Merge tag 'for-6.6-tag' of git://git.kernel.org/pub/scm/linux/kernel/…

…git/kdave/linux

Pull btrfs updates from David Sterba:
 "No new features, the bulk of the changes are fixes, refactoring and
  cleanups. The notable fix is the scrub performance restoration after
  rewrite in 6.4, though still only partial.

  Fixes:

   - scrub performance drop due to rewrite in 6.4 partially restored:
      - do IO grouping by blg_plug/blk_unplug again
      - avoid unnecessary tree searches when processing stripes, in
        extent and checksum trees
      - the drop is noticeable on fast PCIe devices, -66% and restored
        to -33% of the original
      - backports to 6.4 planned

   - handle more corner cases of transaction commit during orphan
     cleanup or delayed ref processing

   - use correct fsid/metadata_uuid when validating super block

   - copy directory permissions and time when creating a stub subvolume

  Core:

   - debugging feature integrity checker deprecated, to be removed in
     6.7

   - in zoned mode, zones are activated just before the write, making
     error handling easier, now the overcommit mechanism can be enabled
     again which improves performance by avoiding more frequent flushing

   - v0 extent handling completely removed, deprecated long time ago

   - error handling improvements

   - tests:
      - extent buffer bitmap tests
      - pinned extent splitting tests

   - cleanups and refactoring:
      - compression writeback
      - extent buffer bitmap
      - space flushing, ENOSPC handling"

* tag 'for-6.6-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (110 commits)
  btrfs: zoned: skip splitting and logical rewriting on pre-alloc write
  btrfs: tests: test invalid splitting when skipping pinned drop extent_map
  btrfs: tests: add a test for btrfs_add_extent_mapping
  btrfs: tests: add extent_map tests for dropping with odd layouts
  btrfs: scrub: move write back of repaired sectors to scrub_stripe_read_repair_worker()
  btrfs: scrub: don't go ordered workqueue for dev-replace
  btrfs: scrub: fix grouping of read IO
  btrfs: scrub: avoid unnecessary csum tree search preparing stripes
  btrfs: scrub: avoid unnecessary extent tree search preparing stripes
  btrfs: copy dir permission and time when creating a stub subvolume
  btrfs: remove pointless empty list check when reading delayed dir indexes
  btrfs: drop redundant check to use fs_devices::metadata_uuid
  btrfs: compare the correct fsid/metadata_uuid in btrfs_validate_super
  btrfs: use the correct superblock to compare fsid in btrfs_validate_super
  btrfs: simplify memcpy either of metadata_uuid or fsid
  btrfs: add a helper to read the superblock metadata_uuid
  btrfs: remove v0 extent handling
  btrfs: output extra debug info if we failed to find an inline backref
  btrfs: move the !zoned assert into run_delalloc_cow
  btrfs: consolidate the error handling in run_delalloc_nocow
  ...

fs/btrfs/Kconfig

@@ -49,9 +49,11 @@ config BTRFS_FS_POSIX_ACL
 	  If you don't know what Access Control Lists are, say N
 
 config BTRFS_FS_CHECK_INTEGRITY
-	bool "Btrfs with integrity check tool compiled in (DANGEROUS)"
+	bool "Btrfs with integrity check tool compiled in (DEPRECATED)"
 	depends on BTRFS_FS
 	help
+	  This feature has been deprecated and will be removed in 6.7.
+
 	  Adds code that examines all block write requests (including
 	  writes of the super block). The goal is to verify that the
 	  state of the filesystem on disk is always consistent, i.e.,

fs/btrfs/accessors.h

@@ -3,6 +3,8 @@
 #ifndef BTRFS_ACCESSORS_H
 #define BTRFS_ACCESSORS_H
 
+#include <linux/stddef.h>
+
 struct btrfs_map_token {
 	struct extent_buffer *eb;
 	char *kaddr;
@@ -34,13 +36,13 @@ static inline void put_unaligned_le8(u8 val, void *p)
 	read_extent_buffer(eb, (char *)(result),			\
 			   ((unsigned long)(ptr)) +			\
 			    offsetof(type, member),			\
-			   sizeof(((type *)0)->member)))
+			    sizeof_field(type, member)))
 
 #define write_eb_member(eb, ptr, type, member, result) (\
 	write_extent_buffer(eb, (char *)(result),			\
 			   ((unsigned long)(ptr)) +			\
 			    offsetof(type, member),			\
-			   sizeof(((type *)0)->member)))
+			    sizeof_field(type, member)))
 
