Merge tag 'for-5.19-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs updates from David Sterba:
 "Features:

   - subpage:
      - support for PAGE_SIZE > 4K (previously only 64K)
      - make it work with raid56

   - repair super block num_devices automatically if it does not match
     the number of device items

   - defrag can convert inline extents to regular extents, up to now
     inline files were skipped but the setting of mount option
     max_inline could affect the decision logic

   - zoned:
      - minimal accepted zone size is explicitly set to 4MiB
      - make zone reclaim less aggressive and don't reclaim if there are
        enough free zones
      - add per-profile sysfs tunable of the reclaim threshold

   - allow automatic block group reclaim for non-zoned filesystems, with
     sysfs tunables

   - tree-checker: new check, compare extent buffer owner against owner
     rootid

  Performance:

   - avoid blocking on space reservation when doing nowait direct io
     writes (+7% throughput for reads and writes)

   - NOCOW write throughput improvement due to refined locking (+3%)

   - send: reduce pressure to page cache by dropping extent pages right
     after they're processed

  Core:

   - convert all radix trees to xarray

   - add iterators for b-tree node items

   - support printk message index

   - user bulk page allocation for extent buffers

   - switch to bio_alloc API, use on-stack bios where convenient, other
     bio cleanups

   - use rw lock for block groups to favor concurrent reads

   - simplify workques, don't allocate high priority threads for all
     normal queues as we need only one

   - refactor scrub, process chunks based on their constraints and
     similarity

   - allocate direct io structures on stack and pass around only
     pointers, avoids allocation and reduces potential error handling

  Fixes:

   - fix count of reserved transaction items for various inode
     operations

   - fix deadlock between concurrent dio writes when low on free data
     space

   - fix a few cases when zones need to be finished

  VFS, iomap:

   - add helper to check if sb write has started (usable for assertions)

   - new helper iomap_dio_alloc_bio, export iomap_dio_bio_end_io"

* tag 'for-5.19-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (173 commits)
  btrfs: zoned: introduce a minimal zone size 4M and reject mount
  btrfs: allow defrag to convert inline extents to regular extents
  btrfs: add "0x" prefix for unsupported optional features
  btrfs: do not account twice for inode ref when reserving metadata units
  btrfs: zoned: fix comparison of alloc_offset vs meta_write_pointer
  btrfs: send: avoid trashing the page cache
  btrfs: send: keep the current inode open while processing it
  btrfs: allocate the btrfs_dio_private as part of the iomap dio bio
  btrfs: move struct btrfs_dio_private to inode.c
  btrfs: remove the disk_bytenr in struct btrfs_dio_private
  btrfs: allocate dio_data on stack
  iomap: add per-iomap_iter private data
  iomap: allow the file system to provide a bio_set for direct I/O
  btrfs: add a btrfs_dio_rw wrapper
  btrfs: zoned: zone finish unused block group
  btrfs: zoned: properly finish block group on metadata write
  btrfs: zoned: finish block group when there are no more allocatable bytes left
  btrfs: zoned: consolidate zone finish functions
  btrfs: zoned: introduce btrfs_zoned_bg_is_full
  btrfs: improve error reporting in lookup_inline_extent_backref
  ...

1 files changed, 954 insertions, 896 deletions

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 95c499b8424e..da13bd0d10f1 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -64,8 +64,36 @@ struct btrfs_iget_args {
 struct btrfs_dio_data {
 	ssize_t submitted;
 	struct extent_changeset *data_reserved;
+	bool data_space_reserved;
+	bool nocow_done;
 };
 
+struct btrfs_dio_private {
+	struct 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.
+	 */
+	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;
+};
+
+static struct bio_set btrfs_dio_bioset;
+
 struct btrfs_rename_ctx {
 	/* Output field. Stores the index number of the old directory entry. */
 	u64 index;
@@ -222,15 +250,25 @@ static inline void btrfs_cleanup_ordered_extents(struct btrfs_inode *inode,
 static int btrfs_dirty_inode(struct inode *inode);
 
 static int btrfs_init_inode_security(struct btrfs_trans_handle *trans,
-				     struct inode *inode,  struct inode *dir,
-				     const struct qstr *qstr)
+				     struct btrfs_new_inode_args *args)
 {
 	int err;
 
-	err = btrfs_init_acl(trans, inode, dir);
-	if (!err)
-		err = btrfs_xattr_security_init(trans, inode, dir, qstr);
-	return err;
+	if (args->default_acl) {
+		err = __btrfs_set_acl(trans, args->inode, args->default_acl,
+				      ACL_TYPE_DEFAULT);
+		if (err)
+			return err;
+	}
+	if (args->acl) {
+		err = __btrfs_set_acl(trans, args->inode, args->acl, ACL_TYPE_ACCESS);
+		if (err)
+			return err;
+	}
+	if (!args->default_acl && !args->acl)
+		cache_no_acl(args->inode);
+	return btrfs_xattr_security_init(trans, args->inode, args->dir,
+					 &args->dentry->d_name);
 }
 
 /*
@@ -1607,6 +1645,141 @@ static int fallback_to_cow(struct btrfs_inode *inode, struct page *locked_page,
 			      nr_written, 1);
 }
 
+struct can_nocow_file_extent_args {
+	/* Input fields. */
+
+	/* Start file offset of the range we want to NOCOW. */
+	u64 start;
+	/* End file offset (inclusive) of the range we want to NOCOW. */
+	u64 end;
+	bool writeback_path;
+	bool strict;
+	/*
+	 * Free the path passed to can_nocow_file_extent() once it's not needed
+	 * anymore.
+	 */
+	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;
+};
+
+/*
+ * Check if we can NOCOW the file extent that the path points to.
+ * This function may return with the path released, so the caller should check
+ * if path->nodes[0] is NULL or not if it needs to use the path afterwards.
+ *
+ * Returns: < 0 on error
+ *            0 if we can not NOCOW
+ *            1 if we can NOCOW
+ */
+static int can_nocow_file_extent(struct btrfs_path *path,
+				 struct btrfs_key *key,
+				 struct btrfs_inode *inode,
+				 struct can_nocow_file_extent_args *args)
+{
+	const bool is_freespace_inode = btrfs_is_free_space_inode(inode);
+	struct extent_buffer *leaf = path->nodes[0];
+	struct btrfs_root *root = inode->root;
+	struct btrfs_file_extent_item *fi;
+	u64 extent_end;
+	u8 extent_type;
+	int can_nocow = 0;
+	int ret = 0;
+
+	fi = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_file_extent_item);
+	extent_type = btrfs_file_extent_type(leaf, fi);
+
+	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;
+
+	/*
+	 * If the extent was created before the generation where the last snapshot
+	 * for its subvolume was created, then this implies the extent is shared,
+	 * hence we must COW.
+	 */
+	if (!args->strict &&
+	    btrfs_file_extent_generation(leaf, fi) <=
+	    btrfs_root_last_snapshot(&root->root_item))
+		goto out;
+
+	/* An explicit hole, must COW. */
+	if (args->disk_bytenr == 0)
+		goto out;
+
+	/* Compressed/encrypted/encoded extents must be COWed. */
+	if (btrfs_file_extent_compression(leaf, fi) ||
+	    btrfs_file_extent_encryption(leaf, fi) ||
+	    btrfs_file_extent_other_encoding(leaf, fi))
+		goto out;
+
+	extent_end = btrfs_file_extent_end(path);
+
+	/*
+	 * 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
+	 * blocking other tasks for too long.
+	 */
+	btrfs_release_path(path);
+
+	ret = btrfs_cross_ref_exist(root, btrfs_ino(inode),
+				    key->offset - args->extent_offset,
+				    args->disk_bytenr, false, path);
+	WARN_ON_ONCE(ret > 0 && is_freespace_inode);
+	if (ret != 0)
+		goto out;
+
+	if (args->free_path) {
+		/*
+		 * We don't need the path anymore, plus through the
+		 * csum_exist_in_range() call below we will end up allocating
+		 * another path. So free the path to avoid unnecessary extra
+		 * memory usage.
+		 */
+		btrfs_free_path(path);
+		path = NULL;
+	}
+
+	/* If there are pending snapshots for this root, we must COW. */
+	if (args->writeback_path && !is_freespace_inode &&
+	    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;
+
+	/*
+	 * Force COW if csums exist in the range. This ensures that csums for a
+	 * given extent are either valid or do not exist.
+	 */
+	ret = csum_exist_in_range(root->fs_info, args->disk_bytenr, args->num_bytes);
+	WARN_ON_ONCE(ret > 0 && is_freespace_inode);
+	if (ret != 0)
+		goto out;
+
+	can_nocow = 1;
+ out:
+	if (args->free_path && path)
+		btrfs_free_path(path);
+
+	return ret < 0 ? ret : can_nocow;
+}
+
 /*
  * when nowcow writeback call back.  This checks for snapshots or COW copies
  * of the extents that exist in the file, and COWs the file as required.
@@ -1627,11 +1800,10 @@ static noinline int run_delalloc_nocow(struct btrfs_inode *inode,
 	u64 cur_offset = start;
 	int ret;
 	bool check_prev = true;
-	const bool freespace_inode = btrfs_is_free_space_inode(inode);
 	u64 ino = btrfs_ino(inode);
+	struct btrfs_block_group *bg;
 	bool nocow = false;
-	u64 disk_bytenr = 0;
-	const bool force = inode->flags & BTRFS_INODE_NODATACOW;
+	struct can_nocow_file_extent_args nocow_args = { 0 };
 
 	path = btrfs_alloc_path();
 	if (!path) {
@@ -1644,15 +1816,16 @@ static noinline int run_delalloc_nocow(struct btrfs_inode *inode,
 		return -ENOMEM;
 	}
 
+	nocow_args.end = end;
+	nocow_args.writeback_path = true;
+
 	while (1) {
 		struct btrfs_key found_key;
 		struct btrfs_file_extent_item *fi;
 		struct extent_buffer *leaf;
 		u64 extent_end;
-		u64 extent_offset;
-		u64 num_bytes = 0;
-		u64 disk_num_bytes;
 		u64 ram_bytes;
+		u64 nocow_end;
 		int extent_type;
 
 		nocow = false;
@@ -1728,116 +1901,38 @@ next_slot:
 		fi = btrfs_item_ptr(leaf, path->slots[0],
 				    struct btrfs_file_extent_item);
 		extent_type = btrfs_file_extent_type(leaf, fi);
-
+		/* If this is triggered then we have a memory corruption. */
+		ASSERT(extent_type < BTRFS_NR_FILE_EXTENT_TYPES);
+		if (WARN_ON(extent_type >= BTRFS_NR_FILE_EXTENT_TYPES)) {
+			ret = -EUCLEAN;
+			goto error;
+		}
 		ram_bytes = btrfs_file_extent_ram_bytes(leaf, fi);
-		if (extent_type == BTRFS_FILE_EXTENT_REG ||
-		    extent_type == BTRFS_FILE_EXTENT_PREALLOC) {
-			disk_bytenr = btrfs_file_extent_disk_bytenr(leaf, fi);
-			extent_offset = btrfs_file_extent_offset(leaf, fi);
-			extent_end = found_key.offset +
-				btrfs_file_extent_num_bytes(leaf, fi);
-			disk_num_bytes =
-				btrfs_file_extent_disk_num_bytes(leaf, fi);
-			/*
-			 * If the extent we got ends before our current offset,
-			 * skip to the next extent.
-			 */
-			if (extent_end <= cur_offset) {
-				path->slots[0]++;
-				goto next_slot;
-			}
-			/* Skip holes */
-			if (disk_bytenr == 0)
-				goto out_check;
-			/* Skip compressed/encrypted/encoded extents */
-			if (btrfs_file_extent_compression(leaf, fi) ||
-			    btrfs_file_extent_encryption(leaf, fi) ||
-			    btrfs_file_extent_other_encoding(leaf, fi))
-				goto out_check;
-			/*
-			 * If extent is created before the last volume's snapshot
-			 * this implies the extent is shared, hence we can't do
-			 * nocow. This is the same check as in
-			 * btrfs_cross_ref_exist but without calling
-			 * btrfs_search_slot.
-			 */
-			if (!freespace_inode &&
-			    btrfs_file_extent_generation(leaf, fi) <=
-			    btrfs_root_last_snapshot(&root->root_item))
-				goto out_check;
-			if (extent_type == BTRFS_FILE_EXTENT_REG && !force)
-				goto out_check;
+		extent_end = btrfs_file_extent_end(path);
 
