Merge tag 'for-6.11-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs updates from David Sterba:
 "The highlights are new logic behind background block group reclaim,
  automatic removal of qgroup after removing a subvolume and new
  'rescue=' mount options.

  The rest is optimizations, cleanups and refactoring.

  User visible features:

   - dynamic block group reclaim:
      - tunable framework to avoid situations where eager data
        allocations prevent creating new metadata chunks due to lack of
        unallocated space
      - reuse sysfs knob bg_reclaim_threshold (otherwise used only in
        zoned mode) for a fixed value threshold
      - new on/off sysfs knob "dynamic_reclaim" calculating the value
        based on heuristics, aiming to keep spare working space for
        relocating chunks but not to needlessly relocate partially
        utilized block groups or reclaim newly allocated ones
      - stats are exported in sysfs per block group type, files
        "reclaim_*"
      - this may increase IO load at unexpected times but the corner
        case of no allocatable block groups is known to be worse

   - automatically remove qgroup of deleted subvolumes:
      - adjust qgroup removal conditions, make sure all related
        subvolume data are already removed, or return EBUSY, also take
        into account setting of sysfs drop_subtree_threshold
      - also works in squota mode

   - mount option updates: new modes of 'rescue=' that allow to mount
     images (read-only) that could have been partially converted by user
     space tools
      - ignoremetacsums  - invalid metadata checksums are ignored
      - ignoresuperflags - super block flags that track conversion in
                           progress (like UUID or checksums)

  Core:

   - size of struct btrfs_inode is now below 1024 (on a release config),
     improved memory packing and other secondary effects

   - switch tracking of open inodes from rb-tree to xarray, minor
     performance improvement

   - reduce number of empty transaction commits when there are no dirty
     data/metadata

   - memory allocation optimizations (reduced numbers, reordering out of
     critical sections)

   - extent map structure optimizations and refactoring, more sanity
     checks

   - more subpage in zoned mode preparations or fixes

   - general snapshot code cleanups, improvements and documentation

   - tree-checker updates: more file extent ram_bytes fixes, continued

   - raid-stripe-tree update (not backward compatible):
      - remove extent encoding field from the structure, can be inferred
        from other information
      - requires btrfs-progs 6.9.1 or newer

   - cleanups and refactoring
      - error message updates
      - error handling improvements
      - return type and parameter cleanups and improvements"

* tag 'for-6.11-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (152 commits)
  btrfs: fix extent map use-after-free when adding pages to compressed bio
  btrfs: fix bitmap leak when loading free space cache on duplicate entry
  btrfs: remove the BUG_ON() inside extent_range_clear_dirty_for_io()
  btrfs: move extent_range_clear_dirty_for_io() into inode.c
  btrfs: enhance compression error messages
  btrfs: fix data race when accessing the last_trans field of a root
  btrfs: rename the extra_gfp parameter of btrfs_alloc_page_array()
  btrfs: remove the extra_gfp parameter from btrfs_alloc_folio_array()
  btrfs: introduce new "rescue=ignoresuperflags" mount option
  btrfs: introduce new "rescue=ignoremetacsums" mount option
  btrfs: output the unrecognized super block flags as hex
  btrfs: remove unused Opt enums
  btrfs: tree-checker: add extra ram_bytes and disk_num_bytes check
  btrfs: fix the ram_bytes assignment for truncated ordered extents
  btrfs: make validate_extent_map() catch ram_bytes mismatch
  btrfs: ignore incorrect btrfs_file_extent_item::ram_bytes
  btrfs: cleanup the bytenr usage inside btrfs_extent_item_to_extent_map()
  btrfs: fix typo in error message in btrfs_validate_super()
  btrfs: move the direct IO code into its own file
  btrfs: pass a btrfs_inode to btrfs_set_prop()
  ...

1 files changed, 316 insertions, 1143 deletions

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index d62c96f00ff8..01eab6955647 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -70,31 +70,13 @@
 #include "orphan.h"
 #include "backref.h"
 #include "raid-stripe-tree.h"
+#include "fiemap.h"
 
 struct btrfs_iget_args {
 	u64 ino;
 	struct btrfs_root *root;
 };
 
-struct btrfs_dio_data {
-	ssize_t submitted;
-	struct extent_changeset *data_reserved;
-	struct btrfs_ordered_extent *ordered;
-	bool data_space_reserved;
-	bool nocow_done;
-};
-
-struct btrfs_dio_private {
-	/* Range of I/O */
-	u64 file_offset;
-	u32 bytes;
-
-	/* This must be last */
-	struct btrfs_bio bbio;
-};
-
-static struct bio_set btrfs_dio_bioset;
-
 struct btrfs_rename_ctx {
 	/* Output field. Stores the index number of the old directory entry. */
 	u64 index;
@@ -137,11 +119,6 @@ static noinline int run_delalloc_cow(struct btrfs_inode *inode,
 				     struct page *locked_page, u64 start,
 				     u64 end, struct writeback_control *wbc,
 				     bool pages_dirty);
-static struct extent_map *create_io_em(struct btrfs_inode *inode, u64 start,
-				       u64 len, u64 orig_start, u64 block_start,
-				       u64 block_len, u64 orig_block_len,
-				       u64 ram_bytes, int compress_type,
-				       int type);
 
 static int data_reloc_print_warning_inode(u64 inum, u64 offset, u64 num_bytes,
 					  u64 root, void *warn_ctx)
@@ -877,7 +854,7 @@ static inline int inode_need_compress(struct btrfs_inode *inode, u64 start,
 	if (btrfs_test_opt(fs_info, COMPRESS) ||
 	    inode->flags & BTRFS_INODE_COMPRESS ||
 	    inode->prop_compress)
-		return btrfs_compress_heuristic(&inode->vfs_inode, start, end);
+		return btrfs_compress_heuristic(inode, start, end);
 	return 0;
 }
 
@@ -890,6 +867,26 @@ static inline void inode_should_defrag(struct btrfs_inode *inode,
 		btrfs_add_inode_defrag(NULL, inode, small_write);
 }
 
+static int extent_range_clear_dirty_for_io(struct inode *inode, u64 start, u64 end)
+{
+	unsigned long end_index = end >> PAGE_SHIFT;
+	struct page *page;
+	int ret = 0;
+
+	for (unsigned long index = start >> PAGE_SHIFT;
+	     index <= end_index; index++) {
+		page = find_get_page(inode->i_mapping, index);
+		if (unlikely(!page)) {
+			if (!ret)
+				ret = -ENOENT;
+			continue;
+		}
+		clear_page_dirty_for_io(page);
+		put_page(page);
+	}
+	return ret;
+}
+
 /*
  * Work queue call back to started compression on a file and pages.
  *
@@ -931,7 +928,16 @@ static void compress_file_range(struct btrfs_work *work)
 	 * Otherwise applications with the file mmap'd can wander in and change
 	 * the page contents while we are compressing them.
 	 */
-	extent_range_clear_dirty_for_io(&inode->vfs_inode, start, end);
+	ret = extent_range_clear_dirty_for_io(&inode->vfs_inode, start, end);
+
+	/*
+	 * All the folios should have been locked thus no failure.
+	 *
+	 * And even if some folios are missing, btrfs_compress_folios()
+	 * would handle them correctly, so here just do an ASSERT() check for
+	 * early logic errors.
+	 */
+	ASSERT(ret == 0);
 
 	/*
 	 * We need to save i_size before now because it could change in between
@@ -1152,6 +1158,7 @@ static void submit_one_async_extent(struct async_chunk *async_chunk,
 	struct btrfs_root *root = inode->root;
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct btrfs_ordered_extent *ordered;
+	struct btrfs_file_extent file_extent;
 	struct btrfs_key ins;
 	struct page *locked_page = NULL;
 	struct extent_state *cached = NULL;
@@ -1198,29 +1205,22 @@ static void submit_one_async_extent(struct async_chunk *async_chunk,
 	lock_extent(io_tree, start, end, &cached);
 
 	/* Here we're doing allocation and writeback of the compressed pages */
-	em = create_io_em(inode, start,
-			  async_extent->ram_size,	/* len */
-			  start,			/* orig_start */
-			  ins.objectid,			/* block_start */
-			  ins.offset,			/* block_len */
-			  ins.offset,			/* orig_block_len */
-			  async_extent->ram_size,	/* ram_bytes */
-			  async_extent->compress_type,
-			  BTRFS_ORDERED_COMPRESSED);
+	file_extent.disk_bytenr = ins.objectid;
+	file_extent.disk_num_bytes = ins.offset;
+	file_extent.ram_bytes = async_extent->ram_size;
+	file_extent.num_bytes = async_extent->ram_size;
+	file_extent.offset = 0;
+	file_extent.compression = async_extent->compress_type;
+
+	em = btrfs_create_io_em(inode, start, &file_extent, BTRFS_ORDERED_COMPRESSED);
 	if (IS_ERR(em)) {
 		ret = PTR_ERR(em);
 		goto out_free_reserve;
 	}
 	free_extent_map(em);
 
-	ordered = btrfs_alloc_ordered_extent(inode, start,	/* file_offset */
-				       async_extent->ram_size,	/* num_bytes */
-				       async_extent->ram_size,	/* ram_bytes */
-				       ins.objectid,		/* disk_bytenr */
-				       ins.offset,		/* disk_num_bytes */
-				       0,			/* offset */
-				       1 << BTRFS_ORDERED_COMPRESSED,
-				       async_extent->compress_type);
+	ordered = btrfs_alloc_ordered_extent(inode, start, &file_extent,
+					     1 << BTRFS_ORDERED_COMPRESSED);
 	if (IS_ERR(ordered)) {
 		btrfs_drop_extent_map_range(inode, start, end, false);
 		ret = PTR_ERR(ordered);
@@ -1264,8 +1264,8 @@ out_free_reserve:
 	kfree(async_extent);
 }
 
-static u64 get_extent_allocation_hint(struct btrfs_inode *inode, u64 start,
-				      u64 num_bytes)
+u64 btrfs_get_extent_allocation_hint(struct btrfs_inode *inode, u64 start,
+				     u64 num_bytes)
 {
 	struct extent_map_tree *em_tree = &inode->extent_tree;
 	struct extent_map *em;
@@ -1279,15 +1279,15 @@ static u64 get_extent_allocation_hint(struct btrfs_inode *inode, u64 start,
 		 * first block in this inode and use that as a hint.  If that
 		 * block is also bogus then just don't worry about it.
 		 */
-		if (em->block_start >= EXTENT_MAP_LAST_BYTE) {
+		if (em->disk_bytenr >= EXTENT_MAP_LAST_BYTE) {
 			free_extent_map(em);
 			em = search_extent_mapping(em_tree, 0, 0);
-			if (em && em->block_start < EXTENT_MAP_LAST_BYTE)
-				alloc_hint = em->block_start;
+			if (em && em->disk_bytenr < EXTENT_MAP_LAST_BYTE)
+				alloc_hint = extent_map_block_start(em);
 			if (em)
 				free_extent_map(em);
 		} else {
-			alloc_hint = em->block_start;
+			alloc_hint = extent_map_block_start(em);
 			free_extent_map(em);
 		}
 	}
@@ -1375,7 +1375,7 @@ static noinline int cow_file_range(struct btrfs_inode *inode,
 		}
 	}
 
-	alloc_hint = get_extent_allocation_hint(inode, start, num_bytes);
+	alloc_hint = btrfs_get_extent_allocation_hint(inode, start, num_bytes);
 
 	/*
 	 * Relocation relies on the relocated extents to have exactly the same
@@ -1395,6 +1395,7 @@ static noinline int cow_file_range(struct btrfs_inode *inode,
 
 	while (num_bytes > 0) {
 		struct btrfs_ordered_extent *ordered;
+		struct btrfs_file_extent file_extent;
 
 		cur_alloc_size = num_bytes;
 		ret = btrfs_reserve_extent(root, cur_alloc_size, cur_alloc_size,
@@ -1431,18 +1432,18 @@ static noinline int cow_file_range(struct btrfs_inode *inode,
 		extent_reserved = true;
 
 		ram_size = ins.offset;
+		file_extent.disk_bytenr = ins.objectid;
+		file_extent.disk_num_bytes = ins.offset;
+		file_extent.num_bytes = ins.offset;
+		file_extent.ram_bytes = ins.offset;
+		file_extent.offset = 0;
+		file_extent.compression = BTRFS_COMPRESS_NONE;
 
 		lock_extent(&inode->io_tree, start, start + ram_size - 1,
 			    &cached);
 
