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, 89 insertions, 552 deletions

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index efee6d35af529..6c18dc9a1831d 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -84,27 +84,12 @@ struct btrfs_dio_data {
 };
 
 struct btrfs_dio_private {
-	struct btrfs_inode *inode;
-
-	/*
-	 * Since DIO can use anonymous page, we cannot use page_offset() to
-	 * grab the file offset, thus need a dedicated member for file offset.
-	 */
+	/* Range of I/O */
 	u64 file_offset;
-	/* Used for bio::bi_size */
 	u32 bytes;
 
-	/*
-	 * References to this structure. There is one reference per in-flight
-	 * bio plus one while we're still setting up.
-	 */
-	refcount_t refs;
-
-	/* Array of checksums */
-	u8 *csums;
-
 	/* This must be last */
-	struct bio bio;
+	struct btrfs_bio bbio;
 };
 
 static struct bio_set btrfs_dio_bioset;
@@ -228,7 +213,7 @@ static inline void btrfs_cleanup_ordered_extents(struct btrfs_inode *inode,
 {
 	unsigned long index = offset >> PAGE_SHIFT;
 	unsigned long end_index = (offset + bytes - 1) >> PAGE_SHIFT;
-	u64 page_start, page_end;
+	u64 page_start = 0, page_end = 0;
 	struct page *page;
 
 	if (locked_page) {
@@ -2536,19 +2521,6 @@ void btrfs_clear_delalloc_extent(struct btrfs_inode *inode,
 }
 
 /*
- * in order to insert checksums into the metadata in large chunks,
- * we wait until bio submission time.   All the pages in the bio are
- * checksummed and sums are attached onto the ordered extent record.
- *
- * At IO completion time the cums attached on the ordered extent record
- * are inserted into the btree
- */
-blk_status_t btrfs_submit_bio_start(struct btrfs_inode *inode, struct bio *bio)
-{
-	return btrfs_csum_one_bio(inode, bio, (u64)-1, false);
-}
-
-/*
  * Split an extent_map at [start, start + len]
  *
  * This function is intended to be used only for extract_ordered_extent().
@@ -2663,19 +2635,19 @@ out:
 	return ret;
 }
 
-static blk_status_t extract_ordered_extent(struct btrfs_inode *inode,
-					   struct bio *bio, loff_t file_offset)
+blk_status_t btrfs_extract_ordered_extent(struct btrfs_bio *bbio)
 {
+	u64 start = (u64)bbio->bio.bi_iter.bi_sector << SECTOR_SHIFT;
+	u64 len = bbio->bio.bi_iter.bi_size;
+	struct btrfs_inode *inode = bbio->inode;
 	struct btrfs_ordered_extent *ordered;
-	u64 start = (u64)bio->bi_iter.bi_sector << SECTOR_SHIFT;
 	u64 file_len;
-	u64 len = bio->bi_iter.bi_size;
 	u64 end = start + len;
 	u64 ordered_end;
 	u64 pre, post;
 	int ret = 0;
 
-	ordered = btrfs_lookup_ordered_extent(inode, file_offset);
+	ordered = btrfs_lookup_ordered_extent(inode, bbio->file_offset);
 	if (WARN_ON_ONCE(!ordered))
 		return BLK_STS_IOERR;
 
@@ -2715,7 +2687,7 @@ static blk_status_t extract_ordered_extent(struct btrfs_inode *inode,
 	ret = btrfs_split_ordered_extent(ordered, pre, post);
 	if (ret)
 		goto out;
-	ret = split_zoned_em(inode, file_offset, file_len, pre, post);
+	ret = split_zoned_em(inode, bbio->file_offset, file_len, pre, post);
 
 out:
 	btrfs_put_ordered_extent(ordered);
@@ -2723,75 +2695,6 @@ out:
 	return errno_to_blk_status(ret);
 }
 
