Merge tag 'for-6.3-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs updates from David Sterba:
 "The usual mix of performance improvements and new features.

  The core change is reworking how checksums are processed, with
  followup cleanups and simplifications. There are two minor changes in
  block layer and iomap code.

  Features:

   - block group allocation class heuristics:
      - pack files by size (up to 128k, up to 8M, more) to avoid
        fragmentation in block groups, assuming that file size and life
        time is correlated, in particular this may help during balance
      - with tracepoints and extensible in the future

  Performance:

   - send: cache directory utimes and only emit the command when
     necessary
      - speedup up to 10x
      - smaller final stream produced (no redundant utimes commands
        issued)
      - compatibility not affected

   - fiemap: skip backref checks for shared leaves
      - speedup 3x on sample filesystem with all leaves shared (e.g. on
        snapshots)

   - micro optimized b-tree key lookup, speedup in metadata operations
     (sample benchmark: fs_mark +10% of files/sec)

  Core changes:

   - change where checksumming is done in the io path:
      - checksum and read repair does verification at lower layer
      - cascaded cleanups and simplifications

   - raid56 refactoring and cleanups

  Fixes:

   - sysfs: make sure that a run-time change of a feature is correctly
     tracked by the feature files

   - scrub: better reporting of tree block errors

  Other:

   - locally enable -Wmaybe-uninitialized after fixing all warnings

   - misc cleanups, spelling fixes

  Other code:

   - block: export bio_split_rw

   - iomap: remove IOMAP_F_ZONE_APPEND"

* tag 'for-6.3-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (109 commits)
  btrfs: make kobj_type structures constant
  btrfs: remove the bdev argument to btrfs_rmap_block
  btrfs: don't rely on unchanging ->bi_bdev for zone append remaps
  btrfs: never return true for reads in btrfs_use_zone_append
  btrfs: pass a btrfs_bio to btrfs_use_append
  btrfs: set bbio->file_offset in alloc_new_bio
  btrfs: use file_offset to limit bios size in calc_bio_boundaries
  btrfs: do unsigned integer division in the extent buffer binary search loop
  btrfs: eliminate extra call when doing binary search on extent buffer
  btrfs: raid56: handle endio in scrub_rbio
  btrfs: raid56: handle endio in recover_rbio
  btrfs: raid56: handle endio in rmw_rbio
  btrfs: raid56: submit the read bios from scrub_assemble_read_bios
  btrfs: raid56: fold rmw_read_wait_recover into rmw_read_bios
  btrfs: raid56: fold recover_assemble_read_bios into recover_rbio
  btrfs: raid56: add a bio_list_put helper
  btrfs: raid56: wait for I/O completion in submit_read_bios
  btrfs: raid56: simplify code flow in rmw_rbio
  btrfs: raid56: simplify error handling and code flow in raid56_parity_write
  btrfs: replace btrfs_wait_tree_block_writeback by wait_on_extent_buffer_writeback
  ...

1 files changed, 69 insertions, 513 deletions

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 3bbf8703db2a..c25fa74d7615 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -36,6 +36,7 @@
 #include "file.h"
 #include "dev-replace.h"
 #include "super.h"
+#include "transaction.h"
 
 static struct kmem_cache *extent_buffer_cache;
 
@@ -99,7 +100,6 @@ struct btrfs_bio_ctrl {
 	struct bio *bio;
 	int mirror_num;
 	enum btrfs_compression_type compress_type;
-	u32 len_to_stripe_boundary;
 	u32 len_to_oe_boundary;
 	btrfs_bio_end_io_t end_io_func;
 
@@ -126,7 +126,7 @@ static void submit_one_bio(struct btrfs_bio_ctrl *bio_ctrl)
 {
 	struct bio *bio;
 	struct bio_vec *bv;
-	struct btrfs_inode *inode;
+	struct inode *inode;
 	int mirror_num;
 
 	if (!bio_ctrl->bio)
@@ -134,15 +134,13 @@ static void submit_one_bio(struct btrfs_bio_ctrl *bio_ctrl)
 
 	bio = bio_ctrl->bio;
 	bv = bio_first_bvec_all(bio);
-	inode = BTRFS_I(bv->bv_page->mapping->host);
+	inode = bv->bv_page->mapping->host;
 	mirror_num = bio_ctrl->mirror_num;
 
