Merge branch 'for-linus' of git://git.kernel.dk/linux-block

Pull second round of block driver updates from Jens Axboe:
 "As mentioned in the original pull request, the bcache bits were pulled
  because of their dependency on the immutable bio vecs.  Kent re-did
  this part and resubmitted it, so here's the 2nd round of (mostly)
  driver updates for 3.13.  It contains:

 - The bcache work from Kent.

 - Conversion of virtio-blk to blk-mq.  This removes the bio and request
   path, and substitutes with the blk-mq path instead.  The end result
   almost 200 deleted lines.  Patch is acked by Asias and Christoph, who
   both did a bunch of testing.

 - A removal of bootmem.h include from Grygorii Strashko, part of a
   larger series of his killing the dependency on that header file.

 - Removal of __cpuinit from blk-mq from Paul Gortmaker"

* 'for-linus' of git://git.kernel.dk/linux-block: (56 commits)
  virtio_blk: blk-mq support
  blk-mq: remove newly added instances of __cpuinit
  bcache: defensively handle format strings
  bcache: Bypass torture test
  bcache: Delete some slower inline asm
  bcache: Use ida for bcache block dev minor
  bcache: Fix sysfs splat on shutdown with flash only devs
  bcache: Better full stripe scanning
  bcache: Have btree_split() insert into parent directly
  bcache: Move spinlock into struct time_stats
  bcache: Kill sequential_merge option
  bcache: Kill bch_next_recurse_key()
  bcache: Avoid deadlocking in garbage collection
  bcache: Incremental gc
  bcache: Add make_btree_freeing_key()
  bcache: Add btree_node_write_sync()
  bcache: PRECEDING_KEY()
  bcache: bch_(btree|extent)_ptr_invalid()
  bcache: Don't bother with bucket refcount for btree node allocations
  bcache: Debug code improvements
  ...

25 files changed, 2587 insertions, 3005 deletions

diff --git a/drivers/md/bcache/Kconfig b/drivers/md/bcache/Kconfig
index f950c9d29f3e..2638417b19aa 100644
--- a/drivers/md/bcache/Kconfig
+++ b/drivers/md/bcache/Kconfig
@@ -13,15 +13,8 @@ config BCACHE_DEBUG
 	---help---
 	Don't select this option unless you're a developer
 
-	Enables extra debugging tools (primarily a fuzz tester)
-
-config BCACHE_EDEBUG
-	bool "Extended runtime checks"
-	depends on BCACHE
-	---help---
-	Don't select this option unless you're a developer
-
-	Enables extra runtime checks which significantly affect performance
+	Enables extra debugging tools, allows expensive runtime checks to be
+	turned on.
 
 config BCACHE_CLOSURES_DEBUG
 	bool "Debug closures"
diff --git a/drivers/md/bcache/alloc.c b/drivers/md/bcache/alloc.c
index e45f5575fd4d..2b46bf1d7e40 100644
--- a/drivers/md/bcache/alloc.c
+++ b/drivers/md/bcache/alloc.c
@@ -63,13 +63,12 @@
 #include "bcache.h"
 #include "btree.h"
 
+#include <linux/blkdev.h>
 #include <linux/freezer.h>
 #include <linux/kthread.h>
 #include <linux/random.h>
 #include <trace/events/bcache.h>
 
-#define MAX_IN_FLIGHT_DISCARDS		8U
-
 /* Bucket heap / gen */
 
 uint8_t bch_inc_gen(struct cache *ca, struct bucket *b)
@@ -121,75 +120,6 @@ void bch_rescale_priorities(struct cache_set *c, int sectors)
 	mutex_unlock(&c->bucket_lock);
 }
 