-			/*
-			 * 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 blocking other tasks for too
-			 * long.
-			 */
-			btrfs_release_path(path);
+		/*
+		 * If the extent we got ends before our current offset, skip to
+		 * the next extent.
+		 */
+		if (extent_end <= cur_offset) {
+			path->slots[0]++;
+			goto next_slot;
+		}
 
-			ret = btrfs_cross_ref_exist(root, ino,
-						    found_key.offset -
-						    extent_offset, disk_bytenr, false);
-			if (ret) {
-				/*
-				 * ret could be -EIO if the above fails to read
-				 * metadata.
-				 */
-				if (ret < 0) {
-					if (cow_start != (u64)-1)
-						cur_offset = cow_start;
-					goto error;
-				}
+		nocow_args.start = cur_offset;
+		ret = can_nocow_file_extent(path, &found_key, inode, &nocow_args);
+		if (ret < 0) {
+			if (cow_start != (u64)-1)
+				cur_offset = cow_start;
+			goto error;
+		} else if (ret == 0) {
+			goto out_check;
+		}
 
-				WARN_ON_ONCE(freespace_inode);
-				goto out_check;
-			}
-			disk_bytenr += extent_offset;
-			disk_bytenr += cur_offset - found_key.offset;
-			num_bytes = min(end + 1, extent_end) - cur_offset;
-			/*
-			 * If there are pending snapshots for this root, we
-			 * fall into common COW way
-			 */
-			if (!freespace_inode && atomic_read(&root->snapshot_force_cow))
-				goto out_check;
-			/*
-			 * force cow if csum exists in the range.
-			 * this ensure that csum for a given extent are
-			 * either valid or do not exist.
-			 */
-			ret = csum_exist_in_range(fs_info, disk_bytenr,
-						  num_bytes);
-			if (ret) {
-				/*
-				 * ret could be -EIO if the above fails to read
-				 * metadata.
-				 */
-				if (ret < 0) {
-					if (cow_start != (u64)-1)
-						cur_offset = cow_start;
-					goto error;
-				}
-				WARN_ON_ONCE(freespace_inode);
-				goto out_check;
-			}
-			/* If the extent's block group is RO, we must COW */
-			if (!btrfs_inc_nocow_writers(fs_info, disk_bytenr))
-				goto out_check;
+		ret = 0;
+		bg = btrfs_inc_nocow_writers(fs_info, nocow_args.disk_bytenr);
+		if (bg)
 			nocow = true;
-		} else if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
-			extent_end = found_key.offset + ram_bytes;
-			extent_end = ALIGN(extent_end, fs_info->sectorsize);
-			/* Skip extents outside of our requested range */
-			if (extent_end <= start) {
-				path->slots[0]++;
-				goto next_slot;
-			}
-		} else {
-			/* If this triggers then we have a memory corruption */
-			BUG();
-		}
 out_check:
 		/*
 		 * If nocow is false then record the beginning of the range
@@ -1869,15 +1964,17 @@ out_check:
 			cow_start = (u64)-1;
 		}
 
+		nocow_end = cur_offset + nocow_args.num_bytes - 1;
+
 		if (extent_type == BTRFS_FILE_EXTENT_PREALLOC) {
-			u64 orig_start = found_key.offset - extent_offset;
+			u64 orig_start = found_key.offset - nocow_args.extent_offset;
 			struct extent_map *em;
 
-			em = create_io_em(inode, cur_offset, num_bytes,
+			em = create_io_em(inode, cur_offset, nocow_args.num_bytes,
 					  orig_start,
-					  disk_bytenr, /* block_start */
-					  num_bytes, /* block_len */
-					  disk_num_bytes, /* orig_block_len */
+					  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);
 			if (IS_ERR(em)) {
@@ -1886,20 +1983,23 @@ out_check:
 			}
 			free_extent_map(em);
 			ret = btrfs_add_ordered_extent(inode,
-					cur_offset, num_bytes, num_bytes,
-					disk_bytenr, num_bytes, 0,
+					cur_offset, nocow_args.num_bytes,
+					nocow_args.num_bytes,
+					nocow_args.disk_bytenr,
+					nocow_args.num_bytes, 0,
 					1 << BTRFS_ORDERED_PREALLOC,
 					BTRFS_COMPRESS_NONE);
 			if (ret) {
 				btrfs_drop_extent_cache(inode, cur_offset,
-							cur_offset + num_bytes - 1,
-							0);
+							nocow_end, 0);
 				goto error;
 			}
 		} else {
 			ret = btrfs_add_ordered_extent(inode, cur_offset,
-						       num_bytes, num_bytes,
-						       disk_bytenr, num_bytes,
+						       nocow_args.num_bytes,
+						       nocow_args.num_bytes,
+						       nocow_args.disk_bytenr,
+						       nocow_args.num_bytes,
 						       0,
 						       1 << BTRFS_ORDERED_NOCOW,
 						       BTRFS_COMPRESS_NONE);
@@ -1907,9 +2007,10 @@ out_check:
 				goto error;
 		}
 
-		if (nocow)
-			btrfs_dec_nocow_writers(fs_info, disk_bytenr);
-		nocow = false;
+		if (nocow) {
+			btrfs_dec_nocow_writers(bg);
+			nocow = false;
+		}
 
 		if (btrfs_is_data_reloc_root(root))
 			/*
@@ -1918,10 +2019,9 @@ out_check:
 			 * from freeing metadata of created ordered extent.
 			 */
 			ret = btrfs_reloc_clone_csums(inode, cur_offset,
-						      num_bytes);
+						      nocow_args.num_bytes);
 
-		extent_clear_unlock_delalloc(inode, cur_offset,
-					     cur_offset + num_bytes - 1,
+		extent_clear_unlock_delalloc(inode, cur_offset, nocow_end,
 					     locked_page, EXTENT_LOCKED |
 					     EXTENT_DELALLOC |
 					     EXTENT_CLEAR_DATA_RESV,
@@ -1954,7 +2054,7 @@ out_check:
 
 error:
 	if (nocow)
-		btrfs_dec_nocow_writers(fs_info, disk_bytenr);
+		btrfs_dec_nocow_writers(bg);
 
 	if (ret && cur_offset < end)
 		extent_clear_unlock_delalloc(inode, cur_offset, end,
@@ -2498,9 +2598,8 @@ out:
  *
  *    c-3) otherwise:			async submit
  */
-blk_status_t btrfs_submit_data_bio(struct inode *inode, struct bio *bio,
-				   int mirror_num, unsigned long bio_flags)
-
+void btrfs_submit_data_bio(struct inode *inode, struct bio *bio,
+			   int mirror_num, enum btrfs_compression_type compress_type)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_root *root = BTRFS_I(inode)->root;
@@ -2529,16 +2628,14 @@ blk_status_t btrfs_submit_data_bio(struct inode *inode, struct bio *bio,
 		if (ret)
 			goto out;
 
-		if (bio_flags & EXTENT_BIO_COMPRESSED) {
+		if (compress_type != BTRFS_COMPRESS_NONE) {
 			/*
 			 * btrfs_submit_compressed_read will handle completing
 			 * the bio if there were any errors, so just return
 			 * here.
 			 */
-			ret = btrfs_submit_compressed_read(inode, bio,
-							   mirror_num,
-							   bio_flags);
-			goto out_no_endio;
+			btrfs_submit_compressed_read(inode, bio, mirror_num);
+			return;
 		} else {
 			/*
 			 * Lookup bio sums does extra checks around whether we
@@ -2555,7 +2652,7 @@ blk_status_t btrfs_submit_data_bio(struct inode *inode, struct bio *bio,
 		if (btrfs_is_data_reloc_root(root))
 			goto mapit;
 		/* we're doing a write, do the async checksumming */
-		ret = btrfs_wq_submit_bio(inode, bio, mirror_num, bio_flags,
+		ret = btrfs_wq_submit_bio(inode, bio, mirror_num,
 					  0, btrfs_submit_bio_start);
 		goto out;
 	} else if (!skip_sum) {
@@ -2572,8 +2669,6 @@ out:
 		bio->bi_status = ret;
 		bio_endio(bio);
 	}
-out_no_endio:
-	return ret;
 }
 
 /*
@@ -3264,11 +3359,11 @@ static int check_data_csum(struct inode *inode, struct btrfs_bio *bbio,
 	shash->tfm = fs_info->csum_shash;
 
 	crypto_shash_digest(shash, kaddr + pgoff, len, csum);
+	kunmap_atomic(kaddr);
 
 	if (memcmp(csum, csum_expected, csum_size))
 		goto zeroit;
 
-	kunmap_atomic(kaddr);
 	return 0;
 zeroit:
 	btrfs_print_data_csum_error(BTRFS_I(inode), start, csum, csum_expected,
@@ -3276,9 +3371,7 @@ zeroit:
 	if (bbio->device)
 		btrfs_dev_stat_inc_and_print(bbio->device,
 					     BTRFS_DEV_STAT_CORRUPTION_ERRS);
-	memset(kaddr + pgoff, 1, len);
-	flush_dcache_page(page);
-	kunmap_atomic(kaddr);
+	memzero_page(page, pgoff, len);
 	return -EIO;
 }
 
@@ -3483,6 +3576,7 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
 	u64 last_objectid = 0;
 	int ret = 0, nr_unlink = 0;
 
+	/* Bail out if the cleanup is already running. */
 	if (test_and_set_bit(BTRFS_ROOT_ORPHAN_CLEANUP, &root->state))
 		return 0;
 
@@ -3565,17 +3659,17 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
 			 *
 			 * btrfs_find_orphan_roots() ran before us, which has
 			 * found all deleted roots and loaded them into
-			 * fs_info->fs_roots_radix. So here we can find if an
+			 * fs_info->fs_roots. So here we can find if an
 			 * orphan item corresponds to a deleted root by looking
-			 * up the root from that radix tree.
+			 * up the root from that xarray.
 			 */
 
-			spin_lock(&fs_info->fs_roots_radix_lock);
-			dead_root = radix_tree_lookup(&fs_info->fs_roots_radix,
-							 (unsigned long)found_key.objectid);
+			spin_lock(&fs_info->fs_roots_lock);
+			dead_root = xa_load(&fs_info->fs_roots,
+					    (unsigned long)found_key.objectid);
 			if (dead_root && btrfs_root_refs(&dead_root->root_item) == 0)
 				is_dead_root = 1;
-			spin_unlock(&fs_info->fs_roots_radix_lock);
+			spin_unlock(&fs_info->fs_roots_lock);
 
 			if (is_dead_root) {
 				/* prevent this orphan from being found again */
@@ -3815,7 +3909,7 @@ cache_index:
 	 * cache.
 	 *
 	 * This is required for both inode re-read from disk and delayed inode
-	 * in delayed_nodes_tree.
+	 * in the delayed_nodes xarray.
 	 */
 	if (BTRFS_I(inode)->last_trans == fs_info->generation)
 		set_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
@@ -4199,8 +4293,9 @@ static struct btrfs_trans_handle *__unlink_start_trans(struct inode *dir)
 	 * 1 for the dir index
 	 * 1 for the inode ref
 	 * 1 for the inode
+	 * 1 for the parent inode
 	 */
-	return btrfs_start_transaction_fallback_global_rsv(root, 5);
+	return btrfs_start_transaction_fallback_global_rsv(root, 6);
 }
 
 static int btrfs_unlink(struct inode *dir, struct dentry *dentry)
@@ -4693,7 +4788,7 @@ int btrfs_truncate_block(struct btrfs_inode *inode, loff_t from, loff_t len,
 			goto out;
 		}
 	}
-	ret = btrfs_delalloc_reserve_metadata(inode, blocksize, blocksize);
+	ret = btrfs_delalloc_reserve_metadata(inode, blocksize, blocksize, false);
 	if (ret < 0) {
 		if (!only_release_metadata)
 			btrfs_free_reserved_data_space(inode, data_reserved,
@@ -5780,8 +5875,6 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx)
 	struct list_head ins_list;
 	struct list_head del_list;
 	int ret;
-	struct extent_buffer *leaf;
-	int slot;
 	char *name_ptr;
 	int name_len;
 	int entries = 0;
@@ -5808,35 +5901,19 @@ again:
 	key.offset = ctx->pos;
 	key.objectid = btrfs_ino(BTRFS_I(inode));
 