 	/* Caller should ensure the bio has at least some range added */
 	ASSERT(bio->bi_iter.bi_size);
 
-	btrfs_bio(bio)->file_offset = page_offset(bv->bv_page) + bv->bv_offset;
-
-	if (!is_data_inode(&inode->vfs_inode)) {
+	if (!is_data_inode(inode)) {
 		if (btrfs_op(bio) != BTRFS_MAP_WRITE) {
 			/*
 			 * For metadata read, we should have the parent_check,
@@ -153,14 +151,15 @@ static void submit_one_bio(struct btrfs_bio_ctrl *bio_ctrl)
 			       bio_ctrl->parent_check,
 			       sizeof(struct btrfs_tree_parent_check));
 		}
-		btrfs_submit_metadata_bio(inode, bio, mirror_num);
-	} else if (btrfs_op(bio) == BTRFS_MAP_WRITE) {
-		btrfs_submit_data_write_bio(inode, bio, mirror_num);
-	} else {
-		btrfs_submit_data_read_bio(inode, bio, mirror_num,
-					   bio_ctrl->compress_type);
+		bio->bi_opf |= REQ_META;
 	}
 
+	if (btrfs_op(bio) == BTRFS_MAP_READ &&
+	    bio_ctrl->compress_type != BTRFS_COMPRESS_NONE)
+		btrfs_submit_compressed_read(inode, bio, mirror_num);
+	else
+		btrfs_submit_bio(bio, mirror_num);
+
 	/* The bio is owned by the end_io handler now */
 	bio_ctrl->bio = NULL;
 }
@@ -515,266 +514,6 @@ void extent_clear_unlock_delalloc(struct btrfs_inode *inode, u64 start, u64 end,
 			       start, end, page_ops, NULL);
 }
 
