULL pointer dereference in create_strip_zones() for dm-raid
  sbitmap: fix all kernel-doc warnings
  ublk: add helper of __ublk_fetch()
  ublk: pass const pointer to ublk_queue_is_zoned()
  ublk: refactor auto buffer register in ublk_dispatch_req()
  ublk: add `union ublk_io_buf` with improved naming
  ublk: add parameter `struct io_uring_cmd *` to ublk_prep_auto_buf_reg()
  kfifo: add kfifo_alloc_node() helper for NUMA awareness
  blk-mq: fix potential uaf for 'queue_hw_ctx'
  blk-mq: use array manage hctx map instead of xarray
  ublk: prevent invalid access with DEBUG
  s390/dasd: Use scnprintf() instead of sprintf()
  s390/dasd: Move device name formatting into separate function
  s390/dasd: Remove unnecessary debugfs_create() return checks
  s390/dasd: Fix gendisk parent after copy pair swap
  ...

20 files changed, 331 insertions, 290 deletions

diff --git a/drivers/md/bcache/alloc.c b/drivers/md/bcache/alloc.c
index 48ce750bf70a..7708d92df23e 100644
--- a/drivers/md/bcache/alloc.c
+++ b/drivers/md/bcache/alloc.c
@@ -24,21 +24,18 @@
  * Since the gens and priorities are all stored contiguously on disk, we can
  * batch this up: We fill up the free_inc list with freshly invalidated buckets,
  * call prio_write(), and when prio_write() finishes we pull buckets off the
- * free_inc list and optionally discard them.
+ * free_inc list.
  *
  * free_inc isn't the only freelist - if it was, we'd often to sleep while
  * priorities and gens were being written before we could allocate. c->free is a
  * smaller freelist, and buckets on that list are always ready to be used.
  *
- * If we've got discards enabled, that happens when a bucket moves from the
- * free_inc list to the free list.
- *
  * There is another freelist, because sometimes we have buckets that we know
  * have nothing pointing into them - these we can reuse without waiting for
  * priorities to be rewritten. These come from freed btree nodes and buckets
  * that garbage collection discovered no longer had valid keys pointing into
  * them (because they were overwritten). That's the unused list - buckets on the
- * unused list move to the free list, optionally being discarded in the process.
+ * unused list move to the free list.
  *
  * It's also important to ensure that gens don't wrap around - with respect to
  * either the oldest gen in the btree or the gen on disk. This is quite
@@ -118,8 +115,7 @@ void bch_rescale_priorities(struct cache_set *c, int sectors)
 /*
  * Background allocation thread: scans for buckets to be invalidated,
  * invalidates them, rewrites prios/gens (marking them as invalidated on disk),
- * then optionally issues discard commands to the newly free buckets, then puts
- * them on the various freelists.
+ * then puts them on the various freelists.
  */
 
 static inline bool can_inc_bucket_gen(struct bucket *b)
@@ -321,8 +317,7 @@ static int bch_allocator_thread(void *arg)
 	while (1) {
 		/*
 		 * First, we pull buckets off of the unused and free_inc lists,
-		 * possibly issue discards to them, then we add the bucket to
-		 * the free list:
+		 * then we add the bucket to the free list:
 		 */
 		while (1) {
 			long bucket;
@@ -330,14 +325,6 @@ static int bch_allocator_thread(void *arg)
 			if (!fifo_pop(&ca->free_inc, bucket))
 				break;
 
-			if (ca->discard) {
-				mutex_unlock(&ca->set->bucket_lock);
-				blkdev_issue_discard(ca->bdev,
-					bucket_to_sector(ca->set, bucket),
-					ca->sb.bucket_size, GFP_KERNEL);
-				mutex_lock(&ca->set->bucket_lock);
-			}
-
 			allocator_wait(ca, bch_allocator_push(ca, bucket));
 			wake_up(&ca->set->btree_cache_wait);
 			wake_up(&ca->set->bucket_wait);
@@ -412,7 +399,11 @@ long bch_bucket_alloc(struct cache *ca, unsigned int reserve, bool wait)
 				TASK_UNINTERRUPTIBLE);
 
 		mutex_unlock(&ca->set->bucket_lock);
+
+		atomic_inc(&ca->set->bucket_wait_cnt);
 		schedule();
+		atomic_dec(&ca->set->bucket_wait_cnt);
+
 		mutex_lock(&ca->set->bucket_lock);
 	} while (!fifo_pop(&ca->free[RESERVE_NONE], r) &&
 		 !fifo_pop(&ca->free[reserve], r));
diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index 1d33e40d26ea..8ccacba85547 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -447,8 +447,7 @@ struct cache {
 	 * free_inc: Incoming buckets - these are buckets that currently have
 	 * cached data in them, and we can't reuse them until after we write
 	 * their new gen to disk. After prio_write() finishes writing the new
-	 * gens/prios, they'll be moved to the free list (and possibly discarded
-	 * in the process)
+	 * gens/prios, they'll be moved to the free list.
 	 */
 	DECLARE_FIFO(long, free)[RESERVE_NR];
 	DECLARE_FIFO(long, free_inc);
@@ -467,8 +466,6 @@ struct cache {
 	 */
 	unsigned int		invalidate_needs_gc;
 
-	bool			discard; /* Get rid of? */
-
 	struct journal_device	journal;
 
 	/* The rest of this all shows up in sysfs */
@@ -607,6 +604,7 @@ struct cache_set {
 	 */
 	atomic_t		prio_blocked;
 	wait_queue_head_t	bucket_wait;
+	atomic_t		bucket_wait_cnt;
 
 	/*
 	 * For any bio we don't skip we subtract the number of sectors from
diff --git a/drivers/md/bcache/bset.h b/drivers/md/bcache/bset.h
index 011f6062c4c0..6ee2c6a506a2 100644
--- a/drivers/md/bcache/bset.h
+++ b/drivers/md/bcache/bset.h
@@ -327,9 +327,13 @@ struct btree_iter {
 /* Fixed-size btree_iter that can be allocated on the stack */
 
 struct btree_iter_stack {
-	struct btree_iter iter;
-	struct btree_iter_set stack_data[MAX_BSETS];
+	/* Must be last as it ends in a flexible-array member. */
+	TRAILING_OVERLAP(struct btree_iter, iter, data,
+		struct btree_iter_set stack_data[MAX_BSETS];
+	);
 };
+static_assert(offsetof(struct btree_iter_stack, iter.data) ==
+	      offsetof(struct btree_iter_stack, stack_data));
 
 typedef bool (*ptr_filter_fn)(struct btree_keys *b, const struct bkey *k);
 
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index 210b59007d98..3ed39c823826 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -89,8 +89,9 @@
  * Test module load/unload
  */
 
-#define MAX_GC_TIMES		100
-#define MIN_GC_NODES		100
+#define MAX_GC_TIMES_SHIFT	7  /* 128 loops */
+#define GC_NODES_MIN		10
+#define GC_SLEEP_MS_MIN		10
 #define GC_SLEEP_MS		100
 
 #define PTR_DIRTY_BIT		(((uint64_t) 1 << 36))
@@ -371,7 +372,7 @@ static void do_btree_node_write(struct btree *b)
 	SET_PTR_OFFSET(&k.key, 0, PTR_OFFSET(&k.key, 0) +
 		       bset_sector_offset(&b->keys, i));
 
