Merge tag 'for-5.2/block-20190507' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:
 "Nothing major in this series, just fixes and improvements all over the
  map. This contains:

   - Series of fixes for sed-opal (David, Jonas)

   - Fixes and performance tweaks for BFQ (via Paolo)

   - Set of fixes for bcache (via Coly)

   - Set of fixes for md (via Song)

   - Enabling multi-page for passthrough requests (Ming)

   - Queue release fix series (Ming)

   - Device notification improvements (Martin)

   - Propagate underlying device rotational status in loop (Holger)

   - Removal of mtip32xx trim support, which has been disabled for years
     (Christoph)

   - Improvement and cleanup of nvme command handling (Christoph)

   - Add block SPDX tags (Christoph)

   - Cleanup/hardening of bio/bvec iteration (Christoph)

   - A few NVMe pull requests (Christoph)

   - Removal of CONFIG_LBDAF (Christoph)

   - Various little fixes here and there"

* tag 'for-5.2/block-20190507' of git://git.kernel.dk/linux-block: (164 commits)
  block: fix mismerge in bvec_advance
  block: don't drain in-progress dispatch in blk_cleanup_queue()
  blk-mq: move cancel of hctx->run_work into blk_mq_hw_sysfs_release
  blk-mq: always free hctx after request queue is freed
  blk-mq: split blk_mq_alloc_and_init_hctx into two parts
  blk-mq: free hw queue's resource in hctx's release handler
  blk-mq: move cancel of requeue_work into blk_mq_release
  blk-mq: grab .q_usage_counter when queuing request from plug code path
  block: fix function name in comment
  nvmet: protect discovery change log event list iteration
  nvme: mark nvme_core_init and nvme_core_exit static
  nvme: move command size checks to the core
  nvme-fabrics: check more command sizes
  nvme-pci: check more command sizes
  nvme-pci: remove an unneeded variable initialization
  nvme-pci: unquiesce admin queue on shutdown
  nvme-pci: shutdown on timeout during deletion
  nvme-pci: fix psdt field for single segment sgls
  nvme-multipath: don't print ANA group state by default
  nvme-multipath: split bios with the ns_head bio_set before submitting
  ...

1 files changed, 29 insertions, 12 deletions

diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index f101bfe8657a..41adcd1546f1 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -329,12 +329,13 @@ void bch_data_insert(struct closure *cl)
 	bch_data_insert_start(cl);
 }
 
-/* Congested? */
-
-unsigned int bch_get_congested(struct cache_set *c)
+/*
+ * Congested?  Return 0 (not congested) or the limit (in sectors)
+ * beyond which we should bypass the cache due to congestion.
+ */
+unsigned int bch_get_congested(const struct cache_set *c)
 {
 	int i;
-	long rand;
 
 	if (!c->congested_read_threshold_us &&
 	    !c->congested_write_threshold_us)
@@ -353,8 +354,7 @@ unsigned int bch_get_congested(struct cache_set *c)
 	if (i > 0)
 		i = fract_exp_two(i, 6);
 
-	rand = get_random_int();
-	i -= bitmap_weight(&rand, BITS_PER_LONG);
+	i -= hweight32(get_random_u32());
 
 	return i > 0 ? i : 1;
 }
@@ -376,7 +376,7 @@ static bool check_should_bypass(struct cached_dev *dc, struct bio *bio)
 {
 	struct cache_set *c = dc->disk.c;
 	unsigned int mode = cache_mode(dc);
-	unsigned int sectors, congested = bch_get_congested(c);
+	unsigned int sectors, congested;
 	struct task_struct *task = current;
 	struct io *i;
 
@@ -412,6 +412,7 @@ static bool check_should_bypass(struct cached_dev *dc, struct bio *bio)
 			goto rescale;
 	}
 
+	congested = bch_get_congested(c);
 	if (!congested && !dc->sequential_cutoff)
 		goto rescale;
 
@@ -706,14 +707,14 @@ static void search_free(struct closure *cl)
 {
 	struct search *s = container_of(cl, struct search, cl);
 
-	atomic_dec(&s->d->c->search_inflight);
+	atomic_dec(&s->iop.c->search_inflight);
 
 	if (s->iop.bio)
 		bio_put(s->iop.bio);
 
 	bio_complete(s);
 	closure_debug_destroy(cl);
-	mempool_free(s, &s->d->c->search);
+	mempool_free(s, &s->iop.c->search);
 }
 
 static inline struct search *search_alloc(struct bio *bio,
@@ -756,13 +757,13 @@ static void cached_dev_bio_complete(struct closure *cl)
 	struct search *s = container_of(cl, struct search, cl);
 	struct cached_dev *dc = container_of(s->d, struct cached_dev, disk);
 
-	search_free(cl);
 	cached_dev_put(dc);
+	search_free(cl);
 }
 
 /* Process reads */
 
-static void cached_dev_cache_miss_done(struct closure *cl)
+static void cached_dev_read_error_done(struct closure *cl)
 {
 	struct search *s = container_of(cl, struct search, cl);
 
@@ -800,7 +801,22 @@ static void cached_dev_read_error(struct closure *cl)
 		closure_bio_submit(s->iop.c, bio, cl);
 	}
 
-	continue_at(cl, cached_dev_cache_miss_done, NULL);
+	continue_at(cl, cached_dev_read_error_done, NULL);
+}
+
+static void cached_dev_cache_miss_done(struct closure *cl)
+{
+	struct search *s = container_of(cl, struct search, cl);
+	struct bcache_device *d = s->d;
+
+	if (s->iop.replace_collision)
+		bch_mark_cache_miss_collision(s->iop.c, s->d);
+
+	if (s->iop.bio)
+		bio_free_pages(s->iop.bio);
+
+	cached_dev_bio_complete(cl);
+	closure_put(&d->cl);
 }
 
 static void cached_dev_read_done(struct closure *cl)
@@ -833,6 +849,7 @@ static void cached_dev_read_done(struct closure *cl)
 	if (verify(dc) && s->recoverable && !s->read_dirty_data)
 		bch_data_verify(dc, s->orig_bio);
 
+	closure_get(&dc->disk.cl);
 	bio_complete(s);
 
 	if (s->iop.bio &&