Merge tag 'for-5.18-rc4-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs fixes from David Sterba:

 - direct IO fixes:

      - restore passing file offset to correctly calculate checksums
        when repairing on read and bio split happens

      - use correct bio when sumitting IO on zoned filesystem

 - zoned mode fixes:

      - fix selection of device to correctly calculate device
        capabilities when allocating a new bio

      - use a dedicated lock for exclusion during relocation

      - fix leaked plug after failure syncing log

 - fix assertion during scrub and relocation

* tag 'for-5.18-rc4-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
  btrfs: zoned: use dedicated lock for data relocation
  btrfs: fix assertion failure during scrub due to block group reallocation
  btrfs: fix direct I/O writes for split bios on zoned devices
  btrfs: fix direct I/O read repair for split bios
  btrfs: fix and document the zoned device choice in alloc_new_bio
  btrfs: fix leaked plug after failure syncing log on zoned filesystems

Author: torvalds

fs/btrfs/ctree.h

@@ -1060,6 +1060,7 @@ struct btrfs_fs_info {
 	 */
 	spinlock_t relocation_bg_lock;
 	u64 data_reloc_bg;
+	struct mutex zoned_data_reloc_io_lock;
 
 	u64 nr_global_roots;
 

fs/btrfs/dev-replace.c

@@ -734,7 +734,12 @@ static int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info,
 
 	btrfs_wait_ordered_roots(fs_info, U64_MAX, 0, (u64)-1);
 
-	/* Commit dev_replace state and reserve 1 item for it. */
+	/*
+	 * Commit dev_replace state and reserve 1 item for it.
+	 * This is crucial to ensure we won't miss copying extents for new block
+	 * groups that are allocated after we started the device replace, and
+	 * must be done after setting up the device replace state.
+	 */
 	trans = btrfs_start_transaction(root, 1);
 	if (IS_ERR(trans)) {
 		ret = PTR_ERR(trans);

fs/btrfs/disk-io.c

@@ -3157,6 +3157,7 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info)
 	mutex_init(&fs_info->reloc_mutex);
 	mutex_init(&fs_info->delalloc_root_mutex);
 	mutex_init(&fs_info->zoned_meta_io_lock);
+	mutex_init(&fs_info->zoned_data_reloc_io_lock);
 	seqlock_init(&fs_info->profiles_lock);
 
 	INIT_LIST_HEAD(&fs_info->dirty_cowonly_roots);

fs/btrfs/extent_io.c

@@ -2658,6 +2658,7 @@ int btrfs_repair_one_sector(struct inode *inode,
 
 	repair_bio = btrfs_bio_alloc(1);
 	repair_bbio = btrfs_bio(repair_bio);
+	repair_bbio->file_offset = start;
 	repair_bio->bi_opf = REQ_OP_READ;
 	repair_bio->bi_end_io = failed_bio->bi_end_io;
 	repair_bio->bi_iter.bi_sector = failrec->logical >> 9;
@@ -3333,24 +3334,37 @@ static int alloc_new_bio(struct btrfs_inode *inode,
 	ret = calc_bio_boundaries(bio_ctrl, inode, file_offset);
 	if (ret < 0)
 		goto error;
-	if (wbc) {
-		struct block_device *bdev;
 
-		bdev = fs_info->fs_devices->latest_dev->bdev;
-		bio_set_dev(bio, bdev);
-		wbc_init_bio(wbc, bio);
-	}
-	if (bio_op(bio) == REQ_OP_ZONE_APPEND) {
-		struct btrfs_device *device;
+	if (wbc) {
+		/*
+		 * For Zone append we need the correct block_device that we are
+		 * going to write to set in the bio to be able to respect the
+		 * hardware limitation.  Look it up here:
+		 */
+		if (bio_op(bio) == REQ_OP_ZONE_APPEND) {
+			struct btrfs_device *dev;
+
+			dev = btrfs_zoned_get_device(fs_info, disk_bytenr,
+						     fs_info->sectorsize);
+			if (IS_ERR(dev)) {
+				ret = PTR_ERR(dev);
+				goto error;
+			}
 