-	if (!bch_bio_alloc_pages(b->bio, __GFP_NOWARN|GFP_NOWAIT)) {
+	if (!bch_bio_alloc_pages(b->bio, GFP_NOWAIT)) {
 		struct bio_vec *bv;
 		void *addr = (void *) ((unsigned long) i & ~(PAGE_SIZE - 1));
 		struct bvec_iter_all iter_all;
@@ -1578,29 +1579,29 @@ static unsigned int btree_gc_count_keys(struct btree *b)
 
 static size_t btree_gc_min_nodes(struct cache_set *c)
 {
-	size_t min_nodes;
+	size_t min_nodes = GC_NODES_MIN;
 
-	/*
-	 * Since incremental GC would stop 100ms when front
-	 * side I/O comes, so when there are many btree nodes,
-	 * if GC only processes constant (100) nodes each time,
-	 * GC would last a long time, and the front side I/Os
-	 * would run out of the buckets (since no new bucket
-	 * can be allocated during GC), and be blocked again.
-	 * So GC should not process constant nodes, but varied
-	 * nodes according to the number of btree nodes, which
-	 * realized by dividing GC into constant(100) times,
-	 * so when there are many btree nodes, GC can process
-	 * more nodes each time, otherwise, GC will process less
-	 * nodes each time (but no less than MIN_GC_NODES)
-	 */
-	min_nodes = c->gc_stats.nodes / MAX_GC_TIMES;
-	if (min_nodes < MIN_GC_NODES)
-		min_nodes = MIN_GC_NODES;
+	if (atomic_read(&c->search_inflight) == 0) {
+		size_t n = c->gc_stats.nodes >> MAX_GC_TIMES_SHIFT;
+
+		if (min_nodes < n)
+			min_nodes = n;
+	}
 
 	return min_nodes;
 }
 
+static uint64_t btree_gc_sleep_ms(struct cache_set *c)
+{
+	uint64_t sleep_ms;
+
+	if (atomic_read(&c->bucket_wait_cnt) > 0)
+		sleep_ms = GC_SLEEP_MS_MIN;
+	else
+		sleep_ms = GC_SLEEP_MS;
+
+	return sleep_ms;
+}
 
 static int btree_gc_recurse(struct btree *b, struct btree_op *op,
 			    struct closure *writes, struct gc_stat *gc)
@@ -1668,8 +1669,7 @@ static int btree_gc_recurse(struct btree *b, struct btree_op *op,
 		memmove(r + 1, r, sizeof(r[0]) * (GC_MERGE_NODES - 1));
 		r->b = NULL;
 
-		if (atomic_read(&b->c->search_inflight) &&
-		    gc->nodes >= gc->nodes_pre + btree_gc_min_nodes(b->c)) {
+		if (gc->nodes >= (gc->nodes_pre + btree_gc_min_nodes(b->c))) {
 			gc->nodes_pre =  gc->nodes;
 			ret = -EAGAIN;
 			break;
@@ -1846,8 +1846,8 @@ static void bch_btree_gc(struct cache_set *c)
 		cond_resched();
 
 		if (ret == -EAGAIN)
-			schedule_timeout_interruptible(msecs_to_jiffies
-						       (GC_SLEEP_MS));
+			schedule_timeout_interruptible(
+				msecs_to_jiffies(btree_gc_sleep_ms(c)));
 		else if (ret)
 			pr_warn("gc failed!\n");
 	} while (ret && !test_bit(CACHE_SET_IO_DISABLE, &c->flags));
@@ -2822,7 +2822,8 @@ void bch_btree_exit(void)
 
 int __init bch_btree_init(void)
 {
-	btree_io_wq = alloc_workqueue("bch_btree_io", WQ_MEM_RECLAIM, 0);
+	btree_io_wq = alloc_workqueue("bch_btree_io",
+				      WQ_MEM_RECLAIM | WQ_PERCPU, 0);
 	if (!btree_io_wq)
 		return -ENOMEM;
 
diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c
index d50eb82ccb4f..144693b7c46a 100644
--- a/drivers/md/bcache/journal.c
+++ b/drivers/md/bcache/journal.c
@@ -275,8 +275,7 @@ bsearch:
 			 * ja->cur_idx
 			 */
 			ja->cur_idx = i;
-			ja->last_idx = ja->discard_idx = (i + 1) %
-				ca->sb.njournal_buckets;
+			ja->last_idx = (i + 1) % ca->sb.njournal_buckets;
 
 		}
 
@@ -336,16 +335,6 @@ void bch_journal_mark(struct cache_set *c, struct list_head *list)
 	}
 }
 
-static bool is_discard_enabled(struct cache_set *s)
-{
-	struct cache *ca = s->cache;
-
-	if (ca->discard)
-		return true;
-
-	return false;
-}
-
 int bch_journal_replay(struct cache_set *s, struct list_head *list)
 {
 	int ret = 0, keys = 0, entries = 0;
@@ -360,15 +349,10 @@ int bch_journal_replay(struct cache_set *s, struct list_head *list)
 		BUG_ON(i->pin && atomic_read(i->pin) != 1);
 
 		if (n != i->j.seq) {
-			if (n == start && is_discard_enabled(s))
-				pr_info("journal entries %llu-%llu may be discarded! (replaying %llu-%llu)\n",
-					n, i->j.seq - 1, start, end);
-			else {
-				pr_err("journal entries %llu-%llu missing! (replaying %llu-%llu)\n",
-					n, i->j.seq - 1, start, end);
-				ret = -EIO;
-				goto err;
-			}
+			pr_err("journal entries %llu-%llu missing! (replaying %llu-%llu)\n",
+				n, i->j.seq - 1, start, end);
+			ret = -EIO;
+			goto err;
 		}
 
 		for (k = i->j.start;
@@ -568,65 +552,6 @@ out:
 
 #define last_seq(j)	((j)->seq - fifo_used(&(j)->pin) + 1)
 
-static void journal_discard_endio(struct bio *bio)
-{
-	struct journal_device *ja =
-		container_of(bio, struct journal_device, discard_bio);
-	struct cache *ca = container_of(ja, struct cache, journal);
-
-	atomic_set(&ja->discard_in_flight, DISCARD_DONE);
-
-	closure_wake_up(&ca->set->journal.wait);
-	closure_put(&ca->set->cl);
-}
-
-static void journal_discard_work(struct work_struct *work)
-{
-	struct journal_device *ja =
-		container_of(work, struct journal_device, discard_work);
-
-	submit_bio(&ja->discard_bio);
-}
-
-static void do_journal_discard(struct cache *ca)
-{
-	struct journal_device *ja = &ca->journal;
-	struct bio *bio = &ja->discard_bio;
-
-	if (!ca->discard) {
-		ja->discard_idx = ja->last_idx;
-		return;
-	}
-
-	switch (atomic_read(&ja->discard_in_flight)) {
-	case DISCARD_IN_FLIGHT:
-		return;
-
-	case DISCARD_DONE:
-		ja->discard_idx = (ja->discard_idx + 1) %
-			ca->sb.njournal_buckets;
-
-		atomic_set(&ja->discard_in_flight, DISCARD_READY);
-		fallthrough;
-
-	case DISCARD_READY:
-		if (ja->discard_idx == ja->last_idx)
-			return;
-
-		atomic_set(&ja->discard_in_flight, DISCARD_IN_FLIGHT);
-
-		bio_init_inline(bio, ca->bdev, 1, REQ_OP_DISCARD);
-		bio->bi_iter.bi_sector	= bucket_to_sector(ca->set,
-						ca->sb.d[ja->discard_idx]);
-		bio->bi_iter.bi_size	= bucket_bytes(ca);
-		bio->bi_end_io		= journal_discard_endio;
-
-		closure_get(&ca->set->cl);
-		INIT_WORK(&ja->discard_work, journal_discard_work);
-		queue_work(bch_journal_wq, &ja->discard_work);
-	}
-}
-
 static unsigned int free_journal_buckets(struct cache_set *c)
 {
 	struct journal *j = &c->journal;
@@ -635,10 +560,10 @@ static unsigned int free_journal_buckets(struct cache_set *c)
 	unsigned int n;
 
