1 files changed, 322 insertions, 255 deletions

diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c
index b2fd412715b1..144693b7c46a 100644
--- a/drivers/md/bcache/journal.c
+++ b/drivers/md/bcache/journal.c
@@ -47,20 +47,18 @@ static int journal_read_bucket(struct cache *ca, struct list_head *list,
 
 	closure_init_stack(&cl);
 
-	pr_debug("reading %u", bucket_index);
+	pr_debug("reading %u\n", bucket_index);
 
 	while (offset < ca->sb.bucket_size) {
 reread:		left = ca->sb.bucket_size - offset;
 		len = min_t(unsigned int, left, PAGE_SECTORS << JSET_BITS);
 
-		bio_reset(bio);
+		bio_reset(bio, ca->bdev, REQ_OP_READ);
 		bio->bi_iter.bi_sector	= bucket + offset;
-		bio_set_dev(bio, ca->bdev);
 		bio->bi_iter.bi_size	= len << 9;
 
 		bio->bi_end_io	= journal_read_endio;
 		bio->bi_private = &cl;
-		bio_set_op_attrs(bio, REQ_OP_READ, 0);
 		bch_bio_map(bio, data);
 
 		closure_bio_submit(ca->set, bio, &cl);
@@ -78,13 +76,13 @@ reread:		left = ca->sb.bucket_size - offset;
 			size_t blocks, bytes = set_bytes(j);
 
 			if (j->magic != jset_magic(&ca->sb)) {
-				pr_debug("%u: bad magic", bucket_index);
+				pr_debug("%u: bad magic\n", bucket_index);
 				return ret;
 			}
 
 			if (bytes > left << 9 ||
 			    bytes > PAGE_SIZE << JSET_BITS) {
-				pr_info("%u: too big, %zu bytes, offset %u",
+				pr_info("%u: too big, %zu bytes, offset %u\n",
 					bucket_index, bytes, offset);
 				return ret;
 			}
@@ -93,13 +91,27 @@ reread:		left = ca->sb.bucket_size - offset;
 				goto reread;
 
 			if (j->csum != csum_set(j)) {
-				pr_info("%u: bad csum, %zu bytes, offset %u",
+				pr_info("%u: bad csum, %zu bytes, offset %u\n",
 					bucket_index, bytes, offset);
 				return ret;
 			}
 
-			blocks = set_blocks(j, block_bytes(ca->set));
+			blocks = set_blocks(j, block_bytes(ca));
 
+			/*
+			 * Nodes in 'list' are in linear increasing order of
+			 * i->j.seq, the node on head has the smallest (oldest)
+			 * journal seq, the node on tail has the biggest
+			 * (latest) journal seq.
+			 */
+
+			/*
+			 * Check from the oldest jset for last_seq. If
+			 * i->j.seq < j->last_seq, it means the oldest jset
+			 * in list is expired and useless, remove it from
+			 * this list. Otherwise, j is a candidate jset for
+			 * further following checks.
+			 */
 			while (!list_empty(list)) {
 				i = list_first_entry(list,
 					struct journal_replay, list);
@@ -109,13 +121,22 @@ reread:		left = ca->sb.bucket_size - offset;
 				kfree(i);
 			}
 
+			/* iterate list in reverse order (from latest jset) */
 			list_for_each_entry_reverse(i, list, list) {
 				if (j->seq == i->j.seq)
 					goto next_set;
 
+				/*
+				 * if j->seq is less than any i->j.last_seq
+				 * in list, j is an expired and useless jset.
+				 */
 				if (j->seq < i->j.last_seq)
 					goto next_set;
 
+				/*
+				 * 'where' points to first jset in list which
+				 * is elder then j.
+				 */
 				if (j->seq > i->j.seq) {
 					where = &i->list;
 					goto add;
@@ -128,11 +149,14 @@ add:
 				    bytes, GFP_KERNEL);
 			if (!i)
 				return -ENOMEM;
-			memcpy(&i->j, j, bytes);
+			unsafe_memcpy(&i->j, j, bytes,
+				/* "bytes" was calculated by set_bytes() above */);
+			/* Add to the location after 'where' points to */
 			list_add(&i->list, where);
 			ret = 1;
 
