From cafe563591446cf80bfbc2fe3bc72a2e36cf1060 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <koverstreet@google.com>
Date: Sat, 23 Mar 2013 16:11:31 -0700
Subject: bcache: A block layer cache

Does writethrough and writeback caching, handles unclean shutdown, and
has a bunch of other nifty features motivated by real world usage.

See the wiki at http://bcache.evilpiepirate.org for more.

Signed-off-by: Kent Overstreet <koverstreet@google.com>
---
 drivers/md/bcache/request.c | 1409 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 1409 insertions(+)
 create mode 100644 drivers/md/bcache/request.c

(limited to 'drivers/md/bcache/request.c')

diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
new file mode 100644
index 00000000000..4f552de49aa
--- /dev/null
+++ b/drivers/md/bcache/request.c
@@ -0,0 +1,1409 @@
+/*
+ * Main bcache entry point - handle a read or a write request and decide what to
+ * do with it; the make_request functions are called by the block layer.
+ *
+ * Copyright 2010, 2011 Kent Overstreet <kent.overstreet@gmail.com>
+ * Copyright 2012 Google, Inc.
+ */
+
+#include "bcache.h"
+#include "btree.h"
+#include "debug.h"
+#include "request.h"
+
+#include <linux/cgroup.h>
+#include <linux/module.h>
+#include <linux/hash.h>
+#include <linux/random.h>
+#include "blk-cgroup.h"
+
+#include <trace/events/bcache.h>
+
+#define CUTOFF_CACHE_ADD	95
+#define CUTOFF_CACHE_READA	90
+#define CUTOFF_WRITEBACK	50
+#define CUTOFF_WRITEBACK_SYNC	75
+
+struct kmem_cache *bch_search_cache;
+
+static void check_should_skip(struct cached_dev *, struct search *);
+
+/* Cgroup interface */
+
+#ifdef CONFIG_CGROUP_BCACHE
+static struct bch_cgroup bcache_default_cgroup = { .cache_mode = -1 };
+
+static struct bch_cgroup *cgroup_to_bcache(struct cgroup *cgroup)
+{
+	struct cgroup_subsys_state *css;
+	return cgroup &&
+		(css = cgroup_subsys_state(cgroup, bcache_subsys_id))
+		? container_of(css, struct bch_cgroup, css)
+		: &bcache_default_cgroup;
+}
+
+struct bch_cgroup *bch_bio_to_cgroup(struct bio *bio)
+{
+	struct cgroup_subsys_state *css = bio->bi_css
+		? cgroup_subsys_state(bio->bi_css->cgroup, bcache_subsys_id)
+		: task_subsys_state(current, bcache_subsys_id);
+
+	return css
+		? container_of(css, struct bch_cgroup, css)
+		: &bcache_default_cgroup;
+}
+
+static ssize_t cache_mode_read(struct cgroup *cgrp, struct cftype *cft,
+			struct file *file,
+			char __user *buf, size_t nbytes, loff_t *ppos)
+{
+	char tmp[1024];
+	int len = snprint_string_list(tmp, PAGE_SIZE, bch_cache_modes,
+				      cgroup_to_bcache(cgrp)->cache_mode + 1);
+
+	if (len < 0)
+		return len;
+
+	return simple_read_from_buffer(buf, nbytes, ppos, tmp, len);
+}
+
+static int cache_mode_write(struct cgroup *cgrp, struct cftype *cft,
+			    const char *buf)
+{
+	int v = read_string_list(buf, bch_cache_modes);
+	if (v < 0)
+		return v;
+
+	cgroup_to_bcache(cgrp)->cache_mode = v - 1;
+	return 0;
+}
+
+static u64 bch_verify_read(struct cgroup *cgrp, struct cftype *cft)
+{
+	return cgroup_to_bcache(cgrp)->verify;
+}
+
+static int bch_verify_write(struct cgroup *cgrp, struct cftype *cft, u64 val)
+{
+	cgroup_to_bcache(cgrp)->verify = val;
+	return 0;
+}
+
+static u64 bch_cache_hits_read(struct cgroup *cgrp, struct cftype *cft)
+{
+	struct bch_cgroup *bcachecg = cgroup_to_bcache(cgrp);
+	return atomic_read(&bcachecg->stats.cache_hits);
+}
+
+static u64 bch_cache_misses_read(struct cgroup *cgrp, struct cftype *cft)
+{
+	struct bch_cgroup *bcachecg = cgroup_to_bcache(cgrp);
+	return atomic_read(&bcachecg->stats.cache_misses);
+}
+
+static u64 bch_cache_bypass_hits_read(struct cgroup *cgrp,
+					 struct cftype *cft)
+{
+	struct bch_cgroup *bcachecg = cgroup_to_bcache(cgrp);
+	return atomic_read(&bcachecg->stats.cache_bypass_hits);
+}
+
+static u64 bch_cache_bypass_misses_read(struct cgroup *cgrp,
+					   struct cftype *cft)
+{
+	struct bch_cgroup *bcachecg = cgroup_to_bcache(cgrp);
+	return atomic_read(&bcachecg->stats.cache_bypass_misses);
+}
+
+static struct cftype bch_files[] = {
+	{
+		.name		= "cache_mode",
+		.read		= cache_mode_read,
+		.write_string	= cache_mode_write,
+	},
+	{
+		.name		= "verify",
+		.read_u64	= bch_verify_read,
+		.write_u64	= bch_verify_write,
+	},
+	{
+		.name		= "cache_hits",
+		.read_u64	= bch_cache_hits_read,
+	},
+	{
+		.name		= "cache_misses",
+		.read_u64	= bch_cache_misses_read,
+	},
+	{
+		.name		= "cache_bypass_hits",
+		.read_u64	= bch_cache_bypass_hits_read,
+	},
+	{
+		.name		= "cache_bypass_misses",
+		.read_u64	= bch_cache_bypass_misses_read,
+	},
+	{ }	/* terminate */
+};
+
+static void init_bch_cgroup(struct bch_cgroup *cg)
+{
+	cg->cache_mode = -1;
+}
+
+static struct cgroup_subsys_state *bcachecg_create(struct cgroup *cgroup)
+{
+	struct bch_cgroup *cg;
+
+	cg = kzalloc(sizeof(*cg), GFP_KERNEL);
+	if (!cg)
+		return ERR_PTR(-ENOMEM);
+	init_bch_cgroup(cg);
+	return &cg->css;
+}
+
+static void bcachecg_destroy(struct cgroup *cgroup)
+{
+	struct bch_cgroup *cg = cgroup_to_bcache(cgroup);
+	free_css_id(&bcache_subsys, &cg->css);
+	kfree(cg);
+}
+
+struct cgroup_subsys bcache_subsys = {
+	.create		= bcachecg_create,
+	.destroy	= bcachecg_destroy,
+	.subsys_id	= bcache_subsys_id,
+	.name		= "bcache",
+	.module		= THIS_MODULE,
+};
+EXPORT_SYMBOL_GPL(bcache_subsys);
+#endif
+
+static unsigned cache_mode(struct cached_dev *dc, struct bio *bio)
+{
+#ifdef CONFIG_CGROUP_BCACHE
+	int r = bch_bio_to_cgroup(bio)->cache_mode;
+	if (r >= 0)
+		return r;
+#endif
+	return BDEV_CACHE_MODE(&dc->sb);
+}
+
+static bool verify(struct cached_dev *dc, struct bio *bio)
+{
+#ifdef CONFIG_CGROUP_BCACHE
+	if (bch_bio_to_cgroup(bio)->verify)
+		return true;
+#endif
+	return dc->verify;
+}
+
+static void bio_csum(struct bio *bio, struct bkey *k)
+{
+	struct bio_vec *bv;
+	uint64_t csum = 0;
+	int i;
+
+	bio_for_each_segment(bv, bio, i) {
+		void *d = kmap(bv->bv_page) + bv->bv_offset;
+		csum = crc64_update(csum, d, bv->bv_len);
+		kunmap(bv->bv_page);
+	}
+
+	k->ptr[KEY_PTRS(k)] = csum & (~0ULL >> 1);
+}
+
+/* Insert data into cache */
+
+static void bio_invalidate(struct closure *cl)
+{
+	struct btree_op *op = container_of(cl, struct btree_op, cl);
+	struct bio *bio = op->cache_bio;
+
+	pr_debug("invalidating %i sectors from %llu",
+		 bio_sectors(bio), (uint64_t) bio->bi_sector);
+
+	while (bio_sectors(bio)) {
+		unsigned len = min(bio_sectors(bio), 1U << 14);
+
+		if (bch_keylist_realloc(&op->keys, 0, op->c))
+			goto out;
+
+		bio->bi_sector	+= len;
+		bio->bi_size	-= len << 9;
+
+		bch_keylist_add(&op->keys,
+				&KEY(op->inode, bio->bi_sector, len));
+	}
+
+	op->insert_data_done = true;
+	bio_put(bio);
+out:
+	continue_at(cl, bch_journal, bcache_wq);
+}
+
+struct open_bucket {
+	struct list_head	list;
+	struct task_struct	*last;
+	unsigned		sectors_free;
+	BKEY_PADDED(key);
+};
+
+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;
+}
+
+/*
+ * 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,
+					    struct task_struct *task,
+					    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 == task)
+			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.
+ */
+static bool bch_alloc_sectors(struct bkey *k, unsigned sectors,
+			      struct search *s)
+{
+	struct cache_set *c = s->op.c;
+	struct open_bucket *b;
+	BKEY_PADDED(key) alloc;
+	struct closure cl, *w = NULL;
+	unsigned i;
+
+	if (s->writeback) {
+		closure_init_stack(&cl);
+		w = &cl;
+	}
+
+	/*
+	 * 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, s->task, &alloc.key))) {
+		unsigned watermark = s->op.write_prio
+			? WATERMARK_MOVINGGC
+			: WATERMARK_NONE;
+
+		spin_unlock(&c->data_bucket_lock);
+
+		if (bch_bucket_alloc_set(c, watermark, &alloc.key, 1, w))
+			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 = s->task;
+
+	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;
+}
+
+static void bch_insert_data_error(struct closure *cl)
+{
+	struct btree_op *op = container_of(cl, struct btree_op, cl);
+
+	/*
+	 * Our data write just errored, which means we've got a bunch of keys to
+	 * insert that point to data that wasn't succesfully written.
+	 *
+	 * We don't have to insert those keys but we still have to invalidate
+	 * that region of the cache - so, if we just strip off all the pointers
+	 * from the keys we'll accomplish just that.
+	 */
+
+	struct bkey *src = op->keys.bottom, *dst = op->keys.bottom;
+
+	while (src != op->keys.top) {
+		struct bkey *n = bkey_next(src);
+
+		SET_KEY_PTRS(src, 0);
+		bkey_copy(dst, src);
+
+		dst = bkey_next(dst);
+		src = n;
+	}
+
+	op->keys.top = dst;
+
+	bch_journal(cl);
+}
+
+static void bch_insert_data_endio(struct bio *bio, int error)
+{
+	struct closure *cl = bio->bi_private;
+	struct btree_op *op = container_of(cl, struct btree_op, cl);
+	struct search *s = container_of(op, struct search, op);
+
+	if (error) {
+		/* TODO: We could try to recover from this. */
+		if (s->writeback)
+			s->error = error;
+		else if (s->write)
+			set_closure_fn(cl, bch_insert_data_error, bcache_wq);
+		else
+			set_closure_fn(cl, NULL, NULL);
+	}
+
+	bch_bbio_endio(op->c, bio, error, "writing data to cache");
+}
+
+static void bch_insert_data_loop(struct closure *cl)
+{
+	struct btree_op *op = container_of(cl, struct btree_op, cl);
+	struct search *s = container_of(op, struct search, op);
+	struct bio *bio = op->cache_bio, *n;
+
+	if (op->skip)
+		return bio_invalidate(cl);
+
+	if (atomic_sub_return(bio_sectors(bio), &op->c->sectors_to_gc) < 0) {
+		set_gc_sectors(op->c);
+		bch_queue_gc(op->c);
+	}
+
+	do {
+		unsigned i;
+		struct bkey *k;
+		struct bio_set *split = s->d
+			? s->d->bio_split : op->c->bio_split;
+
+		/* 1 for the device pointer and 1 for the chksum */
+		if (bch_keylist_realloc(&op->keys,
+					1 + (op->csum ? 1 : 0),
+					op->c))
+			continue_at(cl, bch_journal, bcache_wq);
+
+		k = op->keys.top;
+		bkey_init(k);
+		SET_KEY_INODE(k, op->inode);
+		SET_KEY_OFFSET(k, bio->bi_sector);
+
+		if (!bch_alloc_sectors(k, bio_sectors(bio), s))
+			goto err;
+
+		n = bch_bio_split(bio, KEY_SIZE(k), GFP_NOIO, split);
+		if (!n) {
+			__bkey_put(op->c, k);
+			continue_at(cl, bch_insert_data_loop, bcache_wq);
+		}
+
+		n->bi_end_io	= bch_insert_data_endio;
+		n->bi_private	= cl;
+
+		if (s->writeback) {
+			SET_KEY_DIRTY(k, true);
+
+			for (i = 0; i < KEY_PTRS(k); i++)
+				SET_GC_MARK(PTR_BUCKET(op->c, k, i),
+					    GC_MARK_DIRTY);
+		}
+
+		SET_KEY_CSUM(k, op->csum);
+		if (KEY_CSUM(k))
+			bio_csum(n, k);
+
+		pr_debug("%s", pkey(k));
+		bch_keylist_push(&op->keys);
+
+		trace_bcache_cache_insert(n, n->bi_sector, n->bi_bdev);
+		n->bi_rw |= REQ_WRITE;
+		bch_submit_bbio(n, op->c, k, 0);
+	} while (n != bio);
+
+	op->insert_data_done = true;
+	continue_at(cl, bch_journal, bcache_wq);
+err:
+	/* bch_alloc_sectors() blocks if s->writeback = true */
+	BUG_ON(s->writeback);
+
+	/*
+	 * But if it's not a writeback write we'd rather just bail out if
+	 * there aren't any buckets ready to write to - it might take awhile and