-		em = create_io_em(inode, start, ins.offset, /* len */
-				  start, /* orig_start */
-				  ins.objectid, /* block_start */
-				  ins.offset, /* block_len */
-				  ins.offset, /* orig_block_len */
-				  ram_size, /* ram_bytes */
-				  BTRFS_COMPRESS_NONE, /* compress_type */
-				  BTRFS_ORDERED_REGULAR /* type */);
+		em = btrfs_create_io_em(inode, start, &file_extent,
+					BTRFS_ORDERED_REGULAR);
 		if (IS_ERR(em)) {
 			unlock_extent(&inode->io_tree, start,
 				      start + ram_size - 1, &cached);
@@ -1451,10 +1452,8 @@ static noinline int cow_file_range(struct btrfs_inode *inode,
 		}
 		free_extent_map(em);
 
-		ordered = btrfs_alloc_ordered_extent(inode, start, ram_size,
-					ram_size, ins.objectid, cur_alloc_size,
-					0, 1 << BTRFS_ORDERED_REGULAR,
-					BTRFS_COMPRESS_NONE);
+		ordered = btrfs_alloc_ordered_extent(inode, start, &file_extent,
+						     1 << BTRFS_ORDERED_REGULAR);
 		if (IS_ERR(ordered)) {
 			unlock_extent(&inode->io_tree, start,
 				      start + ram_size - 1, &cached);
@@ -1617,10 +1616,8 @@ static noinline void submit_compressed_extents(struct btrfs_work *work, bool do_
 	u64 alloc_hint = 0;
 
 	if (do_free) {
-		struct async_chunk *async_chunk;
 		struct async_cow *async_cow;
 
-		async_chunk = container_of(work, struct async_chunk, work);
 		btrfs_add_delayed_iput(async_chunk->inode);
 		if (async_chunk->blkcg_css)
 			css_put(async_chunk->blkcg_css);
@@ -1850,13 +1847,11 @@ struct can_nocow_file_extent_args {
 	 */
 	bool free_path;
 
-	/* Output fields. Only set when can_nocow_file_extent() returns 1. */
-
-	u64 disk_bytenr;
-	u64 disk_num_bytes;
-	u64 extent_offset;
-	/* Number of bytes that can be written to in NOCOW mode. */
-	u64 num_bytes;
+	/*
+	 * Output fields. Only set when can_nocow_file_extent() returns 1.
+	 * The expected file extent for the NOCOW write.
+	 */
+	struct btrfs_file_extent file_extent;
 };
 
 /*
@@ -1878,6 +1873,7 @@ static int can_nocow_file_extent(struct btrfs_path *path,
 	struct btrfs_root *root = inode->root;
 	struct btrfs_file_extent_item *fi;
 	struct btrfs_root *csum_root;
+	u64 io_start;
 	u64 extent_end;
 	u8 extent_type;
 	int can_nocow = 0;
@@ -1890,11 +1886,6 @@ static int can_nocow_file_extent(struct btrfs_path *path,
 	if (extent_type == BTRFS_FILE_EXTENT_INLINE)
 		goto out;
 
-	/* Can't access these fields unless we know it's not an inline extent. */
-	args->disk_bytenr = btrfs_file_extent_disk_bytenr(leaf, fi);
-	args->disk_num_bytes = btrfs_file_extent_disk_num_bytes(leaf, fi);
-	args->extent_offset = btrfs_file_extent_offset(leaf, fi);
-
 	if (!(inode->flags & BTRFS_INODE_NODATACOW) &&
 	    extent_type == BTRFS_FILE_EXTENT_REG)
 		goto out;
@@ -1910,7 +1901,7 @@ static int can_nocow_file_extent(struct btrfs_path *path,
 		goto out;
 
 	/* An explicit hole, must COW. */
-	if (args->disk_bytenr == 0)
+	if (btrfs_file_extent_disk_bytenr(leaf, fi) == 0)
 		goto out;
 
 	/* Compressed/encrypted/encoded extents must be COWed. */
@@ -1921,6 +1912,12 @@ static int can_nocow_file_extent(struct btrfs_path *path,
 
 	extent_end = btrfs_file_extent_end(path);
 
+	args->file_extent.disk_bytenr = btrfs_file_extent_disk_bytenr(leaf, fi);
+	args->file_extent.disk_num_bytes = btrfs_file_extent_disk_num_bytes(leaf, fi);
+	args->file_extent.ram_bytes = btrfs_file_extent_ram_bytes(leaf, fi);
+	args->file_extent.offset = btrfs_file_extent_offset(leaf, fi);
+	args->file_extent.compression = btrfs_file_extent_compression(leaf, fi);
+
 	/*
 	 * The following checks can be expensive, as they need to take other
 	 * locks and do btree or rbtree searches, so release the path to avoid
@@ -1929,8 +1926,8 @@ static int can_nocow_file_extent(struct btrfs_path *path,
 	btrfs_release_path(path);
 
 	ret = btrfs_cross_ref_exist(root, btrfs_ino(inode),
-				    key->offset - args->extent_offset,
-				    args->disk_bytenr, args->strict, path);
+				    key->offset - args->file_extent.offset,
+				    args->file_extent.disk_bytenr, args->strict, path);
 	WARN_ON_ONCE(ret > 0 && is_freespace_inode);
 	if (ret != 0)
 		goto out;
@@ -1951,18 +1948,18 @@ static int can_nocow_file_extent(struct btrfs_path *path,
 	    atomic_read(&root->snapshot_force_cow))
 		goto out;
 
-	args->disk_bytenr += args->extent_offset;
-	args->disk_bytenr += args->start - key->offset;
-	args->num_bytes = min(args->end + 1, extent_end) - args->start;
+	args->file_extent.num_bytes = min(args->end + 1, extent_end) - args->start;
+	args->file_extent.offset += args->start - key->offset;
+	io_start = args->file_extent.disk_bytenr + args->file_extent.offset;
 
 	/*
 	 * Force COW if csums exist in the range. This ensures that csums for a
 	 * given extent are either valid or do not exist.
 	 */
 
-	csum_root = btrfs_csum_root(root->fs_info, args->disk_bytenr);
-	ret = btrfs_lookup_csums_list(csum_root, args->disk_bytenr,
-				      args->disk_bytenr + args->num_bytes - 1,
+	csum_root = btrfs_csum_root(root->fs_info, io_start);
+	ret = btrfs_lookup_csums_list(csum_root, io_start,
+				      io_start + args->file_extent.num_bytes - 1,
 				      NULL, nowait);
 	WARN_ON_ONCE(ret > 0 && is_freespace_inode);
 	if (ret != 0)
@@ -2021,7 +2018,6 @@ static noinline int run_delalloc_nocow(struct btrfs_inode *inode,
 		struct extent_buffer *leaf;
 		struct extent_state *cached_state = NULL;
 		u64 extent_end;
-		u64 ram_bytes;
 		u64 nocow_end;
 		int extent_type;
 		bool is_prealloc;
@@ -2100,7 +2096,6 @@ next_slot:
 			ret = -EUCLEAN;
 			goto error;
 		}
-		ram_bytes = btrfs_file_extent_ram_bytes(leaf, fi);
 		extent_end = btrfs_file_extent_end(path);
 
 		/*
@@ -2120,7 +2115,9 @@ next_slot:
 			goto must_cow;
 
 		ret = 0;
-		nocow_bg = btrfs_inc_nocow_writers(fs_info, nocow_args.disk_bytenr);
+		nocow_bg = btrfs_inc_nocow_writers(fs_info,
+				nocow_args.file_extent.disk_bytenr +
+				nocow_args.file_extent.offset);
 		if (!nocow_bg) {
 must_cow:
 			/*
@@ -2156,21 +2153,16 @@ must_cow:
 			}
 		}
 
-		nocow_end = cur_offset + nocow_args.num_bytes - 1;
+		nocow_end = cur_offset + nocow_args.file_extent.num_bytes - 1;
 		lock_extent(&inode->io_tree, cur_offset, nocow_end, &cached_state);
 
 		is_prealloc = extent_type == BTRFS_FILE_EXTENT_PREALLOC;
 		if (is_prealloc) {
-			u64 orig_start = found_key.offset - nocow_args.extent_offset;
 			struct extent_map *em;
 
-			em = create_io_em(inode, cur_offset, nocow_args.num_bytes,
-					  orig_start,
-					  nocow_args.disk_bytenr, /* block_start */
-					  nocow_args.num_bytes, /* block_len */
-					  nocow_args.disk_num_bytes, /* orig_block_len */
-					  ram_bytes, BTRFS_COMPRESS_NONE,
-					  BTRFS_ORDERED_PREALLOC);
+			em = btrfs_create_io_em(inode, cur_offset,
+						&nocow_args.file_extent,
+						BTRFS_ORDERED_PREALLOC);
 			if (IS_ERR(em)) {
 				unlock_extent(&inode->io_tree, cur_offset,
 					      nocow_end, &cached_state);
@@ -2182,12 +2174,10 @@ must_cow:
 		}
 
 		ordered = btrfs_alloc_ordered_extent(inode, cur_offset,
-				nocow_args.num_bytes, nocow_args.num_bytes,
-				nocow_args.disk_bytenr, nocow_args.num_bytes, 0,
+				&nocow_args.file_extent,
 				is_prealloc
 				? (1 << BTRFS_ORDERED_PREALLOC)
-				: (1 << BTRFS_ORDERED_NOCOW),
-				BTRFS_COMPRESS_NONE);
+				: (1 << BTRFS_ORDERED_NOCOW));
 		btrfs_dec_nocow_writers(nocow_bg);
 		if (IS_ERR(ordered)) {
 			if (is_prealloc) {
@@ -2601,44 +2591,6 @@ void btrfs_clear_delalloc_extent(struct btrfs_inode *inode,
 	}
 }
 
-static int btrfs_extract_ordered_extent(struct btrfs_bio *bbio,
-					struct btrfs_ordered_extent *ordered)
-{
-	u64 start = (u64)bbio->bio.bi_iter.bi_sector << SECTOR_SHIFT;
-	u64 len = bbio->bio.bi_iter.bi_size;
-	struct btrfs_ordered_extent *new;
-	int ret;
-
-	/* Must always be called for the beginning of an ordered extent. */
-	if (WARN_ON_ONCE(start != ordered->disk_bytenr))
-		return -EINVAL;
-
-	/* No need to split if the ordered extent covers the entire bio. */
-	if (ordered->disk_num_bytes == len) {
-		refcount_inc(&ordered->refs);
-		bbio->ordered = ordered;
-		return 0;
-	}
-
-	/*
-	 * Don't split the extent_map for NOCOW extents, as we're writing into
-	 * a pre-existing one.
-	 */
-	if (!test_bit(BTRFS_ORDERED_NOCOW, &ordered->flags)) {
-		ret = split_extent_map(bbio->inode, bbio->file_offset,
-				       ordered->num_bytes, len,
-				       ordered->disk_bytenr);
-		if (ret)
-			return ret;
-	}
-
-	new = btrfs_split_ordered_extent(ordered, len);
-	if (IS_ERR(new))
-		return PTR_ERR(new);
-	bbio->ordered = new;
-	return 0;
-}
-
 /*
  * 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.
@@ -2681,7 +2633,7 @@ static int btrfs_find_new_delalloc_bytes(struct btrfs_inode *inode,
 		if (IS_ERR(em))
 			return PTR_ERR(em);
 
