Merge tag 'for-6.10-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs updates from David Sterba:
 "This update brings a few minor performance improvements, otherwise
  there's a lot of refactoring, cleanups and other sort of not user
  visible changes.

  Performance improvements:

   - inline b-tree locking functions, improvement in metadata-heavy
     changes

   - relax locking on a range that's being reflinked, allows read
     operations to run in parallel

   - speed up NOCOW write checks (throughput +9% on a sample test)

   - extent locking ranges have been reduced in several places, namely
     around delayed ref processing

  Core:

   - more page to folio conversions:
      - relocation
      - send
      - compression
      - inline extent handling
      - super block write and wait

   - extent_map structure optimizations:
      - reduced structure size
      - code simplifications
      - add shrinker for allocated objects, the numbers can go high and
        could exhaust memory on smaller systems (reported) as they may
        not get an opportunity to be freed fast enough

   - extent locking optimizations:
      - reduce locking ranges where it does not seem to be necessary and
        are safe due to other means of synchronization
      - potential improvements due to lower contention,
        allocation/freeing and state management operations of extent
        state tracking structures

   - delayed ref cleanups and simplifications

   - updated trace points

   - improved error handling, warnings and assertions

   - cleanups and refactoring, unification of error handling paths"

* tag 'for-6.10-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (122 commits)
  btrfs: qgroup: fix initialization of auto inherit array
  btrfs: count super block write errors in device instead of tracking folio error state
  btrfs: use the folio iterator in btrfs_end_super_write()
  btrfs: convert super block writes to folio in write_dev_supers()
  btrfs: convert super block writes to folio in wait_dev_supers()
  bio: Export bio_add_folio_nofail to modules
  btrfs: remove duplicate included header from fs.h
  btrfs: add a cached state to extent_clear_unlock_delalloc
  btrfs: push extent lock down in submit_one_async_extent
  btrfs: push lock_extent down in cow_file_range()
  btrfs: move can_cow_file_range_inline() outside of the extent lock
  btrfs: push lock_extent into cow_file_range_inline
  btrfs: push extent lock into cow_file_range
  btrfs: push extent lock into run_delalloc_cow
  btrfs: remove unlock_extent from run_delalloc_compressed
  btrfs: push extent lock down in run_delalloc_nocow
  btrfs: adjust while loop condition in run_delalloc_nocow
  btrfs: push extent lock into run_delalloc_nocow
  btrfs: push the extent lock into btrfs_run_delalloc_range
  btrfs: lock extent when doing inline extent in compression
  ...

50 files changed, 2517 insertions, 2309 deletions

diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index 58110c968667..a2de5c05f97c 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -261,7 +261,7 @@ static void update_share_count(struct share_check *sc, int oldcount,
 	else if (oldcount < 1 && newcount > 0)
 		sc->share_count++;
 
-	if (newref->root_id == sc->root->root_key.objectid &&
+	if (newref->root_id == btrfs_root_id(sc->root) &&
 	    newref->wanted_disk_byte == sc->data_bytenr &&
 	    newref->key_for_search.objectid == sc->inum)
 		sc->self_ref_count += newref->count;
@@ -769,7 +769,7 @@ static int resolve_indirect_refs(struct btrfs_backref_walk_ctx *ctx,
 			continue;
 		}
 
-		if (sc && ref->root_id != sc->root->root_key.objectid) {
+		if (sc && ref->root_id != btrfs_root_id(sc->root)) {
 			free_pref(ref);
 			ret = BACKREF_FOUND_SHARED;
 			goto out;
@@ -919,40 +919,38 @@ static int add_delayed_refs(const struct btrfs_fs_info *fs_info,
 		switch (node->type) {
 		case BTRFS_TREE_BLOCK_REF_KEY: {
 			/* NORMAL INDIRECT METADATA backref */
-			struct btrfs_delayed_tree_ref *ref;
 			struct btrfs_key *key_ptr = NULL;
+			/* The owner of a tree block ref is the level. */
+			int level = btrfs_delayed_ref_owner(node);
 
 			if (head->extent_op && head->extent_op->update_key) {
 				btrfs_disk_key_to_cpu(&key, &head->extent_op->key);
 				key_ptr = &key;
 			}
 
-			ref = btrfs_delayed_node_to_tree_ref(node);
-			ret = add_indirect_ref(fs_info, preftrees, ref->root,
-					       key_ptr, ref->level + 1,
-					       node->bytenr, count, sc,
-					       GFP_ATOMIC);
+			ret = add_indirect_ref(fs_info, preftrees, node->ref_root,
+					       key_ptr, level + 1, node->bytenr,
+					       count, sc, GFP_ATOMIC);
 			break;
 		}
 		case BTRFS_SHARED_BLOCK_REF_KEY: {
-			/* SHARED DIRECT METADATA backref */
-			struct btrfs_delayed_tree_ref *ref;
-
-			ref = btrfs_delayed_node_to_tree_ref(node);
+			/*
+			 * SHARED DIRECT METADATA backref
+			 *
+			 * The owner of a tree block ref is the level.
+			 */
+			int level = btrfs_delayed_ref_owner(node);
 
-			ret = add_direct_ref(fs_info, preftrees, ref->level + 1,
-					     ref->parent, node->bytenr, count,
+			ret = add_direct_ref(fs_info, preftrees, level + 1,
+					     node->parent, node->bytenr, count,
 					     sc, GFP_ATOMIC);
 			break;
 		}
 		case BTRFS_EXTENT_DATA_REF_KEY: {
 			/* NORMAL INDIRECT DATA backref */
-			struct btrfs_delayed_data_ref *ref;
-			ref = btrfs_delayed_node_to_data_ref(node);
-
-			key.objectid = ref->objectid;
+			key.objectid = btrfs_delayed_ref_owner(node);
 			key.type = BTRFS_EXTENT_DATA_KEY;
-			key.offset = ref->offset;
+			key.offset = btrfs_delayed_ref_offset(node);
 
 			/*
 			 * If we have a share check context and a reference for
@@ -972,18 +970,14 @@ static int add_delayed_refs(const struct btrfs_fs_info *fs_info,
 			if (sc && count < 0)
 				sc->have_delayed_delete_refs = true;
 
-			ret = add_indirect_ref(fs_info, preftrees, ref->root,
+			ret = add_indirect_ref(fs_info, preftrees, node->ref_root,
 					       &key, 0, node->bytenr, count, sc,
 					       GFP_ATOMIC);
 			break;
 		}
 		case BTRFS_SHARED_DATA_REF_KEY: {
 			/* SHARED DIRECT FULL backref */
-			struct btrfs_delayed_data_ref *ref;
-
-			ref = btrfs_delayed_node_to_data_ref(node);
-
-			ret = add_direct_ref(fs_info, preftrees, 0, ref->parent,
+			ret = add_direct_ref(fs_info, preftrees, 0, node->parent,
 					     node->bytenr, count, sc,
 					     GFP_ATOMIC);
 			break;
@@ -2629,7 +2623,7 @@ static int iterate_inode_refs(u64 inum, struct inode_fs_paths *ipath)
 			btrfs_debug(fs_root->fs_info,
 				"following ref at offset %u for inode %llu in tree %llu",
 				cur, found_key.objectid,
-				fs_root->root_key.objectid);
+				btrfs_root_id(fs_root));
 			ret = inode_to_path(parent, name_len,
 				      (unsigned long)(iref + 1), eb, ipath);
 			if (ret)
@@ -3361,7 +3355,7 @@ static int handle_indirect_tree_backref(struct btrfs_trans_handle *trans,
 	if (btrfs_node_blockptr(eb, path->slots[level]) != cur->bytenr) {
 		btrfs_err(fs_info,
 "couldn't find block (%llu) (level %d) in tree (%llu) with key (%llu %u %llu)",
-			  cur->bytenr, level - 1, root->root_key.objectid,
+			  cur->bytenr, level - 1, btrfs_root_id(root),
 			  tree_key->objectid, tree_key->type, tree_key->offset);
 		btrfs_put_root(root);
 		ret = -ENOENT;
diff --git a/fs/btrfs/block-rsv.c b/fs/btrfs/block-rsv.c
index 95c174f9fd4f..b299b82d676e 100644
--- a/fs/btrfs/block-rsv.c
+++ b/fs/btrfs/block-rsv.c
@@ -341,9 +341,9 @@ void btrfs_update_global_block_rsv(struct btrfs_fs_info *fs_info)
 	read_lock(&fs_info->global_root_lock);
 	rbtree_postorder_for_each_entry_safe(root, tmp, &fs_info->global_root_tree,
 					     rb_node) {
-		if (root->root_key.objectid == BTRFS_EXTENT_TREE_OBJECTID ||
-		    root->root_key.objectid == BTRFS_CSUM_TREE_OBJECTID ||
-		    root->root_key.objectid == BTRFS_FREE_SPACE_TREE_OBJECTID) {
+		if (btrfs_root_id(root) == BTRFS_EXTENT_TREE_OBJECTID ||
+		    btrfs_root_id(root) == BTRFS_CSUM_TREE_OBJECTID ||
+		    btrfs_root_id(root) == BTRFS_FREE_SPACE_TREE_OBJECTID) {
 			num_bytes += btrfs_root_used(&root->root_item);
 			min_items++;
 		}
@@ -406,7 +406,7 @@ void btrfs_init_root_block_rsv(struct btrfs_root *root)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
 
-	switch (root->root_key.objectid) {
+	switch (btrfs_root_id(root)) {
 	case BTRFS_CSUM_TREE_OBJECTID:
 	case BTRFS_EXTENT_TREE_OBJECTID:
 	case BTRFS_FREE_SPACE_TREE_OBJECTID:
@@ -468,8 +468,7 @@ static struct btrfs_block_rsv *get_block_rsv(
 
 	if (test_bit(BTRFS_ROOT_SHAREABLE, &root->state) ||
 	    (root == fs_info->uuid_root) ||
-	    (trans->adding_csums &&
-	     root->root_key.objectid == BTRFS_CSUM_TREE_OBJECTID))
+	    (trans->adding_csums && btrfs_root_id(root) == BTRFS_CSUM_TREE_OBJECTID))
 		block_rsv = trans->block_rsv;
 
 	if (!block_rsv)
diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 100020ca4658..91c994b569f3 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -381,9 +381,11 @@ static inline void btrfs_set_inode_last_sub_trans(struct btrfs_inode *inode)
 }
 
 /*
- * Should be called while holding the inode's VFS lock in exclusive mode or in a
- * context where no one else can access the inode concurrently (during inode
- * creation or when loading an inode from disk).
+ * Should be called while holding the inode's VFS lock in exclusive mode, or
+ * while holding the inode's mmap lock (struct btrfs_inode::i_mmap_lock) in
+ * either shared or exclusive mode, or in a context where no one else can access
+ * the inode concurrently (during inode creation or when loading an inode from
+ * disk).
  */
 static inline void btrfs_set_inode_full_sync(struct btrfs_inode *inode)
 {
@@ -496,7 +498,6 @@ void btrfs_merge_delalloc_extent(struct btrfs_inode *inode, struct extent_state
 void btrfs_split_delalloc_extent(struct btrfs_inode *inode,
 				 struct extent_state *orig, u64 split);
 void btrfs_set_range_writeback(struct btrfs_inode *inode, u64 start, u64 end);
-vm_fault_t btrfs_page_mkwrite(struct vm_fault *vmf);
 void btrfs_evict_inode(struct inode *inode);
 struct inode *btrfs_alloc_inode(struct super_block *sb);
 void btrfs_destroy_inode(struct inode *inode);
@@ -544,6 +545,7 @@ ssize_t btrfs_dio_read(struct kiocb *iocb, struct iov_iter *iter,
 		       size_t done_before);
 struct iomap_dio *btrfs_dio_write(struct kiocb *iocb, struct iov_iter *iter,
 				  size_t done_before);
+struct btrfs_inode *btrfs_find_first_inode(struct btrfs_root *root, u64 min_ino);
 
 extern const struct dentry_operations btrfs_dentry_operations;
 
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index b2b94009959d..6441e47d8a5e 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -90,20 +90,20 @@ bool btrfs_compress_is_valid_type(const char *str, size_t len)
 }
 
 static int compression_compress_pages(int type, struct list_head *ws,
-               struct address_space *mapping, u64 start, struct page **pages,
-               unsigned long *out_pages, unsigned long *total_in,
-               unsigned long *total_out)
+				      struct address_space *mapping, u64 start,
+				      struct folio **folios, unsigned long *out_folios,
+				      unsigned long *total_in, unsigned long *total_out)
 {
 	switch (type) {
 	case BTRFS_COMPRESS_ZLIB:
-		return zlib_compress_pages(ws, mapping, start, pages,
-				out_pages, total_in, total_out);
+		return zlib_compress_folios(ws, mapping, start, folios,
+					    out_folios, total_in, total_out);
 	case BTRFS_COMPRESS_LZO:
-		return lzo_compress_pages(ws, mapping, start, pages,
-				out_pages, total_in, total_out);
+		return lzo_compress_folios(ws, mapping, start, folios,
+					   out_folios, total_in, total_out);
 	case BTRFS_COMPRESS_ZSTD:
-		return zstd_compress_pages(ws, mapping, start, pages,
-				out_pages, total_in, total_out);
+		return zstd_compress_folios(ws, mapping, start, folios,
+					    out_folios, total_in, total_out);
 	case BTRFS_COMPRESS_NONE:
 	default:
 		/*
@@ -115,7 +115,7 @@ static int compression_compress_pages(int type, struct list_head *ws,
 		 * Not a big deal, just need to inform caller that we
 		 * haven't allocated any pages yet.
 		 */
-		*out_pages = 0;
+		*out_folios = 0;
 		return -E2BIG;
 	}
 }
@@ -158,11 +158,11 @@ static int compression_decompress(int type, struct list_head *ws,
 	}
 }
 
-static void btrfs_free_compressed_pages(struct compressed_bio *cb)
+static void btrfs_free_compressed_folios(struct compressed_bio *cb)
 {
-	for (unsigned int i = 0; i < cb->nr_pages; i++)
-		btrfs_free_compr_page(cb->compressed_pages[i]);
-	kfree(cb->compressed_pages);
+	for (unsigned int i = 0; i < cb->nr_folios; i++)
+		btrfs_free_compr_folio(cb->compressed_folios[i]);
+	kfree(cb->compressed_folios);
 }
 
 static int btrfs_decompress_bio(struct compressed_bio *cb);
@@ -223,25 +223,25 @@ static unsigned long btrfs_compr_pool_scan(struct shrinker *sh, struct shrink_co
 /*
  * Common wrappers for page allocation from compression wrappers
  */
-struct page *btrfs_alloc_compr_page(void)
+struct folio *btrfs_alloc_compr_folio(void)
 {
-	struct page *page = NULL;
+	struct folio *folio = NULL;
 
 	spin_lock(&compr_pool.lock);
 	if (compr_pool.count > 0) {
-		page = list_first_entry(&compr_pool.list, struct page, lru);
-		list_del_init(&page->lru);
+		folio = list_first_entry(&compr_pool.list, struct folio, lru);
+		list_del_init(&folio->lru);
 		compr_pool.count--;
 	}
 	spin_unlock(&compr_pool.lock);
 
-	if (page)
-		return page;
+	if (folio)
+		return folio;
 
-	return alloc_page(GFP_NOFS);
+	return folio_alloc(GFP_NOFS, 0);
 }
 
-void btrfs_free_compr_page(struct page *page)
+void btrfs_free_compr_folio(struct folio *folio)
 {
 	bool do_free = false;
 
@@ -249,7 +249,7 @@ void btrfs_free_compr_page(struct page *page)
 	if (compr_pool.count > compr_pool.thresh) {
 		do_free = true;
 	} else {
-		list_add(&page->lru, &compr_pool.list);
+		list_add(&folio->lru, &compr_pool.list);
 		compr_pool.count++;
 	}
 	spin_unlock(&compr_pool.lock);
@@ -257,8 +257,8 @@ void btrfs_free_compr_page(struct page *page)
 	if (!do_free)
 		return;
 
-	ASSERT(page_ref_count(page) == 1);
-	put_page(page);
+	ASSERT(folio_ref_count(folio) == 1);
+	folio_put(folio);
 }
 
 static void end_bbio_comprssed_read(struct btrfs_bio *bbio)
@@ -269,7 +269,7 @@ static void end_bbio_comprssed_read(struct btrfs_bio *bbio)
 	if (!status)
 		status = errno_to_blk_status(btrfs_decompress_bio(cb));
 
-	btrfs_free_compressed_pages(cb);
+	btrfs_free_compressed_folios(cb);
 	btrfs_bio_end_io(cb->orig_bbio, status);
 	bio_put(&bbio->bio);
 }
@@ -323,7 +323,7 @@ static void btrfs_finish_compressed_write_work(struct work_struct *work)
 		end_compressed_writeback(cb);
 	/* Note, our inode could be gone now */
 
-	btrfs_free_compressed_pages(cb);
+	btrfs_free_compressed_folios(cb);
 	bio_put(&cb->bbio.bio);
 }
 
@@ -342,17 +342,19 @@ static void end_bbio_comprssed_write(struct btrfs_bio *bbio)
 	queue_work(fs_info->compressed_write_workers, &cb->write_end_work);
 }
 
-static void btrfs_add_compressed_bio_pages(struct compressed_bio *cb)
+static void btrfs_add_compressed_bio_folios(struct compressed_bio *cb)
 {
 	struct bio *bio = &cb->bbio.bio;
 	u32 offset = 0;
 
 	while (offset < cb->compressed_len) {
+		int ret;
 		u32 len = min_t(u32, cb->compressed_len - offset, PAGE_SIZE);
 
 		/* Maximum compressed extent is smaller than bio size limit. */
-		__bio_add_page(bio, cb->compressed_pages[offset >> PAGE_SHIFT],
-			       len, 0);
+		ret = bio_add_folio(bio, cb->compressed_folios[offset >> PAGE_SHIFT],
+				    len, 0);
+		ASSERT(ret);
 		offset += len;
 	}
 }
@@ -367,8 +369,8 @@ static void btrfs_add_compressed_bio_pages(struct compressed_bio *cb)
  * the end io hooks.
  */
 void btrfs_submit_compressed_write(struct btrfs_ordered_extent *ordered,
-				   struct page **compressed_pages,
-				   unsigned int nr_pages,
+				   struct folio **compressed_folios,
+				   unsigned int nr_folios,
 				   blk_opf_t write_flags,
 				   bool writeback)
 {
@@ -384,14 +386,14 @@ void btrfs_submit_compressed_write(struct btrfs_ordered_extent *ordered,
 				  end_bbio_comprssed_write);
 	cb->start = ordered->file_offset;
 	cb->len = ordered->num_bytes;
-	cb->compressed_pages = compressed_pages;
+	cb->compressed_folios = compressed_folios;
 	cb->compressed_len = ordered->disk_num_bytes;
 	cb->writeback = writeback;
 	INIT_WORK(&cb->write_end_work, btrfs_finish_compressed_write_work);
-	cb->nr_pages = nr_pages;
+	cb->nr_folios = nr_folios;
 	cb->bbio.bio.bi_iter.bi_sector = ordered->disk_bytenr >> SECTOR_SHIFT;
 	cb->bbio.ordered = ordered;
-	btrfs_add_compressed_bio_pages(cb);
+	btrfs_add_compressed_bio_folios(cb);
 
 	btrfs_submit_bio(&cb->bbio, 0);
 }
@@ -599,14 +601,14 @@ void btrfs_submit_compressed_read(struct btrfs_bio *bbio)
 
 	free_extent_map(em);
 
-	cb->nr_pages = DIV_ROUND_UP(compressed_len, PAGE_SIZE);
-	cb->compressed_pages = kcalloc(cb->nr_pages, sizeof(struct page *), GFP_NOFS);
-	if (!cb->compressed_pages) {
+	cb->nr_folios = DIV_ROUND_UP(compressed_len, PAGE_SIZE);
+	cb->compressed_folios = kcalloc(cb->nr_folios, sizeof(struct page *), GFP_NOFS);
+	if (!cb->compressed_folios) {
 		ret = BLK_STS_RESOURCE;
 		goto out_free_bio;
 	}
 
-	ret2 = btrfs_alloc_page_array(cb->nr_pages, cb->compressed_pages, 0);
+	ret2 = btrfs_alloc_folio_array(cb->nr_folios, cb->compressed_folios, 0);
 	if (ret2) {
 		ret = BLK_STS_RESOURCE;
 		goto out_free_compressed_pages;
@@ -618,7 +620,7 @@ void btrfs_submit_compressed_read(struct btrfs_bio *bbio)
 	/* include any pages we added in add_ra-bio_pages */
 	cb->len = bbio->bio.bi_iter.bi_size;
 	cb->bbio.bio.bi_iter.bi_sector = bbio->bio.bi_iter.bi_sector;
-	btrfs_add_compressed_bio_pages(cb);
+	btrfs_add_compressed_bio_folios(cb);
 
 	if (memstall)
 		psi_memstall_leave(&pflags);
@@ -627,7 +629,7 @@ void btrfs_submit_compressed_read(struct btrfs_bio *bbio)
 	return;
 
 out_free_compressed_pages:
-	kfree(cb->compressed_pages);
+	kfree(cb->compressed_folios);
 out_free_bio:
 	bio_put(&cb->bbio.bio);
 out:
@@ -974,6 +976,29 @@ static unsigned int btrfs_compress_set_level(int type, unsigned level)
 	return level;
 }
 
+/* Wrapper around find_get_page(), with extra error message. */
+int btrfs_compress_filemap_get_folio(struct address_space *mapping, u64 start,
+				     struct folio **in_folio_ret)
+{
+	struct folio *in_folio;
+
+	/*
+	 * The compressed write path should have the folio locked already, thus
+	 * we only need to grab one reference.
+	 */
+	in_folio = filemap_get_folio(mapping, start >> PAGE_SHIFT);
+	if (IS_ERR(in_folio)) {
+		struct btrfs_inode *inode = BTRFS_I(mapping->host);
+
+		btrfs_crit(inode->root->fs_info,
+		"failed to get page cache, root %lld ino %llu file offset %llu",
+			   btrfs_root_id(inode->root), btrfs_ino(inode), start);
+		return -ENOENT;
+	}
+	*in_folio_ret = in_folio;
+	return 0;
+}
+
 /*
  * Given an address space and start and length, compress the bytes into @pages
  * that are allocated on demand.
@@ -994,11 +1019,9 @@ static unsigned int btrfs_compress_set_level(int type, unsigned level)
  * @total_out is an in/out parameter, must be set to the input length and will
  * be also used to return the total number of compressed bytes
  */
-int btrfs_compress_pages(unsigned int type_level, struct address_space *mapping,
-			 u64 start, struct page **pages,
-			 unsigned long *out_pages,
-			 unsigned long *total_in,
-			 unsigned long *total_out)
+int btrfs_compress_folios(unsigned int type_level, struct address_space *mapping,
+			 u64 start, struct folio **folios, unsigned long *out_folios,
+			 unsigned long *total_in, unsigned long *total_out)
 {
 	int type = btrfs_compress_type(type_level);
 	int level = btrfs_compress_level(type_level);
@@ -1007,8 +1030,8 @@ int btrfs_compress_pages(unsigned int type_level, struct address_space *mapping,
 
 	level = btrfs_compress_set_level(type, level);
 	workspace = get_workspace(type, level);
-	ret = compression_compress_pages(type, workspace, mapping, start, pages,
-					 out_pages, total_in, total_out);
+	ret = compression_compress_pages(type, workspace, mapping, start, folios,
+					 out_folios, total_in, total_out);
 	put_workspace(type, workspace);
 	return ret;
 }
diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h
index 4691a84ca838..c20c1a1b09d5 100644
--- a/fs/btrfs/compression.h
+++ b/fs/btrfs/compression.h
@@ -41,11 +41,11 @@ static_assert((BTRFS_MAX_COMPRESSED % PAGE_SIZE) == 0);
 #define	BTRFS_ZLIB_DEFAULT_LEVEL		3
 
 struct compressed_bio {
-	/* Number of compressed pages in the array */
-	unsigned int nr_pages;
+	/* Number of compressed folios in the array. */
+	unsigned int nr_folios;
 
-	/* the pages with the compressed data on them */
-	struct page **compressed_pages;
+	/* The folios with the compressed data on them. */
+	struct folio **compressed_folios;
 
 	/* starting offset in the inode for our pages */
 	u64 start;
@@ -85,27 +85,24 @@ static inline unsigned int btrfs_compress_level(unsigned int type_level)
 int __init btrfs_init_compress(void);
 void __cold btrfs_exit_compress(void);
 
-int btrfs_compress_pages(unsigned int type_level, struct address_space *mapping,
-			 u64 start, struct page **pages,
-			 unsigned long *out_pages,
-			 unsigned long *total_in,
-			 unsigned long *total_out);
+int btrfs_compress_folios(unsigned int type_level, struct address_space *mapping,
+			  u64 start, struct folio **folios, unsigned long *out_folios,
+			 unsigned long *total_in, unsigned long *total_out);
 int btrfs_decompress(int type, const u8 *data_in, struct page *dest_page,
 		     unsigned long start_byte, size_t srclen, size_t destlen);
 int btrfs_decompress_buf2page(const char *buf, u32 buf_len,
 			      struct compressed_bio *cb, u32 decompressed);
 
 void btrfs_submit_compressed_write(struct btrfs_ordered_extent *ordered,
-				  struct page **compressed_pages,
-				  unsigned int nr_pages,
-				  blk_opf_t write_flags,
-				  bool writeback);
+				   struct folio **compressed_folios,
+				   unsigned int nr_folios, blk_opf_t write_flags,
+				   bool writeback);
 void btrfs_submit_compressed_read(struct btrfs_bio *bbio);
 
 unsigned int btrfs_compress_str2level(unsigned int type, const char *str);
 
-struct page *btrfs_alloc_compr_page(void);
-void btrfs_free_compr_page(struct page *page);
+struct folio *btrfs_alloc_compr_folio(void);
+void btrfs_free_compr_folio(struct folio *folio);
 
 enum btrfs_compression_type {
 	BTRFS_COMPRESS_NONE  = 0,
@@ -149,8 +146,11 @@ bool btrfs_compress_is_valid_type(const char *str, size_t len);
 
 int btrfs_compress_heuristic(struct inode *inode, u64 start, u64 end);
 
-int zlib_compress_pages(struct list_head *ws, struct address_space *mapping,
-		u64 start, struct page **pages, unsigned long *out_pages,
+int btrfs_compress_filemap_get_folio(struct address_space *mapping, u64 start,
+				     struct folio **in_folio_ret);
+
+int zlib_compress_folios(struct list_head *ws, struct address_space *mapping,
+			 u64 start, struct folio **folios, unsigned long *out_folios,
 		unsigned long *total_in, unsigned long *total_out);
 int zlib_decompress_bio(struct list_head *ws, struct compressed_bio *cb);
 int zlib_decompress(struct list_head *ws, const u8 *data_in,
@@ -160,8 +160,8 @@ struct list_head *zlib_alloc_workspace(unsigned int level);
 void zlib_free_workspace(struct list_head *ws);
 struct list_head *zlib_get_workspace(unsigned int level);
 
-int lzo_compress_pages(struct list_head *ws, struct address_space *mapping,
-		u64 start, struct page **pages, unsigned long *out_pages,
+int lzo_compress_folios(struct list_head *ws, struct address_space *mapping,
+			u64 start, struct folio **folios, unsigned long *out_folios,
 		unsigned long *total_in, unsigned long *total_out);
 int lzo_decompress_bio(struct list_head *ws, struct compressed_bio *cb);
 int lzo_decompress(struct list_head *ws, const u8 *data_in,
@@ -170,8 +170,8 @@ int lzo_decompress(struct list_head *ws, const u8 *data_in,
 struct list_head *lzo_alloc_workspace(unsigned int level);
 void lzo_free_workspace(struct list_head *ws);
 
-int zstd_compress_pages(struct list_head *ws, struct address_space *mapping,
-		u64 start, struct page **pages, unsigned long *out_pages,
+int zstd_compress_folios(struct list_head *ws, struct address_space *mapping,
+			 u64 start, struct folio **folios, unsigned long *out_folios,
 		unsigned long *total_in, unsigned long *total_out);
 int zstd_decompress_bio(struct list_head *ws, struct compressed_bio *cb);
 int zstd_decompress(struct list_head *ws, const u8 *data_in,
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index aaf53fd84358..1a49b9232990 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -291,7 +291,7 @@ static void add_root_to_dirty_list(struct btrfs_root *root)
 	spin_lock(&fs_info->trans_lock);
 	if (!test_and_set_bit(BTRFS_ROOT_DIRTY, &root->state)) {
 		/* Want the extent tree to be the last on the list */
-		if (root->root_key.objectid == BTRFS_EXTENT_TREE_OBJECTID)
+		if (btrfs_root_id(root) == BTRFS_EXTENT_TREE_OBJECTID)
 			list_move_tail(&root->dirty_list,
 				       &fs_info->dirty_cowonly_roots);
 		else
@@ -454,7 +454,7 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans,
 		}
 	} else {
 		refs = 1;
-		if (root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID ||
+		if (btrfs_root_id(root) == BTRFS_TREE_RELOC_OBJECTID ||
 		    btrfs_header_backref_rev(buf) < BTRFS_MIXED_BACKREF_REV)
 			flags = BTRFS_BLOCK_FLAG_FULL_BACKREF;
 		else
@@ -466,15 +466,14 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans,
 	       !(flags & BTRFS_BLOCK_FLAG_FULL_BACKREF));
 
 	if (refs > 1) {
-		if ((owner == root->root_key.objectid ||
-		     root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID) &&
+		if ((owner == btrfs_root_id(root) ||
+		     btrfs_root_id(root) == BTRFS_TREE_RELOC_OBJECTID) &&
 		    !(flags & BTRFS_BLOCK_FLAG_FULL_BACKREF)) {
 			ret = btrfs_inc_ref(trans, root, buf, 1);
 			if (ret)
 				return ret;
 
-			if (root->root_key.objectid ==
-			    BTRFS_TREE_RELOC_OBJECTID) {
+			if (btrfs_root_id(root) == BTRFS_TREE_RELOC_OBJECTID) {
 				ret = btrfs_dec_ref(trans, root, buf, 0);
 				if (ret)
 					return ret;
@@ -485,8 +484,7 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans,
 			new_flags |= BTRFS_BLOCK_FLAG_FULL_BACKREF;
 		} else {
 
-			if (root->root_key.objectid ==
-			    BTRFS_TREE_RELOC_OBJECTID)
+			if (btrfs_root_id(root) == BTRFS_TREE_RELOC_OBJECTID)
 				ret = btrfs_inc_ref(trans, root, cow, 1);
 			else
 				ret = btrfs_inc_ref(trans, root, cow, 0);
@@ -500,8 +498,7 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans,
 		}
 	} else {
 		if (flags & BTRFS_BLOCK_FLAG_FULL_BACKREF) {
-			if (root->root_key.objectid ==
-			    BTRFS_TREE_RELOC_OBJECTID)
+			if (btrfs_root_id(root) == BTRFS_TREE_RELOC_OBJECTID)
 				ret = btrfs_inc_ref(trans, root, cow, 1);
 			else
 				ret = btrfs_inc_ref(trans, root, cow, 0);
@@ -563,13 +560,13 @@ int btrfs_force_cow_block(struct btrfs_trans_handle *trans,
 	else
 		btrfs_node_key(buf, &disk_key, 0);
 
-	if (root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID) {
+	if (btrfs_root_id(root) == BTRFS_TREE_RELOC_OBJECTID) {
 		if (parent)
 			parent_start = parent->start;
 		reloc_src_root = btrfs_header_owner(buf);
 	}
 	cow = btrfs_alloc_tree_block(trans, root, parent_start,
-				     root->root_key.objectid, &disk_key, level,
+				     btrfs_root_id(root), &disk_key, level,
 				     search_start, empty_size, reloc_src_root, nest);
 	if (IS_ERR(cow))
 		return PTR_ERR(cow);
@@ -582,10 +579,10 @@ int btrfs_force_cow_block(struct btrfs_trans_handle *trans,
 	btrfs_set_header_backref_rev(cow, BTRFS_MIXED_BACKREF_REV);
 	btrfs_clear_header_flag(cow, BTRFS_HEADER_FLAG_WRITTEN |
 				     BTRFS_HEADER_FLAG_RELOC);
-	if (root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID)
+	if (btrfs_root_id(root) == BTRFS_TREE_RELOC_OBJECTID)
 		btrfs_set_header_flag(cow, BTRFS_HEADER_FLAG_RELOC);
 	else
-		btrfs_set_header_owner(cow, root->root_key.objectid);
+		btrfs_set_header_owner(cow, btrfs_root_id(root));
 
 	write_extent_buffer_fsid(cow, fs_info->fs_devices->metadata_uuid);
 
@@ -609,7 +606,7 @@ int btrfs_force_cow_block(struct btrfs_trans_handle *trans,
 
 	if (buf == root->node) {
 		WARN_ON(parent && parent != buf);
-		if (root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID ||
+		if (btrfs_root_id(root) == BTRFS_TREE_RELOC_OBJECTID ||
 		    btrfs_header_backref_rev(buf) < BTRFS_MIXED_BACKREF_REV)
 			parent_start = buf->start;
 
@@ -685,7 +682,7 @@ static inline int should_cow_block(struct btrfs_trans_handle *trans,
 	 */
 	if (btrfs_header_generation(buf) == trans->transid &&
 	    !btrfs_header_flag(buf, BTRFS_HEADER_FLAG_WRITTEN) &&
-	    !(root->root_key.objectid != BTRFS_TREE_RELOC_OBJECTID &&
+	    !(btrfs_root_id(root) != BTRFS_TREE_RELOC_OBJECTID &&
 	      btrfs_header_flag(buf, BTRFS_HEADER_FLAG_RELOC)) &&
 	    !test_bit(BTRFS_ROOT_FORCE_COW, &root->state))
 		return 0;
@@ -1003,7 +1000,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
 			goto out;
 		}
 
-		__btrfs_tree_lock(left, BTRFS_NESTING_LEFT);
+		btrfs_tree_lock_nested(left, BTRFS_NESTING_LEFT);
 		wret = btrfs_cow_block(trans, root, left,
 				       parent, pslot - 1, &left,
 				       BTRFS_NESTING_LEFT_COW);
@@ -1021,7 +1018,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
 			goto out;
 		}
 
-		__btrfs_tree_lock(right, BTRFS_NESTING_RIGHT);
+		btrfs_tree_lock_nested(right, BTRFS_NESTING_RIGHT);
 		wret = btrfs_cow_block(trans, root, right,
 				       parent, pslot + 1, &right,
 				       BTRFS_NESTING_RIGHT_COW);
@@ -1205,7 +1202,7 @@ static noinline int push_nodes_for_insert(struct btrfs_trans_handle *trans,
 		if (IS_ERR(left))
 			return PTR_ERR(left);
 
-		__btrfs_tree_lock(left, BTRFS_NESTING_LEFT);
+		btrfs_tree_lock_nested(left, BTRFS_NESTING_LEFT);
 
 		left_nr = btrfs_header_nritems(left);
 		if (left_nr >= BTRFS_NODEPTRS_PER_BLOCK(fs_info) - 1) {
@@ -1265,7 +1262,7 @@ static noinline int push_nodes_for_insert(struct btrfs_trans_handle *trans,
 		if (IS_ERR(right))
 			return PTR_ERR(right);
 
-		__btrfs_tree_lock(right, BTRFS_NESTING_RIGHT);
+		btrfs_tree_lock_nested(right, BTRFS_NESTING_RIGHT);
 
 		right_nr = btrfs_header_nritems(right);
 		if (right_nr >= BTRFS_NODEPTRS_PER_BLOCK(fs_info) - 1) {
@@ -1511,7 +1508,7 @@ read_block_for_search(struct btrfs_root *root, struct btrfs_path *p,
 	check.has_first_key = true;
 	check.level = parent_level - 1;
 	check.transid = gen;
-	check.owner_root = root->root_key.objectid;
+	check.owner_root = btrfs_root_id(root);
 
 	/*
 	 * If we need to read an extent buffer from disk and we are holding locks
@@ -1556,7 +1553,7 @@ read_block_for_search(struct btrfs_root *root, struct btrfs_path *p,
 			btrfs_release_path(p);
 			return -EIO;
 		}
-		if (btrfs_check_eb_owner(tmp, root->root_key.objectid)) {
+		if (btrfs_check_eb_owner(tmp, btrfs_root_id(root))) {
 			free_extent_buffer(tmp);
 			btrfs_release_path(p);
 			return -EUCLEAN;
@@ -2865,7 +2862,7 @@ static noinline int insert_new_root(struct btrfs_trans_handle *trans,
 	else
 		btrfs_node_key(lower, &lower_key, 0);
 
-	c = btrfs_alloc_tree_block(trans, root, 0, root->root_key.objectid,
+	c = btrfs_alloc_tree_block(trans, root, 0, btrfs_root_id(root),
 				   &lower_key, level, root->node->start, 0,
 				   0, BTRFS_NESTING_NEW_ROOT);
 	if (IS_ERR(c))
@@ -3009,7 +3006,7 @@ static noinline int split_node(struct btrfs_trans_handle *trans,
 	mid = (c_nritems + 1) / 2;
 	btrfs_node_key(c, &disk_key, mid);
 
-	split = btrfs_alloc_tree_block(trans, root, 0, root->root_key.objectid,
+	split = btrfs_alloc_tree_block(trans, root, 0, btrfs_root_id(root),
 				       &disk_key, level, c->start, 0,
 				       0, BTRFS_NESTING_SPLIT);
 	if (IS_ERR(split))
@@ -3267,7 +3264,7 @@ static int push_leaf_right(struct btrfs_trans_handle *trans, struct btrfs_root
 	if (IS_ERR(right))
 		return PTR_ERR(right);
 
-	__btrfs_tree_lock(right, BTRFS_NESTING_RIGHT);
+	btrfs_tree_lock_nested(right, BTRFS_NESTING_RIGHT);
 
 	free_space = btrfs_leaf_free_space(right);
 	if (free_space < data_size)
@@ -3483,7 +3480,7 @@ static int push_leaf_left(struct btrfs_trans_handle *trans, struct btrfs_root
 	if (IS_ERR(left))
 		return PTR_ERR(left);
 
-	__btrfs_tree_lock(left, BTRFS_NESTING_LEFT);
+	btrfs_tree_lock_nested(left, BTRFS_NESTING_LEFT);
 
 	free_space = btrfs_leaf_free_space(left);
 	if (free_space < data_size) {
@@ -3761,7 +3758,7 @@ again:
 	 * BTRFS_NESTING_SPLIT_THE_SPLITTENING if we need to, but for now just
 	 * use BTRFS_NESTING_NEW_ROOT.
 	 */
-	right = btrfs_alloc_tree_block(trans, root, 0, root->root_key.objectid,
+	right = btrfs_alloc_tree_block(trans, root, 0, btrfs_root_id(root),
 				       &disk_key, 0, l->start, 0, 0,
 				       num_doubles ? BTRFS_NESTING_NEW_ROOT :
 				       BTRFS_NESTING_SPLIT);
diff --git a/fs/btrfs/defrag.c b/fs/btrfs/defrag.c
index f015fa1b6301..407ccec3e57e 100644
--- a/fs/btrfs/defrag.c
+++ b/fs/btrfs/defrag.c
@@ -147,7 +147,7 @@ int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans,
 
 	defrag->ino = btrfs_ino(inode);
 	defrag->transid = transid;
-	defrag->root = root->root_key.objectid;
+	defrag->root = btrfs_root_id(root);
 	defrag->extent_thresh = extent_thresh;
 
 	spin_lock(&fs_info->defrag_inodes_lock);
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 121ab890bd05..95a0497fa866 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -1651,7 +1651,7 @@ int btrfs_delete_delayed_dir_index(struct btrfs_trans_handle *trans,
 	if (unlikely(ret)) {
 		btrfs_err(trans->fs_info,
 			  "err add delayed dir index item(index: %llu) into the deletion tree of the delayed node(root id: %llu, inode id: %llu, errno: %d)",
-			  index, node->root->root_key.objectid,
+			  index, btrfs_root_id(node->root),
 			  node->inode_id, ret);
 		btrfs_delayed_item_release_metadata(dir->root, item);
 		btrfs_release_delayed_item(item);
diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c
index e44e62cf76bc..6cc80fb10da2 100644
--- a/fs/btrfs/delayed-ref.c
+++ b/fs/btrfs/delayed-ref.c
@@ -16,8 +16,7 @@
 #include "fs.h"
 
 struct kmem_cache *btrfs_delayed_ref_head_cachep;
-struct kmem_cache *btrfs_delayed_tree_ref_cachep;
-struct kmem_cache *btrfs_delayed_data_ref_cachep;
+struct kmem_cache *btrfs_delayed_ref_node_cachep;
 struct kmem_cache *btrfs_delayed_extent_op_cachep;
 /*
  * delayed back reference update tracking.  For subvolume trees
@@ -305,50 +304,19 @@ int btrfs_delayed_refs_rsv_refill(struct btrfs_fs_info *fs_info,
 }
 
 /*
- * compare two delayed tree backrefs with same bytenr and type
- */
-static int comp_tree_refs(struct btrfs_delayed_tree_ref *ref1,
-			  struct btrfs_delayed_tree_ref *ref2)
-{
-	if (ref1->node.type == BTRFS_TREE_BLOCK_REF_KEY) {
-		if (ref1->root < ref2->root)
-			return -1;
-		if (ref1->root > ref2->root)
-			return 1;
-	} else {
-		if (ref1->parent < ref2->parent)
-			return -1;
-		if (ref1->parent > ref2->parent)
-			return 1;
-	}
-	return 0;
-}
-
-/*
  * compare two delayed data backrefs with same bytenr and type
  */
-static int comp_data_refs(struct btrfs_delayed_data_ref *ref1,
-			  struct btrfs_delayed_data_ref *ref2)
+static int comp_data_refs(struct btrfs_delayed_ref_node *ref1,
+			  struct btrfs_delayed_ref_node *ref2)
 {
-	if (ref1->node.type == BTRFS_EXTENT_DATA_REF_KEY) {
-		if (ref1->root < ref2->root)
-			return -1;
-		if (ref1->root > ref2->root)
-			return 1;
-		if (ref1->objectid < ref2->objectid)
-			return -1;
-		if (ref1->objectid > ref2->objectid)
-			return 1;
-		if (ref1->offset < ref2->offset)
-			return -1;
-		if (ref1->offset > ref2->offset)
-			return 1;
-	} else {
-		if (ref1->parent < ref2->parent)
-			return -1;
-		if (ref1->parent > ref2->parent)
-			return 1;
-	}
+	if (ref1->data_ref.objectid < ref2->data_ref.objectid)
+		return -1;
+	if (ref1->data_ref.objectid > ref2->data_ref.objectid)
+		return 1;
+	if (ref1->data_ref.offset < ref2->data_ref.offset)
+		return -1;
+	if (ref1->data_ref.offset > ref2->data_ref.offset)
+		return 1;
 	return 0;
 }
 
@@ -362,13 +330,20 @@ static int comp_refs(struct btrfs_delayed_ref_node *ref1,
 		return -1;
 	if (ref1->type > ref2->type)
 		return 1;
-	if (ref1->type == BTRFS_TREE_BLOCK_REF_KEY ||
-	    ref1->type == BTRFS_SHARED_BLOCK_REF_KEY)
-		ret = comp_tree_refs(btrfs_delayed_node_to_tree_ref(ref1),
-				     btrfs_delayed_node_to_tree_ref(ref2));
-	else
-		ret = comp_data_refs(btrfs_delayed_node_to_data_ref(ref1),
-				     btrfs_delayed_node_to_data_ref(ref2));
+	if (ref1->type == BTRFS_SHARED_BLOCK_REF_KEY ||
+	    ref1->type == BTRFS_SHARED_DATA_REF_KEY) {
+		if (ref1->parent < ref2->parent)
+			return -1;
+		if (ref1->parent > ref2->parent)
+			return 1;
+	} else {
+		if (ref1->ref_root < ref2->ref_root)
+			return -1;
+		if (ref1->ref_root > ref2->ref_root)
+			return -1;
+		if (ref1->type == BTRFS_EXTENT_DATA_REF_KEY)
+			ret = comp_data_refs(ref1, ref2);
+	}
 	if (ret)
 		return ret;
 	if (check_seq) {
@@ -828,18 +803,20 @@ static noinline void update_existing_head_ref(struct btrfs_trans_handle *trans,
 }
 
 static void init_delayed_ref_head(struct btrfs_delayed_ref_head *head_ref,
+				  struct btrfs_ref *generic_ref,
 				  struct btrfs_qgroup_extent_record *qrecord,
-				  u64 bytenr, u64 num_bytes, u64 ref_root,
-				  u64 reserved, int action, bool is_data,
-				  bool is_system, u64 owning_root)
+				  u64 reserved)
 {
 	int count_mod = 1;
 	bool must_insert_reserved = false;
 
 	/* If reserved is provided, it must be a data extent. */
-	BUG_ON(!is_data && reserved);
+	BUG_ON(generic_ref->type != BTRFS_REF_DATA && reserved);
 
-	switch (action) {
+	switch (generic_ref->action) {
+	case BTRFS_ADD_DELAYED_REF:
+		/* count_mod is already set to 1. */
+		break;
 	case BTRFS_UPDATE_DELAYED_HEAD:
 		count_mod = 0;
 		break;
@@ -868,14 +845,14 @@ static void init_delayed_ref_head(struct btrfs_delayed_ref_head *head_ref,
 	}
 
 	refcount_set(&head_ref->refs, 1);
-	head_ref->bytenr = bytenr;
-	head_ref->num_bytes = num_bytes;
+	head_ref->bytenr = generic_ref->bytenr;
+	head_ref->num_bytes = generic_ref->num_bytes;
 	head_ref->ref_mod = count_mod;
 	head_ref->reserved_bytes = reserved;
 	head_ref->must_insert_reserved = must_insert_reserved;
-	head_ref->owning_root = owning_root;
-	head_ref->is_data = is_data;
-	head_ref->is_system = is_system;
+	head_ref->owning_root = generic_ref->owning_root;
+	head_ref->is_data = (generic_ref->type == BTRFS_REF_DATA);
+	head_ref->is_system = (generic_ref->ref_root == BTRFS_CHUNK_TREE_OBJECTID);
 	head_ref->ref_tree = RB_ROOT_CACHED;
 	INIT_LIST_HEAD(&head_ref->ref_add_list);
 	RB_CLEAR_NODE(&head_ref->href_node);
@@ -885,12 +862,12 @@ static void init_delayed_ref_head(struct btrfs_delayed_ref_head *head_ref,
 	mutex_init(&head_ref->mutex);
 
 	if (qrecord) {
-		if (ref_root && reserved) {
+		if (generic_ref->ref_root && reserved) {
 			qrecord->data_rsv = reserved;
-			qrecord->data_rsv_refroot = ref_root;
+			qrecord->data_rsv_refroot = generic_ref->ref_root;
 		}
-		qrecord->bytenr = bytenr;
-		qrecord->num_bytes = num_bytes;
+		qrecord->bytenr = generic_ref->bytenr;
+		qrecord->num_bytes = generic_ref->num_bytes;
 		qrecord->old_roots = NULL;
 	}
 }
@@ -982,49 +959,45 @@ add_delayed_ref_head(struct btrfs_trans_handle *trans,
  */
 static void init_delayed_ref_common(struct btrfs_fs_info *fs_info,
 				    struct btrfs_delayed_ref_node *ref,
-				    u64 bytenr, u64 num_bytes, u64 ref_root,
-				    int action, u8 ref_type)
+				    struct btrfs_ref *generic_ref)
 {
+	int action = generic_ref->action;
 	u64 seq = 0;
 
 	if (action == BTRFS_ADD_DELAYED_EXTENT)
 		action = BTRFS_ADD_DELAYED_REF;
 
-	if (is_fstree(ref_root))
+	if (is_fstree(generic_ref->ref_root))
 		seq = atomic64_read(&fs_info->tree_mod_seq);
 
 	refcount_set(&ref->refs, 1);
-	ref->bytenr = bytenr;
-	ref->num_bytes = num_bytes;
+	ref->bytenr = generic_ref->bytenr;
+	ref->num_bytes = generic_ref->num_bytes;
 	ref->ref_mod = 1;
 	ref->action = action;
 	ref->seq = seq;
-	ref->type = ref_type;
+	ref->type = btrfs_ref_type(generic_ref);
+	ref->ref_root = generic_ref->ref_root;
+	ref->parent = generic_ref->parent;
 	RB_CLEAR_NODE(&ref->ref_node);
 	INIT_LIST_HEAD(&ref->add_list);
-}
 
-void btrfs_init_generic_ref(struct btrfs_ref *generic_ref, int action, u64 bytenr,
-			    u64 len, u64 parent, u64 owning_root)
-{
-	generic_ref->action = action;
-	generic_ref->bytenr = bytenr;
-	generic_ref->len = len;
-	generic_ref->parent = parent;
-	generic_ref->owning_root = owning_root;
+	if (generic_ref->type == BTRFS_REF_DATA)
+		ref->data_ref = generic_ref->data_ref;
+	else
+		ref->tree_ref = generic_ref->tree_ref;
 }
 
-void btrfs_init_tree_ref(struct btrfs_ref *generic_ref, int level, u64 root,
-			 u64 mod_root, bool skip_qgroup)
+void btrfs_init_tree_ref(struct btrfs_ref *generic_ref, int level, u64 mod_root,
+			 bool skip_qgroup)
 {
 #ifdef CONFIG_BTRFS_FS_REF_VERIFY
 	/* If @real_root not set, use @root as fallback */
-	generic_ref->real_root = mod_root ?: root;
+	generic_ref->real_root = mod_root ?: generic_ref->ref_root;
 #endif
 	generic_ref->tree_ref.level = level;
-	generic_ref->tree_ref.ref_root = root;
 	generic_ref->type = BTRFS_REF_METADATA;
-	if (skip_qgroup || !(is_fstree(root) &&
+	if (skip_qgroup || !(is_fstree(generic_ref->ref_root) &&
 			     (!mod_root || is_fstree(mod_root))))
 		generic_ref->skip_qgroup = true;
 	else
@@ -1032,85 +1005,58 @@ void btrfs_init_tree_ref(struct btrfs_ref *generic_ref, int level, u64 root,
 
 }
 
-void btrfs_init_data_ref(struct btrfs_ref *generic_ref, u64 ref_root, u64 ino,
-			 u64 offset, u64 mod_root, bool skip_qgroup)
+void btrfs_init_data_ref(struct btrfs_ref *generic_ref, u64 ino, u64 offset,
+			 u64 mod_root, bool skip_qgroup)
 {
 #ifdef CONFIG_BTRFS_FS_REF_VERIFY
 	/* If @real_root not set, use @root as fallback */
-	generic_ref->real_root = mod_root ?: ref_root;
+	generic_ref->real_root = mod_root ?: generic_ref->ref_root;
 #endif
-	generic_ref->data_ref.ref_root = ref_root;
-	generic_ref->data_ref.ino = ino;
+	generic_ref->data_ref.objectid = ino;
 	generic_ref->data_ref.offset = offset;
 	generic_ref->type = BTRFS_REF_DATA;
-	if (skip_qgroup || !(is_fstree(ref_root) &&
+	if (skip_qgroup || !(is_fstree(generic_ref->ref_root) &&
 			     (!mod_root || is_fstree(mod_root))))
 		generic_ref->skip_qgroup = true;
 	else
 		generic_ref->skip_qgroup = false;
 }
 
-/*
- * add a delayed tree ref.  This does all of the accounting required
- * to make sure the delayed ref is eventually processed before this
- * transaction commits.
- */
-int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans,
-			       struct btrfs_ref *generic_ref,
-			       struct btrfs_delayed_extent_op *extent_op)
+static int add_delayed_ref(struct btrfs_trans_handle *trans,
+			   struct btrfs_ref *generic_ref,
+			   struct btrfs_delayed_extent_op *extent_op,
+			   u64 reserved)
 {
 	struct btrfs_fs_info *fs_info = trans->fs_info;
-	struct btrfs_delayed_tree_ref *ref;
+	struct btrfs_delayed_ref_node *node;
 	struct btrfs_delayed_ref_head *head_ref;
 	struct btrfs_delayed_ref_root *delayed_refs;
 	struct btrfs_qgroup_extent_record *record = NULL;
 	bool qrecord_inserted;
-	bool is_system;
-	bool merged;
 	int action = generic_ref->action;
-	int level = generic_ref->tree_ref.level;
-	u64 bytenr = generic_ref->bytenr;
-	u64 num_bytes = generic_ref->len;
-	u64 parent = generic_ref->parent;
-	u8 ref_type;
-
-	is_system = (generic_ref->tree_ref.ref_root == BTRFS_CHUNK_TREE_OBJECTID);
+	bool merged;
 
-	ASSERT(generic_ref->type == BTRFS_REF_METADATA && generic_ref->action);
-	ref = kmem_cache_alloc(btrfs_delayed_tree_ref_cachep, GFP_NOFS);
-	if (!ref)
+	node = kmem_cache_alloc(btrfs_delayed_ref_node_cachep, GFP_NOFS);
+	if (!node)
 		return -ENOMEM;
 
 	head_ref = kmem_cache_alloc(btrfs_delayed_ref_head_cachep, GFP_NOFS);
 	if (!head_ref) {
-		kmem_cache_free(btrfs_delayed_tree_ref_cachep, ref);
+		kmem_cache_free(btrfs_delayed_ref_node_cachep, node);
 		return -ENOMEM;
 	}
 
 	if (btrfs_qgroup_full_accounting(fs_info) && !generic_ref->skip_qgroup) {
 		record = kzalloc(sizeof(*record), GFP_NOFS);
 		if (!record) {
-			kmem_cache_free(btrfs_delayed_tree_ref_cachep, ref);
+			kmem_cache_free(btrfs_delayed_ref_node_cachep, node);
 			kmem_cache_free(btrfs_delayed_ref_head_cachep, head_ref);
 			return -ENOMEM;
 		}
 	}
 
-	if (parent)
-		ref_type = BTRFS_SHARED_BLOCK_REF_KEY;
-	else
-		ref_type = BTRFS_TREE_BLOCK_REF_KEY;
-
-	init_delayed_ref_common(fs_info, &ref->node, bytenr, num_bytes,
-				generic_ref->tree_ref.ref_root, action,
-				ref_type);
-	ref->root = generic_ref->tree_ref.ref_root;
-	ref->parent = parent;
-	ref->level = level;
-
-	init_delayed_ref_head(head_ref, record, bytenr, num_bytes,
-			      generic_ref->tree_ref.ref_root, 0, action,
-			      false, is_system, generic_ref->owning_root);
+	init_delayed_ref_common(fs_info, node, generic_ref);
+	init_delayed_ref_head(head_ref, generic_ref, record, reserved);
 	head_ref->extent_op = extent_op;
 
 	delayed_refs = &trans->transaction->delayed_refs;
@@ -1123,7 +1069,7 @@ int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans,
 	head_ref = add_delayed_ref_head(trans, head_ref, record,
 					action, &qrecord_inserted);
 
-	merged = insert_delayed_ref(trans, head_ref, &ref->node);
+	merged = insert_delayed_ref(trans, head_ref, node);
 	spin_unlock(&delayed_refs->lock);
 
 	/*
@@ -1132,107 +1078,39 @@ int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans,
 	 */
 	btrfs_update_delayed_refs_rsv(trans);
 
