1 files changed, 134 insertions, 123 deletions

diff --git a/drivers/md/dm-zoned-metadata.c b/drivers/md/dm-zoned-metadata.c
index 8545dcee9fd0..516c7b671d25 100644
--- a/drivers/md/dm-zoned-metadata.c
+++ b/drivers/md/dm-zoned-metadata.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2017 Western Digital Corporation or its affiliates.
  *
@@ -34,7 +35,7 @@
  *    (1) Super block (1 block)
  *    (2) Chunk mapping table (nr_map_blocks)
  *    (3) Bitmap blocks (nr_bitmap_blocks)
- * All metadata blocks are stored in conventional zones, starting from the
+ * All metadata blocks are stored in conventional zones, starting from
  * the first conventional zone found on disk.
  */
 struct dmz_super {
@@ -133,6 +134,7 @@ struct dmz_metadata {
 
 	sector_t		zone_bitmap_size;
 	unsigned int		zone_nr_bitmap_blocks;
+	unsigned int		zone_bits_per_mblk;
 
 	unsigned int		nr_bitmap_blocks;
 	unsigned int		nr_map_blocks;
@@ -233,7 +235,7 @@ void dmz_unlock_map(struct dmz_metadata *zmd)
  * Lock/unlock metadata access. This is a "read" lock on a semaphore
  * that prevents metadata flush from running while metadata are being
  * modified. The actual metadata write mutual exclusion is achieved with
- * the map lock and zone styate management (active and reclaim state are
+ * the map lock and zone state management (active and reclaim state are
  * mutually exclusive).
  */
 void dmz_lock_metadata(struct dmz_metadata *zmd)
@@ -402,15 +404,18 @@ static struct dmz_mblock *dmz_get_mblock_slow(struct dmz_metadata *zmd,
 	sector_t block = zmd->sb[zmd->mblk_primary].block + mblk_no;
 	struct bio *bio;
 
+	if (dmz_bdev_is_dying(zmd->dev))
+		return ERR_PTR(-EIO);
+
 	/* Get a new block and a BIO to read it */
 	mblk = dmz_alloc_mblock(zmd, mblk_no);
 	if (!mblk)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	bio = bio_alloc(GFP_NOIO, 1);
 	if (!bio) {
 		dmz_free_mblock(zmd, mblk);
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 	}
 
 	spin_lock(&zmd->mblk_lock);
@@ -541,8 +546,8 @@ static struct dmz_mblock *dmz_get_mblock(struct dmz_metadata *zmd,
 	if (!mblk) {
 		/* Cache miss: read the block from disk */
 		mblk = dmz_get_mblock_slow(zmd, mblk_no);
-		if (!mblk)
-			return ERR_PTR(-ENOMEM);
+		if (IS_ERR(mblk))
+			return mblk;
 	}
 
 	/* Wait for on-going read I/O and check for error */
@@ -550,6 +555,7 @@ static struct dmz_mblock *dmz_get_mblock(struct dmz_metadata *zmd,
 		       TASK_UNINTERRUPTIBLE);
 	if (test_bit(DMZ_META_ERROR, &mblk->state)) {
 		dmz_release_mblock(zmd, mblk);
+		dmz_check_bdev(zmd->dev);
 		return ERR_PTR(-EIO);
 	}
 
@@ -570,16 +576,19 @@ static void dmz_dirty_mblock(struct dmz_metadata *zmd, struct dmz_mblock *mblk)
 /*
  * Issue a metadata block write BIO.
  */
-static void dmz_write_mblock(struct dmz_metadata *zmd, struct dmz_mblock *mblk,
-			     unsigned int set)
+static int dmz_write_mblock(struct dmz_metadata *zmd, struct dmz_mblock *mblk,
+			    unsigned int set)
 {
 	sector_t block = zmd->sb[set].block + mblk->no;
 	struct bio *bio;
 