 	/* In case njournal_buckets is not power of 2 */
-	if (ja->cur_idx >= ja->discard_idx)
-		n = ca->sb.njournal_buckets +  ja->discard_idx - ja->cur_idx;
+	if (ja->cur_idx >= ja->last_idx)
+		n = ca->sb.njournal_buckets + ja->last_idx - ja->cur_idx;
 	else
-		n = ja->discard_idx - ja->cur_idx;
+		n = ja->last_idx - ja->cur_idx;
 
 	if (n > (1 + j->do_reserve))
 		return n - (1 + j->do_reserve);
@@ -668,8 +593,6 @@ static void journal_reclaim(struct cache_set *c)
 		ja->last_idx = (ja->last_idx + 1) %
 			ca->sb.njournal_buckets;
 
-	do_journal_discard(ca);
-
 	if (c->journal.blocks_free)
 		goto out;
 
diff --git a/drivers/md/bcache/journal.h b/drivers/md/bcache/journal.h
index cd316b4a1e95..9e9d1b3016a5 100644
--- a/drivers/md/bcache/journal.h
+++ b/drivers/md/bcache/journal.h
@@ -139,19 +139,6 @@ struct journal_device {
 	/* Last journal bucket that still contains an open journal entry */
 	unsigned int		last_idx;
 
-	/* Next journal bucket to be discarded */
-	unsigned int		discard_idx;
-
-#define DISCARD_READY		0
-#define DISCARD_IN_FLIGHT	1
-#define DISCARD_DONE		2
-	/* 1 - discard in flight, -1 - discard completed */
-	atomic_t		discard_in_flight;
-
-	struct work_struct	discard_work;
-	struct bio		discard_bio;
-	struct bio_vec		discard_bv;
-
 	/* Bio for journal reads/writes to this device */
 	struct bio		bio;
 	struct bio_vec		bv[8];
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 6d250e366412..c17d4517af22 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -1388,7 +1388,7 @@ static CLOSURE_CALLBACK(cached_dev_flush)
 	bch_cache_accounting_destroy(&dc->accounting);
 	kobject_del(&d->kobj);
 
-	continue_at(cl, cached_dev_free, system_wq);
+	continue_at(cl, cached_dev_free, system_percpu_wq);
 }
 
 static int cached_dev_init(struct cached_dev *dc, unsigned int block_size)
@@ -1400,7 +1400,7 @@ static int cached_dev_init(struct cached_dev *dc, unsigned int block_size)
 	__module_get(THIS_MODULE);
 	INIT_LIST_HEAD(&dc->list);
 	closure_init(&dc->disk.cl, NULL);
-	set_closure_fn(&dc->disk.cl, cached_dev_flush, system_wq);
+	set_closure_fn(&dc->disk.cl, cached_dev_flush, system_percpu_wq);
 	kobject_init(&dc->disk.kobj, &bch_cached_dev_ktype);
 	INIT_WORK(&dc->detach, cached_dev_detach_finish);
 	sema_init(&dc->sb_write_mutex, 1);
@@ -1513,7 +1513,7 @@ static CLOSURE_CALLBACK(flash_dev_flush)
 	bcache_device_unlink(d);
 	mutex_unlock(&bch_register_lock);
 	kobject_del(&d->kobj);
-	continue_at(cl, flash_dev_free, system_wq);
+	continue_at(cl, flash_dev_free, system_percpu_wq);
 }
 
 static int flash_dev_run(struct cache_set *c, struct uuid_entry *u)
@@ -1525,7 +1525,7 @@ static int flash_dev_run(struct cache_set *c, struct uuid_entry *u)
 		goto err_ret;
 
 	closure_init(&d->cl, NULL);
-	set_closure_fn(&d->cl, flash_dev_flush, system_wq);
+	set_closure_fn(&d->cl, flash_dev_flush, system_percpu_wq);
 
 	kobject_init(&d->kobj, &bch_flash_dev_ktype);
 
@@ -1833,7 +1833,7 @@ static CLOSURE_CALLBACK(__cache_set_unregister)
 
 	mutex_unlock(&bch_register_lock);
 
-	continue_at(cl, cache_set_flush, system_wq);
+	continue_at(cl, cache_set_flush, system_percpu_wq);
 }
 
 void bch_cache_set_stop(struct cache_set *c)
@@ -1863,10 +1863,10 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb)
 
 	__module_get(THIS_MODULE);
 	closure_init(&c->cl, NULL);
-	set_closure_fn(&c->cl, cache_set_free, system_wq);
+	set_closure_fn(&c->cl, cache_set_free, system_percpu_wq);
 
 	closure_init(&c->caching, &c->cl);
-	set_closure_fn(&c->caching, __cache_set_unregister, system_wq);
+	set_closure_fn(&c->caching, __cache_set_unregister, system_percpu_wq);
 
 	/* Maybe create continue_at_noreturn() and use it here? */
 	closure_set_stopped(&c->cl);
@@ -1939,7 +1939,8 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb)
 	if (!c->uuids)
 		goto err;
 
-	c->moving_gc_wq = alloc_workqueue("bcache_gc", WQ_MEM_RECLAIM, 0);
+	c->moving_gc_wq = alloc_workqueue("bcache_gc",
+					  WQ_MEM_RECLAIM | WQ_PERCPU, 0);
 	if (!c->moving_gc_wq)
 		goto err;
 
@@ -2382,9 +2383,6 @@ static int register_cache(struct cache_sb *sb, struct cache_sb_disk *sb_disk,
 	ca->bdev = file_bdev(bdev_file);
 	ca->sb_disk = sb_disk;
 
-	if (bdev_max_discard_sectors(file_bdev(bdev_file)))
-		ca->discard = CACHE_DISCARD(&ca->sb);
-
 	ret = cache_alloc(ca);
 	if (ret != 0) {
 		if (ret == -ENOMEM)
@@ -2531,7 +2529,7 @@ static void register_device_async(struct async_reg_args *args)
 		INIT_DELAYED_WORK(&args->reg_work, register_cache_worker);
 
 	/* 10 jiffies is enough for a delay */
-	queue_delayed_work(system_wq, &args->reg_work, 10);
+	queue_delayed_work(system_percpu_wq, &args->reg_work, 10);
 }
 
 static void *alloc_holder_object(struct cache_sb *sb)
@@ -2905,24 +2903,25 @@ static int __init bcache_init(void)
 	if (bch_btree_init())
 		goto err;
 