-			ja->seq[bucket_index] = j->seq;
+			if (j->seq > ja->seq[bucket_index])
+				ja->seq[bucket_index] = j->seq;
 next_set:
 			offset	+= blocks * ca->sb.block_size;
 			len	-= blocks * ca->sb.block_size;
@@ -147,121 +171,115 @@ int bch_journal_read(struct cache_set *c, struct list_head *list)
 {
 #define read_bucket(b)							\
 	({								\
-		int ret = journal_read_bucket(ca, list, b);		\
+		ret = journal_read_bucket(ca, list, b);			\
 		__set_bit(b, bitmap);					\
 		if (ret < 0)						\
 			return ret;					\
 		ret;							\
 	})
 
-	struct cache *ca;
-	unsigned int iter;
-
-	for_each_cache(ca, c, iter) {
-		struct journal_device *ja = &ca->journal;
-		DECLARE_BITMAP(bitmap, SB_JOURNAL_BUCKETS);
-		unsigned int i, l, r, m;
-		uint64_t seq;
+	struct cache *ca = c->cache;
+	int ret = 0;
+	struct journal_device *ja = &ca->journal;
+	DECLARE_BITMAP(bitmap, SB_JOURNAL_BUCKETS);
+	unsigned int i, l, r, m;
+	uint64_t seq;
 
-		bitmap_zero(bitmap, SB_JOURNAL_BUCKETS);
-		pr_debug("%u journal buckets", ca->sb.njournal_buckets);
+	bitmap_zero(bitmap, SB_JOURNAL_BUCKETS);
+	pr_debug("%u journal buckets\n", ca->sb.njournal_buckets);
 
+	/*
+	 * Read journal buckets ordered by golden ratio hash to quickly
+	 * find a sequence of buckets with valid journal entries
+	 */
+	for (i = 0; i < ca->sb.njournal_buckets; i++) {
 		/*
-		 * Read journal buckets ordered by golden ratio hash to quickly
-		 * find a sequence of buckets with valid journal entries
+		 * We must try the index l with ZERO first for
+		 * correctness due to the scenario that the journal
+		 * bucket is circular buffer which might have wrapped
 		 */
-		for (i = 0; i < ca->sb.njournal_buckets; i++) {
-			/*
-			 * We must try the index l with ZERO first for
-			 * correctness due to the scenario that the journal
-			 * bucket is circular buffer which might have wrapped
-			 */
-			l = (i * 2654435769U) % ca->sb.njournal_buckets;
+		l = (i * 2654435769U) % ca->sb.njournal_buckets;
 
-			if (test_bit(l, bitmap))
-				break;
+		if (test_bit(l, bitmap))
+			break;
 
-			if (read_bucket(l))
-				goto bsearch;
-		}
+		if (read_bucket(l))
+			goto bsearch;
+	}
 
-		/*
-		 * If that fails, check all the buckets we haven't checked
-		 * already
-		 */
-		pr_debug("falling back to linear search");
+	/*
+	 * If that fails, check all the buckets we haven't checked
+	 * already
+	 */
+	pr_debug("falling back to linear search\n");
 
-		for (l = find_first_zero_bit(bitmap, ca->sb.njournal_buckets);
-		     l < ca->sb.njournal_buckets;
-		     l = find_next_zero_bit(bitmap, ca->sb.njournal_buckets,
-					    l + 1))
-			if (read_bucket(l))
-				goto bsearch;
+	for_each_clear_bit(l, bitmap, ca->sb.njournal_buckets)
+		if (read_bucket(l))
+			goto bsearch;
 
-		/* no journal entries on this device? */
-		if (l == ca->sb.njournal_buckets)
-			continue;
+	/* no journal entries on this device? */
+	if (l == ca->sb.njournal_buckets)
+		goto out;
 bsearch:
-		BUG_ON(list_empty(list));
+	BUG_ON(list_empty(list));
 
-		/* Binary search */
-		m = l;
-		r = find_next_bit(bitmap, ca->sb.njournal_buckets, l + 1);
-		pr_debug("starting binary search, l %u r %u", l, r);
+	/* Binary search */
+	m = l;
+	r = find_next_bit(bitmap, ca->sb.njournal_buckets, l + 1);
+	pr_debug("starting binary search, l %u r %u\n", l, r);
 
-		while (l + 1 < r) {
-			seq = list_entry(list->prev, struct journal_replay,
-					 list)->j.seq;
+	while (l + 1 < r) {
+		seq = list_entry(list->prev, struct journal_replay,
+				 list)->j.seq;
 
