1 files changed, 121 insertions, 579 deletions

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 98a800b8bd43..957e4d76a7b6 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_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;
+	}
 
-	if (btrfs_check_sector_csum(fs_info, page, pgoff, csum, csum_expected))
+	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;
 	}
@@ -5281,7 +5128,7 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr)
 	return ret;
 }
 
-static int btrfs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+static int btrfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 			 struct iattr *attr)
 {
 	struct inode *inode = d_inode(dentry);
@@ -5291,7 +5138,7 @@ static int btrfs_setattr(struct user_namespace *mnt_userns, struct dentry *dentr
 	if (btrfs_root_readonly(root))
 		return -EROFS;
 
-	err = setattr_prepare(mnt_userns, dentry, attr);
+	err = setattr_prepare(idmap, dentry, attr);
 	if (err)
 		return err;
 
@@ -5302,12 +5149,12 @@ static int btrfs_setattr(struct user_namespace *mnt_userns, struct dentry *dentr
 	}
 
 	if (attr->ia_valid) {
-		setattr_copy(mnt_userns, inode, attr);
+		setattr_copy(idmap, inode, attr);
 		inode_inc_iversion(inode);
 		err = btrfs_dirty_inode(BTRFS_I(inode));
 
 		if (!err && attr->ia_valid & ATTR_MODE)
-			err = posix_acl_chmod(mnt_userns, dentry, inode->i_mode);
+			err = posix_acl_chmod(idmap, dentry, inode->i_mode);
 	}
 
 	return err;
@@ -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;
 
@@ -5576,8 +5421,13 @@ static int btrfs_inode_by_name(struct btrfs_inode *dir, struct dentry *dentry,
 		return -ENOMEM;
 
 	ret = fscrypt_setup_filename(&dir->vfs_inode, &dentry->d_name, 1, &fname);
-	if (ret)
+	if (ret < 0)
 		goto out;
+	/*
+	 * fscrypt_setup_filename() should never return a positive value, but
+	 * gcc on sparc/parisc thinks it can, so assert that doesn't happen.
+	 */
+	ASSERT(ret == 0);
 
 	/* This needs to handle no-key deletions later on */
 
@@ -6724,7 +6574,7 @@ out_inode:
 	return err;
 }
 
-static int btrfs_mknod(struct user_namespace *mnt_userns, struct inode *dir,
+static int btrfs_mknod(struct mnt_idmap *idmap, struct inode *dir,
 		       struct dentry *dentry, umode_t mode, dev_t rdev)
 {
 	struct inode *inode;
@@ -6732,13 +6582,13 @@ static int btrfs_mknod(struct user_namespace *mnt_userns, struct inode *dir,
 	inode = new_inode(dir->i_sb);
 	if (!inode)
 		return -ENOMEM;
-	inode_init_owner(mnt_userns, inode, dir, mode);
+	inode_init_owner(idmap, inode, dir, mode);
 	inode->i_op = &btrfs_special_inode_operations;
 	init_special_inode(inode, inode->i_mode, rdev);
 	return btrfs_create_common(dir, dentry, inode);
 }
 
-static int btrfs_create(struct user_namespace *mnt_userns, struct inode *dir,
+static int btrfs_create(struct mnt_idmap *idmap, struct inode *dir,
 			struct dentry *dentry, umode_t mode, bool excl)
 {
 	struct inode *inode;
@@ -6746,7 +6596,7 @@ static int btrfs_create(struct user_namespace *mnt_userns, struct inode *dir,
 	inode = new_inode(dir->i_sb);
 	if (!inode)
 		return -ENOMEM;
-	inode_init_owner(mnt_userns, inode, dir, mode);
+	inode_init_owner(idmap, inode, dir, mode);
 	inode->i_fop = &btrfs_file_operations;
 	inode->i_op = &btrfs_file_inode_operations;
 	inode->i_mapping->a_ops = &btrfs_aops;
@@ -6837,7 +6687,7 @@ fail:
 	return err;
 }
 
