Merge tag 'for-5.14/dm-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm

Pull device mapper updates from Mike Snitzer:

 - Various DM persistent-data library improvements and fixes that
   benefit both the DM thinp and cache targets.

 - A few small DM kcopyd efficiency improvements.

 - Significant zoned related block core, DM core and DM zoned target
   changes that culminate with adding zoned append emulation (which is
   required to properly fix DM crypt's zoned support).

 - Various DM writecache target changes that improve efficiency. Adds an
   optional "metadata_only" feature that only promotes bios flagged with
   REQ_META. But the most significant improvement is writecache's
   ability to pause writeback, for a confiurable time, if/when the
   working set is larger than the cache (and the cache is full) -- this
   ensures performance is no worse than the slower origin device.

* tag 'for-5.14/dm-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm: (35 commits)
  dm writecache: make writeback pause configurable
  dm writecache: pause writeback if cache full and origin being written directly
  dm io tracker: factor out IO tracker
  dm btree remove: assign new_root only when removal succeeds
  dm zone: fix dm_revalidate_zones() memory allocation
  dm ps io affinity: remove redundant continue statement
  dm writecache: add optional "metadata_only" parameter
  dm writecache: add "cleaner" and "max_age" to Documentation
  dm writecache: write at least 4k when committing
  dm writecache: flush origin device when writing and cache is full
  dm writecache: have ssd writeback wait if the kcopyd workqueue is busy
  dm writecache: use list_move instead of list_del/list_add in writecache_writeback()
  dm writecache: commit just one block, not a full page
  dm writecache: remove unused gfp_t argument from wc_add_block()
  dm crypt: Fix zoned block device support
  dm: introduce zone append emulation
  dm: rearrange core declarations for extended use from dm-zone.c
  block: introduce BIO_ZONE_WRITE_LOCKED bio flag
  block: introduce bio zone helpers
  block: improve handling of all zones reset operation
  ...

1 files changed, 92 insertions, 27 deletions

diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index 250cb76ee61532..86fce751bb1736 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -161,18 +161,89 @@ int blkdev_report_zones(struct block_device *bdev, sector_t sector,
 }
 EXPORT_SYMBOL_GPL(blkdev_report_zones);
 
-static inline bool blkdev_allow_reset_all_zones(struct block_device *bdev,
-						sector_t sector,
-						sector_t nr_sectors)
+static inline unsigned long *blk_alloc_zone_bitmap(int node,
+						   unsigned int nr_zones)
 {
-	if (!blk_queue_zone_resetall(bdev_get_queue(bdev)))
-		return false;
+	return kcalloc_node(BITS_TO_LONGS(nr_zones), sizeof(unsigned long),
+			    GFP_NOIO, node);
+}
 