+	if (dmz_bdev_is_dying(zmd->dev))
+		return -EIO;
+
 	bio = bio_alloc(GFP_NOIO, 1);
 	if (!bio) {
 		set_bit(DMZ_META_ERROR, &mblk->state);
-		return;
+		return -ENOMEM;
 	}
 
 	set_bit(DMZ_META_WRITING, &mblk->state);
@@ -591,6 +600,8 @@ static void dmz_write_mblock(struct dmz_metadata *zmd, struct dmz_mblock *mblk,
 	bio_set_op_attrs(bio, REQ_OP_WRITE, REQ_META | REQ_PRIO);
 	bio_add_page(bio, mblk->page, DMZ_BLOCK_SIZE, 0);
 	submit_bio(bio);
+
+	return 0;
 }
 
 /*
@@ -602,6 +613,9 @@ static int dmz_rdwr_block(struct dmz_metadata *zmd, int op, sector_t block,
 	struct bio *bio;
 	int ret;
 
+	if (dmz_bdev_is_dying(zmd->dev))
+		return -EIO;
+
 	bio = bio_alloc(GFP_NOIO, 1);
 	if (!bio)
 		return -ENOMEM;
@@ -613,6 +627,8 @@ static int dmz_rdwr_block(struct dmz_metadata *zmd, int op, sector_t block,
 	ret = submit_bio_wait(bio);
 	bio_put(bio);
 
+	if (ret)
+		dmz_check_bdev(zmd->dev);
 	return ret;
 }
 
@@ -659,22 +675,30 @@ static int dmz_write_dirty_mblocks(struct dmz_metadata *zmd,
 {
 	struct dmz_mblock *mblk;
 	struct blk_plug plug;
-	int ret = 0;
+	int ret = 0, nr_mblks_submitted = 0;
 
 	/* Issue writes */
 	blk_start_plug(&plug);
-	list_for_each_entry(mblk, write_list, link)
-		dmz_write_mblock(zmd, mblk, set);
+	list_for_each_entry(mblk, write_list, link) {
+		ret = dmz_write_mblock(zmd, mblk, set);
+		if (ret)
+			break;
+		nr_mblks_submitted++;
+	}
 	blk_finish_plug(&plug);
 
 	/* Wait for completion */
 	list_for_each_entry(mblk, write_list, link) {
+		if (!nr_mblks_submitted)
+			break;
 		wait_on_bit_io(&mblk->state, DMZ_META_WRITING,
 			       TASK_UNINTERRUPTIBLE);
 		if (test_bit(DMZ_META_ERROR, &mblk->state)) {
 			clear_bit(DMZ_META_ERROR, &mblk->state);
+			dmz_check_bdev(zmd->dev);
 			ret = -EIO;
 		}
+		nr_mblks_submitted--;
 	}
 
 	/* Flush drive cache (this will also sync data) */
@@ -736,6 +760,11 @@ int dmz_flush_metadata(struct dmz_metadata *zmd)
 	 */
 	dmz_lock_flush(zmd);
 
+	if (dmz_bdev_is_dying(zmd->dev)) {
+		ret = -EIO;
+		goto out;
+	}
+
 	/* Get dirty blocks */
 	spin_lock(&zmd->mblk_lock);
 	list_splice_init(&zmd->mblk_dirty_list, &write_list);
@@ -744,7 +773,7 @@ int dmz_flush_metadata(struct dmz_metadata *zmd)
 	/* If there are no dirty metadata blocks, just flush the device cache */
 	if (list_empty(&write_list)) {
 		ret = blkdev_issue_flush(zmd->dev->bdev, GFP_NOIO, NULL);
-		goto out;
+		goto err;
 	}
 
 	/*
@@ -754,7 +783,7 @@ int dmz_flush_metadata(struct dmz_metadata *zmd)
 	 */
 	ret = dmz_log_dirty_mblocks(zmd, &write_list);
 	if (ret)
-		goto out;
+		goto err;
 
 	/*
 	 * The log is on disk. It is now safe to update in place
@@ -762,11 +791,11 @@ int dmz_flush_metadata(struct dmz_metadata *zmd)
 	 */
 	ret = dmz_write_dirty_mblocks(zmd, &write_list, zmd->mblk_primary);
 	if (ret)
-		goto out;
+		goto err;
 
 	ret = dmz_write_sb(zmd, zmd->mblk_primary);
 	if (ret)
-		goto out;
+		goto err;
 
 	while (!list_empty(&write_list)) {
 		mblk = list_first_entry(&write_list, struct dmz_mblock, link);
@@ -781,16 +810,20 @@ int dmz_flush_metadata(struct dmz_metadata *zmd)
 