+	 * we might be starving btree writes for gc or something.
+	 */
+
+	if (s->write) {
+		/*
+		 * Writethrough write: We can't complete the write until we've
+		 * updated the index. But we don't want to delay the write while
+		 * we wait for buckets to be freed up, so just invalidate the
+		 * rest of the write.
+		 */
+		op->skip = true;
+		return bio_invalidate(cl);
+	} else {
+		/*
+		 * From a cache miss, we can just insert the keys for the data
+		 * we have written or bail out if we didn't do anything.
+		 */
+		op->insert_data_done = true;
+		bio_put(bio);
+
+		if (!bch_keylist_empty(&op->keys))
+			continue_at(cl, bch_journal, bcache_wq);
+		else
+			closure_return(cl);
+	}
+}
+
+/**
+ * bch_insert_data - stick some data in the cache
+ *
+ * This is the starting point for any data to end up in a cache device; it could
+ * be from a normal write, or a writeback write, or a write to a flash only
+ * volume - it's also used by the moving garbage collector to compact data in
+ * mostly empty buckets.
+ *
+ * It first writes the data to the cache, creating a list of keys to be inserted
+ * (if the data had to be fragmented there will be multiple keys); after the
+ * data is written it calls bch_journal, and after the keys have been added to
+ * the next journal write they're inserted into the btree.
+ *
+ * It inserts the data in op->cache_bio; bi_sector is used for the key offset,
+ * and op->inode is used for the key inode.
+ *
+ * If op->skip is true, instead of inserting the data it invalidates the region
+ * of the cache represented by op->cache_bio and op->inode.
+ */
+void bch_insert_data(struct closure *cl)
+{
+	struct btree_op *op = container_of(cl, struct btree_op, cl);
+
+	bch_keylist_init(&op->keys);
+	bio_get(op->cache_bio);
+	bch_insert_data_loop(cl);
+}
+
+void bch_btree_insert_async(struct closure *cl)
+{
+	struct btree_op *op = container_of(cl, struct btree_op, cl);
+	struct search *s = container_of(op, struct search, op);
+
+	if (bch_btree_insert(op, op->c)) {
+		s->error		= -ENOMEM;
+		op->insert_data_done	= true;
+	}
+
+	if (op->insert_data_done) {
+		bch_keylist_free(&op->keys);
+		closure_return(cl);
+	} else
+		continue_at(cl, bch_insert_data_loop, bcache_wq);
+}
+
+/* Common code for the make_request functions */
+
+static void request_endio(struct bio *bio, int error)
+{
+	struct closure *cl = bio->bi_private;
+
+	if (error) {
+		struct search *s = container_of(cl, struct search, cl);
+		s->error = error;
+		/* Only cache read errors are recoverable */
+		s->recoverable = false;
+	}
+
+	bio_put(bio);
+	closure_put(cl);
+}
+
+void bch_cache_read_endio(struct bio *bio, int error)
+{
+	struct bbio *b = container_of(bio, struct bbio, bio);
+	struct closure *cl = bio->bi_private;
+	struct search *s = container_of(cl, struct search, cl);
+
+	/*
+	 * If the bucket was reused while our bio was in flight, we might have
+	 * read the wrong data. Set s->error but not error so it doesn't get
+	 * counted against the cache device, but we'll still reread the data
+	 * from the backing device.
+	 */
+
+	if (error)
+		s->error = error;
+	else if (ptr_stale(s->op.c, &b->key, 0)) {
+		atomic_long_inc(&s->op.c->cache_read_races);
+		s->error = -EINTR;
+	}
+
+	bch_bbio_endio(s->op.c, bio, error, "reading from cache");
+}
+
+static void bio_complete(struct search *s)
+{
+	if (s->orig_bio) {
+		int cpu, rw = bio_data_dir(s->orig_bio);
+		unsigned long duration = jiffies - s->start_time;
+
+		cpu = part_stat_lock();
+		part_round_stats(cpu, &s->d->disk->part0);
+		part_stat_add(cpu, &s->d->disk->part0, ticks[rw], duration);
+		part_stat_unlock();
+
+		trace_bcache_request_end(s, s->orig_bio);
+		bio_endio(s->orig_bio, s->error);
+		s->orig_bio = NULL;
+	}
+}
+
+static void do_bio_hook(struct search *s)
+{
+	struct bio *bio = &s->bio.bio;
+	memcpy(bio, s->orig_bio, sizeof(struct bio));
+
+	bio->bi_end_io		= request_endio;
+	bio->bi_private		= &s->cl;
+	atomic_set(&bio->bi_cnt, 3);
+}
+
+static void search_free(struct closure *cl)
+{
+	struct search *s = container_of(cl, struct search, cl);
+	bio_complete(s);
+
+	if (s->op.cache_bio)
+		bio_put(s->op.cache_bio);
+
+	if (s->unaligned_bvec)
+		mempool_free(s->bio.bio.bi_io_vec, s->d->unaligned_bvec);
+
+	closure_debug_destroy(cl);
+	mempool_free(s, s->d->c->search);
+}
+
+static struct search *search_alloc(struct bio *bio, struct bcache_device *d)
+{
+	struct bio_vec *bv;
+	struct search *s = mempool_alloc(d->c->search, GFP_NOIO);
+	memset(s, 0, offsetof(struct search, op.keys));
+
+	__closure_init(&s->cl, NULL);
+
+	s->op.inode		= d->id;
+	s->op.c			= d->c;
+	s->d			= d;
+	s->op.lock		= -1;
+	s->task			= current;
+	s->orig_bio		= bio;
+	s->write		= (bio->bi_rw & REQ_WRITE) != 0;
+	s->op.flush_journal	= (bio->bi_rw & REQ_FLUSH) != 0;
+	s->op.skip		= (bio->bi_rw & REQ_DISCARD) != 0;
+	s->recoverable		= 1;
+	s->start_time		= jiffies;
+	do_bio_hook(s);
+
+	if (bio->bi_size != bio_segments(bio) * PAGE_SIZE) {
+		bv = mempool_alloc(d->unaligned_bvec, GFP_NOIO);
+		memcpy(bv, bio_iovec(bio),
+		       sizeof(struct bio_vec) * bio_segments(bio));
+
+		s->bio.bio.bi_io_vec	= bv;
+		s->unaligned_bvec	= 1;
+	}
+
+	return s;
+}
+
+static void btree_read_async(struct closure *cl)
+{
+	struct btree_op *op = container_of(cl, struct btree_op, cl);
+
+	int ret = btree_root(search_recurse, op->c, op);
+
+	if (ret == -EAGAIN)
+		continue_at(cl, btree_read_async, bcache_wq);
+
+	closure_return(cl);
+}
+
+/* Cached devices */
+
+static void cached_dev_bio_complete(struct closure *cl)
+{
+	struct search *s = container_of(cl, struct search, cl);
+	struct cached_dev *dc = container_of(s->d, struct cached_dev, disk);
+
+	search_free(cl);
+	cached_dev_put(dc);
+}
+
+/* Process reads */
+
+static void cached_dev_read_complete(struct closure *cl)
+{
+	struct search *s = container_of(cl, struct search, cl);
+
+	if (s->op.insert_collision)
+		bch_mark_cache_miss_collision(s);
+
+	if (s->op.cache_bio) {
+		int i;
+		struct bio_vec *bv;
+
+		__bio_for_each_segment(bv, s->op.cache_bio, i, 0)
+			__free_page(bv->bv_page);
+	}
+
+	cached_dev_bio_complete(cl);
+}
+
+static void request_read_error(struct closure *cl)
+{
+	struct search *s = container_of(cl, struct search, cl);
+	struct bio_vec *bv;
+	int i;
+
+	if (s->recoverable) {
+		/* The cache read failed, but we can retry from the backing
+		 * device.
+		 */
+		pr_debug("recovering at sector %llu",
+			 (uint64_t) s->orig_bio->bi_sector);
+
+		s->error = 0;
+		bv = s->bio.bio.bi_io_vec;
+		do_bio_hook(s);
+		s->bio.bio.bi_io_vec = bv;
+
+		if (!s->unaligned_bvec)
+			bio_for_each_segment(bv, s->orig_bio, i)
+				bv->bv_offset = 0, bv->bv_len = PAGE_SIZE;
+		else
+			memcpy(s->bio.bio.bi_io_vec,
+			       bio_iovec(s->orig_bio),
+			       sizeof(struct bio_vec) *
+			       bio_segments(s->orig_bio));
+
+		/* XXX: invalidate cache */
+
+		trace_bcache_read_retry(&s->bio.bio);
+		closure_bio_submit(&s->bio.bio, &s->cl, s->d);
+	}
+
+	continue_at(cl, cached_dev_read_complete, NULL);
+}
+
+static void request_read_done(struct closure *cl)
+{
+	struct search *s = container_of(cl, struct search, cl);
+	struct cached_dev *dc = container_of(s->d, struct cached_dev, disk);
+
+	/*
+	 * s->cache_bio != NULL implies that we had a cache miss; cache_bio now
+	 * contains data ready to be inserted into the cache.
+	 *
+	 * First, we copy the data we just read from cache_bio's bounce buffers
+	 * to the buffers the original bio pointed to:
+	 */
+
+	if (s->op.cache_bio) {
+		struct bio_vec *src, *dst;
+		unsigned src_offset, dst_offset, bytes;
+		void *dst_ptr;
+
+		bio_reset(s->op.cache_bio);
+		s->op.cache_bio->bi_sector	= s->cache_miss->bi_sector;
+		s->op.cache_bio->bi_bdev	= s->cache_miss->bi_bdev;
+		s->op.cache_bio->bi_size	= s->cache_bio_sectors << 9;
+		bio_map(s->op.cache_bio, NULL);
+
+		src = bio_iovec(s->op.cache_bio);
+		dst = bio_iovec(s->cache_miss);
+		src_offset = src->bv_offset;
+		dst_offset = dst->bv_offset;
+		dst_ptr = kmap(dst->bv_page);
+
+		while (1) {
+			if (dst_offset == dst->bv_offset + dst->bv_len) {
+				kunmap(dst->bv_page);
+				dst++;
+				if (dst == bio_iovec_idx(s->cache_miss,
+						s->cache_miss->bi_vcnt))
+					break;
+
+				dst_offset = dst->bv_offset;
+				dst_ptr = kmap(dst->bv_page);
+			}
+
+			if (src_offset == src->bv_offset + src->bv_len) {
+				src++;
+				if (src == bio_iovec_idx(s->op.cache_bio,
+						 s->op.cache_bio->bi_vcnt))
+					BUG();
+
+				src_offset = src->bv_offset;
+			}
+
+			bytes = min(dst->bv_offset + dst->bv_len - dst_offset,
+				    src->bv_offset + src->bv_len - src_offset);
+
+			memcpy(dst_ptr + dst_offset,
+			       page_address(src->bv_page) + src_offset,
+			       bytes);
+
+			src_offset	+= bytes;
+			dst_offset	+= bytes;
+		}
+
+		bio_put(s->cache_miss);
+		s->cache_miss = NULL;
+	}
+
+	if (verify(dc, &s->bio.bio) && s->recoverable)
+		bch_data_verify(s);
+
+	bio_complete(s);
+
+	if (s->op.cache_bio &&
+	    !test_bit(CACHE_SET_STOPPING, &s->op.c->flags)) {
+		s->op.type = BTREE_REPLACE;
+		closure_call(&s->op.cl, bch_insert_data, NULL, cl);
+	}
+
+	continue_at(cl, cached_dev_read_complete, NULL);
+}
+
+static void request_read_done_bh(struct closure *cl)
+{
+	struct search *s = container_of(cl, struct search, cl);
+	struct cached_dev *dc = container_of(s->d, struct cached_dev, disk);
+
+	bch_mark_cache_accounting(s, !s->cache_miss, s->op.skip);
+
+	if (s->error)
+		continue_at_nobarrier(cl, request_read_error, bcache_wq);
+	else if (s->op.cache_bio || verify(dc, &s->bio.bio))
+		continue_at_nobarrier(cl, request_read_done, bcache_wq);
+	else
+		continue_at_nobarrier(cl, cached_dev_read_complete, NULL);
+}
+
+static int cached_dev_cache_miss(struct btree *b, struct search *s,
+				 struct bio *bio, unsigned sectors)
+{
+	int ret = 0;
+	unsigned reada;
+	struct cached_dev *dc = container_of(s->d, struct cached_dev, disk);
+	struct bio *miss;
+
+	miss = bch_bio_split(bio, sectors, GFP_NOIO, s->d->bio_split);
+	if (!miss)
+		return -EAGAIN;
+
+	if (miss == bio)
+		s->op.lookup_done = true;
+
+	miss->bi_end_io		= request_endio;
+	miss->bi_private	= &s->cl;
+
+	if (s->cache_miss || s->op.skip)
+		goto out_submit;
+
+	if (miss != bio ||
+	    (bio->bi_rw & REQ_RAHEAD) ||
+	    (bio->bi_rw & REQ_META) ||
+	    s->op.c->gc_stats.in_use >= CUTOFF_CACHE_READA)
+		reada = 0;
+	else {
+		reada = min(dc->readahead >> 9,
+			    sectors - bio_sectors(miss));
+
+		if (bio_end(miss) + reada > bdev_sectors(miss->bi_bdev))
+			reada = bdev_sectors(miss->bi_bdev) - bio_end(miss);
+	}
+
+	s->cache_bio_sectors = bio_sectors(miss) + reada;
+	s->op.cache_bio = bio_alloc_bioset(GFP_NOWAIT,
+			DIV_ROUND_UP(s->cache_bio_sectors, PAGE_SECTORS),
+			dc->disk.bio_split);
+
+	if (!s->op.cache_bio)
+		goto out_submit;
+
+	s->op.cache_bio->bi_sector	= miss->bi_sector;
+	s->op.cache_bio->bi_bdev	= miss->bi_bdev;
+	s->op.cache_bio->bi_size	= s->cache_bio_sectors << 9;
+