-			m = (l + r) >> 1;
-			read_bucket(m);
+		m = (l + r) >> 1;
+		read_bucket(m);
 
-			if (seq != list_entry(list->prev, struct journal_replay,
-					      list)->j.seq)
-				l = m;
-			else
-				r = m;
-		}
+		if (seq != list_entry(list->prev, struct journal_replay,
+				      list)->j.seq)
+			l = m;
+		else
+			r = m;
+	}
 
-		/*
-		 * Read buckets in reverse order until we stop finding more
-		 * journal entries
-		 */
-		pr_debug("finishing up: m %u njournal_buckets %u",
-			 m, ca->sb.njournal_buckets);
-		l = m;
+	/*
+	 * Read buckets in reverse order until we stop finding more
+	 * journal entries
+	 */
+	pr_debug("finishing up: m %u njournal_buckets %u\n",
+		 m, ca->sb.njournal_buckets);
+	l = m;
 
-		while (1) {
-			if (!l--)
-				l = ca->sb.njournal_buckets - 1;
+	while (1) {
+		if (!l--)
+			l = ca->sb.njournal_buckets - 1;
 
-			if (l == m)
-				break;
+		if (l == m)
+			break;
 
-			if (test_bit(l, bitmap))
-				continue;
+		if (test_bit(l, bitmap))
+			continue;
 
-			if (!read_bucket(l))
-				break;
-		}
+		if (!read_bucket(l))
+			break;
+	}
 
-		seq = 0;
+	seq = 0;
 
-		for (i = 0; i < ca->sb.njournal_buckets; i++)
-			if (ja->seq[i] > seq) {
-				seq = ja->seq[i];
-				/*
-				 * When journal_reclaim() goes to allocate for
-				 * the first time, it'll use the bucket after
-				 * ja->cur_idx
-				 */
-				ja->cur_idx = i;
-				ja->last_idx = ja->discard_idx = (i + 1) %
-					ca->sb.njournal_buckets;
+	for (i = 0; i < ca->sb.njournal_buckets; i++)
+		if (ja->seq[i] > seq) {
+			seq = ja->seq[i];
+			/*
+			 * When journal_reclaim() goes to allocate for
+			 * the first time, it'll use the bucket after
+			 * ja->cur_idx
+			 */
+			ja->cur_idx = i;
+			ja->last_idx = (i + 1) % ca->sb.njournal_buckets;
 
-			}
-	}
+		}
 
+out:
 	if (!list_empty(list))
 		c->journal.seq = list_entry(list->prev,
 					    struct journal_replay,
@@ -330,9 +348,12 @@ int bch_journal_replay(struct cache_set *s, struct list_head *list)
 	list_for_each_entry(i, list, list) {
 		BUG_ON(i->pin && atomic_read(i->pin) != 1);
 
-		cache_set_err_on(n != i->j.seq, s,
-"bcache: journal entries %llu-%llu missing! (replaying %llu-%llu)",
-				 n, i->j.seq - 1, start, end);
+		if (n != i->j.seq) {
+			pr_err("journal entries %llu-%llu missing! (replaying %llu-%llu)\n",
+				n, i->j.seq - 1, start, end);
+			ret = -EIO;
+			goto err;
+		}
 
 		for (k = i->j.start;
 		     k < bset_bkey_last(&i->j);
@@ -357,7 +378,7 @@ int bch_journal_replay(struct cache_set *s, struct list_head *list)
 		entries++;
 	}
 
-	pr_info("journal replay done, %i keys in %i entries, seq %llu",
+	pr_info("journal replay done, %i keys in %i entries, seq %llu\n",
 		keys, entries, end);
 err:
 	while (!list_empty(list)) {
@@ -369,132 +390,193 @@ err:
 	return ret;
 }
 
+void bch_journal_space_reserve(struct journal *j)
+{
+	j->do_reserve = true;
+}
+
 /* Journalling */
-#define journal_max_cmp(l, r) \
-	(fifo_idx(&c->journal.pin, btree_current_write(l)->journal) < \
-	 fifo_idx(&(c)->journal.pin, btree_current_write(r)->journal))
-#define journal_min_cmp(l, r) \
-	(fifo_idx(&c->journal.pin, btree_current_write(l)->journal) > \
-	 fifo_idx(&(c)->journal.pin, btree_current_write(r)->journal))
 
 static void btree_flush_write(struct cache_set *c)
 {
-	/*
-	 * Try to find the btree node with that references the oldest journal
-	 * entry, best is our current candidate and is locked if non NULL:
-	 */
-	struct btree *b;
-	int i;
+	struct btree *b, *t, *btree_nodes[BTREE_FLUSH_NR];
+	unsigned int i, nr;
+	int ref_nr;
+	atomic_t *fifo_front_p, *now_fifo_front_p;
+	size_t mask;
 
