Adding upstream version 6.7.7.upstream/6.7.7

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

47 files changed, 1599 insertions, 1730 deletions

diff --git a/drivers/md/bcache/Kconfig b/drivers/md/bcache/Kconfig
index 529c9d04e9..b2d10063d3 100644
--- a/drivers/md/bcache/Kconfig
+++ b/drivers/md/bcache/Kconfig
@@ -4,6 +4,7 @@ config BCACHE
 	tristate "Block device as cache"
 	select BLOCK_HOLDER_DEPRECATED if SYSFS
 	select CRC64
+	select CLOSURES
 	help
 	Allows a block device to be used as cache for other devices; uses
 	a btree for indexing and the layout is optimized for SSDs.
@@ -19,15 +20,6 @@ config BCACHE_DEBUG
 	Enables extra debugging tools, allows expensive runtime checks to be
 	turned on.
 
-config BCACHE_CLOSURES_DEBUG
-	bool "Debug closures"
-	depends on BCACHE
-	select DEBUG_FS
-	help
-	Keeps all active closures in a linked list and provides a debugfs
-	interface to list them, which makes it possible to see asynchronous
-	operations that get stuck.
-
 config BCACHE_ASYNC_REGISTRATION
 	bool "Asynchronous device registration"
 	depends on BCACHE
diff --git a/drivers/md/bcache/Makefile b/drivers/md/bcache/Makefile
index 5b87e59676..054e8a33a7 100644
--- a/drivers/md/bcache/Makefile
+++ b/drivers/md/bcache/Makefile
@@ -2,6 +2,6 @@
 
 obj-$(CONFIG_BCACHE)	+= bcache.o
 
-bcache-y		:= alloc.o bset.o btree.o closure.o debug.o extents.o\
-	io.o journal.o movinggc.o request.o stats.o super.o sysfs.o trace.o\
+bcache-y		:= alloc.o bset.o btree.o debug.o extents.o io.o\
+	journal.o movinggc.o request.o stats.o super.o sysfs.o trace.o\
 	util.o writeback.o features.o
diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index 83eb7f27db..6ae2329052 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -179,6 +179,7 @@
 #define pr_fmt(fmt) "bcache: %s() " fmt, __func__
 
 #include <linux/bio.h>
+#include <linux/closure.h>
 #include <linux/kobject.h>
 #include <linux/list.h>
 #include <linux/mutex.h>
@@ -192,7 +193,6 @@
 #include "bcache_ondisk.h"
 #include "bset.h"
 #include "util.h"
-#include "closure.h"
 
 struct bucket {
 	atomic_t	pin;
@@ -300,6 +300,7 @@ struct cached_dev {
 	struct list_head	list;
 	struct bcache_device	disk;
 	struct block_device	*bdev;
+	struct bdev_handle	*bdev_handle;
 
 	struct cache_sb		sb;
 	struct cache_sb_disk	*sb_disk;
@@ -422,6 +423,7 @@ struct cache {
 
 	struct kobject		kobj;
 	struct block_device	*bdev;
+	struct bdev_handle	*bdev_handle;
 
 	struct task_struct	*alloc_thread;
 
@@ -542,7 +544,7 @@ struct cache_set {
 	struct bio_set		bio_split;
 
 	/* For the btree cache */
-	struct shrinker		shrink;
+	struct shrinker		*shrink;
 
 	/* For the btree cache and anything allocation related */
 	struct mutex		bucket_lock;
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index b709c2fde7..196cdacce3 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -293,16 +293,16 @@ static void btree_complete_write(struct btree *b, struct btree_write *w)
 	w->journal	= NULL;
 }
 
-static void btree_node_write_unlock(struct closure *cl)
+static CLOSURE_CALLBACK(btree_node_write_unlock)
 {
-	struct btree *b = container_of(cl, struct btree, io);
+	closure_type(b, struct btree, io);
 
 	up(&b->io_mutex);
 }
 
-static void __btree_node_write_done(struct closure *cl)
+static CLOSURE_CALLBACK(__btree_node_write_done)
 {
-	struct btree *b = container_of(cl, struct btree, io);
+	closure_type(b, struct btree, io);
 	struct btree_write *w = btree_prev_write(b);
 
 	bch_bbio_free(b->bio, b->c);
@@ -315,12 +315,12 @@ static void __btree_node_write_done(struct closure *cl)
 	closure_return_with_destructor(cl, btree_node_write_unlock);
 }
 
-static void btree_node_write_done(struct closure *cl)
+static CLOSURE_CALLBACK(btree_node_write_done)
 {
-	struct btree *b = container_of(cl, struct btree, io);
+	closure_type(b, struct btree, io);
 
 	bio_free_pages(b->bio);
-	__btree_node_write_done(cl);
+	__btree_node_write_done(&cl->work);
 }
 
 static void btree_node_write_endio(struct bio *bio)
@@ -667,7 +667,7 @@ out_unlock:
 static unsigned long bch_mca_scan(struct shrinker *shrink,
 				  struct shrink_control *sc)
 {
-	struct cache_set *c = container_of(shrink, struct cache_set, shrink);
+	struct cache_set *c = shrink->private_data;
 	struct btree *b, *t;
 	unsigned long i, nr = sc->nr_to_scan;
 	unsigned long freed = 0;
@@ -734,7 +734,7 @@ out:
 static unsigned long bch_mca_count(struct shrinker *shrink,
 				   struct shrink_control *sc)
 {
-	struct cache_set *c = container_of(shrink, struct cache_set, shrink);
+	struct cache_set *c = shrink->private_data;
 
 	if (c->shrinker_disabled)
 		return 0;
@@ -752,8 +752,8 @@ void bch_btree_cache_free(struct cache_set *c)
 
 	closure_init_stack(&cl);
 
-	if (c->shrink.list.next)
-		unregister_shrinker(&c->shrink);
+	if (c->shrink)
+		shrinker_free(c->shrink);
 
 	mutex_lock(&c->bucket_lock);
 
@@ -828,14 +828,19 @@ int bch_btree_cache_alloc(struct cache_set *c)
 		c->verify_data = NULL;
 #endif
 
-	c->shrink.count_objects = bch_mca_count;
-	c->shrink.scan_objects = bch_mca_scan;
-	c->shrink.seeks = 4;
-	c->shrink.batch = c->btree_pages * 2;
+	c->shrink = shrinker_alloc(0, "md-bcache:%pU", c->set_uuid);
+	if (!c->shrink) {
+		pr_warn("bcache: %s: could not allocate shrinker\n", __func__);
+		return 0;
+	}
+
+	c->shrink->count_objects = bch_mca_count;
+	c->shrink->scan_objects = bch_mca_scan;
+	c->shrink->seeks = 4;
+	c->shrink->batch = c->btree_pages * 2;
+	c->shrink->private_data = c;
 
-	if (register_shrinker(&c->shrink, "md-bcache:%pU", c->set_uuid))
-		pr_warn("bcache: %s: could not register shrinker\n",
-				__func__);
+	shrinker_register(c->shrink);
 
 	return 0;
 }
diff --git a/drivers/md/bcache/closure.c b/drivers/md/bcache/closure.c
deleted file mode 100644
index d8d9394a6b..0000000000
--- a/drivers/md/bcache/closure.c
+++ /dev/null
@@ -1,207 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Asynchronous refcounty things
- *
- * Copyright 2010, 2011 Kent Overstreet <kent.overstreet@gmail.com>
- * Copyright 2012 Google, Inc.
- */
-
-#include <linux/debugfs.h>
-#include <linux/module.h>
-#include <linux/seq_file.h>
-#include <linux/sched/debug.h>
-
-#include "closure.h"
-
-static inline void closure_put_after_sub(struct closure *cl, int flags)
-{
-	int r = flags & CLOSURE_REMAINING_MASK;
-
-	BUG_ON(flags & CLOSURE_GUARD_MASK);
-	BUG_ON(!r && (flags & ~CLOSURE_DESTRUCTOR));
-
-	if (!r) {
-		if (cl->fn && !(flags & CLOSURE_DESTRUCTOR)) {
-			atomic_set(&cl->remaining,
-				   CLOSURE_REMAINING_INITIALIZER);
-			closure_queue(cl);
-		} else {
-			struct closure *parent = cl->parent;
-			closure_fn *destructor = cl->fn;
-
-			closure_debug_destroy(cl);
-
-			if (destructor)
-				destructor(cl);
-
-			if (parent)
-				closure_put(parent);
-		}
-	}
-}
-
-/* For clearing flags with the same atomic op as a put */
-void closure_sub(struct closure *cl, int v)
-{
-	closure_put_after_sub(cl, atomic_sub_return(v, &cl->remaining));
-}
-
-/*
- * closure_put - decrement a closure's refcount
- */
-void closure_put(struct closure *cl)
-{
-	closure_put_after_sub(cl, atomic_dec_return(&cl->remaining));
-}
-
-/*
- * closure_wake_up - wake up all closures on a wait list, without memory barrier
- */
-void __closure_wake_up(struct closure_waitlist *wait_list)
-{
-	struct llist_node *list;
-	struct closure *cl, *t;
-	struct llist_node *reverse = NULL;
-
-	list = llist_del_all(&wait_list->list);
-
-	/* We first reverse the list to preserve FIFO ordering and fairness */
-	reverse = llist_reverse_order(list);
-
-	/* Then do the wakeups */
-	llist_for_each_entry_safe(cl, t, reverse, list) {
-		closure_set_waiting(cl, 0);
-		closure_sub(cl, CLOSURE_WAITING + 1);
-	}
-}
-
-/**
- * closure_wait - add a closure to a waitlist
- * @waitlist: will own a ref on @cl, which will be released when
- * closure_wake_up() is called on @waitlist.
- * @cl: closure pointer.
- *
- */
-bool closure_wait(struct closure_waitlist *waitlist, struct closure *cl)
-{
-	if (atomic_read(&cl->remaining) & CLOSURE_WAITING)
-		return false;
-
-	closure_set_waiting(cl, _RET_IP_);
-	atomic_add(CLOSURE_WAITING + 1, &cl->remaining);
-	llist_add(&cl->list, &waitlist->list);
-
-	return true;
-}
-
-struct closure_syncer {
-	struct task_struct	*task;
-	int			done;
-};
-
-static void closure_sync_fn(struct closure *cl)
-{
-	struct closure_syncer *s = cl->s;
-	struct task_struct *p;
-
-	rcu_read_lock();
-	p = READ_ONCE(s->task);
-	s->done = 1;
-	wake_up_process(p);
-	rcu_read_unlock();
-}
-
-void __sched __closure_sync(struct closure *cl)
-{
-	struct closure_syncer s = { .task = current };
-
-	cl->s = &s;
-	continue_at(cl, closure_sync_fn, NULL);
-
-	while (1) {
-		set_current_state(TASK_UNINTERRUPTIBLE);
-		if (s.done)
-			break;
-		schedule();
-	}
-
-	__set_current_state(TASK_RUNNING);
-}
-
-#ifdef CONFIG_BCACHE_CLOSURES_DEBUG
-
-static LIST_HEAD(closure_list);
-static DEFINE_SPINLOCK(closure_list_lock);
-
-void closure_debug_create(struct closure *cl)
-{
-	unsigned long flags;
-
-	BUG_ON(cl->magic == CLOSURE_MAGIC_ALIVE);
-	cl->magic = CLOSURE_MAGIC_ALIVE;
-
-	spin_lock_irqsave(&closure_list_lock, flags);
-	list_add(&cl->all, &closure_list);
-	spin_unlock_irqrestore(&closure_list_lock, flags);
-}
-
-void closure_debug_destroy(struct closure *cl)
-{
-	unsigned long flags;
-
-	BUG_ON(cl->magic != CLOSURE_MAGIC_ALIVE);
-	cl->magic = CLOSURE_MAGIC_DEAD;
-
-	spin_lock_irqsave(&closure_list_lock, flags);
-	list_del(&cl->all);
-	spin_unlock_irqrestore(&closure_list_lock, flags);
-}
-
-static struct dentry *closure_debug;
-
-static int debug_show(struct seq_file *f, void *data)
-{
-	struct closure *cl;
-
-	spin_lock_irq(&closure_list_lock);
-
-	list_for_each_entry(cl, &closure_list, all) {
-		int r = atomic_read(&cl->remaining);
-
-		seq_printf(f, "%p: %pS -> %pS p %p r %i ",
-			   cl, (void *) cl->ip, cl->fn, cl->parent,
-			   r & CLOSURE_REMAINING_MASK);
-
-		seq_printf(f, "%s%s\n",
-			   test_bit(WORK_STRUCT_PENDING_BIT,
-				    work_data_bits(&cl->work)) ? "Q" : "",
-			   r & CLOSURE_RUNNING	? "R" : "");
-
-		if (r & CLOSURE_WAITING)
-			seq_printf(f, " W %pS\n",
-				   (void *) cl->waiting_on);
-
-		seq_printf(f, "\n");
-	}
-
-	spin_unlock_irq(&closure_list_lock);
-	return 0;
-}
-
-DEFINE_SHOW_ATTRIBUTE(debug);
-
-void  __init closure_debug_init(void)
-{
-	if (!IS_ERR_OR_NULL(bcache_debug))
-		/*
-		 * it is unnecessary to check return value of
-		 * debugfs_create_file(), we should not care
-		 * about this.
-		 */
-		closure_debug = debugfs_create_file(
-			"closures", 0400, bcache_debug, NULL, &debug_fops);
-}
-#endif
-
-MODULE_AUTHOR("Kent Overstreet <koverstreet@google.com>");
-MODULE_LICENSE("GPL");
diff --git a/drivers/md/bcache/closure.h b/drivers/md/bcache/closure.h
deleted file mode 100644
index c88cdc4ae4..0000000000
--- a/drivers/md/bcache/closure.h
+++ /dev/null
@@ -1,378 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _LINUX_CLOSURE_H
-#define _LINUX_CLOSURE_H
-
-#include <linux/llist.h>
-#include <linux/sched.h>
-#include <linux/sched/task_stack.h>
-#include <linux/workqueue.h>
-
-/*
- * Closure is perhaps the most overused and abused term in computer science, but
- * since I've been unable to come up with anything better you're stuck with it
- * again.
- *
- * What are closures?
- *
- * They embed a refcount. The basic idea is they count "things that are in
- * progress" - in flight bios, some other thread that's doing something else -
- * anything you might want to wait on.
- *
- * The refcount may be manipulated with closure_get() and closure_put().
- * closure_put() is where many of the interesting things happen, when it causes
- * the refcount to go to 0.
- *
- * Closures can be used to wait on things both synchronously and asynchronously,
- * and synchronous and asynchronous use can be mixed without restriction. To
- * wait synchronously, use closure_sync() - you will sleep until your closure's
- * refcount hits 1.
- *
- * To wait asynchronously, use
- *   continue_at(cl, next_function, workqueue);
- *
- * passing it, as you might expect, the function to run when nothing is pending
- * and the workqueue to run that function out of.
- *
- * continue_at() also, critically, requires a 'return' immediately following the
- * location where this macro is referenced, to return to the calling function.
- * There's good reason for this.
- *
- * To use safely closures asynchronously, they must always have a refcount while
- * they are running owned by the thread that is running them. Otherwise, suppose
- * you submit some bios and wish to have a function run when they all complete:
- *
- * foo_endio(struct bio *bio)
- * {
- *	closure_put(cl);
- * }
- *
- * closure_init(cl);
- *
- * do_stuff();
- * closure_get(cl);
- * bio1->bi_endio = foo_endio;
- * bio_submit(bio1);
- *
- * do_more_stuff();
- * closure_get(cl);
- * bio2->bi_endio = foo_endio;
- * bio_submit(bio2);
- *
- * continue_at(cl, complete_some_read, system_wq);
- *
- * If closure's refcount started at 0, complete_some_read() could run before the
- * second bio was submitted - which is almost always not what you want! More
- * importantly, it wouldn't be possible to say whether the original thread or
- * complete_some_read()'s thread owned the closure - and whatever state it was
- * associated with!
- *
- * So, closure_init() initializes a closure's refcount to 1 - and when a
- * closure_fn is run, the refcount will be reset to 1 first.
- *
- * Then, the rule is - if you got the refcount with closure_get(), release it
- * with closure_put() (i.e, in a bio->bi_endio function). If you have a refcount
- * on a closure because you called closure_init() or you were run out of a
- * closure - _always_ use continue_at(). Doing so consistently will help
- * eliminate an entire class of particularly pernicious races.
- *
- * Lastly, you might have a wait list dedicated to a specific event, and have no
- * need for specifying the condition - you just want to wait until someone runs
- * closure_wake_up() on the appropriate wait list. In that case, just use
- * closure_wait(). It will return either true or false, depending on whether the
- * closure was already on a wait list or not - a closure can only be on one wait
- * list at a time.
- *
- * Parents:
- *
- * closure_init() takes two arguments - it takes the closure to initialize, and
- * a (possibly null) parent.
- *
- * If parent is non null, the new closure will have a refcount for its lifetime;
- * a closure is considered to be "finished" when its refcount hits 0 and the
- * function to run is null. Hence
- *
- * continue_at(cl, NULL, NULL);
- *
- * returns up the (spaghetti) stack of closures, precisely like normal return
- * returns up the C stack. continue_at() with non null fn is better thought of
- * as doing a tail call.
- *
- * All this implies that a closure should typically be embedded in a particular
- * struct (which its refcount will normally control the lifetime of), and that
- * struct can very much be thought of as a stack frame.
- */
-
-struct closure;
-struct closure_syncer;
-typedef void (closure_fn) (struct closure *);
-extern struct dentry *bcache_debug;
-
-struct closure_waitlist {
-	struct llist_head	list;
-};
-
-enum closure_state {
-	/*
-	 * CLOSURE_WAITING: Set iff the closure is on a waitlist. Must be set by
-	 * the thread that owns the closure, and cleared by the thread that's
-	 * waking up the closure.
-	 *
-	 * The rest are for debugging and don't affect behaviour:
-	 *
-	 * CLOSURE_RUNNING: Set when a closure is running (i.e. by
-	 * closure_init() and when closure_put() runs then next function), and
-	 * must be cleared before remaining hits 0. Primarily to help guard
-	 * against incorrect usage and accidentally transferring references.
-	 * continue_at() and closure_return() clear it for you, if you're doing
-	 * something unusual you can use closure_set_dead() which also helps
-	 * annotate where references are being transferred.
-	 */
-
-	CLOSURE_BITS_START	= (1U << 26),
-	CLOSURE_DESTRUCTOR	= (1U << 26),
-	CLOSURE_WAITING		= (1U << 28),
-	CLOSURE_RUNNING		= (1U << 30),
-};
-
-#define CLOSURE_GUARD_MASK					\
-	((CLOSURE_DESTRUCTOR|CLOSURE_WAITING|CLOSURE_RUNNING) << 1)
-
-#define CLOSURE_REMAINING_MASK		(CLOSURE_BITS_START - 1)
-#define CLOSURE_REMAINING_INITIALIZER	(1|CLOSURE_RUNNING)
-
-struct closure {
-	union {
-		struct {
-			struct workqueue_struct *wq;
-			struct closure_syncer	*s;
-			struct llist_node	list;
-			closure_fn		*fn;
-		};
-		struct work_struct	work;
-	};
-
-	struct closure		*parent;
-
-	atomic_t		remaining;
-
-#ifdef CONFIG_BCACHE_CLOSURES_DEBUG
-#define CLOSURE_MAGIC_DEAD	0xc054dead
-#define CLOSURE_MAGIC_ALIVE	0xc054a11e
-
-	unsigned int		magic;
-	struct list_head	all;
-	unsigned long		ip;
-	unsigned long		waiting_on;
-#endif
-};
-
-void closure_sub(struct closure *cl, int v);
-void closure_put(struct closure *cl);
-void __closure_wake_up(struct closure_waitlist *list);
-bool closure_wait(struct closure_waitlist *list, struct closure *cl);
-void __closure_sync(struct closure *cl);
-
-/**
- * closure_sync - sleep until a closure a closure has nothing left to wait on
- *
- * Sleeps until the refcount hits 1 - the thread that's running the closure owns
- * the last refcount.
- */
-static inline void closure_sync(struct closure *cl)
-{
-	if ((atomic_read(&cl->remaining) & CLOSURE_REMAINING_MASK) != 1)
-		__closure_sync(cl);
-}
-
-#ifdef CONFIG_BCACHE_CLOSURES_DEBUG
-
-void closure_debug_init(void);
-void closure_debug_create(struct closure *cl);
-void closure_debug_destroy(struct closure *cl);
-
-#else
-
-static inline void closure_debug_init(void) {}
-static inline void closure_debug_create(struct closure *cl) {}
-static inline void closure_debug_destroy(struct closure *cl) {}
-
-#endif
-
-static inline void closure_set_ip(struct closure *cl)
-{
-#ifdef CONFIG_BCACHE_CLOSURES_DEBUG
-	cl->ip = _THIS_IP_;
-#endif
-}
-
-static inline void closure_set_ret_ip(struct closure *cl)
-{
-#ifdef CONFIG_BCACHE_CLOSURES_DEBUG
-	cl->ip = _RET_IP_;
-#endif
-}
-
-static inline void closure_set_waiting(struct closure *cl, unsigned long f)
-{
-#ifdef CONFIG_BCACHE_CLOSURES_DEBUG
-	cl->waiting_on = f;
-#endif
-}
-
-static inline void closure_set_stopped(struct closure *cl)
-{
-	atomic_sub(CLOSURE_RUNNING, &cl->remaining);
-}
-
-static inline void set_closure_fn(struct closure *cl, closure_fn *fn,
-				  struct workqueue_struct *wq)
-{
-	closure_set_ip(cl);
-	cl->fn = fn;
-	cl->wq = wq;
-	/* between atomic_dec() in closure_put() */
-	smp_mb__before_atomic();
-}
-
-static inline void closure_queue(struct closure *cl)
-{
-	struct workqueue_struct *wq = cl->wq;
-	/**
-	 * Changes made to closure, work_struct, or a couple of other structs
-	 * may cause work.func not pointing to the right location.
-	 */
-	BUILD_BUG_ON(offsetof(struct closure, fn)
-		     != offsetof(struct work_struct, func));
-	if (wq) {
-		INIT_WORK(&cl->work, cl->work.func);
-		BUG_ON(!queue_work(wq, &cl->work));
-	} else
-		cl->fn(cl);
-}
-
-/**
- * closure_get - increment a closure's refcount
- */
-static inline void closure_get(struct closure *cl)
-{
-#ifdef CONFIG_BCACHE_CLOSURES_DEBUG
-	BUG_ON((atomic_inc_return(&cl->remaining) &
-		CLOSURE_REMAINING_MASK) <= 1);
-#else
-	atomic_inc(&cl->remaining);
-#endif
-}
-
-/**
- * closure_init - Initialize a closure, setting the refcount to 1
- * @cl:		closure to initialize
- * @parent:	parent of the new closure. cl will take a refcount on it for its
- *		lifetime; may be NULL.
- */
-static inline void closure_init(struct closure *cl, struct closure *parent)
-{
-	memset(cl, 0, sizeof(struct closure));
-	cl->parent = parent;
-	if (parent)
-		closure_get(parent);
-
-	atomic_set(&cl->remaining, CLOSURE_REMAINING_INITIALIZER);
-
-	closure_debug_create(cl);
-	closure_set_ip(cl);
-}
-
-static inline void closure_init_stack(struct closure *cl)
-{
-	memset(cl, 0, sizeof(struct closure));
-	atomic_set(&cl->remaining, CLOSURE_REMAINING_INITIALIZER);
-}
-
-/**
- * closure_wake_up - wake up all closures on a wait list,
- *		     with memory barrier
- */
-static inline void closure_wake_up(struct closure_waitlist *list)
-{
-	/* Memory barrier for the wait list */
-	smp_mb();
-	__closure_wake_up(list);
-}
-
-/**
- * continue_at - jump to another function with barrier
- *
- * After @cl is no longer waiting on anything (i.e. all outstanding refs have
- * been dropped with closure_put()), it will resume execution at @fn running out
- * of @wq (or, if @wq is NULL, @fn will be called by closure_put() directly).
- *
- * This is because after calling continue_at() you no longer have a ref on @cl,
- * and whatever @cl owns may be freed out from under you - a running closure fn
- * has a ref on its own closure which continue_at() drops.
- *
- * Note you are expected to immediately return after using this macro.
- */
-#define continue_at(_cl, _fn, _wq)					\
-do {									\
-	set_closure_fn(_cl, _fn, _wq);					\
-	closure_sub(_cl, CLOSURE_RUNNING + 1);				\
-} while (0)
-
-/**
- * closure_return - finish execution of a closure
- *
- * This is used to indicate that @cl is finished: when all outstanding refs on
- * @cl have been dropped @cl's ref on its parent closure (as passed to
- * closure_init()) will be dropped, if one was specified - thus this can be
- * thought of as returning to the parent closure.
- */
-#define closure_return(_cl)	continue_at((_cl), NULL, NULL)
-
-/**
- * continue_at_nobarrier - jump to another function without barrier
- *
- * Causes @fn to be executed out of @cl, in @wq context (or called directly if
- * @wq is NULL).
- *
- * The ref the caller of continue_at_nobarrier() had on @cl is now owned by @fn,
- * thus it's not safe to touch anything protected by @cl after a
- * continue_at_nobarrier().
- */
-#define continue_at_nobarrier(_cl, _fn, _wq)				\
-do {									\
-	set_closure_fn(_cl, _fn, _wq);					\
-	closure_queue(_cl);						\
-} while (0)
-
-/**
- * closure_return_with_destructor - finish execution of a closure,
- *				    with destructor
- *
- * Works like closure_return(), except @destructor will be called when all
- * outstanding refs on @cl have been dropped; @destructor may be used to safely
- * free the memory occupied by @cl, and it is called with the ref on the parent
- * closure still held - so @destructor could safely return an item to a
- * freelist protected by @cl's parent.
- */
-#define closure_return_with_destructor(_cl, _destructor)		\
-do {									\
-	set_closure_fn(_cl, _destructor, NULL);				\
-	closure_sub(_cl, CLOSURE_RUNNING - CLOSURE_DESTRUCTOR + 1);	\
-} while (0)
-
-/**
- * closure_call - execute @fn out of a new, uninitialized closure
- *
- * Typically used when running out of one closure, and we want to run @fn
- * asynchronously out of a new closure - @parent will then wait for @cl to
- * finish.
- */
-static inline void closure_call(struct closure *cl, closure_fn fn,
-				struct workqueue_struct *wq,
-				struct closure *parent)
-{
-	closure_init(cl, parent);
-	continue_at_nobarrier(cl, fn, wq);
-}
-
-#endif /* _LINUX_CLOSURE_H */
diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c
index c182c21de2..7ff14bd2fe 100644
--- a/drivers/md/bcache/journal.c
+++ b/drivers/md/bcache/journal.c
@@ -723,11 +723,11 @@ static void journal_write_endio(struct bio *bio)
 	closure_put(&w->c->journal.io);
 }
 
-static void journal_write(struct closure *cl);
+static CLOSURE_CALLBACK(journal_write);
 
-static void journal_write_done(struct closure *cl)
+static CLOSURE_CALLBACK(journal_write_done)
 {
-	struct journal *j = container_of(cl, struct journal, io);
+	closure_type(j, struct journal, io);
 	struct journal_write *w = (j->cur == j->w)
 		? &j->w[1]
 		: &j->w[0];
@@ -736,19 +736,19 @@ static void journal_write_done(struct closure *cl)
 	continue_at_nobarrier(cl, journal_write, bch_journal_wq);
 }
 
-static void journal_write_unlock(struct closure *cl)
+static CLOSURE_CALLBACK(journal_write_unlock)
 	__releases(&c->journal.lock)
 {
-	struct cache_set *c = container_of(cl, struct cache_set, journal.io);
+	closure_type(c, struct cache_set, journal.io);
 
 	c->journal.io_in_flight = 0;
 	spin_unlock(&c->journal.lock);
 }
 
-static void journal_write_unlocked(struct closure *cl)
+static CLOSURE_CALLBACK(journal_write_unlocked)
 	__releases(c->journal.lock)
 {
-	struct cache_set *c = container_of(cl, struct cache_set, journal.io);
+	closure_type(c, struct cache_set, journal.io);
 	struct cache *ca = c->cache;
 	struct journal_write *w = c->journal.cur;
 	struct bkey *k = &c->journal.key;
@@ -823,12 +823,12 @@ static void journal_write_unlocked(struct closure *cl)
 	continue_at(cl, journal_write_done, NULL);
 }
 
-static void journal_write(struct closure *cl)
+static CLOSURE_CALLBACK(journal_write)
 {
-	struct cache_set *c = container_of(cl, struct cache_set, journal.io);
+	closure_type(c, struct cache_set, journal.io);
 
 	spin_lock(&c->journal.lock);
-	journal_write_unlocked(cl);
+	journal_write_unlocked(&cl->work);
 }
 
 static void journal_try_write(struct cache_set *c)
diff --git a/drivers/md/bcache/movinggc.c b/drivers/md/bcache/movinggc.c
index 9f32901fda..ebd500bdf0 100644
--- a/drivers/md/bcache/movinggc.c
+++ b/drivers/md/bcache/movinggc.c
@@ -35,16 +35,16 @@ static bool moving_pred(struct keybuf *buf, struct bkey *k)
 
 /* Moving GC - IO loop */
 
-static void moving_io_destructor(struct closure *cl)
+static CLOSURE_CALLBACK(moving_io_destructor)
 {
-	struct moving_io *io = container_of(cl, struct moving_io, cl);
+	closure_type(io, struct moving_io, cl);
 
 	kfree(io);
 }
 
-static void write_moving_finish(struct closure *cl)
+static CLOSURE_CALLBACK(write_moving_finish)
 {
-	struct moving_io *io = container_of(cl, struct moving_io, cl);
+	closure_type(io, struct moving_io, cl);
 	struct bio *bio = &io->bio.bio;
 
 	bio_free_pages(bio);
@@ -89,9 +89,9 @@ static void moving_init(struct moving_io *io)
 	bch_bio_map(bio, NULL);
 }
 
-static void write_moving(struct closure *cl)
+static CLOSURE_CALLBACK(write_moving)
 {
-	struct moving_io *io = container_of(cl, struct moving_io, cl);
+	closure_type(io, struct moving_io, cl);
 	struct data_insert_op *op = &io->op;
 
 	if (!op->status) {
@@ -113,9 +113,9 @@ static void write_moving(struct closure *cl)
 	continue_at(cl, write_moving_finish, op->wq);
 }
 
-static void read_moving_submit(struct closure *cl)
+static CLOSURE_CALLBACK(read_moving_submit)
 {
-	struct moving_io *io = container_of(cl, struct moving_io, cl);
+	closure_type(io, struct moving_io, cl);
 	struct bio *bio = &io->bio.bio;
 
 	bch_submit_bbio(bio, io->op.c, &io->w->key, 0);
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index a9b1f38962..83d112bd2b 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -25,7 +25,7 @@
 
 struct kmem_cache *bch_search_cache;
 
-static void bch_data_insert_start(struct closure *cl);
+static CLOSURE_CALLBACK(bch_data_insert_start);
 
 static unsigned int cache_mode(struct cached_dev *dc)
 {
@@ -55,9 +55,9 @@ static void bio_csum(struct bio *bio, struct bkey *k)
 
 /* Insert data into cache */
 
-static void bch_data_insert_keys(struct closure *cl)
+static CLOSURE_CALLBACK(bch_data_insert_keys)
 {
-	struct data_insert_op *op = container_of(cl, struct data_insert_op, cl);
+	closure_type(op, struct data_insert_op, cl);
 	atomic_t *journal_ref = NULL;
 	struct bkey *replace_key = op->replace ? &op->replace_key : NULL;
 	int ret;
@@ -136,9 +136,9 @@ out:
 	continue_at(cl, bch_data_insert_keys, op->wq);
 }
 
