bcache: Convert btree_insert_check_key() to btree_insert_node()

This was the main point of all this refactoring - now,
btree_insert_check_key() won't fail just because the leaf node happened
to be full.

Signed-off-by: Kent Overstreet <kmo@daterainc.com>

drivers/md/bcache/bcache.h

@@ -1091,14 +1091,6 @@ do {									\
 	for (b = (ca)->buckets + (ca)->sb.first_bucket;			\
 	     b < (ca)->buckets + (ca)->sb.nbuckets; b++)
 
-static inline void __bkey_put(struct cache_set *c, struct bkey *k)
-{
-	unsigned i;
-
-	for (i = 0; i < KEY_PTRS(k); i++)
-		atomic_dec_bug(&PTR_BUCKET(c, k, i)->pin);
-}
-
 static inline void cached_dev_put(struct cached_dev *dc)
 {
 	if (atomic_dec_and_test(&dc->count))

drivers/md/bcache/btree.c

@@ -118,6 +118,15 @@ void bch_btree_op_init_stack(struct btree_op *op)
 
 /* Btree key manipulation */
 
+void __bkey_put(struct cache_set *c, struct bkey *k)
+{
+	unsigned i;
+
+	for (i = 0; i < KEY_PTRS(k); i++)
+		if (ptr_available(c, k, i))
+			atomic_dec_bug(&PTR_BUCKET(c, k, i)->pin);
+}
+
 static void bkey_put(struct cache_set *c, struct bkey *k, int level)
 {
 	if ((level && KEY_OFFSET(k)) || !level)
@@ -1855,8 +1864,6 @@ static bool bch_btree_insert_keys(struct btree *b, struct btree_op *op,
 	bool ret = false;
 	unsigned oldsize = bch_count_data(b);
 
-	BUG_ON(!insert_lock(op, b));
-
 	while (!bch_keylist_empty(insert_keys)) {
 		struct bset *i = write_block(b);
 		struct bkey *k = insert_keys->bottom;
@@ -1898,39 +1905,6 @@ static bool bch_btree_insert_keys(struct btree *b, struct btree_op *op,
 	return ret;
 }
 
-bool bch_btree_insert_check_key(struct btree *b, struct btree_op *op,
-				   struct bio *bio)
-{
-	bool ret = false;
-	uint64_t btree_ptr = b->key.ptr[0];
-	unsigned long seq = b->seq;
-	BKEY_PADDED(k) tmp;
-
-	rw_unlock(false, b);
-	rw_lock(true, b, b->level);
-
-	if (b->key.ptr[0] != btree_ptr ||
-	    b->seq != seq + 1 ||
-	    should_split(b))
-		goto out;
-
-	op->replace = KEY(op->inode, bio_end_sector(bio), bio_sectors(bio));
-
-	SET_KEY_PTRS(&op->replace, 1);
-	get_random_bytes(&op->replace.ptr[0], sizeof(uint64_t));
-
-	SET_PTR_DEV(&op->replace, 0, PTR_CHECK_DEV);
-
-	bkey_copy(&tmp.k, &op->replace);
-
-	BUG_ON(op->type != BTREE_INSERT);
-	BUG_ON(!btree_insert_key(b, op, &tmp.k));
-	ret = true;
-out:
-	downgrade_write(&b->lock);
-	return ret;
-}
-
 static int btree_split(struct btree *b, struct btree_op *op,
 		       struct keylist *insert_keys,
 		       struct keylist *parent_keys)
@@ -2097,6 +2071,44 @@ static int bch_btree_insert_node(struct btree *b, struct btree_op *op,
 	return ret;
 }
 
+int bch_btree_insert_check_key(struct btree *b, struct btree_op *op,
+			       struct bkey *check_key)
+{
+	int ret = -EINTR;
+	uint64_t btree_ptr = b->key.ptr[0];
+	unsigned long seq = b->seq;
+	struct keylist insert;
+	bool upgrade = op->lock == -1;
+
+	bch_keylist_init(&insert);
+
+	if (upgrade) {
+		rw_unlock(false, b);
+		rw_lock(true, b, b->level);
+
+		if (b->key.ptr[0] != btree_ptr ||
+		    b->seq != seq + 1)
+			goto out;
+	}
+
+	SET_KEY_PTRS(check_key, 1);
+	get_random_bytes(&check_key->ptr[0], sizeof(uint64_t));
+
+	SET_PTR_DEV(check_key, 0, PTR_CHECK_DEV);
+
+	bch_keylist_add(&insert, check_key);
+
+	BUG_ON(op->type != BTREE_INSERT);
+
+	ret = bch_btree_insert_node(b, op, &insert);
+
+	BUG_ON(!ret && !bch_keylist_empty(&insert));
+out:
+	if (upgrade)
+		downgrade_write(&b->lock);
+	return ret;
+}
+
 static int bch_btree_insert_recurse(struct btree *b, struct btree_op *op)
 {
 	if (bch_keylist_empty(&op->keys))

