[Bcache v15 10/16] bcache: Superblock/initialization/sysfs code

[Kent Overstreet]

Signed-off-by: Kent Overstreet <koverstreet@xxxxxxxxxx>
---
 drivers/md/bcache/stats.c |  245 ++++++
 drivers/md/bcache/stats.h |   58 ++
 drivers/md/bcache/super.c | 1992 +++++++++++++++++++++++++++++++++++++++++++++
 drivers/md/bcache/sysfs.c |  812 ++++++++++++++++++
 drivers/md/bcache/sysfs.h |   91 ++
 5 files changed, 3198 insertions(+), 0 deletions(-)
 create mode 100644 drivers/md/bcache/stats.c
 create mode 100644 drivers/md/bcache/stats.h
 create mode 100644 drivers/md/bcache/super.c
 create mode 100644 drivers/md/bcache/sysfs.c
 create mode 100644 drivers/md/bcache/sysfs.h

diff --git a/drivers/md/bcache/stats.c b/drivers/md/bcache/stats.c
new file mode 100644
index 0000000..3c9e4ab
--- /dev/null
+++ b/drivers/md/bcache/stats.c
@@ -0,0 +1,245 @@
+#include "bcache.h"
+#include "stats.h"
+#include "btree.h"
+#include "request.h"
+#include "sysfs.h"
+
+/* We keep absolute totals of various statistics, and addionally a set of three
+ * rolling averages.
+ *
+ * Every so often, a timer goes off and rescales the rolling averages.
+ * accounting_rescale[] is how many times the timer has to go off before we
+ * rescale each set of numbers; that gets us half lives of 5 minutes, one hour,
+ * and one day.
+ *
+ * accounting_delay is how often the timer goes off - 22 times in 5 minutes,
+ * and accounting_weight is what we use to rescale:
+ *
+ * pow(31 / 32, 22) ~= 1/2
+ *
+ * So that we don't have to increment each set of numbers every time we (say)
+ * get a cache hit, we increment a single atomic_t in acc->collector, and when
+ * the rescale function runs it resets the atomic counter to 0 and adds its
+ * old value to each of the exported numbers.
+ *
+ * To reduce rounding error, the numbers in struct cache_stats are all
+ * stored left shifted by 16, and scaled back in the sysfs show() function.
+ */
+
+static const unsigned DAY_RESCALE		= 288;
+static const unsigned HOUR_RESCALE		= 12;
+static const unsigned FIVE_MINUTE_RESCALE	= 1;
+static const unsigned accounting_delay		= (HZ * 300) / 22;
+static const unsigned accounting_weight		= 32;
+
+/* sysfs reading/writing */
+
+read_attribute(cache_hits);
+read_attribute(cache_misses);
+read_attribute(cache_bypass_hits);
+read_attribute(cache_bypass_misses);
+read_attribute(cache_hit_ratio);
+read_attribute(cache_readaheads);
+read_attribute(cache_miss_collisions);
+read_attribute(bypassed);
+
+static struct attribute *accounting_files[] = {
+	&sysfs_cache_hits,
+	&sysfs_cache_misses,
+	&sysfs_cache_bypass_hits,
+	&sysfs_cache_bypass_misses,
+	&sysfs_cache_hit_ratio,
+	&sysfs_cache_readaheads,
+	&sysfs_cache_miss_collisions,
+	&sysfs_bypassed,
+	NULL
+};
+
+static ssize_t cache_stats_show(struct kobject *kobj,
+				struct attribute *attr,
+			      char *buf) {
+	struct cache_stats *s =
+		container_of(kobj, struct cache_stats, kobj);
+#define var(stat)		(s->stat >> 16)
+	var_print(cache_hits);
+	var_print(cache_misses);
+	var_print(cache_bypass_hits);
+	var_print(cache_bypass_misses);
+
+	sysfs_print(cache_hit_ratio,
+		    DIV_SAFE(var(cache_hits) * 100,
+			     var(cache_hits) + var(cache_misses)));
+
+	var_print(cache_readaheads);
+	var_print(cache_miss_collisions);
+	sysfs_printf(bypassed,	"%hli", var(sectors_bypassed) << 9);
+#undef var
+	return 0;
+}
+
+/* kobjects */
+
+static void unregister_fake(struct kobject *k)
+{
+}
+
+static const struct sysfs_ops accounting_ops = {
+	.show = cache_stats_show,
+	.store = NULL
+};
+static struct kobj_type accounting_obj = {
+	.release = unregister_fake,
+	.sysfs_ops = &accounting_ops,
+	.default_attrs = accounting_files
+};
+
+static void scale_accounting(unsigned long data);
+
+void bch_cache_accounting_init(struct cache_accounting *acc, struct closure *parent)
+{
+	kobject_init(&acc->total.kobj,		&accounting_obj);
+	kobject_init(&acc->five_minute.kobj,	&accounting_obj);
+	kobject_init(&acc->hour.kobj,		&accounting_obj);
+	kobject_init(&acc->day.kobj,		&accounting_obj);
+
+	closure_init(&acc->cl, parent);
+	init_timer(&acc->timer);
+	acc->timer.expires	= jiffies + accounting_delay;
+	acc->timer.data		= (unsigned long) acc;
+	acc->timer.function	= scale_accounting;
+	add_timer(&acc->timer);
+}
+
+int bch_cache_accounting_add_kobjs(struct cache_accounting *acc,
+				   struct kobject *parent)
+{
+	int ret = kobject_add(&acc->total.kobj, parent,
+			      "stats_total");
+	ret = ret ?: kobject_add(&acc->five_minute.kobj, parent,
+				 "stats_five_minute");
+	ret = ret ?: kobject_add(&acc->hour.kobj, parent,
+				 "stats_hour");
+	ret = ret ?: kobject_add(&acc->day.kobj, parent,
+				 "stats_day");
+	return ret;
+}
+
+void bch_cache_accounting_clear(struct cache_accounting *acc)
+{
+	memset(&acc->total.cache_hits,
+	       0,
+	       sizeof(unsigned long) * 7);
+}
+
+void bch_cache_accounting_destroy(struct cache_accounting *acc)
+{
+	kobject_put(&acc->total.kobj);
+	kobject_put(&acc->five_minute.kobj);
+	kobject_put(&acc->hour.kobj);
+	kobject_put(&acc->day.kobj);
+
+	atomic_set(&acc->closing, 1);
+	if (del_timer_sync(&acc->timer))
+		closure_return(&acc->cl);
+}
+
+/* EWMA scaling */
+
+static void scale_stat(unsigned long *stat)
+{
+	*stat =  ewma_add(*stat, 0, accounting_weight, 0);
+}
+
+static void scale_stats(struct cache_stats *stats, unsigned long rescale_at)
+{
+	if (++stats->rescale == rescale_at) {
+		stats->rescale = 0;
+		scale_stat(&stats->cache_hits);
+		scale_stat(&stats->cache_misses);
+		scale_stat(&stats->cache_bypass_hits);
+		scale_stat(&stats->cache_bypass_misses);
+		scale_stat(&stats->cache_readaheads);
+		scale_stat(&stats->cache_miss_collisions);
+		scale_stat(&stats->sectors_bypassed);
+	}
+}
+
+static void scale_accounting(unsigned long data)
+{
+	struct cache_accounting *acc = (struct cache_accounting *) data;
+
+#define move_stat(name) do {						\
+	unsigned long t = atomic_xchg(&acc->collector.name, 0);		\
+	t <<= 16;							\
+	acc->five_minute.name += t;					\
+	acc->hour.name += t;						\
+	acc->day.name += t;						\
+	acc->total.name += t;						\
+} while (0)
+
+	move_stat(cache_hits);
+	move_stat(cache_misses);
+	move_stat(cache_bypass_hits);
+	move_stat(cache_bypass_misses);
+	move_stat(cache_readaheads);
+	move_stat(cache_miss_collisions);
+	move_stat(sectors_bypassed);
+
+	scale_stats(&acc->total, 0);
+	scale_stats(&acc->day, DAY_RESCALE);
+	scale_stats(&acc->hour, HOUR_RESCALE);
+	scale_stats(&acc->five_minute, FIVE_MINUTE_RESCALE);
+
+	acc->timer.expires += accounting_delay;
+
+	if (!atomic_read(&acc->closing))
+		add_timer(&acc->timer);
+	else
+		closure_return(&acc->cl);
+}
+
+static void mark_cache_stats(struct cache_stat_collector *stats,
+			     bool hit, bool bypass)
+{
+	if (!bypass)
+		if (hit)
+			atomic_inc(&stats->cache_hits);
+		else
+			atomic_inc(&stats->cache_misses);
+	else
+		if (hit)
+			atomic_inc(&stats->cache_bypass_hits);
+		else
+			atomic_inc(&stats->cache_bypass_misses);
+}
+
+void bch_mark_cache_accounting(struct search *s, bool hit, bool bypass)
+{
+	struct cached_dev *dc = container_of(s->d, struct cached_dev, disk);
+	mark_cache_stats(&dc->accounting.collector, hit, bypass);
+	mark_cache_stats(&s->op.c->accounting.collector, hit, bypass);
+#ifdef CONFIG_CGROUP_BCACHE
+	mark_cache_stats(&(bch_bio_to_cgroup(s->orig_bio)->stats), hit, bypass);
+#endif
+}
+
+void bch_mark_cache_readahead(struct search *s)
+{
+	struct cached_dev *dc = container_of(s->d, struct cached_dev, disk);
+	atomic_inc(&dc->accounting.collector.cache_readaheads);
+	atomic_inc(&s->op.c->accounting.collector.cache_readaheads);
+}
+
+void bch_mark_cache_miss_collision(struct search *s)
+{
+	struct cached_dev *dc = container_of(s->d, struct cached_dev, disk);
+	atomic_inc(&dc->accounting.collector.cache_miss_collisions);
+	atomic_inc(&s->op.c->accounting.collector.cache_miss_collisions);
+}
+
+void bch_mark_sectors_bypassed(struct search *s, int sectors)
+{
+	struct cached_dev *dc = container_of(s->d, struct cached_dev, disk);
+	atomic_add(sectors, &dc->accounting.collector.sectors_bypassed);
+	atomic_add(sectors, &s->op.c->accounting.collector.sectors_bypassed);
+}
diff --git a/drivers/md/bcache/stats.h b/drivers/md/bcache/stats.h
new file mode 100644
index 0000000..c7c7a8f
--- /dev/null
+++ b/drivers/md/bcache/stats.h
@@ -0,0 +1,58 @@
+#ifndef _BCACHE_STATS_H_
+#define _BCACHE_STATS_H_
+
+struct cache_stat_collector {
+	atomic_t cache_hits;
+	atomic_t cache_misses;
+	atomic_t cache_bypass_hits;
+	atomic_t cache_bypass_misses;
+	atomic_t cache_readaheads;
+	atomic_t cache_miss_collisions;
+	atomic_t sectors_bypassed;
+};
+
+struct cache_stats {
+	struct kobject		kobj;
+
+	unsigned long cache_hits;
+	unsigned long cache_misses;
+	unsigned long cache_bypass_hits;
+	unsigned long cache_bypass_misses;
+	unsigned long cache_readaheads;
+	unsigned long cache_miss_collisions;
+	unsigned long sectors_bypassed;
+
+	unsigned		rescale;
+};
+
+struct cache_accounting {
+	struct closure		cl;
+	struct timer_list	timer;
+	atomic_t		closing;
+
+	struct cache_stat_collector collector;
+
+	struct cache_stats total;
+	struct cache_stats five_minute;
+	struct cache_stats hour;
+	struct cache_stats day;
+};
+
+struct search;
+
+void bch_cache_accounting_init(struct cache_accounting *acc,
+			       struct closure *parent);
+
+int bch_cache_accounting_add_kobjs(struct cache_accounting *acc,
+				   struct kobject *parent);
+
+void bch_cache_accounting_clear(struct cache_accounting *acc);
+
+void bch_cache_accounting_destroy(struct cache_accounting *acc);
+
+void bch_mark_cache_accounting(struct search *s, bool hit, bool bypass);
+void bch_mark_cache_readahead(struct search *s);
+void bch_mark_cache_miss_collision(struct search *s);
+void bch_mark_sectors_bypassed(struct search *s, int sectors);
+
+#endif /* _BCACHE_STATS_H_ */
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
new file mode 100644
index 0000000..32ed111
--- /dev/null
+++ b/drivers/md/bcache/super.c
@@ -0,0 +1,1992 @@
+
+#include "bcache.h"
+#include "btree.h"
+#include "debug.h"
+#include "request.h"
+#include "sysfs.h"
+
+#include <linux/buffer_head.h>
+#include <linux/debugfs.h>
+#include <linux/genhd.h>
+#include <linux/module.h>
+#include <linux/random.h>
+#include <linux/reboot.h>
+#include <linux/sort.h>
+#include <linux/sysfs.h>
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Kent Overstreet <kent.overstreet@xxxxxxxxx>");
+
+static const char bcache_magic[] = {
+	0xc6, 0x85, 0x73, 0xf6, 0x4e, 0x1a, 0x45, 0xca,
+	0x82, 0x65, 0xf5, 0x7f, 0x48, 0xba, 0x6d, 0x81
+};
+
+static const char invalid_uuid[] = {
+	0xa0, 0x3e, 0xf8, 0xed, 0x3e, 0xe1, 0xb8, 0x78,
+	0xc8, 0x50, 0xfc, 0x5e, 0xcb, 0x16, 0xcd, 0x99
+};
+
+/* Default is -1; we skip past it for struct cached_dev's cache mode */
+const char * const bch_cache_modes[] = {
+	"default",
+	"writethrough",
+	"writeback",
+	"writearound",
+	"none",
+	NULL
+};
+
+static const char * const cache_replacement_policies[] = {
+	"lru",
+	"fifo",
+	"random",
+	NULL
+};
+
+struct uuid_entry_v0 {
+	uint8_t		uuid[16];
+	uint8_t		label[32];
+	uint32_t	first_reg;
+	uint32_t	last_reg;
+	uint32_t	invalidated;
+	uint32_t	pad;
+};
+
+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);
+
+/* We keep absolute totals of various statistics, and addionally a set of three
+ * rolling averages.
+ *
+ * Every so often, a timer goes off and rescales the rolling averages.