-static int btrfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
+static int btrfs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 		       struct dentry *dentry, umode_t mode)
 {
 	struct inode *inode;
@@ -6845,7 +6695,7 @@ static int btrfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
 	inode = new_inode(dir->i_sb);
 	if (!inode)
 		return -ENOMEM;
-	inode_init_owner(mnt_userns, inode, dir, S_IFDIR | mode);
+	inode_init_owner(idmap, inode, dir, S_IFDIR | mode);
 	inode->i_op = &btrfs_dir_inode_operations;
 	inode->i_fop = &btrfs_dir_file_operations;
 	return btrfs_create_common(dir, dentry, inode);
@@ -7392,7 +7242,7 @@ 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 +7683,6 @@ 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 +7734,47 @@ 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)
+static void btrfs_dio_end_io(struct btrfs_bio *bbio)
 {
-	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)
-{
-	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);
-
-		/*
-		 * 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;
+	btrfs_bio_init(bbio, BTRFS_I(iter->inode), btrfs_dio_end_io, bio->bi_private);
+	bbio->file_offset = file_offset;
 
-		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 +7783,7 @@ 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 +8178,7 @@ 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;
 	}
@@ -8802,7 +8428,7 @@ out:
 	return ret;
 }
 
-struct inode *btrfs_new_subvol_inode(struct user_namespace *mnt_userns,
+struct inode *btrfs_new_subvol_inode(struct mnt_idmap *idmap,
 				     struct inode *dir)
 {
 	struct inode *inode;
@@ -8813,7 +8439,7 @@ struct inode *btrfs_new_subvol_inode(struct user_namespace *mnt_userns,
 		 * Subvolumes don't inherit the sgid bit or the parent's gid if
 		 * the parent's sgid bit is set. This is probably a bug.
 		 */
-		inode_init_owner(mnt_userns, inode, NULL,
+		inode_init_owner(idmap, inode, NULL,
 				 S_IFDIR | (~current_umask() & S_IRWXUGO));
 		inode->i_op = &btrfs_dir_inode_operations;
 		inode->i_fop = &btrfs_dir_file_operations;
@@ -8850,7 +8476,6 @@ 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 +8495,6 @@ 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 +8618,7 @@ 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;
 
@@ -9004,7 +8628,7 @@ fail:
 	return -ENOMEM;
 }
 
-static int btrfs_getattr(struct user_namespace *mnt_userns,
+static int btrfs_getattr(struct mnt_idmap *idmap,
 			 const struct path *path, struct kstat *stat,
 			 u32 request_mask, unsigned int flags)
 {
@@ -9034,7 +8658,7 @@ static int btrfs_getattr(struct user_namespace *mnt_userns,
 				  STATX_ATTR_IMMUTABLE |
 				  STATX_ATTR_NODUMP);
 
-	generic_fillattr(mnt_userns, inode, stat);
+	generic_fillattr(idmap, inode, stat);
 	stat->dev = BTRFS_I(inode)->root->anon_dev;
 
 	spin_lock(&BTRFS_I(inode)->lock);
@@ -9289,14 +8913,14 @@ out_notrans:
 	return ret;
 }
 
-static struct inode *new_whiteout_inode(struct user_namespace *mnt_userns,
+static struct inode *new_whiteout_inode(struct mnt_idmap *idmap,
 					struct inode *dir)
 {
 	struct inode *inode;
 
 	inode = new_inode(dir->i_sb);
 	if (inode) {
-		inode_init_owner(mnt_userns, inode, dir,
+		inode_init_owner(idmap, inode, dir,
 				 S_IFCHR | WHITEOUT_MODE);
 		inode->i_op = &btrfs_special_inode_operations;
 		init_special_inode(inode, inode->i_mode, WHITEOUT_DEV);
@@ -9304,7 +8928,7 @@ static struct inode *new_whiteout_inode(struct user_namespace *mnt_userns,
 	return inode;
 }
 