drivers/md/bcache/btree.h

@@ -216,6 +216,8 @@ static inline struct bkey *bch_btree_iter_init(struct btree *b,
 	return __bch_btree_iter_init(b, iter, search, b->sets);
 }
 
+void __bkey_put(struct cache_set *c, struct bkey *k);
+
 /* Looping macros */
 
 #define for_each_cached_btree(b, c, iter)				\
@@ -380,8 +382,8 @@ struct btree *bch_btree_node_alloc(struct cache_set *, int, struct closure *);
 struct btree *bch_btree_node_get(struct cache_set *, struct bkey *,
 				int, struct btree_op *);
 
-bool bch_btree_insert_check_key(struct btree *, struct btree_op *,
-				   struct bio *);
+int bch_btree_insert_check_key(struct btree *, struct btree_op *,
+			       struct bkey *);
 int bch_btree_insert(struct btree_op *, struct cache_set *);
 
 int bch_btree_search_recurse(struct btree *, struct btree_op *);

drivers/md/bcache/request.c

@@ -869,35 +869,39 @@ static int cached_dev_cache_miss(struct btree *b, struct search *s,
 				 struct bio *bio, unsigned sectors)
 {
 	int ret = 0;
-	unsigned reada;
+	unsigned reada = 0;
 	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 == bio)
-		s->op.lookup_done = true;
+	if (s->cache_miss || s->op.skip) {
+		miss = bch_bio_split(bio, sectors, GFP_NOIO, s->d->bio_split);
+		if (miss == bio)
+			s->op.lookup_done = true;
+		goto out_submit;
+	}
 
-	miss->bi_end_io		= request_endio;
-	miss->bi_private	= &s->cl;
+	if (!(bio->bi_rw & REQ_RAHEAD) &&
+	    !(bio->bi_rw & REQ_META) &&
+	    s->op.c->gc_stats.in_use < CUTOFF_CACHE_READA)
+		reada = min_t(sector_t, dc->readahead >> 9,
+			      bdev_sectors(bio->bi_bdev) - bio_end_sector(bio));
 
-	if (s->cache_miss || s->op.skip)
-		goto out_submit;
+	s->cache_bio_sectors = min(sectors, bio_sectors(bio) + reada);
 
-	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_sector(miss) + reada > bdev_sectors(miss->bi_bdev))
-			reada = bdev_sectors(miss->bi_bdev) -
-				bio_end_sector(miss);
-	}
+	s->op.replace = KEY(s->op.inode, bio->bi_sector +
+			    s->cache_bio_sectors, s->cache_bio_sectors);
+
+	ret = bch_btree_insert_check_key(b, &s->op, &s->op.replace);
+	if (ret)
+		return ret;
+
+	miss = bch_bio_split(bio, sectors, GFP_NOIO, s->d->bio_split);
+	if (miss == bio)
+		s->op.lookup_done = true;
+	else
+		/* btree_search_recurse()'s btree iterator is no good anymore */
+		ret = -EINTR;
 
-	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);
@@ -912,11 +916,6 @@ static int cached_dev_cache_miss(struct btree *b, struct search *s,
 	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;
-
 	bch_bio_map(s->op.cache_bio, NULL);
 	if (bio_alloc_pages(s->op.cache_bio, __GFP_NOWARN|GFP_NOIO))
 		goto out_put;
@@ -931,6 +930,8 @@ out_put:
 	bio_put(s->op.cache_bio);
 	s->op.cache_bio = NULL;
 out_submit:
+	miss->bi_end_io		= request_endio;
+	miss->bi_private	= &s->cl;
 	closure_bio_submit(miss, &s->cl, s->d);
 	return ret;
 }