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

Pull block fixes from Jens Axboe:
 "A selection of fixes/changes that should make it into this series.
  This contains:

   - NVMe, two merges, containing:
        - pci-e, rdma, and fc fixes
        - Device quirks

   - Fix for a badblocks leak in null_blk

   - bcache fix from Rui Hua for a race condition regression where
     -EINTR was returned to upper layers that didn't expect it.

   - Regression fix for blktrace for a bug introduced in this series.

   - blktrace cleanup for cgroup id.

   - bdi registration error handling.

   - Small series with cleanups for blk-wbt.

   - Various little fixes for typos and the like.

  Nothing earth shattering, most important are the NVMe and bcache fixes"

* 'for-linus' of git://git.kernel.dk/linux-block: (34 commits)
  nvme-pci: fix NULL pointer dereference in nvme_free_host_mem()
  nvme-rdma: fix memory leak during queue allocation
  blktrace: fix trace mutex deadlock
  nvme-rdma: Use mr pool
  nvme-rdma: Check remotely invalidated rkey matches our expected rkey
  nvme-rdma: wait for local invalidation before completing a request
  nvme-rdma: don't complete requests before a send work request has completed
  nvme-rdma: don't suppress send completions
  bcache: check return value of register_shrinker
  bcache: recover data from backing when data is clean
  bcache: Fix building error on MIPS
  bcache: add a comment in journal bucket reading
  nvme-fc: don't use bit masks for set/test_bit() numbers
  blk-wbt: fix comments typo
  blk-wbt: move wbt_clear_stat to common place in wbt_done
  blk-sysfs: remove NULL pointer checking in queue_wb_lat_store
  blk-wbt: remove duplicated setting in wbt_init
  nvme-pci: add quirk for delay before CHK RDY for WDC SN200
  block: remove useless assignment in bio_split
  null_blk: fix dev->badblocks leak
  ...

5 files changed, 18 insertions, 11 deletions

diff --git a/drivers/md/bcache/alloc.c b/drivers/md/bcache/alloc.c
index a27d85232ce1..a0cc1bc6d884 100644
--- a/drivers/md/bcache/alloc.c
+++ b/drivers/md/bcache/alloc.c
@@ -490,7 +490,7 @@ int __bch_bucket_alloc_set(struct cache_set *c, unsigned reserve,
 		if (b == -1)
 			goto err;
 
-		k->ptr[i] = PTR(ca->buckets[b].gen,
+		k->ptr[i] = MAKE_PTR(ca->buckets[b].gen,
 				bucket_to_sector(c, b),
 				ca->sb.nr_this_dev);
 
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index 11c5503d31dc..81e8dc3dbe5e 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -807,7 +807,10 @@ int bch_btree_cache_alloc(struct cache_set *c)
 	c->shrink.scan_objects = bch_mca_scan;
 	c->shrink.seeks = 4;
 	c->shrink.batch = c->btree_pages * 2;
-	register_shrinker(&c->shrink);
+
+	if (register_shrinker(&c->shrink))
+		pr_warn("bcache: %s: could not register shrinker",
+				__func__);
 
 	return 0;
 }
diff --git a/drivers/md/bcache/extents.c b/drivers/md/bcache/extents.c
index 41c238fc3733..f9d391711595 100644
--- a/drivers/md/bcache/extents.c
+++ b/drivers/md/bcache/extents.c
@@ -585,7 +585,7 @@ static bool bch_extent_merge(struct btree_keys *bk, struct bkey *l, struct bkey
 		return false;
 
 	for (i = 0; i < KEY_PTRS(l); i++)
-		if (l->ptr[i] + PTR(0, KEY_SIZE(l), 0) != r->ptr[i] ||
+		if (l->ptr[i] + MAKE_PTR(0, KEY_SIZE(l), 0) != r->ptr[i] ||
 		    PTR_BUCKET_NR(b->c, l, i) != PTR_BUCKET_NR(b->c, r, i))
 			return false;
 
diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c
index 02a98ddb592d..a87165c1d8e5 100644
--- a/drivers/md/bcache/journal.c
+++ b/drivers/md/bcache/journal.c
@@ -170,6 +170,11 @@ int bch_journal_read(struct cache_set *c, struct list_head *list)
 		 * find a sequence of buckets with valid journal entries
 		 */
 		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;
 
 			if (test_bit(l, bitmap))
@@ -507,7 +512,7 @@ static void journal_reclaim(struct cache_set *c)
 			continue;
 
 		ja->cur_idx = next;
-		k->ptr[n++] = PTR(0,
+		k->ptr[n++] = MAKE_PTR(0,
 				  bucket_to_sector(c, ca->sb.d[ja->cur_idx]),
 				  ca->sb.nr_this_dev);
 	}
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index 3a7aed7282b2..643c3021624f 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -708,16 +708,15 @@ static void cached_dev_read_error(struct closure *cl)
 {
 	struct search *s = container_of(cl, struct search, cl);
 	struct bio *bio = &s->bio.bio;
-	struct cached_dev *dc = container_of(s->d, struct cached_dev, disk);
 
 	/*
-	 * If cache device is dirty (dc->has_dirty is non-zero), then
-	 * recovery a failed read request from cached device may get a
-	 * stale data back. So read failure recovery is only permitted
-	 * when cache device is clean.
+	 * If read request hit dirty data (s->read_dirty_data is true),
+	 * then recovery a failed read request from cached device may
+	 * get a stale data back. So read failure recovery is only
+	 * permitted when read request hit clean data in cache device,
+	 * or when cache read race happened.
 	 */
-	if (s->recoverable &&
-	    (dc && !atomic_read(&dc->has_dirty))) {
+	if (s->recoverable && !s->read_dirty_data) {
 		/* Retry from the backing device: */
 		trace_bcache_read_retry(s->orig_bio);