-	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
-	if (ret < 0)
-		goto err;
-
-	while (1) {
+	btrfs_for_each_slot(root, &key, &found_key, path, ret) {
 		struct dir_entry *entry;
-
-		leaf = path->nodes[0];
-		slot = path->slots[0];
-		if (slot >= btrfs_header_nritems(leaf)) {
-			ret = btrfs_next_leaf(root, path);
-			if (ret < 0)
-				goto err;
-			else if (ret > 0)
-				break;
-			continue;
-		}
-
-		btrfs_item_key_to_cpu(leaf, &found_key, slot);
+		struct extent_buffer *leaf = path->nodes[0];
 
 		if (found_key.objectid != key.objectid)
 			break;
 		if (found_key.type != BTRFS_DIR_INDEX_KEY)
 			break;
 		if (found_key.offset < ctx->pos)
-			goto next;
+			continue;
 		if (btrfs_should_delete_dir_index(&del_list, found_key.offset))
-			goto next;
-		di = btrfs_item_ptr(leaf, slot, struct btrfs_dir_item);
+			continue;
+		di = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_dir_item);
 		name_len = btrfs_dir_name_len(leaf, di);
 		if ((total_len + sizeof(struct dir_entry) + name_len) >=
 		    PAGE_SIZE) {
@@ -5863,9 +5940,11 @@ again:
 		entries++;
 		addr += sizeof(struct dir_entry) + name_len;
 		total_len += sizeof(struct dir_entry) + name_len;
-next:
-		path->slots[0]++;
 	}
+	/* Catch error encountered during iteration */
+	if (ret < 0)
+		goto err;
+
 	btrfs_release_path(path);
 
 	ret = btrfs_filldir(private->filldir_buf, entries, ctx);
@@ -6053,6 +6132,57 @@ static int btrfs_insert_inode_locked(struct inode *inode)
 		   btrfs_find_actor, &args);
 }
 
+int btrfs_new_inode_prepare(struct btrfs_new_inode_args *args,
+			    unsigned int *trans_num_items)
+{
+	struct inode *dir = args->dir;
+	struct inode *inode = args->inode;
+	int ret;
+
+	ret = posix_acl_create(dir, &inode->i_mode, &args->default_acl, &args->acl);
+	if (ret)
+		return ret;
+
+	/* 1 to add inode item */
+	*trans_num_items = 1;
+	/* 1 to add compression property */
+	if (BTRFS_I(dir)->prop_compress)
+		(*trans_num_items)++;
+	/* 1 to add default ACL xattr */
+	if (args->default_acl)
+		(*trans_num_items)++;
+	/* 1 to add access ACL xattr */
+	if (args->acl)
+		(*trans_num_items)++;
+#ifdef CONFIG_SECURITY
+	/* 1 to add LSM xattr */
+	if (dir->i_security)
+		(*trans_num_items)++;
+#endif
+	if (args->orphan) {
+		/* 1 to add orphan item */
+		(*trans_num_items)++;
+	} else {
+		/*
+		 * 1 to add dir item
+		 * 1 to add dir index
+		 * 1 to update parent inode item
+		 *
+		 * No need for 1 unit for the inode ref item because it is
+		 * inserted in a batch together with the inode item at
+		 * btrfs_create_new_inode().
+		 */
+		*trans_num_items += 3;
+	}
+	return 0;
+}
+
+void btrfs_new_inode_args_destroy(struct btrfs_new_inode_args *args)
+{
+	posix_acl_release(args->acl);
+	posix_acl_release(args->default_acl);
+}
+
 /*
  * Inherit flags from the parent inode.
  *
@@ -6062,9 +6192,6 @@ static void btrfs_inherit_iflags(struct inode *inode, struct inode *dir)
 {
 	unsigned int flags;
 
-	if (!dir)
-		return;
-
 	flags = BTRFS_I(dir)->flags;
 
 	if (flags & BTRFS_INODE_NOCOMPRESS) {
@@ -6084,76 +6211,86 @@ static void btrfs_inherit_iflags(struct inode *inode, struct inode *dir)
 	btrfs_sync_inode_flags_to_i_flags(inode);
 }
 
-static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
-				     struct btrfs_root *root,
-				     struct user_namespace *mnt_userns,
-				     struct inode *dir,
-				     const char *name, int name_len,
-				     u64 ref_objectid, u64 objectid,
-				     umode_t mode, u64 *index)
+int btrfs_create_new_inode(struct btrfs_trans_handle *trans,
+			   struct btrfs_new_inode_args *args)
 {
-	struct btrfs_fs_info *fs_info = root->fs_info;
-	struct inode *inode;
+	struct inode *dir = args->dir;
+	struct inode *inode = args->inode;
+	const char *name = args->orphan ? NULL : args->dentry->d_name.name;
+	int name_len = args->orphan ? 0 : args->dentry->d_name.len;
+	struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb);
+	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;
 	struct btrfs_key key[2];
 	u32 sizes[2];
 	struct btrfs_item_batch batch;
 	unsigned long ptr;
-	unsigned int nofs_flag;
 	int ret;
 
 	path = btrfs_alloc_path();
 	if (!path)
-		return ERR_PTR(-ENOMEM);
-
-	nofs_flag = memalloc_nofs_save();
-	inode = new_inode(fs_info->sb);
-	memalloc_nofs_restore(nofs_flag);
-	if (!inode) {
-		btrfs_free_path(path);
-		return ERR_PTR(-ENOMEM);
-	}
+		return -ENOMEM;
 
-	/*
-	 * O_TMPFILE, set link count to 0, so that after this point,
-	 * we fill in an inode item with the correct link count.
-	 */
-	if (!name)
-		set_nlink(inode, 0);
+	if (!args->subvol)
+		BTRFS_I(inode)->root = btrfs_grab_root(BTRFS_I(dir)->root);
+	root = BTRFS_I(inode)->root;
 
-	/*
-	 * we have to initialize this early, so we can reclaim the inode
-	 * number if we fail afterwards in this function.
-	 */
+	ret = btrfs_get_free_objectid(root, &objectid);
+	if (ret)
+		goto out;
 	inode->i_ino = objectid;
 
-	if (dir && name) {
+	if (args->orphan) {
+		/*
+		 * O_TMPFILE, set link count to 0, so that after this point, we
+		 * fill in an inode item with the correct link count.
+		 */
+		set_nlink(inode, 0);
+	} else {
 		trace_btrfs_inode_request(dir);
 
-		ret = btrfs_set_inode_index(BTRFS_I(dir), index);
-		if (ret) {
-			btrfs_free_path(path);
-			iput(inode);
-			return ERR_PTR(ret);
-		}
-	} else if (dir) {
-		*index = 0;
+		ret = btrfs_set_inode_index(BTRFS_I(dir), &BTRFS_I(inode)->dir_index);
+		if (ret)
+			goto out;
 	}
-	/*
-	 * index_cnt is ignored for everything but a dir,
-	 * btrfs_set_inode_index_count has an explanation for the magic
-	 * number
-	 */
-	BTRFS_I(inode)->index_cnt = 2;
-	BTRFS_I(inode)->dir_index = *index;
-	BTRFS_I(inode)->root = btrfs_grab_root(root);
+	/* index_cnt is ignored for everything but a dir. */
+	BTRFS_I(inode)->index_cnt = BTRFS_DIR_START_INDEX;
 	BTRFS_I(inode)->generation = trans->transid;
 	inode->i_generation = BTRFS_I(inode)->generation;
 
 	/*
+	 * Subvolumes don't inherit flags from their parent directory.
+	 * Originally this was probably by accident, but we probably can't
+	 * change it now without compatibility issues.
+	 */
+	if (!args->subvol)
+		btrfs_inherit_iflags(inode, dir);
+
+	if (S_ISREG(inode->i_mode)) {
+		if (btrfs_test_opt(fs_info, NODATASUM))
+			BTRFS_I(inode)->flags |= BTRFS_INODE_NODATASUM;
+		if (btrfs_test_opt(fs_info, NODATACOW))
+			BTRFS_I(inode)->flags |= BTRFS_INODE_NODATACOW |
+				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)
+			BTRFS_I(dir)->index_cnt--;
+		goto out;
+	}
+
+	/*
 	 * We could have gotten an inode number from somebody who was fsynced
 	 * and then removed in this same transaction, so let's just set full
 	 * sync since it will be a full sync anyway and this will blow away the
@@ -6167,7 +6304,7 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
 
 	sizes[0] = sizeof(struct btrfs_inode_item);
 
-	if (name) {
+	if (!args->orphan) {
 		/*
 		 * Start new inodes with an inode_ref. This is slightly more
 		 * efficient for small numbers of hard links since they will
@@ -6176,64 +6313,95 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
 		 */
 		key[1].objectid = objectid;
 		key[1].type = BTRFS_INODE_REF_KEY;
-		key[1].offset = ref_objectid;
-
-		sizes[1] = name_len + sizeof(*ref);
-	}
-
-	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) {
-		iput(inode);
-		goto fail;
+		if (args->subvol) {
+			key[1].offset = objectid;
+			sizes[1] = 2 + sizeof(*ref);
+		} else {
+			key[1].offset = btrfs_ino(BTRFS_I(dir));
+			sizes[1] = name_len + sizeof(*ref);
+		}
 	}
 
 	batch.keys = &key[0];
 	batch.data_sizes = &sizes[0];
-	batch.total_data_size = sizes[0] + (name ? sizes[1] : 0);
-	batch.nr = name ? 2 : 1;
+	batch.total_data_size = sizes[0] + (args->orphan ? 0 : sizes[1]);
+	batch.nr = args->orphan ? 1 : 2;
 	ret = btrfs_insert_empty_items(trans, root, path, &batch);
-	if (ret != 0)
-		goto fail_unlock;
-
-	inode_init_owner(mnt_userns, inode, dir, mode);
-	inode_set_bytes(inode, 0);
+	if (ret != 0) {
+		btrfs_abort_transaction(trans, ret);
+		goto discard;
+	}
 
 	inode->i_mtime = current_time(inode);
 	inode->i_atime = inode->i_mtime;
 	inode->i_ctime = inode->i_mtime;
 	BTRFS_I(inode)->i_otime = inode->i_mtime;
 
+	/*
+	 * We're going to fill the inode item now, so at this point the inode
+	 * must be fully initialized.
+	 */
+
 	inode_item = btrfs_item_ptr(path->nodes[0], path->slots[0],
 				  struct btrfs_inode_item);
 	memzero_extent_buffer(path->nodes[0], (unsigned long)inode_item,
 			     sizeof(*inode_item));
 	fill_inode_item(trans, path->nodes[0], inode_item, inode);
 
