Merge tag 'for-4.20/block-20181021' of git://git.kernel.dk/linux-block

Pull block layer updates from Jens Axboe:
 "This is the main pull request for block changes for 4.20. This
  contains:

   - Series enabling runtime PM for blk-mq (Bart).

   - Two pull requests from Christoph for NVMe, with items such as;
      - Better AEN tracking
      - Multipath improvements
      - RDMA fixes
      - Rework of FC for target removal
      - Fixes for issues identified by static checkers
      - Fabric cleanups, as prep for TCP transport
      - Various cleanups and bug fixes

   - Block merging cleanups (Christoph)

   - Conversion of drivers to generic DMA mapping API (Christoph)

   - Series fixing ref count issues with blkcg (Dennis)

   - Series improving BFQ heuristics (Paolo, et al)

   - Series improving heuristics for the Kyber IO scheduler (Omar)

   - Removal of dangerous bio_rewind_iter() API (Ming)

   - Apply single queue IPI redirection logic to blk-mq (Ming)

   - Set of fixes and improvements for bcache (Coly et al)

   - Series closing a hotplug race with sysfs group attributes (Hannes)

   - Set of patches for lightnvm:
      - pblk trace support (Hans)
      - SPDX license header update (Javier)
      - Tons of refactoring patches to cleanly abstract the 1.2 and 2.0
        specs behind a common core interface. (Javier, Matias)
      - Enable pblk to use a common interface to retrieve chunk metadata
        (Matias)
      - Bug fixes (Various)

   - Set of fixes and updates to the blk IO latency target (Josef)

   - blk-mq queue number updates fixes (Jianchao)

   - Convert a bunch of drivers from the old legacy IO interface to
     blk-mq. This will conclude with the removal of the legacy IO
     interface itself in 4.21, with the rest of the drivers (me, Omar)

   - Removal of the DAC960 driver. The SCSI tree will introduce two
     replacement drivers for this (Hannes)"

* tag 'for-4.20/block-20181021' of git://git.kernel.dk/linux-block: (204 commits)
  block: setup bounce bio_sets properly
  blkcg: reassociate bios when make_request() is called recursively
  blkcg: fix edge case for blk_get_rl() under memory pressure
  nvme-fabrics: move controller options matching to fabrics
  nvme-rdma: always have a valid trsvcid
  mtip32xx: fully switch to the generic DMA API
  rsxx: switch to the generic DMA API
  umem: switch to the generic DMA API
  sx8: switch to the generic DMA API
  sx8: remove dead IF_64BIT_DMA_IS_POSSIBLE code
  skd: switch to the generic DMA API
  ubd: remove use of blk_rq_map_sg
  nvme-pci: remove duplicate check
  drivers/block: Remove DAC960 driver
  nvme-pci: fix hot removal during error handling
  nvmet-fcloop: suppress a compiler warning
  nvme-core: make implicit seed truncation explicit
  nvmet-fc: fix kernel-doc headers
  nvme-fc: rework the request initialization code
  nvme-fc: introduce struct nvme_fcp_op_w_sgl
  ...

11 files changed, 110 insertions, 31 deletions

diff --git a/drivers/md/bcache/alloc.c b/drivers/md/bcache/alloc.c
index 7a28232d868b..5002838ea476 100644
--- a/drivers/md/bcache/alloc.c
+++ b/drivers/md/bcache/alloc.c
@@ -484,7 +484,7 @@ int __bch_bucket_alloc_set(struct cache_set *c, unsigned int reserve,
 	int i;
 
 	lockdep_assert_held(&c->bucket_lock);
-	BUG_ON(!n || n > c->caches_loaded || n > 8);
+	BUG_ON(!n || n > c->caches_loaded || n > MAX_CACHES_PER_SET);
 
 	bkey_init(k);
 
diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index 954dad29e6e8..b61b83bbcfff 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -1004,7 +1004,7 @@ void bch_open_buckets_free(struct cache_set *c);
 int bch_cache_allocator_start(struct cache *ca);
 
 void bch_debug_exit(void);
-void bch_debug_init(struct kobject *kobj);
+void bch_debug_init(void);
 void bch_request_exit(void);
 int bch_request_init(void);
 
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index e7d4817681f2..3f4211b5cd33 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -2434,7 +2434,7 @@ static int refill_keybuf_fn(struct btree_op *op, struct btree *b,
 	struct keybuf *buf = refill->buf;
 	int ret = MAP_CONTINUE;
 
