for-6.12-rc4-tag

-----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCgAdFiEE8rQSAMVO+zA4DBdWxWXV+ddtWDsFAmcZGqsACgkQxWXV+ddt
 WDsZTg//dSLAAswT3dTAvWDt7rGxPhJC1V+gnzWdj/0Q3CUimNaw7zHp1QHtJDFT
 S+3TVvJJ2JDvOnbi3u24s/bL5YdkWcvIyy87oVE4trJMbQPc/E45pkYFqF3TRQAH
 wEYAVEnO9f9WUY+ekxX2XBzhmKp3xol93j9BBHDXOF9kHsDC5lI0D5YVYEhRY8Qu
 D4GcqAhqUj5Hj6I6ppiqO47NCJBNzw1Se9QsgruPpmItRbB0/LYJFhUfevwosTKg
 xVpkRVntFqQjkIdIdBfBv/ZGWfxJyM7K4M49QwLUqUQfxugu7BiGYuEjkBkiy07a
 pZDEOF9s8wUZsxvRVohqKlhL0zHBF+/pAANowYuhKNW1sqKt4GVCdN3V34AbH8ST
 JIbPvC2g1tUzIc2wckE8GO/NnsNR4r3k6iPB53MdCHrIo3jnENOeb9wF0GiVDb6s
 OrhCa3ph2ps80YC1aCnc4Jr/yV2ONebSivnqvHCIUQEZfpjtAc07atm0i946/7nx
 eiBE+9zSVJZB0LoooIVz2I3HX3lRnm3Wwi4nj8U/sNL/IbGaHNCurIETR23NivYP
 yWVql2njwE+yMc8q9YZXs4MBdKsSGP6eGJW3ZwKi6ru2PJdf5eIib+ffvR4bLqXD
 UUDfMyC1esGsQB24sc8wppk97wmmMrdqQUj9WnmNlTP8FUFggvQ=
 =sYxX
 -----END PGP SIGNATURE-----

Merge tag 'for-6.12-rc4-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs fixes from David Sterba:

 - mount option fixes:
     - fix handling of compression mount options on remount
     - reject rw remount in case there are options that don't work
       in read-write mode (like rescue options)

 - fix zone accounting of unusable space

 - fix in-memory corruption when merging extent maps

 - fix delalloc range locking for sector < page

 - use more convenient default value of drop subtree threshold, clean
   more subvolumes without the fallback to marking quotas inconsistent

 - fix smatch warning about incorrect value passed to ERR_PTR

* tag 'for-6.12-rc4-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
  btrfs: fix passing 0 to ERR_PTR in btrfs_search_dir_index_item()
  btrfs: reject ro->rw reconfiguration if there are hard ro requirements
  btrfs: fix read corruption due to race with extent map merging
  btrfs: fix the delalloc range locking if sector size < page size
  btrfs: qgroup: set a more sane default value for subtree drop threshold
  btrfs: clear force-compress on remount when compress mount option is given
  btrfs: zoned: fix zone unusable accounting for freed reserved extent

fs/btrfs/block-group.c

@@ -3819,6 +3819,8 @@ void btrfs_free_reserved_bytes(struct btrfs_block_group *cache,
 	spin_lock(&cache->lock);
 	if (cache->ro)
 		space_info->bytes_readonly += num_bytes;
+	else if (btrfs_is_zoned(cache->fs_info))
+		space_info->bytes_zone_unusable += num_bytes;
 	cache->reserved -= num_bytes;
 	space_info->bytes_reserved -= num_bytes;
 	space_info->max_extent_size = 0;

fs/btrfs/dir-item.c

@@ -347,8 +347,8 @@ btrfs_search_dir_index_item(struct btrfs_root *root, struct btrfs_path *path,
 			return di;
 	}
 	/* Adjust return code if the key was not found in the next leaf. */
-	if (ret > 0)
-		ret = 0;
+	if (ret >= 0)
+		ret = -ENOENT;
 
 	return ERR_PTR(ret);
 }

fs/btrfs/disk-io.c

@@ -1959,7 +1959,7 @@ static void btrfs_init_qgroup(struct btrfs_fs_info *fs_info)
 	fs_info->qgroup_seq = 1;
 	fs_info->qgroup_ulist = NULL;
 	fs_info->qgroup_rescan_running = false;
-	fs_info->qgroup_drop_subtree_thres = BTRFS_MAX_LEVEL;
+	fs_info->qgroup_drop_subtree_thres = BTRFS_QGROUP_DROP_SUBTREE_THRES_DEFAULT;
 	mutex_init(&fs_info->qgroup_rescan_lock);
 }
 

fs/btrfs/extent_io.c

@@ -262,22 +262,23 @@ static noinline int lock_delalloc_folios(struct inode *inode,
 
 		for (i = 0; i < found_folios; i++) {
 			struct folio *folio = fbatch.folios[i];
-			u32 len = end + 1 - start;
+			u64 range_start;
+			u32 range_len;
 
 			if (folio == locked_folio)
 				continue;
 