-	trace_add_delayed_tree_ref(fs_info, &ref->node, ref,
-				   action == BTRFS_ADD_DELAYED_EXTENT ?
-				   BTRFS_ADD_DELAYED_REF : action);
+	if (generic_ref->type == BTRFS_REF_DATA)
+		trace_add_delayed_data_ref(trans->fs_info, node);
+	else
+		trace_add_delayed_tree_ref(trans->fs_info, node);
 	if (merged)
-		kmem_cache_free(btrfs_delayed_tree_ref_cachep, ref);
+		kmem_cache_free(btrfs_delayed_ref_node_cachep, node);
 
 	if (qrecord_inserted)
-		btrfs_qgroup_trace_extent_post(trans, record);
-
+		return btrfs_qgroup_trace_extent_post(trans, record);
 	return 0;
 }
 
 /*
+ * Add a delayed tree ref. This does all of the accounting required to make sure
+ * the delayed ref is eventually processed before this transaction commits.
+ */
+int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans,
+			       struct btrfs_ref *generic_ref,
+			       struct btrfs_delayed_extent_op *extent_op)
+{
+	ASSERT(generic_ref->type == BTRFS_REF_METADATA && generic_ref->action);
+	return add_delayed_ref(trans, generic_ref, extent_op, 0);
+}
+
+/*
  * add a delayed data ref. it's similar to btrfs_add_delayed_tree_ref.
  */
 int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans,
 			       struct btrfs_ref *generic_ref,
 			       u64 reserved)
 {
-	struct btrfs_fs_info *fs_info = trans->fs_info;
-	struct btrfs_delayed_data_ref *ref;
-	struct btrfs_delayed_ref_head *head_ref;
-	struct btrfs_delayed_ref_root *delayed_refs;
-	struct btrfs_qgroup_extent_record *record = NULL;
-	bool qrecord_inserted;
-	int action = generic_ref->action;
-	bool merged;
-	u64 bytenr = generic_ref->bytenr;
-	u64 num_bytes = generic_ref->len;
-	u64 parent = generic_ref->parent;
-	u64 ref_root = generic_ref->data_ref.ref_root;
-	u64 owner = generic_ref->data_ref.ino;
-	u64 offset = generic_ref->data_ref.offset;
-	u8 ref_type;
-
-	ASSERT(generic_ref->type == BTRFS_REF_DATA && action);
-	ref = kmem_cache_alloc(btrfs_delayed_data_ref_cachep, GFP_NOFS);
-	if (!ref)
-		return -ENOMEM;
-
-	if (parent)
-	        ref_type = BTRFS_SHARED_DATA_REF_KEY;
-	else
-	        ref_type = BTRFS_EXTENT_DATA_REF_KEY;
-	init_delayed_ref_common(fs_info, &ref->node, bytenr, num_bytes,
-				ref_root, action, ref_type);
-	ref->root = ref_root;
-	ref->parent = parent;
-	ref->objectid = owner;
-	ref->offset = offset;
-
-
-	head_ref = kmem_cache_alloc(btrfs_delayed_ref_head_cachep, GFP_NOFS);
-	if (!head_ref) {
-		kmem_cache_free(btrfs_delayed_data_ref_cachep, ref);
-		return -ENOMEM;
-	}
-
-	if (btrfs_qgroup_full_accounting(fs_info) && !generic_ref->skip_qgroup) {
-		record = kzalloc(sizeof(*record), GFP_NOFS);
-		if (!record) {
-			kmem_cache_free(btrfs_delayed_data_ref_cachep, ref);
-			kmem_cache_free(btrfs_delayed_ref_head_cachep,
-					head_ref);
-			return -ENOMEM;
-		}
-	}
-
-	init_delayed_ref_head(head_ref, record, bytenr, num_bytes, ref_root,
-			      reserved, action, true, false, generic_ref->owning_root);
-	head_ref->extent_op = NULL;
-
-	delayed_refs = &trans->transaction->delayed_refs;
-	spin_lock(&delayed_refs->lock);
-
-	/*
-	 * insert both the head node and the new ref without dropping
-	 * the spin lock
-	 */
-	head_ref = add_delayed_ref_head(trans, head_ref, record,
-					action, &qrecord_inserted);
-
-	merged = insert_delayed_ref(trans, head_ref, &ref->node);
-	spin_unlock(&delayed_refs->lock);
-
-	/*
-	 * Need to update the delayed_refs_rsv with any changes we may have
-	 * made.
-	 */
-	btrfs_update_delayed_refs_rsv(trans);
-
-	trace_add_delayed_data_ref(trans->fs_info, &ref->node, ref,
-				   action == BTRFS_ADD_DELAYED_EXTENT ?
-				   BTRFS_ADD_DELAYED_REF : action);
-	if (merged)
-		kmem_cache_free(btrfs_delayed_data_ref_cachep, ref);
-
-
-	if (qrecord_inserted)
-		return btrfs_qgroup_trace_extent_post(trans, record);
-	return 0;
+	ASSERT(generic_ref->type == BTRFS_REF_DATA && generic_ref->action);
+	return add_delayed_ref(trans, generic_ref, NULL, reserved);
 }
 
 int btrfs_add_delayed_extent_op(struct btrfs_trans_handle *trans,
@@ -1241,13 +1119,18 @@ int btrfs_add_delayed_extent_op(struct btrfs_trans_handle *trans,
 {
 	struct btrfs_delayed_ref_head *head_ref;
 	struct btrfs_delayed_ref_root *delayed_refs;
+	struct btrfs_ref generic_ref = {
+		.type = BTRFS_REF_METADATA,
+		.action = BTRFS_UPDATE_DELAYED_HEAD,
+		.bytenr = bytenr,
+		.num_bytes = num_bytes,
+	};
 
 	head_ref = kmem_cache_alloc(btrfs_delayed_ref_head_cachep, GFP_NOFS);
 	if (!head_ref)
 		return -ENOMEM;
 
-	init_delayed_ref_head(head_ref, NULL, bytenr, num_bytes, 0, 0,
-			      BTRFS_UPDATE_DELAYED_HEAD, false, false, 0);
+	init_delayed_ref_head(head_ref, &generic_ref, NULL, 0);
 	head_ref->extent_op = extent_op;
 
 	delayed_refs = &trans->transaction->delayed_refs;
@@ -1270,18 +1153,7 @@ void btrfs_put_delayed_ref(struct btrfs_delayed_ref_node *ref)
 {
 	if (refcount_dec_and_test(&ref->refs)) {
 		WARN_ON(!RB_EMPTY_NODE(&ref->ref_node));
-		switch (ref->type) {
-		case BTRFS_TREE_BLOCK_REF_KEY:
-		case BTRFS_SHARED_BLOCK_REF_KEY:
-			kmem_cache_free(btrfs_delayed_tree_ref_cachep, ref);
-			break;
-		case BTRFS_EXTENT_DATA_REF_KEY:
-		case BTRFS_SHARED_DATA_REF_KEY:
-			kmem_cache_free(btrfs_delayed_data_ref_cachep, ref);
-			break;
-		default:
-			BUG();
-		}
+		kmem_cache_free(btrfs_delayed_ref_node_cachep, ref);
 	}
 }
 
@@ -1300,8 +1172,7 @@ btrfs_find_delayed_ref_head(struct btrfs_delayed_ref_root *delayed_refs, u64 byt
 void __cold btrfs_delayed_ref_exit(void)
 {
 	kmem_cache_destroy(btrfs_delayed_ref_head_cachep);
-	kmem_cache_destroy(btrfs_delayed_tree_ref_cachep);
-	kmem_cache_destroy(btrfs_delayed_data_ref_cachep);
+	kmem_cache_destroy(btrfs_delayed_ref_node_cachep);
 	kmem_cache_destroy(btrfs_delayed_extent_op_cachep);
 }
 
@@ -1311,12 +1182,8 @@ int __init btrfs_delayed_ref_init(void)
 	if (!btrfs_delayed_ref_head_cachep)
 		goto fail;
 
-	btrfs_delayed_tree_ref_cachep = KMEM_CACHE(btrfs_delayed_tree_ref, 0);
-	if (!btrfs_delayed_tree_ref_cachep)
-		goto fail;
-
-	btrfs_delayed_data_ref_cachep = KMEM_CACHE(btrfs_delayed_data_ref, 0);
-	if (!btrfs_delayed_data_ref_cachep)
+	btrfs_delayed_ref_node_cachep = KMEM_CACHE(btrfs_delayed_ref_node, 0);
+	if (!btrfs_delayed_ref_node_cachep)
 		goto fail;
 
 	btrfs_delayed_extent_op_cachep = KMEM_CACHE(btrfs_delayed_extent_op, 0);
diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h
index b291147cb8ab..04b180ebe1fe 100644
--- a/fs/btrfs/delayed-ref.h
+++ b/fs/btrfs/delayed-ref.h
@@ -30,6 +30,32 @@ enum btrfs_delayed_ref_action {
 	BTRFS_UPDATE_DELAYED_HEAD,
 } __packed;
 
+struct btrfs_data_ref {
+	/* For EXTENT_DATA_REF */
+
+	/* Inode which refers to this data extent */
+	u64 objectid;
+
+	/*
+	 * file_offset - extent_offset
+	 *
+	 * file_offset is the key.offset of the EXTENT_DATA key.
+	 * extent_offset is btrfs_file_extent_offset() of the EXTENT_DATA data.
+	 */
+	u64 offset;
+};
+
+struct btrfs_tree_ref {
+	/*
+	 * Level of this tree block.
+	 *
+	 * Shared for skinny (TREE_BLOCK_REF) and normal tree ref.
+	 */
+	int level;
+
+	/* For non-skinny metadata, no special member needed */
+};
+
 struct btrfs_delayed_ref_node {
 	struct rb_node ref_node;
 	/*
@@ -48,6 +74,15 @@ struct btrfs_delayed_ref_node {
 	/* seq number to keep track of insertion order */
 	u64 seq;
 
+	/* The ref_root for this ref */
+	u64 ref_root;
+
+	/*
+	 * The parent for this ref, if this isn't set the ref_root is the
+	 * reference owner.
+	 */
+	u64 parent;
+
 	/* ref count on this data structure */
 	refcount_t refs;
 
@@ -64,6 +99,11 @@ struct btrfs_delayed_ref_node {
 
 	unsigned int action:8;
 	unsigned int type:8;
+
+	union {
+		struct btrfs_tree_ref tree_ref;
+		struct btrfs_data_ref data_ref;
+	};
 };
 
 struct btrfs_delayed_extent_op {
@@ -151,21 +191,6 @@ struct btrfs_delayed_ref_head {
 	bool processing;
 };
 
-struct btrfs_delayed_tree_ref {
-	struct btrfs_delayed_ref_node node;
-	u64 root;
-	u64 parent;
-	int level;
-};
-
-struct btrfs_delayed_data_ref {
-	struct btrfs_delayed_ref_node node;
-	u64 root;
-	u64 parent;
-	u64 objectid;
-	u64 offset;
-};
-
 enum btrfs_delayed_ref_flags {
 	/* Indicate that we are flushing delayed refs for the commit */
 	BTRFS_DELAYED_REFS_FLUSHING,
@@ -214,42 +239,6 @@ enum btrfs_ref_type {
 	BTRFS_REF_LAST,
 } __packed;
 
-struct btrfs_data_ref {
-	/* For EXTENT_DATA_REF */
-
-	/* Root which owns this data reference. */
-	u64 ref_root;
-
-	/* Inode which refers to this data extent */
-	u64 ino;
-
-	/*
-	 * file_offset - extent_offset
-	 *
-	 * file_offset is the key.offset of the EXTENT_DATA key.
-	 * extent_offset is btrfs_file_extent_offset() of the EXTENT_DATA data.
-	 */
-	u64 offset;
-};
-
-struct btrfs_tree_ref {
-	/*
-	 * Level of this tree block
-	 *
-	 * Shared for skinny (TREE_BLOCK_REF) and normal tree ref.
-	 */
-	int level;
-
-	/*
-	 * Root which owns this tree block reference.
-	 *
-	 * For TREE_BLOCK_REF (skinny metadata, either inline or keyed)
-	 */
-	u64 ref_root;
-
-	/* For non-skinny metadata, no special member needed */
-};
-
 struct btrfs_ref {
 	enum btrfs_ref_type type;
 	enum btrfs_delayed_ref_action action;
@@ -267,9 +256,15 @@ struct btrfs_ref {
 	u64 real_root;
 #endif
 	u64 bytenr;
-	u64 len;
+	u64 num_bytes;
 	u64 owning_root;
 
+	/*
+	 * The root that owns the reference for this reference, this will be set
+	 * or ->parent will be set, depending on what type of reference this is.
+	 */
+	u64 ref_root;
+
 	/* Bytenr of the parent tree block */
 	u64 parent;
 	union {
@@ -279,8 +274,7 @@ struct btrfs_ref {
 };
 
 extern struct kmem_cache *btrfs_delayed_ref_head_cachep;
-extern struct kmem_cache *btrfs_delayed_tree_ref_cachep;
-extern struct kmem_cache *btrfs_delayed_data_ref_cachep;
+extern struct kmem_cache *btrfs_delayed_ref_node_cachep;
 extern struct kmem_cache *btrfs_delayed_extent_op_cachep;
 
 int __init btrfs_delayed_ref_init(void);
@@ -318,12 +312,10 @@ static inline u64 btrfs_calc_delayed_ref_csum_bytes(const struct btrfs_fs_info *
 	return btrfs_calc_metadata_size(fs_info, num_csum_items);
 }
 
-void btrfs_init_generic_ref(struct btrfs_ref *generic_ref, int action, u64 bytenr,
-			    u64 len, u64 parent, u64 owning_root);
-void btrfs_init_tree_ref(struct btrfs_ref *generic_ref, int level, u64 root,
+void btrfs_init_tree_ref(struct btrfs_ref *generic_ref, int level, u64 mod_root,
+			 bool skip_qgroup);
+void btrfs_init_data_ref(struct btrfs_ref *generic_ref, u64 ino, u64 offset,
 			 u64 mod_root, bool skip_qgroup);
-void btrfs_init_data_ref(struct btrfs_ref *generic_ref, u64 ref_root, u64 ino,
-			 u64 offset, u64 mod_root, bool skip_qgroup);
 
 static inline struct btrfs_delayed_extent_op *
 btrfs_alloc_delayed_extent_op(void)
@@ -398,19 +390,39 @@ void btrfs_migrate_to_delayed_refs_rsv(struct btrfs_fs_info *fs_info,
 				       u64 num_bytes);
 bool btrfs_check_space_for_delayed_refs(struct btrfs_fs_info *fs_info);
 
-/*
- * helper functions to cast a node into its container
- */
-static inline struct btrfs_delayed_tree_ref *
-btrfs_delayed_node_to_tree_ref(struct btrfs_delayed_ref_node *node)
+static inline u64 btrfs_delayed_ref_owner(struct btrfs_delayed_ref_node *node)
+{
+	if (node->type == BTRFS_EXTENT_DATA_REF_KEY ||
+	    node->type == BTRFS_SHARED_DATA_REF_KEY)
+		return node->data_ref.objectid;
+	return node->tree_ref.level;
+}
+
+static inline u64 btrfs_delayed_ref_offset(struct btrfs_delayed_ref_node *node)
 {
-	return container_of(node, struct btrfs_delayed_tree_ref, node);
+	if (node->type == BTRFS_EXTENT_DATA_REF_KEY ||
+	    node->type == BTRFS_SHARED_DATA_REF_KEY)
+		return node->data_ref.offset;
+	return 0;
 }
 
-static inline struct btrfs_delayed_data_ref *
-btrfs_delayed_node_to_data_ref(struct btrfs_delayed_ref_node *node)
+static inline u8 btrfs_ref_type(struct btrfs_ref *ref)
 {
-	return container_of(node, struct btrfs_delayed_data_ref, node);
+	ASSERT(ref->type == BTRFS_REF_DATA || ref->type == BTRFS_REF_METADATA);
+
+	if (ref->type == BTRFS_REF_DATA) {
+		if (ref->parent)
+			return BTRFS_SHARED_DATA_REF_KEY;
+		else
+			return BTRFS_EXTENT_DATA_REF_KEY;
+	} else {
+		if (ref->parent)
+			return BTRFS_SHARED_BLOCK_REF_KEY;
+		else
+			return BTRFS_TREE_BLOCK_REF_KEY;
+	}
+
+	return 0;
 }
 
 #endif
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 3df5477d48a8..a91a8056758a 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -646,7 +646,7 @@ struct extent_buffer *read_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr,
 static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info,
 			 u64 objectid)
 {
-	bool dummy = test_bit(BTRFS_FS_STATE_DUMMY_FS_INFO, &fs_info->fs_state);
+	bool dummy = btrfs_is_testing(fs_info);
 
 	memset(&root->root_key, 0, sizeof(root->root_key));
 	memset(&root->root_item, 0, sizeof(root->root_item));
@@ -663,8 +663,7 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info,
 	root->nr_delalloc_inodes = 0;
 	root->nr_ordered_extents = 0;
 	root->inode_tree = RB_ROOT;
-	/* GFP flags are compatible with XA_FLAGS_*. */
-	xa_init_flags(&root->delayed_nodes, GFP_ATOMIC);
+	xa_init(&root->delayed_nodes);
 
 	btrfs_init_root_block_rsv(root);
 
@@ -776,7 +775,7 @@ int btrfs_global_root_insert(struct btrfs_root *root)
 	if (tmp) {
 		ret = -EEXIST;
 		btrfs_warn(fs_info, "global root %llu %llu already exists",
-				root->root_key.objectid, root->root_key.offset);
+			   btrfs_root_id(root), root->root_key.offset);
 	}
 	return ret;
 }
@@ -1012,7 +1011,7 @@ int btrfs_add_log_tree(struct btrfs_trans_handle *trans,
 	}
 
 	log_root->last_trans = trans->transid;
-	log_root->root_key.offset = root->root_key.objectid;
+	log_root->root_key.offset = btrfs_root_id(root);
 
 	inode_item = &log_root->root_item.inode;
 	btrfs_set_stack_inode_generation(inode_item, 1);
@@ -1076,15 +1075,15 @@ static struct btrfs_root *read_tree_root_path(struct btrfs_root *tree_root,
 	 * For real fs, and not log/reloc trees, root owner must
 	 * match its root node owner
 	 */
-	if (!test_bit(BTRFS_FS_STATE_DUMMY_FS_INFO, &fs_info->fs_state) &&
-	    root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID &&
-	    root->root_key.objectid != BTRFS_TREE_RELOC_OBJECTID &&
-	    root->root_key.objectid != btrfs_header_owner(root->node)) {
+	if (!btrfs_is_testing(fs_info) &&
+	    btrfs_root_id(root) != BTRFS_TREE_LOG_OBJECTID &&
+	    btrfs_root_id(root) != BTRFS_TREE_RELOC_OBJECTID &&
+	    btrfs_root_id(root) != btrfs_header_owner(root->node)) {
 		btrfs_crit(fs_info,
 "root=%llu block=%llu, tree root owner mismatch, have %llu expect %llu",
-			   root->root_key.objectid, root->node->start,
+			   btrfs_root_id(root), root->node->start,
 			   btrfs_header_owner(root->node),
-			   root->root_key.objectid);
+			   btrfs_root_id(root));
 		ret = -EUCLEAN;
 		goto fail;
 	}
@@ -1121,9 +1120,9 @@ static int btrfs_init_fs_root(struct btrfs_root *root, dev_t anon_dev)
 
 	btrfs_drew_lock_init(&root->snapshot_lock);
 
-	if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID &&
+	if (btrfs_root_id(root) != BTRFS_TREE_LOG_OBJECTID &&
 	    !btrfs_is_data_reloc_root(root) &&
-	    is_fstree(root->root_key.objectid)) {
+	    is_fstree(btrfs_root_id(root))) {
 		set_bit(BTRFS_ROOT_SHAREABLE, &root->state);
 		btrfs_check_and_init_root_item(&root->root_item);
 	}
@@ -1132,7 +1131,7 @@ static int btrfs_init_fs_root(struct btrfs_root *root, dev_t anon_dev)
 	 * Don't assign anonymous block device to roots that are not exposed to
 	 * userspace, the id pool is limited to 1M
 	 */
-	if (is_fstree(root->root_key.objectid) &&
+	if (is_fstree(btrfs_root_id(root)) &&
 	    btrfs_root_refs(&root->root_item) > 0) {
 		if (!anon_dev) {
 			ret = get_anon_bdev(&root->anon_dev);
@@ -1219,7 +1218,7 @@ int btrfs_insert_fs_root(struct btrfs_fs_info *fs_info,
 
 	spin_lock(&fs_info->fs_roots_radix_lock);
 	ret = radix_tree_insert(&fs_info->fs_roots_radix,
-				(unsigned long)root->root_key.objectid,
+				(unsigned long)btrfs_root_id(root),
 				root);
 	if (ret == 0) {
 		btrfs_grab_root(root);
@@ -1266,9 +1265,14 @@ static void free_global_roots(struct btrfs_fs_info *fs_info)
 
 void btrfs_free_fs_info(struct btrfs_fs_info *fs_info)
 {
+	struct percpu_counter *em_counter = &fs_info->evictable_extent_maps;
+
 	percpu_counter_destroy(&fs_info->dirty_metadata_bytes);
 	percpu_counter_destroy(&fs_info->delalloc_bytes);
 	percpu_counter_destroy(&fs_info->ordered_bytes);
+	if (percpu_counter_initialized(em_counter))
+		ASSERT(percpu_counter_sum_positive(em_counter) == 0);
+	percpu_counter_destroy(em_counter);
 	percpu_counter_destroy(&fs_info->dev_replace.bio_counter);
 	btrfs_free_csum_hash(fs_info);
 	btrfs_free_stripe_hash_table(fs_info);
@@ -2584,7 +2588,7 @@ static int load_super_root(struct btrfs_root *root, u64 bytenr, u64 gen, int lev
 	struct btrfs_tree_parent_check check = {
 		.level = level,
 		.transid = gen,
-		.owner_root = root->root_key.objectid
+		.owner_root = btrfs_root_id(root)
 	};
 	int ret = 0;
 
@@ -2848,6 +2852,10 @@ static int init_mount_fs_info(struct btrfs_fs_info *fs_info, struct super_block
 	if (ret)
 		return ret;
 
+	ret = percpu_counter_init(&fs_info->evictable_extent_maps, 0, GFP_KERNEL);
+	if (ret)
+		return ret;
+
 	ret = percpu_counter_init(&fs_info->dirty_metadata_bytes, 0, GFP_KERNEL);
 	if (ret)
 		return ret;
@@ -2930,7 +2938,7 @@ static int btrfs_cleanup_fs_roots(struct btrfs_fs_info *fs_info)
 			spin_unlock(&fs_info->fs_roots_radix_lock);
 			break;
 		}
-		root_objectid = gang[ret - 1]->root_key.objectid + 1;
+		root_objectid = btrfs_root_id(gang[ret - 1]) + 1;
 
 		for (i = 0; i < ret; i++) {
 			/* Avoid to grab roots in dead_roots. */
@@ -2946,7 +2954,7 @@ static int btrfs_cleanup_fs_roots(struct btrfs_fs_info *fs_info)
 		for (i = 0; i < ret; i++) {
 			if (!gang[i])
 				continue;
-			root_objectid = gang[i]->root_key.objectid;
+			root_objectid = btrfs_root_id(gang[i]);
 			err = btrfs_orphan_cleanup(gang[i]);
 			if (err)
 				goto out;
@@ -3618,28 +3626,25 @@ ALLOW_ERROR_INJECTION(open_ctree, ERRNO);
 static void btrfs_end_super_write(struct bio *bio)
 {
 	struct btrfs_device *device = bio->bi_private;
-	struct bio_vec *bvec;
-	struct bvec_iter_all iter_all;
-	struct page *page;
-
-	bio_for_each_segment_all(bvec, bio, iter_all) {
-		page = bvec->bv_page;
+	struct folio_iter fi;
 
+	bio_for_each_folio_all(fi, bio) {
 		if (bio->bi_status) {
 			btrfs_warn_rl_in_rcu(device->fs_info,
-				"lost page write due to IO error on %s (%d)",
+				"lost super block write due to IO error on %s (%d)",
 				btrfs_dev_name(device),
 				blk_status_to_errno(bio->bi_status));
-			ClearPageUptodate(page);
-			SetPageError(page);
 			btrfs_dev_stat_inc_and_print(device,
 						     BTRFS_DEV_STAT_WRITE_ERRS);
-		} else {
-			SetPageUptodate(page);
+			/* Ensure failure if the primary sb fails. */
+			if (bio->bi_opf & REQ_FUA)
+				atomic_add(BTRFS_SUPER_PRIMARY_WRITE_ERROR,
+					   &device->sb_write_errors);
+			else
+				atomic_inc(&device->sb_write_errors);
 		}
-
-		put_page(page);
-		unlock_page(page);
+		folio_unlock(fi.folio);
+		folio_put(fi.folio);
 	}
 
 	bio_put(bio);
@@ -3726,13 +3731,13 @@ struct btrfs_super_block *btrfs_read_dev_super(struct block_device *bdev)
 
 /*
  * Write superblock @sb to the @device. Do not wait for completion, all the
- * pages we use for writing are locked.
+ * folios we use for writing are locked.
  *
  * Write @max_mirrors copies of the superblock, where 0 means default that fit
  * the expected device size at commit time. Note that max_mirrors must be
  * same for write and wait phases.
  *
- * Return number of errors when page is not found or submission fails.
+ * Return number of errors when folio is not found or submission fails.
  */
 static int write_dev_supers(struct btrfs_device *device,
 			    struct btrfs_super_block *sb, int max_mirrors)
@@ -3741,19 +3746,21 @@ static int write_dev_supers(struct btrfs_device *device,
 	struct address_space *mapping = device->bdev->bd_inode->i_mapping;
 	SHASH_DESC_ON_STACK(shash, fs_info->csum_shash);
 	int i;
-	int errors = 0;
 	int ret;
 	u64 bytenr, bytenr_orig;
 
+	atomic_set(&device->sb_write_errors, 0);
+
 	if (max_mirrors == 0)
 		max_mirrors = BTRFS_SUPER_MIRROR_MAX;
 
 	shash->tfm = fs_info->csum_shash;
 
 	for (i = 0; i < max_mirrors; i++) {
-		struct page *page;
+		struct folio *folio;
 		struct bio *bio;
 		struct btrfs_super_block *disk_super;
+		size_t offset;
 
 		bytenr_orig = btrfs_sb_offset(i);
 		ret = btrfs_sb_log_location(device, i, WRITE, &bytenr);
@@ -3763,7 +3770,7 @@ static int write_dev_supers(struct btrfs_device *device,
 			btrfs_err(device->fs_info,
 				"couldn't get super block location for mirror %d",
 				i);
-			errors++;
+			atomic_inc(&device->sb_write_errors);
 			continue;
 		}
 		if (bytenr + BTRFS_SUPER_INFO_SIZE >=
@@ -3776,20 +3783,20 @@ static int write_dev_supers(struct btrfs_device *device,
 				    BTRFS_SUPER_INFO_SIZE - BTRFS_CSUM_SIZE,
 				    sb->csum);
 
-		page = find_or_create_page(mapping, bytenr >> PAGE_SHIFT,
-					   GFP_NOFS);
-		if (!page) {
+		folio = __filemap_get_folio(mapping, bytenr >> PAGE_SHIFT,
+					    FGP_LOCK | FGP_ACCESSED | FGP_CREAT,
+					    GFP_NOFS);
+		if (IS_ERR(folio)) {
 			btrfs_err(device->fs_info,
 			    "couldn't get super block page for bytenr %llu",
 			    bytenr);
-			errors++;
+			atomic_inc(&device->sb_write_errors);
 			continue;
 		}
+		ASSERT(folio_order(folio) == 0);
 
-		/* Bump the refcount for wait_dev_supers() */
-		get_page(page);
-
-		disk_super = page_address(page);
+		offset = offset_in_folio(folio, bytenr);
+		disk_super = folio_address(folio) + offset;
 		memcpy(disk_super, sb, BTRFS_SUPER_INFO_SIZE);
 
 		/*
@@ -3803,8 +3810,7 @@ static int write_dev_supers(struct btrfs_device *device,
 		bio->bi_iter.bi_sector = bytenr >> SECTOR_SHIFT;
 		bio->bi_private = device;
 		bio->bi_end_io = btrfs_end_super_write;
-		__bio_add_page(bio, page, BTRFS_SUPER_INFO_SIZE,
-			       offset_in_page(bytenr));
+		bio_add_folio_nofail(bio, folio, BTRFS_SUPER_INFO_SIZE, offset);
 
 		/*
 		 * We FUA only the first super block.  The others we allow to
@@ -3816,17 +3822,17 @@ static int write_dev_supers(struct btrfs_device *device,
 		submit_bio(bio);
 
 		if (btrfs_advance_sb_log(device, i))
-			errors++;
+			atomic_inc(&device->sb_write_errors);
 	}
-	return errors < i ? 0 : -1;
+	return atomic_read(&device->sb_write_errors) < i ? 0 : -1;
 }
 
 /*
  * Wait for write completion of superblocks done by write_dev_supers,
  * @max_mirrors same for write and wait phases.
  *
- * Return number of errors when page is not found or not marked up to
- * date.
+ * Return -1 if primary super block write failed or when there were no super block
+ * copies written. Otherwise 0.
  */
 static int wait_dev_supers(struct btrfs_device *device, int max_mirrors)
 {
@@ -3840,7 +3846,7 @@ static int wait_dev_supers(struct btrfs_device *device, int max_mirrors)
 		max_mirrors = BTRFS_SUPER_MIRROR_MAX;
 
 	for (i = 0; i < max_mirrors; i++) {
-		struct page *page;
+		struct folio *folio;
 
 		ret = btrfs_sb_log_location(device, i, READ, &bytenr);
 		if (ret == -ENOENT) {
@@ -3855,30 +3861,21 @@ static int wait_dev_supers(struct btrfs_device *device, int max_mirrors)
 		    device->commit_total_bytes)
 			break;
 
-		page = find_get_page(device->bdev->bd_inode->i_mapping,
-				     bytenr >> PAGE_SHIFT);
-		if (!page) {
-			errors++;
-			if (i == 0)
-				primary_failed = true;
+		folio = filemap_get_folio(device->bdev->bd_inode->i_mapping,
+					  bytenr >> PAGE_SHIFT);
+		/* If the folio has been removed, then we know it completed. */
+		if (IS_ERR(folio))
 			continue;
-		}
-		/* Page is submitted locked and unlocked once the IO completes */
-		wait_on_page_locked(page);
-		if (PageError(page)) {
-			errors++;
-			if (i == 0)
-				primary_failed = true;
-		}
-
-		/* Drop our reference */
-		put_page(page);
+		ASSERT(folio_order(folio) == 0);
 
-		/* Drop the reference from the writing run */
-		put_page(page);
+		/* Folio will be unlocked once the write completes. */
+		folio_wait_locked(folio);
+		folio_put(folio);
 	}
 
-	/* log error, force error return */
+	errors += atomic_read(&device->sb_write_errors);
+	if (errors >= BTRFS_SUPER_PRIMARY_WRITE_ERROR)
+		primary_failed = true;
 	if (primary_failed) {
 		btrfs_err(device->fs_info, "error writing primary super block to device %llu",
 			  device->devid);
@@ -4139,7 +4136,7 @@ void btrfs_drop_and_free_fs_root(struct btrfs_fs_info *fs_info,
 
 	spin_lock(&fs_info->fs_roots_radix_lock);
 	radix_tree_delete(&fs_info->fs_roots_radix,
-			  (unsigned long)root->root_key.objectid);
+			  (unsigned long)btrfs_root_id(root));
 	if (test_and_clear_bit(BTRFS_ROOT_IN_RADIX, &root->state))
 		drop_ref = true;
 	spin_unlock(&fs_info->fs_roots_radix_lock);
@@ -4182,9 +4179,6 @@ static void warn_about_uncommitted_trans(struct btrfs_fs_info *fs_info)
 	struct btrfs_transaction *tmp;
 	bool found = false;
 
-	if (list_empty(&fs_info->trans_list))
-		return;
-
 	/*
 	 * This function is only called at the very end of close_ctree(),
 	 * thus no other running transaction, no need to take trans_lock.
@@ -4484,7 +4478,7 @@ static void btrfs_drop_all_logs(struct btrfs_fs_info *fs_info)
 		for (i = 0; i < ret; i++) {
 			if (!gang[i])
 				continue;
-			root_objectid = gang[i]->root_key.objectid;
+			root_objectid = btrfs_root_id(gang[i]);
 			btrfs_free_log(NULL, gang[i]);
 			btrfs_put_root(gang[i]);
 		}
@@ -4815,7 +4809,7 @@ static void btrfs_free_all_qgroup_pertrans(struct btrfs_fs_info *fs_info)
 
 			btrfs_qgroup_free_meta_all_pertrans(root);
 			radix_tree_tag_clear(&fs_info->fs_roots_radix,
-					(unsigned long)root->root_key.objectid,
+					(unsigned long)btrfs_root_id(root),
 					BTRFS_ROOT_TRANS_TAG);
 		}
 	}
@@ -4844,14 +4838,10 @@ void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans,
 	cur_trans->state = TRANS_STATE_UNBLOCKED;
 	wake_up(&fs_info->transaction_wait);
 
-	btrfs_destroy_delayed_inodes(fs_info);
-
 	btrfs_destroy_marked_extents(fs_info, &cur_trans->dirty_pages,
 				     EXTENT_DIRTY);
 	btrfs_destroy_pinned_extent(fs_info, &cur_trans->pinned_extents);
 
-	btrfs_free_all_qgroup_pertrans(fs_info);
-
 	cur_trans->state =TRANS_STATE_COMPLETED;
 	wake_up(&cur_trans->commit_wait);
 }
@@ -4904,6 +4894,7 @@ static int btrfs_cleanup_transaction(struct btrfs_fs_info *fs_info)
 	btrfs_assert_delayed_root_empty(fs_info);
 	btrfs_destroy_all_delalloc_inodes(fs_info);
 	btrfs_drop_all_logs(fs_info);
+	btrfs_free_all_qgroup_pertrans(fs_info);
 	mutex_unlock(&fs_info->transaction_kthread_mutex);
 
 	return 0;
@@ -4959,7 +4950,7 @@ int btrfs_get_free_objectid(struct btrfs_root *root, u64 *objectid)
 	if (unlikely(root->free_objectid >= BTRFS_LAST_FREE_OBJECTID)) {
 		btrfs_warn(root->fs_info,
 			   "the objectid of root %llu reaches its highest value",
-			   root->root_key.objectid);
+			   btrfs_root_id(root));
 		ret = -ENOSPC;
 		goto out;
 	}
diff --git a/fs/btrfs/export.c b/fs/btrfs/export.c
index 8398d345ec5b..9e81f89e76d8 100644
--- a/fs/btrfs/export.c
+++ b/fs/btrfs/export.c
@@ -34,7 +34,7 @@ static int btrfs_encode_fh(struct inode *inode, u32 *fh, int *max_len,
 	type = FILEID_BTRFS_WITHOUT_PARENT;
 
 	fid->objectid = btrfs_ino(BTRFS_I(inode));
-	fid->root_objectid = BTRFS_I(inode)->root->root_key.objectid;
+	fid->root_objectid = btrfs_root_id(BTRFS_I(inode)->root);
 	fid->gen = inode->i_generation;
 
 	if (parent) {
@@ -42,7 +42,7 @@ static int btrfs_encode_fh(struct inode *inode, u32 *fh, int *max_len,
 
 		fid->parent_objectid = BTRFS_I(parent)->location.objectid;
 		fid->parent_gen = parent->i_generation;
-		parent_root_id = BTRFS_I(parent)->root->root_key.objectid;
+		parent_root_id = btrfs_root_id(BTRFS_I(parent)->root);
 
 		if (parent_root_id != fid->root_objectid) {
 			fid->parent_root_objectid = parent_root_id;
@@ -160,7 +160,7 @@ struct dentry *btrfs_get_parent(struct dentry *child)
 		return ERR_PTR(-ENOMEM);
 
 	if (btrfs_ino(BTRFS_I(dir)) == BTRFS_FIRST_FREE_OBJECTID) {
-		key.objectid = root->root_key.objectid;
+		key.objectid = btrfs_root_id(root);
 		key.type = BTRFS_ROOT_BACKREF_KEY;
 		key.offset = (u64)-1;
 		root = fs_info->tree_root;
@@ -243,7 +243,7 @@ static int btrfs_get_name(struct dentry *parent, char *name,
 		return -ENOMEM;
 
 	if (ino == BTRFS_FIRST_FREE_OBJECTID) {
-		key.objectid = BTRFS_I(inode)->root->root_key.objectid;
+		key.objectid = btrfs_root_id(BTRFS_I(inode)->root);
 		key.type = BTRFS_ROOT_BACKREF_KEY;
 		key.offset = (u64)-1;
 		root = fs_info->tree_root;
diff --git a/fs/btrfs/extent-io-tree.c b/fs/btrfs/extent-io-tree.c
index c09b428823d7..ed2cfc3d5d8a 100644
--- a/fs/btrfs/extent-io-tree.c
+++ b/fs/btrfs/extent-io-tree.c
@@ -1059,7 +1059,7 @@ static int __set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 	struct extent_state *prealloc = NULL;
 	struct rb_node **p = NULL;
 	struct rb_node *parent = NULL;
-	int err = 0;
+	int ret = 0;
 	u64 last_start;
 	u64 last_end;
 	u32 exclusive_bits = (bits & EXTENT_LOCKED);
@@ -1122,7 +1122,7 @@ hit_next:
 		if (state->state & exclusive_bits) {
 			*failed_start = state->start;
 			cache_state(state, failed_state);
-			err = -EEXIST;
+			ret = -EEXIST;
 			goto out;
 		}
 
@@ -1158,7 +1158,7 @@ hit_next:
 		if (state->state & exclusive_bits) {
 			*failed_start = start;
 			cache_state(state, failed_state);
-			err = -EEXIST;
+			ret = -EEXIST;
 			goto out;
 		}
 
@@ -1175,12 +1175,12 @@ hit_next:
 		prealloc = alloc_extent_state_atomic(prealloc);
 		if (!prealloc)
 			goto search_again;
-		err = split_state(tree, state, prealloc, start);
-		if (err)
-			extent_io_tree_panic(tree, state, "split", err);
+		ret = split_state(tree, state, prealloc, start);
+		if (ret)
+			extent_io_tree_panic(tree, state, "split", ret);
 
 		prealloc = NULL;
-		if (err)
+		if (ret)
 			goto out;
 		if (state->end <= end) {
 			set_state_bits(tree, state, bits, changeset);
@@ -1224,8 +1224,8 @@ hit_next:
 		prealloc->end = this_end;
 		inserted_state = insert_state(tree, prealloc, bits, changeset);
 		if (IS_ERR(inserted_state)) {
-			err = PTR_ERR(inserted_state);
-			extent_io_tree_panic(tree, prealloc, "insert", err);
+			ret = PTR_ERR(inserted_state);
+			extent_io_tree_panic(tree, prealloc, "insert", ret);
 		}
 
 		cache_state(inserted_state, cached_state);
@@ -1244,16 +1244,16 @@ hit_next:
 		if (state->state & exclusive_bits) {
 			*failed_start = start;
 			cache_state(state, failed_state);
-			err = -EEXIST;
+			ret = -EEXIST;
 			goto out;
 		}
 
 		prealloc = alloc_extent_state_atomic(prealloc);
 		if (!prealloc)
 			goto search_again;
-		err = split_state(tree, state, prealloc, end + 1);
-		if (err)
-			extent_io_tree_panic(tree, state, "split", err);
+		ret = split_state(tree, state, prealloc, end + 1);
+		if (ret)
+			extent_io_tree_panic(tree, state, "split", ret);
 
 		set_state_bits(tree, prealloc, bits, changeset);
 		cache_state(prealloc, cached_state);
@@ -1275,7 +1275,7 @@ out:
 	if (prealloc)
 		free_extent_state(prealloc);
 
-	return err;
+	return ret;
 
 }
 
@@ -1312,7 +1312,7 @@ int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 	struct extent_state *prealloc = NULL;
 	struct rb_node **p = NULL;
 	struct rb_node *parent = NULL;
-	int err = 0;
+	int ret = 0;
 	u64 last_start;
 	u64 last_end;
 	bool first_iteration = true;
@@ -1351,7 +1351,7 @@ again:
 	if (!state) {
 		prealloc = alloc_extent_state_atomic(prealloc);
 		if (!prealloc) {
-			err = -ENOMEM;
+			ret = -ENOMEM;
 			goto out;
 		}
 		prealloc->start = start;
@@ -1402,14 +1402,14 @@ hit_next:
 	if (state->start < start) {
 		prealloc = alloc_extent_state_atomic(prealloc);
 		if (!prealloc) {
-			err = -ENOMEM;
+			ret = -ENOMEM;
 			goto out;
 		}
-		err = split_state(tree, state, prealloc, start);
-		if (err)
-			extent_io_tree_panic(tree, state, "split", err);
+		ret = split_state(tree, state, prealloc, start);
+		if (ret)
+			extent_io_tree_panic(tree, state, "split", ret);
 		prealloc = NULL;
-		if (err)
+		if (ret)
 			goto out;
 		if (state->end <= end) {
 			set_state_bits(tree, state, bits, NULL);
@@ -1442,7 +1442,7 @@ hit_next:
 
 		prealloc = alloc_extent_state_atomic(prealloc);
 		if (!prealloc) {
-			err = -ENOMEM;
+			ret = -ENOMEM;
 			goto out;
 		}
 
@@ -1454,8 +1454,8 @@ hit_next:
 		prealloc->end = this_end;
 		inserted_state = insert_state(tree, prealloc, bits, NULL);
 		if (IS_ERR(inserted_state)) {
-			err = PTR_ERR(inserted_state);
-			extent_io_tree_panic(tree, prealloc, "insert", err);
+			ret = PTR_ERR(inserted_state);
+			extent_io_tree_panic(tree, prealloc, "insert", ret);
 		}
 		cache_state(inserted_state, cached_state);
 		if (inserted_state == prealloc)
@@ -1472,13 +1472,13 @@ hit_next:
 	if (state->start <= end && state->end > end) {
 		prealloc = alloc_extent_state_atomic(prealloc);
 		if (!prealloc) {
-			err = -ENOMEM;
+			ret = -ENOMEM;
 			goto out;
 		}
 
-		err = split_state(tree, state, prealloc, end + 1);
-		if (err)
-			extent_io_tree_panic(tree, state, "split", err);
+		ret = split_state(tree, state, prealloc, end + 1);
+		if (ret)
+			extent_io_tree_panic(tree, state, "split", ret);
 
 		set_state_bits(tree, prealloc, bits, NULL);
 		cache_state(prealloc, cached_state);
@@ -1500,7 +1500,7 @@ out:
 	if (prealloc)
 		free_extent_state(prealloc);
 
-	return err;
+	return ret;
 }
 
 /*
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 257d044bca91..47d48233b592 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -46,9 +46,7 @@
 
 static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
 			       struct btrfs_delayed_ref_head *href,
-			       struct btrfs_delayed_ref_node *node, u64 parent,
-			       u64 root_objectid, u64 owner_objectid,
-			       u64 owner_offset,
+			       struct btrfs_delayed_ref_node *node,
 			       struct btrfs_delayed_extent_op *extra_op);
 static void __run_delayed_extent_op(struct btrfs_delayed_extent_op *extent_op,
 				    struct extent_buffer *leaf,
@@ -448,9 +446,8 @@ static noinline int lookup_extent_data_ref(struct btrfs_trans_handle *trans,
 	struct btrfs_extent_data_ref *ref;
 	struct extent_buffer *leaf;
 	u32 nritems;
-	int ret;
 	int recow;
-	int err = -ENOENT;
+	int ret;
 
 	key.objectid = bytenr;
 	if (parent) {
@@ -464,26 +461,26 @@ static noinline int lookup_extent_data_ref(struct btrfs_trans_handle *trans,
 again:
 	recow = 0;
 	ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
-	if (ret < 0) {
-		err = ret;
-		goto fail;
-	}
+	if (ret < 0)
+		return ret;
 
 	if (parent) {
-		if (!ret)
-			return 0;
-		goto fail;
+		if (ret)
+			return -ENOENT;
+		return 0;
 	}
 
+	ret = -ENOENT;
 	leaf = path->nodes[0];
 	nritems = btrfs_header_nritems(leaf);
 	while (1) {
 		if (path->slots[0] >= nritems) {
 			ret = btrfs_next_leaf(root, path);
-			if (ret < 0)
-				err = ret;
-			if (ret)
-				goto fail;
+			if (ret) {
+				if (ret > 1)
+					return -ENOENT;
+				return ret;
+			}
 
 			leaf = path->nodes[0];
 			nritems = btrfs_header_nritems(leaf);
@@ -504,37 +501,37 @@ again:
 				btrfs_release_path(path);
 				goto again;
 			}
-			err = 0;
+			ret = 0;
 			break;
 		}
 		path->slots[0]++;
 	}
 fail:
-	return err;
+	return ret;
 }
 
 static noinline int insert_extent_data_ref(struct btrfs_trans_handle *trans,
 					   struct btrfs_path *path,
-					   u64 bytenr, u64 parent,
-					   u64 root_objectid, u64 owner,
-					   u64 offset, int refs_to_add)
+					   struct btrfs_delayed_ref_node *node,
+					   u64 bytenr)
 {
 	struct btrfs_root *root = btrfs_extent_root(trans->fs_info, bytenr);
 	struct btrfs_key key;
 	struct extent_buffer *leaf;
+	u64 owner = btrfs_delayed_ref_owner(node);
+	u64 offset = btrfs_delayed_ref_offset(node);
 	u32 size;
 	u32 num_refs;
 	int ret;
 
 	key.objectid = bytenr;
-	if (parent) {
+	if (node->parent) {
 		key.type = BTRFS_SHARED_DATA_REF_KEY;
-		key.offset = parent;
+		key.offset = node->parent;
 		size = sizeof(struct btrfs_shared_data_ref);
 	} else {
 		key.type = BTRFS_EXTENT_DATA_REF_KEY;
-		key.offset = hash_extent_data_ref(root_objectid,
-						  owner, offset);
+		key.offset = hash_extent_data_ref(node->ref_root, owner, offset);
 		size = sizeof(struct btrfs_extent_data_ref);
 	}
 
@@ -543,15 +540,15 @@ static noinline int insert_extent_data_ref(struct btrfs_trans_handle *trans,
 		goto fail;
 
 	leaf = path->nodes[0];
-	if (parent) {
+	if (node->parent) {
 		struct btrfs_shared_data_ref *ref;
 		ref = btrfs_item_ptr(leaf, path->slots[0],
 				     struct btrfs_shared_data_ref);
 		if (ret == 0) {
-			btrfs_set_shared_data_ref_count(leaf, ref, refs_to_add);
+			btrfs_set_shared_data_ref_count(leaf, ref, node->ref_mod);
 		} else {
 			num_refs = btrfs_shared_data_ref_count(leaf, ref);
-			num_refs += refs_to_add;
+			num_refs += node->ref_mod;
 			btrfs_set_shared_data_ref_count(leaf, ref, num_refs);
 		}
 	} else {
@@ -559,7 +556,7 @@ static noinline int insert_extent_data_ref(struct btrfs_trans_handle *trans,
 		while (ret == -EEXIST) {
 			ref = btrfs_item_ptr(leaf, path->slots[0],
 					     struct btrfs_extent_data_ref);
-			if (match_extent_data_ref(leaf, ref, root_objectid,
+			if (match_extent_data_ref(leaf, ref, node->ref_root,
 						  owner, offset))
 				break;
 			btrfs_release_path(path);
@@ -574,14 +571,13 @@ static noinline int insert_extent_data_ref(struct btrfs_trans_handle *trans,
 		ref = btrfs_item_ptr(leaf, path->slots[0],
 				     struct btrfs_extent_data_ref);
 		if (ret == 0) {
-			btrfs_set_extent_data_ref_root(leaf, ref,
-						       root_objectid);
+			btrfs_set_extent_data_ref_root(leaf, ref, node->ref_root);
 			btrfs_set_extent_data_ref_objectid(leaf, ref, owner);
 			btrfs_set_extent_data_ref_offset(leaf, ref, offset);
-			btrfs_set_extent_data_ref_count(leaf, ref, refs_to_add);
+			btrfs_set_extent_data_ref_count(leaf, ref, node->ref_mod);
 		} else {
 			num_refs = btrfs_extent_data_ref_count(leaf, ref);
-			num_refs += refs_to_add;
+			num_refs += node->ref_mod;
 			btrfs_set_extent_data_ref_count(leaf, ref, num_refs);
 		}
 	}
@@ -705,20 +701,20 @@ static noinline int lookup_tree_block_ref(struct btrfs_trans_handle *trans,
 
 static noinline int insert_tree_block_ref(struct btrfs_trans_handle *trans,
 					  struct btrfs_path *path,
-					  u64 bytenr, u64 parent,
-					  u64 root_objectid)
+					  struct btrfs_delayed_ref_node *node,
+					  u64 bytenr)
 {
 	struct btrfs_root *root = btrfs_extent_root(trans->fs_info, bytenr);
 	struct btrfs_key key;
 	int ret;
 
 	key.objectid = bytenr;
-	if (parent) {
+	if (node->parent) {
 		key.type = BTRFS_SHARED_BLOCK_REF_KEY;
-		key.offset = parent;
+		key.offset = node->parent;
 	} else {
 		key.type = BTRFS_TREE_BLOCK_REF_KEY;
-		key.offset = root_objectid;
+		key.offset = node->ref_root;
 	}
 
 	ret = btrfs_insert_empty_item(trans, root, path, &key, 0);
@@ -1439,7 +1435,7 @@ int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
 	ASSERT(generic_ref->type != BTRFS_REF_NOT_SET &&
 	       generic_ref->action);
 	BUG_ON(generic_ref->type == BTRFS_REF_METADATA &&
-	       generic_ref->tree_ref.ref_root == BTRFS_TREE_LOG_OBJECTID);
+	       generic_ref->ref_root == BTRFS_TREE_LOG_OBJECTID);
 
 	if (generic_ref->type == BTRFS_REF_METADATA)
 		ret = btrfs_add_delayed_tree_ref(trans, generic_ref, NULL);
@@ -1462,34 +1458,12 @@ int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
  * @node:	    The delayed ref node used to get the bytenr/length for
  *		    extent whose references are incremented.
  *
- * @parent:	    If this is a shared extent (BTRFS_SHARED_DATA_REF_KEY/
- *		    BTRFS_SHARED_BLOCK_REF_KEY) then it holds the logical
- *		    bytenr of the parent block. Since new extents are always
- *		    created with indirect references, this will only be the case
- *		    when relocating a shared extent. In that case, root_objectid
- *		    will be BTRFS_TREE_RELOC_OBJECTID. Otherwise, parent must
- *		    be 0
- *
- * @root_objectid:  The id of the root where this modification has originated,
- *		    this can be either one of the well-known metadata trees or
- *		    the subvolume id which references this extent.
- *
- * @owner:	    For data extents it is the inode number of the owning file.
- *		    For metadata extents this parameter holds the level in the
- *		    tree of the extent.
- *
- * @offset:	    For metadata extents the offset is ignored and is currently
- *		    always passed as 0. For data extents it is the fileoffset
- *		    this extent belongs to.
- *
  * @extent_op       Pointer to a structure, holding information necessary when
  *                  updating a tree block's flags
  *
  */
 static int __btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
 				  struct btrfs_delayed_ref_node *node,
-				  u64 parent, u64 root_objectid,
-				  u64 owner, u64 offset,
 				  struct btrfs_delayed_extent_op *extent_op)
 {
 	struct btrfs_path *path;
@@ -1498,6 +1472,8 @@ static int __btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
 	struct btrfs_key key;
 	u64 bytenr = node->bytenr;
 	u64 num_bytes = node->num_bytes;
+	u64 owner = btrfs_delayed_ref_owner(node);
+	u64 offset = btrfs_delayed_ref_offset(node);
 	u64 refs;
 	int refs_to_add = node->ref_mod;
 	int ret;
@@ -1508,7 +1484,7 @@ static int __btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
 
 	/* this will setup the path even if it fails to insert the back ref */
 	ret = insert_inline_extent_backref(trans, path, bytenr, num_bytes,
-					   parent, root_objectid, owner,
+					   node->parent, node->ref_root, owner,
 					   offset, refs_to_add, extent_op);
 	if ((ret < 0 && ret != -EAGAIN) || !ret)
 		goto out;
@@ -1531,12 +1507,9 @@ static int __btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
 
 	/* now insert the actual backref */
 	if (owner < BTRFS_FIRST_FREE_OBJECTID)
-		ret = insert_tree_block_ref(trans, path, bytenr, parent,
-					    root_objectid);
+		ret = insert_tree_block_ref(trans, path, node, bytenr);
 	else
-		ret = insert_extent_data_ref(trans, path, bytenr, parent,
-					     root_objectid, owner, offset,
-					     refs_to_add);
+		ret = insert_extent_data_ref(trans, path, node, bytenr);
 
 	if (ret)
 		btrfs_abort_transaction(trans, ret);
@@ -1569,15 +1542,13 @@ static int run_delayed_data_ref(struct btrfs_trans_handle *trans,
 				bool insert_reserved)
 {
 	int ret = 0;
-	struct btrfs_delayed_data_ref *ref;
 	u64 parent = 0;
 	u64 flags = 0;
 
-	ref = btrfs_delayed_node_to_data_ref(node);
-	trace_run_delayed_data_ref(trans->fs_info, node, ref, node->action);
+	trace_run_delayed_data_ref(trans->fs_info, node);
 
 	if (node->type == BTRFS_SHARED_DATA_REF_KEY)
-		parent = ref->parent;
+		parent = node->parent;
 
 	if (node->action == BTRFS_ADD_DELAYED_REF && insert_reserved) {
 		struct btrfs_key key;
@@ -1588,6 +1559,8 @@ static int run_delayed_data_ref(struct btrfs_trans_handle *trans,
 			.is_inc	= true,
 			.generation = trans->transid,
 		};
+		u64 owner = btrfs_delayed_ref_owner(node);
+		u64 offset = btrfs_delayed_ref_offset(node);
 
 		if (extent_op)
 			flags |= extent_op->flags_to_set;
@@ -1596,21 +1569,17 @@ static int run_delayed_data_ref(struct btrfs_trans_handle *trans,
 		key.type = BTRFS_EXTENT_ITEM_KEY;
 		key.offset = node->num_bytes;
 
-		ret = alloc_reserved_file_extent(trans, parent, ref->root,
-						 flags, ref->objectid,
-						 ref->offset, &key,
-						 node->ref_mod, href->owning_root);
+		ret = alloc_reserved_file_extent(trans, parent, node->ref_root,
+						 flags, owner, offset, &key,
+						 node->ref_mod,
+						 href->owning_root);
 		free_head_ref_squota_rsv(trans->fs_info, href);
 		if (!ret)
 			ret = btrfs_record_squota_delta(trans->fs_info, &delta);
 	} else if (node->action == BTRFS_ADD_DELAYED_REF) {
-		ret = __btrfs_inc_extent_ref(trans, node, parent, ref->root,
-					     ref->objectid, ref->offset,
-					     extent_op);
+		ret = __btrfs_inc_extent_ref(trans, node, extent_op);
 	} else if (node->action == BTRFS_DROP_DELAYED_REF) {
-		ret = __btrfs_free_extent(trans, href, node, parent,
-					  ref->root, ref->objectid,
-					  ref->offset, extent_op);
+		ret = __btrfs_free_extent(trans, href, node, extent_op);
 	} else {
 		BUG();
 	}
@@ -1732,16 +1701,14 @@ static int run_delayed_tree_ref(struct btrfs_trans_handle *trans,
 {
 	int ret = 0;
 	struct btrfs_fs_info *fs_info = trans->fs_info;
-	struct btrfs_delayed_tree_ref *ref;
 	u64 parent = 0;
 	u64 ref_root = 0;
 