-static void bch_data_insert_error(struct closure *cl)
+static CLOSURE_CALLBACK(bch_data_insert_error)
 {
-	struct data_insert_op *op = container_of(cl, struct data_insert_op, cl);
+	closure_type(op, struct data_insert_op, cl);
 
 	/*
 	 * Our data write just errored, which means we've got a bunch of keys to
@@ -163,7 +163,7 @@ static void bch_data_insert_error(struct closure *cl)
 
 	op->insert_keys.top = dst;
 
-	bch_data_insert_keys(cl);
+	bch_data_insert_keys(&cl->work);
 }
 
 static void bch_data_insert_endio(struct bio *bio)
@@ -184,9 +184,9 @@ static void bch_data_insert_endio(struct bio *bio)
 	bch_bbio_endio(op->c, bio, bio->bi_status, "writing data to cache");
 }
 
-static void bch_data_insert_start(struct closure *cl)
+static CLOSURE_CALLBACK(bch_data_insert_start)
 {
-	struct data_insert_op *op = container_of(cl, struct data_insert_op, cl);
+	closure_type(op, struct data_insert_op, cl);
 	struct bio *bio = op->bio, *n;
 
 	if (op->bypass)
@@ -305,16 +305,16 @@ err:
  * If op->bypass is true, instead of inserting the data it invalidates the
  * region of the cache represented by op->bio and op->inode.
  */
-void bch_data_insert(struct closure *cl)
+CLOSURE_CALLBACK(bch_data_insert)
 {
-	struct data_insert_op *op = container_of(cl, struct data_insert_op, cl);
+	closure_type(op, struct data_insert_op, cl);
 
 	trace_bcache_write(op->c, op->inode, op->bio,
 			   op->writeback, op->bypass);
 
 	bch_keylist_init(&op->insert_keys);
 	bio_get(op->bio);
-	bch_data_insert_start(cl);
+	bch_data_insert_start(&cl->work);
 }
 
 /*
@@ -575,9 +575,9 @@ static int cache_lookup_fn(struct btree_op *op, struct btree *b, struct bkey *k)
 	return n == bio ? MAP_DONE : MAP_CONTINUE;
 }
 
-static void cache_lookup(struct closure *cl)
+static CLOSURE_CALLBACK(cache_lookup)
 {
-	struct search *s = container_of(cl, struct search, iop.cl);
+	closure_type(s, struct search, iop.cl);
 	struct bio *bio = &s->bio.bio;
 	struct cached_dev *dc;
 	int ret;
@@ -698,9 +698,9 @@ static void do_bio_hook(struct search *s,
 	bio_cnt_set(bio, 3);
 }
 
-static void search_free(struct closure *cl)
+static CLOSURE_CALLBACK(search_free)
 {
-	struct search *s = container_of(cl, struct search, cl);
+	closure_type(s, struct search, cl);
 
 	atomic_dec(&s->iop.c->search_inflight);
 
@@ -749,20 +749,20 @@ static inline struct search *search_alloc(struct bio *bio,
 
 /* Cached devices */
 
-static void cached_dev_bio_complete(struct closure *cl)
+static CLOSURE_CALLBACK(cached_dev_bio_complete)
 {
-	struct search *s = container_of(cl, struct search, cl);
+	closure_type(s, struct search, cl);
 	struct cached_dev *dc = container_of(s->d, struct cached_dev, disk);
 
 	cached_dev_put(dc);
-	search_free(cl);
+	search_free(&cl->work);
 }
 
 /* Process reads */
 
-static void cached_dev_read_error_done(struct closure *cl)
+static CLOSURE_CALLBACK(cached_dev_read_error_done)
 {
-	struct search *s = container_of(cl, struct search, cl);
+	closure_type(s, struct search, cl);
 
 	if (s->iop.replace_collision)
 		bch_mark_cache_miss_collision(s->iop.c, s->d);
@@ -770,12 +770,12 @@ static void cached_dev_read_error_done(struct closure *cl)
 	if (s->iop.bio)
 		bio_free_pages(s->iop.bio);
 
-	cached_dev_bio_complete(cl);
+	cached_dev_bio_complete(&cl->work);
 }
 
-static void cached_dev_read_error(struct closure *cl)
+static CLOSURE_CALLBACK(cached_dev_read_error)
 {
-	struct search *s = container_of(cl, struct search, cl);
+	closure_type(s, struct search, cl);
 	struct bio *bio = &s->bio.bio;
 
 	/*
@@ -801,9 +801,9 @@ static void cached_dev_read_error(struct closure *cl)
 	continue_at(cl, cached_dev_read_error_done, NULL);
 }
 
-static void cached_dev_cache_miss_done(struct closure *cl)
+static CLOSURE_CALLBACK(cached_dev_cache_miss_done)
 {
-	struct search *s = container_of(cl, struct search, cl);
+	closure_type(s, struct search, cl);
 	struct bcache_device *d = s->d;
 
 	if (s->iop.replace_collision)
@@ -812,13 +812,13 @@ static void cached_dev_cache_miss_done(struct closure *cl)
 	if (s->iop.bio)
 		bio_free_pages(s->iop.bio);
 
-	cached_dev_bio_complete(cl);
+	cached_dev_bio_complete(&cl->work);
 	closure_put(&d->cl);
 }
 
-static void cached_dev_read_done(struct closure *cl)
+static CLOSURE_CALLBACK(cached_dev_read_done)
 {
-	struct search *s = container_of(cl, struct search, cl);
+	closure_type(s, struct search, cl);
 	struct cached_dev *dc = container_of(s->d, struct cached_dev, disk);
 
 	/*
@@ -858,9 +858,9 @@ static void cached_dev_read_done(struct closure *cl)
 	continue_at(cl, cached_dev_cache_miss_done, NULL);
 }
 
-static void cached_dev_read_done_bh(struct closure *cl)
+static CLOSURE_CALLBACK(cached_dev_read_done_bh)
 {
-	struct search *s = container_of(cl, struct search, cl);
+	closure_type(s, struct search, cl);
 	struct cached_dev *dc = container_of(s->d, struct cached_dev, disk);
 
 	bch_mark_cache_accounting(s->iop.c, s->d,
@@ -955,13 +955,13 @@ static void cached_dev_read(struct cached_dev *dc, struct search *s)
 
 /* Process writes */
 
-static void cached_dev_write_complete(struct closure *cl)
+static CLOSURE_CALLBACK(cached_dev_write_complete)
 {
-	struct search *s = container_of(cl, struct search, cl);
+	closure_type(s, struct search, cl);
 	struct cached_dev *dc = container_of(s->d, struct cached_dev, disk);
 
 	up_read_non_owner(&dc->writeback_lock);
-	cached_dev_bio_complete(cl);
+	cached_dev_bio_complete(&cl->work);
 }
 
 static void cached_dev_write(struct cached_dev *dc, struct search *s)
@@ -1048,9 +1048,9 @@ insert_data:
 	continue_at(cl, cached_dev_write_complete, NULL);
 }
 
-static void cached_dev_nodata(struct closure *cl)
+static CLOSURE_CALLBACK(cached_dev_nodata)
 {
-	struct search *s = container_of(cl, struct search, cl);
+	closure_type(s, struct search, cl);
 	struct bio *bio = &s->bio.bio;
 
 	if (s->iop.flush_journal)
@@ -1265,9 +1265,9 @@ static int flash_dev_cache_miss(struct btree *b, struct search *s,
 	return MAP_CONTINUE;
 }
 
-static void flash_dev_nodata(struct closure *cl)
+static CLOSURE_CALLBACK(flash_dev_nodata)
 {
-	struct search *s = container_of(cl, struct search, cl);
+	closure_type(s, struct search, cl);
 
 	if (s->iop.flush_journal)
 		bch_journal_meta(s->iop.c, cl);
diff --git a/drivers/md/bcache/request.h b/drivers/md/bcache/request.h
index 38ab4856ea..46bbef00ae 100644
--- a/drivers/md/bcache/request.h
+++ b/drivers/md/bcache/request.h
@@ -34,7 +34,7 @@ struct data_insert_op {
 };
 
 unsigned int bch_get_congested(const struct cache_set *c);
-void bch_data_insert(struct closure *cl);
+CLOSURE_CALLBACK(bch_data_insert);
 
 void bch_cached_dev_request_init(struct cached_dev *dc);
 void cached_dev_submit_bio(struct bio *bio);
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 1e677af385..1402096b80 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -327,9 +327,9 @@ static void __write_super(struct cache_sb *sb, struct cache_sb_disk *out,
 	submit_bio(bio);
 }
 
-static void bch_write_bdev_super_unlock(struct closure *cl)
+static CLOSURE_CALLBACK(bch_write_bdev_super_unlock)
 {
-	struct cached_dev *dc = container_of(cl, struct cached_dev, sb_write);
+	closure_type(dc, struct cached_dev, sb_write);
 
 	up(&dc->sb_write_mutex);
 }
@@ -363,9 +363,9 @@ static void write_super_endio(struct bio *bio)
 	closure_put(&ca->set->sb_write);
 }
 
-static void bcache_write_super_unlock(struct closure *cl)
+static CLOSURE_CALLBACK(bcache_write_super_unlock)
 {
-	struct cache_set *c = container_of(cl, struct cache_set, sb_write);
+	closure_type(c, struct cache_set, sb_write);
 
 	up(&c->sb_write_mutex);
 }
@@ -407,9 +407,9 @@ static void uuid_endio(struct bio *bio)
 	closure_put(cl);
 }
 
-static void uuid_io_unlock(struct closure *cl)
+static CLOSURE_CALLBACK(uuid_io_unlock)
 {
-	struct cache_set *c = container_of(cl, struct cache_set, uuid_write);
+	closure_type(c, struct cache_set, uuid_write);
 
 	up(&c->uuid_write_mutex);
 }
@@ -1344,9 +1344,9 @@ void bch_cached_dev_release(struct kobject *kobj)
 	module_put(THIS_MODULE);
 }
 
-static void cached_dev_free(struct closure *cl)
+static CLOSURE_CALLBACK(cached_dev_free)
 {
-	struct cached_dev *dc = container_of(cl, struct cached_dev, disk.cl);
+	closure_type(dc, struct cached_dev, disk.cl);
 
 	if (test_and_clear_bit(BCACHE_DEV_WB_RUNNING, &dc->disk.flags))
 		cancel_writeback_rate_update_dwork(dc);
@@ -1370,17 +1370,17 @@ static void cached_dev_free(struct closure *cl)
 	if (dc->sb_disk)
 		put_page(virt_to_page(dc->sb_disk));
 
-	if (!IS_ERR_OR_NULL(dc->bdev))
-		blkdev_put(dc->bdev, dc);
+	if (dc->bdev_handle)
+		bdev_release(dc->bdev_handle);
 
 	wake_up(&unregister_wait);
 
 	kobject_put(&dc->disk.kobj);
 }
 
-static void cached_dev_flush(struct closure *cl)
+static CLOSURE_CALLBACK(cached_dev_flush)
 {
-	struct cached_dev *dc = container_of(cl, struct cached_dev, disk.cl);
+	closure_type(dc, struct cached_dev, disk.cl);
 	struct bcache_device *d = &dc->disk;
 
 	mutex_lock(&bch_register_lock);
@@ -1446,7 +1446,7 @@ static int cached_dev_init(struct cached_dev *dc, unsigned int block_size)
 /* Cached device - bcache superblock */
 
 static int register_bdev(struct cache_sb *sb, struct cache_sb_disk *sb_disk,
-				 struct block_device *bdev,
+				 struct bdev_handle *bdev_handle,
 				 struct cached_dev *dc)
 {
 	const char *err = "cannot allocate memory";
@@ -1454,14 +1454,15 @@ static int register_bdev(struct cache_sb *sb, struct cache_sb_disk *sb_disk,
 	int ret = -ENOMEM;
 
 	memcpy(&dc->sb, sb, sizeof(struct cache_sb));
-	dc->bdev = bdev;
+	dc->bdev_handle = bdev_handle;
+	dc->bdev = bdev_handle->bdev;
 	dc->sb_disk = sb_disk;
 
 	if (cached_dev_init(dc, sb->block_size << 9))
 		goto err;
 
 	err = "error creating kobject";
-	if (kobject_add(&dc->disk.kobj, bdev_kobj(bdev), "bcache"))
+	if (kobject_add(&dc->disk.kobj, bdev_kobj(dc->bdev), "bcache"))
 		goto err;
 	if (bch_cache_accounting_add_kobjs(&dc->accounting, &dc->disk.kobj))
 		goto err;
@@ -1498,9 +1499,9 @@ void bch_flash_dev_release(struct kobject *kobj)
 	kfree(d);
 }
 
-static void flash_dev_free(struct closure *cl)
+static CLOSURE_CALLBACK(flash_dev_free)
 {
-	struct bcache_device *d = container_of(cl, struct bcache_device, cl);
+	closure_type(d, struct bcache_device, cl);
 
 	mutex_lock(&bch_register_lock);
 	atomic_long_sub(bcache_dev_sectors_dirty(d),
@@ -1511,9 +1512,9 @@ static void flash_dev_free(struct closure *cl)
 	kobject_put(&d->kobj);
 }
 
-static void flash_dev_flush(struct closure *cl)
+static CLOSURE_CALLBACK(flash_dev_flush)
 {
-	struct bcache_device *d = container_of(cl, struct bcache_device, cl);
+	closure_type(d, struct bcache_device, cl);
 
 	mutex_lock(&bch_register_lock);
 	bcache_device_unlink(d);
@@ -1669,9 +1670,9 @@ void bch_cache_set_release(struct kobject *kobj)
 	module_put(THIS_MODULE);
 }
 
-static void cache_set_free(struct closure *cl)
+static CLOSURE_CALLBACK(cache_set_free)
 {
-	struct cache_set *c = container_of(cl, struct cache_set, cl);
+	closure_type(c, struct cache_set, cl);
 	struct cache *ca;
 
 	debugfs_remove(c->debug);
@@ -1710,9 +1711,9 @@ static void cache_set_free(struct closure *cl)
 	kobject_put(&c->kobj);
 }
 
-static void cache_set_flush(struct closure *cl)
+static CLOSURE_CALLBACK(cache_set_flush)
 {
-	struct cache_set *c = container_of(cl, struct cache_set, caching);
+	closure_type(c, struct cache_set, caching);
 	struct cache *ca = c->cache;
 	struct btree *b;
 
@@ -1807,9 +1808,9 @@ static void conditional_stop_bcache_device(struct cache_set *c,
 	}
 }
 
-static void __cache_set_unregister(struct closure *cl)
+static CLOSURE_CALLBACK(__cache_set_unregister)
 {
-	struct cache_set *c = container_of(cl, struct cache_set, caching);
+	closure_type(c, struct cache_set, caching);
 	struct cached_dev *dc;
 	struct bcache_device *d;
 	size_t i;
@@ -2218,8 +2219,8 @@ void bch_cache_release(struct kobject *kobj)
 	if (ca->sb_disk)
 		put_page(virt_to_page(ca->sb_disk));
 
-	if (!IS_ERR_OR_NULL(ca->bdev))
-		blkdev_put(ca->bdev, ca);
+	if (ca->bdev_handle)
+		bdev_release(ca->bdev_handle);
 
 	kfree(ca);
 	module_put(THIS_MODULE);
@@ -2339,38 +2340,42 @@ err_free:
 }
 
 static int register_cache(struct cache_sb *sb, struct cache_sb_disk *sb_disk,
-				struct block_device *bdev, struct cache *ca)
+				struct bdev_handle *bdev_handle,
+				struct cache *ca)
 {
 	const char *err = NULL; /* must be set for any error case */
 	int ret = 0;
 
 	memcpy(&ca->sb, sb, sizeof(struct cache_sb));
-	ca->bdev = bdev;
+	ca->bdev_handle = bdev_handle;
+	ca->bdev = bdev_handle->bdev;
 	ca->sb_disk = sb_disk;
 
-	if (bdev_max_discard_sectors((bdev)))
+	if (bdev_max_discard_sectors((bdev_handle->bdev)))
 		ca->discard = CACHE_DISCARD(&ca->sb);
 
 	ret = cache_alloc(ca);
 	if (ret != 0) {
-		/*
-		 * If we failed here, it means ca->kobj is not initialized yet,
-		 * kobject_put() won't be called and there is no chance to
-		 * call blkdev_put() to bdev in bch_cache_release(). So we
-		 * explicitly call blkdev_put() here.
-		 */
-		blkdev_put(bdev, ca);
 		if (ret == -ENOMEM)
 			err = "cache_alloc(): -ENOMEM";
 		else if (ret == -EPERM)
 			err = "cache_alloc(): cache device is too small";
 		else
 			err = "cache_alloc(): unknown error";
-		goto err;
+		pr_notice("error %pg: %s\n", bdev_handle->bdev, err);
+		/*
+		 * If we failed here, it means ca->kobj is not initialized yet,
+		 * kobject_put() won't be called and there is no chance to
+		 * call bdev_release() to bdev in bch_cache_release(). So
+		 * we explicitly call bdev_release() here.
+		 */
+		bdev_release(bdev_handle);
+		return ret;
 	}
 
-	if (kobject_add(&ca->kobj, bdev_kobj(bdev), "bcache")) {
-		err = "error calling kobject_add";
+	if (kobject_add(&ca->kobj, bdev_kobj(bdev_handle->bdev), "bcache")) {
+		pr_notice("error %pg: error calling kobject_add\n",
+			  bdev_handle->bdev);
 		ret = -ENOMEM;
 		goto out;
 	}
@@ -2384,15 +2389,10 @@ static int register_cache(struct cache_sb *sb, struct cache_sb_disk *sb_disk,
 		goto out;
 	}
 
-	pr_info("registered cache device %pg\n", ca->bdev);
+	pr_info("registered cache device %pg\n", ca->bdev_handle->bdev);
 
 out:
 	kobject_put(&ca->kobj);
-
-err:
-	if (err)
-		pr_notice("error %pg: %s\n", ca->bdev, err);
-
 	return ret;
 }
 
@@ -2447,7 +2447,7 @@ struct async_reg_args {
 	char *path;
 	struct cache_sb *sb;
 	struct cache_sb_disk *sb_disk;
-	struct block_device *bdev;
+	struct bdev_handle *bdev_handle;
 	void *holder;
 };
 
@@ -2458,8 +2458,8 @@ static void register_bdev_worker(struct work_struct *work)
 		container_of(work, struct async_reg_args, reg_work.work);
 
 	mutex_lock(&bch_register_lock);
-	if (register_bdev(args->sb, args->sb_disk, args->bdev, args->holder)
-	    < 0)
+	if (register_bdev(args->sb, args->sb_disk, args->bdev_handle,
+			  args->holder) < 0)
 		fail = true;
 	mutex_unlock(&bch_register_lock);
 
@@ -2479,7 +2479,8 @@ static void register_cache_worker(struct work_struct *work)
 		container_of(work, struct async_reg_args, reg_work.work);
 
 	/* blkdev_put() will be called in bch_cache_release() */
-	if (register_cache(args->sb, args->sb_disk, args->bdev, args->holder))
+	if (register_cache(args->sb, args->sb_disk, args->bdev_handle,
+			   args->holder))
 		fail = true;
 
 	if (fail)
@@ -2516,7 +2517,7 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
 	char *path = NULL;
 	struct cache_sb *sb;
 	struct cache_sb_disk *sb_disk;
-	struct block_device *bdev, *bdev2;
+	struct bdev_handle *bdev_handle, *bdev_handle2;
 	void *holder = NULL;
 	ssize_t ret;
 	bool async_registration = false;
@@ -2549,15 +2550,15 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
 
 	ret = -EINVAL;
 	err = "failed to open device";
-	bdev = blkdev_get_by_path(strim(path), BLK_OPEN_READ, NULL, NULL);
-	if (IS_ERR(bdev))
+	bdev_handle = bdev_open_by_path(strim(path), BLK_OPEN_READ, NULL, NULL);
+	if (IS_ERR(bdev_handle))
 		goto out_free_sb;
 
 	err = "failed to set blocksize";
-	if (set_blocksize(bdev, 4096))
+	if (set_blocksize(bdev_handle->bdev, 4096))
 		goto out_blkdev_put;
 
-	err = read_super(sb, bdev, &sb_disk);
+	err = read_super(sb, bdev_handle->bdev, &sb_disk);
 	if (err)
 		goto out_blkdev_put;
 
@@ -2569,13 +2570,13 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
 	}
 
 	/* Now reopen in exclusive mode with proper holder */
-	bdev2 = blkdev_get_by_dev(bdev->bd_dev, BLK_OPEN_READ | BLK_OPEN_WRITE,
-				  holder, NULL);
-	blkdev_put(bdev, NULL);
-	bdev = bdev2;
-	if (IS_ERR(bdev)) {
-		ret = PTR_ERR(bdev);
-		bdev = NULL;
+	bdev_handle2 = bdev_open_by_dev(bdev_handle->bdev->bd_dev,
+			BLK_OPEN_READ | BLK_OPEN_WRITE, holder, NULL);
+	bdev_release(bdev_handle);
+	bdev_handle = bdev_handle2;
+	if (IS_ERR(bdev_handle)) {
+		ret = PTR_ERR(bdev_handle);
+		bdev_handle = NULL;
 		if (ret == -EBUSY) {
 			dev_t dev;
 
@@ -2610,7 +2611,7 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
 		args->path	= path;
 		args->sb	= sb;
 		args->sb_disk	= sb_disk;
-		args->bdev	= bdev;
+		args->bdev_handle	= bdev_handle;
 		args->holder	= holder;
 		register_device_async(args);
 		/* No wait and returns to user space */
@@ -2619,14 +2620,14 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
 
 	if (SB_IS_BDEV(sb)) {
 		mutex_lock(&bch_register_lock);
-		ret = register_bdev(sb, sb_disk, bdev, holder);
+		ret = register_bdev(sb, sb_disk, bdev_handle, holder);
 		mutex_unlock(&bch_register_lock);
 		/* blkdev_put() will be called in cached_dev_free() */
 		if (ret < 0)
 			goto out_free_sb;
 	} else {
 		/* blkdev_put() will be called in bch_cache_release() */
-		ret = register_cache(sb, sb_disk, bdev, holder);
+		ret = register_cache(sb, sb_disk, bdev_handle, holder);
 		if (ret)
 			goto out_free_sb;
 	}
@@ -2642,8 +2643,8 @@ out_free_holder:
 out_put_sb_page:
 	put_page(virt_to_page(sb_disk));
 out_blkdev_put:
-	if (bdev)
-		blkdev_put(bdev, holder);
+	if (bdev_handle)
+		bdev_release(bdev_handle);
 out_free_sb:
 	kfree(sb);
 out_free_path:
@@ -2907,7 +2908,6 @@ static int __init bcache_init(void)
 		goto err;
 
 	bch_debug_init();
-	closure_debug_init();
 
 	bcache_is_reboot = false;
 
diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c
index 18ac98dc89..a438efb660 100644
--- a/drivers/md/bcache/sysfs.c
+++ b/drivers/md/bcache/sysfs.c
@@ -866,7 +866,8 @@ STORE(__bch_cache_set)
 
 		sc.gfp_mask = GFP_KERNEL;
 		sc.nr_to_scan = strtoul_or_return(buf);
-		c->shrink.scan_objects(&c->shrink, &sc);
+		if (c->shrink)
+			c->shrink->scan_objects(c->shrink, &sc);
 	}
 
 	sysfs_strtoul_clamp(congested_read_threshold_us,
diff --git a/drivers/md/bcache/util.h b/drivers/md/bcache/util.h
index 6f3cb7c921..f61ab1bada 100644
--- a/drivers/md/bcache/util.h
+++ b/drivers/md/bcache/util.h
@@ -4,6 +4,7 @@
 #define _BCACHE_UTIL_H
 
 #include <linux/blkdev.h>
+#include <linux/closure.h>
 #include <linux/errno.h>
 #include <linux/kernel.h>
 #include <linux/sched/clock.h>
@@ -13,8 +14,6 @@
 #include <linux/workqueue.h>
 #include <linux/crc64.h>
 
-#include "closure.h"
-
 struct closure;
 
 #ifdef CONFIG_BCACHE_DEBUG
diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index 3accfdaee6..8827a6f130 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -341,16 +341,16 @@ static void dirty_init(struct keybuf_key *w)
 	bch_bio_map(bio, NULL);
 }
 
-static void dirty_io_destructor(struct closure *cl)
+static CLOSURE_CALLBACK(dirty_io_destructor)
 {
-	struct dirty_io *io = container_of(cl, struct dirty_io, cl);
+	closure_type(io, struct dirty_io, cl);
 
 	kfree(io);
 }
 
-static void write_dirty_finish(struct closure *cl)
+static CLOSURE_CALLBACK(write_dirty_finish)
 {
-	struct dirty_io *io = container_of(cl, struct dirty_io, cl);
+	closure_type(io, struct dirty_io, cl);
 	struct keybuf_key *w = io->bio.bi_private;
 	struct cached_dev *dc = io->dc;
 
@@ -400,9 +400,9 @@ static void dirty_endio(struct bio *bio)
 	closure_put(&io->cl);
 }
 
-static void write_dirty(struct closure *cl)
+static CLOSURE_CALLBACK(write_dirty)
 {
-	struct dirty_io *io = container_of(cl, struct dirty_io, cl);
+	closure_type(io, struct dirty_io, cl);
 	struct keybuf_key *w = io->bio.bi_private;
 	struct cached_dev *dc = io->dc;
 
@@ -462,9 +462,9 @@ static void read_dirty_endio(struct bio *bio)
 	dirty_endio(bio);
 }
 
-static void read_dirty_submit(struct closure *cl)
+static CLOSURE_CALLBACK(read_dirty_submit)
 {
-	struct dirty_io *io = container_of(cl, struct dirty_io, cl);
+	closure_type(io, struct dirty_io, cl);
 
 	closure_bio_submit(io->dc->disk.c, &io->bio, cl);
 
diff --git a/drivers/md/dm-bio-prison-v1.c b/drivers/md/dm-bio-prison-v1.c
index 92afdca760..9ab32abe5e 100644
--- a/drivers/md/dm-bio-prison-v1.c
+++ b/drivers/md/dm-bio-prison-v1.c
@@ -26,7 +26,7 @@ struct prison_region {
 struct dm_bio_prison {
 	mempool_t cell_pool;
 	unsigned int num_locks;
-	struct prison_region regions[];
+	struct prison_region regions[] __counted_by(num_locks);
 };
 
 static struct kmem_cache *_cell_cache;
diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index 486e1180cc..f03d7dba27 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -1001,7 +1001,7 @@ struct dm_bufio_client {
 
 	sector_t start;
 
-	struct shrinker shrinker;
+	struct shrinker *shrinker;
 	struct work_struct shrink_work;
 	atomic_long_t need_shrink;
 
@@ -2405,7 +2405,7 @@ static unsigned long dm_bufio_shrink_scan(struct shrinker *shrink, struct shrink
 {
 	struct dm_bufio_client *c;
 
-	c = container_of(shrink, struct dm_bufio_client, shrinker);
+	c = shrink->private_data;
 	atomic_long_add(sc->nr_to_scan, &c->need_shrink);
 	queue_work(dm_bufio_wq, &c->shrink_work);
 
@@ -2414,7 +2414,7 @@ static unsigned long dm_bufio_shrink_scan(struct shrinker *shrink, struct shrink
 
 static unsigned long dm_bufio_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
 {
-	struct dm_bufio_client *c = container_of(shrink, struct dm_bufio_client, shrinker);
+	struct dm_bufio_client *c = shrink->private_data;
 	unsigned long count = cache_total(&c->cache);
 	unsigned long retain_target = get_retain_buffers(c);
 	unsigned long queued_for_cleanup = atomic_long_read(&c->need_shrink);
@@ -2527,14 +2527,20 @@ struct dm_bufio_client *dm_bufio_client_create(struct block_device *bdev, unsign
 	INIT_WORK(&c->shrink_work, shrink_work);
 	atomic_long_set(&c->need_shrink, 0);
 
-	c->shrinker.count_objects = dm_bufio_shrink_count;
-	c->shrinker.scan_objects = dm_bufio_shrink_scan;
-	c->shrinker.seeks = 1;
-	c->shrinker.batch = 0;
-	r = register_shrinker(&c->shrinker, "dm-bufio:(%u:%u)",
-			      MAJOR(bdev->bd_dev), MINOR(bdev->bd_dev));
-	if (r)
+	c->shrinker = shrinker_alloc(0, "dm-bufio:(%u:%u)",
+				     MAJOR(bdev->bd_dev), MINOR(bdev->bd_dev));
+	if (!c->shrinker) {
+		r = -ENOMEM;
 		goto bad;
+	}
+
+	c->shrinker->count_objects = dm_bufio_shrink_count;
+	c->shrinker->scan_objects = dm_bufio_shrink_scan;
+	c->shrinker->seeks = 1;
+	c->shrinker->batch = 0;
+	c->shrinker->private_data = c;
+
+	shrinker_register(c->shrinker);
 
 	mutex_lock(&dm_bufio_clients_lock);
 	dm_bufio_client_count++;
@@ -2574,7 +2580,7 @@ void dm_bufio_client_destroy(struct dm_bufio_client *c)
 
 	drop_buffers(c);
 
-	unregister_shrinker(&c->shrinker);
+	shrinker_free(c->shrinker);
 	flush_work(&c->shrink_work);
 
 	mutex_lock(&dm_bufio_clients_lock);
diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c
index acffed750e..96751cd3d1 100644
--- a/drivers/md/dm-cache-metadata.c
+++ b/drivers/md/dm-cache-metadata.c
@@ -597,7 +597,7 @@ static void read_superblock_fields(struct dm_cache_metadata *cmd,
 	cmd->discard_nr_blocks = to_dblock(le64_to_cpu(disk_super->discard_nr_blocks));
 	cmd->data_block_size = le32_to_cpu(disk_super->data_block_size);
 	cmd->cache_blocks = to_cblock(le32_to_cpu(disk_super->cache_blocks));
-	strncpy(cmd->policy_name, disk_super->policy_name, sizeof(cmd->policy_name));
+	strscpy(cmd->policy_name, disk_super->policy_name, sizeof(cmd->policy_name));
 	cmd->policy_version[0] = le32_to_cpu(disk_super->policy_version[0]);
 	cmd->policy_version[1] = le32_to_cpu(disk_super->policy_version[1]);
 	cmd->policy_version[2] = le32_to_cpu(disk_super->policy_version[2]);
@@ -707,7 +707,7 @@ static int __commit_transaction(struct dm_cache_metadata *cmd,
 	disk_super->discard_block_size = cpu_to_le64(cmd->discard_block_size);
 	disk_super->discard_nr_blocks = cpu_to_le64(from_dblock(cmd->discard_nr_blocks));
 	disk_super->cache_blocks = cpu_to_le32(from_cblock(cmd->cache_blocks));
-	strncpy(disk_super->policy_name, cmd->policy_name, sizeof(disk_super->policy_name));
+	strscpy(disk_super->policy_name, cmd->policy_name, sizeof(disk_super->policy_name));
 	disk_super->policy_version[0] = cpu_to_le32(cmd->policy_version[0]);
 	disk_super->policy_version[1] = cpu_to_le32(cmd->policy_version[1]);
 	disk_super->policy_version[2] = cpu_to_le32(cmd->policy_version[2]);
@@ -1726,7 +1726,7 @@ static int write_hints(struct dm_cache_metadata *cmd, struct dm_cache_policy *po
 	    (strlen(policy_name) > sizeof(cmd->policy_name) - 1))
 		return -EINVAL;
 