+	s->op.cache_bio->bi_end_io	= request_endio;
+	s->op.cache_bio->bi_private	= &s->cl;
+
+	/* btree_search_recurse()'s btree iterator is no good anymore */
+	ret = -EINTR;
+	if (!bch_btree_insert_check_key(b, &s->op, s->op.cache_bio))
+		goto out_put;
+
+	bio_map(s->op.cache_bio, NULL);
+	if (bio_alloc_pages(s->op.cache_bio, __GFP_NOWARN|GFP_NOIO))
+		goto out_put;
+
+	s->cache_miss = miss;
+	bio_get(s->op.cache_bio);
+
+	trace_bcache_cache_miss(s->orig_bio);
+	closure_bio_submit(s->op.cache_bio, &s->cl, s->d);
+
+	return ret;
+out_put:
+	bio_put(s->op.cache_bio);
+	s->op.cache_bio = NULL;
+out_submit:
+	closure_bio_submit(miss, &s->cl, s->d);
+	return ret;
+}
+
+static void request_read(struct cached_dev *dc, struct search *s)
+{
+	struct closure *cl = &s->cl;
+
+	check_should_skip(dc, s);
+	closure_call(&s->op.cl, btree_read_async, NULL, cl);
+
+	continue_at(cl, request_read_done_bh, NULL);
+}
+
+/* Process writes */
+
+static void cached_dev_write_complete(struct closure *cl)
+{
+	struct search *s = container_of(cl, struct search, cl);
+	struct cached_dev *dc = container_of(s->d, struct cached_dev, disk);
+
+	up_read_non_owner(&dc->writeback_lock);
+	cached_dev_bio_complete(cl);
+}
+
+static bool should_writeback(struct cached_dev *dc, struct bio *bio)
+{
+	unsigned threshold = (bio->bi_rw & REQ_SYNC)
+		? CUTOFF_WRITEBACK_SYNC
+		: CUTOFF_WRITEBACK;
+
+	return !atomic_read(&dc->disk.detaching) &&
+		cache_mode(dc, bio) == CACHE_MODE_WRITEBACK &&
+		dc->disk.c->gc_stats.in_use < threshold;
+}
+
+static void request_write(struct cached_dev *dc, struct search *s)
+{
+	struct closure *cl = &s->cl;
+	struct bio *bio = &s->bio.bio;
+	struct bkey start, end;
+	start = KEY(dc->disk.id, bio->bi_sector, 0);
+	end = KEY(dc->disk.id, bio_end(bio), 0);
+
+	bch_keybuf_check_overlapping(&s->op.c->moving_gc_keys, &start, &end);
+
+	check_should_skip(dc, s);
+	down_read_non_owner(&dc->writeback_lock);
+
+	if (bch_keybuf_check_overlapping(&dc->writeback_keys, &start, &end)) {
+		s->op.skip	= false;
+		s->writeback	= true;
+	}
+
+	if (bio->bi_rw & REQ_DISCARD)
+		goto skip;
+
+	if (s->op.skip)
+		goto skip;
+
+	if (should_writeback(dc, s->orig_bio))
+		s->writeback = true;
+
+	if (!s->writeback) {
+		s->op.cache_bio = bio_clone_bioset(bio, GFP_NOIO,
+						   dc->disk.bio_split);
+
+		trace_bcache_writethrough(s->orig_bio);
+		closure_bio_submit(bio, cl, s->d);
+	} else {
+		s->op.cache_bio = bio;
+		trace_bcache_writeback(s->orig_bio);
+		bch_writeback_add(dc, bio_sectors(bio));
+	}
+out:
+	closure_call(&s->op.cl, bch_insert_data, NULL, cl);
+	continue_at(cl, cached_dev_write_complete, NULL);
+skip:
+	s->op.skip = true;
+	s->op.cache_bio = s->orig_bio;
+	bio_get(s->op.cache_bio);
+	trace_bcache_write_skip(s->orig_bio);
+
+	if ((bio->bi_rw & REQ_DISCARD) &&
+	    !blk_queue_discard(bdev_get_queue(dc->bdev)))
+		goto out;
+
+	closure_bio_submit(bio, cl, s->d);
+	goto out;
+}
+
+static void request_nodata(struct cached_dev *dc, struct search *s)
+{
+	struct closure *cl = &s->cl;
+	struct bio *bio = &s->bio.bio;
+
+	if (bio->bi_rw & REQ_DISCARD) {
+		request_write(dc, s);
+		return;
+	}
+
+	if (s->op.flush_journal)
+		bch_journal_meta(s->op.c, cl);
+
+	closure_bio_submit(bio, cl, s->d);
+
+	continue_at(cl, cached_dev_bio_complete, NULL);
+}
+
+/* Cached devices - read & write stuff */
+
+int bch_get_congested(struct cache_set *c)
+{
+	int i;
+
+	if (!c->congested_read_threshold_us &&
+	    !c->congested_write_threshold_us)
+		return 0;
+
+	i = (local_clock_us() - c->congested_last_us) / 1024;
+	if (i < 0)
+		return 0;
+
+	i += atomic_read(&c->congested);
+	if (i >= 0)
+		return 0;
+
+	i += CONGESTED_MAX;
+
+	return i <= 0 ? 1 : fract_exp_two(i, 6);
+}
+
+static void add_sequential(struct task_struct *t)
+{
+	ewma_add(t->sequential_io_avg,
+		 t->sequential_io, 8, 0);
+
+	t->sequential_io = 0;
+}
+
+static void check_should_skip(struct cached_dev *dc, struct search *s)
+{
+	struct hlist_head *iohash(uint64_t k)
+	{ return &dc->io_hash[hash_64(k, RECENT_IO_BITS)]; }
+
+	struct cache_set *c = s->op.c;
+	struct bio *bio = &s->bio.bio;
+
+	long rand;
+	int cutoff = bch_get_congested(c);
+	unsigned mode = cache_mode(dc, bio);
+
+	if (atomic_read(&dc->disk.detaching) ||
+	    c->gc_stats.in_use > CUTOFF_CACHE_ADD ||
+	    (bio->bi_rw & REQ_DISCARD))
+		goto skip;
+
+	if (mode == CACHE_MODE_NONE ||
+	    (mode == CACHE_MODE_WRITEAROUND &&
+	     (bio->bi_rw & REQ_WRITE)))
+		goto skip;
+
+	if (bio->bi_sector   & (c->sb.block_size - 1) ||
+	    bio_sectors(bio) & (c->sb.block_size - 1)) {
+		pr_debug("skipping unaligned io");
+		goto skip;
+	}
+
+	if (!cutoff) {
+		cutoff = dc->sequential_cutoff >> 9;
+
+		if (!cutoff)
+			goto rescale;
+
+		if (mode == CACHE_MODE_WRITEBACK &&
+		    (bio->bi_rw & REQ_WRITE) &&
+		    (bio->bi_rw & REQ_SYNC))
+			goto rescale;
+	}
+
+	if (dc->sequential_merge) {
+		struct io *i;
+
+		spin_lock(&dc->io_lock);
+
+		hlist_for_each_entry(i, iohash(bio->bi_sector), hash)
+			if (i->last == bio->bi_sector &&
+			    time_before(jiffies, i->jiffies))
+				goto found;
+
+		i = list_first_entry(&dc->io_lru, struct io, lru);
+
+		add_sequential(s->task);
+		i->sequential = 0;
+found:
+		if (i->sequential + bio->bi_size > i->sequential)
+			i->sequential	+= bio->bi_size;
+
+		i->last			 = bio_end(bio);
+		i->jiffies		 = jiffies + msecs_to_jiffies(5000);
+		s->task->sequential_io	 = i->sequential;
+
+		hlist_del(&i->hash);
+		hlist_add_head(&i->hash, iohash(i->last));
+		list_move_tail(&i->lru, &dc->io_lru);
+
+		spin_unlock(&dc->io_lock);
+	} else {
+		s->task->sequential_io = bio->bi_size;
+
+		add_sequential(s->task);
+	}
+
+	rand = get_random_int();
+	cutoff -= bitmap_weight(&rand, BITS_PER_LONG);
+
+	if (cutoff <= (int) (max(s->task->sequential_io,
+				 s->task->sequential_io_avg) >> 9))
+		goto skip;
+
+rescale:
+	bch_rescale_priorities(c, bio_sectors(bio));
+	return;
+skip:
+	bch_mark_sectors_bypassed(s, bio_sectors(bio));
+	s->op.skip = true;
+}
+
+static void cached_dev_make_request(struct request_queue *q, struct bio *bio)
+{
+	struct search *s;
+	struct bcache_device *d = bio->bi_bdev->bd_disk->private_data;
+	struct cached_dev *dc = container_of(d, struct cached_dev, disk);
+	int cpu, rw = bio_data_dir(bio);
+
+	cpu = part_stat_lock();
+	part_stat_inc(cpu, &d->disk->part0, ios[rw]);
+	part_stat_add(cpu, &d->disk->part0, sectors[rw], bio_sectors(bio));
+	part_stat_unlock();
+
+	bio->bi_bdev = dc->bdev;
+	bio->bi_sector += BDEV_DATA_START;
+
+	if (cached_dev_get(dc)) {
+		s = search_alloc(bio, d);
+		trace_bcache_request_start(s, bio);
+
+		if (!bio_has_data(bio))
+			request_nodata(dc, s);
+		else if (rw)
+			request_write(dc, s);
+		else
+			request_read(dc, s);
+	} else {
+		if ((bio->bi_rw & REQ_DISCARD) &&
+		    !blk_queue_discard(bdev_get_queue(dc->bdev)))
+			bio_endio(bio, 0);
+		else
+			bch_generic_make_request(bio, &d->bio_split_hook);
+	}
+}
+
+static int cached_dev_ioctl(struct bcache_device *d, fmode_t mode,
+			    unsigned int cmd, unsigned long arg)
+{
+	struct cached_dev *dc = container_of(d, struct cached_dev, disk);
+	return __blkdev_driver_ioctl(dc->bdev, mode, cmd, arg);
+}
+
+static int cached_dev_congested(void *data, int bits)
+{
+	struct bcache_device *d = data;
+	struct cached_dev *dc = container_of(d, struct cached_dev, disk);
+	struct request_queue *q = bdev_get_queue(dc->bdev);
+	int ret = 0;
+
+	if (bdi_congested(&q->backing_dev_info, bits))
+		return 1;
+
+	if (cached_dev_get(dc)) {
+		unsigned i;
+		struct cache *ca;
+
+		for_each_cache(ca, d->c, i) {
+			q = bdev_get_queue(ca->bdev);
+			ret |= bdi_congested(&q->backing_dev_info, bits);
+		}
+
+		cached_dev_put(dc);
+	}
+
+	return ret;
+}
+
+void bch_cached_dev_request_init(struct cached_dev *dc)
+{
+	struct gendisk *g = dc->disk.disk;
+
+	g->queue->make_request_fn		= cached_dev_make_request;
+	g->queue->backing_dev_info.congested_fn = cached_dev_congested;
+	dc->disk.cache_miss			= cached_dev_cache_miss;
+	dc->disk.ioctl				= cached_dev_ioctl;
+}
+
+/* Flash backed devices */
+
+static int flash_dev_cache_miss(struct btree *b, struct search *s,
+				struct bio *bio, unsigned sectors)
+{
+	/* Zero fill bio */
+
+	while (bio->bi_idx != bio->bi_vcnt) {
+		struct bio_vec *bv = bio_iovec(bio);
+		unsigned j = min(bv->bv_len >> 9, sectors);
+
+		void *p = kmap(bv->bv_page);
+		memset(p + bv->bv_offset, 0, j << 9);
+		kunmap(bv->bv_page);
+
+		bv->bv_len	-= j << 9;
+		bv->bv_offset	+= j << 9;
+
+		if (bv->bv_len)
+			return 0;
+
+		bio->bi_sector	+= j;
+		bio->bi_size	-= j << 9;
+
+		bio->bi_idx++;
+		sectors		-= j;
+	}
+
+	s->op.lookup_done = true;
+
+	return 0;
+}
+
+static void flash_dev_make_request(struct request_queue *q, struct bio *bio)
+{
+	struct search *s;
+	struct closure *cl;
+	struct bcache_device *d = bio->bi_bdev->bd_disk->private_data;
+	int cpu, rw = bio_data_dir(bio);
+
+	cpu = part_stat_lock();
+	part_stat_inc(cpu, &d->disk->part0, ios[rw]);
+	part_stat_add(cpu, &d->disk->part0, sectors[rw], bio_sectors(bio));
+	part_stat_unlock();
+
+	s = search_alloc(bio, d);
+	cl = &s->cl;
+	bio = &s->bio.bio;
+
+	trace_bcache_request_start(s, bio);
+
+	if (bio_has_data(bio) && !rw) {
+		closure_call(&s->op.cl, btree_read_async, NULL, cl);
+	} else if (bio_has_data(bio) || s->op.skip) {
+		bch_keybuf_check_overlapping(&s->op.c->moving_gc_keys,
+					     &KEY(d->id, bio->bi_sector, 0),
+					     &KEY(d->id, bio_end(bio), 0));
+
+		s->writeback	= true;
+		s->op.cache_bio	= bio;
+
+		closure_call(&s->op.cl, bch_insert_data, NULL, cl);
+	} else {
+		/* No data - probably a cache flush */
+		if (s->op.flush_journal)
+			bch_journal_meta(s->op.c, cl);
+	}
+
+	continue_at(cl, search_free, NULL);
+}
+
+static int flash_dev_ioctl(struct bcache_device *d, fmode_t mode,
+			   unsigned int cmd, unsigned long arg)
+{
+	return -ENOTTY;
+}
+
+static int flash_dev_congested(void *data, int bits)
+{
+	struct bcache_device *d = data;
+	struct request_queue *q;
+	struct cache *ca;
+	unsigned i;
+	int ret = 0;
+
+	for_each_cache(ca, d->c, i) {
+		q = bdev_get_queue(ca->bdev);
+		ret |= bdi_congested(&q->backing_dev_info, bits);
+	}
+
+	return ret;
+}
+
+void bch_flash_dev_request_init(struct bcache_device *d)
+{
+	struct gendisk *g = d->disk;
+
+	g->queue->make_request_fn		= flash_dev_make_request;
+	g->queue->backing_dev_info.congested_fn = flash_dev_congested;
+	d->cache_miss				= flash_dev_cache_miss;
+	d->ioctl				= flash_dev_ioctl;
+}
+
+void bch_request_exit(void)
+{
+#ifdef CONFIG_CGROUP_BCACHE
+	cgroup_unload_subsys(&bcache_subsys);
+#endif
+	if (bch_search_cache)
+		kmem_cache_destroy(bch_search_cache);
+}
+
+int __init bch_request_init(void)
+{
+	bch_search_cache = KMEM_CACHE(search, 0);
+	if (!bch_search_cache)
+		return -ENOMEM;
+
+#ifdef CONFIG_CGROUP_BCACHE
+	cgroup_load_subsys(&bcache_subsys);
+	init_bch_cgroup(&bcache_default_cgroup);
+
+	cgroup_add_cftypes(&bcache_subsys, bch_files);
+#endif
+	return 0;
+}
-- 
cgit v1.2.3-70-g09d2