-	ref = btrfs_delayed_node_to_tree_ref(node);
-	trace_run_delayed_tree_ref(trans->fs_info, node, ref, node->action);
+	trace_run_delayed_tree_ref(trans->fs_info, node);
 
 	if (node->type == BTRFS_SHARED_BLOCK_REF_KEY)
-		parent = ref->parent;
-	ref_root = ref->root;
+		parent = node->parent;
+	ref_root = node->ref_root;
 
 	if (unlikely(node->ref_mod != 1)) {
 		btrfs_err(trans->fs_info,
@@ -1764,11 +1731,9 @@ static int run_delayed_tree_ref(struct btrfs_trans_handle *trans,
 		if (!ret)
 			btrfs_record_squota_delta(fs_info, &delta);
 	} else if (node->action == BTRFS_ADD_DELAYED_REF) {
-		ret = __btrfs_inc_extent_ref(trans, node, parent, ref_root,
-					     ref->level, 0, extent_op);
+		ret = __btrfs_inc_extent_ref(trans, node, extent_op);
 	} else if (node->action == BTRFS_DROP_DELAYED_REF) {
-		ret = __btrfs_free_extent(trans, href, node, parent, ref_root,
-					  ref->level, 0, extent_op);
+		ret = __btrfs_free_extent(trans, href, node, extent_op);
 	} else {
 		BUG();
 	}
@@ -2292,7 +2257,6 @@ static noinline int check_delayed_ref(struct btrfs_root *root,
 {
 	struct btrfs_delayed_ref_head *head;
 	struct btrfs_delayed_ref_node *ref;
-	struct btrfs_delayed_data_ref *data_ref;
 	struct btrfs_delayed_ref_root *delayed_refs;
 	struct btrfs_transaction *cur_trans;
 	struct rb_node *node;
@@ -2346,6 +2310,9 @@ static noinline int check_delayed_ref(struct btrfs_root *root,
 	 */
 	for (node = rb_first_cached(&head->ref_tree); node;
 	     node = rb_next(node)) {
+		u64 ref_owner;
+		u64 ref_offset;
+
 		ref = rb_entry(node, struct btrfs_delayed_ref_node, ref_node);
 		/* If it's a shared ref we know a cross reference exists */
 		if (ref->type != BTRFS_EXTENT_DATA_REF_KEY) {
@@ -2353,15 +2320,15 @@ static noinline int check_delayed_ref(struct btrfs_root *root,
 			break;
 		}
 
-		data_ref = btrfs_delayed_node_to_data_ref(ref);
+		ref_owner = btrfs_delayed_ref_owner(ref);
+		ref_offset = btrfs_delayed_ref_offset(ref);
 
 		/*
 		 * If our ref doesn't match the one we're currently looking at
 		 * then we have a cross reference.
 		 */
-		if (data_ref->root != root->root_key.objectid ||
-		    data_ref->objectid != objectid ||
-		    data_ref->offset != offset) {
+		if (ref->ref_root != btrfs_root_id(root) ||
+		    ref_owner != objectid || ref_offset != offset) {
 			ret = 1;
 			break;
 		}
@@ -2454,8 +2421,7 @@ static noinline int check_committed_ref(struct btrfs_root *root,
 	ref = (struct btrfs_extent_data_ref *)(&iref->offset);
 	if (btrfs_extent_refs(leaf, ei) !=
 	    btrfs_extent_data_ref_count(leaf, ref) ||
-	    btrfs_extent_data_ref_root(leaf, ref) !=
-	    root->root_key.objectid ||
+	    btrfs_extent_data_ref_root(leaf, ref) != btrfs_root_id(root) ||
 	    btrfs_extent_data_ref_objectid(leaf, ref) != objectid ||
 	    btrfs_extent_data_ref_offset(leaf, ref) != offset)
 		goto out;
@@ -2492,14 +2458,11 @@ static int __btrfs_mod_ref(struct btrfs_trans_handle *trans,
 			   int full_backref, int inc)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
-	u64 bytenr;
-	u64 num_bytes;
 	u64 parent;
 	u64 ref_root;
 	u32 nritems;
 	struct btrfs_key key;
 	struct btrfs_file_extent_item *fi;
-	struct btrfs_ref generic_ref = { 0 };
 	bool for_reloc = btrfs_header_flag(buf, BTRFS_HEADER_FLAG_RELOC);
 	int i;
 	int action;
@@ -2526,6 +2489,12 @@ static int __btrfs_mod_ref(struct btrfs_trans_handle *trans,
 		action = BTRFS_DROP_DELAYED_REF;
 
 	for (i = 0; i < nritems; i++) {
+		struct btrfs_ref ref = {
+			.action = action,
+			.parent = parent,
+			.ref_root = ref_root,
+		};
+
 		if (level == 0) {
 			btrfs_item_key_to_cpu(buf, &key, i);
 			if (key.type != BTRFS_EXTENT_DATA_KEY)
@@ -2535,35 +2504,33 @@ static int __btrfs_mod_ref(struct btrfs_trans_handle *trans,
 			if (btrfs_file_extent_type(buf, fi) ==
 			    BTRFS_FILE_EXTENT_INLINE)
 				continue;
-			bytenr = btrfs_file_extent_disk_bytenr(buf, fi);
-			if (bytenr == 0)
+			ref.bytenr = btrfs_file_extent_disk_bytenr(buf, fi);
+			if (ref.bytenr == 0)
 				continue;
 
-			num_bytes = btrfs_file_extent_disk_num_bytes(buf, fi);
+			ref.num_bytes = btrfs_file_extent_disk_num_bytes(buf, fi);
+			ref.owning_root = ref_root;
+
 			key.offset -= btrfs_file_extent_offset(buf, fi);
-			btrfs_init_generic_ref(&generic_ref, action, bytenr,
-					       num_bytes, parent, ref_root);
-			btrfs_init_data_ref(&generic_ref, ref_root, key.objectid,
-					    key.offset, root->root_key.objectid,
-					    for_reloc);
+			btrfs_init_data_ref(&ref, key.objectid, key.offset,
+					    btrfs_root_id(root), for_reloc);
 			if (inc)
-				ret = btrfs_inc_extent_ref(trans, &generic_ref);
+				ret = btrfs_inc_extent_ref(trans, &ref);
 			else
-				ret = btrfs_free_extent(trans, &generic_ref);
+				ret = btrfs_free_extent(trans, &ref);
 			if (ret)
 				goto fail;
 		} else {
-			bytenr = btrfs_node_blockptr(buf, i);
-			num_bytes = fs_info->nodesize;
-			/* We don't know the owning_root, use 0. */
-			btrfs_init_generic_ref(&generic_ref, action, bytenr,
-					       num_bytes, parent, 0);
-			btrfs_init_tree_ref(&generic_ref, level - 1, ref_root,
-					    root->root_key.objectid, for_reloc);
+			/* We don't know the owning_root, leave as 0. */
+			ref.bytenr = btrfs_node_blockptr(buf, i);
+			ref.num_bytes = fs_info->nodesize;
+
+			btrfs_init_tree_ref(&ref, level - 1,
+					    btrfs_root_id(root), for_reloc);
 			if (inc)
-				ret = btrfs_inc_extent_ref(trans, &generic_ref);
+				ret = btrfs_inc_extent_ref(trans, &ref);
 			else
-				ret = btrfs_free_extent(trans, &generic_ref);
+				ret = btrfs_free_extent(trans, &ref);
 			if (ret)
 				goto fail;
 		}
@@ -3099,9 +3066,7 @@ static int do_free_extent_accounting(struct btrfs_trans_handle *trans,
  */
 static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
 			       struct btrfs_delayed_ref_head *href,
-			       struct btrfs_delayed_ref_node *node, u64 parent,
-			       u64 root_objectid, u64 owner_objectid,
-			       u64 owner_offset,
+			       struct btrfs_delayed_ref_node *node,
 			       struct btrfs_delayed_extent_op *extent_op)
 {
 	struct btrfs_fs_info *info = trans->fs_info;
@@ -3121,6 +3086,8 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
 	u64 refs;
 	u64 bytenr = node->bytenr;
 	u64 num_bytes = node->num_bytes;
+	u64 owner_objectid = btrfs_delayed_ref_owner(node);
+	u64 owner_offset = btrfs_delayed_ref_offset(node);
 	bool skinny_metadata = btrfs_fs_incompat(info, SKINNY_METADATA);
 	u64 delayed_ref_root = href->owning_root;
 
@@ -3146,7 +3113,7 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
 		skinny_metadata = false;
 
 	ret = lookup_extent_backref(trans, path, &iref, bytenr, num_bytes,
-				    parent, root_objectid, owner_objectid,
+				    node->parent, node->ref_root, owner_objectid,
 				    owner_offset);
 	if (ret == 0) {
 		/*
@@ -3248,7 +3215,7 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
 	} else if (WARN_ON(ret == -ENOENT)) {
 		abort_and_dump(trans, path,
 "unable to find ref byte nr %llu parent %llu root %llu owner %llu offset %llu slot %d",
-			       bytenr, parent, root_objectid, owner_objectid,
+			       bytenr, node->parent, node->ref_root, owner_objectid,
 			       owner_offset, path->slots[0]);
 		goto out;
 	} else {
@@ -3462,7 +3429,14 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
 	int ret;
 
 	if (root_id != BTRFS_TREE_LOG_OBJECTID) {
-		struct btrfs_ref generic_ref = { 0 };
+		struct btrfs_ref generic_ref = {
+			.action = BTRFS_DROP_DELAYED_REF,
+			.bytenr = buf->start,
+			.num_bytes = buf->len,
+			.parent = parent,
+			.owning_root = btrfs_header_owner(buf),
+			.ref_root = root_id,
+		};
 
 		/*
 		 * Assert that the extent buffer is not cleared due to
@@ -3472,11 +3446,7 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
 		 */
 		ASSERT(btrfs_header_bytenr(buf) != 0);
 
-		btrfs_init_generic_ref(&generic_ref, BTRFS_DROP_DELAYED_REF,
-				       buf->start, buf->len, parent,
-				       btrfs_header_owner(buf));
-		btrfs_init_tree_ref(&generic_ref, btrfs_header_level(buf),
-				    root_id, 0, false);
+		btrfs_init_tree_ref(&generic_ref, btrfs_header_level(buf), 0, false);
 		btrfs_ref_tree_mod(fs_info, &generic_ref);
 		ret = btrfs_add_delayed_tree_ref(trans, &generic_ref, NULL);
 		BUG_ON(ret); /* -ENOMEM */
@@ -3555,11 +3525,8 @@ int btrfs_free_extent(struct btrfs_trans_handle *trans, struct btrfs_ref *ref)
 	 * tree log blocks never actually go into the extent allocation
 	 * tree, just update pinning info and exit early.
 	 */
-	if ((ref->type == BTRFS_REF_METADATA &&
-	     ref->tree_ref.ref_root == BTRFS_TREE_LOG_OBJECTID) ||
-	    (ref->type == BTRFS_REF_DATA &&
-	     ref->data_ref.ref_root == BTRFS_TREE_LOG_OBJECTID)) {
-		btrfs_pin_extent(trans, ref->bytenr, ref->len, 1);
+	if (ref->ref_root == BTRFS_TREE_LOG_OBJECTID) {
+		btrfs_pin_extent(trans, ref->bytenr, ref->num_bytes, 1);
 		ret = 0;
 	} else if (ref->type == BTRFS_REF_METADATA) {
 		ret = btrfs_add_delayed_tree_ref(trans, ref, NULL);
@@ -3567,10 +3534,7 @@ int btrfs_free_extent(struct btrfs_trans_handle *trans, struct btrfs_ref *ref)
 		ret = btrfs_add_delayed_data_ref(trans, ref, 0);
 	}
 
-	if (!((ref->type == BTRFS_REF_METADATA &&
-	       ref->tree_ref.ref_root == BTRFS_TREE_LOG_OBJECTID) ||
-	      (ref->type == BTRFS_REF_DATA &&
-	       ref->data_ref.ref_root == BTRFS_TREE_LOG_OBJECTID)))
+	if (ref->ref_root != BTRFS_TREE_LOG_OBJECTID)
 		btrfs_ref_tree_mod(fs_info, ref);
 
 	return ret;
@@ -4705,7 +4669,7 @@ int btrfs_reserve_extent(struct btrfs_root *root, u64 ram_bytes,
 	bool final_tried = num_bytes == min_alloc_size;
 	u64 flags;
 	int ret;
-	bool for_treelog = (root->root_key.objectid == BTRFS_TREE_LOG_OBJECTID);
+	bool for_treelog = (btrfs_root_id(root) == BTRFS_TREE_LOG_OBJECTID);
 	bool for_data_reloc = (btrfs_is_data_reloc_root(root) && is_data);
 
 	flags = get_alloc_profile_by_root(root, is_data);
@@ -4899,16 +4863,16 @@ static int alloc_reserved_tree_block(struct btrfs_trans_handle *trans,
 	struct btrfs_extent_inline_ref *iref;
 	struct btrfs_path *path;
 	struct extent_buffer *leaf;
-	struct btrfs_delayed_tree_ref *ref;
 	u32 size = sizeof(*extent_item) + sizeof(*iref);
 	u64 flags = extent_op->flags_to_set;
+	/* The owner of a tree block is the level. */
+	int level = btrfs_delayed_ref_owner(node);
 	bool skinny_metadata = btrfs_fs_incompat(fs_info, SKINNY_METADATA);
 
-	ref = btrfs_delayed_node_to_tree_ref(node);
-
 	extent_key.objectid = node->bytenr;
 	if (skinny_metadata) {
-		extent_key.offset = ref->level;
+		/* The owner of a tree block is the level. */
+		extent_key.offset = level;
 		extent_key.type = BTRFS_METADATA_ITEM_KEY;
 	} else {
 		extent_key.offset = node->num_bytes;
@@ -4941,18 +4905,18 @@ static int alloc_reserved_tree_block(struct btrfs_trans_handle *trans,
 	} else {
 		block_info = (struct btrfs_tree_block_info *)(extent_item + 1);
 		btrfs_set_tree_block_key(leaf, block_info, &extent_op->key);
-		btrfs_set_tree_block_level(leaf, block_info, ref->level);
+		btrfs_set_tree_block_level(leaf, block_info, level);
 		iref = (struct btrfs_extent_inline_ref *)(block_info + 1);
 	}
 
 	if (node->type == BTRFS_SHARED_BLOCK_REF_KEY) {
 		btrfs_set_extent_inline_ref_type(leaf, iref,
 						 BTRFS_SHARED_BLOCK_REF_KEY);
-		btrfs_set_extent_inline_ref_offset(leaf, iref, ref->parent);
+		btrfs_set_extent_inline_ref_offset(leaf, iref, node->parent);
 	} else {
 		btrfs_set_extent_inline_ref_type(leaf, iref,
 						 BTRFS_TREE_BLOCK_REF_KEY);
-		btrfs_set_extent_inline_ref_offset(leaf, iref, ref->root);
+		btrfs_set_extent_inline_ref_offset(leaf, iref, node->ref_root);
 	}
 
 	btrfs_mark_buffer_dirty(trans, leaf);
@@ -4966,19 +4930,20 @@ int btrfs_alloc_reserved_file_extent(struct btrfs_trans_handle *trans,
 				     u64 offset, u64 ram_bytes,
 				     struct btrfs_key *ins)
 {
-	struct btrfs_ref generic_ref = { 0 };
-	u64 root_objectid = root->root_key.objectid;
-	u64 owning_root = root_objectid;
+	struct btrfs_ref generic_ref = {
+		.action = BTRFS_ADD_DELAYED_EXTENT,
+		.bytenr = ins->objectid,
+		.num_bytes = ins->offset,
+		.owning_root = btrfs_root_id(root),
+		.ref_root = btrfs_root_id(root),
+	};
 
-	ASSERT(root_objectid != BTRFS_TREE_LOG_OBJECTID);
+	ASSERT(generic_ref.ref_root != BTRFS_TREE_LOG_OBJECTID);
 
 	if (btrfs_is_data_reloc_root(root) && is_fstree(root->relocation_src_root))
-		owning_root = root->relocation_src_root;
+		generic_ref.owning_root = root->relocation_src_root;
 
-	btrfs_init_generic_ref(&generic_ref, BTRFS_ADD_DELAYED_EXTENT,
-			       ins->objectid, ins->offset, 0, owning_root);
-	btrfs_init_data_ref(&generic_ref, root_objectid, owner,
-			    offset, 0, false);
+	btrfs_init_data_ref(&generic_ref, owner, offset, 0, false);
 	btrfs_ref_tree_mod(root->fs_info, &generic_ref);
 
 	return btrfs_add_delayed_data_ref(trans, &generic_ref, ram_bytes);
@@ -5101,7 +5066,7 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 	 */
 	btrfs_set_buffer_lockdep_class(lockdep_owner, buf, level);
 
-	__btrfs_tree_lock(buf, nest);
+	btrfs_tree_lock_nested(buf, nest);
 	btrfs_clear_buffer_dirty(trans, buf);
 	clear_bit(EXTENT_BUFFER_STALE, &buf->bflags);
 	clear_bit(EXTENT_BUFFER_ZONED_ZEROOUT, &buf->bflags);
@@ -5116,7 +5081,7 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 	btrfs_set_header_owner(buf, owner);
 	write_extent_buffer_fsid(buf, fs_info->fs_devices->metadata_uuid);
 	write_extent_buffer_chunk_tree_uuid(buf, fs_info->chunk_tree_uuid);
-	if (root->root_key.objectid == BTRFS_TREE_LOG_OBJECTID) {
+	if (btrfs_root_id(root) == BTRFS_TREE_LOG_OBJECTID) {
 		buf->log_index = root->log_transid % 2;
 		/*
 		 * we allow two log transactions at a time, use different
@@ -5157,7 +5122,6 @@ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans,
 	struct btrfs_block_rsv *block_rsv;
 	struct extent_buffer *buf;
 	struct btrfs_delayed_extent_op *extent_op;
-	struct btrfs_ref generic_ref = { 0 };
 	u64 flags = 0;
 	int ret;
 	u32 blocksize = fs_info->nodesize;
@@ -5200,6 +5164,14 @@ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans,
 		BUG_ON(parent > 0);
 
 	if (root_objectid != BTRFS_TREE_LOG_OBJECTID) {
+		struct btrfs_ref generic_ref = {
+			.action = BTRFS_ADD_DELAYED_EXTENT,
+			.bytenr = ins.objectid,
+			.num_bytes = ins.offset,
+			.parent = parent,
+			.owning_root = owning_root,
+			.ref_root = root_objectid,
+		};
 		extent_op = btrfs_alloc_delayed_extent_op();
 		if (!extent_op) {
 			ret = -ENOMEM;
@@ -5214,10 +5186,7 @@ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans,
 		extent_op->update_flags = true;
 		extent_op->level = level;
 
-		btrfs_init_generic_ref(&generic_ref, BTRFS_ADD_DELAYED_EXTENT,
-				       ins.objectid, ins.offset, parent, owning_root);
-		btrfs_init_tree_ref(&generic_ref, level, root_objectid,
-				    root->root_key.objectid, false);
+		btrfs_init_tree_ref(&generic_ref, level, btrfs_root_id(root), false);
 		btrfs_ref_tree_mod(fs_info, &generic_ref);
 		ret = btrfs_add_delayed_tree_ref(trans, &generic_ref, extent_op);
 		if (ret)
@@ -5355,8 +5324,7 @@ static noinline int walk_down_proc(struct btrfs_trans_handle *trans,
 	u64 flag = BTRFS_BLOCK_FLAG_FULL_BACKREF;
 	int ret;
 
-	if (wc->stage == UPDATE_BACKREF &&
-	    btrfs_header_owner(eb) != root->root_key.objectid)
+	if (wc->stage == UPDATE_BACKREF && btrfs_header_owner(eb) != btrfs_root_id(root))
 		return 1;
 
 	/*
@@ -5430,7 +5398,7 @@ static int check_ref_exists(struct btrfs_trans_handle *trans,
 
 	ret = lookup_extent_backref(trans, path, &iref, bytenr,
 				    root->fs_info->nodesize, parent,
-				    root->root_key.objectid, level, 0);
+				    btrfs_root_id(root), level, 0);
 	btrfs_free_path(path);
 	if (ret == -ENOENT)
 		return 0;
@@ -5460,11 +5428,9 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans,
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	u64 bytenr;
 	u64 generation;
-	u64 parent;
 	u64 owner_root = 0;
 	struct btrfs_tree_parent_check check = { 0 };
 	struct btrfs_key key;
-	struct btrfs_ref ref = { 0 };
 	struct extent_buffer *next;
 	int level = wc->level;
 	int reada = 0;
@@ -5488,7 +5454,7 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans,
 
 	check.level = level - 1;
 	check.transid = generation;
-	check.owner_root = root->root_key.objectid;
+	check.owner_root = btrfs_root_id(root);
 	check.has_first_key = true;
 	btrfs_node_key_to_cpu(path->nodes[level], &check.first_key,
 			      path->slots[level]);
@@ -5496,7 +5462,7 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans,
 	next = find_extent_buffer(fs_info, bytenr);
 	if (!next) {
 		next = btrfs_find_create_tree_block(fs_info, bytenr,
-				root->root_key.objectid, level - 1);
+				btrfs_root_id(root), level - 1);
 		if (IS_ERR(next))
 			return PTR_ERR(next);
 		reada = 1;
@@ -5581,19 +5547,25 @@ skip:
 	wc->refs[level - 1] = 0;
 	wc->flags[level - 1] = 0;
 	if (wc->stage == DROP_REFERENCE) {
+		struct btrfs_ref ref = {
+			.action = BTRFS_DROP_DELAYED_REF,
+			.bytenr = bytenr,
+			.num_bytes = fs_info->nodesize,
+			.owning_root = owner_root,
+			.ref_root = btrfs_root_id(root),
+		};
 		if (wc->flags[level] & BTRFS_BLOCK_FLAG_FULL_BACKREF) {
-			parent = path->nodes[level]->start;
+			ref.parent = path->nodes[level]->start;
 		} else {
-			ASSERT(root->root_key.objectid ==
+			ASSERT(btrfs_root_id(root) ==
 			       btrfs_header_owner(path->nodes[level]));
-			if (root->root_key.objectid !=
+			if (btrfs_root_id(root) !=
 			    btrfs_header_owner(path->nodes[level])) {
 				btrfs_err(root->fs_info,
 						"mismatched block owner");
 				ret = -EIO;
 				goto out_unlock;
 			}
-			parent = 0;
 		}
 
 		/*
@@ -5603,7 +5575,7 @@ skip:
 		 * ->restarted flag.
 		 */
 		if (wc->restarted) {
-			ret = check_ref_exists(trans, root, bytenr, parent,
+			ret = check_ref_exists(trans, root, bytenr, ref.parent,
 					       level - 1);
 			if (ret < 0)
 				goto out_unlock;
@@ -5618,8 +5590,7 @@ skip:
 		 * already accounted them at merge time (replace_path),
 		 * thus we could skip expensive subtree trace here.
 		 */
-		if (root->root_key.objectid != BTRFS_TREE_RELOC_OBJECTID &&
-		    need_account) {
+		if (btrfs_root_id(root) != BTRFS_TREE_RELOC_OBJECTID && need_account) {
 			ret = btrfs_qgroup_trace_subtree(trans, next,
 							 generation, level - 1);
 			if (ret) {
@@ -5638,10 +5609,7 @@ skip:
 		wc->drop_level = level;
 		find_next_key(path, level, &wc->drop_progress);
 
-		btrfs_init_generic_ref(&ref, BTRFS_DROP_DELAYED_REF, bytenr,
-				       fs_info->nodesize, parent, owner_root);
-		btrfs_init_tree_ref(&ref, level - 1, root->root_key.objectid,
-				    0, false);
+		btrfs_init_tree_ref(&ref, level - 1, 0, false);
 		ret = btrfs_free_extent(trans, &ref);
 		if (ret)
 			goto out_unlock;
@@ -5732,7 +5700,7 @@ static noinline int walk_up_proc(struct btrfs_trans_handle *trans,
 			else
 				ret = btrfs_dec_ref(trans, root, eb, 0);
 			BUG_ON(ret); /* -ENOMEM */
-			if (is_fstree(root->root_key.objectid)) {
+			if (is_fstree(btrfs_root_id(root))) {
 				ret = btrfs_qgroup_trace_leaf_items(trans, eb);
 				if (ret) {
 					btrfs_err_rl(fs_info,
@@ -5752,12 +5720,12 @@ static noinline int walk_up_proc(struct btrfs_trans_handle *trans,
 	if (eb == root->node) {
 		if (wc->flags[level] & BTRFS_BLOCK_FLAG_FULL_BACKREF)
 			parent = eb->start;
-		else if (root->root_key.objectid != btrfs_header_owner(eb))
+		else if (btrfs_root_id(root) != btrfs_header_owner(eb))
 			goto owner_mismatch;
 	} else {
 		if (wc->flags[level + 1] & BTRFS_BLOCK_FLAG_FULL_BACKREF)
 			parent = path->nodes[level + 1]->start;
-		else if (root->root_key.objectid !=
+		else if (btrfs_root_id(root) !=
 			 btrfs_header_owner(path->nodes[level + 1]))
 			goto owner_mismatch;
 	}
@@ -5771,7 +5739,7 @@ out:
 
 owner_mismatch:
 	btrfs_err_rl(fs_info, "unexpected tree owner, have %llu expect %llu",
-		     btrfs_header_owner(eb), root->root_key.objectid);
+		     btrfs_header_owner(eb), btrfs_root_id(root));
 	return -EUCLEAN;
 }
 
@@ -5857,8 +5825,7 @@ static noinline int walk_up_tree(struct btrfs_trans_handle *trans,
  */
 int btrfs_drop_snapshot(struct btrfs_root *root, int update_ref, int for_reloc)
 {
-	const bool is_reloc_root = (root->root_key.objectid ==
-				    BTRFS_TREE_RELOC_OBJECTID);
+	const bool is_reloc_root = (btrfs_root_id(root) == BTRFS_TREE_RELOC_OBJECTID);
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct btrfs_path *path;
 	struct btrfs_trans_handle *trans;
@@ -5872,7 +5839,7 @@ int btrfs_drop_snapshot(struct btrfs_root *root, int update_ref, int for_reloc)
 	bool root_dropped = false;
 	bool unfinished_drop = false;
 
-	btrfs_debug(fs_info, "Drop subvolume %llu", root->root_key.objectid);
+	btrfs_debug(fs_info, "Drop subvolume %llu", btrfs_root_id(root));
 
 	path = btrfs_alloc_path();
 	if (!path) {
@@ -6070,8 +6037,7 @@ int btrfs_drop_snapshot(struct btrfs_root *root, int update_ref, int for_reloc)
 			 *
 			 * The most common failure here is just -ENOENT.
 			 */
-			btrfs_del_orphan_item(trans, tree_root,
-					      root->root_key.objectid);
+			btrfs_del_orphan_item(trans, tree_root, btrfs_root_id(root));
 		}
 	}
 
@@ -6133,9 +6099,8 @@ int btrfs_drop_subtree(struct btrfs_trans_handle *trans,
 	int level;
 	int parent_level;
 	int ret = 0;
-	int wret;
 
-	BUG_ON(root->root_key.objectid != BTRFS_TREE_RELOC_OBJECTID);
+	BUG_ON(btrfs_root_id(root) != BTRFS_TREE_RELOC_OBJECTID);
 
 	path = btrfs_alloc_path();
 	if (!path)
@@ -6169,17 +6134,16 @@ int btrfs_drop_subtree(struct btrfs_trans_handle *trans,
 	wc->reada_count = BTRFS_NODEPTRS_PER_BLOCK(fs_info);
 
 	while (1) {
-		wret = walk_down_tree(trans, root, path, wc);
-		if (wret < 0) {
-			ret = wret;
+		ret = walk_down_tree(trans, root, path, wc);
+		if (ret < 0)
 			break;
-		}
 
-		wret = walk_up_tree(trans, root, path, wc, parent_level);
-		if (wret < 0)
-			ret = wret;
-		if (wret != 0)
+		ret = walk_up_tree(trans, root, path, wc, parent_level);
+		if (ret) {
+			if (ret > 0)
+				ret = 0;
 			break;
+		}
 	}
 
 	kfree(wc);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 2776112dbdf8..597387e9f040 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -396,15 +396,14 @@ again:
 	/* then test to make sure it is all still delalloc */
 	ret = test_range_bit(tree, delalloc_start, delalloc_end,
 			     EXTENT_DELALLOC, cached_state);
+
+	unlock_extent(tree, delalloc_start, delalloc_end, &cached_state);
 	if (!ret) {
-		unlock_extent(tree, delalloc_start, delalloc_end,
-			      &cached_state);
 		__unlock_for_delalloc(inode, locked_page,
 			      delalloc_start, delalloc_end);
 		cond_resched();
 		goto again;
 	}
-	free_extent_state(cached_state);
 	*start = delalloc_start;
 	*end = delalloc_end;
 out_failed:
@@ -413,9 +412,10 @@ out_failed:
 
 void extent_clear_unlock_delalloc(struct btrfs_inode *inode, u64 start, u64 end,
 				  struct page *locked_page,
+				  struct extent_state **cached,
 				  u32 clear_bits, unsigned long page_ops)
 {
-	clear_extent_bit(&inode->io_tree, start, end, clear_bits, NULL);
+	clear_extent_bit(&inode->io_tree, start, end, clear_bits, cached);
 
 	__process_pages_contig(inode->vfs_inode.i_mapping, locked_page,
 			       start, end, page_ops);
@@ -667,6 +667,37 @@ static void end_bbio_data_read(struct btrfs_bio *bbio)
 }
 
 /*
+ * Populate every free slot in a provided array with folios.
+ *
+ * @nr_folios:   number of folios to allocate
+ * @folio_array: the array to fill with folios; any existing non-NULL entries in
+ *		 the array will be skipped
+ * @extra_gfp:	 the extra GFP flags for the allocation
+ *
+ * Return: 0        if all folios were able to be allocated;
+ *         -ENOMEM  otherwise, the partially allocated folios would be freed and
+ *                  the array slots zeroed
+ */
+int btrfs_alloc_folio_array(unsigned int nr_folios, struct folio **folio_array,
+			    gfp_t extra_gfp)
+{
+	for (int i = 0; i < nr_folios; i++) {
+		if (folio_array[i])
+			continue;
+		folio_array[i] = folio_alloc(GFP_NOFS | extra_gfp, 0);
+		if (!folio_array[i])
+			goto error;
+	}
+	return 0;
+error:
+	for (int i = 0; i < nr_folios; i++) {
+		if (folio_array[i])
+			folio_put(folio_array[i]);
+	}
+	return -ENOMEM;
+}
+
+/*
  * Populate every free slot in a provided array with pages.
  *
  * @nr_pages:   number of pages to allocate
@@ -1571,7 +1602,7 @@ static void set_btree_ioerr(struct extent_buffer *eb)
 	 * can be no longer dirty nor marked anymore for writeback (if a
 	 * subsequent modification to the extent buffer didn't happen before the
 	 * transaction commit), which makes filemap_fdata[write|wait]_range not
-	 * able to find the pages tagged with SetPageError at transaction
+	 * able to find the pages which contain errors at transaction
 	 * commit time. So if this happens we must abort the transaction,
 	 * otherwise we commit a super block with btree roots that point to
 	 * btree nodes/leafs whose content on disk is invalid - either garbage
@@ -2246,8 +2277,7 @@ next_page:
 	submit_write_bio(&bio_ctrl, found_error ? ret : 0);
 }
 
-int extent_writepages(struct address_space *mapping,
-		      struct writeback_control *wbc)
+int btrfs_writepages(struct address_space *mapping, struct writeback_control *wbc)
 {
 	struct inode *inode = mapping->host;
 	int ret = 0;
@@ -2267,7 +2297,7 @@ int extent_writepages(struct address_space *mapping,
 	return ret;
 }
 
-void extent_readahead(struct readahead_control *rac)
+void btrfs_readahead(struct readahead_control *rac)
 {
 	struct btrfs_bio_ctrl bio_ctrl = { .opf = REQ_OP_READ | REQ_RAHEAD };
 	struct page *pagepool[16];
@@ -2325,19 +2355,20 @@ int extent_invalidate_folio(struct extent_io_tree *tree,
  * are locked or under IO and drops the related state bits if it is safe
  * to drop the page.
  */
-static int try_release_extent_state(struct extent_io_tree *tree,
+static bool try_release_extent_state(struct extent_io_tree *tree,
 				    struct page *page, gfp_t mask)
 {
 	u64 start = page_offset(page);
 	u64 end = start + PAGE_SIZE - 1;
-	int ret = 1;
+	bool ret;
 
 	if (test_range_bit_exists(tree, start, end, EXTENT_LOCKED)) {
-		ret = 0;
+		ret = false;
 	} else {
 		u32 clear_bits = ~(EXTENT_LOCKED | EXTENT_NODATASUM |
 				   EXTENT_DELALLOC_NEW | EXTENT_CTLBITS |
 				   EXTENT_QGROUP_RESERVED);
+		int ret2;
 
 		/*
 		 * At this point we can safely clear everything except the
@@ -2345,15 +2376,15 @@ static int try_release_extent_state(struct extent_io_tree *tree,
 		 * The delalloc new bit will be cleared by ordered extent
 		 * completion.
 		 */
-		ret = __clear_extent_bit(tree, start, end, clear_bits, NULL, NULL);
+		ret2 = __clear_extent_bit(tree, start, end, clear_bits, NULL, NULL);
 
 		/* if clear_extent_bit failed for enomem reasons,
 		 * we can't allow the release to continue.
 		 */
-		if (ret < 0)
-			ret = 0;
+		if (ret2 < 0)
+			ret = false;
 		else
-			ret = 1;
+			ret = true;
 	}
 	return ret;
 }
@@ -2363,84 +2394,80 @@ static int try_release_extent_state(struct extent_io_tree *tree,
  * in the range corresponding to the page, both state records and extent
  * map records are removed
  */
-int try_release_extent_mapping(struct page *page, gfp_t mask)
+bool try_release_extent_mapping(struct page *page, gfp_t mask)
 {
-	struct extent_map *em;
 	u64 start = page_offset(page);
 	u64 end = start + PAGE_SIZE - 1;
-	struct btrfs_inode *btrfs_inode = page_to_inode(page);
-	struct extent_io_tree *tree = &btrfs_inode->io_tree;
-	struct extent_map_tree *map = &btrfs_inode->extent_tree;
-
-	if (gfpflags_allow_blocking(mask) &&
-	    page->mapping->host->i_size > SZ_16M) {
-		u64 len;
-		while (start <= end) {
-			struct btrfs_fs_info *fs_info;
-			u64 cur_gen;
-
-			len = end - start + 1;
-			write_lock(&map->lock);
-			em = lookup_extent_mapping(map, start, len);
-			if (!em) {
-				write_unlock(&map->lock);
-				break;
-			}
-			if ((em->flags & EXTENT_FLAG_PINNED) ||
-			    em->start != start) {
-				write_unlock(&map->lock);
-				free_extent_map(em);
-				break;
-			}
-			if (test_range_bit_exists(tree, em->start,
-						  extent_map_end(em) - 1,
-						  EXTENT_LOCKED))
-				goto next;
-			/*
-			 * If it's not in the list of modified extents, used
-			 * by a fast fsync, we can remove it. If it's being
-			 * logged we can safely remove it since fsync took an
-			 * extra reference on the em.
-			 */
-			if (list_empty(&em->list) ||
-			    (em->flags & EXTENT_FLAG_LOGGING))
-				goto remove_em;
-			/*
-			 * If it's in the list of modified extents, remove it
-			 * only if its generation is older then the current one,
-			 * in which case we don't need it for a fast fsync.
-			 * Otherwise don't remove it, we could be racing with an
-			 * ongoing fast fsync that could miss the new extent.
-			 */
-			fs_info = btrfs_inode->root->fs_info;
-			spin_lock(&fs_info->trans_lock);
-			cur_gen = fs_info->generation;
-			spin_unlock(&fs_info->trans_lock);
-			if (em->generation >= cur_gen)
-				goto next;
-remove_em:
-			/*
-			 * We only remove extent maps that are not in the list of
-			 * modified extents or that are in the list but with a
-			 * generation lower then the current generation, so there
-			 * is no need to set the full fsync flag on the inode (it
-			 * hurts the fsync performance for workloads with a data
-			 * size that exceeds or is close to the system's memory).
-			 */
-			remove_extent_mapping(map, em);
-			/* once for the rb tree */
+	struct btrfs_inode *inode = page_to_inode(page);
+	struct extent_io_tree *io_tree = &inode->io_tree;
+
+	while (start <= end) {
+		const u64 cur_gen = btrfs_get_fs_generation(inode->root->fs_info);
+		const u64 len = end - start + 1;
+		struct extent_map_tree *extent_tree = &inode->extent_tree;
+		struct extent_map *em;
+
+		write_lock(&extent_tree->lock);
+		em = lookup_extent_mapping(extent_tree, start, len);
+		if (!em) {
+			write_unlock(&extent_tree->lock);
+			break;
+		}
+		if ((em->flags & EXTENT_FLAG_PINNED) || em->start != start) {
+			write_unlock(&extent_tree->lock);
 			free_extent_map(em);
+			break;
+		}
+		if (test_range_bit_exists(io_tree, em->start,
+					  extent_map_end(em) - 1, EXTENT_LOCKED))
+			goto next;
+		/*
+		 * If it's not in the list of modified extents, used by a fast
+		 * fsync, we can remove it. If it's being logged we can safely
+		 * remove it since fsync took an extra reference on the em.
+		 */
+		if (list_empty(&em->list) || (em->flags & EXTENT_FLAG_LOGGING))
+			goto remove_em;
+		/*
+		 * If it's in the list of modified extents, remove it only if
+		 * its generation is older then the current one, in which case
+		 * we don't need it for a fast fsync. Otherwise don't remove it,
+		 * we could be racing with an ongoing fast fsync that could miss
+		 * the new extent.
+		 */
+		if (em->generation >= cur_gen)
+			goto next;
+remove_em:
+		/*
+		 * We only remove extent maps that are not in the list of
+		 * modified extents or that are in the list but with a
+		 * generation lower then the current generation, so there is no
+		 * need to set the full fsync flag on the inode (it hurts the
+		 * fsync performance for workloads with a data size that exceeds
+		 * or is close to the system's memory).
+		 */
+		remove_extent_mapping(inode, em);
+		/* Once for the inode's extent map tree. */
+		free_extent_map(em);
 next:
-			start = extent_map_end(em);
-			write_unlock(&map->lock);
+		start = extent_map_end(em);
+		write_unlock(&extent_tree->lock);
 
-			/* once for us */
-			free_extent_map(em);
+		/* Once for us, for the lookup_extent_mapping() reference. */
+		free_extent_map(em);
+
+		if (need_resched()) {
+			/*
+			 * If we need to resched but we can't block just exit
+			 * and leave any remaining extent maps.
+			 */
+			if (!gfpflags_allow_blocking(mask))
+				break;
 
-			cond_resched(); /* Allow large-extent preemption. */
+			cond_resched();
 		}
 	}
-	return try_release_extent_state(tree, page, mask);
+	return try_release_extent_state(io_tree, page, mask);
 }
 
 struct btrfs_fiemap_entry {
@@ -2773,13 +2800,19 @@ static int fiemap_next_leaf_item(struct btrfs_inode *inode, struct btrfs_path *p
 		goto out;
 	}
 
-	/* See the comment at fiemap_search_slot() about why we clone. */
-	copy_extent_buffer_full(clone, path->nodes[0]);
 	/*
 	 * Important to preserve the start field, for the optimizations when
 	 * checking if extents are shared (see extent_fiemap()).
+	 *
+	 * We must set ->start before calling copy_extent_buffer_full().  If we
+	 * are on sub-pagesize blocksize, we use ->start to determine the offset
+	 * into the folio where our eb exists, and if we update ->start after
+	 * the fact then any subsequent reads of the eb may read from a
+	 * different offset in the folio than where we originally copied into.
 	 */
 	clone->start = path->nodes[0]->start;
+	/* See the comment at fiemap_search_slot() about why we clone. */
+	copy_extent_buffer_full(clone, path->nodes[0]);
 
 	slot = path->slots[0];
 	btrfs_release_path(path);
@@ -4261,6 +4294,13 @@ void set_extent_buffer_uptodate(struct extent_buffer *eb)
 	}
 }
 
+static void clear_extent_buffer_reading(struct extent_buffer *eb)
+{
+	clear_bit(EXTENT_BUFFER_READING, &eb->bflags);
+	smp_mb__after_atomic();
+	wake_up_bit(&eb->bflags, EXTENT_BUFFER_READING);
+}
+
 static void end_bbio_meta_read(struct btrfs_bio *bbio)
 {
 	struct extent_buffer *eb = bbio->private;
@@ -4269,6 +4309,13 @@ static void end_bbio_meta_read(struct btrfs_bio *bbio)
 	struct folio_iter fi;
 	u32 bio_offset = 0;
 
+	/*
+	 * If the extent buffer is marked UPTODATE before the read operation
+	 * completes, other calls to read_extent_buffer_pages() will return
+	 * early without waiting for the read to finish, causing data races.
+	 */
+	WARN_ON(test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags));
+
 	eb->read_mirror = bbio->mirror_num;
 
 	if (uptodate &&
@@ -4295,9 +4342,7 @@ static void end_bbio_meta_read(struct btrfs_bio *bbio)
 		bio_offset += len;
 	}
 
-	clear_bit(EXTENT_BUFFER_READING, &eb->bflags);
-	smp_mb__after_atomic();
-	wake_up_bit(&eb->bflags, EXTENT_BUFFER_READING);
+	clear_extent_buffer_reading(eb);
 	free_extent_buffer(eb);
 
 	bio_put(&bbio->bio);
@@ -4331,9 +4376,7 @@ int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num,
 	 * will now be set, and we shouldn't read it in again.
 	 */
 	if (unlikely(test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags))) {
-		clear_bit(EXTENT_BUFFER_READING, &eb->bflags);
-		smp_mb__after_atomic();
-		wake_up_bit(&eb->bflags, EXTENT_BUFFER_READING);
+		clear_extent_buffer_reading(eb);
 		return 0;
 	}
 
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index e3530d427e1f..dca6b12769ec 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -27,6 +27,7 @@ struct address_space;
 struct writeback_control;
 struct extent_io_tree;
 struct extent_map_tree;
+struct extent_state;
 struct btrfs_block_group;
 struct btrfs_fs_info;
 struct btrfs_inode;
@@ -230,18 +231,17 @@ static inline void extent_changeset_free(struct extent_changeset *changeset)
 	kfree(changeset);
 }
 
-int try_release_extent_mapping(struct page *page, gfp_t mask);
+bool try_release_extent_mapping(struct page *page, gfp_t mask);
 int try_release_extent_buffer(struct page *page);
 
 int btrfs_read_folio(struct file *file, struct folio *folio);
 void extent_write_locked_range(struct inode *inode, struct page *locked_page,
 			       u64 start, u64 end, struct writeback_control *wbc,
 			       bool pages_dirty);
-int extent_writepages(struct address_space *mapping,
-		      struct writeback_control *wbc);
+int btrfs_writepages(struct address_space *mapping, struct writeback_control *wbc);
 int btree_write_cache_pages(struct address_space *mapping,
 			    struct writeback_control *wbc);
-void extent_readahead(struct readahead_control *rac);
+void btrfs_readahead(struct readahead_control *rac);
 int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo,
 		  u64 start, u64 len);
 int set_folio_extent_mapped(struct folio *folio);
@@ -353,6 +353,7 @@ void clear_extent_buffer_uptodate(struct extent_buffer *eb);
 void extent_range_clear_dirty_for_io(struct inode *inode, u64 start, u64 end);
 void extent_clear_unlock_delalloc(struct btrfs_inode *inode, u64 start, u64 end,
 				  struct page *locked_page,
+				  struct extent_state **cached,
 				  u32 bits_to_clear, unsigned long page_ops);
 int extent_invalidate_folio(struct extent_io_tree *tree,
 			    struct folio *folio, size_t offset);
@@ -361,6 +362,8 @@ void btrfs_clear_buffer_dirty(struct btrfs_trans_handle *trans,
 
 int btrfs_alloc_page_array(unsigned int nr_pages, struct page **page_array,
 			   gfp_t extra_gfp);
+int btrfs_alloc_folio_array(unsigned int nr_folios, struct folio **folio_array,
+			    gfp_t extra_gfp);
 
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
 bool find_lock_delalloc_range(struct inode *inode,
diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index 24a048210b15..744e8952abb0 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -8,6 +8,7 @@
 #include "extent_map.h"
 #include "compression.h"
 #include "btrfs_inode.h"
+#include "disk-io.h"
 
 
 static struct kmem_cache *extent_map_cache;
@@ -76,6 +77,14 @@ static u64 range_end(u64 start, u64 len)
 	return start + len;
 }
 
+static void dec_evictable_extent_maps(struct btrfs_inode *inode)
+{
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
+
+	if (!btrfs_is_testing(fs_info) && is_fstree(btrfs_root_id(inode->root)))
+		percpu_counter_dec(&fs_info->evictable_extent_maps);
+}
+
 static int tree_insert(struct rb_root_cached *root, struct extent_map *em)
 {
 	struct rb_node **p = &root->rb_root.rb_node;
@@ -223,8 +232,9 @@ static bool mergeable_maps(const struct extent_map *prev, const struct extent_ma
 	return next->block_start == prev->block_start;
 }
 
-static void try_merge_map(struct extent_map_tree *tree, struct extent_map *em)
+static void try_merge_map(struct btrfs_inode *inode, struct extent_map *em)
 {
+	struct extent_map_tree *tree = &inode->extent_tree;
 	struct extent_map *merge = NULL;
 	struct rb_node *rb;
 
@@ -252,14 +262,13 @@ static void try_merge_map(struct extent_map_tree *tree, struct extent_map *em)
 			em->len += merge->len;
 			em->block_len += merge->block_len;
 			em->block_start = merge->block_start;
-			em->mod_len = (em->mod_len + em->mod_start) - merge->mod_start;
-			em->mod_start = merge->mod_start;
 			em->generation = max(em->generation, merge->generation);
 			em->flags |= EXTENT_FLAG_MERGED;
 
 			rb_erase_cached(&merge->rb_node, &tree->map);
 			RB_CLEAR_NODE(&merge->rb_node);
 			free_extent_map(merge);
+			dec_evictable_extent_maps(inode);
 		}
 	}
 
@@ -271,10 +280,10 @@ static void try_merge_map(struct extent_map_tree *tree, struct extent_map *em)
 		em->block_len += merge->block_len;
 		rb_erase_cached(&merge->rb_node, &tree->map);
 		RB_CLEAR_NODE(&merge->rb_node);
-		em->mod_len = (merge->mod_start + merge->mod_len) - em->mod_start;
 		em->generation = max(em->generation, merge->generation);
 		em->flags |= EXTENT_FLAG_MERGED;
 		free_extent_map(merge);
+		dec_evictable_extent_maps(inode);
 	}
 }
 
@@ -300,7 +309,6 @@ int unpin_extent_cache(struct btrfs_inode *inode, u64 start, u64 len, u64 gen)
 	struct extent_map_tree *tree = &inode->extent_tree;
 	int ret = 0;
 	struct extent_map *em;
-	bool prealloc = false;
 
 	write_lock(&tree->lock);
 	em = lookup_extent_mapping(tree, start, len);
@@ -325,20 +333,8 @@ int unpin_extent_cache(struct btrfs_inode *inode, u64 start, u64 len, u64 gen)
 
 	em->generation = gen;
 	em->flags &= ~EXTENT_FLAG_PINNED;
-	em->mod_start = em->start;
-	em->mod_len = em->len;
 
-	if (em->flags & EXTENT_FLAG_FILLING) {
-		prealloc = true;
-		em->flags &= ~EXTENT_FLAG_FILLING;
-	}
-
-	try_merge_map(tree, em);
-
-	if (prealloc) {
-		em->mod_start = em->start;
-		em->mod_len = em->len;
-	}
+	try_merge_map(inode, em);
 
 out:
 	write_unlock(&tree->lock);
@@ -347,58 +343,62 @@ out:
 
 }
 
-void clear_em_logging(struct extent_map_tree *tree, struct extent_map *em)
+void clear_em_logging(struct btrfs_inode *inode, struct extent_map *em)
 {
-	lockdep_assert_held_write(&tree->lock);
+	lockdep_assert_held_write(&inode->extent_tree.lock);
 
 	em->flags &= ~EXTENT_FLAG_LOGGING;
 	if (extent_map_in_tree(em))
-		try_merge_map(tree, em);
+		try_merge_map(inode, em);
 }
 
-static inline void setup_extent_mapping(struct extent_map_tree *tree,
+static inline void setup_extent_mapping(struct btrfs_inode *inode,
 					struct extent_map *em,
 					int modified)
 {
 	refcount_inc(&em->refs);
-	em->mod_start = em->start;
-	em->mod_len = em->len;
 
 	ASSERT(list_empty(&em->list));
 
 	if (modified)
-		list_add(&em->list, &tree->modified_extents);
+		list_add(&em->list, &inode->extent_tree.modified_extents);
 	else
-		try_merge_map(tree, em);
+		try_merge_map(inode, em);
 }
 
 /*
- * Add new extent map to the extent tree
+ * Add a new extent map to an inode's extent map tree.
  *
- * @tree:	tree to insert new map in
+ * @inode:	the target inode
  * @em:		map to insert
  * @modified:	indicate whether the given @em should be added to the
  *	        modified list, which indicates the extent needs to be logged
  *
- * Insert @em into @tree or perform a simple forward/backward merge with
- * existing mappings.  The extent_map struct passed in will be inserted
- * into the tree directly, with an additional reference taken, or a
- * reference dropped if the merge attempt was successful.
+ * Insert @em into the @inode's extent map tree or perform a simple
+ * forward/backward merge with existing mappings.  The extent_map struct passed
+ * in will be inserted into the tree directly, with an additional reference
+ * taken, or a reference dropped if the merge attempt was successful.
  */
-static int add_extent_mapping(struct extent_map_tree *tree,
+static int add_extent_mapping(struct btrfs_inode *inode,
 			      struct extent_map *em, int modified)
 {
-	int ret = 0;
+	struct extent_map_tree *tree = &inode->extent_tree;
+	struct btrfs_root *root = inode->root;
+	struct btrfs_fs_info *fs_info = root->fs_info;
+	int ret;
 
 	lockdep_assert_held_write(&tree->lock);
 
 	ret = tree_insert(&tree->map, em);
 	if (ret)
-		goto out;
+		return ret;
 
-	setup_extent_mapping(tree, em, modified);
-out:
-	return ret;
+	setup_extent_mapping(inode, em, modified);
+
+	if (!btrfs_is_testing(fs_info) && is_fstree(btrfs_root_id(root)))
+		percpu_counter_inc(&fs_info->evictable_extent_maps);
+
+	return 0;
 }
 
 static struct extent_map *
@@ -464,16 +464,18 @@ struct extent_map *search_extent_mapping(struct extent_map_tree *tree,
 }
 
 /*
- * Remove an extent_map from the extent tree.
+ * Remove an extent_map from its inode's extent tree.
  *
- * @tree:	extent tree to remove from
+ * @inode:	the inode the extent map belongs to
  * @em:		extent map being removed
  *
- * Remove @em from @tree.  No reference counts are dropped, and no checks
- * are done to see if the range is in use.
+ * Remove @em from the extent tree of @inode.  No reference counts are dropped,
+ * and no checks are done to see if the range is in use.
  */
-void remove_extent_mapping(struct extent_map_tree *tree, struct extent_map *em)
+void remove_extent_mapping(struct btrfs_inode *inode, struct extent_map *em)
 {
+	struct extent_map_tree *tree = &inode->extent_tree;
+
 	lockdep_assert_held_write(&tree->lock);
 
 	WARN_ON(em->flags & EXTENT_FLAG_PINNED);
@@ -481,13 +483,17 @@ void remove_extent_mapping(struct extent_map_tree *tree, struct extent_map *em)
 	if (!(em->flags & EXTENT_FLAG_LOGGING))
 		list_del_init(&em->list);
 	RB_CLEAR_NODE(&em->rb_node);
+
+	dec_evictable_extent_maps(inode);
 }
 
-static void replace_extent_mapping(struct extent_map_tree *tree,
+static void replace_extent_mapping(struct btrfs_inode *inode,
 				   struct extent_map *cur,
 				   struct extent_map *new,
 				   int modified)
 {
+	struct extent_map_tree *tree = &inode->extent_tree;
+
 	lockdep_assert_held_write(&tree->lock);
 
 	WARN_ON(cur->flags & EXTENT_FLAG_PINNED);
@@ -497,7 +503,7 @@ static void replace_extent_mapping(struct extent_map_tree *tree,
 	rb_replace_node_cached(&cur->rb_node, &new->rb_node, &tree->map);
 	RB_CLEAR_NODE(&cur->rb_node);
 
-	setup_extent_mapping(tree, new, modified);
+	setup_extent_mapping(inode, new, modified);
 }
 
 static struct extent_map *next_extent_map(const struct extent_map *em)
@@ -526,7 +532,7 @@ static struct extent_map *prev_extent_map(struct extent_map *em)
  * and an extent that you want to insert, deal with overlap and insert
  * the best fitted new extent into the tree.
  */
-static noinline int merge_extent_mapping(struct extent_map_tree *em_tree,
+static noinline int merge_extent_mapping(struct btrfs_inode *inode,
 					 struct extent_map *existing,
 					 struct extent_map *em,
 					 u64 map_start)
@@ -560,14 +566,13 @@ static noinline int merge_extent_mapping(struct extent_map_tree *em_tree,
 		em->block_start += start_diff;
 		em->block_len = em->len;
 	}
-	return add_extent_mapping(em_tree, em, 0);
+	return add_extent_mapping(inode, em, 0);
 }
 
 /*
- * Add extent mapping into em_tree.
+ * Add extent mapping into an inode's extent map tree.
  *
- * @fs_info:  the filesystem
- * @em_tree:  extent tree into which we want to insert the extent mapping
+ * @inode:    target inode
  * @em_in:    extent we are inserting
  * @start:    start of the logical range btrfs_get_extent() is requesting
  * @len:      length of the logical range btrfs_get_extent() is requesting
@@ -575,8 +580,8 @@ static noinline int merge_extent_mapping(struct extent_map_tree *em_tree,
  * Note that @em_in's range may be different from [start, start+len),
  * but they must be overlapped.
  *
- * Insert @em_in into @em_tree. In case there is an overlapping range, handle
- * the -EEXIST by either:
+ * Insert @em_in into the inode's extent map tree. In case there is an
+ * overlapping range, handle the -EEXIST by either:
  * a) Returning the existing extent in @em_in if @start is within the
  *    existing em.
  * b) Merge the existing extent with @em_in passed in.
@@ -584,12 +589,12 @@ static noinline int merge_extent_mapping(struct extent_map_tree *em_tree,
  * Return 0 on success, otherwise -EEXIST.
  *
  */
-int btrfs_add_extent_mapping(struct btrfs_fs_info *fs_info,
-			     struct extent_map_tree *em_tree,
+int btrfs_add_extent_mapping(struct btrfs_inode *inode,
 			     struct extent_map **em_in, u64 start, u64 len)
 {
 	int ret;
 	struct extent_map *em = *em_in;
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 
 	/*
 	 * Tree-checker should have rejected any inline extent with non-zero
@@ -598,7 +603,7 @@ int btrfs_add_extent_mapping(struct btrfs_fs_info *fs_info,
 	if (em->block_start == EXTENT_MAP_INLINE)
 		ASSERT(em->start == 0);
 