-	if (name) {
+	if (!args->orphan) {
 		ref = btrfs_item_ptr(path->nodes[0], path->slots[0] + 1,
 				     struct btrfs_inode_ref);
-		btrfs_set_inode_ref_name_len(path->nodes[0], ref, name_len);
-		btrfs_set_inode_ref_index(path->nodes[0], ref, *index);
 		ptr = (unsigned long)(ref + 1);
-		write_extent_buffer(path->nodes[0], name, ptr, name_len);
+		if (args->subvol) {
+			btrfs_set_inode_ref_name_len(path->nodes[0], ref, 2);
+			btrfs_set_inode_ref_index(path->nodes[0], ref, 0);
+			write_extent_buffer(path->nodes[0], "..", ptr, 2);
+		} else {
+			btrfs_set_inode_ref_name_len(path->nodes[0], ref, name_len);
+			btrfs_set_inode_ref_index(path->nodes[0], ref,
+						  BTRFS_I(inode)->dir_index);
+			write_extent_buffer(path->nodes[0], name, ptr, name_len);
+		}
 	}
 
 	btrfs_mark_buffer_dirty(path->nodes[0]);
-	btrfs_free_path(path);
+	btrfs_release_path(path);
 
-	btrfs_inherit_iflags(inode, dir);
+	if (args->subvol) {
+		struct inode *parent;
 
-	if (S_ISREG(mode)) {
-		if (btrfs_test_opt(fs_info, NODATASUM))
-			BTRFS_I(inode)->flags |= BTRFS_INODE_NODATASUM;
-		if (btrfs_test_opt(fs_info, NODATACOW))
-			BTRFS_I(inode)->flags |= BTRFS_INODE_NODATACOW |
-				BTRFS_INODE_NODATASUM;
+		/*
+		 * 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);
+		if (IS_ERR(parent)) {
+			ret = PTR_ERR(parent);
+		} else {
+			ret = btrfs_inode_inherit_props(trans, inode, parent);
+			iput(parent);
+		}
+	} else {
+		ret = btrfs_inode_inherit_props(trans, inode, dir);
+	}
+	if (ret) {
+		btrfs_err(fs_info,
+			  "error inheriting props for ino %llu (root %llu): %d",
+			  btrfs_ino(BTRFS_I(inode)), root->root_key.objectid,
+			  ret);
+	}
+
+	/*
+	 * Subvolumes don't inherit ACLs or get passed to the LSM. This is
+	 * probably a bug.
+	 */
+	if (!args->subvol) {
+		ret = btrfs_init_inode_security(trans, args);
+		if (ret) {
+			btrfs_abort_transaction(trans, ret);
+			goto discard;
+		}
 	}
 
 	inode_tree_add(inode);
@@ -6243,21 +6411,30 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
 
 	btrfs_update_root_times(trans, root);
 
-	ret = btrfs_inode_inherit_props(trans, inode, dir);
-	if (ret)
-		btrfs_err(fs_info,
-			  "error inheriting props for ino %llu (root %llu): %d",
-			btrfs_ino(BTRFS_I(inode)), root->root_key.objectid, ret);
+	if (args->orphan) {
+		ret = btrfs_orphan_add(trans, BTRFS_I(inode));
+	} else {
+		ret = btrfs_add_link(trans, BTRFS_I(dir), BTRFS_I(inode), name,
+				     name_len, 0, BTRFS_I(inode)->dir_index);
+	}
+	if (ret) {
+		btrfs_abort_transaction(trans, ret);
+		goto discard;
+	}
 
-	return inode;
+	ret = 0;
+	goto out;
 
-fail_unlock:
+discard:
+	/*
+	 * discard_new_inode() calls iput(), but the caller owns the reference
+	 * to the inode.
+	 */
+	ihold(inode);
 	discard_new_inode(inode);
-fail:
-	if (dir && name)
-		BTRFS_I(dir)->index_cnt--;
+out:
 	btrfs_free_path(path);
-	return ERR_PTR(ret);
+	return ret;
 }
 
 /*
@@ -6349,147 +6526,71 @@ fail_dir_item:
 	return ret;
 }
 
-static int btrfs_add_nondir(struct btrfs_trans_handle *trans,
-			    struct btrfs_inode *dir, struct dentry *dentry,
-			    struct btrfs_inode *inode, int backref, u64 index)
-{
-	int err = btrfs_add_link(trans, dir, inode,
-				 dentry->d_name.name, dentry->d_name.len,
-				 backref, index);
-	if (err > 0)
-		err = -EEXIST;
-	return err;
-}
-
-static int btrfs_mknod(struct user_namespace *mnt_userns, struct inode *dir,
-		       struct dentry *dentry, umode_t mode, dev_t rdev)
+static int btrfs_create_common(struct inode *dir, struct dentry *dentry,
+			       struct inode *inode)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb);
-	struct btrfs_trans_handle *trans;
 	struct btrfs_root *root = BTRFS_I(dir)->root;
-	struct inode *inode = NULL;
+	struct btrfs_new_inode_args new_inode_args = {
+		.dir = dir,
+		.dentry = dentry,
+		.inode = inode,
+	};
+	unsigned int trans_num_items;
+	struct btrfs_trans_handle *trans;
 	int err;
-	u64 objectid;
-	u64 index = 0;
 
-	/*
-	 * 2 for inode item and ref
-	 * 2 for dir items
-	 * 1 for xattr if selinux is on
-	 */
-	trans = btrfs_start_transaction(root, 5);
-	if (IS_ERR(trans))
-		return PTR_ERR(trans);
-
-	err = btrfs_get_free_objectid(root, &objectid);
+	err = btrfs_new_inode_prepare(&new_inode_args, &trans_num_items);
 	if (err)
-		goto out_unlock;
+		goto out_inode;
 
-	inode = btrfs_new_inode(trans, root, mnt_userns, dir,
-			dentry->d_name.name, dentry->d_name.len,
-			btrfs_ino(BTRFS_I(dir)), objectid, mode, &index);
-	if (IS_ERR(inode)) {
-		err = PTR_ERR(inode);
-		inode = NULL;
-		goto out_unlock;
+	trans = btrfs_start_transaction(root, trans_num_items);
+	if (IS_ERR(trans)) {
+		err = PTR_ERR(trans);
+		goto out_new_inode_args;
 	}
 
-	/*
-	* If the active LSM wants to access the inode during
-	* d_instantiate it needs these. Smack checks to see
-	* if the filesystem supports xattrs by looking at the
-	* ops vector.
-	*/
-	inode->i_op = &btrfs_special_inode_operations;
-	init_special_inode(inode, inode->i_mode, rdev);
-
-	err = btrfs_init_inode_security(trans, inode, dir, &dentry->d_name);
-	if (err)
-		goto out_unlock;
-
-	err = btrfs_add_nondir(trans, BTRFS_I(dir), dentry, BTRFS_I(inode),
-			0, index);
-	if (err)
-		goto out_unlock;
-
-	btrfs_update_inode(trans, root, BTRFS_I(inode));
-	d_instantiate_new(dentry, inode);
+	err = btrfs_create_new_inode(trans, &new_inode_args);
+	if (!err)
+		d_instantiate_new(dentry, inode);
 
-out_unlock:
 	btrfs_end_transaction(trans);
 	btrfs_btree_balance_dirty(fs_info);
-	if (err && inode) {
-		inode_dec_link_count(inode);
-		discard_new_inode(inode);
-	}
+out_new_inode_args:
+	btrfs_new_inode_args_destroy(&new_inode_args);
+out_inode:
+	if (err)
+		iput(inode);
 	return err;
 }
 
-static int btrfs_create(struct user_namespace *mnt_userns, struct inode *dir,
-			struct dentry *dentry, umode_t mode, bool excl)
+static int btrfs_mknod(struct user_namespace *mnt_userns, struct inode *dir,
+		       struct dentry *dentry, umode_t mode, dev_t rdev)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb);
-	struct btrfs_trans_handle *trans;
-	struct btrfs_root *root = BTRFS_I(dir)->root;
-	struct inode *inode = NULL;
-	int err;
-	u64 objectid;
-	u64 index = 0;
+	struct inode *inode;
 
-	/*
-	 * 2 for inode item and ref
-	 * 2 for dir items
-	 * 1 for xattr if selinux is on
-	 */
-	trans = btrfs_start_transaction(root, 5);
-	if (IS_ERR(trans))
-		return PTR_ERR(trans);
+	inode = new_inode(dir->i_sb);
+	if (!inode)
+		return -ENOMEM;
+	inode_init_owner(mnt_userns, 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);
+}
 
-	err = btrfs_get_free_objectid(root, &objectid);
-	if (err)
-		goto out_unlock;
+static int btrfs_create(struct user_namespace *mnt_userns, struct inode *dir,
+			struct dentry *dentry, umode_t mode, bool excl)
+{
+	struct inode *inode;
 
-	inode = btrfs_new_inode(trans, root, mnt_userns, dir,
-			dentry->d_name.name, dentry->d_name.len,
-			btrfs_ino(BTRFS_I(dir)), objectid, mode, &index);
-	if (IS_ERR(inode)) {
-		err = PTR_ERR(inode);
-		inode = NULL;
-		goto out_unlock;
-	}
-	/*
-	* If the active LSM wants to access the inode during
-	* d_instantiate it needs these. Smack checks to see
-	* if the filesystem supports xattrs by looking at the
-	* ops vector.
-	*/
+	inode = new_inode(dir->i_sb);
+	if (!inode)
+		return -ENOMEM;
+	inode_init_owner(mnt_userns, inode, dir, mode);
 	inode->i_fop = &btrfs_file_operations;
 	inode->i_op = &btrfs_file_inode_operations;
 	inode->i_mapping->a_ops = &btrfs_aops;
-
-	err = btrfs_init_inode_security(trans, inode, dir, &dentry->d_name);
-	if (err)
-		goto out_unlock;
-
-	err = btrfs_update_inode(trans, root, BTRFS_I(inode));
-	if (err)
-		goto out_unlock;
-
-	err = btrfs_add_nondir(trans, BTRFS_I(dir), dentry, BTRFS_I(inode),
-			0, index);
-	if (err)
-		goto out_unlock;
-
-	d_instantiate_new(dentry, inode);
-
-out_unlock:
-	btrfs_end_transaction(trans);
-	if (err && inode) {
-		inode_dec_link_count(inode);
-		discard_new_inode(inode);
-	}
-	btrfs_btree_balance_dirty(fs_info);
-	return err;
+	return btrfs_create_common(dir, dentry, inode);
 }
 
 static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
@@ -6535,8 +6636,8 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
 	ihold(inode);
 	set_bit(BTRFS_INODE_COPY_EVERYTHING, &BTRFS_I(inode)->runtime_flags);
 
-	err = btrfs_add_nondir(trans, BTRFS_I(dir), dentry, BTRFS_I(inode),
-			1, index);
+	err = btrfs_add_link(trans, BTRFS_I(dir), BTRFS_I(inode),
+			     dentry->d_name.name, dentry->d_name.len, 1, index);
 
 	if (err) {
 		drop_inode = 1;
@@ -6573,66 +6674,15 @@ fail:
 static int btrfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
 		       struct dentry *dentry, umode_t mode)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb);
-	struct inode *inode = NULL;
-	struct btrfs_trans_handle *trans;
-	struct btrfs_root *root = BTRFS_I(dir)->root;
-	int err = 0;
-	u64 objectid = 0;
-	u64 index = 0;
-
-	/*
-	 * 2 items for inode and ref
-	 * 2 items for dir items
-	 * 1 for xattr if selinux is on
-	 */
-	trans = btrfs_start_transaction(root, 5);
-	if (IS_ERR(trans))
-		return PTR_ERR(trans);
-
-	err = btrfs_get_free_objectid(root, &objectid);
-	if (err)
-		goto out_fail;
-
-	inode = btrfs_new_inode(trans, root, mnt_userns, dir,
-			dentry->d_name.name, dentry->d_name.len,
-			btrfs_ino(BTRFS_I(dir)), objectid,
-			S_IFDIR | mode, &index);
-	if (IS_ERR(inode)) {
-		err = PTR_ERR(inode);
-		inode = NULL;
-		goto out_fail;
-	}
+	struct inode *inode;
 