-	strncpy(cmd->policy_name, policy_name, sizeof(cmd->policy_name));
+	strscpy(cmd->policy_name, policy_name, sizeof(cmd->policy_name));
 	memcpy(cmd->policy_version, policy_version, sizeof(cmd->policy_version));
 
 	hint_size = dm_cache_policy_get_hint_size(policy);
@@ -1828,7 +1828,7 @@ int dm_cache_metadata_abort(struct dm_cache_metadata *cmd)
 	 * Replacement block manager (new_bm) is created and old_bm destroyed outside of
 	 * cmd root_lock to avoid ABBA deadlock that would result (due to life-cycle of
 	 * shrinker associated with the block manager's bufio client vs cmd root_lock).
-	 * - must take shrinker_rwsem without holding cmd->root_lock
+	 * - must take shrinker_mutex without holding cmd->root_lock
 	 */
 	new_bm = dm_block_manager_create(cmd->bdev, DM_CACHE_METADATA_BLOCK_SIZE << SECTOR_SHIFT,
 					 CACHE_MAX_CONCURRENT_LOCKS);
diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h
index 095b9b49aa..e6757a30dc 100644
--- a/drivers/md/dm-core.h
+++ b/drivers/md/dm-core.h
@@ -22,6 +22,8 @@
 #include "dm-ima.h"
 
 #define DM_RESERVED_MAX_IOS		1024
+#define DM_MAX_TARGETS			1048576
+#define DM_MAX_TARGET_PARAMS		1024
 
 struct dm_io;
 
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 17ffbf7fbe..4ab4e8dcfd 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -62,6 +62,8 @@ struct convert_context {
 		struct skcipher_request *req;
 		struct aead_request *req_aead;
 	} r;
+	bool aead_recheck;
+	bool aead_failed;
 
 };
 
@@ -73,10 +75,8 @@ struct dm_crypt_io {
 	struct bio *base_bio;
 	u8 *integrity_metadata;
 	bool integrity_metadata_from_pool:1;
-	bool in_tasklet:1;
 
 	struct work_struct work;
-	struct tasklet_struct tasklet;
 
 	struct convert_context ctx;
 
@@ -84,6 +84,8 @@ struct dm_crypt_io {
 	blk_status_t error;
 	sector_t sector;
 
+	struct bvec_iter saved_bi_iter;
+
 	struct rb_node rb_node;
 } CRYPTO_MINALIGN_ATTR;
 
@@ -224,7 +226,7 @@ struct crypt_config {
 	struct mutex bio_alloc_lock;
 
 	u8 *authenc_key; /* space for keys in authenc() format (if used) */
-	u8 key[];
+	u8 key[] __counted_by(key_size);
 };
 
 #define MIN_IOS		64
@@ -652,13 +654,7 @@ static int crypt_iv_tcw_whitening(struct crypt_config *cc,
 	/* calculate crc32 for every 32bit part and xor it */
 	desc->tfm = tcw->crc32_tfm;
 	for (i = 0; i < 4; i++) {
-		r = crypto_shash_init(desc);
-		if (r)
-			goto out;
-		r = crypto_shash_update(desc, &buf[i * 4], 4);
-		if (r)
-			goto out;
-		r = crypto_shash_final(desc, &buf[i * 4]);
+		r = crypto_shash_digest(desc, &buf[i * 4], 4, &buf[i * 4]);
 		if (r)
 			goto out;
 	}
@@ -1378,10 +1374,13 @@ static int crypt_convert_block_aead(struct crypt_config *cc,
 	if (r == -EBADMSG) {
 		sector_t s = le64_to_cpu(*sector);
 
-		DMERR_LIMIT("%pg: INTEGRITY AEAD ERROR, sector %llu",
-			    ctx->bio_in->bi_bdev, s);
-		dm_audit_log_bio(DM_MSG_PREFIX, "integrity-aead",
-				 ctx->bio_in, s, 0);
+		ctx->aead_failed = true;
+		if (ctx->aead_recheck) {
+			DMERR_LIMIT("%pg: INTEGRITY AEAD ERROR, sector %llu",
+				    ctx->bio_in->bi_bdev, s);
+			dm_audit_log_bio(DM_MSG_PREFIX, "integrity-aead",
+					 ctx->bio_in, s, 0);
+		}
 	}
 
 	if (!r && cc->iv_gen_ops && cc->iv_gen_ops->post)
@@ -1765,10 +1764,11 @@ static void crypt_io_init(struct dm_crypt_io *io, struct crypt_config *cc,
 	io->base_bio = bio;
 	io->sector = sector;
 	io->error = 0;
+	io->ctx.aead_recheck = false;
+	io->ctx.aead_failed = false;
 	io->ctx.r.req = NULL;
 	io->integrity_metadata = NULL;
 	io->integrity_metadata_from_pool = false;
-	io->in_tasklet = false;
 	atomic_set(&io->io_pending, 0);
 }
 
@@ -1777,12 +1777,7 @@ static void crypt_inc_pending(struct dm_crypt_io *io)
 	atomic_inc(&io->io_pending);
 }
 
-static void kcryptd_io_bio_endio(struct work_struct *work)
-{
-	struct dm_crypt_io *io = container_of(work, struct dm_crypt_io, work);
-
-	bio_endio(io->base_bio);
-}
+static void kcryptd_queue_read(struct dm_crypt_io *io);
 
 /*
  * One of the bios was finished. Check for completion of
@@ -1797,6 +1792,15 @@ static void crypt_dec_pending(struct dm_crypt_io *io)
 	if (!atomic_dec_and_test(&io->io_pending))
 		return;
 
+	if (likely(!io->ctx.aead_recheck) && unlikely(io->ctx.aead_failed) &&
+	    cc->on_disk_tag_size && bio_data_dir(base_bio) == READ) {
+		io->ctx.aead_recheck = true;
+		io->ctx.aead_failed = false;
+		io->error = 0;
+		kcryptd_queue_read(io);
+		return;
+	}
+
 	if (io->ctx.r.req)
 		crypt_free_req(cc, io->ctx.r.req, base_bio);
 
@@ -1807,20 +1811,6 @@ static void crypt_dec_pending(struct dm_crypt_io *io)
 
 	base_bio->bi_status = error;
 
-	/*
-	 * If we are running this function from our tasklet,
-	 * we can't call bio_endio() here, because it will call
-	 * clone_endio() from dm.c, which in turn will
-	 * free the current struct dm_crypt_io structure with
-	 * our tasklet. In this case we need to delay bio_endio()
-	 * execution to after the tasklet is done and dequeued.
-	 */
-	if (io->in_tasklet) {
-		INIT_WORK(&io->work, kcryptd_io_bio_endio);
-		queue_work(cc->io_queue, &io->work);
-		return;
-	}
-
 	bio_endio(base_bio);
 }
 
@@ -1846,15 +1836,19 @@ static void crypt_endio(struct bio *clone)
 	struct dm_crypt_io *io = clone->bi_private;
 	struct crypt_config *cc = io->cc;
 	unsigned int rw = bio_data_dir(clone);
-	blk_status_t error;
+	blk_status_t error = clone->bi_status;
+
+	if (io->ctx.aead_recheck && !error) {
+		kcryptd_queue_crypt(io);
+		return;
+	}
 
 	/*
 	 * free the processed pages
 	 */
-	if (rw == WRITE)
+	if (rw == WRITE || io->ctx.aead_recheck)
 		crypt_free_buffer_pages(cc, clone);
 
-	error = clone->bi_status;
 	bio_put(clone);
 
 	if (rw == READ && !error) {
@@ -1875,6 +1869,22 @@ static int kcryptd_io_read(struct dm_crypt_io *io, gfp_t gfp)
 	struct crypt_config *cc = io->cc;
 	struct bio *clone;
 
+	if (io->ctx.aead_recheck) {
+		if (!(gfp & __GFP_DIRECT_RECLAIM))
+			return 1;
+		crypt_inc_pending(io);
+		clone = crypt_alloc_buffer(io, io->base_bio->bi_iter.bi_size);
+		if (unlikely(!clone)) {
+			crypt_dec_pending(io);
+			return 1;
+		}
+		clone->bi_iter.bi_sector = cc->start + io->sector;
+		crypt_convert_init(cc, &io->ctx, clone, clone, io->sector);
+		io->saved_bi_iter = clone->bi_iter;
+		dm_submit_bio_remap(io->base_bio, clone);
+		return 0;
+	}
+
 	/*
 	 * We need the original biovec array in order to decrypt the whole bio
 	 * data *afterwards* -- thanks to immutable biovecs we don't need to
@@ -2101,6 +2111,12 @@ static void kcryptd_crypt_write_convert(struct dm_crypt_io *io)
 	io->ctx.bio_out = clone;
 	io->ctx.iter_out = clone->bi_iter;
 
+	if (crypt_integrity_aead(cc)) {
+		bio_copy_data(clone, io->base_bio);
+		io->ctx.bio_in = clone;
+		io->ctx.iter_in = clone->bi_iter;
+	}
+
 	sector += bio_sectors(clone);
 
 	crypt_inc_pending(io);
@@ -2137,6 +2153,14 @@ dec:
 
 static void kcryptd_crypt_read_done(struct dm_crypt_io *io)
 {
+	if (io->ctx.aead_recheck) {
+		if (!io->error) {
+			io->ctx.bio_in->bi_iter = io->saved_bi_iter;
+			bio_copy_data(io->base_bio, io->ctx.bio_in);
+		}
+		crypt_free_buffer_pages(io->cc, io->ctx.bio_in);
+		bio_put(io->ctx.bio_in);
+	}
 	crypt_dec_pending(io);
 }
 
@@ -2166,11 +2190,17 @@ static void kcryptd_crypt_read_convert(struct dm_crypt_io *io)
 
 	crypt_inc_pending(io);
 
-	crypt_convert_init(cc, &io->ctx, io->base_bio, io->base_bio,
-			   io->sector);
+	if (io->ctx.aead_recheck) {
+		io->ctx.cc_sector = io->sector + cc->iv_offset;
+		r = crypt_convert(cc, &io->ctx,
+				  test_bit(DM_CRYPT_NO_READ_WORKQUEUE, &cc->flags), true);
+	} else {
+		crypt_convert_init(cc, &io->ctx, io->base_bio, io->base_bio,
+				   io->sector);
 
-	r = crypt_convert(cc, &io->ctx,
-			  test_bit(DM_CRYPT_NO_READ_WORKQUEUE, &cc->flags), true);
+		r = crypt_convert(cc, &io->ctx,
+				  test_bit(DM_CRYPT_NO_READ_WORKQUEUE, &cc->flags), true);
+	}
 	/*
 	 * Crypto API backlogged the request, because its queue was full
 	 * and we're in softirq context, so continue from a workqueue
@@ -2212,10 +2242,13 @@ static void kcryptd_async_done(void *data, int error)
 	if (error == -EBADMSG) {
 		sector_t s = le64_to_cpu(*org_sector_of_dmreq(cc, dmreq));
 
-		DMERR_LIMIT("%pg: INTEGRITY AEAD ERROR, sector %llu",
-			    ctx->bio_in->bi_bdev, s);
-		dm_audit_log_bio(DM_MSG_PREFIX, "integrity-aead",
-				 ctx->bio_in, s, 0);
+		ctx->aead_failed = true;
+		if (ctx->aead_recheck) {
+			DMERR_LIMIT("%pg: INTEGRITY AEAD ERROR, sector %llu",
+				    ctx->bio_in->bi_bdev, s);
+			dm_audit_log_bio(DM_MSG_PREFIX, "integrity-aead",
+					 ctx->bio_in, s, 0);
+		}
 		io->error = BLK_STS_PROTECTION;
 	} else if (error < 0)
 		io->error = BLK_STS_IOERR;
@@ -2252,11 +2285,6 @@ static void kcryptd_crypt(struct work_struct *work)
 		kcryptd_crypt_write_convert(io);
 }
 
-static void kcryptd_crypt_tasklet(unsigned long work)
-{
-	kcryptd_crypt((struct work_struct *)work);
-}
-
 static void kcryptd_queue_crypt(struct dm_crypt_io *io)
 {
 	struct crypt_config *cc = io->cc;
@@ -2268,15 +2296,10 @@ static void kcryptd_queue_crypt(struct dm_crypt_io *io)
 		 * irqs_disabled(): the kernel may run some IO completion from the idle thread, but
 		 * it is being executed with irqs disabled.
 		 */
-		if (in_hardirq() || irqs_disabled()) {
-			io->in_tasklet = true;
-			tasklet_init(&io->tasklet, kcryptd_crypt_tasklet, (unsigned long)&io->work);
-			tasklet_schedule(&io->tasklet);
+		if (!(in_hardirq() || irqs_disabled())) {
+			kcryptd_crypt(&io->work);
 			return;
 		}
-
-		kcryptd_crypt(&io->work);
-		return;
 	}
 
 	INIT_WORK(&io->work, kcryptd_crypt);
@@ -2868,10 +2891,9 @@ static int crypt_ctr_auth_cipher(struct crypt_config *cc, char *cipher_api)
 	if (!start || !end || ++start > end)
 		return -EINVAL;
 
-	mac_alg = kzalloc(end - start + 1, GFP_KERNEL);
+	mac_alg = kmemdup_nul(start, end - start, GFP_KERNEL);
 	if (!mac_alg)
 		return -ENOMEM;
-	strncpy(mac_alg, start, end - start);
 
 	mac = crypto_alloc_ahash(mac_alg, 0, CRYPTO_ALG_ALLOCATES_MEMORY);
 	kfree(mac_alg);
@@ -3151,7 +3173,7 @@ static int crypt_ctr_optional(struct dm_target *ti, unsigned int argc, char **ar
 			sval = strchr(opt_string + strlen("integrity:"), ':') + 1;
 			if (!strcasecmp(sval, "aead")) {
 				set_bit(CRYPT_MODE_INTEGRITY_AEAD, &cc->cipher_flags);
-			} else  if (strcasecmp(sval, "none")) {
+			} else if (strcasecmp(sval, "none")) {
 				ti->error = "Unknown integrity profile";
 				return -EINVAL;
 			}
diff --git a/drivers/md/dm-delay.c b/drivers/md/dm-delay.c
index 3726fae300..5eabdb06c6 100644
--- a/drivers/md/dm-delay.c
+++ b/drivers/md/dm-delay.c
@@ -13,6 +13,7 @@
 #include <linux/blkdev.h>
 #include <linux/bio.h>
 #include <linux/slab.h>
+#include <linux/kthread.h>
 
 #include <linux/device-mapper.h>
 
@@ -31,6 +32,7 @@ struct delay_c {
 	struct workqueue_struct *kdelayd_wq;
 	struct work_struct flush_expired_bios;
 	struct list_head delayed_bios;
+	struct task_struct *worker;
 	bool may_delay;
 
 	struct delay_class read;
@@ -66,6 +68,11 @@ static void queue_timeout(struct delay_c *dc, unsigned long expires)
 	mutex_unlock(&dc->timer_lock);
 }
 
+static inline bool delay_is_fast(struct delay_c *dc)
+{
+	return !!dc->worker;
+}
+
 static void flush_bios(struct bio *bio)
 {
 	struct bio *n;
@@ -78,36 +85,61 @@ static void flush_bios(struct bio *bio)
 	}
 }
 
-static struct bio *flush_delayed_bios(struct delay_c *dc, int flush_all)
+static void flush_delayed_bios(struct delay_c *dc, bool flush_all)
 {
 	struct dm_delay_info *delayed, *next;
+	struct bio_list flush_bio_list;
 	unsigned long next_expires = 0;
-	unsigned long start_timer = 0;
-	struct bio_list flush_bios = { };
+	bool start_timer = false;
+	bio_list_init(&flush_bio_list);
 
 	mutex_lock(&delayed_bios_lock);
 	list_for_each_entry_safe(delayed, next, &dc->delayed_bios, list) {
+		cond_resched();
 		if (flush_all || time_after_eq(jiffies, delayed->expires)) {
 			struct bio *bio = dm_bio_from_per_bio_data(delayed,
 						sizeof(struct dm_delay_info));
 			list_del(&delayed->list);
-			bio_list_add(&flush_bios, bio);
+			bio_list_add(&flush_bio_list, bio);
 			delayed->class->ops--;
 			continue;
 		}
 
-		if (!start_timer) {
-			start_timer = 1;
-			next_expires = delayed->expires;
-		} else
-			next_expires = min(next_expires, delayed->expires);
+		if (!delay_is_fast(dc)) {
+			if (!start_timer) {
+				start_timer = true;
+				next_expires = delayed->expires;
+			} else {
+				next_expires = min(next_expires, delayed->expires);
+			}
+		}
 	}
 	mutex_unlock(&delayed_bios_lock);
 
 	if (start_timer)
 		queue_timeout(dc, next_expires);
 
-	return bio_list_get(&flush_bios);
+	flush_bios(bio_list_get(&flush_bio_list));
+}
+
+static int flush_worker_fn(void *data)
+{
+	struct delay_c *dc = data;
+
+	while (!kthread_should_stop()) {
+		flush_delayed_bios(dc, false);
+		mutex_lock(&delayed_bios_lock);
+		if (unlikely(list_empty(&dc->delayed_bios))) {
+			set_current_state(TASK_INTERRUPTIBLE);
+			mutex_unlock(&delayed_bios_lock);
+			schedule();
+		} else {
+			mutex_unlock(&delayed_bios_lock);
+			cond_resched();
+		}
+	}
+
+	return 0;
 }
 
 static void flush_expired_bios(struct work_struct *work)
@@ -115,7 +147,7 @@ static void flush_expired_bios(struct work_struct *work)
 	struct delay_c *dc;
 
 	dc = container_of(work, struct delay_c, flush_expired_bios);
-	flush_bios(flush_delayed_bios(dc, 0));
+	flush_delayed_bios(dc, false);
 }
 
 static void delay_dtr(struct dm_target *ti)
@@ -131,6 +163,8 @@ static void delay_dtr(struct dm_target *ti)
 		dm_put_device(ti, dc->write.dev);
 	if (dc->flush.dev)
 		dm_put_device(ti, dc->flush.dev);
+	if (dc->worker)
+		kthread_stop(dc->worker);
 
 	mutex_destroy(&dc->timer_lock);
 
@@ -175,6 +209,7 @@ static int delay_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 {
 	struct delay_c *dc;
 	int ret;
+	unsigned int max_delay;
 
 	if (argc != 3 && argc != 6 && argc != 9) {
 		ti->error = "Requires exactly 3, 6 or 9 arguments";
@@ -188,8 +223,6 @@ static int delay_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	}
 
 	ti->private = dc;
-	timer_setup(&dc->delay_timer, handle_delayed_timer, 0);
-	INIT_WORK(&dc->flush_expired_bios, flush_expired_bios);
 	INIT_LIST_HEAD(&dc->delayed_bios);
 	mutex_init(&dc->timer_lock);
 	dc->may_delay = true;
@@ -198,6 +231,7 @@ static int delay_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	ret = delay_class_ctr(ti, &dc->read, argv);
 	if (ret)
 		goto bad;
+	max_delay = dc->read.delay;
 
 	if (argc == 3) {
 		ret = delay_class_ctr(ti, &dc->write, argv);
@@ -206,6 +240,8 @@ static int delay_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		ret = delay_class_ctr(ti, &dc->flush, argv);
 		if (ret)
 			goto bad;
+		max_delay = max(max_delay, dc->write.delay);
+		max_delay = max(max_delay, dc->flush.delay);
 		goto out;
 	}
 
@@ -216,19 +252,37 @@ static int delay_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		ret = delay_class_ctr(ti, &dc->flush, argv + 3);
 		if (ret)
 			goto bad;
+		max_delay = max(max_delay, dc->flush.delay);
 		goto out;
 	}
 
 	ret = delay_class_ctr(ti, &dc->flush, argv + 6);
 	if (ret)
 		goto bad;
+	max_delay = max(max_delay, dc->flush.delay);
 
 out:
-	dc->kdelayd_wq = alloc_workqueue("kdelayd", WQ_MEM_RECLAIM, 0);
-	if (!dc->kdelayd_wq) {
-		ret = -EINVAL;
-		DMERR("Couldn't start kdelayd");
-		goto bad;
+	if (max_delay < 50) {
+		/*
+		 * In case of small requested delays, use kthread instead of
+		 * timers and workqueue to achieve better latency.
+		 */
+		dc->worker = kthread_create(&flush_worker_fn, dc,
+					    "dm-delay-flush-worker");
+		if (IS_ERR(dc->worker)) {
+			ret = PTR_ERR(dc->worker);
+			dc->worker = NULL;
+			goto bad;
+		}
+	} else {
+		timer_setup(&dc->delay_timer, handle_delayed_timer, 0);
+		INIT_WORK(&dc->flush_expired_bios, flush_expired_bios);
+		dc->kdelayd_wq = alloc_workqueue("kdelayd", WQ_MEM_RECLAIM, 0);
+		if (!dc->kdelayd_wq) {
+			ret = -EINVAL;
+			DMERR("Couldn't start kdelayd");
+			goto bad;
+		}
 	}
 
 	ti->num_flush_bios = 1;
@@ -264,7 +318,10 @@ static int delay_bio(struct delay_c *dc, struct delay_class *c, struct bio *bio)
 	list_add_tail(&delayed->list, &dc->delayed_bios);
 	mutex_unlock(&delayed_bios_lock);
 
-	queue_timeout(dc, expires);
+	if (delay_is_fast(dc))
+		wake_up_process(dc->worker);
+	else
+		queue_timeout(dc, expires);
 
 	return DM_MAPIO_SUBMITTED;
 }
@@ -277,8 +334,9 @@ static void delay_presuspend(struct dm_target *ti)
 	dc->may_delay = false;
 	mutex_unlock(&delayed_bios_lock);
 
-	del_timer_sync(&dc->delay_timer);
-	flush_bios(flush_delayed_bios(dc, 1));
+	if (!delay_is_fast(dc))
+		del_timer_sync(&dc->delay_timer);
+	flush_delayed_bios(dc, true);
 }
 
 static void delay_resume(struct dm_target *ti)
@@ -363,7 +421,7 @@ out:
 
 static struct target_type delay_target = {
 	.name	     = "delay",
-	.version     = {1, 3, 0},
+	.version     = {1, 4, 0},
 	.features    = DM_TARGET_PASSES_INTEGRITY,
 	.module      = THIS_MODULE,
 	.ctr	     = delay_ctr,
diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c
index 120153e44a..f57fb82152 100644
--- a/drivers/md/dm-flakey.c
+++ b/drivers/md/dm-flakey.c
@@ -434,7 +434,7 @@ static struct bio *clone_bio(struct dm_target *ti, struct flakey_c *fc, struct b
 
 	remaining_size = size;
 
-	order = MAX_ORDER - 1;
+	order = MAX_ORDER;
 	while (remaining_size) {
 		struct page *pages;
 		unsigned size_to_add, to_copy;
diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c
index 9261bbebd6..e8e8fc33d3 100644
--- a/drivers/md/dm-integrity.c
+++ b/drivers/md/dm-integrity.c
@@ -278,6 +278,8 @@ struct dm_integrity_c {
 
 	atomic64_t number_of_mismatches;
 
+	mempool_t recheck_pool;
+
 	struct notifier_block reboot_notifier;
 };
 
@@ -493,42 +495,32 @@ static int sb_mac(struct dm_integrity_c *ic, bool wr)
 {
 	SHASH_DESC_ON_STACK(desc, ic->journal_mac);
 	int r;
-	unsigned int size = crypto_shash_digestsize(ic->journal_mac);
+	unsigned int mac_size = crypto_shash_digestsize(ic->journal_mac);
+	__u8 *sb = (__u8 *)ic->sb;
+	__u8 *mac = sb + (1 << SECTOR_SHIFT) - mac_size;
 
-	if (sizeof(struct superblock) + size > 1 << SECTOR_SHIFT) {
+	if (sizeof(struct superblock) + mac_size > 1 << SECTOR_SHIFT) {
 		dm_integrity_io_error(ic, "digest is too long", -EINVAL);
 		return -EINVAL;
 	}
 
 	desc->tfm = ic->journal_mac;
 
-	r = crypto_shash_init(desc);
-	if (unlikely(r < 0)) {
-		dm_integrity_io_error(ic, "crypto_shash_init", r);
-		return r;
-	}
-
-	r = crypto_shash_update(desc, (__u8 *)ic->sb, (1 << SECTOR_SHIFT) - size);
-	if (unlikely(r < 0)) {
-		dm_integrity_io_error(ic, "crypto_shash_update", r);
-		return r;
-	}
-
 	if (likely(wr)) {
-		r = crypto_shash_final(desc, (__u8 *)ic->sb + (1 << SECTOR_SHIFT) - size);
+		r = crypto_shash_digest(desc, sb, mac - sb, mac);
 		if (unlikely(r < 0)) {
-			dm_integrity_io_error(ic, "crypto_shash_final", r);
+			dm_integrity_io_error(ic, "crypto_shash_digest", r);
 			return r;
 		}
 	} else {
-		__u8 result[HASH_MAX_DIGESTSIZE];
+		__u8 actual_mac[HASH_MAX_DIGESTSIZE];
 
-		r = crypto_shash_final(desc, result);
+		r = crypto_shash_digest(desc, sb, mac - sb, actual_mac);
 		if (unlikely(r < 0)) {
-			dm_integrity_io_error(ic, "crypto_shash_final", r);
+			dm_integrity_io_error(ic, "crypto_shash_digest", r);
 			return r;
 		}
-		if (memcmp((__u8 *)ic->sb + (1 << SECTOR_SHIFT) - size, result, size)) {
+		if (memcmp(mac, actual_mac, mac_size)) {
 			dm_integrity_io_error(ic, "superblock mac", -EILSEQ);
 			dm_audit_log_target(DM_MSG_PREFIX, "mac-superblock", ic->ti, 0);
 			return -EILSEQ;
@@ -1699,6 +1691,77 @@ failed:
 	get_random_bytes(result, ic->tag_size);
 }
 
+static noinline void integrity_recheck(struct dm_integrity_io *dio, char *checksum)
+{
+	struct bio *bio = dm_bio_from_per_bio_data(dio, sizeof(struct dm_integrity_io));
+	struct dm_integrity_c *ic = dio->ic;
+	struct bvec_iter iter;
+	struct bio_vec bv;
+	sector_t sector, logical_sector, area, offset;
+	struct page *page;
+	void *buffer;
+
+	get_area_and_offset(ic, dio->range.logical_sector, &area, &offset);
+	dio->metadata_block = get_metadata_sector_and_offset(ic, area, offset,
+							     &dio->metadata_offset);
+	sector = get_data_sector(ic, area, offset);
+	logical_sector = dio->range.logical_sector;
+
+	page = mempool_alloc(&ic->recheck_pool, GFP_NOIO);
+	buffer = page_to_virt(page);
+
+	__bio_for_each_segment(bv, bio, iter, dio->bio_details.bi_iter) {
+		unsigned pos = 0;
+
+		do {
+			char *mem;
+			int r;
+			struct dm_io_request io_req;
+			struct dm_io_region io_loc;
+			io_req.bi_opf = REQ_OP_READ;
+			io_req.mem.type = DM_IO_KMEM;
+			io_req.mem.ptr.addr = buffer;
+			io_req.notify.fn = NULL;
+			io_req.client = ic->io;
+			io_loc.bdev = ic->dev->bdev;
+			io_loc.sector = sector;
+			io_loc.count = ic->sectors_per_block;
+
+			r = dm_io(&io_req, 1, &io_loc, NULL);
+			if (unlikely(r)) {
+				dio->bi_status = errno_to_blk_status(r);
+				goto free_ret;
+			}
+
+			integrity_sector_checksum(ic, logical_sector, buffer, checksum);
+			r = dm_integrity_rw_tag(ic, checksum, &dio->metadata_block,
+						&dio->metadata_offset, ic->tag_size, TAG_CMP);
+			if (r) {
+				if (r > 0) {
+					DMERR_LIMIT("%pg: Checksum failed at sector 0x%llx",
+						    bio->bi_bdev, logical_sector);
+					atomic64_inc(&ic->number_of_mismatches);
+					dm_audit_log_bio(DM_MSG_PREFIX, "integrity-checksum",
+							 bio, logical_sector, 0);
+					r = -EILSEQ;
+				}
+				dio->bi_status = errno_to_blk_status(r);
+				goto free_ret;
+			}
+
+			mem = bvec_kmap_local(&bv);
+			memcpy(mem + pos, buffer, ic->sectors_per_block << SECTOR_SHIFT);
+			kunmap_local(mem);
+
+			pos += ic->sectors_per_block << SECTOR_SHIFT;
+			sector += ic->sectors_per_block;
+			logical_sector += ic->sectors_per_block;
+		} while (pos < bv.bv_len);
+	}
+free_ret:
+	mempool_free(page, &ic->recheck_pool);
+}
+
 static void integrity_metadata(struct work_struct *w)
 {
 	struct dm_integrity_io *dio = container_of(w, struct dm_integrity_io, work);
@@ -1786,15 +1849,8 @@ again:
 						checksums_ptr - checksums, dio->op == REQ_OP_READ ? TAG_CMP : TAG_WRITE);
 			if (unlikely(r)) {
 				if (r > 0) {
-					sector_t s;
-
-					s = sector - ((r + ic->tag_size - 1) / ic->tag_size);
-					DMERR_LIMIT("%pg: Checksum failed at sector 0x%llx",
-						    bio->bi_bdev, s);
-					r = -EILSEQ;
-					atomic64_inc(&ic->number_of_mismatches);
-					dm_audit_log_bio(DM_MSG_PREFIX, "integrity-checksum",
-							 bio, s, 0);
+					integrity_recheck(dio, checksums);
+					goto skip_io;
 				}
 				if (likely(checksums != checksums_onstack))
 					kfree(checksums);
@@ -4271,6 +4327,12 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned int argc, char **argv
 		goto bad;
 	}
 
+	r = mempool_init_page_pool(&ic->recheck_pool, 1, 0);
+	if (r) {
+		ti->error = "Cannot allocate mempool";
+		goto bad;
+	}
+
 	ic->metadata_wq = alloc_workqueue("dm-integrity-metadata",
 					  WQ_MEM_RECLAIM, METADATA_WORKQUEUE_MAX_ACTIVE);
 	if (!ic->metadata_wq) {
@@ -4619,6 +4681,7 @@ static void dm_integrity_dtr(struct dm_target *ti)
 	kvfree(ic->bbs);
 	if (ic->bufio)
 		dm_bufio_client_destroy(ic->bufio);
+	mempool_exit(&ic->recheck_pool);
 	mempool_exit(&ic->journal_io_mempool);
 	if (ic->io)
 		dm_io_client_destroy(ic->io);
diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c
index 21ebb6c393..3b1ad7127c 100644
--- a/drivers/md/dm-ioctl.c
+++ b/drivers/md/dm-ioctl.c
@@ -1295,8 +1295,8 @@ static void retrieve_status(struct dm_table *table,
 		spec->status = 0;
 		spec->sector_start = ti->begin;
 		spec->length = ti->len;
-		strncpy(spec->target_type, ti->type->name,
-			sizeof(spec->target_type) - 1);
+		strscpy_pad(spec->target_type, ti->type->name,
+			sizeof(spec->target_type));
 
 		outptr += sizeof(struct dm_target_spec);
 		remaining = len - (outptr - outbuf);
@@ -1941,7 +1941,8 @@ static int copy_params(struct dm_ioctl __user *user, struct dm_ioctl *param_kern
 			   minimum_data_size - sizeof(param_kernel->version)))
 		return -EFAULT;
 
-	if (param_kernel->data_size < minimum_data_size) {
+	if (unlikely(param_kernel->data_size < minimum_data_size) ||
+	    unlikely(param_kernel->data_size > DM_MAX_TARGETS * DM_MAX_TARGET_PARAMS)) {
 		DMERR("Invalid data size in the ioctl structure: %u",
 		      param_kernel->data_size);
 		return -EINVAL;
diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c
index f4448d520e..2d3e186ca8 100644
--- a/drivers/md/dm-linear.c
+++ b/drivers/md/dm-linear.c
@@ -85,7 +85,7 @@ static sector_t linear_map_sector(struct dm_target *ti, sector_t bi_sector)
 	return lc->start + dm_target_offset(ti, bi_sector);
 }
 