-void btrfs_submit_data_write_bio(struct btrfs_inode *inode, struct bio *bio, int mirror_num)
-{
-	struct btrfs_fs_info *fs_info = inode->root->fs_info;
-	blk_status_t ret;
-
-	if (bio_op(bio) == REQ_OP_ZONE_APPEND) {
-		ret = extract_ordered_extent(inode, bio,
-				page_offset(bio_first_bvec_all(bio)->bv_page));
-		if (ret) {
-			btrfs_bio_end_io(btrfs_bio(bio), ret);
-			return;
-		}
-	}
-
-	/*
-	 * If we need to checksum, and the I/O is not issued by fsync and
-	 * friends, that is ->sync_writers != 0, defer the submission to a
-	 * workqueue to parallelize it.
-	 *
-	 * Csum items for reloc roots have already been cloned at this point,
-	 * so they are handled as part of the no-checksum case.
-	 */
-	if (!(inode->flags & BTRFS_INODE_NODATASUM) &&
-	    !test_bit(BTRFS_FS_STATE_NO_CSUMS, &fs_info->fs_state) &&
-	    !btrfs_is_data_reloc_root(inode->root)) {
-		if (!atomic_read(&inode->sync_writers) &&
-		    btrfs_wq_submit_bio(inode, bio, mirror_num, 0, WQ_SUBMIT_DATA))
-			return;
-
-		ret = btrfs_csum_one_bio(inode, bio, (u64)-1, false);
-		if (ret) {
-			btrfs_bio_end_io(btrfs_bio(bio), ret);
-			return;
-		}
-	}
-	btrfs_submit_bio(fs_info, bio, mirror_num);
-}
-
-void btrfs_submit_data_read_bio(struct btrfs_inode *inode, struct bio *bio,
-			int mirror_num, enum btrfs_compression_type compress_type)
-{
-	struct btrfs_fs_info *fs_info = inode->root->fs_info;
-	blk_status_t ret;
-
-	if (compress_type != BTRFS_COMPRESS_NONE) {
-		/*
-		 * btrfs_submit_compressed_read will handle completing the bio
-		 * if there were any errors, so just return here.
-		 */
-		btrfs_submit_compressed_read(&inode->vfs_inode, bio, mirror_num);
-		return;
-	}
-
-	/* Save the original iter for read repair */
-	btrfs_bio(bio)->iter = bio->bi_iter;
-
-	/*
-	 * Lookup bio sums does extra checks around whether we need to csum or
-	 * not, which is why we ignore skip_sum here.
-	 */
-	ret = btrfs_lookup_bio_sums(&inode->vfs_inode, bio, NULL);
-	if (ret) {
-		btrfs_bio_end_io(btrfs_bio(bio), ret);
-		return;
-	}
-
-	btrfs_submit_bio(fs_info, bio, mirror_num);
-}
-
 /*
  * given a list of ordered sums record them in the inode.  This happens
  * at IO completion time based on sums calculated at bio submission time.
@@ -2969,7 +2872,7 @@ again:
 		unlock_extent(&inode->io_tree, page_start, page_end,
 			      &cached_state);
 		unlock_page(page);
-		btrfs_start_ordered_extent(ordered, 1);
+		btrfs_start_ordered_extent(ordered);
 		btrfs_put_ordered_extent(ordered);
 		goto again;
 	}
@@ -3259,15 +3162,13 @@ int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
 		goto out;
 	}
 
-	/* A valid bdev implies a write on a sequential zone */
-	if (ordered_extent->bdev) {
+	/* A valid ->physical implies a write on a sequential zone. */
+	if (ordered_extent->physical != (u64)-1) {
 		btrfs_rewrite_logical_zoned(ordered_extent);
 		btrfs_zone_finish_endio(fs_info, ordered_extent->disk_bytenr,
 					ordered_extent->disk_num_bytes);
 	}
 
-	btrfs_free_io_failure_record(inode, start, end);
-
 	if (test_bit(BTRFS_ORDERED_TRUNCATED, &ordered_extent->flags)) {
 		truncated = true;
 		logical_len = ordered_extent->truncated_len;
@@ -3474,109 +3375,55 @@ static u8 *btrfs_csum_ptr(const struct btrfs_fs_info *fs_info, u8 *csums, u64 of
 }
 
 /*
- * check_data_csum - verify checksum of one sector of uncompressed data
- * @inode:	inode
- * @bbio:	btrfs_bio which contains the csum
+ * Verify the checksum of a single data sector.
+ *
+ * @bbio:	btrfs_io_bio which contains the csum
+ * @dev:	device the sector is on
  * @bio_offset:	offset to the beginning of the bio (in bytes)
- * @page:	page where is the data to be verified
- * @pgoff:	offset inside the page
+ * @bv:		bio_vec to check
  *
- * The length of such check is always one sector size.
+ * Check if the checksum on a data block is valid.  When a checksum mismatch is
+ * detected, report the error and fill the corrupted range with zero.
  *
- * When csum mismatch is detected, we will also report the error and fill the
- * corrupted range with zero. (Thus it needs the extra parameters)
+ * Return %true if the sector is ok or had no checksum to start with, else %false.
  */
-int btrfs_check_data_csum(struct btrfs_inode *inode, struct btrfs_bio *bbio,
-			  u32 bio_offset, struct page *page, u32 pgoff)
+bool btrfs_data_csum_ok(struct btrfs_bio *bbio, struct btrfs_device *dev,
+			u32 bio_offset, struct bio_vec *bv)
 {
+	struct btrfs_inode *inode = bbio->inode;
 	struct btrfs_fs_info *fs_info = inode->root->fs_info;
-	u32 len = fs_info->sectorsize;
+	u64 file_offset = bbio->file_offset + bio_offset;
+	u64 end = file_offset + bv->bv_len - 1;
 	u8 *csum_expected;
 	u8 csum[BTRFS_CSUM_SIZE];
 
