Merge tag 'for-4.18/dm-fixes' of...

Merge tag 'for-4.18/dm-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm

Pull device mapper fixes from Mike Snitzer:

 - Fix dm core to use more efficient bio_split() instead of
   bio_clone_bioset(). Also fixes splitting bio that has integrity
   payload.

 - Three fixes related to properly validating DAX capabilities of a
   stacked DM device that will advertise DAX support.

 - Update DM writecache target to use 2-factor allocator arguments. Kees
   says this is the last related change for 4.18.

 - Fix DM zoned target to use GFP_NOIO to avoid triggering reclaim
   during IO submission (caught by lockdep).

 - Fix DM thinp to gracefully recover from running out of data space
   while a previous async discard completes (whereby freeing space).

 - Fix DM thinp's metadata transaction commit to avoid needless work.

* tag 'for-4.18/dm-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm:
  dm: prevent DAX mounts if not supported
  dax: check for QUEUE_FLAG_DAX in bdev_dax_supported()
  pmem: only set QUEUE_FLAG_DAX for fsdax mode
  dm thin: handle running out of data space vs concurrent discard
  dm raid: don't use 'const' in function return
  dm zoned: avoid triggering reclaim from inside dmz_map()
  dm writecache: use 2-factor allocator arguments
  dm thin metadata: remove needless work from __commit_transaction
  dm: use bio_split() when splitting out the already processed bio

drivers/dax/super.c

@@ -86,6 +86,7 @@ bool __bdev_dax_supported(struct block_device *bdev, int blocksize)
 {
 	struct dax_device *dax_dev;
 	bool dax_enabled = false;
+	struct request_queue *q;
 	pgoff_t pgoff;
 	int err, id;
 	void *kaddr;
@@ -99,6 +100,13 @@ bool __bdev_dax_supported(struct block_device *bdev, int blocksize)
 		return false;
 	}
 
+	q = bdev_get_queue(bdev);
+	if (!q || !blk_queue_dax(q)) {
+		pr_debug("%s: error: request queue doesn't support dax\n",
+				bdevname(bdev, buf));
+		return false;
+	}
+
 	err = bdev_dax_pgoff(bdev, 0, PAGE_SIZE, &pgoff);
 	if (err) {
 		pr_debug("%s: error: unaligned partition for dax\n",

drivers/md/dm-raid.c

@@ -588,7 +588,7 @@ static const char *raid10_md_layout_to_format(int layout)
 }
 
 /* Return md raid10 algorithm for @name */
-static const int raid10_name_to_format(const char *name)
+static int raid10_name_to_format(const char *name)
 {
 	if (!strcasecmp(name, "near"))
 		return ALGORITHM_RAID10_NEAR;

drivers/md/dm-table.c

@@ -885,9 +885,7 @@ EXPORT_SYMBOL_GPL(dm_table_set_type);
 static int device_supports_dax(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 && blk_queue_dax(q);
+	return bdev_dax_supported(dev->bdev, PAGE_SIZE);
 }
 
 static bool dm_table_supports_dax(struct dm_table *t)
@@ -1907,6 +1905,9 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 
 	if (dm_table_supports_dax(t))
 		blk_queue_flag_set(QUEUE_FLAG_DAX, q);
+	else
+		blk_queue_flag_clear(QUEUE_FLAG_DAX, q);
+
 	if (dm_table_supports_dax_write_cache(t))
 		dax_write_cache(t->md->dax_dev, true);
 

drivers/md/dm-thin-metadata.c

@@ -776,7 +776,6 @@ static int __write_changed_details(struct dm_pool_metadata *pmd)
 static int __commit_transaction(struct dm_pool_metadata *pmd)
 {
 	int r;
-	size_t metadata_len, data_len;
 	struct thin_disk_superblock *disk_super;
 	struct dm_block *sblock;
 
@@ -797,14 +796,6 @@ static int __commit_transaction(struct dm_pool_metadata *pmd)
 	if (r < 0)
 		return r;
 
-	r = dm_sm_root_size(pmd->metadata_sm, &metadata_len);
-	if (r < 0)
-		return r;
-
-	r = dm_sm_root_size(pmd->data_sm, &data_len);
-	if (r < 0)
-		return r;
-
 	r = save_sm_roots(pmd);
 	if (r < 0)
 		return r;

drivers/md/dm-thin.c

@@ -1386,6 +1386,8 @@ static void schedule_external_copy(struct thin_c *tc, dm_block_t virt_block,
 
 static void set_pool_mode(struct pool *pool, enum pool_mode new_mode);
 
+static void requeue_bios(struct pool *pool);
+
 static void check_for_space(struct pool *pool)
 {
 	int r;
@@ -1398,8 +1400,10 @@ static void check_for_space(struct pool *pool)
 	if (r)
 		return;
 
-	if (nr_free)
+	if (nr_free) {
 		set_pool_mode(pool, PM_WRITE);
+		requeue_bios(pool);
+	}
 }
 