-	bcache_wq = alloc_workqueue("bcache", WQ_MEM_RECLAIM, 0);
+	bcache_wq = alloc_workqueue("bcache", WQ_MEM_RECLAIM | WQ_PERCPU, 0);
 	if (!bcache_wq)
 		goto err;
 
 	/*
 	 * Let's not make this `WQ_MEM_RECLAIM` for the following reasons:
 	 *
-	 * 1. It used `system_wq` before which also does no memory reclaim.
+	 * 1. It used `system_percpu_wq` before which also does no memory reclaim.
 	 * 2. With `WQ_MEM_RECLAIM` desktop stalls, increased boot times, and
 	 *    reduced throughput can be observed.
 	 *
-	 * We still want to user our own queue to not congest the `system_wq`.
+	 * We still want to user our own queue to not congest the `system_percpu_wq`.
 	 */
-	bch_flush_wq = alloc_workqueue("bch_flush", 0, 0);
+	bch_flush_wq = alloc_workqueue("bch_flush", WQ_PERCPU, 0);
 	if (!bch_flush_wq)
 		goto err;
 
-	bch_journal_wq = alloc_workqueue("bch_journal", WQ_MEM_RECLAIM, 0);
+	bch_journal_wq = alloc_workqueue("bch_journal",
+					 WQ_MEM_RECLAIM | WQ_PERCPU, 0);
 	if (!bch_journal_wq)
 		goto err;
 
diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c
index 826b14cae4e5..72f38e5b6f5c 100644
--- a/drivers/md/bcache/sysfs.c
+++ b/drivers/md/bcache/sysfs.c
@@ -134,7 +134,6 @@ read_attribute(partial_stripes_expensive);
 rw_attribute(synchronous);
 rw_attribute(journal_delay_ms);
 rw_attribute(io_disable);
-rw_attribute(discard);
 rw_attribute(running);
 rw_attribute(label);
 rw_attribute(errors);
@@ -1036,7 +1035,6 @@ SHOW(__bch_cache)
 	sysfs_hprint(bucket_size,	bucket_bytes(ca));
 	sysfs_hprint(block_size,	block_bytes(ca));
 	sysfs_print(nbuckets,		ca->sb.nbuckets);
-	sysfs_print(discard,		ca->discard);
 	sysfs_hprint(written, atomic_long_read(&ca->sectors_written) << 9);
 	sysfs_hprint(btree_written,
 		     atomic_long_read(&ca->btree_sectors_written) << 9);
@@ -1142,18 +1140,6 @@ STORE(__bch_cache)
 	if (bcache_is_reboot)
 		return -EBUSY;
 
-	if (attr == &sysfs_discard) {
-		bool v = strtoul_or_return(buf);
-
-		if (bdev_max_discard_sectors(ca->bdev))
-			ca->discard = v;
-
-		if (v != CACHE_DISCARD(&ca->sb)) {
-			SET_CACHE_DISCARD(&ca->sb, v);
-			bcache_write_super(ca->set);
-		}
-	}
-
 	if (attr == &sysfs_cache_replacement_policy) {
 		v = __sysfs_match_string(cache_replacement_policies, -1, buf);
 		if (v < 0)
@@ -1185,7 +1171,6 @@ static struct attribute *bch_cache_attrs[] = {
 	&sysfs_block_size,
 	&sysfs_nbuckets,
 	&sysfs_priority_stats,
-	&sysfs_discard,
 	&sysfs_written,
 	&sysfs_btree_written,
 	&sysfs_metadata_written,
diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index 6ba73dc1a3df..4b237074f453 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -805,8 +805,7 @@ static int bch_writeback_thread(void *arg)
 			 * may set BCH_ENABLE_AUTO_GC via sysfs, then when
 			 * BCH_DO_AUTO_GC is set, garbage collection thread
 			 * will be wake up here. After moving gc, the shrunk
-			 * btree and discarded free buckets SSD space may be
-			 * helpful for following write requests.
+			 * btree may be helpful for following write requests.
 			 */
 			if (c->gc_after_writeback ==
 			    (BCH_ENABLE_AUTO_GC|BCH_DO_AUTO_GC)) {
@@ -1076,7 +1075,7 @@ void bch_cached_dev_writeback_init(struct cached_dev *dc)
 int bch_cached_dev_writeback_start(struct cached_dev *dc)
 {
 	dc->writeback_write_wq = alloc_workqueue("bcache_writeback_wq",
-						WQ_MEM_RECLAIM, 0);
+						WQ_MEM_RECLAIM | WQ_PERCPU, 0);
 	if (!dc->writeback_write_wq)
 		return -ENOMEM;
 
diff --git a/drivers/md/dm-zone.c b/drivers/md/dm-zone.c
index 78e17dd4d01b..5a840c4ae316 100644
--- a/drivers/md/dm-zone.c
+++ b/drivers/md/dm-zone.c
@@ -17,33 +17,26 @@
  * For internal zone reports bypassing the top BIO submission path.
  */
 static int dm_blk_do_report_zones(struct mapped_device *md, struct dm_table *t,
-				  sector_t sector, unsigned int nr_zones,
-				  report_zones_cb cb, void *data)
+				  unsigned int nr_zones,
+				  struct dm_report_zones_args *args)
 {
-	struct gendisk *disk = md->disk;
-	int ret;
-	struct dm_report_zones_args args = {
-		.next_sector = sector,
-		.orig_data = data,
-		.orig_cb = cb,
-	};
-
 	do {
 		struct dm_target *tgt;
+		int ret;
 
-		tgt = dm_table_find_target(t, args.next_sector);
+		tgt = dm_table_find_target(t, args->next_sector);
 		if (WARN_ON_ONCE(!tgt->type->report_zones))
 			return -EIO;
 
-		args.tgt = tgt;
-		ret = tgt->type->report_zones(tgt, &args,
-					      nr_zones - args.zone_idx);
+		args->tgt = tgt;
+		ret = tgt->type->report_zones(tgt, args,
+					      nr_zones - args->zone_idx);
 		if (ret < 0)
 			return ret;
-	} while (args.zone_idx < nr_zones &&
-		 args.next_sector < get_capacity(disk));
+	} while (args->zone_idx < nr_zones &&
+		 args->next_sector < get_capacity(md->disk));
 
-	return args.zone_idx;
+	return args->zone_idx;
 }
 
 /*
@@ -52,7 +45,8 @@ static int dm_blk_do_report_zones(struct mapped_device *md, struct dm_table *t,
  * generally implemented by targets using dm_report_zones().
  */
 int dm_blk_report_zones(struct gendisk *disk, sector_t sector,
-			unsigned int nr_zones, report_zones_cb cb, void *data)
+			unsigned int nr_zones,
+			struct blk_report_zones_args *args)
 {
 	struct mapped_device *md = disk->private_data;
 	struct dm_table *map;
@@ -76,9 +70,14 @@ int dm_blk_report_zones(struct gendisk *disk, sector_t sector,
 		map = zone_revalidate_map;
 	}
 