-	atomic_long_inc(&c->flush_write);
-
-retry:
-	spin_lock(&c->journal.lock);
-	if (heap_empty(&c->flush_btree)) {
-		for_each_cached_btree(b, c, i)
-			if (btree_current_write(b)->journal) {
-				if (!heap_full(&c->flush_btree))
-					heap_add(&c->flush_btree, b,
-						 journal_max_cmp);
-				else if (journal_max_cmp(b,
-					 heap_peek(&c->flush_btree))) {
-					c->flush_btree.data[0] = b;
-					heap_sift(&c->flush_btree, 0,
-						  journal_max_cmp);
-				}
-			}
+	if (c->journal.btree_flushing)
+		return;
 
-		for (i = c->flush_btree.used / 2 - 1; i >= 0; --i)
-			heap_sift(&c->flush_btree, i, journal_min_cmp);
+	spin_lock(&c->journal.flush_write_lock);
+	if (c->journal.btree_flushing) {
+		spin_unlock(&c->journal.flush_write_lock);
+		return;
 	}
+	c->journal.btree_flushing = true;
+	spin_unlock(&c->journal.flush_write_lock);
 
-	b = NULL;
-	heap_pop(&c->flush_btree, b, journal_min_cmp);
+	/* get the oldest journal entry and check its refcount */
+	spin_lock(&c->journal.lock);
+	fifo_front_p = &fifo_front(&c->journal.pin);
+	ref_nr = atomic_read(fifo_front_p);
+	if (ref_nr <= 0) {
+		/*
+		 * do nothing if no btree node references
+		 * the oldest journal entry
+		 */
+		spin_unlock(&c->journal.lock);
+		goto out;
+	}
 	spin_unlock(&c->journal.lock);
 
-	if (b) {
+	mask = c->journal.pin.mask;
+	nr = 0;
+	atomic_long_inc(&c->flush_write);
+	memset(btree_nodes, 0, sizeof(btree_nodes));
+
+	mutex_lock(&c->bucket_lock);
+	list_for_each_entry_safe_reverse(b, t, &c->btree_cache, list) {
+		/*
+		 * It is safe to get now_fifo_front_p without holding
+		 * c->journal.lock here, because we don't need to know
+		 * the exactly accurate value, just check whether the
+		 * front pointer of c->journal.pin is changed.
+		 */
+		now_fifo_front_p = &fifo_front(&c->journal.pin);
+		/*
+		 * If the oldest journal entry is reclaimed and front
+		 * pointer of c->journal.pin changes, it is unnecessary
+		 * to scan c->btree_cache anymore, just quit the loop and
+		 * flush out what we have already.
+		 */
+		if (now_fifo_front_p != fifo_front_p)
+			break;
+		/*
+		 * quit this loop if all matching btree nodes are
+		 * scanned and record in btree_nodes[] already.
+		 */
+		ref_nr = atomic_read(fifo_front_p);
+		if (nr >= ref_nr)
+			break;
+
+		if (btree_node_journal_flush(b))
+			pr_err("BUG: flush_write bit should not be set here!\n");
+
 		mutex_lock(&b->write_lock);
+
+		if (!btree_node_dirty(b)) {
+			mutex_unlock(&b->write_lock);
+			continue;
+		}
+
 		if (!btree_current_write(b)->journal) {
 			mutex_unlock(&b->write_lock);
-			/* We raced */
-			atomic_long_inc(&c->retry_flush_write);
-			goto retry;
+			continue;
 		}
 