-	if (bkey_cmp(k, refill->end) >= 0) {
+	if (bkey_cmp(k, refill->end) > 0) {
 		ret = MAP_DONE;
 		goto out;
 	}
diff --git a/drivers/md/bcache/closure.h b/drivers/md/bcache/closure.h
index eca0d496b686..c88cdc4ae4ec 100644
--- a/drivers/md/bcache/closure.h
+++ b/drivers/md/bcache/closure.h
@@ -345,7 +345,8 @@ do {									\
 } while (0)
 
 /**
- * closure_return - finish execution of a closure, with destructor
+ * closure_return_with_destructor - finish execution of a closure,
+ *				    with destructor
  *
  * Works like closure_return(), except @destructor will be called when all
  * outstanding refs on @cl have been dropped; @destructor may be used to safely
diff --git a/drivers/md/bcache/debug.c b/drivers/md/bcache/debug.c
index 06da66b2488a..8f448b9c96a1 100644
--- a/drivers/md/bcache/debug.c
+++ b/drivers/md/bcache/debug.c
@@ -253,7 +253,7 @@ void bch_debug_exit(void)
 		debugfs_remove_recursive(bcache_debug);
 }
 
-void __init bch_debug_init(struct kobject *kobj)
+void __init bch_debug_init(void)
 {
 	/*
 	 * it is unnecessary to check return value of
diff --git a/drivers/md/bcache/extents.c b/drivers/md/bcache/extents.c
index c809724e6571..956004366699 100644
--- a/drivers/md/bcache/extents.c
+++ b/drivers/md/bcache/extents.c
@@ -553,7 +553,7 @@ static bool bch_extent_bad(struct btree_keys *bk, const struct bkey *k)
 	for (i = 0; i < KEY_PTRS(k); i++) {
 		stale = ptr_stale(b->c, k, i);
 
-		btree_bug_on(stale > 96, b,
+		btree_bug_on(stale > BUCKET_GC_GEN_MAX, b,
 			     "key too stale: %i, need_gc %u",
 			     stale, b->c->need_gc);
 
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index 51be355a3309..3bf35914bb57 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -395,7 +395,7 @@ static bool check_should_bypass(struct cached_dev *dc, struct bio *bio)
 	 * unless the read-ahead request is for metadata (eg, for gfs2).
 	 */
 	if (bio->bi_opf & (REQ_RAHEAD|REQ_BACKGROUND) &&
-	    !(bio->bi_opf & REQ_META))
+	    !(bio->bi_opf & REQ_PRIO))
 		goto skip;
 
 	if (bio->bi_iter.bi_sector & (c->sb.block_size - 1) ||
@@ -850,7 +850,7 @@ static void cached_dev_read_done_bh(struct closure *cl)
 
 	bch_mark_cache_accounting(s->iop.c, s->d,
 				  !s->cache_missed, s->iop.bypass);
-	trace_bcache_read(s->orig_bio, !s->cache_miss, s->iop.bypass);
+	trace_bcache_read(s->orig_bio, !s->cache_missed, s->iop.bypass);
 
 	if (s->iop.status)
 		continue_at_nobarrier(cl, cached_dev_read_error, bcache_wq);
@@ -877,7 +877,7 @@ static int cached_dev_cache_miss(struct btree *b, struct search *s,
 	}
 
 	if (!(bio->bi_opf & REQ_RAHEAD) &&
-	    !(bio->bi_opf & REQ_META) &&
+	    !(bio->bi_opf & 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));
@@ -1218,6 +1218,9 @@ static int cached_dev_ioctl(struct bcache_device *d, fmode_t mode,
 {
 	struct cached_dev *dc = container_of(d, struct cached_dev, disk);
 
+	if (dc->io_disable)
+		return -EIO;
+
 	return __blkdev_driver_ioctl(dc->bdev, mode, cmd, arg);
 }
 
diff --git a/drivers/md/bcache/request.h b/drivers/md/bcache/request.h
index aa055cfeb099..721bf336ed1a 100644
--- a/drivers/md/bcache/request.h
+++ b/drivers/md/bcache/request.h
@@ -39,6 +39,6 @@ void bch_data_insert(struct closure *cl);
 void bch_cached_dev_request_init(struct cached_dev *dc);
 void bch_flash_dev_request_init(struct bcache_device *d);
 
-extern struct kmem_cache *bch_search_cache, *bch_passthrough_cache;
+extern struct kmem_cache *bch_search_cache;
 