From b1a67b0f4c747ca10c96ebb24f04e2a74b3c298d Mon Sep 17 00:00:00 2001
From: Kent Overstreet <koverstreet@google.com>
Date: Mon, 25 Mar 2013 11:46:44 -0700
Subject: bcache: Style/checkpatch fixes

Took out some nested functions, and fixed some more checkpatch
complaints.

Signed-off-by: Kent Overstreet <koverstreet@google.com>
Cc: linux-bcache@vger.kernel.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/md/bcache/alloc.c    | 22 ++++++----------------
 drivers/md/bcache/bcache.h   | 10 +++++-----
 drivers/md/bcache/bset.c     |  9 +++++----
 drivers/md/bcache/btree.c    |  4 ++--
 drivers/md/bcache/debug.c    |  8 ++++----
 drivers/md/bcache/journal.c  |  8 ++++----
 drivers/md/bcache/movinggc.c | 24 ++++++++++++------------
 drivers/md/bcache/request.c  | 12 +++++++-----
 drivers/md/bcache/stats.c    |  3 ++-
 drivers/md/bcache/super.c    |  7 ++++---
 10 files changed, 51 insertions(+), 56 deletions(-)

(limited to 'drivers/md/bcache/request.c')

diff --git a/drivers/md/bcache/alloc.c b/drivers/md/bcache/alloc.c
index ed18115e078..2879487d036 100644
--- a/drivers/md/bcache/alloc.c
+++ b/drivers/md/bcache/alloc.c
@@ -229,24 +229,14 @@ static void invalidate_one_bucket(struct cache *ca, struct bucket *b)
 	fifo_push(&ca->free_inc, b - ca->buckets);
 }
 
-static void invalidate_buckets_lru(struct cache *ca)
-{
-	unsigned bucket_prio(struct bucket *b)
-	{
-		return ((unsigned) (b->prio - ca->set->min_prio)) *
-			GC_SECTORS_USED(b);
-	}
-
-	bool bucket_max_cmp(struct bucket *l, struct bucket *r)
-	{
-		return bucket_prio(l) < bucket_prio(r);
-	}
+#define bucket_prio(b)				\
+	(((unsigned) (b->prio - ca->set->min_prio)) * GC_SECTORS_USED(b))
 
-	bool bucket_min_cmp(struct bucket *l, struct bucket *r)
-	{
-		return bucket_prio(l) > bucket_prio(r);
-	}
+#define bucket_max_cmp(l, r)	(bucket_prio(l) < bucket_prio(r))
+#define bucket_min_cmp(l, r)	(bucket_prio(l) > bucket_prio(r))
 
+static void invalidate_buckets_lru(struct cache *ca)
+{
 	struct bucket *b;
 	ssize_t i;
 
diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index d01a553f63f..b2846e70149 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -644,8 +644,8 @@ struct gc_stat {
  * we'll continue to run normally for awhile with CACHE_SET_STOPPING set (i.e.
  * flushing dirty data).
  *
- * CACHE_SET_STOPPING_2 gets set at the last phase, when it's time to shut down the
- * allocation thread.
+ * CACHE_SET_STOPPING_2 gets set at the last phase, when it's time to shut down
+ * the allocation thread.
  */
 #define CACHE_SET_UNREGISTERING		0
 #define	CACHE_SET_STOPPING		1
@@ -1012,11 +1012,11 @@ static inline struct bucket *PTR_BUCKET(struct cache_set *c,
  * searches - it told you where a key started. It's not used anymore,
  * and can probably be safely dropped.
  */
-#define KEY(dev, sector, len)	(struct bkey)				\
-{									\
+#define KEY(dev, sector, len)						\
+((struct bkey) {							\
 	.high = (1ULL << 63) | ((uint64_t) (len) << 20) | (dev),	\
 	.low = (sector)							\
-}
+})
 
 static inline void bkey_init(struct bkey *k)
 {
diff --git a/drivers/md/bcache/bset.c b/drivers/md/bcache/bset.c
index 79fe1f0190f..4dc9cb4efac 100644
--- a/drivers/md/bcache/bset.c
+++ b/drivers/md/bcache/bset.c
@@ -161,9 +161,9 @@ bool bch_ptr_bad(struct btree *b, const struct bkey *k)
 #ifdef CONFIG_BCACHE_EDEBUG
 bug:
 	mutex_unlock(&b->c->bucket_lock);
-	btree_bug(b, "inconsistent pointer %s: bucket %zu pin %i "
-		  "prio %i gen %i last_gc %i mark %llu gc_gen %i", pkey(k),
-		  PTR_BUCKET_NR(b->c, k, i), atomic_read(&g->pin),
+	btree_bug(b,
+"inconsistent pointer %s: bucket %zu pin %i prio %i gen %i last_gc %i mark %llu gc_gen %i",
+		  pkey(k), PTR_BUCKET_NR(b->c, k, i), atomic_read(&g->pin),
 		  g->prio, g->gen, g->last_gc, GC_MARK(g), g->gc_gen);
 	return true;
 #endif
@@ -1049,7 +1049,8 @@ void bch_btree_sort_partial(struct btree *b, unsigned start)
 		for (i = start; i <= b->nsets; i++)
 			keys += b->sets[i].data->keys;
 