-static int insert_failrec(struct btrfs_inode *inode,
-			  struct io_failure_record *failrec)
-{
-	struct rb_node *exist;
-
-	spin_lock(&inode->io_failure_lock);
-	exist = rb_simple_insert(&inode->io_failure_tree, failrec->bytenr,
-				 &failrec->rb_node);
-	spin_unlock(&inode->io_failure_lock);
-
-	return (exist == NULL) ? 0 : -EEXIST;
-}
-
-static struct io_failure_record *get_failrec(struct btrfs_inode *inode, u64 start)
-{
-	struct rb_node *node;
-	struct io_failure_record *failrec = ERR_PTR(-ENOENT);
-
-	spin_lock(&inode->io_failure_lock);
-	node = rb_simple_search(&inode->io_failure_tree, start);
-	if (node)
-		failrec = rb_entry(node, struct io_failure_record, rb_node);
-	spin_unlock(&inode->io_failure_lock);
-	return failrec;
-}
-
-static void free_io_failure(struct btrfs_inode *inode,
-			    struct io_failure_record *rec)
-{
-	spin_lock(&inode->io_failure_lock);
-	rb_erase(&rec->rb_node, &inode->io_failure_tree);
-	spin_unlock(&inode->io_failure_lock);
-
-	kfree(rec);
-}
-
-static int next_mirror(const struct io_failure_record *failrec, int cur_mirror)
-{
-	if (cur_mirror == failrec->num_copies)
-		return cur_mirror + 1 - failrec->num_copies;
-	return cur_mirror + 1;
-}
-
-static int prev_mirror(const struct io_failure_record *failrec, int cur_mirror)
-{
-	if (cur_mirror == 1)
-		return failrec->num_copies;
-	return cur_mirror - 1;
-}
-
-/*
- * each time an IO finishes, we do a fast check in the IO failure tree
- * to see if we need to process or clean up an io_failure_record
- */
-int btrfs_clean_io_failure(struct btrfs_inode *inode, u64 start,
-			   struct page *page, unsigned int pg_offset)
-{
-	struct btrfs_fs_info *fs_info = inode->root->fs_info;
-	struct extent_io_tree *io_tree = &inode->io_tree;
-	u64 ino = btrfs_ino(inode);
-	u64 locked_start, locked_end;
-	struct io_failure_record *failrec;
-	int mirror;
-	int ret;
-
-	failrec = get_failrec(inode, start);
-	if (IS_ERR(failrec))
-		return 0;
-
-	BUG_ON(!failrec->this_mirror);
-
-	if (sb_rdonly(fs_info->sb))
-		goto out;
-
-	ret = find_first_extent_bit(io_tree, failrec->bytenr, &locked_start,
-				    &locked_end, EXTENT_LOCKED, NULL);
-	if (ret || locked_start > failrec->bytenr ||
-	    locked_end < failrec->bytenr + failrec->len - 1)
-		goto out;
-
-	mirror = failrec->this_mirror;
-	do {
-		mirror = prev_mirror(failrec, mirror);
-		btrfs_repair_io_failure(fs_info, ino, start, failrec->len,
-				  failrec->logical, page, pg_offset, mirror);
-	} while (mirror != failrec->failed_mirror);
-
-out:
-	free_io_failure(inode, failrec);
-	return 0;
-}
-
-/*
- * Can be called when
- * - hold extent lock
- * - under ordered extent
- * - the inode is freeing
- */
-void btrfs_free_io_failure_record(struct btrfs_inode *inode, u64 start, u64 end)
-{
-	struct io_failure_record *failrec;
-	struct rb_node *node, *next;
-
-	if (RB_EMPTY_ROOT(&inode->io_failure_tree))
-		return;
-
-	spin_lock(&inode->io_failure_lock);
-	node = rb_simple_search_first(&inode->io_failure_tree, start);
-	while (node) {
-		failrec = rb_entry(node, struct io_failure_record, rb_node);
-		if (failrec->bytenr > end)
-			break;
-
-		next = rb_next(node);
-		rb_erase(&failrec->rb_node, &inode->io_failure_tree);
-		kfree(failrec);
-
-		node = next;
-	}
-	spin_unlock(&inode->io_failure_lock);
-}
-
-static struct io_failure_record *btrfs_get_io_failure_record(struct inode *inode,
-							     struct btrfs_bio *bbio,
-							     unsigned int bio_offset)
-{
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
-	u64 start = bbio->file_offset + bio_offset;
-	struct io_failure_record *failrec;
-	const u32 sectorsize = fs_info->sectorsize;
-	int ret;
-
-	failrec = get_failrec(BTRFS_I(inode), start);
-	if (!IS_ERR(failrec)) {
-		btrfs_debug(fs_info,
-	"Get IO Failure Record: (found) logical=%llu, start=%llu, len=%llu",
-			failrec->logical, failrec->bytenr, failrec->len);
-		/*
-		 * when data can be on disk more than twice, add to failrec here
-		 * (e.g. with a list for failed_mirror) to make
-		 * clean_io_failure() clean all those errors at once.
-		 */
-		ASSERT(failrec->this_mirror == bbio->mirror_num);
-		ASSERT(failrec->len == fs_info->sectorsize);
-		return failrec;
-	}
-
-	failrec = kzalloc(sizeof(*failrec), GFP_NOFS);
-	if (!failrec)
-		return ERR_PTR(-ENOMEM);
-
-	RB_CLEAR_NODE(&failrec->rb_node);
-	failrec->bytenr = start;
-	failrec->len = sectorsize;
-	failrec->failed_mirror = bbio->mirror_num;
-	failrec->this_mirror = bbio->mirror_num;
-	failrec->logical = (bbio->iter.bi_sector << SECTOR_SHIFT) + bio_offset;
-
-	btrfs_debug(fs_info,
-		    "new io failure record logical %llu start %llu",
-		    failrec->logical, start);
-
-	failrec->num_copies = btrfs_num_copies(fs_info, failrec->logical, sectorsize);
-	if (failrec->num_copies == 1) {
-		/*
-		 * We only have a single copy of the data, so don't bother with
-		 * all the retry and error correction code that follows. No
-		 * matter what the error is, it is very likely to persist.
-		 */
-		btrfs_debug(fs_info,
-			"cannot repair logical %llu num_copies %d",
-			failrec->logical, failrec->num_copies);
-		kfree(failrec);
-		return ERR_PTR(-EIO);
-	}
-
-	/* Set the bits in the private failure tree */
-	ret = insert_failrec(BTRFS_I(inode), failrec);
-	if (ret) {
-		kfree(failrec);
-		return ERR_PTR(ret);
-	}
-
-	return failrec;
-}
-
-int btrfs_repair_one_sector(struct btrfs_inode *inode, struct btrfs_bio *failed_bbio,
-			    u32 bio_offset, struct page *page, unsigned int pgoff,
-			    bool submit_buffered)
-{
-	u64 start = failed_bbio->file_offset + bio_offset;
-	struct io_failure_record *failrec;
-	struct btrfs_fs_info *fs_info = inode->root->fs_info;
-	struct bio *failed_bio = &failed_bbio->bio;
-	const int icsum = bio_offset >> fs_info->sectorsize_bits;
-	struct bio *repair_bio;
-	struct btrfs_bio *repair_bbio;
-
-	btrfs_debug(fs_info,
-		   "repair read error: read error at %llu", start);
-
-	BUG_ON(bio_op(failed_bio) == REQ_OP_WRITE);
-
-	failrec = btrfs_get_io_failure_record(&inode->vfs_inode, failed_bbio, bio_offset);
-	if (IS_ERR(failrec))
-		return PTR_ERR(failrec);
-
-	/*
-	 * There are two premises:
-	 * a) deliver good data to the caller
-	 * b) correct the bad sectors on disk
-	 *
-	 * Since we're only doing repair for one sector, we only need to get
-	 * a good copy of the failed sector and if we succeed, we have setup
-	 * everything for btrfs_repair_io_failure to do the rest for us.
-	 */
-	failrec->this_mirror = next_mirror(failrec, failrec->this_mirror);
-	if (failrec->this_mirror == failrec->failed_mirror) {
-		btrfs_debug(fs_info,
-			"failed to repair num_copies %d this_mirror %d failed_mirror %d",
-			failrec->num_copies, failrec->this_mirror, failrec->failed_mirror);
-		free_io_failure(inode, failrec);
-		return -EIO;
-	}
-
-	repair_bio = btrfs_bio_alloc(1, REQ_OP_READ, failed_bbio->end_io,
-				     failed_bbio->private);
-	repair_bbio = btrfs_bio(repair_bio);
-	repair_bbio->file_offset = start;
-	repair_bio->bi_iter.bi_sector = failrec->logical >> 9;
-
-	if (failed_bbio->csum) {
-		const u32 csum_size = fs_info->csum_size;
-
-		repair_bbio->csum = repair_bbio->csum_inline;
-		memcpy(repair_bbio->csum,
-		       failed_bbio->csum + csum_size * icsum, csum_size);
-	}
-
-	bio_add_page(repair_bio, page, failrec->len, pgoff);
-	repair_bbio->iter = repair_bio->bi_iter;
-
-	btrfs_debug(fs_info,
-		    "repair read error: submitting new read to mirror %d",
-		    failrec->this_mirror);
-
-	/*
-	 * At this point we have a bio, so any errors from bio submission will
-	 * be handled by the endio on the repair_bio, so we can't return an
-	 * error here.
-	 */
-	if (submit_buffered)
-		btrfs_submit_data_read_bio(inode, repair_bio,
-					   failrec->this_mirror, 0);
-	else
-		btrfs_submit_dio_repair_bio(inode, repair_bio, failrec->this_mirror);
-
-	return BLK_STS_OK;
-}
-
 static void end_page_read(struct page *page, bool uptodate, u64 start, u32 len)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(page->mapping->host->i_sb);
@@ -803,79 +542,6 @@ static void end_page_read(struct page *page, bool uptodate, u64 start, u32 len)
 		btrfs_subpage_end_reader(fs_info, page, start, len);
 }
 