-	ret = add_extent_mapping(em_tree, em, 0);
+	ret = add_extent_mapping(inode, em, 0);
 	/* it is possible that someone inserted the extent into the tree
 	 * while we had the lock dropped.  It is also possible that
 	 * an overlapping map exists in the tree
@@ -606,7 +611,7 @@ int btrfs_add_extent_mapping(struct btrfs_fs_info *fs_info,
 	if (ret == -EEXIST) {
 		struct extent_map *existing;
 
-		existing = search_extent_mapping(em_tree, start, len);
+		existing = search_extent_mapping(&inode->extent_tree, start, len);
 
 		trace_btrfs_handle_em_exist(fs_info, existing, em, start, len);
 
@@ -627,8 +632,7 @@ int btrfs_add_extent_mapping(struct btrfs_fs_info *fs_info,
 			 * The existing extent map is the one nearest to
 			 * the [start, start + len) range which overlaps
 			 */
-			ret = merge_extent_mapping(em_tree, existing,
-						   em, start);
+			ret = merge_extent_mapping(inode, existing, em, start);
 			if (WARN_ON(ret)) {
 				free_extent_map(em);
 				*em_in = NULL;
@@ -650,8 +654,10 @@ int btrfs_add_extent_mapping(struct btrfs_fs_info *fs_info,
  * if needed. This avoids searching the tree, from the root down to the first
  * extent map, before each deletion.
  */
-static void drop_all_extent_maps_fast(struct extent_map_tree *tree)
+static void drop_all_extent_maps_fast(struct btrfs_inode *inode)
 {
+	struct extent_map_tree *tree = &inode->extent_tree;
+
 	write_lock(&tree->lock);
 	while (!RB_EMPTY_ROOT(&tree->map.rb_root)) {
 		struct extent_map *em;
@@ -660,7 +666,7 @@ static void drop_all_extent_maps_fast(struct extent_map_tree *tree)
 		node = rb_first_cached(&tree->map);
 		em = rb_entry(node, struct extent_map, rb_node);
 		em->flags &= ~(EXTENT_FLAG_PINNED | EXTENT_FLAG_LOGGING);
-		remove_extent_mapping(tree, em);
+		remove_extent_mapping(inode, em);
 		free_extent_map(em);
 		cond_resched_rwlock_write(&tree->lock);
 	}
@@ -693,7 +699,7 @@ void btrfs_drop_extent_map_range(struct btrfs_inode *inode, u64 start, u64 end,
 	WARN_ON(end < start);
 	if (end == (u64)-1) {
 		if (start == 0 && !skip_pinned) {
-			drop_all_extent_maps_fast(em_tree);
+			drop_all_extent_maps_fast(inode);
 			return;
 		}
 		len = (u64)-1;
@@ -790,7 +796,7 @@ void btrfs_drop_extent_map_range(struct btrfs_inode *inode, u64 start, u64 end,
 
 			split->generation = gen;
 			split->flags = flags;
-			replace_extent_mapping(em_tree, em, split, modified);
+			replace_extent_mapping(inode, em, split, modified);
 			free_extent_map(split);
 			split = split2;
 			split2 = NULL;
@@ -831,13 +837,11 @@ void btrfs_drop_extent_map_range(struct btrfs_inode *inode, u64 start, u64 end,
 			}
 
 			if (extent_map_in_tree(em)) {
-				replace_extent_mapping(em_tree, em, split,
-						       modified);
+				replace_extent_mapping(inode, em, split, modified);
 			} else {
 				int ret;
 
-				ret = add_extent_mapping(em_tree, split,
-							 modified);
+				ret = add_extent_mapping(inode, split, modified);
 				/* Logic error, shouldn't happen. */
 				ASSERT(ret == 0);
 				if (WARN_ON(ret != 0) && modified)
@@ -872,7 +876,7 @@ remove_em:
 				ASSERT(!split);
 				btrfs_set_inode_full_sync(inode);
 			}
-			remove_extent_mapping(em_tree, em);
+			remove_extent_mapping(inode, em);
 		}
 
 		/*
@@ -927,7 +931,7 @@ int btrfs_replace_extent_map_range(struct btrfs_inode *inode,
 	do {
 		btrfs_drop_extent_map_range(inode, new_em->start, end, false);
 		write_lock(&tree->lock);
-		ret = add_extent_mapping(tree, new_em, modified);
+		ret = add_extent_mapping(inode, new_em, modified);
 		write_unlock(&tree->lock);
 	} while (ret == -EEXIST);
 
@@ -991,7 +995,7 @@ int split_extent_map(struct btrfs_inode *inode, u64 start, u64 len, u64 pre,
 	split_pre->flags = flags;
 	split_pre->generation = em->generation;
 
-	replace_extent_mapping(em_tree, em, split_pre, 1);
+	replace_extent_mapping(inode, em, split_pre, 1);
 
 	/*
 	 * Now we only have an extent_map at:
@@ -1008,7 +1012,7 @@ int split_extent_map(struct btrfs_inode *inode, u64 start, u64 len, u64 pre,
 	split_mid->ram_bytes = split_mid->len;
 	split_mid->flags = flags;
 	split_mid->generation = em->generation;
-	add_extent_mapping(em_tree, split_mid, 1);
+	add_extent_mapping(inode, split_mid, 1);
 
 	/* Once for us */
 	free_extent_map(em);
@@ -1023,3 +1027,175 @@ out_free_pre:
 	free_extent_map(split_pre);
 	return ret;
 }
+
+static long btrfs_scan_inode(struct btrfs_inode *inode, long *scanned, long nr_to_scan)
+{
+	const u64 cur_fs_gen = btrfs_get_fs_generation(inode->root->fs_info);
+	struct extent_map_tree *tree = &inode->extent_tree;
+	long nr_dropped = 0;
+	struct rb_node *node;
+
+	/*
+	 * Take the mmap lock so that we serialize with the inode logging phase
+	 * of fsync because we may need to set the full sync flag on the inode,
+	 * in case we have to remove extent maps in the tree's list of modified
+	 * extents. If we set the full sync flag in the inode while an fsync is
+	 * in progress, we may risk missing new extents because before the flag
+	 * is set, fsync decides to only wait for writeback to complete and then
+	 * during inode logging it sees the flag set and uses the subvolume tree
+	 * to find new extents, which may not be there yet because ordered
+	 * extents haven't completed yet.
+	 *
+	 * We also do a try lock because otherwise we could deadlock. This is
+	 * because the shrinker for this filesystem may be invoked while we are
+	 * in a path that is holding the mmap lock in write mode. For example in
+	 * a reflink operation while COWing an extent buffer, when allocating
+	 * pages for a new extent buffer and under memory pressure, the shrinker
+	 * may be invoked, and therefore we would deadlock by attempting to read
+	 * lock the mmap lock while we are holding already a write lock on it.
+	 */
+	if (!down_read_trylock(&inode->i_mmap_lock))
+		return 0;
+
+	write_lock(&tree->lock);
+	node = rb_first_cached(&tree->map);
+	while (node) {
+		struct extent_map *em;
+
+		em = rb_entry(node, struct extent_map, rb_node);
+		node = rb_next(node);
+		(*scanned)++;
+
+		if (em->flags & EXTENT_FLAG_PINNED)
+			goto next;
+
+		/*
+		 * If the inode is in the list of modified extents (new) and its
+		 * generation is the same (or is greater than) the current fs
+		 * generation, it means it was not yet persisted so we have to
+		 * set the full sync flag so that the next fsync will not miss
+		 * it.
+		 */
+		if (!list_empty(&em->list) && em->generation >= cur_fs_gen)
+			btrfs_set_inode_full_sync(inode);
+
+		remove_extent_mapping(inode, em);
+		trace_btrfs_extent_map_shrinker_remove_em(inode, em);
+		/* Drop the reference for the tree. */
+		free_extent_map(em);
+		nr_dropped++;
+next:
+		if (*scanned >= nr_to_scan)
+			break;
+
+		/*
+		 * Restart if we had to reschedule, and any extent maps that were
+		 * pinned before may have become unpinned after we released the
+		 * lock and took it again.
+		 */
+		if (cond_resched_rwlock_write(&tree->lock))
+			node = rb_first_cached(&tree->map);
+	}
+	write_unlock(&tree->lock);
+	up_read(&inode->i_mmap_lock);
+
+	return nr_dropped;
+}
+
+static long btrfs_scan_root(struct btrfs_root *root, long *scanned, long nr_to_scan)
+{
+	struct btrfs_fs_info *fs_info = root->fs_info;
+	struct btrfs_inode *inode;
+	long nr_dropped = 0;
+	u64 min_ino = fs_info->extent_map_shrinker_last_ino + 1;
+
+	inode = btrfs_find_first_inode(root, min_ino);
+	while (inode) {
+		nr_dropped += btrfs_scan_inode(inode, scanned, nr_to_scan);
+
+		min_ino = btrfs_ino(inode) + 1;
+		fs_info->extent_map_shrinker_last_ino = btrfs_ino(inode);
+		iput(&inode->vfs_inode);
+
+		if (*scanned >= nr_to_scan)
+			break;
+
+		cond_resched();
+		inode = btrfs_find_first_inode(root, min_ino);
+	}
+
+	if (inode) {
+		/*
+		 * There are still inodes in this root or we happened to process
+		 * the last one and reached the scan limit. In either case set
+		 * the current root to this one, so we'll resume from the next
+		 * inode if there is one or we will find out this was the last
+		 * one and move to the next root.
+		 */
+		fs_info->extent_map_shrinker_last_root = btrfs_root_id(root);
+	} else {
+		/*
+		 * No more inodes in this root, set extent_map_shrinker_last_ino to 0 so
+		 * that when processing the next root we start from its first inode.
+		 */
+		fs_info->extent_map_shrinker_last_ino = 0;
+		fs_info->extent_map_shrinker_last_root = btrfs_root_id(root) + 1;
+	}
+
+	return nr_dropped;
+}
+
+long btrfs_free_extent_maps(struct btrfs_fs_info *fs_info, long nr_to_scan)
+{
+	const u64 start_root_id = fs_info->extent_map_shrinker_last_root;
+	u64 next_root_id = start_root_id;
+	bool cycled = false;
+	long nr_dropped = 0;
+	long scanned = 0;
+
+	if (trace_btrfs_extent_map_shrinker_scan_enter_enabled()) {
+		s64 nr = percpu_counter_sum_positive(&fs_info->evictable_extent_maps);
+
+		trace_btrfs_extent_map_shrinker_scan_enter(fs_info, nr_to_scan, nr);
+	}
+
+	while (scanned < nr_to_scan) {
+		struct btrfs_root *root;
+		unsigned long count;
+
+		spin_lock(&fs_info->fs_roots_radix_lock);
+		count = radix_tree_gang_lookup(&fs_info->fs_roots_radix,
+					       (void **)&root,
+					       (unsigned long)next_root_id, 1);
+		if (count == 0) {
+			spin_unlock(&fs_info->fs_roots_radix_lock);
+			if (start_root_id > 0 && !cycled) {
+				next_root_id = 0;
+				fs_info->extent_map_shrinker_last_root = 0;
+				fs_info->extent_map_shrinker_last_ino = 0;
+				cycled = true;
+				continue;
+			}
+			break;
+		}
+		next_root_id = btrfs_root_id(root) + 1;
+		root = btrfs_grab_root(root);
+		spin_unlock(&fs_info->fs_roots_radix_lock);
+
+		if (!root)
+			continue;
+
+		if (is_fstree(btrfs_root_id(root)))
+			nr_dropped += btrfs_scan_root(root, &scanned, nr_to_scan);
+
+		btrfs_put_root(root);
+	}
+
+	if (trace_btrfs_extent_map_shrinker_scan_exit_enabled()) {
+		s64 nr = percpu_counter_sum_positive(&fs_info->evictable_extent_maps);
+
+		trace_btrfs_extent_map_shrinker_scan_exit(fs_info, nr_dropped, nr);
+	}
+
+	return nr_dropped;
+}
diff --git a/fs/btrfs/extent_map.h b/fs/btrfs/extent_map.h
index c5a098c99cc6..6d587111f73a 100644
--- a/fs/btrfs/extent_map.h
+++ b/fs/btrfs/extent_map.h
@@ -30,28 +30,77 @@ enum {
 	ENUM_BIT(EXTENT_FLAG_PREALLOC),
 	/* Logging this extent */
 	ENUM_BIT(EXTENT_FLAG_LOGGING),
-	/* Filling in a preallocated extent */
-	ENUM_BIT(EXTENT_FLAG_FILLING),
 	/* This em is merged from two or more physically adjacent ems */
 	ENUM_BIT(EXTENT_FLAG_MERGED),
 };
 
 /*
+ * This structure represents file extents and holes.
+ *
+ * Unlike on-disk file extent items, extent maps can be merged to save memory.
+ * This means members only match file extent items before any merging.
+ *
  * Keep this structure as compact as possible, as we can have really large
  * amounts of allocated extent maps at any time.
  */
 struct extent_map {
 	struct rb_node rb_node;
 
-	/* all of these are in bytes */
+	/* All of these are in bytes. */
+
+	/* File offset matching the offset of a BTRFS_EXTENT_ITEM_KEY key. */
 	u64 start;
+
+	/*
+	 * Length of the file extent.
+	 *
+	 * For non-inlined file extents it's btrfs_file_extent_item::num_bytes.
+	 * For inline extents it's sectorsize, since inline data starts at
+	 * offsetof(struct btrfs_file_extent_item, disk_bytenr) thus
+	 * btrfs_file_extent_item::num_bytes is not valid.
+	 */
 	u64 len;
-	u64 mod_start;
-	u64 mod_len;
+
+	/*
+	 * The file offset of the original file extent before splitting.
+	 *
+	 * This is an in-memory only member, matching
+	 * extent_map::start - btrfs_file_extent_item::offset for
+	 * regular/preallocated extents. EXTENT_MAP_HOLE otherwise.
+	 */
 	u64 orig_start;
+
+	/*
+	 * The full on-disk extent length, matching
+	 * btrfs_file_extent_item::disk_num_bytes.
+	 */
 	u64 orig_block_len;
+
+	/*
+	 * The decompressed size of the whole on-disk extent, matching
+	 * btrfs_file_extent_item::ram_bytes.
+	 */
 	u64 ram_bytes;
+
+	/*
+	 * The on-disk logical bytenr for the file extent.
+	 *
+	 * For compressed extents it matches btrfs_file_extent_item::disk_bytenr.
+	 * For uncompressed extents it matches
+	 * btrfs_file_extent_item::disk_bytenr + btrfs_file_extent_item::offset
+	 *
+	 * For holes it is EXTENT_MAP_HOLE and for inline extents it is
+	 * EXTENT_MAP_INLINE.
+	 */
 	u64 block_start;
+
+	/*
+	 * The on-disk length for the file extent.
+	 *
+	 * For compressed extents it matches btrfs_file_extent_item::disk_num_bytes.
+	 * For uncompressed extents it matches extent_map::len.
+	 * For holes and inline extents it's -1 and shouldn't be used.
+	 */
 	u64 block_len;
 
 	/*
@@ -124,7 +173,7 @@ static inline u64 extent_map_end(const struct extent_map *em)
 void extent_map_tree_init(struct extent_map_tree *tree);
 struct extent_map *lookup_extent_mapping(struct extent_map_tree *tree,
 					 u64 start, u64 len);
-void remove_extent_mapping(struct extent_map_tree *tree, struct extent_map *em);
+void remove_extent_mapping(struct btrfs_inode *inode, struct extent_map *em);
 int split_extent_map(struct btrfs_inode *inode, u64 start, u64 len, u64 pre,
 		     u64 new_logical);
 
@@ -133,11 +182,10 @@ void free_extent_map(struct extent_map *em);
 int __init extent_map_init(void);
 void __cold extent_map_exit(void);
 int unpin_extent_cache(struct btrfs_inode *inode, u64 start, u64 len, u64 gen);
-void clear_em_logging(struct extent_map_tree *tree, struct extent_map *em);
+void clear_em_logging(struct btrfs_inode *inode, struct extent_map *em);
 struct extent_map *search_extent_mapping(struct extent_map_tree *tree,
 					 u64 start, u64 len);
-int btrfs_add_extent_mapping(struct btrfs_fs_info *fs_info,
-			     struct extent_map_tree *em_tree,
+int btrfs_add_extent_mapping(struct btrfs_inode *inode,
 			     struct extent_map **em_in, u64 start, u64 len);
 void btrfs_drop_extent_map_range(struct btrfs_inode *inode,
 				 u64 start, u64 end,
@@ -145,5 +193,6 @@ void btrfs_drop_extent_map_range(struct btrfs_inode *inode,
 int btrfs_replace_extent_map_range(struct btrfs_inode *inode,
 				   struct extent_map *new_em,
 				   bool modified);
+long btrfs_free_extent_maps(struct btrfs_fs_info *fs_info, long nr_to_scan);
 
 #endif
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index e58fb5347e65..bce95f871750 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -430,8 +430,7 @@ blk_status_t btrfs_lookup_bio_sums(struct btrfs_bio *bbio)
 			memset(csum_dst, 0, csum_size);
 			count = 1;
 
-			if (inode->root->root_key.objectid ==
-			    BTRFS_DATA_RELOC_TREE_OBJECTID) {
+			if (btrfs_root_id(inode->root) == BTRFS_DATA_RELOC_TREE_OBJECTID) {
 				u64 file_offset = bbio->file_offset + bio_offset;
 
 				set_extent_bit(&inode->io_tree, file_offset,
@@ -450,9 +449,22 @@ blk_status_t btrfs_lookup_bio_sums(struct btrfs_bio *bbio)
 	return ret;
 }
 
+/*
+ * Search for checksums for a given logical range.
+ *
+ * @root:		The root where to look for checksums.
+ * @start:		Logical address of target checksum range.
+ * @end:		End offset (inclusive) of the target checksum range.
+ * @list:		List for adding each checksum that was found.
+ *			Can be NULL in case the caller only wants to check if
+ *			there any checksums for the range.
+ * @nowait:		Indicate if the search must be non-blocking or not.
+ *
+ * Return < 0 on error, 0 if no checksums were found, or 1 if checksums were
+ * found.
+ */
 int btrfs_lookup_csums_list(struct btrfs_root *root, u64 start, u64 end,
-			    struct list_head *list, int search_commit,
-			    bool nowait)
+			    struct list_head *list, bool nowait)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct btrfs_key key;
@@ -460,8 +472,8 @@ int btrfs_lookup_csums_list(struct btrfs_root *root, u64 start, u64 end,
 	struct extent_buffer *leaf;
 	struct btrfs_ordered_sum *sums;
 	struct btrfs_csum_item *item;
-	LIST_HEAD(tmplist);
 	int ret;
+	bool found_csums = false;
 
 	ASSERT(IS_ALIGNED(start, fs_info->sectorsize) &&
 	       IS_ALIGNED(end + 1, fs_info->sectorsize));
@@ -471,11 +483,6 @@ int btrfs_lookup_csums_list(struct btrfs_root *root, u64 start, u64 end,
 		return -ENOMEM;
 
 	path->nowait = nowait;
-	if (search_commit) {
-		path->skip_locking = 1;
-		path->reada = READA_FORWARD;
-		path->search_commit_root = 1;
-	}
 
 	key.objectid = BTRFS_EXTENT_CSUM_OBJECTID;
 	key.offset = start;
@@ -483,7 +490,7 @@ int btrfs_lookup_csums_list(struct btrfs_root *root, u64 start, u64 end,
 
 	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
 	if (ret < 0)
-		goto fail;
+		goto out;
 	if (ret > 0 && path->slots[0] > 0) {
 		leaf = path->nodes[0];
 		btrfs_item_key_to_cpu(leaf, &key, path->slots[0] - 1);
@@ -518,7 +525,7 @@ int btrfs_lookup_csums_list(struct btrfs_root *root, u64 start, u64 end,
 		if (path->slots[0] >= btrfs_header_nritems(leaf)) {
 			ret = btrfs_next_leaf(root, path);
 			if (ret < 0)
-				goto fail;
+				goto out;
 			if (ret > 0)
 				break;
 			leaf = path->nodes[0];
@@ -540,6 +547,10 @@ int btrfs_lookup_csums_list(struct btrfs_root *root, u64 start, u64 end,
 			continue;
 		}
 
+		found_csums = true;
+		if (!list)
+			goto out;
+
 		csum_end = min(csum_end, end + 1);
 		item = btrfs_item_ptr(path->nodes[0], path->slots[0],
 				      struct btrfs_csum_item);
@@ -553,7 +564,7 @@ int btrfs_lookup_csums_list(struct btrfs_root *root, u64 start, u64 end,
 				       GFP_NOFS);
 			if (!sums) {
 				ret = -ENOMEM;
-				goto fail;
+				goto out;
 			}
 
 			sums->logical = start;
@@ -567,21 +578,24 @@ int btrfs_lookup_csums_list(struct btrfs_root *root, u64 start, u64 end,
 					   bytes_to_csum_size(fs_info, size));
 
 			start += size;
-			list_add_tail(&sums->list, &tmplist);
+			list_add_tail(&sums->list, list);
 		}
 		path->slots[0]++;
 	}
-	ret = 0;
-fail:
-	while (ret < 0 && !list_empty(&tmplist)) {
-		sums = list_entry(tmplist.next, struct btrfs_ordered_sum, list);
-		list_del(&sums->list);
-		kfree(sums);
+out:
+	btrfs_free_path(path);
+	if (ret < 0) {
+		if (list) {
+			struct btrfs_ordered_sum *tmp_sums;
+
+			list_for_each_entry_safe(sums, tmp_sums, list, list)
+				kfree(sums);
+		}
+
+		return ret;
 	}
-	list_splice_tail(&tmplist, list);
 
-	btrfs_free_path(path);
-	return ret;
+	return found_csums ? 1 : 0;
 }
 
 /*
@@ -870,8 +884,8 @@ int btrfs_del_csums(struct btrfs_trans_handle *trans,
 	const u32 csum_size = fs_info->csum_size;
 	u32 blocksize_bits = fs_info->sectorsize_bits;
 
-	ASSERT(root->root_key.objectid == BTRFS_CSUM_TREE_OBJECTID ||
-	       root->root_key.objectid == BTRFS_TREE_LOG_OBJECTID);
+	ASSERT(btrfs_root_id(root) == BTRFS_CSUM_TREE_OBJECTID ||
+	       btrfs_root_id(root) == BTRFS_TREE_LOG_OBJECTID);
 
 	path = btrfs_alloc_path();
 	if (!path)
@@ -1171,7 +1185,7 @@ extend_csum:
 		 * search, etc, because log trees are temporary anyway and it
 		 * would only save a few bytes of leaf space.
 		 */
-		if (root->root_key.objectid == BTRFS_TREE_LOG_OBJECTID) {
+		if (btrfs_root_id(root) == BTRFS_TREE_LOG_OBJECTID) {
 			if (path->slots[0] + 1 >=
 			    btrfs_header_nritems(path->nodes[0])) {
 				ret = find_next_csum_offset(root, path, &next_offset);
@@ -1265,20 +1279,19 @@ void btrfs_extent_item_to_extent_map(struct btrfs_inode *inode,
 	struct extent_buffer *leaf = path->nodes[0];
 	const int slot = path->slots[0];
 	struct btrfs_key key;
-	u64 extent_start, extent_end;
+	u64 extent_start;
 	u64 bytenr;
 	u8 type = btrfs_file_extent_type(leaf, fi);
 	int compress_type = btrfs_file_extent_compression(leaf, fi);
 
 	btrfs_item_key_to_cpu(leaf, &key, slot);
 	extent_start = key.offset;
-	extent_end = btrfs_file_extent_end(path);
 	em->ram_bytes = btrfs_file_extent_ram_bytes(leaf, fi);
 	em->generation = btrfs_file_extent_generation(leaf, fi);
 	if (type == BTRFS_FILE_EXTENT_REG ||
 	    type == BTRFS_FILE_EXTENT_PREALLOC) {
 		em->start = extent_start;
-		em->len = extent_end - extent_start;
+		em->len = btrfs_file_extent_end(path) - extent_start;
 		em->orig_start = extent_start -
 			btrfs_file_extent_offset(leaf, fi);
 		em->orig_block_len = btrfs_file_extent_disk_num_bytes(leaf, fi);
@@ -1299,9 +1312,12 @@ void btrfs_extent_item_to_extent_map(struct btrfs_inode *inode,
 				em->flags |= EXTENT_FLAG_PREALLOC;
 		}
 	} else if (type == BTRFS_FILE_EXTENT_INLINE) {
+		/* Tree-checker has ensured this. */
+		ASSERT(extent_start == 0);
+
 		em->block_start = EXTENT_MAP_INLINE;
-		em->start = extent_start;
-		em->len = extent_end - extent_start;
+		em->start = 0;
+		em->len = fs_info->sectorsize;
 		/*
 		 * Initialize orig_start and block_len with the same values
 		 * as in inode.c:btrfs_get_extent().
@@ -1313,7 +1329,7 @@ void btrfs_extent_item_to_extent_map(struct btrfs_inode *inode,
 		btrfs_err(fs_info,
 			  "unknown file extent item type %d, inode %llu, offset %llu, "
 			  "root %llu", type, btrfs_ino(inode), extent_start,
-			  root->root_key.objectid);
+			  btrfs_root_id(root));
 	}
 }
 
@@ -1334,12 +1350,10 @@ u64 btrfs_file_extent_end(const struct btrfs_path *path)
 	ASSERT(key.type == BTRFS_EXTENT_DATA_KEY);
 	fi = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item);
 
-	if (btrfs_file_extent_type(leaf, fi) == BTRFS_FILE_EXTENT_INLINE) {
-		end = btrfs_file_extent_ram_bytes(leaf, fi);
-		end = ALIGN(key.offset + end, leaf->fs_info->sectorsize);
-	} else {
+	if (btrfs_file_extent_type(leaf, fi) == BTRFS_FILE_EXTENT_INLINE)
+		end = leaf->fs_info->sectorsize;
+	else
 		end = key.offset + btrfs_file_extent_num_bytes(leaf, fi);
-	}
 
 	return end;
 }
diff --git a/fs/btrfs/file-item.h b/fs/btrfs/file-item.h
index 15c05cc0fce6..557dc43d7142 100644
--- a/fs/btrfs/file-item.h
+++ b/fs/btrfs/file-item.h
@@ -68,8 +68,7 @@ int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end,
 			     struct list_head *list, int search_commit,
 			     bool nowait);
 int btrfs_lookup_csums_list(struct btrfs_root *root, u64 start, u64 end,
-			    struct list_head *list, int search_commit,
-			    bool nowait);
+			    struct list_head *list, bool nowait);
 int btrfs_lookup_csums_bitmap(struct btrfs_root *root, struct btrfs_path *path,
 			      u64 start, u64 end, u8 *csum_buf,
 			      unsigned long *csum_bitmap);
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 1640c46f2153..e764ac3f22e2 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -128,7 +128,7 @@ int btrfs_dirty_pages(struct btrfs_inode *inode, struct page **pages,
 		      struct extent_state **cached, bool noreserve)
 {
 	struct btrfs_fs_info *fs_info = inode->root->fs_info;
-	int err = 0;
+	int ret = 0;
 	int i;
 	u64 num_bytes;
 	u64 start_pos;
@@ -158,10 +158,10 @@ int btrfs_dirty_pages(struct btrfs_inode *inode, struct page **pages,
 			 EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG,
 			 cached);
 
-	err = btrfs_set_extent_delalloc(inode, start_pos, end_of_last_block,
+	ret = btrfs_set_extent_delalloc(inode, start_pos, end_of_last_block,
 					extra_bits, cached);
-	if (err)
-		return err;
+	if (ret)
+		return ret;
 
 	for (i = 0; i < num_pages; i++) {
 		struct page *p = pages[i];
@@ -206,7 +206,6 @@ int btrfs_drop_extents(struct btrfs_trans_handle *trans,
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct extent_buffer *leaf;
 	struct btrfs_file_extent_item *fi;
-	struct btrfs_ref ref = { 0 };
 	struct btrfs_key key;
 	struct btrfs_key new_key;
 	u64 ino = btrfs_ino(inode);
@@ -246,7 +245,7 @@ int btrfs_drop_extents(struct btrfs_trans_handle *trans,
 	if (args->start >= inode->disk_i_size && !args->replace_extent)
 		modify_tree = 0;
 
-	update_refs = (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID);
+	update_refs = (btrfs_root_id(root) != BTRFS_TREE_LOG_OBJECTID);
 	while (1) {
 		recow = 0;
 		ret = btrfs_lookup_file_extent(trans, root, path, ino,
@@ -373,15 +372,17 @@ next_slot:
 			btrfs_mark_buffer_dirty(trans, leaf);
 
 			if (update_refs && disk_bytenr > 0) {
-				btrfs_init_generic_ref(&ref,
-						BTRFS_ADD_DELAYED_REF,
-						disk_bytenr, num_bytes, 0,
-						root->root_key.objectid);
-				btrfs_init_data_ref(&ref,
-						root->root_key.objectid,
-						new_key.objectid,
-						args->start - extent_offset,
-						0, false);
+				struct btrfs_ref ref = {
+					.action = BTRFS_ADD_DELAYED_REF,
+					.bytenr = disk_bytenr,
+					.num_bytes = num_bytes,
+					.parent = 0,
+					.owning_root = btrfs_root_id(root),
+					.ref_root = btrfs_root_id(root),
+				};
+				btrfs_init_data_ref(&ref, new_key.objectid,
+						    args->start - extent_offset,
+						    0, false);
 				ret = btrfs_inc_extent_ref(trans, &ref);
 				if (ret) {
 					btrfs_abort_transaction(trans, ret);
@@ -464,15 +465,17 @@ delete_extent_item:
 				extent_end = ALIGN(extent_end,
 						   fs_info->sectorsize);
 			} else if (update_refs && disk_bytenr > 0) {
-				btrfs_init_generic_ref(&ref,
-						BTRFS_DROP_DELAYED_REF,
-						disk_bytenr, num_bytes, 0,
-						root->root_key.objectid);
-				btrfs_init_data_ref(&ref,
-						root->root_key.objectid,
-						key.objectid,
-						key.offset - extent_offset, 0,
-						false);
+				struct btrfs_ref ref = {
+					.action = BTRFS_DROP_DELAYED_REF,
+					.bytenr = disk_bytenr,
+					.num_bytes = num_bytes,
+					.parent = 0,
+					.owning_root = btrfs_root_id(root),
+					.ref_root = btrfs_root_id(root),
+				};
+				btrfs_init_data_ref(&ref, key.objectid,
+						    key.offset - extent_offset,
+						    0, false);
 				ret = btrfs_free_extent(trans, &ref);
 				if (ret) {
 					btrfs_abort_transaction(trans, ret);
@@ -748,10 +751,13 @@ again:
 						extent_end - split);
 		btrfs_mark_buffer_dirty(trans, leaf);
 
-		btrfs_init_generic_ref(&ref, BTRFS_ADD_DELAYED_REF, bytenr,
-				       num_bytes, 0, root->root_key.objectid);
-		btrfs_init_data_ref(&ref, root->root_key.objectid, ino,
-				    orig_offset, 0, false);
+		ref.action = BTRFS_ADD_DELAYED_REF;
+		ref.bytenr = bytenr;
+		ref.num_bytes = num_bytes;
+		ref.parent = 0;
+		ref.owning_root = btrfs_root_id(root);
+		ref.ref_root = btrfs_root_id(root);
+		btrfs_init_data_ref(&ref, ino, orig_offset, 0, false);
 		ret = btrfs_inc_extent_ref(trans, &ref);
 		if (ret) {
 			btrfs_abort_transaction(trans, ret);
@@ -774,10 +780,14 @@ again:
 
 	other_start = end;
 	other_end = 0;
-	btrfs_init_generic_ref(&ref, BTRFS_DROP_DELAYED_REF, bytenr,
-			       num_bytes, 0, root->root_key.objectid);
-	btrfs_init_data_ref(&ref, root->root_key.objectid, ino, orig_offset,
-			    0, false);
+
+	ref.action = BTRFS_DROP_DELAYED_REF;
+	ref.bytenr = bytenr;
+	ref.num_bytes = num_bytes;
+	ref.parent = 0;
+	ref.owning_root = btrfs_root_id(root);
+	ref.ref_root = btrfs_root_id(root);
+	btrfs_init_data_ref(&ref, ino, orig_offset, 0, false);
 	if (extent_mergeable(leaf, path->slots[0] + 1,
 			     ino, bytenr, orig_offset,
 			     &other_start, &other_end)) {
@@ -915,7 +925,7 @@ static noinline int prepare_pages(struct inode *inode, struct page **pages,
 	unsigned long index = pos >> PAGE_SHIFT;
 	gfp_t mask = get_prepare_gfp_flags(inode, nowait);
 	fgf_t fgp_flags = get_prepare_fgp_flags(nowait);
-	int err = 0;
+	int ret = 0;
 	int faili;
 
 	for (i = 0; i < num_pages; i++) {
@@ -925,28 +935,28 @@ again:
 		if (!pages[i]) {
 			faili = i - 1;
 			if (nowait)
-				err = -EAGAIN;
+				ret = -EAGAIN;
 			else
-				err = -ENOMEM;
+				ret = -ENOMEM;
 			goto fail;
 		}
 
-		err = set_page_extent_mapped(pages[i]);
-		if (err < 0) {
+		ret = set_page_extent_mapped(pages[i]);
+		if (ret < 0) {
 			faili = i;
 			goto fail;
 		}
 
 		if (i == 0)
-			err = prepare_uptodate_page(inode, pages[i], pos,
+			ret = prepare_uptodate_page(inode, pages[i], pos,
 						    force_uptodate);
-		if (!err && i == num_pages - 1)
-			err = prepare_uptodate_page(inode, pages[i],
+		if (!ret && i == num_pages - 1)
+			ret = prepare_uptodate_page(inode, pages[i],
 						    pos + write_bytes, false);
-		if (err) {
+		if (ret) {
 			put_page(pages[i]);
-			if (!nowait && err == -EAGAIN) {
-				err = 0;
+			if (!nowait && ret == -EAGAIN) {
+				ret = 0;
 				goto again;
 			}
 			faili = i - 1;
@@ -962,7 +972,7 @@ fail:
 		put_page(pages[faili]);
 		faili--;
 	}
-	return err;
+	return ret;
 
 }
 
@@ -1465,7 +1475,7 @@ static ssize_t btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from)
 	ssize_t written_buffered;
 	size_t prev_left = 0;
 	loff_t endbyte;
-	ssize_t err;
+	ssize_t ret;
 	unsigned int ilock_flags = 0;
 	struct iomap_dio *dio;
 
@@ -1482,9 +1492,9 @@ static ssize_t btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from)
 		ilock_flags |= BTRFS_ILOCK_SHARED;
 
 relock:
-	err = btrfs_inode_lock(BTRFS_I(inode), ilock_flags);
-	if (err < 0)
-		return err;
+	ret = btrfs_inode_lock(BTRFS_I(inode), ilock_flags);
+	if (ret < 0)
+		return ret;
 
 	/* Shared lock cannot be used with security bits set. */
 	if ((ilock_flags & BTRFS_ILOCK_SHARED) && !IS_NOSEC(inode)) {
@@ -1493,14 +1503,14 @@ relock:
 		goto relock;
 	}
 
-	err = generic_write_checks(iocb, from);
-	if (err <= 0) {
+	ret = generic_write_checks(iocb, from);
+	if (ret <= 0) {
 		btrfs_inode_unlock(BTRFS_I(inode), ilock_flags);
-		return err;
+		return ret;
 	}
 
-	err = btrfs_write_check(iocb, from, err);
-	if (err < 0) {
+	ret = btrfs_write_check(iocb, from, ret);
+	if (ret < 0) {
 		btrfs_inode_unlock(BTRFS_I(inode), ilock_flags);
 		goto out;
 	}
@@ -1552,15 +1562,15 @@ relock:
 	btrfs_inode_unlock(BTRFS_I(inode), ilock_flags);
 
 	if (IS_ERR_OR_NULL(dio))
-		err = PTR_ERR_OR_ZERO(dio);
+		ret = PTR_ERR_OR_ZERO(dio);
 	else
-		err = iomap_dio_complete(dio);
+		ret = iomap_dio_complete(dio);
 
 	/* No increment (+=) because iomap returns a cumulative value. */
-	if (err > 0)
-		written = err;
+	if (ret > 0)
+		written = ret;
 
-	if (iov_iter_count(from) > 0 && (err == -EFAULT || err > 0)) {
+	if (iov_iter_count(from) > 0 && (ret == -EFAULT || ret > 0)) {
 		const size_t left = iov_iter_count(from);
 		/*
 		 * We have more data left to write. Try to fault in as many as
@@ -1577,7 +1587,7 @@ relock:
 		 * to buffered IO in case we haven't made any progress.
 		 */
 		if (left == prev_left) {
-			err = -ENOTBLK;
+			ret = -ENOTBLK;
 		} else {
 			fault_in_iov_iter_readable(from, left);
 			prev_left = left;
@@ -1586,10 +1596,10 @@ relock:
 	}
 
 	/*
-	 * If 'err' is -ENOTBLK or we have not written all data, then it means
+	 * If 'ret' is -ENOTBLK or we have not written all data, then it means
 	 * we must fallback to buffered IO.
 	 */
-	if ((err < 0 && err != -ENOTBLK) || !iov_iter_count(from))
+	if ((ret < 0 && ret != -ENOTBLK) || !iov_iter_count(from))
 		goto out;
 
 buffered:
@@ -1600,14 +1610,14 @@ buffered:
 	 * below, we will block when flushing and waiting for the IO.
 	 */
 	if (iocb->ki_flags & IOCB_NOWAIT) {
-		err = -EAGAIN;
+		ret = -EAGAIN;
 		goto out;
 	}
 
 	pos = iocb->ki_pos;
 	written_buffered = btrfs_buffered_write(iocb, from);
 	if (written_buffered < 0) {
-		err = written_buffered;
+		ret = written_buffered;
 		goto out;
 	}
 	/*
@@ -1615,18 +1625,18 @@ buffered:
 	 * able to read what was just written.
 	 */
 	endbyte = pos + written_buffered - 1;
-	err = btrfs_fdatawrite_range(inode, pos, endbyte);
-	if (err)
+	ret = btrfs_fdatawrite_range(inode, pos, endbyte);
+	if (ret)
 		goto out;
-	err = filemap_fdatawait_range(inode->i_mapping, pos, endbyte);
-	if (err)
+	ret = filemap_fdatawait_range(inode->i_mapping, pos, endbyte);
+	if (ret)
 		goto out;
 	written += written_buffered;
 	iocb->ki_pos = pos + written_buffered;
 	invalidate_mapping_pages(file->f_mapping, pos >> PAGE_SHIFT,
 				 endbyte >> PAGE_SHIFT);
 out:
-	return err < 0 ? err : written;
+	return ret < 0 ? ret : written;
 }
 
 static ssize_t btrfs_encoded_write(struct kiocb *iocb, struct iov_iter *from,
@@ -2029,6 +2039,172 @@ out_release_extents:
 	goto out;
 }
 
+/*
+ * btrfs_page_mkwrite() is not allowed to change the file size as it gets
+ * called from a page fault handler when a page is first dirtied. Hence we must
+ * be careful to check for EOF conditions here. We set the page up correctly
+ * for a written page which means we get ENOSPC checking when writing into
+ * holes and correct delalloc and unwritten extent mapping on filesystems that
+ * support these features.
+ *
+ * We are not allowed to take the i_mutex here so we have to play games to
+ * protect against truncate races as the page could now be beyond EOF.  Because
+ * truncate_setsize() writes the inode size before removing pages, once we have
+ * the page lock we can determine safely if the page is beyond EOF. If it is not
+ * beyond EOF, then the page is guaranteed safe against truncation until we
+ * unlock the page.
+ */
+static vm_fault_t btrfs_page_mkwrite(struct vm_fault *vmf)
+{
+	struct page *page = vmf->page;
+	struct folio *folio = page_folio(page);
+	struct inode *inode = file_inode(vmf->vma->vm_file);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
+	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
+	struct btrfs_ordered_extent *ordered;
+	struct extent_state *cached_state = NULL;
+	struct extent_changeset *data_reserved = NULL;
+	unsigned long zero_start;
+	loff_t size;
+	vm_fault_t ret;
+	int ret2;
+	int reserved = 0;
+	u64 reserved_space;
+	u64 page_start;
+	u64 page_end;
+	u64 end;
+
+	ASSERT(folio_order(folio) == 0);
+
+	reserved_space = PAGE_SIZE;
+
+	sb_start_pagefault(inode->i_sb);
+	page_start = page_offset(page);
+	page_end = page_start + PAGE_SIZE - 1;
+	end = page_end;
+
+	/*
+	 * Reserving delalloc space after obtaining the page lock can lead to
+	 * deadlock. For example, if a dirty page is locked by this function
+	 * and the call to btrfs_delalloc_reserve_space() ends up triggering
+	 * dirty page write out, then the btrfs_writepages() function could
+	 * end up waiting indefinitely to get a lock on the page currently
+	 * being processed by btrfs_page_mkwrite() function.
+	 */
+	ret2 = btrfs_delalloc_reserve_space(BTRFS_I(inode), &data_reserved,
+					    page_start, reserved_space);
+	if (!ret2) {
+		ret2 = file_update_time(vmf->vma->vm_file);
+		reserved = 1;
+	}
+	if (ret2) {
+		ret = vmf_error(ret2);
+		if (reserved)
+			goto out;
+		goto out_noreserve;
+	}
+
+	/* Make the VM retry the fault. */
+	ret = VM_FAULT_NOPAGE;
+again:
+	down_read(&BTRFS_I(inode)->i_mmap_lock);
+	lock_page(page);
+	size = i_size_read(inode);
+
+	if ((page->mapping != inode->i_mapping) ||
+	    (page_start >= size)) {
+		/* Page got truncated out from underneath us. */
+		goto out_unlock;
+	}
+	wait_on_page_writeback(page);
+
+	lock_extent(io_tree, page_start, page_end, &cached_state);
+	ret2 = set_page_extent_mapped(page);
+	if (ret2 < 0) {
+		ret = vmf_error(ret2);
+		unlock_extent(io_tree, page_start, page_end, &cached_state);
+		goto out_unlock;
+	}
+
+	/*
+	 * We can't set the delalloc bits if there are pending ordered
+	 * extents.  Drop our locks and wait for them to finish.
+	 */
+	ordered = btrfs_lookup_ordered_range(BTRFS_I(inode), page_start, PAGE_SIZE);
+	if (ordered) {
+		unlock_extent(io_tree, page_start, page_end, &cached_state);
+		unlock_page(page);
+		up_read(&BTRFS_I(inode)->i_mmap_lock);
+		btrfs_start_ordered_extent(ordered);
+		btrfs_put_ordered_extent(ordered);
+		goto again;
+	}
+
+	if (page->index == ((size - 1) >> PAGE_SHIFT)) {
+		reserved_space = round_up(size - page_start, fs_info->sectorsize);
+		if (reserved_space < PAGE_SIZE) {
+			end = page_start + reserved_space - 1;
+			btrfs_delalloc_release_space(BTRFS_I(inode),
+					data_reserved, page_start,
+					PAGE_SIZE - reserved_space, true);
+		}
+	}
+
+	/*
+	 * page_mkwrite gets called when the page is firstly dirtied after it's
+	 * faulted in, but write(2) could also dirty a page and set delalloc
+	 * bits, thus in this case for space account reason, we still need to
+	 * clear any delalloc bits within this page range since we have to
+	 * reserve data&meta space before lock_page() (see above comments).
+	 */
+	clear_extent_bit(&BTRFS_I(inode)->io_tree, page_start, end,
+			  EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING |
+			  EXTENT_DEFRAG, &cached_state);
+
+	ret2 = btrfs_set_extent_delalloc(BTRFS_I(inode), page_start, end, 0,
+					&cached_state);
+	if (ret2) {
+		unlock_extent(io_tree, page_start, page_end, &cached_state);
+		ret = VM_FAULT_SIGBUS;
+		goto out_unlock;
+	}
+
+	/* Page is wholly or partially inside EOF. */
+	if (page_start + PAGE_SIZE > size)
+		zero_start = offset_in_page(size);
+	else
+		zero_start = PAGE_SIZE;
+
+	if (zero_start != PAGE_SIZE)
+		memzero_page(page, zero_start, PAGE_SIZE - zero_start);
+
+	btrfs_folio_clear_checked(fs_info, folio, page_start, PAGE_SIZE);
+	btrfs_folio_set_dirty(fs_info, folio, page_start, end + 1 - page_start);
+	btrfs_folio_set_uptodate(fs_info, folio, page_start, end + 1 - page_start);
+
+	btrfs_set_inode_last_sub_trans(BTRFS_I(inode));
+
+	unlock_extent(io_tree, page_start, page_end, &cached_state);
+	up_read(&BTRFS_I(inode)->i_mmap_lock);
+
+	btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE);
+	sb_end_pagefault(inode->i_sb);
+	extent_changeset_free(data_reserved);
+	return VM_FAULT_LOCKED;
+
+out_unlock:
+	unlock_page(page);
+	up_read(&BTRFS_I(inode)->i_mmap_lock);
+out:
+	btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE);
+	btrfs_delalloc_release_space(BTRFS_I(inode), data_reserved, page_start,
+				     reserved_space, (ret != 0));
+out_noreserve:
+	sb_end_pagefault(inode->i_sb);
+	extent_changeset_free(data_reserved);
+	return ret;
+}
+
 static const struct vm_operations_struct btrfs_file_vm_ops = {
 	.fault		= filemap_fault,
 	.map_pages	= filemap_map_pages,
@@ -2258,7 +2434,6 @@ static int btrfs_insert_replace_extent(struct btrfs_trans_handle *trans,
 	struct extent_buffer *leaf;
 	struct btrfs_key key;
 	int slot;
-	struct btrfs_ref ref = { 0 };
 	int ret;
 
 	if (replace_len == 0)
@@ -2314,15 +2489,17 @@ static int btrfs_insert_replace_extent(struct btrfs_trans_handle *trans,
 						       extent_info->qgroup_reserved,
 						       &key);
 	} else {
+		struct btrfs_ref ref = {
+			.action = BTRFS_ADD_DELAYED_REF,
+			.bytenr = extent_info->disk_offset,
+			.num_bytes = extent_info->disk_len,
+			.owning_root = btrfs_root_id(root),
+			.ref_root = btrfs_root_id(root),
+		};
 		u64 ref_offset;
 
-		btrfs_init_generic_ref(&ref, BTRFS_ADD_DELAYED_REF,
-				       extent_info->disk_offset,
-				       extent_info->disk_len, 0,
-				       root->root_key.objectid);
 		ref_offset = extent_info->file_offset - extent_info->data_offset;
-		btrfs_init_data_ref(&ref, root->root_key.objectid,
-				    btrfs_ino(inode), ref_offset, 0, false);
+		btrfs_init_data_ref(&ref, btrfs_ino(inode), ref_offset, 0, false);
 		ret = btrfs_inc_extent_ref(trans, &ref);
 	}
 
diff --git a/fs/btrfs/fs.h b/fs/btrfs/fs.h
index 93f5c57ea4e3..89f0650631cd 100644
--- a/fs/btrfs/fs.h
+++ b/fs/btrfs/fs.h
@@ -9,7 +9,6 @@
 #include <linux/compiler.h>
 #include <linux/math.h>
 #include <linux/atomic.h>
-#include <linux/blkdev.h>
 #include <linux/percpu_counter.h>
 #include <linux/completion.h>
 #include <linux/lockdep.h>
@@ -630,6 +629,10 @@ struct btrfs_fs_info {
 	s32 dirty_metadata_batch;
 	s32 delalloc_batch;
 
+	struct percpu_counter evictable_extent_maps;
+	u64 extent_map_shrinker_last_root;
+	u64 extent_map_shrinker_last_ino;
+
 	/* Protected by 'trans_lock'. */
 	struct list_head dirty_cowonly_roots;
 
diff --git a/fs/btrfs/inode-item.c b/fs/btrfs/inode-item.c
index 9c1394c0a6d7..84a94d19b22c 100644
--- a/fs/btrfs/inode-item.c
+++ b/fs/btrfs/inode-item.c
@@ -670,16 +670,18 @@ delete:
 		}
 
 		if (del_item && extent_start != 0 && !control->skip_ref_updates) {
-			struct btrfs_ref ref = { 0 };
+			struct btrfs_ref ref = {
+				.action = BTRFS_DROP_DELAYED_REF,
+				.bytenr = extent_start,
+				.num_bytes = extent_num_bytes,
+				.owning_root = btrfs_root_id(root),
+				.ref_root = btrfs_header_owner(leaf),
+			};
 
 			bytes_deleted += extent_num_bytes;
 
-			btrfs_init_generic_ref(&ref, BTRFS_DROP_DELAYED_REF,
-					extent_start, extent_num_bytes, 0,
-					root->root_key.objectid);
-			btrfs_init_data_ref(&ref, btrfs_header_owner(leaf),
-					control->ino, extent_offset,
-					root->root_key.objectid, false);
+			btrfs_init_data_ref(&ref, control->ino, extent_offset,
+					    btrfs_root_id(root), false);
 			ret = btrfs_free_extent(trans, &ref);
 			if (ret) {
 				btrfs_abort_transaction(trans, ret);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index f454ba349683..753db965f7c0 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -254,7 +254,7 @@ static void print_data_reloc_error(const struct btrfs_inode *inode, u64 file_off
 		btrfs_warn_rl(fs_info, "has data reloc tree but no running relocation");
 		btrfs_warn_rl(fs_info,
 "csum failed root %lld ino %llu off %llu csum " CSUM_FMT " expected csum " CSUM_FMT " mirror %d",
-			inode->root->root_key.objectid, btrfs_ino(inode), file_off,
+			btrfs_root_id(inode->root), btrfs_ino(inode), file_off,
 			CSUM_FMT_VALUE(csum_size, csum),
 			CSUM_FMT_VALUE(csum_size, csum_expected),
 			mirror_num);
@@ -264,7 +264,7 @@ static void print_data_reloc_error(const struct btrfs_inode *inode, u64 file_off
 	logical += file_off;
 	btrfs_warn_rl(fs_info,
 "csum failed root %lld ino %llu off %llu logical %llu csum " CSUM_FMT " expected csum " CSUM_FMT " mirror %d",
-			inode->root->root_key.objectid,
+			btrfs_root_id(inode->root),
 			btrfs_ino(inode), file_off, logical,
 			CSUM_FMT_VALUE(csum_size, csum),
 			CSUM_FMT_VALUE(csum_size, csum_expected),
@@ -331,15 +331,15 @@ static void __cold btrfs_print_data_csum_error(struct btrfs_inode *inode,
 	const u32 csum_size = root->fs_info->csum_size;
 
 	/* For data reloc tree, it's better to do a backref lookup instead. */
-	if (root->root_key.objectid == BTRFS_DATA_RELOC_TREE_OBJECTID)
+	if (btrfs_root_id(root) == BTRFS_DATA_RELOC_TREE_OBJECTID)
 		return print_data_reloc_error(inode, logical_start, csum,
 					      csum_expected, mirror_num);
 
 	/* Output without objectid, which is more meaningful */
-	if (root->root_key.objectid >= BTRFS_LAST_FREE_OBJECTID) {
+	if (btrfs_root_id(root) >= BTRFS_LAST_FREE_OBJECTID) {
 		btrfs_warn_rl(root->fs_info,
 "csum failed root %lld ino %lld off %llu csum " CSUM_FMT " expected csum " CSUM_FMT " mirror %d",
-			root->root_key.objectid, btrfs_ino(inode),
+			btrfs_root_id(root), btrfs_ino(inode),
 			logical_start,
 			CSUM_FMT_VALUE(csum_size, csum),
 			CSUM_FMT_VALUE(csum_size, csum_expected),
@@ -347,7 +347,7 @@ static void __cold btrfs_print_data_csum_error(struct btrfs_inode *inode,
 	} else {
 		btrfs_warn_rl(root->fs_info,
 "csum failed root %llu ino %llu off %llu csum " CSUM_FMT " expected csum " CSUM_FMT " mirror %d",
-			root->root_key.objectid, btrfs_ino(inode),
+			btrfs_root_id(root), btrfs_ino(inode),
 			logical_start,
 			CSUM_FMT_VALUE(csum_size, csum),
 			CSUM_FMT_VALUE(csum_size, csum_expected),
@@ -512,12 +512,13 @@ static int insert_inline_extent(struct btrfs_trans_handle *trans,
 				struct btrfs_inode *inode, bool extent_inserted,
 				size_t size, size_t compressed_size,
 				int compress_type,
-				struct page **compressed_pages,
+				struct folio *compressed_folio,
 				bool update_i_size)
 {
 	struct btrfs_root *root = inode->root;
 	struct extent_buffer *leaf;
 	struct page *page = NULL;
+	const u32 sectorsize = trans->fs_info->sectorsize;
 	char *kaddr;
 	unsigned long ptr;
 	struct btrfs_file_extent_item *ei;
@@ -525,10 +526,23 @@ static int insert_inline_extent(struct btrfs_trans_handle *trans,
 	size_t cur_size = size;
 	u64 i_size;
 
-	ASSERT((compressed_size > 0 && compressed_pages) ||
-	       (compressed_size == 0 && !compressed_pages));
+	/*
+	 * The decompressed size must still be no larger than a sector.  Under
+	 * heavy race, we can have size == 0 passed in, but that shouldn't be a
+	 * big deal and we can continue the insertion.
+	 */
+	ASSERT(size <= sectorsize);
+
+	/*
+	 * The compressed size also needs to be no larger than a sector.
+	 * That's also why we only need one page as the parameter.
+	 */
+	if (compressed_folio)
+		ASSERT(compressed_size <= sectorsize);
+	else
+		ASSERT(compressed_size == 0);
 
-	if (compressed_size && compressed_pages)
+	if (compressed_size && compressed_folio)
 		cur_size = compressed_size;
 
 	if (!extent_inserted) {
@@ -556,21 +570,10 @@ static int insert_inline_extent(struct btrfs_trans_handle *trans,
 	ptr = btrfs_file_extent_inline_start(ei);
 
 	if (compress_type != BTRFS_COMPRESS_NONE) {
-		struct page *cpage;
-		int i = 0;
-		while (compressed_size > 0) {
-			cpage = compressed_pages[i];
-			cur_size = min_t(unsigned long, compressed_size,
-				       PAGE_SIZE);
-
-			kaddr = kmap_local_page(cpage);
-			write_extent_buffer(leaf, kaddr, ptr, cur_size);
-			kunmap_local(kaddr);
+		kaddr = kmap_local_folio(compressed_folio, 0);
+		write_extent_buffer(leaf, kaddr, ptr, compressed_size);
+		kunmap_local(kaddr);
 
-			i++;
-			ptr += cur_size;
-			compressed_size -= cur_size;
-		}
 		btrfs_set_file_extent_compression(leaf, ei,
 						  compress_type);
 	} else {
@@ -611,17 +614,62 @@ fail:
 	return ret;
 }
 