-		order = roundup_pow_of_two(__set_bytes(b->sets->data, keys)) / PAGE_SIZE;
+		order = roundup_pow_of_two(__set_bytes(b->sets->data,
+						       keys)) / PAGE_SIZE;
 		if (order)
 			order = ilog2(order);
 	}
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index af9ea4a9633..24b67805909 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -1021,8 +1021,8 @@ retry:
 		goto err_free;
 
 	if (!b) {
-		cache_bug(c, "Tried to allocate bucket"
-			  " that was in btree cache");
+		cache_bug(c,
+			"Tried to allocate bucket that was in btree cache");
 		__bkey_put(c, &k.key);
 		goto retry;
 	}
diff --git a/drivers/md/bcache/debug.c b/drivers/md/bcache/debug.c
index 4b37ef2b80e..141a5cac11a 100644
--- a/drivers/md/bcache/debug.c
+++ b/drivers/md/bcache/debug.c
@@ -217,8 +217,8 @@ void bch_data_verify(struct search *s)
 		if (memcmp(p1 + bv->bv_offset,
 			   p2 + bv->bv_offset,
 			   bv->bv_len))
-			printk(KERN_ERR "bcache (%s): verify failed"
-			       " at sector %llu\n",
+			printk(KERN_ERR
+			       "bcache (%s): verify failed at sector %llu\n",
 			       bdevname(dc->bdev, name),
 			       (uint64_t) s->orig_bio->bi_sector);
 
@@ -525,8 +525,8 @@ static ssize_t btree_fuzz(struct kobject *k, struct kobj_attribute *a,
 			     k = bkey_next(k), l = bkey_next(l))
 				if (bkey_cmp(k, l) ||
 				    KEY_SIZE(k) != KEY_SIZE(l))
-					pr_err("key %zi differs: %s "
-					       "!= %s", (uint64_t *) k - i->d,
+					pr_err("key %zi differs: %s != %s",
+					       (uint64_t *) k - i->d,
 					       pkey(k), pkey(l));
 
 			for (j = 0; j < 3; j++) {
diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c
index c871ffaabbb..21fd1010cf5 100644
--- a/drivers/md/bcache/journal.c
+++ b/drivers/md/bcache/journal.c
@@ -293,9 +293,9 @@ int bch_journal_replay(struct cache_set *s, struct list_head *list,
 		BUG_ON(i->pin && atomic_read(i->pin) != 1);
 
 		if (n != i->j.seq)
-			pr_err("journal entries %llu-%llu "
-			       "missing! (replaying %llu-%llu)\n",
-			       n, i->j.seq - 1, start, end);
+			pr_err(
+		"journal entries %llu-%llu missing! (replaying %llu-%llu)\n",
+		n, i->j.seq - 1, start, end);
 
 		for (k = i->j.start;
 		     k < end(&i->j);
@@ -439,7 +439,7 @@ static void do_journal_discard(struct cache *ca)
 
 		bio_init(bio);
 		bio->bi_sector		= bucket_to_sector(ca->set,
-							   ca->sb.d[ja->discard_idx]);
+						ca->sb.d[ja->discard_idx]);
 		bio->bi_bdev		= ca->bdev;
 		bio->bi_rw		= REQ_WRITE|REQ_DISCARD;
 		bio->bi_max_vecs	= 1;
diff --git a/drivers/md/bcache/movinggc.c b/drivers/md/bcache/movinggc.c
index c69fc92b02c..e3ec0a550b0 100644
--- a/drivers/md/bcache/movinggc.c
+++ b/drivers/md/bcache/movinggc.c
@@ -183,6 +183,16 @@ err:		if (!IS_ERR_OR_NULL(w->private))
 	closure_return(cl);
 }
 
+static bool bucket_cmp(struct bucket *l, struct bucket *r)
+{
+	return GC_SECTORS_USED(l) < GC_SECTORS_USED(r);
+}
+
+static unsigned bucket_heap_top(struct cache *ca)
+{
+	return GC_SECTORS_USED(heap_peek(&ca->heap));
+}
+
 void bch_moving_gc(struct closure *cl)
 {
 	struct cache_set *c = container_of(cl, struct cache_set, gc.cl);
@@ -190,16 +200,6 @@ void bch_moving_gc(struct closure *cl)
 	struct bucket *b;
 	unsigned i;
 
-	bool bucket_cmp(struct bucket *l, struct bucket *r)
-	{
-		return GC_SECTORS_USED(l) < GC_SECTORS_USED(r);
-	}
-
-	unsigned top(struct cache *ca)
-	{
-		return GC_SECTORS_USED(heap_peek(&ca->heap));
-	}
-
 	if (!c->copy_gc_enabled)
 		closure_return(cl);
 
@@ -220,7 +220,7 @@ void bch_moving_gc(struct closure *cl)
 				sectors_to_move += GC_SECTORS_USED(b);
 				heap_add(&ca->heap, b, bucket_cmp);
 			} else if (bucket_cmp(b, heap_peek(&ca->heap))) {
-				sectors_to_move -= top(ca);
+				sectors_to_move -= bucket_heap_top(ca);
 				sectors_to_move += GC_SECTORS_USED(b);
 
 				ca->heap.data[0] = b;
@@ -233,7 +233,7 @@ void bch_moving_gc(struct closure *cl)
 			sectors_to_move -= GC_SECTORS_USED(b);
 		}
 
-		ca->gc_move_threshold = top(ca);
+		ca->gc_move_threshold = bucket_heap_top(ca);
 
 		pr_debug("threshold %u", ca->gc_move_threshold);
 	}
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index 4f552de49aa..dbda9646ef3 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -1117,11 +1117,13 @@ static void add_sequential(struct task_struct *t)
 	t->sequential_io = 0;
 }
 
-static void check_should_skip(struct cached_dev *dc, struct search *s)
+static struct hlist_head *iohash(struct cached_dev *dc, uint64_t k)
 {
-	struct hlist_head *iohash(uint64_t k)
-	{ return &dc->io_hash[hash_64(k, RECENT_IO_BITS)]; }
+	return &dc->io_hash[hash_64(k, RECENT_IO_BITS)];
+}
 
+static void check_should_skip(struct cached_dev *dc, struct search *s)
+{
 	struct cache_set *c = s->op.c;
 	struct bio *bio = &s->bio.bio;
 
@@ -1162,7 +1164,7 @@ static void check_should_skip(struct cached_dev *dc, struct search *s)
 
 		spin_lock(&dc->io_lock);
 
-		hlist_for_each_entry(i, iohash(bio->bi_sector), hash)
+		hlist_for_each_entry(i, iohash(dc, bio->bi_sector), hash)
 			if (i->last == bio->bi_sector &&
 			    time_before(jiffies, i->jiffies))
 				goto found;
@@ -1180,7 +1182,7 @@ found:
 		s->task->sequential_io	 = i->sequential;
 
 		hlist_del(&i->hash);
-		hlist_add_head(&i->hash, iohash(i->last));
+		hlist_add_head(&i->hash, iohash(dc, i->last));
 		list_move_tail(&i->lru, &dc->io_lru);
 
 		spin_unlock(&dc->io_lock);
diff --git a/drivers/md/bcache/stats.c b/drivers/md/bcache/stats.c
index bf6cf9518c8..64e679449c2 100644
--- a/drivers/md/bcache/stats.c
+++ b/drivers/md/bcache/stats.c
@@ -95,7 +95,8 @@ static KTYPE(bch_stats);
 
 static void scale_accounting(unsigned long data);
 
-void bch_cache_accounting_init(struct cache_accounting *acc, struct closure *parent)
+void bch_cache_accounting_init(struct cache_accounting *acc,
+			       struct closure *parent)
 {
 	kobject_init(&acc->total.kobj,		&bch_stats_ktype);
 	kobject_init(&acc->five_minute.kobj,	&bch_stats_ktype);
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 7b8efc77087..484ae6c8f43 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -526,7 +526,8 @@ void bch_prio_write(struct cache *ca)
 	for (i = prio_buckets(ca) - 1; i >= 0; --i) {
 		long bucket;
 		struct prio_set *p = ca->disk_buckets;
-		struct bucket_disk *d = p->data, *end = d + prios_per_bucket(ca);
+		struct bucket_disk *d = p->data;
+		struct bucket_disk *end = d + prios_per_bucket(ca);
 
 		for (b = ca->buckets + i * prios_per_bucket(ca);
 		     b < ca->buckets + ca->sb.nbuckets && d < end;
@@ -865,8 +866,8 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c)
 
 	if (dc->sb.block_size < c->sb.block_size) {
 		/* Will die */
-		pr_err("Couldn't attach %s: block size "
-		       "less than set's block size", buf);
+		pr_err("Couldn't attach %s: block size less than set's block size",
+		       buf);
 		return -EINVAL;
 	}
 
-- 
cgit v1.2.3-70-g09d2


From 169ef1cf6171d35550fef85645b83b960e241cff Mon Sep 17 00:00:00 2001
From: Kent Overstreet <koverstreet@google.com>
Date: Thu, 28 Mar 2013 12:50:55 -0600
Subject: bcache: Don't export utility code, prefix with bch_

Signed-off-by: Kent Overstreet <koverstreet@google.com>
Cc: linux-bcache@vger.kernel.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/md/bcache/bcache.h    |  2 +-
 drivers/md/bcache/bset.c      |  4 ++--
 drivers/md/bcache/btree.c     | 18 +++++++--------
 drivers/md/bcache/debug.c     |  2 +-
 drivers/md/bcache/journal.c   |  4 ++--
 drivers/md/bcache/movinggc.c  |  4 ++--
 drivers/md/bcache/request.c   | 14 +++++------
 drivers/md/bcache/super.c     | 18 +++++++--------
 drivers/md/bcache/sysfs.c     | 24 +++++++++----------
 drivers/md/bcache/sysfs.h     |  2 +-
 drivers/md/bcache/util.c      | 38 +++++++++++-------------------
 drivers/md/bcache/util.h      | 54 +++++++++++++++++++++----------------------
 drivers/md/bcache/writeback.c |  6 ++---
 13 files changed, 89 insertions(+), 101 deletions(-)

(limited to 'drivers/md/bcache/request.c')

diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index b2846e70149..f05723565f1 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -1033,7 +1033,7 @@ static inline void bkey_init(struct bkey *k)
  * jset: The checksum is _always_ the first 8 bytes of these structs
  */
 #define csum_set(i)							\
-	crc64(((void *) (i)) + sizeof(uint64_t),			\
+	bch_crc64(((void *) (i)) + sizeof(uint64_t),			\
 	      ((void *) end(i)) - (((void *) (i)) + sizeof(uint64_t)))
 