-		__bch_btree_node_write(b, NULL);
-		mutex_unlock(&b->write_lock);
-	}
-}
+		/*
+		 * Only select the btree node which exactly references
+		 * the oldest journal entry.
+		 *
+		 * If the journal entry pointed by fifo_front_p is
+		 * reclaimed in parallel, don't worry:
+		 * - the list_for_each_xxx loop will quit when checking
+		 *   next now_fifo_front_p.
+		 * - If there are matched nodes recorded in btree_nodes[],
+		 *   they are clean now (this is why and how the oldest
+		 *   journal entry can be reclaimed). These selected nodes
+		 *   will be ignored and skipped in the following for-loop.
+		 */
+		if (((btree_current_write(b)->journal - fifo_front_p) &
+		     mask) != 0) {
+			mutex_unlock(&b->write_lock);
+			continue;
+		}
 
-#define last_seq(j)	((j)->seq - fifo_used(&(j)->pin) + 1)
+		set_btree_node_journal_flush(b);
 
-static void journal_discard_endio(struct bio *bio)
-{
-	struct journal_device *ja =
-		container_of(bio, struct journal_device, discard_bio);
-	struct cache *ca = container_of(ja, struct cache, journal);
+		mutex_unlock(&b->write_lock);
 
-	atomic_set(&ja->discard_in_flight, DISCARD_DONE);
+		btree_nodes[nr++] = b;
+		/*
+		 * To avoid holding c->bucket_lock too long time,
+		 * only scan for BTREE_FLUSH_NR matched btree nodes
+		 * at most. If there are more btree nodes reference
+		 * the oldest journal entry, try to flush them next
+		 * time when btree_flush_write() is called.
+		 */
+		if (nr == BTREE_FLUSH_NR)
+			break;
+	}
+	mutex_unlock(&c->bucket_lock);
 
-	closure_wake_up(&ca->set->journal.wait);
-	closure_put(&ca->set->cl);
-}
+	for (i = 0; i < nr; i++) {
+		b = btree_nodes[i];
+		if (!b) {
+			pr_err("BUG: btree_nodes[%d] is NULL\n", i);
+			continue;
+		}
 
-static void journal_discard_work(struct work_struct *work)
-{
-	struct journal_device *ja =
-		container_of(work, struct journal_device, discard_work);
+		/* safe to check without holding b->write_lock */
+		if (!btree_node_journal_flush(b)) {
+			pr_err("BUG: bnode %p: journal_flush bit cleaned\n", b);
+			continue;
+		}
 
-	submit_bio(&ja->discard_bio);
-}
+		mutex_lock(&b->write_lock);
+		if (!btree_current_write(b)->journal) {
+			clear_bit(BTREE_NODE_journal_flush, &b->flags);
+			mutex_unlock(&b->write_lock);
+			pr_debug("bnode %p: written by others\n", b);
+			continue;
+		}
 
-static void do_journal_discard(struct cache *ca)
-{
-	struct journal_device *ja = &ca->journal;
-	struct bio *bio = &ja->discard_bio;
+		if (!btree_node_dirty(b)) {
+			clear_bit(BTREE_NODE_journal_flush, &b->flags);
+			mutex_unlock(&b->write_lock);
+			pr_debug("bnode %p: dirty bit cleaned by others\n", b);
+			continue;
+		}
 
-	if (!ca->discard) {
-		ja->discard_idx = ja->last_idx;
-		return;
+		__bch_btree_node_write(b, NULL);
+		clear_bit(BTREE_NODE_journal_flush, &b->flags);
+		mutex_unlock(&b->write_lock);
 	}
 
-	switch (atomic_read(&ja->discard_in_flight)) {
-	case DISCARD_IN_FLIGHT:
-		return;
-
-	case DISCARD_DONE:
-		ja->discard_idx = (ja->discard_idx + 1) %
-			ca->sb.njournal_buckets;
+out:
+	spin_lock(&c->journal.flush_write_lock);
+	c->journal.btree_flushing = false;
+	spin_unlock(&c->journal.flush_write_lock);
+}
 
-		atomic_set(&ja->discard_in_flight, DISCARD_READY);
-		/* fallthrough */
+#define last_seq(j)	((j)->seq - fifo_used(&(j)->pin) + 1)
 
-	case DISCARD_READY:
-		if (ja->discard_idx == ja->last_idx)
-			return;
+static unsigned int free_journal_buckets(struct cache_set *c)
+{
+	struct journal *j = &c->journal;
+	struct cache *ca = c->cache;
+	struct journal_device *ja = &c->cache->journal;
+	unsigned int n;
 