-		if (em->block_start != EXTENT_MAP_HOLE)
+		if (em->disk_bytenr != EXTENT_MAP_HOLE)
 			goto next;
 
 		em_len = em->len;
@@ -3037,10 +2989,8 @@ static int insert_ordered_extent_file_extent(struct btrfs_trans_handle *trans,
 	btrfs_set_stack_file_extent_disk_num_bytes(&stack_fi,
 						   oe->disk_num_bytes);
 	btrfs_set_stack_file_extent_offset(&stack_fi, oe->offset);
-	if (test_bit(BTRFS_ORDERED_TRUNCATED, &oe->flags)) {
+	if (test_bit(BTRFS_ORDERED_TRUNCATED, &oe->flags))
 		num_bytes = oe->truncated_len;
-		ram_bytes = num_bytes;
-	}
 	btrfs_set_stack_file_extent_num_bytes(&stack_fi, num_bytes);
 	btrfs_set_stack_file_extent_ram_bytes(&stack_fi, ram_bytes);
 	btrfs_set_stack_file_extent_compression(&stack_fi, oe->compress_type);
@@ -3056,7 +3006,7 @@ static int insert_ordered_extent_file_extent(struct btrfs_trans_handle *trans,
 			     test_bit(BTRFS_ORDERED_ENCODED, &oe->flags) ||
 			     test_bit(BTRFS_ORDERED_TRUNCATED, &oe->flags);
 
-	return insert_reserved_file_extent(trans, BTRFS_I(oe->inode),
+	return insert_reserved_file_extent(trans, oe->inode,
 					   oe->file_offset, &stack_fi,
 					   update_inode_bytes, oe->qgroup_rsv);
 }
@@ -3068,7 +3018,7 @@ static int insert_ordered_extent_file_extent(struct btrfs_trans_handle *trans,
  */
 int btrfs_finish_one_ordered(struct btrfs_ordered_extent *ordered_extent)
 {
-	struct btrfs_inode *inode = BTRFS_I(ordered_extent->inode);
+	struct btrfs_inode *inode = ordered_extent->inode;
 	struct btrfs_root *root = inode->root;
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct btrfs_trans_handle *trans = NULL;
@@ -3302,7 +3252,7 @@ out:
 
 int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered)
 {
-	if (btrfs_is_zoned(inode_to_fs_info(ordered->inode)) &&
+	if (btrfs_is_zoned(ordered->inode->root->fs_info) &&
 	    !test_bit(BTRFS_ORDERED_IOERR, &ordered->flags) &&
 	    list_empty(&ordered->bioc_list))
 		btrfs_finish_ordered_zoned(ordered);
@@ -3596,7 +3546,7 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
 		found_key.objectid = found_key.offset;
 		found_key.type = BTRFS_INODE_ITEM_KEY;
 		found_key.offset = 0;
-		inode = btrfs_iget(fs_info->sb, last_objectid, root);
+		inode = btrfs_iget(last_objectid, root);
 		if (IS_ERR(inode)) {
 			ret = PTR_ERR(inode);
 			inode = NULL;
@@ -3781,6 +3731,30 @@ static noinline int acls_after_inode_item(struct extent_buffer *leaf,
 	return 1;
 }
 
+static int btrfs_init_file_extent_tree(struct btrfs_inode *inode)
+{
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
+
+	if (WARN_ON_ONCE(inode->file_extent_tree))
+		return 0;
+	if (btrfs_fs_incompat(fs_info, NO_HOLES))
+		return 0;
+	if (!S_ISREG(inode->vfs_inode.i_mode))
+		return 0;
+	if (btrfs_is_free_space_inode(inode))
+		return 0;
+
+	inode->file_extent_tree = kmalloc(sizeof(struct extent_io_tree), GFP_KERNEL);
+	if (!inode->file_extent_tree)
+		return -ENOMEM;
+
+	extent_io_tree_init(fs_info, inode->file_extent_tree, IO_TREE_INODE_FILE_EXTENT);
+	/* Lockdep class is set only for the file extent tree. */
+	lockdep_set_class(&inode->file_extent_tree->lock, &file_extent_tree_class);
+
+	return 0;
+}
+
 /*
  * read an inode from the btree into the in-memory inode
  */
@@ -3800,6 +3774,10 @@ static int btrfs_read_locked_inode(struct inode *inode,
 	bool filled = false;
 	int first_xattr_slot;
 
+	ret = btrfs_init_file_extent_tree(BTRFS_I(inode));
+	if (ret)
+		return ret;
+
 	ret = btrfs_fill_inode(inode, &rdev);
 	if (!ret)
 		filled = true;
@@ -3810,7 +3788,7 @@ static int btrfs_read_locked_inode(struct inode *inode,
 			return -ENOMEM;
 	}
 
-	memcpy(&location, &BTRFS_I(inode)->location, sizeof(location));
+	btrfs_get_inode_key(BTRFS_I(inode), &location);
 
 	ret = btrfs_lookup_inode(NULL, root, path, &location, 0);
 	if (ret) {
@@ -3856,7 +3834,9 @@ static int btrfs_read_locked_inode(struct inode *inode,
 	inode->i_rdev = 0;
 	rdev = btrfs_inode_rdev(leaf, inode_item);
 
-	BTRFS_I(inode)->index_cnt = (u64)-1;
+	if (S_ISDIR(inode->i_mode))
+		BTRFS_I(inode)->index_cnt = (u64)-1;
+
 	btrfs_inode_split_flags(btrfs_inode_flags(leaf, inode_item),
 				&BTRFS_I(inode)->flags, &BTRFS_I(inode)->ro_flags);
 
@@ -4038,13 +4018,15 @@ static noinline int btrfs_update_inode_item(struct btrfs_trans_handle *trans,
 	struct btrfs_inode_item *inode_item;
 	struct btrfs_path *path;
 	struct extent_buffer *leaf;
+	struct btrfs_key key;
 	int ret;
 
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
 
-	ret = btrfs_lookup_inode(trans, inode->root, path, &inode->location, 1);
+	btrfs_get_inode_key(inode, &key);
+	ret = btrfs_lookup_inode(trans, inode->root, path, &key, 1);
 	if (ret) {
 		if (ret > 0)
 			ret = -ENOENT;
@@ -4308,7 +4290,7 @@ static int btrfs_unlink_subvol(struct btrfs_trans_handle *trans,
 	if (btrfs_ino(inode) == BTRFS_FIRST_FREE_OBJECTID) {
 		objectid = btrfs_root_id(inode->root);
 	} else if (btrfs_ino(inode) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID) {
-		objectid = inode->location.objectid;
+		objectid = inode->ref_root_id;
 	} else {
 		WARN_ON(1);
 		fscrypt_free_filename(&fname);
@@ -4539,11 +4521,6 @@ int btrfs_delete_subvolume(struct btrfs_inode *dir, struct dentry *dentry)
 		ret = PTR_ERR(trans);
 		goto out_release;
 	}
-	ret = btrfs_record_root_in_trans(trans, root);
-	if (ret) {
-		btrfs_abort_transaction(trans, ret);
-		goto out_end_trans;
-	}
 	btrfs_qgroup_convert_reserved_meta(root, qgroup_reserved);
 	qgroup_reserved = 0;
 	trans->block_rsv = &block_rsv;
@@ -4967,11 +4944,9 @@ int btrfs_cont_expand(struct btrfs_inode *inode, loff_t oldsize, loff_t size)
 			}
 			hole_em->start = cur_offset;
 			hole_em->len = hole_size;
-			hole_em->orig_start = cur_offset;
 
-			hole_em->block_start = EXTENT_MAP_HOLE;
-			hole_em->block_len = 0;
-			hole_em->orig_block_len = 0;
+			hole_em->disk_bytenr = EXTENT_MAP_HOLE;
+			hole_em->disk_num_bytes = 0;
 			hole_em->ram_bytes = hole_size;
 			hole_em->generation = btrfs_get_fs_generation(fs_info);
 
@@ -5049,7 +5024,7 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr)
 		struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
 
 		if (btrfs_is_zoned(fs_info)) {
-			ret = btrfs_wait_ordered_range(inode,
+			ret = btrfs_wait_ordered_range(BTRFS_I(inode),
 					ALIGN(newsize, fs_info->sectorsize),
 					(u64)-1);
 			if (ret)
@@ -5079,7 +5054,7 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr)
 			 * wait for disk_i_size to be stable and then update the
 			 * in-memory size to match.
 			 */
-			err = btrfs_wait_ordered_range(inode, 0, (u64)-1);
+			err = btrfs_wait_ordered_range(BTRFS_I(inode), 0, (u64)-1);
 			if (err)
 				return err;
 			i_size_write(inode, BTRFS_I(inode)->disk_i_size);
@@ -5493,59 +5468,52 @@ out:
 	return err;
 }
 
-static void inode_tree_add(struct btrfs_inode *inode)
+static int btrfs_add_inode_to_root(struct btrfs_inode *inode, bool prealloc)
 {
 	struct btrfs_root *root = inode->root;
-	struct btrfs_inode *entry;
-	struct rb_node **p;
-	struct rb_node *parent;
-	struct rb_node *new = &inode->rb_node;
-	u64 ino = btrfs_ino(inode);
+	struct btrfs_inode *existing;
+	const u64 ino = btrfs_ino(inode);
+	int ret;
 
 	if (inode_unhashed(&inode->vfs_inode))
-		return;
-	parent = NULL;
-	spin_lock(&root->inode_lock);
-	p = &root->inode_tree.rb_node;
-	while (*p) {
-		parent = *p;
-		entry = rb_entry(parent, struct btrfs_inode, rb_node);
+		return 0;
 
-		if (ino < btrfs_ino(entry))
-			p = &parent->rb_left;
-		else if (ino > btrfs_ino(entry))
-			p = &parent->rb_right;
-		else {
-			WARN_ON(!(entry->vfs_inode.i_state &
-				  (I_WILL_FREE | I_FREEING)));
-			rb_replace_node(parent, new, &root->inode_tree);
-			RB_CLEAR_NODE(parent);
-			spin_unlock(&root->inode_lock);
-			return;
-		}
+	if (prealloc) {
+		ret = xa_reserve(&root->inodes, ino, GFP_NOFS);
+		if (ret)
+			return ret;
 	}
-	rb_link_node(new, parent, p);
-	rb_insert_color(new, &root->inode_tree);
-	spin_unlock(&root->inode_lock);
+
+	existing = xa_store(&root->inodes, ino, inode, GFP_ATOMIC);
+
+	if (xa_is_err(existing)) {
+		ret = xa_err(existing);
+		ASSERT(ret != -EINVAL);
+		ASSERT(ret != -ENOMEM);
+		return ret;
+	} else if (existing) {
+		WARN_ON(!(existing->vfs_inode.i_state & (I_WILL_FREE | I_FREEING)));
+	}
+
+	return 0;
 }
 
-static void inode_tree_del(struct btrfs_inode *inode)
+static void btrfs_del_inode_from_root(struct btrfs_inode *inode)
 {
 	struct btrfs_root *root = inode->root;
-	int empty = 0;
+	struct btrfs_inode *entry;
+	bool empty = false;
 
-	spin_lock(&root->inode_lock);
-	if (!RB_EMPTY_NODE(&inode->rb_node)) {
-		rb_erase(&inode->rb_node, &root->inode_tree);
-		RB_CLEAR_NODE(&inode->rb_node);
-		empty = RB_EMPTY_ROOT(&root->inode_tree);
-	}
-	spin_unlock(&root->inode_lock);
+	xa_lock(&root->inodes);
+	entry = __xa_erase(&root->inodes, btrfs_ino(inode));
+	if (entry == inode)
+		empty = xa_empty(&root->inodes);
+	xa_unlock(&root->inodes);
 
 	if (empty && btrfs_root_refs(&root->root_item) == 0) {
-		spin_lock(&root->inode_lock);
-		empty = RB_EMPTY_ROOT(&root->inode_tree);
-		spin_unlock(&root->inode_lock);
+		xa_lock(&root->inodes);
+		empty = xa_empty(&root->inodes);
+		xa_unlock(&root->inodes);
 		if (empty)
 			btrfs_add_dead_root(root);
 	}
@@ -5556,10 +5524,7 @@ static int btrfs_init_locked_inode(struct inode *inode, void *p)
 {
 	struct btrfs_iget_args *args = p;
 
-	inode->i_ino = args->ino;
-	BTRFS_I(inode)->location.objectid = args->ino;
-	BTRFS_I(inode)->location.type = BTRFS_INODE_ITEM_KEY;
-	BTRFS_I(inode)->location.offset = 0;
+	btrfs_set_inode_number(BTRFS_I(inode), args->ino);
 	BTRFS_I(inode)->root = btrfs_grab_root(args->root);
 
 	if (args->root && args->root == args->root->fs_info->tree_root &&
@@ -5573,12 +5538,11 @@ static int btrfs_find_actor(struct inode *inode, void *opaque)
 {
 	struct btrfs_iget_args *args = opaque;
 