-/* Discard/TRIM */
-
-struct discard {
-	struct list_head	list;
-	struct work_struct	work;
-	struct cache		*ca;
-	long			bucket;
-
-	struct bio		bio;
-	struct bio_vec		bv;
-};
-
-static void discard_finish(struct work_struct *w)
-{
-	struct discard *d = container_of(w, struct discard, work);
-	struct cache *ca = d->ca;
-	char buf[BDEVNAME_SIZE];
-
-	if (!test_bit(BIO_UPTODATE, &d->bio.bi_flags)) {
-		pr_notice("discard error on %s, disabling",
-			 bdevname(ca->bdev, buf));
-		d->ca->discard = 0;
-	}
-
-	mutex_lock(&ca->set->bucket_lock);
-
-	fifo_push(&ca->free, d->bucket);
-	list_add(&d->list, &ca->discards);
-	atomic_dec(&ca->discards_in_flight);
-
-	mutex_unlock(&ca->set->bucket_lock);
-
-	closure_wake_up(&ca->set->bucket_wait);
-	wake_up_process(ca->alloc_thread);
-
-	closure_put(&ca->set->cl);
-}
-
-static void discard_endio(struct bio *bio, int error)
-{
-	struct discard *d = container_of(bio, struct discard, bio);
-	schedule_work(&d->work);
-}
-
-static void do_discard(struct cache *ca, long bucket)
-{
-	struct discard *d = list_first_entry(&ca->discards,
-					     struct discard, list);
-
-	list_del(&d->list);
-	d->bucket = bucket;
-
-	atomic_inc(&ca->discards_in_flight);
-	closure_get(&ca->set->cl);
-
-	bio_init(&d->bio);
-
-	d->bio.bi_sector	= bucket_to_sector(ca->set, d->bucket);
-	d->bio.bi_bdev		= ca->bdev;
-	d->bio.bi_rw		= REQ_WRITE|REQ_DISCARD;
-	d->bio.bi_max_vecs	= 1;
-	d->bio.bi_io_vec	= d->bio.bi_inline_vecs;
-	d->bio.bi_size		= bucket_bytes(ca);
-	d->bio.bi_end_io	= discard_endio;
-	bio_set_prio(&d->bio, IOPRIO_PRIO_VALUE(IOPRIO_CLASS_IDLE, 0));
-
-	submit_bio(0, &d->bio);
-}
-
 /* Allocation */
 
 static inline bool can_inc_bucket_gen(struct bucket *b)
@@ -280,7 +210,7 @@ static void invalidate_buckets_lru(struct cache *ca)
 			 * multiple times when it can't do anything
 			 */
 			ca->invalidate_needs_gc = 1;
-			bch_queue_gc(ca->set);
+			wake_up_gc(ca->set);
 			return;
 		}
 
@@ -305,7 +235,7 @@ static void invalidate_buckets_fifo(struct cache *ca)
 
 		if (++checked >= ca->sb.nbuckets) {
 			ca->invalidate_needs_gc = 1;
-			bch_queue_gc(ca->set);
+			wake_up_gc(ca->set);
 			return;
 		}
 	}
@@ -330,7 +260,7 @@ static void invalidate_buckets_random(struct cache *ca)
 
 		if (++checked >= ca->sb.nbuckets / 2) {
 			ca->invalidate_needs_gc = 1;
-			bch_queue_gc(ca->set);
+			wake_up_gc(ca->set);
 			return;
 		}
 	}
@@ -398,16 +328,18 @@ static int bch_allocator_thread(void *arg)
 			else
 				break;
 
-			allocator_wait(ca, (int) fifo_free(&ca->free) >
-				       atomic_read(&ca->discards_in_flight));
-
 			if (ca->discard) {
-				allocator_wait(ca, !list_empty(&ca->discards));
-				do_discard(ca, bucket);
-			} else {
-				fifo_push(&ca->free, bucket);
-				closure_wake_up(&ca->set->bucket_wait);
+				mutex_unlock(&ca->set->bucket_lock);
+				blkdev_issue_discard(ca->bdev,
+					bucket_to_sector(ca->set, bucket),
+					ca->sb.block_size, GFP_KERNEL, 0);
+				mutex_lock(&ca->set->bucket_lock);
 			}
+
+			allocator_wait(ca, !fifo_full(&ca->free));
+
+			fifo_push(&ca->free, bucket);
+			wake_up(&ca->set->bucket_wait);
 		}
 
 		/*
@@ -433,16 +365,40 @@ static int bch_allocator_thread(void *arg)
 	}
 }
 
-long bch_bucket_alloc(struct cache *ca, unsigned watermark, struct closure *cl)
+long bch_bucket_alloc(struct cache *ca, unsigned watermark, bool wait)
 {
-	long r = -1;
-again:
+	DEFINE_WAIT(w);
+	struct bucket *b;
+	long r;
+
+	/* fastpath */
+	if (fifo_used(&ca->free) > ca->watermark[watermark]) {
+		fifo_pop(&ca->free, r);
+		goto out;
+	}
+
+	if (!wait)
+		return -1;
+
+	while (1) {
+		if (fifo_used(&ca->free) > ca->watermark[watermark]) {
+			fifo_pop(&ca->free, r);
+			break;
+		}
+
+		prepare_to_wait(&ca->set->bucket_wait, &w,
+				TASK_UNINTERRUPTIBLE);
+
+		mutex_unlock(&ca->set->bucket_lock);
+		schedule();
+		mutex_lock(&ca->set->bucket_lock);
+	}
+
+	finish_wait(&ca->set->bucket_wait, &w);
+out:
 	wake_up_process(ca->alloc_thread);
 
