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, 33 insertions, 9 deletions

diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c
index b2fd412715b1..12dae9348147 100644
--- a/drivers/md/bcache/journal.c
+++ b/drivers/md/bcache/journal.c
@@ -147,7 +147,7 @@ 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;					\
@@ -156,6 +156,7 @@ int bch_journal_read(struct cache_set *c, struct list_head *list)
 
 	struct cache *ca;
 	unsigned int iter;
+	int ret = 0;
 
 	for_each_cache(ca, c, iter) {
 		struct journal_device *ja = &ca->journal;
@@ -267,7 +268,7 @@ bsearch:
 					    struct journal_replay,
 					    list)->j.seq;
 
-	return 0;
+	return ret;
 #undef read_bucket
 }
 
@@ -317,6 +318,18 @@ void bch_journal_mark(struct cache_set *c, struct list_head *list)
 	}
 }
 
+static bool is_discard_enabled(struct cache_set *s)
+{
+	struct cache *ca;
+	unsigned int i;
+
+	for_each_cache(ca, s, i)
+		if (ca->discard)
+			return true;
+
+	return false;
+}
+
 int bch_journal_replay(struct cache_set *s, struct list_head *list)
 {
 	int ret = 0, keys = 0, entries = 0;
@@ -330,9 +343,17 @@ 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) {
+			if (n == start && is_discard_enabled(s))
+				pr_info("bcache: journal entries %llu-%llu may be discarded! (replaying %llu-%llu)",
+					n, i->j.seq - 1, start, end);
+			else {
+				pr_err("bcache: journal entries %llu-%llu missing! (replaying %llu-%llu)",
+					n, i->j.seq - 1, start, end);
+				ret = -EIO;
+				goto err;
+			}
+		}
 
 		for (k = i->j.start;
 		     k < bset_bkey_last(&i->j);
@@ -540,11 +561,11 @@ static void journal_reclaim(struct cache_set *c)
 				  ca->sb.nr_this_dev);
 	}
 
-	bkey_init(k);
-	SET_KEY_PTRS(k, n);
-
-	if (n)
+	if (n) {
+		bkey_init(k);
+		SET_KEY_PTRS(k, n);
 		c->journal.blocks_free = c->sb.bucket_size >> c->block_bits;
+	}
 out:
 	if (!journal_full(&c->journal))
 		__closure_wake_up(&c->journal.wait);
@@ -671,6 +692,9 @@ 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);