-static void end_sector_io(struct page *page, u64 offset, bool uptodate)
-{
-	struct btrfs_inode *inode = BTRFS_I(page->mapping->host);
-	const u32 sectorsize = inode->root->fs_info->sectorsize;
-
-	end_page_read(page, uptodate, offset, sectorsize);
-	unlock_extent(&inode->io_tree, offset, offset + sectorsize - 1, NULL);
-}
-
-static void submit_data_read_repair(struct inode *inode,
-				    struct btrfs_bio *failed_bbio,
-				    u32 bio_offset, const struct bio_vec *bvec,
-				    unsigned int error_bitmap)
-{
-	const unsigned int pgoff = bvec->bv_offset;
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
-	struct page *page = bvec->bv_page;
-	const u64 start = page_offset(bvec->bv_page) + bvec->bv_offset;
-	const u64 end = start + bvec->bv_len - 1;
-	const u32 sectorsize = fs_info->sectorsize;
-	const int nr_bits = (end + 1 - start) >> fs_info->sectorsize_bits;
-	int i;
-
-	BUG_ON(bio_op(&failed_bbio->bio) == REQ_OP_WRITE);
-
-	/* This repair is only for data */
-	ASSERT(is_data_inode(inode));
-
-	/* We're here because we had some read errors or csum mismatch */
-	ASSERT(error_bitmap);
-
-	/*
-	 * We only get called on buffered IO, thus page must be mapped and bio
-	 * must not be cloned.
-	 */
-	ASSERT(page->mapping && !bio_flagged(&failed_bbio->bio, BIO_CLONED));
-
-	/* Iterate through all the sectors in the range */
-	for (i = 0; i < nr_bits; i++) {
-		const unsigned int offset = i * sectorsize;
-		bool uptodate = false;
-		int ret;
-
-		if (!(error_bitmap & (1U << i))) {
-			/*
-			 * This sector has no error, just end the page read
-			 * and unlock the range.
-			 */
-			uptodate = true;
-			goto next;
-		}
-
-		ret = btrfs_repair_one_sector(BTRFS_I(inode), failed_bbio,
-				bio_offset + offset, page, pgoff + offset,
-				true);
-		if (!ret) {
-			/*
-			 * We have submitted the read repair, the page release
-			 * will be handled by the endio function of the
-			 * submitted repair bio.
-			 * Thus we don't need to do any thing here.
-			 */
-			continue;
-		}
-		/*
-		 * Continue on failed repair, otherwise the remaining sectors
-		 * will not be properly unlocked.
-		 */
-next:
-		end_sector_io(page, start + offset, uptodate);
-	}
-}
-
 /* lots and lots of room for performance fixes in the end_bio funcs */
 