-		atomic_set(&ja->discard_in_flight, DISCARD_IN_FLIGHT);
+	/* In case njournal_buckets is not power of 2 */
+	if (ja->cur_idx >= ja->last_idx)
+		n = ca->sb.njournal_buckets + ja->last_idx - ja->cur_idx;
+	else
+		n = ja->last_idx - ja->cur_idx;
 
-		bio_init(bio, bio->bi_inline_vecs, 1);
-		bio_set_op_attrs(bio, REQ_OP_DISCARD, 0);
-		bio->bi_iter.bi_sector	= bucket_to_sector(ca->set,
-						ca->sb.d[ja->discard_idx]);
-		bio_set_dev(bio, ca->bdev);
-		bio->bi_iter.bi_size	= bucket_bytes(ca);
-		bio->bi_end_io		= journal_discard_endio;
+	if (n > (1 + j->do_reserve))
+		return n - (1 + j->do_reserve);
 
-		closure_get(&ca->set->cl);
-		INIT_WORK(&ja->discard_work, journal_discard_work);
-		queue_work(bch_journal_wq, &ja->discard_work);
-	}
+	return 0;
 }
 
 static void journal_reclaim(struct cache_set *c)
 {
 	struct bkey *k = &c->journal.key;
-	struct cache *ca;
+	struct cache *ca = c->cache;
 	uint64_t last_seq;
-	unsigned int iter, n = 0;
+	struct journal_device *ja = &ca->journal;
 	atomic_t p __maybe_unused;
 
 	atomic_long_inc(&c->reclaim);
@@ -506,45 +588,27 @@ static void journal_reclaim(struct cache_set *c)
 
 	/* Update last_idx */
 
-	for_each_cache(ca, c, iter) {
-		struct journal_device *ja = &ca->journal;
-
-		while (ja->last_idx != ja->cur_idx &&
-		       ja->seq[ja->last_idx] < last_seq)
-			ja->last_idx = (ja->last_idx + 1) %
-				ca->sb.njournal_buckets;
-	}
-
-	for_each_cache(ca, c, iter)
-		do_journal_discard(ca);
+	while (ja->last_idx != ja->cur_idx &&
+	       ja->seq[ja->last_idx] < last_seq)
+		ja->last_idx = (ja->last_idx + 1) %
+			ca->sb.njournal_buckets;
 
 	if (c->journal.blocks_free)
 		goto out;
 
-	/*
-	 * Allocate:
-	 * XXX: Sort by free journal space
-	 */
-
-	for_each_cache(ca, c, iter) {
-		struct journal_device *ja = &ca->journal;
-		unsigned int next = (ja->cur_idx + 1) % ca->sb.njournal_buckets;
-
-		/* No space available on this device */
-		if (next == ja->discard_idx)
-			continue;
+	if (!free_journal_buckets(c))
+		goto out;
 
-		ja->cur_idx = next;
-		k->ptr[n++] = MAKE_PTR(0,
-				  bucket_to_sector(c, ca->sb.d[ja->cur_idx]),
-				  ca->sb.nr_this_dev);
-	}
+	ja->cur_idx = (ja->cur_idx + 1) % ca->sb.njournal_buckets;
+	k->ptr[0] = MAKE_PTR(0,
+			     bucket_to_sector(c, ca->sb.d[ja->cur_idx]),
+			     ca->sb.nr_this_dev);
+	atomic_long_inc(&c->reclaimed_journal_buckets);
 
 	bkey_init(k);
-	SET_KEY_PTRS(k, n);
+	SET_KEY_PTRS(k, 1);
+	c->journal.blocks_free = ca->sb.bucket_size >> c->block_bits;
 
-	if (n)
-		c->journal.blocks_free = c->sb.bucket_size >> c->block_bits;
 out:
 	if (!journal_full(&c->journal))
 		__closure_wake_up(&c->journal.wait);
@@ -571,7 +635,7 @@ void bch_journal_next(struct journal *j)
 	j->cur->data->keys	= 0;
 
 	if (fifo_full(&j->pin))
-		pr_debug("journal_pin full (%zu)", fifo_used(&j->pin));
+		pr_debug("journal_pin full (%zu)\n", fifo_used(&j->pin));
 }
 
 static void journal_write_endio(struct bio *bio)
@@ -582,11 +646,11 @@ static void journal_write_endio(struct bio *bio)
 	closure_put(&w->c->journal.io);
 }
 
-static void journal_write(struct closure *cl);
+static CLOSURE_CALLBACK(journal_write);
 
