Merge tag 'for-5.1/block-20190302' of git://git.kernel.dk/linux-block

Pull block layer updates from Jens Axboe:
 "Not a huge amount of changes in this round, the biggest one is that we
  finally have Mings multi-page bvec support merged. Apart from that,
  this pull request contains:

   - Small series that avoids quiescing the queue for sysfs changes that
     match what we currently have (Aleksei)

   - Series of bcache fixes (via Coly)

   - Series of lightnvm fixes (via Mathias)

   - NVMe pull request from Christoph. Nothing major, just SPDX/license
     cleanups, RR mp policy (Hannes), and little fixes (Bart,
     Chaitanya).

   - BFQ series (Paolo)

   - Save blk-mq cpu -> hw queue mapping, removing a pointer indirection
     for the fast path (Jianchao)

   - fops->iopoll() added for async IO polling, this is a feature that
     the upcoming io_uring interface will use (Christoph, me)

   - Partition scan loop fixes (Dongli)

   - mtip32xx conversion from managed resource API (Christoph)

   - cdrom registration race fix (Guenter)

   - MD pull from Song, two minor fixes.

   - Various documentation fixes (Marcos)

   - Multi-page bvec feature. This brings a lot of nice improvements
     with it, like more efficient splitting, larger IOs can be supported
     without growing the bvec table size, and so on. (Ming)

   - Various little fixes to core and drivers"

* tag 'for-5.1/block-20190302' of git://git.kernel.dk/linux-block: (117 commits)
  block: fix updating bio's front segment size
  block: Replace function name in string with __func__
  nbd: propagate genlmsg_reply return code
  floppy: remove set but not used variable 'q'
  null_blk: fix checking for REQ_FUA
  block: fix NULL pointer dereference in register_disk
  fs: fix guard_bio_eod to check for real EOD errors
  blk-mq: use HCTX_TYPE_DEFAULT but not 0 to index blk_mq_tag_set->map
  block: optimize bvec iteration in bvec_iter_advance
  block: introduce mp_bvec_for_each_page() for iterating over page
  block: optimize blk_bio_segment_split for single-page bvec
  block: optimize __blk_segment_map_sg() for single-page bvec
  block: introduce bvec_nth_page()
  iomap: wire up the iopoll method
  block: add bio_set_polled() helper
  block: wire up block device iopoll method
  fs: add an iopoll method to struct file_operations
  loop: set GENHD_FL_NO_PART_SCAN after blkdev_reread_part()
  loop: do not print warn message if partition scan is successful
  block: bounce: make sure that bvec table is updated
  ...

14 files changed, 124 insertions, 74 deletions

diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index 23cb1dc7296b..64def336f053 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -432,8 +432,9 @@ static void do_btree_node_write(struct btree *b)
 		int j;
 		struct bio_vec *bv;
 		void *base = (void *) ((unsigned long) i & ~(PAGE_SIZE - 1));
+		struct bvec_iter_all iter_all;
 
-		bio_for_each_segment_all(bv, b->bio, j)
+		bio_for_each_segment_all(bv, b->bio, j, iter_all)
 			memcpy(page_address(bv->bv_page),
 			       base + j * PAGE_SIZE, PAGE_SIZE);
 
diff --git a/drivers/md/bcache/extents.c b/drivers/md/bcache/extents.c
index 956004366699..886710043025 100644
--- a/drivers/md/bcache/extents.c
+++ b/drivers/md/bcache/extents.c
@@ -538,6 +538,7 @@ static bool bch_extent_bad(struct btree_keys *bk, const struct bkey *k)
 {
 	struct btree *b = container_of(bk, struct btree, keys);
 	unsigned int i, stale;
+	char buf[80];
 
 	if (!KEY_PTRS(k) ||
 	    bch_extent_invalid(bk, k))
@@ -547,19 +548,19 @@ static bool bch_extent_bad(struct btree_keys *bk, const struct bkey *k)
 		if (!ptr_available(b->c, k, i))
 			return true;
 
-	if (!expensive_debug_checks(b->c) && KEY_DIRTY(k))
-		return false;
-
 	for (i = 0; i < KEY_PTRS(k); i++) {
 		stale = ptr_stale(b->c, k, i);
 
+		if (stale && KEY_DIRTY(k)) {
+			bch_extent_to_text(buf, sizeof(buf), k);
+			pr_info("stale dirty pointer, stale %u, key: %s",
+				stale, buf);
+		}
+
 		btree_bug_on(stale > BUCKET_GC_GEN_MAX, b,
 			     "key too stale: %i, need_gc %u",
 			     stale, b->c->need_gc);
 