 /* Error handling macros */
diff --git a/drivers/md/bcache/bset.c b/drivers/md/bcache/bset.c
index 4dc9cb4efac..0b33aac1f14 100644
--- a/drivers/md/bcache/bset.c
+++ b/drivers/md/bcache/bset.c
@@ -1026,7 +1026,7 @@ static void __btree_sort(struct btree *b, struct btree_iter *iter,
 
 	if (!start) {
 		spin_lock(&b->c->sort_time_lock);
-		time_stats_update(&b->c->sort_time, start_time);
+		bch_time_stats_update(&b->c->sort_time, start_time);
 		spin_unlock(&b->c->sort_time_lock);
 	}
 }
@@ -1076,7 +1076,7 @@ void bch_btree_sort_into(struct btree *b, struct btree *new)
 	btree_mergesort(b, new->sets->data, &iter, false, true);
 
 	spin_lock(&b->c->sort_time_lock);
-	time_stats_update(&b->c->sort_time, start_time);
+	bch_time_stats_update(&b->c->sort_time, start_time);
 	spin_unlock(&b->c->sort_time_lock);
 
 	bkey_copy_key(&new->key, &b->key);
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index 24b67805909..f2b2c653c5a 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -129,7 +129,7 @@ static uint64_t btree_csum_set(struct btree *b, struct bset *i)
 	uint64_t crc = b->key.ptr[0];
 	void *data = (void *) i + 8, *end = end(i);
 
-	crc = crc64_update(crc, data, end - data);
+	crc = bch_crc64_update(crc, data, end - data);
 	return crc ^ 0xffffffffffffffff;
 }
 
@@ -231,7 +231,7 @@ out:
 	mutex_unlock(&b->c->fill_lock);
 
 	spin_lock(&b->c->btree_read_time_lock);
-	time_stats_update(&b->c->btree_read_time, b->io_start_time);
+	bch_time_stats_update(&b->c->btree_read_time, b->io_start_time);
 	spin_unlock(&b->c->btree_read_time_lock);
 
 	smp_wmb(); /* read_done is our write lock */
@@ -259,7 +259,7 @@ void bch_btree_read(struct btree *b)
 	b->bio->bi_rw	= REQ_META|READ_SYNC;
 	b->bio->bi_size	= KEY_SIZE(&b->key) << 9;
 
-	bio_map(b->bio, b->sets[0].data);
+	bch_bio_map(b->bio, b->sets[0].data);
 
 	pr_debug("%s", pbtree(b));
 	trace_bcache_btree_read(b->bio);
@@ -327,12 +327,12 @@ static void do_btree_write(struct btree *b)
 	btree_bio_init(b);
 	b->bio->bi_rw	= REQ_META|WRITE_SYNC;
 	b->bio->bi_size	= set_blocks(i, b->c) * block_bytes(b->c);
-	bio_map(b->bio, i);
+	bch_bio_map(b->bio, i);
 
 	bkey_copy(&k.key, &b->key);
 	SET_PTR_OFFSET(&k.key, 0, PTR_OFFSET(&k.key, 0) + bset_offset(b, i));
 
-	if (!bio_alloc_pages(b->bio, GFP_NOIO)) {
+	if (!bch_bio_alloc_pages(b->bio, GFP_NOIO)) {
 		int j;
 		struct bio_vec *bv;
 		void *base = (void *) ((unsigned long) i & ~(PAGE_SIZE - 1));
@@ -347,7 +347,7 @@ static void do_btree_write(struct btree *b)
 		continue_at(cl, btree_write_done, NULL);
 	} else {
 		b->bio->bi_vcnt = 0;
-		bio_map(b->bio, i);
+		bch_bio_map(b->bio, i);
 
 		trace_bcache_btree_write(b->bio);
 		bch_submit_bbio(b->bio, b->c, &k.key, 0);
@@ -815,7 +815,7 @@ retry:
 void bch_cannibalize_unlock(struct cache_set *c, struct closure *cl)
 {
 	if (c->try_harder == cl) {
-		time_stats_update(&c->try_harder_time, c->try_harder_start);
+		bch_time_stats_update(&c->try_harder_time, c->try_harder_start);
 		c->try_harder = NULL;
 		__closure_wake_up(&c->try_wait);
 	}
@@ -1536,7 +1536,7 @@ static void bch_btree_gc(struct closure *cl)
 
 	available = bch_btree_gc_finish(c);
 
-	time_stats_update(&c->btree_gc_time, start_time);
+	bch_time_stats_update(&c->btree_gc_time, start_time);
 
 	stats.key_bytes *= sizeof(uint64_t);
 	stats.dirty	<<= 9;
@@ -2007,7 +2007,7 @@ static int btree_split(struct btree *b, struct btree_op *op)
 	rw_unlock(true, n1);
 	btree_node_free(b, op);
 
-	time_stats_update(&b->c->btree_split_time, start_time);
+	bch_time_stats_update(&b->c->btree_split_time, start_time);
 
 	return 0;
 err_free2:
diff --git a/drivers/md/bcache/debug.c b/drivers/md/bcache/debug.c
index 141a5cac11a..732234d9ec0 100644
--- a/drivers/md/bcache/debug.c
+++ b/drivers/md/bcache/debug.c
@@ -200,7 +200,7 @@ void bch_data_verify(struct search *s)
 	if (!check)
 		return;
 
-	if (bio_alloc_pages(check, GFP_NOIO))
+	if (bch_bio_alloc_pages(check, GFP_NOIO))
 		goto out_put;
 
 	check->bi_rw		= READ_SYNC;
diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c
index 21fd1010cf5..b0a3d0577d1 100644
--- a/drivers/md/bcache/journal.c
+++ b/drivers/md/bcache/journal.c
@@ -54,7 +54,7 @@ reread:		left = ca->sb.bucket_size - offset;
 
 		bio->bi_end_io	= journal_read_endio;
 		bio->bi_private = &op->cl;
-		bio_map(bio, data);
+		bch_bio_map(bio, data);
 
 		closure_bio_submit(bio, &op->cl, ca);
 		closure_sync(&op->cl);
@@ -621,7 +621,7 @@ static void journal_write_unlocked(struct closure *cl)
 
 		bio->bi_end_io	= journal_write_endio;
 		bio->bi_private = w;
-		bio_map(bio, w->data);
+		bch_bio_map(bio, w->data);
 
 		trace_bcache_journal_write(bio);
 		bio_list_add(&list, bio);
diff --git a/drivers/md/bcache/movinggc.c b/drivers/md/bcache/movinggc.c
index e3ec0a550b0..8589512c972 100644
--- a/drivers/md/bcache/movinggc.c
+++ b/drivers/md/bcache/movinggc.c
@@ -85,7 +85,7 @@ static void moving_init(struct moving_io *io)
 					       PAGE_SECTORS);
 	bio->bi_private		= &io->s.cl;
 	bio->bi_io_vec		= bio->bi_inline_vecs;
-	bio_map(bio, NULL);
+	bch_bio_map(bio, NULL);
 }
 
 static void write_moving(struct closure *cl)
@@ -159,7 +159,7 @@ static void read_moving(struct closure *cl)
 		bio->bi_rw	= READ;
 		bio->bi_end_io	= read_moving_endio;
 
-		if (bio_alloc_pages(bio, GFP_KERNEL))
+		if (bch_bio_alloc_pages(bio, GFP_KERNEL))
 			goto err;
 
 		pr_debug("%s", pkey(&w->key));
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index dbda9646ef3..83731dc36f3 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -58,8 +58,8 @@ static ssize_t cache_mode_read(struct cgroup *cgrp, struct cftype *cft,
 			char __user *buf, size_t nbytes, loff_t *ppos)
 {
 	char tmp[1024];
-	int len = snprint_string_list(tmp, PAGE_SIZE, bch_cache_modes,
-				      cgroup_to_bcache(cgrp)->cache_mode + 1);
+	int len = bch_snprint_string_list(tmp, PAGE_SIZE, bch_cache_modes,
+					  cgroup_to_bcache(cgrp)->cache_mode + 1);
 
 	if (len < 0)
 		return len;
@@ -70,7 +70,7 @@ static ssize_t cache_mode_read(struct cgroup *cgrp, struct cftype *cft,
 static int cache_mode_write(struct cgroup *cgrp, struct cftype *cft,
 			    const char *buf)
 {
-	int v = read_string_list(buf, bch_cache_modes);
+	int v = bch_read_string_list(buf, bch_cache_modes);
 	if (v < 0)
 		return v;
 
@@ -205,7 +205,7 @@ static void bio_csum(struct bio *bio, struct bkey *k)
 
 	bio_for_each_segment(bv, bio, i) {
 		void *d = kmap(bv->bv_page) + bv->bv_offset;
-		csum = crc64_update(csum, d, bv->bv_len);
+		csum = bch_crc64_update(csum, d, bv->bv_len);
 		kunmap(bv->bv_page);
 	}
 
@@ -835,7 +835,7 @@ static void request_read_done(struct closure *cl)
 		s->op.cache_bio->bi_sector	= s->cache_miss->bi_sector;
 		s->op.cache_bio->bi_bdev	= s->cache_miss->bi_bdev;
 		s->op.cache_bio->bi_size	= s->cache_bio_sectors << 9;
-		bio_map(s->op.cache_bio, NULL);
+		bch_bio_map(s->op.cache_bio, NULL);
 
 		src = bio_iovec(s->op.cache_bio);
 		dst = bio_iovec(s->cache_miss);
@@ -962,8 +962,8 @@ static int cached_dev_cache_miss(struct btree *b, struct search *s,
 	if (!bch_btree_insert_check_key(b, &s->op, s->op.cache_bio))
 		goto out_put;
 
-	bio_map(s->op.cache_bio, NULL);
-	if (bio_alloc_pages(s->op.cache_bio, __GFP_NOWARN|GFP_NOIO))
+	bch_bio_map(s->op.cache_bio, NULL);
+	if (bch_bio_alloc_pages(s->op.cache_bio, __GFP_NOWARN|GFP_NOIO))
 		goto out_put;
 
 	s->cache_miss = miss;
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 484ae6c8f43..f47ecb5cb31 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -142,7 +142,7 @@ static const char *read_super(struct cache_sb *sb, struct block_device *bdev,
 		goto err;
 
 	err = "Bad UUID";
-	if (is_zero(sb->uuid, 16))
+	if (bch_is_zero(sb->uuid, 16))
 		goto err;
 
 	err = "Unsupported superblock version";
@@ -170,7 +170,7 @@ static const char *read_super(struct cache_sb *sb, struct block_device *bdev,
 		goto out;
 
 	err = "Bad UUID";
-	if (is_zero(sb->set_uuid, 16))
+	if (bch_is_zero(sb->set_uuid, 16))
 		goto err;
 
 	err = "Bad cache device number in set";
@@ -218,7 +218,7 @@ static void __write_super(struct cache_sb *sb, struct bio *bio)
 	bio->bi_sector	= SB_SECTOR;
 	bio->bi_rw	= REQ_SYNC|REQ_META;
 	bio->bi_size	= SB_SIZE;
-	bio_map(bio, NULL);
+	bch_bio_map(bio, NULL);
 
 	out->offset		= cpu_to_le64(sb->offset);
 	out->version		= cpu_to_le64(sb->version);
@@ -332,7 +332,7 @@ static void uuid_io(struct cache_set *c, unsigned long rw,
 
 		bio->bi_end_io	= uuid_endio;
 		bio->bi_private = cl;
-		bio_map(bio, c->uuids);
+		bch_bio_map(bio, c->uuids);
 
 		bch_submit_bbio(bio, c, k, i);
 
@@ -344,7 +344,7 @@ static void uuid_io(struct cache_set *c, unsigned long rw,
 		 pkey(&c->uuid_bucket));
 
 	for (u = c->uuids; u < c->uuids + c->nr_uuids; u++)
-		if (!is_zero(u->uuid, 16))
+		if (!bch_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);
@@ -491,7 +491,7 @@ static void prio_io(struct cache *ca, uint64_t bucket, unsigned long rw)
 
 	bio->bi_end_io	= prio_endio;
 	bio->bi_private = ca;
-	bio_map(bio, ca->disk_buckets);
+	bch_bio_map(bio, ca->disk_buckets);
 
 	closure_bio_submit(bio, &ca->prio, ca);
 	closure_sync(cl);
@@ -538,7 +538,7 @@ void bch_prio_write(struct cache *ca)
 
 		p->next_bucket	= ca->prio_buckets[i + 1];
 		p->magic	= pset_magic(ca);
-		p->csum		= crc64(&p->magic, bucket_bytes(ca) - 8);
+		p->csum		= bch_crc64(&p->magic, bucket_bytes(ca) - 8);
 
 		bucket = bch_bucket_alloc(ca, WATERMARK_PRIO, &cl);
 		BUG_ON(bucket == -1);
@@ -585,7 +585,7 @@ static void prio_read(struct cache *ca, uint64_t bucket)
 
 			prio_io(ca, bucket, READ_SYNC);
 