-	if (map)
-		ret = dm_blk_do_report_zones(md, map, sector, nr_zones, cb,
-					     data);
+	if (map) {
+		struct dm_report_zones_args dm_args = {
+			.disk = md->disk,
+			.next_sector = sector,
+			.rep_args = args,
+		};
+		ret = dm_blk_do_report_zones(md, map, nr_zones, &dm_args);
+	}
 
 	if (put_table)
 		dm_put_live_table(md, srcu_idx);
@@ -113,7 +112,18 @@ static int dm_report_zones_cb(struct blk_zone *zone, unsigned int idx,
 	}
 
 	args->next_sector = zone->start + zone->len;
-	return args->orig_cb(zone, args->zone_idx++, args->orig_data);
+
+	/* If we have an internal callback, call it first. */
+	if (args->cb) {
+		int ret;
+
+		ret = args->cb(zone, args->zone_idx, args->data);
+		if (ret)
+			return ret;
+	}
+
+	return disk_report_zone(args->disk, zone, args->zone_idx++,
+				args->rep_args);
 }
 
 /*
@@ -492,10 +502,15 @@ int dm_zone_get_reset_bitmap(struct mapped_device *md, struct dm_table *t,
 			     sector_t sector, unsigned int nr_zones,
 			     unsigned long *need_reset)
 {
+	struct dm_report_zones_args args = {
+		.disk = md->disk,
+		.next_sector = sector,
+		.cb = dm_zone_need_reset_cb,
+		.data = need_reset,
+	};
 	int ret;
 
-	ret = dm_blk_do_report_zones(md, t, sector, nr_zones,
-				     dm_zone_need_reset_cb, need_reset);
+	ret = dm_blk_do_report_zones(md, t, nr_zones, &args);
 	if (ret != nr_zones) {
 		DMERR("Get %s zone reset bitmap failed\n",
 		      md->disk->disk_name);
diff --git a/drivers/md/dm.h b/drivers/md/dm.h
index 245f52b59215..7a795979ec72 100644
--- a/drivers/md/dm.h
+++ b/drivers/md/dm.h
@@ -109,7 +109,8 @@ void dm_finalize_zone_settings(struct dm_table *t, struct queue_limits *lim);
 void dm_zone_endio(struct dm_io *io, struct bio *clone);
 #ifdef CONFIG_BLK_DEV_ZONED
 int dm_blk_report_zones(struct gendisk *disk, sector_t sector,
-			unsigned int nr_zones, report_zones_cb cb, void *data);
+			unsigned int nr_zones,
+			struct blk_report_zones_args *args);
 bool dm_is_zone_write(struct mapped_device *md, struct bio *bio);
 int dm_zone_get_reset_bitmap(struct mapped_device *md, struct dm_table *t,
 			     sector_t sector, unsigned int nr_zones,
diff --git a/drivers/md/md-linear.c b/drivers/md/md-linear.c
index 7033d982d377..8d7b82c4a723 100644
--- a/drivers/md/md-linear.c
+++ b/drivers/md/md-linear.c
@@ -72,9 +72,11 @@ static int linear_set_limits(struct mddev *mddev)
 
 	md_init_stacking_limits(&lim);
 	lim.max_hw_sectors = mddev->chunk_sectors;
+	lim.logical_block_size = mddev->logical_block_size;
 	lim.max_write_zeroes_sectors = mddev->chunk_sectors;
 	lim.max_hw_wzeroes_unmap_sectors = mddev->chunk_sectors;
 	lim.io_min = mddev->chunk_sectors << 9;
+	lim.features |= BLK_FEAT_ATOMIC_WRITES;
 	err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY);
 	if (err)
 		return err;
diff --git a/drivers/md/md-llbitmap.c b/drivers/md/md-llbitmap.c
index 1eb434306162..9c1ade19b774 100644
--- a/drivers/md/md-llbitmap.c
+++ b/drivers/md/md-llbitmap.c
@@ -378,7 +378,7 @@ static void llbitmap_infect_dirty_bits(struct llbitmap *llbitmap,
 		case BitClean:
 			pctl->state[pos] = BitDirty;
 			break;
-		};
+		}
 	}
 }
 
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 41c476b40c7a..e5922a682953 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -99,7 +99,7 @@ static int remove_and_add_spares(struct mddev *mddev,
 				 struct md_rdev *this);
 static void mddev_detach(struct mddev *mddev);
 static void export_rdev(struct md_rdev *rdev, struct mddev *mddev);
-static void md_wakeup_thread_directly(struct md_thread __rcu *thread);
+static void md_wakeup_thread_directly(struct md_thread __rcu **thread);
 
 /*
  * Default number of read corrections we'll attempt on an rdev
@@ -339,6 +339,7 @@ static int start_readonly;
  */
 static bool create_on_open = true;
 static bool legacy_async_del_gendisk = true;
+static bool check_new_feature = true;
 
 /*
  * We have a system wide 'event count' that is incremented
@@ -730,6 +731,8 @@ static void mddev_clear_bitmap_ops(struct mddev *mddev)
 
 int mddev_init(struct mddev *mddev)
 {
+	int err = 0;
+
 	if (!IS_ENABLED(CONFIG_MD_BITMAP))
 		mddev->bitmap_id = ID_BITMAP_NONE;
 	else
@@ -741,10 +744,23 @@ int mddev_init(struct mddev *mddev)
 
 	if (percpu_ref_init(&mddev->writes_pending, no_op,
 			    PERCPU_REF_ALLOW_REINIT, GFP_KERNEL)) {
-		percpu_ref_exit(&mddev->active_io);
-		return -ENOMEM;
+		err = -ENOMEM;
+		goto exit_acitve_io;
 	}
 
+	err = bioset_init(&mddev->bio_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
+	if (err)
+		goto exit_writes_pending;
+
+	err = bioset_init(&mddev->sync_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
+	if (err)
+		goto exit_bio_set;
+
+	err = bioset_init(&mddev->io_clone_set, BIO_POOL_SIZE,
+			  offsetof(struct md_io_clone, bio_clone), 0);
+	if (err)
+		goto exit_sync_set;
+
 	/* We want to start with the refcount at zero */
 	percpu_ref_put(&mddev->writes_pending);
 
@@ -773,11 +789,24 @@ int mddev_init(struct mddev *mddev)
 	INIT_WORK(&mddev->del_work, mddev_delayed_delete);
 
 	return 0;
+
+exit_sync_set:
+	bioset_exit(&mddev->sync_set);
+exit_bio_set:
+	bioset_exit(&mddev->bio_set);
+exit_writes_pending:
+	percpu_ref_exit(&mddev->writes_pending);
+exit_acitve_io:
+	percpu_ref_exit(&mddev->active_io);
+	return err;
 }
 EXPORT_SYMBOL_GPL(mddev_init);
 