 /*
@@ -1476,7 +1480,10 @@ static int alloc_data_block(struct thin_c *tc, dm_block_t *result)
 
 	r = dm_pool_alloc_data_block(pool->pmd, result);
 	if (r) {
-		metadata_operation_failed(pool, "dm_pool_alloc_data_block", r);
+		if (r == -ENOSPC)
+			set_pool_mode(pool, PM_OUT_OF_DATA_SPACE);
+		else
+			metadata_operation_failed(pool, "dm_pool_alloc_data_block", r);
 		return r;
 	}
 

drivers/md/dm-writecache.c

@@ -259,7 +259,7 @@ static int persistent_memory_claim(struct dm_writecache *wc)
 	if (da != p) {
 		long i;
 		wc->memory_map = NULL;
-		pages = kvmalloc(p * sizeof(struct page *), GFP_KERNEL);
+		pages = kvmalloc_array(p, sizeof(struct page *), GFP_KERNEL);
 		if (!pages) {
 			r = -ENOMEM;
 			goto err2;
@@ -859,7 +859,7 @@ static int writecache_alloc_entries(struct dm_writecache *wc)
 
 	if (wc->entries)
 		return 0;
-	wc->entries = vmalloc(sizeof(struct wc_entry) * wc->n_blocks);
+	wc->entries = vmalloc(array_size(sizeof(struct wc_entry), wc->n_blocks));
 	if (!wc->entries)
 		return -ENOMEM;
 	for (b = 0; b < wc->n_blocks; b++) {
@@ -1481,9 +1481,9 @@ static void __writecache_writeback_pmem(struct dm_writecache *wc, struct writeba
 		wb->bio.bi_iter.bi_sector = read_original_sector(wc, e);
 		wb->page_offset = PAGE_SIZE;
 		if (max_pages <= WB_LIST_INLINE ||
-		    unlikely(!(wb->wc_list = kmalloc(max_pages * sizeof(struct wc_entry *),
-						     GFP_NOIO | __GFP_NORETRY |
-						     __GFP_NOMEMALLOC | __GFP_NOWARN)))) {
+		    unlikely(!(wb->wc_list = kmalloc_array(max_pages, sizeof(struct wc_entry *),
+							   GFP_NOIO | __GFP_NORETRY |
+							   __GFP_NOMEMALLOC | __GFP_NOWARN)))) {
 			wb->wc_list = wb->wc_list_inline;
 			max_pages = WB_LIST_INLINE;
 		}

drivers/md/dm-zoned-target.c

@@ -787,7 +787,7 @@ static int dmz_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 
 	/* Chunk BIO work */
 	mutex_init(&dmz->chunk_lock);
-	INIT_RADIX_TREE(&dmz->chunk_rxtree, GFP_KERNEL);
+	INIT_RADIX_TREE(&dmz->chunk_rxtree, GFP_NOIO);
 	dmz->chunk_wq = alloc_workqueue("dmz_cwq_%s", WQ_MEM_RECLAIM | WQ_UNBOUND,
 					0, dev->name);
 	if (!dmz->chunk_wq) {

drivers/md/dm.c

@@ -1056,8 +1056,7 @@ static long dm_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
 	if (len < 1)
 		goto out;
 	nr_pages = min(len, nr_pages);
-	if (ti->type->direct_access)
-		ret = ti->type->direct_access(ti, pgoff, nr_pages, kaddr, pfn);
+	ret = ti->type->direct_access(ti, pgoff, nr_pages, kaddr, pfn);
 
  out:
 	dm_put_live_table(md, srcu_idx);
@@ -1606,10 +1605,9 @@ static blk_qc_t __split_and_process_bio(struct mapped_device *md,
 				 * the usage of io->orig_bio in dm_remap_zone_report()
 				 * won't be affected by this reassignment.
 				 */
-				struct bio *b = bio_clone_bioset(bio, GFP_NOIO,
-								 &md->queue->bio_split);
+				struct bio *b = bio_split(bio, bio_sectors(bio) - ci.sector_count,
+							  GFP_NOIO, &md->queue->bio_split);
 				ci.io->orig_bio = b;
-				bio_advance(bio, (bio_sectors(bio) - ci.sector_count) << 9);
 				bio_chain(b, bio);
 				ret = generic_make_request(bio);
 				break;

drivers/nvdimm/pmem.c

@@ -414,7 +414,8 @@ static int pmem_attach_disk(struct device *dev,
 	blk_queue_logical_block_size(q, pmem_sector_size(ndns));
 	blk_queue_max_hw_sectors(q, UINT_MAX);
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
-	blk_queue_flag_set(QUEUE_FLAG_DAX, q);
+	if (pmem->pfn_flags & PFN_MAP)
+		blk_queue_flag_set(QUEUE_FLAG_DAX, q);
 	q->queuedata = pmem;
 
 	disk = alloc_disk_node(0, nid);