 	zmd->sb_gen++;
 out:
-	if (ret && !list_empty(&write_list)) {
-		spin_lock(&zmd->mblk_lock);
-		list_splice(&write_list, &zmd->mblk_dirty_list);
-		spin_unlock(&zmd->mblk_lock);
-	}
-
 	dmz_unlock_flush(zmd);
 	up_write(&zmd->mblk_sem);
 
 	return ret;
+
+err:
+	if (!list_empty(&write_list)) {
+		spin_lock(&zmd->mblk_lock);
+		list_splice(&write_list, &zmd->mblk_dirty_list);
+		spin_unlock(&zmd->mblk_lock);
+	}
+	if (!dmz_check_bdev(zmd->dev))
+		ret = -EIO;
+	goto out;
 }
 
 /*
@@ -1056,9 +1089,10 @@ static int dmz_load_sb(struct dmz_metadata *zmd)
 /*
  * Initialize a zone descriptor.
  */
-static int dmz_init_zone(struct dmz_metadata *zmd, struct dm_zone *zone,
-			 struct blk_zone *blkz)
+static int dmz_init_zone(struct blk_zone *blkz, unsigned int idx, void *data)
 {
+	struct dmz_metadata *zmd = data;
+	struct dm_zone *zone = &zmd->zones[idx];
 	struct dmz_dev *dev = zmd->dev;
 
 	/* Ignore the eventual last runt (smaller) zone */
@@ -1072,26 +1106,29 @@ static int dmz_init_zone(struct dmz_metadata *zmd, struct dm_zone *zone,
 	atomic_set(&zone->refcount, 0);
 	zone->chunk = DMZ_MAP_UNMAPPED;
 
-	if (blkz->type == BLK_ZONE_TYPE_CONVENTIONAL) {
+	switch (blkz->type) {
+	case BLK_ZONE_TYPE_CONVENTIONAL:
 		set_bit(DMZ_RND, &zone->flags);
 		zmd->nr_rnd_zones++;
-	} else if (blkz->type == BLK_ZONE_TYPE_SEQWRITE_REQ ||
-		   blkz->type == BLK_ZONE_TYPE_SEQWRITE_PREF) {
+		break;
+	case BLK_ZONE_TYPE_SEQWRITE_REQ:
+	case BLK_ZONE_TYPE_SEQWRITE_PREF:
 		set_bit(DMZ_SEQ, &zone->flags);
-	} else
+		break;
+	default:
 		return -ENXIO;
-
-	if (blkz->cond == BLK_ZONE_COND_OFFLINE)
-		set_bit(DMZ_OFFLINE, &zone->flags);
-	else if (blkz->cond == BLK_ZONE_COND_READONLY)
-		set_bit(DMZ_READ_ONLY, &zone->flags);
+	}
 
 	if (dmz_is_rnd(zone))
 		zone->wp_block = 0;
 	else
 		zone->wp_block = dmz_sect2blk(blkz->wp - blkz->start);
 
-	if (!dmz_is_offline(zone) && !dmz_is_readonly(zone)) {
+	if (blkz->cond == BLK_ZONE_COND_OFFLINE)
+		set_bit(DMZ_OFFLINE, &zone->flags);
+	else if (blkz->cond == BLK_ZONE_COND_READONLY)
+		set_bit(DMZ_READ_ONLY, &zone->flags);
+	else {
 		zmd->nr_useable_zones++;
 		if (dmz_is_rnd(zone)) {
 			zmd->nr_rnd_zones++;
@@ -1115,27 +1152,20 @@ static void dmz_drop_zones(struct dmz_metadata *zmd)
 }
 
 /*
- * The size of a zone report in number of zones.
- * This results in 4096*64B=256KB report zones commands.
- */
-#define DMZ_REPORT_NR_ZONES	4096
-
-/*
  * Allocate and initialize zone descriptors using the zone
  * information from disk.
  */
 static int dmz_init_zones(struct dmz_metadata *zmd)
 {
 	struct dmz_dev *dev = zmd->dev;
-	struct dm_zone *zone;
-	struct blk_zone *blkz;
-	unsigned int nr_blkz;
-	sector_t sector = 0;
-	int i, ret = 0;
+	int ret;
 