-			if (p->csum != crc64(&p->magic, bucket_bytes(ca) - 8))
+			if (p->csum != bch_crc64(&p->magic, bucket_bytes(ca) - 8))
 				pr_warn("bad csum reading priorities");
 
 			if (p->magic != pset_magic(ca))
@@ -898,7 +898,7 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c)
 	sysfs_remove_file(&dc->kobj, &sysfs_attach);
 	 */
 
-	if (is_zero(u->uuid, 16)) {
+	if (bch_is_zero(u->uuid, 16)) {
 		struct closure cl;
 		closure_init_stack(&cl);
 
diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c
index 5c7e77073b1..4d9cca47e4c 100644
--- a/drivers/md/bcache/sysfs.c
+++ b/drivers/md/bcache/sysfs.c
@@ -105,9 +105,9 @@ SHOW(__bch_cached_dev)
 #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));
+		return bch_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");
@@ -126,10 +126,10 @@ SHOW(__bch_cached_dev)
 		char dirty[20];
 		char derivative[20];
 		char target[20];
-		hprint(dirty,
+		bch_hprint(dirty,
 		       atomic_long_read(&dc->disk.sectors_dirty) << 9);
-		hprint(derivative,	dc->writeback_rate_derivative << 9);
-		hprint(target,		dc->writeback_rate_target << 9);
+		bch_hprint(derivative,	dc->writeback_rate_derivative << 9);
+		bch_hprint(target,	dc->writeback_rate_target << 9);
 
 		return sprintf(buf,
 			       "rate:\t\t%u\n"
@@ -202,7 +202,7 @@ STORE(__cached_dev)
 		bch_cached_dev_run(dc);
 
 	if (attr == &sysfs_cache_mode) {
-		ssize_t v = read_string_list(buf, bch_cache_modes + 1);
+		ssize_t v = bch_read_string_list(buf, bch_cache_modes + 1);
 
 		if (v < 0)
 			return v;
@@ -224,7 +224,7 @@ STORE(__cached_dev)
 	}
 
 	if (attr == &sysfs_attach) {
-		if (parse_uuid(buf, dc->sb.set_uuid) < 16)
+		if (bch_parse_uuid(buf, dc->sb.set_uuid) < 16)
 			return -EINVAL;
 
 		list_for_each_entry(c, &bch_cache_sets, list) {
@@ -657,9 +657,9 @@ SHOW(__bch_cache)
 		    ((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));
+		return bch_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)
@@ -747,7 +747,7 @@ STORE(__bch_cache)
 	}
 
 	if (attr == &sysfs_cache_replacement_policy) {
-		ssize_t v = read_string_list(buf, cache_replacement_policies);
+		ssize_t v = bch_read_string_list(buf, cache_replacement_policies);
 
 		if (v < 0)
 			return v;
diff --git a/drivers/md/bcache/sysfs.h b/drivers/md/bcache/sysfs.h
index 34e4ba1184f..0526fe92a68 100644
--- a/drivers/md/bcache/sysfs.h
+++ b/drivers/md/bcache/sysfs.h
@@ -62,7 +62,7 @@ do {									\
 #define sysfs_hprint(file, val)						\
 do {									\
 	if (attr == &sysfs_ ## file) {					\
-		ssize_t ret = hprint(buf, val);				\
+		ssize_t ret = bch_hprint(buf, val);			\
 		strcat(buf, "\n");					\
 		return ret + 1;						\
 	}								\
diff --git a/drivers/md/bcache/util.c b/drivers/md/bcache/util.c
index dcec2e4f84a..22324d8b284 100644
--- a/drivers/md/bcache/util.c
+++ b/drivers/md/bcache/util.c
@@ -19,7 +19,7 @@
 #define simple_strtouint(c, end, base)	simple_strtoul(c, end, base)
 
 #define STRTO_H(name, type)					\
-int name ## _h(const char *cp, type *res)		        \
+int bch_ ## name ## _h(const char *cp, type *res)		\
 {								\
 	int u = 0;						\
 	char *e;						\
@@ -67,14 +67,13 @@ int name ## _h(const char *cp, type *res)		        \
 	*res = i;						\
 	return 0;						\
 }								\
-EXPORT_SYMBOL_GPL(name ## _h);
 
 STRTO_H(strtoint, int)
 STRTO_H(strtouint, unsigned int)
 STRTO_H(strtoll, long long)
 STRTO_H(strtoull, unsigned long long)
 
-ssize_t hprint(char *buf, int64_t v)
+ssize_t bch_hprint(char *buf, int64_t v)
 {
 	static const char units[] = "?kMGTPEZY";
 	char dec[3] = "";
@@ -93,9 +92,8 @@ ssize_t hprint(char *buf, int64_t v)
 
 	return sprintf(buf, "%lli%s%c", v, dec, units[u]);
 }
-EXPORT_SYMBOL_GPL(hprint);
 
-ssize_t snprint_string_list(char *buf, size_t size, const char * const list[],
+ssize_t bch_snprint_string_list(char *buf, size_t size, const char * const list[],
 			    size_t selected)
 {
 	char *out = buf;
@@ -108,9 +106,8 @@ ssize_t snprint_string_list(char *buf, size_t size, const char * const list[],
 	out[-1] = '\n';
 	return out - buf;
 }
-EXPORT_SYMBOL_GPL(snprint_string_list);
 
-ssize_t read_string_list(const char *buf, const char * const list[])
+ssize_t bch_read_string_list(const char *buf, const char * const list[])
 {
 	size_t i;
 	char *s, *d = kstrndup(buf, PAGE_SIZE - 1, GFP_KERNEL);
@@ -130,9 +127,8 @@ ssize_t read_string_list(const char *buf, const char * const list[])
 
 	return i;
 }
-EXPORT_SYMBOL_GPL(read_string_list);
 
-bool is_zero(const char *p, size_t n)
+bool bch_is_zero(const char *p, size_t n)
 {
 	size_t i;
 
@@ -141,9 +137,8 @@ bool is_zero(const char *p, size_t n)
 			return false;
 	return true;
 }
-EXPORT_SYMBOL_GPL(is_zero);
 
-int parse_uuid(const char *s, char *uuid)
+int bch_parse_uuid(const char *s, char *uuid)
 {
 	size_t i, j, x;
 	memset(uuid, 0, 16);
@@ -170,9 +165,8 @@ int parse_uuid(const char *s, char *uuid)
 	}
 	return i;
 }
-EXPORT_SYMBOL_GPL(parse_uuid);
 
-void time_stats_update(struct time_stats *stats, uint64_t start_time)
+void bch_time_stats_update(struct time_stats *stats, uint64_t start_time)
 {
 	uint64_t now		= local_clock();
 	uint64_t duration	= time_after64(now, start_time)
@@ -195,9 +189,8 @@ void time_stats_update(struct time_stats *stats, uint64_t start_time)
 
 	stats->last = now ?: 1;
 }
-EXPORT_SYMBOL_GPL(time_stats_update);
 
-unsigned next_delay(struct ratelimit *d, uint64_t done)
+unsigned bch_next_delay(struct ratelimit *d, uint64_t done)
 {
 	uint64_t now = local_clock();
 
@@ -207,9 +200,8 @@ unsigned next_delay(struct ratelimit *d, uint64_t done)
 		? div_u64(d->next - now, NSEC_PER_SEC / HZ)
 		: 0;
 }
-EXPORT_SYMBOL_GPL(next_delay);
 
-void bio_map(struct bio *bio, void *base)
+void bch_bio_map(struct bio *bio, void *base)
 {
 	size_t size = bio->bi_size;
 	struct bio_vec *bv = bio->bi_io_vec;
@@ -235,9 +227,8 @@ start:		bv->bv_len	= min_t(size_t, PAGE_SIZE - bv->bv_offset,
 		size -= bv->bv_len;
 	}
 }
-EXPORT_SYMBOL_GPL(bio_map);
 
-int bio_alloc_pages(struct bio *bio, gfp_t gfp)
+int bch_bio_alloc_pages(struct bio *bio, gfp_t gfp)
 {
 	int i;
 	struct bio_vec *bv;
@@ -253,7 +244,6 @@ int bio_alloc_pages(struct bio *bio, gfp_t gfp)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(bio_alloc_pages);
 
 /*
  * Portions Copyright (c) 1996-2001, PostgreSQL Global Development Group (Any
@@ -365,7 +355,7 @@ static const uint64_t crc_table[256] = {
 	0x9AFCE626CE85B507
 };
 
-uint64_t crc64_update(uint64_t crc, const void *_data, size_t len)
+uint64_t bch_crc64_update(uint64_t crc, const void *_data, size_t len)
 {
 	const unsigned char *data = _data;
 
@@ -376,14 +366,12 @@ uint64_t crc64_update(uint64_t crc, const void *_data, size_t len)
 
 	return crc;
 }
-EXPORT_SYMBOL(crc64_update);
 
-uint64_t crc64(const void *data, size_t len)
+uint64_t bch_crc64(const void *data, size_t len)
 {
 	uint64_t crc = 0xffffffffffffffff;
 
-	crc = crc64_update(crc, data, len);
+	crc = bch_crc64_update(crc, data, len);
 
 	return crc ^ 0xffffffffffffffff;
 }
-EXPORT_SYMBOL(crc64);
diff --git a/drivers/md/bcache/util.h b/drivers/md/bcache/util.h
index 56705fdcc14..577393e38c3 100644
--- a/drivers/md/bcache/util.h
+++ b/drivers/md/bcache/util.h
@@ -307,42 +307,42 @@ do {									\
 #define ANYSINT_MAX(t)							\
 	((((t) 1 << (sizeof(t) * 8 - 2)) - (t) 1) * (t) 2 + (t) 1)
 
-int strtoint_h(const char *, int *);
-int strtouint_h(const char *, unsigned int *);
-int strtoll_h(const char *, long long *);
-int strtoull_h(const char *, unsigned long long *);
+int bch_strtoint_h(const char *, int *);
+int bch_strtouint_h(const char *, unsigned int *);
+int bch_strtoll_h(const char *, long long *);
+int bch_strtoull_h(const char *, unsigned long long *);
 
-static inline int strtol_h(const char *cp, long *res)
+static inline int bch_strtol_h(const char *cp, long *res)
 {
 #if BITS_PER_LONG == 32
-	return strtoint_h(cp, (int *) res);
+	return bch_strtoint_h(cp, (int *) res);
 #else
-	return strtoll_h(cp, (long long *) res);
+	return bch_strtoll_h(cp, (long long *) res);
 #endif
 }
 
-static inline int strtoul_h(const char *cp, long *res)
+static inline int bch_strtoul_h(const char *cp, long *res)
 {
 #if BITS_PER_LONG == 32
-	return strtouint_h(cp, (unsigned int *) res);
+	return bch_strtouint_h(cp, (unsigned int *) res);
 #else
-	return strtoull_h(cp, (unsigned long long *) res);
+	return bch_strtoull_h(cp, (unsigned long long *) res);
 #endif
 }
 