-		btree_bug_on(stale && KEY_DIRTY(k) && KEY_SIZE(k),
-			     b, "stale dirty pointer");
-
 		if (stale)
 			return true;
 
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index 15070412a32e..f101bfe8657a 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -392,10 +392,11 @@ static bool check_should_bypass(struct cached_dev *dc, struct bio *bio)
 
 	/*
 	 * Flag for bypass if the IO is for read-ahead or background,
-	 * unless the read-ahead request is for metadata (eg, for gfs2).
+	 * unless the read-ahead request is for metadata
+	 * (eg, for gfs2 or xfs).
 	 */
 	if (bio->bi_opf & (REQ_RAHEAD|REQ_BACKGROUND) &&
-	    !(bio->bi_opf & REQ_PRIO))
+	    !(bio->bi_opf & (REQ_META|REQ_PRIO)))
 		goto skip;
 
 	if (bio->bi_iter.bi_sector & (c->sb.block_size - 1) ||
@@ -877,7 +878,7 @@ static int cached_dev_cache_miss(struct btree *b, struct search *s,
 	}
 
 	if (!(bio->bi_opf & REQ_RAHEAD) &&
-	    !(bio->bi_opf & REQ_PRIO) &&
+	    !(bio->bi_opf & (REQ_META|REQ_PRIO)) &&
 	    s->iop.c->gc_stats.in_use < CUTOFF_CACHE_READA)
 		reada = min_t(sector_t, dc->readahead >> 9,
 			      get_capacity(bio->bi_disk) - bio_end_sector(bio));
diff --git a/drivers/md/bcache/stats.c b/drivers/md/bcache/stats.c
index 894410f3f829..ba1c93791d8d 100644
--- a/drivers/md/bcache/stats.c
+++ b/drivers/md/bcache/stats.c
@@ -111,7 +111,7 @@ void bch_cache_accounting_clear(struct cache_accounting *acc)
 {
 	memset(&acc->total.cache_hits,
 	       0,
-	       sizeof(unsigned long) * 7);
+	       sizeof(struct cache_stats));
 }
 
 void bch_cache_accounting_destroy(struct cache_accounting *acc)
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 4dee119c3664..a697a3a923cd 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -1615,21 +1615,21 @@ static void conditional_stop_bcache_device(struct cache_set *c,
 		 */
 		pr_warn("stop_when_cache_set_failed of %s is \"auto\" and cache is dirty, stop it to avoid potential data corruption.",
 			d->disk->disk_name);
-			/*
-			 * There might be a small time gap that cache set is
-			 * released but bcache device is not. Inside this time
-			 * gap, regular I/O requests will directly go into
-			 * backing device as no cache set attached to. This
-			 * behavior may also introduce potential inconsistence
-			 * data in writeback mode while cache is dirty.
-			 * Therefore before calling bcache_device_stop() due
-			 * to a broken cache device, dc->io_disable should be
-			 * explicitly set to true.
-			 */
-			dc->io_disable = true;
-			/* make others know io_disable is true earlier */
-			smp_mb();
-			bcache_device_stop(d);
+		/*
+		 * There might be a small time gap that cache set is
+		 * released but bcache device is not. Inside this time
+		 * gap, regular I/O requests will directly go into
+		 * backing device as no cache set attached to. This
+		 * behavior may also introduce potential inconsistence
+		 * data in writeback mode while cache is dirty.
+		 * Therefore before calling bcache_device_stop() due
+		 * to a broken cache device, dc->io_disable should be
+		 * explicitly set to true.
+		 */
+		dc->io_disable = true;
+		/* make others know io_disable is true earlier */
+		smp_mb();
+		bcache_device_stop(d);
 	} else {
 		/*
 		 * dc->stop_when_cache_set_failed == BCH_CACHED_STOP_AUTO
diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c
index 557a8a3270a1..17bae9c14ca0 100644
--- a/drivers/md/bcache/sysfs.c
+++ b/drivers/md/bcache/sysfs.c
@@ -67,6 +67,8 @@ read_attribute(written);
 read_attribute(btree_written);
 read_attribute(metadata_written);
 read_attribute(active_journal_entries);
+read_attribute(backing_dev_name);
+read_attribute(backing_dev_uuid);
 
 sysfs_time_stats_attribute(btree_gc,	sec, ms);
 sysfs_time_stats_attribute(btree_split, sec, us);
@@ -243,6 +245,19 @@ SHOW(__bch_cached_dev)
 		return strlen(buf);
 	}
 