 void mddev_destroy(struct mddev *mddev)
 {
+	bioset_exit(&mddev->bio_set);
+	bioset_exit(&mddev->sync_set);
+	bioset_exit(&mddev->io_clone_set);
 	percpu_ref_exit(&mddev->active_io);
 	percpu_ref_exit(&mddev->writes_pending);
 }
@@ -941,8 +970,11 @@ void mddev_unlock(struct mddev *mddev)
 		 * 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))
+		if (test_bit(MD_DELETED, &mddev->flags) &&
+		    !test_and_set_bit(MD_DO_DELETE, &mddev->flags)) {
+			kobject_del(&mddev->kobj);
 			del_gendisk(mddev->gendisk);
+		}
 	}
 }
 EXPORT_SYMBOL_GPL(mddev_unlock);
@@ -1820,9 +1852,13 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_
 	}
 	if (sb->pad0 ||
 	    sb->pad3[0] ||
-	    memcmp(sb->pad3, sb->pad3+1, sizeof(sb->pad3) - sizeof(sb->pad3[1])))
-		/* Some padding is non-zero, might be a new feature */
-		return -EINVAL;
+	    memcmp(sb->pad3, sb->pad3+1, sizeof(sb->pad3) - sizeof(sb->pad3[1]))) {
+		pr_warn("Some padding is non-zero on %pg, might be a new feature\n",
+			rdev->bdev);
+		if (check_new_feature)
+			return -EINVAL;
+		pr_warn("check_new_feature is disabled, data corruption possible\n");
+	}
 
 	rdev->preferred_minor = 0xffff;
 	rdev->data_offset = le64_to_cpu(sb->data_offset);
@@ -1963,6 +1999,7 @@ 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;
@@ -2172,6 +2209,7 @@ static void super_1_sync(struct mddev *mddev, struct md_rdev *rdev)
 	sb->chunksize = cpu_to_le32(mddev->chunk_sectors);
 	sb->level = cpu_to_le32(mddev->level);
 	sb->layout = cpu_to_le32(mddev->layout);
+	sb->logical_block_size = cpu_to_le32(mddev->logical_block_size);
 	if (test_bit(FailFast, &rdev->flags))
 		sb->devflags |= FailFast1;
 	else
@@ -2750,6 +2788,7 @@ void md_update_sb(struct mddev *mddev, int force_change)
 	if (!md_is_rdwr(mddev)) {
 		if (force_change)
 			set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
+		pr_err("%s: can't update sb for read-only array %s\n", __func__, mdname(mddev));
 		return;
 	}
 
@@ -5134,7 +5173,7 @@ static void stop_sync_thread(struct mddev *mddev, bool locked)
 	 * Thread might be blocked waiting for metadata update which will now
 	 * never happen
 	 */
-	md_wakeup_thread_directly(mddev->sync_thread);
+	md_wakeup_thread_directly(&mddev->sync_thread);
 	if (work_pending(&mddev->sync_work))
 		flush_work(&mddev->sync_work);
 
@@ -5900,6 +5939,68 @@ static struct md_sysfs_entry md_serialize_policy =
 __ATTR(serialize_policy, S_IRUGO | S_IWUSR, serialize_policy_show,
        serialize_policy_store);
 
+static int mddev_set_logical_block_size(struct mddev *mddev,
+				unsigned int lbs)
+{
+	int err = 0;
+	struct queue_limits lim;
+
+	if (queue_logical_block_size(mddev->gendisk->queue) >= lbs) {
+		pr_err("%s: Cannot set LBS smaller than mddev LBS %u\n",
+		       mdname(mddev), lbs);
+		return -EINVAL;
+	}
+
+	lim = queue_limits_start_update(mddev->gendisk->queue);
+	lim.logical_block_size = lbs;
+	pr_info("%s: logical_block_size is changed, data may be lost\n",
+		mdname(mddev));
+	err = queue_limits_commit_update(mddev->gendisk->queue, &lim);
+	if (err)
+		return err;
+
+	mddev->logical_block_size = lbs;
+	/* New lbs will be written to superblock after array is running */
+	set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
+	return 0;
+}
+
+static ssize_t
+lbs_show(struct mddev *mddev, char *page)
+{
+	return sprintf(page, "%u\n", mddev->logical_block_size);
+}
+
+static ssize_t
+lbs_store(struct mddev *mddev, const char *buf, size_t len)
+{
+	unsigned int lbs;
+	int err = -EBUSY;
+
+	/* Only 1.x meta supports configurable LBS */
+	if (mddev->major_version == 0)
+		return -EINVAL;
+
+	if (mddev->pers)
+		return -EBUSY;
+
+	err = kstrtouint(buf, 10, &lbs);
+	if (err < 0)
+		return -EINVAL;
+
+	err = mddev_lock(mddev);
+	if (err)
+		goto unlock;
+
+	err = mddev_set_logical_block_size(mddev, lbs);
+
+unlock:
+	mddev_unlock(mddev);
+	return err ?: len;
+}
+
+static struct md_sysfs_entry md_logical_block_size =
+__ATTR(logical_block_size, 0644, lbs_show, lbs_store);
 
 static struct attribute *md_default_attrs[] = {
 	&md_level.attr,
@@ -5922,6 +6023,7 @@ static struct attribute *md_default_attrs[] = {
 	&md_consistency_policy.attr,
 	&md_fail_last_dev.attr,
 	&md_serialize_policy.attr,
+	&md_logical_block_size.attr,
 	NULL,
 };
 
@@ -6052,6 +6154,17 @@ int mddev_stack_rdev_limits(struct mddev *mddev, struct queue_limits *lim,
 			return -EINVAL;
 	}
 
+	/*
+	 * Before RAID adding folio support, the logical_block_size
+	 * should be smaller than the page size.
+	 */
+	if (lim->logical_block_size > PAGE_SIZE) {
+		pr_err("%s: logical_block_size must not larger than PAGE_SIZE\n",
+			mdname(mddev));
+		return -EINVAL;
+	}
+	mddev->logical_block_size = lim->logical_block_size;
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(mddev_stack_rdev_limits);
@@ -6064,6 +6177,13 @@ int mddev_stack_new_rdev(struct mddev *mddev, struct md_rdev *rdev)
 	if (mddev_is_dm(mddev))
 		return 0;
 
+	if (queue_logical_block_size(rdev->bdev->bd_disk->queue) >
+	    queue_logical_block_size(mddev->gendisk->queue)) {
+		pr_err("%s: incompatible logical_block_size, can not add\n",
+		       mdname(mddev));
+		return -EINVAL;
+	}
+
 	lim = queue_limits_start_update(mddev->gendisk->queue);
 	queue_limits_stack_bdev(&lim, rdev->bdev, rdev->data_offset,
 				mddev->gendisk->disk_name);
@@ -6384,29 +6504,9 @@ int md_run(struct mddev *mddev)
 		nowait = nowait && bdev_nowait(rdev->bdev);
 	}
 