-	ASSERT(pgoff + len <= PAGE_SIZE);
+	ASSERT(bv->bv_len == fs_info->sectorsize);
 
-	csum_expected = btrfs_csum_ptr(fs_info, bbio->csum, bio_offset);
+	if (!bbio->csum)
+		return true;
 
-	if (btrfs_check_sector_csum(fs_info, page, pgoff, csum, csum_expected))
+	if (btrfs_is_data_reloc_root(inode->root) &&
+	    test_range_bit(&inode->io_tree, file_offset, end, EXTENT_NODATASUM,
+			   1, NULL)) {
+		/* Skip the range without csum for data reloc inode */
+		clear_extent_bits(&inode->io_tree, file_offset, end,
+				  EXTENT_NODATASUM);
+		return true;
+	}
+
+	csum_expected = btrfs_csum_ptr(fs_info, bbio->csum, bio_offset);
+	if (btrfs_check_sector_csum(fs_info, bv->bv_page, bv->bv_offset, csum,
+				    csum_expected))
 		goto zeroit;
-	return 0;
+	return true;
 
 zeroit:
-	btrfs_print_data_csum_error(inode, bbio->file_offset + bio_offset,
-				    csum, csum_expected, bbio->mirror_num);
-	if (bbio->device)
-		btrfs_dev_stat_inc_and_print(bbio->device,
-					     BTRFS_DEV_STAT_CORRUPTION_ERRS);
-	memzero_page(page, pgoff, len);
-	return -EIO;
-}
-
-/*
- * When reads are done, we need to check csums to verify the data is correct.
- * if there's a match, we allow the bio to finish.  If not, the code in
- * extent_io.c will try to find good copies for us.
- *
- * @bio_offset:	offset to the beginning of the bio (in bytes)
- * @start:	file offset of the range start
- * @end:	file offset of the range end (inclusive)
- *
- * Return a bitmap where bit set means a csum mismatch, and bit not set means
- * csum match.
- */
-unsigned int btrfs_verify_data_csum(struct btrfs_bio *bbio,
-				    u32 bio_offset, struct page *page,
-				    u64 start, u64 end)
-{
-	struct btrfs_inode *inode = BTRFS_I(page->mapping->host);
-	struct btrfs_root *root = inode->root;
-	struct btrfs_fs_info *fs_info = root->fs_info;
-	struct extent_io_tree *io_tree = &inode->io_tree;
-	const u32 sectorsize = root->fs_info->sectorsize;
-	u32 pg_off;
-	unsigned int result = 0;
-
-	/*
-	 * This only happens for NODATASUM or compressed read.
-	 * Normally this should be covered by above check for compressed read
-	 * or the next check for NODATASUM.  Just do a quicker exit here.
-	 */
-	if (bbio->csum == NULL)
-		return 0;
-
-	if (inode->flags & BTRFS_INODE_NODATASUM)
-		return 0;
-
-	if (unlikely(test_bit(BTRFS_FS_STATE_NO_CSUMS, &fs_info->fs_state)))
-		return 0;
-
-	ASSERT(page_offset(page) <= start &&
-	       end <= page_offset(page) + PAGE_SIZE - 1);
-	for (pg_off = offset_in_page(start);
-	     pg_off < offset_in_page(end);
-	     pg_off += sectorsize, bio_offset += sectorsize) {
-		u64 file_offset = pg_off + page_offset(page);
-		int ret;
-
-		if (btrfs_is_data_reloc_root(root) &&
-		    test_range_bit(io_tree, file_offset,
-				   file_offset + sectorsize - 1,
-				   EXTENT_NODATASUM, 1, NULL)) {
-			/* Skip the range without csum for data reloc inode */
-			clear_extent_bits(io_tree, file_offset,
-					  file_offset + sectorsize - 1,
-					  EXTENT_NODATASUM);
-			continue;
-		}
-		ret = btrfs_check_data_csum(inode, bbio, bio_offset, page, pg_off);
-		if (ret < 0) {
-			const int nr_bit = (pg_off - offset_in_page(start)) >>
-				     root->fs_info->sectorsize_bits;
-
-			result |= (1U << nr_bit);
-		}
-	}
-	return result;
+	btrfs_print_data_csum_error(inode, file_offset, csum, csum_expected,
+				    bbio->mirror_num);
+	if (dev)
+		btrfs_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_CORRUPTION_ERRS);
+	memzero_bvec(bv);
+	return false;
 }
 