+ * accounting_rescale[] is how many times the timer has to go off before we
+ * rescale each set of numbers; that gets us half lives of 5 minutes, one hour,
+ * and one day.
+ *
+ * accounting_delay is how often the timer goes off - 22 times in 5 minutes,
+ * and accounting_weight is what we use to rescale:
+ *
+ * pow(31 / 32, 22) ~= 1/2
+ *
+ * So that we don't have to increment each set of numbers every time we (say)
+ * get a cache hit, we increment a single atomic_t and when the rescale
+ * function it runs it resets the atomic counter to 0 and adds its old value to
+ * each of the exported numbers.
+ *
+ * To reduce rounding error, the numbers in struct cache_accounting are all
+ * stored left shifted by 16, and scaled back in the sysfs show() function.
+ */
+
+static const unsigned accounting_rescale[]	= { 0, 1, 12, 288 };
+static const unsigned accounting_delay		= (HZ * 300) / 22;
+static const unsigned accounting_weight		= 32;
+
+static const char * const accounting_types[]	= {
+	"total", "five_minute", "hour", "day" };
+
+static struct kobject *bcache_kobj;
+static struct mutex register_lock;
+static LIST_HEAD(uncached_devices);
+static LIST_HEAD(cache_sets);
+static int bcache_major, bcache_minor;
+static wait_queue_head_t unregister_wait;
+
+struct workqueue_struct *bcache_wq;
+
+static int uuid_write(struct cache_set *);
+static void bcache_device_stop(struct bcache_device *);
+
+static void __cached_dev_free(struct kobject *);
+static void cached_dev_run(struct cached_dev *);
+static int cached_dev_attach(struct cached_dev *, struct cache_set *);
+static void cached_dev_detach(struct cached_dev *);
+
+static void __flash_dev_free(struct kobject *);
+static int flash_dev_create(struct cache_set *c, uint64_t size);
+
+static void __cache_set_free(struct kobject *);
+static void cache_set_unregister(struct cache_set *);
+static void cache_set_stop(struct cache_set *);
+static void bcache_write_super(struct cache_set *);
+
+static void cache_free(struct kobject *);
+
+#include "sysfs.c"
+
+#define BTREE_MAX_PAGES		(256 * 1024 / PAGE_SIZE)
+
+/* Superblock */
+
+static const char *read_super(struct cache_sb *sb, struct block_device *bdev,
+			      struct page **res)
+{
+	const char *err;
+	struct cache_sb *s;
+	struct buffer_head *bh = __bread(bdev, 1, SB_SIZE);
+
+	if (!bh)
+		return "IO error";
+
+	s = (struct cache_sb *) bh->b_data;
+
+	sb->offset		= le64_to_cpu(s->offset);
+	sb->version		= le64_to_cpu(s->version);
+
+	memcpy(sb->magic,	s->magic, 16);
+	memcpy(sb->uuid,	s->uuid, 16);
+	memcpy(sb->set_uuid,	s->set_uuid, 16);
+	memcpy(sb->label,	s->label, SB_LABEL_SIZE);
+
+	sb->flags		= le64_to_cpu(s->flags);
+	sb->seq			= le64_to_cpu(s->seq);
+
+	sb->nbuckets		= le64_to_cpu(s->nbuckets);
+	sb->block_size		= le16_to_cpu(s->block_size);
+	sb->bucket_size		= le16_to_cpu(s->bucket_size);
+
+	sb->nr_in_set		= le16_to_cpu(s->nr_in_set);
+	sb->nr_this_dev		= le16_to_cpu(s->nr_this_dev);
+	sb->last_mount		= le32_to_cpu(s->last_mount);
+
+	sb->first_bucket	= le16_to_cpu(s->first_bucket);
+	sb->keys		= le16_to_cpu(s->keys);
+
+	for (int i = 0; i < SB_JOURNAL_BUCKETS; i++)
+		sb->d[i] = le64_to_cpu(s->d[i]);
+
+	pr_debug("read sb version %llu, flags %llu, seq %llu, journal size %u",
+		 sb->version, sb->flags, sb->seq, sb->keys);
+
+	err = "Not a bcache superblock";
+	if (sb->offset != SB_SECTOR)
+		goto err;
+
+	if (memcmp(sb->magic, bcache_magic, 16))
+		goto err;
+
+	err = "Too many journal buckets";
+	if (sb->keys > SB_JOURNAL_BUCKETS)
+		goto err;
+
+	err = "Bad checksum";
+	if (s->csum != csum_set(s))
+		goto err;
+
+	err = "Bad UUID";
+	if (is_zero(sb->uuid, 16))
+		goto err;
+
+	err = "Unsupported superblock version";
+	if (sb->version > BCACHE_SB_VERSION)
+		goto err;
+
+	err = "Bad block/bucket size";
+	if (!is_power_of_2(sb->block_size) || sb->block_size > PAGE_SECTORS ||
+	    !is_power_of_2(sb->bucket_size) || sb->bucket_size < PAGE_SECTORS)
+		goto err;
+
+	err = "Too many buckets";
+	if (sb->nbuckets > LONG_MAX)
+		goto err;
+
+	err = "Not enough buckets";
+	if (sb->nbuckets < 1 << 7)
+		goto err;
+
+	err = "Invalid superblock: device too small";
+	if (get_capacity(bdev->bd_disk) < sb->bucket_size * sb->nbuckets)
+		goto err;
+
+	if (sb->version == CACHE_BACKING_DEV)
+		goto out;
+
+	err = "Bad UUID";
+	if (is_zero(sb->set_uuid, 16))
+		goto err;
+
+	err = "Bad cache device number in set";
+	if (!sb->nr_in_set ||
+	    sb->nr_in_set <= sb->nr_this_dev ||
+	    sb->nr_in_set > MAX_CACHES_PER_SET)
+		goto err;
+
+	err = "Journal buckets not sequential";
+	for (unsigned i = 0; i < sb->keys; i++)
+		if (sb->d[i] != sb->first_bucket + i)
+			goto err;
+
+	err = "Too many journal buckets";
+	if (sb->first_bucket + sb->keys > sb->nbuckets)
+		goto err;
+
+	err = "Invalid superblock: first bucket comes before end of super";
+	if (sb->first_bucket * sb->bucket_size < 16)
+		goto err;
+out:
+	sb->last_mount = get_seconds();
+	err = NULL;
+
+	get_page(bh->b_page);
+	*res = bh->b_page;
+err:
+	put_bh(bh);
+	return err;
+}
+
+static void write_bdev_super_endio(struct bio *bio, int error)
+{
+	struct cached_dev *dc = bio->bi_private;
+	/* XXX: error checking */
+
+	closure_put(&dc->sb_write.cl);
+}
+
+static void __write_super(struct cache_sb *sb, struct bio *bio)
+{
+	struct cache_sb *out = page_address(bio->bi_io_vec[0].bv_page);
+
+	bio->bi_sector	= SB_SECTOR;
+	bio->bi_rw	= REQ_SYNC|REQ_META;
+	bio->bi_size	= SB_SIZE;
+	bio_map(bio, NULL);
+
+	out->offset		= cpu_to_le64(sb->offset);
+	out->version		= cpu_to_le64(sb->version);
+
+	memcpy(out->uuid,	sb->uuid, 16);
+	memcpy(out->set_uuid,	sb->set_uuid, 16);
+	memcpy(out->label,	sb->label, SB_LABEL_SIZE);
+
+	out->flags		= cpu_to_le64(sb->flags);
+	out->seq		= cpu_to_le64(sb->seq);
+
+	out->last_mount		= cpu_to_le32(sb->last_mount);
+	out->first_bucket	= cpu_to_le16(sb->first_bucket);
+	out->keys		= cpu_to_le16(sb->keys);
+
+	for (int i = 0; i < sb->keys; i++)
+		out->d[i] = cpu_to_le64(sb->d[i]);
+
+	out->csum = csum_set(out);
+
+	pr_debug("ver %llu, flags %llu, seq %llu",
+		 sb->version, sb->flags, sb->seq);
+
+	submit_bio(REQ_WRITE, bio);
+}
+
+void bch_write_bdev_super(struct cached_dev *dc, struct closure *parent)
+{
+	struct closure *cl = &dc->sb_write.cl;
+	struct bio *bio = &dc->sb_bio;
+
+	closure_lock(&dc->sb_write, parent);
+
+	bio_reset(bio);
+	bio->bi_bdev	= dc->bdev;
+	bio->bi_end_io	= write_bdev_super_endio;
+	bio->bi_private = dc;
+
+	closure_get(cl);
+	__write_super(&dc->sb, bio);
+
+	closure_return(cl);
+}
+
+static void write_super_endio(struct bio *bio, int error)
+{
+	struct cache *ca = bio->bi_private;
+
+	bch_count_io_errors(ca, error, "writing superblock");
+	closure_put(&ca->set->sb_write.cl);
+}
+
+static void bcache_write_super(struct cache_set *c)
+{
+	struct closure *cl = &c->sb_write.cl;
+	struct cache *ca;
+
+	closure_lock(&c->sb_write, &c->cl);
+
+	c->sb.seq++;
+
+	for_each_cache(ca, c) {
+		struct bio *bio = &ca->sb_bio;
+
+		ca->sb.version		= BCACHE_SB_VERSION;
+		ca->sb.seq		= c->sb.seq;
+		ca->sb.last_mount	= c->sb.last_mount;
+
+		SET_CACHE_SYNC(&ca->sb, CACHE_SYNC(&c->sb));
+
+		bio_reset(bio);
+		bio->bi_bdev	= ca->bdev;
+		bio->bi_end_io	= write_super_endio;
+		bio->bi_private = ca;
+
+		closure_get(cl);
+		__write_super(&ca->sb, bio);
+	}
+
+	closure_return(cl);
+}
+
+/* UUID io */
+
+static void uuid_endio(struct bio *bio, int error)
+{
+	struct closure *cl = bio->bi_private;
+	struct cache_set *c = container_of(cl, struct cache_set, uuid_write.cl);
+
+	cache_set_err_on(error, c, "accessing uuids");
+	bch_bbio_free(bio, c);
+	closure_put(cl);
+}
+
+static void uuid_io(struct cache_set *c, unsigned long rw,
+		    struct bkey *k, struct closure *parent)
+{
+	struct closure *cl = &c->uuid_write.cl;
+
+	BUG_ON(!parent);
+	closure_lock(&c->uuid_write, parent);
+
+	for (unsigned i = 0; i < KEY_PTRS(k); i++) {
+		struct bio *bio = bch_bbio_alloc(c);
+
+		bio->bi_rw	= REQ_SYNC|REQ_META|rw;
+		bio->bi_size	= KEY_SIZE(k) << 9;
+
+		bio->bi_end_io	= uuid_endio;
+		bio->bi_private = cl;
+		bio_map(bio, c->uuids);
+
+		bch_submit_bbio(bio, c, k, i);
+
+		if (!(rw & WRITE))
+			break;
+	}
+
+	pr_debug("%s UUIDs at %s", rw & REQ_WRITE ? "wrote" : "read",
+		 pkey(&c->uuid_bucket));
+
+	for (struct uuid_entry *u = c->uuids; u < c->uuids + c->nr_uuids; u++)
+		if (!is_zero(u->uuid, 16))
+			pr_debug("Slot %zi: %pU: %s: 1st: %u last: %u inv: %u",
+				 u - c->uuids, u->uuid, u->label,
+				 u->first_reg, u->last_reg, u->invalidated);
+
+	closure_return(cl);
+}
+
+static char *uuid_read(struct cache_set *c, struct jset *j, struct closure *cl)
+{
+	struct bkey *k = &j->uuid_bucket;
+
+	if (__bch_ptr_invalid(c, 1, k))
+		return "bad uuid pointer";
+
+	bkey_copy(&c->uuid_bucket, k);
+	uuid_io(c, READ_SYNC, k, cl);
+
+	if (j->version < BCACHE_JSET_VERSION_UUIDv1) {
+		struct uuid_entry_v0	*u0 = (void *) c->uuids;
+		struct uuid_entry	*u1 = (void *) c->uuids;
+
+		closure_sync(cl);
+
+		/*
+		 * Since the new uuid entry is bigger than the old, we have to
+		 * convert starting at the highest memory address and work down
+		 * in order to do it in place
+		 */
+
+		for (int i = c->nr_uuids - 1;
+		     i >= 0;
+		     --i) {
+			memcpy(u1[i].uuid,	u0[i].uuid, 16);
+			memcpy(u1[i].label,	u0[i].label, 32);
+
+			u1[i].first_reg		= u0[i].first_reg;
+			u1[i].last_reg		= u0[i].last_reg;
+			u1[i].invalidated	= u0[i].invalidated;
+
+			u1[i].flags	= 0;
+			u1[i].sectors	= 0;
+		}
+	}
+
+	return NULL;
+}
+
+static int __uuid_write(struct cache_set *c)
+{
+	BKEY_PADDED(key) k;
+	struct closure cl;
+	closure_init_stack(&cl);
+
+	lockdep_assert_held(&register_lock);
+
+	if (bch_bucket_alloc_set(c, GC_MARK_BTREE, 0, &k.key, 1, &cl))
+		return 1;
+
+	SET_KEY_SIZE(&k.key, c->sb.bucket_size);
+	uuid_io(c, REQ_WRITE, &k.key, &cl);
+	closure_sync(&cl);
+
+	bkey_copy(&c->uuid_bucket, &k.key);
+	__bkey_put(c, &k.key);
+	return 0;
+}
+
+static int uuid_write(struct cache_set *c)
+{
+	int ret = __uuid_write(c);
+
+	if (!ret)
+		bch_journal_meta(c, NULL);
+
+	return ret;
+}
+
+static struct uuid_entry *uuid_find(struct cache_set *c, const char *uuid)
+{
+	for (struct uuid_entry *u = c->uuids;
+	     u < c->uuids + c->nr_uuids; u++)
+		if (!memcmp(u->uuid, uuid, 16))
+			return u;
+
+	return NULL;
+}
+
+static struct uuid_entry *uuid_find_empty(struct cache_set *c)
+{
+	static const char zero_uuid[16] = "\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0";
+	return uuid_find(c, zero_uuid);
+}
+
+/*
+ * Bucket priorities/gens:
+ *
+ * For each bucket, we store on disk its
+   * 8 bit gen
+   * 16 bit priority
+ *
+ * See alloc.c for an explanation of the gen. The priority is used to implement
+ * lru (and in the future other) cache replacement policies; for most purposes
+ * it's just an opaque integer.