 void end_extent_writepage(struct page *page, int err, u64 start, u64 end)
@@ -919,7 +585,6 @@ static void end_bio_extent_writepage(struct btrfs_bio *bbio)
 	u64 start;
 	u64 end;
 	struct bvec_iter_all iter_all;
-	bool first_bvec = true;
 
 	ASSERT(!bio_flagged(bio, BIO_CLONED));
 	bio_for_each_segment_all(bvec, bio, iter_all) {
@@ -941,11 +606,6 @@ static void end_bio_extent_writepage(struct btrfs_bio *bbio)
 		start = page_offset(page) + bvec->bv_offset;
 		end = start + bvec->bv_len - 1;
 
-		if (first_bvec) {
-			btrfs_record_physical_zoned(inode, start, bio);
-			first_bvec = false;
-		}
-
 		end_extent_writepage(page, error, start, end);
 
 		btrfs_page_clear_writeback(fs_info, page, start, bvec->bv_len);
@@ -1093,8 +753,6 @@ static void end_bio_extent_readpage(struct btrfs_bio *bbio)
 		struct inode *inode = page->mapping->host;
 		struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 		const u32 sectorsize = fs_info->sectorsize;
-		unsigned int error_bitmap = (unsigned int)-1;
-		bool repair = false;
 		u64 start;
 		u64 end;
 		u32 len;
@@ -1126,25 +784,14 @@ static void end_bio_extent_readpage(struct btrfs_bio *bbio)
 		len = bvec->bv_len;
 
 		mirror = bbio->mirror_num;
-		if (likely(uptodate)) {
-			if (is_data_inode(inode)) {
-				error_bitmap = btrfs_verify_data_csum(bbio,
-						bio_offset, page, start, end);
-				if (error_bitmap)
-					uptodate = false;
-			} else {
-				if (btrfs_validate_metadata_buffer(bbio,
-						page, start, end, mirror))
-					uptodate = false;
-			}
-		}
+		if (uptodate && !is_data_inode(inode) &&
+		    btrfs_validate_metadata_buffer(bbio, page, start, end, mirror))
+			uptodate = false;
 
 		if (likely(uptodate)) {
 			loff_t i_size = i_size_read(inode);
 			pgoff_t end_index = i_size >> PAGE_SHIFT;
 