+static bool can_cow_file_range_inline(struct btrfs_inode *inode,
+				      u64 offset, u64 size,
+				      size_t compressed_size)
+{
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
+	u64 data_len = (compressed_size ?: size);
+
+	/* Inline extents must start at offset 0. */
+	if (offset != 0)
+		return false;
+
+	/*
+	 * Due to the page size limit, for subpage we can only trigger the
+	 * writeback for the dirty sectors of page, that means data writeback
+	 * is doing more writeback than what we want.
+	 *
+	 * This is especially unexpected for some call sites like fallocate,
+	 * where we only increase i_size after everything is done.
+	 * This means we can trigger inline extent even if we didn't want to.
+	 * So here we skip inline extent creation completely.
+	 */
+	if (fs_info->sectorsize != PAGE_SIZE)
+		return false;
+
+	/* Inline extents are limited to sectorsize. */
+	if (size > fs_info->sectorsize)
+		return false;
+
+	/* We cannot exceed the maximum inline data size. */
+	if (data_len > BTRFS_MAX_INLINE_DATA_SIZE(fs_info))
+		return false;
+
+	/* We cannot exceed the user specified max_inline size. */
+	if (data_len > fs_info->max_inline)
+		return false;
+
+	/* Inline extents must be the entirety of the file. */
+	if (size < i_size_read(&inode->vfs_inode))
+		return false;
+
+	return true;
+}
 
 /*
  * conditionally insert an inline extent into the file.  This
  * does the checks required to make sure the data is small enough
  * to fit as an inline extent.
+ *
+ * If being used directly, you must have already checked we're allowed to cow
+ * the range by getting true from can_cow_file_range_inline().
  */
-static noinline int cow_file_range_inline(struct btrfs_inode *inode, u64 size,
-					  size_t compressed_size,
-					  int compress_type,
-					  struct page **compressed_pages,
-					  bool update_i_size)
+static noinline int __cow_file_range_inline(struct btrfs_inode *inode, u64 offset,
+					    u64 size, size_t compressed_size,
+					    int compress_type,
+					    struct folio *compressed_folio,
+					    bool update_i_size)
 {
 	struct btrfs_drop_extents_args drop_args = { 0 };
 	struct btrfs_root *root = inode->root;
@@ -631,18 +679,6 @@ static noinline int cow_file_range_inline(struct btrfs_inode *inode, u64 size,
 	int ret;
 	struct btrfs_path *path;
 
-	/*
-	 * We can create an inline extent if it ends at or beyond the current
-	 * i_size, is no larger than a sector (decompressed), and the (possibly
-	 * compressed) data fits in a leaf and the configured maximum inline
-	 * size.
-	 */
-	if (size < i_size_read(&inode->vfs_inode) ||
-	    size > fs_info->sectorsize ||
-	    data_len > BTRFS_MAX_INLINE_DATA_SIZE(fs_info) ||
-	    data_len > fs_info->max_inline)
-		return 1;
-
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
@@ -668,7 +704,7 @@ static noinline int cow_file_range_inline(struct btrfs_inode *inode, u64 size,
 
 	ret = insert_inline_extent(trans, path, inode, drop_args.extent_inserted,
 				   size, compressed_size, compress_type,
-				   compressed_pages, update_i_size);
+				   compressed_folio, update_i_size);
 	if (ret && ret != -ENOSPC) {
 		btrfs_abort_transaction(trans, ret);
 		goto out;
@@ -701,12 +737,44 @@ out:
 	return ret;
 }
 
+static noinline int cow_file_range_inline(struct btrfs_inode *inode, u64 offset,
+					  u64 end,
+					  size_t compressed_size,
+					  int compress_type,
+					  struct folio *compressed_folio,
+					  bool update_i_size)
+{
+	struct extent_state *cached = NULL;
+	unsigned long clear_flags = EXTENT_DELALLOC | EXTENT_DELALLOC_NEW |
+		EXTENT_DEFRAG | EXTENT_DO_ACCOUNTING | EXTENT_LOCKED;
+	u64 size = min_t(u64, i_size_read(&inode->vfs_inode), end + 1);
+	int ret;
+
+	if (!can_cow_file_range_inline(inode, offset, size, compressed_size))
+		return 1;
+
+	lock_extent(&inode->io_tree, offset, end, &cached);
+	ret = __cow_file_range_inline(inode, offset, size, compressed_size,
+				      compress_type, compressed_folio,
+				      update_i_size);
+	if (ret > 0) {
+		unlock_extent(&inode->io_tree, offset, end, &cached);
+		return ret;
+	}
+
+	extent_clear_unlock_delalloc(inode, offset, end, NULL, &cached,
+				     clear_flags,
+				     PAGE_UNLOCK | PAGE_START_WRITEBACK |
+				     PAGE_END_WRITEBACK);
+	return ret;
+}
+
 struct async_extent {
 	u64 start;
 	u64 ram_size;
 	u64 compressed_size;
-	struct page **pages;
-	unsigned long nr_pages;
+	struct folio **folios;
+	unsigned long nr_folios;
 	int compress_type;
 	struct list_head list;
 };
@@ -731,8 +799,8 @@ struct async_cow {
 static noinline int add_async_extent(struct async_chunk *cow,
 				     u64 start, u64 ram_size,
 				     u64 compressed_size,
-				     struct page **pages,
-				     unsigned long nr_pages,
+				     struct folio **folios,
+				     unsigned long nr_folios,
 				     int compress_type)
 {
 	struct async_extent *async_extent;
@@ -743,8 +811,8 @@ static noinline int add_async_extent(struct async_chunk *cow,
 	async_extent->start = start;
 	async_extent->ram_size = ram_size;
 	async_extent->compressed_size = compressed_size;
-	async_extent->pages = pages;
-	async_extent->nr_pages = nr_pages;
+	async_extent->folios = folios;
+	async_extent->nr_folios = nr_folios;
 	async_extent->compress_type = compress_type;
 	list_add_tail(&async_extent->list, &cow->extents);
 	return 0;
@@ -848,8 +916,8 @@ static void compress_file_range(struct btrfs_work *work)
 	u64 actual_end;
 	u64 i_size;
 	int ret = 0;
-	struct page **pages;
-	unsigned long nr_pages;
+	struct folio **folios;
+	unsigned long nr_folios;
 	unsigned long total_compressed = 0;
 	unsigned long total_in = 0;
 	unsigned int poff;
@@ -879,9 +947,9 @@ static void compress_file_range(struct btrfs_work *work)
 	barrier();
 	actual_end = min_t(u64, i_size, end + 1);
 again:
-	pages = NULL;
-	nr_pages = (end >> PAGE_SHIFT) - (start >> PAGE_SHIFT) + 1;
-	nr_pages = min_t(unsigned long, nr_pages, BTRFS_MAX_COMPRESSED_PAGES);
+	folios = NULL;
+	nr_folios = (end >> PAGE_SHIFT) - (start >> PAGE_SHIFT) + 1;
+	nr_folios = min_t(unsigned long, nr_folios, BTRFS_MAX_COMPRESSED_PAGES);
 
 	/*
 	 * we don't want to send crud past the end of i_size through
@@ -930,8 +998,8 @@ again:
 	if (!inode_need_compress(inode, start, end))
 		goto cleanup_and_bail_uncompressed;
 
-	pages = kcalloc(nr_pages, sizeof(struct page *), GFP_NOFS);
-	if (!pages) {
+	folios = kcalloc(nr_folios, sizeof(struct folio *), GFP_NOFS);
+	if (!folios) {
 		/*
 		 * Memory allocation failure is not a fatal error, we can fall
 		 * back to uncompressed code.
@@ -945,9 +1013,9 @@ again:
 		compress_type = inode->prop_compress;
 
 	/* Compression level is applied here. */
-	ret = btrfs_compress_pages(compress_type | (fs_info->compress_level << 4),
-				   mapping, start, pages, &nr_pages, &total_in,
-				   &total_compressed);
+	ret = btrfs_compress_folios(compress_type | (fs_info->compress_level << 4),
+				    mapping, start, folios, &nr_folios, &total_in,
+				    &total_compressed);
 	if (ret)
 		goto mark_incompressible;
 
@@ -957,7 +1025,7 @@ again:
 	 */
 	poff = offset_in_page(total_compressed);
 	if (poff)
-		memzero_page(pages[nr_pages - 1], poff, PAGE_SIZE - poff);
+		folio_zero_range(folios[nr_folios - 1], poff, PAGE_SIZE - poff);
 
 	/*
 	 * Try to create an inline extent.
@@ -968,43 +1036,16 @@ again:
 	 * Check cow_file_range() for why we don't even try to create inline
 	 * extent for the subpage case.
 	 */
-	if (start == 0 && fs_info->sectorsize == PAGE_SIZE) {
-		if (total_in < actual_end) {
-			ret = cow_file_range_inline(inode, actual_end, 0,
-						    BTRFS_COMPRESS_NONE, NULL,
-						    false);
-		} else {
-			ret = cow_file_range_inline(inode, actual_end,
-						    total_compressed,
-						    compress_type, pages,
-						    false);
-		}
-		if (ret <= 0) {
-			unsigned long clear_flags = EXTENT_DELALLOC |
-				EXTENT_DELALLOC_NEW | EXTENT_DEFRAG |
-				EXTENT_DO_ACCOUNTING;
-
-			if (ret < 0)
-				mapping_set_error(mapping, -EIO);
-
-			/*
-			 * inline extent creation worked or returned error,
-			 * we don't need to create any more async work items.
-			 * Unlock and free up our temp pages.
-			 *
-			 * We use DO_ACCOUNTING here because we need the
-			 * delalloc_release_metadata to be done _after_ we drop
-			 * our outstanding extent for clearing delalloc for this
-			 * range.
-			 */
-			extent_clear_unlock_delalloc(inode, start, end,
-						     NULL,
-						     clear_flags,
-						     PAGE_UNLOCK |
-						     PAGE_START_WRITEBACK |
-						     PAGE_END_WRITEBACK);
-			goto free_pages;
-		}
+	if (total_in < actual_end)
+		ret = cow_file_range_inline(inode, start, end, 0,
+					    BTRFS_COMPRESS_NONE, NULL, false);
+	else
+		ret = cow_file_range_inline(inode, start, end, total_compressed,
+					    compress_type, folios[0], false);
+	if (ret <= 0) {
+		if (ret < 0)
+			mapping_set_error(mapping, -EIO);
+		goto free_pages;
 	}
 
 	/*
@@ -1026,8 +1067,8 @@ again:
 	 * The async work queues will take care of doing actual allocation on
 	 * disk for these compressed pages, and will submit the bios.
 	 */
-	ret = add_async_extent(async_chunk, start, total_in, total_compressed, pages,
-			       nr_pages, compress_type);
+	ret = add_async_extent(async_chunk, start, total_in, total_compressed, folios,
+			       nr_folios, compress_type);
 	BUG_ON(ret);
 	if (start + total_in < end) {
 		start += total_in;
@@ -1044,12 +1085,12 @@ cleanup_and_bail_uncompressed:
 			       BTRFS_COMPRESS_NONE);
 	BUG_ON(ret);
 free_pages:
-	if (pages) {
-		for (i = 0; i < nr_pages; i++) {
-			WARN_ON(pages[i]->mapping);
-			btrfs_free_compr_page(pages[i]);
+	if (folios) {
+		for (i = 0; i < nr_folios; i++) {
+			WARN_ON(folios[i]->mapping);
+			btrfs_free_compr_folio(folios[i]);
 		}
-		kfree(pages);
+		kfree(folios);
 	}
 }
 
@@ -1057,16 +1098,16 @@ static void free_async_extent_pages(struct async_extent *async_extent)
 {
 	int i;
 
-	if (!async_extent->pages)
+	if (!async_extent->folios)
 		return;
 
-	for (i = 0; i < async_extent->nr_pages; i++) {
-		WARN_ON(async_extent->pages[i]->mapping);
-		btrfs_free_compr_page(async_extent->pages[i]);
+	for (i = 0; i < async_extent->nr_folios; i++) {
+		WARN_ON(async_extent->folios[i]->mapping);
+		btrfs_free_compr_folio(async_extent->folios[i]);
 	}
-	kfree(async_extent->pages);
-	async_extent->nr_pages = 0;
-	async_extent->pages = NULL;
+	kfree(async_extent->folios);
+	async_extent->nr_folios = 0;
+	async_extent->folios = NULL;
 }
 
 static void submit_uncompressed_range(struct btrfs_inode *inode,
@@ -1113,6 +1154,7 @@ static void submit_one_async_extent(struct async_chunk *async_chunk,
 	struct btrfs_ordered_extent *ordered;
 	struct btrfs_key ins;
 	struct page *locked_page = NULL;
+	struct extent_state *cached = NULL;
 	struct extent_map *em;
 	int ret = 0;
 	u64 start = async_extent->start;
@@ -1132,7 +1174,6 @@ static void submit_one_async_extent(struct async_chunk *async_chunk,
 		if (!(start >= locked_page_end || end <= locked_page_start))
 			locked_page = async_chunk->locked_page;
 	}
-	lock_extent(io_tree, start, end, NULL);
 
 	if (async_extent->compress_type == BTRFS_COMPRESS_NONE) {
 		submit_uncompressed_range(inode, async_extent, locked_page);
@@ -1154,6 +1195,8 @@ static void submit_one_async_extent(struct async_chunk *async_chunk,
 		goto done;
 	}
 
+	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 */
@@ -1187,11 +1230,11 @@ static void submit_one_async_extent(struct async_chunk *async_chunk,
 
 	/* Clear dirty, set writeback and unlock the pages. */
 	extent_clear_unlock_delalloc(inode, start, end,
-			NULL, EXTENT_LOCKED | EXTENT_DELALLOC,
+			NULL, &cached, EXTENT_LOCKED | EXTENT_DELALLOC,
 			PAGE_UNLOCK | PAGE_START_WRITEBACK);
 	btrfs_submit_compressed_write(ordered,
-			    async_extent->pages,	/* compressed_pages */
-			    async_extent->nr_pages,
+			    async_extent->folios,	/* compressed_folios */
+			    async_extent->nr_folios,
 			    async_chunk->write_flags, true);
 	*alloc_hint = ins.objectid + ins.offset;
 done:
@@ -1205,7 +1248,8 @@ out_free_reserve:
 	btrfs_free_reserved_extent(fs_info, ins.objectid, ins.offset, 1);
 	mapping_set_error(inode->vfs_inode.i_mapping, -EIO);
 	extent_clear_unlock_delalloc(inode, start, end,
-				     NULL, EXTENT_LOCKED | EXTENT_DELALLOC |
+				     NULL, &cached,
+				     EXTENT_LOCKED | EXTENT_DELALLOC |
 				     EXTENT_DELALLOC_NEW |
 				     EXTENT_DEFRAG | EXTENT_DO_ACCOUNTING,
 				     PAGE_UNLOCK | PAGE_START_WRITEBACK |
@@ -1215,7 +1259,7 @@ out_free_reserve:
 		kthread_associate_blkcg(NULL);
 	btrfs_debug(fs_info,
 "async extent submission failed root=%lld inode=%llu start=%llu len=%llu ret=%d",
-		    root->root_key.objectid, btrfs_ino(inode), start,
+		    btrfs_root_id(root), btrfs_ino(inode), start,
 		    async_extent->ram_size, ret);
 	kfree(async_extent);
 }
@@ -1287,6 +1331,7 @@ static noinline int cow_file_range(struct btrfs_inode *inode,
 {
 	struct btrfs_root *root = inode->root;
 	struct btrfs_fs_info *fs_info = root->fs_info;
+	struct extent_state *cached = NULL;
 	u64 alloc_hint = 0;
 	u64 orig_start = start;
 	u64 num_bytes;
@@ -1312,53 +1357,21 @@ static noinline int cow_file_range(struct btrfs_inode *inode,
 
 	inode_should_defrag(inode, start, end, num_bytes, SZ_64K);
 
-	/*
-	 * Due to the page size limit, for subpage we can only trigger the
-	 * writeback for the dirty sectors of page, that means data writeback
-	 * is doing more writeback than what we want.
-	 *
-	 * This is especially unexpected for some call sites like fallocate,
-	 * where we only increase i_size after everything is done.
-	 * This means we can trigger inline extent even if we didn't want to.
-	 * So here we skip inline extent creation completely.
-	 */
-	if (start == 0 && fs_info->sectorsize == PAGE_SIZE && !no_inline) {
-		u64 actual_end = min_t(u64, i_size_read(&inode->vfs_inode),
-				       end + 1);
-
+	if (!no_inline) {
 		/* lets try to make an inline extent */
-		ret = cow_file_range_inline(inode, actual_end, 0,
+		ret = cow_file_range_inline(inode, start, end, 0,
 					    BTRFS_COMPRESS_NONE, NULL, false);
-		if (ret == 0) {
-			/*
-			 * We use DO_ACCOUNTING here because we need the
-			 * delalloc_release_metadata to be run _after_ we drop
-			 * our outstanding extent for clearing delalloc for this
-			 * range.
-			 */
-			extent_clear_unlock_delalloc(inode, start, end,
-				     locked_page,
-				     EXTENT_LOCKED | EXTENT_DELALLOC |
-				     EXTENT_DELALLOC_NEW | EXTENT_DEFRAG |
-				     EXTENT_DO_ACCOUNTING, PAGE_UNLOCK |
-				     PAGE_START_WRITEBACK | PAGE_END_WRITEBACK);
+		if (ret <= 0) {
 			/*
-			 * locked_page is locked by the caller of
-			 * writepage_delalloc(), not locked by
-			 * __process_pages_contig().
+			 * We succeeded, return 1 so the caller knows we're done
+			 * with this page and already handled the IO.
 			 *
-			 * We can't let __process_pages_contig() to unlock it,
-			 * as it doesn't have any subpage::writers recorded.
-			 *
-			 * Here we manually unlock the page, since the caller
-			 * can't determine if it's an inline extent or a
-			 * compressed extent.
+			 * If there was an error then cow_file_range_inline() has
+			 * already done the cleanup.
 			 */
-			unlock_page(locked_page);
-			ret = 1;
+			if (ret == 0)
+				ret = 1;
 			goto done;
-		} else if (ret < 0) {
-			goto out_unlock;
 		}
 	}
 
@@ -1418,6 +1431,10 @@ static noinline int cow_file_range(struct btrfs_inode *inode,
 		extent_reserved = true;
 
 		ram_size = ins.offset;
+
+		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 */
@@ -1427,6 +1444,8 @@ static noinline int cow_file_range(struct btrfs_inode *inode,
 				  BTRFS_COMPRESS_NONE, /* compress_type */
 				  BTRFS_ORDERED_REGULAR /* type */);
 		if (IS_ERR(em)) {
+			unlock_extent(&inode->io_tree, start,
+				      start + ram_size - 1, &cached);
 			ret = PTR_ERR(em);
 			goto out_reserve;
 		}
@@ -1437,6 +1456,8 @@ static noinline int cow_file_range(struct btrfs_inode *inode,
 					0, 1 << BTRFS_ORDERED_REGULAR,
 					BTRFS_COMPRESS_NONE);
 		if (IS_ERR(ordered)) {
+			unlock_extent(&inode->io_tree, start,
+				      start + ram_size - 1, &cached);
 			ret = PTR_ERR(ordered);
 			goto out_drop_extent_cache;
 		}
@@ -1476,7 +1497,7 @@ static noinline int cow_file_range(struct btrfs_inode *inode,
 		page_ops |= PAGE_SET_ORDERED;
 
 		extent_clear_unlock_delalloc(inode, start, start + ram_size - 1,
-					     locked_page,
+					     locked_page, &cached,
 					     EXTENT_LOCKED | EXTENT_DELALLOC,
 					     page_ops);
 		if (num_bytes < cur_alloc_size)
@@ -1535,10 +1556,17 @@ out_unlock:
 		if (!locked_page)
 			mapping_set_error(inode->vfs_inode.i_mapping, ret);
 		extent_clear_unlock_delalloc(inode, orig_start, start - 1,
-					     locked_page, 0, page_ops);
+					     locked_page, NULL, 0, page_ops);
 	}
 
 	/*
+	 * At this point we're unlocked, we want to make sure we're only
+	 * clearing these flags under the extent lock, so lock the rest of the
+	 * range and clear everything up.
+	 */
+	lock_extent(&inode->io_tree, start, end, NULL);
+
+	/*
 	 * For the range (2). If we reserved an extent for our delalloc range
 	 * (or a subrange) and failed to create the respective ordered extent,
 	 * then it means that when we reserved the extent we decremented the
@@ -1551,7 +1579,7 @@ out_unlock:
 	if (extent_reserved) {
 		extent_clear_unlock_delalloc(inode, start,
 					     start + cur_alloc_size - 1,
-					     locked_page,
+					     locked_page, &cached,
 					     clear_bits,
 					     page_ops);
 		start += cur_alloc_size;
@@ -1566,7 +1594,7 @@ out_unlock:
 	if (start < end) {
 		clear_bits |= EXTENT_CLEAR_DATA_RESV;
 		extent_clear_unlock_delalloc(inode, start, end, locked_page,
-					     clear_bits, page_ops);
+					     &cached, clear_bits, page_ops);
 	}
 	return ret;
 }
@@ -1639,7 +1667,6 @@ static bool run_delalloc_compressed(struct btrfs_inode *inode,
 	if (!ctx)
 		return false;
 
-	unlock_extent(&inode->io_tree, start, end, NULL);
 	set_bit(BTRFS_INODE_HAS_ASYNC_EXTENT, &inode->runtime_flags);
 
 	async_chunk = ctx->chunks;
@@ -1733,29 +1760,6 @@ static noinline int run_delalloc_cow(struct btrfs_inode *inode,
 	return 1;
 }
 
-static noinline int csum_exist_in_range(struct btrfs_fs_info *fs_info,
-					u64 bytenr, u64 num_bytes, bool nowait)
-{
-	struct btrfs_root *csum_root = btrfs_csum_root(fs_info, bytenr);
-	struct btrfs_ordered_sum *sums;
-	int ret;
-	LIST_HEAD(list);
-
-	ret = btrfs_lookup_csums_list(csum_root, bytenr, bytenr + num_bytes - 1,
-				      &list, 0, nowait);
-	if (ret == 0 && list_empty(&list))
-		return 0;
-
-	while (!list_empty(&list)) {
-		sums = list_entry(list.next, struct btrfs_ordered_sum, list);
-		list_del(&sums->list);
-		kfree(sums);
-	}
-	if (ret < 0)
-		return ret;
-	return 1;
-}
-
 static int fallback_to_cow(struct btrfs_inode *inode, struct page *locked_page,
 			   const u64 start, const u64 end)
 {
@@ -1763,6 +1767,7 @@ static int fallback_to_cow(struct btrfs_inode *inode, struct page *locked_page,
 	const bool is_reloc_ino = btrfs_is_data_reloc_root(inode->root);
 	const u64 range_bytes = end + 1 - start;
 	struct extent_io_tree *io_tree = &inode->io_tree;
+	struct extent_state *cached_state = NULL;
 	u64 range_start = start;
 	u64 count;
 	int ret;
@@ -1799,6 +1804,7 @@ static int fallback_to_cow(struct btrfs_inode *inode, struct page *locked_page,
 	 * group that contains that extent to RO mode and therefore force COW
 	 * when starting writeback.
 	 */
+	lock_extent(io_tree, start, end, &cached_state);
 	count = count_range_bits(io_tree, &range_start, end, range_bytes,
 				 EXTENT_NORESERVE, 0, NULL);
 	if (count > 0 || is_space_ino || is_reloc_ino) {
@@ -1817,6 +1823,7 @@ static int fallback_to_cow(struct btrfs_inode *inode, struct page *locked_page,
 			clear_extent_bit(io_tree, start, end, EXTENT_NORESERVE,
 					 NULL);
 	}
+	unlock_extent(io_tree, start, end, &cached_state);
 
 	/*
 	 * Don't try to create inline extents, as a mix of inline extent that
@@ -1870,6 +1877,7 @@ static int can_nocow_file_extent(struct btrfs_path *path,
 	struct extent_buffer *leaf = path->nodes[0];
 	struct btrfs_root *root = inode->root;
 	struct btrfs_file_extent_item *fi;
+	struct btrfs_root *csum_root;
 	u64 extent_end;
 	u8 extent_type;
 	int can_nocow = 0;
@@ -1930,7 +1938,7 @@ static int can_nocow_file_extent(struct btrfs_path *path,
 	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
+		 * btrfs_lookup_csums_list() call below we will end up allocating
 		 * another path. So free the path to avoid unnecessary extra
 		 * memory usage.
 		 */
@@ -1951,8 +1959,11 @@ static int can_nocow_file_extent(struct btrfs_path *path,
 	 * 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,
-				  nowait);
+
+	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,
+				      NULL, nowait);
 	WARN_ON_ONCE(ret > 0 && is_freespace_inode);
 	if (ret != 0)
 		goto out;
@@ -2002,12 +2013,13 @@ static noinline int run_delalloc_nocow(struct btrfs_inode *inode,
 	nocow_args.end = end;
 	nocow_args.writeback_path = true;
 
-	while (1) {
+	while (cur_offset <= end) {
 		struct btrfs_block_group *nocow_bg = NULL;
 		struct btrfs_ordered_extent *ordered;
 		struct btrfs_key found_key;
 		struct btrfs_file_extent_item *fi;
 		struct extent_buffer *leaf;
+		struct extent_state *cached_state = NULL;
 		u64 extent_end;
 		u64 ram_bytes;
 		u64 nocow_end;
@@ -2145,6 +2157,8 @@ must_cow:
 		}
 
 		nocow_end = cur_offset + nocow_args.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;
@@ -2158,6 +2172,8 @@ must_cow:
 					  ram_bytes, BTRFS_COMPRESS_NONE,
 					  BTRFS_ORDERED_PREALLOC);
 			if (IS_ERR(em)) {
+				unlock_extent(&inode->io_tree, cur_offset,
+					      nocow_end, &cached_state);
 				btrfs_dec_nocow_writers(nocow_bg);
 				ret = PTR_ERR(em);
 				goto error;
@@ -2178,6 +2194,8 @@ must_cow:
 				btrfs_drop_extent_map_range(inode, cur_offset,
 							    nocow_end, false);
 			}
+			unlock_extent(&inode->io_tree, cur_offset,
+				      nocow_end, &cached_state);
 			ret = PTR_ERR(ordered);
 			goto error;
 		}
@@ -2192,8 +2210,8 @@ must_cow:
 		btrfs_put_ordered_extent(ordered);
 
 		extent_clear_unlock_delalloc(inode, cur_offset, nocow_end,
-					     locked_page, EXTENT_LOCKED |
-					     EXTENT_DELALLOC |
+					     locked_page, &cached_state,
+					     EXTENT_LOCKED | EXTENT_DELALLOC |
 					     EXTENT_CLEAR_DATA_RESV,
 					     PAGE_UNLOCK | PAGE_SET_ORDERED);
 
@@ -2206,8 +2224,6 @@ must_cow:
 		 */
 		if (ret)
 			goto error;
-		if (cur_offset > end)
-			break;
 	}
 	btrfs_release_path(path);
 
@@ -2233,13 +2249,23 @@ error:
 	 */
 	if (cow_start != (u64)-1)
 		cur_offset = cow_start;
-	if (cur_offset < end)
+
+	/*
+	 * We need to lock the extent here because we're clearing DELALLOC and
+	 * we're not locked at this point.
+	 */
+	if (cur_offset < end) {
+		struct extent_state *cached = NULL;
+
+		lock_extent(&inode->io_tree, cur_offset, end, &cached);
 		extent_clear_unlock_delalloc(inode, cur_offset, end,
-					     locked_page, EXTENT_LOCKED |
-					     EXTENT_DELALLOC | EXTENT_DEFRAG |
+					     locked_page, &cached,
+					     EXTENT_LOCKED | EXTENT_DELALLOC |
+					     EXTENT_DEFRAG |
 					     EXTENT_DO_ACCOUNTING, PAGE_UNLOCK |
 					     PAGE_START_WRITEBACK |
 					     PAGE_END_WRITEBACK);
+	}
 	btrfs_free_path(path);
 	return ret;
 }
@@ -3181,7 +3207,6 @@ int btrfs_finish_one_ordered(struct btrfs_ordered_extent *ordered_extent)
 		btrfs_abort_transaction(trans, ret);
 		goto out;
 	}
-	ret = 0;
 out:
 	clear_extent_bit(&inode->io_tree, start, end, clear_bits,
 			 &cached_state);
@@ -3200,9 +3225,8 @@ out:
 		 * set the mapping error, so we need to set it if we're the ones
 		 * marking this ordered extent as failed.
 		 */
-		if (ret && !test_and_set_bit(BTRFS_ORDERED_IOERR,
-					     &ordered_extent->flags))
-			mapping_set_error(ordered_extent->inode->i_mapping, -EIO);
+		if (ret)
+			btrfs_mark_ordered_extent_error(ordered_extent);
 
 		if (truncated)
 			unwritten_start += logical_len;
@@ -3256,7 +3280,7 @@ out:
 			 * Actually free the qgroup rsv which was released when
 			 * the ordered extent was created.
 			 */
-			btrfs_qgroup_free_refroot(fs_info, inode->root->root_key.objectid,
+			btrfs_qgroup_free_refroot(fs_info, btrfs_root_id(inode->root),
 						  ordered_extent->qgroup_rsv,
 						  BTRFS_QGROUP_RSV_DATA);
 		}
@@ -3923,7 +3947,7 @@ cache_acl:
 			btrfs_err(fs_info,
 				  "error loading props for ino %llu (root %llu): %d",
 				  btrfs_ino(BTRFS_I(inode)),
-				  root->root_key.objectid, ret);
+				  btrfs_root_id(root), ret);
 	}
 	if (path != in_path)
 		btrfs_free_path(path);
@@ -4282,7 +4306,7 @@ static int btrfs_unlink_subvol(struct btrfs_trans_handle *trans,
 	/* This needs to handle no-key deletions later on */
 
 	if (btrfs_ino(inode) == BTRFS_FIRST_FREE_OBJECTID) {
-		objectid = inode->root->root_key.objectid;
+		objectid = btrfs_root_id(inode->root);
 	} else if (btrfs_ino(inode) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID) {
 		objectid = inode->location.objectid;
 	} else {
@@ -4340,7 +4364,7 @@ static int btrfs_unlink_subvol(struct btrfs_trans_handle *trans,
 		btrfs_release_path(path);
 	} else {
 		ret = btrfs_del_root_ref(trans, objectid,
-					 root->root_key.objectid, dir_ino,
+					 btrfs_root_id(root), dir_ino,
 					 &index, &fname.disk_name);
 		if (ret) {
 			btrfs_abort_transaction(trans, ret);
@@ -4390,7 +4414,7 @@ static noinline int may_destroy_subvol(struct btrfs_root *root)
 				   dir_id, &name, 0);
 	if (di && !IS_ERR(di)) {
 		btrfs_dir_item_key_to_cpu(path->nodes[0], di, &key);
-		if (key.objectid == root->root_key.objectid) {
+		if (key.objectid == btrfs_root_id(root)) {
 			ret = -EPERM;
 			btrfs_err(fs_info,
 				  "deleting default subvolume %llu is not allowed",
@@ -4400,7 +4424,7 @@ static noinline int may_destroy_subvol(struct btrfs_root *root)
 		btrfs_release_path(path);
 	}
 
-	key.objectid = root->root_key.objectid;
+	key.objectid = btrfs_root_id(root);
 	key.type = BTRFS_ROOT_REF_KEY;
 	key.offset = (u64)-1;
 
@@ -4420,8 +4444,7 @@ static noinline int may_destroy_subvol(struct btrfs_root *root)
 	if (path->slots[0] > 0) {
 		path->slots[0]--;
 		btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
-		if (key.objectid == root->root_key.objectid &&
-		    key.type == BTRFS_ROOT_REF_KEY)
+		if (key.objectid == btrfs_root_id(root) && key.type == BTRFS_ROOT_REF_KEY)
 			ret = -ENOTEMPTY;
 	}
 out:
@@ -4433,64 +4456,26 @@ out:
 static void btrfs_prune_dentries(struct btrfs_root *root)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
-	struct rb_node *node;
-	struct rb_node *prev;
-	struct btrfs_inode *entry;
-	struct inode *inode;
-	u64 objectid = 0;
+	struct btrfs_inode *inode;
+	u64 min_ino = 0;
 
 	if (!BTRFS_FS_ERROR(fs_info))
 		WARN_ON(btrfs_root_refs(&root->root_item) != 0);
 
-	spin_lock(&root->inode_lock);
-again:
-	node = root->inode_tree.rb_node;
-	prev = NULL;
-	while (node) {
-		prev = node;
-		entry = rb_entry(node, struct btrfs_inode, rb_node);
+	inode = btrfs_find_first_inode(root, min_ino);
+	while (inode) {
+		if (atomic_read(&inode->vfs_inode.i_count) > 1)
+			d_prune_aliases(&inode->vfs_inode);
 
-		if (objectid < btrfs_ino(entry))
-			node = node->rb_left;
-		else if (objectid > btrfs_ino(entry))
-			node = node->rb_right;
-		else
-			break;
-	}
-	if (!node) {
-		while (prev) {
-			entry = rb_entry(prev, struct btrfs_inode, rb_node);
-			if (objectid <= btrfs_ino(entry)) {
-				node = prev;
-				break;
-			}
-			prev = rb_next(prev);
-		}
-	}
-	while (node) {
-		entry = rb_entry(node, struct btrfs_inode, rb_node);
-		objectid = btrfs_ino(entry) + 1;
-		inode = igrab(&entry->vfs_inode);
-		if (inode) {
-			spin_unlock(&root->inode_lock);
-			if (atomic_read(&inode->i_count) > 1)
-				d_prune_aliases(inode);
-			/*
-			 * btrfs_drop_inode will have it removed from the inode
-			 * cache when its usage count hits zero.
-			 */
-			iput(inode);
-			cond_resched();
-			spin_lock(&root->inode_lock);
-			goto again;
-		}
-
-		if (cond_resched_lock(&root->inode_lock))
-			goto again;
-
-		node = rb_next(node);
+		min_ino = btrfs_ino(inode) + 1;
+		/*
+		 * btrfs_drop_inode() will have it removed from the inode
+		 * cache when its usage count hits zero.
+		 */
+		iput(&inode->vfs_inode);
+		cond_resched();
+		inode = btrfs_find_first_inode(root, min_ino);
 	}
-	spin_unlock(&root->inode_lock);
 }
 
 int btrfs_delete_subvolume(struct btrfs_inode *dir, struct dentry *dentry)
@@ -4517,7 +4502,7 @@ int btrfs_delete_subvolume(struct btrfs_inode *dir, struct dentry *dentry)
 		spin_unlock(&dest->root_item_lock);
 		btrfs_warn(fs_info,
 			   "attempt to delete subvolume %llu during send",
-			   dest->root_key.objectid);
+			   btrfs_root_id(dest));
 		ret = -EPERM;
 		goto out_up_write;
 	}
@@ -4525,7 +4510,7 @@ int btrfs_delete_subvolume(struct btrfs_inode *dir, struct dentry *dentry)
 		spin_unlock(&dest->root_item_lock);
 		btrfs_warn(fs_info,
 			   "attempt to delete subvolume %llu with active swapfile",
-			   root->root_key.objectid);
+			   btrfs_root_id(root));
 		ret = -EPERM;
 		goto out_up_write;
 	}
@@ -4586,7 +4571,7 @@ int btrfs_delete_subvolume(struct btrfs_inode *dir, struct dentry *dentry)
 	if (!test_and_set_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &dest->state)) {
 		ret = btrfs_insert_orphan_item(trans,
 					fs_info->tree_root,
-					dest->root_key.objectid);
+					btrfs_root_id(dest));
 		if (ret) {
 			btrfs_abort_transaction(trans, ret);
 			goto out_end_trans;
@@ -4594,8 +4579,7 @@ int btrfs_delete_subvolume(struct btrfs_inode *dir, struct dentry *dentry)
 	}
 
 	ret = btrfs_uuid_tree_remove(trans, dest->root_item.uuid,
-				  BTRFS_UUID_KEY_SUBVOL,
-				  dest->root_key.objectid);
+				     BTRFS_UUID_KEY_SUBVOL, btrfs_root_id(dest));
 	if (ret && ret != -ENOENT) {
 		btrfs_abort_transaction(trans, ret);
 		goto out_end_trans;
@@ -4604,7 +4588,7 @@ int btrfs_delete_subvolume(struct btrfs_inode *dir, struct dentry *dentry)
 		ret = btrfs_uuid_tree_remove(trans,
 					  dest->root_item.received_uuid,
 					  BTRFS_UUID_KEY_RECEIVED_SUBVOL,
-					  dest->root_key.objectid);
+					  btrfs_root_id(dest));
 		if (ret && ret != -ENOENT) {
 			btrfs_abort_transaction(trans, ret);
 			goto out_end_trans;
@@ -4645,7 +4629,7 @@ static int btrfs_rmdir(struct inode *dir, struct dentry *dentry)
 {
 	struct inode *inode = d_inode(dentry);
 	struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info;
-	int err = 0;
+	int ret = 0;
 	struct btrfs_trans_handle *trans;
 	u64 last_unlink_trans;
 	struct fscrypt_name fname;
@@ -4661,33 +4645,33 @@ static int btrfs_rmdir(struct inode *dir, struct dentry *dentry)
 		return btrfs_delete_subvolume(BTRFS_I(dir), dentry);
 	}
 
-	err = fscrypt_setup_filename(dir, &dentry->d_name, 1, &fname);
-	if (err)
-		return err;
+	ret = fscrypt_setup_filename(dir, &dentry->d_name, 1, &fname);
+	if (ret)
+		return ret;
 
 	/* This needs to handle no-key deletions later on */
 
 	trans = __unlink_start_trans(BTRFS_I(dir));
 	if (IS_ERR(trans)) {
-		err = PTR_ERR(trans);
+		ret = PTR_ERR(trans);
 		goto out_notrans;
 	}
 
 	if (unlikely(btrfs_ino(BTRFS_I(inode)) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)) {
-		err = btrfs_unlink_subvol(trans, BTRFS_I(dir), dentry);
+		ret = btrfs_unlink_subvol(trans, BTRFS_I(dir), dentry);
 		goto out;
 	}
 
-	err = btrfs_orphan_add(trans, BTRFS_I(inode));
-	if (err)
+	ret = btrfs_orphan_add(trans, BTRFS_I(inode));
+	if (ret)
 		goto out;
 
 	last_unlink_trans = BTRFS_I(inode)->last_unlink_trans;
 
 	/* now the directory is empty */
-	err = btrfs_unlink_inode(trans, BTRFS_I(dir), BTRFS_I(d_inode(dentry)),
+	ret = btrfs_unlink_inode(trans, BTRFS_I(dir), BTRFS_I(d_inode(dentry)),
 				 &fname.disk_name);
-	if (!err) {
+	if (!ret) {
 		btrfs_i_size_write(BTRFS_I(inode), 0);
 		/*
 		 * Propagate the last_unlink_trans value of the deleted dir to
@@ -4709,7 +4693,7 @@ out_notrans:
 	btrfs_btree_balance_dirty(fs_info);
 	fscrypt_free_filename(&fname);
 
-	return err;
+	return ret;
 }
 
 /*
@@ -4933,16 +4917,16 @@ int btrfs_cont_expand(struct btrfs_inode *inode, loff_t oldsize, loff_t size)
 	u64 last_byte;
 	u64 cur_offset;
 	u64 hole_size;
-	int err = 0;
+	int ret = 0;
 
 	/*
 	 * If our size started in the middle of a block we need to zero out the
 	 * rest of the block before we expand the i_size, otherwise we could
 	 * expose stale data.
 	 */
-	err = btrfs_truncate_block(inode, oldsize, 0, 0);
-	if (err)
-		return err;
+	ret = btrfs_truncate_block(inode, oldsize, 0, 0);
+	if (ret)
+		return ret;
 
 	if (size <= hole_start)
 		return 0;
@@ -4953,7 +4937,7 @@ int btrfs_cont_expand(struct btrfs_inode *inode, loff_t oldsize, loff_t size)
 	while (1) {
 		em = btrfs_get_extent(inode, NULL, cur_offset, block_end - cur_offset);
 		if (IS_ERR(em)) {
-			err = PTR_ERR(em);
+			ret = PTR_ERR(em);
 			em = NULL;
 			break;
 		}
@@ -4964,13 +4948,13 @@ int btrfs_cont_expand(struct btrfs_inode *inode, loff_t oldsize, loff_t size)
 		if (!(em->flags & EXTENT_FLAG_PREALLOC)) {
 			struct extent_map *hole_em;
 
-			err = maybe_insert_hole(inode, cur_offset, hole_size);
-			if (err)
+			ret = maybe_insert_hole(inode, cur_offset, hole_size);
+			if (ret)
 				break;
 
-			err = btrfs_inode_set_file_extent_range(inode,
+			ret = btrfs_inode_set_file_extent_range(inode,
 							cur_offset, hole_size);
-			if (err)
+			if (ret)
 				break;
 
 			hole_em = alloc_extent_map();
@@ -4991,12 +4975,12 @@ int btrfs_cont_expand(struct btrfs_inode *inode, loff_t oldsize, loff_t size)
 			hole_em->ram_bytes = hole_size;
 			hole_em->generation = btrfs_get_fs_generation(fs_info);
 
-			err = btrfs_replace_extent_map_range(inode, hole_em, true);
+			ret = btrfs_replace_extent_map_range(inode, hole_em, true);
 			free_extent_map(hole_em);
 		} else {
-			err = btrfs_inode_set_file_extent_range(inode,
+			ret = btrfs_inode_set_file_extent_range(inode,
 							cur_offset, hole_size);
-			if (err)
+			if (ret)
 				break;
 		}
 next:
@@ -5008,7 +4992,7 @@ next:
 	}
 	free_extent_map(em);
 	unlock_extent(io_tree, hole_start, block_end - 1, &cached_state);
-	return err;
+	return ret;
 }
 
 static int btrfs_setsize(struct inode *inode, struct iattr *attr)
@@ -5284,7 +5268,7 @@ void btrfs_evict_inode(struct inode *inode)
 
 	if (inode->i_nlink &&
 	    ((btrfs_root_refs(&root->root_item) != 0 &&
-	      root->root_key.objectid != BTRFS_ROOT_TREE_OBJECTID) ||
+	      btrfs_root_id(root) != BTRFS_ROOT_TREE_OBJECTID) ||
 	     btrfs_is_free_space_inode(BTRFS_I(inode))))
 		goto out;
 
@@ -5296,7 +5280,7 @@ void btrfs_evict_inode(struct inode *inode)
 
 	if (inode->i_nlink > 0) {
 		BUG_ON(btrfs_root_refs(&root->root_item) != 0 &&
-		       root->root_key.objectid != BTRFS_ROOT_TREE_OBJECTID);
+		       btrfs_root_id(root) != BTRFS_ROOT_TREE_OBJECTID);
 		goto out;
 	}
 
@@ -5468,7 +5452,7 @@ static int fixup_tree_root_location(struct btrfs_fs_info *fs_info,
 	}
 
 	err = -ENOENT;
-	key.objectid = dir->root->root_key.objectid;
+	key.objectid = btrfs_root_id(dir->root);
 	key.type = BTRFS_ROOT_REF_KEY;
 	key.offset = location->objectid;
 
@@ -6427,8 +6411,7 @@ int btrfs_create_new_inode(struct btrfs_trans_handle *trans,
 	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);
+			  btrfs_ino(BTRFS_I(inode)), btrfs_root_id(root), ret);
 	}
 
 	/*
@@ -6501,7 +6484,7 @@ int btrfs_add_link(struct btrfs_trans_handle *trans,
 
 	if (unlikely(ino == BTRFS_FIRST_FREE_OBJECTID)) {
 		ret = btrfs_add_root_ref(trans, key.objectid,
-					 root->root_key.objectid, parent_ino,
+					 btrfs_root_id(root), parent_ino,
 					 index, name);
 	} else if (add_backref) {
 		ret = btrfs_insert_inode_ref(trans, root, name,
@@ -6544,7 +6527,7 @@ fail_dir_item:
 		u64 local_index;
 		int err;
 		err = btrfs_del_root_ref(trans, key.objectid,
-					 root->root_key.objectid, parent_ino,
+					 btrfs_root_id(root), parent_ino,
 					 &local_index, name);
 		if (err)
 			btrfs_abort_transaction(trans, err);
@@ -6642,7 +6625,7 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
 	int drop_inode = 0;
 
 	/* do not allow sys_link's with other subvols of the same device */
-	if (root->root_key.objectid != BTRFS_I(inode)->root->root_key.objectid)
+	if (btrfs_root_id(root) != btrfs_root_id(BTRFS_I(inode)->root))
 		return -EXDEV;
 
 	if (inode->i_nlink >= BTRFS_LINK_MAX)
@@ -6989,7 +6972,7 @@ insert:
 	}
 
 	write_lock(&em_tree->lock);
-	ret = btrfs_add_extent_mapping(fs_info, em_tree, &em, start, len);
+	ret = btrfs_add_extent_mapping(inode, &em, start, len);
 	write_unlock(&em_tree->lock);
 out:
 	btrfs_free_path(path);
@@ -7316,11 +7299,49 @@ static struct extent_map *create_io_em(struct btrfs_inode *inode, u64 start,
 	struct extent_map *em;
 	int ret;
 
+	/*
+	 * Note the missing NOCOW type.
+	 *
+	 * For pure NOCOW writes, we should not create an io extent map, but
+	 * just reusing the existing one.
+	 * Only PREALLOC writes (NOCOW write into preallocated range) can
+	 * create an io extent map.
+	 */
 	ASSERT(type == BTRFS_ORDERED_PREALLOC ||
 	       type == BTRFS_ORDERED_COMPRESSED ||
-	       type == BTRFS_ORDERED_NOCOW ||
 	       type == BTRFS_ORDERED_REGULAR);
 
+	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);
+		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);
+
+		/* Since it's a new extent, we should not have any offset. */
+		ASSERT(orig_start == start);
+		break;
+	case BTRFS_ORDERED_COMPRESSED:
+		/* Must be compressed. */
+		ASSERT(compress_type != BTRFS_COMPRESS_NONE);
+
+		/*
+		 * Encoded write can make us to refer to part of the
+		 * uncompressed extent.
+		 */
+		ASSERT(len <= ram_bytes);
+		break;
+	}
+
 	em = alloc_extent_map();
 	if (!em)
 		return ERR_PTR(-ENOMEM);
@@ -7334,9 +7355,7 @@ static struct extent_map *create_io_em(struct btrfs_inode *inode, u64 start,
 	em->ram_bytes = ram_bytes;
 	em->generation = -1;
 	em->flags |= EXTENT_FLAG_PINNED;
-	if (type == BTRFS_ORDERED_PREALLOC)
-		em->flags |= EXTENT_FLAG_FILLING;
-	else if (type == BTRFS_ORDERED_COMPRESSED)
+	if (type == BTRFS_ORDERED_COMPRESSED)
 		extent_map_set_compression(em, compress_type);
 
 	ret = btrfs_replace_extent_map_range(inode, em, true);
@@ -7923,17 +7942,6 @@ static int btrfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 	return ret;
 }
 
-static int btrfs_writepages(struct address_space *mapping,
-			    struct writeback_control *wbc)
-{
-	return extent_writepages(mapping, wbc);
-}
-
-static void btrfs_readahead(struct readahead_control *rac)
-{
-	extent_readahead(rac);
-}
-
 /*
  * 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.
@@ -7970,13 +7978,12 @@ static void wait_subpage_spinlock(struct page *page)
 
 static bool __btrfs_release_folio(struct folio *folio, gfp_t gfp_flags)
 {
-	int ret = try_release_extent_mapping(&folio->page, gfp_flags);
-
-	if (ret == 1) {
+	if (try_release_extent_mapping(&folio->page, gfp_flags)) {
 		wait_subpage_spinlock(&folio->page);
 		clear_page_extent_mapped(&folio->page);
+		return true;
 	}
-	return ret;
+	return false;
 }
 
 static bool btrfs_release_folio(struct folio *folio, gfp_t gfp_flags)
@@ -8174,173 +8181,6 @@ next:
 	clear_page_extent_mapped(&folio->page);
 }
 
-/*
- * btrfs_page_mkwrite() is not allowed to change the file size as it gets
- * called from a page fault handler when a page is first dirtied. Hence we must
- * be careful to check for EOF conditions here. We set the page up correctly
- * for a written page which means we get ENOSPC checking when writing into
- * holes and correct delalloc and unwritten extent mapping on filesystems that
- * support these features.
- *
- * We are not allowed to take the i_mutex here so we have to play games to
- * protect against truncate races as the page could now be beyond EOF.  Because
- * truncate_setsize() writes the inode size before removing pages, once we have
- * the page lock we can determine safely if the page is beyond EOF. If it is not
- * beyond EOF, then the page is guaranteed safe against truncation until we
- * unlock the page.
- */
-vm_fault_t btrfs_page_mkwrite(struct vm_fault *vmf)
-{
-	struct page *page = vmf->page;
-	struct folio *folio = page_folio(page);
-	struct inode *inode = file_inode(vmf->vma->vm_file);
-	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
-	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
-	struct btrfs_ordered_extent *ordered;
-	struct extent_state *cached_state = NULL;
-	struct extent_changeset *data_reserved = NULL;
-	unsigned long zero_start;
-	loff_t size;
-	vm_fault_t ret;
-	int ret2;
-	int reserved = 0;
-	u64 reserved_space;
-	u64 page_start;
-	u64 page_end;
-	u64 end;
-
-	ASSERT(folio_order(folio) == 0);
-
-	reserved_space = PAGE_SIZE;
-
-	sb_start_pagefault(inode->i_sb);
-	page_start = page_offset(page);
-	page_end = page_start + PAGE_SIZE - 1;
-	end = page_end;
-
-	/*
-	 * Reserving delalloc space after obtaining the page lock can lead to
-	 * deadlock. For example, if a dirty page is locked by this function
-	 * and the call to btrfs_delalloc_reserve_space() ends up triggering
-	 * dirty page write out, then the btrfs_writepages() function could
-	 * end up waiting indefinitely to get a lock on the page currently
-	 * being processed by btrfs_page_mkwrite() function.
-	 */
-	ret2 = btrfs_delalloc_reserve_space(BTRFS_I(inode), &data_reserved,
-					    page_start, reserved_space);
-	if (!ret2) {
-		ret2 = file_update_time(vmf->vma->vm_file);
-		reserved = 1;
-	}
-	if (ret2) {
-		ret = vmf_error(ret2);
-		if (reserved)
-			goto out;
-		goto out_noreserve;
-	}
-
-	ret = VM_FAULT_NOPAGE; /* make the VM retry the fault */
-again:
-	down_read(&BTRFS_I(inode)->i_mmap_lock);
-	lock_page(page);
-	size = i_size_read(inode);
-
-	if ((page->mapping != inode->i_mapping) ||
-	    (page_start >= size)) {
-		/* page got truncated out from underneath us */
-		goto out_unlock;
-	}
-	wait_on_page_writeback(page);
-
-	lock_extent(io_tree, page_start, page_end, &cached_state);
-	ret2 = set_page_extent_mapped(page);
-	if (ret2 < 0) {
-		ret = vmf_error(ret2);
-		unlock_extent(io_tree, page_start, page_end, &cached_state);
-		goto out_unlock;
-	}
-
-	/*
-	 * we can't set the delalloc bits if there are pending ordered
-	 * extents.  Drop our locks and wait for them to finish
-	 */
-	ordered = btrfs_lookup_ordered_range(BTRFS_I(inode), page_start,
-			PAGE_SIZE);
-	if (ordered) {
-		unlock_extent(io_tree, page_start, page_end, &cached_state);
-		unlock_page(page);
-		up_read(&BTRFS_I(inode)->i_mmap_lock);
-		btrfs_start_ordered_extent(ordered);
-		btrfs_put_ordered_extent(ordered);
-		goto again;
-	}
-
-	if (page->index == ((size - 1) >> PAGE_SHIFT)) {
-		reserved_space = round_up(size - page_start,
-					  fs_info->sectorsize);
-		if (reserved_space < PAGE_SIZE) {
-			end = page_start + reserved_space - 1;
-			btrfs_delalloc_release_space(BTRFS_I(inode),
-					data_reserved, page_start,
-					PAGE_SIZE - reserved_space, true);
-		}
-	}
-
-	/*
-	 * page_mkwrite gets called when the page is firstly dirtied after it's
-	 * faulted in, but write(2) could also dirty a page and set delalloc
-	 * bits, thus in this case for space account reason, we still need to
-	 * clear any delalloc bits within this page range since we have to
-	 * reserve data&meta space before lock_page() (see above comments).
-	 */
-	clear_extent_bit(&BTRFS_I(inode)->io_tree, page_start, end,
-			  EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING |
-			  EXTENT_DEFRAG, &cached_state);
-
-	ret2 = btrfs_set_extent_delalloc(BTRFS_I(inode), page_start, end, 0,
-					&cached_state);
-	if (ret2) {
-		unlock_extent(io_tree, page_start, page_end, &cached_state);
-		ret = VM_FAULT_SIGBUS;
-		goto out_unlock;
-	}
-
-	/* page is wholly or partially inside EOF */
-	if (page_start + PAGE_SIZE > size)
-		zero_start = offset_in_page(size);
-	else
-		zero_start = PAGE_SIZE;
-
-	if (zero_start != PAGE_SIZE)
-		memzero_page(page, zero_start, PAGE_SIZE - zero_start);
-
-	btrfs_folio_clear_checked(fs_info, folio, page_start, PAGE_SIZE);
-	btrfs_folio_set_dirty(fs_info, folio, page_start, end + 1 - page_start);
-	btrfs_folio_set_uptodate(fs_info, folio, page_start, end + 1 - page_start);
-
-	btrfs_set_inode_last_sub_trans(BTRFS_I(inode));
-
-	unlock_extent(io_tree, page_start, page_end, &cached_state);
-	up_read(&BTRFS_I(inode)->i_mmap_lock);
-
-	btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE);
-	sb_end_pagefault(inode->i_sb);
-	extent_changeset_free(data_reserved);
-	return VM_FAULT_LOCKED;
-
-out_unlock:
-	unlock_page(page);
-	up_read(&BTRFS_I(inode)->i_mmap_lock);
-out:
-	btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE);
-	btrfs_delalloc_release_space(BTRFS_I(inode), data_reserved, page_start,
-				     reserved_space, (ret != 0));
-out_noreserve:
-	sb_end_pagefault(inode->i_sb);
-	extent_changeset_free(data_reserved);
-	return ret;
-}
-
 static int btrfs_truncate(struct btrfs_inode *inode, bool skip_writeback)
 {
 	struct btrfs_truncate_control control = {
@@ -9671,7 +9511,7 @@ free_qgroup:
 	 * or we leak qgroup data reservation.
 	 */
 	btrfs_qgroup_free_refroot(inode->root->fs_info,
-			inode->root->root_key.objectid, qgroup_released,
+			btrfs_root_id(inode->root), qgroup_released,
 			BTRFS_QGROUP_RSV_DATA);
 	return ERR_PTR(ret);
 }
@@ -10319,8 +10159,8 @@ ssize_t btrfs_do_encoded_write(struct kiocb *iocb, struct iov_iter *from,
 	size_t orig_count;
 	u64 start, end;
 	u64 num_bytes, ram_bytes, disk_num_bytes;
-	unsigned long nr_pages, i;
-	struct page **pages;
+	unsigned long nr_folios, i;
+	struct folio **folios;
 	struct btrfs_key ins;
 	bool extent_reserved = false;
 	struct extent_map *em;
@@ -10409,24 +10249,24 @@ ssize_t btrfs_do_encoded_write(struct kiocb *iocb, struct iov_iter *from,
 	 * isn't.
 	 */
 	disk_num_bytes = ALIGN(orig_count, fs_info->sectorsize);
-	nr_pages = DIV_ROUND_UP(disk_num_bytes, PAGE_SIZE);
-	pages = kvcalloc(nr_pages, sizeof(struct page *), GFP_KERNEL_ACCOUNT);
-	if (!pages)
+	nr_folios = DIV_ROUND_UP(disk_num_bytes, PAGE_SIZE);
+	folios = kvcalloc(nr_folios, sizeof(struct page *), GFP_KERNEL_ACCOUNT);
+	if (!folios)
 		return -ENOMEM;
-	for (i = 0; i < nr_pages; i++) {
+	for (i = 0; i < nr_folios; i++) {
 		size_t bytes = min_t(size_t, PAGE_SIZE, iov_iter_count(from));
 		char *kaddr;
 
