Merge tag 'for-6.16-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs updates from David Sterba:
 "Apart from numerous cleanups, there are some performance improvements
  and one minor mount option update. There's one more radix-tree
  conversion (one remaining), and continued work towards enabling large
  folios (almost finished).

  Performance:

   - extent buffer conversion to xarray gains throughput and runtime
     improvements on metadata heavy operations doing writeback (sample
     test shows +50% throughput, -33% runtime)

   - extent io tree cleanups lead to performance improvements by
     avoiding unnecessary searches or repeated searches

   - more efficient extent unpinning when committing transaction
     (estimated run time improvement 3-5%)

  User visible changes:

   - remove standalone mount option 'nologreplay', deprecated in 5.9,
     replacement is 'rescue=nologreplay'

   - in scrub, update reporting, add back device stats message after
     detected errors (accidentally removed during recent refactoring)

  Core:

   - convert extent buffer radix tree to xarray

   - in subpage mode, move block perfect compression out of experimental
     build

   - in zoned mode, introduce sub block groups to allow managing special
     block groups, like the one for relocation or tree-log, to handle
     some corner cases of ENOSPC

   - in scrub, simplify bitmaps for block tracking status

   - continued preparations for large folios:
       - remove assertions for folio order 0
       - add support where missing: compression, buffered write, defrag,
         hole punching, subpage, send

   - fix fsync of files with no hard links not persisting deletion

   - reject tree blocks which are not nodesize aligned, a precaution
     from 4.9 times

   - move transaction abort calls closer to the error sites

   - remove usage of some struct bio_vec internals

   - simplifications in extent map

   - extent IO cleanups and optimizations

   - error handling improvements

   - enhanced ASSERT() macro with optional format strings

   - cleanups:
       - remove unused code
       - naming unifications, dropped __, added prefix
       - merge similar functions
       - use common helpers for various data structures"

* tag 'for-6.16-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (198 commits)
  btrfs: move misplaced comment of btrfs_path::keep_locks
  btrfs: remove standalone "nologreplay" mount option
  btrfs: use a single variable to track return value at btrfs_page_mkwrite()
  btrfs: don't return VM_FAULT_SIGBUS on failure to set delalloc for mmap write
  btrfs: simplify early error checking in btrfs_page_mkwrite()
  btrfs: pass true to btrfs_delalloc_release_space() at btrfs_page_mkwrite()
  btrfs: fix wrong start offset for delalloc space release during mmap write
  btrfs: fix harmless race getting delayed ref head count when running delayed refs
  btrfs: log error codes during failures when writing super blocks
  btrfs: simplify error return logic when getting folio at prepare_one_folio()
  btrfs: return real error from __filemap_get_folio() calls
  btrfs: remove superfluous return value check at btrfs_dio_iomap_begin()
  btrfs: fix invalid data space release when truncating block in NOCOW mode
  btrfs: update Kconfig option descriptions
  btrfs: update list of features built under experimental config
  btrfs: send: remove btrfs_debug() calls
  btrfs: use boolean for delalloc argument to btrfs_free_reserved_extent()
  btrfs: use boolean for delalloc argument to btrfs_free_reserved_bytes()
  btrfs: fold error checks when allocating ordered extent and update comments
  btrfs: check we grabbed inode reference when allocating an ordered extent
  ...

1 files changed, 42 insertions, 9 deletions

diff --git a/fs/btrfs/delalloc-space.c b/fs/btrfs/delalloc-space.c
index 88e900e5a43d..288e1776c02d 100644
--- a/fs/btrfs/delalloc-space.c
+++ b/fs/btrfs/delalloc-space.c
@@ -111,6 +111,18 @@
  *  making error handling and cleanup easier.
  */
 
