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
  ...

block/bio.c

@@ -1136,6 +1136,7 @@ void bio_add_folio_nofail(struct bio *bio, struct folio *folio, size_t len,
 	WARN_ON_ONCE(off > UINT_MAX);
 	__bio_add_page(bio, &folio->page, len, off);
 }
+EXPORT_SYMBOL_GPL(bio_add_folio_nofail);
 
 /**
  * bio_add_folio - Attempt to add part of a folio to a bio.

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;

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)

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;
 

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;
 }

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,

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 @@ static noinline int split_leaf(struct btrfs_trans_handle *trans,
 	 * 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);

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);

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);

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

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;

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 @@ static int __set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 		if (state->state & exclusive_bits) {
 			*failed_start = state->start;
 			cache_state(state, failed_state);
-			err = -EEXIST;
+			ret = -EEXIST;
 			goto out;
 		}
 
@@ -1158,7 +1158,7 @@ static int __set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 		if (state->state & exclusive_bits) {
 			*failed_start = start;
 			cache_state(state, failed_state);
-			err = -EEXIST;
+			ret = -EEXIST;
 			goto out;
 		}
 
@@ -1175,12 +1175,12 @@ static int __set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 		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 @@ static int __set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 		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 @@ static int __set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 		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 @@ static int __set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 	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 @@ int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 	if (!state) {
 		prealloc = alloc_extent_state_atomic(prealloc);
 		if (!prealloc) {
-			err = -ENOMEM;
+			ret = -ENOMEM;
 			goto out;
 		}
 		prealloc->start = start;
@@ -1402,14 +1402,14 @@ int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 	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 @@ int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 
 		prealloc = alloc_extent_state_atomic(prealloc);
 		if (!prealloc) {
-			err = -ENOMEM;
+			ret = -ENOMEM;
 			goto out;
 		}
 
@@ -1454,8 +1454,8 @@ int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 		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 @@ int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 	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 @@ int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 	if (prealloc)
 		free_extent_state(prealloc);
 
-	return err;
+	return ret;
 }
 
 /*

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,

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

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 @@ int btrfs_csum_file_blocks(struct btrfs_trans_handle *trans,
 		 * 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;
 }

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);

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;
 

fs/btrfs/inode-item.c

@@ -670,16 +670,18 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
 		}
 
 		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);

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 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
 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);

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)

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);
 

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);
 }