Adding upstream version 6.7.7.upstream/6.7.7

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

14 files changed, 165 insertions, 751 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);