+static int blk_zone_need_reset_cb(struct blk_zone *zone, unsigned int idx,
+				  void *data)
+{
 	/*
-	 * REQ_OP_ZONE_RESET_ALL can be executed only if the number of sectors
-	 * of the applicable zone range is the entire disk.
+	 * For an all-zones reset, ignore conventional, empty, read-only
+	 * and offline zones.
 	 */
-	return !sector && nr_sectors == get_capacity(bdev->bd_disk);
+	switch (zone->cond) {
+	case BLK_ZONE_COND_NOT_WP:
+	case BLK_ZONE_COND_EMPTY:
+	case BLK_ZONE_COND_READONLY:
+	case BLK_ZONE_COND_OFFLINE:
+		return 0;
+	default:
+		set_bit(idx, (unsigned long *)data);
+		return 0;
+	}
+}
+
+static int blkdev_zone_reset_all_emulated(struct block_device *bdev,
+					  gfp_t gfp_mask)
+{
+	struct request_queue *q = bdev_get_queue(bdev);
+	sector_t capacity = get_capacity(bdev->bd_disk);
+	sector_t zone_sectors = blk_queue_zone_sectors(q);
+	unsigned long *need_reset;
+	struct bio *bio = NULL;
+	sector_t sector = 0;
+	int ret;
+
+	need_reset = blk_alloc_zone_bitmap(q->node, q->nr_zones);
+	if (!need_reset)
+		return -ENOMEM;
+
+	ret = bdev->bd_disk->fops->report_zones(bdev->bd_disk, 0,
+				q->nr_zones, blk_zone_need_reset_cb,
+				need_reset);
+	if (ret < 0)
+		goto out_free_need_reset;
+
+	ret = 0;
+	while (sector < capacity) {
+		if (!test_bit(blk_queue_zone_no(q, sector), need_reset)) {
+			sector += zone_sectors;
+			continue;
+		}
+
+		bio = blk_next_bio(bio, 0, gfp_mask);
+		bio_set_dev(bio, bdev);
+		bio->bi_opf = REQ_OP_ZONE_RESET | REQ_SYNC;
+		bio->bi_iter.bi_sector = sector;
+		sector += zone_sectors;
+
+		/* This may take a while, so be nice to others */
+		cond_resched();
+	}
+
+	if (bio) {
+		ret = submit_bio_wait(bio);
+		bio_put(bio);
+	}
+
+out_free_need_reset:
+	kfree(need_reset);
+	return ret;
+}
+
+static int blkdev_zone_reset_all(struct block_device *bdev, gfp_t gfp_mask)
+{
+	struct bio bio;
+
+	bio_init(&bio, NULL, 0);
+	bio_set_dev(&bio, bdev);
+	bio.bi_opf = REQ_OP_ZONE_RESET_ALL | REQ_SYNC;
+
+	return submit_bio_wait(&bio);
 }
 
 /**
@@ -200,7 +271,7 @@ int blkdev_zone_mgmt(struct block_device *bdev, enum req_opf op,
 	sector_t capacity = get_capacity(bdev->bd_disk);
 	sector_t end_sector = sector + nr_sectors;
 	struct bio *bio = NULL;
-	int ret;
+	int ret = 0;
 
 	if (!blk_queue_is_zoned(q))
 		return -EOPNOTSUPP;
@@ -222,20 +293,21 @@ int blkdev_zone_mgmt(struct block_device *bdev, enum req_opf op,
 	if ((nr_sectors & (zone_sectors - 1)) && end_sector != capacity)
 		return -EINVAL;
 
+	/*
+	 * In the case of a zone reset operation over all zones,
+	 * REQ_OP_ZONE_RESET_ALL can be used with devices supporting this
+	 * command. For other devices, we emulate this command behavior by
+	 * identifying the zones needing a reset.
+	 */
+	if (op == REQ_OP_ZONE_RESET && sector == 0 && nr_sectors == capacity) {
+		if (!blk_queue_zone_resetall(q))
+			return blkdev_zone_reset_all_emulated(bdev, gfp_mask);
+		return blkdev_zone_reset_all(bdev, gfp_mask);
+	}
+
 	while (sector < end_sector) {
 		bio = blk_next_bio(bio, 0, gfp_mask);
 		bio_set_dev(bio, bdev);
-
-		/*
-		 * Special case for the zone reset operation that reset all
-		 * zones, this is useful for applications like mkfs.
-		 */
-		if (op == REQ_OP_ZONE_RESET &&
-		    blkdev_allow_reset_all_zones(bdev, sector, nr_sectors)) {
-			bio->bi_opf = REQ_OP_ZONE_RESET_ALL | REQ_SYNC;
-			break;
-		}
-
 		bio->bi_opf = op | REQ_SYNC;
 		bio->bi_iter.bi_sector = sector;
 		sector += zone_sectors;
@@ -396,13 +468,6 @@ int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode,
 	return ret;
 }
 
-static inline unsigned long *blk_alloc_zone_bitmap(int node,
-						   unsigned int nr_zones)
-{
-	return kcalloc_node(BITS_TO_LONGS(nr_zones), sizeof(unsigned long),
-			    GFP_NOIO, node);
-}
-
 void blk_queue_free_zone_bitmaps(struct request_queue *q)
 {
 	kfree(q->conv_zones_bitmap);