-		pages[i] = alloc_page(GFP_KERNEL_ACCOUNT);
-		if (!pages[i]) {
+		folios[i] = folio_alloc(GFP_KERNEL_ACCOUNT, 0);
+		if (!folios[i]) {
 			ret = -ENOMEM;
-			goto out_pages;
+			goto out_folios;
 		}
-		kaddr = kmap_local_page(pages[i]);
+		kaddr = kmap_local_folio(folios[i], 0);
 		if (copy_from_iter(kaddr, bytes, from) != bytes) {
 			kunmap_local(kaddr);
 			ret = -EFAULT;
-			goto out_pages;
+			goto out_folios;
 		}
 		if (bytes < PAGE_SIZE)
 			memset(kaddr + bytes, 0, PAGE_SIZE - bytes);
@@ -10438,12 +10278,12 @@ ssize_t btrfs_do_encoded_write(struct kiocb *iocb, struct iov_iter *from,
 
 		ret = btrfs_wait_ordered_range(&inode->vfs_inode, start, num_bytes);
 		if (ret)
-			goto out_pages;
+			goto out_folios;
 		ret = invalidate_inode_pages2_range(inode->vfs_inode.i_mapping,
 						    start >> PAGE_SHIFT,
 						    end >> PAGE_SHIFT);
 		if (ret)
-			goto out_pages;
+			goto out_folios;
 		lock_extent(io_tree, start, end, &cached_state);
 		ordered = btrfs_lookup_ordered_range(inode, start, num_bytes);
 		if (!ordered &&
@@ -10471,10 +10311,12 @@ ssize_t btrfs_do_encoded_write(struct kiocb *iocb, struct iov_iter *from,
 		goto out_qgroup_free_data;
 
 	/* Try an inline extent first. */
-	if (start == 0 && encoded->unencoded_len == encoded->len &&
-	    encoded->unencoded_offset == 0) {
-		ret = cow_file_range_inline(inode, encoded->len, orig_count,
-					    compression, pages, true);
+	if (encoded->unencoded_len == encoded->len &&
+	    encoded->unencoded_offset == 0 &&
+	    can_cow_file_range_inline(inode, start, encoded->len, orig_count)) {
+		ret = __cow_file_range_inline(inode, start, encoded->len,
+					      orig_count, compression, folios[0],
+					      true);
 		if (ret <= 0) {
 			if (ret == 0)
 				ret = orig_count;
@@ -10518,7 +10360,7 @@ ssize_t btrfs_do_encoded_write(struct kiocb *iocb, struct iov_iter *from,
 
 	btrfs_delalloc_release_extents(inode, num_bytes);
 
-	btrfs_submit_compressed_write(ordered, pages, nr_pages, 0, false);
+	btrfs_submit_compressed_write(ordered, folios, nr_folios, 0, false);
 	ret = orig_count;
 	goto out;
 
@@ -10540,12 +10382,12 @@ out_free_data_space:
 		btrfs_free_reserved_data_space_noquota(fs_info, disk_num_bytes);
 out_unlock:
 	unlock_extent(io_tree, start, end, &cached_state);
-out_pages:
-	for (i = 0; i < nr_pages; i++) {
-		if (pages[i])
-			__free_page(pages[i]);
+out_folios:
+	for (i = 0; i < nr_folios; i++) {
+		if (folios[i])
+			__folio_put(folios[i]);
 	}
-	kvfree(pages);
+	kvfree(folios);
 out:
 	if (ret >= 0)
 		iocb->ki_pos += encoded->len;
@@ -10772,7 +10614,7 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file,
 		btrfs_exclop_finish(fs_info);
 		btrfs_warn(fs_info,
 		"cannot activate swapfile because subvolume %llu is being deleted",
-			root->root_key.objectid);
+			btrfs_root_id(root));
 		return -EPERM;
 	}
 	atomic_inc(&root->nr_swapfiles);
@@ -10998,7 +10840,7 @@ void btrfs_assert_inode_range_clean(struct btrfs_inode *inode, u64 start, u64 en
 	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,
+			  start, end, btrfs_ino(inode), btrfs_root_id(root),
 			  ordered->file_offset,
 			  ordered->file_offset + ordered->num_bytes - 1);
 		btrfs_put_ordered_extent(ordered);
@@ -11007,6 +10849,65 @@ void btrfs_assert_inode_range_clean(struct btrfs_inode *inode, u64 start, u64 en
 	ASSERT(ordered == NULL);
 }
 
+/*
+ * Find the first inode with a minimum number.
+ *
+ * @root:	The root to search for.
+ * @min_ino:	The minimum inode number.
+ *
+ * Find the first inode in the @root with a number >= @min_ino and return it.
+ * Returns NULL if no such inode found.
+ */
+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;
+
+	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
+			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);
+	}
+	spin_unlock(&root->inode_lock);
+
+	return NULL;
+}
+
 static const struct inode_operations btrfs_dir_inode_operations = {
 	.getattr	= btrfs_getattr,
 	.lookup		= btrfs_lookup,
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 0493272a7668..efd5d6e9589e 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -668,7 +668,7 @@ static noinline int create_subvol(struct mnt_idmap *idmap,
 	/* Tree log can't currently deal with an inode which is a new root. */
 	btrfs_set_log_full_commit(trans);
 
-	ret = btrfs_qgroup_inherit(trans, 0, objectid, root->root_key.objectid, inherit);
+	ret = btrfs_qgroup_inherit(trans, 0, objectid, btrfs_root_id(root), inherit);
 	if (ret)
 		goto out;
 
@@ -1510,7 +1510,7 @@ static noinline int btrfs_ioctl_subvol_setflags(struct file *file,
 			spin_unlock(&root->root_item_lock);
 			btrfs_warn(fs_info,
 				   "Attempt to set subvolume %llu read-write during send",
-				   root->root_key.objectid);
+				   btrfs_root_id(root));
 			ret = -EPERM;
 			goto out_drop_sem;
 		}
@@ -1919,7 +1919,7 @@ static int btrfs_search_path_in_tree_user(struct mnt_idmap *idmap,
 	struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info;
 	struct super_block *sb = inode->i_sb;
 	struct btrfs_key upper_limit = BTRFS_I(inode)->location;
-	u64 treeid = BTRFS_I(inode)->root->root_key.objectid;
+	u64 treeid = btrfs_root_id(BTRFS_I(inode)->root);
 	u64 dirid = args->dirid;
 	unsigned long item_off;
 	unsigned long item_len;
@@ -2091,7 +2091,7 @@ static noinline int btrfs_ioctl_ino_lookup(struct btrfs_root *root,
 	 * path is reset so it's consistent with btrfs_search_path_in_tree.
 	 */
 	if (args->treeid == 0)
-		args->treeid = root->root_key.objectid;
+		args->treeid = btrfs_root_id(root);
 
 	if (args->objectid == BTRFS_FIRST_FREE_OBJECTID) {
 		args->name[0] = 0;
@@ -2187,7 +2187,7 @@ static int btrfs_ioctl_get_subvol_info(struct inode *inode, void __user *argp)
 	fs_info = BTRFS_I(inode)->root->fs_info;
 
 	/* Get root_item of inode's subvolume */
-	key.objectid = BTRFS_I(inode)->root->root_key.objectid;
+	key.objectid = btrfs_root_id(BTRFS_I(inode)->root);
 	root = btrfs_get_fs_root(fs_info, key.objectid, true);
 	if (IS_ERR(root)) {
 		ret = PTR_ERR(root);
@@ -2302,7 +2302,7 @@ static int btrfs_ioctl_get_subvol_rootref(struct btrfs_root *root,
 		return PTR_ERR(rootrefs);
 	}
 
-	objectid = root->root_key.objectid;
+	objectid = btrfs_root_id(root);
 	key.objectid = objectid;
 	key.type = BTRFS_ROOT_REF_KEY;
 	key.offset = rootrefs->min_treeid;
@@ -2386,7 +2386,7 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
 	struct mnt_idmap *idmap = file_mnt_idmap(file);
 	char *subvol_name, *subvol_name_ptr = NULL;
 	int subvol_namelen;
-	int err = 0;
+	int ret = 0;
 	bool destroy_parent = false;
 
 	/* We don't support snapshots with extent tree v2 yet. */
@@ -2402,7 +2402,7 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
 			return PTR_ERR(vol_args2);
 
 		if (vol_args2->flags & ~BTRFS_SUBVOL_DELETE_ARGS_MASK) {
-			err = -EOPNOTSUPP;
+			ret = -EOPNOTSUPP;
 			goto out;
 		}
 
@@ -2411,31 +2411,31 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
 		 * name, same as v1 currently does.
 		 */
 		if (!(vol_args2->flags & BTRFS_SUBVOL_SPEC_BY_ID)) {
-			err = btrfs_check_ioctl_vol_args2_subvol_name(vol_args2);
-			if (err < 0)
+			ret = btrfs_check_ioctl_vol_args2_subvol_name(vol_args2);
+			if (ret < 0)
 				goto out;
 			subvol_name = vol_args2->name;
 
-			err = mnt_want_write_file(file);
-			if (err)
+			ret = mnt_want_write_file(file);
+			if (ret)
 				goto out;
 		} else {
 			struct inode *old_dir;
 
 			if (vol_args2->subvolid < BTRFS_FIRST_FREE_OBJECTID) {
-				err = -EINVAL;
+				ret = -EINVAL;
 				goto out;
 			}
 
-			err = mnt_want_write_file(file);
-			if (err)
+			ret = mnt_want_write_file(file);
+			if (ret)
 				goto out;
 
 			dentry = btrfs_get_dentry(fs_info->sb,
 					BTRFS_FIRST_FREE_OBJECTID,
 					vol_args2->subvolid, 0);
 			if (IS_ERR(dentry)) {
-				err = PTR_ERR(dentry);
+				ret = PTR_ERR(dentry);
 				goto out_drop_write;
 			}
 
@@ -2455,7 +2455,7 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
 			 */
 			dput(dentry);
 			if (IS_ERR(parent)) {
-				err = PTR_ERR(parent);
+				ret = PTR_ERR(parent);
 				goto out_drop_write;
 			}
 			old_dir = dir;
@@ -2479,14 +2479,14 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
 			 * to delete without an idmapped mount.
 			 */
 			if (old_dir != dir && idmap != &nop_mnt_idmap) {
-				err = -EOPNOTSUPP;
+				ret = -EOPNOTSUPP;
 				goto free_parent;
 			}
 
 			subvol_name_ptr = btrfs_get_subvol_name_from_objectid(
 						fs_info, vol_args2->subvolid);
 			if (IS_ERR(subvol_name_ptr)) {
-				err = PTR_ERR(subvol_name_ptr);
+				ret = PTR_ERR(subvol_name_ptr);
 				goto free_parent;
 			}
 			/* subvol_name_ptr is already nul terminated */
@@ -2497,14 +2497,14 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
 		if (IS_ERR(vol_args))
 			return PTR_ERR(vol_args);
 
-		err = btrfs_check_ioctl_vol_args_path(vol_args);
-		if (err < 0)
+		ret = btrfs_check_ioctl_vol_args_path(vol_args);
+		if (ret < 0)
 			goto out;
 
 		subvol_name = vol_args->name;
 
-		err = mnt_want_write_file(file);
-		if (err)
+		ret = mnt_want_write_file(file);
+		if (ret)
 			goto out;
 	}
 
@@ -2512,26 +2512,26 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
 
 	if (strchr(subvol_name, '/') ||
 	    strncmp(subvol_name, "..", subvol_namelen) == 0) {
-		err = -EINVAL;
+		ret = -EINVAL;
 		goto free_subvol_name;
 	}
 
 	if (!S_ISDIR(dir->i_mode)) {
-		err = -ENOTDIR;
+		ret = -ENOTDIR;
 		goto free_subvol_name;
 	}
 
-	err = down_write_killable_nested(&dir->i_rwsem, I_MUTEX_PARENT);
-	if (err == -EINTR)
+	ret = down_write_killable_nested(&dir->i_rwsem, I_MUTEX_PARENT);
+	if (ret == -EINTR)
 		goto free_subvol_name;
 	dentry = lookup_one(idmap, subvol_name, parent, subvol_namelen);
 	if (IS_ERR(dentry)) {
-		err = PTR_ERR(dentry);
+		ret = PTR_ERR(dentry);
 		goto out_unlock_dir;
 	}
 
 	if (d_really_is_negative(dentry)) {
-		err = -ENOENT;
+		ret = -ENOENT;
 		goto out_dput;
 	}
 
@@ -2551,7 +2551,7 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
 		 * Users who want to delete empty subvols should try
 		 * rmdir(2).
 		 */
-		err = -EPERM;
+		ret = -EPERM;
 		if (!btrfs_test_opt(fs_info, USER_SUBVOL_RM_ALLOWED))
 			goto out_dput;
 
@@ -2562,29 +2562,29 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
 		 * of the subvol, not a random directory contained
 		 * within it.
 		 */
-		err = -EINVAL;
+		ret = -EINVAL;
 		if (root == dest)
 			goto out_dput;
 
-		err = inode_permission(idmap, inode, MAY_WRITE | MAY_EXEC);
-		if (err)
+		ret = inode_permission(idmap, inode, MAY_WRITE | MAY_EXEC);
+		if (ret)
 			goto out_dput;
 	}
 
 	/* check if subvolume may be deleted by a user */
-	err = btrfs_may_delete(idmap, dir, dentry, 1);
-	if (err)
+	ret = btrfs_may_delete(idmap, dir, dentry, 1);
+	if (ret)
 		goto out_dput;
 
 	if (btrfs_ino(BTRFS_I(inode)) != BTRFS_FIRST_FREE_OBJECTID) {
-		err = -EINVAL;
+		ret = -EINVAL;
 		goto out_dput;
 	}
 
 	btrfs_inode_lock(BTRFS_I(inode), 0);
-	err = btrfs_delete_subvolume(BTRFS_I(dir), dentry);
+	ret = btrfs_delete_subvolume(BTRFS_I(dir), dentry);
 	btrfs_inode_unlock(BTRFS_I(inode), 0);
-	if (!err)
+	if (!ret)
 		d_delete_notify(dir, dentry);
 
 out_dput:
@@ -2601,7 +2601,7 @@ out_drop_write:
 out:
 	kfree(vol_args2);
 	kfree(vol_args);
-	return err;
+	return ret;
 }
 
 static int btrfs_ioctl_defrag(struct file *file, void __user *argp)
@@ -2981,7 +2981,7 @@ static long btrfs_ioctl_default_subvol(struct file *file, void __user *argp)
 		ret = PTR_ERR(new_root);
 		goto out;
 	}
-	if (!is_fstree(new_root->root_key.objectid)) {
+	if (!is_fstree(btrfs_root_id(new_root))) {
 		ret = -ENOENT;
 		goto out_free;
 	}
@@ -3947,7 +3947,7 @@ static long btrfs_ioctl_qgroup_limit(struct file *file, void __user *arg)
 	qgroupid = sa->qgroupid;
 	if (!qgroupid) {
 		/* take the current subvol as qgroup */
-		qgroupid = root->root_key.objectid;
+		qgroupid = btrfs_root_id(root);
 	}
 
 	ret = btrfs_limit_qgroup(trans, qgroupid, &sa->lim);
@@ -4078,7 +4078,7 @@ static long _btrfs_ioctl_set_received_subvol(struct file *file,
 	    !btrfs_is_empty_uuid(root_item->received_uuid)) {
 		ret = btrfs_uuid_tree_remove(trans, root_item->received_uuid,
 					  BTRFS_UUID_KEY_RECEIVED_SUBVOL,
-					  root->root_key.objectid);
+					  btrfs_root_id(root));
 		if (ret && ret != -ENOENT) {
 		        btrfs_abort_transaction(trans, ret);
 		        btrfs_end_transaction(trans);
@@ -4102,7 +4102,7 @@ static long _btrfs_ioctl_set_received_subvol(struct file *file,
 	if (received_uuid_changed && !btrfs_is_empty_uuid(sa->uuid)) {
 		ret = btrfs_uuid_tree_add(trans, sa->uuid,
 					  BTRFS_UUID_KEY_RECEIVED_SUBVOL,
-					  root->root_key.objectid);
+					  btrfs_root_id(root));
 		if (ret < 0 && ret != -EEXIST) {
 			btrfs_abort_transaction(trans, ret);
 			btrfs_end_transaction(trans);
diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c
index 99ccab86bb86..6a0b7abb5bd9 100644
--- a/fs/btrfs/locking.c
+++ b/fs/btrfs/locking.c
@@ -97,7 +97,7 @@ void btrfs_set_buffer_lockdep_class(u64 objectid, struct extent_buffer *eb, int
 void btrfs_maybe_reset_lockdep_class(struct btrfs_root *root, struct extent_buffer *eb)
 {
 	if (test_bit(BTRFS_ROOT_RESET_LOCKDEP_CLASS, &root->state))
-		btrfs_set_buffer_lockdep_class(root->root_key.objectid,
+		btrfs_set_buffer_lockdep_class(btrfs_root_id(root),
 					       eb, btrfs_header_level(eb));
 }
 
@@ -129,14 +129,14 @@ static void btrfs_set_eb_lock_owner(struct extent_buffer *eb, pid_t owner) { }
  */
 
 /*
- * __btrfs_tree_read_lock - lock extent buffer for read
+ * btrfs_tree_read_lock_nested - lock extent buffer for read
  * @eb:		the eb to be locked
  * @nest:	the nesting level to be used for lockdep
  *
  * This takes the read lock on the extent buffer, using the specified nesting
  * level for lockdep purposes.
  */
-void __btrfs_tree_read_lock(struct extent_buffer *eb, enum btrfs_lock_nesting nest)
+void btrfs_tree_read_lock_nested(struct extent_buffer *eb, enum btrfs_lock_nesting nest)
 {
 	u64 start_ns = 0;
 
@@ -147,11 +147,6 @@ void __btrfs_tree_read_lock(struct extent_buffer *eb, enum btrfs_lock_nesting ne
 	trace_btrfs_tree_read_lock(eb, start_ns);
 }
 
-void btrfs_tree_read_lock(struct extent_buffer *eb)
-{
-	__btrfs_tree_read_lock(eb, BTRFS_NESTING_NORMAL);
-}
-
 /*
  * Try-lock for read.
  *
@@ -198,7 +193,7 @@ void btrfs_tree_read_unlock(struct extent_buffer *eb)
  *
  * Returns with the eb->lock write locked.
  */
-void __btrfs_tree_lock(struct extent_buffer *eb, enum btrfs_lock_nesting nest)
+void btrfs_tree_lock_nested(struct extent_buffer *eb, enum btrfs_lock_nesting nest)
 	__acquires(&eb->lock)
 {
 	u64 start_ns = 0;
@@ -211,11 +206,6 @@ void __btrfs_tree_lock(struct extent_buffer *eb, enum btrfs_lock_nesting nest)
 	trace_btrfs_tree_lock(eb, start_ns);
 }
 
-void btrfs_tree_lock(struct extent_buffer *eb)
-{
-	__btrfs_tree_lock(eb, BTRFS_NESTING_NORMAL);
-}
-
 /*
  * Release the write lock.
  */
@@ -374,8 +364,12 @@ void btrfs_drew_write_lock(struct btrfs_drew_lock *lock)
 
 void btrfs_drew_write_unlock(struct btrfs_drew_lock *lock)
 {
-	atomic_dec(&lock->writers);
-	cond_wake_up(&lock->pending_readers);
+	/*
+	 * atomic_dec_and_test() implies a full barrier, so woken up readers are
+	 * guaranteed to see the decrement.
+	 */
+	if (atomic_dec_and_test(&lock->writers))
+		wake_up(&lock->pending_readers);
 }
 
 void btrfs_drew_read_lock(struct btrfs_drew_lock *lock)
diff --git a/fs/btrfs/locking.h b/fs/btrfs/locking.h
index 9576f485a300..1bc8e6738879 100644
--- a/fs/btrfs/locking.h
+++ b/fs/btrfs/locking.h
@@ -163,12 +163,22 @@ enum btrfs_lockdep_trans_states {
 static_assert(BTRFS_NESTING_MAX <= MAX_LOCKDEP_SUBCLASSES,
 	      "too many lock subclasses defined");
 
-void __btrfs_tree_lock(struct extent_buffer *eb, enum btrfs_lock_nesting nest);
-void btrfs_tree_lock(struct extent_buffer *eb);
+void btrfs_tree_lock_nested(struct extent_buffer *eb, enum btrfs_lock_nesting nest);
+
+static inline void btrfs_tree_lock(struct extent_buffer *eb)
+{
+	btrfs_tree_lock_nested(eb, BTRFS_NESTING_NORMAL);
+}
+
 void btrfs_tree_unlock(struct extent_buffer *eb);
 
-void __btrfs_tree_read_lock(struct extent_buffer *eb, enum btrfs_lock_nesting nest);
-void btrfs_tree_read_lock(struct extent_buffer *eb);
+void btrfs_tree_read_lock_nested(struct extent_buffer *eb, enum btrfs_lock_nesting nest);
+
+static inline void btrfs_tree_read_lock(struct extent_buffer *eb)
+{
+	btrfs_tree_read_lock_nested(eb, BTRFS_NESTING_NORMAL);
+}
+
 void btrfs_tree_read_unlock(struct extent_buffer *eb);
 int btrfs_try_tree_read_lock(struct extent_buffer *eb);
 int btrfs_try_tree_write_lock(struct extent_buffer *eb);
diff --git a/fs/btrfs/lzo.c b/fs/btrfs/lzo.c
index 3e5d3b7028e8..1c396ac167aa 100644
--- a/fs/btrfs/lzo.c
+++ b/fs/btrfs/lzo.c
@@ -130,17 +130,17 @@ static inline size_t read_compress_length(const char *buf)
  */
 static int copy_compressed_data_to_page(char *compressed_data,
 					size_t compressed_size,
-					struct page **out_pages,
-					unsigned long max_nr_page,
+					struct folio **out_folios,
+					unsigned long max_nr_folio,
 					u32 *cur_out,
 					const u32 sectorsize)
 {
 	u32 sector_bytes_left;
 	u32 orig_out;
-	struct page *cur_page;
+	struct folio *cur_folio;
 	char *kaddr;
 
-	if ((*cur_out / PAGE_SIZE) >= max_nr_page)
+	if ((*cur_out / PAGE_SIZE) >= max_nr_folio)
 		return -E2BIG;
 
 	/*
@@ -149,16 +149,16 @@ static int copy_compressed_data_to_page(char *compressed_data,
 	 */
 	ASSERT((*cur_out / sectorsize) == (*cur_out + LZO_LEN - 1) / sectorsize);
 
-	cur_page = out_pages[*cur_out / PAGE_SIZE];
+	cur_folio = out_folios[*cur_out / PAGE_SIZE];
 	/* Allocate a new page */
-	if (!cur_page) {
-		cur_page = btrfs_alloc_compr_page();
-		if (!cur_page)
+	if (!cur_folio) {
+		cur_folio = btrfs_alloc_compr_folio();
+		if (!cur_folio)
 			return -ENOMEM;
-		out_pages[*cur_out / PAGE_SIZE] = cur_page;
+		out_folios[*cur_out / PAGE_SIZE] = cur_folio;
 	}
 
-	kaddr = kmap_local_page(cur_page);
+	kaddr = kmap_local_folio(cur_folio, 0);
 	write_compress_length(kaddr + offset_in_page(*cur_out),
 			      compressed_size);
 	*cur_out += LZO_LEN;
@@ -172,18 +172,18 @@ static int copy_compressed_data_to_page(char *compressed_data,
 
 		kunmap_local(kaddr);
 
-		if ((*cur_out / PAGE_SIZE) >= max_nr_page)
+		if ((*cur_out / PAGE_SIZE) >= max_nr_folio)
 			return -E2BIG;
 
-		cur_page = out_pages[*cur_out / PAGE_SIZE];
+		cur_folio = out_folios[*cur_out / PAGE_SIZE];
 		/* Allocate a new page */
-		if (!cur_page) {
-			cur_page = btrfs_alloc_compr_page();
-			if (!cur_page)
+		if (!cur_folio) {
+			cur_folio = btrfs_alloc_compr_folio();
+			if (!cur_folio)
 				return -ENOMEM;
-			out_pages[*cur_out / PAGE_SIZE] = cur_page;
+			out_folios[*cur_out / PAGE_SIZE] = cur_folio;
 		}
-		kaddr = kmap_local_page(cur_page);
+		kaddr = kmap_local_folio(cur_folio, 0);
 
 		memcpy(kaddr + offset_in_page(*cur_out),
 		       compressed_data + *cur_out - orig_out, copy_len);
@@ -209,15 +209,15 @@ out:
 	return 0;
 }
 
-int lzo_compress_pages(struct list_head *ws, struct address_space *mapping,
-		u64 start, struct page **pages, unsigned long *out_pages,
-		unsigned long *total_in, unsigned long *total_out)
+int lzo_compress_folios(struct list_head *ws, struct address_space *mapping,
+			u64 start, struct folio **folios, unsigned long *out_folios,
+			unsigned long *total_in, unsigned long *total_out)
 {
 	struct workspace *workspace = list_entry(ws, struct workspace, list);
 	const u32 sectorsize = inode_to_fs_info(mapping->host)->sectorsize;
-	struct page *page_in = NULL;
+	struct folio *folio_in = NULL;
 	char *sizes_ptr;
-	const unsigned long max_nr_page = *out_pages;
+	const unsigned long max_nr_folio = *out_folios;
 	int ret = 0;
 	/* Points to the file offset of input data */
 	u64 cur_in = start;
@@ -225,8 +225,8 @@ int lzo_compress_pages(struct list_head *ws, struct address_space *mapping,
 	u32 cur_out = 0;
 	u32 len = *total_out;
 
-	ASSERT(max_nr_page > 0);
-	*out_pages = 0;
+	ASSERT(max_nr_folio > 0);
+	*out_folios = 0;
 	*total_out = 0;
 	*total_in = 0;
 
@@ -243,15 +243,16 @@ int lzo_compress_pages(struct list_head *ws, struct address_space *mapping,
 		size_t out_len;
 
 		/* Get the input page first */
-		if (!page_in) {
-			page_in = find_get_page(mapping, cur_in >> PAGE_SHIFT);
-			ASSERT(page_in);
+		if (!folio_in) {
+			ret = btrfs_compress_filemap_get_folio(mapping, cur_in, &folio_in);
+			if (ret < 0)
+				goto out;
 		}
 
 		/* Compress at most one sector of data each time */
 		in_len = min_t(u32, start + len - cur_in, sectorsize - sector_off);
 		ASSERT(in_len);
-		data_in = kmap_local_page(page_in);
+		data_in = kmap_local_folio(folio_in, 0);
 		ret = lzo1x_1_compress(data_in +
 				       offset_in_page(cur_in), in_len,
 				       workspace->cbuf, &out_len,
@@ -264,7 +265,7 @@ int lzo_compress_pages(struct list_head *ws, struct address_space *mapping,
 		}
 
 		ret = copy_compressed_data_to_page(workspace->cbuf, out_len,
-						   pages, max_nr_page,
+						   folios, max_nr_folio,
 						   &cur_out, sectorsize);
 		if (ret < 0)
 			goto out;
@@ -282,13 +283,13 @@ int lzo_compress_pages(struct list_head *ws, struct address_space *mapping,
 
 		/* Check if we have reached page boundary */
 		if (PAGE_ALIGNED(cur_in)) {
-			put_page(page_in);
-			page_in = NULL;
+			folio_put(folio_in);
+			folio_in = NULL;
 		}
 	}
 
 	/* Store the size of all chunks of compressed data */
-	sizes_ptr = kmap_local_page(pages[0]);
+	sizes_ptr = kmap_local_folio(folios[0], 0);
 	write_compress_length(sizes_ptr, cur_out);
 	kunmap_local(sizes_ptr);
 
@@ -296,9 +297,9 @@ int lzo_compress_pages(struct list_head *ws, struct address_space *mapping,
 	*total_out = cur_out;
 	*total_in = cur_in - start;
 out:
-	if (page_in)
-		put_page(page_in);
-	*out_pages = DIV_ROUND_UP(cur_out, PAGE_SIZE);
+	if (folio_in)
+		folio_put(folio_in);
+	*out_folios = DIV_ROUND_UP(cur_out, PAGE_SIZE);
 	return ret;
 }
 
@@ -313,15 +314,15 @@ static void copy_compressed_segment(struct compressed_bio *cb,
 	u32 orig_in = *cur_in;
 
 	while (*cur_in < orig_in + len) {
-		struct page *cur_page;
+		struct folio *cur_folio;
 		u32 copy_len = min_t(u32, PAGE_SIZE - offset_in_page(*cur_in),
 					  orig_in + len - *cur_in);
 
 		ASSERT(copy_len);
-		cur_page = cb->compressed_pages[*cur_in / PAGE_SIZE];
+		cur_folio = cb->compressed_folios[*cur_in / PAGE_SIZE];
 
-		memcpy_from_page(dest + *cur_in - orig_in, cur_page,
-				 offset_in_page(*cur_in), copy_len);
+		memcpy_from_folio(dest + *cur_in - orig_in, cur_folio,
+				  offset_in_folio(cur_folio, *cur_in), copy_len);
 
 		*cur_in += copy_len;
 	}
@@ -341,7 +342,7 @@ int lzo_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
 	/* Bytes decompressed so far */
 	u32 cur_out = 0;
 
-	kaddr = kmap_local_page(cb->compressed_pages[0]);
+	kaddr = kmap_local_folio(cb->compressed_folios[0], 0);
 	len_in = read_compress_length(kaddr);
 	kunmap_local(kaddr);
 	cur_in += LZO_LEN;
@@ -363,7 +364,7 @@ int lzo_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
 
 	/* Go through each lzo segment */
 	while (cur_in < len_in) {
-		struct page *cur_page;
+		struct folio *cur_folio;
 		/* Length of the compressed segment */
 		u32 seg_len;
 		u32 sector_bytes_left;
@@ -375,9 +376,9 @@ int lzo_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
 		 */
 		ASSERT(cur_in / sectorsize ==
 		       (cur_in + LZO_LEN - 1) / sectorsize);
-		cur_page = cb->compressed_pages[cur_in / PAGE_SIZE];
-		ASSERT(cur_page);
-		kaddr = kmap_local_page(cur_page);
+		cur_folio = cb->compressed_folios[cur_in / PAGE_SIZE];
+		ASSERT(cur_folio);
+		kaddr = kmap_local_folio(cur_folio, 0);
 		seg_len = read_compress_length(kaddr + offset_in_page(cur_in));
 		kunmap_local(kaddr);
 		cur_in += LZO_LEN;
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index c2a42bcde98e..c5bdd674f55c 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -294,6 +294,12 @@ void btrfs_add_ordered_sum(struct btrfs_ordered_extent *entry,
 	spin_unlock_irq(&inode->ordered_tree_lock);
 }
 
+void btrfs_mark_ordered_extent_error(struct btrfs_ordered_extent *ordered)
+{
+	if (!test_and_set_bit(BTRFS_ORDERED_IOERR, &ordered->flags))
+		mapping_set_error(ordered->inode->i_mapping, -EIO);
+}
+
 static void finish_ordered_fn(struct btrfs_work *work)
 {
 	struct btrfs_ordered_extent *ordered_extent;
@@ -332,7 +338,7 @@ static bool can_finish_ordered_extent(struct btrfs_ordered_extent *ordered,
 	if (WARN_ON_ONCE(len > ordered->bytes_left)) {
 		btrfs_crit(fs_info,
 "bad ordered extent accounting, root=%llu ino=%llu OE offset=%llu OE len=%llu to_dec=%llu left=%llu",
-			   inode->root->root_key.objectid, btrfs_ino(inode),
+			   btrfs_root_id(inode->root), btrfs_ino(inode),
 			   ordered->file_offset, ordered->num_bytes,
 			   len, ordered->bytes_left);
 		ordered->bytes_left = 0;
diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h
index 34413fc5b4bd..b6f6c6b91732 100644
--- a/fs/btrfs/ordered-data.h
+++ b/fs/btrfs/ordered-data.h
@@ -203,6 +203,7 @@ bool btrfs_try_lock_ordered_range(struct btrfs_inode *inode, u64 start, u64 end,
 				  struct extent_state **cached_state);
 struct btrfs_ordered_extent *btrfs_split_ordered_extent(
 			struct btrfs_ordered_extent *ordered, u64 len);
+void btrfs_mark_ordered_extent_error(struct btrfs_ordered_extent *ordered);
 int __init ordered_data_init(void);
 void __cold ordered_data_exit(void);
 
diff --git a/fs/btrfs/props.c b/fs/btrfs/props.c
index 2a9b7b029eeb..155570e20f45 100644
--- a/fs/btrfs/props.c
+++ b/fs/btrfs/props.c
@@ -268,7 +268,7 @@ static void inode_prop_iterator(void *ctx,
 		btrfs_warn(root->fs_info,
 			   "error applying prop %s to ino %llu (root %llu): %d",
 			   handler->xattr_name, btrfs_ino(BTRFS_I(inode)),
-			   root->root_key.objectid, ret);
+			   btrfs_root_id(root), ret);
 	else
 		set_bit(BTRFS_INODE_HAS_PROPS, &BTRFS_I(inode)->runtime_flags);
 }
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 40e5f7f2fcb7..eb28141d5c37 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1536,18 +1536,15 @@ static int quick_update_accounting(struct btrfs_fs_info *fs_info,
 {
 	struct btrfs_qgroup *qgroup;
 	int ret = 1;
-	int err = 0;
 
 	qgroup = find_qgroup_rb(fs_info, src);
 	if (!qgroup)
 		goto out;
 	if (qgroup->excl == qgroup->rfer) {
-		ret = 0;
-		err = __qgroup_excl_accounting(fs_info, dst, qgroup, sign);
-		if (err < 0) {
-			ret = err;
+		ret = __qgroup_excl_accounting(fs_info, dst, qgroup, sign);
+		if (ret < 0)
 			goto out;
-		}
+		ret = 0;
 	}
 out:
 	if (ret)
@@ -3064,9 +3061,6 @@ int btrfs_qgroup_check_inherit(struct btrfs_fs_info *fs_info,
 	if (inherit->num_ref_copies > 0 || inherit->num_excl_copies > 0)
 		return -EINVAL;
 
-	if (inherit->num_qgroups > PAGE_SIZE)
-		return -EINVAL;
-
 	if (size != struct_size(inherit, qgroups, inherit->num_qgroups))
 		return -EINVAL;
 
@@ -3129,7 +3123,7 @@ static int qgroup_auto_inherit(struct btrfs_fs_info *fs_info,
 	qgids = res->qgroups;
 
 	list_for_each_entry(qg_list, &inode_qg->groups, next_group)
-		qgids[i] = qg_list->group->qgroupid;
+		qgids[i++] = qg_list->group->qgroupid;
 
 	*inherit = res;
 	return 0;
@@ -3471,7 +3465,7 @@ static int qgroup_reserve(struct btrfs_root *root, u64 num_bytes, bool enforce,
 {
 	struct btrfs_qgroup *qgroup;
 	struct btrfs_fs_info *fs_info = root->fs_info;
-	u64 ref_root = root->root_key.objectid;
+	u64 ref_root = btrfs_root_id(root);
 	int ret = 0;
 	LIST_HEAD(qgroup_list);
 
@@ -3706,7 +3700,6 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work)
 						     qgroup_rescan_work);
 	struct btrfs_path *path;
 	struct btrfs_trans_handle *trans = NULL;
-	int err = -ENOMEM;
 	int ret = 0;
 	bool stopped = false;
 	bool did_leaf_rescans = false;
@@ -3715,8 +3708,10 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work)
 		return;
 
 	path = btrfs_alloc_path();
-	if (!path)
+	if (!path) {
+		ret = -ENOMEM;
 		goto out;
+	}
 	/*
 	 * Rescan should only search for commit root, and any later difference
 	 * should be recorded by qgroup
@@ -3724,18 +3719,17 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work)
 	path->search_commit_root = 1;
 	path->skip_locking = 1;
 
-	err = 0;
-	while (!err && !(stopped = rescan_should_stop(fs_info))) {
+	while (!ret && !(stopped = rescan_should_stop(fs_info))) {
 		trans = btrfs_start_transaction(fs_info->fs_root, 0);
 		if (IS_ERR(trans)) {
-			err = PTR_ERR(trans);
+			ret = PTR_ERR(trans);
 			break;
 		}
 
-		err = qgroup_rescan_leaf(trans, path);
+		ret = qgroup_rescan_leaf(trans, path);
 		did_leaf_rescans = true;
 
-		if (err > 0)
+		if (ret > 0)
 			btrfs_commit_transaction(trans);
 		else
 			btrfs_end_transaction(trans);
@@ -3745,10 +3739,10 @@ out:
 	btrfs_free_path(path);
 
 	mutex_lock(&fs_info->qgroup_rescan_lock);
-	if (err > 0 &&
+	if (ret > 0 &&
 	    fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT) {
 		fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT;
-	} else if (err < 0 || stopped) {
+	} else if (ret < 0 || stopped) {
 		fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT;
 	}
 	mutex_unlock(&fs_info->qgroup_rescan_lock);
@@ -3763,11 +3757,11 @@ out:
 	if (did_leaf_rescans) {
 		trans = btrfs_start_transaction(fs_info->quota_root, 1);
 		if (IS_ERR(trans)) {
-			err = PTR_ERR(trans);
+			ret = PTR_ERR(trans);
 			trans = NULL;
 			btrfs_err(fs_info,
 				  "fail to start transaction for status update: %d",
-				  err);
+				  ret);
 		}
 	} else {
 		trans = NULL;
@@ -3778,11 +3772,11 @@ out:
 	    fs_info->qgroup_flags & BTRFS_QGROUP_RUNTIME_FLAG_CANCEL_RESCAN)
 		fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_RESCAN;
 	if (trans) {
-		ret = update_qgroup_status_item(trans);
-		if (ret < 0) {
-			err = ret;
-			btrfs_err(fs_info, "fail to update qgroup status: %d",
-				  err);
+		int ret2 = update_qgroup_status_item(trans);
+
+		if (ret2 < 0) {
+			ret = ret2;
+			btrfs_err(fs_info, "fail to update qgroup status: %d", ret);
 		}
 	}
 	fs_info->qgroup_rescan_running = false;
@@ -3799,11 +3793,11 @@ out:
 		btrfs_info(fs_info, "qgroup scan paused");
 	} else if (fs_info->qgroup_flags & BTRFS_QGROUP_RUNTIME_FLAG_CANCEL_RESCAN) {
 		btrfs_info(fs_info, "qgroup scan cancelled");
-	} else if (err >= 0) {
+	} else if (ret >= 0) {
 		btrfs_info(fs_info, "qgroup scan completed%s",
-			err > 0 ? " (inconsistency flag cleared)" : "");
+			ret > 0 ? " (inconsistency flag cleared)" : "");
 	} else {
-		btrfs_err(fs_info, "qgroup scan failed with %d", err);
+		btrfs_err(fs_info, "qgroup scan failed with %d", ret);
 	}
 }
 
@@ -4112,7 +4106,7 @@ static int qgroup_reserve_data(struct btrfs_inode *inode,
 	int ret;
 
 	if (btrfs_qgroup_mode(root->fs_info) == BTRFS_QGROUP_MODE_DISABLED ||
-	    !is_fstree(root->root_key.objectid) || len == 0)
+	    !is_fstree(btrfs_root_id(root)) || len == 0)
 		return 0;
 
 	/* @reserved parameter is mandatory for qgroup */
@@ -4228,7 +4222,7 @@ static int qgroup_free_reserved_data(struct btrfs_inode *inode,
 			goto out;
 		freed += changeset.bytes_changed;
 	}
-	btrfs_qgroup_free_refroot(root->fs_info, root->root_key.objectid, freed,
+	btrfs_qgroup_free_refroot(root->fs_info, btrfs_root_id(root), freed,
 				  BTRFS_QGROUP_RSV_DATA);
 	if (freed_ret)
 		*freed_ret = freed;
@@ -4269,7 +4263,7 @@ static int __btrfs_qgroup_release_data(struct btrfs_inode *inode,
 					changeset.bytes_changed, trace_op);
 	if (free)
 		btrfs_qgroup_free_refroot(inode->root->fs_info,
-				inode->root->root_key.objectid,
+				btrfs_root_id(inode->root),
 				changeset.bytes_changed, BTRFS_QGROUP_RSV_DATA);
 	if (released)
 		*released = changeset.bytes_changed;
@@ -4364,7 +4358,7 @@ int btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes,
 	int ret;
 
 	if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_DISABLED ||
-	    !is_fstree(root->root_key.objectid) || num_bytes == 0)
+	    !is_fstree(btrfs_root_id(root)) || num_bytes == 0)
 		return 0;
 
 	BUG_ON(num_bytes != round_down(num_bytes, fs_info->nodesize));
@@ -4409,13 +4403,13 @@ void btrfs_qgroup_free_meta_all_pertrans(struct btrfs_root *root)
 	struct btrfs_fs_info *fs_info = root->fs_info;
 
 	if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_DISABLED ||
-	    !is_fstree(root->root_key.objectid))
+	    !is_fstree(btrfs_root_id(root)))
 		return;
 
 	/* TODO: Update trace point to handle such free */
 	trace_qgroup_meta_free_all_pertrans(root);
 	/* Special value -1 means to free all reserved space */
-	btrfs_qgroup_free_refroot(fs_info, root->root_key.objectid, (u64)-1,
+	btrfs_qgroup_free_refroot(fs_info, btrfs_root_id(root), (u64)-1,
 				  BTRFS_QGROUP_RSV_META_PERTRANS);
 }
 
@@ -4425,7 +4419,7 @@ void __btrfs_qgroup_free_meta(struct btrfs_root *root, int num_bytes,
 	struct btrfs_fs_info *fs_info = root->fs_info;
 
 	if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_DISABLED ||
-	    !is_fstree(root->root_key.objectid))
+	    !is_fstree(btrfs_root_id(root)))
 		return;
 
 	/*
@@ -4436,8 +4430,7 @@ void __btrfs_qgroup_free_meta(struct btrfs_root *root, int num_bytes,
 	num_bytes = sub_root_meta_rsv(root, num_bytes, type);
 	BUG_ON(num_bytes != round_down(num_bytes, fs_info->nodesize));
 	trace_qgroup_meta_reserve(root, -(s64)num_bytes, type);
-	btrfs_qgroup_free_refroot(fs_info, root->root_key.objectid,
-				  num_bytes, type);
+	btrfs_qgroup_free_refroot(fs_info, btrfs_root_id(root), num_bytes, type);
 }
 
 static void qgroup_convert_meta(struct btrfs_fs_info *fs_info, u64 ref_root,
@@ -4485,13 +4478,13 @@ void btrfs_qgroup_convert_reserved_meta(struct btrfs_root *root, int num_bytes)
 	struct btrfs_fs_info *fs_info = root->fs_info;
 
 	if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_DISABLED ||
-	    !is_fstree(root->root_key.objectid))
+	    !is_fstree(btrfs_root_id(root)))
 		return;
 	/* Same as btrfs_qgroup_free_meta_prealloc() */
 	num_bytes = sub_root_meta_rsv(root, num_bytes,
 				      BTRFS_QGROUP_RSV_META_PREALLOC);
 	trace_qgroup_meta_convert(root, num_bytes);
-	qgroup_convert_meta(fs_info, root->root_key.objectid, num_bytes);
+	qgroup_convert_meta(fs_info, btrfs_root_id(root), num_bytes);
 	if (!sb_rdonly(fs_info->sb))
 		add_root_meta_rsv(root, num_bytes, BTRFS_QGROUP_RSV_META_PERTRANS);
 }
@@ -4520,7 +4513,7 @@ void btrfs_qgroup_check_reserved_leak(struct btrfs_inode *inode)
 				btrfs_ino(inode), unode->val, unode->aux);
 		}
 		btrfs_qgroup_free_refroot(inode->root->fs_info,
-				inode->root->root_key.objectid,
+				btrfs_root_id(inode->root),
 				changeset.bytes_changed, BTRFS_QGROUP_RSV_DATA);
 
 	}
@@ -4706,7 +4699,7 @@ int btrfs_qgroup_trace_subtree_after_cow(struct btrfs_trans_handle *trans,
 
 	if (!btrfs_qgroup_full_accounting(fs_info))
 		return 0;
-	if (!is_fstree(root->root_key.objectid) || !root->reloc_root)
+	if (!is_fstree(btrfs_root_id(root)) || !root->reloc_root)
 		return 0;
 
 	spin_lock(&blocks->lock);
diff --git a/fs/btrfs/ref-verify.c b/fs/btrfs/ref-verify.c
index 8c4fc98ca9ce..cf531255ab76 100644
--- a/fs/btrfs/ref-verify.c
+++ b/fs/btrfs/ref-verify.c
@@ -673,7 +673,7 @@ int btrfs_ref_tree_mod(struct btrfs_fs_info *fs_info,
 	int ret = 0;
 	bool metadata;
 	u64 bytenr = generic_ref->bytenr;
-	u64 num_bytes = generic_ref->len;
+	u64 num_bytes = generic_ref->num_bytes;
 	u64 parent = generic_ref->parent;
 	u64 ref_root = 0;
 	u64 owner = 0;
@@ -684,11 +684,11 @@ int btrfs_ref_tree_mod(struct btrfs_fs_info *fs_info,
 
 	if (generic_ref->type == BTRFS_REF_METADATA) {
 		if (!parent)
-			ref_root = generic_ref->tree_ref.ref_root;
+			ref_root = generic_ref->ref_root;
 		owner = generic_ref->tree_ref.level;
 	} else if (!parent) {
-		ref_root = generic_ref->data_ref.ref_root;
-		owner = generic_ref->data_ref.ino;
+		ref_root = generic_ref->ref_root;
+		owner = generic_ref->data_ref.objectid;
 		offset = generic_ref->data_ref.offset;
 	}
 	metadata = owner < BTRFS_FIRST_FREE_OBJECTID;
diff --git a/fs/btrfs/reflink.c b/fs/btrfs/reflink.c
index 08d0fb46ceec..d0a3fcecc46a 100644
--- a/fs/btrfs/reflink.c
+++ b/fs/btrfs/reflink.c
@@ -616,35 +616,6 @@ out:
 	return ret;
 }
 
-static void btrfs_double_extent_unlock(struct inode *inode1, u64 loff1,
-				       struct inode *inode2, u64 loff2, u64 len)
-{
-	unlock_extent(&BTRFS_I(inode1)->io_tree, loff1, loff1 + len - 1, NULL);
-	unlock_extent(&BTRFS_I(inode2)->io_tree, loff2, loff2 + len - 1, NULL);
-}
-
-static void btrfs_double_extent_lock(struct inode *inode1, u64 loff1,
-				     struct inode *inode2, u64 loff2, u64 len)
-{
-	u64 range1_end = loff1 + len - 1;
-	u64 range2_end = loff2 + len - 1;
-
-	if (inode1 < inode2) {
-		swap(inode1, inode2);
-		swap(loff1, loff2);
-		swap(range1_end, range2_end);
-	} else if (inode1 == inode2 && loff2 < loff1) {
-		swap(loff1, loff2);
-		swap(range1_end, range2_end);
-	}
-
-	lock_extent(&BTRFS_I(inode1)->io_tree, loff1, range1_end, NULL);
-	lock_extent(&BTRFS_I(inode2)->io_tree, loff2, range2_end, NULL);
-
-	btrfs_assert_inode_range_clean(BTRFS_I(inode1), loff1, range1_end);
-	btrfs_assert_inode_range_clean(BTRFS_I(inode2), loff2, range2_end);
-}
-
 static void btrfs_double_mmap_lock(struct inode *inode1, struct inode *inode2)
 {
 	if (inode1 < inode2)
@@ -662,17 +633,21 @@ static void btrfs_double_mmap_unlock(struct inode *inode1, struct inode *inode2)
 static int btrfs_extent_same_range(struct inode *src, u64 loff, u64 len,
 				   struct inode *dst, u64 dst_loff)
 {
+	const u64 end = dst_loff + len - 1;
+	struct extent_state *cached_state = NULL;
 	struct btrfs_fs_info *fs_info = BTRFS_I(src)->root->fs_info;
 	const u64 bs = fs_info->sectorsize;
 	int ret;
 
 	/*
-	 * Lock destination range to serialize with concurrent readahead() and
-	 * source range to serialize with relocation.
+	 * Lock destination range to serialize with concurrent readahead(), and
+	 * we are safe from concurrency with relocation of source extents
+	 * because we have already locked the inode's i_mmap_lock in exclusive
+	 * mode.
 	 */
-	btrfs_double_extent_lock(src, loff, dst, dst_loff, len);
+	lock_extent(&BTRFS_I(dst)->io_tree, dst_loff, end, &cached_state);
 	ret = btrfs_clone(src, dst, loff, len, ALIGN(len, bs), dst_loff, 1);
-	btrfs_double_extent_unlock(src, loff, dst, dst_loff, len);
+	unlock_extent(&BTRFS_I(dst)->io_tree, dst_loff, end, &cached_state);
 
 	btrfs_btree_balance_dirty(fs_info);
 
@@ -690,7 +665,7 @@ static int btrfs_extent_same(struct inode *src, u64 loff, u64 olen,
 	if (root_dst->send_in_progress) {
 		btrfs_warn_rl(root_dst->fs_info,
 "cannot deduplicate to root %llu while send operations are using it (%d in progress)",
-			      root_dst->root_key.objectid,
+			      btrfs_root_id(root_dst),
 			      root_dst->send_in_progress);
 		spin_unlock(&root_dst->root_item_lock);
 		return -EAGAIN;
@@ -724,6 +699,7 @@ out:
 static noinline int btrfs_clone_files(struct file *file, struct file *file_src,
 					u64 off, u64 olen, u64 destoff)
 {
+	struct extent_state *cached_state = NULL;
 	struct inode *inode = file_inode(file);
 	struct inode *src = file_inode(file_src);
 	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
@@ -731,6 +707,7 @@ static noinline int btrfs_clone_files(struct file *file, struct file *file_src,
 	int wb_ret;
 	u64 len = olen;
 	u64 bs = fs_info->sectorsize;
+	u64 end;
 
 	/*
 	 * VFS's generic_remap_file_range_prep() protects us from cloning the
@@ -763,12 +740,15 @@ static noinline int btrfs_clone_files(struct file *file, struct file *file_src,
 	}
 
 	/*
-	 * Lock destination range to serialize with concurrent readahead() and
-	 * source range to serialize with relocation.
+	 * Lock destination range to serialize with concurrent readahead(), and
+	 * we are safe from concurrency with relocation of source extents
+	 * because we have already locked the inode's i_mmap_lock in exclusive
+	 * mode.
 	 */
-	btrfs_double_extent_lock(src, off, inode, destoff, len);
+	end = destoff + len - 1;
+	lock_extent(&BTRFS_I(inode)->io_tree, destoff, end, &cached_state);
 	ret = btrfs_clone(src, inode, off, olen, len, destoff, 0);
-	btrfs_double_extent_unlock(src, off, inode, destoff, len);
+	unlock_extent(&BTRFS_I(inode)->io_tree, destoff, end, &cached_state);
 
 	/*
 	 * We may have copied an inline extent into a page of the destination
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index f96f267fb4aa..8b24bb5a0aa1 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -473,20 +473,19 @@ static noinline_for_stack struct btrfs_backref_node *build_backref_tree(
 	struct btrfs_backref_node *node = NULL;
 	struct btrfs_backref_edge *edge;
 	int ret;
-	int err = 0;
 
 	iter = btrfs_backref_iter_alloc(rc->extent_root->fs_info);
 	if (!iter)
 		return ERR_PTR(-ENOMEM);
 	path = btrfs_alloc_path();
 	if (!path) {
-		err = -ENOMEM;
+		ret = -ENOMEM;
 		goto out;
 	}
 
 	node = btrfs_backref_alloc_node(cache, bytenr, level);
 	if (!node) {
-		err = -ENOMEM;
+		ret = -ENOMEM;
 		goto out;
 	}
 
@@ -497,10 +496,9 @@ static noinline_for_stack struct btrfs_backref_node *build_backref_tree(
 	do {
 		ret = btrfs_backref_add_tree_node(trans, cache, path, iter,
 						  node_key, cur);
-		if (ret < 0) {
-			err = ret;
+		if (ret < 0)
 			goto out;
-		}
+
 		edge = list_first_entry_or_null(&cache->pending_edge,
 				struct btrfs_backref_edge, list[UPPER]);
 		/*
@@ -515,10 +513,8 @@ static noinline_for_stack struct btrfs_backref_node *build_backref_tree(
 
 	/* Finish the upper linkage of newly added edges/nodes */
 	ret = btrfs_backref_finish_upper_links(cache, node);
-	if (ret < 0) {
-		err = ret;
+	if (ret < 0)
 		goto out;
-	}
 
 	if (handle_useless_nodes(rc, node))
 		node = NULL;
@@ -526,9 +522,9 @@ out:
 	btrfs_free_path(iter->path);
 	kfree(iter);
 	btrfs_free_path(path);
-	if (err) {
+	if (ret) {
 		btrfs_backref_error_cleanup(cache, node);
-		return ERR_PTR(err);
+		return ERR_PTR(ret);
 	}
 	ASSERT(!node || !node->detached);
 	ASSERT(list_empty(&cache->useless_node) &&
@@ -754,7 +750,7 @@ static struct btrfs_root *create_reloc_root(struct btrfs_trans_handle *trans,
 	root_key.type = BTRFS_ROOT_ITEM_KEY;
 	root_key.offset = objectid;
 
-	if (root->root_key.objectid == objectid) {
+	if (btrfs_root_id(root) == objectid) {
 		u64 commit_root_gen;
 
 		/* called by btrfs_init_reloc_root */
@@ -798,7 +794,7 @@ static struct btrfs_root *create_reloc_root(struct btrfs_trans_handle *trans,
 	btrfs_set_root_level(root_item, btrfs_header_level(eb));
 	btrfs_set_root_generation(root_item, trans->transid);
 