-			btrfs_clean_io_failure(BTRFS_I(inode), start, page, 0);
-
 			/*
 			 * Zero out the remaining part if this range straddles
 			 * i_size.
@@ -1161,19 +808,7 @@ static void end_bio_extent_readpage(struct btrfs_bio *bbio)
 				zero_user_segment(page, zero_start,
 						  offset_in_page(end) + 1);
 			}
-		} else if (is_data_inode(inode)) {
-			/*
-			 * Only try to repair bios that actually made it to a
-			 * device.  If the bio failed to be submitted mirror
-			 * is 0 and we need to fail it without retrying.
-			 *
-			 * This also includes the high level bios for compressed
-			 * extents - these never make it to a device and repair
-			 * is already handled on the lower compressed bio.
-			 */
-			if (mirror > 0)
-				repair = true;
-		} else {
+		} else if (!is_data_inode(inode)) {
 			struct extent_buffer *eb;
 
 			eb = find_extent_buffer_readpage(fs_info, page, start);
@@ -1182,19 +817,10 @@ static void end_bio_extent_readpage(struct btrfs_bio *bbio)
 			atomic_dec(&eb->io_pages);
 		}
 
-		if (repair) {
-			/*
-			 * submit_data_read_repair() will handle all the good
-			 * and bad sectors, we just continue to the next bvec.
-			 */
-			submit_data_read_repair(inode, bbio, bio_offset, bvec,
-						error_bitmap);
-		} else {
-			/* Update page status and unlock */
-			end_page_read(page, uptodate, start, len);
-			endio_readpage_release_extent(&processed, BTRFS_I(inode),
-					start, end, PageUptodate(page));
-		}
+		/* Update page status and unlock. */
+		end_page_read(page, uptodate, start, len);
+		endio_readpage_release_extent(&processed, BTRFS_I(inode),
+					      start, end, PageUptodate(page));
 
 		ASSERT(bio_offset + len > bio_offset);
 		bio_offset += len;
@@ -1202,7 +828,6 @@ static void end_bio_extent_readpage(struct btrfs_bio *bbio)
 	}
 	/* Release the last extent */
 	endio_readpage_release_extent(&processed, NULL, 0, 0, false);
-	btrfs_bio_free_csum(bbio);
 	bio_put(bio);
 }
 
@@ -1270,11 +895,10 @@ static int btrfs_bio_add_page(struct btrfs_bio_ctrl *bio_ctrl,
 	u32 real_size;
 	const sector_t sector = disk_bytenr >> SECTOR_SHIFT;
 	bool contig = false;
-	int ret;
 
 	ASSERT(bio);
 	/* The limit should be calculated when bio_ctrl->bio is allocated */
-	ASSERT(bio_ctrl->len_to_oe_boundary && bio_ctrl->len_to_stripe_boundary);
+	ASSERT(bio_ctrl->len_to_oe_boundary);
 	if (bio_ctrl->compress_type != compress_type)
 		return 0;
 
@@ -1310,9 +934,7 @@ static int btrfs_bio_add_page(struct btrfs_bio_ctrl *bio_ctrl,
 	if (!contig)
 		return 0;
 
-	real_size = min(bio_ctrl->len_to_oe_boundary,
-			bio_ctrl->len_to_stripe_boundary) - bio_size;
-	real_size = min(real_size, size);
+	real_size = min(bio_ctrl->len_to_oe_boundary - bio_size, size);
 
 	/*
 	 * If real_size is 0, never call bio_add_*_page(), as even size is 0,
@@ -1321,82 +943,45 @@ static int btrfs_bio_add_page(struct btrfs_bio_ctrl *bio_ctrl,
 	if (real_size == 0)
 		return 0;
 
-	if (bio_op(bio) == REQ_OP_ZONE_APPEND)
-		ret = bio_add_zone_append_page(bio, page, real_size, pg_offset);
-	else
-		ret = bio_add_page(bio, page, real_size, pg_offset);
-
-	return ret;
+	return bio_add_page(bio, page, real_size, pg_offset);
 }
 
-static int calc_bio_boundaries(struct btrfs_bio_ctrl *bio_ctrl,
-			       struct btrfs_inode *inode, u64 file_offset)
+static void calc_bio_boundaries(struct btrfs_bio_ctrl *bio_ctrl,
+				struct btrfs_inode *inode, u64 file_offset)
 {
-	struct btrfs_fs_info *fs_info = inode->root->fs_info;
-	struct btrfs_io_geometry geom;
 	struct btrfs_ordered_extent *ordered;
-	struct extent_map *em;
-	u64 logical = (bio_ctrl->bio->bi_iter.bi_sector << SECTOR_SHIFT);
-	int ret;
 