-static int btrfs_rename(struct user_namespace *mnt_userns,
+static int btrfs_rename(struct mnt_idmap *idmap,
 			struct inode *old_dir, struct dentry *old_dentry,
 			struct inode *new_dir, struct dentry *new_dentry,
 			unsigned int flags)
@@ -9376,7 +9000,7 @@ static int btrfs_rename(struct user_namespace *mnt_userns,
 		filemap_flush(old_inode->i_mapping);
 
 	if (flags & RENAME_WHITEOUT) {
-		whiteout_args.inode = new_whiteout_inode(mnt_userns, old_dir);
+		whiteout_args.inode = new_whiteout_inode(idmap, old_dir);
 		if (!whiteout_args.inode) {
 			ret = -ENOMEM;
 			goto out_fscrypt_names;
@@ -9545,7 +9169,7 @@ out_fscrypt_names:
 	return ret;
 }
 
-static int btrfs_rename2(struct user_namespace *mnt_userns, struct inode *old_dir,
+static int btrfs_rename2(struct mnt_idmap *idmap, struct inode *old_dir,
 			 struct dentry *old_dentry, struct inode *new_dir,
 			 struct dentry *new_dentry, unsigned int flags)
 {
@@ -9558,7 +9182,7 @@ static int btrfs_rename2(struct user_namespace *mnt_userns, struct inode *old_di
 		ret = btrfs_rename_exchange(old_dir, old_dentry, new_dir,
 					    new_dentry);
 	else
-		ret = btrfs_rename(mnt_userns, old_dir, old_dentry, new_dir,
+		ret = btrfs_rename(idmap, old_dir, old_dentry, new_dir,
 				   new_dentry, flags);
 
 	btrfs_btree_balance_dirty(BTRFS_I(new_dir)->root->fs_info);
@@ -9758,7 +9382,7 @@ out:
 	return ret;
 }
 
-static int btrfs_symlink(struct user_namespace *mnt_userns, struct inode *dir,
+static int btrfs_symlink(struct mnt_idmap *idmap, struct inode *dir,
 			 struct dentry *dentry, const char *symname)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb);
@@ -9786,7 +9410,7 @@ static int btrfs_symlink(struct user_namespace *mnt_userns, struct inode *dir,
 	inode = new_inode(dir->i_sb);
 	if (!inode)
 		return -ENOMEM;
-	inode_init_owner(mnt_userns, inode, dir, S_IFLNK | S_IRWXUGO);
+	inode_init_owner(idmap, inode, dir, S_IFLNK | S_IRWXUGO);
 	inode->i_op = &btrfs_symlink_inode_operations;
 	inode_nohighmem(inode);
 	inode->i_mapping->a_ops = &btrfs_aops;
@@ -10075,7 +9699,7 @@ int btrfs_prealloc_file_range_trans(struct inode *inode,
 					   min_size, actual_len, alloc_hint, trans);
 }
 
-static int btrfs_permission(struct user_namespace *mnt_userns,
+static int btrfs_permission(struct mnt_idmap *idmap,
 			    struct inode *inode, int mask)
 {
 	struct btrfs_root *root = BTRFS_I(inode)->root;
@@ -10088,10 +9712,10 @@ static int btrfs_permission(struct user_namespace *mnt_userns,
 		if (BTRFS_I(inode)->flags & BTRFS_INODE_READONLY)
 			return -EACCES;
 	}
-	return generic_permission(mnt_userns, inode, mask);
+	return generic_permission(idmap, inode, mask);
 }
 
-static int btrfs_tmpfile(struct user_namespace *mnt_userns, struct inode *dir,
+static int btrfs_tmpfile(struct mnt_idmap *idmap, struct inode *dir,
 			 struct file *file, umode_t mode)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb);
@@ -10109,7 +9733,7 @@ static int btrfs_tmpfile(struct user_namespace *mnt_userns, struct inode *dir,
 	inode = new_inode(dir->i_sb);
 	if (!inode)
 		return -ENOMEM;
-	inode_init_owner(mnt_userns, inode, dir, mode);
+	inode_init_owner(idmap, inode, dir, mode);
 	inode->i_fop = &btrfs_file_operations;
 	inode->i_op = &btrfs_file_inode_operations;
 	inode->i_mapping->a_ops = &btrfs_aops;
@@ -10289,65 +9913,13 @@ 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 +9928,10 @@ 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 +9939,26 @@ 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 +9967,8 @@ 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 +9979,6 @@ 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 +10538,8 @@ 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;