 /*
@@ -4987,7 +4834,7 @@ again:
 		unlock_extent(io_tree, block_start, block_end, &cached_state);
 		unlock_page(page);
 		put_page(page);
-		btrfs_start_ordered_extent(ordered, 1);
+		btrfs_start_ordered_extent(ordered);
 		btrfs_put_ordered_extent(ordered);
 		goto again;
 	}
@@ -5466,8 +5313,6 @@ void btrfs_evict_inode(struct inode *inode)
 	if (is_bad_inode(inode))
 		goto no_delete;
 
-	btrfs_free_io_failure_record(BTRFS_I(inode), 0, (u64)-1);
-
 	if (test_bit(BTRFS_FS_LOG_RECOVERING, &fs_info->flags))
 		goto no_delete;
 
@@ -7392,7 +7237,7 @@ static int lock_extent_direct(struct inode *inode, u64 lockstart, u64 lockend,
 			 */
 			if (writing ||
 			    test_bit(BTRFS_ORDERED_DIRECT, &ordered->flags))
-				btrfs_start_ordered_extent(ordered, 1);
+				btrfs_start_ordered_extent(ordered);
 			else
 				ret = nowait ? -EAGAIN : -ENOTBLK;
 			btrfs_put_ordered_extent(ordered);
@@ -7833,10 +7678,6 @@ static int btrfs_dio_iomap_begin(struct inode *inode, loff_t start,
 	iomap->offset = start;
 	iomap->bdev = fs_info->fs_devices->latest_dev->bdev;
 	iomap->length = len;
-
-	if (write && btrfs_use_zone_append(BTRFS_I(inode), em->block_start))
-		iomap->flags |= IOMAP_F_ZONE_APPEND;
-
 	free_extent_map(em);
 
 	return 0;
@@ -7888,267 +7729,47 @@ static int btrfs_dio_iomap_end(struct inode *inode, loff_t pos, loff_t length,
 	return ret;
 }
 
-static void btrfs_dio_private_put(struct btrfs_dio_private *dip)
-{
-	/*
-	 * This implies a barrier so that stores to dio_bio->bi_status before
-	 * this and loads of dio_bio->bi_status after this are fully ordered.
-	 */
-	if (!refcount_dec_and_test(&dip->refs))
-		return;
-
-	if (btrfs_op(&dip->bio) == BTRFS_MAP_WRITE) {
-		btrfs_mark_ordered_io_finished(dip->inode, NULL,
-					       dip->file_offset, dip->bytes,
-					       !dip->bio.bi_status);
-	} else {
-		unlock_extent(&dip->inode->io_tree,
-			      dip->file_offset,
-			      dip->file_offset + dip->bytes - 1, NULL);
-	}
-
-	kfree(dip->csums);
-	bio_endio(&dip->bio);
-}
-
-void btrfs_submit_dio_repair_bio(struct btrfs_inode *inode, struct bio *bio, int mirror_num)
-{
-	struct btrfs_dio_private *dip = btrfs_bio(bio)->private;
-
-	BUG_ON(bio_op(bio) == REQ_OP_WRITE);
-
-	refcount_inc(&dip->refs);
-	btrfs_submit_bio(inode->root->fs_info, bio, mirror_num);
-}
-
-static blk_status_t btrfs_check_read_dio_bio(struct btrfs_dio_private *dip,
-					     struct btrfs_bio *bbio,
-					     const bool uptodate)
-{
-	struct inode *inode = &dip->inode->vfs_inode;
-	struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info;
-	const bool csum = !(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM);
-	blk_status_t err = BLK_STS_OK;
-	struct bvec_iter iter;
-	struct bio_vec bv;
-	u32 offset;
-
-	btrfs_bio_for_each_sector(fs_info, bv, bbio, iter, offset) {
-		u64 start = bbio->file_offset + offset;
-
-		if (uptodate &&
-		    (!csum || !btrfs_check_data_csum(BTRFS_I(inode), bbio, offset,
-						     bv.bv_page, bv.bv_offset))) {
-			btrfs_clean_io_failure(BTRFS_I(inode), start,
-					       bv.bv_page, bv.bv_offset);
-		} else {
-			int ret;
-
-			ret = btrfs_repair_one_sector(BTRFS_I(inode), bbio, offset,
-					bv.bv_page, bv.bv_offset, false);
-			if (ret)
-				err = errno_to_blk_status(ret);
-		}
-	}
-
-	return err;
-}
-
-blk_status_t btrfs_submit_bio_start_direct_io(struct btrfs_inode *inode,
-					      struct bio *bio,
-					      u64 dio_file_offset)
+static void btrfs_dio_end_io(struct btrfs_bio *bbio)
 {
-	return btrfs_csum_one_bio(inode, bio, dio_file_offset, false);
-}
-
-static void btrfs_end_dio_bio(struct btrfs_bio *bbio)
-{
-	struct btrfs_dio_private *dip = bbio->private;
+	struct btrfs_dio_private *dip =
+		container_of(bbio, struct btrfs_dio_private, bbio);
+	struct btrfs_inode *inode = bbio->inode;
 	struct bio *bio = &bbio->bio;
-	blk_status_t err = bio->bi_status;
-
-	if (err)
-		btrfs_warn(dip->inode->root->fs_info,
-			   "direct IO failed ino %llu rw %d,%u sector %#Lx len %u err no %d",
-			   btrfs_ino(dip->inode), bio_op(bio),
-			   bio->bi_opf, bio->bi_iter.bi_sector,
-			   bio->bi_iter.bi_size, err);
-
-	if (bio_op(bio) == REQ_OP_READ)
-		err = btrfs_check_read_dio_bio(dip, bbio, !err);
-
-	if (err)
-		dip->bio.bi_status = err;
-
-	btrfs_record_physical_zoned(&dip->inode->vfs_inode, bbio->file_offset, bio);
-
-	bio_put(bio);
-	btrfs_dio_private_put(dip);
-}
 