 #endif /* _BCACHE_REQUEST_H_ */
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 30ba9aeb5ee8..7bbd670a5a84 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -418,6 +418,7 @@ static int __uuid_write(struct cache_set *c)
 {
 	BKEY_PADDED(key) k;
 	struct closure cl;
+	struct cache *ca;
 
 	closure_init_stack(&cl);
 	lockdep_assert_held(&bch_register_lock);
@@ -429,6 +430,10 @@ static int __uuid_write(struct cache_set *c)
 	uuid_io(c, REQ_OP_WRITE, 0, &k.key, &cl);
 	closure_sync(&cl);
 
+	/* Only one bucket used for uuid write */
+	ca = PTR_CACHE(c, &k.key, 0);
+	atomic_long_add(ca->sb.bucket_size, &ca->meta_sectors_written);
+
 	bkey_copy(&c->uuid_bucket, &k.key);
 	bkey_put(c, &k.key);
 	return 0;
@@ -643,10 +648,6 @@ static int ioctl_dev(struct block_device *b, fmode_t mode,
 		     unsigned int cmd, unsigned long arg)
 {
 	struct bcache_device *d = b->bd_disk->private_data;
-	struct cached_dev *dc = container_of(d, struct cached_dev, disk);
-
-	if (dc->io_disable)
-		return -EIO;
 
 	return d->ioctl(d, mode, cmd, arg);
 }
@@ -1008,6 +1009,7 @@ static void cached_dev_detach_finish(struct work_struct *w)
 	bch_write_bdev_super(dc, &cl);
 	closure_sync(&cl);
 
+	calc_cached_dev_sectors(dc->disk.c);
 	bcache_device_detach(&dc->disk);
 	list_move(&dc->list, &uncached_devices);
 
@@ -1152,11 +1154,12 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c,
 	}
 
 	if (BDEV_STATE(&dc->sb) == BDEV_STATE_DIRTY) {
-		bch_sectors_dirty_init(&dc->disk);
 		atomic_set(&dc->has_dirty, 1);
 		bch_writeback_queue(dc);
 	}
 
+	bch_sectors_dirty_init(&dc->disk);
+
 	bch_cached_dev_run(dc);
 	bcache_device_link(&dc->disk, c, "bdev");
 	atomic_inc(&c->attached_dev_nr);
@@ -2049,6 +2052,8 @@ static int cache_alloc(struct cache *ca)
 	size_t free;
 	size_t btree_buckets;
 	struct bucket *b;
+	int ret = -ENOMEM;
+	const char *err = NULL;
 
 	__module_get(THIS_MODULE);
 	kobject_init(&ca->kobj, &bch_cache_ktype);
@@ -2066,27 +2071,93 @@ static int cache_alloc(struct cache *ca)
 	 */
 	btree_buckets = ca->sb.njournal_buckets ?: 8;
 	free = roundup_pow_of_two(ca->sb.nbuckets) >> 10;
+	if (!free) {
+		ret = -EPERM;
+		err = "ca->sb.nbuckets is too small";
+		goto err_free;
+	}
 
-	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) ||
-	    !init_fifo(&ca->free_inc,	free << 2, GFP_KERNEL) ||
-	    !init_heap(&ca->heap,	free << 3, GFP_KERNEL) ||
-	    !(ca->buckets	= vzalloc(array_size(sizeof(struct bucket),
-						     ca->sb.nbuckets))) ||
-	    !(ca->prio_buckets	= kzalloc(array3_size(sizeof(uint64_t),
-						      prio_buckets(ca), 2),
-					  GFP_KERNEL)) ||
-	    !(ca->disk_buckets	= alloc_bucket_pages(GFP_KERNEL, ca)))
-		return -ENOMEM;
+	if (!init_fifo(&ca->free[RESERVE_BTREE], btree_buckets,
+						GFP_KERNEL)) {
+		err = "ca->free[RESERVE_BTREE] alloc failed";
+		goto err_btree_alloc;
+	}
+
+	if (!init_fifo_exact(&ca->free[RESERVE_PRIO], prio_buckets(ca),
+							GFP_KERNEL)) {
+		err = "ca->free[RESERVE_PRIO] alloc failed";
+		goto err_prio_alloc;
+	}
+
+	if (!init_fifo(&ca->free[RESERVE_MOVINGGC], free, GFP_KERNEL)) {
+		err = "ca->free[RESERVE_MOVINGGC] alloc failed";
+		goto err_movinggc_alloc;
+	}
+
+	if (!init_fifo(&ca->free[RESERVE_NONE], free, GFP_KERNEL)) {
+		err = "ca->free[RESERVE_NONE] alloc failed";
+		goto err_none_alloc;
+	}
+
+	if (!init_fifo(&ca->free_inc, free << 2, GFP_KERNEL)) {
+		err = "ca->free_inc alloc failed";
+		goto err_free_inc_alloc;
+	}
+
+	if (!init_heap(&ca->heap, free << 3, GFP_KERNEL)) {
+		err = "ca->heap alloc failed";
+		goto err_heap_alloc;
+	}
+
+	ca->buckets = vzalloc(array_size(sizeof(struct bucket),
+			      ca->sb.nbuckets));
+	if (!ca->buckets) {
+		err = "ca->buckets alloc failed";
+		goto err_buckets_alloc;
+	}
+
+	ca->prio_buckets = kzalloc(array3_size(sizeof(uint64_t),
+				   prio_buckets(ca), 2),
+				   GFP_KERNEL);
+	if (!ca->prio_buckets) {
+		err = "ca->prio_buckets alloc failed";
+		goto err_prio_buckets_alloc;
+	}
+
+	ca->disk_buckets = alloc_bucket_pages(GFP_KERNEL, ca);
+	if (!ca->disk_buckets) {
+		err = "ca->disk_buckets alloc failed";
+		goto err_disk_buckets_alloc;
+	}
 