-	if (!bioset_initialized(&mddev->bio_set)) {
-		err = bioset_init(&mddev->bio_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
-		if (err)
-			return err;
-	}
-	if (!bioset_initialized(&mddev->sync_set)) {
-		err = bioset_init(&mddev->sync_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
-		if (err)
-			goto exit_bio_set;
-	}
-
-	if (!bioset_initialized(&mddev->io_clone_set)) {
-		err = bioset_init(&mddev->io_clone_set, BIO_POOL_SIZE,
-				  offsetof(struct md_io_clone, bio_clone), 0);
-		if (err)
-			goto exit_sync_set;
-	}
-
 	pers = get_pers(mddev->level, mddev->clevel);
-	if (!pers) {
-		err = -EINVAL;
-		goto abort;
-	}
+	if (!pers)
+		return -EINVAL;
 	if (mddev->level != pers->head.id) {
 		mddev->level = pers->head.id;
 		mddev->new_level = pers->head.id;
@@ -6417,8 +6517,7 @@ int md_run(struct mddev *mddev)
 	    pers->start_reshape == NULL) {
 		/* This personality cannot handle reshaping... */
 		put_pers(pers);
-		err = -EINVAL;
-		goto abort;
+		return -EINVAL;
 	}
 
 	if (pers->sync_request) {
@@ -6545,12 +6644,6 @@ bitmap_abort:
 	mddev->private = NULL;
 	put_pers(pers);
 	md_bitmap_destroy(mddev);
-abort:
-	bioset_exit(&mddev->io_clone_set);
-exit_sync_set:
-	bioset_exit(&mddev->sync_set);
-exit_bio_set:
-	bioset_exit(&mddev->bio_set);
 	return err;
 }
 EXPORT_SYMBOL_GPL(md_run);
@@ -6683,6 +6776,7 @@ static void md_clean(struct mddev *mddev)
 	mddev->chunk_sectors = 0;
 	mddev->ctime = mddev->utime = 0;
 	mddev->layout = 0;
+	mddev->logical_block_size = 0;
 	mddev->max_disks = 0;
 	mddev->events = 0;
 	mddev->can_decrease_events = 0;
@@ -6775,10 +6869,6 @@ static void __md_stop(struct mddev *mddev)
 	mddev->private = NULL;
 	put_pers(pers);
 	clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
-
-	bioset_exit(&mddev->bio_set);
-	bioset_exit(&mddev->sync_set);
-	bioset_exit(&mddev->io_clone_set);
 }
 
 void md_stop(struct mddev *mddev)
@@ -6869,6 +6959,10 @@ static int do_md_stop(struct mddev *mddev, int mode)
 		if (!md_is_rdwr(mddev))
 			set_disk_ro(disk, 0);
 
+		if (mode == 2 && mddev->pers->sync_request &&
+		    mddev->to_remove == NULL)
+			mddev->to_remove = &md_redundancy_group;
+
 		__md_stop_writes(mddev);
 		__md_stop(mddev);
 
@@ -8373,22 +8467,21 @@ static int md_thread(void *arg)
 	return 0;
 }
 
-static void md_wakeup_thread_directly(struct md_thread __rcu *thread)
+static void md_wakeup_thread_directly(struct md_thread __rcu **thread)
 {
 	struct md_thread *t;
 
 	rcu_read_lock();
-	t = rcu_dereference(thread);
+	t = rcu_dereference(*thread);
 	if (t)
 		wake_up_process(t->tsk);
 	rcu_read_unlock();
 }
 
-void md_wakeup_thread(struct md_thread __rcu *thread)
+void __md_wakeup_thread(struct md_thread __rcu *thread)
 {
 	struct md_thread *t;
 
-	rcu_read_lock();
 	t = rcu_dereference(thread);
 	if (t) {
 		pr_debug("md: waking up MD thread %s.\n", t->tsk->comm);
@@ -8396,9 +8489,8 @@ void md_wakeup_thread(struct md_thread __rcu *thread)
 		if (wq_has_sleeper(&t->wqueue))
 			wake_up(&t->wqueue);
 	}
-	rcu_read_unlock();
 }
-EXPORT_SYMBOL(md_wakeup_thread);
+EXPORT_SYMBOL(__md_wakeup_thread);
 
 struct md_thread *md_register_thread(void (*run) (struct md_thread *),
 		struct mddev *mddev, const char *name)
@@ -9978,6 +10070,52 @@ static void unregister_sync_thread(struct mddev *mddev)
 	md_reap_sync_thread(mddev);
 }
 
+static bool md_should_do_recovery(struct mddev *mddev)
+{
+	/*
+	 * As long as one of the following flags is set,
+	 * recovery needs to do or cleanup.
+	 */
+	if (test_bit(MD_RECOVERY_NEEDED, &mddev->recovery) ||
+	    test_bit(MD_RECOVERY_DONE, &mddev->recovery))
+		return true;
+
+	/*
+	 * If no flags are set and it is in read-only status,
+	 * there is nothing to do.
+	 */
+	if (!md_is_rdwr(mddev))
+		return false;
+
+	/*
+	 * MD_SB_CHANGE_PENDING indicates that the array is switching from clean to
+	 * active, and no action is needed for now.
+	 * All other MD_SB_* flags require to update the superblock.
+	 */
+	if (mddev->sb_flags & ~ (1<<MD_SB_CHANGE_PENDING))
+		return true;
+
+	/*
+	 * If the array is not using external metadata and there has been no data
+	 * written for some time, then the array's status needs to be set to
+	 * in_sync.
+	 */
+	if (mddev->external == 0 && mddev->safemode == 1)
+		return true;
+
+	/*
+	 * When the system is about to restart or the process receives an signal,
+	 * the array needs to be synchronized as soon as possible.
+	 * Once the data synchronization is completed, need to change the array
+	 * status to in_sync.
+	 */
+	if (mddev->safemode == 2 && !mddev->in_sync &&
+	    mddev->resync_offset == MaxSector)
+		return true;
+
+	return false;
+}
+
 /*
  * This routine is regularly called by all per-raid-array threads to
  * deal with generic issues like resync and super-block update.
@@ -10014,18 +10152,7 @@ void md_check_recovery(struct mddev *mddev)
 		flush_signals(current);
 	}
 
-	if (!md_is_rdwr(mddev) &&
-	    !test_bit(MD_RECOVERY_NEEDED, &mddev->recovery) &&
-	    !test_bit(MD_RECOVERY_DONE, &mddev->recovery))
-		return;
-	if ( ! (
-		(mddev->sb_flags & ~ (1<<MD_SB_CHANGE_PENDING)) ||
-		test_bit(MD_RECOVERY_NEEDED, &mddev->recovery) ||
-		test_bit(MD_RECOVERY_DONE, &mddev->recovery) ||
-		(mddev->external == 0 && mddev->safemode == 1) ||
-		(mddev->safemode == 2
-		 && !mddev->in_sync && mddev->resync_offset == MaxSector)
-		))
+	if (!md_should_do_recovery(mddev))
 		return;
 
 	if (mddev_trylock(mddev)) {
@@ -10281,7 +10408,6 @@ static int md_notify_reboot(struct notifier_block *this,
 			    unsigned long code, void *x)
 {
 	struct mddev *mddev;
-	int need_delay = 0;
 
 	spin_lock(&all_mddevs_lock);
 	list_for_each_entry(mddev, &all_mddevs, all_mddevs) {
@@ -10295,21 +10421,11 @@ static int md_notify_reboot(struct notifier_block *this,
 				mddev->safemode = 2;
 			mddev_unlock(mddev);
 		}
-		need_delay = 1;
 		spin_lock(&all_mddevs_lock);
 		mddev_put_locked(mddev);
 	}
 	spin_unlock(&all_mddevs_lock);
 
-	/*
-	 * certain more exotic SCSI devices are known to be
-	 * volatile wrt too early system reboots. While the
-	 * right place to handle this issue is the given
-	 * driver, we do want to have a safe RAID driver ...
-	 */
-	if (need_delay)
-		msleep(1000);
-
 	return NOTIFY_DONE;
 }
 