-static void journal_write_done(struct closure *cl)
+static CLOSURE_CALLBACK(journal_write_done)
 {
-	struct journal *j = container_of(cl, struct journal, io);
+	closure_type(j, struct journal, io);
 	struct journal_write *w = (j->cur == j->w)
 		? &j->w[1]
 		: &j->w[0];
@@ -595,24 +659,24 @@ static void journal_write_done(struct closure *cl)
 	continue_at_nobarrier(cl, journal_write, bch_journal_wq);
 }
 
-static void journal_write_unlock(struct closure *cl)
+static CLOSURE_CALLBACK(journal_write_unlock)
 	__releases(&c->journal.lock)
 {
-	struct cache_set *c = container_of(cl, struct cache_set, journal.io);
+	closure_type(c, struct cache_set, journal.io);
 
 	c->journal.io_in_flight = 0;
 	spin_unlock(&c->journal.lock);
 }
 
-static void journal_write_unlocked(struct closure *cl)
+static CLOSURE_CALLBACK(journal_write_unlocked)
 	__releases(c->journal.lock)
 {
-	struct cache_set *c = container_of(cl, struct cache_set, journal.io);
-	struct cache *ca;
+	closure_type(c, struct cache_set, journal.io);
+	struct cache *ca = c->cache;
 	struct journal_write *w = c->journal.cur;
 	struct bkey *k = &c->journal.key;
-	unsigned int i, sectors = set_blocks(w->data, block_bytes(c)) *
-		c->sb.block_size;
+	unsigned int i, sectors = set_blocks(w->data, block_bytes(ca)) *
+		ca->sb.block_size;
 
 	struct bio *bio;
 	struct bio_list list;
@@ -631,36 +695,32 @@ static void journal_write_unlocked(struct closure *cl)
 		return;
 	}
 
-	c->journal.blocks_free -= set_blocks(w->data, block_bytes(c));
+	c->journal.blocks_free -= set_blocks(w->data, block_bytes(ca));
 
 	w->data->btree_level = c->root->level;
 
 	bkey_copy(&w->data->btree_root, &c->root->key);
 	bkey_copy(&w->data->uuid_bucket, &c->uuid_bucket);
 
-	for_each_cache(ca, c, i)
-		w->data->prio_bucket[ca->sb.nr_this_dev] = ca->prio_buckets[0];
-
-	w->data->magic		= jset_magic(&c->sb);
+	w->data->prio_bucket[ca->sb.nr_this_dev] = ca->prio_buckets[0];
+	w->data->magic		= jset_magic(&ca->sb);
 	w->data->version	= BCACHE_JSET_VERSION;
 	w->data->last_seq	= last_seq(&c->journal);
 	w->data->csum		= csum_set(w->data);
 
 	for (i = 0; i < KEY_PTRS(k); i++) {
-		ca = PTR_CACHE(c, k, i);
+		ca = c->cache;
 		bio = &ca->journal.bio;
 
 		atomic_long_add(sectors, &ca->meta_sectors_written);
 
-		bio_reset(bio);
+		bio_reset(bio, ca->bdev, REQ_OP_WRITE | 
+			  REQ_SYNC | REQ_META | REQ_PREFLUSH | REQ_FUA);
 		bio->bi_iter.bi_sector	= PTR_OFFSET(k, i);
-		bio_set_dev(bio, ca->bdev);
 		bio->bi_iter.bi_size = sectors << 9;
 
 		bio->bi_end_io	= journal_write_endio;
 		bio->bi_private = w;
-		bio_set_op_attrs(bio, REQ_OP_WRITE,
-				 REQ_SYNC|REQ_META|REQ_PREFLUSH|REQ_FUA);
 		bch_bio_map(bio, w->data);
 
 		trace_bcache_journal_write(bio, w->data->keys);
@@ -671,6 +731,9 @@ static void journal_write_unlocked(struct closure *cl)
 		ca->journal.seq[ca->journal.cur_idx] = w->data->seq;
 	}
 
+	/* If KEY_PTRS(k) == 0, this jset gets lost in air */
+	BUG_ON(i == 0);
+
 	atomic_dec_bug(&fifo_back(&c->journal.pin));
 	bch_journal_next(&c->journal);
 	journal_reclaim(c);
@@ -683,12 +746,12 @@ static void journal_write_unlocked(struct closure *cl)
 	continue_at(cl, journal_write_done, NULL);
 }
 