 #define strtoi_h(cp, res)						\
 	(__builtin_types_compatible_p(typeof(*res), int)		\
-	? strtoint_h(cp, (void *) res)					\
+	? bch_strtoint_h(cp, (void *) res)				\
 	: __builtin_types_compatible_p(typeof(*res), long)		\
-	? strtol_h(cp, (void *) res)					\
+	? bch_strtol_h(cp, (void *) res)				\
 	: __builtin_types_compatible_p(typeof(*res), long long)		\
-	? strtoll_h(cp, (void *) res)					\
+	? bch_strtoll_h(cp, (void *) res)				\
 	: __builtin_types_compatible_p(typeof(*res), unsigned int)	\
-	? strtouint_h(cp, (void *) res)					\
+	? bch_strtouint_h(cp, (void *) res)				\
 	: __builtin_types_compatible_p(typeof(*res), unsigned long)	\
-	? strtoul_h(cp, (void *) res)					\
+	? bch_strtoul_h(cp, (void *) res)				\
 	: __builtin_types_compatible_p(typeof(*res), unsigned long long)\
-	? strtoull_h(cp, (void *) res) : -EINVAL)
+	? bch_strtoull_h(cp, (void *) res) : -EINVAL)
 
 #define strtoul_safe(cp, var)						\
 ({									\
@@ -379,15 +379,15 @@ static inline int strtoul_h(const char *cp, long *res)
 		__builtin_types_compatible_p(typeof(var), const char *)	\
 		     ? "%s\n" : "%i\n", var)
 
-ssize_t hprint(char *buf, int64_t v);
+ssize_t bch_hprint(char *buf, int64_t v);
 
-bool is_zero(const char *p, size_t n);
-int parse_uuid(const char *s, char *uuid);
+bool bch_is_zero(const char *p, size_t n);
+int bch_parse_uuid(const char *s, char *uuid);
 
-ssize_t snprint_string_list(char *buf, size_t size, const char * const list[],
+ssize_t bch_snprint_string_list(char *buf, size_t size, const char * const list[],
 			    size_t selected);
 
-ssize_t read_string_list(const char *buf, const char * const list[]);
+ssize_t bch_read_string_list(const char *buf, const char * const list[]);
 
 struct time_stats {
 	/*
@@ -400,7 +400,7 @@ struct time_stats {
 	uint64_t	last;
 };
 
-void time_stats_update(struct time_stats *stats, uint64_t time);
+void bch_time_stats_update(struct time_stats *stats, uint64_t time);
 
 #define NSEC_PER_ns			1L
 #define NSEC_PER_us			NSEC_PER_USEC
@@ -462,7 +462,7 @@ static inline void ratelimit_reset(struct ratelimit *d)
 	d->next = local_clock();
 }
 
-unsigned next_delay(struct ratelimit *d, uint64_t done);
+unsigned bch_next_delay(struct ratelimit *d, uint64_t done);
 
 #define __DIV_SAFE(n, d, zero)						\
 ({									\
@@ -568,9 +568,9 @@ static inline unsigned fract_exp_two(unsigned x, unsigned fract_bits)
 
 #define bio_end(bio)	((bio)->bi_sector + bio_sectors(bio))
 
-void bio_map(struct bio *bio, void *base);
+void bch_bio_map(struct bio *bio, void *base);
 
-int bio_alloc_pages(struct bio *bio, gfp_t gfp);
+int bch_bio_alloc_pages(struct bio *bio, gfp_t gfp);
 
 static inline sector_t bdev_sectors(struct block_device *bdev)
 {
@@ -583,7 +583,7 @@ do {									\
 	bch_generic_make_request(bio, &(dev)->bio_split_hook);		\
 } while (0)
 
-uint64_t crc64_update(uint64_t, const void *, size_t);
-uint64_t crc64(const void *, size_t);
+uint64_t bch_crc64_update(uint64_t, const void *, size_t);
+uint64_t bch_crc64(const void *, size_t);
 
 #endif /* _BCACHE_UTIL_H */
diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index a80ee5373fd..93e7e31a4bd 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -95,7 +95,7 @@ static unsigned writeback_delay(struct cached_dev *dc, unsigned sectors)
 	    !dc->writeback_percent)
 		return 0;
 
-	return next_delay(&dc->writeback_rate, sectors * 10000000ULL);
+	return bch_next_delay(&dc->writeback_rate, sectors * 10000000ULL);
 }
 
 /* Background writeback */
@@ -118,7 +118,7 @@ static void dirty_init(struct keybuf_key *w)
 	bio->bi_max_vecs	= DIV_ROUND_UP(KEY_SIZE(&w->key), PAGE_SECTORS);
 	bio->bi_private		= w;
 	bio->bi_io_vec		= bio->bi_inline_vecs;
-	bio_map(bio, NULL);
+	bch_bio_map(bio, NULL);
 }
 
 static void refill_dirty(struct closure *cl)
@@ -349,7 +349,7 @@ static void read_dirty(struct closure *cl)
 		io->bio.bi_rw		= READ;
 		io->bio.bi_end_io	= read_dirty_endio;
 
-		if (bio_alloc_pages(&io->bio, GFP_KERNEL))
+		if (bch_bio_alloc_pages(&io->bio, GFP_KERNEL))
 			goto err_free;
 
 		pr_debug("%s", pkey(&w->key));
-- 
cgit v1.2.3-70-g09d2


From 2903381fce71004a7ce24d40fad53ba8236a3921 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <koverstreet@google.com>
Date: Thu, 11 Apr 2013 15:14:35 -0700
Subject: bcache: Take data offset from the bdev superblock.

Add a new superblock version, and consolidate related defines.

Signed-off-by: Gabriel de Perthuis <g2p.code+bcache@gmail.com>
Signed-off-by: Kent Overstreet <koverstreet@google.com>
---
 drivers/md/bcache/bcache.h  |  47 +++++++++++++++----
 drivers/md/bcache/request.c |   2 +-
 drivers/md/bcache/super.c   | 108 +++++++++++++++++++++++++-------------------
 3 files changed, 100 insertions(+), 57 deletions(-)

(limited to 'drivers/md/bcache/request.c')

diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index f05723565f1..340146d7c17 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -223,11 +223,17 @@ struct bkey {
 #define BKEY_PADDED(key)					\
 	union { struct bkey key; uint64_t key ## _pad[BKEY_PAD]; }
 
-/* Version 1: Backing device
+/* Version 0: Cache device
+ * Version 1: Backing device
  * Version 2: Seed pointer into btree node checksum
- * Version 3: New UUID format
+ * Version 3: Cache device with new UUID format
+ * Version 4: Backing device with data offset
  */
-#define BCACHE_SB_VERSION	3
+#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
@@ -236,13 +242,12 @@ struct bkey {
 /* SB_JOURNAL_BUCKETS must be divisible by BITS_PER_LONG */
 #define MAX_CACHES_PER_SET	8
 
-#define BDEV_DATA_START		16	/* sectors */
+#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;
-#define CACHE_BACKING_DEV	1
 
 	uint8_t			magic[16];
 
@@ -257,12 +262,28 @@ struct cache_sb {
 	uint64_t		seq;
 	uint64_t		pad[8];
 
-	uint64_t		nbuckets;	/* device size */
-	uint16_t		block_size;	/* sectors */
-	uint16_t		bucket_size;	/* sectors */
+	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;
+		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 */
 
@@ -861,6 +882,12 @@ static inline bool key_merging_disabled(struct cache_set *c)
 #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 {
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index 83731dc36f3..e5ff12e52d5 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -1220,7 +1220,7 @@ static void cached_dev_make_request(struct request_queue *q, struct bio *bio)
 	part_stat_unlock();
 
 	bio->bi_bdev = dc->bdev;
-	bio->bi_sector += BDEV_DATA_START;
+	bio->bi_sector += dc->sb.data_offset;
 
 	if (cached_dev_get(dc)) {
 		s = search_alloc(bio, d);
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 5fa3cd2d9ff..f1e69f2fad3 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -110,15 +110,7 @@ static const char *read_super(struct cache_sb *sb, struct block_device *bdev,
 
 	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);
 
@@ -147,53 +139,77 @@ static const char *read_super(struct cache_sb *sb, struct block_device *bdev,
 	if (bch_is_zero(sb->uuid, 16))
 		goto err;
 
-	err = "Unsupported superblock version";
-	if (sb->version > BCACHE_SB_VERSION)
-		goto err;
+	switch (sb->version) {
+	case BCACHE_SB_VERSION_BDEV:
+		sb->block_size	= le16_to_cpu(s->block_size);
+		sb->data_offset	= BDEV_DATA_START_DEFAULT;
+		break;
+	case BCACHE_SB_VERSION_BDEV_WITH_OFFSET:
+		sb->block_size	= le16_to_cpu(s->block_size);
+		sb->data_offset	= le64_to_cpu(s->data_offset);
+
+		err = "Bad data offset";
+		if (sb->data_offset < BDEV_DATA_START_DEFAULT)
+			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;
+		break;
+	case BCACHE_SB_VERSION_CDEV:
+	case BCACHE_SB_VERSION_CDEV_WITH_UUID:
+		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);
 
-	err = "Too many buckets";
-	if (sb->nbuckets > LONG_MAX)
-		goto err;
+		sb->nr_in_set	= le16_to_cpu(s->nr_in_set);
+		sb->nr_this_dev	= le16_to_cpu(s->nr_this_dev);
 
-	err = "Not enough buckets";
-	if (sb->nbuckets < 1 << 7)
-		goto err;
+		err = "Too many buckets";
+		if (sb->nbuckets > LONG_MAX)
+			goto err;
 
-	err = "Invalid superblock: device too small";
-	if (get_capacity(bdev->bd_disk) < sb->bucket_size * sb->nbuckets)
-		goto err;
+		err = "Not enough buckets";
+		if (sb->nbuckets < 1 << 7)
+			goto err;
 
-	if (sb->version == CACHE_BACKING_DEV)
-		goto out;
+		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 = "Bad UUID";
-	if (bch_is_zero(sb->set_uuid, 16))
-		goto err;
+		err = "Invalid superblock: device too small";
+		if (get_capacity(bdev->bd_disk) < sb->bucket_size * sb->nbuckets)
+			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 = "Bad UUID";
+		if (bch_is_zero(sb->set_uuid, 16))
+			goto err;
 
-	err = "Journal buckets not sequential";
-	for (i = 0; i < sb->keys; i++)
-		if (sb->d[i] != sb->first_bucket + i)
+		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 = "Too many journal buckets";
-	if (sb->first_bucket + sb->keys > sb->nbuckets)
-		goto err;
+		err = "Journal buckets not sequential";
+		for (i = 0; i < sb->keys; i++)
+			if (sb->d[i] != sb->first_bucket + i)
+				goto err;
 
-	err = "Invalid superblock: first bucket comes before end of super";
-	if (sb->first_bucket * sb->bucket_size < 16)
+		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;
+
+		break;
+	default:
+		err = "Unsupported superblock version";
 		goto err;
-out:
+	}
+
 	sb->last_mount = get_seconds();
 	err = NULL;
 
@@ -286,7 +302,7 @@ void bcache_write_super(struct cache_set *c)
 	for_each_cache(ca, c, i) {
 		struct bio *bio = &ca->sb_bio;
 
-		ca->sb.version		= BCACHE_SB_VERSION;
+		ca->sb.version		= BCACHE_SB_VERSION_CDEV_WITH_UUID;
 		ca->sb.seq		= c->sb.seq;
 		ca->sb.last_mount	= c->sb.last_mount;
 
@@ -1049,7 +1065,7 @@ static const char *register_bdev(struct cache_sb *sb, struct page *sb_page,
 
 	g = dc->disk.disk;
 
-	set_capacity(g, dc->bdev->bd_part->nr_sects - 16);
+	set_capacity(g, dc->bdev->bd_part->nr_sects - dc->sb.data_offset);
 
 	bch_cached_dev_request_init(dc);
 
@@ -1802,7 +1818,7 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
 	if (err)
 		goto err_close;
 
-	if (sb->version == CACHE_BACKING_DEV) {
+	if (SB_IS_BDEV(sb)) {
 		struct cached_dev *dc = kzalloc(sizeof(*dc), GFP_KERNEL);
 
 		err = register_bdev(sb, sb_page, bdev, dc);
-- 
cgit v1.2.3-70-g09d2