-static void btrfs_submit_dio_bio(struct bio *bio, struct btrfs_inode *inode,
-				 u64 file_offset, int async_submit)
-{
-	struct btrfs_fs_info *fs_info = inode->root->fs_info;
-	struct btrfs_dio_private *dip = btrfs_bio(bio)->private;
-	blk_status_t ret;
-
-	/* Save the original iter for read repair */
-	if (btrfs_op(bio) == BTRFS_MAP_READ)
-		btrfs_bio(bio)->iter = bio->bi_iter;
-
-	if (inode->flags & BTRFS_INODE_NODATASUM)
-		goto map;
+	if (bio->bi_status) {
+		btrfs_warn(inode->root->fs_info,
+		"direct IO failed ino %llu op 0x%0x offset %#llx len %u err no %d",
+			   btrfs_ino(inode), bio->bi_opf,
+			   dip->file_offset, dip->bytes, bio->bi_status);
+	}
 
-	if (btrfs_op(bio) == BTRFS_MAP_WRITE) {
-		/* Check btrfs_submit_data_write_bio() for async submit rules */
-		if (async_submit && !atomic_read(&inode->sync_writers) &&
-		    btrfs_wq_submit_bio(inode, bio, 0, file_offset,
-					WQ_SUBMIT_DATA_DIO))
-			return;
+	if (btrfs_op(bio) == BTRFS_MAP_WRITE)
+		btrfs_mark_ordered_io_finished(inode, NULL, dip->file_offset,
+					       dip->bytes, !bio->bi_status);
+	else
+		unlock_extent(&inode->io_tree, dip->file_offset,
+			      dip->file_offset + dip->bytes - 1, NULL);
 
-		/*
-		 * If we aren't doing async submit, calculate the csum of the
-		 * bio now.
-		 */
-		ret = btrfs_csum_one_bio(inode, bio, file_offset, false);
-		if (ret) {
-			btrfs_bio_end_io(btrfs_bio(bio), ret);
-			return;
-		}
-	} else {
-		btrfs_bio(bio)->csum = btrfs_csum_ptr(fs_info, dip->csums,
-						      file_offset - dip->file_offset);
-	}
-map:
-	btrfs_submit_bio(fs_info, bio, 0);
+	bbio->bio.bi_private = bbio->private;
+	iomap_dio_bio_end_io(bio);
 }
 