 	/*
-	 * Pages for compressed extent are never submitted to disk directly,
-	 * thus it has no real boundary, just set them to U32_MAX.
-	 *
-	 * The split happens for real compressed bio, which happens in
-	 * btrfs_submit_compressed_read/write().
+	 * Limit the extent to the ordered boundary for Zone Append.
+	 * Compressed bios aren't submitted directly, so it doesn't apply to
+	 * them.
 	 */
-	if (bio_ctrl->compress_type != BTRFS_COMPRESS_NONE) {
-		bio_ctrl->len_to_oe_boundary = U32_MAX;
-		bio_ctrl->len_to_stripe_boundary = U32_MAX;
-		return 0;
-	}
-	em = btrfs_get_chunk_map(fs_info, logical, fs_info->sectorsize);
-	if (IS_ERR(em))
-		return PTR_ERR(em);
-	ret = btrfs_get_io_geometry(fs_info, em, btrfs_op(bio_ctrl->bio),
-				    logical, &geom);
-	free_extent_map(em);
-	if (ret < 0) {
-		return ret;
-	}
-	if (geom.len > U32_MAX)
-		bio_ctrl->len_to_stripe_boundary = U32_MAX;
-	else
-		bio_ctrl->len_to_stripe_boundary = (u32)geom.len;
-
-	if (bio_op(bio_ctrl->bio) != REQ_OP_ZONE_APPEND) {
-		bio_ctrl->len_to_oe_boundary = U32_MAX;
-		return 0;
-	}
-
-	/* Ordered extent not yet created, so we're good */
-	ordered = btrfs_lookup_ordered_extent(inode, file_offset);
-	if (!ordered) {
-		bio_ctrl->len_to_oe_boundary = U32_MAX;
-		return 0;
+	if (bio_ctrl->compress_type == BTRFS_COMPRESS_NONE &&
+	    btrfs_use_zone_append(btrfs_bio(bio_ctrl->bio))) {
+		ordered = btrfs_lookup_ordered_extent(inode, file_offset);
+		if (ordered) {
+			bio_ctrl->len_to_oe_boundary = min_t(u32, U32_MAX,
+					ordered->file_offset +
+					ordered->disk_num_bytes - file_offset);
+			btrfs_put_ordered_extent(ordered);
+			return;
+		}
 	}
 
-	bio_ctrl->len_to_oe_boundary = min_t(u32, U32_MAX,
-		ordered->disk_bytenr + ordered->disk_num_bytes - logical);
-	btrfs_put_ordered_extent(ordered);
-	return 0;
+	bio_ctrl->len_to_oe_boundary = U32_MAX;
 }
 
-static int alloc_new_bio(struct btrfs_inode *inode,
-			 struct btrfs_bio_ctrl *bio_ctrl,
-			 struct writeback_control *wbc,
-			 blk_opf_t opf,
-			 u64 disk_bytenr, u32 offset, u64 file_offset,
-			 enum btrfs_compression_type compress_type)
+static void alloc_new_bio(struct btrfs_inode *inode,
+			  struct btrfs_bio_ctrl *bio_ctrl,
+			  struct writeback_control *wbc, blk_opf_t opf,
+			  u64 disk_bytenr, u32 offset, u64 file_offset,
+			  enum btrfs_compression_type compress_type)
 {
 	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	struct bio *bio;
-	int ret;
 
-	ASSERT(bio_ctrl->end_io_func);
-
-	bio = btrfs_bio_alloc(BIO_MAX_VECS, opf, bio_ctrl->end_io_func, NULL);
+	bio = btrfs_bio_alloc(BIO_MAX_VECS, opf, inode, bio_ctrl->end_io_func,
+			      NULL);
 	/*
 	 * For compressed page range, its disk_bytenr is always @disk_bytenr
 	 * passed in, no matter if we have added any range into previous bio.
@@ -1405,48 +990,21 @@ static int alloc_new_bio(struct btrfs_inode *inode,
 		bio->bi_iter.bi_sector = disk_bytenr >> SECTOR_SHIFT;
 	else
 		bio->bi_iter.bi_sector = (disk_bytenr + offset) >> SECTOR_SHIFT;
+	btrfs_bio(bio)->file_offset = file_offset;
 	bio_ctrl->bio = bio;
 	bio_ctrl->compress_type = compress_type;
-	ret = calc_bio_boundaries(bio_ctrl, inode, file_offset);
-	if (ret < 0)
-		goto error;
+	calc_bio_boundaries(bio_ctrl, inode, file_offset);
 