-	return args->ino == BTRFS_I(inode)->location.objectid &&
+	return args->ino == btrfs_ino(BTRFS_I(inode)) &&
 		args->root == BTRFS_I(inode)->root;
 }
 
-static struct inode *btrfs_iget_locked(struct super_block *s, u64 ino,
-				       struct btrfs_root *root)
+static struct inode *btrfs_iget_locked(u64 ino, struct btrfs_root *root)
 {
 	struct inode *inode;
 	struct btrfs_iget_args args;
@@ -5587,7 +5551,7 @@ static struct inode *btrfs_iget_locked(struct super_block *s, u64 ino,
 	args.ino = ino;
 	args.root = root;
 
-	inode = iget5_locked_rcu(s, hashval, btrfs_find_actor,
+	inode = iget5_locked_rcu(root->fs_info->sb, hashval, btrfs_find_actor,
 			     btrfs_init_locked_inode,
 			     (void *)&args);
 	return inode;
@@ -5599,41 +5563,44 @@ static struct inode *btrfs_iget_locked(struct super_block *s, u64 ino,
  * allocator. NULL is also valid but may require an additional allocation
  * later.
  */
-struct inode *btrfs_iget_path(struct super_block *s, u64 ino,
-			      struct btrfs_root *root, struct btrfs_path *path)
+struct inode *btrfs_iget_path(u64 ino, struct btrfs_root *root,
+			      struct btrfs_path *path)
 {
 	struct inode *inode;
+	int ret;
 
-	inode = btrfs_iget_locked(s, ino, root);
+	inode = btrfs_iget_locked(ino, root);
 	if (!inode)
 		return ERR_PTR(-ENOMEM);
 
-	if (inode->i_state & I_NEW) {
-		int ret;
+	if (!(inode->i_state & I_NEW))
+		return inode;
 
-		ret = btrfs_read_locked_inode(inode, path);
-		if (!ret) {
-			inode_tree_add(BTRFS_I(inode));
-			unlock_new_inode(inode);
-		} else {
-			iget_failed(inode);
-			/*
-			 * ret > 0 can come from btrfs_search_slot called by
-			 * btrfs_read_locked_inode, this means the inode item
-			 * was not found.
-			 */
-			if (ret > 0)
-				ret = -ENOENT;
-			inode = ERR_PTR(ret);
-		}
-	}
+	ret = btrfs_read_locked_inode(inode, path);
+	/*
+	 * ret > 0 can come from btrfs_search_slot called by
+	 * btrfs_read_locked_inode(), this means the inode item was not found.
+	 */
+	if (ret > 0)
+		ret = -ENOENT;
+	if (ret < 0)
+		goto error;
+
+	ret = btrfs_add_inode_to_root(BTRFS_I(inode), true);
+	if (ret < 0)
+		goto error;
+
+	unlock_new_inode(inode);
 
 	return inode;
+error:
+	iget_failed(inode);
+	return ERR_PTR(ret);
 }
 
-struct inode *btrfs_iget(struct super_block *s, u64 ino, struct btrfs_root *root)
+struct inode *btrfs_iget(u64 ino, struct btrfs_root *root)
 {
-	return btrfs_iget_path(s, ino, root, NULL);
+	return btrfs_iget_path(ino, root, NULL);
 }
 
 static struct inode *new_simple_dir(struct inode *dir,
@@ -5647,10 +5614,11 @@ static struct inode *new_simple_dir(struct inode *dir,
 		return ERR_PTR(-ENOMEM);
 
 	BTRFS_I(inode)->root = btrfs_grab_root(root);
-	memcpy(&BTRFS_I(inode)->location, key, sizeof(*key));
+	BTRFS_I(inode)->ref_root_id = key->objectid;
+	set_bit(BTRFS_INODE_ROOT_STUB, &BTRFS_I(inode)->runtime_flags);
 	set_bit(BTRFS_INODE_DUMMY, &BTRFS_I(inode)->runtime_flags);
 
-	inode->i_ino = BTRFS_EMPTY_SUBVOL_DIR_OBJECTID;
+	btrfs_set_inode_number(BTRFS_I(inode), BTRFS_EMPTY_SUBVOL_DIR_OBJECTID);
 	/*
 	 * We only need lookup, the rest is read-only and there's no inode
 	 * associated with the dentry
@@ -5704,7 +5672,7 @@ struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry)
 		return ERR_PTR(ret);
 
 	if (location.type == BTRFS_INODE_ITEM_KEY) {
-		inode = btrfs_iget(dir->i_sb, location.objectid, root);
+		inode = btrfs_iget(location.objectid, root);
 		if (IS_ERR(inode))
 			return inode;
 
@@ -5728,7 +5696,7 @@ struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry)
 		else
 			inode = new_simple_dir(dir, &location, root);
 	} else {
-		inode = btrfs_iget(dir->i_sb, location.objectid, sub_root);
+		inode = btrfs_iget(location.objectid, sub_root);
 		btrfs_put_root(sub_root);
 
 		if (IS_ERR(inode))
@@ -5948,7 +5916,7 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx)
 	addr = private->filldir_buf;
 	path->reada = READA_FORWARD;
 
-	put = btrfs_readdir_get_delayed_items(inode, private->last_index,
+	put = btrfs_readdir_get_delayed_items(BTRFS_I(inode), private->last_index,
 					      &ins_list, &del_list);
 
 again:
@@ -6038,7 +6006,7 @@ nopos:
 	ret = 0;
 err:
 	if (put)
-		btrfs_readdir_put_delayed_items(inode, &ins_list, &del_list);
+		btrfs_readdir_put_delayed_items(BTRFS_I(inode), &ins_list, &del_list);
 	btrfs_free_path(path);
 	return ret;
 }
@@ -6123,7 +6091,7 @@ static int btrfs_insert_inode_locked(struct inode *inode)
 {
 	struct btrfs_iget_args args;
 
-	args.ino = BTRFS_I(inode)->location.objectid;
+	args.ino = btrfs_ino(BTRFS_I(inode));
 	args.root = BTRFS_I(inode)->root;
 
 	return insert_inode_locked4(inode,
@@ -6230,7 +6198,6 @@ int btrfs_create_new_inode(struct btrfs_trans_handle *trans,
 	struct btrfs_fs_info *fs_info = inode_to_fs_info(dir);
 	struct btrfs_root *root;
 	struct btrfs_inode_item *inode_item;
-	struct btrfs_key *location;
 	struct btrfs_path *path;
 	u64 objectid;
 	struct btrfs_inode_ref *ref;
@@ -6239,6 +6206,7 @@ int btrfs_create_new_inode(struct btrfs_trans_handle *trans,
 	struct btrfs_item_batch batch;
 	unsigned long ptr;
 	int ret;
+	bool xa_reserved = false;
 
 	path = btrfs_alloc_path();
 	if (!path)
@@ -6248,10 +6216,19 @@ int btrfs_create_new_inode(struct btrfs_trans_handle *trans,
 		BTRFS_I(inode)->root = btrfs_grab_root(BTRFS_I(dir)->root);
 	root = BTRFS_I(inode)->root;
 
+	ret = btrfs_init_file_extent_tree(BTRFS_I(inode));
+	if (ret)
+		goto out;
+
 	ret = btrfs_get_free_objectid(root, &objectid);
 	if (ret)
 		goto out;
-	inode->i_ino = objectid;
+	btrfs_set_inode_number(BTRFS_I(inode), objectid);
+
+	ret = xa_reserve(&root->inodes, objectid, GFP_NOFS);
+	if (ret)
+		goto out;
+	xa_reserved = true;
 
 	if (args->orphan) {
 		/*
@@ -6266,8 +6243,10 @@ int btrfs_create_new_inode(struct btrfs_trans_handle *trans,
 		if (ret)
 			goto out;
 	}
-	/* index_cnt is ignored for everything but a dir. */
-	BTRFS_I(inode)->index_cnt = BTRFS_DIR_START_INDEX;
+
+	if (S_ISDIR(inode->i_mode))
+		BTRFS_I(inode)->index_cnt = BTRFS_DIR_START_INDEX;
+
 	BTRFS_I(inode)->generation = trans->transid;
 	inode->i_generation = BTRFS_I(inode)->generation;
 
@@ -6294,11 +6273,6 @@ int btrfs_create_new_inode(struct btrfs_trans_handle *trans,
 				BTRFS_INODE_NODATASUM;
 	}
 
-	location = &BTRFS_I(inode)->location;
-	location->objectid = objectid;
-	location->offset = 0;
-	location->type = BTRFS_INODE_ITEM_KEY;
-
 	ret = btrfs_insert_inode_locked(inode);
 	if (ret < 0) {
 		if (!args->orphan)
@@ -6397,8 +6371,7 @@ int btrfs_create_new_inode(struct btrfs_trans_handle *trans,
 		 * Subvolumes inherit properties from their parent subvolume,
 		 * not the directory they were created in.
 		 */
-		parent = btrfs_iget(fs_info->sb, BTRFS_FIRST_FREE_OBJECTID,
-				    BTRFS_I(dir)->root);
+		parent = btrfs_iget(BTRFS_FIRST_FREE_OBJECTID, BTRFS_I(dir)->root);
 		if (IS_ERR(parent)) {
 			ret = PTR_ERR(parent);
 		} else {
@@ -6426,7 +6399,12 @@ int btrfs_create_new_inode(struct btrfs_trans_handle *trans,
 		}
 	}
 
-	inode_tree_add(BTRFS_I(inode));
+	ret = btrfs_add_inode_to_root(BTRFS_I(inode), false);
+	if (WARN_ON(ret)) {
+		/* Shouldn't happen, we used xa_reserve() before. */
+		btrfs_abort_transaction(trans, ret);
+		goto discard;
+	}
 
 	trace_btrfs_inode_new(inode);
 	btrfs_set_inode_last_trans(trans, BTRFS_I(inode));
@@ -6454,6 +6432,9 @@ discard:
 	ihold(inode);
 	discard_new_inode(inode);
 out:
+	if (xa_reserved)
+		xa_release(&root->inodes, objectid);
+
 	btrfs_free_path(path);
 	return ret;
 }
@@ -6818,7 +6799,7 @@ struct extent_map *btrfs_get_extent(struct btrfs_inode *inode,
 	if (em) {
 		if (em->start > start || em->start + em->len <= start)
 			free_extent_map(em);
-		else if (em->block_start == EXTENT_MAP_INLINE && page)
+		else if (em->disk_bytenr == EXTENT_MAP_INLINE && page)
 			free_extent_map(em);
 		else
 			goto out;
@@ -6829,9 +6810,8 @@ struct extent_map *btrfs_get_extent(struct btrfs_inode *inode,
 		goto out;
 	}
 	em->start = EXTENT_MAP_HOLE;
-	em->orig_start = EXTENT_MAP_HOLE;
+	em->disk_bytenr = EXTENT_MAP_HOLE;
 	em->len = (u64)-1;
-	em->block_len = (u64)-1;
 
 	path = btrfs_alloc_path();
 	if (!path) {
@@ -6921,9 +6901,8 @@ next:
 
 		/* New extent overlaps with existing one */
 		em->start = start;
-		em->orig_start = start;
 		em->len = found_key.offset - start;
-		em->block_start = EXTENT_MAP_HOLE;
+		em->disk_bytenr = EXTENT_MAP_HOLE;
 		goto insert;
 	}
 
@@ -6947,7 +6926,7 @@ next:
 		 *
 		 * Other members are not utilized for inline extents.
 		 */
-		ASSERT(em->block_start == EXTENT_MAP_INLINE);
+		ASSERT(em->disk_bytenr == EXTENT_MAP_INLINE);
 		ASSERT(em->len == fs_info->sectorsize);
 
 		ret = read_inline_extent(inode, path, page);
@@ -6957,9 +6936,8 @@ next:
 	}
 not_found:
 	em->start = start;
-	em->orig_start = start;
 	em->len = len;
-	em->block_start = EXTENT_MAP_HOLE;
+	em->disk_bytenr = EXTENT_MAP_HOLE;
 insert:
 	ret = 0;
 	btrfs_release_path(path);
@@ -6986,84 +6964,6 @@ out:
 	return em;
 }
 