-static int linear_map(struct dm_target *ti, struct bio *bio)
+int linear_map(struct dm_target *ti, struct bio *bio)
 {
 	struct linear_c *lc = ti->private;
 
diff --git a/drivers/md/dm-log-userspace-base.c b/drivers/md/dm-log-userspace-base.c
index 5aace6ee6d..7e4f27e861 100644
--- a/drivers/md/dm-log-userspace-base.c
+++ b/drivers/md/dm-log-userspace-base.c
@@ -224,7 +224,7 @@ static int userspace_ctr(struct dm_dirty_log *log, struct dm_target *ti,
 
 	lc->usr_argc = argc;
 
-	strncpy(lc->uuid, argv[0], DM_UUID_LEN);
+	strscpy(lc->uuid, argv[0], sizeof(lc->uuid));
 	argc--;
 	argv++;
 	spin_lock_init(&lc->flush_lock);
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 5f9991765f..eb009d6bb0 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -254,7 +254,7 @@ struct raid_set {
 		int mode;
 	} journal_dev;
 
-	struct raid_dev dev[];
+	struct raid_dev dev[] __counted_by(raid_disks);
 };
 
 static void rs_config_backup(struct raid_set *rs, struct rs_layout *l)
@@ -749,7 +749,11 @@ static struct raid_set *raid_set_alloc(struct dm_target *ti, struct raid_type *r
 		return ERR_PTR(-ENOMEM);
 	}
 
-	mddev_init(&rs->md);
+	if (mddev_init(&rs->md)) {
+		kfree(rs);
+		ti->error = "Cannot initialize raid context";
+		return ERR_PTR(-ENOMEM);
+	}
 
 	rs->raid_disks = raid_devs;
 	rs->delta_disks = 0;
@@ -798,6 +802,7 @@ static void raid_set_free(struct raid_set *rs)
 			dm_put_device(rs->ti, rs->dev[i].data_dev);
 	}
 
+	mddev_destroy(&rs->md);
 	kfree(rs);
 }
 
@@ -3239,7 +3244,7 @@ size_check:
 	set_bit(MD_RECOVERY_FROZEN, &rs->md.recovery);
 
 	/* Has to be held on running the array */
-	mddev_lock_nointr(&rs->md);
+	mddev_suspend_and_lock_nointr(&rs->md);
 	r = md_run(&rs->md);
 	rs->md.in_sync = 0; /* Assume already marked dirty */
 	if (r) {
@@ -3263,7 +3268,6 @@ size_check:
 		}
 	}
 
-	mddev_suspend(&rs->md);
 	set_bit(RT_FLAG_RS_SUSPENDED, &rs->runtime_flags);
 
 	/* Try to adjust the raid4/5/6 stripe cache size to the stripe size */
@@ -3313,6 +3317,9 @@ static void raid_dtr(struct dm_target *ti)
 	mddev_lock_nointr(&rs->md);
 	md_stop(&rs->md);
 	mddev_unlock(&rs->md);
+
+	if (work_pending(&rs->md.event_work))
+		flush_work(&rs->md.event_work);
 	raid_set_free(rs);
 }
 
@@ -3793,9 +3800,7 @@ static void raid_postsuspend(struct dm_target *ti)
 		if (!test_bit(MD_RECOVERY_FROZEN, &rs->md.recovery))
 			md_stop_writes(&rs->md);
 
-		mddev_lock_nointr(&rs->md);
-		mddev_suspend(&rs->md);
-		mddev_unlock(&rs->md);
+		mddev_suspend(&rs->md, false);
 	}
 }
 
@@ -4054,8 +4059,7 @@ static void raid_resume(struct dm_target *ti)
 		clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 		mddev->ro = 0;
 		mddev->in_sync = 0;
-		mddev_resume(mddev);
-		mddev_unlock(mddev);
+		mddev_unlock_and_resume(mddev);
 	}
 }
 
diff --git a/drivers/md/dm-stats.c b/drivers/md/dm-stats.c
index db2d997a6c..bdc14ec998 100644
--- a/drivers/md/dm-stats.c
+++ b/drivers/md/dm-stats.c
@@ -56,7 +56,7 @@ struct dm_stat {
 	size_t percpu_alloc_size;
 	size_t histogram_alloc_size;
 	struct dm_stat_percpu *stat_percpu[NR_CPUS];
-	struct dm_stat_shared stat_shared[];
+	struct dm_stat_shared stat_shared[] __counted_by(n_entries);
 };
 
 #define STAT_PRECISE_TIMESTAMPS		1
diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c
index e2854a3cbd..16b93ae51d 100644
--- a/drivers/md/dm-stripe.c
+++ b/drivers/md/dm-stripe.c
@@ -44,7 +44,7 @@ struct stripe_c {
 	/* Work struct used for triggering events*/
 	struct work_struct trigger_event;
 
-	struct stripe stripe[];
+	struct stripe stripe[] __counted_by(stripes);
 };
 
 /*
@@ -268,7 +268,7 @@ static int stripe_map_range(struct stripe_c *sc, struct bio *bio,
 	return DM_MAPIO_SUBMITTED;
 }
 
-static int stripe_map(struct dm_target *ti, struct bio *bio)
+int stripe_map(struct dm_target *ti, struct bio *bio)
 {
 	struct stripe_c *sc = ti->private;
 	uint32_t stripe;
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 37b48f63ae..08c9c20f9c 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -129,7 +129,12 @@ static int alloc_targets(struct dm_table *t, unsigned int num)
 int dm_table_create(struct dm_table **result, blk_mode_t mode,
 		    unsigned int num_targets, struct mapped_device *md)
 {
-	struct dm_table *t = kzalloc(sizeof(*t), GFP_KERNEL);
+	struct dm_table *t;
+
+	if (num_targets > DM_MAX_TARGETS)
+		return -EOVERFLOW;
+
+	t = kzalloc(sizeof(*t), GFP_KERNEL);
 
 	if (!t)
 		return -ENOMEM;
@@ -144,7 +149,7 @@ int dm_table_create(struct dm_table **result, blk_mode_t mode,
 
 	if (!num_targets) {
 		kfree(t);
-		return -ENOMEM;
+		return -EOVERFLOW;
 	}
 
 	if (alloc_targets(t, num_targets)) {
@@ -844,7 +849,8 @@ static bool dm_table_supports_dax(struct dm_table *t,
 		if (!ti->type->direct_access)
 			return false;
 
-		if (!ti->type->iterate_devices ||
+		if (dm_target_is_wildcard(ti->type) ||
+		    !ti->type->iterate_devices ||
 		    ti->type->iterate_devices(ti, iterate_fn, NULL))
 			return false;
 	}
@@ -1587,6 +1593,14 @@ static int device_not_zoned_model(struct dm_target *ti, struct dm_dev *dev,
 	return blk_queue_zoned_model(q) != *zoned_model;
 }
 
+static int device_is_zoned_model(struct dm_target *ti, struct dm_dev *dev,
+				 sector_t start, sector_t len, void *data)
+{
+	struct request_queue *q = bdev_get_queue(dev->bdev);
+
+	return blk_queue_zoned_model(q) != BLK_ZONED_NONE;
+}
+
 /*
  * Check the device zoned model based on the target feature flag. If the target
  * has the DM_TARGET_ZONED_HM feature flag set, host-managed zoned devices are
@@ -1600,6 +1614,18 @@ static bool dm_table_supports_zoned_model(struct dm_table *t,
 	for (unsigned int i = 0; i < t->num_targets; i++) {
 		struct dm_target *ti = dm_table_get_target(t, i);
 
+		/*
+		 * For the wildcard target (dm-error), if we do not have a
+		 * backing device, we must always return false. If we have a
+		 * backing device, the result must depend on checking zoned
+		 * model, like for any other target. So for this, check directly
+		 * if the target backing device is zoned as we get "false" when
+		 * dm-error was set without a backing device.
+		 */
+		if (dm_target_is_wildcard(ti->type) &&
+		    !ti->type->iterate_devices(ti, device_is_zoned_model, NULL))
+			return false;
+
 		if (dm_target_supports_zoned_hm(ti->type)) {
 			if (!ti->type->iterate_devices ||
 			    ti->type->iterate_devices(ti, device_not_zoned_model,
diff --git a/drivers/md/dm-target.c b/drivers/md/dm-target.c
index 27e2992ff2..0c4efb0bef 100644
--- a/drivers/md/dm-target.c
+++ b/drivers/md/dm-target.c
@@ -116,9 +116,63 @@ EXPORT_SYMBOL(dm_unregister_target);
  * io-err: always fails an io, useful for bringing
  * up LVs that have holes in them.
  */
+struct io_err_c {
+	struct dm_dev *dev;
+	sector_t start;
+};
+
+static int io_err_get_args(struct dm_target *tt, unsigned int argc, char **args)
+{
+	unsigned long long start;
+	struct io_err_c *ioec;
+	char dummy;
+	int ret;
+
+	ioec = kmalloc(sizeof(*ioec), GFP_KERNEL);
+	if (!ioec) {
+		tt->error = "Cannot allocate io_err context";
+		return -ENOMEM;
+	}
+
+	ret = -EINVAL;
+	if (sscanf(args[1], "%llu%c", &start, &dummy) != 1 ||
+	    start != (sector_t)start) {
+		tt->error = "Invalid device sector";
+		goto bad;
+	}
+	ioec->start = start;
+
+	ret = dm_get_device(tt, args[0], dm_table_get_mode(tt->table), &ioec->dev);
+	if (ret) {
+		tt->error = "Device lookup failed";
+		goto bad;
+	}
+
+	tt->private = ioec;
+
+	return 0;
+
+bad:
+	kfree(ioec);
+
+	return ret;
+}
+
 static int io_err_ctr(struct dm_target *tt, unsigned int argc, char **args)
 {
 	/*
+	 * If we have arguments, assume it is the path to the backing
+	 * block device and its mapping start sector (same as dm-linear).
+	 * In this case, get the device so that we can get its limits.
+	 */
+	if (argc == 2) {
+		int ret = io_err_get_args(tt, argc, args);
+
+		if (ret)
+			return ret;
+	}
+
+	/*
 	 * Return error for discards instead of -EOPNOTSUPP
 	 */
 	tt->num_discard_bios = 1;
@@ -129,7 +183,12 @@ static int io_err_ctr(struct dm_target *tt, unsigned int argc, char **args)
 
 static void io_err_dtr(struct dm_target *tt)
 {
-	/* empty */
+	struct io_err_c *ioec = tt->private;
+
+	if (ioec) {
+		dm_put_device(tt, ioec->dev);
+		kfree(ioec);
+	}
 }
 
 static int io_err_map(struct dm_target *tt, struct bio *bio)
@@ -149,6 +208,45 @@ static void io_err_release_clone_rq(struct request *clone,
 {
 }
 
+#ifdef CONFIG_BLK_DEV_ZONED
+static sector_t io_err_map_sector(struct dm_target *ti, sector_t bi_sector)
+{
+	struct io_err_c *ioec = ti->private;
+
+	return ioec->start + dm_target_offset(ti, bi_sector);
+}
+
+static int io_err_report_zones(struct dm_target *ti,
+		struct dm_report_zones_args *args, unsigned int nr_zones)
+{
+	struct io_err_c *ioec = ti->private;
+
+	/*
+	 * This should never be called when we do not have a backing device
+	 * as that mean the target is not a zoned one.
+	 */
+	if (WARN_ON_ONCE(!ioec))
+		return -EIO;
+
+	return dm_report_zones(ioec->dev->bdev, ioec->start,
+			       io_err_map_sector(ti, args->next_sector),
+			       args, nr_zones);
+}
+#else
+#define io_err_report_zones NULL
+#endif
+
+static int io_err_iterate_devices(struct dm_target *ti,
+				  iterate_devices_callout_fn fn, void *data)
+{
+	struct io_err_c *ioec = ti->private;
+
+	if (!ioec)
+		return 0;
+
+	return fn(ti, ioec->dev, ioec->start, ti->len, data);
+}
+
 static void io_err_io_hints(struct dm_target *ti, struct queue_limits *limits)
 {
 	limits->max_discard_sectors = UINT_MAX;
@@ -165,15 +263,17 @@ static long io_err_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
 
 static struct target_type error_target = {
 	.name = "error",
-	.version = {1, 6, 0},
-	.features = DM_TARGET_WILDCARD,
+	.version = {1, 7, 0},
+	.features = DM_TARGET_WILDCARD | DM_TARGET_ZONED_HM,
 	.ctr  = io_err_ctr,
 	.dtr  = io_err_dtr,
 	.map  = io_err_map,
 	.clone_and_map_rq = io_err_clone_and_map_rq,
 	.release_clone_rq = io_err_release_clone_rq,
+	.iterate_devices = io_err_iterate_devices,
 	.io_hints = io_err_io_hints,
 	.direct_access = io_err_dax_direct_access,
+	.report_zones = io_err_report_zones,
 };
 
 int __init dm_target_init(void)
diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c
index 14e58ae705..7b620b187d 100644
--- a/drivers/md/dm-verity-target.c
+++ b/drivers/md/dm-verity-target.c
@@ -482,6 +482,63 @@ int verity_for_bv_block(struct dm_verity *v, struct dm_verity_io *io,
 	return 0;
 }
 
+static int verity_recheck_copy(struct dm_verity *v, struct dm_verity_io *io,
+			       u8 *data, size_t len)
+{
+	memcpy(data, io->recheck_buffer, len);
+	io->recheck_buffer += len;
+
+	return 0;
+}
+
+static noinline int verity_recheck(struct dm_verity *v, struct dm_verity_io *io,
+				   struct bvec_iter start, sector_t cur_block)
+{
+	struct page *page;
+	void *buffer;
+	int r;
+	struct dm_io_request io_req;
+	struct dm_io_region io_loc;
+
+	page = mempool_alloc(&v->recheck_pool, GFP_NOIO);
+	buffer = page_to_virt(page);
+
+	io_req.bi_opf = REQ_OP_READ;
+	io_req.mem.type = DM_IO_KMEM;
+	io_req.mem.ptr.addr = buffer;
+	io_req.notify.fn = NULL;
+	io_req.client = v->io;
+	io_loc.bdev = v->data_dev->bdev;
+	io_loc.sector = cur_block << (v->data_dev_block_bits - SECTOR_SHIFT);
+	io_loc.count = 1 << (v->data_dev_block_bits - SECTOR_SHIFT);
+	r = dm_io(&io_req, 1, &io_loc, NULL);
+	if (unlikely(r))
+		goto free_ret;
+
+	r = verity_hash(v, verity_io_hash_req(v, io), buffer,
+			1 << v->data_dev_block_bits,
+			verity_io_real_digest(v, io), true);
+	if (unlikely(r))
+		goto free_ret;
+
+	if (memcmp(verity_io_real_digest(v, io),
+		   verity_io_want_digest(v, io), v->digest_size)) {
+		r = -EIO;
+		goto free_ret;
+	}
+
+	io->recheck_buffer = buffer;
+	r = verity_for_bv_block(v, io, &start, verity_recheck_copy);
+	if (unlikely(r))
+		goto free_ret;
+
+	r = 0;
+free_ret:
+	mempool_free(page, &v->recheck_pool);
+
+	return r;
+}
+
 static int verity_bv_zero(struct dm_verity *v, struct dm_verity_io *io,
 			  u8 *data, size_t len)
 {
@@ -508,9 +565,7 @@ static int verity_verify_io(struct dm_verity_io *io)
 {
 	bool is_zero;
 	struct dm_verity *v = io->v;
-#if defined(CONFIG_DM_VERITY_FEC)
 	struct bvec_iter start;
-#endif
 	struct bvec_iter iter_copy;
 	struct bvec_iter *iter;
 	struct crypto_wait wait;
@@ -561,10 +616,7 @@ static int verity_verify_io(struct dm_verity_io *io)
 		if (unlikely(r < 0))
 			return r;
 
-#if defined(CONFIG_DM_VERITY_FEC)
-		if (verity_fec_is_enabled(v))
-			start = *iter;
-#endif
+		start = *iter;
 		r = verity_for_io_block(v, io, iter, &wait);
 		if (unlikely(r < 0))
 			return r;
@@ -586,6 +638,10 @@ static int verity_verify_io(struct dm_verity_io *io)
 			 * tasklet since it may sleep, so fallback to work-queue.
 			 */
 			return -EAGAIN;
+		} else if (verity_recheck(v, io, start, cur_block) == 0) {
+			if (v->validated_blocks)
+				set_bit(cur_block, v->validated_blocks);
+			continue;
 #if defined(CONFIG_DM_VERITY_FEC)
 		} else if (verity_fec_decode(v, io, DM_VERITY_BLOCK_TYPE_DATA,
 					     cur_block, NULL, &start) == 0) {
@@ -645,23 +701,6 @@ static void verity_work(struct work_struct *w)
 	verity_finish_io(io, errno_to_blk_status(verity_verify_io(io)));
 }
 
-static void verity_tasklet(unsigned long data)
-{
-	struct dm_verity_io *io = (struct dm_verity_io *)data;
-	int err;
-
-	io->in_tasklet = true;
-	err = verity_verify_io(io);
-	if (err == -EAGAIN || err == -ENOMEM) {
-		/* fallback to retrying with work-queue */
-		INIT_WORK(&io->work, verity_work);
-		queue_work(io->v->verify_wq, &io->work);
-		return;
-	}
-
-	verity_finish_io(io, errno_to_blk_status(err));
-}
-
 static void verity_end_io(struct bio *bio)
 {
 	struct dm_verity_io *io = bio->bi_private;
@@ -674,13 +713,8 @@ static void verity_end_io(struct bio *bio)
 		return;
 	}
 
-	if (static_branch_unlikely(&use_tasklet_enabled) && io->v->use_tasklet) {
-		tasklet_init(&io->tasklet, verity_tasklet, (unsigned long)io);
-		tasklet_schedule(&io->tasklet);
-	} else {
-		INIT_WORK(&io->work, verity_work);
-		queue_work(io->v->verify_wq, &io->work);
-	}
+	INIT_WORK(&io->work, verity_work);
+	queue_work(io->v->verify_wq, &io->work);
 }
 
 /*
@@ -963,6 +997,10 @@ static void verity_dtr(struct dm_target *ti)
 	if (v->verify_wq)
 		destroy_workqueue(v->verify_wq);
 
+	mempool_exit(&v->recheck_pool);
+	if (v->io)
+		dm_io_client_destroy(v->io);
+
 	if (v->bufio)
 		dm_bufio_client_destroy(v->bufio);
 
@@ -1401,6 +1439,20 @@ static int verity_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	}
 	v->hash_blocks = hash_position;
 
+	r = mempool_init_page_pool(&v->recheck_pool, 1, 0);
+	if (unlikely(r)) {
+		ti->error = "Cannot allocate mempool";
+		goto bad;
+	}
+
+	v->io = dm_io_client_create();
+	if (IS_ERR(v->io)) {
+		r = PTR_ERR(v->io);
+		v->io = NULL;
+		ti->error = "Cannot allocate dm io";
+		goto bad;
+	}
+
 	v->bufio = dm_bufio_client_create(v->hash_dev->bdev,
 		1 << v->hash_dev_block_bits, 1, sizeof(struct buffer_aux),
 		dm_bufio_alloc_callback, NULL,
diff --git a/drivers/md/dm-verity.h b/drivers/md/dm-verity.h
index f9d522c870..4620a98c99 100644
--- a/drivers/md/dm-verity.h
+++ b/drivers/md/dm-verity.h
@@ -11,6 +11,7 @@
 #ifndef DM_VERITY_H
 #define DM_VERITY_H
 
+#include <linux/dm-io.h>
 #include <linux/dm-bufio.h>
 #include <linux/device-mapper.h>
 #include <linux/interrupt.h>
@@ -68,6 +69,9 @@ struct dm_verity {
 	unsigned long *validated_blocks; /* bitset blocks validated */
 
 	char *signature_key_desc; /* signature keyring reference */
+
+	struct dm_io_client *io;
+	mempool_t recheck_pool;
 };
 
 struct dm_verity_io {
@@ -83,7 +87,8 @@ struct dm_verity_io {
 	struct bvec_iter iter;
 
 	struct work_struct work;
-	struct tasklet_struct tasklet;
+
+	char *recheck_buffer;
 
 	/*
 	 * Three variably-size fields follow this struct:
diff --git a/drivers/md/dm-zoned-metadata.c b/drivers/md/dm-zoned-metadata.c
index 9d3cca8e3d..60a4dc01ea 100644
--- a/drivers/md/dm-zoned-metadata.c
+++ b/drivers/md/dm-zoned-metadata.c
@@ -187,7 +187,7 @@ struct dmz_metadata {
 	struct rb_root		mblk_rbtree;
 	struct list_head	mblk_lru_list;
 	struct list_head	mblk_dirty_list;
-	struct shrinker		mblk_shrinker;
+	struct shrinker		*mblk_shrinker;
 
 	/* Zone allocation management */
 	struct mutex		map_lock;
@@ -615,7 +615,7 @@ static unsigned long dmz_shrink_mblock_cache(struct dmz_metadata *zmd,
 static unsigned long dmz_mblock_shrinker_count(struct shrinker *shrink,
 					       struct shrink_control *sc)
 {
-	struct dmz_metadata *zmd = container_of(shrink, struct dmz_metadata, mblk_shrinker);
+	struct dmz_metadata *zmd = shrink->private_data;
 
 	return atomic_read(&zmd->nr_mblks);
 }
@@ -626,7 +626,7 @@ static unsigned long dmz_mblock_shrinker_count(struct shrinker *shrink,
 static unsigned long dmz_mblock_shrinker_scan(struct shrinker *shrink,
 					      struct shrink_control *sc)
 {
-	struct dmz_metadata *zmd = container_of(shrink, struct dmz_metadata, mblk_shrinker);
+	struct dmz_metadata *zmd = shrink->private_data;
 	unsigned long count;
 
 	spin_lock(&zmd->mblk_lock);
@@ -2936,19 +2936,23 @@ int dmz_ctr_metadata(struct dmz_dev *dev, int num_dev,
 	 */
 	zmd->min_nr_mblks = 2 + zmd->nr_map_blocks + zmd->zone_nr_bitmap_blocks * 16;
 	zmd->max_nr_mblks = zmd->min_nr_mblks + 512;
-	zmd->mblk_shrinker.count_objects = dmz_mblock_shrinker_count;
-	zmd->mblk_shrinker.scan_objects = dmz_mblock_shrinker_scan;
-	zmd->mblk_shrinker.seeks = DEFAULT_SEEKS;
 
 	/* Metadata cache shrinker */
-	ret = register_shrinker(&zmd->mblk_shrinker, "dm-zoned-meta:(%u:%u)",
-				MAJOR(dev->bdev->bd_dev),
-				MINOR(dev->bdev->bd_dev));
-	if (ret) {
-		dmz_zmd_err(zmd, "Register metadata cache shrinker failed");
+	zmd->mblk_shrinker = shrinker_alloc(0,  "dm-zoned-meta:(%u:%u)",
+					    MAJOR(dev->bdev->bd_dev),
+					    MINOR(dev->bdev->bd_dev));
+	if (!zmd->mblk_shrinker) {
+		ret = -ENOMEM;
+		dmz_zmd_err(zmd, "Allocate metadata cache shrinker failed");
 		goto err;
 	}
 
+	zmd->mblk_shrinker->count_objects = dmz_mblock_shrinker_count;
+	zmd->mblk_shrinker->scan_objects = dmz_mblock_shrinker_scan;
+	zmd->mblk_shrinker->private_data = zmd;
+
+	shrinker_register(zmd->mblk_shrinker);
+
 	dmz_zmd_info(zmd, "DM-Zoned metadata version %d", zmd->sb_version);
 	for (i = 0; i < zmd->nr_devs; i++)
 		dmz_print_dev(zmd, i);
@@ -2995,7 +2999,7 @@ err:
  */
 void dmz_dtr_metadata(struct dmz_metadata *zmd)
 {
-	unregister_shrinker(&zmd->mblk_shrinker);
+	shrinker_free(zmd->mblk_shrinker);
 	dmz_cleanup_metadata(zmd);
 	kfree(zmd);
 }
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 64a1f306c9..23c32cd1f1 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -570,13 +570,15 @@ static void dm_end_io_acct(struct dm_io *io)
 	dm_io_acct(io, true);
 }
 
-static struct dm_io *alloc_io(struct mapped_device *md, struct bio *bio)
+static struct dm_io *alloc_io(struct mapped_device *md, struct bio *bio, gfp_t gfp_mask)
 {
 	struct dm_io *io;
 	struct dm_target_io *tio;
 	struct bio *clone;
 
-	clone = bio_alloc_clone(NULL, bio, GFP_NOIO, &md->mempools->io_bs);
+	clone = bio_alloc_clone(NULL, bio, gfp_mask, &md->mempools->io_bs);
+	if (unlikely(!clone))
+		return NULL;
 	tio = clone_to_tio(clone);
 	tio->flags = 0;
 	dm_tio_set_flag(tio, DM_TIO_INSIDE_DM_IO);
@@ -724,7 +726,7 @@ static struct table_device *open_table_device(struct mapped_device *md,
 		dev_t dev, blk_mode_t mode)
 {
 	struct table_device *td;
-	struct block_device *bdev;
+	struct bdev_handle *bdev_handle;
 	u64 part_off;
 	int r;
 
@@ -733,9 +735,9 @@ static struct table_device *open_table_device(struct mapped_device *md,
 		return ERR_PTR(-ENOMEM);
 	refcount_set(&td->count, 1);
 
-	bdev = blkdev_get_by_dev(dev, mode, _dm_claim_ptr, NULL);
-	if (IS_ERR(bdev)) {
-		r = PTR_ERR(bdev);
+	bdev_handle = bdev_open_by_dev(dev, mode, _dm_claim_ptr, NULL);
+	if (IS_ERR(bdev_handle)) {
+		r = PTR_ERR(bdev_handle);
 		goto out_free_td;
 	}
 
@@ -745,20 +747,22 @@ static struct table_device *open_table_device(struct mapped_device *md,
 	 * called.
 	 */
 	if (md->disk->slave_dir) {
-		r = bd_link_disk_holder(bdev, md->disk);
+		r = bd_link_disk_holder(bdev_handle->bdev, md->disk);
 		if (r)
 			goto out_blkdev_put;
 	}
 
 	td->dm_dev.mode = mode;
-	td->dm_dev.bdev = bdev;
-	td->dm_dev.dax_dev = fs_dax_get_by_bdev(bdev, &part_off, NULL, NULL);
+	td->dm_dev.bdev = bdev_handle->bdev;
+	td->dm_dev.bdev_handle = bdev_handle;
+	td->dm_dev.dax_dev = fs_dax_get_by_bdev(bdev_handle->bdev, &part_off,
+						NULL, NULL);
 	format_dev_t(td->dm_dev.name, dev);
 	list_add(&td->list, &md->table_devices);
 	return td;
 
 out_blkdev_put:
-	blkdev_put(bdev, _dm_claim_ptr);
+	bdev_release(bdev_handle);
 out_free_td:
 	kfree(td);
 	return ERR_PTR(r);
@@ -771,7 +775,7 @@ static void close_table_device(struct table_device *td, struct mapped_device *md
 {
 	if (md->disk->slave_dir)
 		bd_unlink_disk_holder(td->dm_dev.bdev, md->disk);
-	blkdev_put(td->dm_dev.bdev, _dm_claim_ptr);
+	bdev_release(td->dm_dev.bdev_handle);
 	put_dax(td->dm_dev.dax_dev);
 	list_del(&td->list);
 	kfree(td);
@@ -1424,9 +1428,16 @@ static void __map_bio(struct bio *clone)
 		if (unlikely(dm_emulate_zone_append(md)))
 			r = dm_zone_map_bio(tio);
 		else
+			goto do_map;
+	} else {
+do_map:
+		if (likely(ti->type->map == linear_map))
+			r = linear_map(ti, clone);
+		else if (ti->type->map == stripe_map)
+			r = stripe_map(ti, clone);
+		else
 			r = ti->type->map(ti, clone);
-	} else
-		r = ti->type->map(ti, clone);
+	}
 
 	switch (r) {
 	case DM_MAPIO_SUBMITTED:
@@ -1471,15 +1482,15 @@ static void setup_split_accounting(struct clone_info *ci, unsigned int len)
 
 static void alloc_multiple_bios(struct bio_list *blist, struct clone_info *ci,
 				struct dm_target *ti, unsigned int num_bios,
-				unsigned *len)
+				unsigned *len, gfp_t gfp_flag)
 {
 	struct bio *bio;
-	int try;
+	int try = (gfp_flag & GFP_NOWAIT) ? 0 : 1;
 
-	for (try = 0; try < 2; try++) {
+	for (; try < 2; try++) {
 		int bio_nr;
 
-		if (try)
+		if (try && num_bios > 1)
 			mutex_lock(&ci->io->md->table_devices_lock);
 		for (bio_nr = 0; bio_nr < num_bios; bio_nr++) {
 			bio = alloc_tio(ci, ti, bio_nr, len,
@@ -1489,7 +1500,7 @@ static void alloc_multiple_bios(struct bio_list *blist, struct clone_info *ci,
 
 			bio_list_add(blist, bio);
 		}
-		if (try)
+		if (try && num_bios > 1)
 			mutex_unlock(&ci->io->md->table_devices_lock);
 		if (bio_nr == num_bios)
 			return;
@@ -1499,34 +1510,31 @@ static void alloc_multiple_bios(struct bio_list *blist, struct clone_info *ci,
 	}
 }
 
-static int __send_duplicate_bios(struct clone_info *ci, struct dm_target *ti,
-				 unsigned int num_bios, unsigned int *len)
+static unsigned int __send_duplicate_bios(struct clone_info *ci, struct dm_target *ti,
+					  unsigned int num_bios, unsigned int *len,
+					  gfp_t gfp_flag)
 {
 	struct bio_list blist = BIO_EMPTY_LIST;
 	struct bio *clone;
 	unsigned int ret = 0;
 
-	switch (num_bios) {
-	case 0:
-		break;
-	case 1:
-		if (len)
-			setup_split_accounting(ci, *len);
-		clone = alloc_tio(ci, ti, 0, len, GFP_NOIO);
-		__map_bio(clone);
-		ret = 1;
-		break;
-	default:
-		if (len)
-			setup_split_accounting(ci, *len);
-		/* dm_accept_partial_bio() is not supported with shared tio->len_ptr */
-		alloc_multiple_bios(&blist, ci, ti, num_bios, len);
-		while ((clone = bio_list_pop(&blist))) {
+	if (WARN_ON_ONCE(num_bios == 0)) /* num_bios = 0 is a bug in caller */
+		return 0;
+
+	/* dm_accept_partial_bio() is not supported with shared tio->len_ptr */
+	if (len)
+		setup_split_accounting(ci, *len);
+
+	/*
+	 * Using alloc_multiple_bios(), even if num_bios is 1, to consistently
+	 * support allocating using GFP_NOWAIT with GFP_NOIO fallback.
+	 */
+	alloc_multiple_bios(&blist, ci, ti, num_bios, len, gfp_flag);
+	while ((clone = bio_list_pop(&blist))) {
+		if (num_bios > 1)
 			dm_tio_set_flag(clone_to_tio(clone), DM_TIO_IS_DUPLICATE_BIO);
-			__map_bio(clone);
-			ret += 1;
-		}
-		break;
+		__map_bio(clone);
+		ret += 1;
 	}
 
 	return ret;
@@ -1553,8 +1561,12 @@ static void __send_empty_flush(struct clone_info *ci)
 		unsigned int bios;
 		struct dm_target *ti = dm_table_get_target(t, i);
 