-	if (fifo_used(&ca->free) > ca->watermark[watermark] &&
-	    fifo_pop(&ca->free, r)) {
-		struct bucket *b = ca->buckets + r;
-#ifdef CONFIG_BCACHE_EDEBUG
+	if (expensive_debug_checks(ca->set)) {
 		size_t iter;
 		long i;
 
@@ -455,36 +411,23 @@ again:
 			BUG_ON(i == r);
 		fifo_for_each(i, &ca->unused, iter)
 			BUG_ON(i == r);
-#endif
-		BUG_ON(atomic_read(&b->pin) != 1);
-
-		SET_GC_SECTORS_USED(b, ca->sb.bucket_size);
-
-		if (watermark <= WATERMARK_METADATA) {
-			SET_GC_MARK(b, GC_MARK_METADATA);
-			b->prio = BTREE_PRIO;
-		} else {
-			SET_GC_MARK(b, GC_MARK_RECLAIMABLE);
-			b->prio = INITIAL_PRIO;
-		}
-
-		return r;
 	}
 
-	trace_bcache_alloc_fail(ca);
+	b = ca->buckets + r;
 
-	if (cl) {
-		closure_wait(&ca->set->bucket_wait, cl);
+	BUG_ON(atomic_read(&b->pin) != 1);
 
-		if (closure_blocking(cl)) {
-			mutex_unlock(&ca->set->bucket_lock);
-			closure_sync(cl);
-			mutex_lock(&ca->set->bucket_lock);
-			goto again;
-		}
+	SET_GC_SECTORS_USED(b, ca->sb.bucket_size);
+
+	if (watermark <= WATERMARK_METADATA) {
+		SET_GC_MARK(b, GC_MARK_METADATA);
+		b->prio = BTREE_PRIO;
+	} else {
+		SET_GC_MARK(b, GC_MARK_RECLAIMABLE);
+		b->prio = INITIAL_PRIO;
 	}
 
-	return -1;
+	return r;
 }
 
 void bch_bucket_free(struct cache_set *c, struct bkey *k)
@@ -501,7 +444,7 @@ void bch_bucket_free(struct cache_set *c, struct bkey *k)
 }
 
 int __bch_bucket_alloc_set(struct cache_set *c, unsigned watermark,
-			   struct bkey *k, int n, struct closure *cl)
+			   struct bkey *k, int n, bool wait)
 {
 	int i;
 
@@ -514,7 +457,7 @@ int __bch_bucket_alloc_set(struct cache_set *c, unsigned watermark,
 
 	for (i = 0; i < n; i++) {
 		struct cache *ca = c->cache_by_alloc[i];
-		long b = bch_bucket_alloc(ca, watermark, cl);
+		long b = bch_bucket_alloc(ca, watermark, wait);
 
 		if (b == -1)
 			goto err;
@@ -529,22 +472,202 @@ int __bch_bucket_alloc_set(struct cache_set *c, unsigned watermark,
 	return 0;
 err:
 	bch_bucket_free(c, k);
-	__bkey_put(c, k);
+	bkey_put(c, k);
 	return -1;
 }
 
 int bch_bucket_alloc_set(struct cache_set *c, unsigned watermark,
-			 struct bkey *k, int n, struct closure *cl)
+			 struct bkey *k, int n, bool wait)
 {
 	int ret;
 	mutex_lock(&c->bucket_lock);
-	ret = __bch_bucket_alloc_set(c, watermark, k, n, cl);
+	ret = __bch_bucket_alloc_set(c, watermark, k, n, wait);
 	mutex_unlock(&c->bucket_lock);
 	return ret;
 }
 