+	if (attr == &sysfs_backing_dev_name) {
+		snprintf(buf, BDEVNAME_SIZE + 1, "%s", dc->backing_dev_name);
+		strcat(buf, "\n");
+		return strlen(buf);
+	}
+
+	if (attr == &sysfs_backing_dev_uuid) {
+		/* convert binary uuid into 36-byte string plus '\0' */
+		snprintf(buf, 36+1, "%pU", dc->sb.uuid);
+		strcat(buf, "\n");
+		return strlen(buf);
+	}
+
 #undef var
 	return 0;
 }
@@ -262,10 +277,10 @@ STORE(__cached_dev)
 
 	sysfs_strtoul(data_csum,	dc->disk.data_csum);
 	d_strtoul(verify);
-	d_strtoul(bypass_torture_test);
-	d_strtoul(writeback_metadata);
-	d_strtoul(writeback_running);
-	d_strtoul(writeback_delay);
+	sysfs_strtoul_bool(bypass_torture_test, dc->bypass_torture_test);
+	sysfs_strtoul_bool(writeback_metadata, dc->writeback_metadata);
+	sysfs_strtoul_bool(writeback_running, dc->writeback_running);
+	sysfs_strtoul_clamp(writeback_delay, dc->writeback_delay, 0, UINT_MAX);
 
 	sysfs_strtoul_clamp(writeback_percent, dc->writeback_percent,
 			    0, bch_cutoff_writeback);
@@ -287,9 +302,15 @@ STORE(__cached_dev)
 	sysfs_strtoul_clamp(writeback_rate_update_seconds,
 			    dc->writeback_rate_update_seconds,
 			    1, WRITEBACK_RATE_UPDATE_SECS_MAX);
-	d_strtoul(writeback_rate_i_term_inverse);
-	d_strtoul_nonzero(writeback_rate_p_term_inverse);
-	d_strtoul_nonzero(writeback_rate_minimum);
+	sysfs_strtoul_clamp(writeback_rate_i_term_inverse,
+			    dc->writeback_rate_i_term_inverse,
+			    1, UINT_MAX);
+	sysfs_strtoul_clamp(writeback_rate_p_term_inverse,
+			    dc->writeback_rate_p_term_inverse,
+			    1, UINT_MAX);
+	sysfs_strtoul_clamp(writeback_rate_minimum,
+			    dc->writeback_rate_minimum,
+			    1, UINT_MAX);
 
 	sysfs_strtoul_clamp(io_error_limit, dc->error_limit, 0, INT_MAX);
 
@@ -299,7 +320,9 @@ STORE(__cached_dev)
 		dc->io_disable = v ? 1 : 0;
 	}
 
-	d_strtoi_h(sequential_cutoff);
+	sysfs_strtoul_clamp(sequential_cutoff,
+			    dc->sequential_cutoff,
+			    0, UINT_MAX);
 	d_strtoi_h(readahead);
 
 	if (attr == &sysfs_clear_stats)
@@ -452,6 +475,8 @@ static struct attribute *bch_cached_dev_files[] = {
 	&sysfs_verify,
 	&sysfs_bypass_torture_test,
 #endif
+	&sysfs_backing_dev_name,
+	&sysfs_backing_dev_uuid,
 	NULL
 };
 KTYPE(bch_cached_dev);
@@ -761,10 +786,12 @@ STORE(__bch_cache_set)
 		c->shrink.scan_objects(&c->shrink, &sc);
 	}
 
-	sysfs_strtoul(congested_read_threshold_us,
-		      c->congested_read_threshold_us);
-	sysfs_strtoul(congested_write_threshold_us,
-		      c->congested_write_threshold_us);
+	sysfs_strtoul_clamp(congested_read_threshold_us,
+			    c->congested_read_threshold_us,
+			    0, UINT_MAX);
+	sysfs_strtoul_clamp(congested_write_threshold_us,
+			    c->congested_write_threshold_us,
+			    0, UINT_MAX);
 
 	if (attr == &sysfs_errors) {
 		v = __sysfs_match_string(error_actions, -1, buf);
@@ -774,12 +801,20 @@ STORE(__bch_cache_set)
 		c->on_error = v;
 	}
 
-	if (attr == &sysfs_io_error_limit)
-		c->error_limit = strtoul_or_return(buf);
+	sysfs_strtoul_clamp(io_error_limit, c->error_limit, 0, UINT_MAX);
 
 	/* See count_io_errors() for why 88 */
-	if (attr == &sysfs_io_error_halflife)
-		c->error_decay = strtoul_or_return(buf) / 88;
+	if (attr == &sysfs_io_error_halflife) {
+		unsigned long v = 0;
+		ssize_t ret;
+
+		ret = strtoul_safe_clamp(buf, v, 0, UINT_MAX);
+		if (!ret) {
+			c->error_decay = v / 88;
+			return size;
+		}
+		return ret;
+	}
 
 	if (attr == &sysfs_io_disable) {
 		v = strtoul_or_return(buf);
@@ -794,13 +829,15 @@ STORE(__bch_cache_set)
 		}
 	}
 