+ *
+ * The gens and the priorities don't have a whole lot to do with each other, and
+ * it's actually the gens that must be written out at specific times - it's no
+ * big deal if the priorities don't get written, if we lose them we just reuse
+ * buckets in suboptimal order.
+ *
+ * On disk they're stored in a packed array, and in as many buckets are required
+ * to fit them all. The buckets we use to store them form a list; the journal
+ * header points to the first bucket, the first bucket points to the second
+ * bucket, et cetera.
+ *
+ * This code is primarily used by the allocation code; periodically (whenever
+ * it runs out of buckets to allocate from) the allocation code will invalidate
+ * some buckets, but it can't use those buckets until their new gens are safely
+ * on disk.
+ *
+ * So it calls prio_write(), which does a bunch of work and eventually stores
+ * the pointer to the new first prio bucket in the current open journal entry
+ * header; when that journal entry is written, we can mark the buckets that have
+ * been invalidated as being ready for use by toggling c->prio_written.
+ */
+
+static void prio_endio(struct bio *bio, int error)
+{
+	struct cache *ca = bio->bi_private;
+
+	cache_set_err_on(error, ca->set, "accessing priorities");
+	bch_bbio_free(bio, ca->set);
+	closure_put(&ca->prio);
+}
+
+static void prio_io(struct cache *ca, uint64_t bucket, unsigned long rw)
+{
+	struct bio *bio = bch_bbio_alloc(ca->set);
+
+	bio->bi_sector	= bucket * ca->sb.bucket_size;
+	bio->bi_bdev	= ca->bdev;
+	bio->bi_rw	= REQ_SYNC|REQ_META|rw;
+	bio->bi_size	= bucket_bytes(ca);
+
+	bio->bi_end_io	= prio_endio;
+	bio->bi_private = ca;
+	bio_map(bio, ca->disk_buckets);
+
+	closure_bio_submit(bio, &ca->prio);
+}
+
+#define buckets_free(c)	"free %zu, free_inc %zu, unused %zu",		\
+	fifo_used(&c->free), fifo_used(&c->free_inc), fifo_used(&c->unused)
+
+static void prio_write_done(struct closure *cl)
+{
+	struct cache *ca = container_of(cl, struct cache, prio);
+
+	pr_debug("free %zu, free_inc %zu, unused %zu", fifo_used(&ca->free),
+		 fifo_used(&ca->free_inc), fifo_used(&ca->unused));
+	blktrace_msg(ca, "Finished priorities: " buckets_free(ca));
+
+	mutex_lock(&ca->set->bucket_lock);
+
+	/*
+	 * XXX: Terrible hack
+	 *
+	 * We really should be using this closure as the lock for writing
+	 * priorities, but we don't - we use ca->prio_written. So we have to
+	 * finish with the closure before we unlock bucket_lock:
+	 */
+	set_closure_fn(&ca->prio, NULL, NULL);
+	closure_set_stopped(&ca->prio);
+	closure_put(&ca->prio);
+
+	atomic_set(&ca->prio_written, 1);
+	mutex_unlock(&ca->set->bucket_lock);
+
+	closure_wake_up(&ca->set->bucket_wait);
+}
+
+static void prio_write_journal(struct closure *cl)
+{
+	struct cache *ca = container_of(cl, struct cache, prio);
+
+	pr_debug("free %zu, free_inc %zu, unused %zu", fifo_used(&ca->free),
+		 fifo_used(&ca->free_inc), fifo_used(&ca->unused));
+	blktrace_msg(ca, "Journalling priorities: " buckets_free(ca));
+
+	mutex_lock(&ca->set->bucket_lock);
+
+	for (unsigned i = 0; i < prio_buckets(ca); i++)
+		ca->prio_buckets[i] = ca->prio_next[i];
+
+	ca->prio_alloc = 0;
+	ca->need_save_prio = 0;
+
+	/*
+	 * We have to call bcache_journal_meta() with bucket_lock still held,
+	 * because after we set prio_buckets = prio_next things are inconsistent
+	 * until the next journal entry is updated
+	 */
+	bch_journal_meta(ca->set, cl);
+
+	mutex_unlock(&ca->set->bucket_lock);
+
+	continue_at(cl, prio_write_done, system_wq);
+}
+
+static void prio_write_bucket(struct closure *cl)
+{
+	struct cache *ca = container_of(cl, struct cache, prio);
+	struct prio_set *p = ca->disk_buckets;
+	struct bucket_disk *d = p->data, *end = d + prios_per_bucket(ca);
+
+	unsigned i = ca->prio_write++;
+
+	for (struct bucket *b = ca->buckets + i * prios_per_bucket(ca);
+	     b < ca->buckets + ca->sb.nbuckets && d < end;
+	     b++, d++) {
+		d->prio = cpu_to_le16(b->prio);
+		d->gen = b->disk_gen;
+	}
+
+	if (ca->prio_write != prio_buckets(ca))
+		p->next_bucket = ca->prio_next[ca->prio_write];
+
+	p->magic = pset_magic(ca);
+	p->csum = crc64(&p->magic, bucket_bytes(ca) - 8);
+
+	prio_io(ca, ca->prio_next[i], REQ_WRITE);
+
+	continue_at(cl, ca->prio_write == prio_buckets(ca)
+		    ? prio_write_journal
+		    : prio_write_bucket, system_wq);
+}
+
+void bch_prio_write(struct cache *ca)
+{
+	lockdep_assert_held(&ca->set->bucket_lock);
+	BUG_ON(atomic_read(&ca->prio_written));
+	BUG_ON(ca->prio_alloc != prio_buckets(ca));
+
+	closure_init(&ca->prio, &ca->set->cl);
+
+	for (struct bucket *b = ca->buckets;
+	     b < ca->buckets + ca->sb.nbuckets; b++)
+		b->disk_gen = b->gen;
+
+	ca->prio_write = 0;
+	ca->disk_buckets->seq++;
+
+	atomic_long_add(ca->sb.bucket_size * prio_buckets(ca),
+			&ca->meta_sectors_written);
+
+	atomic_set(&ca->prio_written, -1);
+
+	pr_debug("free %zu, free_inc %zu, unused %zu", fifo_used(&ca->free),
+		 fifo_used(&ca->free_inc), fifo_used(&ca->unused));
+	blktrace_msg(ca, "Starting priorities: " buckets_free(ca));
+
+	continue_at(&ca->prio, prio_write_bucket, system_wq);
+}
+
+static void prio_read(struct cache *ca, uint64_t bucket)
+{
+	struct prio_set *p = ca->disk_buckets;
+	struct bucket_disk *d = p->data + prios_per_bucket(ca), *end = d;
+
+	closure_init(&ca->prio, NULL);
+
+	for (struct bucket *b = ca->buckets;
+	     b < ca->buckets + ca->sb.nbuckets;
+	     b++, d++) {
+		if (d == end) {
+			ca->prio_buckets[ca->prio_write++] = bucket;
+
+			prio_io(ca, bucket, READ_SYNC);
+			closure_sync(&ca->prio);
+
+			if (p->csum != crc64(&p->magic, bucket_bytes(ca) - 8))
+				printk(KERN_WARNING "bcache: "
+				       "bad csum reading priorities\n");
+
+			if (p->magic != pset_magic(ca))
+				printk(KERN_WARNING "bcache: "
+				       "bad magic reading priorities\n");
+
+			bucket = p->next_bucket;
+			d = p->data;
+		}
+
+		b->prio = le16_to_cpu(d->prio);
+		b->gen = b->disk_gen = b->last_gc = b->gc_gen = d->gen;
+	}
+
+	continue_at(&ca->prio, NULL, NULL);
+}
+
+/* Bcache device */
+
+static int open_dev(struct block_device *b, fmode_t mode)
+{
+	struct bcache_device *d = b->bd_disk->private_data;
+	if (atomic_read(&d->closing))
+		return -ENXIO;
+
+	closure_get(&d->cl);
+	return 0;
+}
+
+static int release_dev(struct gendisk *b, fmode_t mode)
+{
+	struct bcache_device *d = b->private_data;
+	closure_put(&d->cl);
+	return 0;
+}
+
+static int ioctl_dev(struct block_device *b, fmode_t mode,
+		     unsigned int cmd, unsigned long arg)
+{
+	struct bcache_device *d = b->bd_disk->private_data;
+	return d->ioctl(d, mode, cmd, arg);
+}
+
+static const struct block_device_operations bcache_ops = {
+	.open		= open_dev,
+	.release	= release_dev,
+	.ioctl		= ioctl_dev,
+	.owner		= THIS_MODULE,
+};
+
+static void bcache_device_stop(struct bcache_device *d)
+{
+	if (!atomic_xchg(&d->closing, 1))
+		closure_queue(&d->cl);
+}
+
+static void bcache_device_detach(struct bcache_device *d)
+{
+	lockdep_assert_held(&register_lock);
+
+	if (atomic_read(&d->detaching)) {
+		struct uuid_entry *u = d->c->uuids + d->id;
+
+		SET_UUID_FLASH_ONLY(u, 0);
+		memcpy(u->uuid, invalid_uuid, 16);
+		u->invalidated = cpu_to_le32(get_seconds());
+		uuid_write(d->c);
+
+		atomic_set(&d->detaching, 0);
+	}
+
+	d->c->devices[d->id] = NULL;
+	closure_put(&d->c->caching);
+	d->c = NULL;
+}
+
+static void bcache_device_attach(struct bcache_device *d, struct cache_set *c,
+				 unsigned id)
+{
+	BUG_ON(atomic_read(&c->closing));
+
+	d->id = id;
+	d->c = c;
+	c->devices[id] = d;
+
+	closure_get(&c->caching);
+}
+
+static void bcache_device_link(struct bcache_device *d, struct cache_set *c,
+			       const char *name)
+{
+	snprintf(d->name, BCACHEDEVNAME_SIZE,
+		 "%s%u", name, d->id);
+
+	WARN(sysfs_create_link(&d->kobj, &c->kobj, "cache") ||
+	     sysfs_create_link(&c->kobj, &d->kobj, d->name),
+	     "Couldn't create device <-> cache set symlinks");
+}
+
+static void bcache_device_free(struct bcache_device *d)
+{
+	lockdep_assert_held(&register_lock);
+
+	printk(KERN_INFO "bcache: %s stopped\n", d->disk->disk_name);
+
+	if (d->c)
+		bcache_device_detach(d);
+
+	if (d->disk)
+		del_gendisk(d->disk);
+	if (d->disk && d->disk->queue)
+		blk_cleanup_queue(d->disk->queue);
+	if (d->disk)
+		put_disk(d->disk);
+
+	if (d->unaligned_bvec)
+		mempool_destroy(d->unaligned_bvec);
+	if (d->bio_split)
+		bioset_free(d->bio_split);
+
+	closure_debug_destroy(&d->cl);
+}
+
+static int bcache_device_init(struct bcache_device *d, unsigned block_size)
+{
+	struct request_queue *q;
+
+	if (!(d->bio_split = bioset_create(4, offsetof(struct bbio, bio))) ||
+	    !(d->unaligned_bvec = mempool_create_kmalloc_pool(1,
+				sizeof(struct bio_vec) * BIO_MAX_PAGES)))
+		return -ENOMEM;
+
+	d->disk = alloc_disk(1);
+	if (!d->disk)
+		return -ENOMEM;
+
+	snprintf(d->disk->disk_name, DISK_NAME_LEN, "bcache%i", bcache_minor);
+
+	d->disk->major		= bcache_major;
+	d->disk->first_minor	= bcache_minor++;
+	d->disk->fops		= &bcache_ops;
+	d->disk->private_data	= d;
+
+	q = blk_alloc_queue(GFP_KERNEL);
+	if (!q)
+		return -ENOMEM;
+
+	blk_queue_make_request(q, NULL);
+	d->disk->queue			= q;
+	q->queuedata			= d;
+	q->backing_dev_info.congested_data = d;
+	q->limits.max_hw_sectors	= UINT_MAX;
+	q->limits.max_sectors		= UINT_MAX;
+	q->limits.max_segment_size	= UINT_MAX;
+	q->limits.max_segments		= BIO_MAX_PAGES;
+	q->limits.max_discard_sectors	= UINT_MAX;
+	q->limits.io_min		= block_size;
+	q->limits.logical_block_size	= block_size;
+	q->limits.physical_block_size	= block_size;
+	set_bit(QUEUE_FLAG_NONROT,	&d->disk->queue->queue_flags);
+	set_bit(QUEUE_FLAG_DISCARD,	&d->disk->queue->queue_flags);
+
+	return 0;
+}
+
+/* Cached device */
+
+static void calc_cached_dev_sectors(struct cache_set *c)
+{
+	uint64_t sectors = 0;
+	struct cached_dev *dc;
+
+	list_for_each_entry(dc, &c->cached_devs, list)
+		sectors += bdev_sectors(dc->bdev);
+
+	c->cached_dev_sectors = sectors;
+}
+
+static void cached_dev_run(struct cached_dev *dc)
+{
+	struct bcache_device *d = &dc->disk;
+
+	if (atomic_xchg(&dc->running, 1))
+		return;
+
+	if (!d->c &&
+	    BDEV_STATE(&dc->sb) != BDEV_STATE_NONE) {
+		struct closure cl;
+		closure_init_stack(&cl);
+
+		SET_BDEV_STATE(&dc->sb, BDEV_STATE_STALE);
+		bch_write_bdev_super(dc, &cl);
+		closure_sync(&cl);
+	}
+
+	add_disk(d->disk);
+#if 0
+	char *env[] = { "SYMLINK=label" , NULL };
+	kobject_uevent_env(&disk_to_dev(d->disk)->kobj, KOBJ_CHANGE, env);
+#endif
+	if (sysfs_create_link(&d->kobj, &disk_to_dev(d->disk)->kobj, "dev") ||
+	    sysfs_create_link(&disk_to_dev(d->disk)->kobj, &d->kobj, "bcache"))
+		pr_debug("error creating sysfs link");
+}
+
+static void cached_dev_detach_finish(struct work_struct *w)
+{
+	struct cached_dev *dc = container_of(w, struct cached_dev, detach);
+	char buf[BDEVNAME_SIZE];
+	struct closure cl;
+	closure_init_stack(&cl);
+
+	BUG_ON(!atomic_read(&dc->disk.detaching));
+	BUG_ON(atomic_read(&dc->count));
+
+	sysfs_remove_link(&dc->disk.c->kobj, dc->disk.name);
+	sysfs_remove_link(&dc->disk.kobj, "cache");
+
+	mutex_lock(&register_lock);
+
+	memset(&dc->sb.set_uuid, 0, 16);
+	SET_BDEV_STATE(&dc->sb, BDEV_STATE_NONE);
+
+	bch_write_bdev_super(dc, &cl);
+	closure_sync(&cl);
+
+	bcache_device_detach(&dc->disk);
+	list_move(&dc->list, &uncached_devices);
+
+	mutex_unlock(&register_lock);
+
+	printk(KERN_DEBUG "bcache: Caching disabled for %s\n",
+	       bdevname(dc->bdev, buf));
+}
+
+static void cached_dev_detach(struct cached_dev *dc)
+{
+	lockdep_assert_held(&register_lock);
+
+	if (atomic_xchg(&dc->disk.detaching, 1))
+		return;
+
+	bch_writeback_queue(dc);
+	cached_dev_put(dc);
+}
+
+static int cached_dev_attach(struct cached_dev *dc, struct cache_set *c)
+{
+	uint32_t rtime = cpu_to_le32(get_seconds());
+	struct uuid_entry *u;
+	char buf[BDEVNAME_SIZE];
+
+	bdevname(dc->bdev, buf);
+
+	if (dc->disk.c ||
+	    atomic_read(&c->closing) ||
+	    memcmp(dc->sb.set_uuid, c->sb.set_uuid, 16))
+		return -ENOENT;
+
+	if (dc->sb.block_size < c->sb.block_size) {
+		/* Will die */
+		err_printk("Couldn't attach %s: block size "
+			   "less than set's block size\n", buf);
+		return -EINVAL;
+	}
+
+	u = uuid_find(c, dc->sb.uuid);
+
+	if (u &&
+	    (BDEV_STATE(&dc->sb) == BDEV_STATE_STALE ||
+	     BDEV_STATE(&dc->sb) == BDEV_STATE_NONE)) {
+		memcpy(u->uuid, invalid_uuid, 16);
+		u->invalidated = cpu_to_le32(get_seconds());
+		u = NULL;
+	}
+
+	if (!u) {
+		if (BDEV_STATE(&dc->sb) == BDEV_STATE_DIRTY) {
+			err_printk("Couldn't find uuid for %s in set\n", buf);
+			return -ENOENT;
+		}
+
+		u = uuid_find_empty(c);
+		if (!u) {
+			err_printk("Not caching %s, no room for UUID\n", buf);
+			return -EINVAL;
+		}
+	}
+
+	/* Deadlocks since we're called via sysfs...