 #define DECLARE_BTRFS_SETGET_BITS(bits)					\
 u##bits btrfs_get_token_##bits(struct btrfs_map_token *token,		\
@@ -62,25 +64,25 @@ DECLARE_BTRFS_SETGET_BITS(64)
 static inline u##bits btrfs_##name(const struct extent_buffer *eb,	\
 				   const type *s)			\
 {									\
-	static_assert(sizeof(u##bits) == sizeof(((type *)0))->member);	\
+	static_assert(sizeof(u##bits) == sizeof_field(type, member));	\
 	return btrfs_get_##bits(eb, s, offsetof(type, member));		\
 }									\
 static inline void btrfs_set_##name(const struct extent_buffer *eb, type *s, \
 				    u##bits val)			\
 {									\
-	static_assert(sizeof(u##bits) == sizeof(((type *)0))->member);	\
+	static_assert(sizeof(u##bits) == sizeof_field(type, member));	\
 	btrfs_set_##bits(eb, s, offsetof(type, member), val);		\
 }									\
 static inline u##bits btrfs_token_##name(struct btrfs_map_token *token,	\
 					 const type *s)			\
 {									\
-	static_assert(sizeof(u##bits) == sizeof(((type *)0))->member);	\
+	static_assert(sizeof(u##bits) == sizeof_field(type, member));	\
 	return btrfs_get_token_##bits(token, s, offsetof(type, member));\
 }									\
 static inline void btrfs_set_token_##name(struct btrfs_map_token *token,\
 					  type *s, u##bits val)		\
 {									\
-	static_assert(sizeof(u##bits) == sizeof(((type *)0))->member);	\
+	static_assert(sizeof(u##bits) == sizeof_field(type, member));	\
 	btrfs_set_token_##bits(token, s, offsetof(type, member), val);	\
 }
 
@@ -111,17 +113,14 @@ static inline void btrfs_set_##name(type *s, u##bits val)		\
 static inline u64 btrfs_device_total_bytes(const struct extent_buffer *eb,
 					   struct btrfs_dev_item *s)
 {
-	static_assert(sizeof(u64) ==
-		      sizeof(((struct btrfs_dev_item *)0))->total_bytes);
-	return btrfs_get_64(eb, s, offsetof(struct btrfs_dev_item,
-					    total_bytes));
+	static_assert(sizeof(u64) == sizeof_field(struct btrfs_dev_item, total_bytes));
+	return btrfs_get_64(eb, s, offsetof(struct btrfs_dev_item, total_bytes));
 }
 static inline void btrfs_set_device_total_bytes(const struct extent_buffer *eb,
 						struct btrfs_dev_item *s,
 						u64 val)
 {
-	static_assert(sizeof(u64) ==
-		      sizeof(((struct btrfs_dev_item *)0))->total_bytes);
+	static_assert(sizeof(u64) == sizeof_field(struct btrfs_dev_item, total_bytes));
 	WARN_ON(!IS_ALIGNED(val, eb->fs_info->sectorsize));
 	btrfs_set_64(eb, s, offsetof(struct btrfs_dev_item, total_bytes), val);
 }

fs/btrfs/backref.c

@@ -3373,7 +3373,6 @@ int btrfs_backref_add_tree_node(struct btrfs_backref_cache *cache,
 				struct btrfs_key *node_key,
 				struct btrfs_backref_node *cur)
 {
-	struct btrfs_fs_info *fs_info = cache->fs_info;
 	struct btrfs_backref_edge *edge;
 	struct btrfs_backref_node *exist;
 	int ret;
@@ -3462,25 +3461,21 @@ int btrfs_backref_add_tree_node(struct btrfs_backref_cache *cache,
 			ret = handle_direct_tree_backref(cache, &key, cur);
 			if (ret < 0)
 				goto out;
-			continue;
-		} else if (unlikely(key.type == BTRFS_EXTENT_REF_V0_KEY)) {
-			ret = -EINVAL;
-			btrfs_print_v0_err(fs_info);
-			btrfs_handle_fs_error(fs_info, ret, NULL);
-			goto out;
-		} else if (key.type != BTRFS_TREE_BLOCK_REF_KEY) {
-			continue;
+		} else if (key.type == BTRFS_TREE_BLOCK_REF_KEY) {
+			/*
+			 * key.type == BTRFS_TREE_BLOCK_REF_KEY, inline ref
+			 * offset means the root objectid. We need to search
+			 * the tree to get its parent bytenr.
+			 */
+			ret = handle_indirect_tree_backref(cache, path, &key, node_key,
+							   cur);
+			if (ret < 0)
+				goto out;
 		}
-
 		/*
-		 * key.type == BTRFS_TREE_BLOCK_REF_KEY, inline ref offset
-		 * means the root objectid. We need to search the tree to get
-		 * its parent bytenr.
+		 * Unrecognized tree backref items (if it can pass tree-checker)
+		 * would be ignored.
 		 */
-		ret = handle_indirect_tree_backref(cache, path, &key, node_key,
-						   cur);
-		if (ret < 0)
-			goto out;
 	}
 	ret = 0;
 	cur->checked = 1;

fs/btrfs/block-group.c

@@ -504,13 +504,20 @@ static void fragment_free_space(struct btrfs_block_group *block_group)
 #endif
 