+/* Sector allocator */
+
+struct open_bucket {
+	struct list_head	list;
+	unsigned		last_write_point;
+	unsigned		sectors_free;
+	BKEY_PADDED(key);
+};
+
+/*
+ * We keep multiple buckets open for writes, and try to segregate different
+ * write streams for better cache utilization: first we look for a bucket where
+ * the last write to it was sequential with the current write, and failing that
+ * we look for a bucket that was last used by the same task.
+ *
+ * The ideas is if you've got multiple tasks pulling data into the cache at the
+ * same time, you'll get better cache utilization if you try to segregate their
+ * data and preserve locality.
+ *
+ * For example, say you've starting Firefox at the same time you're copying a
+ * bunch of files. Firefox will likely end up being fairly hot and stay in the
+ * cache awhile, but the data you copied might not be; if you wrote all that
+ * data to the same buckets it'd get invalidated at the same time.
+ *
+ * Both of those tasks will be doing fairly random IO so we can't rely on
+ * detecting sequential IO to segregate their data, but going off of the task
+ * should be a sane heuristic.
+ */
+static struct open_bucket *pick_data_bucket(struct cache_set *c,
+					    const struct bkey *search,
+					    unsigned write_point,
+					    struct bkey *alloc)
+{
+	struct open_bucket *ret, *ret_task = NULL;
+
+	list_for_each_entry_reverse(ret, &c->data_buckets, list)
+		if (!bkey_cmp(&ret->key, search))
+			goto found;
+		else if (ret->last_write_point == write_point)
+			ret_task = ret;
+
+	ret = ret_task ?: list_first_entry(&c->data_buckets,
+					   struct open_bucket, list);
+found:
+	if (!ret->sectors_free && KEY_PTRS(alloc)) {
+		ret->sectors_free = c->sb.bucket_size;
+		bkey_copy(&ret->key, alloc);
+		bkey_init(alloc);
+	}
+
+	if (!ret->sectors_free)
+		ret = NULL;
+
+	return ret;
+}
+
+/*
+ * Allocates some space in the cache to write to, and k to point to the newly
+ * allocated space, and updates KEY_SIZE(k) and KEY_OFFSET(k) (to point to the
+ * end of the newly allocated space).
+ *
+ * May allocate fewer sectors than @sectors, KEY_SIZE(k) indicates how many
+ * sectors were actually allocated.
+ *
+ * If s->writeback is true, will not fail.
+ */
+bool bch_alloc_sectors(struct cache_set *c, struct bkey *k, unsigned sectors,
+		       unsigned write_point, unsigned write_prio, bool wait)
+{
+	struct open_bucket *b;
+	BKEY_PADDED(key) alloc;
+	unsigned i;
+
+	/*
+	 * We might have to allocate a new bucket, which we can't do with a
+	 * spinlock held. So if we have to allocate, we drop the lock, allocate
+	 * and then retry. KEY_PTRS() indicates whether alloc points to
+	 * allocated bucket(s).
+	 */
+
+	bkey_init(&alloc.key);
+	spin_lock(&c->data_bucket_lock);
+
+	while (!(b = pick_data_bucket(c, k, write_point, &alloc.key))) {
+		unsigned watermark = write_prio
+			? WATERMARK_MOVINGGC
+			: WATERMARK_NONE;
+
+		spin_unlock(&c->data_bucket_lock);
+
+		if (bch_bucket_alloc_set(c, watermark, &alloc.key, 1, wait))
+			return false;
+
+		spin_lock(&c->data_bucket_lock);
+	}
+
+	/*
+	 * If we had to allocate, we might race and not need to allocate the
+	 * second time we call find_data_bucket(). If we allocated a bucket but
+	 * didn't use it, drop the refcount bch_bucket_alloc_set() took:
+	 */
+	if (KEY_PTRS(&alloc.key))
+		bkey_put(c, &alloc.key);
+
+	for (i = 0; i < KEY_PTRS(&b->key); i++)
+		EBUG_ON(ptr_stale(c, &b->key, i));
+
+	/* Set up the pointer to the space we're allocating: */
+
+	for (i = 0; i < KEY_PTRS(&b->key); i++)
+		k->ptr[i] = b->key.ptr[i];
+
+	sectors = min(sectors, b->sectors_free);
+
+	SET_KEY_OFFSET(k, KEY_OFFSET(k) + sectors);
+	SET_KEY_SIZE(k, sectors);
+	SET_KEY_PTRS(k, KEY_PTRS(&b->key));
+
+	/*
+	 * Move b to the end of the lru, and keep track of what this bucket was
+	 * last used for:
+	 */
+	list_move_tail(&b->list, &c->data_buckets);
+	bkey_copy_key(&b->key, k);
+	b->last_write_point = write_point;
+
+	b->sectors_free	-= sectors;
+
+	for (i = 0; i < KEY_PTRS(&b->key); i++) {
+		SET_PTR_OFFSET(&b->key, i, PTR_OFFSET(&b->key, i) + sectors);
+
+		atomic_long_add(sectors,
+				&PTR_CACHE(c, &b->key, i)->sectors_written);
+	}
+
+	if (b->sectors_free < c->sb.block_size)
+		b->sectors_free = 0;
+
+	/*
+	 * k takes refcounts on the buckets it points to until it's inserted
+	 * into the btree, but if we're done with this bucket we just transfer
+	 * get_data_bucket()'s refcount.
+	 */
+	if (b->sectors_free)
+		for (i = 0; i < KEY_PTRS(&b->key); i++)
+			atomic_inc(&PTR_BUCKET(c, &b->key, i)->pin);
+
+	spin_unlock(&c->data_bucket_lock);
+	return true;
+}
+
 /* Init */
 
