Merge tag 'for-linus-20180210' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:
 "A few fixes to round off the merge window on the block side:

   - a set of bcache fixes by way of Michael Lyle, from the usual bcache
     suspects.

   - add a simple-to-hook-into function for bpf EIO error injection.

   - fix blk-wbt that mischarectized flushes as reads. Improve the logic
     so that flushes and writes are accounted as writes, and only reads
     as reads. From me.

   - fix requeue crash in BFQ, from Paolo"

* tag 'for-linus-20180210' of git://git.kernel.dk/linux-block:
  block, bfq: add requeue-request hook
  bcache: fix for data collapse after re-attaching an attached device
  bcache: return attach error when no cache set exist
  bcache: set writeback_rate_update_seconds in range [1, 60] seconds
  bcache: fix for allocator and register thread race
  bcache: set error_limit correctly
  bcache: properly set task state in bch_writeback_thread()
  bcache: fix high CPU occupancy during journal
  bcache: add journal statistic
  block: Add should_fail_bio() for bpf error injection
  blk-wbt: account flush requests correctly

1 files changed, 19 insertions, 6 deletions

diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 133b81225ea9..312895788036 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -957,7 +957,8 @@ void bch_cached_dev_detach(struct cached_dev *dc)
 	cached_dev_put(dc);
 }
 
-int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c)
+int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c,
+			  uint8_t *set_uuid)
 {
 	uint32_t rtime = cpu_to_le32(get_seconds());
 	struct uuid_entry *u;
@@ -965,7 +966,8 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c)
 
 	bdevname(dc->bdev, buf);
 
-	if (memcmp(dc->sb.set_uuid, c->sb.set_uuid, 16))
+	if ((set_uuid && memcmp(set_uuid, c->sb.set_uuid, 16)) ||
+	    (!set_uuid && memcmp(dc->sb.set_uuid, c->sb.set_uuid, 16)))
 		return -ENOENT;
 
 	if (dc->disk.c) {
@@ -1194,7 +1196,7 @@ static void register_bdev(struct cache_sb *sb, struct page *sb_page,
 
 	list_add(&dc->list, &uncached_devices);
 	list_for_each_entry(c, &bch_cache_sets, list)
-		bch_cached_dev_attach(dc, c);
+		bch_cached_dev_attach(dc, c, NULL);
 
 	if (BDEV_STATE(&dc->sb) == BDEV_STATE_NONE ||
 	    BDEV_STATE(&dc->sb) == BDEV_STATE_STALE)
@@ -1553,7 +1555,7 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb)
 
 	c->congested_read_threshold_us	= 2000;
 	c->congested_write_threshold_us	= 20000;
-	c->error_limit	= 8 << IO_ERROR_SHIFT;
+	c->error_limit	= DEFAULT_IO_ERROR_LIMIT;
 
 	return c;
 err:
@@ -1716,7 +1718,7 @@ static void run_cache_set(struct cache_set *c)
 	bcache_write_super(c);
 
 	list_for_each_entry_safe(dc, t, &uncached_devices, list)
-		bch_cached_dev_attach(dc, c);
+		bch_cached_dev_attach(dc, c, NULL);
 
 	flash_devs_run(c);
 
@@ -1833,6 +1835,7 @@ void bch_cache_release(struct kobject *kobj)
 static int cache_alloc(struct cache *ca)
 {
 	size_t free;
+	size_t btree_buckets;
 	struct bucket *b;
 
 	__module_get(THIS_MODULE);
@@ -1840,9 +1843,19 @@ static int cache_alloc(struct cache *ca)
 
 	bio_init(&ca->journal.bio, ca->journal.bio.bi_inline_vecs, 8);
 
+	/*
+	 * when ca->sb.njournal_buckets is not zero, journal exists,
+	 * and in bch_journal_replay(), tree node may split,
+	 * so bucket of RESERVE_BTREE type is needed,
+	 * the worst situation is all journal buckets are valid journal,
+	 * and all the keys need to replay,
+	 * so the number of  RESERVE_BTREE type buckets should be as much
+	 * as journal buckets
+	 */
+	btree_buckets = ca->sb.njournal_buckets ?: 8;
 	free = roundup_pow_of_two(ca->sb.nbuckets) >> 10;
 
-	if (!init_fifo(&ca->free[RESERVE_BTREE], 8, GFP_KERNEL) ||
+	if (!init_fifo(&ca->free[RESERVE_BTREE], btree_buckets, GFP_KERNEL) ||
 	    !init_fifo_exact(&ca->free[RESERVE_PRIO], prio_buckets(ca), GFP_KERNEL) ||
 	    !init_fifo(&ca->free[RESERVE_MOVINGGC], free, GFP_KERNEL) ||
 	    !init_fifo(&ca->free[RESERVE_NONE], free, GFP_KERNEL) ||