-static void btrfs_submit_direct(const struct iomap_iter *iter,
-		struct bio *dio_bio, loff_t file_offset)
+static void btrfs_dio_submit_io(const struct iomap_iter *iter, struct bio *bio,
+				loff_t file_offset)
 {
+	struct btrfs_bio *bbio = btrfs_bio(bio);
 	struct btrfs_dio_private *dip =
-		container_of(dio_bio, struct btrfs_dio_private, bio);
-	struct inode *inode = iter->inode;
-	const bool write = (btrfs_op(dio_bio) == BTRFS_MAP_WRITE);
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
-	const bool raid56 = (btrfs_data_alloc_profile(fs_info) &
-			     BTRFS_BLOCK_GROUP_RAID56_MASK);
-	struct bio *bio;
-	u64 start_sector;
-	int async_submit = 0;
-	u64 submit_len;
-	u64 clone_offset = 0;
-	u64 clone_len;
-	u64 logical;
-	int ret;
-	blk_status_t status;
-	struct btrfs_io_geometry geom;
+		container_of(bbio, struct btrfs_dio_private, bbio);
 	struct btrfs_dio_data *dio_data = iter->private;
-	struct extent_map *em = NULL;
-
-	dip->inode = BTRFS_I(inode);
-	dip->file_offset = file_offset;
-	dip->bytes = dio_bio->bi_iter.bi_size;
-	refcount_set(&dip->refs, 1);
-	dip->csums = NULL;
-
-	if (!write && !(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)) {
-		unsigned int nr_sectors =
-			(dio_bio->bi_iter.bi_size >> fs_info->sectorsize_bits);
-
-		/*
-		 * Load the csums up front to reduce csum tree searches and
-		 * contention when submitting bios.
-		 */
-		status = BLK_STS_RESOURCE;
-		dip->csums = kcalloc(nr_sectors, fs_info->csum_size, GFP_NOFS);
-		if (!dip->csums)
-			goto out_err;
-
-		status = btrfs_lookup_bio_sums(inode, dio_bio, dip->csums);
-		if (status != BLK_STS_OK)
-			goto out_err;
-	}
-
-	start_sector = dio_bio->bi_iter.bi_sector;
-	submit_len = dio_bio->bi_iter.bi_size;
-
-	do {
-		logical = start_sector << 9;
-		em = btrfs_get_chunk_map(fs_info, logical, submit_len);
-		if (IS_ERR(em)) {
-			status = errno_to_blk_status(PTR_ERR(em));
-			em = NULL;
-			goto out_err_em;
-		}
-		ret = btrfs_get_io_geometry(fs_info, em, btrfs_op(dio_bio),
-					    logical, &geom);
-		if (ret) {
-			status = errno_to_blk_status(ret);
-			goto out_err_em;
-		}
 
-		clone_len = min(submit_len, geom.len);
-		ASSERT(clone_len <= UINT_MAX);
+	btrfs_bio_init(bbio, BTRFS_I(iter->inode), btrfs_dio_end_io, bio->bi_private);
+	bbio->file_offset = file_offset;
 
-		/*
-		 * This will never fail as it's passing GPF_NOFS and
-		 * the allocation is backed by btrfs_bioset.
-		 */
-		bio = btrfs_bio_clone_partial(dio_bio, clone_offset, clone_len,
-					      btrfs_end_dio_bio, dip);
-		btrfs_bio(bio)->file_offset = file_offset;
-
-		if (bio_op(bio) == REQ_OP_ZONE_APPEND) {
-			status = extract_ordered_extent(BTRFS_I(inode), bio,
-							file_offset);
-			if (status) {
-				bio_put(bio);
-				goto out_err;
-			}
-		}
-
-		ASSERT(submit_len >= clone_len);
-		submit_len -= clone_len;
-
-		/*
-		 * Increase the count before we submit the bio so we know
-		 * the end IO handler won't happen before we increase the
-		 * count. Otherwise, the dip might get freed before we're
-		 * done setting it up.
-		 *
-		 * We transfer the initial reference to the last bio, so we
-		 * don't need to increment the reference count for the last one.
-		 */
-		if (submit_len > 0) {
-			refcount_inc(&dip->refs);
-			/*
-			 * If we are submitting more than one bio, submit them
-			 * all asynchronously. The exception is RAID 5 or 6, as
-			 * asynchronous checksums make it difficult to collect
-			 * full stripe writes.
-			 */
-			if (!raid56)
-				async_submit = 1;
-		}
-
-		btrfs_submit_dio_bio(bio, BTRFS_I(inode), file_offset, async_submit);
-
-		dio_data->submitted += clone_len;
-		clone_offset += clone_len;
-		start_sector += clone_len >> 9;
-		file_offset += clone_len;
-
-		free_extent_map(em);
-	} while (submit_len > 0);
-	return;
+	dip->file_offset = file_offset;
+	dip->bytes = bio->bi_iter.bi_size;
 