 	/* Init */
 	zmd->zone_bitmap_size = dev->zone_nr_blocks >> 3;
-	zmd->zone_nr_bitmap_blocks = zmd->zone_bitmap_size >> DMZ_BLOCK_SHIFT;
+	zmd->zone_nr_bitmap_blocks =
+		max_t(sector_t, 1, zmd->zone_bitmap_size >> DMZ_BLOCK_SHIFT);
+	zmd->zone_bits_per_mblk = min_t(sector_t, dev->zone_nr_blocks,
+					DMZ_BLOCK_SIZE_BITS);
 
 	/* Allocate zone array */
 	zmd->zones = kcalloc(dev->nr_zones, sizeof(struct dm_zone), GFP_KERNEL);
@@ -1145,54 +1175,38 @@ static int dmz_init_zones(struct dmz_metadata *zmd)
 	dmz_dev_info(dev, "Using %zu B for zone information",
 		     sizeof(struct dm_zone) * dev->nr_zones);
 
-	/* Get zone information */
-	nr_blkz = DMZ_REPORT_NR_ZONES;
-	blkz = kcalloc(nr_blkz, sizeof(struct blk_zone), GFP_KERNEL);
-	if (!blkz) {
-		ret = -ENOMEM;
-		goto out;
-	}
-
 	/*
-	 * Get zone information and initialize zone descriptors.
-	 * At the same time, determine where the super block
-	 * should be: first block of the first randomly writable
-	 * zone.
+	 * Get zone information and initialize zone descriptors.  At the same
+	 * time, determine where the super block should be: first block of the
+	 * first randomly writable zone.
 	 */
-	zone = zmd->zones;
-	while (sector < dev->capacity) {
-		/* Get zone information */
-		nr_blkz = DMZ_REPORT_NR_ZONES;
-		ret = blkdev_report_zones(dev->bdev, sector, blkz, &nr_blkz);
-		if (ret) {
-			dmz_dev_err(dev, "Report zones failed %d", ret);
-			goto out;
-		}
+	ret = blkdev_report_zones(dev->bdev, 0, BLK_ALL_ZONES, dmz_init_zone,
+				  zmd);
+	if (ret < 0) {
+		dmz_drop_zones(zmd);
+		return ret;
+	}
 
-		if (!nr_blkz)
-			break;
+	return 0;
+}
 
-		/* Process report */
-		for (i = 0; i < nr_blkz; i++) {
-			ret = dmz_init_zone(zmd, zone, &blkz[i]);
-			if (ret)
-				goto out;
-			sector += dev->zone_nr_sectors;
-			zone++;
-		}
-	}
+static int dmz_update_zone_cb(struct blk_zone *blkz, unsigned int idx,
+			      void *data)
+{
+	struct dm_zone *zone = data;
 
-	/* The entire zone configuration of the disk should now be known */
-	if (sector < dev->capacity) {
-		dmz_dev_err(dev, "Failed to get correct zone information");
-		ret = -ENXIO;
-	}
-out:
-	kfree(blkz);
-	if (ret)
-		dmz_drop_zones(zmd);
+	clear_bit(DMZ_OFFLINE, &zone->flags);
+	clear_bit(DMZ_READ_ONLY, &zone->flags);
+	if (blkz->cond == BLK_ZONE_COND_OFFLINE)
+		set_bit(DMZ_OFFLINE, &zone->flags);
+	else if (blkz->cond == BLK_ZONE_COND_READONLY)
+		set_bit(DMZ_READ_ONLY, &zone->flags);
 
-	return ret;
+	if (dmz_is_seq(zone))
+		zone->wp_block = dmz_sect2blk(blkz->wp - blkz->start);
+	else
+		zone->wp_block = 0;
+	return 0;
 }
 
 /*
@@ -1200,9 +1214,7 @@ out:
  */
 static int dmz_update_zone(struct dmz_metadata *zmd, struct dm_zone *zone)
 {
-	unsigned int nr_blkz = 1;
 	unsigned int noio_flag;
-	struct blk_zone blkz;
 	int ret;
 