-static struct extent_map *btrfs_create_dio_extent(struct btrfs_inode *inode,
-						  struct btrfs_dio_data *dio_data,
-						  const u64 start,
-						  const u64 len,
-						  const u64 orig_start,
-						  const u64 block_start,
-						  const u64 block_len,
-						  const u64 orig_block_len,
-						  const u64 ram_bytes,
-						  const int type)
-{
-	struct extent_map *em = NULL;
-	struct btrfs_ordered_extent *ordered;
-
-	if (type != BTRFS_ORDERED_NOCOW) {
-		em = create_io_em(inode, start, len, orig_start, block_start,
-				  block_len, orig_block_len, ram_bytes,
-				  BTRFS_COMPRESS_NONE, /* compress_type */
-				  type);
-		if (IS_ERR(em))
-			goto out;
-	}
-	ordered = btrfs_alloc_ordered_extent(inode, start, len, len,
-					     block_start, block_len, 0,
-					     (1 << type) |
-					     (1 << BTRFS_ORDERED_DIRECT),
-					     BTRFS_COMPRESS_NONE);
-	if (IS_ERR(ordered)) {
-		if (em) {
-			free_extent_map(em);
-			btrfs_drop_extent_map_range(inode, start,
-						    start + len - 1, false);
-		}
-		em = ERR_CAST(ordered);
-	} else {
-		ASSERT(!dio_data->ordered);
-		dio_data->ordered = ordered;
-	}
- out:
-
-	return em;
-}
-
-static struct extent_map *btrfs_new_extent_direct(struct btrfs_inode *inode,
-						  struct btrfs_dio_data *dio_data,
-						  u64 start, u64 len)
-{
-	struct btrfs_root *root = inode->root;
-	struct btrfs_fs_info *fs_info = root->fs_info;
-	struct extent_map *em;
-	struct btrfs_key ins;
-	u64 alloc_hint;
-	int ret;
-
-	alloc_hint = get_extent_allocation_hint(inode, start, len);
-again:
-	ret = btrfs_reserve_extent(root, len, len, fs_info->sectorsize,
-				   0, alloc_hint, &ins, 1, 1);
-	if (ret == -EAGAIN) {
-		ASSERT(btrfs_is_zoned(fs_info));
-		wait_on_bit_io(&inode->root->fs_info->flags, BTRFS_FS_NEED_ZONE_FINISH,
-			       TASK_UNINTERRUPTIBLE);
-		goto again;
-	}
-	if (ret)
-		return ERR_PTR(ret);
-
-	em = btrfs_create_dio_extent(inode, dio_data, start, ins.offset, start,
-				     ins.objectid, ins.offset, ins.offset,
-				     ins.offset, BTRFS_ORDERED_REGULAR);
-	btrfs_dec_block_group_reservations(fs_info, ins.objectid);
-	if (IS_ERR(em))
-		btrfs_free_reserved_extent(fs_info, ins.objectid, ins.offset,
-					   1);
-
-	return em;
-}
-
 static bool btrfs_extent_readonly(struct btrfs_fs_info *fs_info, u64 bytenr)
 {
 	struct btrfs_block_group *block_group;
@@ -7098,8 +6998,8 @@ static bool btrfs_extent_readonly(struct btrfs_fs_info *fs_info, u64 bytenr)
  *	 any ordered extents.
  */
 noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len,
-			      u64 *orig_start, u64 *orig_block_len,
-			      u64 *ram_bytes, bool nowait, bool strict)
+			      struct btrfs_file_extent *file_extent,
+			      bool nowait, bool strict)
 {
 	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
 	struct can_nocow_file_extent_args nocow_args = { 0 };
@@ -7149,8 +7049,6 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len,
 
 	fi = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_file_extent_item);
 	found_type = btrfs_file_extent_type(leaf, fi);
-	if (ram_bytes)
-		*ram_bytes = btrfs_file_extent_ram_bytes(leaf, fi);
 
 	nocow_args.start = offset;
 	nocow_args.end = offset + *len - 1;
@@ -7168,14 +7066,16 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len,
 	}
 
 	ret = 0;
-	if (btrfs_extent_readonly(fs_info, nocow_args.disk_bytenr))
+	if (btrfs_extent_readonly(fs_info,
+				  nocow_args.file_extent.disk_bytenr +
+				  nocow_args.file_extent.offset))
 		goto out;
 
 	if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW) &&
 	    found_type == BTRFS_FILE_EXTENT_PREALLOC) {
 		u64 range_end;
 
-		range_end = round_up(offset + nocow_args.num_bytes,
+		range_end = round_up(offset + nocow_args.file_extent.num_bytes,
 				     root->fs_info->sectorsize) - 1;
 		ret = test_range_bit_exists(io_tree, offset, range_end, EXTENT_DELALLOC);
 		if (ret) {
@@ -7184,117 +7084,20 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len,
 		}
 	}
 
-	if (orig_start)
-		*orig_start = key.offset - nocow_args.extent_offset;
-	if (orig_block_len)
-		*orig_block_len = nocow_args.disk_num_bytes;
+	if (file_extent)
+		memcpy(file_extent, &nocow_args.file_extent, sizeof(*file_extent));
 
-	*len = nocow_args.num_bytes;
+	*len = nocow_args.file_extent.num_bytes;
 	ret = 1;
 out:
 	btrfs_free_path(path);
 	return ret;
 }
 
-static int lock_extent_direct(struct inode *inode, u64 lockstart, u64 lockend,
-			      struct extent_state **cached_state,
-			      unsigned int iomap_flags)
-{
-	const bool writing = (iomap_flags & IOMAP_WRITE);
-	const bool nowait = (iomap_flags & IOMAP_NOWAIT);
-	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
-	struct btrfs_ordered_extent *ordered;
-	int ret = 0;
-
-	while (1) {
-		if (nowait) {
-			if (!try_lock_extent(io_tree, lockstart, lockend,
-					     cached_state))
-				return -EAGAIN;
-		} else {
-			lock_extent(io_tree, lockstart, lockend, cached_state);
-		}
-		/*
-		 * We're concerned with the entire range that we're going to be
-		 * doing DIO to, so we need to make sure there's no ordered
-		 * extents in this range.
-		 */
-		ordered = btrfs_lookup_ordered_range(BTRFS_I(inode), lockstart,
-						     lockend - lockstart + 1);
-
-		/*
-		 * We need to make sure there are no buffered pages in this
-		 * range either, we could have raced between the invalidate in
-		 * generic_file_direct_write and locking the extent.  The
-		 * invalidate needs to happen so that reads after a write do not
-		 * get stale data.
-		 */
-		if (!ordered &&
-		    (!writing || !filemap_range_has_page(inode->i_mapping,
-							 lockstart, lockend)))
-			break;
-
-		unlock_extent(io_tree, lockstart, lockend, cached_state);
-
-		if (ordered) {
-			if (nowait) {
-				btrfs_put_ordered_extent(ordered);
-				ret = -EAGAIN;
-				break;
-			}
-			/*
-			 * If we are doing a DIO read and the ordered extent we
-			 * found is for a buffered write, we can not wait for it
-			 * to complete and retry, because if we do so we can
-			 * deadlock with concurrent buffered writes on page
-			 * locks. This happens only if our DIO read covers more
-			 * than one extent map, if at this point has already
-			 * created an ordered extent for a previous extent map
-			 * and locked its range in the inode's io tree, and a
-			 * concurrent write against that previous extent map's
-			 * range and this range started (we unlock the ranges
-			 * in the io tree only when the bios complete and
-			 * buffered writes always lock pages before attempting
-			 * to lock range in the io tree).
-			 */
-			if (writing ||
-			    test_bit(BTRFS_ORDERED_DIRECT, &ordered->flags))
-				btrfs_start_ordered_extent(ordered);
-			else
-				ret = nowait ? -EAGAIN : -ENOTBLK;
-			btrfs_put_ordered_extent(ordered);
-		} else {
-			/*
-			 * We could trigger writeback for this range (and wait
-			 * for it to complete) and then invalidate the pages for
-			 * this range (through invalidate_inode_pages2_range()),
-			 * but that can lead us to a deadlock with a concurrent
-			 * call to readahead (a buffered read or a defrag call
-			 * triggered a readahead) on a page lock due to an
-			 * ordered dio extent we created before but did not have
-			 * yet a corresponding bio submitted (whence it can not
-			 * complete), which makes readahead wait for that
-			 * ordered extent to complete while holding a lock on
-			 * that page.
-			 */
-			ret = nowait ? -EAGAIN : -ENOTBLK;
-		}
-
-		if (ret)
-			break;
-
-		cond_resched();
-	}
-
-	return ret;
-}
-
 /* The callers of this must take lock_extent() */
-static struct extent_map *create_io_em(struct btrfs_inode *inode, u64 start,
-				       u64 len, u64 orig_start, u64 block_start,
-				       u64 block_len, u64 orig_block_len,
-				       u64 ram_bytes, int compress_type,
-				       int type)
+struct extent_map *btrfs_create_io_em(struct btrfs_inode *inode, u64 start,
+				      const struct btrfs_file_extent *file_extent,
+				      int type)
 {
 	struct extent_map *em;
 	int ret;
@@ -7313,32 +7116,26 @@ static struct extent_map *create_io_em(struct btrfs_inode *inode, u64 start,
 
 	switch (type) {
 	case BTRFS_ORDERED_PREALLOC:
-		/* Uncompressed extents. */
-		ASSERT(block_len == len);
-
 		/* We're only referring part of a larger preallocated extent. */
-		ASSERT(block_len <= ram_bytes);
+		ASSERT(file_extent->num_bytes <= file_extent->ram_bytes);
 		break;
 	case BTRFS_ORDERED_REGULAR:
-		/* Uncompressed extents. */
-		ASSERT(block_len == len);
-
 		/* COW results a new extent matching our file extent size. */
-		ASSERT(orig_block_len == len);
-		ASSERT(ram_bytes == len);
+		ASSERT(file_extent->disk_num_bytes == file_extent->num_bytes);
+		ASSERT(file_extent->ram_bytes == file_extent->num_bytes);
 
 		/* Since it's a new extent, we should not have any offset. */
-		ASSERT(orig_start == start);
+		ASSERT(file_extent->offset == 0);
 		break;
 	case BTRFS_ORDERED_COMPRESSED:
 		/* Must be compressed. */
-		ASSERT(compress_type != BTRFS_COMPRESS_NONE);
+		ASSERT(file_extent->compression != BTRFS_COMPRESS_NONE);
 
 		/*
 		 * Encoded write can make us to refer to part of the
 		 * uncompressed extent.
 		 */
-		ASSERT(len <= ram_bytes);
+		ASSERT(file_extent->num_bytes <= file_extent->ram_bytes);
 		break;
 	}
 
@@ -7347,16 +7144,15 @@ static struct extent_map *create_io_em(struct btrfs_inode *inode, u64 start,
 		return ERR_PTR(-ENOMEM);
 
 	em->start = start;
-	em->orig_start = orig_start;
-	em->len = len;
-	em->block_len = block_len;
-	em->block_start = block_start;
-	em->orig_block_len = orig_block_len;
-	em->ram_bytes = ram_bytes;
+	em->len = file_extent->num_bytes;
+	em->disk_bytenr = file_extent->disk_bytenr;
+	em->disk_num_bytes = file_extent->disk_num_bytes;
+	em->ram_bytes = file_extent->ram_bytes;
 	em->generation = -1;
+	em->offset = file_extent->offset;
 	em->flags |= EXTENT_FLAG_PINNED;
 	if (type == BTRFS_ORDERED_COMPRESSED)
-		extent_map_set_compression(em, compress_type);
+		extent_map_set_compression(em, file_extent->compression);
 
 	ret = btrfs_replace_extent_map_range(inode, em, true);
 	if (ret) {
@@ -7368,580 +7164,6 @@ static struct extent_map *create_io_em(struct btrfs_inode *inode, u64 start,
 	return em;
 }
 