+	sysfs_remove_file(&dc->kobj, &sysfs_attach);
+	 */
+
+	if (is_zero(u->uuid, 16)) {
+		struct closure cl;
+		closure_init_stack(&cl);
+
+		memcpy(u->uuid, dc->sb.uuid, 16);
+		memcpy(u->label, dc->sb.label, SB_LABEL_SIZE);
+		u->first_reg = u->last_reg = rtime;
+		uuid_write(c);
+
+		memcpy(dc->sb.set_uuid, c->sb.set_uuid, 16);
+		SET_BDEV_STATE(&dc->sb, BDEV_STATE_CLEAN);
+
+		bch_write_bdev_super(dc, &cl);
+		closure_sync(&cl);
+	} else {
+		u->last_reg = rtime;
+		uuid_write(c);
+	}
+
+	bcache_device_attach(&dc->disk, c, u - c->uuids);
+	bcache_device_link(&dc->disk, c, "bdev");
+	list_move(&dc->list, &c->cached_devs);
+	calc_cached_dev_sectors(c);
+
+	smp_wmb();
+	/*
+	 * dc->c must be set before dc->count != 0 - paired with the mb in
+	 * cached_dev_get()
+	 */
+	atomic_set(&dc->count, 1);
+
+	if (BDEV_STATE(&dc->sb) == BDEV_STATE_DIRTY) {
+		atomic_set(&dc->has_dirty, 1);
+		atomic_inc(&dc->count);
+		bch_writeback_queue(dc);
+	}
+
+	cached_dev_run(dc);
+
+	printk(KERN_INFO "bcache: Caching %s as %s on set %pU\n",
+	       bdevname(dc->bdev, buf), dc->disk.disk->disk_name,
+	       dc->disk.c->sb.set_uuid);
+	return 0;
+}
+
+static void __cached_dev_free(struct kobject *kobj)
+{
+	struct cached_dev *dc = container_of(kobj, struct cached_dev, disk.kobj);
+	kfree(dc);
+	module_put(THIS_MODULE);
+}
+
+static void cached_dev_free(struct closure *cl)
+{
+	struct cached_dev *dc = container_of(cl, struct cached_dev, disk.cl);
+
+	cancel_delayed_work_sync(&dc->writeback_rate_update);
+
+	mutex_lock(&register_lock);
+
+	bcache_device_free(&dc->disk);
+	list_del(&dc->list);
+
+	mutex_unlock(&register_lock);
+
+	if (!IS_ERR_OR_NULL(dc->bdev)) {
+		blk_sync_queue(bdev_get_queue(dc->bdev));
+		blkdev_put(dc->bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
+	}
+
+	wake_up(&unregister_wait);
+
+	kobject_put(&dc->disk.kobj);
+}
+
+static void cached_dev_flush(struct closure *cl)
+{
+	struct cached_dev *dc = container_of(cl, struct cached_dev, disk.cl);
+	struct bcache_device *d = &dc->disk;
+
+	bch_cache_accounting_destroy(&dc->accounting);
+	kobject_del(&d->kobj);
+
+	continue_at(cl, cached_dev_free, system_wq);
+}
+
+static int cached_dev_init(struct cached_dev *dc, unsigned block_size)
+{
+	int err;
+
+	closure_init(&dc->disk.cl, NULL);
+	set_closure_fn(&dc->disk.cl, cached_dev_flush, system_wq);
+
+	__module_get(THIS_MODULE);
+	INIT_LIST_HEAD(&dc->list);
+	cached_dev_kobject_init(dc);
+	bch_cache_accounting_init(&dc->accounting, &dc->disk.cl);
+
+	err = bcache_device_init(&dc->disk, block_size);
+	if (err)
+		goto err;
+
+	spin_lock_init(&dc->io_lock);
+	closure_init_unlocked(&dc->sb_write);
+	INIT_WORK(&dc->detach, cached_dev_detach_finish);
+
+	dc->sequential_merge		= true;
+	dc->sequential_cutoff		= 4 << 20;
+
+	INIT_LIST_HEAD(&dc->io_lru);
+	dc->sb_bio.bi_max_vecs	= 1;
+	dc->sb_bio.bi_io_vec	= dc->sb_bio.bi_inline_vecs;
+
+	for (struct io *j = dc->io; j < dc->io + RECENT_IO; j++) {
+		list_add(&j->lru, &dc->io_lru);
+		hlist_add_head(&j->hash, dc->io_hash + RECENT_IO);
+	}
+
+	bch_writeback_init_cached_dev(dc);
+	return 0;
+err:
+	bcache_device_stop(&dc->disk);
+	return err;
+}
+
+/* Cached device - bcache superblock */
+
+static const char *register_bdev(struct cache_sb *sb, struct page *sb_page,
+				 struct block_device *bdev, struct cached_dev *dc)
+{
+	char name[BDEVNAME_SIZE];
+	const char *err = "cannot allocate memory";
+	struct gendisk *g;
+	struct cache_set *c;
+
+	if (!dc || cached_dev_init(dc, sb->block_size << 9) != 0)
+		return err;
+
+	memcpy(&dc->sb, sb, sizeof(struct cache_sb));
+	dc->sb_bio.bi_io_vec[0].bv_page = sb_page;
+	dc->bdev = bdev;
+	dc->bdev->bd_holder = dc;
+
+	g = dc->disk.disk;
+
+	set_capacity(g, dc->bdev->bd_part->nr_sects - 16);
+
+	bch_cached_dev_request_init(dc);
+
+	err = "error creating kobject";
+	if (kobject_add(&dc->disk.kobj, &part_to_dev(bdev->bd_part)->kobj,
+			"bcache"))
+		goto err;
+	if (bch_cache_accounting_add_kobjs(&dc->accounting, &dc->disk.kobj))
+		goto err;
+
+	list_add(&dc->list, &uncached_devices);
+	list_for_each_entry(c, &cache_sets, list)
+		cached_dev_attach(dc, c);
+
+	if (BDEV_STATE(&dc->sb) == BDEV_STATE_NONE ||
+	    BDEV_STATE(&dc->sb) == BDEV_STATE_STALE)
+		cached_dev_run(dc);
+
+	return NULL;
+err:
+	kobject_put(&dc->disk.kobj);
+	printk(KERN_DEBUG "bcache: error opening %s: %s\n",
+	       bdevname(bdev, name), err);
+	/*
+	 * Return NULL instead of an error because kobject_put() cleans
+	 * everything up
+	 */
+	return NULL;
+}
+
+/* Flash only volumes */
+
+static void __flash_dev_free(struct kobject *kobj)
+{
+	struct bcache_device *d = container_of(kobj, struct bcache_device,
+					       kobj);
+	kfree(d);
+}
+
+static void flash_dev_free(struct closure *cl)
+{
+	struct bcache_device *d = container_of(cl, struct bcache_device, cl);
+	bcache_device_free(d);
+	kobject_put(&d->kobj);
+}
+
+static void flash_dev_flush(struct closure *cl)
+{
+	struct bcache_device *d = container_of(cl, struct bcache_device, cl);
+
+	sysfs_remove_link(&d->c->kobj, d->name);
+	sysfs_remove_link(&d->kobj, "cache");
+	kobject_del(&d->kobj);
+	continue_at(cl, flash_dev_free, system_wq);
+}
+
+static int flash_dev_run(struct cache_set *c, struct uuid_entry *u)
+{
+	struct bcache_device *d = kzalloc(sizeof(struct bcache_device),
+					  GFP_KERNEL);
+	if (!d)
+		return -ENOMEM;
+
+	closure_init(&d->cl, NULL);
+	set_closure_fn(&d->cl, flash_dev_flush, system_wq);
+
+	flash_dev_kobject_init(d);
+
+	if (bcache_device_init(d, block_bytes(c)))
+		goto err;
+
+	bcache_device_attach(d, c, u - c->uuids);
+	set_capacity(d->disk, u->sectors);
+	bch_flash_dev_request_init(d);
+	add_disk(d->disk);
+
+	if (kobject_add(&d->kobj, &disk_to_dev(d->disk)->kobj, "bcache"))
+		goto err;
+
+	bcache_device_link(d, c, "volume");
+
+	return 0;
+err:
+	kobject_put(&d->kobj);
+	return -ENOMEM;
+}
+
+static int flash_devs_run(struct cache_set *c)
+{
+	int ret = 0;
+
+	for (struct uuid_entry *u = c->uuids;
+	     u < c->uuids + c->nr_uuids && !ret;
+	     u++)
+		if (UUID_FLASH_ONLY(u))
+			ret = flash_dev_run(c, u);
+
+	return ret;
+}
+
+static int flash_dev_create(struct cache_set *c, uint64_t size)
+{
+	struct uuid_entry *u;
+
+	if (atomic_read(&c->closing))
+		return -EINTR;
+
+	u = uuid_find_empty(c);
+	if (!u) {
+		err_printk("Can't create volume, no room for UUID\n");
+		return -EINVAL;
+	}
+
+	get_random_bytes(u->uuid, 16);
+	memset(u->label, 0, 32);
+	u->first_reg = u->last_reg = cpu_to_le32(get_seconds());
+
+	SET_UUID_FLASH_ONLY(u, 1);
+	u->sectors = size >> 9;
+
+	uuid_write(c);
+
+	return flash_dev_run(c, u);
+}
+
+/* Cache set */
+
+__printf(2, 3)
+bool bch_cache_set_error(struct cache_set *c, const char *fmt, ...)