+void bch_open_buckets_free(struct cache_set *c)
+{
+	struct open_bucket *b;
+
+	while (!list_empty(&c->data_buckets)) {
+		b = list_first_entry(&c->data_buckets,
+				     struct open_bucket, list);
+		list_del(&b->list);
+		kfree(b);
+	}
+}
+
+int bch_open_buckets_alloc(struct cache_set *c)
+{
+	int i;
+
+	spin_lock_init(&c->data_bucket_lock);
+
+	for (i = 0; i < 6; i++) {
+		struct open_bucket *b = kzalloc(sizeof(*b), GFP_KERNEL);
+		if (!b)
+			return -ENOMEM;
+
+		list_add(&b->list, &c->data_buckets);
+	}
+
+	return 0;
+}
+
 int bch_cache_allocator_start(struct cache *ca)
 {
 	struct task_struct *k = kthread_run(bch_allocator_thread,
@@ -556,22 +679,8 @@ int bch_cache_allocator_start(struct cache *ca)
 	return 0;
 }
 
-void bch_cache_allocator_exit(struct cache *ca)
-{
-	struct discard *d;
-
-	while (!list_empty(&ca->discards)) {
-		d = list_first_entry(&ca->discards, struct discard, list);
-		cancel_work_sync(&d->work);
-		list_del(&d->list);
-		kfree(d);
-	}
-}
-
 int bch_cache_allocator_init(struct cache *ca)
 {
-	unsigned i;
-
 	/*
 	 * Reserve:
 	 * Prio/gen writes first
@@ -589,15 +698,5 @@ int bch_cache_allocator_init(struct cache *ca)
 	ca->watermark[WATERMARK_NONE] = ca->free.size / 2 +
 		ca->watermark[WATERMARK_MOVINGGC];
 
-	for (i = 0; i < MAX_IN_FLIGHT_DISCARDS; i++) {
-		struct discard *d = kzalloc(sizeof(*d), GFP_KERNEL);
-		if (!d)
-			return -ENOMEM;
-
-		d->ca = ca;
-		INIT_WORK(&d->work, discard_finish);
-		list_add(&d->list, &ca->discards);
-	}
-
 	return 0;
 }
diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index 0f12382aa35d..4beb55a0ff30 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -177,6 +177,7 @@
 
 #define pr_fmt(fmt) "bcache: %s() " fmt "\n", __func__
 
+#include <linux/bcache.h>
 #include <linux/bio.h>
 #include <linux/kobject.h>
 #include <linux/list.h>
@@ -210,168 +211,6 @@ BITMASK(GC_MARK,	 struct bucket, gc_mark, 0, 2);
 #define GC_MARK_METADATA	2
 BITMASK(GC_SECTORS_USED, struct bucket, gc_mark, 2, 14);
 