-		device = btrfs_zoned_get_device(fs_info, disk_bytenr,
-						fs_info->sectorsize);
-		if (IS_ERR(device)) {
-			ret = PTR_ERR(device);
-			goto error;
+			bio_set_dev(bio, dev->bdev);
+		} else {
+			/*
+			 * Otherwise pick the last added device to support
+			 * cgroup writeback.  For multi-device file systems this
+			 * means blk-cgroup policies have to always be set on the
+			 * last added/replaced device.  This is a bit odd but has
+			 * been like that for a long time.
+			 */
+			bio_set_dev(bio, fs_info->fs_devices->latest_dev->bdev);
 		}
-
-		btrfs_bio(bio)->device = device;
+		wbc_init_bio(wbc, bio);
+	} else {
+		ASSERT(bio_op(bio) != REQ_OP_ZONE_APPEND);
 	}
 	return 0;
 error:

fs/btrfs/inode.c

@@ -7810,8 +7810,6 @@ static blk_status_t btrfs_check_read_dio_bio(struct btrfs_dio_private *dip,
 	const bool csum = !(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM);
 	struct bio_vec bvec;
 	struct bvec_iter iter;
-	const u64 orig_file_offset = dip->file_offset;
-	u64 start = orig_file_offset;
 	u32 bio_offset = 0;
 	blk_status_t err = BLK_STS_OK;
 
@@ -7821,6 +7819,8 @@ static blk_status_t btrfs_check_read_dio_bio(struct btrfs_dio_private *dip,
 		nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info, bvec.bv_len);
 		pgoff = bvec.bv_offset;
 		for (i = 0; i < nr_sectors; i++) {
+			u64 start = bbio->file_offset + bio_offset;
+
 			ASSERT(pgoff < PAGE_SIZE);
 			if (uptodate &&
 			    (!csum || !check_data_csum(inode, bbio,
@@ -7833,17 +7833,13 @@ static blk_status_t btrfs_check_read_dio_bio(struct btrfs_dio_private *dip,
 			} else {
 				int ret;
 
-				ASSERT((start - orig_file_offset) < UINT_MAX);
-				ret = btrfs_repair_one_sector(inode,
-						&bbio->bio,
-						start - orig_file_offset,
-						bvec.bv_page, pgoff,
+				ret = btrfs_repair_one_sector(inode, &bbio->bio,
+						bio_offset, bvec.bv_page, pgoff,
 						start, bbio->mirror_num,
 						submit_dio_repair_bio);
 				if (ret)
 					err = errno_to_blk_status(ret);
 			}
-			start += sectorsize;
 			ASSERT(bio_offset + sectorsize > bio_offset);
 			bio_offset += sectorsize;
 			pgoff += sectorsize;
@@ -7870,6 +7866,7 @@ static blk_status_t btrfs_submit_bio_start_direct_io(struct inode *inode,
 static void btrfs_end_dio_bio(struct bio *bio)
 {
 	struct btrfs_dio_private *dip = bio->bi_private;
+	struct btrfs_bio *bbio = btrfs_bio(bio);
 	blk_status_t err = bio->bi_status;
 
 	if (err)
@@ -7880,12 +7877,12 @@ static void btrfs_end_dio_bio(struct bio *bio)
 			   bio->bi_iter.bi_size, err);
 
 	if (bio_op(bio) == REQ_OP_READ)
-		err = btrfs_check_read_dio_bio(dip, btrfs_bio(bio), !err);
+		err = btrfs_check_read_dio_bio(dip, bbio, !err);
 
 	if (err)
 		dip->dio_bio->bi_status = err;
 