-	sysfs_strtoul(journal_delay_ms,		c->journal_delay_ms);
-	sysfs_strtoul(verify,			c->verify);
-	sysfs_strtoul(key_merging_disabled,	c->key_merging_disabled);
+	sysfs_strtoul_clamp(journal_delay_ms,
+			    c->journal_delay_ms,
+			    0, USHRT_MAX);
+	sysfs_strtoul_bool(verify,		c->verify);
+	sysfs_strtoul_bool(key_merging_disabled, c->key_merging_disabled);
 	sysfs_strtoul(expensive_debug_checks,	c->expensive_debug_checks);
-	sysfs_strtoul(gc_always_rewrite,	c->gc_always_rewrite);
-	sysfs_strtoul(btree_shrinker_disabled,	c->shrinker_disabled);
-	sysfs_strtoul(copy_gc_enabled,		c->copy_gc_enabled);
+	sysfs_strtoul_bool(gc_always_rewrite,	c->gc_always_rewrite);
+	sysfs_strtoul_bool(btree_shrinker_disabled, c->shrinker_disabled);
+	sysfs_strtoul_bool(copy_gc_enabled,	c->copy_gc_enabled);
 	/*
 	 * write gc_after_writeback here may overwrite an already set
 	 * BCH_DO_AUTO_GC, it doesn't matter because this flag will be
diff --git a/drivers/md/bcache/sysfs.h b/drivers/md/bcache/sysfs.h
index 3fe82425859c..215df32f567b 100644
--- a/drivers/md/bcache/sysfs.h
+++ b/drivers/md/bcache/sysfs.h
@@ -79,11 +79,28 @@ do {									\
 		return strtoul_safe(buf, var) ?: (ssize_t) size;	\
 } while (0)
 
+#define sysfs_strtoul_bool(file, var)					\
+do {									\
+	if (attr == &sysfs_ ## file) {					\
+		unsigned long v = strtoul_or_return(buf);		\
+									\
+		var = v ? 1 : 0;					\
+		return size;						\
+	}								\
+} while (0)
+
 #define sysfs_strtoul_clamp(file, var, min, max)			\
 do {									\
-	if (attr == &sysfs_ ## file)					\
-		return strtoul_safe_clamp(buf, var, min, max)		\
-			?: (ssize_t) size;				\
+	if (attr == &sysfs_ ## file) {					\
+		unsigned long v = 0;					\
+		ssize_t ret;						\
+		ret = strtoul_safe_clamp(buf, v, min, max);		\
+		if (!ret) {						\
+			var = v;					\
+			return size;					\
+		}							\
+		return ret;						\
+	}								\
 } while (0)
 
 #define strtoul_or_return(cp)						\
diff --git a/drivers/md/bcache/util.c b/drivers/md/bcache/util.c
index 20eddeac1531..62fb917f7a4f 100644
--- a/drivers/md/bcache/util.c
+++ b/drivers/md/bcache/util.c
@@ -270,7 +270,11 @@ int bch_bio_alloc_pages(struct bio *bio, gfp_t gfp_mask)
 	int i;
 	struct bio_vec *bv;
 
-	bio_for_each_segment_all(bv, bio, i) {
+	/*
+	 * This is called on freshly new bio, so it is safe to access the
+	 * bvec table directly.
+	 */
+	for (i = 0, bv = bio->bi_io_vec; i < bio->bi_vcnt; bv++, i++) {
 		bv->bv_page = alloc_page(gfp_mask);
 		if (!bv->bv_page) {
 			while (--bv >= bio->bi_io_vec)
diff --git a/drivers/md/bcache/writeback.h b/drivers/md/bcache/writeback.h
index 6a743d3bb338..4e4c6810dc3c 100644
--- a/drivers/md/bcache/writeback.h
+++ b/drivers/md/bcache/writeback.h
@@ -71,6 +71,9 @@ static inline bool should_writeback(struct cached_dev *dc, struct bio *bio,
 	    in_use > bch_cutoff_writeback_sync)
 		return false;
 
+	if (bio_op(bio) == REQ_OP_DISCARD)
+		return false;
+
 	if (dc->partial_stripes_expensive &&
 	    bcache_dev_stripe_dirty(dc, bio->bi_iter.bi_sector,
 				    bio_sectors(bio)))
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index dd538e6b2748..dd6565798778 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -1447,8 +1447,9 @@ static void crypt_free_buffer_pages(struct crypt_config *cc, struct bio *clone)
 {
 	unsigned int i;
 	struct bio_vec *bv;
+	struct bvec_iter_all iter_all;
 