 	ca->prio_last_buckets = ca->prio_buckets + prio_buckets(ca);
 
 	for_each_bucket(b, ca)
 		atomic_set(&b->pin, 0);
-
 	return 0;
+
+err_disk_buckets_alloc:
+	kfree(ca->prio_buckets);
+err_prio_buckets_alloc:
+	vfree(ca->buckets);
+err_buckets_alloc:
+	free_heap(&ca->heap);
+err_heap_alloc:
+	free_fifo(&ca->free_inc);
+err_free_inc_alloc:
+	free_fifo(&ca->free[RESERVE_NONE]);
+err_none_alloc:
+	free_fifo(&ca->free[RESERVE_MOVINGGC]);
+err_movinggc_alloc:
+	free_fifo(&ca->free[RESERVE_PRIO]);
+err_prio_alloc:
+	free_fifo(&ca->free[RESERVE_BTREE]);
+err_btree_alloc:
+err_free:
+	module_put(THIS_MODULE);
+	if (err)
+		pr_notice("error %s: %s", ca->cache_dev_name, err);
+	return ret;
 }
 
 static int register_cache(struct cache_sb *sb, struct page *sb_page,
@@ -2112,6 +2183,8 @@ static int register_cache(struct cache_sb *sb, struct page *sb_page,
 		blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
 		if (ret == -ENOMEM)
 			err = "cache_alloc(): -ENOMEM";
+		else if (ret == -EPERM)
+			err = "cache_alloc(): cache device is too small";
 		else
 			err = "cache_alloc(): unknown error";
 		goto err;
@@ -2386,7 +2459,7 @@ static int __init bcache_init(void)
 	    sysfs_create_files(bcache_kobj, files))
 		goto err;
 
-	bch_debug_init(bcache_kobj);
+	bch_debug_init();
 	closure_debug_init();
 
 	return 0;
diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c
index 150cf4f4cf74..26f035a0c5b9 100644
--- a/drivers/md/bcache/sysfs.c
+++ b/drivers/md/bcache/sysfs.c
@@ -285,6 +285,7 @@ STORE(__cached_dev)
 			    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(io_error_limit, dc->error_limit, 0, INT_MAX);
 
@@ -412,6 +413,7 @@ static struct attribute *bch_cached_dev_files[] = {
 	&sysfs_writeback_rate_update_seconds,
 	&sysfs_writeback_rate_i_term_inverse,
 	&sysfs_writeback_rate_p_term_inverse,
+	&sysfs_writeback_rate_minimum,
 	&sysfs_writeback_rate_debug,
 	&sysfs_errors,
 	&sysfs_io_error_limit,
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index ac1cffd2a09b..f3fb5bb8c82a 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -542,7 +542,7 @@ static void raid0_handle_discard(struct mddev *mddev, struct bio *bio)
 		    !discard_bio)
 			continue;
 		bio_chain(discard_bio, bio);
-		bio_clone_blkcg_association(discard_bio, bio);
+		bio_clone_blkg_association(discard_bio, bio);
 		if (mddev->gendisk)
 			trace_block_bio_remap(bdev_get_queue(rdev->bdev),
 				discard_bio, disk_devt(mddev->gendisk),