+{
+	va_list args;
+
+	if (atomic_read(&c->closing))
+		return false;
+
+	/* XXX: we can be called from atomic context
+	acquire_console_sem();
+	*/
+
+	printk(KERN_ERR "bcache: error on %pU: ", c->sb.set_uuid);
+
+	va_start(args, fmt);
+	vprintk(fmt, args);
+	va_end(args);
+
+	printk(", disabling caching\n");
+
+	cache_set_unregister(c);
+	return true;
+}
+
+static void __cache_set_free(struct kobject *kobj)
+{
+	struct cache_set *c = container_of(kobj, struct cache_set, kobj);
+	kfree(c);
+	module_put(THIS_MODULE);
+}
+
+static void cache_set_free(struct closure *cl)
+{
+	struct cache_set *c = container_of(cl, struct cache_set, cl);
+	struct cache *ca;
+
+	if (!IS_ERR_OR_NULL(c->debug))
+		debugfs_remove(c->debug);
+
+	bch_open_buckets_free(c);
+	bch_btree_cache_free(c);
+	bch_journal_free(c);
+
+	for_each_cache(ca, c)
+		if (ca)
+			kobject_put(&ca->kobj);
+
+	free_pages((unsigned long) c->uuids, ilog2(bucket_pages(c)));
+	free_pages((unsigned long) c->sort, ilog2(bucket_pages(c)));
+
+	kfree(c->fill_iter);
+	if (c->bio_split)
+		bioset_free(c->bio_split);
+	if (c->bio_meta)
+		mempool_destroy(c->bio_meta);
+	if (c->search)
+		mempool_destroy(c->search);
+	kfree(c->devices);
+
+	mutex_lock(&register_lock);
+	list_del(&c->list);
+	mutex_unlock(&register_lock);
+
+	printk(KERN_INFO "bcache: Cache set %pU unregistered\n",
+	       c->sb.set_uuid);
+	wake_up(&unregister_wait);
+
+	closure_debug_destroy(&c->cl);
+	kobject_put(&c->kobj);
+}
+
+static void cache_set_flush(struct closure *cl)
+{
+	struct cache_set *c = container_of(cl, struct cache_set, caching);
+	struct btree *b;
+
+	bch_cache_accounting_destroy(&c->accounting);
+
+	kobject_put(&c->internal);
+	kobject_del(&c->kobj);
+
+	if (!IS_ERR_OR_NULL(c->root))
+		list_add(&c->root->list, &c->btree_cache);
+
+	/* Should skip this if we're unregistering because of an error */
+	list_for_each_entry(b, &c->btree_cache, list)
+		if (btree_node_dirty(b))
+			bch_btree_write(b, true, NULL);
+
+	closure_return(cl);
+}
+
+static void __cache_set_unregister(struct closure *cl)
+{
+	struct cache_set *c = container_of(cl, struct cache_set, caching);
+	struct cached_dev *dc, *t;
+
+	mutex_lock(&register_lock);
+
+	if (atomic_read(&c->unregistering))
+		list_for_each_entry_safe(dc, t, &c->cached_devs, list)
+			cached_dev_detach(dc);
+
+	for (size_t i = 0; i < c->nr_uuids; i++)
+		if (c->devices[i] && UUID_FLASH_ONLY(&c->uuids[i]))
+			bcache_device_stop(c->devices[i]);
+
+	mutex_unlock(&register_lock);
+
+	continue_at(cl, cache_set_flush, system_wq);
+}
+
+static void cache_set_stop(struct cache_set *c)
+{
+	if (!atomic_xchg(&c->closing, 1))
+		closure_queue(&c->caching);
+}
+
+static void cache_set_unregister(struct cache_set *c)
+{
+	atomic_set(&c->unregistering, 1);
+	cache_set_stop(c);
+}
+
+#define alloc_bucket_pages(gfp, c)			\
+	((void *) __get_free_pages(__GFP_ZERO|gfp, ilog2(bucket_pages(c))))
+
+struct cache_set *bch_cache_set_alloc(struct cache_sb *sb)
+{
+	int iter_size;
+	struct cache_set *c = kzalloc(sizeof(struct cache_set), GFP_KERNEL);
+	if (!c)
+		return NULL;
+
+	__module_get(THIS_MODULE);
+	closure_init(&c->cl, NULL);
+	set_closure_fn(&c->cl, cache_set_free, system_wq);
+
+	closure_init(&c->caching, &c->cl);
+	set_closure_fn(&c->caching, __cache_set_unregister, system_wq);
+
+	/* Maybe create continue_at_noreturn() and use it here? */
+	closure_set_stopped(&c->cl);
+	closure_put(&c->cl);
+
+	cache_set_kobject_init(c);
+	bch_cache_accounting_init(&c->accounting, &c->cl);
+
+	memcpy(c->sb.set_uuid, sb->set_uuid, 16);
+	c->sb.block_size	= sb->block_size;
+	c->sb.bucket_size	= sb->bucket_size;
+	c->sb.nr_in_set		= sb->nr_in_set;
+	c->sb.last_mount	= sb->last_mount;
+	c->bucket_bits		= ilog2(sb->bucket_size);
+	c->block_bits		= ilog2(sb->block_size);
+	c->nr_uuids		= bucket_bytes(c) / sizeof(struct uuid_entry);
+
+	c->btree_pages		= c->sb.bucket_size / PAGE_SECTORS;
+	if (c->btree_pages > BTREE_MAX_PAGES)
+		c->btree_pages = max_t(int, c->btree_pages / 4,
+				       BTREE_MAX_PAGES);
+
+	mutex_init(&c->bucket_lock);
+	mutex_init(&c->fill_lock);
+	mutex_init(&c->sort_lock);
+	spin_lock_init(&c->sort_time_lock);
+	closure_init_unlocked(&c->sb_write);
+	closure_init_unlocked(&c->uuid_write);
+	spin_lock_init(&c->btree_read_time_lock);
+	bch_moving_init_cache_set(c);
+
+	INIT_LIST_HEAD(&c->list);
+	INIT_LIST_HEAD(&c->cached_devs);
+	INIT_LIST_HEAD(&c->btree_cache);
+	INIT_LIST_HEAD(&c->btree_cache_freeable);
+	INIT_LIST_HEAD(&c->btree_cache_freed);
+	INIT_LIST_HEAD(&c->data_buckets);
+
+	c->search = mempool_create_slab_pool(32, bch_search_cache);
+	if (!c->search)
+		goto err;
+
+	iter_size = (sb->bucket_size / sb->block_size + 1) *
+		sizeof(struct btree_iter_set);
+
+	if (!(c->devices = kzalloc(c->nr_uuids * sizeof(void *), GFP_KERNEL)) ||
+	    !(c->bio_meta = mempool_create_kmalloc_pool(2,
+				sizeof(struct bbio) + sizeof(struct bio_vec) *
+				bucket_pages(c))) ||
+	    !(c->bio_split = bioset_create(4, offsetof(struct bbio, bio))) ||
+	    !(c->fill_iter = kmalloc(iter_size, GFP_KERNEL)) ||
+	    !(c->sort = alloc_bucket_pages(GFP_KERNEL, c)) ||
+	    !(c->uuids = alloc_bucket_pages(GFP_KERNEL, c)) ||
+	    bch_journal_alloc(c) ||
+	    bch_btree_cache_alloc(c) ||
+	    bch_open_buckets_alloc(c))
+		goto err;
+
+	c->fill_iter->size = sb->bucket_size / sb->block_size;
+
+	c->congested_read_threshold_us	= 2000;
+	c->congested_write_threshold_us	= 20000;
+	c->error_limit	= 8 << IO_ERROR_SHIFT;
+
+	return c;
+err:
+	cache_set_unregister(c);
+	return NULL;
+}
+
+static void run_cache_set(struct cache_set *c)
+{
+	const char *err = "cannot allocate memory";
+	struct cached_dev *dc, *t;
+	struct cache *ca;
+
+	struct btree_op op;
+	bch_btree_op_init_stack(&op);
+	op.lock = SHRT_MAX;
+
+	for_each_cache(ca, c)
+		c->nbuckets += ca->sb.nbuckets;
+
+	if (CACHE_SYNC(&c->sb)) {
+		LIST_HEAD(journal);
+		struct bkey *k;
+		struct jset *j;
+
+		err = "cannot allocate memory for journal";
+		if (bch_journal_read(c, &journal, &op))
+			goto err;
+
+		printk(KERN_DEBUG "bcache: btree_journal_read() done\n");
+
+		err = "no journal entries found";
+		if (list_empty(&journal))
+			goto err;
+
+		j = &list_entry(journal.prev, struct journal_replay, list)->j;
+
+		err = "IO error reading priorities";
+		for_each_cache(ca, c)
+			prio_read(ca, j->prio_bucket[ca->sb.nr_this_dev]);
+
+		/*
+		 * If prio_read() fails it'll call cache_set_error and we'll
+		 * tear everything down right away, but if we perhaps checked
+		 * sooner we could avoid journal replay.
+		 */
+
+		k = &j->btree_root;
+
+		err = "bad btree root";
+		if (__bch_ptr_invalid(c, j->btree_level + 1, k))
+			goto err;
+
+		err = "error reading btree root";
+		c->root = bch_btree_node_get(c, k, j->btree_level, &op);
+		if (IS_ERR_OR_NULL(c->root))
+			goto err;
+
+		list_del_init(&c->root->list);
+		rw_unlock(true, c->root);
+
+		err = uuid_read(c, j, &op.cl);
+		if (err)
+			goto err;
+
+		err = "error in recovery";
+		if (bch_btree_check(c, &op))
+			goto err;
+
+		bch_journal_mark(c, &journal);
+		bch_btree_gc_finish(c);
+		printk(KERN_DEBUG "bcache: btree_check() done\n");
+
+		/*
+		 * bcache_journal_next() can't happen sooner, or
+		 * btree_gc_finish() will give spurious errors about last_gc >
+		 * gc_gen - this is a hack but oh well.
+		 */
+		bch_journal_next(&c->journal);
+
+		/*
+		 * First place it's safe to allocate: btree_check() and
+		 * btree_gc_finish() have to run before we have buckets to
+		 * allocate, and bch_bucket_alloc_set() might cause a journal
+		 * entry to be written so bcache_journal_next() has to be called
+		 * first.
+		 *
+		 * If the uuids were in the old format we have to rewrite them
+		 * before the next journal entry is written:
+		 */
+		if (j->version < BCACHE_JSET_VERSION_UUID)
+			__uuid_write(c);
+
+		bch_journal_replay(c, &journal, &op);
+	} else {
+		printk(KERN_NOTICE "bcache: invalidating existing data\n");
+		/* Don't want invalidate_buckets() to queue a gc yet */
+		closure_lock(&c->gc, NULL);
+
+		for_each_cache(ca, c) {
+			ca->sb.keys = clamp_t(int, ca->sb.nbuckets >> 7,
+					      2, SB_JOURNAL_BUCKETS);
+
+			for (int i = 0; i < ca->sb.keys; i++)
+				ca->sb.d[i] = ca->sb.first_bucket + i;
+		}
+
+		bch_btree_gc_finish(c);
+
+		err = "cannot allocate new UUID bucket";
+		if (uuid_write(c))
+			goto err_unlock_gc;
+
+		err = "cannot allocate new btree root";
+		c->root = bch_btree_node_alloc(c, 0, &op.cl);
+		if (IS_ERR_OR_NULL(c->root))
+			goto err_unlock_gc;
+
+		bkey_copy_key(&c->root->key, &MAX_KEY);
+		bch_btree_write(c->root, true, &op);
+
+		mutex_lock(&c->bucket_lock);
+		for_each_cache(ca, c) {
+			bch_free_some_buckets(ca);
+			bch_prio_write(ca);
+		}
+		mutex_unlock(&c->bucket_lock);
+
+		/*
+		 * Wait for prio_write() to finish, so the SET_CACHE_SYNC()
+		 * doesn't race
+		 */
+		for_each_cache(ca, c)
+			closure_wait_event(&c->bucket_wait, &op.cl,
+				   atomic_read(&ca->prio_written) == -1);
+
+		bch_btree_set_root(c->root);
+		rw_unlock(true, c->root);
+
+		/*
+		 * We don't want to write the first journal entry until
+		 * everything is set up - fortunately journal entries won't be
+		 * written until the SET_CACHE_SYNC() here:
+		 */
+		SET_CACHE_SYNC(&c->sb, true);
+
+		bch_journal_next(&c->journal);
+		bch_journal_meta(c, &op.cl);
+
+		/* Unlock */
+		closure_set_stopped(&c->gc.cl);
+		closure_put(&c->gc.cl);
+	}
+
+	closure_sync(&op.cl);
+	c->sb.last_mount = get_seconds();
+	bcache_write_super(c);
+
+	list_for_each_entry_safe(dc, t, &uncached_devices, list)
+		cached_dev_attach(dc, c);
+
+	flash_devs_run(c);
+
+	return;
+err_unlock_gc:
+	closure_set_stopped(&c->gc.cl);
+	closure_put(&c->gc.cl);
+err:
+	closure_sync(&op.cl);
+	/* XXX: test this, it's broken */
+	bch_cache_set_error(c, err);
+}
+
+static bool can_attach_cache(struct cache *ca, struct cache_set *c)
+{
+	return ca->sb.block_size	== c->sb.block_size &&
+		ca->sb.bucket_size	== c->sb.block_size &&
+		ca->sb.nr_in_set	== c->sb.nr_in_set;
+}
+
+static const char *register_cache_set(struct cache *ca)
+{
+	char buf[12];
+	const char *err = "cannot allocate memory";
+	struct cache_set *c;
+
+	list_for_each_entry(c, &cache_sets, list)
+		if (!memcmp(c->sb.set_uuid, ca->sb.set_uuid, 16)) {
+			if (c->cache[ca->sb.nr_this_dev])
+				return "duplicate cache set member";
+
+			if (!can_attach_cache(ca, c))
+				return "cache sb does not match set";
+
+			if (!CACHE_SYNC(&ca->sb))
+				SET_CACHE_SYNC(&c->sb, false);
+
+			goto found;
+		}
+
+	c = bch_cache_set_alloc(&ca->sb);
+	if (!c)
+		return err;
+
+	err = "error creating kobject";
+	if (kobject_add(&c->kobj, bcache_kobj, "%pU", c->sb.set_uuid) ||
+	    kobject_add(&c->internal, &c->kobj, "internal"))
+		goto err;
+
+	if (bch_cache_accounting_add_kobjs(&c->accounting, &c->kobj))
+		goto err;
+
+	bch_debug_init_cache_set(c);
+
+	list_add(&c->list, &cache_sets);