-	/* these must be set before we unlock the inode */
+	inode = new_inode(dir->i_sb);
+	if (!inode)
+		return -ENOMEM;
+	inode_init_owner(mnt_userns, inode, dir, S_IFDIR | mode);
 	inode->i_op = &btrfs_dir_inode_operations;
 	inode->i_fop = &btrfs_dir_file_operations;
-
-	err = btrfs_init_inode_security(trans, inode, dir, &dentry->d_name);
-	if (err)
-		goto out_fail;
-
-	btrfs_i_size_write(BTRFS_I(inode), 0);
-	err = btrfs_update_inode(trans, root, BTRFS_I(inode));
-	if (err)
-		goto out_fail;
-
-	err = btrfs_add_link(trans, BTRFS_I(dir), BTRFS_I(inode),
-			dentry->d_name.name,
-			dentry->d_name.len, 0, index);
-	if (err)
-		goto out_fail;
-
-	d_instantiate_new(dentry, inode);
-
-out_fail:
-	btrfs_end_transaction(trans);
-	if (err && inode) {
-		inode_dec_link_count(inode);
-		discard_new_inode(inode);
-	}
-	btrfs_btree_balance_dirty(fs_info);
-	return err;
+	return btrfs_create_common(dir, dentry, inode);
 }
 
 static noinline int uncompress_inline(struct btrfs_path *path,
@@ -7141,6 +7191,7 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len,
 			      u64 *ram_bytes, bool strict)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct can_nocow_file_extent_args nocow_args = { 0 };
 	struct btrfs_path *path;
 	int ret;
 	struct extent_buffer *leaf;
@@ -7148,13 +7199,7 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len,
 	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
 	struct btrfs_file_extent_item *fi;
 	struct btrfs_key key;
-	u64 disk_bytenr;
-	u64 backref_offset;
-	u64 extent_end;
-	u64 num_bytes;
-	int slot;
 	int found_type;
-	bool nocow = (BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW);
 
 	path = btrfs_alloc_path();
 	if (!path)
@@ -7165,18 +7210,17 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len,
 	if (ret < 0)
 		goto out;
 
-	slot = path->slots[0];
 	if (ret == 1) {
-		if (slot == 0) {
+		if (path->slots[0] == 0) {
 			/* can't find the item, must cow */
 			ret = 0;
 			goto out;
 		}
-		slot--;
+		path->slots[0]--;
 	}
 	ret = 0;
 	leaf = path->nodes[0];
-	btrfs_item_key_to_cpu(leaf, &key, slot);
+	btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
 	if (key.objectid != btrfs_ino(BTRFS_I(inode)) ||
 	    key.type != BTRFS_EXTENT_DATA_KEY) {
 		/* not our file or wrong item type, must cow */
@@ -7188,55 +7232,38 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len,
 		goto out;
 	}
 
-	fi = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item);
-	found_type = btrfs_file_extent_type(leaf, fi);
-	if (found_type != BTRFS_FILE_EXTENT_REG &&
-	    found_type != BTRFS_FILE_EXTENT_PREALLOC) {
-		/* not a regular extent, must cow */
-		goto out;
-	}
-
-	if (!nocow && found_type == BTRFS_FILE_EXTENT_REG)
+	if (btrfs_file_extent_end(path) <= offset)
 		goto out;
 
-	extent_end = key.offset + btrfs_file_extent_num_bytes(leaf, fi);
-	if (extent_end <= offset)
-		goto out;
+	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);
 
-	disk_bytenr = btrfs_file_extent_disk_bytenr(leaf, fi);
-	if (disk_bytenr == 0)
-		goto out;
+	nocow_args.start = offset;
+	nocow_args.end = offset + *len - 1;
+	nocow_args.strict = strict;
+	nocow_args.free_path = true;
 
-	if (btrfs_file_extent_compression(leaf, fi) ||
-	    btrfs_file_extent_encryption(leaf, fi) ||
-	    btrfs_file_extent_other_encoding(leaf, fi))
-		goto out;
+	ret = can_nocow_file_extent(path, &key, BTRFS_I(inode), &nocow_args);
+	/* can_nocow_file_extent() has freed the path. */
+	path = NULL;
 
-	/*
-	 * Do the same check as in btrfs_cross_ref_exist but without the
-	 * unnecessary search.
-	 */
-	if (!strict &&
-	    (btrfs_file_extent_generation(leaf, fi) <=
-	     btrfs_root_last_snapshot(&root->root_item)))
+	if (ret != 1) {
+		/* Treat errors as not being able to NOCOW. */
+		ret = 0;
 		goto out;
-
-	backref_offset = btrfs_file_extent_offset(leaf, fi);
-
-	if (orig_start) {
-		*orig_start = key.offset - backref_offset;
-		*orig_block_len = btrfs_file_extent_disk_num_bytes(leaf, fi);
-		*ram_bytes = btrfs_file_extent_ram_bytes(leaf, fi);
 	}
 
-	if (btrfs_extent_readonly(fs_info, disk_bytenr))
+	ret = 0;
+	if (btrfs_extent_readonly(fs_info, nocow_args.disk_bytenr))
 		goto out;
 
-	num_bytes = min(offset + *len, extent_end) - offset;
-	if (!nocow && found_type == BTRFS_FILE_EXTENT_PREALLOC) {
+	if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW) &&
+	    found_type == BTRFS_FILE_EXTENT_PREALLOC) {
 		u64 range_end;
 
-		range_end = round_up(offset + num_bytes,
+		range_end = round_up(offset + nocow_args.num_bytes,
 				     root->fs_info->sectorsize) - 1;
 		ret = test_range_bit(io_tree, offset, range_end,
 				     EXTENT_DELALLOC, 0, NULL);
@@ -7246,36 +7273,12 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len,
 		}
 	}
 
-	btrfs_release_path(path);
-
-	/*
-	 * look for other files referencing this extent, if we
-	 * find any we must cow
-	 */
-
-	ret = btrfs_cross_ref_exist(root, btrfs_ino(BTRFS_I(inode)),
-				    key.offset - backref_offset, disk_bytenr,
-				    strict);
-	if (ret) {
-		ret = 0;
-		goto out;
-	}
+	if (orig_start)
+		*orig_start = key.offset - nocow_args.extent_offset;
+	if (orig_block_len)
+		*orig_block_len = nocow_args.disk_num_bytes;
 
-	/*
-	 * adjust disk_bytenr and num_bytes to cover just the bytes
-	 * in this extent we are about to write.  If there
-	 * are any csums in that range we have to cow in order
-	 * to keep the csums correct
-	 */
-	disk_bytenr += backref_offset;
-	disk_bytenr += offset - key.offset;
-	if (csum_exist_in_range(fs_info, disk_bytenr, num_bytes))
-		goto out;
-	/*
-	 * all of the above have passed, it is safe to overwrite this extent
-	 * without cow
-	 */
-	*len = num_bytes;
+	*len = nocow_args.num_bytes;
 	ret = 1;
 out:
 	btrfs_free_path(path);
@@ -7283,14 +7286,22 @@ out:
 }
 
 static int lock_extent_direct(struct inode *inode, u64 lockstart, u64 lockend,
-			      struct extent_state **cached_state, bool writing)
+			      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) {
-		lock_extent_bits(&BTRFS_I(inode)->io_tree, lockstart, lockend,
-				 cached_state);
+		if (nowait) {
+			if (!try_lock_extent(io_tree, lockstart, lockend))
+				return -EAGAIN;
+		} else {
+			lock_extent_bits(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
@@ -7311,10 +7322,14 @@ static int lock_extent_direct(struct inode *inode, u64 lockstart, u64 lockend,
 							 lockstart, lockend)))
 			break;
 
-		unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart, lockend,
-				     cached_state);
+		unlock_extent_cached(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
@@ -7334,7 +7349,7 @@ static int lock_extent_direct(struct inode *inode, u64 lockstart, u64 lockend,
 			    test_bit(BTRFS_ORDERED_DIRECT, &ordered->flags))
 				btrfs_start_ordered_extent(ordered, 1);
 			else
-				ret = -ENOTBLK;
+				ret = nowait ? -EAGAIN : -ENOTBLK;
 			btrfs_put_ordered_extent(ordered);
 		} else {
 			/*
@@ -7350,7 +7365,7 @@ static int lock_extent_direct(struct inode *inode, u64 lockstart, u64 lockend,
 			 * ordered extent to complete while holding a lock on
 			 * that page.
 			 */
-			ret = -ENOTBLK;
+			ret = nowait ? -EAGAIN : -ENOTBLK;
 		}
 
 		if (ret)
@@ -7424,12 +7439,15 @@ static struct extent_map *create_io_em(struct btrfs_inode *inode, u64 start,
 static int btrfs_get_blocks_direct_write(struct extent_map **map,
 					 struct inode *inode,
 					 struct btrfs_dio_data *dio_data,
-					 u64 start, u64 len)
+					 u64 start, u64 len,
+					 unsigned int iomap_flags)
 {
+	const bool nowait = (iomap_flags & IOMAP_NOWAIT);
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	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 prev_len;
@@ -7455,9 +7473,11 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map,
 		block_start = em->block_start + (start - em->start);
 
 		if (can_nocow_extent(inode, start, &len, &orig_start,
-				     &orig_block_len, &ram_bytes, false) == 1 &&
-		    btrfs_inc_nocow_writers(fs_info, block_start))
-			can_nocow = true;
+				     &orig_block_len, &ram_bytes, false) == 1) {
+			bg = btrfs_inc_nocow_writers(fs_info, block_start);
+			if (bg)
+				can_nocow = true;
+		}
 	}
 
 	prev_len = len;
@@ -7465,12 +7485,15 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map,
 		struct extent_map *em2;
 
 		/* We can NOCOW, so only need to reserve metadata space. */
-		ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode), len, len);
+		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(fs_info, block_start);
+			btrfs_dec_nocow_writers(bg);
+			if (nowait && (ret == -ENOSPC || ret == -EDQUOT))
+				ret = -EAGAIN;
 			goto out;
 		}
 		space_reserved = true;
@@ -7479,7 +7502,7 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map,
 					      orig_start, block_start,
 					      len, orig_block_len,
 					      ram_bytes, type);
-		btrfs_dec_nocow_writers(fs_info, block_start);
+		btrfs_dec_nocow_writers(bg);
 		if (type == BTRFS_ORDERED_PREALLOC) {
 			free_extent_map(em);
 			*map = em = em2;
@@ -7489,15 +7512,29 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map,
 			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;
 
-		/* We have to COW, so need to reserve metadata and data space. */
-		ret = btrfs_delalloc_reserve_space(BTRFS_I(inode),
-						   &dio_data->data_reserved,
-						   start, len);
+		if (nowait)
+			return -EAGAIN;
+
+		/*
+		 * 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)
+			return -ENOSPC;
+
+		/*
+		 * 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;
@@ -7510,10 +7547,8 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map,
 		*map = em;
 		len = min(len, em->len - (start - em->start));
 		if (len < prev_len)
-			btrfs_delalloc_release_space(BTRFS_I(inode),
-						     dio_data->data_reserved,
-						     start + len, prev_len - len,
-						     true);
+			btrfs_delalloc_release_metadata(BTRFS_I(inode),
+							prev_len - len, true);
 	}
 
