Merge tag 'for-5.8/dm-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm

Pull device mapper fixes from Mike Snitzer:

 - Quite a few DM zoned target fixes and a Zone append fix in DM core.

   Considering the amount of dm-zoned changes that went in during the
   5.8 merge window these fixes are not that surprising.

 - A few DM writecache target fixes.

 - A fix to Documentation index to include DM ebs target docs.

 - Small cleanup to use struct_size() in DM core's retrieve_deps().

* tag 'for-5.8/dm-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm:
  dm writecache: add cond_resched to loop in persistent_memory_claim()
  dm zoned: Fix reclaim zone selection
  dm zoned: Fix random zone reclaim selection
  dm: update original bio sector on Zone Append
  dm zoned: Fix metadata zone size check
  docs: device-mapper: add dm-ebs.rst to an index file
  dm ioctl: use struct_size() helper in retrieve_deps()
  dm writecache: skip writecache_wait when using pmem mode
  dm writecache: correct uncommitted_block when discarding uncommitted entry
  dm zoned: assign max_io_len correctly
  dm zoned: fix uninitialized pointer dereference

Author: torvalds

Documentation/admin-guide/device-mapper/index.rst

@@ -11,6 +11,7 @@ Device Mapper
     dm-clone
     dm-crypt
     dm-dust
+    dm-ebs
     dm-flakey
     dm-init
     dm-integrity

drivers/md/dm-ioctl.c

@@ -1471,7 +1471,7 @@ static void retrieve_deps(struct dm_table *table,
 	/*
 	 * Check we have enough space.
 	 */
-	needed = sizeof(*deps) + (sizeof(*deps->dev) * count);
+	needed = struct_size(deps, dev, count);
 	if (len < needed) {
 		param->flags |= DM_BUFFER_FULL_FLAG;
 		return;

drivers/md/dm-writecache.c

@@ -282,6 +282,8 @@ static int persistent_memory_claim(struct dm_writecache *wc)
 			while (daa-- && i < p) {
 				pages[i++] = pfn_t_to_page(pfn);
 				pfn.val++;
+				if (!(i & 15))
+					cond_resched();
 			}
 		} while (i < p);
 		wc->memory_map = vmap(pages, p, VM_MAP, PAGE_KERNEL);
@@ -849,10 +851,14 @@ static void writecache_discard(struct dm_writecache *wc, sector_t start, sector_
 
 		if (likely(!e->write_in_progress)) {
 			if (!discarded_something) {
-				writecache_wait_for_ios(wc, READ);
-				writecache_wait_for_ios(wc, WRITE);
+				if (!WC_MODE_PMEM(wc)) {
+					writecache_wait_for_ios(wc, READ);
+					writecache_wait_for_ios(wc, WRITE);
+				}
 				discarded_something = true;
 			}
+			if (!writecache_entry_is_committed(wc, e))
+				wc->uncommitted_blocks--;
 			writecache_free_entry(wc, e);
 		}
 

drivers/md/dm-zoned-metadata.c

@@ -1078,7 +1078,8 @@ static int dmz_check_sb(struct dmz_metadata *zmd, struct dmz_sb *dsb,
 	nr_meta_zones = (le32_to_cpu(sb->nr_meta_blocks) + zmd->zone_nr_blocks - 1)
 		>> zmd->zone_nr_blocks_shift;
 	if (!nr_meta_zones ||
-	    nr_meta_zones >= zmd->nr_rnd_zones) {
+	    (zmd->nr_devs <= 1 && nr_meta_zones >= zmd->nr_rnd_zones) ||
+	    (zmd->nr_devs > 1 && nr_meta_zones >= zmd->nr_cache_zones)) {
 		dmz_dev_err(dev, "Invalid number of metadata blocks");
 		return -ENXIO;
 	}
@@ -1949,7 +1950,7 @@ static struct dm_zone *dmz_get_rnd_zone_for_reclaim(struct dmz_metadata *zmd,
 						    unsigned int idx, bool idle)
 {
 	struct dm_zone *dzone = NULL;
-	struct dm_zone *zone, *last = NULL;
+	struct dm_zone *zone, *maxw_z = NULL;
 	struct list_head *zone_list;
 
 	/* If we have cache zones select from the cache zone list */
@@ -1961,18 +1962,37 @@ static struct dm_zone *dmz_get_rnd_zone_for_reclaim(struct dmz_metadata *zmd,
 	} else
 		zone_list = &zmd->dev[idx].map_rnd_list;
 