+found:
+	sprintf(buf, "cache%i", ca->sb.nr_this_dev);
+	if (sysfs_create_link(&ca->kobj, &c->kobj, "set") ||
+	    sysfs_create_link(&c->kobj, &ca->kobj, buf))
+		goto err;
+
+	if (ca->sb.seq > c->sb.seq) {
+		c->sb.version		= ca->sb.version;
+		memcpy(c->sb.set_uuid, ca->sb.set_uuid, 16);
+		c->sb.flags             = ca->sb.flags;
+		c->sb.seq		= ca->sb.seq;
+		pr_debug("set version = %llu", c->sb.version);
+	}
+
+	ca->set = c;
+	ca->set->cache[ca->sb.nr_this_dev] = ca;
+	c->cache_by_alloc[c->caches_loaded++] = ca;
+
+	if (c->caches_loaded == c->sb.nr_in_set)
+		run_cache_set(c);
+
+	return NULL;
+err:
+	cache_set_unregister(c);
+	return err;
+}
+
+/* Cache device */
+
+static void cache_free(struct kobject *kobj)
+{
+	struct cache *ca = container_of(kobj, struct cache, kobj);
+
+	if (ca->set)
+		ca->set->cache[ca->sb.nr_this_dev] = NULL;
+
+	bch_free_discards(ca);
+
+	free_pages((unsigned long) ca->disk_buckets, ilog2(bucket_pages(ca)));
+	kfree(ca->prio_buckets);
+	vfree(ca->buckets);
+
+	if (ca->discard_page)
+		put_page(ca->discard_page);
+
+	free_heap(&ca->heap);
+	free_fifo(&ca->unused);
+	free_fifo(&ca->free_inc);
+	free_fifo(&ca->free);
+
+	if (ca->sb_bio.bi_inline_vecs[0].bv_page)
+		put_page(ca->sb_bio.bi_io_vec[0].bv_page);
+
+	if (!IS_ERR_OR_NULL(ca->bdev)) {
+		blk_sync_queue(bdev_get_queue(ca->bdev));
+		blkdev_put(ca->bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
+	}
+
+	kfree(ca);
+	module_put(THIS_MODULE);
+}
+
+static int cache_alloc(struct cache_sb *sb, struct cache *ca)
+{
+	size_t free;
+	struct bucket *b;
+
+	if (!ca)
+		return -ENOMEM;
+
+	__module_get(THIS_MODULE);
+	cache_kobject_init(ca);
+
+	memcpy(&ca->sb, sb, sizeof(struct cache_sb));
+
+	INIT_LIST_HEAD(&ca->discards);
+
+	bio_init(&ca->sb_bio);
+	ca->sb_bio.bi_max_vecs	= 1;
+	ca->sb_bio.bi_io_vec	= ca->sb_bio.bi_inline_vecs;
+
+	bio_init(&ca->journal.bio);
+	ca->journal.bio.bi_max_vecs = 8;
+	ca->journal.bio.bi_io_vec = ca->journal.bio.bi_inline_vecs;
+
+	free = roundup_pow_of_two(ca->sb.nbuckets) >> 9;
+	free = max_t(size_t, free, 16);
+	free = max_t(size_t, free, prio_buckets(ca) + 4);
+
+	if (!init_fifo(&ca->free,	free, GFP_KERNEL) ||
+	    !init_fifo(&ca->free_inc,	free << 2, GFP_KERNEL) ||
+	    !init_fifo(&ca->unused,	free << 2, GFP_KERNEL) ||
+	    !init_heap(&ca->heap,	free << 3, GFP_KERNEL) ||
+	    !(ca->discard_page	= alloc_page(__GFP_ZERO|GFP_KERNEL)) ||
+	    !(ca->buckets	= vmalloc(sizeof(struct bucket) *
+					  ca->sb.nbuckets)) ||
+	    !(ca->prio_buckets	= kzalloc(sizeof(uint64_t) * prio_buckets(ca) *
+					  2, GFP_KERNEL)) ||
+	    !(ca->disk_buckets	= alloc_bucket_pages(GFP_KERNEL, ca)))
+		goto err;
+
+	ca->prio_next = ca->prio_buckets + prio_buckets(ca);
+
+	memset(ca->buckets, 0, ca->sb.nbuckets * sizeof(struct bucket));
+	for_each_bucket(b, ca)
+		atomic_set(&b->pin, 0);
+
+	if (bch_alloc_discards(ca))
+		goto err;
+
+	return 0;
+err:
+	kobject_put(&ca->kobj);
+	return -ENOMEM;
+}
+
+static const char *register_cache(struct cache_sb *sb, struct page *sb_page,
+				  struct block_device *bdev, struct cache *ca)
+{
+	char name[BDEVNAME_SIZE];
+	const char *err = "cannot allocate memory";
+
+	if (cache_alloc(sb, ca) != 0)
+		return err;
+
+	ca->sb_bio.bi_io_vec[0].bv_page = sb_page;
+	ca->bdev = bdev;
+	ca->bdev->bd_holder = ca;
+
+	if (blk_queue_discard(bdev_get_queue(ca->bdev)))
+		ca->discard = CACHE_DISCARD(&ca->sb);
+
+	err = "error creating kobject";
+	if (kobject_add(&ca->kobj, &part_to_dev(bdev->bd_part)->kobj, "bcache"))
+		goto err;
+
+	err = register_cache_set(ca);
+	if (err)
+		goto err;
+
+	printk(KERN_DEBUG "bcache: registered cache device %s\n",
+	       bdevname(bdev, name));
+
+	return NULL;
+err:
+	kobject_put(&ca->kobj);
+	printk(KERN_DEBUG "bcache: error opening %s: %s\n",
+	       bdevname(bdev, name), err);
+	/* Return NULL instead of an error because kobject_put() cleans
+	 * everything up
+	 */
+	return NULL;
+}
+
+/* Global interfaces/init */
+
+static ssize_t register_bcache(struct kobject *, struct kobj_attribute *,
+			       const char *, size_t);
+
+kobj_attribute_write(register,		register_bcache);
+kobj_attribute_write(register_quiet,	register_bcache);
+
+static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
+			       const char *buffer, size_t size)
+{
+	ssize_t ret = size;
+	const char *err = "cannot allocate memory";
+	char *path = NULL;
+	struct cache_sb *sb = NULL;
+	struct block_device *bdev = NULL;
+	struct page *sb_page = NULL;
+
+	if (!try_module_get(THIS_MODULE))
+		return -EBUSY;
+
+	mutex_lock(&register_lock);
+
+	if (!(path = kstrndup(buffer, size, GFP_KERNEL)) ||
+	    !(sb = kmalloc(sizeof(struct cache_sb), GFP_KERNEL)))
+		goto err;
+
+	err = "failed to open device";
+	bdev = blkdev_get_by_path(strim(path),
+				  FMODE_READ|FMODE_WRITE|FMODE_EXCL,
+				  sb);
+	if (bdev == ERR_PTR(-EBUSY))
+		err = "device busy";
+
+	if (IS_ERR(bdev) ||
+	    set_blocksize(bdev, 4096))
+		goto err;
+
+	err = read_super(sb, bdev, &sb_page);
+	if (err)
+		goto err_close;
+
+	if (sb->version == CACHE_BACKING_DEV) {
+		struct cached_dev *dc = kzalloc(sizeof(*dc), GFP_KERNEL);
+
+		err = register_bdev(sb, sb_page, bdev, dc);
+	} else {
+		struct cache *ca = kzalloc(sizeof(*ca), GFP_KERNEL);
+
+		err = register_cache(sb, sb_page, bdev, ca);
+	}
+
+	if (err) {
+		/* register_(bdev|cache) will only return an error if they
+		 * didn't get far enough to create the kobject - if they did,
+		 * the kobject destructor will do this cleanup.
+		 */
+		put_page(sb_page);
+err_close:
+		blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
+err:
+		if (attr != &ksysfs_register_quiet)
+			printk(KERN_DEBUG "bcache: error opening %s: %s\n",
+			       path, err);
+		ret = -EINVAL;
+	}
+
+	kfree(sb);
+	kfree(path);
+	mutex_unlock(&register_lock);
+	module_put(THIS_MODULE);
+	return ret;
+}
+
+static int bcache_reboot(struct notifier_block *n, unsigned long code, void *x)
+{
+	if (code == SYS_DOWN ||
+	    code == SYS_HALT ||
+	    code == SYS_POWER_OFF) {
+		DEFINE_WAIT(wait);
+		unsigned long start = jiffies;
+		bool stopped = false;
+
+		struct cache_set *c, *tc;
+		struct cached_dev *dc, *tdc;
+
+		mutex_lock(&register_lock);
+
+		if (list_empty(&cache_sets) && list_empty(&uncached_devices))
+			goto out;
+
+		printk(KERN_INFO "bcache: Stopping all devices:\n");
+
+		list_for_each_entry_safe(c, tc, &cache_sets, list)
+			cache_set_stop(c);
+
+		list_for_each_entry_safe(dc, tdc, &uncached_devices, list)
+			bcache_device_stop(&dc->disk);
+
+		/* What's a condition variable? */
+		while (1) {
+			long timeout = start + 2 * HZ - jiffies;
+
+			stopped = list_empty(&cache_sets) &&
+				list_empty(&uncached_devices);
+
+			if (timeout < 0 || stopped)
+				break;
+
+			prepare_to_wait(&unregister_wait, &wait,
+					TASK_UNINTERRUPTIBLE);
+
+			mutex_unlock(&register_lock);
+			schedule_timeout(timeout);
+			mutex_lock(&register_lock);
+		}
+
+		finish_wait(&unregister_wait, &wait);
+
+		printk(KERN_INFO "bcache: %s\n", stopped
+		       ? "All devices stopped"
+		       : "Timeout waiting for devices to be closed");
+out:
+		mutex_unlock(&register_lock);
+	}
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block reboot = {
+	.notifier_call	= bcache_reboot,
+	.priority	= INT_MAX, /* before any real devices */
+};
+
+static void bcache_exit(void)
+{
+	bch_debug_exit();
+	bch_writeback_exit();
+	bch_request_exit();
+	bch_btree_exit();
+	if (bcache_kobj)
+		kobject_put(bcache_kobj);
+	if (bcache_wq)
+		destroy_workqueue(bcache_wq);
+	unregister_blkdev(bcache_major, "bcache");
+	unregister_reboot_notifier(&reboot);
+}
+
+static int __init bcache_init(void)
+{
+	static const struct attribute *files[] = {
+		&ksysfs_register.attr,
+		&ksysfs_register_quiet.attr,
+		NULL
+	};
+
+	mutex_init(&register_lock);
+	init_waitqueue_head(&unregister_wait);
+	register_reboot_notifier(&reboot);
+
+	bcache_major = register_blkdev(0, "bcache");
+	if (bcache_major < 0)
+		return bcache_major;
+
+	if (!(bcache_wq = create_workqueue("bcache")) ||
+	    !(bcache_kobj = kobject_create_and_add("bcache", fs_kobj)) ||
+	    sysfs_create_files(bcache_kobj, files) ||
+	    bch_btree_init() ||
+	    bch_request_init() ||
+	    bch_writeback_init() ||
+	    bch_debug_init(bcache_kobj))
+		goto err;
+
+	return 0;
+err:
+	bcache_exit();
+	return -ENOMEM;
+}
+
+module_exit(bcache_exit);
+module_init(bcache_init);
diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c
new file mode 100644
index 0000000..1800b48
--- /dev/null
+++ b/drivers/md/bcache/sysfs.c
@@ -0,0 +1,812 @@
+write_attribute(attach);
+write_attribute(detach);
+write_attribute(unregister);
+write_attribute(stop);
+write_attribute(clear_stats);
+write_attribute(trigger_gc);
+write_attribute(prune_cache);
+write_attribute(flash_vol_create);
+
+read_attribute(bucket_size);
+read_attribute(block_size);
+read_attribute(nbuckets);
+read_attribute(tree_depth);
+read_attribute(root_usage_percent);
+read_attribute(priority_stats);
+read_attribute(btree_cache_size);
+read_attribute(btree_cache_max_chain);
+read_attribute(cache_available_percent);
+read_attribute(written);
+read_attribute(btree_written);
+read_attribute(metadata_written);
+read_attribute(active_journal_entries);
+
+sysfs_time_stats_attribute(btree_gc,	sec, ms);
+sysfs_time_stats_attribute(btree_split, sec, us);
+sysfs_time_stats_attribute(btree_sort,	ms,  us);
+sysfs_time_stats_attribute(btree_read,	ms,  us);
+sysfs_time_stats_attribute(try_harder,	ms,  us);
+
+read_attribute(btree_nodes);
+read_attribute(btree_used_percent);
+read_attribute(average_key_size);
+read_attribute(dirty_data);
+read_attribute(bset_tree_stats);
+
+read_attribute(state);
+read_attribute(cache_read_races);
+read_attribute(writeback_keys_done);
+read_attribute(writeback_keys_failed);
+read_attribute(io_errors);
+read_attribute(congested);
+rw_attribute(congested_read_threshold_us);
+rw_attribute(congested_write_threshold_us);
+
+rw_attribute(sequential_cutoff);
+rw_attribute(sequential_merge);
+rw_attribute(data_csum);
+rw_attribute(cache_mode);
+rw_attribute(writeback_metadata);
+rw_attribute(writeback_running);
+rw_attribute(writeback_percent);
+rw_attribute(writeback_delay);
+rw_attribute(writeback_rate);
+
+rw_attribute(writeback_rate_update_seconds);
+rw_attribute(writeback_rate_d_term);
+rw_attribute(writeback_rate_p_term_inverse);
+rw_attribute(writeback_rate_d_smooth);
+read_attribute(writeback_rate_debug);
+
+rw_attribute(synchronous);
+rw_attribute(journal_delay_ms);
+rw_attribute(discard);
+rw_attribute(running);
+rw_attribute(label);
+rw_attribute(readahead);
+rw_attribute(io_error_limit);
+rw_attribute(io_error_halflife);
+rw_attribute(verify);
+rw_attribute(key_merging_disabled);
+rw_attribute(gc_always_rewrite);
+rw_attribute(freelist_percent);
+rw_attribute(cache_replacement_policy);
+rw_attribute(btree_shrinker_disabled);