 	/*
@@ -7531,15 +7566,7 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map,
 out:
 	if (ret && space_reserved) {
 		btrfs_delalloc_release_extents(BTRFS_I(inode), len);
-		if (can_nocow) {
-			btrfs_delalloc_release_metadata(BTRFS_I(inode), len, true);
-		} else {
-			btrfs_delalloc_release_space(BTRFS_I(inode),
-						     dio_data->data_reserved,
-						     start, len, true);
-			extent_changeset_free(dio_data->data_reserved);
-			dio_data->data_reserved = NULL;
-		}
+		btrfs_delalloc_release_metadata(BTRFS_I(inode), len, true);
 	}
 	return ret;
 }
@@ -7548,14 +7575,16 @@ 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 = btrfs_sb(inode->i_sb);
 	struct extent_map *em;
 	struct extent_state *cached_state = NULL;
-	struct btrfs_dio_data *dio_data = 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;
 
 	if (!write)
@@ -7565,34 +7594,67 @@ static int btrfs_dio_iomap_begin(struct inode *inode, loff_t start,
 	lockend = start + len - 1;
 
 	/*
-	 * The generic stuff 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.
+	 * 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)) {
-		ret = filemap_fdatawrite_range(inode->i_mapping, start,
-					       start + length - 1);
-		if (ret)
-			return ret;
+		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;
+		}
 	}
 
-	dio_data = kzalloc(sizeof(*dio_data), GFP_NOFS);
-	if (!dio_data)
-		return -ENOMEM;
-
-	iomap->private = dio_data;
+	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);
+		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.
+	 * this range and we need to fallback to buffered IO, or we are doing a
+	 * NOWAIT read/write and we need to block.
 	 */
-	if (lock_extent_direct(inode, lockstart, lockend, &cached_state, write)) {
-		ret = -ENOTBLK;
+	ret = lock_extent_direct(inode, lockstart, lockend, &cached_state, flags);
+	if (ret < 0)
 		goto err;
-	}
 
 	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, start, len);
 	if (IS_ERR(em)) {
@@ -7652,12 +7714,30 @@ static int btrfs_dio_iomap_begin(struct inode *inode, loff_t start,
 
 	if (write) {
 		ret = btrfs_get_blocks_direct_write(&em, inode, dio_data,
-						    start, len);
+						    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.
@@ -7702,7 +7782,12 @@ unlock_err:
 	unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart, lockend,
 			     &cached_state);
 err:
-	kfree(dio_data);
+	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;
 }
@@ -7710,15 +7795,16 @@ err:
 static int btrfs_dio_iomap_end(struct inode *inode, loff_t pos, loff_t length,
 		ssize_t written, unsigned int flags, struct iomap *iomap)
 {
-	int ret = 0;
-	struct btrfs_dio_data *dio_data = iomap->private;
+	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);
-		goto out;
+		return 0;
 	}
 
 	if (submitted < length) {
@@ -7735,10 +7821,6 @@ static int btrfs_dio_iomap_end(struct inode *inode, loff_t pos, loff_t length,
 
 	if (write)
 		extent_changeset_free(dio_data->data_reserved);
-out:
-	kfree(dio_data);
-	iomap->private = NULL;
-
 	return ret;
 }
 
@@ -7751,40 +7833,36 @@ static void btrfs_dio_private_put(struct btrfs_dio_private *dip)
 	if (!refcount_dec_and_test(&dip->refs))
 		return;
 
-	if (btrfs_op(dip->dio_bio) == BTRFS_MAP_WRITE) {
+	if (btrfs_op(&dip->bio) == BTRFS_MAP_WRITE) {
 		__endio_write_update_ordered(BTRFS_I(dip->inode),
 					     dip->file_offset,
 					     dip->bytes,
-					     !dip->dio_bio->bi_status);
+					     !dip->bio.bi_status);
 	} else {
 		unlock_extent(&BTRFS_I(dip->inode)->io_tree,
 			      dip->file_offset,
 			      dip->file_offset + dip->bytes - 1);
 	}
 
-	bio_endio(dip->dio_bio);
-	kfree(dip);
+	kfree(dip->csums);
+	bio_endio(&dip->bio);
 }
 
-static blk_status_t submit_dio_repair_bio(struct inode *inode, struct bio *bio,
-					  int mirror_num,
-					  unsigned long bio_flags)
+static void submit_dio_repair_bio(struct inode *inode, struct bio *bio,
+				  int mirror_num,
+				  enum btrfs_compression_type compress_type)
 {
 	struct btrfs_dio_private *dip = bio->bi_private;
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
-	blk_status_t ret;
 
 	BUG_ON(bio_op(bio) == REQ_OP_WRITE);
 
-	ret = btrfs_bio_wq_end_io(fs_info, bio, BTRFS_WQ_ENDIO_DATA);
-	if (ret)
-		return ret;
+	if (btrfs_bio_wq_end_io(fs_info, bio, BTRFS_WQ_ENDIO_DATA))
+		return;
 
 	refcount_inc(&dip->refs);
-	ret = btrfs_map_bio(fs_info, bio, mirror_num);
-	if (ret)
+	if (btrfs_map_bio(fs_info, bio, mirror_num))
 		refcount_dec(&dip->refs);
-	return ret;
 }
 
 static blk_status_t btrfs_check_read_dio_bio(struct btrfs_dio_private *dip,
@@ -7869,7 +7947,7 @@ static void btrfs_end_dio_bio(struct bio *bio)
 		err = btrfs_check_read_dio_bio(dip, bbio, !err);
 
 	if (err)
-		dip->dio_bio->bi_status = err;
+		dip->bio.bi_status = err;
 
 	btrfs_record_physical_zoned(dip->inode, bbio->file_offset, bio);
 
@@ -7899,7 +7977,7 @@ static inline blk_status_t btrfs_submit_dio_bio(struct bio *bio,
 		goto map;
 
 	if (write && async_submit) {
-		ret = btrfs_wq_submit_bio(inode, bio, 0, 0, file_offset,
+		ret = btrfs_wq_submit_bio(inode, bio, 0, file_offset,
 					  btrfs_submit_bio_start_direct_io);
 		goto err;
 	} else if (write) {
@@ -7924,50 +8002,16 @@ err:
 	return ret;
 }
 
-/*
- * If this succeeds, the btrfs_dio_private is responsible for cleaning up locked
- * or ordered extents whether or not we submit any bios.
- */
-static struct btrfs_dio_private *btrfs_create_dio_private(struct bio *dio_bio,
-							  struct inode *inode,
-							  loff_t file_offset)
-{
-	const bool write = (btrfs_op(dio_bio) == BTRFS_MAP_WRITE);
-	const bool csum = !(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM);
-	size_t dip_size;
-	struct btrfs_dio_private *dip;
-
-	dip_size = sizeof(*dip);
-	if (!write && csum) {
-		struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
-		size_t nblocks;
-
-		nblocks = dio_bio->bi_iter.bi_size >> fs_info->sectorsize_bits;
-		dip_size += fs_info->csum_size * nblocks;
-	}
-
-	dip = kzalloc(dip_size, GFP_NOFS);
-	if (!dip)
-		return NULL;
-
-	dip->inode = inode;
-	dip->file_offset = file_offset;
-	dip->bytes = dio_bio->bi_iter.bi_size;
-	dip->disk_bytenr = dio_bio->bi_iter.bi_sector << 9;
-	dip->dio_bio = dio_bio;
-	refcount_set(&dip->refs, 1);
-	return dip;
-}
-
 static void btrfs_submit_direct(const struct iomap_iter *iter,
 		struct bio *dio_bio, loff_t file_offset)
 {
+	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 btrfs_dio_private *dip;
 	struct bio *bio;
 	u64 start_sector;
 	int async_submit = 0;
@@ -7978,27 +8022,28 @@ static void btrfs_submit_direct(const struct iomap_iter *iter,
 	int ret;
 	blk_status_t status;
 	struct btrfs_io_geometry geom;
-	struct btrfs_dio_data *dio_data = iter->iomap.private;
+	struct btrfs_dio_data *dio_data = iter->private;
 	struct extent_map *em = NULL;
 
-	dip = btrfs_create_dio_private(dio_bio, inode, file_offset);
-	if (!dip) {
-		if (!write) {
-			unlock_extent(&BTRFS_I(inode)->io_tree, file_offset,
-				file_offset + dio_bio->bi_iter.bi_size - 1);
-		}
-		dio_bio->bi_status = BLK_STS_RESOURCE;
-		bio_endio(dio_bio);
-		return;
-	}
+	dip->inode = 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);
 
-	if (!write) {
 		/*
 		 * Load the csums up front to reduce csum tree searches and
 		 * contention when submitting bios.
-		 *
-		 * If we have csums disabled this will do nothing.
 		 */
+		status = BLK_STS_RESOURCE;
+		dip->csums = kcalloc(nr_sectors, fs_info->csum_size, GFP_NOFS);
+		if (!dip)
+			goto out_err;
+
 		status = btrfs_lookup_bio_sums(inode, dio_bio, dip->csums);
 		if (status != BLK_STS_OK)
 			goto out_err;
@@ -8088,19 +8133,28 @@ static void btrfs_submit_direct(const struct iomap_iter *iter,
 out_err_em:
 	free_extent_map(em);
 out_err:
-	dip->dio_bio->bi_status = status;
+	dio_bio->bi_status = status;
 	btrfs_dio_private_put(dip);
 }
 
-const struct iomap_ops btrfs_dio_iomap_ops = {
+static const struct iomap_ops btrfs_dio_iomap_ops = {
 	.iomap_begin            = btrfs_dio_iomap_begin,
 	.iomap_end              = btrfs_dio_iomap_end,
 };
 
-const struct iomap_dio_ops btrfs_dio_ops = {
+static const struct iomap_dio_ops btrfs_dio_ops = {
 	.submit_io		= btrfs_submit_direct,
+	.bio_set		= &btrfs_dio_bioset,
 };
 
+ssize_t btrfs_dio_rw(struct kiocb *iocb, struct iov_iter *iter, size_t done_before)
+{
+	struct btrfs_dio_data data;
+
+	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)
 {
@@ -8113,27 +8167,6 @@ static int btrfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 	return extent_fiemap(BTRFS_I(inode), fieinfo, start, len);
 }
 
-int btrfs_readpage(struct file *file, struct page *page)
-{
-	struct btrfs_inode *inode = BTRFS_I(page->mapping->host);
-	u64 start = page_offset(page);
-	u64 end = start + PAGE_SIZE - 1;
-	struct btrfs_bio_ctrl bio_ctrl = { 0 };
-	int ret;
-
-	btrfs_lock_and_flush_ordered_range(inode, start, end, NULL);
-
-	ret = btrfs_do_readpage(page, NULL, &bio_ctrl, 0, NULL);
-	if (bio_ctrl.bio) {
-		int ret2;
-
-		ret2 = submit_one_bio(bio_ctrl.bio, 0, bio_ctrl.bio_flags);
-		if (ret == 0)
-			ret = ret2;
-	}
-	return ret;
-}
-
 static int btrfs_writepage(struct page *page, struct writeback_control *wbc)
 {
 	struct inode *inode = page->mapping->host;
@@ -8182,7 +8215,7 @@ static void wait_subpage_spinlock(struct page *page)
 	struct btrfs_fs_info *fs_info = btrfs_sb(page->mapping->host->i_sb);
 	struct btrfs_subpage *subpage;
 
-	if (fs_info->sectorsize == PAGE_SIZE)
+	if (!btrfs_is_subpage(fs_info, page))
 		return;
 
 	ASSERT(PagePrivate(page) && page->private);
@@ -8764,46 +8797,23 @@ out:
 	return ret;
 }
 