+		if (unlikely(ti->num_flush_bios == 0))
+			continue;
+
 		atomic_add(ti->num_flush_bios, &ci->io->io_count);
-		bios = __send_duplicate_bios(ci, ti, ti->num_flush_bios, NULL);
+		bios = __send_duplicate_bios(ci, ti, ti->num_flush_bios,
+					     NULL, GFP_NOWAIT);
 		atomic_sub(ti->num_flush_bios - bios, &ci->io->io_count);
 	}
 
@@ -1567,10 +1579,9 @@ static void __send_empty_flush(struct clone_info *ci)
 	bio_uninit(ci->bio);
 }
 
-static void __send_changing_extent_only(struct clone_info *ci, struct dm_target *ti,
-					unsigned int num_bios,
-					unsigned int max_granularity,
-					unsigned int max_sectors)
+static void __send_abnormal_io(struct clone_info *ci, struct dm_target *ti,
+			       unsigned int num_bios, unsigned int max_granularity,
+			       unsigned int max_sectors)
 {
 	unsigned int len, bios;
 
@@ -1578,7 +1589,7 @@ static void __send_changing_extent_only(struct clone_info *ci, struct dm_target
 		    __max_io_len(ti, ci->sector, max_granularity, max_sectors));
 
 	atomic_add(num_bios, &ci->io->io_count);
-	bios = __send_duplicate_bios(ci, ti, num_bios, &len);
+	bios = __send_duplicate_bios(ci, ti, num_bios, &len, GFP_NOIO);
 	/*
 	 * alloc_io() takes one extra reference for submission, so the
 	 * reference won't reach 0 without the following (+1) subtraction
@@ -1647,8 +1658,8 @@ static blk_status_t __process_abnormal_io(struct clone_info *ci,
 	if (unlikely(!num_bios))
 		return BLK_STS_NOTSUPP;
 
-	__send_changing_extent_only(ci, ti, num_bios,
-				    max_granularity, max_sectors);
+	__send_abnormal_io(ci, ti, num_bios, max_granularity, max_sectors);
+
 	return BLK_STS_OK;
 }
 
@@ -1707,10 +1718,6 @@ static blk_status_t __split_and_process_bio(struct clone_info *ci)
 	if (unlikely(!ti))
 		return BLK_STS_IOERR;
 
-	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);
 
@@ -1722,7 +1729,17 @@ static blk_status_t __split_and_process_bio(struct clone_info *ci)
 
 	len = min_t(sector_t, max_io_len(ti, ci->sector), ci->sector_count);
 	setup_split_accounting(ci, len);
-	clone = alloc_tio(ci, ti, 0, &len, GFP_NOIO);
+
+	if (unlikely(ci->bio->bi_opf & REQ_NOWAIT)) {
+		if (unlikely(!dm_target_supports_nowait(ti->type)))
+			return BLK_STS_NOTSUPP;
+
+		clone = alloc_tio(ci, ti, 0, &len, GFP_NOWAIT);
+		if (unlikely(!clone))
+			return BLK_STS_AGAIN;
+	} else {
+		clone = alloc_tio(ci, ti, 0, &len, GFP_NOIO);
+	}
 	__map_bio(clone);
 
 	ci->sector += len;
@@ -1731,11 +1748,11 @@ static blk_status_t __split_and_process_bio(struct clone_info *ci)
 	return BLK_STS_OK;
 }
 
-static void init_clone_info(struct clone_info *ci, struct mapped_device *md,
+static void init_clone_info(struct clone_info *ci, struct dm_io *io,
 			    struct dm_table *map, struct bio *bio, bool is_abnormal)
 {
 	ci->map = map;
-	ci->io = alloc_io(md, bio);
+	ci->io = io;
 	ci->bio = bio;
 	ci->is_abnormal_io = is_abnormal;
 	ci->submit_as_polled = false;
@@ -1770,8 +1787,18 @@ static void dm_split_and_process_bio(struct mapped_device *md,
 			return;
 	}
 
-	init_clone_info(&ci, md, map, bio, is_abnormal);
-	io = ci.io;
+	/* Only support nowait for normal IO */
+	if (unlikely(bio->bi_opf & REQ_NOWAIT) && !is_abnormal) {
+		io = alloc_io(md, bio, GFP_NOWAIT);
+		if (unlikely(!io)) {
+			/* Unable to do anything without dm_io. */
+			bio_wouldblock_error(bio);
+			return;
+		}
+	} else {
+		io = alloc_io(md, bio, GFP_NOIO);
+	}
+	init_clone_info(&ci, io, map, bio, is_abnormal);
 
 	if (bio->bi_opf & REQ_PREFLUSH) {
 		__send_empty_flush(&ci);
diff --git a/drivers/md/dm.h b/drivers/md/dm.h
index f682295af9..7f1acbf6bd 100644
--- a/drivers/md/dm.h
+++ b/drivers/md/dm.h
@@ -188,9 +188,11 @@ void dm_kobject_release(struct kobject *kobj);
 /*
  * Targets for linear and striped mappings
  */
+int linear_map(struct dm_target *ti, struct bio *bio);
 int dm_linear_init(void);
 void dm_linear_exit(void);
 
+int stripe_map(struct dm_target *ti, struct bio *bio);
 int dm_stripe_init(void);
 void dm_stripe_exit(void);
 
diff --git a/drivers/md/md-autodetect.c b/drivers/md/md-autodetect.c
index 6eaa0eab40..4b80165afd 100644
--- a/drivers/md/md-autodetect.c
+++ b/drivers/md/md-autodetect.c
@@ -175,7 +175,7 @@ static void __init md_setup_drive(struct md_setup_args *args)
 		return;
 	}
 
-	err = mddev_lock(mddev);
+	err = mddev_suspend_and_lock(mddev);
 	if (err) {
 		pr_err("md: failed to lock array %s\n", name);
 		goto out_mddev_put;
@@ -221,7 +221,7 @@ static void __init md_setup_drive(struct md_setup_args *args)
 	if (err)
 		pr_warn("md: starting %s failed\n", name);
 out_unlock:
-	mddev_unlock(mddev);
+	mddev_unlock_and_resume(mddev);
 out_mddev_put:
 	mddev_put(mddev);
 }
diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c
index 6f9ff14971..9672f75c30 100644
--- a/drivers/md/md-bitmap.c
+++ b/drivers/md/md-bitmap.c
@@ -1861,7 +1861,7 @@ void md_bitmap_destroy(struct mddev *mddev)
 
 	md_bitmap_wait_behind_writes(mddev);
 	if (!mddev->serialize_policy)
-		mddev_destroy_serial_pool(mddev, NULL, true);
+		mddev_destroy_serial_pool(mddev, NULL);
 
 	mutex_lock(&mddev->bitmap_info.mutex);
 	spin_lock(&mddev->lock);
@@ -1977,7 +1977,7 @@ int md_bitmap_load(struct mddev *mddev)
 		goto out;
 
 	rdev_for_each(rdev, mddev)
-		mddev_create_serial_pool(mddev, rdev, true);
+		mddev_create_serial_pool(mddev, rdev);
 
 	if (mddev_is_clustered(mddev))
 		md_cluster_ops->load_bitmaps(mddev, mddev->bitmap_info.nodes);
@@ -2348,14 +2348,11 @@ location_store(struct mddev *mddev, const char *buf, size_t len)
 {
 	int rv;
 
-	rv = mddev_lock(mddev);
+	rv = mddev_suspend_and_lock(mddev);
 	if (rv)
 		return rv;
+
 	if (mddev->pers) {
-		if (!mddev->pers->quiesce) {
-			rv = -EBUSY;
-			goto out;
-		}
 		if (mddev->recovery || mddev->sync_thread) {
 			rv = -EBUSY;
 			goto out;
@@ -2369,11 +2366,8 @@ location_store(struct mddev *mddev, const char *buf, size_t len)
 			rv = -EBUSY;
 			goto out;
 		}
-		if (mddev->pers) {
-			mddev_suspend(mddev);
-			md_bitmap_destroy(mddev);
-			mddev_resume(mddev);
-		}
+
+		md_bitmap_destroy(mddev);
 		mddev->bitmap_info.offset = 0;
 		if (mddev->bitmap_info.file) {
 			struct file *f = mddev->bitmap_info.file;
@@ -2383,6 +2377,8 @@ location_store(struct mddev *mddev, const char *buf, size_t len)
 	} else {
 		/* No bitmap, OK to set a location */
 		long long offset;
+		struct bitmap *bitmap;
+
 		if (strncmp(buf, "none", 4) == 0)
 			/* nothing to be done */;
 		else if (strncmp(buf, "file:", 5) == 0) {
@@ -2406,25 +2402,20 @@ location_store(struct mddev *mddev, const char *buf, size_t len)
 				rv = -EINVAL;
 				goto out;
 			}
+
 			mddev->bitmap_info.offset = offset;
-			if (mddev->pers) {
-				struct bitmap *bitmap;
-				bitmap = md_bitmap_create(mddev, -1);
-				mddev_suspend(mddev);
-				if (IS_ERR(bitmap))
-					rv = PTR_ERR(bitmap);
-				else {
-					mddev->bitmap = bitmap;
-					rv = md_bitmap_load(mddev);
-					if (rv)
-						mddev->bitmap_info.offset = 0;
-				}
-				if (rv) {
-					md_bitmap_destroy(mddev);
-					mddev_resume(mddev);
-					goto out;
-				}
-				mddev_resume(mddev);
+			bitmap = md_bitmap_create(mddev, -1);
+			if (IS_ERR(bitmap)) {
+				rv = PTR_ERR(bitmap);
+				goto out;
+			}
+
+			mddev->bitmap = bitmap;
+			rv = md_bitmap_load(mddev);
+			if (rv) {
+				mddev->bitmap_info.offset = 0;
+				md_bitmap_destroy(mddev);
+				goto out;
 			}
 		}
 	}
@@ -2437,7 +2428,7 @@ location_store(struct mddev *mddev, const char *buf, size_t len)
 	}
 	rv = 0;
 out:
-	mddev_unlock(mddev);
+	mddev_unlock_and_resume(mddev);
 	if (rv)
 		return rv;
 	return len;
@@ -2546,7 +2537,7 @@ backlog_store(struct mddev *mddev, const char *buf, size_t len)
 	if (backlog > COUNTER_MAX)
 		return -EINVAL;
 
-	rv = mddev_lock(mddev);
+	rv = mddev_suspend_and_lock(mddev);
 	if (rv)
 		return rv;
 
@@ -2571,16 +2562,16 @@ backlog_store(struct mddev *mddev, const char *buf, size_t len)
 	if (!backlog && mddev->serial_info_pool) {
 		/* serial_info_pool is not needed if backlog is zero */
 		if (!mddev->serialize_policy)
-			mddev_destroy_serial_pool(mddev, NULL, false);
+			mddev_destroy_serial_pool(mddev, NULL);
 	} else if (backlog && !mddev->serial_info_pool) {
 		/* serial_info_pool is needed since backlog is not zero */
 		rdev_for_each(rdev, mddev)
-			mddev_create_serial_pool(mddev, rdev, false);
+			mddev_create_serial_pool(mddev, rdev);
 	}
 	if (old_mwb != backlog)
 		md_bitmap_update_sb(mddev->bitmap);
 
-	mddev_unlock(mddev);
+	mddev_unlock_and_resume(mddev);
 	return len;
 }
 
diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c
index 1e26eb2233..8e36a0feec 100644
--- a/drivers/md/md-cluster.c
+++ b/drivers/md/md-cluster.c
@@ -501,7 +501,7 @@ static void process_suspend_info(struct mddev *mddev,
 	mddev->pers->quiesce(mddev, 0);
 }
 
-static void process_add_new_disk(struct mddev *mddev, struct cluster_msg *cmsg)
+static int process_add_new_disk(struct mddev *mddev, struct cluster_msg *cmsg)
 {
 	char disk_uuid[64];
 	struct md_cluster_info *cinfo = mddev->cluster_info;
@@ -509,6 +509,7 @@ static void process_add_new_disk(struct mddev *mddev, struct cluster_msg *cmsg)
 	char raid_slot[16];
 	char *envp[] = {event_name, disk_uuid, raid_slot, NULL};
 	int len;
+	int res = 0;
 
 	len = snprintf(disk_uuid, 64, "DEVICE_UUID=");
 	sprintf(disk_uuid + len, "%pU", cmsg->uuid);
@@ -517,9 +518,14 @@ static void process_add_new_disk(struct mddev *mddev, struct cluster_msg *cmsg)
 	init_completion(&cinfo->newdisk_completion);
 	set_bit(MD_CLUSTER_WAITING_FOR_NEWDISK, &cinfo->state);
 	kobject_uevent_env(&disk_to_dev(mddev->gendisk)->kobj, KOBJ_CHANGE, envp);
-	wait_for_completion_timeout(&cinfo->newdisk_completion,
-			NEW_DEV_TIMEOUT);
+	if (!wait_for_completion_timeout(&cinfo->newdisk_completion,
+					NEW_DEV_TIMEOUT)) {
+		pr_err("md-cluster(%s:%d): timeout on a new disk adding\n",
+			__func__, __LINE__);
+		res = -1;
+	}
 	clear_bit(MD_CLUSTER_WAITING_FOR_NEWDISK, &cinfo->state);
+	return res;
 }
 
 
@@ -594,7 +600,8 @@ static int process_recvd_msg(struct mddev *mddev, struct cluster_msg *msg)
 				     le64_to_cpu(msg->high));
 		break;
 	case NEWDISK:
-		process_add_new_disk(mddev, msg);
+		if (process_add_new_disk(mddev, msg))
+			ret = -1;
 		break;
 	case REMOVE:
 		process_remove_disk(mddev, msg);
diff --git a/drivers/md/md-linear.c b/drivers/md/md-linear.c
index 71ac996468..8eca7693b7 100644
--- a/drivers/md/md-linear.c
+++ b/drivers/md/md-linear.c
@@ -69,6 +69,19 @@ static struct linear_conf *linear_conf(struct mddev *mddev, int raid_disks)
 	if (!conf)
 		return NULL;
 
+	/*
+	 * conf->raid_disks is copy of mddev->raid_disks. The reason to
+	 * keep a copy of mddev->raid_disks in struct linear_conf is,
+	 * mddev->raid_disks may not be consistent with pointers number of
+	 * conf->disks[] when it is updated in linear_add() and used to
+	 * iterate old conf->disks[] earray in linear_congested().
+	 * Here conf->raid_disks is always consitent with number of
+	 * pointers in conf->disks[] array, and mddev->private is updated
+	 * with rcu_assign_pointer() in linear_addr(), such race can be
+	 * avoided.
+	 */
+	conf->raid_disks = raid_disks;
+
 	cnt = 0;
 	conf->array_sectors = 0;
 
@@ -112,19 +125,6 @@ static struct linear_conf *linear_conf(struct mddev *mddev, int raid_disks)
 			conf->disks[i-1].end_sector +
 			conf->disks[i].rdev->sectors;
 
-	/*
-	 * conf->raid_disks is copy of mddev->raid_disks. The reason to
-	 * keep a copy of mddev->raid_disks in struct linear_conf is,
-	 * mddev->raid_disks may not be consistent with pointers number of
-	 * conf->disks[] when it is updated in linear_add() and used to
-	 * iterate old conf->disks[] earray in linear_congested().
-	 * Here conf->raid_disks is always consitent with number of
-	 * pointers in conf->disks[] array, and mddev->private is updated
-	 * with rcu_assign_pointer() in linear_addr(), such race can be
-	 * avoided.
-	 */
-	conf->raid_disks = raid_disks;
-
 	return conf;
 
 out:
@@ -183,7 +183,6 @@ static int linear_add(struct mddev *mddev, struct md_rdev *rdev)
 	 * in linear_congested(), therefore kfree_rcu() is used to free
 	 * oldconf until no one uses it anymore.
 	 */
-	mddev_suspend(mddev);
 	oldconf = rcu_dereference_protected(mddev->private,
 			lockdep_is_held(&mddev->reconfig_mutex));
 	mddev->raid_disks++;
@@ -192,7 +191,6 @@ static int linear_add(struct mddev *mddev, struct md_rdev *rdev)
 	rcu_assign_pointer(mddev->private, newconf);
 	md_set_array_sectors(mddev, linear_size(mddev, 0, 0));
 	set_capacity_and_notify(mddev->gendisk, mddev->array_sectors);
-	mddev_resume(mddev);
 	kfree_rcu(oldconf, rcu);
 	return 0;
 }
diff --git a/drivers/md/md-linear.h b/drivers/md/md-linear.h
index 24e97db50e..5587eeedb8 100644
--- a/drivers/md/md-linear.h
+++ b/drivers/md/md-linear.h
@@ -12,6 +12,6 @@ struct linear_conf
 	struct rcu_head		rcu;
 	sector_t		array_sectors;
 	int			raid_disks; /* a copy of mddev->raid_disks */
-	struct dev_info		disks[];
+	struct dev_info		disks[] __counted_by(raid_disks);
 };
 #endif
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 8c40c1c395..58889bc726 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -82,6 +82,14 @@ static struct module *md_cluster_mod;
 
 static DECLARE_WAIT_QUEUE_HEAD(resync_wait);
 static struct workqueue_struct *md_wq;
+
+/*
+ * This workqueue is used for sync_work to register new sync_thread, and for
+ * del_work to remove rdev, and for event_work that is only set by dm-raid.
+ *
+ * Noted that sync_work will grab reconfig_mutex, hence never flush this
+ * workqueue whith reconfig_mutex grabbed.
+ */
 static struct workqueue_struct *md_misc_wq;
 struct workqueue_struct *md_bitmap_wq;
 
@@ -91,6 +99,18 @@ 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);
 
+enum md_ro_state {
+	MD_RDWR,
+	MD_RDONLY,
+	MD_AUTO_READ,
+	MD_MAX_STATE
+};
+
+static bool md_is_rdwr(struct mddev *mddev)
+{
+	return (mddev->ro == MD_RDWR);
+}
+
 /*
  * Default number of read corrections we'll attempt on an rdev
  * before ejecting it from the array. We divide the read error
@@ -206,8 +226,7 @@ static int rdev_need_serial(struct md_rdev *rdev)
  * 1. rdev is the first device which return true from rdev_enable_serial.
  * 2. rdev is NULL, means we want to enable serialization for all rdevs.
  */
-void mddev_create_serial_pool(struct mddev *mddev, struct md_rdev *rdev,
-			      bool is_suspend)
+void mddev_create_serial_pool(struct mddev *mddev, struct md_rdev *rdev)
 {
 	int ret = 0;
 
@@ -215,15 +234,12 @@ void mddev_create_serial_pool(struct mddev *mddev, struct md_rdev *rdev,
 	    !test_bit(CollisionCheck, &rdev->flags))
 		return;
 
-	if (!is_suspend)
-		mddev_suspend(mddev);
-
 	if (!rdev)
 		ret = rdevs_init_serial(mddev);
 	else
 		ret = rdev_init_serial(rdev);
 	if (ret)
-		goto abort;
+		return;
 
 	if (mddev->serial_info_pool == NULL) {
 		/*
@@ -238,10 +254,6 @@ void mddev_create_serial_pool(struct mddev *mddev, struct md_rdev *rdev,
 			pr_err("can't alloc memory pool for serialization\n");
 		}
 	}
-
-abort:
-	if (!is_suspend)
-		mddev_resume(mddev);
 }
 
 /*
@@ -250,8 +262,7 @@ abort:
  * 2. when bitmap is destroyed while policy is not enabled.
  * 3. for disable policy, the pool is destroyed only when no rdev needs it.
  */
-void mddev_destroy_serial_pool(struct mddev *mddev, struct md_rdev *rdev,
-			       bool is_suspend)
+void mddev_destroy_serial_pool(struct mddev *mddev, struct md_rdev *rdev)
 {
 	if (rdev && !test_bit(CollisionCheck, &rdev->flags))
 		return;
@@ -260,8 +271,6 @@ void mddev_destroy_serial_pool(struct mddev *mddev, struct md_rdev *rdev,
 		struct md_rdev *temp;
 		int num = 0; /* used to track if other rdevs need the pool */
 
-		if (!is_suspend)
-			mddev_suspend(mddev);
 		rdev_for_each(temp, mddev) {
 			if (!rdev) {
 				if (!mddev->serialize_policy ||
@@ -283,8 +292,6 @@ void mddev_destroy_serial_pool(struct mddev *mddev, struct md_rdev *rdev,
 			mempool_destroy(mddev->serial_info_pool);
 			mddev->serial_info_pool = NULL;
 		}
-		if (!is_suspend)
-			mddev_resume(mddev);
 	}
 }
 
@@ -305,7 +312,6 @@ static struct ctl_table raid_table[] = {
 		.mode		= S_IRUGO|S_IWUSR,
 		.proc_handler	= proc_dointvec,
 	},
-	{ }
 };
 
 static int start_readonly;
@@ -346,6 +352,10 @@ EXPORT_SYMBOL_GPL(md_new_event);
 static LIST_HEAD(all_mddevs);
 static DEFINE_SPINLOCK(all_mddevs_lock);
 
+static bool is_md_suspended(struct mddev *mddev)
+{
+	return percpu_ref_is_dying(&mddev->active_io);
+}
 /* Rather than calling directly into the personality make_request function,
  * IO requests come here first so that we can check if the device is
  * being suspended pending a reconfiguration.
@@ -359,11 +369,11 @@ static bool is_suspended(struct mddev *mddev, struct bio *bio)
 		return true;
 	if (bio_data_dir(bio) != WRITE)
 		return false;
-	if (mddev->suspend_lo >= mddev->suspend_hi)
+	if (READ_ONCE(mddev->suspend_lo) >= READ_ONCE(mddev->suspend_hi))
 		return false;
-	if (bio->bi_iter.bi_sector >= mddev->suspend_hi)
+	if (bio->bi_iter.bi_sector >= READ_ONCE(mddev->suspend_hi))
 		return false;
-	if (bio_end_sector(bio) < mddev->suspend_lo)
+	if (bio_end_sector(bio) < READ_ONCE(mddev->suspend_lo))
 		return false;
 	return true;
 }
@@ -431,42 +441,73 @@ static void md_submit_bio(struct bio *bio)
 	md_handle_request(mddev, bio);
 }
 
-/* mddev_suspend makes sure no new requests are submitted
- * to the device, and that any requests that have been submitted
- * are completely handled.
- * Once mddev_detach() is called and completes, the module will be
- * completely unused.
+/*
+ * Make sure no new requests are submitted to the device, and any requests that
+ * have been submitted are completely handled.
  */
-void mddev_suspend(struct mddev *mddev)
+int mddev_suspend(struct mddev *mddev, bool interruptible)
 {
-	struct md_thread *thread = rcu_dereference_protected(mddev->thread,
-			lockdep_is_held(&mddev->reconfig_mutex));
+	int err = 0;
 
-	WARN_ON_ONCE(thread && current == thread->tsk);
-	if (mddev->suspended++)
-		return;
-	wake_up(&mddev->sb_wait);
-	set_bit(MD_ALLOW_SB_UPDATE, &mddev->flags);
-	percpu_ref_kill(&mddev->active_io);
+	/*
+	 * hold reconfig_mutex to wait for normal io will deadlock, because
+	 * other context can't update super_block, and normal io can rely on
+	 * updating super_block.
+	 */
+	lockdep_assert_not_held(&mddev->reconfig_mutex);
 
-	if (mddev->pers && mddev->pers->prepare_suspend)
-		mddev->pers->prepare_suspend(mddev);
+	if (interruptible)
+		err = mutex_lock_interruptible(&mddev->suspend_mutex);
+	else
+		mutex_lock(&mddev->suspend_mutex);
+	if (err)
+		return err;
 
-	wait_event(mddev->sb_wait, percpu_ref_is_zero(&mddev->active_io));
-	clear_bit_unlock(MD_ALLOW_SB_UPDATE, &mddev->flags);
-	wait_event(mddev->sb_wait, !test_bit(MD_UPDATING_SB, &mddev->flags));
+	if (mddev->suspended) {
+		WRITE_ONCE(mddev->suspended, mddev->suspended + 1);
+		mutex_unlock(&mddev->suspend_mutex);
+		return 0;
+	}
+
+	percpu_ref_kill(&mddev->active_io);
+	if (interruptible)
+		err = wait_event_interruptible(mddev->sb_wait,
+				percpu_ref_is_zero(&mddev->active_io));
+	else
+		wait_event(mddev->sb_wait,
+				percpu_ref_is_zero(&mddev->active_io));
+	if (err) {
+		percpu_ref_resurrect(&mddev->active_io);
+		mutex_unlock(&mddev->suspend_mutex);
+		return err;
+	}
+
+	/*
+	 * For raid456, io might be waiting for reshape to make progress,
+	 * allow new reshape to start while waiting for io to be done to
+	 * prevent deadlock.
+	 */
+	WRITE_ONCE(mddev->suspended, mddev->suspended + 1);
 
 	del_timer_sync(&mddev->safemode_timer);
 	/* restrict memory reclaim I/O during raid array is suspend */
 	mddev->noio_flag = memalloc_noio_save();
+
+	mutex_unlock(&mddev->suspend_mutex);
+	return 0;
 }
 EXPORT_SYMBOL_GPL(mddev_suspend);
 
-void mddev_resume(struct mddev *mddev)
+static void __mddev_resume(struct mddev *mddev, bool recovery_needed)
 {
-	lockdep_assert_held(&mddev->reconfig_mutex);
-	if (--mddev->suspended)
+	lockdep_assert_not_held(&mddev->reconfig_mutex);
+
+	mutex_lock(&mddev->suspend_mutex);
+	WRITE_ONCE(mddev->suspended, mddev->suspended - 1);
+	if (mddev->suspended) {
+		mutex_unlock(&mddev->suspend_mutex);
 		return;
+	}
 
 	/* entred the memalloc scope from mddev_suspend() */
 	memalloc_noio_restore(mddev->noio_flag);
@@ -474,9 +515,17 @@ void mddev_resume(struct mddev *mddev)
 	percpu_ref_resurrect(&mddev->active_io);
 	wake_up(&mddev->sb_wait);
 
-	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+	if (recovery_needed)
+		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	md_wakeup_thread(mddev->thread);
 	md_wakeup_thread(mddev->sync_thread); /* possibly kick off a reshape */
+
+	mutex_unlock(&mddev->suspend_mutex);
+}
+
+void mddev_resume(struct mddev *mddev)
+{
+	return __mddev_resume(mddev, true);
 }
 EXPORT_SYMBOL_GPL(mddev_resume);
 
@@ -530,8 +579,12 @@ static void submit_flushes(struct work_struct *ws)
 			rcu_read_lock();
 		}
 	rcu_read_unlock();
-	if (atomic_dec_and_test(&mddev->flush_pending))
+	if (atomic_dec_and_test(&mddev->flush_pending)) {
+		/* The pair is percpu_ref_get() from md_flush_request() */
+		percpu_ref_put(&mddev->active_io);
+
 		queue_work(md_wq, &mddev->flush_work);
+	}
 }
 
 static void md_submit_flush_data(struct work_struct *ws)
@@ -626,34 +679,63 @@ static inline struct mddev *mddev_get(struct mddev *mddev)
 
 static void mddev_delayed_delete(struct work_struct *ws);
 
+static void __mddev_put(struct mddev *mddev)
+{
+	if (mddev->raid_disks || !list_empty(&mddev->disks) ||
+	    mddev->ctime || mddev->hold_active)
+		return;
+
+	/* Array is not configured at all, and not held active, so destroy it */
+	set_bit(MD_DELETED, &mddev->flags);
+
+	/*
+	 * Call queue_work inside the spinlock so that flush_workqueue() after
+	 * mddev_find will succeed in waiting for the work to be done.
+	 */
+	queue_work(md_misc_wq, &mddev->del_work);
+}
+
 void mddev_put(struct mddev *mddev)
 {
 	if (!atomic_dec_and_lock(&mddev->active, &all_mddevs_lock))
 		return;
-	if (!mddev->raid_disks && list_empty(&mddev->disks) &&
-	    mddev->ctime == 0 && !mddev->hold_active) {
-		/* Array is not configured at all, and not held active,
-		 * so destroy it */
-		set_bit(MD_DELETED, &mddev->flags);
 
-		/*
-		 * Call queue_work inside the spinlock so that
-		 * flush_workqueue() after mddev_find will succeed in waiting
-		 * for the work to be done.
-		 */
-		INIT_WORK(&mddev->del_work, mddev_delayed_delete);
-		queue_work(md_misc_wq, &mddev->del_work);
-	}
+	__mddev_put(mddev);
 	spin_unlock(&all_mddevs_lock);
 }
 
 static void md_safemode_timeout(struct timer_list *t);
+static void md_start_sync(struct work_struct *ws);
+
+static void active_io_release(struct percpu_ref *ref)
+{
+	struct mddev *mddev = container_of(ref, struct mddev, active_io);
+
+	wake_up(&mddev->sb_wait);
+}
+
+static void no_op(struct percpu_ref *r) {}
 
-void mddev_init(struct mddev *mddev)
+int mddev_init(struct mddev *mddev)
 {
+
+	if (percpu_ref_init(&mddev->active_io, active_io_release,
+			    PERCPU_REF_ALLOW_REINIT, GFP_KERNEL))
+		return -ENOMEM;
+
+	if (percpu_ref_init(&mddev->writes_pending, no_op,
+			    PERCPU_REF_ALLOW_REINIT, GFP_KERNEL)) {
+		percpu_ref_exit(&mddev->active_io);
+		return -ENOMEM;
+	}
+
+	/* We want to start with the refcount at zero */
+	percpu_ref_put(&mddev->writes_pending);
+
 	mutex_init(&mddev->open_mutex);
 	mutex_init(&mddev->reconfig_mutex);
 	mutex_init(&mddev->sync_mutex);
+	mutex_init(&mddev->suspend_mutex);
 	mutex_init(&mddev->bitmap_info.mutex);
 	INIT_LIST_HEAD(&mddev->disks);
 	INIT_LIST_HEAD(&mddev->all_mddevs);
@@ -672,9 +754,21 @@ void mddev_init(struct mddev *mddev)
 	mddev->resync_min = 0;
 	mddev->resync_max = MaxSector;
 	mddev->level = LEVEL_NONE;
+
+	INIT_WORK(&mddev->sync_work, md_start_sync);
+	INIT_WORK(&mddev->del_work, mddev_delayed_delete);
+
+	return 0;
 }
 EXPORT_SYMBOL_GPL(mddev_init);
 
+void mddev_destroy(struct mddev *mddev)
+{
+	percpu_ref_exit(&mddev->active_io);
+	percpu_ref_exit(&mddev->writes_pending);
+}
+EXPORT_SYMBOL_GPL(mddev_destroy);
+
 static struct mddev *mddev_find_locked(dev_t unit)
 {
 	struct mddev *mddev;
@@ -718,13 +812,16 @@ static struct mddev *mddev_alloc(dev_t unit)
 	new = kzalloc(sizeof(*new), GFP_KERNEL);
 	if (!new)
 		return ERR_PTR(-ENOMEM);
-	mddev_init(new);
+
+	error = mddev_init(new);
+	if (error)
+		goto out_free_new;
 
 	spin_lock(&all_mddevs_lock);
 	if (unit) {
 		error = -EEXIST;
 		if (mddev_find_locked(unit))
-			goto out_free_new;
+			goto out_destroy_new;
 		new->unit = unit;
 		if (MAJOR(unit) == MD_MAJOR)
 			new->md_minor = MINOR(unit);
@@ -735,7 +832,7 @@ static struct mddev *mddev_alloc(dev_t unit)
 		error = -ENODEV;
 		new->unit = mddev_alloc_unit();
 		if (!new->unit)
-			goto out_free_new;
+			goto out_destroy_new;
 		new->md_minor = MINOR(new->unit);
 		new->hold_active = UNTIL_STOP;
 	}
@@ -743,8 +840,11 @@ static struct mddev *mddev_alloc(dev_t unit)
 	list_add(&new->all_mddevs, &all_mddevs);
 	spin_unlock(&all_mddevs_lock);
 	return new;
-out_free_new:
+
+out_destroy_new:
 	spin_unlock(&all_mddevs_lock);
+	mddev_destroy(new);
+out_free_new:
 	kfree(new);
 	return ERR_PTR(error);
 }
@@ -755,6 +855,7 @@ static void mddev_free(struct mddev *mddev)
 	list_del(&mddev->all_mddevs);
 	spin_unlock(&all_mddevs_lock);
 