 	/*
@@ -1212,29 +1224,19 @@ static int dmz_update_zone(struct dmz_metadata *zmd, struct dm_zone *zone)
 	 * GFP_NOIO was specified.
 	 */
 	noio_flag = memalloc_noio_save();
-	ret = blkdev_report_zones(zmd->dev->bdev, dmz_start_sect(zmd, zone),
-				  &blkz, &nr_blkz);
+	ret = blkdev_report_zones(zmd->dev->bdev, dmz_start_sect(zmd, zone), 1,
+				  dmz_update_zone_cb, zone);
 	memalloc_noio_restore(noio_flag);
-	if (!nr_blkz)
+
+	if (ret == 0)
 		ret = -EIO;
-	if (ret) {
+	if (ret < 0) {
 		dmz_dev_err(zmd->dev, "Get zone %u report failed",
 			    dmz_id(zmd, zone));
+		dmz_check_bdev(zmd->dev);
 		return ret;
 	}
 
-	clear_bit(DMZ_OFFLINE, &zone->flags);
-	clear_bit(DMZ_READ_ONLY, &zone->flags);
-	if (blkz.cond == BLK_ZONE_COND_OFFLINE)
-		set_bit(DMZ_OFFLINE, &zone->flags);
-	else if (blkz.cond == BLK_ZONE_COND_READONLY)
-		set_bit(DMZ_READ_ONLY, &zone->flags);
-
-	if (dmz_is_seq(zone))
-		zone->wp_block = dmz_sect2blk(blkz.wp - blkz.start);
-	else
-		zone->wp_block = 0;
-
 	return 0;
 }
 
@@ -1288,9 +1290,9 @@ static int dmz_reset_zone(struct dmz_metadata *zmd, struct dm_zone *zone)
 	if (!dmz_is_empty(zone) || dmz_seq_write_err(zone)) {
 		struct dmz_dev *dev = zmd->dev;
 
-		ret = blkdev_reset_zones(dev->bdev,
-					 dmz_start_sect(zmd, zone),
-					 dev->zone_nr_sectors, GFP_NOIO);
+		ret = blkdev_zone_mgmt(dev->bdev, REQ_OP_ZONE_RESET,
+				       dmz_start_sect(zmd, zone),
+				       dev->zone_nr_sectors, GFP_NOIO);
 		if (ret) {
 			dmz_dev_err(dev, "Reset zone %u failed %d",
 				    dmz_id(zmd, zone), ret);
@@ -1542,7 +1544,7 @@ static struct dm_zone *dmz_get_rnd_zone_for_reclaim(struct dmz_metadata *zmd)
 	struct dm_zone *zone;
 
 	if (list_empty(&zmd->map_rnd_list))
-		return NULL;
+		return ERR_PTR(-EBUSY);
 
 	list_for_each_entry(zone, &zmd->map_rnd_list, link) {
 		if (dmz_is_buf(zone))
@@ -1553,7 +1555,7 @@ static struct dm_zone *dmz_get_rnd_zone_for_reclaim(struct dmz_metadata *zmd)
 			return dzone;
 	}
 
-	return NULL;
+	return ERR_PTR(-EBUSY);
 }
 
 /*
@@ -1564,7 +1566,7 @@ static struct dm_zone *dmz_get_seq_zone_for_reclaim(struct dmz_metadata *zmd)
 	struct dm_zone *zone;
 
 	if (list_empty(&zmd->map_seq_list))
-		return NULL;
+		return ERR_PTR(-EBUSY);
 
 	list_for_each_entry(zone, &zmd->map_seq_list, link) {
 		if (!zone->bzone)
@@ -1573,7 +1575,7 @@ static struct dm_zone *dmz_get_seq_zone_for_reclaim(struct dmz_metadata *zmd)
 			return zone;
 	}
 
-	return NULL;
+	return ERR_PTR(-EBUSY);
 }
 
 /*
@@ -1628,9 +1630,13 @@ again:
 		if (op != REQ_OP_WRITE)
 			goto out;
 
-		/* Alloate a random zone */
+		/* Allocate a random zone */
 		dzone = dmz_alloc_zone(zmd, DMZ_ALLOC_RND);
 		if (!dzone) {
+			if (dmz_bdev_is_dying(zmd->dev)) {
+				dzone = ERR_PTR(-EIO);
+				goto out;
+			}
 			dmz_wait_for_free_zones(zmd);
 			goto again;
 		}
@@ -1725,9 +1731,13 @@ again:
 	if (bzone)
 		goto out;
 