-/*
- * create a new subvolume directory/inode (helper for the ioctl).
- */
-int btrfs_create_subvol_root(struct btrfs_trans_handle *trans,
-			     struct btrfs_root *new_root,
-			     struct btrfs_root *parent_root,
-			     struct user_namespace *mnt_userns)
+struct inode *btrfs_new_subvol_inode(struct user_namespace *mnt_userns,
+				     struct inode *dir)
 {
 	struct inode *inode;
-	int err;
-	u64 index = 0;
-	u64 ino;
-
-	err = btrfs_get_free_objectid(new_root, &ino);
-	if (err < 0)
-		return err;
-
-	inode = btrfs_new_inode(trans, new_root, mnt_userns, NULL, "..", 2,
-				ino, ino,
-				S_IFDIR | (~current_umask() & S_IRWXUGO),
-				&index);
-	if (IS_ERR(inode))
-		return PTR_ERR(inode);
-	inode->i_op = &btrfs_dir_inode_operations;
-	inode->i_fop = &btrfs_dir_file_operations;
-
-	set_nlink(inode, 1);
-	btrfs_i_size_write(BTRFS_I(inode), 0);
-	unlock_new_inode(inode);
-
-	err = btrfs_subvol_inherit_props(trans, new_root, parent_root);
-	if (err)
-		btrfs_err(new_root->fs_info,
-			  "error inheriting subvolume %llu properties: %d",
-			  new_root->root_key.objectid, err);
 
-	err = btrfs_update_inode(trans, new_root, BTRFS_I(inode));
-
-	iput(inode);
-	return err;
+	inode = new_inode(dir->i_sb);
+	if (inode) {
+		/*
+		 * 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,
+				 S_IFDIR | (~current_umask() & S_IRWXUGO));
+		inode->i_op = &btrfs_dir_inode_operations;
+		inode->i_fop = &btrfs_dir_file_operations;
+	}
+	return inode;
 }
 
 struct inode *btrfs_alloc_inode(struct super_block *sb)
@@ -8943,7 +8953,7 @@ int btrfs_drop_inode(struct inode *inode)
 
 static void init_once(void *foo)
 {
-	struct btrfs_inode *ei = (struct btrfs_inode *) foo;
+	struct btrfs_inode *ei = foo;
 
 	inode_init_once(&ei->vfs_inode);
 }
@@ -8955,6 +8965,7 @@ void __cold btrfs_destroy_cachep(void)
 	 * destroy cache.
 	 */
 	rcu_barrier();
+	bioset_exit(&btrfs_dio_bioset);
 	kmem_cache_destroy(btrfs_inode_cachep);
 	kmem_cache_destroy(btrfs_trans_handle_cachep);
 	kmem_cache_destroy(btrfs_path_cachep);
@@ -8995,6 +9006,11 @@ int __init btrfs_init_cachep(void)
 	if (!btrfs_free_space_bitmap_cachep)
 		goto fail;
 
+	if (bioset_init(&btrfs_dio_bioset, BIO_POOL_SIZE,
+			offsetof(struct btrfs_dio_private, bio),
+			BIOSET_NEED_BVECS))
+		goto fail;
+
 	return 0;
 fail:
 	btrfs_destroy_cachep();
@@ -9050,6 +9066,7 @@ static int btrfs_rename_exchange(struct inode *old_dir,
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(old_dir->i_sb);
 	struct btrfs_trans_handle *trans;
+	unsigned int trans_num_items;
 	struct btrfs_root *root = BTRFS_I(old_dir)->root;
 	struct btrfs_root *dest = BTRFS_I(new_dir)->root;
 	struct inode *new_inode = new_dentry->d_inode;
@@ -9081,14 +9098,37 @@ static int btrfs_rename_exchange(struct inode *old_dir,
 		down_read(&fs_info->subvol_sem);
 
 	/*
-	 * We want to reserve the absolute worst case amount of items.  So if
-	 * both inodes are subvols and we need to unlink them then that would
-	 * require 4 item modifications, but if they are both normal inodes it
-	 * would require 5 item modifications, so we'll assume their normal
-	 * inodes.  So 5 * 2 is 10, plus 2 for the new links, so 12 total items
-	 * should cover the worst case number of items we'll modify.
+	 * For each inode:
+	 * 1 to remove old dir item
+	 * 1 to remove old dir index
+	 * 1 to add new dir item
+	 * 1 to add new dir index
+	 * 1 to update parent inode
+	 *
+	 * If the parents are the same, we only need to account for one
 	 */
-	trans = btrfs_start_transaction(root, 12);
+	trans_num_items = (old_dir == new_dir ? 9 : 10);
+	if (old_ino == BTRFS_FIRST_FREE_OBJECTID) {
+		/*
+		 * 1 to remove old root ref
+		 * 1 to remove old root backref
+		 * 1 to add new root ref
+		 * 1 to add new root backref
+		 */
+		trans_num_items += 4;
+	} else {
+		/*
+		 * 1 to update inode item
+		 * 1 to remove old inode ref
+		 * 1 to add new inode ref
+		 */
+		trans_num_items += 3;
+	}
+	if (new_ino == BTRFS_FIRST_FREE_OBJECTID)
+		trans_num_items += 4;
+	else
+		trans_num_items += 3;
+	trans = btrfs_start_transaction(root, trans_num_items);
 	if (IS_ERR(trans)) {
 		ret = PTR_ERR(trans);
 		goto out_notrans;
@@ -9255,56 +9295,19 @@ out_notrans:
 	return ret;
 }
 
-static int btrfs_whiteout_for_rename(struct btrfs_trans_handle *trans,
-				     struct btrfs_root *root,
-				     struct user_namespace *mnt_userns,
-				     struct inode *dir,
-				     struct dentry *dentry)
+static struct inode *new_whiteout_inode(struct user_namespace *mnt_userns,
+					struct inode *dir)
 {
-	int ret;
 	struct inode *inode;
-	u64 objectid;
-	u64 index;
-
-	ret = btrfs_get_free_objectid(root, &objectid);
-	if (ret)
-		return ret;
 
-	inode = btrfs_new_inode(trans, root, mnt_userns, dir,
-				dentry->d_name.name,
-				dentry->d_name.len,
-				btrfs_ino(BTRFS_I(dir)),
-				objectid,
-				S_IFCHR | WHITEOUT_MODE,
-				&index);
-
-	if (IS_ERR(inode)) {
-		ret = PTR_ERR(inode);
-		return ret;
+	inode = new_inode(dir->i_sb);
+	if (inode) {
+		inode_init_owner(mnt_userns, inode, dir,
+				 S_IFCHR | WHITEOUT_MODE);
+		inode->i_op = &btrfs_special_inode_operations;
+		init_special_inode(inode, inode->i_mode, WHITEOUT_DEV);
 	}
-
-	inode->i_op = &btrfs_special_inode_operations;
-	init_special_inode(inode, inode->i_mode,
-		WHITEOUT_DEV);
-
-	ret = btrfs_init_inode_security(trans, inode, dir,
-				&dentry->d_name);
-	if (ret)
-		goto out;
-
-	ret = btrfs_add_nondir(trans, BTRFS_I(dir), dentry,
-				BTRFS_I(inode), 0, index);
-	if (ret)
-		goto out;
-
-	ret = btrfs_update_inode(trans, root, BTRFS_I(inode));
-out:
-	unlock_new_inode(inode);
-	if (ret)
-		inode_dec_link_count(inode);
-	iput(inode);
-
-	return ret;
+	return inode;
 }
 
 static int btrfs_rename(struct user_namespace *mnt_userns,
@@ -9313,6 +9316,10 @@ static int btrfs_rename(struct user_namespace *mnt_userns,
 			unsigned int flags)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(old_dir->i_sb);
+	struct btrfs_new_inode_args whiteout_args = {
+		.dir = old_dir,
+		.dentry = old_dentry,
+	};
 	struct btrfs_trans_handle *trans;
 	unsigned int trans_num_items;
 	struct btrfs_root *root = BTRFS_I(old_dir)->root;
@@ -9367,23 +9374,56 @@ static int btrfs_rename(struct user_namespace *mnt_userns,
 	if (new_inode && S_ISREG(old_inode->i_mode) && new_inode->i_size)
 		filemap_flush(old_inode->i_mapping);
 
-	/* close the racy window with snapshot create/destroy ioctl */
-	if (old_ino == BTRFS_FIRST_FREE_OBJECTID)
+	if (flags & RENAME_WHITEOUT) {
+		whiteout_args.inode = new_whiteout_inode(mnt_userns, old_dir);
+		if (!whiteout_args.inode)
+			return -ENOMEM;
+		ret = btrfs_new_inode_prepare(&whiteout_args, &trans_num_items);
+		if (ret)
+			goto out_whiteout_inode;
+	} else {
+		/* 1 to update the old parent inode. */
+		trans_num_items = 1;
+	}
+
+	if (old_ino == BTRFS_FIRST_FREE_OBJECTID) {
+		/* Close the race window with snapshot create/destroy ioctl */
 		down_read(&fs_info->subvol_sem);
+		/*
+		 * 1 to remove old root ref
+		 * 1 to remove old root backref
+		 * 1 to add new root ref
+		 * 1 to add new root backref
+		 */
+		trans_num_items += 4;
+	} else {
+		/*
+		 * 1 to update inode
+		 * 1 to remove old inode ref
+		 * 1 to add new inode ref
+		 */
+		trans_num_items += 3;
+	}
 	/*
-	 * We want to reserve the absolute worst case amount of items.  So if
-	 * both inodes are subvols and we need to unlink them then that would
-	 * require 4 item modifications, but if they are both normal inodes it
-	 * would require 5 item modifications, so we'll assume they are normal
-	 * inodes.  So 5 * 2 is 10, plus 1 for the new link, so 11 total items
-	 * should cover the worst case number of items we'll modify.
-	 * If our rename has the whiteout flag, we need more 5 units for the
-	 * new inode (1 inode item, 1 inode ref, 2 dir items and 1 xattr item
-	 * when selinux is enabled).
+	 * 1 to remove old dir item
+	 * 1 to remove old dir index
+	 * 1 to add new dir item
+	 * 1 to add new dir index
 	 */
-	trans_num_items = 11;
-	if (flags & RENAME_WHITEOUT)
+	trans_num_items += 4;
+	/* 1 to update new parent inode if it's not the same as the old parent */
+	if (new_dir != old_dir)
+		trans_num_items++;
+	if (new_inode) {
+		/*
+		 * 1 to update inode
+		 * 1 to remove inode ref
+		 * 1 to remove dir item
+		 * 1 to remove dir index
+		 * 1 to possibly add orphan item
+		 */
 		trans_num_items += 5;
+	}
 	trans = btrfs_start_transaction(root, trans_num_items);
 	if (IS_ERR(trans)) {
 		ret = PTR_ERR(trans);
@@ -9479,12 +9519,14 @@ static int btrfs_rename(struct user_namespace *mnt_userns,
 				   rename_ctx.index, new_dentry->d_parent);
 
 	if (flags & RENAME_WHITEOUT) {
-		ret = btrfs_whiteout_for_rename(trans, root, mnt_userns,
-						old_dir, old_dentry);
-
+		ret = btrfs_create_new_inode(trans, &whiteout_args);
 		if (ret) {
 			btrfs_abort_transaction(trans, ret);
 			goto out_fail;
+		} else {
+			unlock_new_inode(whiteout_args.inode);
+			iput(whiteout_args.inode);
+			whiteout_args.inode = NULL;
 		}
 	}
 out_fail:
@@ -9493,7 +9535,11 @@ out_fail:
 out_notrans:
 	if (old_ino == BTRFS_FIRST_FREE_OBJECTID)
 		up_read(&fs_info->subvol_sem);
-
+	if (flags & RENAME_WHITEOUT)
+		btrfs_new_inode_args_destroy(&whiteout_args);
+out_whiteout_inode:
+	if (flags & RENAME_WHITEOUT)
+		iput(whiteout_args.inode);
 	return ret;
 }
 