+	mddev_destroy(mddev);
 	kfree(mddev);
 }
 
@@ -940,9 +1041,10 @@ void md_super_write(struct mddev *mddev, struct md_rdev *rdev,
 		return;
 
 	bio = bio_alloc_bioset(rdev->meta_bdev ? rdev->meta_bdev : rdev->bdev,
-			       1,
-			       REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH | REQ_FUA,
-			       GFP_NOIO, &mddev->sync_set);
+			      1,
+			      REQ_OP_WRITE | REQ_SYNC | REQ_IDLE | REQ_META
+				  | REQ_PREFLUSH | REQ_FUA,
+			      GFP_NOIO, &mddev->sync_set);
 
 	atomic_inc(&rdev->nr_pending);
 
@@ -1122,6 +1224,7 @@ struct super_type  {
 					  struct md_rdev *refdev,
 					  int minor_version);
 	int		    (*validate_super)(struct mddev *mddev,
+					      struct md_rdev *freshest,
 					      struct md_rdev *rdev);
 	void		    (*sync_super)(struct mddev *mddev,
 					  struct md_rdev *rdev);
@@ -1259,8 +1362,9 @@ static int super_90_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor
 
 /*
  * validate_super for 0.90.0
+ * note: we are not using "freshest" for 0.9 superblock
  */
-static int super_90_validate(struct mddev *mddev, struct md_rdev *rdev)
+static int super_90_validate(struct mddev *mddev, struct md_rdev *freshest, struct md_rdev *rdev)
 {
 	mdp_disk_t *desc;
 	mdp_super_t *sb = page_address(rdev->sb_page);
@@ -1772,7 +1876,7 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_
 	return ret;
 }
 
-static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev)
+static int super_1_validate(struct mddev *mddev, struct md_rdev *freshest, struct md_rdev *rdev)
 {
 	struct mdp_superblock_1 *sb = page_address(rdev->sb_page);
 	__u64 ev1 = le64_to_cpu(sb->events);
@@ -1868,13 +1972,15 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev)
 		}
 	} else if (mddev->pers == NULL) {
 		/* Insist of good event counter while assembling, except for
-		 * spares (which don't need an event count) */
-		++ev1;
+		 * spares (which don't need an event count).
+		 * Similar to mdadm, we allow event counter difference of 1
+		 * from the freshest device.
+		 */
 		if (rdev->desc_nr >= 0 &&
 		    rdev->desc_nr < le32_to_cpu(sb->max_dev) &&
 		    (le16_to_cpu(sb->dev_roles[rdev->desc_nr]) < MD_DISK_ROLE_MAX ||
 		     le16_to_cpu(sb->dev_roles[rdev->desc_nr]) == MD_DISK_ROLE_JOURNAL))
-			if (ev1 < mddev->events)
+			if (ev1 + 1 < mddev->events)
 				return -EINVAL;
 	} else if (mddev->bitmap) {
 		/* If adding to array with a bitmap, then we can accept an
@@ -1895,8 +2001,38 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev)
 		    rdev->desc_nr >= le32_to_cpu(sb->max_dev)) {
 			role = MD_DISK_ROLE_SPARE;
 			rdev->desc_nr = -1;
-		} else
+		} else if (mddev->pers == NULL && freshest && ev1 < mddev->events) {
+			/*
+			 * If we are assembling, and our event counter is smaller than the
+			 * highest event counter, we cannot trust our superblock about the role.
+			 * It could happen that our rdev was marked as Faulty, and all other
+			 * superblocks were updated with +1 event counter.
+			 * Then, before the next superblock update, which typically happens when
+			 * remove_and_add_spares() removes the device from the array, there was
+			 * a crash or reboot.
+			 * If we allow current rdev without consulting the freshest superblock,
+			 * we could cause data corruption.
+			 * Note that in this case our event counter is smaller by 1 than the
+			 * highest, otherwise, this rdev would not be allowed into array;
+			 * both kernel and mdadm allow event counter difference of 1.
+			 */
+			struct mdp_superblock_1 *freshest_sb = page_address(freshest->sb_page);
+			u32 freshest_max_dev = le32_to_cpu(freshest_sb->max_dev);
+
+			if (rdev->desc_nr >= freshest_max_dev) {
+				/* this is unexpected, better not proceed */
+				pr_warn("md: %s: rdev[%pg]: desc_nr(%d) >= freshest(%pg)->sb->max_dev(%u)\n",
+						mdname(mddev), rdev->bdev, rdev->desc_nr,
+						freshest->bdev, freshest_max_dev);
+				return -EUCLEAN;
+			}
+
+			role = le16_to_cpu(freshest_sb->dev_roles[rdev->desc_nr]);
+			pr_debug("md: %s: rdev[%pg]: role=%d(0x%x) according to freshest %pg\n",
+				     mdname(mddev), rdev->bdev, role, role, freshest->bdev);
+		} else {
 			role = le16_to_cpu(sb->dev_roles[rdev->desc_nr]);
+		}
 		switch(role) {
 		case MD_DISK_ROLE_SPARE: /* spare */
 			break;
@@ -2422,7 +2558,7 @@ static int bind_rdev_to_array(struct md_rdev *rdev, struct mddev *mddev)
 	pr_debug("md: bind<%s>\n", b);
 
 	if (mddev->raid_disks)
-		mddev_create_serial_pool(mddev, rdev, false);
+		mddev_create_serial_pool(mddev, rdev);
 
 	if ((err = kobject_add(&rdev->kobj, &mddev->kobj, "dev-%s", b)))
 		goto fail;
@@ -2462,8 +2598,7 @@ static void export_rdev(struct md_rdev *rdev, struct mddev *mddev)
 	if (test_bit(AutoDetected, &rdev->flags))
 		md_autodetect_dev(rdev->bdev->bd_dev);
 #endif
-	blkdev_put(rdev->bdev,
-		   test_bit(Holder, &rdev->flags) ? rdev : &claim_rdev);
+	bdev_release(rdev->bdev_handle);
 	rdev->bdev = NULL;
 	kobject_put(&rdev->kobj);
 }
@@ -2475,7 +2610,7 @@ static void md_kick_rdev_from_array(struct md_rdev *rdev)
 	bd_unlink_disk_holder(rdev->bdev, rdev->mddev->gendisk);
 	list_del_rcu(&rdev->same_set);
 	pr_debug("md: unbind<%pg>\n", rdev->bdev);
-	mddev_destroy_serial_pool(rdev->mddev, rdev, false);
+	mddev_destroy_serial_pool(rdev->mddev, rdev);
 	rdev->mddev = NULL;
 	sysfs_remove_link(&rdev->kobj, "block");
 	sysfs_put(rdev->sysfs_state);
@@ -2804,12 +2939,8 @@ static int add_bound_rdev(struct md_rdev *rdev)
 		 * and should be added immediately.
 		 */
 		super_types[mddev->major_version].
-			validate_super(mddev, rdev);
-		if (add_journal)
-			mddev_suspend(mddev);
+			validate_super(mddev, NULL/*freshest*/, rdev);
 		err = mddev->pers->hot_add_disk(mddev, rdev);
-		if (add_journal)
-			mddev_resume(mddev);
 		if (err) {
 			md_kick_rdev_from_array(rdev);
 			return err;
@@ -2946,11 +3077,11 @@ state_store(struct md_rdev *rdev, const char *buf, size_t len)
 		}
 	} else if (cmd_match(buf, "writemostly")) {
 		set_bit(WriteMostly, &rdev->flags);
-		mddev_create_serial_pool(rdev->mddev, rdev, false);
+		mddev_create_serial_pool(rdev->mddev, rdev);
 		need_update_sb = true;
 		err = 0;
 	} else if (cmd_match(buf, "-writemostly")) {
-		mddev_destroy_serial_pool(rdev->mddev, rdev, false);
+		mddev_destroy_serial_pool(rdev->mddev, rdev);
 		clear_bit(WriteMostly, &rdev->flags);
 		need_update_sb = true;
 		err = 0;
@@ -3562,6 +3693,7 @@ rdev_attr_store(struct kobject *kobj, struct attribute *attr,
 	struct rdev_sysfs_entry *entry = container_of(attr, struct rdev_sysfs_entry, attr);
 	struct md_rdev *rdev = container_of(kobj, struct md_rdev, kobj);
 	struct kernfs_node *kn = NULL;
+	bool suspend = false;
 	ssize_t rv;
 	struct mddev *mddev = rdev->mddev;
 
@@ -3569,17 +3701,25 @@ rdev_attr_store(struct kobject *kobj, struct attribute *attr,
 		return -EIO;
 	if (!capable(CAP_SYS_ADMIN))
 		return -EACCES;
+	if (!mddev)
+		return -ENODEV;
 
-	if (entry->store == state_store && cmd_match(page, "remove"))
-		kn = sysfs_break_active_protection(kobj, attr);
+	if (entry->store == state_store) {
+		if (cmd_match(page, "remove"))
+			kn = sysfs_break_active_protection(kobj, attr);
+		if (cmd_match(page, "remove") || cmd_match(page, "re-add") ||
+		    cmd_match(page, "writemostly") ||
+		    cmd_match(page, "-writemostly"))
+			suspend = true;
+	}
 
-	rv = mddev ? mddev_lock(mddev) : -ENODEV;
+	rv = suspend ? mddev_suspend_and_lock(mddev) : mddev_lock(mddev);
 	if (!rv) {
 		if (rdev->mddev == NULL)
 			rv = -ENODEV;
 		else
 			rv = entry->store(rdev, page, length);
-		mddev_unlock(mddev);
+		suspend ? mddev_unlock_and_resume(mddev) : mddev_unlock(mddev);
 	}
 
 	if (kn)
@@ -3643,7 +3783,6 @@ EXPORT_SYMBOL_GPL(md_rdev_init);
 static struct md_rdev *md_import_device(dev_t newdev, int super_format, int super_minor)
 {
 	struct md_rdev *rdev;
-	struct md_rdev *holder;
 	sector_t size;
 	int err;
 
@@ -3658,21 +3797,16 @@ static struct md_rdev *md_import_device(dev_t newdev, int super_format, int supe
 	if (err)
 		goto out_clear_rdev;
 
-	if (super_format == -2) {
-		holder = &claim_rdev;
-	} else {
-		holder = rdev;
-		set_bit(Holder, &rdev->flags);
-	}
-
-	rdev->bdev = blkdev_get_by_dev(newdev, BLK_OPEN_READ | BLK_OPEN_WRITE,
-				       holder, NULL);
-	if (IS_ERR(rdev->bdev)) {
+	rdev->bdev_handle = bdev_open_by_dev(newdev,
+			BLK_OPEN_READ | BLK_OPEN_WRITE,
+			super_format == -2 ? &claim_rdev : rdev, NULL);
+	if (IS_ERR(rdev->bdev_handle)) {
 		pr_warn("md: could not open device unknown-block(%u,%u).\n",
 			MAJOR(newdev), MINOR(newdev));
-		err = PTR_ERR(rdev->bdev);
+		err = PTR_ERR(rdev->bdev_handle);
 		goto out_clear_rdev;
 	}
+	rdev->bdev = rdev->bdev_handle->bdev;
 
 	kobject_init(&rdev->kobj, &rdev_ktype);
 
@@ -3703,7 +3837,7 @@ static struct md_rdev *md_import_device(dev_t newdev, int super_format, int supe
 	return rdev;
 
 out_blkdev_put:
-	blkdev_put(rdev->bdev, holder);
+	bdev_release(rdev->bdev_handle);
 out_clear_rdev:
 	md_rdev_clear(rdev);
 out_free_rdev:
@@ -3742,7 +3876,7 @@ static int analyze_sbs(struct mddev *mddev)
 	}
 
 	super_types[mddev->major_version].
-		validate_super(mddev, freshest);
+		validate_super(mddev, NULL/*freshest*/, freshest);
 
 	i = 0;
 	rdev_for_each_safe(rdev, tmp, mddev) {
@@ -3757,7 +3891,7 @@ static int analyze_sbs(struct mddev *mddev)
 		}
 		if (rdev != freshest) {
 			if (super_types[mddev->major_version].
-			    validate_super(mddev, rdev)) {
+			    validate_super(mddev, freshest, rdev)) {
 				pr_warn("md: kicking non-fresh %pg from array!\n",
 					rdev->bdev);
 				md_kick_rdev_from_array(rdev);
@@ -3884,12 +4018,12 @@ level_store(struct mddev *mddev, const char *buf, size_t len)
 	if (slen == 0 || slen >= sizeof(clevel))
 		return -EINVAL;
 
-	rv = mddev_lock(mddev);
+	rv = mddev_suspend_and_lock(mddev);
 	if (rv)
 		return rv;
 
 	if (mddev->pers == NULL) {
-		strncpy(mddev->clevel, buf, slen);
+		memcpy(mddev->clevel, buf, slen);
 		if (mddev->clevel[slen-1] == '\n')
 			slen--;
 		mddev->clevel[slen] = 0;
@@ -3922,7 +4056,7 @@ level_store(struct mddev *mddev, const char *buf, size_t len)
 	}
 
 	/* Now find the new personality */
-	strncpy(clevel, buf, slen);
+	memcpy(clevel, buf, slen);
 	if (clevel[slen-1] == '\n')
 		slen--;
 	clevel[slen] = 0;
@@ -3977,7 +4111,6 @@ level_store(struct mddev *mddev, const char *buf, size_t len)
 	}
 
 	/* Looks like we have a winner */
-	mddev_suspend(mddev);
 	mddev_detach(mddev);
 
 	spin_lock(&mddev->lock);
@@ -4063,14 +4196,13 @@ level_store(struct mddev *mddev, const char *buf, size_t len)
 	blk_set_stacking_limits(&mddev->queue->limits);
 	pers->run(mddev);
 	set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
-	mddev_resume(mddev);
 	if (!mddev->thread)
 		md_update_sb(mddev, 1);
 	sysfs_notify_dirent_safe(mddev->sysfs_level);
 	md_new_event();
 	rv = len;
 out_unlock:
-	mddev_unlock(mddev);
+	mddev_unlock_and_resume(mddev);
 	return rv;
 }
 
@@ -4378,6 +4510,18 @@ array_state_store(struct mddev *mddev, const char *buf, size_t len)
 	int err = 0;
 	enum array_state st = match_word(buf, array_states);
 
+	/* No lock dependent actions */
+	switch (st) {
+	case suspended:		/* not supported yet */
+	case write_pending:	/* cannot be set */
+	case active_idle:	/* cannot be set */
+	case broken:		/* cannot be set */
+	case bad_word:
+		return -EINVAL;
+	default:
+		break;
+	}
+
 	if (mddev->pers && (st == active || st == clean) &&
 	    mddev->ro != MD_RDONLY) {
 		/* don't take reconfig_mutex when toggling between
@@ -4402,23 +4546,16 @@ array_state_store(struct mddev *mddev, const char *buf, size_t len)
 	err = mddev_lock(mddev);
 	if (err)
 		return err;
-	err = -EINVAL;
-	switch(st) {
-	case bad_word:
-		break;
-	case clear:
-		/* stopping an active array */
-		err = do_md_stop(mddev, 0, NULL);
-		break;
+
+	switch (st) {
 	case inactive:
-		/* stopping an active array */
+		/* stop an active array, return 0 otherwise */
 		if (mddev->pers)
 			err = do_md_stop(mddev, 2, NULL);
-		else
-			err = 0; /* already inactive */
 		break;
-	case suspended:
-		break; /* not supported yet */
+	case clear:
+		err = do_md_stop(mddev, 0, NULL);
+		break;
 	case readonly:
 		if (mddev->pers)
 			err = md_set_readonly(mddev, NULL);
@@ -4469,10 +4606,8 @@ array_state_store(struct mddev *mddev, const char *buf, size_t len)
 			err = do_md_run(mddev);
 		}
 		break;
-	case write_pending:
-	case active_idle:
-	case broken:
-		/* these cannot be set */
+	default:
+		err = -EINVAL;
 		break;
 	}
 
@@ -4545,7 +4680,7 @@ new_dev_store(struct mddev *mddev, const char *buf, size_t len)
 	    minor != MINOR(dev))
 		return -EOVERFLOW;
 
-	err = mddev_lock(mddev);
+	err = mddev_suspend_and_lock(mddev);
 	if (err)
 		return err;
 	if (mddev->persistent) {
@@ -4566,14 +4701,14 @@ new_dev_store(struct mddev *mddev, const char *buf, size_t len)
 		rdev = md_import_device(dev, -1, -1);
 
 	if (IS_ERR(rdev)) {
-		mddev_unlock(mddev);
+		mddev_unlock_and_resume(mddev);
 		return PTR_ERR(rdev);
 	}
 	err = bind_rdev_to_array(rdev, mddev);
  out:
 	if (err)
 		export_rdev(rdev, mddev);
-	mddev_unlock(mddev);
+	mddev_unlock_and_resume(mddev);
 	if (!err)
 		md_new_event();
 	return err ? err : len;
@@ -4708,7 +4843,7 @@ metadata_store(struct mddev *mddev, const char *buf, size_t len)
 		size_t namelen = len-9;
 		if (namelen >= sizeof(mddev->metadata_type))
 			namelen = sizeof(mddev->metadata_type)-1;
-		strncpy(mddev->metadata_type, buf+9, namelen);
+		memcpy(mddev->metadata_type, buf+9, namelen);
 		mddev->metadata_type[namelen] = 0;
 		if (namelen && mddev->metadata_type[namelen-1] == '\n')
 			mddev->metadata_type[--namelen] = 0;
@@ -4768,25 +4903,29 @@ action_show(struct mddev *mddev, char *page)
 	return sprintf(page, "%s\n", type);
 }
 
-static void stop_sync_thread(struct mddev *mddev)
+/**
+ * stop_sync_thread() - wait for sync_thread to stop if it's running.
+ * @mddev:	the array.
+ * @locked:	if set, reconfig_mutex will still be held after this function
+ *		return; if not set, reconfig_mutex will be released after this
+ *		function return.
+ * @check_seq:	if set, only wait for curent running sync_thread to stop, noted
+ *		that new sync_thread can still start.
+ */
+static void stop_sync_thread(struct mddev *mddev, bool locked, bool check_seq)
 {
-	if (!test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
-		return;
+	int sync_seq;
 
-	if (mddev_lock(mddev))
-		return;
+	if (check_seq)
+		sync_seq = atomic_read(&mddev->sync_seq);
 
-	/*
-	 * Check again in case MD_RECOVERY_RUNNING is cleared before lock is
-	 * held.
-	 */
 	if (!test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) {
-		mddev_unlock(mddev);
+		if (!locked)
+			mddev_unlock(mddev);
 		return;
 	}
 
-	if (work_pending(&mddev->del_work))
-		flush_workqueue(md_misc_wq);
+	mddev_unlock(mddev);
 
 	set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 	/*
@@ -4794,21 +4933,28 @@ static void stop_sync_thread(struct mddev *mddev)
 	 * never happen
 	 */
 	md_wakeup_thread_directly(mddev->sync_thread);
+	if (work_pending(&mddev->sync_work))
+		flush_work(&mddev->sync_work);
 
-	mddev_unlock(mddev);
+	wait_event(resync_wait,
+		   !test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
+		   (check_seq && sync_seq != atomic_read(&mddev->sync_seq)));
+
+	if (locked)
+		mddev_lock_nointr(mddev);
 }
 
 static void idle_sync_thread(struct mddev *mddev)
 {
-	int sync_seq = atomic_read(&mddev->sync_seq);
-
 	mutex_lock(&mddev->sync_mutex);
 	clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
-	stop_sync_thread(mddev);
 
-	wait_event(resync_wait, sync_seq != atomic_read(&mddev->sync_seq) ||
-			!test_bit(MD_RECOVERY_RUNNING, &mddev->recovery));
+	if (mddev_lock(mddev)) {
+		mutex_unlock(&mddev->sync_mutex);
+		return;
+	}
 
+	stop_sync_thread(mddev, false, true);
 	mutex_unlock(&mddev->sync_mutex);
 }
 
@@ -4816,11 +4962,13 @@ static void frozen_sync_thread(struct mddev *mddev)
 {
 	mutex_lock(&mddev->sync_mutex);
 	set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
-	stop_sync_thread(mddev);
 
-	wait_event(resync_wait, mddev->sync_thread == NULL &&
-			!test_bit(MD_RECOVERY_RUNNING, &mddev->recovery));
+	if (mddev_lock(mddev)) {
+		mutex_unlock(&mddev->sync_mutex);
+		return;
+	}
 
+	stop_sync_thread(mddev, false, false);
 	mutex_unlock(&mddev->sync_mutex);
 }
 
@@ -4882,6 +5030,7 @@ action_store(struct mddev *mddev, const char *page, size_t len)
 		/* A write to sync_action is enough to justify
 		 * canceling read-auto mode
 		 */
+		flush_work(&mddev->sync_work);
 		mddev->ro = MD_RDWR;
 		md_wakeup_thread(mddev->sync_thread);
 	}
@@ -5138,7 +5287,8 @@ __ATTR(sync_max, S_IRUGO|S_IWUSR, max_sync_show, max_sync_store);
 static ssize_t
 suspend_lo_show(struct mddev *mddev, char *page)
 {
-	return sprintf(page, "%llu\n", (unsigned long long)mddev->suspend_lo);
+	return sprintf(page, "%llu\n",
+		       (unsigned long long)READ_ONCE(mddev->suspend_lo));
 }
 
 static ssize_t
@@ -5153,21 +5303,14 @@ suspend_lo_store(struct mddev *mddev, const char *buf, size_t len)
 	if (new != (sector_t)new)
 		return -EINVAL;
 
-	err = mddev_lock(mddev);
+	err = mddev_suspend(mddev, true);
 	if (err)
 		return err;
-	err = -EINVAL;
-	if (mddev->pers == NULL ||
-	    mddev->pers->quiesce == NULL)
-		goto unlock;
-	mddev_suspend(mddev);
-	mddev->suspend_lo = new;
+
+	WRITE_ONCE(mddev->suspend_lo, new);
 	mddev_resume(mddev);
 
-	err = 0;
-unlock:
-	mddev_unlock(mddev);
-	return err ?: len;
+	return len;
 }
 static struct md_sysfs_entry md_suspend_lo =
 __ATTR(suspend_lo, S_IRUGO|S_IWUSR, suspend_lo_show, suspend_lo_store);
@@ -5175,7 +5318,8 @@ __ATTR(suspend_lo, S_IRUGO|S_IWUSR, suspend_lo_show, suspend_lo_store);
 static ssize_t
 suspend_hi_show(struct mddev *mddev, char *page)
 {
-	return sprintf(page, "%llu\n", (unsigned long long)mddev->suspend_hi);
+	return sprintf(page, "%llu\n",
+		       (unsigned long long)READ_ONCE(mddev->suspend_hi));
 }
 
 static ssize_t
@@ -5190,21 +5334,14 @@ suspend_hi_store(struct mddev *mddev, const char *buf, size_t len)
 	if (new != (sector_t)new)
 		return -EINVAL;
 
-	err = mddev_lock(mddev);
+	err = mddev_suspend(mddev, true);
 	if (err)
 		return err;
-	err = -EINVAL;
-	if (mddev->pers == NULL)
-		goto unlock;
 
-	mddev_suspend(mddev);
-	mddev->suspend_hi = new;
+	WRITE_ONCE(mddev->suspend_hi, new);
 	mddev_resume(mddev);
 
-	err = 0;
-unlock:
-	mddev_unlock(mddev);
-	return err ?: len;
+	return len;
 }
 static struct md_sysfs_entry md_suspend_hi =
 __ATTR(suspend_hi, S_IRUGO|S_IWUSR, suspend_hi_show, suspend_hi_store);
@@ -5451,7 +5588,7 @@ serialize_policy_store(struct mddev *mddev, const char *buf, size_t len)
 	if (value == mddev->serialize_policy)
 		return len;
 
-	err = mddev_lock(mddev);
+	err = mddev_suspend_and_lock(mddev);
 	if (err)
 		return err;
 	if (mddev->pers == NULL || (mddev->pers->level != 1)) {
@@ -5460,15 +5597,13 @@ serialize_policy_store(struct mddev *mddev, const char *buf, size_t len)
 		goto unlock;
 	}
 
-	mddev_suspend(mddev);
 	if (value)
-		mddev_create_serial_pool(mddev, NULL, true);
+		mddev_create_serial_pool(mddev, NULL);
 	else
-		mddev_destroy_serial_pool(mddev, NULL, true);
+		mddev_destroy_serial_pool(mddev, NULL);
 	mddev->serialize_policy = value;
-	mddev_resume(mddev);
 unlock:
-	mddev_unlock(mddev);
+	mddev_unlock_and_resume(mddev);
 	return err ?: len;
 }
 
@@ -5607,21 +5742,6 @@ static void mddev_delayed_delete(struct work_struct *ws)
 	kobject_put(&mddev->kobj);
 }
 
-static void no_op(struct percpu_ref *r) {}
-
-int mddev_init_writes_pending(struct mddev *mddev)
-{
-	if (mddev->writes_pending.percpu_count_ptr)
-		return 0;
-	if (percpu_ref_init(&mddev->writes_pending, no_op,
-			    PERCPU_REF_ALLOW_REINIT, GFP_KERNEL) < 0)
-		return -ENOMEM;
-	/* We want to start with the refcount at zero */
-	percpu_ref_put(&mddev->writes_pending);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(mddev_init_writes_pending);
-
 struct mddev *md_alloc(dev_t dev, char *name)
 {
 	/*
@@ -5793,12 +5913,6 @@ static void md_safemode_timeout(struct timer_list *t)
 }
 
 static int start_dirty_degraded;
-static void active_io_release(struct percpu_ref *ref)
-{
-	struct mddev *mddev = container_of(ref, struct mddev, active_io);
-
-	wake_up(&mddev->sb_wait);
-}
 
 int md_run(struct mddev *mddev)
 {
@@ -5879,15 +5993,10 @@ int md_run(struct mddev *mddev)
 		nowait = nowait && bdev_nowait(rdev->bdev);
 	}
 
-	err = percpu_ref_init(&mddev->active_io, active_io_release,
-				PERCPU_REF_ALLOW_REINIT, GFP_KERNEL);
-	if (err)
-		return err;
-
 	if (!bioset_initialized(&mddev->bio_set)) {
 		err = bioset_init(&mddev->bio_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
 		if (err)
-			goto exit_active_io;
+			return err;
 	}
 	if (!bioset_initialized(&mddev->sync_set)) {
 		err = bioset_init(&mddev->sync_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
@@ -6084,8 +6193,6 @@ exit_sync_set:
 	bioset_exit(&mddev->sync_set);
 exit_bio_set:
 	bioset_exit(&mddev->bio_set);
-exit_active_io:
-	percpu_ref_exit(&mddev->active_io);
 	return err;
 }
 EXPORT_SYMBOL_GPL(md_run);
@@ -6233,14 +6340,7 @@ static void md_clean(struct mddev *mddev)
 
 static void __md_stop_writes(struct mddev *mddev)
 {
-	set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
-	if (work_pending(&mddev->del_work))
-		flush_workqueue(md_misc_wq);
-	if (mddev->sync_thread) {
-		set_bit(MD_RECOVERY_INTR, &mddev->recovery);
-		md_reap_sync_thread(mddev);
-	}
-
+	stop_sync_thread(mddev, true, false);
 	del_timer_sync(&mddev->safemode_timer);
 
 	if (mddev->pers && mddev->pers->quiesce) {
@@ -6259,7 +6359,7 @@ static void __md_stop_writes(struct mddev *mddev)
 	}
 	/* disable policy to guarantee rdevs free resources for serialization */
 	mddev->serialize_policy = 0;
-	mddev_destroy_serial_pool(mddev, NULL, true);
+	mddev_destroy_serial_pool(mddev, NULL);
 }
 
 void md_stop_writes(struct mddev *mddev)
@@ -6287,9 +6387,6 @@ static void __md_stop(struct mddev *mddev)
 	struct md_personality *pers = mddev->pers;
 	md_bitmap_destroy(mddev);
 	mddev_detach(mddev);
-	/* Ensure ->event_work is done */
-	if (mddev->event_work.func)
-		flush_workqueue(md_misc_wq);
 	spin_lock(&mddev->lock);
 	mddev->pers = NULL;
 	spin_unlock(&mddev->lock);
@@ -6301,7 +6398,6 @@ static void __md_stop(struct mddev *mddev)
 	module_put(pers->owner);
 	clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 
-	percpu_ref_exit(&mddev->active_io);
 	bioset_exit(&mddev->bio_set);
 	bioset_exit(&mddev->sync_set);
 	bioset_exit(&mddev->io_clone_set);
@@ -6316,7 +6412,6 @@ void md_stop(struct mddev *mddev)
 	 */
 	__md_stop_writes(mddev);
 	__md_stop(mddev);
-	percpu_ref_exit(&mddev->writes_pending);
 }
 
 EXPORT_SYMBOL_GPL(md_stop);
@@ -6334,18 +6429,8 @@ static int md_set_readonly(struct mddev *mddev, struct block_device *bdev)
 		set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 		md_wakeup_thread(mddev->thread);
 	}
-	if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
-		set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 
-	/*
-	 * Thread might be blocked waiting for metadata update which will now
-	 * never happen
-	 */
-	md_wakeup_thread_directly(mddev->sync_thread);
-
-	mddev_unlock(mddev);
-	wait_event(resync_wait, !test_bit(MD_RECOVERY_RUNNING,
-					  &mddev->recovery));
+	stop_sync_thread(mddev, false, false);
 	wait_event(mddev->sb_wait,
 		   !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags));
 	mddev_lock_nointr(mddev);
@@ -6399,20 +6484,8 @@ static int do_md_stop(struct mddev *mddev, int mode,
 		set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 		md_wakeup_thread(mddev->thread);
 	}
-	if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
-		set_bit(MD_RECOVERY_INTR, &mddev->recovery);
-
-	/*
-	 * Thread might be blocked waiting for metadata update which will now
-	 * never happen
-	 */
-	md_wakeup_thread_directly(mddev->sync_thread);
 
-	mddev_unlock(mddev);
-	wait_event(resync_wait, (mddev->sync_thread == NULL &&
-				 !test_bit(MD_RECOVERY_RUNNING,
-					   &mddev->recovery)));
-	mddev_lock_nointr(mddev);
+	stop_sync_thread(mddev, true, false);
 
 	mutex_lock(&mddev->open_mutex);
 	if ((mddev->pers && atomic_read(&mddev->openers) > !!bdev) ||
@@ -6555,13 +6628,13 @@ static void autorun_devices(int part)
 		if (IS_ERR(mddev))
 			break;
 