-	if (root->root_key.objectid == objectid) {
+	if (btrfs_root_id(root) == objectid) {
 		btrfs_set_root_refs(root_item, 0);
 		memset(&root_item->drop_progress, 0,
 		       sizeof(struct btrfs_disk_key));
@@ -876,8 +872,7 @@ int btrfs_init_reloc_root(struct btrfs_trans_handle *trans,
 	 * We are merging reloc roots, we do not need new reloc trees.  Also
 	 * reloc trees never need their own reloc tree.
 	 */
-	if (!rc->create_reloc_tree ||
-	    root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID)
+	if (!rc->create_reloc_tree || btrfs_root_id(root) == BTRFS_TREE_RELOC_OBJECTID)
 		return 0;
 
 	if (!trans->reloc_reserved) {
@@ -885,7 +880,7 @@ int btrfs_init_reloc_root(struct btrfs_trans_handle *trans,
 		trans->block_rsv = rc->block_rsv;
 		clear_rsv = 1;
 	}
-	reloc_root = create_reloc_root(trans, root, root->root_key.objectid);
+	reloc_root = create_reloc_root(trans, root, btrfs_root_id(root));
 	if (clear_rsv)
 		trans->block_rsv = rsv;
 	if (IS_ERR(reloc_root))
@@ -952,60 +947,6 @@ int btrfs_update_reloc_root(struct btrfs_trans_handle *trans,
 }
 
 /*
- * helper to find first cached inode with inode number >= objectid
- * in a subvolume
- */
-static struct inode *find_next_inode(struct btrfs_root *root, u64 objectid)
-{
-	struct rb_node *node;
-	struct rb_node *prev;
-	struct btrfs_inode *entry;
-	struct inode *inode;
-
-	spin_lock(&root->inode_lock);
-again:
-	node = root->inode_tree.rb_node;
-	prev = NULL;
-	while (node) {
-		prev = node;
-		entry = rb_entry(node, struct btrfs_inode, rb_node);
-
-		if (objectid < btrfs_ino(entry))
-			node = node->rb_left;
-		else if (objectid > btrfs_ino(entry))
-			node = node->rb_right;
-		else
-			break;
-	}
-	if (!node) {
-		while (prev) {
-			entry = rb_entry(prev, struct btrfs_inode, rb_node);
-			if (objectid <= btrfs_ino(entry)) {
-				node = prev;
-				break;
-			}
-			prev = rb_next(prev);
-		}
-	}
-	while (node) {
-		entry = rb_entry(node, struct btrfs_inode, rb_node);
-		inode = igrab(&entry->vfs_inode);
-		if (inode) {
-			spin_unlock(&root->inode_lock);
-			return inode;
-		}
-
-		objectid = btrfs_ino(entry) + 1;
-		if (cond_resched_lock(&root->inode_lock))
-			goto again;
-
-		node = rb_next(node);
-	}
-	spin_unlock(&root->inode_lock);
-	return NULL;
-}
-
-/*
  * get new location of data
  */
 static int get_new_location(struct inode *reloc_inode, u64 *new_bytenr,
@@ -1065,7 +1006,7 @@ int replace_file_extents(struct btrfs_trans_handle *trans,
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct btrfs_key key;
 	struct btrfs_file_extent_item *fi;
-	struct inode *inode = NULL;
+	struct btrfs_inode *inode = NULL;
 	u64 parent;
 	u64 bytenr;
 	u64 new_bytenr = 0;
@@ -1081,7 +1022,7 @@ int replace_file_extents(struct btrfs_trans_handle *trans,
 		return 0;
 
 	/* reloc trees always use full backref */
-	if (root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID)
+	if (btrfs_root_id(root) == BTRFS_TREE_RELOC_OBJECTID)
 		parent = leaf->start;
 	else
 		parent = 0;
@@ -1110,15 +1051,15 @@ int replace_file_extents(struct btrfs_trans_handle *trans,
 		 * if we are modifying block in fs tree, wait for read_folio
 		 * to complete and drop the extent cache
 		 */
-		if (root->root_key.objectid != BTRFS_TREE_RELOC_OBJECTID) {
+		if (btrfs_root_id(root) != BTRFS_TREE_RELOC_OBJECTID) {
 			if (first) {
-				inode = find_next_inode(root, key.objectid);
+				inode = btrfs_find_first_inode(root, key.objectid);
 				first = 0;
-			} else if (inode && btrfs_ino(BTRFS_I(inode)) < key.objectid) {
-				btrfs_add_delayed_iput(BTRFS_I(inode));
-				inode = find_next_inode(root, key.objectid);
+			} else if (inode && btrfs_ino(inode) < key.objectid) {
+				btrfs_add_delayed_iput(inode);
+				inode = btrfs_find_first_inode(root, key.objectid);
 			}
-			if (inode && btrfs_ino(BTRFS_I(inode)) == key.objectid) {
+			if (inode && btrfs_ino(inode) == key.objectid) {
 				struct extent_state *cached_state = NULL;
 
 				end = key.offset +
@@ -1127,16 +1068,20 @@ int replace_file_extents(struct btrfs_trans_handle *trans,
 						    fs_info->sectorsize));
 				WARN_ON(!IS_ALIGNED(end, fs_info->sectorsize));
 				end--;
-				ret = try_lock_extent(&BTRFS_I(inode)->io_tree,
-						      key.offset, end,
-						      &cached_state);
-				if (!ret)
+				/* Take mmap lock to serialize with reflinks. */
+				if (!down_read_trylock(&inode->i_mmap_lock))
+					continue;
+				ret = try_lock_extent(&inode->io_tree, key.offset,
+						      end, &cached_state);
+				if (!ret) {
+					up_read(&inode->i_mmap_lock);
 					continue;
+				}
 
-				btrfs_drop_extent_map_range(BTRFS_I(inode),
-							    key.offset, end, true);
-				unlock_extent(&BTRFS_I(inode)->io_tree,
-					      key.offset, end, &cached_state);
+				btrfs_drop_extent_map_range(inode, key.offset, end, true);
+				unlock_extent(&inode->io_tree, key.offset, end,
+					      &cached_state);
+				up_read(&inode->i_mmap_lock);
 			}
 		}
 
@@ -1154,22 +1099,28 @@ int replace_file_extents(struct btrfs_trans_handle *trans,
 		dirty = 1;
 
 		key.offset -= btrfs_file_extent_offset(leaf, fi);
-		btrfs_init_generic_ref(&ref, BTRFS_ADD_DELAYED_REF, new_bytenr,
-				       num_bytes, parent, root->root_key.objectid);
-		btrfs_init_data_ref(&ref, btrfs_header_owner(leaf),
-				    key.objectid, key.offset,
-				    root->root_key.objectid, false);
+		ref.action = BTRFS_ADD_DELAYED_REF;
+		ref.bytenr = new_bytenr;
+		ref.num_bytes = num_bytes;
+		ref.parent = parent;
+		ref.owning_root = btrfs_root_id(root);
+		ref.ref_root = btrfs_header_owner(leaf);
+		btrfs_init_data_ref(&ref, key.objectid, key.offset,
+				    btrfs_root_id(root), false);
 		ret = btrfs_inc_extent_ref(trans, &ref);
 		if (ret) {
 			btrfs_abort_transaction(trans, ret);
 			break;
 		}
 
-		btrfs_init_generic_ref(&ref, BTRFS_DROP_DELAYED_REF, bytenr,
-				       num_bytes, parent, root->root_key.objectid);
-		btrfs_init_data_ref(&ref, btrfs_header_owner(leaf),
-				    key.objectid, key.offset,
-				    root->root_key.objectid, false);
+		ref.action = BTRFS_DROP_DELAYED_REF;
+		ref.bytenr = bytenr;
+		ref.num_bytes = num_bytes;
+		ref.parent = parent;
+		ref.owning_root = btrfs_root_id(root);
+		ref.ref_root = btrfs_header_owner(leaf);
+		btrfs_init_data_ref(&ref, key.objectid, key.offset,
+				    btrfs_root_id(root), false);
 		ret = btrfs_free_extent(trans, &ref);
 		if (ret) {
 			btrfs_abort_transaction(trans, ret);
@@ -1179,7 +1130,7 @@ int replace_file_extents(struct btrfs_trans_handle *trans,
 	if (dirty)
 		btrfs_mark_buffer_dirty(trans, leaf);
 	if (inode)
-		btrfs_add_delayed_iput(BTRFS_I(inode));
+		btrfs_add_delayed_iput(inode);
 	return ret;
 }
 
@@ -1225,8 +1176,8 @@ int replace_path(struct btrfs_trans_handle *trans, struct reloc_control *rc,
 	int ret;
 	int slot;
 
-	ASSERT(src->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID);
-	ASSERT(dest->root_key.objectid != BTRFS_TREE_RELOC_OBJECTID);
+	ASSERT(btrfs_root_id(src) == BTRFS_TREE_RELOC_OBJECTID);
+	ASSERT(btrfs_root_id(dest) != BTRFS_TREE_RELOC_OBJECTID);
 
 	last_snapshot = btrfs_root_last_snapshot(&src->root_item);
 again:
@@ -1378,20 +1329,26 @@ again:
 					      path->slots[level], old_ptr_gen);
 		btrfs_mark_buffer_dirty(trans, path->nodes[level]);
 
-		btrfs_init_generic_ref(&ref, BTRFS_ADD_DELAYED_REF, old_bytenr,
-				       blocksize, path->nodes[level]->start,
-				       src->root_key.objectid);
-		btrfs_init_tree_ref(&ref, level - 1, src->root_key.objectid,
-				    0, true);
+		ref.action = BTRFS_ADD_DELAYED_REF;
+		ref.bytenr = old_bytenr;
+		ref.num_bytes = blocksize;
+		ref.parent = path->nodes[level]->start;
+		ref.owning_root = btrfs_root_id(src);
+		ref.ref_root = btrfs_root_id(src);
+		btrfs_init_tree_ref(&ref, level - 1, 0, true);
 		ret = btrfs_inc_extent_ref(trans, &ref);
 		if (ret) {
 			btrfs_abort_transaction(trans, ret);
 			break;
 		}
-		btrfs_init_generic_ref(&ref, BTRFS_ADD_DELAYED_REF, new_bytenr,
-				       blocksize, 0, dest->root_key.objectid);
-		btrfs_init_tree_ref(&ref, level - 1, dest->root_key.objectid, 0,
-				    true);
+
+		ref.action = BTRFS_ADD_DELAYED_REF;
+		ref.bytenr = new_bytenr;
+		ref.num_bytes = blocksize;
+		ref.parent = 0;
+		ref.owning_root = btrfs_root_id(dest);
+		ref.ref_root = btrfs_root_id(dest);
+		btrfs_init_tree_ref(&ref, level - 1, 0, true);
 		ret = btrfs_inc_extent_ref(trans, &ref);
 		if (ret) {
 			btrfs_abort_transaction(trans, ret);
@@ -1399,10 +1356,13 @@ again:
 		}
 
 		/* We don't know the real owning_root, use 0. */
-		btrfs_init_generic_ref(&ref, BTRFS_DROP_DELAYED_REF, new_bytenr,
-				       blocksize, path->nodes[level]->start, 0);
-		btrfs_init_tree_ref(&ref, level - 1, src->root_key.objectid,
-				    0, true);
+		ref.action = BTRFS_DROP_DELAYED_REF;
+		ref.bytenr = new_bytenr;
+		ref.num_bytes = blocksize;
+		ref.parent = path->nodes[level]->start;
+		ref.owning_root = 0;
+		ref.ref_root = btrfs_root_id(src);
+		btrfs_init_tree_ref(&ref, level - 1, 0, true);
 		ret = btrfs_free_extent(trans, &ref);
 		if (ret) {
 			btrfs_abort_transaction(trans, ret);
@@ -1410,10 +1370,13 @@ again:
 		}
 
 		/* We don't know the real owning_root, use 0. */
-		btrfs_init_generic_ref(&ref, BTRFS_DROP_DELAYED_REF, old_bytenr,
-				       blocksize, 0, 0);
-		btrfs_init_tree_ref(&ref, level - 1, dest->root_key.objectid,
-				    0, true);
+		ref.action = BTRFS_DROP_DELAYED_REF;
+		ref.bytenr = old_bytenr;
+		ref.num_bytes = blocksize;
+		ref.parent = 0;
+		ref.owning_root = 0;
+		ref.ref_root = btrfs_root_id(dest);
+		btrfs_init_tree_ref(&ref, level - 1, 0, true);
 		ret = btrfs_free_extent(trans, &ref);
 		if (ret) {
 			btrfs_abort_transaction(trans, ret);
@@ -1521,7 +1484,7 @@ static int invalidate_extent_cache(struct btrfs_root *root,
 				   const struct btrfs_key *max_key)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
-	struct inode *inode = NULL;
+	struct btrfs_inode *inode = NULL;
 	u64 objectid;
 	u64 start, end;
 	u64 ino;
@@ -1531,23 +1494,24 @@ static int invalidate_extent_cache(struct btrfs_root *root,
 		struct extent_state *cached_state = NULL;
 
 		cond_resched();
-		iput(inode);
+		if (inode)
+			iput(&inode->vfs_inode);
 
 		if (objectid > max_key->objectid)
 			break;
 
-		inode = find_next_inode(root, objectid);
+		inode = btrfs_find_first_inode(root, objectid);
 		if (!inode)
 			break;
-		ino = btrfs_ino(BTRFS_I(inode));
+		ino = btrfs_ino(inode);
 
 		if (ino > max_key->objectid) {
-			iput(inode);
+			iput(&inode->vfs_inode);
 			break;
 		}
 
 		objectid = ino + 1;
-		if (!S_ISREG(inode->i_mode))
+		if (!S_ISREG(inode->vfs_inode.i_mode))
 			continue;
 
 		if (unlikely(min_key->objectid == ino)) {
@@ -1580,9 +1544,9 @@ static int invalidate_extent_cache(struct btrfs_root *root,
 		}
 
 		/* the lock_extent waits for read_folio to complete */
-		lock_extent(&BTRFS_I(inode)->io_tree, start, end, &cached_state);
-		btrfs_drop_extent_map_range(BTRFS_I(inode), start, end, true);
-		unlock_extent(&BTRFS_I(inode)->io_tree, start, end, &cached_state);
+		lock_extent(&inode->io_tree, start, end, &cached_state);
+		btrfs_drop_extent_map_range(inode, start, end, true);
+		unlock_extent(&inode->io_tree, start, end, &cached_state);
 	}
 	return 0;
 }
@@ -1617,7 +1581,7 @@ static int insert_dirty_subvol(struct btrfs_trans_handle *trans,
 	int ret;
 
 	/* @root must be a subvolume tree root with a valid reloc tree */
-	ASSERT(root->root_key.objectid != BTRFS_TREE_RELOC_OBJECTID);
+	ASSERT(btrfs_root_id(root) != BTRFS_TREE_RELOC_OBJECTID);
 	ASSERT(reloc_root);
 
 	reloc_root_item = &reloc_root->root_item;
@@ -1646,7 +1610,7 @@ static int clean_dirty_subvols(struct reloc_control *rc)
 
 	list_for_each_entry_safe(root, next, &rc->dirty_subvol_roots,
 				 reloc_dirty_list) {
-		if (root->root_key.objectid != BTRFS_TREE_RELOC_OBJECTID) {
+		if (btrfs_root_id(root) != BTRFS_TREE_RELOC_OBJECTID) {
 			/* Merged subvolume, cleanup its reloc root */
 			struct btrfs_root *reloc_root = root->reloc_root;
 
@@ -1921,13 +1885,13 @@ again:
 			if (root->reloc_root) {
 				btrfs_err(fs_info,
 "reloc tree mismatch, root %lld has reloc root key (%lld %u %llu) gen %llu, expect reloc root key (%lld %u %llu) gen %llu",
-					  root->root_key.objectid,
-					  root->reloc_root->root_key.objectid,
+					  btrfs_root_id(root),
+					  btrfs_root_id(root->reloc_root),
 					  root->reloc_root->root_key.type,
 					  root->reloc_root->root_key.offset,
 					  btrfs_root_generation(
 						  &root->reloc_root->root_item),
-					  reloc_root->root_key.objectid,
+					  btrfs_root_id(reloc_root),
 					  reloc_root->root_key.type,
 					  reloc_root->root_key.offset,
 					  btrfs_root_generation(
@@ -1935,8 +1899,8 @@ again:
 			} else {
 				btrfs_err(fs_info,
 "reloc tree mismatch, root %lld has no reloc root, expect reloc root key (%lld %u %llu) gen %llu",
-					  root->root_key.objectid,
-					  reloc_root->root_key.objectid,
+					  btrfs_root_id(root),
+					  btrfs_root_id(reloc_root),
 					  reloc_root->root_key.type,
 					  reloc_root->root_key.offset,
 					  btrfs_root_generation(
@@ -2193,7 +2157,7 @@ struct btrfs_root *select_reloc_root(struct btrfs_trans_handle *trans,
 			return ERR_PTR(-EUCLEAN);
 		}
 
-		if (root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID) {
+		if (btrfs_root_id(root) == BTRFS_TREE_RELOC_OBJECTID) {
 			ret = record_reloc_root_in_trans(trans, root);
 			if (ret)
 				return ERR_PTR(ret);
@@ -2300,7 +2264,7 @@ struct btrfs_root *select_one_root(struct btrfs_backref_node *node)
 		if (!test_bit(BTRFS_ROOT_SHAREABLE, &root->state))
 			return root;
 
-		if (root->root_key.objectid != BTRFS_TREE_RELOC_OBJECTID)
+		if (btrfs_root_id(root) != BTRFS_TREE_RELOC_OBJECTID)
 			fs_root = root;
 
 		if (next != node)
@@ -2316,9 +2280,8 @@ struct btrfs_root *select_one_root(struct btrfs_backref_node *node)
 	return fs_root;
 }
 
-static noinline_for_stack
-u64 calcu_metadata_size(struct reloc_control *rc,
-			struct btrfs_backref_node *node, int reserve)
+static noinline_for_stack u64 calcu_metadata_size(struct reloc_control *rc,
+						  struct btrfs_backref_node *node)
 {
 	struct btrfs_fs_info *fs_info = rc->extent_root->fs_info;
 	struct btrfs_backref_node *next = node;
@@ -2327,12 +2290,12 @@ u64 calcu_metadata_size(struct reloc_control *rc,
 	u64 num_bytes = 0;
 	int index = 0;
 
-	BUG_ON(reserve && node->processed);
+	BUG_ON(node->processed);
 
 	while (next) {
 		cond_resched();
 		while (1) {
-			if (next->processed && (reserve || next != node))
+			if (next->processed)
 				break;
 
 			num_bytes += fs_info->nodesize;
@@ -2360,7 +2323,7 @@ static int reserve_metadata_space(struct btrfs_trans_handle *trans,
 	int ret;
 	u64 tmp;
 
-	num_bytes = calcu_metadata_size(rc, node, 1) * 2;
+	num_bytes = calcu_metadata_size(rc, node) * 2;
 
 	trans->block_rsv = rc->block_rsv;
 	rc->reserved_bytes += num_bytes;
@@ -2423,8 +2386,6 @@ static int do_relocation(struct btrfs_trans_handle *trans,
 	path->lowest_level = node->level + 1;
 	rc->backref_cache.path[node->level] = node;
 	list_for_each_entry(edge, &node->upper, list[LOWER]) {
-		struct btrfs_ref ref = { 0 };
-
 		cond_resched();
 
 		upper = edge->node[UPPER];
@@ -2512,19 +2473,23 @@ static int do_relocation(struct btrfs_trans_handle *trans,
 			 */
 			ASSERT(node->eb == eb);
 		} else {
+			struct btrfs_ref ref = {
+				.action = BTRFS_ADD_DELAYED_REF,
+				.bytenr = node->eb->start,
+				.num_bytes = blocksize,
+				.parent = upper->eb->start,
+				.owning_root = btrfs_header_owner(upper->eb),
+				.ref_root = btrfs_header_owner(upper->eb),
+			};
+
 			btrfs_set_node_blockptr(upper->eb, slot,
 						node->eb->start);
 			btrfs_set_node_ptr_generation(upper->eb, slot,
 						      trans->transid);
 			btrfs_mark_buffer_dirty(trans, upper->eb);
 
-			btrfs_init_generic_ref(&ref, BTRFS_ADD_DELAYED_REF,
-					       node->eb->start, blocksize,
-					       upper->eb->start,
-					       btrfs_header_owner(upper->eb));
 			btrfs_init_tree_ref(&ref, node->level,
-					    btrfs_header_owner(upper->eb),
-					    root->root_key.objectid, false);
+					    btrfs_root_id(root), false);
 			ret = btrfs_inc_extent_ref(trans, &ref);
 			if (!ret)
 				ret = btrfs_drop_subtree(trans, root, eb,
@@ -2776,12 +2741,11 @@ int relocate_tree_blocks(struct btrfs_trans_handle *trans,
 	struct btrfs_path *path;
 	struct tree_block *block;
 	struct tree_block *next;
-	int ret;
-	int err = 0;
+	int ret = 0;
 
 	path = btrfs_alloc_path();
 	if (!path) {
-		err = -ENOMEM;
+		ret = -ENOMEM;
 		goto out_free_blocks;
 	}
 
@@ -2796,8 +2760,8 @@ int relocate_tree_blocks(struct btrfs_trans_handle *trans,
 	/* Get first keys */
 	rbtree_postorder_for_each_entry_safe(block, next, blocks, rb_node) {
 		if (!block->key_ready) {
-			err = get_tree_block_key(fs_info, block);
-			if (err)
+			ret = get_tree_block_key(fs_info, block);
+			if (ret)
 				goto out_free_path;
 		}
 	}
@@ -2807,25 +2771,23 @@ int relocate_tree_blocks(struct btrfs_trans_handle *trans,
 		node = build_backref_tree(trans, rc, &block->key,
 					  block->level, block->bytenr);
 		if (IS_ERR(node)) {
-			err = PTR_ERR(node);
+			ret = PTR_ERR(node);
 			goto out;
 		}
 
 		ret = relocate_tree_block(trans, rc, node, &block->key,
 					  path);
-		if (ret < 0) {
-			err = ret;
+		if (ret < 0)
 			break;
-		}
 	}
 out:
-	err = finish_pending_nodes(trans, rc, path, err);
+	ret = finish_pending_nodes(trans, rc, path, ret);
 
 out_free_path:
 	btrfs_free_path(path);
 out_free_blocks:
 	free_block_list(blocks);
-	return err;
+	return ret;
 }
 
 static noinline_for_stack int prealloc_file_extent_cluster(
@@ -2850,7 +2812,7 @@ static noinline_for_stack int prealloc_file_extent_cluster(
 	 * btrfs_do_readpage() call of previously relocated file cluster.
 	 *
 	 * If the current cluster starts in the above range, btrfs_do_readpage()
-	 * will skip the read, and relocate_one_page() will later writeback
+	 * will skip the read, and relocate_one_folio() will later writeback
 	 * the padding zeros as new data, causing data corruption.
 	 *
 	 * Here we have to manually invalidate the range (i_size, PAGE_END + 1).
@@ -2859,7 +2821,7 @@ static noinline_for_stack int prealloc_file_extent_cluster(
 		struct address_space *mapping = inode->vfs_inode.i_mapping;
 		struct btrfs_fs_info *fs_info = inode->root->fs_info;
 		const u32 sectorsize = fs_info->sectorsize;
-		struct page *page;
+		struct folio *folio;
 
 		ASSERT(sectorsize < PAGE_SIZE);
 		ASSERT(IS_ALIGNED(i_size, sectorsize));
@@ -2890,16 +2852,16 @@ static noinline_for_stack int prealloc_file_extent_cluster(
 		clear_extent_bits(&inode->io_tree, i_size,
 				  round_up(i_size, PAGE_SIZE) - 1,
 				  EXTENT_UPTODATE);
-		page = find_lock_page(mapping, i_size >> PAGE_SHIFT);
+		folio = filemap_lock_folio(mapping, i_size >> PAGE_SHIFT);
 		/*
 		 * If page is freed we don't need to do anything then, as we
 		 * will re-read the whole page anyway.
 		 */
-		if (page) {
-			btrfs_subpage_clear_uptodate(fs_info, page_folio(page), i_size,
+		if (!IS_ERR(folio)) {
+			btrfs_subpage_clear_uptodate(fs_info, folio, i_size,
 					round_up(i_size, PAGE_SIZE) - i_size);
-			unlock_page(page);
-			put_page(page);
+			folio_unlock(folio);
+			folio_put(folio);
 		}
 	}
 
@@ -2984,68 +2946,71 @@ static u64 get_cluster_boundary_end(const struct file_extent_cluster *cluster,
 	return cluster->boundary[cluster_nr + 1] - 1;
 }
 
-static int relocate_one_page(struct inode *inode, struct file_ra_state *ra,
-			     const struct file_extent_cluster *cluster,
-			     int *cluster_nr, unsigned long page_index)
+static int relocate_one_folio(struct inode *inode, struct file_ra_state *ra,
+			      const struct file_extent_cluster *cluster,
+			      int *cluster_nr, unsigned long index)
 {
 	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
 	u64 offset = BTRFS_I(inode)->index_cnt;
 	const unsigned long last_index = (cluster->end - offset) >> PAGE_SHIFT;
 	gfp_t mask = btrfs_alloc_write_mask(inode->i_mapping);
-	struct page *page;
-	u64 page_start;
-	u64 page_end;
+	struct folio *folio;
+	u64 folio_start;
+	u64 folio_end;
 	u64 cur;
 	int ret;
 
-	ASSERT(page_index <= last_index);
-	page = find_lock_page(inode->i_mapping, page_index);
-	if (!page) {
+	ASSERT(index <= last_index);
+	folio = filemap_lock_folio(inode->i_mapping, index);
+	if (IS_ERR(folio)) {
 		page_cache_sync_readahead(inode->i_mapping, ra, NULL,
-				page_index, last_index + 1 - page_index);
-		page = find_or_create_page(inode->i_mapping, page_index, mask);
-		if (!page)
-			return -ENOMEM;
+					  index, last_index + 1 - index);
+		folio = __filemap_get_folio(inode->i_mapping, index,
+					    FGP_LOCK | FGP_ACCESSED | FGP_CREAT, mask);
+		if (IS_ERR(folio))
+			return PTR_ERR(folio);
 	}
 
-	if (PageReadahead(page))
+	WARN_ON(folio_order(folio));
+
+	if (folio_test_readahead(folio))
 		page_cache_async_readahead(inode->i_mapping, ra, NULL,
-				page_folio(page), page_index,
-				last_index + 1 - page_index);
+					   folio, index,
+					   last_index + 1 - index);
 
-	if (!PageUptodate(page)) {
-		btrfs_read_folio(NULL, page_folio(page));
-		lock_page(page);
-		if (!PageUptodate(page)) {
+	if (!folio_test_uptodate(folio)) {
+		btrfs_read_folio(NULL, folio);
+		folio_lock(folio);
+		if (!folio_test_uptodate(folio)) {
 			ret = -EIO;
-			goto release_page;
+			goto release_folio;
 		}
 	}
 
 	/*
-	 * We could have lost page private when we dropped the lock to read the
-	 * page above, make sure we set_page_extent_mapped here so we have any
+	 * We could have lost folio private when we dropped the lock to read the
+	 * folio above, make sure we set_page_extent_mapped here so we have any
 	 * of the subpage blocksize stuff we need in place.
 	 */
-	ret = set_page_extent_mapped(page);
+	ret = set_folio_extent_mapped(folio);
 	if (ret < 0)
-		goto release_page;
+		goto release_folio;
 
-	page_start = page_offset(page);
-	page_end = page_start + PAGE_SIZE - 1;
+	folio_start = folio_pos(folio);
+	folio_end = folio_start + PAGE_SIZE - 1;
 
 	/*
 	 * Start from the cluster, as for subpage case, the cluster can start
-	 * inside the page.
+	 * inside the folio.
 	 */
-	cur = max(page_start, cluster->boundary[*cluster_nr] - offset);
-	while (cur <= page_end) {
+	cur = max(folio_start, cluster->boundary[*cluster_nr] - offset);
+	while (cur <= folio_end) {
 		struct extent_state *cached_state = NULL;
 		u64 extent_start = cluster->boundary[*cluster_nr] - offset;
 		u64 extent_end = get_cluster_boundary_end(cluster,
 						*cluster_nr) - offset;
-		u64 clamped_start = max(page_start, extent_start);
-		u64 clamped_end = min(page_end, extent_end);
+		u64 clamped_start = max(folio_start, extent_start);
+		u64 clamped_end = min(folio_end, extent_end);
 		u32 clamped_len = clamped_end + 1 - clamped_start;
 
 		/* Reserve metadata for this range */
@@ -3053,7 +3018,7 @@ static int relocate_one_page(struct inode *inode, struct file_ra_state *ra,
 						      clamped_len, clamped_len,
 						      false);
 		if (ret)
-			goto release_page;
+			goto release_folio;
 
 		/* Mark the range delalloc and dirty for later writeback */
 		lock_extent(&BTRFS_I(inode)->io_tree, clamped_start, clamped_end,
@@ -3069,20 +3034,18 @@ static int relocate_one_page(struct inode *inode, struct file_ra_state *ra,
 							clamped_len, true);
 			btrfs_delalloc_release_extents(BTRFS_I(inode),
 						       clamped_len);
-			goto release_page;
+			goto release_folio;
 		}
-		btrfs_folio_set_dirty(fs_info, page_folio(page),
-				      clamped_start, clamped_len);
+		btrfs_folio_set_dirty(fs_info, folio, clamped_start, clamped_len);
 
 		/*
-		 * Set the boundary if it's inside the page.
+		 * Set the boundary if it's inside the folio.
 		 * Data relocation requires the destination extents to have the
 		 * same size as the source.
 		 * EXTENT_BOUNDARY bit prevents current extent from being merged
 		 * with previous extent.
 		 */
-		if (in_range(cluster->boundary[*cluster_nr] - offset,
-			     page_start, PAGE_SIZE)) {
+		if (in_range(cluster->boundary[*cluster_nr] - offset, folio_start, PAGE_SIZE)) {
 			u64 boundary_start = cluster->boundary[*cluster_nr] -
 						offset;
 			u64 boundary_end = boundary_start +
@@ -3105,8 +3068,8 @@ static int relocate_one_page(struct inode *inode, struct file_ra_state *ra,
 				break;
 		}
 	}
-	unlock_page(page);
-	put_page(page);
+	folio_unlock(folio);
+	folio_put(folio);
 
 	balance_dirty_pages_ratelimited(inode->i_mapping);
 	btrfs_throttle(fs_info);
@@ -3114,9 +3077,9 @@ static int relocate_one_page(struct inode *inode, struct file_ra_state *ra,
 		ret = -ECANCELED;
 	return ret;
 
-release_page:
-	unlock_page(page);
-	put_page(page);
+release_folio:
+	folio_unlock(folio);
+	folio_put(folio);
 	return ret;
 }
 
@@ -3151,7 +3114,7 @@ static int relocate_file_extent_cluster(struct inode *inode,
 	last_index = (cluster->end - offset) >> PAGE_SHIFT;
 	for (index = (cluster->start - offset) >> PAGE_SHIFT;
 	     index <= last_index && !ret; index++)
-		ret = relocate_one_page(inode, ra, cluster, &cluster_nr, index);
+		ret = relocate_one_folio(inode, ra, cluster, &cluster_nr, index);
 	if (ret == 0)
 		WARN_ON(cluster_nr != cluster->nr);
 out:
@@ -3928,7 +3891,7 @@ static noinline_for_stack struct inode *create_reloc_inode(
 	struct btrfs_trans_handle *trans;
 	struct btrfs_root *root;
 	u64 objectid;
-	int err = 0;
+	int ret = 0;
 
 	root = btrfs_grab_root(fs_info->data_reloc_root);
 	trans = btrfs_start_transaction(root, 6);
@@ -3937,31 +3900,31 @@ static noinline_for_stack struct inode *create_reloc_inode(
 		return ERR_CAST(trans);
 	}
 
-	err = btrfs_get_free_objectid(root, &objectid);
-	if (err)
+	ret = btrfs_get_free_objectid(root, &objectid);
+	if (ret)
 		goto out;
 
-	err = __insert_orphan_inode(trans, root, objectid);
-	if (err)
+	ret = __insert_orphan_inode(trans, root, objectid);
+	if (ret)
 		goto out;
 
 	inode = btrfs_iget(fs_info->sb, objectid, root);
 	if (IS_ERR(inode)) {
 		delete_orphan_inode(trans, root, objectid);
-		err = PTR_ERR(inode);
+		ret = PTR_ERR(inode);
 		inode = NULL;
 		goto out;
 	}
 	BTRFS_I(inode)->index_cnt = group->start;
 
-	err = btrfs_orphan_add(trans, BTRFS_I(inode));
+	ret = btrfs_orphan_add(trans, BTRFS_I(inode));
 out:
 	btrfs_put_root(root);
 	btrfs_end_transaction(trans);
 	btrfs_btree_balance_dirty(fs_info);
-	if (err) {
+	if (ret) {
 		iput(inode);
-		inode = ERR_PTR(err);
+		inode = ERR_PTR(ret);
 	}
 	return inode;
 }
@@ -4439,9 +4402,11 @@ int btrfs_reloc_clone_csums(struct btrfs_ordered_extent *ordered)
 
 	ret = btrfs_lookup_csums_list(csum_root, disk_bytenr,
 				      disk_bytenr + ordered->num_bytes - 1,
-				      &list, 0, false);
-	if (ret)
+				      &list, false);
+	if (ret < 0) {
+		btrfs_mark_ordered_extent_error(ordered);
 		return ret;
+	}
 
 	while (!list_empty(&list)) {
 		struct btrfs_ordered_sum *sums =
@@ -4491,8 +4456,7 @@ int btrfs_reloc_cow_block(struct btrfs_trans_handle *trans,
 	    btrfs_root_last_snapshot(&root->root_item))
 		first_cow = 1;
 
-	if (root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID &&
-	    rc->create_reloc_tree) {
+	if (btrfs_root_id(root) == BTRFS_TREE_RELOC_OBJECTID && rc->create_reloc_tree) {
 		WARN_ON(!first_cow && level == 0);
 
 		node = rc->backref_cache.path[level];
@@ -4585,8 +4549,7 @@ int btrfs_reloc_post_snapshot(struct btrfs_trans_handle *trans,
 	}
 
 	new_root = pending->snap;
-	reloc_root = create_reloc_root(trans, root->reloc_root,
-				       new_root->root_key.objectid);
+	reloc_root = create_reloc_root(trans, root->reloc_root, btrfs_root_id(new_root));
 	if (IS_ERR(reloc_root))
 		return PTR_ERR(reloc_root);
 
diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c
index 7007f9e0c972..33962671a96c 100644
--- a/fs/btrfs/root-tree.c
+++ b/fs/btrfs/root-tree.c
@@ -148,8 +148,7 @@ int btrfs_update_root(struct btrfs_trans_handle *trans, struct btrfs_root
 	if (ret > 0) {
 		btrfs_crit(fs_info,
 			"unable to find root key (%llu %u %llu) in tree %llu",
-			key->objectid, key->type, key->offset,
-			root->root_key.objectid);
+			key->objectid, key->type, key->offset, btrfs_root_id(root));
 		ret = -EUCLEAN;
 		btrfs_abort_transaction(trans, ret);
 		goto out;
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 50b4a76ac88e..3dd4a48479a9 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -392,9 +392,8 @@ static void inconsistent_snapshot_error(struct send_ctx *sctx,
 	btrfs_err(sctx->send_root->fs_info,
 		  "Send: inconsistent snapshot, found %s %s for inode %llu without updated inode item, send root is %llu, parent root is %llu",
 		  result_string, what, sctx->cmp_key->objectid,
-		  sctx->send_root->root_key.objectid,
-		  (sctx->parent_root ?
-		   sctx->parent_root->root_key.objectid : 0));
+		  btrfs_root_id(sctx->send_root),
+		  (sctx->parent_root ?  btrfs_root_id(sctx->parent_root) : 0));
 }
 
 __maybe_unused
@@ -1316,9 +1315,9 @@ static int __clone_root_cmp_bsearch(const void *key, const void *elt)
 	u64 root = (u64)(uintptr_t)key;
 	const struct clone_root *cr = elt;
 
-	if (root < cr->root->root_key.objectid)
+	if (root < btrfs_root_id(cr->root))
 		return -1;
-	if (root > cr->root->root_key.objectid)
+	if (root > btrfs_root_id(cr->root))
 		return 1;
 	return 0;
 }
@@ -1328,9 +1327,9 @@ static int __clone_root_cmp_sort(const void *e1, const void *e2)
 	const struct clone_root *cr1 = e1;
 	const struct clone_root *cr2 = e2;
 
-	if (cr1->root->root_key.objectid < cr2->root->root_key.objectid)
+	if (btrfs_root_id(cr1->root) < btrfs_root_id(cr2->root))
 		return -1;
-	if (cr1->root->root_key.objectid > cr2->root->root_key.objectid)
+	if (btrfs_root_id(cr1->root) > btrfs_root_id(cr2->root))
 		return 1;
 	return 0;
 }
@@ -1778,7 +1777,7 @@ static int read_symlink(struct btrfs_root *root,
 		 */
 		btrfs_err(root->fs_info,
 			  "Found empty symlink inode %llu at root %llu",
-			  ino, root->root_key.objectid);
+			  ino, btrfs_root_id(root));
 		ret = -EIO;
 		goto out;
 	}
@@ -2532,7 +2531,7 @@ static int send_subvol_begin(struct send_ctx *sctx)
 		return -ENOMEM;
 	}
 
-	key.objectid = send_root->root_key.objectid;
+	key.objectid = btrfs_root_id(send_root);
 	key.type = BTRFS_ROOT_BACKREF_KEY;
 	key.offset = 0;
 
@@ -2548,7 +2547,7 @@ static int send_subvol_begin(struct send_ctx *sctx)
 	leaf = path->nodes[0];
 	btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
 	if (key.type != BTRFS_ROOT_BACKREF_KEY ||
-	    key.objectid != send_root->root_key.objectid) {
+	    key.objectid != btrfs_root_id(send_root)) {
 		ret = -ENOENT;
 		goto out;
 	}
@@ -5274,10 +5273,11 @@ static int put_file_data(struct send_ctx *sctx, u64 offset, u32 len)
 {
 	struct btrfs_root *root = sctx->send_root;
 	struct btrfs_fs_info *fs_info = root->fs_info;
-	struct page *page;
+	struct folio *folio;
 	pgoff_t index = offset >> PAGE_SHIFT;
 	pgoff_t last_index;
 	unsigned pg_offset = offset_in_page(offset);
+	struct address_space *mapping = sctx->cur_inode->i_mapping;
 	int ret;
 
 	ret = put_data_header(sctx, len);
@@ -5290,44 +5290,44 @@ static int put_file_data(struct send_ctx *sctx, u64 offset, u32 len)
 		unsigned cur_len = min_t(unsigned, len,
 					 PAGE_SIZE - pg_offset);
 
-		page = find_lock_page(sctx->cur_inode->i_mapping, index);
-		if (!page) {
-			page_cache_sync_readahead(sctx->cur_inode->i_mapping,
+		folio = filemap_lock_folio(mapping, index);
+		if (IS_ERR(folio)) {
+			page_cache_sync_readahead(mapping,
 						  &sctx->ra, NULL, index,
 						  last_index + 1 - index);
 
-			page = find_or_create_page(sctx->cur_inode->i_mapping,
-						   index, GFP_KERNEL);
-			if (!page) {
-				ret = -ENOMEM;
+	                folio = filemap_grab_folio(mapping, index);
+			if (IS_ERR(folio)) {
+				ret = PTR_ERR(folio);
 				break;
 			}
 		}
 
-		if (PageReadahead(page))
-			page_cache_async_readahead(sctx->cur_inode->i_mapping,
-						   &sctx->ra, NULL, page_folio(page),
+		WARN_ON(folio_order(folio));
+
+		if (folio_test_readahead(folio))
+			page_cache_async_readahead(mapping, &sctx->ra, NULL, folio,
 						   index, last_index + 1 - index);
 
-		if (!PageUptodate(page)) {
-			btrfs_read_folio(NULL, page_folio(page));
-			lock_page(page);
-			if (!PageUptodate(page)) {
-				unlock_page(page);
+		if (!folio_test_uptodate(folio)) {
+			btrfs_read_folio(NULL, folio);
+			folio_lock(folio);
+			if (!folio_test_uptodate(folio)) {
+				folio_unlock(folio);
 				btrfs_err(fs_info,
 			"send: IO error at offset %llu for inode %llu root %llu",
-					page_offset(page), sctx->cur_ino,
-					sctx->send_root->root_key.objectid);
-				put_page(page);
+					folio_pos(folio), sctx->cur_ino,
+					btrfs_root_id(sctx->send_root));
+				folio_put(folio);
 				ret = -EIO;
 				break;
 			}
 		}
 
-		memcpy_from_page(sctx->send_buf + sctx->send_size, page,
-				 pg_offset, cur_len);
-		unlock_page(page);
-		put_page(page);
+		memcpy_from_folio(sctx->send_buf + sctx->send_size, folio,
+				  pg_offset, cur_len);
+		folio_unlock(folio);
+		folio_put(folio);
 		index++;
 		pg_offset = 0;
 		len -= cur_len;
@@ -5388,7 +5388,7 @@ static int send_clone(struct send_ctx *sctx,
 
 	btrfs_debug(sctx->send_root->fs_info,
 		    "send_clone offset=%llu, len=%d, clone_root=%llu, clone_inode=%llu, clone_offset=%llu",
-		    offset, len, clone_root->root->root_key.objectid,
+		    offset, len, btrfs_root_id(clone_root->root),
 		    clone_root->ino, clone_root->offset);
 
 	p = fs_path_alloc();
@@ -7337,7 +7337,7 @@ static int search_key_again(const struct send_ctx *sctx,
 "send: key (%llu %u %llu) not found in %s root %llu, lowest_level %d, slot %d",
 			  key->objectid, key->type, key->offset,
 			  (root == sctx->parent_root ? "parent" : "send"),
-			  root->root_key.objectid, path->lowest_level,
+			  btrfs_root_id(root), path->lowest_level,
 			  path->slots[path->lowest_level]);
 		return -EUCLEAN;
 	}
@@ -8071,7 +8071,7 @@ static void btrfs_root_dec_send_in_progress(struct btrfs_root* root)
 	if (root->send_in_progress < 0)
 		btrfs_err(root->fs_info,
 			  "send_in_progress unbalanced %d root %llu",
-			  root->send_in_progress, root->root_key.objectid);
+			  root->send_in_progress, btrfs_root_id(root));
 	spin_unlock(&root->root_item_lock);
 }
 
@@ -8079,7 +8079,7 @@ static void dedupe_in_progress_warn(const struct btrfs_root *root)
 {
 	btrfs_warn_rl(root->fs_info,
 "cannot use root %llu for send while deduplications on it are in progress (%d in progress)",
-		      root->root_key.objectid, root->dedupe_in_progress);
+		      btrfs_root_id(root), root->dedupe_in_progress);
 }
 
 long btrfs_ioctl_send(struct inode *inode, struct btrfs_ioctl_send_args *arg)
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 7e44ccaf348f..2dbc930a20f7 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -1097,10 +1097,9 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry)
 #endif
 	if (btrfs_test_opt(info, REF_VERIFY))
 		seq_puts(seq, ",ref_verify");
-	seq_printf(seq, ",subvolid=%llu",
-		  BTRFS_I(d_inode(dentry))->root->root_key.objectid);
+	seq_printf(seq, ",subvolid=%llu", btrfs_root_id(BTRFS_I(d_inode(dentry))->root));
 	subvol_name = btrfs_get_subvol_name_from_objectid(info,
-			BTRFS_I(d_inode(dentry))->root->root_key.objectid);
+			btrfs_root_id(BTRFS_I(d_inode(dentry))->root));
 	if (!IS_ERR(subvol_name)) {
 		seq_puts(seq, ",subvol=");
 		seq_escape(seq, subvol_name, " \t\n\\");
@@ -1152,7 +1151,7 @@ static struct dentry *mount_subvol(const char *subvol_name, u64 subvol_objectid,
 		struct super_block *s = root->d_sb;
 		struct btrfs_fs_info *fs_info = btrfs_sb(s);
 		struct inode *root_inode = d_inode(root);
-		u64 root_objectid = BTRFS_I(root_inode)->root->root_key.objectid;
+		u64 root_objectid = btrfs_root_id(BTRFS_I(root_inode)->root);
 
 		ret = 0;
 		if (!is_subvolume_inode(root_inode)) {
@@ -1774,10 +1773,8 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_fsid.val[0] = be32_to_cpu(fsid[0]) ^ be32_to_cpu(fsid[2]);
 	buf->f_fsid.val[1] = be32_to_cpu(fsid[1]) ^ be32_to_cpu(fsid[3]);
 	/* Mask in the root object ID too, to disambiguate subvols */
-	buf->f_fsid.val[0] ^=
-		BTRFS_I(d_inode(dentry))->root->root_key.objectid >> 32;
-	buf->f_fsid.val[1] ^=
-		BTRFS_I(d_inode(dentry))->root->root_key.objectid;
+	buf->f_fsid.val[0] ^= btrfs_root_id(BTRFS_I(d_inode(dentry))->root) >> 32;
+	buf->f_fsid.val[1] ^= btrfs_root_id(BTRFS_I(d_inode(dentry))->root);
 
 	return 0;
 }
@@ -2374,6 +2371,24 @@ static int btrfs_show_devname(struct seq_file *m, struct dentry *root)
 	return 0;
 }
 
+static long btrfs_nr_cached_objects(struct super_block *sb, struct shrink_control *sc)
+{
+	struct btrfs_fs_info *fs_info = btrfs_sb(sb);
+	const s64 nr = percpu_counter_sum_positive(&fs_info->evictable_extent_maps);
+
+	trace_btrfs_extent_map_shrinker_count(fs_info, nr);
+
+	return nr;
+}
+
+static long btrfs_free_cached_objects(struct super_block *sb, struct shrink_control *sc)
+{
+	const long nr_to_scan = min_t(unsigned long, LONG_MAX, sc->nr_to_scan);
+	struct btrfs_fs_info *fs_info = btrfs_sb(sb);
+
+	return btrfs_free_extent_maps(fs_info, nr_to_scan);
+}
+
 static const struct super_operations btrfs_super_ops = {
 	.drop_inode	= btrfs_drop_inode,
 	.evict_inode	= btrfs_evict_inode,
@@ -2387,6 +2402,8 @@ static const struct super_operations btrfs_super_ops = {
 	.statfs		= btrfs_statfs,
 	.freeze_fs	= btrfs_freeze,
 	.unfreeze_fs	= btrfs_unfreeze,
+	.nr_cached_objects = btrfs_nr_cached_objects,
+	.free_cached_objects = btrfs_free_cached_objects,
 };
 
 static const struct file_operations btrfs_ctl_fops = {
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index c6387a8ddb94..af545b6b1190 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -2339,7 +2339,7 @@ int btrfs_sysfs_add_one_qgroup(struct btrfs_fs_info *fs_info,
 	struct kobject *qgroups_kobj = fs_info->qgroups_kobj;
 	int ret;
 
-	if (test_bit(BTRFS_FS_STATE_DUMMY_FS_INFO, &fs_info->fs_state))
+	if (btrfs_is_testing(fs_info))
 		return 0;
 	if (qgroup->kobj.state_initialized)
 		return 0;
@@ -2360,7 +2360,7 @@ void btrfs_sysfs_del_qgroups(struct btrfs_fs_info *fs_info)
 	struct btrfs_qgroup *qgroup;
 	struct btrfs_qgroup *next;
 
-	if (test_bit(BTRFS_FS_STATE_DUMMY_FS_INFO, &fs_info->fs_state))
+	if (btrfs_is_testing(fs_info))
 		return;
 
 	rbtree_postorder_for_each_entry_safe(qgroup, next,
@@ -2381,7 +2381,7 @@ int btrfs_sysfs_add_qgroups(struct btrfs_fs_info *fs_info)
 	struct btrfs_qgroup *next;
 	int ret = 0;
 
-	if (test_bit(BTRFS_FS_STATE_DUMMY_FS_INFO, &fs_info->fs_state))
+	if (btrfs_is_testing(fs_info))
 		return 0;
 
 	ASSERT(fsid_kobj);
@@ -2413,7 +2413,7 @@ out:
 void btrfs_sysfs_del_one_qgroup(struct btrfs_fs_info *fs_info,
 				struct btrfs_qgroup *qgroup)
 {
-	if (test_bit(BTRFS_FS_STATE_DUMMY_FS_INFO, &fs_info->fs_state))
+	if (btrfs_is_testing(fs_info))
 		return;
 
 	if (qgroup->kobj.state_initialized) {
diff --git a/fs/btrfs/tests/btrfs-tests.c b/fs/btrfs/tests/btrfs-tests.c
index 709c6cc9706a..dce0387ef155 100644
--- a/fs/btrfs/tests/btrfs-tests.c
+++ b/fs/btrfs/tests/btrfs-tests.c
@@ -160,8 +160,7 @@ void btrfs_free_dummy_fs_info(struct btrfs_fs_info *fs_info)
 	if (!fs_info)
 		return;
 
-	if (WARN_ON(!test_bit(BTRFS_FS_STATE_DUMMY_FS_INFO,
-			      &fs_info->fs_state)))
+	if (WARN_ON(!btrfs_is_testing(fs_info)))
 		return;
 
 	test_mnt->mnt_sb->s_fs_info = NULL;
diff --git a/fs/btrfs/tests/extent-map-tests.c b/fs/btrfs/tests/extent-map-tests.c
index 47b5d301038e..ba36794ba2d5 100644
--- a/fs/btrfs/tests/extent-map-tests.c
+++ b/fs/btrfs/tests/extent-map-tests.c
@@ -11,19 +11,22 @@
 #include "../disk-io.h"
 #include "../block-group.h"
 
-static void free_extent_map_tree(struct extent_map_tree *em_tree)
+static int free_extent_map_tree(struct btrfs_inode *inode)
 {
+	struct extent_map_tree *em_tree = &inode->extent_tree;
 	struct extent_map *em;
 	struct rb_node *node;
+	int ret = 0;
 
 	write_lock(&em_tree->lock);
 	while (!RB_EMPTY_ROOT(&em_tree->map.rb_root)) {
 		node = rb_first_cached(&em_tree->map);
 		em = rb_entry(node, struct extent_map, rb_node);
-		remove_extent_mapping(em_tree, em);
+		remove_extent_mapping(inode, em);
 
 #ifdef CONFIG_BTRFS_DEBUG
 		if (refcount_read(&em->refs) != 1) {
+			ret = -EINVAL;
 			test_err(
 "em leak: em (start %llu len %llu block_start %llu block_len %llu) refs %d",
 				 em->start, em->len, em->block_start,
@@ -35,6 +38,8 @@ static void free_extent_map_tree(struct extent_map_tree *em_tree)
 		free_extent_map(em);
 	}
 	write_unlock(&em_tree->lock);
+
+	return ret;
 }
 
 /*
@@ -53,13 +58,14 @@ static void free_extent_map_tree(struct extent_map_tree *em_tree)
  *                                    ->add_extent_mapping(0, 16K)
  *                                    -> #handle -EEXIST
  */
-static int test_case_1(struct btrfs_fs_info *fs_info,
-		struct extent_map_tree *em_tree)
+static int test_case_1(struct btrfs_fs_info *fs_info, struct btrfs_inode *inode)
 {
+	struct extent_map_tree *em_tree = &inode->extent_tree;
 	struct extent_map *em;
 	u64 start = 0;
 	u64 len = SZ_8K;
 	int ret;
+	int ret2;
 
 	em = alloc_extent_map();
 	if (!em) {
@@ -73,7 +79,7 @@ static int test_case_1(struct btrfs_fs_info *fs_info,
 	em->block_start = 0;
 	em->block_len = SZ_16K;
 	write_lock(&em_tree->lock);
-	ret = btrfs_add_extent_mapping(fs_info, em_tree, &em, em->start, em->len);
+	ret = btrfs_add_extent_mapping(inode, &em, em->start, em->len);
 	write_unlock(&em_tree->lock);
 	if (ret < 0) {
 		test_err("cannot add extent range [0, 16K)");
@@ -94,7 +100,7 @@ static int test_case_1(struct btrfs_fs_info *fs_info,
 	em->block_start = SZ_32K; /* avoid merging */
 	em->block_len = SZ_4K;
 	write_lock(&em_tree->lock);
-	ret = btrfs_add_extent_mapping(fs_info, em_tree, &em, em->start, em->len);
+	ret = btrfs_add_extent_mapping(inode, &em, em->start, em->len);
 	write_unlock(&em_tree->lock);
 	if (ret < 0) {
 		test_err("cannot add extent range [16K, 20K)");
@@ -115,7 +121,7 @@ static int test_case_1(struct btrfs_fs_info *fs_info,
 	em->block_start = start;
 	em->block_len = len;
 	write_lock(&em_tree->lock);
-	ret = btrfs_add_extent_mapping(fs_info, em_tree, &em, em->start, em->len);
+	ret = btrfs_add_extent_mapping(inode, &em, em->start, em->len);
 	write_unlock(&em_tree->lock);
 	if (ret) {
 		test_err("case1 [%llu %llu]: ret %d", start, start + len, ret);
@@ -137,7 +143,9 @@ static int test_case_1(struct btrfs_fs_info *fs_info,
 	}
 	free_extent_map(em);
 out:
-	free_extent_map_tree(em_tree);
+	ret2 = free_extent_map_tree(inode);
+	if (ret == 0)
+		ret = ret2;
 
 	return ret;
 }
@@ -148,11 +156,12 @@ out:
  * Reading the inline ending up with EEXIST, ie. read an inline
  * extent and discard page cache and read it again.
  */
-static int test_case_2(struct btrfs_fs_info *fs_info,
-		struct extent_map_tree *em_tree)
+static int test_case_2(struct btrfs_fs_info *fs_info, struct btrfs_inode *inode)
 {
+	struct extent_map_tree *em_tree = &inode->extent_tree;
 	struct extent_map *em;
 	int ret;
+	int ret2;
 
 	em = alloc_extent_map();
 	if (!em) {
@@ -166,7 +175,7 @@ static int test_case_2(struct btrfs_fs_info *fs_info,
 	em->block_start = EXTENT_MAP_INLINE;
 	em->block_len = (u64)-1;
 	write_lock(&em_tree->lock);
-	ret = btrfs_add_extent_mapping(fs_info, em_tree, &em, em->start, em->len);
+	ret = btrfs_add_extent_mapping(inode, &em, em->start, em->len);
 	write_unlock(&em_tree->lock);
 	if (ret < 0) {
 		test_err("cannot add extent range [0, 1K)");
@@ -187,7 +196,7 @@ static int test_case_2(struct btrfs_fs_info *fs_info,
 	em->block_start = SZ_4K;
 	em->block_len = SZ_4K;
 	write_lock(&em_tree->lock);
-	ret = btrfs_add_extent_mapping(fs_info, em_tree, &em, em->start, em->len);
+	ret = btrfs_add_extent_mapping(inode, &em, em->start, em->len);
 	write_unlock(&em_tree->lock);
 	if (ret < 0) {
 		test_err("cannot add extent range [4K, 8K)");
@@ -208,7 +217,7 @@ static int test_case_2(struct btrfs_fs_info *fs_info,
 	em->block_start = EXTENT_MAP_INLINE;
 	em->block_len = (u64)-1;
 	write_lock(&em_tree->lock);
-	ret = btrfs_add_extent_mapping(fs_info, em_tree, &em, em->start, em->len);
+	ret = btrfs_add_extent_mapping(inode, &em, em->start, em->len);
 	write_unlock(&em_tree->lock);
 	if (ret) {
 		test_err("case2 [0 1K]: ret %d", ret);
@@ -229,17 +238,21 @@ static int test_case_2(struct btrfs_fs_info *fs_info,
 	}
 	free_extent_map(em);
 out:
-	free_extent_map_tree(em_tree);
+	ret2 = free_extent_map_tree(inode);
+	if (ret == 0)
+		ret = ret2;
 
 	return ret;
 }
 
 static int __test_case_3(struct btrfs_fs_info *fs_info,
-		struct extent_map_tree *em_tree, u64 start)
+			 struct btrfs_inode *inode, u64 start)
 {
+	struct extent_map_tree *em_tree = &inode->extent_tree;
 	struct extent_map *em;
 	u64 len = SZ_4K;
 	int ret;
+	int ret2;
 
 	em = alloc_extent_map();
 	if (!em) {
@@ -253,7 +266,7 @@ static int __test_case_3(struct btrfs_fs_info *fs_info,
 	em->block_start = SZ_4K;
 	em->block_len = SZ_4K;
 	write_lock(&em_tree->lock);
-	ret = btrfs_add_extent_mapping(fs_info, em_tree, &em, em->start, em->len);
+	ret = btrfs_add_extent_mapping(inode, &em, em->start, em->len);
 	write_unlock(&em_tree->lock);
 	if (ret < 0) {
 		test_err("cannot add extent range [4K, 8K)");
@@ -274,7 +287,7 @@ static int __test_case_3(struct btrfs_fs_info *fs_info,
 	em->block_start = 0;
 	em->block_len = SZ_16K;
 	write_lock(&em_tree->lock);
-	ret = btrfs_add_extent_mapping(fs_info, em_tree, &em, start, len);
+	ret = btrfs_add_extent_mapping(inode, &em, start, len);
 	write_unlock(&em_tree->lock);
 	if (ret) {
 		test_err("case3 [%llu %llu): ret %d",
@@ -301,7 +314,9 @@ static int __test_case_3(struct btrfs_fs_info *fs_info,
 	}
 	free_extent_map(em);
 out:
-	free_extent_map_tree(em_tree);
+	ret2 = free_extent_map_tree(inode);
+	if (ret == 0)
+		ret = ret2;
 
 	return ret;
 }
@@ -322,28 +337,29 @@ out:
  *   -> add_extent_mapping()
  *                            -> add_extent_mapping()
  */
-static int test_case_3(struct btrfs_fs_info *fs_info,
-		struct extent_map_tree *em_tree)
+static int test_case_3(struct btrfs_fs_info *fs_info, struct btrfs_inode *inode)
 {
 	int ret;
 
