bcache: reduce cache_set devices iteration by devices_max_used

Member devices of struct cache_set is used to reference all attached
bcache devices to this cache set. If it is treated as array of pointers,
size of devices[] is indicated by member nr_uuids of struct cache_set.

nr_uuids is calculated in drivers/md/super.c:bch_cache_set_alloc(),
	bucket_bytes(c) / sizeof(struct uuid_entry)
Bucket size is determined by user space tool "make-bcache", by default it
is 1024 sectors (defined in bcache-tools/make-bcache.c:main()). So default
nr_uuids value is 4096 from the above calculation.

Every time when bcache code iterates bcache devices of a cache set, all
the 4096 pointers are checked even only 1 bcache device is attached to the
cache set, that's a wast of time and unncessary.

This patch adds a member devices_max_used to struct cache_set. Its value
is 1 + the maximum used index of devices[] in a cache set. When iterating
all valid bcache devices of a cache set, use c->devices_max_used in
for-loop may reduce a lot of useless checking.

Personally, my motivation of this patch is not for performance, I use it
in bcache debugging, which helps me to narrow down the scape to check
valid bcached devices of a cache set.
Signed-off-by: Coly Li <colyli@suse.de>
Reviewed-by: Michael Lyle <mlyle@lyle.org>
Reviewed-by: Tang Junhui <tang.junhui@zte.com.cn>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

drivers/md/bcache/bcache.h

@@ -497,6 +497,7 @@ struct cache_set {
 	int			caches_loaded;
 
 	struct bcache_device	**devices;
+	unsigned		devices_max_used;
 	struct list_head	cached_devs;
 	uint64_t		cached_dev_sectors;
 	struct closure		caching;

drivers/md/bcache/btree.c

@@ -1679,7 +1679,7 @@ static void bch_btree_gc_finish(struct cache_set *c)
 
 	/* don't reclaim buckets to which writeback keys point */
 	rcu_read_lock();
-	for (i = 0; i < c->nr_uuids; i++) {
+	for (i = 0; i < c->devices_max_used; i++) {
 		struct bcache_device *d = c->devices[i];
 		struct cached_dev *dc;
 		struct keybuf_key *w, *n;

drivers/md/bcache/super.c

@@ -721,6 +721,9 @@ static void bcache_device_attach(struct bcache_device *d, struct cache_set *c,
 	d->c = c;
 	c->devices[id] = d;
 
+	if (id >= c->devices_max_used)
+		c->devices_max_used = id + 1;
+
 	closure_get(&c->caching);
 }
 
@@ -1267,7 +1270,7 @@ static int flash_devs_run(struct cache_set *c)
 	struct uuid_entry *u;
 
 	for (u = c->uuids;
-	     u < c->uuids + c->nr_uuids && !ret;
+	     u < c->uuids + c->devices_max_used && !ret;
 	     u++)
 		if (UUID_FLASH_ONLY(u))
 			ret = flash_dev_run(c, u);
@@ -1433,7 +1436,7 @@ static void __cache_set_unregister(struct closure *cl)
 
 	mutex_lock(&bch_register_lock);
 
-	for (i = 0; i < c->nr_uuids; i++)
+	for (i = 0; i < c->devices_max_used; i++)
 		if (c->devices[i]) {
 			if (!UUID_FLASH_ONLY(&c->uuids[i]) &&
 			    test_bit(CACHE_SET_UNREGISTERING, &c->flags)) {
@@ -1496,7 +1499,7 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb)
 	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->devices_max_used	= 0;
 	c->btree_pages		= bucket_pages(c);
 	if (c->btree_pages > BTREE_MAX_PAGES)
 		c->btree_pages = max_t(int, c->btree_pages / 4,

drivers/md/bcache/writeback.h

@@ -24,7 +24,7 @@ static inline uint64_t  bcache_flash_devs_sectors_dirty(struct cache_set *c)
 
 	mutex_lock(&bch_register_lock);
 
-	for (i = 0; i < c->nr_uuids; i++) {
+	for (i = 0; i < c->devices_max_used; i++) {
 		struct bcache_device *d = c->devices[i];
 
 		if (!d || !UUID_FLASH_ONLY(&c->uuids[i]))