-
-static int btrfs_get_blocks_direct_write(struct extent_map **map,
-					 struct inode *inode,
-					 struct btrfs_dio_data *dio_data,
-					 u64 start, u64 *lenp,
-					 unsigned int iomap_flags)
-{
-	const bool nowait = (iomap_flags & IOMAP_NOWAIT);
-	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
-	struct extent_map *em = *map;
-	int type;
-	u64 block_start, orig_start, orig_block_len, ram_bytes;
-	struct btrfs_block_group *bg;
-	bool can_nocow = false;
-	bool space_reserved = false;
-	u64 len = *lenp;
-	u64 prev_len;
-	int ret = 0;
-
-	/*
-	 * We don't allocate a new extent in the following cases
-	 *
-	 * 1) The inode is marked as NODATACOW. In this case we'll just use the
-	 * existing extent.
-	 * 2) The extent is marked as PREALLOC. We're good to go here and can
-	 * just use the extent.
-	 *
-	 */
-	if ((em->flags & EXTENT_FLAG_PREALLOC) ||
-	    ((BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW) &&
-	     em->block_start != EXTENT_MAP_HOLE)) {
-		if (em->flags & EXTENT_FLAG_PREALLOC)
-			type = BTRFS_ORDERED_PREALLOC;
-		else
-			type = BTRFS_ORDERED_NOCOW;
-		len = min(len, em->len - (start - em->start));
-		block_start = em->block_start + (start - em->start);
-
-		if (can_nocow_extent(inode, start, &len, &orig_start,
-				     &orig_block_len, &ram_bytes, false, false) == 1) {
-			bg = btrfs_inc_nocow_writers(fs_info, block_start);
-			if (bg)
-				can_nocow = true;
-		}
-	}
-
-	prev_len = len;
-	if (can_nocow) {
-		struct extent_map *em2;
-
-		/* We can NOCOW, so only need to reserve metadata space. */
-		ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode), len, len,
-						      nowait);
-		if (ret < 0) {
-			/* Our caller expects us to free the input extent map. */
-			free_extent_map(em);
-			*map = NULL;
-			btrfs_dec_nocow_writers(bg);
-			if (nowait && (ret == -ENOSPC || ret == -EDQUOT))
-				ret = -EAGAIN;
-			goto out;
-		}
-		space_reserved = true;
-
-		em2 = btrfs_create_dio_extent(BTRFS_I(inode), dio_data, start, len,
-					      orig_start, block_start,
-					      len, orig_block_len,
-					      ram_bytes, type);
-		btrfs_dec_nocow_writers(bg);
-		if (type == BTRFS_ORDERED_PREALLOC) {
-			free_extent_map(em);
-			*map = em2;
-			em = em2;
-		}
-
-		if (IS_ERR(em2)) {
-			ret = PTR_ERR(em2);
-			goto out;
-		}
-
-		dio_data->nocow_done = true;
-	} else {
-		/* Our caller expects us to free the input extent map. */
-		free_extent_map(em);
-		*map = NULL;
-
-		if (nowait) {
-			ret = -EAGAIN;
-			goto out;
-		}
-
-		/*
-		 * If we could not allocate data space before locking the file
-		 * range and we can't do a NOCOW write, then we have to fail.
-		 */
-		if (!dio_data->data_space_reserved) {
-			ret = -ENOSPC;
-			goto out;
-		}
-
-		/*
-		 * We have to COW and we have already reserved data space before,
-		 * so now we reserve only metadata.
-		 */
-		ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode), len, len,
-						      false);
-		if (ret < 0)
-			goto out;
-		space_reserved = true;
-
-		em = btrfs_new_extent_direct(BTRFS_I(inode), dio_data, start, len);
-		if (IS_ERR(em)) {
-			ret = PTR_ERR(em);
-			goto out;
-		}
-		*map = em;
-		len = min(len, em->len - (start - em->start));
-		if (len < prev_len)
-			btrfs_delalloc_release_metadata(BTRFS_I(inode),
-							prev_len - len, true);
-	}
-
-	/*
-	 * We have created our ordered extent, so we can now release our reservation
-	 * for an outstanding extent.
-	 */
-	btrfs_delalloc_release_extents(BTRFS_I(inode), prev_len);
-
-	/*
-	 * Need to update the i_size under the extent lock so buffered
-	 * readers will get the updated i_size when we unlock.
-	 */
-	if (start + len > i_size_read(inode))
-		i_size_write(inode, start + len);
-out:
-	if (ret && space_reserved) {
-		btrfs_delalloc_release_extents(BTRFS_I(inode), len);
-		btrfs_delalloc_release_metadata(BTRFS_I(inode), len, true);
-	}
-	*lenp = len;
-	return ret;
-}
-
-static int btrfs_dio_iomap_begin(struct inode *inode, loff_t start,
-		loff_t length, unsigned int flags, struct iomap *iomap,
-		struct iomap *srcmap)
-{
-	struct iomap_iter *iter = container_of(iomap, struct iomap_iter, iomap);
-	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
-	struct extent_map *em;
-	struct extent_state *cached_state = NULL;
-	struct btrfs_dio_data *dio_data = iter->private;
-	u64 lockstart, lockend;
-	const bool write = !!(flags & IOMAP_WRITE);
-	int ret = 0;
-	u64 len = length;
-	const u64 data_alloc_len = length;
-	bool unlock_extents = false;
-
-	/*
-	 * We could potentially fault if we have a buffer > PAGE_SIZE, and if
-	 * we're NOWAIT we may submit a bio for a partial range and return
-	 * EIOCBQUEUED, which would result in an errant short read.
-	 *
-	 * The best way to handle this would be to allow for partial completions
-	 * of iocb's, so we could submit the partial bio, return and fault in
-	 * the rest of the pages, and then submit the io for the rest of the
-	 * range.  However we don't have that currently, so simply return
-	 * -EAGAIN at this point so that the normal path is used.
-	 */
-	if (!write && (flags & IOMAP_NOWAIT) && length > PAGE_SIZE)
-		return -EAGAIN;
-
-	/*
-	 * Cap the size of reads to that usually seen in buffered I/O as we need
-	 * to allocate a contiguous array for the checksums.
-	 */
-	if (!write)
-		len = min_t(u64, len, fs_info->sectorsize * BTRFS_MAX_BIO_SECTORS);
-
-	lockstart = start;
-	lockend = start + len - 1;
-
-	/*
-	 * iomap_dio_rw() only does filemap_write_and_wait_range(), which isn't
-	 * enough if we've written compressed pages to this area, so we need to
-	 * flush the dirty pages again to make absolutely sure that any
-	 * outstanding dirty pages are on disk - the first flush only starts
-	 * compression on the data, while keeping the pages locked, so by the
-	 * time the second flush returns we know bios for the compressed pages
-	 * were submitted and finished, and the pages no longer under writeback.
-	 *
-	 * If we have a NOWAIT request and we have any pages in the range that
-	 * are locked, likely due to compression still in progress, we don't want
-	 * to block on page locks. We also don't want to block on pages marked as
-	 * dirty or under writeback (same as for the non-compression case).
-	 * iomap_dio_rw() did the same check, but after that and before we got
-	 * here, mmap'ed writes may have happened or buffered reads started
-	 * (readpage() and readahead(), which lock pages), as we haven't locked
-	 * the file range yet.
-	 */
-	if (test_bit(BTRFS_INODE_HAS_ASYNC_EXTENT,
-		     &BTRFS_I(inode)->runtime_flags)) {
-		if (flags & IOMAP_NOWAIT) {
-			if (filemap_range_needs_writeback(inode->i_mapping,
-							  lockstart, lockend))
-				return -EAGAIN;
-		} else {
-			ret = filemap_fdatawrite_range(inode->i_mapping, start,
-						       start + length - 1);
-			if (ret)
-				return ret;
-		}
-	}
-
-	memset(dio_data, 0, sizeof(*dio_data));
-
-	/*
-	 * We always try to allocate data space and must do it before locking
-	 * the file range, to avoid deadlocks with concurrent writes to the same
-	 * range if the range has several extents and the writes don't expand the
-	 * current i_size (the inode lock is taken in shared mode). If we fail to
-	 * allocate data space here we continue and later, after locking the
-	 * file range, we fail with ENOSPC only if we figure out we can not do a
-	 * NOCOW write.
-	 */
-	if (write && !(flags & IOMAP_NOWAIT)) {
-		ret = btrfs_check_data_free_space(BTRFS_I(inode),
-						  &dio_data->data_reserved,
-						  start, data_alloc_len, false);
-		if (!ret)
-			dio_data->data_space_reserved = true;
-		else if (ret && !(BTRFS_I(inode)->flags &
-				  (BTRFS_INODE_NODATACOW | BTRFS_INODE_PREALLOC)))
-			goto err;
-	}
-
-	/*
-	 * If this errors out it's because we couldn't invalidate pagecache for
-	 * this range and we need to fallback to buffered IO, or we are doing a
-	 * NOWAIT read/write and we need to block.
-	 */
-	ret = lock_extent_direct(inode, lockstart, lockend, &cached_state, flags);
-	if (ret < 0)
-		goto err;
-
-	em = btrfs_get_extent(BTRFS_I(inode), NULL, start, len);
-	if (IS_ERR(em)) {
-		ret = PTR_ERR(em);
-		goto unlock_err;
-	}
-
-	/*
-	 * Ok for INLINE and COMPRESSED extents we need to fallback on buffered
-	 * io.  INLINE is special, and we could probably kludge it in here, but
-	 * it's still buffered so for safety lets just fall back to the generic
-	 * buffered path.
-	 *
-	 * For COMPRESSED we _have_ to read the entire extent in so we can
-	 * decompress it, so there will be buffering required no matter what we
-	 * do, so go ahead and fallback to buffered.
-	 *
-	 * We return -ENOTBLK because that's what makes DIO go ahead and go back
-	 * to buffered IO.  Don't blame me, this is the price we pay for using
-	 * the generic code.
-	 */
-	if (extent_map_is_compressed(em) ||
-	    em->block_start == EXTENT_MAP_INLINE) {
-		free_extent_map(em);
-		/*
-		 * If we are in a NOWAIT context, return -EAGAIN in order to
-		 * fallback to buffered IO. This is not only because we can
-		 * block with buffered IO (no support for NOWAIT semantics at
-		 * the moment) but also to avoid returning short reads to user
-		 * space - this happens if we were able to read some data from
-		 * previous non-compressed extents and then when we fallback to
-		 * buffered IO, at btrfs_file_read_iter() by calling
-		 * filemap_read(), we fail to fault in pages for the read buffer,
-		 * in which case filemap_read() returns a short read (the number
-		 * of bytes previously read is > 0, so it does not return -EFAULT).
-		 */
-		ret = (flags & IOMAP_NOWAIT) ? -EAGAIN : -ENOTBLK;
-		goto unlock_err;
-	}
-
-	len = min(len, em->len - (start - em->start));
-
-	/*
-	 * If we have a NOWAIT request and the range contains multiple extents
-	 * (or a mix of extents and holes), then we return -EAGAIN to make the
-	 * caller fallback to a context where it can do a blocking (without
-	 * NOWAIT) request. This way we avoid doing partial IO and returning
-	 * success to the caller, which is not optimal for writes and for reads
-	 * it can result in unexpected behaviour for an application.
-	 *
-	 * When doing a read, because we use IOMAP_DIO_PARTIAL when calling
-	 * iomap_dio_rw(), we can end up returning less data then what the caller
-	 * asked for, resulting in an unexpected, and incorrect, short read.
-	 * That is, the caller asked to read N bytes and we return less than that,
-	 * which is wrong unless we are crossing EOF. This happens if we get a
-	 * page fault error when trying to fault in pages for the buffer that is
-	 * associated to the struct iov_iter passed to iomap_dio_rw(), and we
-	 * have previously submitted bios for other extents in the range, in
-	 * which case iomap_dio_rw() may return us EIOCBQUEUED if not all of
-	 * those bios have completed by the time we get the page fault error,
-	 * which we return back to our caller - we should only return EIOCBQUEUED
-	 * after we have submitted bios for all the extents in the range.
-	 */
-	if ((flags & IOMAP_NOWAIT) && len < length) {
-		free_extent_map(em);
-		ret = -EAGAIN;
-		goto unlock_err;
-	}
-
-	if (write) {
-		ret = btrfs_get_blocks_direct_write(&em, inode, dio_data,
-						    start, &len, flags);
-		if (ret < 0)
-			goto unlock_err;
-		unlock_extents = true;
-		/* Recalc len in case the new em is smaller than requested */
-		len = min(len, em->len - (start - em->start));
-		if (dio_data->data_space_reserved) {
-			u64 release_offset;
-			u64 release_len = 0;
-
-			if (dio_data->nocow_done) {
-				release_offset = start;
-				release_len = data_alloc_len;
-			} else if (len < data_alloc_len) {
-				release_offset = start + len;
-				release_len = data_alloc_len - len;
-			}
-
-			if (release_len > 0)
-				btrfs_free_reserved_data_space(BTRFS_I(inode),
-							       dio_data->data_reserved,
-							       release_offset,
-							       release_len);
-		}
-	} else {
-		/*
-		 * We need to unlock only the end area that we aren't using.
-		 * The rest is going to be unlocked by the endio routine.
-		 */
-		lockstart = start + len;
-		if (lockstart < lockend)
-			unlock_extents = true;
-	}
-
-	if (unlock_extents)
-		unlock_extent(&BTRFS_I(inode)->io_tree, lockstart, lockend,
-			      &cached_state);
-	else
-		free_extent_state(cached_state);
-
-	/*
-	 * Translate extent map information to iomap.
-	 * We trim the extents (and move the addr) even though iomap code does
-	 * that, since we have locked only the parts we are performing I/O in.
-	 */
-	if ((em->block_start == EXTENT_MAP_HOLE) ||
-	    ((em->flags & EXTENT_FLAG_PREALLOC) && !write)) {
-		iomap->addr = IOMAP_NULL_ADDR;
-		iomap->type = IOMAP_HOLE;
-	} else {
-		iomap->addr = em->block_start + (start - em->start);
-		iomap->type = IOMAP_MAPPED;
-	}
-	iomap->offset = start;
-	iomap->bdev = fs_info->fs_devices->latest_dev->bdev;
-	iomap->length = len;
-	free_extent_map(em);
-
-	return 0;
-
-unlock_err:
-	unlock_extent(&BTRFS_I(inode)->io_tree, lockstart, lockend,
-		      &cached_state);
-err:
-	if (dio_data->data_space_reserved) {
-		btrfs_free_reserved_data_space(BTRFS_I(inode),
-					       dio_data->data_reserved,
-					       start, data_alloc_len);
-		extent_changeset_free(dio_data->data_reserved);
-	}
-
-	return ret;
-}
-
-static int btrfs_dio_iomap_end(struct inode *inode, loff_t pos, loff_t length,
-		ssize_t written, unsigned int flags, struct iomap *iomap)
-{
-	struct iomap_iter *iter = container_of(iomap, struct iomap_iter, iomap);
-	struct btrfs_dio_data *dio_data = iter->private;
-	size_t submitted = dio_data->submitted;
-	const bool write = !!(flags & IOMAP_WRITE);
-	int ret = 0;
-
-	if (!write && (iomap->type == IOMAP_HOLE)) {
-		/* If reading from a hole, unlock and return */
-		unlock_extent(&BTRFS_I(inode)->io_tree, pos, pos + length - 1,
-			      NULL);
-		return 0;
-	}
-
-	if (submitted < length) {
-		pos += submitted;
-		length -= submitted;
-		if (write)
-			btrfs_finish_ordered_extent(dio_data->ordered, NULL,
-						    pos, length, false);
-		else
-			unlock_extent(&BTRFS_I(inode)->io_tree, pos,
-				      pos + length - 1, NULL);
-		ret = -ENOTBLK;
-	}
-	if (write) {
-		btrfs_put_ordered_extent(dio_data->ordered);
-		dio_data->ordered = NULL;
-	}
-
-	if (write)
-		extent_changeset_free(dio_data->data_reserved);
-	return ret;
-}
-
-static void btrfs_dio_end_io(struct btrfs_bio *bbio)
-{
-	struct btrfs_dio_private *dip =
-		container_of(bbio, struct btrfs_dio_private, bbio);
-	struct btrfs_inode *inode = bbio->inode;
-	struct bio *bio = &bbio->bio;
-
-	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) {
-		btrfs_finish_ordered_extent(bbio->ordered, 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);
-	}
-
-	bbio->bio.bi_private = bbio->private;
-	iomap_dio_bio_end_io(bio);
-}
-
-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(bbio, struct btrfs_dio_private, bbio);
-	struct btrfs_dio_data *dio_data = iter->private;
-
-	btrfs_bio_init(bbio, BTRFS_I(iter->inode)->root->fs_info,
-		       btrfs_dio_end_io, bio->bi_private);
-	bbio->inode = BTRFS_I(iter->inode);
-	bbio->file_offset = file_offset;
-
-	dip->file_offset = file_offset;
-	dip->bytes = bio->bi_iter.bi_size;
-
-	dio_data->submitted += bio->bi_iter.bi_size;
-
-	/*
-	 * Check if we are doing a partial write.  If we are, we need to split
-	 * the ordered extent to match the submitted bio.  Hang on to the
-	 * remaining unfinishable ordered_extent in dio_data so that it can be
-	 * cancelled in iomap_end to avoid a deadlock wherein faulting the
-	 * remaining pages is blocked on the outstanding ordered extent.
-	 */
-	if (iter->flags & IOMAP_WRITE) {
-		int ret;
-
-		ret = btrfs_extract_ordered_extent(bbio, dio_data->ordered);
-		if (ret) {
-			btrfs_finish_ordered_extent(dio_data->ordered, NULL,
-						    file_offset, dip->bytes,
-						    !ret);
-			bio->bi_status = errno_to_blk_status(ret);
-			iomap_dio_bio_end_io(bio);
-			return;
-		}
-	}
-
-	btrfs_submit_bio(bbio, 0);
-}
-
-static const struct iomap_ops btrfs_dio_iomap_ops = {
-	.iomap_begin            = btrfs_dio_iomap_begin,
-	.iomap_end              = btrfs_dio_iomap_end,
-};
-
-static const struct iomap_dio_ops btrfs_dio_ops = {
-	.submit_io		= btrfs_dio_submit_io,
-	.bio_set		= &btrfs_dio_bioset,
-};
-
-ssize_t btrfs_dio_read(struct kiocb *iocb, struct iov_iter *iter, size_t done_before)
-{
-	struct btrfs_dio_data data = { 0 };
-
-	return iomap_dio_rw(iocb, iter, &btrfs_dio_iomap_ops, &btrfs_dio_ops,
-			    IOMAP_DIO_PARTIAL, &data, done_before);
-}
-
-struct iomap_dio *btrfs_dio_write(struct kiocb *iocb, struct iov_iter *iter,
-				  size_t done_before)
-{
-	struct btrfs_dio_data data = { 0 };
-
-	return __iomap_dio_rw(iocb, iter, &btrfs_dio_iomap_ops, &btrfs_dio_ops,
-			    IOMAP_DIO_PARTIAL, &data, done_before);
-}
-
-static int btrfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
-			u64 start, u64 len)
-{
-	struct btrfs_inode *btrfs_inode = BTRFS_I(inode);
-	int	ret;
-
-	ret = fiemap_prep(inode, fieinfo, start, &len, 0);
-	if (ret)
-		return ret;
-
-	/*
-	 * fiemap_prep() called filemap_write_and_wait() for the whole possible
-	 * file range (0 to LLONG_MAX), but that is not enough if we have
-	 * compression enabled. The first filemap_fdatawrite_range() only kicks
-	 * in the compression of data (in an async thread) and will return
-	 * before the compression is done and writeback is started. A second
-	 * filemap_fdatawrite_range() is needed to wait for the compression to
-	 * complete and writeback to start. We also need to wait for ordered
-	 * extents to complete, because our fiemap implementation uses mainly
-	 * file extent items to list the extents, searching for extent maps
-	 * only for file ranges with holes or prealloc extents to figure out
-	 * if we have delalloc in those ranges.
-	 */
-	if (fieinfo->fi_flags & FIEMAP_FLAG_SYNC) {
-		ret = btrfs_wait_ordered_range(inode, 0, LLONG_MAX);
-		if (ret)
-			return ret;
-	}
-
-	btrfs_inode_lock(btrfs_inode, BTRFS_ILOCK_SHARED);
-
-	/*
-	 * We did an initial flush to avoid holding the inode's lock while
-	 * triggering writeback and waiting for the completion of IO and ordered
-	 * extents. Now after we locked the inode we do it again, because it's
-	 * possible a new write may have happened in between those two steps.
-	 */
-	if (fieinfo->fi_flags & FIEMAP_FLAG_SYNC) {
-		ret = btrfs_wait_ordered_range(inode, 0, LLONG_MAX);
-		if (ret) {
-			btrfs_inode_unlock(btrfs_inode, BTRFS_ILOCK_SHARED);
-			return ret;
-		}
-	}
-
-	ret = extent_fiemap(btrfs_inode, fieinfo, start, len);
-	btrfs_inode_unlock(btrfs_inode, BTRFS_ILOCK_SHARED);
-
-	return ret;
-}
-
 /*
  * For release_folio() and invalidate_folio() we have a race window where
  * folio_end_writeback() is called but the subpage spinlock is not yet released.
@@ -8198,7 +7420,7 @@ static int btrfs_truncate(struct btrfs_inode *inode, bool skip_writeback)
 	const u64 min_size = btrfs_calc_metadata_size(fs_info, 1);
 