 	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:
+		 * 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.
 		 */
-		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;
-			}
-
-			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);
-		}
+		bio_set_dev(bio, fs_info->fs_devices->latest_dev->bdev);
 		wbc_init_bio(wbc, bio);
-	} else {
-		ASSERT(bio_op(bio) != REQ_OP_ZONE_APPEND);
 	}
-	return 0;
-error:
-	bio_ctrl->bio = NULL;
-	btrfs_bio_end_io(btrfs_bio(bio), errno_to_blk_status(ret));
-	return ret;
 }
 
 /*
@@ -1472,7 +1030,6 @@ static int submit_extent_page(blk_opf_t opf,
 			      enum btrfs_compression_type compress_type,
 			      bool force_bio_submit)
 {
-	int ret = 0;
 	struct btrfs_inode *inode = BTRFS_I(page->mapping->host);
 	unsigned int cur = pg_offset;
 
@@ -1492,12 +1049,9 @@ static int submit_extent_page(blk_opf_t opf,
 
 		/* Allocate new bio if needed */
 		if (!bio_ctrl->bio) {
-			ret = alloc_new_bio(inode, bio_ctrl, wbc, opf,
-					    disk_bytenr, offset,
-					    page_offset(page) + cur,
-					    compress_type);
-			if (ret < 0)
-				return ret;
+			alloc_new_bio(inode, bio_ctrl, wbc, opf, disk_bytenr,
+				      offset, page_offset(page) + cur,
+				      compress_type);
 		}
 		/*
 		 * We must go through btrfs_bio_add_page() to ensure each
@@ -2054,10 +1608,6 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode,
 		 * find_next_dirty_byte() are all exclusive
 		 */
 		iosize = min(min(em_end, end + 1), dirty_range_end) - cur;
-
-		if (btrfs_use_zone_append(inode, em->block_start))
-			op = REQ_OP_ZONE_APPEND;
-
 		free_extent_map(em);
 		em = NULL;
 
@@ -2361,13 +1911,6 @@ static void set_btree_ioerr(struct page *page, struct extent_buffer *eb)
 	mapping_set_error(page->mapping, -EIO);
 
 	/*
-	 * If we error out, we should add back the dirty_metadata_bytes
-	 * to make it consistent.
-	 */
-	percpu_counter_add_batch(&fs_info->dirty_metadata_bytes,
-				 eb->len, fs_info->dirty_metadata_batch);
-
-	/*
 	 * If writeback for a btree extent that doesn't belong to a log tree
 	 * failed, increment the counter transaction->eb_write_errors.
 	 * We do this because while the transaction is running and before it's
@@ -4724,12 +4267,25 @@ static void clear_subpage_extent_buffer_dirty(const struct extent_buffer *eb)
 	WARN_ON(atomic_read(&eb->refs) == 0);
 }
 
-void clear_extent_buffer_dirty(const struct extent_buffer *eb)
+void btrfs_clear_buffer_dirty(struct btrfs_trans_handle *trans,
+			      struct extent_buffer *eb)
 {
+	struct btrfs_fs_info *fs_info = eb->fs_info;
 	int i;
 	int num_pages;
 	struct page *page;
 
+	btrfs_assert_tree_write_locked(eb);
+
+	if (trans && btrfs_header_generation(eb) != trans->transid)
+		return;
+
+	if (!test_and_clear_bit(EXTENT_BUFFER_DIRTY, &eb->bflags))
+		return;
+
+	percpu_counter_add_batch(&fs_info->dirty_metadata_bytes, -eb->len,
+				 fs_info->dirty_metadata_batch);
+
 	if (eb->fs_info->nodesize < PAGE_SIZE)
 		return clear_subpage_extent_buffer_dirty(eb);