-	/* Alloate a random zone */
+	/* Allocate a random zone */
 	bzone = dmz_alloc_zone(zmd, DMZ_ALLOC_RND);
 	if (!bzone) {
+		if (dmz_bdev_is_dying(zmd->dev)) {
+			bzone = ERR_PTR(-EIO);
+			goto out;
+		}
 		dmz_wait_for_free_zones(zmd);
 		goto again;
 	}
@@ -1950,7 +1960,7 @@ int dmz_copy_valid_blocks(struct dmz_metadata *zmd, struct dm_zone *from_zone,
 		dmz_release_mblock(zmd, to_mblk);
 		dmz_release_mblock(zmd, from_mblk);
 
-		chunk_block += DMZ_BLOCK_SIZE_BITS;
+		chunk_block += zmd->zone_bits_per_mblk;
 	}
 
 	to_zone->weight = from_zone->weight;
@@ -2011,7 +2021,7 @@ int dmz_validate_blocks(struct dmz_metadata *zmd, struct dm_zone *zone,
 
 		/* Set bits */
 		bit = chunk_block & DMZ_BLOCK_MASK_BITS;
-		nr_bits = min(nr_blocks, DMZ_BLOCK_SIZE_BITS - bit);
+		nr_bits = min(nr_blocks, zmd->zone_bits_per_mblk - bit);
 
 		count = dmz_set_bits((unsigned long *)mblk->data, bit, nr_bits);
 		if (count) {
@@ -2090,7 +2100,7 @@ int dmz_invalidate_blocks(struct dmz_metadata *zmd, struct dm_zone *zone,
 
 		/* Clear bits */
 		bit = chunk_block & DMZ_BLOCK_MASK_BITS;
-		nr_bits = min(nr_blocks, DMZ_BLOCK_SIZE_BITS - bit);
+		nr_bits = min(nr_blocks, zmd->zone_bits_per_mblk - bit);
 
 		count = dmz_clear_bits((unsigned long *)mblk->data,
 				       bit, nr_bits);
@@ -2150,6 +2160,7 @@ static int dmz_to_next_set_block(struct dmz_metadata *zmd, struct dm_zone *zone,
 {
 	struct dmz_mblock *mblk;
 	unsigned int bit, set_bit, nr_bits;
+	unsigned int zone_bits = zmd->zone_bits_per_mblk;
 	unsigned long *bitmap;
 	int n = 0;
 
@@ -2164,15 +2175,15 @@ static int dmz_to_next_set_block(struct dmz_metadata *zmd, struct dm_zone *zone,
 		/* Get offset */
 		bitmap = (unsigned long *) mblk->data;
 		bit = chunk_block & DMZ_BLOCK_MASK_BITS;
-		nr_bits = min(nr_blocks, DMZ_BLOCK_SIZE_BITS - bit);
+		nr_bits = min(nr_blocks, zone_bits - bit);
 		if (set)
-			set_bit = find_next_bit(bitmap, DMZ_BLOCK_SIZE_BITS, bit);
+			set_bit = find_next_bit(bitmap, zone_bits, bit);
 		else
-			set_bit = find_next_zero_bit(bitmap, DMZ_BLOCK_SIZE_BITS, bit);
+			set_bit = find_next_zero_bit(bitmap, zone_bits, bit);
 		dmz_release_mblock(zmd, mblk);
 
 		n += set_bit - bit;
-		if (set_bit < DMZ_BLOCK_SIZE_BITS)
+		if (set_bit < zone_bits)
 			break;
 
 		nr_blocks -= nr_bits;
@@ -2275,7 +2286,7 @@ static void dmz_get_zone_weight(struct dmz_metadata *zmd, struct dm_zone *zone)
 		/* Count bits in this block */
 		bitmap = mblk->data;
 		bit = chunk_block & DMZ_BLOCK_MASK_BITS;
-		nr_bits = min(nr_blocks, DMZ_BLOCK_SIZE_BITS - bit);
+		nr_bits = min(nr_blocks, zmd->zone_bits_per_mblk - bit);
 		n += dmz_count_bits(bitmap, bit, nr_bits);
 
 		dmz_release_mblock(zmd, mblk);