 /*
- * This is only called by btrfs_cache_block_group, since we could have freed
- * extents we need to check the pinned_extents for any extents that can't be
- * used yet since their free space will be released as soon as the transaction
- * commits.
+ * Add a free space range to the in memory free space cache of a block group.
+ * This checks if the range contains super block locations and any such
+ * locations are not added to the free space cache.
+ *
+ * @block_group:      The target block group.
+ * @start:            Start offset of the range.
+ * @end:              End offset of the range (exclusive).
+ * @total_added_ret:  Optional pointer to return the total amount of space
+ *                    added to the block group's free space cache.
+ *
+ * Returns 0 on success or < 0 on error.
  */
-int add_new_free_space(struct btrfs_block_group *block_group, u64 start, u64 end,
-		       u64 *total_added_ret)
+int btrfs_add_new_free_space(struct btrfs_block_group *block_group, u64 start,
+			     u64 end, u64 *total_added_ret)
 {
 	struct btrfs_fs_info *info = block_group->fs_info;
 	u64 extent_start, extent_end, size;
@@ -520,11 +527,10 @@ int add_new_free_space(struct btrfs_block_group *block_group, u64 start, u64 end
 		*total_added_ret = 0;
 
 	while (start < end) {
-		ret = find_first_extent_bit(&info->excluded_extents, start,
-					    &extent_start, &extent_end,
-					    EXTENT_DIRTY | EXTENT_UPTODATE,
-					    NULL);
-		if (ret)
+		if (!find_first_extent_bit(&info->excluded_extents, start,
+					   &extent_start, &extent_end,
+					   EXTENT_DIRTY | EXTENT_UPTODATE,
+					   NULL))
 			break;
 
 		if (extent_start <= start) {
@@ -799,8 +805,8 @@ static int load_extent_tree_free(struct btrfs_caching_control *caching_ctl)
 		    key.type == BTRFS_METADATA_ITEM_KEY) {
 			u64 space_added;
 
-			ret = add_new_free_space(block_group, last, key.objectid,
-						 &space_added);
+			ret = btrfs_add_new_free_space(block_group, last,
+						       key.objectid, &space_added);
 			if (ret)
 				goto out;
 			total_found += space_added;
@@ -821,14 +827,20 @@ static int load_extent_tree_free(struct btrfs_caching_control *caching_ctl)
 		path->slots[0]++;
 	}
 
-	ret = add_new_free_space(block_group, last,
-				 block_group->start + block_group->length,
-				 NULL);
+	ret = btrfs_add_new_free_space(block_group, last,
+				       block_group->start + block_group->length,
+				       NULL);
 out:
 	btrfs_free_path(path);
 	return ret;
 }
 
+static inline void btrfs_free_excluded_extents(const struct btrfs_block_group *bg)
+{
+	clear_extent_bits(&bg->fs_info->excluded_extents, bg->start,
+			  bg->start + bg->length - 1, EXTENT_UPTODATE);
+}
+
 static noinline void caching_thread(struct btrfs_work *work)
 {
 	struct btrfs_block_group *block_group;
@@ -2098,8 +2110,9 @@ static int exclude_super_stripes(struct btrfs_block_group *cache)
 	if (cache->start < BTRFS_SUPER_INFO_OFFSET) {
 		stripe_len = BTRFS_SUPER_INFO_OFFSET - cache->start;
 		cache->bytes_super += stripe_len;
-		ret = btrfs_add_excluded_extent(fs_info, cache->start,
-						stripe_len);
+		ret = set_extent_bit(&fs_info->excluded_extents, cache->start,
+				     cache->start + stripe_len - 1,
+				     EXTENT_UPTODATE, NULL);
 		if (ret)
 			return ret;
 	}
@@ -2125,8 +2138,9 @@ static int exclude_super_stripes(struct btrfs_block_group *cache)
 				cache->start + cache->length - logical[nr]);
 
 			cache->bytes_super += len;
-			ret = btrfs_add_excluded_extent(fs_info, logical[nr],
-							len);
+			ret = set_extent_bit(&fs_info->excluded_extents, logical[nr],
+					     logical[nr] + len - 1,
+					     EXTENT_UPTODATE, NULL);
 			if (ret) {
 				kfree(logical);
 				return ret;
@@ -2319,8 +2333,8 @@ static int read_one_block_group(struct btrfs_fs_info *info,
 		btrfs_free_excluded_extents(cache);
 	} else if (cache->used == 0) {
 		cache->cached = BTRFS_CACHE_FINISHED;
-		ret = add_new_free_space(cache, cache->start,
-					 cache->start + cache->length, NULL);
+		ret = btrfs_add_new_free_space(cache, cache->start,
+					       cache->start + cache->length, NULL);
 		btrfs_free_excluded_extents(cache);
 		if (ret)
 			goto error;
@@ -2767,7 +2781,7 @@ struct btrfs_block_group *btrfs_make_block_group(struct btrfs_trans_handle *tran
 		return ERR_PTR(ret);
 	}
 