-struct bkey {
-	uint64_t	high;
-	uint64_t	low;
-	uint64_t	ptr[];
-};
-
-/* Enough for a key with 6 pointers */
-#define BKEY_PAD		8
-
-#define BKEY_PADDED(key)					\
-	union { struct bkey key; uint64_t key ## _pad[BKEY_PAD]; }
-
-/* Version 0: Cache device
- * Version 1: Backing device
- * Version 2: Seed pointer into btree node checksum
- * Version 3: Cache device with new UUID format
- * Version 4: Backing device with data offset
- */
-#define BCACHE_SB_VERSION_CDEV			0
-#define BCACHE_SB_VERSION_BDEV			1
-#define BCACHE_SB_VERSION_CDEV_WITH_UUID	3
-#define BCACHE_SB_VERSION_BDEV_WITH_OFFSET	4
-#define BCACHE_SB_MAX_VERSION			4
-
-#define SB_SECTOR		8
-#define SB_SIZE			4096
-#define SB_LABEL_SIZE		32
-#define SB_JOURNAL_BUCKETS	256U
-/* SB_JOURNAL_BUCKETS must be divisible by BITS_PER_LONG */
-#define MAX_CACHES_PER_SET	8
-
-#define BDEV_DATA_START_DEFAULT	16	/* sectors */
-
-struct cache_sb {
-	uint64_t		csum;
-	uint64_t		offset;	/* sector where this sb was written */
-	uint64_t		version;
-
-	uint8_t			magic[16];
-
-	uint8_t			uuid[16];
-	union {
-		uint8_t		set_uuid[16];
-		uint64_t	set_magic;
-	};
-	uint8_t			label[SB_LABEL_SIZE];
-
-	uint64_t		flags;
-	uint64_t		seq;
-	uint64_t		pad[8];
-
-	union {
-	struct {
-		/* Cache devices */
-		uint64_t	nbuckets;	/* device size */
-
-		uint16_t	block_size;	/* sectors */
-		uint16_t	bucket_size;	/* sectors */
-
-		uint16_t	nr_in_set;
-		uint16_t	nr_this_dev;
-	};
-	struct {
-		/* Backing devices */
-		uint64_t	data_offset;
-
-		/*
-		 * block_size from the cache device section is still used by
-		 * backing devices, so don't add anything here until we fix
-		 * things to not need it for backing devices anymore
-		 */
-	};
-	};
-
-	uint32_t		last_mount;	/* time_t */
-
-	uint16_t		first_bucket;
-	union {
-		uint16_t	njournal_buckets;
-		uint16_t	keys;
-	};
-	uint64_t		d[SB_JOURNAL_BUCKETS];	/* journal buckets */
-};
-
-BITMASK(CACHE_SYNC,		struct cache_sb, flags, 0, 1);
-BITMASK(CACHE_DISCARD,		struct cache_sb, flags, 1, 1);
-BITMASK(CACHE_REPLACEMENT,	struct cache_sb, flags, 2, 3);
-#define CACHE_REPLACEMENT_LRU	0U
-#define CACHE_REPLACEMENT_FIFO	1U
-#define CACHE_REPLACEMENT_RANDOM 2U
-
-BITMASK(BDEV_CACHE_MODE,	struct cache_sb, flags, 0, 4);
-#define CACHE_MODE_WRITETHROUGH	0U
-#define CACHE_MODE_WRITEBACK	1U
-#define CACHE_MODE_WRITEAROUND	2U
-#define CACHE_MODE_NONE		3U
-BITMASK(BDEV_STATE,		struct cache_sb, flags, 61, 2);
-#define BDEV_STATE_NONE		0U
-#define BDEV_STATE_CLEAN	1U
-#define BDEV_STATE_DIRTY	2U
-#define BDEV_STATE_STALE	3U
-
-/* Version 1: Seed pointer into btree node checksum
- */
-#define BCACHE_BSET_VERSION	1
-
-/*
- * This is the on disk format for btree nodes - a btree node on disk is a list
- * of these; within each set the keys are sorted
- */
-struct bset {
-	uint64_t		csum;
-	uint64_t		magic;
-	uint64_t		seq;
-	uint32_t		version;
-	uint32_t		keys;
-
-	union {
-		struct bkey	start[0];
-		uint64_t	d[0];
-	};
-};
-
-/*
- * On disk format for priorities and gens - see super.c near prio_write() for
- * more.
- */
-struct prio_set {
-	uint64_t		csum;
-	uint64_t		magic;
-	uint64_t		seq;
-	uint32_t		version;
-	uint32_t		pad;
-
-	uint64_t		next_bucket;
-
-	struct bucket_disk {
-		uint16_t	prio;
-		uint8_t		gen;
-	} __attribute((packed)) data[];
-};
-
-struct uuid_entry {
-	union {
-		struct {
-			uint8_t		uuid[16];
-			uint8_t		label[32];
-			uint32_t	first_reg;
-			uint32_t	last_reg;
-			uint32_t	invalidated;
-
-			uint32_t	flags;
-			/* Size of flash only volumes */
-			uint64_t	sectors;
-		};
-
-		uint8_t	pad[128];
-	};
-};
-
-BITMASK(UUID_FLASH_ONLY,	struct uuid_entry, flags, 0, 1);
-
 #include "journal.h"
 #include "stats.h"
 struct search;
@@ -384,8 +223,6 @@ struct keybuf_key {
 	void			*private;
 };
 