@@ -10697,6 +10813,7 @@ 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_param(check_new_feature, bool, 0600);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("MD RAID framework");
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 1979c2d4fe89..6985f2829bbd 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -354,6 +354,7 @@ enum mddev_flags {
 	MD_HAS_MULTIPLE_PPLS,
 	MD_NOT_READY,
 	MD_BROKEN,
+	MD_DO_DELETE,
 	MD_DELETED,
 };
 
@@ -432,6 +433,7 @@ struct mddev {
 	sector_t			array_sectors; /* exported array size */
 	int				external_size; /* size managed
 							* externally */
+	unsigned int			logical_block_size;
 	__u64				events;
 	/* If the last 'event' was simply a clean->dirty transition, and
 	 * we didn't write it to the spares, then it is safe and simple
@@ -882,6 +884,12 @@ struct md_io_clone {
 
 #define THREAD_WAKEUP  0
 
+#define md_wakeup_thread(thread) do {   \
+	rcu_read_lock();                    \
+	__md_wakeup_thread(thread);         \
+	rcu_read_unlock();                  \
+} while (0)
+
 static inline void safe_put_page(struct page *p)
 {
 	if (p) put_page(p);
@@ -895,7 +903,7 @@ extern struct md_thread *md_register_thread(
 	struct mddev *mddev,
 	const char *name);
 extern void md_unregister_thread(struct mddev *mddev, struct md_thread __rcu **threadp);
-extern void md_wakeup_thread(struct md_thread __rcu *thread);
+extern void __md_wakeup_thread(struct md_thread __rcu *thread);
 extern void md_check_recovery(struct mddev *mddev);
 extern void md_reap_sync_thread(struct mddev *mddev);
 extern enum sync_action md_sync_action(struct mddev *mddev);
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index e443e478645a..985c377356eb 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -68,7 +68,10 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf)
 	struct strip_zone *zone;
 	int cnt;
 	struct r0conf *conf = kzalloc(sizeof(*conf), GFP_KERNEL);
-	unsigned blksize = 512;
+	unsigned int blksize = 512;
+
+	if (!mddev_is_dm(mddev))
+		blksize = queue_logical_block_size(mddev->gendisk->queue);
 
 	*private_conf = ERR_PTR(-ENOMEM);
 	if (!conf)
@@ -84,7 +87,8 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf)
 		sector_div(sectors, mddev->chunk_sectors);
 		rdev1->sectors = sectors * mddev->chunk_sectors;
 
-		blksize = max(blksize, queue_logical_block_size(
+		if (mddev_is_dm(mddev))
+			blksize = max(blksize, queue_logical_block_size(
 				      rdev1->bdev->bd_disk->queue));
 
 		rdev_for_each(rdev2, mddev) {
@@ -383,6 +387,7 @@ static int raid0_set_limits(struct mddev *mddev)
 	lim.max_hw_sectors = mddev->chunk_sectors;
 	lim.max_write_zeroes_sectors = mddev->chunk_sectors;
 	lim.max_hw_wzeroes_unmap_sectors = mddev->chunk_sectors;
+	lim.logical_block_size = mddev->logical_block_size;
 	lim.io_min = mddev->chunk_sectors << 9;
 	lim.io_opt = lim.io_min * mddev->raid_disks;
 	lim.chunk_sectors = mddev->chunk_sectors;
@@ -405,6 +410,12 @@ static int raid0_run(struct mddev *mddev)
 	if (md_check_no_bitmap(mddev))
 		return -EINVAL;
 
+	if (!mddev_is_dm(mddev)) {
+		ret = raid0_set_limits(mddev);
+		if (ret)
+			return ret;
+	}
+
 	/* if private is not null, we are here after takeover */
 	if (mddev->private == NULL) {
 		ret = create_strip_zones(mddev, &conf);
@@ -413,11 +424,6 @@ static int raid0_run(struct mddev *mddev)
 		mddev->private = conf;
 	}
 	conf = mddev->private;
-	if (!mddev_is_dm(mddev)) {
-		ret = raid0_set_limits(mddev);
-		if (ret)
-			return ret;
-	}
 
 	/* calculate array device size */
 	md_set_array_sectors(mddev, raid0_size(mddev, 0, 0));
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 592a40233004..57d50465eed1 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -3213,6 +3213,7 @@ static int raid1_set_limits(struct mddev *mddev)
 	md_init_stacking_limits(&lim);
 	lim.max_write_zeroes_sectors = 0;
 	lim.max_hw_wzeroes_unmap_sectors = 0;
+	lim.logical_block_size = mddev->logical_block_size;
 	lim.features |= BLK_FEAT_ATOMIC_WRITES;
 	err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY);
 	if (err)
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 14dcd5142eb4..84be4cc7e873 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -4000,6 +4000,7 @@ static int raid10_set_queue_limits(struct mddev *mddev)
 	md_init_stacking_limits(&lim);
 	lim.max_write_zeroes_sectors = 0;
 	lim.max_hw_wzeroes_unmap_sectors = 0;
+	lim.logical_block_size = mddev->logical_block_size;
 	lim.io_min = mddev->chunk_sectors << 9;
 	lim.chunk_sectors = mddev->chunk_sectors;
 	lim.io_opt = lim.io_min * raid10_nr_stripes(conf);
diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c
index ba768ca7f422..e29e69335c69 100644
--- a/drivers/md/raid5-cache.c
+++ b/drivers/md/raid5-cache.c
@@ -3104,7 +3104,7 @@ int r5l_init_log(struct r5conf *conf, struct md_rdev *rdev)
 		goto out_mempool;
 
 	spin_lock_init(&log->tree_lock);
-	INIT_RADIX_TREE(&log->big_stripe_tree, GFP_NOWAIT | __GFP_NOWARN);
+	INIT_RADIX_TREE(&log->big_stripe_tree, GFP_NOWAIT);
 
 	thread = md_register_thread(r5l_reclaim_thread, log->rdev->mddev,
 				    "reclaim");
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 24b32a0c95b4..e57ce3295292 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -4956,7 +4956,8 @@ static void handle_stripe(struct stripe_head *sh)
 		goto finish;
 
 	if (s.handle_bad_blocks ||
-	    test_bit(MD_SB_CHANGE_PENDING, &conf->mddev->sb_flags)) {
+	    (md_is_rdwr(conf->mddev) &&
+	     test_bit(MD_SB_CHANGE_PENDING, &conf->mddev->sb_flags))) {
 		set_bit(STRIPE_HANDLE, &sh->state);
 		goto finish;
 	}
@@ -6768,7 +6769,8 @@ static void raid5d(struct md_thread *thread)
 		int batch_size, released;
 		unsigned int offset;
 
-		if (test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags))
+		if (md_is_rdwr(mddev) &&
+		    test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags))
 			break;
 
 		released = release_stripe_list(conf, conf->temp_inactive_list);
@@ -7745,6 +7747,7 @@ static int raid5_set_limits(struct mddev *mddev)
 	stripe = roundup_pow_of_two(data_disks * (mddev->chunk_sectors << 9));
 
 	md_init_stacking_limits(&lim);
+	lim.logical_block_size = mddev->logical_block_size;
 	lim.io_min = mddev->chunk_sectors << 9;
 	lim.io_opt = lim.io_min * (conf->raid_disks - conf->max_degraded);
 	lim.features |= BLK_FEAT_RAID_PARTIAL_STRIPES_EXPENSIVE;