-	btrfs_record_physical_zoned(dip->inode, dip->file_offset, bio);
+	btrfs_record_physical_zoned(dip->inode, bbio->file_offset, bio);
 
 	bio_put(bio);
 	btrfs_dio_private_put(dip);
@@ -8046,6 +8043,7 @@ static void btrfs_submit_direct(const struct iomap_iter *iter,
 		bio = btrfs_bio_clone_partial(dio_bio, clone_offset, clone_len);
 		bio->bi_private = dip;
 		bio->bi_end_io = btrfs_end_dio_bio;
+		btrfs_bio(bio)->file_offset = file_offset;
 
 		if (bio_op(bio) == REQ_OP_ZONE_APPEND) {
 			status = extract_ordered_extent(BTRFS_I(inode), bio,

fs/btrfs/scrub.c

@@ -3699,6 +3699,31 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
 		if (!cache)
 			goto skip;
 
+		ASSERT(cache->start <= chunk_offset);
+		/*
+		 * We are using the commit root to search for device extents, so
+		 * that means we could have found a device extent item from a
+		 * block group that was deleted in the current transaction. The
+		 * logical start offset of the deleted block group, stored at
+		 * @chunk_offset, might be part of the logical address range of
+		 * a new block group (which uses different physical extents).
+		 * In this case btrfs_lookup_block_group() has returned the new
+		 * block group, and its start address is less than @chunk_offset.
+		 *
+		 * We skip such new block groups, because it's pointless to
+		 * process them, as we won't find their extents because we search
+		 * for them using the commit root of the extent tree. For a device
+		 * replace it's also fine to skip it, we won't miss copying them
+		 * to the target device because we have the write duplication
+		 * setup through the regular write path (by btrfs_map_block()),
+		 * and we have committed a transaction when we started the device
+		 * replace, right after setting up the device replace state.
+		 */
+		if (cache->start < chunk_offset) {
+			btrfs_put_block_group(cache);
+			goto skip;
+		}
+
 		if (sctx->is_dev_replace && btrfs_is_zoned(fs_info)) {
 			spin_lock(&cache->lock);
 			if (!cache->to_copy) {
@@ -3822,7 +3847,6 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
 		dev_replace->item_needs_writeback = 1;
 		up_write(&dev_replace->rwsem);
 
-		ASSERT(cache->start == chunk_offset);
 		ret = scrub_chunk(sctx, cache, scrub_dev, found_key.offset,
 				  dev_extent_len);
 

fs/btrfs/tree-log.c

@@ -3188,6 +3188,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 			ret = btrfs_alloc_log_tree_node(trans, log_root_tree);
 			if (ret) {
 				mutex_unlock(&fs_info->tree_root->log_mutex);
+				blk_finish_plug(&plug);
 				goto out;
 			}
 		}

fs/btrfs/volumes.h

@@ -328,6 +328,9 @@ struct btrfs_fs_devices {
 struct btrfs_bio {
 	unsigned int mirror_num;
 
+	/* for direct I/O */
+	u64 file_offset;
+
 	/* @device is for stripe IO submission. */
 	struct btrfs_device *device;
 	u8 *csum;

fs/btrfs/zoned.h

@@ -359,15 +359,15 @@ static inline void btrfs_zoned_data_reloc_lock(struct btrfs_inode *inode)
 	struct btrfs_root *root = inode->root;
 
 	if (btrfs_is_data_reloc_root(root) && btrfs_is_zoned(root->fs_info))
-		btrfs_inode_lock(&inode->vfs_inode, 0);
+		mutex_lock(&root->fs_info->zoned_data_reloc_io_lock);
 }
 
 static inline void btrfs_zoned_data_reloc_unlock(struct btrfs_inode *inode)
 {
 	struct btrfs_root *root = inode->root;
 
 	if (btrfs_is_data_reloc_root(root) && btrfs_is_zoned(root->fs_info))
-		btrfs_inode_unlock(&inode->vfs_inode, 0);
+		mutex_unlock(&root->fs_info->zoned_data_reloc_io_lock);
 }
 
 #endif