-		if (mddev_lock(mddev))
+		if (mddev_suspend_and_lock(mddev))
 			pr_warn("md: %s locked, cannot run\n", mdname(mddev));
 		else if (mddev->raid_disks || mddev->major_version
 			 || !list_empty(&mddev->disks)) {
 			pr_warn("md: %s already running, cannot run %pg\n",
 				mdname(mddev), rdev0->bdev);
-			mddev_unlock(mddev);
+			mddev_unlock_and_resume(mddev);
 		} else {
 			pr_debug("md: created %s\n", mdname(mddev));
 			mddev->persistent = 1;
@@ -6571,7 +6644,7 @@ static void autorun_devices(int part)
 					export_rdev(rdev, mddev);
 			}
 			autorun_array(mddev);
-			mddev_unlock(mddev);
+			mddev_unlock_and_resume(mddev);
 		}
 		/* on success, candidates will be empty, on error
 		 * it won't...
@@ -6809,7 +6882,7 @@ int md_add_new_disk(struct mddev *mddev, struct mdu_disk_info_s *info)
 			rdev->saved_raid_disk = rdev->raid_disk;
 		} else
 			super_types[mddev->major_version].
-				validate_super(mddev, rdev);
+				validate_super(mddev, NULL/*freshest*/, rdev);
 		if ((info->state & (1<<MD_DISK_SYNC)) &&
 		     rdev->raid_disk != info->raid_disk) {
 			/* This was a hot-add request, but events doesn't
@@ -7121,7 +7194,6 @@ static int set_bitmap_file(struct mddev *mddev, int fd)
 			struct bitmap *bitmap;
 
 			bitmap = md_bitmap_create(mddev, -1);
-			mddev_suspend(mddev);
 			if (!IS_ERR(bitmap)) {
 				mddev->bitmap = bitmap;
 				err = md_bitmap_load(mddev);
@@ -7131,11 +7203,8 @@ static int set_bitmap_file(struct mddev *mddev, int fd)
 				md_bitmap_destroy(mddev);
 				fd = -1;
 			}
-			mddev_resume(mddev);
 		} else if (fd < 0) {
-			mddev_suspend(mddev);
 			md_bitmap_destroy(mddev);
-			mddev_resume(mddev);
 		}
 	}
 	if (fd < 0) {
@@ -7424,7 +7493,6 @@ static int update_array_info(struct mddev *mddev, mdu_array_info_t *info)
 			mddev->bitmap_info.space =
 				mddev->bitmap_info.default_space;
 			bitmap = md_bitmap_create(mddev, -1);
-			mddev_suspend(mddev);
 			if (!IS_ERR(bitmap)) {
 				mddev->bitmap = bitmap;
 				rv = md_bitmap_load(mddev);
@@ -7432,7 +7500,6 @@ static int update_array_info(struct mddev *mddev, mdu_array_info_t *info)
 				rv = PTR_ERR(bitmap);
 			if (rv)
 				md_bitmap_destroy(mddev);
-			mddev_resume(mddev);
 		} else {
 			/* remove the bitmap */
 			if (!mddev->bitmap) {
@@ -7457,9 +7524,7 @@ static int update_array_info(struct mddev *mddev, mdu_array_info_t *info)
 				module_put(md_cluster_mod);
 				mddev->safemode_delay = DEFAULT_SAFEMODE_DELAY;
 			}
-			mddev_suspend(mddev);
 			md_bitmap_destroy(mddev);
-			mddev_resume(mddev);
 			mddev->bitmap_info.offset = 0;
 		}
 	}
@@ -7530,6 +7595,20 @@ static inline bool md_ioctl_valid(unsigned int cmd)
 	}
 }
 
+static bool md_ioctl_need_suspend(unsigned int cmd)
+{
+	switch (cmd) {
+	case ADD_NEW_DISK:
+	case HOT_ADD_DISK:
+	case HOT_REMOVE_DISK:
+	case SET_BITMAP_FILE:
+	case SET_ARRAY_INFO:
+		return true;
+	default:
+		return false;
+	}
+}
+
 static int __md_set_array_info(struct mddev *mddev, void __user *argp)
 {
 	mdu_array_info_t info;
@@ -7658,7 +7737,12 @@ static int md_ioctl(struct block_device *bdev, blk_mode_t mode,
 		mutex_unlock(&mddev->open_mutex);
 		sync_blockdev(bdev);
 	}
-	err = mddev_lock(mddev);
+
+	if (!md_is_rdwr(mddev))
+		flush_work(&mddev->sync_work);
+
+	err = md_ioctl_need_suspend(cmd) ? mddev_suspend_and_lock(mddev) :
+					   mddev_lock(mddev);
 	if (err) {
 		pr_debug("md: ioctl lock interrupted, reason %d, cmd %d\n",
 			 err, cmd);
@@ -7786,7 +7870,10 @@ unlock:
 	if (mddev->hold_active == UNTIL_IOCTL &&
 	    err != -EINVAL)
 		mddev->hold_active = 0;
-	mddev_unlock(mddev);
+
+	md_ioctl_need_suspend(cmd) ? mddev_unlock_and_resume(mddev) :
+				     mddev_unlock(mddev);
+
 out:
 	if(did_set_md_closing)
 		clear_bit(MD_CLOSING, &mddev->flags);
@@ -7898,7 +7985,6 @@ static void md_free_disk(struct gendisk *disk)
 {
 	struct mddev *mddev = disk->private_data;
 
-	percpu_ref_exit(&mddev->writes_pending);
 	mddev_free(mddev);
 }
 
@@ -8075,6 +8161,19 @@ static void status_unused(struct seq_file *seq)
 	seq_printf(seq, "\n");
 }
 
+static void status_personalities(struct seq_file *seq)
+{
+	struct md_personality *pers;
+
+	seq_puts(seq, "Personalities : ");
+	spin_lock(&pers_lock);
+	list_for_each_entry(pers, &pers_list, list)
+		seq_printf(seq, "[%s] ", pers->name);
+
+	spin_unlock(&pers_lock);
+	seq_puts(seq, "\n");
+}
+
 static int status_resync(struct seq_file *seq, struct mddev *mddev)
 {
 	sector_t max_sectors, resync, res;
@@ -8214,105 +8313,43 @@ static int status_resync(struct seq_file *seq, struct mddev *mddev)
 }
 
 static void *md_seq_start(struct seq_file *seq, loff_t *pos)
+	__acquires(&all_mddevs_lock)
 {
-	struct list_head *tmp;
-	loff_t l = *pos;
-	struct mddev *mddev;
-
-	if (l == 0x10000) {
-		++*pos;
-		return (void *)2;
-	}
-	if (l > 0x10000)
-		return NULL;
-	if (!l--)
-		/* header */
-		return (void*)1;
-
+	seq->poll_event = atomic_read(&md_event_count);
 	spin_lock(&all_mddevs_lock);
-	list_for_each(tmp,&all_mddevs)
-		if (!l--) {
-			mddev = list_entry(tmp, struct mddev, all_mddevs);
-			if (!mddev_get(mddev))
-				continue;
-			spin_unlock(&all_mddevs_lock);
-			return mddev;
-		}
-	spin_unlock(&all_mddevs_lock);
-	if (!l--)
-		return (void*)2;/* tail */
-	return NULL;
+
+	return seq_list_start_head(&all_mddevs, *pos);
 }
 
 static void *md_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
-	struct list_head *tmp;
-	struct mddev *next_mddev, *mddev = v;
-	struct mddev *to_put = NULL;
-
-	++*pos;
-	if (v == (void*)2)
-		return NULL;
-
-	spin_lock(&all_mddevs_lock);
-	if (v == (void*)1) {
-		tmp = all_mddevs.next;
-	} else {
-		to_put = mddev;
-		tmp = mddev->all_mddevs.next;
-	}
-
-	for (;;) {
-		if (tmp == &all_mddevs) {
-			next_mddev = (void*)2;
-			*pos = 0x10000;
-			break;
-		}
-		next_mddev = list_entry(tmp, struct mddev, all_mddevs);
-		if (mddev_get(next_mddev))
-			break;
-		mddev = next_mddev;
-		tmp = mddev->all_mddevs.next;
-	}
-	spin_unlock(&all_mddevs_lock);
-
-	if (to_put)
-		mddev_put(to_put);
-	return next_mddev;
-
+	return seq_list_next(v, &all_mddevs, pos);
 }
 
 static void md_seq_stop(struct seq_file *seq, void *v)
+	__releases(&all_mddevs_lock)
 {
-	struct mddev *mddev = v;
-
-	if (mddev && v != (void*)1 && v != (void*)2)
-		mddev_put(mddev);
+	spin_unlock(&all_mddevs_lock);
 }
 
 static int md_seq_show(struct seq_file *seq, void *v)
 {
-	struct mddev *mddev = v;
+	struct mddev *mddev;
 	sector_t sectors;
 	struct md_rdev *rdev;
 
-	if (v == (void*)1) {
-		struct md_personality *pers;
-		seq_printf(seq, "Personalities : ");
-		spin_lock(&pers_lock);
-		list_for_each_entry(pers, &pers_list, list)
-			seq_printf(seq, "[%s] ", pers->name);
-
-		spin_unlock(&pers_lock);
-		seq_printf(seq, "\n");
-		seq->poll_event = atomic_read(&md_event_count);
+	if (v == &all_mddevs) {
+		status_personalities(seq);
+		if (list_empty(&all_mddevs))
+			status_unused(seq);
 		return 0;
 	}
-	if (v == (void*)2) {
-		status_unused(seq);
+
+	mddev = list_entry(v, struct mddev, all_mddevs);
+	if (!mddev_get(mddev))
 		return 0;
-	}
 
+	spin_unlock(&all_mddevs_lock);
 	spin_lock(&mddev->lock);
 	if (mddev->pers || mddev->raid_disks || !list_empty(&mddev->disks)) {
 		seq_printf(seq, "%s : %sactive", mdname(mddev),
@@ -8383,6 +8420,13 @@ static int md_seq_show(struct seq_file *seq, void *v)
 		seq_printf(seq, "\n");
 	}
 	spin_unlock(&mddev->lock);
+	spin_lock(&all_mddevs_lock);
+
+	if (mddev == list_last_entry(&all_mddevs, struct mddev, all_mddevs))
+		status_unused(seq);
+
+	if (atomic_dec_and_test(&mddev->active))
+		__mddev_put(mddev);
 
 	return 0;
 }
@@ -8582,6 +8626,7 @@ bool md_write_start(struct mddev *mddev, struct bio *bi)
 	BUG_ON(mddev->ro == MD_RDONLY);
 	if (mddev->ro == MD_AUTO_READ) {
 		/* need to switch to read/write */
+		flush_work(&mddev->sync_work);
 		mddev->ro = MD_RDWR;
 		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 		md_wakeup_thread(mddev->thread);
@@ -8772,12 +8817,16 @@ void md_do_sync(struct md_thread *thread)
 	int ret;
 
 	/* just incase thread restarts... */
-	if (test_bit(MD_RECOVERY_DONE, &mddev->recovery) ||
-	    test_bit(MD_RECOVERY_WAIT, &mddev->recovery))
+	if (test_bit(MD_RECOVERY_DONE, &mddev->recovery))
 		return;
-	if (!md_is_rdwr(mddev)) {/* never try to sync a read-only array */
+
+	if (test_bit(MD_RECOVERY_INTR, &mddev->recovery))
+		goto skip;
+
+	if (test_bit(MD_RECOVERY_WAIT, &mddev->recovery) ||
+	    !md_is_rdwr(mddev)) {/* never try to sync a read-only array */
 		set_bit(MD_RECOVERY_INTR, &mddev->recovery);
-		return;
+		goto skip;
 	}
 
 	if (mddev_is_clustered(mddev)) {
@@ -9168,12 +9217,90 @@ void md_do_sync(struct md_thread *thread)
 	spin_unlock(&mddev->lock);
 
 	wake_up(&resync_wait);
-	wake_up(&mddev->sb_wait);
 	md_wakeup_thread(mddev->thread);
 	return;
 }
 EXPORT_SYMBOL_GPL(md_do_sync);
 
+static bool rdev_removeable(struct md_rdev *rdev)
+{
+	/* rdev is not used. */
+	if (rdev->raid_disk < 0)
+		return false;
+
+	/* There are still inflight io, don't remove this rdev. */
+	if (atomic_read(&rdev->nr_pending))
+		return false;
+
+	/*
+	 * An error occurred but has not yet been acknowledged by the metadata
+	 * handler, don't remove this rdev.
+	 */
+	if (test_bit(Blocked, &rdev->flags))
+		return false;
+
+	/* Fautly rdev is not used, it's safe to remove it. */
+	if (test_bit(Faulty, &rdev->flags))
+		return true;
+
+	/* Journal disk can only be removed if it's faulty. */
+	if (test_bit(Journal, &rdev->flags))
+		return false;
+
+	/*
+	 * 'In_sync' is cleared while 'raid_disk' is valid, which means
+	 * replacement has just become active from pers->spare_active(), and
+	 * then pers->hot_remove_disk() will replace this rdev with replacement.
+	 */
+	if (!test_bit(In_sync, &rdev->flags))
+		return true;
+
+	return false;
+}
+
+static bool rdev_is_spare(struct md_rdev *rdev)
+{
+	return !test_bit(Candidate, &rdev->flags) && rdev->raid_disk >= 0 &&
+	       !test_bit(In_sync, &rdev->flags) &&
+	       !test_bit(Journal, &rdev->flags) &&
+	       !test_bit(Faulty, &rdev->flags);
+}
+
+static bool rdev_addable(struct md_rdev *rdev)
+{
+	/* rdev is already used, don't add it again. */
+	if (test_bit(Candidate, &rdev->flags) || rdev->raid_disk >= 0 ||
+	    test_bit(Faulty, &rdev->flags))
+		return false;
+
+	/* Allow to add journal disk. */
+	if (test_bit(Journal, &rdev->flags))
+		return true;
+
+	/* Allow to add if array is read-write. */
+	if (md_is_rdwr(rdev->mddev))
+		return true;
+
+	/*
+	 * For read-only array, only allow to readd a rdev. And if bitmap is
+	 * used, don't allow to readd a rdev that is too old.
+	 */
+	if (rdev->saved_raid_disk >= 0 && !test_bit(Bitmap_sync, &rdev->flags))
+		return true;
+
+	return false;
+}
+
+static bool md_spares_need_change(struct mddev *mddev)
+{
+	struct md_rdev *rdev;
+
+	rdev_for_each(rdev, mddev)
+		if (rdev_removeable(rdev) || rdev_addable(rdev))
+			return true;
+	return false;
+}
+
 static int remove_and_add_spares(struct mddev *mddev,
 				 struct md_rdev *this)
 {
@@ -9206,12 +9333,8 @@ static int remove_and_add_spares(struct mddev *mddev,
 		synchronize_rcu();
 	rdev_for_each(rdev, mddev) {
 		if ((this == NULL || rdev == this) &&
-		    rdev->raid_disk >= 0 &&
-		    !test_bit(Blocked, &rdev->flags) &&
-		    ((test_bit(RemoveSynchronized, &rdev->flags) ||
-		     (!test_bit(In_sync, &rdev->flags) &&
-		      !test_bit(Journal, &rdev->flags))) &&
-		    atomic_read(&rdev->nr_pending)==0)) {
+		    (test_bit(RemoveSynchronized, &rdev->flags) ||
+		     rdev_removeable(rdev))) {
 			if (mddev->pers->hot_remove_disk(
 				    mddev, rdev) == 0) {
 				sysfs_unlink_rdev(mddev, rdev);
@@ -9233,25 +9356,12 @@ static int remove_and_add_spares(struct mddev *mddev,
 	rdev_for_each(rdev, mddev) {
 		if (this && this != rdev)
 			continue;
-		if (test_bit(Candidate, &rdev->flags))
-			continue;
-		if (rdev->raid_disk >= 0 &&
-		    !test_bit(In_sync, &rdev->flags) &&
-		    !test_bit(Journal, &rdev->flags) &&
-		    !test_bit(Faulty, &rdev->flags))
+		if (rdev_is_spare(rdev))
 			spares++;
-		if (rdev->raid_disk >= 0)
+		if (!rdev_addable(rdev))
 			continue;
-		if (test_bit(Faulty, &rdev->flags))
-			continue;
-		if (!test_bit(Journal, &rdev->flags)) {
-			if (!md_is_rdwr(mddev) &&
-			    !(rdev->saved_raid_disk >= 0 &&
-			      !test_bit(Bitmap_sync, &rdev->flags)))
-				continue;
-
+		if (!test_bit(Journal, &rdev->flags))
 			rdev->recovery_offset = 0;
-		}
 		if (mddev->pers->hot_add_disk(mddev, rdev) == 0) {
 			/* failure here is OK */
 			sysfs_link_rdev(mddev, rdev);
@@ -9267,30 +9377,152 @@ no_add:
 	return spares;
 }
 
+static bool md_choose_sync_action(struct mddev *mddev, int *spares)
+{
+	/* Check if reshape is in progress first. */
+	if (mddev->reshape_position != MaxSector) {
+		if (mddev->pers->check_reshape == NULL ||
+		    mddev->pers->check_reshape(mddev) != 0)
+			return false;
+
+		set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
+		clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
+		return true;
+	}
+
+	/*
+	 * Remove any failed drives, then add spares if possible. Spares are
+	 * also removed and re-added, to allow the personality to fail the
+	 * re-add.
+	 */
+	*spares = remove_and_add_spares(mddev, NULL);
+	if (*spares) {
+		clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
+		clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
+		clear_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
+
+		/* Start new recovery. */
+		set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
+		return true;
+	}
+
+	/* Check if recovery is in progress. */
+	if (mddev->recovery_cp < MaxSector) {
+		set_bit(MD_RECOVERY_SYNC, &mddev->recovery);
+		clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
+		return true;
+	}
+
+	/* Delay to choose resync/check/repair in md_do_sync(). */
+	if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery))
+		return true;
+
+	/* Nothing to be done */
+	return false;
+}
+
 static void md_start_sync(struct work_struct *ws)
 {
-	struct mddev *mddev = container_of(ws, struct mddev, del_work);
+	struct mddev *mddev = container_of(ws, struct mddev, sync_work);
+	int spares = 0;
+	bool suspend = false;
+	char *name;
+
+	/*
+	 * If reshape is still in progress, spares won't be added or removed
+	 * from conf until reshape is done.
+	 */
+	if (mddev->reshape_position == MaxSector &&
+	    md_spares_need_change(mddev)) {
+		suspend = true;
+		mddev_suspend(mddev, false);
+	}
+
+	mddev_lock_nointr(mddev);
+	if (!md_is_rdwr(mddev)) {
+		/*
+		 * On a read-only array we can:
+		 * - remove failed devices
+		 * - add already-in_sync devices if the array itself is in-sync.
+		 * As we only add devices that are already in-sync, we can
+		 * activate the spares immediately.
+		 */
+		remove_and_add_spares(mddev, NULL);
+		goto not_running;
+	}
+
+	if (!md_choose_sync_action(mddev, &spares))
+		goto not_running;
+
+	if (!mddev->pers->sync_request)
+		goto not_running;
 
+	/*
+	 * We are adding a device or devices to an array which has the bitmap
+	 * stored on all devices. So make sure all bitmap pages get written.
+	 */
+	if (spares)
+		md_bitmap_write_all(mddev->bitmap);
+
+	name = test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) ?
+			"reshape" : "resync";
 	rcu_assign_pointer(mddev->sync_thread,
-			   md_register_thread(md_do_sync, mddev, "resync"));
+			   md_register_thread(md_do_sync, mddev, name));
 	if (!mddev->sync_thread) {
 		pr_warn("%s: could not start resync thread...\n",
 			mdname(mddev));
 		/* leave the spares where they are, it shouldn't hurt */
-		clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
-		clear_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
-		clear_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
-		clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
-		clear_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
-		wake_up(&resync_wait);
-		if (test_and_clear_bit(MD_RECOVERY_RECOVER,
-				       &mddev->recovery))
-			if (mddev->sysfs_action)
-				sysfs_notify_dirent_safe(mddev->sysfs_action);
-	} else
-		md_wakeup_thread(mddev->sync_thread);
+		goto not_running;
+	}
+
+	mddev_unlock(mddev);
+	/*
+	 * md_start_sync was triggered by MD_RECOVERY_NEEDED, so we should
+	 * not set it again. Otherwise, we may cause issue like this one:
+	 *     https://bugzilla.kernel.org/show_bug.cgi?id=218200
+	 * Therefore, use __mddev_resume(mddev, false).
+	 */
+	if (suspend)
+		__mddev_resume(mddev, false);
+	md_wakeup_thread(mddev->sync_thread);
 	sysfs_notify_dirent_safe(mddev->sysfs_action);
 	md_new_event();
+	return;
+
+not_running:
+	clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
+	clear_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
+	clear_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
+	clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
+	clear_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
+	mddev_unlock(mddev);
+	/*
+	 * md_start_sync was triggered by MD_RECOVERY_NEEDED, so we should
+	 * not set it again. Otherwise, we may cause issue like this one:
+	 *     https://bugzilla.kernel.org/show_bug.cgi?id=218200
+	 * Therefore, use __mddev_resume(mddev, false).
+	 */
+	if (suspend)
+		__mddev_resume(mddev, false);
+
+	wake_up(&resync_wait);
+	if (test_and_clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery) &&
+	    mddev->sysfs_action)
+		sysfs_notify_dirent_safe(mddev->sysfs_action);
+}
+
+static void unregister_sync_thread(struct mddev *mddev)
+{
+	if (!test_bit(MD_RECOVERY_DONE, &mddev->recovery)) {
+		/* resync/recovery still happening */
+		clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+		return;
+	}
+
+	if (WARN_ON_ONCE(!mddev->sync_thread))
+		return;
+
+	md_reap_sync_thread(mddev);
 }
 
 /*
@@ -9317,21 +9549,6 @@ static void md_start_sync(struct work_struct *ws)
  */
 void md_check_recovery(struct mddev *mddev)
 {
-	if (test_bit(MD_ALLOW_SB_UPDATE, &mddev->flags) && mddev->sb_flags) {
-		/* Write superblock - thread that called mddev_suspend()
-		 * holds reconfig_mutex for us.
-		 */
-		set_bit(MD_UPDATING_SB, &mddev->flags);
-		smp_mb__after_atomic();
-		if (test_bit(MD_ALLOW_SB_UPDATE, &mddev->flags))
-			md_update_sb(mddev, 0);
-		clear_bit_unlock(MD_UPDATING_SB, &mddev->flags);
-		wake_up(&mddev->sb_wait);
-	}
-
-	if (is_md_suspended(mddev))
-		return;
-
 	if (mddev->bitmap)
 		md_bitmap_daemon_work(mddev);
 
@@ -9345,7 +9562,8 @@ void md_check_recovery(struct mddev *mddev)
 	}
 
 	if (!md_is_rdwr(mddev) &&
-	    !test_bit(MD_RECOVERY_NEEDED, &mddev->recovery))
+	    !test_bit(MD_RECOVERY_NEEDED, &mddev->recovery) &&
+	    !test_bit(MD_RECOVERY_DONE, &mddev->recovery))
 		return;
 	if ( ! (
 		(mddev->sb_flags & ~ (1<<MD_SB_CHANGE_PENDING)) ||
@@ -9358,7 +9576,6 @@ void md_check_recovery(struct mddev *mddev)
 		return;
 
 	if (mddev_trylock(mddev)) {
-		int spares = 0;
 		bool try_set_sync = mddev->safemode != 0;
 
 		if (!mddev->external && mddev->safemode == 1)
@@ -9366,30 +9583,42 @@ void md_check_recovery(struct mddev *mddev)
 
 		if (!md_is_rdwr(mddev)) {
 			struct md_rdev *rdev;
+
+			if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) {
+				unregister_sync_thread(mddev);
+				goto unlock;
+			}
+
 			if (!mddev->external && mddev->in_sync)
-				/* 'Blocked' flag not needed as failed devices
+				/*
+				 * 'Blocked' flag not needed as failed devices
 				 * will be recorded if array switched to read/write.
 				 * Leaving it set will prevent the device
 				 * from being removed.
 				 */
 				rdev_for_each(rdev, mddev)
 					clear_bit(Blocked, &rdev->flags);
-			/* On a read-only array we can:
-			 * - remove failed devices
-			 * - add already-in_sync devices if the array itself
-			 *   is in-sync.
-			 * As we only add devices that are already in-sync,
-			 * we can activate the spares immediately.
-			 */
-			remove_and_add_spares(mddev, NULL);
-			/* There is no thread, but we need to call
+
+			/*
+			 * There is no thread, but we need to call
 			 * ->spare_active and clear saved_raid_disk
 			 */
 			set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 			md_reap_sync_thread(mddev);
+
+			/*
+			 * Let md_start_sync() to remove and add rdevs to the
+			 * array.
+			 */
+			if (md_spares_need_change(mddev)) {
+				set_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
+				queue_work(md_misc_wq, &mddev->sync_work);
+			}
+
 			clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
 			clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 			clear_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags);
+
 			goto unlock;
 		}
 
@@ -9419,16 +9648,7 @@ void md_check_recovery(struct mddev *mddev)
 		 * still set.
 		 */
 		if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) {
-			if (!test_bit(MD_RECOVERY_DONE, &mddev->recovery)) {
-				/* resync/recovery still happening */
-				clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
-				goto unlock;
-			}
-
-			if (WARN_ON_ONCE(!mddev->sync_thread))
-				goto unlock;
-
-			md_reap_sync_thread(mddev);
+			unregister_sync_thread(mddev);
 			goto unlock;
 		}
 
@@ -9445,56 +9665,14 @@ void md_check_recovery(struct mddev *mddev)
 		clear_bit(MD_RECOVERY_INTR, &mddev->recovery);
 		clear_bit(MD_RECOVERY_DONE, &mddev->recovery);
 
-		if (!test_and_clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery) ||
-		    test_bit(MD_RECOVERY_FROZEN, &mddev->recovery))
-			goto not_running;
-		/* no recovery is running.
-		 * remove any failed drives, then
-		 * add spares if possible.
-		 * Spares are also removed and re-added, to allow
-		 * the personality to fail the re-add.
-		 */
-
-		if (mddev->reshape_position != MaxSector) {
-			if (mddev->pers->check_reshape == NULL ||
-			    mddev->pers->check_reshape(mddev) != 0)
-				/* Cannot proceed */
-				goto not_running;
-			set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
-			clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
-		} else if ((spares = remove_and_add_spares(mddev, NULL))) {
-			clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
-			clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
-			clear_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
-			set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
-		} else if (mddev->recovery_cp < MaxSector) {
-			set_bit(MD_RECOVERY_SYNC, &mddev->recovery);
-			clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
-		} else if (!test_bit(MD_RECOVERY_SYNC, &mddev->recovery))
-			/* nothing to be done ... */
-			goto not_running;
-
-		if (mddev->pers->sync_request) {
-			if (spares) {
-				/* We are adding a device or devices to an array
-				 * which has the bitmap stored on all devices.
-				 * So make sure all bitmap pages get written
-				 */
-				md_bitmap_write_all(mddev->bitmap);
-			}
-			INIT_WORK(&mddev->del_work, md_start_sync);
-			queue_work(md_misc_wq, &mddev->del_work);
-			goto unlock;
-		}
-	not_running:
-		if (!mddev->sync_thread) {
+		if (test_and_clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery) &&
+		    !test_bit(MD_RECOVERY_FROZEN, &mddev->recovery)) {
+			queue_work(md_misc_wq, &mddev->sync_work);
+		} else {
 			clear_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
 			wake_up(&resync_wait);
-			if (test_and_clear_bit(MD_RECOVERY_RECOVER,
-					       &mddev->recovery))
-				if (mddev->sysfs_action)
-					sysfs_notify_dirent_safe(mddev->sysfs_action);
 		}
+
 	unlock:
 		wake_up(&mddev->sb_wait);
 		mddev_unlock(mddev);
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 7c9c13abd7..ade83af123 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -59,6 +59,7 @@ struct md_rdev {
 	 */
 	struct block_device *meta_bdev;
 	struct block_device *bdev;	/* block device handle */
+	struct bdev_handle *bdev_handle;	/* Handle from open for bdev */
 
 	struct page	*sb_page, *bb_page;
 	int		sb_loaded;
@@ -211,9 +212,6 @@ enum flag_bits {
 				 * check if there is collision between raid1
 				 * serial bios.
 				 */
-	Holder,			/* rdev is used as holder while opening
-				 * underlying disk exclusively.
-				 */
 };
 
 static inline int is_badblock(struct md_rdev *rdev, sector_t s, int sectors,
@@ -248,10 +246,6 @@ struct md_cluster_info;
  *			    become failed.
  * @MD_HAS_PPL:  The raid array has PPL feature set.
  * @MD_HAS_MULTIPLE_PPLS: The raid array has multiple PPLs feature set.
- * @MD_ALLOW_SB_UPDATE: md_check_recovery is allowed to update the metadata
- *			 without taking reconfig_mutex.
- * @MD_UPDATING_SB: md_check_recovery is updating the metadata without
- *		     explicitly holding reconfig_mutex.
  * @MD_NOT_READY: do_md_run() is active, so 'array_state', ust not report that
  *		   array is ready yet.
  * @MD_BROKEN: This is used to stop writes and mark array as failed.
@@ -268,8 +262,6 @@ enum mddev_flags {
 	MD_FAILFAST_SUPPORTED,
 	MD_HAS_PPL,
 	MD_HAS_MULTIPLE_PPLS,
-	MD_ALLOW_SB_UPDATE,
-	MD_UPDATING_SB,
 	MD_NOT_READY,
 	MD_BROKEN,
 	MD_DELETED,
@@ -316,6 +308,7 @@ struct mddev {
 	unsigned long			sb_flags;
 
 	int				suspended;
+	struct mutex			suspend_mutex;
 	struct percpu_ref		active_io;
 	int				ro;
 	int				sysfs_active; /* set when sysfs deletes
@@ -453,7 +446,10 @@ struct mddev {
 	struct kernfs_node		*sysfs_degraded;	/*handle for 'degraded' */
 	struct kernfs_node		*sysfs_level;		/*handle for 'level' */
 
-	struct work_struct del_work;	/* used for delayed sysfs removal */
+	/* used for delayed sysfs removal */
+	struct work_struct del_work;
+	/* used for register new sync thread */
+	struct work_struct sync_work;
 
 	/* "lock" protects:
 	 *   flush_bio transition from NULL to !NULL
@@ -567,23 +563,6 @@ enum recovery_flags {
 	MD_RESYNCING_REMOTE,	/* remote node is running resync thread */
 };
 
-enum md_ro_state {
-	MD_RDWR,
-	MD_RDONLY,
-	MD_AUTO_READ,
-	MD_MAX_STATE
-};
-
-static inline bool md_is_rdwr(struct mddev *mddev)
-{
-	return (mddev->ro == MD_RDWR);
-}
-
-static inline bool is_md_suspended(struct mddev *mddev)
-{
-	return percpu_ref_is_dying(&mddev->active_io);
-}
-
 static inline int __must_check mddev_lock(struct mddev *mddev)
 {
 	return mutex_lock_interruptible(&mddev->reconfig_mutex);
@@ -643,7 +622,6 @@ struct md_personality
 	int (*start_reshape) (struct mddev *mddev);
 	void (*finish_reshape) (struct mddev *mddev);
 	void (*update_reshape_pos) (struct mddev *mddev);
-	void (*prepare_suspend) (struct mddev *mddev);
 	/* quiesce suspends or resumes internal processing.
 	 * 1 - stop new actions and wait for action io to complete
 	 * 0 - return to normal behaviour
@@ -768,7 +746,6 @@ extern void md_unregister_thread(struct mddev *mddev, struct md_thread __rcu **t
 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 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);
 extern void md_write_end(struct mddev *mddev);
@@ -795,7 +772,8 @@ extern int md_integrity_register(struct mddev *mddev);
 extern int md_integrity_add_rdev(struct md_rdev *rdev, struct mddev *mddev);
 extern int strict_strtoul_scaled(const char *cp, unsigned long *res, int scale);
 