+static inline struct btrfs_space_info *data_sinfo_for_inode(const struct btrfs_inode *inode)
+{
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
+
+	if (btrfs_is_zoned(fs_info) && btrfs_is_data_reloc_root(inode->root)) {
+		ASSERT(fs_info->data_sinfo->sub_group[0]->subgroup_id ==
+		       BTRFS_SUB_GROUP_DATA_RELOC);
+		return fs_info->data_sinfo->sub_group[0];
+	}
+	return fs_info->data_sinfo;
+}
+
 int btrfs_alloc_data_chunk_ondemand(const struct btrfs_inode *inode, u64 bytes)
 {
 	struct btrfs_root *root = inode->root;
@@ -123,7 +135,7 @@ int btrfs_alloc_data_chunk_ondemand(const struct btrfs_inode *inode, u64 bytes)
 	if (btrfs_is_free_space_inode(inode))
 		flush = BTRFS_RESERVE_FLUSH_FREE_SPACE_INODE;
 
-	return btrfs_reserve_data_bytes(fs_info, bytes, flush);
+	return btrfs_reserve_data_bytes(data_sinfo_for_inode(inode), bytes, flush);
 }
 
 int btrfs_check_data_free_space(struct btrfs_inode *inode,
@@ -144,14 +156,14 @@ int btrfs_check_data_free_space(struct btrfs_inode *inode,
 	else if (btrfs_is_free_space_inode(inode))
 		flush = BTRFS_RESERVE_FLUSH_FREE_SPACE_INODE;
 
-	ret = btrfs_reserve_data_bytes(fs_info, len, flush);
+	ret = btrfs_reserve_data_bytes(data_sinfo_for_inode(inode), len, flush);
 	if (ret < 0)
 		return ret;
 
 	/* Use new btrfs_qgroup_reserve_data to reserve precious data space. */
 	ret = btrfs_qgroup_reserve_data(inode, reserved, start, len);
 	if (ret < 0) {
-		btrfs_free_reserved_data_space_noquota(fs_info, len);
+		btrfs_free_reserved_data_space_noquota(inode, len);
 		extent_changeset_free(*reserved);
 		*reserved = NULL;
 	} else {
@@ -168,15 +180,13 @@ int btrfs_check_data_free_space(struct btrfs_inode *inode,
  * which we can't sleep and is sure it won't affect qgroup reserved space.
  * Like clear_bit_hook().
  */
-void btrfs_free_reserved_data_space_noquota(struct btrfs_fs_info *fs_info,
-					    u64 len)
+void btrfs_free_reserved_data_space_noquota(struct btrfs_inode *inode, u64 len)
 {
-	struct btrfs_space_info *data_sinfo;
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 
 	ASSERT(IS_ALIGNED(len, fs_info->sectorsize));
 
-	data_sinfo = fs_info->data_sinfo;
-	btrfs_space_info_free_bytes_may_use(data_sinfo, len);
+	btrfs_space_info_free_bytes_may_use(data_sinfo_for_inode(inode), len);
 }
 
 /*
@@ -196,7 +206,7 @@ void btrfs_free_reserved_data_space(struct btrfs_inode *inode,
 	      round_down(start, fs_info->sectorsize);
 	start = round_down(start, fs_info->sectorsize);
 
-	btrfs_free_reserved_data_space_noquota(fs_info, len);
+	btrfs_free_reserved_data_space_noquota(inode, len);
 	btrfs_qgroup_free_data(inode, reserved, start, len, NULL);
 }
 
@@ -439,6 +449,29 @@ void btrfs_delalloc_release_extents(struct btrfs_inode *inode, u64 num_bytes)
 	btrfs_inode_rsv_release(inode, true);
 }
 
+/* Shrink a previously reserved extent to a new length. */
+void btrfs_delalloc_shrink_extents(struct btrfs_inode *inode, u64 reserved_len, u64 new_len)
+{
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
+	const u32 reserved_num_extents = count_max_extents(fs_info, reserved_len);
+	const u32 new_num_extents = count_max_extents(fs_info, new_len);
+	const int diff_num_extents = new_num_extents - reserved_num_extents;
+
+	ASSERT(new_len <= reserved_len);
+	if (new_num_extents == reserved_num_extents)
+		return;
+
+	spin_lock(&inode->lock);
+	btrfs_mod_outstanding_extents(inode, diff_num_extents);
+	btrfs_calculate_inode_block_rsv_size(fs_info, inode);
+	spin_unlock(&inode->lock);
+
+	if (btrfs_is_testing(fs_info))
+		return;
+
+	btrfs_inode_rsv_release(inode, true);
+}
+
 /*
  * Reserve data and metadata space for delalloc
  *