+rw_attribute(copy_gc_enabled);
+rw_attribute(size);
+
+static void unregister_fake(struct kobject *k)
+{
+}
+
+SHOW(__cached_dev)
+{
+	struct cached_dev *dc = container_of(kobj, struct cached_dev, disk.kobj);
+	const char *states[] = { "no cache", "clean", "dirty", "inconsistent" };
+
+#define var(stat)		(dc->stat)
+
+	if (attr == &sysfs_cache_mode)
+		return snprint_string_list(buf, PAGE_SIZE,
+					   bch_cache_modes + 1,
+					   BDEV_CACHE_MODE(&dc->sb));
+
+	sysfs_printf(data_csum,		"%i", dc->disk.data_csum);
+	var_printf(verify,		"%i");
+	var_printf(writeback_metadata,	"%i");
+	var_printf(writeback_running,	"%i");
+	var_print(writeback_delay);
+	var_print(writeback_percent);
+	sysfs_print(writeback_rate,	dc->writeback_rate.rate);
+
+	var_print(writeback_rate_update_seconds);
+	var_print(writeback_rate_d_term);
+	var_print(writeback_rate_p_term_inverse);
+	var_print(writeback_rate_d_smooth);
+
+	if (attr == &sysfs_writeback_rate_debug) {
+		char dirty[20];
+		char derivative[20];
+		char target[20];
+
+		sprintf(dirty, "%hli",
+			atomic_long_read(&dc->disk.sectors_dirty) << 9);
+		sprintf(derivative, "%hlli",
+			dc->writeback_rate_derivative << 9);
+		sprintf(target, "%hllu",
+			dc->writeback_rate_target << 9);
+
+		return sprintf(buf,
+			       "rate:\t\t%u\n"
+			       "change:\t\t%i\n"
+			       "dirty:\t\t%s\n"
+			       "derivative:\t%s\n"
+			       "target:\t\t%s\n",
+			       dc->writeback_rate.rate,
+			       dc->writeback_rate_change,
+			       dirty, derivative, target);
+	}
+
+	sysfs_printf(dirty_data,	"%hli",
+		     atomic_long_read(&dc->disk.sectors_dirty) << 9);
+
+	var_printf(sequential_merge,	"%i");
+	var_printf(sequential_cutoff,	"%hi");
+	var_printf(readahead,		"%hi");
+
+	sysfs_print(running,		atomic_read(&dc->running));
+	sysfs_print(state,		states[BDEV_STATE(&dc->sb)]);
+
+	if (attr == &sysfs_label) {
+		memcpy(buf, dc->sb.label, SB_LABEL_SIZE);
+		buf[SB_LABEL_SIZE + 1] = '\0';
+		strcat(buf, "\n");
+		return strlen(buf);
+	}
+
+#undef var
+	return 0;
+}
+SHOW_LOCKED(cached_dev)
+
+STORE(__cached_dev)
+{
+	struct cached_dev *dc = container_of(kobj, struct cached_dev, disk.kobj);
+	unsigned v = size;
+	struct cache_set *c;
+
+#define d_strtoul(var)		sysfs_strtoul(var, dc->var)
+#define d_strtoi_h(var)		sysfs_hatoi(var, dc->var)
+
+	sysfs_strtoul(data_csum,	dc->disk.data_csum);
+	d_strtoul(verify);
+	d_strtoul(writeback_metadata);
+	d_strtoul(writeback_running);
+	d_strtoul(writeback_delay);
+	sysfs_strtoul_clamp(writeback_rate, dc->writeback_rate.rate, 1, 1000000);
+	sysfs_strtoul_clamp(writeback_percent, dc->writeback_percent, 0, 40);
+
+	d_strtoul(writeback_rate_update_seconds);
+	d_strtoul(writeback_rate_d_term);
+	d_strtoul(writeback_rate_p_term_inverse);
+	sysfs_strtoul_clamp(writeback_rate_p_term_inverse,
+			    dc->writeback_rate_p_term_inverse, 1, INT_MAX);
+	d_strtoul(writeback_rate_d_smooth);
+
+	d_strtoul(sequential_merge);
+	d_strtoi_h(sequential_cutoff);
+	d_strtoi_h(readahead);
+
+	if (attr == &sysfs_clear_stats)
+		bch_cache_accounting_clear(&dc->accounting);
+
+	if (attr == &sysfs_running &&
+	    strtoul_or_return(buf))
+		cached_dev_run(dc);
+
+	if (attr == &sysfs_cache_mode) {
+		ssize_t v = read_string_list(buf, bch_cache_modes + 1);
+
+		if (v < 0)
+			return v;
+
+		if ((unsigned) v != BDEV_CACHE_MODE(&dc->sb)) {
+			SET_BDEV_CACHE_MODE(&dc->sb, v);
+			bch_write_bdev_super(dc, NULL);
+		}
+	}
+
+	if (attr == &sysfs_label) {
+		memcpy(dc->sb.label, buf, SB_LABEL_SIZE);
+		bch_write_bdev_super(dc, NULL);
+		if (dc->disk.c) {
+			memcpy(dc->disk.c->uuids[dc->disk.id].label,
+			       buf, SB_LABEL_SIZE);
+			uuid_write(dc->disk.c);
+		}
+	}
+
+	if (attr == &sysfs_attach) {
+		if (parse_uuid(buf, dc->sb.set_uuid) < 16)
+			return -EINVAL;
+
+		list_for_each_entry(c, &cache_sets, list) {
+			v = cached_dev_attach(dc, c);
+			if (!v)
+				return size;
+		}
+		size = v;
+	}
+
+	if (attr == &sysfs_detach && dc->disk.c)
+		cached_dev_detach(dc);
+
+	if (attr == &sysfs_stop)
+		bcache_device_stop(&dc->disk);
+
+	return size;
+}
+
+STORE(cached_dev)
+{
+	struct cached_dev *dc = container_of(kobj, struct cached_dev,
+					     disk.kobj);
+
+	mutex_lock(&register_lock);
+	size = __cached_dev_store(kobj, attr, buf, size);
+
+	if (attr == &sysfs_writeback_running)
+		bch_writeback_queue(dc);
+
+	if (attr == &sysfs_writeback_percent)
+		schedule_delayed_work(&dc->writeback_rate_update,
+				      dc->writeback_rate_update_seconds * HZ);
+
+	mutex_unlock(&register_lock);
+	return size;
+}
+
+static void cached_dev_kobject_init(struct cached_dev *dc)
+{
+	static struct attribute *cached_dev_files[] = {
+		&sysfs_attach,
+		&sysfs_detach,
+		&sysfs_stop,
+#if 0
+		&sysfs_data_csum,
+#endif
+		&sysfs_cache_mode,
+		&sysfs_writeback_metadata,
+		&sysfs_writeback_running,
+		&sysfs_writeback_delay,
+		&sysfs_writeback_percent,
+		&sysfs_writeback_rate,
+		&sysfs_writeback_rate_update_seconds,
+		&sysfs_writeback_rate_d_term,
+		&sysfs_writeback_rate_p_term_inverse,
+		&sysfs_writeback_rate_d_smooth,
+		&sysfs_writeback_rate_debug,
+		&sysfs_dirty_data,
+		&sysfs_sequential_cutoff,
+		&sysfs_sequential_merge,
+		&sysfs_clear_stats,
+		&sysfs_running,
+		&sysfs_state,
+		&sysfs_label,
+		&sysfs_readahead,
+#ifdef CONFIG_BCACHE_DEBUG
+		&sysfs_verify,
+#endif
+		NULL
+	};
+	KTYPE(cached_dev, __cached_dev_free);
+
+	kobject_init(&dc->disk.kobj, &cached_dev_obj);
+}
+
+SHOW(flash_dev)
+{
+	struct bcache_device *d = container_of(kobj, struct bcache_device,
+					       kobj);
+	struct uuid_entry *u = &d->c->uuids[d->id];
+
+	sysfs_printf(data_csum,	"%i", d->data_csum);
+	sysfs_printf(size,	"%hllu", u->sectors << 9);
+
+	if (attr == &sysfs_label) {
+		memcpy(buf, u->label, SB_LABEL_SIZE);
+		buf[SB_LABEL_SIZE + 1] = '\0';
+		strcat(buf, "\n");
+		return strlen(buf);
+	}
+
+	return 0;
+}
+
+STORE(__flash_dev)
+{
+	struct bcache_device *d = container_of(kobj, struct bcache_device,
+					       kobj);
+	struct uuid_entry *u = &d->c->uuids[d->id];
+
+	sysfs_strtoul(data_csum,	d->data_csum);
+
+	if (attr == &sysfs_size) {
+		uint64_t v;
+		strtoi_h_or_return(buf, v);
+
+		u->sectors = v >> 9;
+		uuid_write(d->c);
+		set_capacity(d->disk, u->sectors);
+	}
+
+	if (attr == &sysfs_label) {
+		memcpy(u->label, buf, SB_LABEL_SIZE);
+		uuid_write(d->c);
+	}
+
+	if (attr == &sysfs_unregister) {
+		atomic_set(&d->detaching, 1);
+		bcache_device_stop(d);
+	}
+
+	return size;
+}
+STORE_LOCKED(flash_dev)
+
+static void flash_dev_kobject_init(struct bcache_device *d)
+{
+	static struct attribute *flash_dev_files[] = {
+		&sysfs_unregister,
+#if 0
+		&sysfs_data_csum,
+#endif
+		&sysfs_label,
+		&sysfs_size,
+		NULL
+	};
+	KTYPE(flash_dev, __flash_dev_free);
+
+	kobject_init(&d->kobj, &flash_dev_obj);
+}
+
+SHOW(__cache_set)
+{
+	unsigned root_usage(struct cache_set *c)
+	{
+		unsigned bytes = 0;
+		struct bkey *k;
+		struct btree *b;
+		goto lock_root;
+
+		do {
+			rw_unlock(false, b);
+lock_root:
+			b = c->root;
+			rw_lock(false, b, b->level);
+		} while (b != c->root);
+
+		for_each_key_filter(b, k, bch_ptr_bad)
+			bytes += bkey_bytes(k);
+
+		rw_unlock(false, b);
+
+		return (bytes * 100) / btree_bytes(c);
+	}
+
+	size_t cache_size(struct cache_set *c)
+	{
+		size_t ret = 0;
+		struct btree *b;
+
+		mutex_lock(&c->bucket_lock);
+		list_for_each_entry(b, &c->btree_cache, list)
+			ret += 1 << (b->page_order + PAGE_SHIFT);
+
+		mutex_unlock(&c->bucket_lock);
+		return ret;
+	}
+
+	unsigned cache_max_chain(struct cache_set *c)
+	{
+		unsigned ret = 0;
+		mutex_lock(&c->bucket_lock);
+
+		for (struct hlist_head *h = c->bucket_hash;
+		     h < c->bucket_hash + (1 << BUCKET_HASH_BITS);
+		     h++) {
+			unsigned i = 0;
+			struct hlist_node *p;
+
+			hlist_for_each(p, h)
+				i++;
+
+			ret = max(ret, i);
+		}
+
+		mutex_unlock(&c->bucket_lock);
+		return ret;
+	}
+
+	unsigned btree_used(struct cache_set *c)
+	{
+		return div64_u64(c->gc_stats.key_bytes * 100,
+				 (c->gc_stats.nodes ?: 1) * btree_bytes(c));
+	}
+
+	unsigned average_key_size(struct cache_set *c)
+	{
+		return c->gc_stats.nkeys
+			? div64_u64(c->gc_stats.data, c->gc_stats.nkeys)
+			: 0;
+	}
+
+	struct cache_set *c = container_of(kobj, struct cache_set, kobj);
+
+	sysfs_print(synchronous,		CACHE_SYNC(&c->sb));
+	sysfs_print(journal_delay_ms,		c->journal_delay_ms);
+	sysfs_printf(bucket_size,		"%hu", bucket_bytes(c));
+	sysfs_printf(block_size,		"%hu", block_bytes(c));
+	sysfs_print(tree_depth,			c->root->level);
+	sysfs_print(root_usage_percent,		root_usage(c));
+
+	sysfs_printf(btree_cache_size,		"%hzu", cache_size(c));
+	sysfs_print(btree_cache_max_chain,	cache_max_chain(c));
+	sysfs_print(cache_available_percent,	100 - c->gc_stats.in_use);
+
+	sysfs_print_time_stats(&c->btree_gc_time,	btree_gc, sec, ms);
+	sysfs_print_time_stats(&c->btree_split_time,	btree_split, sec, us);
+	sysfs_print_time_stats(&c->sort_time,		btree_sort, ms, us);
+	sysfs_print_time_stats(&c->btree_read_time,	btree_read, ms, us);
+	sysfs_print_time_stats(&c->try_harder_time,	try_harder, ms, us);
+
+	sysfs_print(btree_used_percent,	btree_used(c));
+	sysfs_print(btree_nodes,	c->gc_stats.nodes);
+	sysfs_printf(dirty_data,	"%hllu", c->gc_stats.dirty);
+	sysfs_printf(average_key_size,	"%hu", average_key_size(c));
+
+	sysfs_print(cache_read_races,
+		    atomic_long_read(&c->cache_read_races));
+
+	sysfs_print(writeback_keys_done,
+		    atomic_long_read(&c->writeback_keys_done));
+	sysfs_print(writeback_keys_failed,
+		    atomic_long_read(&c->writeback_keys_failed));
+
+	/* See count_io_errors for why 88 */
+	sysfs_print(io_error_halflife,	c->error_decay * 88);
+	sysfs_print(io_error_limit,	c->error_limit >> IO_ERROR_SHIFT);
+
+	sysfs_printf(congested,			"%hllu",
+		     ((uint64_t) bch_get_congested(c)) << 9);
+	sysfs_print(congested_read_threshold_us,
+		    c->congested_read_threshold_us);
+	sysfs_print(congested_write_threshold_us,
+		    c->congested_write_threshold_us);
+
+	sysfs_print(active_journal_entries,	fifo_used(&c->journal.pin));
+	sysfs_printf(verify,			"%i", c->verify);
+	sysfs_printf(key_merging_disabled,	"%i", c->key_merging_disabled);
+	sysfs_printf(gc_always_rewrite,		"%i", c->gc_always_rewrite);
+	sysfs_printf(btree_shrinker_disabled,	"%i", c->shrinker_disabled);
+	sysfs_printf(copy_gc_enabled,		"%i", c->copy_gc_enabled);
+
+	if (attr == &sysfs_bset_tree_stats)
+		return bch_bset_print_stats(c, buf);
+
+	return 0;
+}
+SHOW_LOCKED(cache_set)
+
+STORE(__cache_set)
+{
+	struct cache_set *c = container_of(kobj, struct cache_set, kobj);
+
+	if (attr == &sysfs_unregister)
+		cache_set_unregister(c);
+
+	if (attr == &sysfs_stop)
+		cache_set_stop(c);
+
+	if (attr == &sysfs_synchronous) {
+		bool sync = strtoul_or_return(buf);
+
+		if (sync != CACHE_SYNC(&c->sb)) {
+			SET_CACHE_SYNC(&c->sb, sync);
+			bcache_write_super(c);
+		}
+	}
+
+	if (attr == &sysfs_flash_vol_create) {