-extern void mddev_init(struct mddev *mddev);
+extern int mddev_init(struct mddev *mddev);
+extern void mddev_destroy(struct mddev *mddev);
 struct mddev *md_alloc(dev_t dev, char *name);
 void mddev_put(struct mddev *mddev);
 extern int md_run(struct mddev *mddev);
@@ -806,15 +784,14 @@ extern int md_rdev_init(struct md_rdev *rdev);
 extern void md_rdev_clear(struct md_rdev *rdev);
 
 extern void md_handle_request(struct mddev *mddev, struct bio *bio);
-extern void mddev_suspend(struct mddev *mddev);
+extern int mddev_suspend(struct mddev *mddev, bool interruptible);
 extern void mddev_resume(struct mddev *mddev);
 
 extern void md_reload_sb(struct mddev *mddev, int raid_disk);
 extern void md_update_sb(struct mddev *mddev, int force);
-extern void mddev_create_serial_pool(struct mddev *mddev, struct md_rdev *rdev,
-				     bool is_suspend);
-extern void mddev_destroy_serial_pool(struct mddev *mddev, struct md_rdev *rdev,
-				      bool is_suspend);
+extern void mddev_create_serial_pool(struct mddev *mddev, struct md_rdev *rdev);
+extern void mddev_destroy_serial_pool(struct mddev *mddev,
+				      struct md_rdev *rdev);
 struct md_rdev *md_find_rdev_nr_rcu(struct mddev *mddev, int nr);
 struct md_rdev *md_find_rdev_rcu(struct mddev *mddev, dev_t dev);
 
@@ -852,6 +829,33 @@ static inline void mddev_check_write_zeroes(struct mddev *mddev, struct bio *bio
 		mddev->queue->limits.max_write_zeroes_sectors = 0;
 }
 
+static inline int mddev_suspend_and_lock(struct mddev *mddev)
+{
+	int ret;
+
+	ret = mddev_suspend(mddev, true);
+	if (ret)
+		return ret;
+
+	ret = mddev_lock(mddev);
+	if (ret)
+		mddev_resume(mddev);
+
+	return ret;
+}
+
+static inline void mddev_suspend_and_lock_nointr(struct mddev *mddev)
+{
+	mddev_suspend(mddev, false);
+	mutex_lock(&mddev->reconfig_mutex);
+}
+
+static inline void mddev_unlock_and_resume(struct mddev *mddev)
+{
+	mddev_unlock(mddev);
+	mddev_resume(mddev);
+}
+
 struct mdu_array_info_s;
 struct mdu_disk_info_s;
 
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 911670273d..e138922d51 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1345,6 +1345,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 	int first_clone;
 	int max_sectors;
 	bool write_behind = false;
+	bool is_discard = (bio_op(bio) == REQ_OP_DISCARD);
 
 	if (mddev_is_clustered(mddev) &&
 	     md_cluster_ops->area_resyncing(mddev, WRITE,
@@ -1405,7 +1406,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 		 * write-mostly, which means we could allocate write behind
 		 * bio later.
 		 */
-		if (rdev && test_bit(WriteMostly, &rdev->flags))
+		if (!is_discard && rdev && test_bit(WriteMostly, &rdev->flags))
 			write_behind = true;
 
 		if (rdev && unlikely(test_bit(Blocked, &rdev->flags))) {
@@ -3122,8 +3123,7 @@ static int raid1_run(struct mddev *mddev)
 			mdname(mddev));
 		return -EIO;
 	}
-	if (mddev_init_writes_pending(mddev) < 0)
-		return -ENOMEM;
+
 	/*
 	 * copy the already verified devices into our private RAID1
 	 * bookkeeping area. [whatever we allocate in run(),
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 0234131208..b7b0a573e7 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -4154,9 +4154,6 @@ static int raid10_run(struct mddev *mddev)
 	sector_t min_offset_diff = 0;
 	int first = 1;
 
-	if (mddev_init_writes_pending(mddev) < 0)
-		return -ENOMEM;
-
 	if (mddev->private == NULL) {
 		conf = setup_conf(mddev);
 		if (IS_ERR(conf))
@@ -4310,11 +4307,7 @@ static int raid10_run(struct mddev *mddev)
 		clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
 		clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
 		set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
-		set_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
-		rcu_assign_pointer(mddev->sync_thread,
-			md_register_thread(md_do_sync, mddev, "reshape"));
-		if (!mddev->sync_thread)
-			goto out_free_conf;
+		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	}
 
 	return 0;
@@ -4710,16 +4703,8 @@ out:
 	clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
 	clear_bit(MD_RECOVERY_DONE, &mddev->recovery);
 	set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
-	set_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
-
-	rcu_assign_pointer(mddev->sync_thread,
-			   md_register_thread(md_do_sync, mddev, "reshape"));
-	if (!mddev->sync_thread) {
-		ret = -EAGAIN;
-		goto abort;
-	}
+	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	conf->reshape_checkpoint = jiffies;
-	md_wakeup_thread(mddev->sync_thread);
 	md_new_event();
 	return 0;
 
diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c
index 518b7cfa78..6157f5beb9 100644
--- a/drivers/md/raid5-cache.c
+++ b/drivers/md/raid5-cache.c
@@ -327,8 +327,9 @@ void r5l_wake_reclaim(struct r5l_log *log, sector_t space);
 void r5c_check_stripe_cache_usage(struct r5conf *conf)
 {
 	int total_cached;
+	struct r5l_log *log = READ_ONCE(conf->log);
 
-	if (!r5c_is_writeback(conf->log))
+	if (!r5c_is_writeback(log))
 		return;
 
 	total_cached = atomic_read(&conf->r5c_cached_partial_stripes) +
@@ -344,7 +345,7 @@ void r5c_check_stripe_cache_usage(struct r5conf *conf)
 	 */
 	if (total_cached > conf->min_nr_stripes * 1 / 2 ||
 	    atomic_read(&conf->empty_inactive_list_nr) > 0)
-		r5l_wake_reclaim(conf->log, 0);
+		r5l_wake_reclaim(log, 0);
 }
 
 /*
@@ -353,7 +354,9 @@ void r5c_check_stripe_cache_usage(struct r5conf *conf)
  */
 void r5c_check_cached_full_stripe(struct r5conf *conf)
 {
-	if (!r5c_is_writeback(conf->log))
+	struct r5l_log *log = READ_ONCE(conf->log);
+
+	if (!r5c_is_writeback(log))
 		return;
 
 	/*
@@ -363,7 +366,7 @@ void r5c_check_cached_full_stripe(struct r5conf *conf)
 	if (atomic_read(&conf->r5c_cached_full_stripes) >=
 	    min(R5C_FULL_STRIPE_FLUSH_BATCH(conf),
 		conf->chunk_sectors >> RAID5_STRIPE_SHIFT(conf)))
-		r5l_wake_reclaim(conf->log, 0);
+		r5l_wake_reclaim(log, 0);
 }
 
 /*
@@ -396,7 +399,7 @@ void r5c_check_cached_full_stripe(struct r5conf *conf)
  */
 static sector_t r5c_log_required_to_flush_cache(struct r5conf *conf)
 {
-	struct r5l_log *log = conf->log;
+	struct r5l_log *log = READ_ONCE(conf->log);
 
 	if (!r5c_is_writeback(log))
 		return 0;
@@ -449,7 +452,7 @@ static inline void r5c_update_log_state(struct r5l_log *log)
 void r5c_make_stripe_write_out(struct stripe_head *sh)
 {
 	struct r5conf *conf = sh->raid_conf;
-	struct r5l_log *log = conf->log;
+	struct r5l_log *log = READ_ONCE(conf->log);
 
 	BUG_ON(!r5c_is_writeback(log));
 
@@ -491,7 +494,7 @@ static void r5c_handle_parity_cached(struct stripe_head *sh)
  */
 static void r5c_finish_cache_stripe(struct stripe_head *sh)
 {
-	struct r5l_log *log = sh->raid_conf->log;
+	struct r5l_log *log = READ_ONCE(sh->raid_conf->log);
 
 	if (log->r5c_journal_mode == R5C_JOURNAL_MODE_WRITE_THROUGH) {
 		BUG_ON(test_bit(STRIPE_R5C_CACHING, &sh->state));
@@ -683,7 +686,6 @@ static void r5c_disable_writeback_async(struct work_struct *work)
 					   disable_writeback_work);
 	struct mddev *mddev = log->rdev->mddev;
 	struct r5conf *conf = mddev->private;
-	int locked = 0;
 
 	if (log->r5c_journal_mode == R5C_JOURNAL_MODE_WRITE_THROUGH)
 		return;
@@ -692,14 +694,14 @@ static void r5c_disable_writeback_async(struct work_struct *work)
 
 	/* wait superblock change before suspend */
 	wait_event(mddev->sb_wait,
-		   conf->log == NULL ||
-		   (!test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags) &&
-		    (locked = mddev_trylock(mddev))));
-	if (locked) {
-		mddev_suspend(mddev);
+		   !READ_ONCE(conf->log) ||
+		   !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags));
+
+	log = READ_ONCE(conf->log);
+	if (log) {
+		mddev_suspend(mddev, false);
 		log->r5c_journal_mode = R5C_JOURNAL_MODE_WRITE_THROUGH;
 		mddev_resume(mddev);
-		mddev_unlock(mddev);
 	}
 }
 
@@ -1151,7 +1153,7 @@ static void r5l_run_no_space_stripes(struct r5l_log *log)
 static sector_t r5c_calculate_new_cp(struct r5conf *conf)
 {
 	struct stripe_head *sh;
-	struct r5l_log *log = conf->log;
+	struct r5l_log *log = READ_ONCE(conf->log);
 	sector_t new_cp;
 	unsigned long flags;
 
@@ -1159,12 +1161,12 @@ static sector_t r5c_calculate_new_cp(struct r5conf *conf)
 		return log->next_checkpoint;
 
 	spin_lock_irqsave(&log->stripe_in_journal_lock, flags);
-	if (list_empty(&conf->log->stripe_in_journal_list)) {
+	if (list_empty(&log->stripe_in_journal_list)) {
 		/* all stripes flushed */
 		spin_unlock_irqrestore(&log->stripe_in_journal_lock, flags);
 		return log->next_checkpoint;
 	}
-	sh = list_first_entry(&conf->log->stripe_in_journal_list,
+	sh = list_first_entry(&log->stripe_in_journal_list,
 			      struct stripe_head, r5c);
 	new_cp = sh->log_start;
 	spin_unlock_irqrestore(&log->stripe_in_journal_lock, flags);
@@ -1399,7 +1401,7 @@ void r5c_flush_cache(struct r5conf *conf, int num)
 	struct stripe_head *sh, *next;
 
 	lockdep_assert_held(&conf->device_lock);
-	if (!conf->log)
+	if (!READ_ONCE(conf->log))
 		return;
 
 	count = 0;
@@ -1420,7 +1422,7 @@ void r5c_flush_cache(struct r5conf *conf, int num)
 
 static void r5c_do_reclaim(struct r5conf *conf)
 {
-	struct r5l_log *log = conf->log;
+	struct r5l_log *log = READ_ONCE(conf->log);
 	struct stripe_head *sh;
 	int count = 0;
 	unsigned long flags;
@@ -1549,7 +1551,7 @@ static void r5l_reclaim_thread(struct md_thread *thread)
 {
 	struct mddev *mddev = thread->mddev;
 	struct r5conf *conf = mddev->private;
-	struct r5l_log *log = conf->log;
+	struct r5l_log *log = READ_ONCE(conf->log);
 
 	if (!log)
 		return;
@@ -1591,7 +1593,7 @@ void r5l_quiesce(struct r5l_log *log, int quiesce)
 
 bool r5l_log_disk_error(struct r5conf *conf)
 {
-	struct r5l_log *log = conf->log;
+	struct r5l_log *log = READ_ONCE(conf->log);
 
 	/* don't allow write if journal disk is missing */
 	if (!log)
@@ -2583,9 +2585,7 @@ int r5c_journal_mode_set(struct mddev *mddev, int mode)
 	    mode == R5C_JOURNAL_MODE_WRITE_BACK)
 		return -EINVAL;
 
-	mddev_suspend(mddev);
 	conf->log->r5c_journal_mode = mode;
-	mddev_resume(mddev);
 
 	pr_debug("md/raid:%s: setting r5c cache mode to %d: %s\n",
 		 mdname(mddev), mode, r5c_journal_mode_str[mode]);
@@ -2610,11 +2610,11 @@ static ssize_t r5c_journal_mode_store(struct mddev *mddev,
 		if (strlen(r5c_journal_mode_str[mode]) == len &&
 		    !strncmp(page, r5c_journal_mode_str[mode], len))
 			break;
-	ret = mddev_lock(mddev);
+	ret = mddev_suspend_and_lock(mddev);
 	if (ret)
 		return ret;
 	ret = r5c_journal_mode_set(mddev, mode);
-	mddev_unlock(mddev);
+	mddev_unlock_and_resume(mddev);
 	return ret ?: length;
 }
 
@@ -2635,7 +2635,7 @@ int r5c_try_caching_write(struct r5conf *conf,
 			  struct stripe_head_state *s,
 			  int disks)
 {
-	struct r5l_log *log = conf->log;
+	struct r5l_log *log = READ_ONCE(conf->log);
 	int i;
 	struct r5dev *dev;
 	int to_cache = 0;
@@ -2802,7 +2802,7 @@ void r5c_finish_stripe_write_out(struct r5conf *conf,
 				 struct stripe_head *sh,
 				 struct stripe_head_state *s)
 {
-	struct r5l_log *log = conf->log;
+	struct r5l_log *log = READ_ONCE(conf->log);
 	int i;
 	int do_wakeup = 0;
 	sector_t tree_index;
@@ -2941,7 +2941,7 @@ int r5c_cache_data(struct r5l_log *log, struct stripe_head *sh)
 /* check whether this big stripe is in write back cache. */
 bool r5c_big_stripe_cached(struct r5conf *conf, sector_t sect)
 {
-	struct r5l_log *log = conf->log;
+	struct r5l_log *log = READ_ONCE(conf->log);
 	sector_t tree_index;
 	void *slot;
 
@@ -3049,14 +3049,14 @@ int r5l_start(struct r5l_log *log)
 void r5c_update_on_rdev_error(struct mddev *mddev, struct md_rdev *rdev)
 {
 	struct r5conf *conf = mddev->private;
-	struct r5l_log *log = conf->log;
+	struct r5l_log *log = READ_ONCE(conf->log);
 
 	if (!log)
 		return;
 
 	if ((raid5_calc_degraded(conf) > 0 ||
 	     test_bit(Journal, &rdev->flags)) &&
-	    conf->log->r5c_journal_mode == R5C_JOURNAL_MODE_WRITE_BACK)
+	    log->r5c_journal_mode == R5C_JOURNAL_MODE_WRITE_BACK)
 		schedule_work(&log->disable_writeback_work);
 }
 
@@ -3145,7 +3145,7 @@ int r5l_init_log(struct r5conf *conf, struct md_rdev *rdev)
 	spin_lock_init(&log->stripe_in_journal_lock);
 	atomic_set(&log->stripe_in_journal_count, 0);
 
-	conf->log = log;
+	WRITE_ONCE(conf->log, log);
 
 	set_bit(MD_HAS_JOURNAL, &conf->mddev->flags);
 	return 0;
@@ -3173,7 +3173,7 @@ void r5l_exit_log(struct r5conf *conf)
 	 * 'reconfig_mutex' is held by caller, set 'confg->log' to NULL to
 	 * ensure disable_writeback_work wakes up and exits.
 	 */
-	conf->log = NULL;
+	WRITE_ONCE(conf->log, NULL);
 	wake_up(&conf->mddev->sb_wait);
 	flush_work(&log->disable_writeback_work);
 
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 68d86dbecb..6fe334bb95 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -70,6 +70,8 @@ MODULE_PARM_DESC(devices_handle_discard_safely,
 		 "Set to Y if all devices in each array reliably return zeroes on reads from discarded regions");
 static struct workqueue_struct *raid5_wq;
 
+static void raid5_quiesce(struct mddev *mddev, int quiesce);
+
 static inline struct hlist_head *stripe_hash(struct r5conf *conf, sector_t sect)
 {
 	int hash = (sect >> RAID5_STRIPE_SHIFT(conf)) & HASH_MASK;
@@ -2499,15 +2501,12 @@ static int resize_chunks(struct r5conf *conf, int new_disks, int new_sectors)
 	unsigned long cpu;
 	int err = 0;
 
-	/*
-	 * Never shrink. And mddev_suspend() could deadlock if this is called
-	 * from raid5d. In that case, scribble_disks and scribble_sectors
-	 * should equal to new_disks and new_sectors
-	 */
+	/* Never shrink. */
 	if (conf->scribble_disks >= new_disks &&
 	    conf->scribble_sectors >= new_sectors)
 		return 0;
-	mddev_suspend(conf->mddev);
+
+	raid5_quiesce(conf->mddev, true);
 	cpus_read_lock();
 
 	for_each_present_cpu(cpu) {
@@ -2521,7 +2520,8 @@ static int resize_chunks(struct r5conf *conf, int new_disks, int new_sectors)
 	}
 
 	cpus_read_unlock();
-	mddev_resume(conf->mddev);
+	raid5_quiesce(conf->mddev, false);
+
 	if (!err) {
 		conf->scribble_disks = new_disks;
 		conf->scribble_sectors = new_sectors;
@@ -5960,19 +5960,6 @@ out:
 	return ret;
 }
 
-static bool reshape_inprogress(struct mddev *mddev)
-{
-	return test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) &&
-	       test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) &&
-	       !test_bit(MD_RECOVERY_DONE, &mddev->recovery) &&
-	       !test_bit(MD_RECOVERY_INTR, &mddev->recovery);
-}
-
-static bool reshape_disabled(struct mddev *mddev)
-{
-	return is_md_suspended(mddev) || !md_is_rdwr(mddev);
-}
-
 static enum stripe_result make_stripe_request(struct mddev *mddev,
 		struct r5conf *conf, struct stripe_request_ctx *ctx,
 		sector_t logical_sector, struct bio *bi)
@@ -6004,8 +5991,7 @@ static enum stripe_result make_stripe_request(struct mddev *mddev,
 			if (ahead_of_reshape(mddev, logical_sector,
 					     conf->reshape_safe)) {
 				spin_unlock_irq(&conf->device_lock);
-				ret = STRIPE_SCHEDULE_AND_RETRY;
-				goto out;
+				return STRIPE_SCHEDULE_AND_RETRY;
 			}
 		}
 		spin_unlock_irq(&conf->device_lock);
@@ -6084,15 +6070,6 @@ static enum stripe_result make_stripe_request(struct mddev *mddev,
 
 out_release:
 	raid5_release_stripe(sh);
-out:
-	if (ret == STRIPE_SCHEDULE_AND_RETRY && !reshape_inprogress(mddev) &&
-	    reshape_disabled(mddev)) {
-		bi->bi_status = BLK_STS_IOERR;
-		ret = STRIPE_FAIL;
-		pr_err("md/raid456:%s: io failed across reshape position while reshape can't make progress.\n",
-		       mdname(mddev));
-	}
-
 	return ret;
 }
 
@@ -7032,7 +7009,7 @@ raid5_store_stripe_size(struct mddev  *mddev, const char *page, size_t len)
 			new != roundup_pow_of_two(new))
 		return -EINVAL;
 
-	err = mddev_lock(mddev);
+	err = mddev_suspend_and_lock(mddev);
 	if (err)
 		return err;
 
@@ -7056,7 +7033,6 @@ raid5_store_stripe_size(struct mddev  *mddev, const char *page, size_t len)
 		goto out_unlock;
 	}
 
-	mddev_suspend(mddev);
 	mutex_lock(&conf->cache_size_mutex);
 	size = conf->max_nr_stripes;
 
@@ -7071,10 +7047,9 @@ raid5_store_stripe_size(struct mddev  *mddev, const char *page, size_t len)
 		err = -ENOMEM;
 	}
 	mutex_unlock(&conf->cache_size_mutex);
-	mddev_resume(mddev);
 
 out_unlock:
-	mddev_unlock(mddev);
+	mddev_unlock_and_resume(mddev);
 	return err ?: len;
 }
 
@@ -7160,7 +7135,7 @@ raid5_store_skip_copy(struct mddev *mddev, const char *page, size_t len)
 		return -EINVAL;
 	new = !!new;
 
-	err = mddev_lock(mddev);
+	err = mddev_suspend_and_lock(mddev);
 	if (err)
 		return err;
 	conf = mddev->private;
@@ -7169,15 +7144,13 @@ raid5_store_skip_copy(struct mddev *mddev, const char *page, size_t len)
 	else if (new != conf->skip_copy) {
 		struct request_queue *q = mddev->queue;
 
-		mddev_suspend(mddev);
 		conf->skip_copy = new;
 		if (new)
 			blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, q);
 		else
 			blk_queue_flag_clear(QUEUE_FLAG_STABLE_WRITES, q);
-		mddev_resume(mddev);
 	}
-	mddev_unlock(mddev);
+	mddev_unlock_and_resume(mddev);
 	return err ?: len;
 }
 
@@ -7232,15 +7205,13 @@ raid5_store_group_thread_cnt(struct mddev *mddev, const char *page, size_t len)
 	if (new > 8192)
 		return -EINVAL;
 
-	err = mddev_lock(mddev);
+	err = mddev_suspend_and_lock(mddev);
 	if (err)
 		return err;
 	conf = mddev->private;
 	if (!conf)
 		err = -ENODEV;
 	else if (new != conf->worker_cnt_per_group) {
-		mddev_suspend(mddev);
-
 		old_groups = conf->worker_groups;
 		if (old_groups)
 			flush_workqueue(raid5_wq);
@@ -7257,9 +7228,8 @@ raid5_store_group_thread_cnt(struct mddev *mddev, const char *page, size_t len)
 				kfree(old_groups[0].workers);
 			kfree(old_groups);
 		}
-		mddev_resume(mddev);
 	}
-	mddev_unlock(mddev);
+	mddev_unlock_and_resume(mddev);
 
 	return err ?: len;
 }
@@ -7408,7 +7378,7 @@ static void free_conf(struct r5conf *conf)
 
 	log_exit(conf);
 
-	unregister_shrinker(&conf->shrinker);
+	shrinker_free(conf->shrinker);
 	free_thread_groups(conf);
 	shrink_stripes(conf);
 	raid5_free_percpu(conf);
@@ -7456,7 +7426,7 @@ static int raid5_alloc_percpu(struct r5conf *conf)
 static unsigned long raid5_cache_scan(struct shrinker *shrink,
 				      struct shrink_control *sc)
 {
-	struct r5conf *conf = container_of(shrink, struct r5conf, shrinker);
+	struct r5conf *conf = shrink->private_data;
 	unsigned long ret = SHRINK_STOP;
 
 	if (mutex_trylock(&conf->cache_size_mutex)) {
@@ -7477,7 +7447,7 @@ static unsigned long raid5_cache_scan(struct shrinker *shrink,
 static unsigned long raid5_cache_count(struct shrinker *shrink,
 				       struct shrink_control *sc)
 {
-	struct r5conf *conf = container_of(shrink, struct r5conf, shrinker);
+	struct r5conf *conf = shrink->private_data;
 
 	if (conf->max_nr_stripes < conf->min_nr_stripes)
 		/* unlikely, but not impossible */
@@ -7712,18 +7682,22 @@ static struct r5conf *setup_conf(struct mddev *mddev)
 	 * it reduces the queue depth and so can hurt throughput.
 	 * So set it rather large, scaled by number of devices.
 	 */
-	conf->shrinker.seeks = DEFAULT_SEEKS * conf->raid_disks * 4;
-	conf->shrinker.scan_objects = raid5_cache_scan;
-	conf->shrinker.count_objects = raid5_cache_count;
-	conf->shrinker.batch = 128;
-	conf->shrinker.flags = 0;
-	ret = register_shrinker(&conf->shrinker, "md-raid5:%s", mdname(mddev));
-	if (ret) {
-		pr_warn("md/raid:%s: couldn't register shrinker.\n",
+	conf->shrinker = shrinker_alloc(0, "md-raid5:%s", mdname(mddev));
+	if (!conf->shrinker) {
+		ret = -ENOMEM;
+		pr_warn("md/raid:%s: couldn't allocate shrinker.\n",
 			mdname(mddev));
 		goto abort;
 	}
 
+	conf->shrinker->seeks = DEFAULT_SEEKS * conf->raid_disks * 4;
+	conf->shrinker->scan_objects = raid5_cache_scan;
+	conf->shrinker->count_objects = raid5_cache_count;
+	conf->shrinker->batch = 128;
+	conf->shrinker->private_data = conf;
+
+	shrinker_register(conf->shrinker);
+
 	sprintf(pers_name, "raid%d", mddev->new_level);
 	rcu_assign_pointer(conf->thread,
 			   md_register_thread(raid5d, mddev, pers_name));
@@ -7785,9 +7759,6 @@ static int raid5_run(struct mddev *mddev)
 	long long min_offset_diff = 0;
 	int first = 1;
 
-	if (mddev_init_writes_pending(mddev) < 0)
-		return -ENOMEM;
-
 	if (mddev->recovery_cp != MaxSector)
 		pr_notice("md/raid:%s: not clean -- starting background reconstruction\n",
 			  mdname(mddev));
@@ -8031,11 +8002,7 @@ static int raid5_run(struct mddev *mddev)
 		clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
 		clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
 		set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
-		set_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
-		rcu_assign_pointer(mddev->sync_thread,
-			md_register_thread(md_do_sync, mddev, "reshape"));
-		if (!mddev->sync_thread)
-			goto abort;
+		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	}
 
 	/* Ok, everything is just fine now */
@@ -8568,8 +8535,8 @@ static int raid5_start_reshape(struct mddev *mddev)
 	 * the reshape wasn't running - like Discard or Read - have
 	 * completed.
 	 */
-	mddev_suspend(mddev);
-	mddev_resume(mddev);
+	raid5_quiesce(mddev, true);
+	raid5_quiesce(mddev, false);
 
 	/* Add some new drives, as many as will fit.
 	 * We know there are enough to make the newly sized array work.
@@ -8614,29 +8581,8 @@ static int raid5_start_reshape(struct mddev *mddev)
 	clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
 	clear_bit(MD_RECOVERY_DONE, &mddev->recovery);
 	set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
-	set_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
-	rcu_assign_pointer(mddev->sync_thread,
-			   md_register_thread(md_do_sync, mddev, "reshape"));
-	if (!mddev->sync_thread) {
-		mddev->recovery = 0;
-		spin_lock_irq(&conf->device_lock);
-		write_seqcount_begin(&conf->gen_lock);
-		mddev->raid_disks = conf->raid_disks = conf->previous_raid_disks;
-		mddev->new_chunk_sectors =
-			conf->chunk_sectors = conf->prev_chunk_sectors;
-		mddev->new_layout = conf->algorithm = conf->prev_algo;
-		rdev_for_each(rdev, mddev)
-			rdev->new_data_offset = rdev->data_offset;
-		smp_wmb();
-		conf->generation --;
-		conf->reshape_progress = MaxSector;
-		mddev->reshape_position = MaxSector;
-		write_seqcount_end(&conf->gen_lock);
-		spin_unlock_irq(&conf->device_lock);
-		return -EAGAIN;
-	}
+	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	conf->reshape_checkpoint = jiffies;
-	md_wakeup_thread(mddev->sync_thread);
 	md_new_event();
 	return 0;
 }
@@ -8984,12 +8930,12 @@ static int raid5_change_consistency_policy(struct mddev *mddev, const char *buf)
 	struct r5conf *conf;
 	int err;
 
-	err = mddev_lock(mddev);
+	err = mddev_suspend_and_lock(mddev);
 	if (err)
 		return err;
 	conf = mddev->private;
 	if (!conf) {
-		mddev_unlock(mddev);
+		mddev_unlock_and_resume(mddev);
 		return -ENODEV;
 	}
 
@@ -8999,19 +8945,14 @@ static int raid5_change_consistency_policy(struct mddev *mddev, const char *buf)
 			err = log_init(conf, NULL, true);
 			if (!err) {
 				err = resize_stripes(conf, conf->pool_size);
-				if (err) {
-					mddev_suspend(mddev);
+				if (err)
 					log_exit(conf);
-					mddev_resume(mddev);
-				}
 			}
 		} else
 			err = -EINVAL;
 	} else if (strncmp(buf, "resync", 6) == 0) {
 		if (raid5_has_ppl(conf)) {
-			mddev_suspend(mddev);
 			log_exit(conf);
-			mddev_resume(mddev);
 			err = resize_stripes(conf, conf->pool_size);
 		} else if (test_bit(MD_HAS_JOURNAL, &conf->mddev->flags) &&
 			   r5l_log_disk_error(conf)) {
@@ -9024,11 +8965,9 @@ static int raid5_change_consistency_policy(struct mddev *mddev, const char *buf)
 					break;
 				}
 
-			if (!journal_dev_exists) {
-				mddev_suspend(mddev);
+			if (!journal_dev_exists)
 				clear_bit(MD_HAS_JOURNAL, &mddev->flags);
-				mddev_resume(mddev);
-			} else  /* need remove journal device first */
+			else  /* need remove journal device first */
 				err = -EBUSY;
 		} else
 			err = -EINVAL;
@@ -9039,7 +8978,7 @@ static int raid5_change_consistency_policy(struct mddev *mddev, const char *buf)
 	if (!err)
 		md_update_sb(mddev, 1);
 
-	mddev_unlock(mddev);
+	mddev_unlock_and_resume(mddev);
 
 	return err;
 }
@@ -9051,22 +8990,6 @@ static int raid5_start(struct mddev *mddev)
 	return r5l_start(conf->log);
 }
 
-static void raid5_prepare_suspend(struct mddev *mddev)
-{
-	struct r5conf *conf = mddev->private;
-
-	wait_event(mddev->sb_wait, !reshape_inprogress(mddev) ||
-				    percpu_ref_is_zero(&mddev->active_io));
-	if (percpu_ref_is_zero(&mddev->active_io))
-		return;
-
-	/*
-	 * Reshape is not in progress, and array is suspended, io that is
-	 * waiting for reshpape can never be done.
-	 */
-	wake_up(&conf->wait_for_overlap);
-}
-
 static struct md_personality raid6_personality =
 {
 	.name		= "raid6",
@@ -9087,7 +9010,6 @@ static struct md_personality raid6_personality =
 	.check_reshape	= raid6_check_reshape,
 	.start_reshape  = raid5_start_reshape,
 	.finish_reshape = raid5_finish_reshape,
-	.prepare_suspend = raid5_prepare_suspend,
 	.quiesce	= raid5_quiesce,
 	.takeover	= raid6_takeover,
 	.change_consistency_policy = raid5_change_consistency_policy,
@@ -9112,7 +9034,6 @@ static struct md_personality raid5_personality =
 	.check_reshape	= raid5_check_reshape,
 	.start_reshape  = raid5_start_reshape,
 	.finish_reshape = raid5_finish_reshape,
-	.prepare_suspend = raid5_prepare_suspend,
 	.quiesce	= raid5_quiesce,
 	.takeover	= raid5_takeover,
 	.change_consistency_policy = raid5_change_consistency_policy,
@@ -9138,7 +9059,6 @@ static struct md_personality raid4_personality =
 	.check_reshape	= raid5_check_reshape,
 	.start_reshape  = raid5_start_reshape,
 	.finish_reshape = raid5_finish_reshape,
-	.prepare_suspend = raid5_prepare_suspend,
 	.quiesce	= raid5_quiesce,
 	.takeover	= raid4_takeover,
 	.change_consistency_policy = raid5_change_consistency_policy,
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index 97a795979a..22bea20ecc 100644
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -670,7 +670,7 @@ struct r5conf {
 	wait_queue_head_t	wait_for_stripe;
 	wait_queue_head_t	wait_for_overlap;
 	unsigned long		cache_state;
-	struct shrinker		shrinker;
+	struct shrinker		*shrinker;
 	int			pool_size; /* number of disks in stripeheads in pool */
 	spinlock_t		device_lock;
 	struct disk_info	*disks;