@@ -9712,10 +9758,13 @@ static int btrfs_symlink(struct user_namespace *mnt_userns, struct inode *dir,
 	struct btrfs_root *root = BTRFS_I(dir)->root;
 	struct btrfs_path *path;
 	struct btrfs_key key;
-	struct inode *inode = NULL;
+	struct inode *inode;
+	struct btrfs_new_inode_args new_inode_args = {
+		.dir = dir,
+		.dentry = dentry,
+	};
+	unsigned int trans_num_items;
 	int err;
-	u64 objectid;
-	u64 index = 0;
 	int name_len;
 	int datasize;
 	unsigned long ptr;
@@ -9726,49 +9775,40 @@ static int btrfs_symlink(struct user_namespace *mnt_userns, struct inode *dir,
 	if (name_len > BTRFS_MAX_INLINE_DATA_SIZE(fs_info))
 		return -ENAMETOOLONG;
 
-	/*
-	 * 2 items for inode item and ref
-	 * 2 items for dir items
-	 * 1 item for updating parent inode item
-	 * 1 item for the inline extent item
-	 * 1 item for xattr if selinux is on
-	 */
-	trans = btrfs_start_transaction(root, 7);
-	if (IS_ERR(trans))
-		return PTR_ERR(trans);
+	inode = new_inode(dir->i_sb);
+	if (!inode)
+		return -ENOMEM;
+	inode_init_owner(mnt_userns, inode, dir, S_IFLNK | S_IRWXUGO);
+	inode->i_op = &btrfs_symlink_inode_operations;
+	inode_nohighmem(inode);
+	inode->i_mapping->a_ops = &btrfs_aops;
+	btrfs_i_size_write(BTRFS_I(inode), name_len);
+	inode_set_bytes(inode, name_len);
 
-	err = btrfs_get_free_objectid(root, &objectid);
+	new_inode_args.inode = inode;
+	err = btrfs_new_inode_prepare(&new_inode_args, &trans_num_items);
 	if (err)
-		goto out_unlock;
+		goto out_inode;
+	/* 1 additional item for the inline extent */
+	trans_num_items++;
 
-	inode = btrfs_new_inode(trans, root, mnt_userns, dir,
-				dentry->d_name.name, dentry->d_name.len,
-				btrfs_ino(BTRFS_I(dir)), objectid,
-				S_IFLNK | S_IRWXUGO, &index);
-	if (IS_ERR(inode)) {
-		err = PTR_ERR(inode);
-		inode = NULL;
-		goto out_unlock;
+	trans = btrfs_start_transaction(root, trans_num_items);
+	if (IS_ERR(trans)) {
+		err = PTR_ERR(trans);
+		goto out_new_inode_args;
 	}
 
-	/*
-	* If the active LSM wants to access the inode during
-	* d_instantiate it needs these. Smack checks to see
-	* if the filesystem supports xattrs by looking at the
-	* ops vector.
-	*/
-	inode->i_fop = &btrfs_file_operations;
-	inode->i_op = &btrfs_file_inode_operations;
-	inode->i_mapping->a_ops = &btrfs_aops;
-
-	err = btrfs_init_inode_security(trans, inode, dir, &dentry->d_name);
+	err = btrfs_create_new_inode(trans, &new_inode_args);
 	if (err)
-		goto out_unlock;
+		goto out;
 
 	path = btrfs_alloc_path();
 	if (!path) {
 		err = -ENOMEM;
-		goto out_unlock;
+		btrfs_abort_transaction(trans, err);
+		discard_new_inode(inode);
+		inode = NULL;
+		goto out;
 	}
 	key.objectid = btrfs_ino(BTRFS_I(inode));
 	key.offset = 0;
@@ -9777,8 +9817,11 @@ static int btrfs_symlink(struct user_namespace *mnt_userns, struct inode *dir,
 	err = btrfs_insert_empty_item(trans, root, path, &key,
 				      datasize);
 	if (err) {
+		btrfs_abort_transaction(trans, err);
 		btrfs_free_path(path);
-		goto out_unlock;
+		discard_new_inode(inode);
+		inode = NULL;
+		goto out;
 	}
 	leaf = path->nodes[0];
 	ei = btrfs_item_ptr(leaf, path->slots[0],
@@ -9796,31 +9839,16 @@ static int btrfs_symlink(struct user_namespace *mnt_userns, struct inode *dir,
 	btrfs_mark_buffer_dirty(leaf);
 	btrfs_free_path(path);
 
-	inode->i_op = &btrfs_symlink_inode_operations;
-	inode_nohighmem(inode);
-	inode_set_bytes(inode, name_len);
-	btrfs_i_size_write(BTRFS_I(inode), name_len);
-	err = btrfs_update_inode(trans, root, BTRFS_I(inode));
-	/*
-	 * Last step, add directory indexes for our symlink inode. This is the
-	 * last step to avoid extra cleanup of these indexes if an error happens
-	 * elsewhere above.
-	 */
-	if (!err)
-		err = btrfs_add_nondir(trans, BTRFS_I(dir), dentry,
-				BTRFS_I(inode), 0, index);
-	if (err)
-		goto out_unlock;
-
 	d_instantiate_new(dentry, inode);
-
-out_unlock:
+	err = 0;
+out:
 	btrfs_end_transaction(trans);
-	if (err && inode) {
-		inode_dec_link_count(inode);
-		discard_new_inode(inode);
-	}
 	btrfs_btree_balance_dirty(fs_info);
+out_new_inode_args:
+	btrfs_new_inode_args_destroy(&new_inode_args);
+out_inode:
+	if (err)
+		iput(inode);
 	return err;
 }
 
@@ -10071,62 +10099,58 @@ static int btrfs_tmpfile(struct user_namespace *mnt_userns, struct inode *dir,
 	struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb);
 	struct btrfs_trans_handle *trans;
 	struct btrfs_root *root = BTRFS_I(dir)->root;
-	struct inode *inode = NULL;
-	u64 objectid;
-	u64 index;
-	int ret = 0;
-
-	/*
-	 * 5 units required for adding orphan entry
-	 */
-	trans = btrfs_start_transaction(root, 5);
-	if (IS_ERR(trans))
-		return PTR_ERR(trans);
-
-	ret = btrfs_get_free_objectid(root, &objectid);
-	if (ret)
-		goto out;
-
-	inode = btrfs_new_inode(trans, root, mnt_userns, dir, NULL, 0,
-			btrfs_ino(BTRFS_I(dir)), objectid, mode, &index);
-	if (IS_ERR(inode)) {
-		ret = PTR_ERR(inode);
-		inode = NULL;
-		goto out;
-	}
+	struct inode *inode;
+	struct btrfs_new_inode_args new_inode_args = {
+		.dir = dir,
+		.dentry = dentry,
+		.orphan = true,
+	};
+	unsigned int trans_num_items;
+	int ret;
 
+	inode = new_inode(dir->i_sb);
+	if (!inode)
+		return -ENOMEM;
+	inode_init_owner(mnt_userns, inode, dir, mode);
 	inode->i_fop = &btrfs_file_operations;
 	inode->i_op = &btrfs_file_inode_operations;
-
 	inode->i_mapping->a_ops = &btrfs_aops;
 
-	ret = btrfs_init_inode_security(trans, inode, dir, NULL);
+	new_inode_args.inode = inode;
+	ret = btrfs_new_inode_prepare(&new_inode_args, &trans_num_items);
 	if (ret)
-		goto out;
+		goto out_inode;
 
-	ret = btrfs_update_inode(trans, root, BTRFS_I(inode));
-	if (ret)
-		goto out;
-	ret = btrfs_orphan_add(trans, BTRFS_I(inode));
-	if (ret)
-		goto out;
+	trans = btrfs_start_transaction(root, trans_num_items);
+	if (IS_ERR(trans)) {
+		ret = PTR_ERR(trans);
+		goto out_new_inode_args;
+	}
+
+	ret = btrfs_create_new_inode(trans, &new_inode_args);
 
 	/*
-	 * We set number of links to 0 in btrfs_new_inode(), and here we set
-	 * it to 1 because d_tmpfile() will issue a warning if the count is 0,
-	 * through:
+	 * We set number of links to 0 in btrfs_create_new_inode(), and here we
+	 * set it to 1 because d_tmpfile() will issue a warning if the count is
+	 * 0, through:
 	 *
 	 *    d_tmpfile() -> inode_dec_link_count() -> drop_nlink()
 	 */
 	set_nlink(inode, 1);
-	d_tmpfile(dentry, inode);
-	unlock_new_inode(inode);
-	mark_inode_dirty(inode);
-out:
+
+	if (!ret) {
+		d_tmpfile(dentry, inode);
+		unlock_new_inode(inode);
+		mark_inode_dirty(inode);
+	}
+
 	btrfs_end_transaction(trans);
-	if (ret && inode)
-		discard_new_inode(inode);
 	btrfs_btree_balance_dirty(fs_info);
+out_new_inode_args:
+	btrfs_new_inode_args_destroy(&new_inode_args);
+out_inode:
+	if (ret)
+		iput(inode);
 	return ret;
 }
 
@@ -10458,13 +10482,11 @@ static ssize_t btrfs_encoded_read_regular(struct kiocb *iocb,
 	pages = kcalloc(nr_pages, sizeof(struct page *), GFP_NOFS);
 	if (!pages)
 		return -ENOMEM;
-	for (i = 0; i < nr_pages; i++) {
-		pages[i] = alloc_page(GFP_NOFS);
-		if (!pages[i]) {
-			ret = -ENOMEM;
-			goto out;
+	ret = btrfs_alloc_page_array(nr_pages, pages);
+	if (ret) {
+		ret = -ENOMEM;
+		goto out;
 		}
-	}
 
 	ret = btrfs_encoded_read_regular_fill_pages(inode, start, disk_bytenr,
 						    disk_io_size, pages);
@@ -10800,7 +10822,8 @@ ssize_t btrfs_do_encoded_write(struct kiocb *iocb, struct iov_iter *from,
 	ret = btrfs_qgroup_reserve_data(inode, &data_reserved, start, num_bytes);
 	if (ret)
 		goto out_free_data_space;
-	ret = btrfs_delalloc_reserve_metadata(inode, num_bytes, disk_num_bytes);
+	ret = btrfs_delalloc_reserve_metadata(inode, num_bytes, disk_num_bytes,
+					      false);
 	if (ret)
 		goto out_qgroup_free_data;
 
@@ -11309,6 +11332,41 @@ void btrfs_update_inode_bytes(struct btrfs_inode *inode,
 	spin_unlock(&inode->lock);
 }
 
+/**
+ * Verify that there are no ordered extents for a given file range.
+ *
+ * @inode:   The target inode.
+ * @start:   Start offset of the file range, should be sector size aligned.
+ * @end:     End offset (inclusive) of the file range, its value +1 should be
+ *           sector size aligned.
+ *
+ * This should typically be used for cases where we locked an inode's VFS lock in
+ * exclusive mode, we have also locked the inode's i_mmap_lock in exclusive mode,
+ * we have flushed all delalloc in the range, we have waited for all ordered
+ * extents in the range to complete and finally we have locked the file range in
+ * the inode's io_tree.
+ */
+void btrfs_assert_inode_range_clean(struct btrfs_inode *inode, u64 start, u64 end)
+{
+	struct btrfs_root *root = inode->root;
+	struct btrfs_ordered_extent *ordered;
+
+	if (!IS_ENABLED(CONFIG_BTRFS_ASSERT))
+		return;
+
+	ordered = btrfs_lookup_first_ordered_range(inode, start, end + 1 - start);
+	if (ordered) {
+		btrfs_err(root->fs_info,
+"found unexpected ordered extent in file range [%llu, %llu] for inode %llu root %llu (ordered range [%llu, %llu])",
+			  start, end, btrfs_ino(inode), root->root_key.objectid,
+			  ordered->file_offset,
+			  ordered->file_offset + ordered->num_bytes - 1);
+		btrfs_put_ordered_extent(ordered);
+	}
+
+	ASSERT(ordered == NULL);
+}
+
 static const struct inode_operations btrfs_dir_inode_operations = {
 	.getattr	= btrfs_getattr,
 	.lookup		= btrfs_lookup,