-	bio_for_each_segment_all(bv, clone, i) {
+	bio_for_each_segment_all(bv, clone, i, iter_all) {
 		BUG_ON(!bv->bv_page);
 		mempool_free(bv->bv_page, &cc->page_pool);
 	}
diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c
index a20531e5f3b4..b2c03c079a8d 100644
--- a/drivers/md/dm-rq.c
+++ b/drivers/md/dm-rq.c
@@ -527,7 +527,7 @@ int dm_mq_init_request_queue(struct mapped_device *md, struct dm_table *t)
 	md->tag_set->ops = &dm_mq_ops;
 	md->tag_set->queue_depth = dm_get_blk_mq_queue_depth();
 	md->tag_set->numa_node = md->numa_node_id;
-	md->tag_set->flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_SG_MERGE;
+	md->tag_set->flags = BLK_MQ_F_SHOULD_MERGE;
 	md->tag_set->nr_hw_queues = dm_get_blk_mq_nr_hw_queues();
 	md->tag_set->driver_data = md;
 
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 4b1be754cc41..ba9481f1bf3c 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -1698,14 +1698,6 @@ static int device_is_not_random(struct dm_target *ti, struct dm_dev *dev,
 	return q && !blk_queue_add_random(q);
 }
 
-static int queue_supports_sg_merge(struct dm_target *ti, struct dm_dev *dev,
-				   sector_t start, sector_t len, void *data)
-{
-	struct request_queue *q = bdev_get_queue(dev->bdev);
-
-	return q && !test_bit(QUEUE_FLAG_NO_SG_MERGE, &q->queue_flags);
-}
-
 static bool dm_table_all_devices_attribute(struct dm_table *t,
 					   iterate_devices_callout_fn func)
 {
@@ -1902,11 +1894,6 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 	if (!dm_table_supports_write_zeroes(t))
 		q->limits.max_write_zeroes_sectors = 0;
 
-	if (dm_table_all_devices_attribute(t, queue_supports_sg_merge))
-		blk_queue_flag_clear(QUEUE_FLAG_NO_SG_MERGE, q);
-	else
-		blk_queue_flag_set(QUEUE_FLAG_NO_SG_MERGE, q);
-
 	dm_table_verify_integrity(t);
 
 	/*
diff --git a/drivers/md/md-linear.c b/drivers/md/md-linear.c
index d45c697c0ebe..5998d78aa189 100644
--- a/drivers/md/md-linear.c
+++ b/drivers/md/md-linear.c
@@ -96,8 +96,7 @@ static struct linear_conf *linear_conf(struct mddev *mddev, int raid_disks)
 	int i, cnt;
 	bool discard_supported = false;
 
-	conf = kzalloc (sizeof (*conf) + raid_disks*sizeof(struct dev_info),
-			GFP_KERNEL);
+	conf = kzalloc(struct_size(conf, disks, raid_disks), GFP_KERNEL);
 	if (!conf)
 		return NULL;
 
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index fa47249fa3e4..fdf451aac369 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1603,11 +1603,9 @@ static void raid1_error(struct mddev *mddev, struct md_rdev *rdev)
 		return;
 	}
 	set_bit(Blocked, &rdev->flags);
-	if (test_and_clear_bit(In_sync, &rdev->flags)) {
+	if (test_and_clear_bit(In_sync, &rdev->flags))
 		mddev->degraded++;
-		set_bit(Faulty, &rdev->flags);
-	} else
-		set_bit(Faulty, &rdev->flags);
+	set_bit(Faulty, &rdev->flags);
 	spin_unlock_irqrestore(&conf->device_lock, flags);
 	/*
 	 * if recovery is running, make sure it aborts.
@@ -2120,13 +2118,14 @@ static void process_checks(struct r1bio *r1_bio)
 		struct page **spages = get_resync_pages(sbio)->pages;
 		struct bio_vec *bi;
 		int page_len[RESYNC_PAGES] = { 0 };
+		struct bvec_iter_all iter_all;
 
 		if (sbio->bi_end_io != end_sync_read)
 			continue;
 		/* Now we can 'fixup' the error value */
 		sbio->bi_status = 0;
 
-		bio_for_each_segment_all(bi, sbio, j)
+		bio_for_each_segment_all(bi, sbio, j, iter_all)
 			page_len[j] = bi->bv_len;
 
 		if (!status) {