 	if (!skip_writeback) {
-		ret = btrfs_wait_ordered_range(&inode->vfs_inode,
+		ret = btrfs_wait_ordered_range(inode,
 					       inode->vfs_inode.i_size & (~mask),
 					       (u64)-1);
 		if (ret)
@@ -8399,20 +7621,10 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
 	struct btrfs_fs_info *fs_info = btrfs_sb(sb);
 	struct btrfs_inode *ei;
 	struct inode *inode;
-	struct extent_io_tree *file_extent_tree = NULL;
-
-	/* Self tests may pass a NULL fs_info. */
-	if (fs_info && !btrfs_fs_incompat(fs_info, NO_HOLES)) {
-		file_extent_tree = kmalloc(sizeof(struct extent_io_tree), GFP_KERNEL);
-		if (!file_extent_tree)
-			return NULL;
-	}
 
 	ei = alloc_inode_sb(sb, btrfs_inode_cachep, GFP_KERNEL);
-	if (!ei) {
-		kfree(file_extent_tree);
+	if (!ei)
 		return NULL;
-	}
 
 	ei->root = NULL;
 	ei->generation = 0;
@@ -8425,8 +7637,12 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
 	ei->disk_i_size = 0;
 	ei->flags = 0;
 	ei->ro_flags = 0;
+	/*
+	 * ->index_cnt will be properly initialized later when creating a new
+	 * inode (btrfs_create_new_inode()) or when reading an existing inode
+	 * from disk (btrfs_read_locked_inode()).
+	 */
 	ei->csum_bytes = 0;
-	ei->index_cnt = (u64)-1;
 	ei->dir_index = 0;
 	ei->last_unlink_trans = 0;
 	ei->last_reflink_trans = 0;
@@ -8453,20 +7669,14 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
 	extent_io_tree_init(fs_info, &ei->io_tree, IO_TREE_INODE_IO);
 	ei->io_tree.inode = ei;
 
-	ei->file_extent_tree = file_extent_tree;
-	if (file_extent_tree) {
-		extent_io_tree_init(fs_info, ei->file_extent_tree,
-				    IO_TREE_INODE_FILE_EXTENT);
-		/* Lockdep class is set only for the file extent tree. */
-		lockdep_set_class(&ei->file_extent_tree->lock, &file_extent_tree_class);
-	}
+	ei->file_extent_tree = NULL;
+
 	mutex_init(&ei->log_mutex);
 	spin_lock_init(&ei->ordered_tree_lock);
 	ei->ordered_tree = RB_ROOT;
 	ei->ordered_tree_last = NULL;
 	INIT_LIST_HEAD(&ei->delalloc_inodes);
 	INIT_LIST_HEAD(&ei->delayed_iput);
-	RB_CLEAR_NODE(&ei->rb_node);
 	init_rwsem(&ei->i_mmap_lock);
 
 	return inode;
@@ -8502,9 +7712,10 @@ void btrfs_destroy_inode(struct inode *vfs_inode)
 	if (!S_ISDIR(vfs_inode->i_mode)) {
 		WARN_ON(inode->delalloc_bytes);
 		WARN_ON(inode->new_delalloc_bytes);
+		WARN_ON(inode->csum_bytes);
 	}
-	WARN_ON(inode->csum_bytes);
-	WARN_ON(inode->defrag_bytes);
+	if (!root || !btrfs_is_data_reloc_root(root))
+		WARN_ON(inode->defrag_bytes);
 