+	/*
+	 * Find the buffer zone with the heaviest weight or the first (oldest)
+	 * data zone that can be reclaimed.
+	 */
 	list_for_each_entry(zone, zone_list, link) {
 		if (dmz_is_buf(zone)) {
 			dzone = zone->bzone;
-			if (dzone->dev->dev_idx != idx)
-				continue;
-			if (!last) {
-				last = dzone;
+			if (dmz_is_rnd(dzone) && dzone->dev->dev_idx != idx)
 				continue;
-			}
-			if (last->weight < dzone->weight)
+			if (!maxw_z || maxw_z->weight < dzone->weight)
+				maxw_z = dzone;
+		} else {
+			dzone = zone;
+			if (dmz_lock_zone_reclaim(dzone))
+				return dzone;
+		}
+	}
+
+	if (maxw_z && dmz_lock_zone_reclaim(maxw_z))
+		return maxw_z;
+
+	/*
+	 * If we come here, none of the zones inspected could be locked for
+	 * reclaim. Try again, being more aggressive, that is, find the
+	 * first zone that can be reclaimed regardless of its weitght.
+	 */
+	list_for_each_entry(zone, zone_list, link) {
+		if (dmz_is_buf(zone)) {
+			dzone = zone->bzone;
+			if (dmz_is_rnd(dzone) && dzone->dev->dev_idx != idx)
 				continue;
-			dzone = last;
 		} else
 			dzone = zone;
 		if (dmz_lock_zone_reclaim(dzone))
@@ -2006,7 +2026,7 @@ static struct dm_zone *dmz_get_seq_zone_for_reclaim(struct dmz_metadata *zmd,
 struct dm_zone *dmz_get_zone_for_reclaim(struct dmz_metadata *zmd,
 					 unsigned int dev_idx, bool idle)
 {
-	struct dm_zone *zone;
+	struct dm_zone *zone = NULL;
 
 	/*
 	 * Search for a zone candidate to reclaim: 2 cases are possible.
@@ -2019,7 +2039,7 @@ struct dm_zone *dmz_get_zone_for_reclaim(struct dmz_metadata *zmd,
 	dmz_lock_map(zmd);
 	if (list_empty(&zmd->reserved_seq_zones_list))
 		zone = dmz_get_seq_zone_for_reclaim(zmd, dev_idx);
-	else
+	if (!zone)
 		zone = dmz_get_rnd_zone_for_reclaim(zmd, dev_idx, idle);
 	dmz_unlock_map(zmd);
 

drivers/md/dm-zoned-reclaim.c

@@ -377,6 +377,7 @@ static int dmz_do_reclaim(struct dmz_reclaim *zrc)
 			dmz_metadata_label(zmd), zrc->dev_idx);
 		return -EBUSY;
 	}
+	rzone = dzone;
 
 	start = jiffies;
 	if (dmz_is_cache(dzone) || dmz_is_rnd(dzone)) {
@@ -391,8 +392,6 @@ static int dmz_do_reclaim(struct dmz_reclaim *zrc)
 			 */
 			ret = dmz_reclaim_rnd_data(zrc, dzone);
 		}
-		rzone = dzone;
-
 	} else {
 		struct dm_zone *bzone = dzone->bzone;
 		sector_t chunk_block = 0;
@@ -415,7 +414,6 @@ static int dmz_do_reclaim(struct dmz_reclaim *zrc)
 			 * be later reclaimed.
 			 */
 			ret = dmz_reclaim_seq_data(zrc, dzone);
-			rzone = dzone;
 		}
 	}
 out:

drivers/md/dm-zoned-target.c

@@ -890,7 +890,7 @@ static int dmz_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	}
 
 	/* Set target (no write same support) */
-	ti->max_io_len = dmz_zone_nr_sectors(dmz->metadata) << 9;
+	ti->max_io_len = dmz_zone_nr_sectors(dmz->metadata);
 	ti->num_flush_bios = 1;
 	ti->num_discard_bios = 1;
 	ti->num_write_zeroes_bios = 1;

drivers/md/dm.c

@@ -1009,6 +1009,7 @@ static void clone_endio(struct bio *bio)
 	struct dm_io *io = tio->io;
 	struct mapped_device *md = tio->io->md;
 	dm_endio_fn endio = tio->ti->type->end_io;
+	struct bio *orig_bio = io->orig_bio;
 
 	if (unlikely(error == BLK_STS_TARGET) && md->type != DM_TYPE_NVME_BIO_BASED) {
 		if (bio_op(bio) == REQ_OP_DISCARD &&
@@ -1022,6 +1023,18 @@ static void clone_endio(struct bio *bio)
 			disable_write_zeroes(md);
 	}
 
+	/*
+	 * For zone-append bios get offset in zone of the written
+	 * sector and add that to the original bio sector pos.
+	 */
+	if (bio_op(orig_bio) == REQ_OP_ZONE_APPEND) {
+		sector_t written_sector = bio->bi_iter.bi_sector;
+		struct request_queue *q = orig_bio->bi_disk->queue;
+		u64 mask = (u64)blk_queue_zone_sectors(q) - 1;
+
+		orig_bio->bi_iter.bi_sector += written_sector & mask;
+	}
+
 	if (endio) {
 		int r = endio(tio->ti, bio, &error);
 		switch (r) {