-	ret = add_new_free_space(cache, chunk_offset, chunk_offset + size, NULL);
+	ret = btrfs_add_new_free_space(cache, chunk_offset, chunk_offset + size, NULL);
 	btrfs_free_excluded_extents(cache);
 	if (ret) {
 		btrfs_put_block_group(cache);
@@ -4075,7 +4089,7 @@ int btrfs_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags,
 
 	if (IS_ERR(ret_bg)) {
 		ret = PTR_ERR(ret_bg);
-	} else if (from_extent_allocation) {
+	} else if (from_extent_allocation && (flags & BTRFS_BLOCK_GROUP_DATA)) {
 		/*
 		 * New block group is likely to be used soon. Try to activate
 		 * it now. Failure is OK for now.
@@ -4273,6 +4287,17 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info)
 	struct btrfs_caching_control *caching_ctl;
 	struct rb_node *n;
 
+	if (btrfs_is_zoned(info)) {
+		if (info->active_meta_bg) {
+			btrfs_put_block_group(info->active_meta_bg);
+			info->active_meta_bg = NULL;
+		}
+		if (info->active_system_bg) {
+			btrfs_put_block_group(info->active_system_bg);
+			info->active_system_bg = NULL;
+		}
+	}
+
 	write_lock(&info->block_group_cache_lock);
 	while (!list_empty(&info->caching_block_groups)) {
 		caching_ctl = list_entry(info->caching_block_groups.next,

fs/btrfs/block-group.h

@@ -291,8 +291,8 @@ int btrfs_cache_block_group(struct btrfs_block_group *cache, bool wait);
 void btrfs_put_caching_control(struct btrfs_caching_control *ctl);
 struct btrfs_caching_control *btrfs_get_caching_control(
 		struct btrfs_block_group *cache);
-int add_new_free_space(struct btrfs_block_group *block_group,
-		       u64 start, u64 end, u64 *total_added_ret);
+int btrfs_add_new_free_space(struct btrfs_block_group *block_group,
+			     u64 start, u64 end, u64 *total_added_ret);
 struct btrfs_trans_handle *btrfs_start_trans_remove_block_group(
 				struct btrfs_fs_info *fs_info,
 				const u64 chunk_offset);

fs/btrfs/btrfs_inode.h

@@ -498,12 +498,8 @@ int btrfs_prealloc_file_range_trans(struct inode *inode,
 				    u64 start, u64 num_bytes, u64 min_size,
 				    loff_t actual_len, u64 *alloc_hint);
 int btrfs_run_delalloc_range(struct btrfs_inode *inode, struct page *locked_page,
-			     u64 start, u64 end, int *page_started,
-			     unsigned long *nr_written, struct writeback_control *wbc);
+			     u64 start, u64 end, struct writeback_control *wbc);
 int btrfs_writepage_cow_fixup(struct page *page);
-void btrfs_writepage_endio_finish_ordered(struct btrfs_inode *inode,
-					  struct page *page, u64 start,
-					  u64 end, bool uptodate);
 int btrfs_encoded_io_compression_from_extent(struct btrfs_fs_info *fs_info,
 					     int compress_type);
 int btrfs_encoded_read_regular_fill_pages(struct btrfs_inode *inode,

fs/btrfs/delayed-inode.c

@@ -1736,9 +1736,6 @@ int btrfs_readdir_delayed_dir_index(struct dir_context *ctx,
 	int over = 0;
 	unsigned char d_type;
 
-	if (list_empty(ins_list))
-		return 0;
-
 	/*
 	 * Changing the data of the delayed item is impossible. So
 	 * we needn't lock them. And we have held i_mutex of the

fs/btrfs/dev-replace.c

@@ -792,9 +792,9 @@ static int btrfs_set_target_alloc_state(struct btrfs_device *srcdev,
 
 	lockdep_assert_held(&srcdev->fs_info->chunk_mutex);
 
-	while (!find_first_extent_bit(&srcdev->alloc_state, start,
-				      &found_start, &found_end,
-				      CHUNK_ALLOCATED, &cached_state)) {
+	while (find_first_extent_bit(&srcdev->alloc_state, start,
+				     &found_start, &found_end,
+				     CHUNK_ALLOCATED, &cached_state)) {
 		ret = set_extent_bit(&tgtdev->alloc_state, found_start,
 				     found_end, CHUNK_ALLOCATED, NULL);
 		if (ret)