-typedef bool (keybuf_pred_fn)(struct keybuf *, struct bkey *);
-
 struct keybuf {
 	struct bkey		last_scanned;
 	spinlock_t		lock;
@@ -400,7 +237,7 @@ struct keybuf {
 
 	struct rb_root		keys;
 
-#define KEYBUF_NR		100
+#define KEYBUF_NR		500
 	DECLARE_ARRAY_ALLOCATOR(struct keybuf_key, freelist, KEYBUF_NR);
 };
 
@@ -429,16 +266,15 @@ struct bcache_device {
 
 	struct gendisk		*disk;
 
-	/* If nonzero, we're closing */
-	atomic_t		closing;
-
-	/* If nonzero, we're detaching/unregistering from cache set */
-	atomic_t		detaching;
-	int			flush_done;
+	unsigned long		flags;
+#define BCACHE_DEV_CLOSING	0
+#define BCACHE_DEV_DETACHING	1
+#define BCACHE_DEV_UNLINK_DONE	2
 
-	uint64_t		nr_stripes;
-	unsigned		stripe_size_bits;
+	unsigned		nr_stripes;
+	unsigned		stripe_size;
 	atomic_t		*stripe_sectors_dirty;
+	unsigned long		*full_dirty_stripes;
 
 	unsigned long		sectors_dirty_last;
 	long			sectors_dirty_derivative;
@@ -509,7 +345,7 @@ struct cached_dev {
 
 	/* Limit number of writeback bios in flight */
 	struct semaphore	in_flight;
-	struct closure_with_timer writeback;
+	struct task_struct	*writeback_thread;
 
 	struct keybuf		writeback_keys;
 
@@ -527,8 +363,8 @@ struct cached_dev {
 	unsigned		sequential_cutoff;
 	unsigned		readahead;
 
-	unsigned		sequential_merge:1;
 	unsigned		verify:1;
+	unsigned		bypass_torture_test:1;
 
 	unsigned		partial_stripes_expensive:1;
 	unsigned		writeback_metadata:1;
@@ -620,15 +456,6 @@ struct cache {
 
 	bool			discard; /* Get rid of? */
 
-	/*
-	 * We preallocate structs for issuing discards to buckets, and keep them
-	 * on this list when they're not in use; do_discard() issues discards
-	 * whenever there's work to do and is called by free_some_buckets() and
-	 * when a discard finishes.
-	 */
-	atomic_t		discards_in_flight;
-	struct list_head	discards;
-
 	struct journal_device	journal;
 
 	/* The rest of this all shows up in sysfs */
@@ -649,7 +476,6 @@ struct gc_stat {
 
 	size_t			nkeys;
 	uint64_t		data;	/* sectors */
-	uint64_t		dirty;	/* sectors */
 	unsigned		in_use; /* percent */
 };
 
@@ -744,8 +570,8 @@ struct cache_set {
 	 * basically a lock for this that we can wait on asynchronously. The
 	 * btree_root() macro releases the lock when it returns.
 	 */
-	struct closure		*try_harder;
-	struct closure_waitlist	try_wait;
+	struct task_struct	*try_harder;
+	wait_queue_head_t	try_wait;
 	uint64_t		try_harder_start;
 
 	/*
@@ -759,7 +585,7 @@ struct cache_set {
 	 * written.
 	 */
 	atomic_t		prio_blocked;
-	struct closure_waitlist	bucket_wait;
+	wait_queue_head_t	bucket_wait;
 
 	/*
 	 * For any bio we don't skip we subtract the number of sectors from
@@ -782,7 +608,7 @@ struct cache_set {
 	struct gc_stat		gc_stats;
 	size_t			nbuckets;
 
-	struct closure_with_waitlist gc;
+	struct task_struct	*gc_thread;
 	/* Where in the btree gc currently is */
 	struct bkey		gc_done;
 
@@ -795,11 +621,10 @@ struct cache_set {
 	/* Counts how many sectors bio_insert has added to the cache */
 	atomic_t		sectors_to_gc;
 