-static void journal_write(struct closure *cl)
+static CLOSURE_CALLBACK(journal_write)
 {
-	struct cache_set *c = container_of(cl, struct cache_set, journal.io);
+	closure_type(c, struct cache_set, journal.io);
 
 	spin_lock(&c->journal.lock);
-	journal_write_unlocked(cl);
+	journal_write_unlocked(&cl->work);
 }
 
 static void journal_try_write(struct cache_set *c)
@@ -714,6 +777,7 @@ static struct journal_write *journal_wait_for_write(struct cache_set *c,
 	size_t sectors;
 	struct closure cl;
 	bool wait = false;
+	struct cache *ca = c->cache;
 
 	closure_init_stack(&cl);
 
@@ -723,10 +787,10 @@ static struct journal_write *journal_wait_for_write(struct cache_set *c,
 		struct journal_write *w = c->journal.cur;
 
 		sectors = __set_blocks(w->data, w->data->keys + nkeys,
-				       block_bytes(c)) * c->sb.block_size;
+				       block_bytes(ca)) * ca->sb.block_size;
 
 		if (sectors <= min_t(size_t,
-				     c->journal.blocks_free * c->sb.block_size,
+				     c->journal.blocks_free * ca->sb.block_size,
 				     PAGE_SECTORS << JSET_BITS))
 			return w;
 
@@ -787,7 +851,11 @@ atomic_t *bch_journal(struct cache_set *c,
 	struct journal_write *w;
 	atomic_t *ret;
 
-	if (!CACHE_SYNC(&c->sb))
+	/* No journaling if CACHE_SET_IO_DISABLE set already */
+	if (unlikely(test_bit(CACHE_SET_IO_DISABLE, &c->flags)))
+		return NULL;
+
+	if (!CACHE_SYNC(&c->cache->sb))
 		return NULL;
 
 	w = journal_wait_for_write(c, bch_keylist_nkeys(keys));
@@ -803,8 +871,8 @@ atomic_t *bch_journal(struct cache_set *c,
 		journal_try_write(c);
 	} else if (!w->dirty) {
 		w->dirty = true;
-		schedule_delayed_work(&c->journal.work,
-				      msecs_to_jiffies(c->journal_delay_ms));
+		queue_delayed_work(bch_flush_wq, &c->journal.work,
+				   msecs_to_jiffies(c->journal_delay_ms));
 		spin_unlock(&c->journal.lock);
 	} else {
 		spin_unlock(&c->journal.lock);
@@ -831,7 +899,6 @@ void bch_journal_free(struct cache_set *c)
 	free_pages((unsigned long) c->journal.w[1].data, JSET_BITS);
 	free_pages((unsigned long) c->journal.w[0].data, JSET_BITS);
 	free_fifo(&c->journal.pin);
-	free_heap(&c->flush_btree);
 }
 
 int bch_journal_alloc(struct cache_set *c)
@@ -839,6 +906,7 @@ int bch_journal_alloc(struct cache_set *c)
 	struct journal *j = &c->journal;
 
 	spin_lock_init(&j->lock);
+	spin_lock_init(&j->flush_write_lock);
 	INIT_DELAYED_WORK(&j->work, journal_write_work);
 
 	c->journal_delay_ms = 100;
@@ -846,10 +914,9 @@ int bch_journal_alloc(struct cache_set *c)
 	j->w[0].c = c;
 	j->w[1].c = c;
 
-	if (!(init_heap(&c->flush_btree, 128, GFP_KERNEL)) ||
-	    !(init_fifo(&j->pin, JOURNAL_PIN, GFP_KERNEL)) ||
-	    !(j->w[0].data = (void *) __get_free_pages(GFP_KERNEL, JSET_BITS)) ||
-	    !(j->w[1].data = (void *) __get_free_pages(GFP_KERNEL, JSET_BITS)))
+	if (!(init_fifo(&j->pin, JOURNAL_PIN, GFP_KERNEL)) ||
+	    !(j->w[0].data = (void *) __get_free_pages(GFP_KERNEL|__GFP_COMP, JSET_BITS)) ||
+	    !(j->w[1].data = (void *) __get_free_pages(GFP_KERNEL|__GFP_COMP, JSET_BITS)))
 		return -ENOMEM;
 
 	return 0;