-out_err_em:
-	free_extent_map(em);
-out_err:
-	dio_bio->bi_status = status;
-	btrfs_dio_private_put(dip);
+	dio_data->submitted += bio->bi_iter.bi_size;
+	btrfs_submit_bio(bio, 0);
 }
 
 static const struct iomap_ops btrfs_dio_iomap_ops = {
@@ -8157,7 +7778,7 @@ static const struct iomap_ops btrfs_dio_iomap_ops = {
 };
 
 static const struct iomap_dio_ops btrfs_dio_ops = {
-	.submit_io		= btrfs_submit_direct,
+	.submit_io		= btrfs_dio_submit_io,
 	.bio_set		= &btrfs_dio_bioset,
 };
 
@@ -8552,7 +8173,7 @@ again:
 		unlock_extent(io_tree, page_start, page_end, &cached_state);
 		unlock_page(page);
 		up_read(&BTRFS_I(inode)->i_mmap_lock);
-		btrfs_start_ordered_extent(ordered, 1);
+		btrfs_start_ordered_extent(ordered);
 		btrfs_put_ordered_extent(ordered);
 		goto again;
 	}
@@ -8850,7 +8471,6 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
 	ei->last_log_commit = 0;
 
 	spin_lock_init(&ei->lock);
-	spin_lock_init(&ei->io_failure_lock);
 	ei->outstanding_extents = 0;
 	if (sb->s_magic != BTRFS_TEST_MAGIC)
 		btrfs_init_metadata_block_rsv(fs_info, &ei->block_rsv,
@@ -8870,7 +8490,6 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
 	ei->io_tree.inode = ei;
 	extent_io_tree_init(fs_info, &ei->file_extent_tree,
 			    IO_TREE_INODE_FILE_EXTENT);
-	ei->io_failure_tree = RB_ROOT;
 	atomic_set(&ei->sync_writers, 0);
 	mutex_init(&ei->log_mutex);
 	btrfs_ordered_inode_tree_init(&ei->ordered_tree);
@@ -8994,7 +8613,7 @@ int __init btrfs_init_cachep(void)
 		goto fail;
 
 	if (bioset_init(&btrfs_dio_bioset, BIO_POOL_SIZE,
-			offsetof(struct btrfs_dio_private, bio),
+			offsetof(struct btrfs_dio_private, bbio.bio),
 			BIOSET_NEED_BVECS))
 		goto fail;
 
@@ -10289,65 +9908,13 @@ struct btrfs_encoded_read_private {
 	wait_queue_head_t wait;
 	atomic_t pending;
 	blk_status_t status;
-	bool skip_csum;
 };
 
-static blk_status_t submit_encoded_read_bio(struct btrfs_inode *inode,
-					    struct bio *bio, int mirror_num)
-{
-	struct btrfs_encoded_read_private *priv = btrfs_bio(bio)->private;
-	struct btrfs_fs_info *fs_info = inode->root->fs_info;
-	blk_status_t ret;
-
-	if (!priv->skip_csum) {
-		ret = btrfs_lookup_bio_sums(&inode->vfs_inode, bio, NULL);
-		if (ret)
-			return ret;
-	}
-
-	atomic_inc(&priv->pending);
-	btrfs_submit_bio(fs_info, bio, mirror_num);
-	return BLK_STS_OK;
-}
-
-static blk_status_t btrfs_encoded_read_verify_csum(struct btrfs_bio *bbio)
-{
-	const bool uptodate = (bbio->bio.bi_status == BLK_STS_OK);
-	struct btrfs_encoded_read_private *priv = bbio->private;
-	struct btrfs_inode *inode = priv->inode;
-	struct btrfs_fs_info *fs_info = inode->root->fs_info;
-	u32 sectorsize = fs_info->sectorsize;
-	struct bio_vec *bvec;
-	struct bvec_iter_all iter_all;
-	u32 bio_offset = 0;
-
-	if (priv->skip_csum || !uptodate)
-		return bbio->bio.bi_status;
-
-	bio_for_each_segment_all(bvec, &bbio->bio, iter_all) {
-		unsigned int i, nr_sectors, pgoff;
-
-		nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info, bvec->bv_len);
-		pgoff = bvec->bv_offset;
-		for (i = 0; i < nr_sectors; i++) {
-			ASSERT(pgoff < PAGE_SIZE);
-			if (btrfs_check_data_csum(inode, bbio, bio_offset,
-					    bvec->bv_page, pgoff))
-				return BLK_STS_IOERR;
-			bio_offset += sectorsize;
-			pgoff += sectorsize;
-		}
-	}
-	return BLK_STS_OK;
-}
-
 static void btrfs_encoded_read_endio(struct btrfs_bio *bbio)
 {
 	struct btrfs_encoded_read_private *priv = bbio->private;
-	blk_status_t status;
 