-	ret = __test_case_3(fs_info, em_tree, 0);
+	ret = __test_case_3(fs_info, inode, 0);
 	if (ret)
 		return ret;
-	ret = __test_case_3(fs_info, em_tree, SZ_8K);
+	ret = __test_case_3(fs_info, inode, SZ_8K);
 	if (ret)
 		return ret;
-	ret = __test_case_3(fs_info, em_tree, (12 * SZ_1K));
+	ret = __test_case_3(fs_info, inode, (12 * SZ_1K));
 
 	return ret;
 }
 
 static int __test_case_4(struct btrfs_fs_info *fs_info,
-		struct extent_map_tree *em_tree, u64 start)
+			 struct btrfs_inode *inode, u64 start)
 {
+	struct extent_map_tree *em_tree = &inode->extent_tree;
 	struct extent_map *em;
 	u64 len = SZ_4K;
 	int ret;
+	int ret2;
 
 	em = alloc_extent_map();
 	if (!em) {
@@ -357,7 +373,7 @@ static int __test_case_4(struct btrfs_fs_info *fs_info,
 	em->block_start = 0;
 	em->block_len = SZ_8K;
 	write_lock(&em_tree->lock);
-	ret = btrfs_add_extent_mapping(fs_info, em_tree, &em, em->start, em->len);
+	ret = btrfs_add_extent_mapping(inode, &em, em->start, em->len);
 	write_unlock(&em_tree->lock);
 	if (ret < 0) {
 		test_err("cannot add extent range [0, 8K)");
@@ -378,7 +394,7 @@ static int __test_case_4(struct btrfs_fs_info *fs_info,
 	em->block_start = SZ_16K; /* avoid merging */
 	em->block_len = 24 * SZ_1K;
 	write_lock(&em_tree->lock);
-	ret = btrfs_add_extent_mapping(fs_info, em_tree, &em, em->start, em->len);
+	ret = btrfs_add_extent_mapping(inode, &em, em->start, em->len);
 	write_unlock(&em_tree->lock);
 	if (ret < 0) {
 		test_err("cannot add extent range [8K, 32K)");
@@ -398,7 +414,7 @@ static int __test_case_4(struct btrfs_fs_info *fs_info,
 	em->block_start = 0;
 	em->block_len = SZ_32K;
 	write_lock(&em_tree->lock);
-	ret = btrfs_add_extent_mapping(fs_info, em_tree, &em, start, len);
+	ret = btrfs_add_extent_mapping(inode, &em, start, len);
 	write_unlock(&em_tree->lock);
 	if (ret) {
 		test_err("case4 [%llu %llu): ret %d",
@@ -420,7 +436,9 @@ static int __test_case_4(struct btrfs_fs_info *fs_info,
 	}
 	free_extent_map(em);
 out:
-	free_extent_map_tree(em_tree);
+	ret2 = free_extent_map_tree(inode);
+	if (ret == 0)
+		ret = ret2;
 
 	return ret;
 }
@@ -450,23 +468,22 @@ out:
  *                                             # handle -EEXIST when adding
  *                                             # [0, 32K)
  */
-static int test_case_4(struct btrfs_fs_info *fs_info,
-		struct extent_map_tree *em_tree)
+static int test_case_4(struct btrfs_fs_info *fs_info, struct btrfs_inode *inode)
 {
 	int ret;
 
-	ret = __test_case_4(fs_info, em_tree, 0);
+	ret = __test_case_4(fs_info, inode, 0);
 	if (ret)
 		return ret;
-	ret = __test_case_4(fs_info, em_tree, SZ_4K);
+	ret = __test_case_4(fs_info, inode, SZ_4K);
 
 	return ret;
 }
 
-static int add_compressed_extent(struct btrfs_fs_info *fs_info,
-				 struct extent_map_tree *em_tree,
+static int add_compressed_extent(struct btrfs_inode *inode,
 				 u64 start, u64 len, u64 block_start)
 {
+	struct extent_map_tree *em_tree = &inode->extent_tree;
 	struct extent_map *em;
 	int ret;
 
@@ -482,7 +499,7 @@ static int add_compressed_extent(struct btrfs_fs_info *fs_info,
 	em->block_len = SZ_4K;
 	em->flags |= EXTENT_FLAG_COMPRESS_ZLIB;
 	write_lock(&em_tree->lock);
-	ret = btrfs_add_extent_mapping(fs_info, em_tree, &em, em->start, em->len);
+	ret = btrfs_add_extent_mapping(inode, &em, em->start, em->len);
 	write_unlock(&em_tree->lock);
 	free_extent_map(em);
 	if (ret < 0) {
@@ -588,53 +605,44 @@ static int validate_range(struct extent_map_tree *em_tree, int index)
  * They'll have the EXTENT_FLAG_COMPRESSED flag set to keep the em tree from
  * merging the em's.
  */
-static int test_case_5(struct btrfs_fs_info *fs_info)
+static int test_case_5(struct btrfs_fs_info *fs_info, struct btrfs_inode *inode)
 {
-	struct extent_map_tree *em_tree;
-	struct inode *inode;
 	u64 start, end;
 	int ret;
+	int ret2;
 
 	test_msg("Running btrfs_drop_extent_map_range tests");
 
-	inode = btrfs_new_test_inode();
-	if (!inode) {
-		test_std_err(TEST_ALLOC_INODE);
-		return -ENOMEM;
-	}
-
-	em_tree = &BTRFS_I(inode)->extent_tree;
-
 	/* [0, 12k) */
-	ret = add_compressed_extent(fs_info, em_tree, 0, SZ_4K * 3, 0);
+	ret = add_compressed_extent(inode, 0, SZ_4K * 3, 0);
 	if (ret) {
 		test_err("cannot add extent range [0, 12K)");
 		goto out;
 	}
 
 	/* [12k, 24k) */
-	ret = add_compressed_extent(fs_info, em_tree, SZ_4K * 3, SZ_4K * 3, SZ_4K);
+	ret = add_compressed_extent(inode, SZ_4K * 3, SZ_4K * 3, SZ_4K);
 	if (ret) {
 		test_err("cannot add extent range [12k, 24k)");
 		goto out;
 	}
 
 	/* [24k, 36k) */
-	ret = add_compressed_extent(fs_info, em_tree, SZ_4K * 6, SZ_4K * 3, SZ_8K);
+	ret = add_compressed_extent(inode, SZ_4K * 6, SZ_4K * 3, SZ_8K);
 	if (ret) {
 		test_err("cannot add extent range [12k, 24k)");
 		goto out;
 	}
 
 	/* [36k, 40k) */
-	ret = add_compressed_extent(fs_info, em_tree, SZ_32K + SZ_4K, SZ_4K, SZ_4K * 3);
+	ret = add_compressed_extent(inode, SZ_32K + SZ_4K, SZ_4K, SZ_4K * 3);
 	if (ret) {
 		test_err("cannot add extent range [12k, 24k)");
 		goto out;
 	}
 
 	/* [40k, 64k) */
-	ret = add_compressed_extent(fs_info, em_tree, SZ_4K * 10, SZ_4K * 6, SZ_16K);
+	ret = add_compressed_extent(inode, SZ_4K * 10, SZ_4K * 6, SZ_16K);
 	if (ret) {
 		test_err("cannot add extent range [12k, 24k)");
 		goto out;
@@ -643,36 +651,39 @@ static int test_case_5(struct btrfs_fs_info *fs_info)
 	/* Drop [8k, 12k) */
 	start = SZ_8K;
 	end = (3 * SZ_4K) - 1;
-	btrfs_drop_extent_map_range(BTRFS_I(inode), start, end, false);
-	ret = validate_range(&BTRFS_I(inode)->extent_tree, 0);
+	btrfs_drop_extent_map_range(inode, start, end, false);
+	ret = validate_range(&inode->extent_tree, 0);
 	if (ret)
 		goto out;
 
 	/* Drop [12k, 20k) */
 	start = SZ_4K * 3;
 	end = SZ_16K + SZ_4K - 1;
-	btrfs_drop_extent_map_range(BTRFS_I(inode), start, end, false);
-	ret = validate_range(&BTRFS_I(inode)->extent_tree, 1);
+	btrfs_drop_extent_map_range(inode, start, end, false);
+	ret = validate_range(&inode->extent_tree, 1);
 	if (ret)
 		goto out;
 
 	/* Drop [28k, 32k) */
 	start = SZ_32K - SZ_4K;
 	end = SZ_32K - 1;
-	btrfs_drop_extent_map_range(BTRFS_I(inode), start, end, false);
-	ret = validate_range(&BTRFS_I(inode)->extent_tree, 2);
+	btrfs_drop_extent_map_range(inode, start, end, false);
+	ret = validate_range(&inode->extent_tree, 2);
 	if (ret)
 		goto out;
 
 	/* Drop [32k, 64k) */
 	start = SZ_32K;
 	end = SZ_64K - 1;
-	btrfs_drop_extent_map_range(BTRFS_I(inode), start, end, false);
-	ret = validate_range(&BTRFS_I(inode)->extent_tree, 3);
+	btrfs_drop_extent_map_range(inode, start, end, false);
+	ret = validate_range(&inode->extent_tree, 3);
 	if (ret)
 		goto out;
 out:
-	iput(inode);
+	ret2 = free_extent_map_tree(inode);
+	if (ret == 0)
+		ret = ret2;
+
 	return ret;
 }
 
@@ -681,23 +692,26 @@ out:
  * for areas between two existing ems.  Validate it doesn't do this when there
  * are two unmerged em's side by side.
  */
-static int test_case_6(struct btrfs_fs_info *fs_info, struct extent_map_tree *em_tree)
+static int test_case_6(struct btrfs_fs_info *fs_info, struct btrfs_inode *inode)
 {
+	struct extent_map_tree *em_tree = &inode->extent_tree;
 	struct extent_map *em = NULL;
 	int ret;
+	int ret2;
 
-	ret = add_compressed_extent(fs_info, em_tree, 0, SZ_4K, 0);
+	ret = add_compressed_extent(inode, 0, SZ_4K, 0);
 	if (ret)
 		goto out;
 
-	ret = add_compressed_extent(fs_info, em_tree, SZ_4K, SZ_4K, 0);
+	ret = add_compressed_extent(inode, SZ_4K, SZ_4K, 0);
 	if (ret)
 		goto out;
 
 	em = alloc_extent_map();
 	if (!em) {
 		test_std_err(TEST_ALLOC_EXTENT_MAP);
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto out;
 	}
 
 	em->start = SZ_4K;
@@ -705,7 +719,7 @@ static int test_case_6(struct btrfs_fs_info *fs_info, struct extent_map_tree *em
 	em->block_start = SZ_16K;
 	em->block_len = SZ_16K;
 	write_lock(&em_tree->lock);
-	ret = btrfs_add_extent_mapping(fs_info, em_tree, &em, 0, SZ_8K);
+	ret = btrfs_add_extent_mapping(inode, &em, 0, SZ_8K);
 	write_unlock(&em_tree->lock);
 
 	if (ret != 0) {
@@ -725,7 +739,10 @@ static int test_case_6(struct btrfs_fs_info *fs_info, struct extent_map_tree *em
 	ret = 0;
 out:
 	free_extent_map(em);
-	free_extent_map_tree(em_tree);
+	ret2 = free_extent_map_tree(inode);
+	if (ret == 0)
+		ret = ret2;
+
 	return ret;
 }
 
@@ -734,28 +751,19 @@ out:
  * true would mess up the start/end calculations and subsequent splits would be
  * incorrect.
  */
-static int test_case_7(struct btrfs_fs_info *fs_info)
+static int test_case_7(struct btrfs_fs_info *fs_info, struct btrfs_inode *inode)
 {
-	struct extent_map_tree *em_tree;
+	struct extent_map_tree *em_tree = &inode->extent_tree;
 	struct extent_map *em;
-	struct inode *inode;
 	int ret;
+	int ret2;
 
 	test_msg("Running btrfs_drop_extent_cache with pinned");
 
-	inode = btrfs_new_test_inode();
-	if (!inode) {
-		test_std_err(TEST_ALLOC_INODE);
-		return -ENOMEM;
-	}
-
-	em_tree = &BTRFS_I(inode)->extent_tree;
-
 	em = alloc_extent_map();
 	if (!em) {
 		test_std_err(TEST_ALLOC_EXTENT_MAP);
-		ret = -ENOMEM;
-		goto out;
+		return -ENOMEM;
 	}
 
 	/* [0, 16K), pinned */
@@ -765,7 +773,7 @@ static int test_case_7(struct btrfs_fs_info *fs_info)
 	em->block_len = SZ_4K;
 	em->flags |= EXTENT_FLAG_PINNED;
 	write_lock(&em_tree->lock);
-	ret = btrfs_add_extent_mapping(fs_info, em_tree, &em, em->start, em->len);
+	ret = btrfs_add_extent_mapping(inode, &em, em->start, em->len);
 	write_unlock(&em_tree->lock);
 	if (ret < 0) {
 		test_err("couldn't add extent map");
@@ -786,7 +794,7 @@ static int test_case_7(struct btrfs_fs_info *fs_info)
 	em->block_start = SZ_32K;
 	em->block_len = SZ_16K;
 	write_lock(&em_tree->lock);
-	ret = btrfs_add_extent_mapping(fs_info, em_tree, &em, em->start, em->len);
+	ret = btrfs_add_extent_mapping(inode, &em, em->start, em->len);
 	write_unlock(&em_tree->lock);
 	if (ret < 0) {
 		test_err("couldn't add extent map");
@@ -798,7 +806,7 @@ static int test_case_7(struct btrfs_fs_info *fs_info)
 	 * Drop [0, 36K) This should skip the [0, 4K) extent and then split the
 	 * [32K, 48K) extent.
 	 */
-	btrfs_drop_extent_map_range(BTRFS_I(inode), 0, (36 * SZ_1K) - 1, true);
+	btrfs_drop_extent_map_range(inode, 0, (36 * SZ_1K) - 1, true);
 
 	/* Make sure our extent maps look sane. */
 	ret = -EINVAL;
@@ -865,7 +873,14 @@ static int test_case_7(struct btrfs_fs_info *fs_info)
 	ret = 0;
 out:
 	free_extent_map(em);
-	iput(inode);
+	/* Unpin our extent to prevent warning when removing it below. */
+	ret2 = unpin_extent_cache(inode, 0, SZ_16K, 0);
+	if (ret == 0)
+		ret = ret2;
+	ret2 = free_extent_map_tree(inode);
+	if (ret == 0)
+		ret = ret2;
+
 	return ret;
 }
 
@@ -959,7 +974,8 @@ out_free:
 int btrfs_test_extent_map(void)
 {
 	struct btrfs_fs_info *fs_info = NULL;
-	struct extent_map_tree *em_tree;
+	struct inode *inode;
+	struct btrfs_root *root = NULL;
 	int ret = 0, i;
 	struct rmap_test_vector rmap_tests[] = {
 		{
@@ -1008,33 +1024,42 @@ int btrfs_test_extent_map(void)
 		return -ENOMEM;
 	}
 
-	em_tree = kzalloc(sizeof(*em_tree), GFP_KERNEL);
-	if (!em_tree) {
+	inode = btrfs_new_test_inode();
+	if (!inode) {
+		test_std_err(TEST_ALLOC_INODE);
 		ret = -ENOMEM;
 		goto out;
 	}
 
-	extent_map_tree_init(em_tree);
+	root = btrfs_alloc_dummy_root(fs_info);
+	if (IS_ERR(root)) {
+		test_std_err(TEST_ALLOC_ROOT);
+		ret = PTR_ERR(root);
+		root = NULL;
+		goto out;
+	}
 
-	ret = test_case_1(fs_info, em_tree);
+	BTRFS_I(inode)->root = root;
+
+	ret = test_case_1(fs_info, BTRFS_I(inode));
 	if (ret)
 		goto out;
-	ret = test_case_2(fs_info, em_tree);
+	ret = test_case_2(fs_info, BTRFS_I(inode));
 	if (ret)
 		goto out;
-	ret = test_case_3(fs_info, em_tree);
+	ret = test_case_3(fs_info, BTRFS_I(inode));
 	if (ret)
 		goto out;
-	ret = test_case_4(fs_info, em_tree);
+	ret = test_case_4(fs_info, BTRFS_I(inode));
 	if (ret)
 		goto out;
-	ret = test_case_5(fs_info);
+	ret = test_case_5(fs_info, BTRFS_I(inode));
 	if (ret)
 		goto out;
-	ret = test_case_6(fs_info, em_tree);
+	ret = test_case_6(fs_info, BTRFS_I(inode));
 	if (ret)
 		goto out;
-	ret = test_case_7(fs_info);
+	ret = test_case_7(fs_info, BTRFS_I(inode));
 	if (ret)
 		goto out;
 
@@ -1046,7 +1071,8 @@ int btrfs_test_extent_map(void)
 	}
 
 out:
-	kfree(em_tree);
+	iput(inode);
+	btrfs_free_dummy_root(root);
 	btrfs_free_dummy_fs_info(fs_info);
 
 	return ret;
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 85f359e0e0a7..3388c836b9a5 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -426,7 +426,7 @@ static int record_root_in_trans(struct btrfs_trans_handle *trans,
 			return 0;
 		}
 		radix_tree_tag_set(&fs_info->fs_roots_radix,
-				   (unsigned long)root->root_key.objectid,
+				   (unsigned long)btrfs_root_id(root),
 				   BTRFS_ROOT_TRANS_TAG);
 		spin_unlock(&fs_info->fs_roots_radix_lock);
 		root->last_trans = trans->transid;
@@ -472,7 +472,7 @@ void btrfs_add_dropped_root(struct btrfs_trans_handle *trans,
 	/* Make sure we don't try to update the root at commit time */
 	spin_lock(&fs_info->fs_roots_radix_lock);
 	radix_tree_tag_clear(&fs_info->fs_roots_radix,
-			     (unsigned long)root->root_key.objectid,
+			     (unsigned long)btrfs_root_id(root),
 			     BTRFS_ROOT_TRANS_TAG);
 	spin_unlock(&fs_info->fs_roots_radix_lock);
 }
@@ -550,7 +550,7 @@ static inline bool need_reserve_reloc_root(struct btrfs_root *root)
 
 	if (!fs_info->reloc_ctl ||
 	    !test_bit(BTRFS_ROOT_SHAREABLE, &root->state) ||
-	    root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID ||
+	    btrfs_root_id(root) == BTRFS_TREE_RELOC_OBJECTID ||
 	    root->reloc_root)
 		return false;
 
@@ -1052,7 +1052,7 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
 {
 	struct btrfs_fs_info *info = trans->fs_info;
 	struct btrfs_transaction *cur_trans = trans->transaction;
-	int err = 0;
+	int ret = 0;
 
 	if (refcount_read(&trans->use_count) > 1) {
 		refcount_dec(&trans->use_count);
@@ -1091,13 +1091,13 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
 	if (TRANS_ABORTED(trans) || BTRFS_FS_ERROR(info)) {
 		wake_up_process(info->transaction_kthread);
 		if (TRANS_ABORTED(trans))
-			err = trans->aborted;
+			ret = trans->aborted;
 		else
-			err = -EROFS;
+			ret = -EROFS;
 	}
 
 	kmem_cache_free(btrfs_trans_handle_cachep, trans);
-	return err;
+	return ret;
 }
 
 int btrfs_end_transaction(struct btrfs_trans_handle *trans)
@@ -1118,8 +1118,7 @@ int btrfs_end_transaction_throttle(struct btrfs_trans_handle *trans)
 int btrfs_write_marked_extents(struct btrfs_fs_info *fs_info,
 			       struct extent_io_tree *dirty_pages, int mark)
 {
-	int err = 0;
-	int werr = 0;
+	int ret = 0;
 	struct address_space *mapping = fs_info->btree_inode->i_mapping;
 	struct extent_state *cached_state = NULL;
 	u64 start = 0;
@@ -1129,7 +1128,7 @@ int btrfs_write_marked_extents(struct btrfs_fs_info *fs_info,
 				     mark, &cached_state)) {
 		bool wait_writeback = false;
 
-		err = convert_extent_bit(dirty_pages, start, end,
+		ret = convert_extent_bit(dirty_pages, start, end,
 					 EXTENT_NEED_WAIT,
 					 mark, &cached_state);
 		/*
@@ -1145,22 +1144,22 @@ int btrfs_write_marked_extents(struct btrfs_fs_info *fs_info,
 		 * We cleanup any entries left in the io tree when committing
 		 * the transaction (through extent_io_tree_release()).
 		 */
-		if (err == -ENOMEM) {
-			err = 0;
+		if (ret == -ENOMEM) {
+			ret = 0;
 			wait_writeback = true;
 		}
-		if (!err)
-			err = filemap_fdatawrite_range(mapping, start, end);
-		if (err)
-			werr = err;
-		else if (wait_writeback)
-			werr = filemap_fdatawait_range(mapping, start, end);
+		if (!ret)
+			ret = filemap_fdatawrite_range(mapping, start, end);
+		if (!ret && wait_writeback)
+			ret = filemap_fdatawait_range(mapping, start, end);
 		free_extent_state(cached_state);
+		if (ret)
+			break;
 		cached_state = NULL;
 		cond_resched();
 		start = end + 1;
 	}
-	return werr;
+	return ret;
 }
 
 /*
@@ -1172,12 +1171,11 @@ int btrfs_write_marked_extents(struct btrfs_fs_info *fs_info,
 static int __btrfs_wait_marked_extents(struct btrfs_fs_info *fs_info,
 				       struct extent_io_tree *dirty_pages)
 {
-	int err = 0;
-	int werr = 0;
 	struct address_space *mapping = fs_info->btree_inode->i_mapping;
 	struct extent_state *cached_state = NULL;
 	u64 start = 0;
 	u64 end;
+	int ret = 0;
 
 	while (find_first_extent_bit(dirty_pages, start, &start, &end,
 				     EXTENT_NEED_WAIT, &cached_state)) {
@@ -1189,22 +1187,20 @@ static int __btrfs_wait_marked_extents(struct btrfs_fs_info *fs_info,
 		 * concurrently - we do it only at transaction commit time when
 		 * it's safe to do it (through extent_io_tree_release()).
 		 */
-		err = clear_extent_bit(dirty_pages, start, end,
+		ret = clear_extent_bit(dirty_pages, start, end,
 				       EXTENT_NEED_WAIT, &cached_state);
-		if (err == -ENOMEM)
-			err = 0;
-		if (!err)
-			err = filemap_fdatawait_range(mapping, start, end);
-		if (err)
-			werr = err;
+		if (ret == -ENOMEM)
+			ret = 0;
+		if (!ret)
+			ret = filemap_fdatawait_range(mapping, start, end);
 		free_extent_state(cached_state);
+		if (ret)
+			break;
 		cached_state = NULL;
 		cond_resched();
 		start = end + 1;
 	}
-	if (err)
-		werr = err;
-	return werr;
+	return ret;
 }
 
 static int btrfs_wait_extents(struct btrfs_fs_info *fs_info,
@@ -1229,7 +1225,7 @@ int btrfs_wait_tree_log_extents(struct btrfs_root *log_root, int mark)
 	bool errors = false;
 	int err;
 
-	ASSERT(log_root->root_key.objectid == BTRFS_TREE_LOG_OBJECTID);
+	ASSERT(btrfs_root_id(log_root) == BTRFS_TREE_LOG_OBJECTID);
 
 	err = __btrfs_wait_marked_extents(fs_info, dirty_pages);
 	if ((mark & EXTENT_DIRTY) &&
@@ -1492,7 +1488,7 @@ static noinline int commit_fs_roots(struct btrfs_trans_handle *trans)
 			ASSERT(atomic_read(&root->log_commit[1]) == 0);
 
 			radix_tree_tag_clear(&fs_info->fs_roots_radix,
-					(unsigned long)root->root_key.objectid,
+					(unsigned long)btrfs_root_id(root),
 					BTRFS_ROOT_TRANS_TAG);
 			btrfs_qgroup_free_meta_all_pertrans(root);
 			spin_unlock(&fs_info->fs_roots_radix_lock);
@@ -1583,8 +1579,8 @@ static int qgroup_account_snapshot(struct btrfs_trans_handle *trans,
 		goto out;
 
 	/* Now qgroup are all updated, we can inherit it to new qgroups */
-	ret = btrfs_qgroup_inherit(trans, src->root_key.objectid, dst_objectid,
-				   parent->root_key.objectid, inherit);
+	ret = btrfs_qgroup_inherit(trans, btrfs_root_id(src), dst_objectid,
+				   btrfs_root_id(parent), inherit);
 	if (ret < 0)
 		goto out;
 
@@ -1822,7 +1818,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 	 * insert root back/forward references
 	 */
 	ret = btrfs_add_root_ref(trans, objectid,
-				 parent_root->root_key.objectid,
+				 btrfs_root_id(parent_root),
 				 btrfs_ino(BTRFS_I(parent_inode)), index,
 				 &fname.disk_name);
 	if (ret) {
@@ -1855,16 +1851,14 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 		ret = qgroup_account_snapshot(trans, root, parent_root,
 					      pending->inherit, objectid);
 	else if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_SIMPLE)
-		ret = btrfs_qgroup_inherit(trans, root->root_key.objectid, objectid,
-					   parent_root->root_key.objectid, pending->inherit);
+		ret = btrfs_qgroup_inherit(trans, btrfs_root_id(root), objectid,
+					   btrfs_root_id(parent_root), pending->inherit);
 	if (ret < 0)
 		goto fail;
 
 	ret = btrfs_insert_dir_item(trans, &fname.disk_name,
 				    BTRFS_I(parent_inode), &key, BTRFS_FT_DIR,
 				    index);
-	/* We have check then name at the beginning, so it is impossible. */
-	BUG_ON(ret == -EEXIST || ret == -EOVERFLOW);
 	if (ret) {
 		btrfs_abort_transaction(trans, ret);
 		goto fail;
@@ -2625,7 +2619,7 @@ int btrfs_clean_one_deleted_snapshot(struct btrfs_fs_info *fs_info)
 	list_del_init(&root->root_list);
 	spin_unlock(&fs_info->trans_lock);
 
-	btrfs_debug(fs_info, "cleaner removing %llu", root->root_key.objectid);
+	btrfs_debug(fs_info, "cleaner removing %llu", btrfs_root_id(root));
 
 	btrfs_kill_all_delayed_nodes(root);
 
diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index 32604e9b31c3..a2c3651a3d8f 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -2021,7 +2021,7 @@ int btrfs_check_eb_owner(const struct extent_buffer *eb, u64 root_owner)
 	 * Skip dummy fs, as selftests don't create unique ebs for each dummy
 	 * root.
 	 */
-	if (test_bit(BTRFS_FS_STATE_DUMMY_FS_INFO, &eb->fs_info->fs_state))
+	if (btrfs_is_testing(eb->fs_info))
 		return 0;
 	/*
 	 * There are several call sites (backref walking, qgroup, and data
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 472918a5bc73..5146387b416b 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -391,7 +391,7 @@ static int overwrite_item(struct btrfs_trans_handle *trans,
 	 * the leaf before writing into the log tree. See the comments at
 	 * copy_items() for more details.
 	 */
-	ASSERT(root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID);
+	ASSERT(btrfs_root_id(root) != BTRFS_TREE_LOG_OBJECTID);
 
 	item_size = btrfs_item_size(eb, slot);
 	src_ptr = btrfs_item_ptr_offset(eb, slot);
@@ -748,7 +748,6 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
 			goto out;
 
 		if (ins.objectid > 0) {
-			struct btrfs_ref ref = { 0 };
 			u64 csum_start;
 			u64 csum_end;
 			LIST_HEAD(ordered_sums);
@@ -762,13 +761,15 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
 			if (ret < 0) {
 				goto out;
 			} else if (ret == 0) {
-				btrfs_init_generic_ref(&ref,
-						BTRFS_ADD_DELAYED_REF,
-						ins.objectid, ins.offset, 0,
-						root->root_key.objectid);
-				btrfs_init_data_ref(&ref,
-						root->root_key.objectid,
-						key->objectid, offset, 0, false);
+				struct btrfs_ref ref = {
+					.action = BTRFS_ADD_DELAYED_REF,
+					.bytenr = ins.objectid,
+					.num_bytes = ins.offset,
+					.owning_root = btrfs_root_id(root),
+					.ref_root = btrfs_root_id(root),
+				};
+				btrfs_init_data_ref(&ref, key->objectid, offset,
+						    0, false);
 				ret = btrfs_inc_extent_ref(trans, &ref);
 				if (ret)
 					goto out;
@@ -778,7 +779,7 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
 				 * allocation tree
 				 */
 				ret = btrfs_alloc_logged_file_extent(trans,
-						root->root_key.objectid,
+						btrfs_root_id(root),
 						key->objectid, offset, &ins);
 				if (ret)
 					goto out;
@@ -797,9 +798,10 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
 
 			ret = btrfs_lookup_csums_list(root->log_root,
 						csum_start, csum_end - 1,
-						&ordered_sums, 0, false);
-			if (ret)
+						&ordered_sums, false);
+			if (ret < 0)
 				goto out;
+			ret = 0;
 			/*
 			 * Now delete all existing cums in the csum root that
 			 * cover our range. We do this because we can have an
@@ -3045,7 +3047,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 		if (ret != -ENOSPC)
 			btrfs_err(fs_info,
 				  "failed to update log for root %llu ret %d",
-				  root->root_key.objectid, ret);
+				  btrfs_root_id(root), ret);
 		btrfs_wait_tree_log_extents(log, mark);
 		mutex_unlock(&log_root_tree->log_mutex);
 		goto out;
@@ -4460,9 +4462,10 @@ static noinline int copy_items(struct btrfs_trans_handle *trans,
 		disk_bytenr += extent_offset;
 		ret = btrfs_lookup_csums_list(csum_root, disk_bytenr,
 					      disk_bytenr + extent_num_bytes - 1,
-					      &ordered_sums, 0, false);
-		if (ret)
+					      &ordered_sums, false);
+		if (ret < 0)
 			goto out;
+		ret = 0;
 
 		list_for_each_entry_safe(sums, sums_next, &ordered_sums, list) {
 			if (!ret)
@@ -4574,8 +4577,8 @@ static int log_extent_csums(struct btrfs_trans_handle *trans,
 	struct btrfs_root *csum_root;
 	u64 csum_offset;
 	u64 csum_len;
-	u64 mod_start = em->mod_start;
-	u64 mod_len = em->mod_len;
+	u64 mod_start = em->start;
+	u64 mod_len = em->len;
 	LIST_HEAD(ordered_sums);
 	int ret = 0;
 
@@ -4655,9 +4658,10 @@ static int log_extent_csums(struct btrfs_trans_handle *trans,
 	csum_root = btrfs_csum_root(trans->fs_info, em->block_start);
 	ret = btrfs_lookup_csums_list(csum_root, em->block_start + csum_offset,
 				      em->block_start + csum_offset +
-				      csum_len - 1, &ordered_sums, 0, false);
-	if (ret)
+				      csum_len - 1, &ordered_sums, false);
+	if (ret < 0)
 		return ret;
+	ret = 0;
 
 	while (!list_empty(&ordered_sums)) {
 		struct btrfs_ordered_sum *sums = list_entry(ordered_sums.next,
@@ -4945,7 +4949,7 @@ process:
 		 * private list.
 		 */
 		if (ret) {
-			clear_em_logging(tree, em);
+			clear_em_logging(inode, em);
 			free_extent_map(em);
 			continue;
 		}
@@ -4954,7 +4958,7 @@ process:
 
 		ret = log_one_extent(trans, inode, em, path, ctx);
 		write_lock(&tree->lock);
-		clear_em_logging(tree, em);
+		clear_em_logging(inode, em);
 		free_extent_map(em);
 	}
 	WARN_ON(!list_empty(&extents));
diff --git a/fs/btrfs/tree-mod-log.c b/fs/btrfs/tree-mod-log.c
index 43b3accbed7a..fa45b5fb9683 100644
--- a/fs/btrfs/tree-mod-log.c
+++ b/fs/btrfs/tree-mod-log.c
@@ -1004,7 +1004,7 @@ struct extent_buffer *btrfs_get_old_root(struct btrfs_root *root, u64 time_seq)
 		free_extent_buffer(eb_root);
 
 		check.level = level;
-		check.owner_root = root->root_key.objectid;
+		check.owner_root = btrfs_root_id(root);
 
 		old = read_tree_block(fs_info, logical, &check);
 		if (WARN_ON(IS_ERR(old) || !extent_buffer_uptodate(old))) {
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index ef6bd2f4251b..b6a701011fb0 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -5615,21 +5615,6 @@ struct btrfs_chunk_map *btrfs_alloc_chunk_map(int num_stripes, gfp_t gfp)
 	return map;
 }
 
-struct btrfs_chunk_map *btrfs_clone_chunk_map(struct btrfs_chunk_map *map, gfp_t gfp)
-{
-	const int size = btrfs_chunk_map_size(map->num_stripes);
-	struct btrfs_chunk_map *clone;
-
-	clone = kmemdup(map, size, gfp);
-	if (!clone)
-		return NULL;
-
-	refcount_set(&clone->refs, 1);
-	RB_CLEAR_NODE(&clone->rb_node);
-
-	return clone;
-}
-
 static struct btrfs_block_group *create_chunk(struct btrfs_trans_handle *trans,
 			struct alloc_chunk_ctl *ctl,
 			struct btrfs_device_info *devices_info)
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 93854609a4d5..66e6fc481ecd 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -92,6 +92,9 @@ enum btrfs_raid_types {
 #define BTRFS_DEV_STATE_FLUSH_SENT	(4)
 #define BTRFS_DEV_STATE_NO_READA	(5)
 
+/* Special value encoding failure to write primary super block. */
+#define BTRFS_SUPER_PRIMARY_WRITE_ERROR		(INT_MAX / 2)
+
 struct btrfs_fs_devices;
 
 struct btrfs_device {
@@ -142,6 +145,12 @@ struct btrfs_device {
 	/* type and info about this device */
 	u64 type;
 
+	/*
+	 * Counter of super block write errors, values larger than
+	 * BTRFS_SUPER_PRIMARY_WRITE_ERROR encode primary super block write failure.
+	 */
+	atomic_t sb_write_errors;
+
 	/* minimal io size for this device */
 	u32 sector_size;
 
@@ -743,7 +752,6 @@ struct btrfs_chunk_map *btrfs_alloc_chunk_map(int num_stripes, gfp_t gfp);
 int btrfs_add_chunk_map(struct btrfs_fs_info *fs_info, struct btrfs_chunk_map *map);
 #endif
 
-struct btrfs_chunk_map *btrfs_clone_chunk_map(struct btrfs_chunk_map *map, gfp_t gfp);
 struct btrfs_chunk_map *btrfs_find_chunk_map(struct btrfs_fs_info *fs_info,
 					     u64 logical, u64 length);
 struct btrfs_chunk_map *btrfs_find_chunk_map_nolock(struct btrfs_fs_info *fs_info,
diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c
index 6287763fdccc..15d0999e340e 100644
--- a/fs/btrfs/xattr.c
+++ b/fs/btrfs/xattr.c
@@ -504,7 +504,7 @@ static int btrfs_initxattrs(struct inode *inode,
 	const struct xattr *xattr;
 	unsigned int nofs_flag;
 	char *name;
-	int err = 0;
+	int ret = 0;
 
 	/*
 	 * We're holding a transaction handle, so use a NOFS memory allocation
@@ -515,7 +515,7 @@ static int btrfs_initxattrs(struct inode *inode,
 		name = kmalloc(XATTR_SECURITY_PREFIX_LEN +
 			       strlen(xattr->name) + 1, GFP_KERNEL);
 		if (!name) {
-			err = -ENOMEM;
+			ret = -ENOMEM;
 			break;
 		}
 		strcpy(name, XATTR_SECURITY_PREFIX);
@@ -524,14 +524,14 @@ static int btrfs_initxattrs(struct inode *inode,
 		if (strcmp(name, XATTR_NAME_CAPS) == 0)
 			clear_bit(BTRFS_INODE_NO_CAP_XATTR, &BTRFS_I(inode)->runtime_flags);
 
-		err = btrfs_setxattr(trans, inode, name, xattr->value,
+		ret = btrfs_setxattr(trans, inode, name, xattr->value,
 				     xattr->value_len, 0);
 		kfree(name);
-		if (err < 0)
+		if (ret < 0)
 			break;
 	}
 	memalloc_nofs_restore(nofs_flag);
-	return err;
+	return ret;
 }
 
 int btrfs_xattr_security_init(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c
index e5b3f2003896..d9e5c88a0f85 100644
--- a/fs/btrfs/zlib.c
+++ b/fs/btrfs/zlib.c
@@ -91,24 +91,24 @@ fail:
 	return ERR_PTR(-ENOMEM);
 }
 
-int zlib_compress_pages(struct list_head *ws, struct address_space *mapping,
-		u64 start, struct page **pages, unsigned long *out_pages,
-		unsigned long *total_in, unsigned long *total_out)
+int zlib_compress_folios(struct list_head *ws, struct address_space *mapping,
+			 u64 start, struct folio **folios, unsigned long *out_folios,
+			 unsigned long *total_in, unsigned long *total_out)
 {
 	struct workspace *workspace = list_entry(ws, struct workspace, list);
 	int ret;
 	char *data_in = NULL;
-	char *cpage_out;
-	int nr_pages = 0;
-	struct page *in_page = NULL;
-	struct page *out_page = NULL;
+	char *cfolio_out;
+	int nr_folios = 0;
+	struct folio *in_folio = NULL;
+	struct folio *out_folio = NULL;
 	unsigned long bytes_left;
-	unsigned int in_buf_pages;
+	unsigned int in_buf_folios;
 	unsigned long len = *total_out;
-	unsigned long nr_dest_pages = *out_pages;
-	const unsigned long max_out = nr_dest_pages * PAGE_SIZE;
+	unsigned long nr_dest_folios = *out_folios;
+	const unsigned long max_out = nr_dest_folios * PAGE_SIZE;
 
-	*out_pages = 0;
+	*out_folios = 0;
 	*total_out = 0;
 	*total_in = 0;
 
@@ -121,18 +121,18 @@ int zlib_compress_pages(struct list_head *ws, struct address_space *mapping,
 	workspace->strm.total_in = 0;
 	workspace->strm.total_out = 0;
 
-	out_page = btrfs_alloc_compr_page();
-	if (out_page == NULL) {
+	out_folio = btrfs_alloc_compr_folio();
+	if (out_folio == NULL) {
 		ret = -ENOMEM;
 		goto out;
 	}
-	cpage_out = page_address(out_page);
-	pages[0] = out_page;
-	nr_pages = 1;
+	cfolio_out = folio_address(out_folio);
+	folios[0] = out_folio;
+	nr_folios = 1;
 
 	workspace->strm.next_in = workspace->buf;
 	workspace->strm.avail_in = 0;
-	workspace->strm.next_out = cpage_out;
+	workspace->strm.next_out = cfolio_out;
 	workspace->strm.avail_out = PAGE_SIZE;
 
 	while (workspace->strm.total_in < len) {
@@ -142,19 +142,22 @@ int zlib_compress_pages(struct list_head *ws, struct address_space *mapping,
 		 */
 		if (workspace->strm.avail_in == 0) {
 			bytes_left = len - workspace->strm.total_in;
-			in_buf_pages = min(DIV_ROUND_UP(bytes_left, PAGE_SIZE),
-					   workspace->buf_size / PAGE_SIZE);
-			if (in_buf_pages > 1) {
+			in_buf_folios = min(DIV_ROUND_UP(bytes_left, PAGE_SIZE),
+					    workspace->buf_size / PAGE_SIZE);
+			if (in_buf_folios > 1) {
 				int i;
 
-				for (i = 0; i < in_buf_pages; i++) {
+				for (i = 0; i < in_buf_folios; i++) {
 					if (data_in) {
 						kunmap_local(data_in);
-						put_page(in_page);
+						folio_put(in_folio);
+						data_in = NULL;
 					}
-					in_page = find_get_page(mapping,
-								start >> PAGE_SHIFT);
-					data_in = kmap_local_page(in_page);
+					ret = btrfs_compress_filemap_get_folio(mapping,
+							start, &in_folio);
+					if (ret < 0)
+						goto out;
+					data_in = kmap_local_folio(in_folio, 0);
 					copy_page(workspace->buf + i * PAGE_SIZE,
 						  data_in);
 					start += PAGE_SIZE;
@@ -163,11 +166,14 @@ int zlib_compress_pages(struct list_head *ws, struct address_space *mapping,
 			} else {
 				if (data_in) {
 					kunmap_local(data_in);
-					put_page(in_page);
+					folio_put(in_folio);
+					data_in = NULL;
 				}
-				in_page = find_get_page(mapping,
-							start >> PAGE_SHIFT);
-				data_in = kmap_local_page(in_page);
+				ret = btrfs_compress_filemap_get_folio(mapping,
+						start, &in_folio);
+				if (ret < 0)
+					goto out;
+				data_in = kmap_local_folio(in_folio, 0);
 				start += PAGE_SIZE;
 				workspace->strm.next_in = data_in;
 			}
@@ -196,20 +202,20 @@ int zlib_compress_pages(struct list_head *ws, struct address_space *mapping,
 		 * the stream end if required
 		 */
 		if (workspace->strm.avail_out == 0) {
-			if (nr_pages == nr_dest_pages) {
+			if (nr_folios == nr_dest_folios) {
 				ret = -E2BIG;
 				goto out;
 			}
-			out_page = btrfs_alloc_compr_page();
-			if (out_page == NULL) {
+			out_folio = btrfs_alloc_compr_folio();
+			if (out_folio == NULL) {
 				ret = -ENOMEM;
 				goto out;
 			}
-			cpage_out = page_address(out_page);
-			pages[nr_pages] = out_page;
-			nr_pages++;
+			cfolio_out = folio_address(out_folio);
+			folios[nr_folios] = out_folio;
+			nr_folios++;
 			workspace->strm.avail_out = PAGE_SIZE;
-			workspace->strm.next_out = cpage_out;
+			workspace->strm.next_out = cfolio_out;
 		}
 		/* we're all done */
 		if (workspace->strm.total_in >= len)
@@ -231,21 +237,21 @@ int zlib_compress_pages(struct list_head *ws, struct address_space *mapping,
 			ret = -EIO;
 			goto out;
 		} else if (workspace->strm.avail_out == 0) {
-			/* get another page for the stream end */
-			if (nr_pages == nr_dest_pages) {
+			/* Get another folio for the stream end. */
+			if (nr_folios == nr_dest_folios) {
 				ret = -E2BIG;
 				goto out;
 			}
-			out_page = btrfs_alloc_compr_page();
-			if (out_page == NULL) {
+			out_folio = btrfs_alloc_compr_folio();
+			if (out_folio == NULL) {
 				ret = -ENOMEM;
 				goto out;
 			}
-			cpage_out = page_address(out_page);
-			pages[nr_pages] = out_page;
-			nr_pages++;
+			cfolio_out = folio_address(out_folio);
+			folios[nr_folios] = out_folio;
+			nr_folios++;
 			workspace->strm.avail_out = PAGE_SIZE;
-			workspace->strm.next_out = cpage_out;
+			workspace->strm.next_out = cfolio_out;
 		}
 	}
 	zlib_deflateEnd(&workspace->strm);
@@ -259,10 +265,10 @@ int zlib_compress_pages(struct list_head *ws, struct address_space *mapping,
 	*total_out = workspace->strm.total_out;
 	*total_in = workspace->strm.total_in;
 out:
-	*out_pages = nr_pages;
+	*out_folios = nr_folios;
 	if (data_in) {
 		kunmap_local(data_in);
-		put_page(in_page);
+		folio_put(in_folio);
 	}
 
 	return ret;
@@ -275,13 +281,13 @@ int zlib_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
 	int wbits = MAX_WBITS;
 	char *data_in;
 	size_t total_out = 0;
-	unsigned long page_in_index = 0;
+	unsigned long folio_in_index = 0;
 	size_t srclen = cb->compressed_len;
-	unsigned long total_pages_in = DIV_ROUND_UP(srclen, PAGE_SIZE);
+	unsigned long total_folios_in = DIV_ROUND_UP(srclen, PAGE_SIZE);
 	unsigned long buf_start;
-	struct page **pages_in = cb->compressed_pages;
+	struct folio **folios_in = cb->compressed_folios;
 
-	data_in = kmap_local_page(pages_in[page_in_index]);
+	data_in = kmap_local_folio(folios_in[folio_in_index], 0);
 	workspace->strm.next_in = data_in;
 	workspace->strm.avail_in = min_t(size_t, srclen, PAGE_SIZE);
 	workspace->strm.total_in = 0;
@@ -331,12 +337,12 @@ int zlib_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
 		if (workspace->strm.avail_in == 0) {
 			unsigned long tmp;
 			kunmap_local(data_in);
-			page_in_index++;
-			if (page_in_index >= total_pages_in) {
+			folio_in_index++;
+			if (folio_in_index >= total_folios_in) {
 				data_in = NULL;
 				break;
 			}
-			data_in = kmap_local_page(pages_in[page_in_index]);
+			data_in = kmap_local_folio(folios_in[folio_in_index], 0);
 			workspace->strm.next_in = data_in;
 			tmp = srclen - workspace->strm.total_in;
 			workspace->strm.avail_in = min(tmp, PAGE_SIZE);
diff --git a/fs/btrfs/zstd.c b/fs/btrfs/zstd.c
index 92b3744b819b..2b232b82c3a8 100644
--- a/fs/btrfs/zstd.c
+++ b/fs/btrfs/zstd.c
@@ -374,25 +374,25 @@ fail:
 	return ERR_PTR(-ENOMEM);
 }
 
-int zstd_compress_pages(struct list_head *ws, struct address_space *mapping,
-		u64 start, struct page **pages, unsigned long *out_pages,
-		unsigned long *total_in, unsigned long *total_out)
+int zstd_compress_folios(struct list_head *ws, struct address_space *mapping,
+			 u64 start, struct folio **folios, unsigned long *out_folios,
+			 unsigned long *total_in, unsigned long *total_out)
 {
 	struct workspace *workspace = list_entry(ws, struct workspace, list);
 	zstd_cstream *stream;
 	int ret = 0;
-	int nr_pages = 0;
-	struct page *in_page = NULL;  /* The current page to read */
-	struct page *out_page = NULL; /* The current page to write to */
+	int nr_folios = 0;
+	struct folio *in_folio = NULL;  /* The current folio to read. */
+	struct folio *out_folio = NULL; /* The current folio to write to. */
 	unsigned long tot_in = 0;
 	unsigned long tot_out = 0;
 	unsigned long len = *total_out;
-	const unsigned long nr_dest_pages = *out_pages;
-	unsigned long max_out = nr_dest_pages * PAGE_SIZE;
+	const unsigned long nr_dest_folios = *out_folios;
+	unsigned long max_out = nr_dest_folios * PAGE_SIZE;
 	zstd_parameters params = zstd_get_btrfs_parameters(workspace->req_level,
 							   len);
 
-	*out_pages = 0;
+	*out_folios = 0;
 	*total_out = 0;
 	*total_in = 0;
 
@@ -406,19 +406,21 @@ int zstd_compress_pages(struct list_head *ws, struct address_space *mapping,
 	}
 
 	/* map in the first page of input data */
-	in_page = find_get_page(mapping, start >> PAGE_SHIFT);
-	workspace->in_buf.src = kmap_local_page(in_page);
+	ret = btrfs_compress_filemap_get_folio(mapping, start, &in_folio);
+	if (ret < 0)
+		goto out;
+	workspace->in_buf.src = kmap_local_folio(in_folio, 0);
 	workspace->in_buf.pos = 0;
 	workspace->in_buf.size = min_t(size_t, len, PAGE_SIZE);
 
 	/* Allocate and map in the output buffer */
-	out_page = btrfs_alloc_compr_page();
-	if (out_page == NULL) {
+	out_folio = btrfs_alloc_compr_folio();
+	if (out_folio == NULL) {
 		ret = -ENOMEM;
 		goto out;
 	}
-	pages[nr_pages++] = out_page;
-	workspace->out_buf.dst = page_address(out_page);
+	folios[nr_folios++] = out_folio;
+	workspace->out_buf.dst = folio_address(out_folio);
 	workspace->out_buf.pos = 0;
 	workspace->out_buf.size = min_t(size_t, max_out, PAGE_SIZE);
 
@@ -453,17 +455,17 @@ int zstd_compress_pages(struct list_head *ws, struct address_space *mapping,
 		if (workspace->out_buf.pos == workspace->out_buf.size) {
 			tot_out += PAGE_SIZE;
 			max_out -= PAGE_SIZE;
-			if (nr_pages == nr_dest_pages) {
+			if (nr_folios == nr_dest_folios) {
 				ret = -E2BIG;
 				goto out;
 			}
-			out_page = btrfs_alloc_compr_page();
-			if (out_page == NULL) {
+			out_folio = btrfs_alloc_compr_folio();
+			if (out_folio == NULL) {
 				ret = -ENOMEM;
 				goto out;
 			}
-			pages[nr_pages++] = out_page;
-			workspace->out_buf.dst = page_address(out_page);
+			folios[nr_folios++] = out_folio;
+			workspace->out_buf.dst = folio_address(out_folio);
 			workspace->out_buf.pos = 0;
 			workspace->out_buf.size = min_t(size_t, max_out,
 							PAGE_SIZE);
@@ -479,11 +481,14 @@ int zstd_compress_pages(struct list_head *ws, struct address_space *mapping,
 		if (workspace->in_buf.pos == workspace->in_buf.size) {
 			tot_in += PAGE_SIZE;
 			kunmap_local(workspace->in_buf.src);
-			put_page(in_page);
+			workspace->in_buf.src = NULL;
+			folio_put(in_folio);
 			start += PAGE_SIZE;
 			len -= PAGE_SIZE;
-			in_page = find_get_page(mapping, start >> PAGE_SHIFT);
-			workspace->in_buf.src = kmap_local_page(in_page);
+			ret = btrfs_compress_filemap_get_folio(mapping, start, &in_folio);
+			if (ret < 0)
+				goto out;
+			workspace->in_buf.src = kmap_local_folio(in_folio, 0);
 			workspace->in_buf.pos = 0;
 			workspace->in_buf.size = min_t(size_t, len, PAGE_SIZE);
 		}
@@ -510,17 +515,17 @@ int zstd_compress_pages(struct list_head *ws, struct address_space *mapping,
 
 		tot_out += PAGE_SIZE;
 		max_out -= PAGE_SIZE;
-		if (nr_pages == nr_dest_pages) {
+		if (nr_folios == nr_dest_folios) {
 			ret = -E2BIG;
 			goto out;
 		}
-		out_page = btrfs_alloc_compr_page();
-		if (out_page == NULL) {
+		out_folio = btrfs_alloc_compr_folio();
+		if (out_folio == NULL) {
 			ret = -ENOMEM;
 			goto out;
 		}
-		pages[nr_pages++] = out_page;
-		workspace->out_buf.dst = page_address(out_page);
+		folios[nr_folios++] = out_folio;
+		workspace->out_buf.dst = folio_address(out_folio);
 		workspace->out_buf.pos = 0;
 		workspace->out_buf.size = min_t(size_t, max_out, PAGE_SIZE);
 	}
@@ -534,10 +539,10 @@ int zstd_compress_pages(struct list_head *ws, struct address_space *mapping,
 	*total_in = tot_in;
 	*total_out = tot_out;
 out:
-	*out_pages = nr_pages;
+	*out_folios = nr_folios;
 	if (workspace->in_buf.src) {
 		kunmap_local(workspace->in_buf.src);
-		put_page(in_page);
+		folio_put(in_folio);
 	}
 	return ret;
 }
@@ -545,12 +550,12 @@ out:
 int zstd_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
 {
 	struct workspace *workspace = list_entry(ws, struct workspace, list);
-	struct page **pages_in = cb->compressed_pages;
+	struct folio **folios_in = cb->compressed_folios;
 	size_t srclen = cb->compressed_len;
 	zstd_dstream *stream;
 	int ret = 0;
-	unsigned long page_in_index = 0;
-	unsigned long total_pages_in = DIV_ROUND_UP(srclen, PAGE_SIZE);
+	unsigned long folio_in_index = 0;
+	unsigned long total_folios_in = DIV_ROUND_UP(srclen, PAGE_SIZE);
 	unsigned long buf_start;
 	unsigned long total_out = 0;
 
@@ -562,7 +567,7 @@ int zstd_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
 		goto done;
 	}
 
-	workspace->in_buf.src = kmap_local_page(pages_in[page_in_index]);
+	workspace->in_buf.src = kmap_local_folio(folios_in[folio_in_index], 0);
 	workspace->in_buf.pos = 0;
 	workspace->in_buf.size = min_t(size_t, srclen, PAGE_SIZE);
 
@@ -599,14 +604,15 @@ int zstd_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
 
 		if (workspace->in_buf.pos == workspace->in_buf.size) {
 			kunmap_local(workspace->in_buf.src);
-			page_in_index++;
-			if (page_in_index >= total_pages_in) {
+			folio_in_index++;
+			if (folio_in_index >= total_folios_in) {
 				workspace->in_buf.src = NULL;
 				ret = -EIO;
 				goto done;
 			}
 			srclen -= PAGE_SIZE;
-			workspace->in_buf.src = kmap_local_page(pages_in[page_in_index]);
+			workspace->in_buf.src =
+				kmap_local_folio(folios_in[folio_in_index], 0);
 			workspace->in_buf.pos = 0;
 			workspace->in_buf.size = min_t(size_t, srclen, PAGE_SIZE);
 		}