 	/*
 	 * This can happen where we create an inode, but somebody else also
@@ -8538,7 +7749,7 @@ void btrfs_destroy_inode(struct inode *vfs_inode)
 		}
 	}
 	btrfs_qgroup_check_reserved_leak(inode);
-	inode_tree_del(inode);
+	btrfs_del_inode_from_root(inode);
 	btrfs_drop_extent_map_range(inode, 0, (u64)-1, false);
 	btrfs_inode_clear_file_extent_range(inode, 0, (u64)-1);
 	btrfs_put_root(inode->root);
@@ -8572,7 +7783,6 @@ void __cold btrfs_destroy_cachep(void)
 	 * destroy cache.
 	 */
 	rcu_barrier();
-	bioset_exit(&btrfs_dio_bioset);
 	kmem_cache_destroy(btrfs_inode_cachep);
 }
 
@@ -8583,17 +7793,9 @@ int __init btrfs_init_cachep(void)
 			SLAB_RECLAIM_ACCOUNT | SLAB_ACCOUNT,
 			init_once);
 	if (!btrfs_inode_cachep)
-		goto fail;
-
-	if (bioset_init(&btrfs_dio_bioset, BIO_POOL_SIZE,
-			offsetof(struct btrfs_dio_private, bbio.bio),
-			BIOSET_NEED_BVECS))
-		goto fail;
+		return -ENOMEM;
 
 	return 0;
-fail:
-	btrfs_destroy_cachep();
-	return -ENOMEM;
 }
 
 static int btrfs_getattr(struct mnt_idmap *idmap,
@@ -9586,11 +8788,10 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode,
 		}
 
 		em->start = cur_offset;
-		em->orig_start = cur_offset;
 		em->len = ins.offset;
-		em->block_start = ins.objectid;
-		em->block_len = ins.offset;
-		em->orig_block_len = ins.offset;
+		em->disk_bytenr = ins.objectid;
+		em->offset = 0;
+		em->disk_num_bytes = ins.offset;
 		em->ram_bytes = ins.offset;
 		em->flags |= EXTENT_FLAG_PREALLOC;
 		em->generation = trans->transid;
@@ -9956,7 +9157,7 @@ static ssize_t btrfs_encoded_read_regular(struct kiocb *iocb,
 	pages = kcalloc(nr_pages, sizeof(struct page *), GFP_NOFS);
 	if (!pages)
 		return -ENOMEM;
-	ret = btrfs_alloc_page_array(nr_pages, pages, 0);
+	ret = btrfs_alloc_page_array(nr_pages, pages, false);
 	if (ret) {
 		ret = -ENOMEM;
 		goto out;
@@ -10033,7 +9234,7 @@ ssize_t btrfs_encoded_read(struct kiocb *iocb, struct iov_iter *iter,
 	for (;;) {
 		struct btrfs_ordered_extent *ordered;
 
-		ret = btrfs_wait_ordered_range(&inode->vfs_inode, start,
+		ret = btrfs_wait_ordered_range(inode, start,
 					       lockend - start + 1);
 		if (ret)
 			goto out_unlock_inode;
@@ -10053,7 +9254,7 @@ ssize_t btrfs_encoded_read(struct kiocb *iocb, struct iov_iter *iter,
 		goto out_unlock_extent;
 	}
 
-	if (em->block_start == EXTENT_MAP_INLINE) {
+	if (em->disk_bytenr == EXTENT_MAP_INLINE) {
 		u64 extent_start = em->start;
 
 		/*
@@ -10074,33 +9275,33 @@ ssize_t btrfs_encoded_read(struct kiocb *iocb, struct iov_iter *iter,
 	 */
 	encoded->len = min_t(u64, extent_map_end(em),
 			     inode->vfs_inode.i_size) - iocb->ki_pos;
-	if (em->block_start == EXTENT_MAP_HOLE ||
+	if (em->disk_bytenr == EXTENT_MAP_HOLE ||
 	    (em->flags & EXTENT_FLAG_PREALLOC)) {
 		disk_bytenr = EXTENT_MAP_HOLE;
 		count = min_t(u64, count, encoded->len);
 		encoded->len = count;
 		encoded->unencoded_len = count;
 	} else if (extent_map_is_compressed(em)) {
-		disk_bytenr = em->block_start;
+		disk_bytenr = em->disk_bytenr;
 		/*
 		 * Bail if the buffer isn't large enough to return the whole
 		 * compressed extent.
 		 */
-		if (em->block_len > count) {
+		if (em->disk_num_bytes > count) {
 			ret = -ENOBUFS;
 			goto out_em;
 		}
-		disk_io_size = em->block_len;
-		count = em->block_len;
+		disk_io_size = em->disk_num_bytes;
+		count = em->disk_num_bytes;
 		encoded->unencoded_len = em->ram_bytes;
-		encoded->unencoded_offset = iocb->ki_pos - em->orig_start;
+		encoded->unencoded_offset = iocb->ki_pos - (em->start - em->offset);
 		ret = btrfs_encoded_io_compression_from_extent(fs_info,
 							       extent_map_compression(em));
 		if (ret < 0)
 			goto out_em;
 		encoded->compression = ret;
 	} else {
-		disk_bytenr = em->block_start + (start - em->start);
+		disk_bytenr = extent_map_block_start(em) + (start - em->start);
 		if (encoded->len > count)
 			encoded->len = count;
 		/*
@@ -10155,6 +9356,7 @@ ssize_t btrfs_do_encoded_write(struct kiocb *iocb, struct iov_iter *from,
 	struct extent_changeset *data_reserved = NULL;
 	struct extent_state *cached_state = NULL;
 	struct btrfs_ordered_extent *ordered;
+	struct btrfs_file_extent file_extent;
 	int compression;
 	size_t orig_count;
 	u64 start, end;
@@ -10276,7 +9478,7 @@ ssize_t btrfs_do_encoded_write(struct kiocb *iocb, struct iov_iter *from,
 	for (;;) {
 		struct btrfs_ordered_extent *ordered;
 
-		ret = btrfs_wait_ordered_range(&inode->vfs_inode, start, num_bytes);
+		ret = btrfs_wait_ordered_range(inode, start, num_bytes);
 		if (ret)
 			goto out_folios;
 		ret = invalidate_inode_pages2_range(inode->vfs_inode.i_mapping,
@@ -10330,22 +9532,22 @@ ssize_t btrfs_do_encoded_write(struct kiocb *iocb, struct iov_iter *from,
 		goto out_delalloc_release;
 	extent_reserved = true;
 
-	em = create_io_em(inode, start, num_bytes,
-			  start - encoded->unencoded_offset, ins.objectid,
-			  ins.offset, ins.offset, ram_bytes, compression,
-			  BTRFS_ORDERED_COMPRESSED);
+	file_extent.disk_bytenr = ins.objectid;
+	file_extent.disk_num_bytes = ins.offset;
+	file_extent.num_bytes = num_bytes;
+	file_extent.ram_bytes = ram_bytes;
+	file_extent.offset = encoded->unencoded_offset;
+	file_extent.compression = compression;
+	em = btrfs_create_io_em(inode, start, &file_extent, BTRFS_ORDERED_COMPRESSED);
 	if (IS_ERR(em)) {
 		ret = PTR_ERR(em);
 		goto out_free_reserved;
 	}
 	free_extent_map(em);
 
-	ordered = btrfs_alloc_ordered_extent(inode, start, num_bytes, ram_bytes,
-				       ins.objectid, ins.offset,
-				       encoded->unencoded_offset,
+	ordered = btrfs_alloc_ordered_extent(inode, start, &file_extent,
 				       (1 << BTRFS_ORDERED_ENCODED) |
-				       (1 << BTRFS_ORDERED_COMPRESSED),
-				       compression);
+				       (1 << BTRFS_ORDERED_COMPRESSED));
 	if (IS_ERR(ordered)) {
 		btrfs_drop_extent_map_range(inode, start, end, false);
 		ret = PTR_ERR(ordered);
@@ -10549,7 +9751,7 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file,
 	 * file changes again after this, the user is doing something stupid and
 	 * we don't really care.
 	 */
-	ret = btrfs_wait_ordered_range(inode, 0, (u64)-1);
+	ret = btrfs_wait_ordered_range(BTRFS_I(inode), 0, (u64)-1);
 	if (ret)
 		return ret;
 
@@ -10635,12 +9837,12 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file,
 			goto out;
 		}
 
-		if (em->block_start == EXTENT_MAP_HOLE) {
+		if (em->disk_bytenr == EXTENT_MAP_HOLE) {
 			btrfs_warn(fs_info, "swapfile must not have holes");
 			ret = -EINVAL;
 			goto out;
 		}
-		if (em->block_start == EXTENT_MAP_INLINE) {
+		if (em->disk_bytenr == EXTENT_MAP_INLINE) {
 			/*
 			 * It's unlikely we'll ever actually find ourselves
 			 * here, as a file small enough to fit inline won't be
@@ -10658,12 +9860,12 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file,
 			goto out;
 		}
 
-		logical_block_start = em->block_start + (start - em->start);
+		logical_block_start = extent_map_block_start(em) + (start - em->start);
 		len = min(len, em->len - (start - em->start));
 		free_extent_map(em);
 		em = NULL;
 
-		ret = can_nocow_extent(inode, start, &len, NULL, NULL, NULL, false, true);
+		ret = can_nocow_extent(inode, start, &len, NULL, false, true);
 		if (ret < 0) {
 			goto out;
 		} else if (ret) {
@@ -10860,52 +10062,23 @@ void btrfs_assert_inode_range_clean(struct btrfs_inode *inode, u64 start, u64 en
  */
 struct btrfs_inode *btrfs_find_first_inode(struct btrfs_root *root, u64 min_ino)
 {
-	struct rb_node *node;
-	struct rb_node *prev;
 	struct btrfs_inode *inode;
+	unsigned long from = min_ino;
 
-	spin_lock(&root->inode_lock);
-again:
-	node = root->inode_tree.rb_node;
-	prev = NULL;
-	while (node) {
-		prev = node;
-		inode = rb_entry(node, struct btrfs_inode, rb_node);
-		if (min_ino < btrfs_ino(inode))
-			node = node->rb_left;
-		else if (min_ino > btrfs_ino(inode))
-			node = node->rb_right;
-		else
+	xa_lock(&root->inodes);
+	while (true) {
+		inode = xa_find(&root->inodes, &from, ULONG_MAX, XA_PRESENT);
+		if (!inode)
+			break;
+		if (igrab(&inode->vfs_inode))
 			break;
-	}
-
-	if (!node) {
-		while (prev) {
-			inode = rb_entry(prev, struct btrfs_inode, rb_node);
-			if (min_ino <= btrfs_ino(inode)) {
-				node = prev;
-				break;
-			}
-			prev = rb_next(prev);
-		}
-	}
-
-	while (node) {
-		inode = rb_entry(prev, struct btrfs_inode, rb_node);
-		if (igrab(&inode->vfs_inode)) {
-			spin_unlock(&root->inode_lock);
-			return inode;
-		}
-
-		min_ino = btrfs_ino(inode) + 1;
-		if (cond_resched_lock(&root->inode_lock))
-			goto again;
 
-		node = rb_next(node);
+		from = btrfs_ino(inode) + 1;
+		cond_resched_lock(&root->inodes.xa_lock);
 	}
-	spin_unlock(&root->inode_lock);
+	xa_unlock(&root->inodes);
 
-	return NULL;
+	return inode;
 }
 
 static const struct inode_operations btrfs_dir_inode_operations = {