-	struct closure		moving_gc;
-	struct closure_waitlist	moving_gc_wait;
+	wait_queue_head_t	moving_gc_wait;
 	struct keybuf		moving_gc_keys;
 	/* Number of moving GC bios in flight */
-	atomic_t		in_flight;
+	struct semaphore	moving_in_flight;
 
 	struct btree		*root;
 
@@ -841,22 +666,27 @@ struct cache_set {
 	unsigned		congested_read_threshold_us;
 	unsigned		congested_write_threshold_us;
 
-	spinlock_t		sort_time_lock;
 	struct time_stats	sort_time;
 	struct time_stats	btree_gc_time;
 	struct time_stats	btree_split_time;
-	spinlock_t		btree_read_time_lock;
 	struct time_stats	btree_read_time;
 	struct time_stats	try_harder_time;
 
 	atomic_long_t		cache_read_races;
 	atomic_long_t		writeback_keys_done;
 	atomic_long_t		writeback_keys_failed;
+
+	enum			{
+		ON_ERROR_UNREGISTER,
+		ON_ERROR_PANIC,
+	}			on_error;
 	unsigned		error_limit;
 	unsigned		error_decay;
+
 	unsigned short		journal_delay_ms;
 	unsigned		verify:1;
 	unsigned		key_merging_disabled:1;
+	unsigned		expensive_debug_checks:1;
 	unsigned		gc_always_rewrite:1;
 	unsigned		shrinker_disabled:1;
 	unsigned		copy_gc_enabled:1;
@@ -865,21 +695,6 @@ struct cache_set {
 	struct hlist_head	bucket_hash[1 << BUCKET_HASH_BITS];
 };
 
-static inline bool key_merging_disabled(struct cache_set *c)
-{
-#ifdef CONFIG_BCACHE_DEBUG
-	return c->key_merging_disabled;
-#else
-	return 0;
-#endif
-}
-
-static inline bool SB_IS_BDEV(const struct cache_sb *sb)
-{
-	return sb->version == BCACHE_SB_VERSION_BDEV
-		|| sb->version == BCACHE_SB_VERSION_BDEV_WITH_OFFSET;
-}
-
 struct bbio {
 	unsigned		submit_time_us;
 	union {
@@ -933,59 +748,6 @@ static inline unsigned local_clock_us(void)
 #define prio_buckets(c)					\
 	DIV_ROUND_UP((size_t) (c)->sb.nbuckets, prios_per_bucket(c))
 
-#define JSET_MAGIC		0x245235c1a3625032ULL
-#define PSET_MAGIC		0x6750e15f87337f91ULL
-#define BSET_MAGIC		0x90135c78b99e07f5ULL
-
-#define jset_magic(c)		((c)->sb.set_magic ^ JSET_MAGIC)
-#define pset_magic(c)		((c)->sb.set_magic ^ PSET_MAGIC)
-#define bset_magic(c)		((c)->sb.set_magic ^ BSET_MAGIC)
-
-/* Bkey fields: all units are in sectors */
-
-#define KEY_FIELD(name, field, offset, size)				\
-	BITMASK(name, struct bkey, field, offset, size)
-
-#define PTR_FIELD(name, offset, size)					\
-	static inline uint64_t name(const struct bkey *k, unsigned i)	\
-	{ return (k->ptr[i] >> offset) & ~(((uint64_t) ~0) << size); }	\
-									\
-	static inline void SET_##name(struct bkey *k, unsigned i, uint64_t v)\
-	{								\
-		k->ptr[i] &= ~(~((uint64_t) ~0 << size) << offset);	\
-		k->ptr[i] |= v << offset;				\
-	}
-
-KEY_FIELD(KEY_PTRS,	high, 60, 3)
-KEY_FIELD(HEADER_SIZE,	high, 58, 2)
-KEY_FIELD(KEY_CSUM,	high, 56, 2)
-KEY_FIELD(KEY_PINNED,	high, 55, 1)
-KEY_FIELD(KEY_DIRTY,	high, 36, 1)
-
-KEY_FIELD(KEY_SIZE,	high, 20, 16)
-KEY_FIELD(KEY_INODE,	high, 0,  20)
-
-/* Next time I change the on disk format, KEY_OFFSET() won't be 64 bits */
-
-static inline uint64_t KEY_OFFSET(const struct bkey *k)
-{
-	return k->low;
-}
-
-static inline void SET_KEY_OFFSET(struct bkey *k, uint64_t v)