-	status = btrfs_encoded_read_verify_csum(bbio);
-	if (status) {
+	if (bbio->bio.bi_status) {
 		/*
 		 * The memory barrier implied by the atomic_dec_return() here
 		 * pairs with the memory barrier implied by the
@@ -10356,11 +9923,10 @@ static void btrfs_encoded_read_endio(struct btrfs_bio *bbio)
 		 * write is observed before the load of status in
 		 * btrfs_encoded_read_regular_fill_pages().
 		 */
-		WRITE_ONCE(priv->status, status);
+		WRITE_ONCE(priv->status, bbio->bio.bi_status);
 	}
 	if (!atomic_dec_return(&priv->pending))
 		wake_up(&priv->wait);
-	btrfs_bio_free_csum(bbio);
 	bio_put(&bbio->bio);
 }
 
@@ -10368,47 +9934,26 @@ int btrfs_encoded_read_regular_fill_pages(struct btrfs_inode *inode,
 					  u64 file_offset, u64 disk_bytenr,
 					  u64 disk_io_size, struct page **pages)
 {
-	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	struct btrfs_encoded_read_private priv = {
 		.inode = inode,
 		.file_offset = file_offset,
 		.pending = ATOMIC_INIT(1),
-		.skip_csum = (inode->flags & BTRFS_INODE_NODATASUM),
 	};
 	unsigned long i = 0;
 	u64 cur = 0;
-	int ret;
 
 	init_waitqueue_head(&priv.wait);
-	/*
-	 * Submit bios for the extent, splitting due to bio or stripe limits as
-	 * necessary.
-	 */
+	/* Submit bios for the extent, splitting due to bio limits as necessary. */
 	while (cur < disk_io_size) {
-		struct extent_map *em;
-		struct btrfs_io_geometry geom;
 		struct bio *bio = NULL;
-		u64 remaining;
+		u64 remaining = disk_io_size - cur;
 
-		em = btrfs_get_chunk_map(fs_info, disk_bytenr + cur,
-					 disk_io_size - cur);
-		if (IS_ERR(em)) {
-			ret = PTR_ERR(em);
-		} else {
-			ret = btrfs_get_io_geometry(fs_info, em, BTRFS_MAP_READ,
-						    disk_bytenr + cur, &geom);
-			free_extent_map(em);
-		}
-		if (ret) {
-			WRITE_ONCE(priv.status, errno_to_blk_status(ret));
-			break;
-		}
-		remaining = min(geom.len, disk_io_size - cur);
 		while (bio || remaining) {
 			size_t bytes = min_t(u64, remaining, PAGE_SIZE);
 
 			if (!bio) {
 				bio = btrfs_bio_alloc(BIO_MAX_VECS, REQ_OP_READ,
+						      inode,
 						      btrfs_encoded_read_endio,
 						      &priv);
 				bio->bi_iter.bi_sector =
@@ -10417,14 +9962,8 @@ int btrfs_encoded_read_regular_fill_pages(struct btrfs_inode *inode,
 
 			if (!bytes ||
 			    bio_add_page(bio, pages[i], bytes, 0) < bytes) {
-				blk_status_t status;
-
-				status = submit_encoded_read_bio(inode, bio, 0);
-				if (status) {
-					WRITE_ONCE(priv.status, status);
-					bio_put(bio);
-					goto out;
-				}
+				atomic_inc(&priv.pending);
+				btrfs_submit_bio(bio, 0);
 				bio = NULL;
 				continue;
 			}
@@ -10435,7 +9974,6 @@ int btrfs_encoded_read_regular_fill_pages(struct btrfs_inode *inode,
 		}
 	}
 
-out:
 	if (atomic_dec_return(&priv.pending))
 		io_wait_event(priv.wait, !atomic_read(&priv.pending));
 	/* See btrfs_encoded_read_endio() for ordering. */
@@ -10995,9 +10533,8 @@ static int btrfs_add_swap_extent(struct swap_info_struct *sis,
 		return 0;
 
 	max_pages = sis->max - bsi->nr_pages;
-	first_ppage = ALIGN(bsi->block_start, PAGE_SIZE) >> PAGE_SHIFT;
-	next_ppage = ALIGN_DOWN(bsi->block_start + bsi->block_len,
-				PAGE_SIZE) >> PAGE_SHIFT;
+	first_ppage = PAGE_ALIGN(bsi->block_start) >> PAGE_SHIFT;
+	next_ppage = PAGE_ALIGN_DOWN(bsi->block_start + bsi->block_len) >> PAGE_SHIFT;
 
 	if (first_ppage >= next_ppage)
 		return 0;