+		int r;
+		uint64_t v;
+		strtoi_h_or_return(buf, v);
+
+		r = flash_dev_create(c, v);
+		if (r)
+			return r;
+	}
+
+	if (attr == &sysfs_clear_stats) {
+		atomic_long_set(&c->writeback_keys_done,	0);
+		atomic_long_set(&c->writeback_keys_failed,	0);
+
+		memset(&c->gc_stats, 0, sizeof(struct gc_stat));
+		bch_cache_accounting_clear(&c->accounting);
+	}
+
+	if (attr == &sysfs_trigger_gc)
+		bch_queue_gc(c);
+
+	if (attr == &sysfs_prune_cache) {
+		struct shrink_control sc;
+		sc.gfp_mask = GFP_KERNEL;
+		sc.nr_to_scan = strtoul_or_return(buf);
+		c->shrink.shrink(&c->shrink, &sc);
+	}
+
+	sysfs_strtoul(congested_read_threshold_us,
+		      c->congested_read_threshold_us);
+	sysfs_strtoul(congested_write_threshold_us,
+		      c->congested_write_threshold_us);
+
+	if (attr == &sysfs_io_error_limit)
+		c->error_limit = strtoul_or_return(buf) << IO_ERROR_SHIFT;
+
+	/* See count_io_errors() for why 88 */
+	if (attr == &sysfs_io_error_halflife)
+		c->error_decay = strtoul_or_return(buf) / 88;
+
+	sysfs_strtoul(journal_delay_ms,		c->journal_delay_ms);
+	sysfs_strtoul(verify,			c->verify);
+	sysfs_strtoul(key_merging_disabled,	c->key_merging_disabled);
+	sysfs_strtoul(gc_always_rewrite,	c->gc_always_rewrite);
+	sysfs_strtoul(btree_shrinker_disabled,	c->shrinker_disabled);
+	sysfs_strtoul(copy_gc_enabled,		c->copy_gc_enabled);
+
+	return size;
+}
+STORE_LOCKED(cache_set)
+
+SHOW(cache_set_internal)
+{
+	struct cache_set *c = container_of(kobj, struct cache_set, internal);
+	return cache_set_show(&c->kobj, attr, buf);
+}
+
+STORE(cache_set_internal)
+{
+	struct cache_set *c = container_of(kobj, struct cache_set, internal);
+	return cache_set_store(&c->kobj, attr, buf, size);
+}
+
+static void cache_set_kobject_init(struct cache_set *c)
+{
+	static struct attribute *cache_set_files[] = {
+		&sysfs_unregister,
+		&sysfs_stop,
+		&sysfs_synchronous,
+		&sysfs_journal_delay_ms,
+		&sysfs_flash_vol_create,
+
+		&sysfs_bucket_size,
+		&sysfs_block_size,
+		&sysfs_tree_depth,
+		&sysfs_root_usage_percent,
+		&sysfs_btree_cache_size,
+		&sysfs_cache_available_percent,
+
+		&sysfs_average_key_size,
+		&sysfs_dirty_data,
+
+		&sysfs_io_error_limit,
+		&sysfs_io_error_halflife,
+		&sysfs_congested,
+		&sysfs_congested_read_threshold_us,
+		&sysfs_congested_write_threshold_us,
+		&sysfs_clear_stats,
+		NULL
+	};
+	KTYPE(cache_set, __cache_set_free);
+
+	static struct attribute *cache_set_internal_files[] = {
+		&sysfs_active_journal_entries,
+
+		sysfs_time_stats_attribute_list(btree_gc, sec, ms)
+		sysfs_time_stats_attribute_list(btree_split, sec, us)
+		sysfs_time_stats_attribute_list(btree_sort, ms, us)
+		sysfs_time_stats_attribute_list(btree_read, ms, us)
+		sysfs_time_stats_attribute_list(try_harder, ms, us)
+
+		&sysfs_btree_nodes,
+		&sysfs_btree_used_percent,
+		&sysfs_btree_cache_max_chain,
+
+		&sysfs_bset_tree_stats,
+		&sysfs_cache_read_races,
+		&sysfs_writeback_keys_done,
+		&sysfs_writeback_keys_failed,
+
+		&sysfs_trigger_gc,
+		&sysfs_prune_cache,
+#ifdef CONFIG_BCACHE_DEBUG
+		&sysfs_verify,
+		&sysfs_key_merging_disabled,
+#endif
+		&sysfs_gc_always_rewrite,
+		&sysfs_btree_shrinker_disabled,
+		&sysfs_copy_gc_enabled,
+		NULL
+	};
+	KTYPE(cache_set_internal, unregister_fake);
+
+	kobject_init(&c->kobj, &cache_set_obj);
+	kobject_init(&c->internal, &cache_set_internal_obj);
+}
+
+SHOW(__cache)
+{
+	struct cache *ca = container_of(kobj, struct cache, kobj);
+
+	sysfs_printf(bucket_size,	"%hu", bucket_bytes(ca));
+	sysfs_printf(block_size,	"%hu", block_bytes(ca));
+	sysfs_print(nbuckets,		ca->sb.nbuckets);
+	sysfs_print(discard,		ca->discard);
+	sysfs_printf(written,		"%hli",
+		     atomic_long_read(&ca->sectors_written) << 9);
+	sysfs_printf(btree_written,	"%hli",
+		     atomic_long_read(&ca->btree_sectors_written) << 9);
+	sysfs_printf(metadata_written,	"%hli",
+		     (atomic_long_read(&ca->meta_sectors_written) +
+		      atomic_long_read(&ca->btree_sectors_written)) << 9);
+
+	sysfs_print(io_errors,
+		    atomic_read(&ca->io_errors) >> IO_ERROR_SHIFT);
+
+	sysfs_print(freelist_percent, ca->free.size * 100 /
+		    ((size_t) ca->sb.nbuckets));
+
+	if (attr == &sysfs_cache_replacement_policy)
+		return snprint_string_list(buf, PAGE_SIZE,
+					   cache_replacement_policies,
+					   CACHE_REPLACEMENT(&ca->sb));
+
+	if (attr == &sysfs_priority_stats) {
+		int cmp(const void *l, const void *r)
+		{	return *((uint16_t *) r) - *((uint16_t *) l); }
+
+		/* Number of quantiles we compute */
+		const unsigned nq = 31;
+
+		size_t n = ca->sb.nbuckets, i, unused, btree;
+		uint64_t sum = 0;
+		uint16_t q[nq], *p, *cached;
+		ssize_t ret;
+
+		cached = p = vmalloc(ca->sb.nbuckets * sizeof(uint16_t));
+		if (!p)
+			return -ENOMEM;
+
+		mutex_lock(&ca->set->bucket_lock);
+		for (i = ca->sb.first_bucket; i < n; i++)
+			p[i] = ca->buckets[i].prio;
+		mutex_unlock(&ca->set->bucket_lock);
+
+		sort(p, n, sizeof(uint16_t), cmp, NULL);
+
+		while (n &&
+		       !cached[n - 1])
+			--n;
+
+		unused = ca->sb.nbuckets - n;
+
+		while (cached < p + n &&
+		       *cached == BTREE_PRIO)
+			cached++;
+
+		btree = cached - p;
+		n -= btree;
+
+		for (i = 0; i < n; i++)
+			sum += INITIAL_PRIO - cached[i];
+
+		if (n)
+			do_div(sum, n);
+
+		for (i = 0; i < nq; i++)
+			q[i] = INITIAL_PRIO - cached[n * (i + 1) / (nq + 1)];
+
+		vfree(p);
+
+		ret = snprintf(buf, PAGE_SIZE,
+			       "Unused:		%zu%%\n"
+			       "Metadata:	%zu%%\n"
+			       "Average:	%llu\n"
+			       "Sectors per Q:	%zu\n"
+			       "Quantiles:	[",
+			       unused * 100 / (size_t) ca->sb.nbuckets,
+			       btree * 100 / (size_t) ca->sb.nbuckets, sum,
+			       n * ca->sb.bucket_size / (nq + 1));
+
+		for (i = 0; i < nq && ret < (ssize_t) PAGE_SIZE; i++)
+			ret += snprintf(buf + ret, PAGE_SIZE - ret,
+					i < nq - 1 ? "%u " : "%u]\n", q[i]);
+
+		buf[PAGE_SIZE - 1] = '\0';
+		return ret;
+	}
+
+	return 0;
+}
+SHOW_LOCKED(cache)
+
+STORE(__cache)
+{
+	struct cache *ca = container_of(kobj, struct cache, kobj);
+
+	if (attr == &sysfs_discard) {
+		bool v = strtoul_or_return(buf);
+
+		if (blk_queue_discard(bdev_get_queue(ca->bdev)))
+			ca->discard = v;
+
+		if (v != CACHE_DISCARD(&ca->sb)) {
+			SET_CACHE_DISCARD(&ca->sb, v);
+			bcache_write_super(ca->set);
+		}
+	}
+
+	if (attr == &sysfs_cache_replacement_policy) {
+		ssize_t v = read_string_list(buf, cache_replacement_policies);
+
+		if (v < 0)
+			return v;
+
+		if ((unsigned) v != CACHE_REPLACEMENT(&ca->sb)) {
+			mutex_lock(&ca->set->bucket_lock);
+			SET_CACHE_REPLACEMENT(&ca->sb, v);
+			mutex_unlock(&ca->set->bucket_lock);
+
+			bcache_write_super(ca->set);
+		}
+	}
+
+	if (attr == &sysfs_freelist_percent) {
+		DECLARE_FIFO(long, free);
+		long i;
+		size_t p = strtoul_or_return(buf);
+
+		p = clamp_t(size_t,
+			    ((size_t) ca->sb.nbuckets * p) / 100,
+			    roundup_pow_of_two(ca->sb.nbuckets) >> 9,
+			    ca->sb.nbuckets / 2);
+
+		if (!init_fifo_exact(&free, p, GFP_KERNEL))
+			return -ENOMEM;
+
+		mutex_lock(&ca->set->bucket_lock);
+
+		fifo_move(&free, &ca->free);
+		fifo_swap(&free, &ca->free);
+
+		mutex_unlock(&ca->set->bucket_lock);
+
+		while (fifo_pop(&free, i))
+			atomic_dec(&ca->buckets[i].pin);
+
+		free_fifo(&free);
+	}
+
+	if (attr == &sysfs_clear_stats) {
+		atomic_long_set(&ca->sectors_written, 0);
+		atomic_long_set(&ca->btree_sectors_written, 0);
+		atomic_long_set(&ca->meta_sectors_written, 0);
+		atomic_set(&ca->io_count, 0);
+		atomic_set(&ca->io_errors, 0);
+	}
+
+	return size;
+}
+STORE_LOCKED(cache)
+
+static void cache_kobject_init(struct cache *ca)
+{
+	static struct attribute *cache_files[] = {
+		&sysfs_bucket_size,
+		&sysfs_block_size,
+		&sysfs_nbuckets,
+		&sysfs_priority_stats,
+		&sysfs_discard,
+		&sysfs_written,
+		&sysfs_btree_written,
+		&sysfs_metadata_written,
+		&sysfs_io_errors,
+		&sysfs_clear_stats,
+		&sysfs_freelist_percent,
+		&sysfs_cache_replacement_policy,
+		NULL
+	};
+	KTYPE(cache, cache_free);
+
+	kobject_init(&ca->kobj, &cache_obj);
+}
diff --git a/drivers/md/bcache/sysfs.h b/drivers/md/bcache/sysfs.h
new file mode 100644
index 0000000..1805f1e
--- /dev/null
+++ b/drivers/md/bcache/sysfs.h
@@ -0,0 +1,91 @@
+#ifndef _BCACHE_SYSFS_H_
+#define _BCACHE_SYSFS_H_
+
+#define KTYPE(type, _release)						\
+static const struct sysfs_ops type ## _ops = {				\
+	.show		= type ## _show,				\
+	.store		= type ## _store				\
+};									\
+static struct kobj_type type ## _obj = {				\
+	.release	= _release,					\
+	.sysfs_ops	= &type ## _ops,				\
+	.default_attrs	= type ## _files				\
+}
+
+#define SHOW(fn)							\
+static ssize_t fn ## _show(struct kobject *kobj, struct attribute *attr,\
+			   char *buf)					\
+
+#define STORE(fn)							\
+static ssize_t fn ## _store(struct kobject *kobj, struct attribute *attr,\
+			    const char *buf, size_t size)		\
+
+#define SHOW_LOCKED(fn)							\
+SHOW(fn)								\
+{									\
+	ssize_t ret;							\
+	mutex_lock(&register_lock);					\
+	ret = __ ## fn ## _show(kobj, attr, buf);			\
+	mutex_unlock(&register_lock);					\
+	return ret;							\
+}
+
+#define STORE_LOCKED(fn)						\
+STORE(fn)								\
+{									\
+	ssize_t ret;							\
+	mutex_lock(&register_lock);					\
+	ret = __ ## fn ## _store(kobj, attr, buf, size);		\
+	mutex_unlock(&register_lock);					\
+	return ret;							\
+}
+
+#define __sysfs_attribute(_name, _mode)					\
+	static struct attribute sysfs_##_name =				\
+		{ .name = #_name, .mode = _mode }
+
+#define write_attribute(n)	__sysfs_attribute(n, S_IWUSR)
+#define read_attribute(n)	__sysfs_attribute(n, S_IRUGO)
+#define rw_attribute(n)		__sysfs_attribute(n, S_IRUGO|S_IWUSR)
+
+#define sysfs_printf(file, fmt, ...)					\
+	if (attr == &sysfs_ ## file)					\
+		return snprintf(buf, PAGE_SIZE, fmt "\n", __VA_ARGS__)
+
+#define sysfs_print(file, var)						\
+	if (attr == &sysfs_ ## file)					\
+		return snprint(buf, PAGE_SIZE, var)
+
+#define var_printf(_var, fmt)	sysfs_printf(_var, fmt, var(_var))
+#define var_print(_var)		sysfs_print(_var, var(_var))
+
+#define sysfs_strtoul(file, var)					\
+	if (attr == &sysfs_ ## file)					\
+		return strtoul_safe(buf, var) ?: (ssize_t) size;
+
+#define sysfs_strtoul_clamp(file, var, min, max)			\
+	if (attr == &sysfs_ ## file)					\
+		return strtoul_safe_clamp(buf, var, min, max)		\
+			?: (ssize_t) size;
+
+#define strtoul_or_return(cp)						\
+({									\
+	unsigned long _v;						\
+	int _r = strict_strtoul(cp, 10, &_v);				\
+	if (_r)								\
+		return _r;						\
+	_v;								\
+})
+
+#define strtoi_h_or_return(cp, v)					\
+do {									\
+	int _r = strtoi_h(cp, &v);					\
+	if (_r)								\
+		return _r;						\
+} while (0)
+
+#define sysfs_hatoi(file, var)						\
+	if (attr == &sysfs_ ## file)					\
+		return strtoi_h(buf, &var) ?: (ssize_t) size;
+
+#endif  /* _BCACHE_SYSFS_H_ */
-- 
1.7.7.3

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/