-			if (btrfs_folio_start_writer_lock(fs_info, folio, start,
-							  len))
-				goto out;
-
+			folio_lock(folio);
 			if (!folio_test_dirty(folio) || folio->mapping != mapping) {
-				btrfs_folio_end_writer_lock(fs_info, folio, start,
-							    len);
+				folio_unlock(folio);
 				goto out;
 			}
+			range_start = max_t(u64, folio_pos(folio), start);
+			range_len = min_t(u64, folio_pos(folio) + folio_size(folio),
+					  end + 1) - range_start;
+			btrfs_folio_set_writer_lock(fs_info, folio, range_start, range_len);
 
-			processed_end = folio_pos(folio) + folio_size(folio) - 1;
+			processed_end = range_start + range_len - 1;
 		}
 		folio_batch_release(&fbatch);
 		cond_resched();

fs/btrfs/extent_map.c

@@ -243,13 +243,19 @@ static bool mergeable_maps(const struct extent_map *prev, const struct extent_ma
 /*
  * Handle the on-disk data extents merge for @prev and @next.
  *
+ * @prev:    left extent to merge
+ * @next:    right extent to merge
+ * @merged:  the extent we will not discard after the merge; updated with new values
+ *
+ * After this, one of the two extents is the new merged extent and the other is
+ * removed from the tree and likely freed. Note that @merged is one of @prev/@next
+ * so there is const/non-const aliasing occurring here.
+ *
  * Only touches disk_bytenr/disk_num_bytes/offset/ram_bytes.
  * For now only uncompressed regular extent can be merged.
- *
- * @prev and @next will be both updated to point to the new merged range.
- * Thus one of them should be removed by the caller.
  */
-static void merge_ondisk_extents(struct extent_map *prev, struct extent_map *next)
+static void merge_ondisk_extents(const struct extent_map *prev, const struct extent_map *next,
+				 struct extent_map *merged)
 {
 	u64 new_disk_bytenr;
 	u64 new_disk_num_bytes;
@@ -284,15 +290,10 @@ static void merge_ondisk_extents(struct extent_map *prev, struct extent_map *nex
 			     new_disk_bytenr;
 	new_offset = prev->disk_bytenr + prev->offset - new_disk_bytenr;
 
-	prev->disk_bytenr = new_disk_bytenr;
-	prev->disk_num_bytes = new_disk_num_bytes;
-	prev->ram_bytes = new_disk_num_bytes;
-	prev->offset = new_offset;
-
-	next->disk_bytenr = new_disk_bytenr;
-	next->disk_num_bytes = new_disk_num_bytes;
-	next->ram_bytes = new_disk_num_bytes;
-	next->offset = new_offset;
+	merged->disk_bytenr = new_disk_bytenr;
+	merged->disk_num_bytes = new_disk_num_bytes;
+	merged->ram_bytes = new_disk_num_bytes;
+	merged->offset = new_offset;
 }
 
 static void dump_extent_map(struct btrfs_fs_info *fs_info, const char *prefix,
@@ -361,7 +362,7 @@ static void try_merge_map(struct btrfs_inode *inode, struct extent_map *em)
 			em->generation = max(em->generation, merge->generation);
 
 			if (em->disk_bytenr < EXTENT_MAP_LAST_BYTE)
-				merge_ondisk_extents(merge, em);
+				merge_ondisk_extents(merge, em, em);
 			em->flags |= EXTENT_FLAG_MERGED;
 
 			validate_extent_map(fs_info, em);
@@ -378,7 +379,7 @@ static void try_merge_map(struct btrfs_inode *inode, struct extent_map *em)
 	if (rb && can_merge_extent_map(merge) && mergeable_maps(em, merge)) {
 		em->len += merge->len;
 		if (em->disk_bytenr < EXTENT_MAP_LAST_BYTE)
-			merge_ondisk_extents(em, merge);
+			merge_ondisk_extents(em, merge, em);
 		validate_extent_map(fs_info, em);
 		rb_erase(&merge->rb_node, &tree->root);
 		RB_CLEAR_NODE(&merge->rb_node);

fs/btrfs/inode.c

@@ -4368,11 +4368,8 @@ static int btrfs_unlink_subvol(struct btrfs_trans_handle *trans,
 	 */
 	if (btrfs_ino(inode) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID) {
 		di = btrfs_search_dir_index_item(root, path, dir_ino, &fname.disk_name);
-		if (IS_ERR_OR_NULL(di)) {
-			if (!di)
-				ret = -ENOENT;
-			else
-				ret = PTR_ERR(di);
+		if (IS_ERR(di)) {
+			ret = PTR_ERR(di);
 			btrfs_abort_transaction(trans, ret);
 			goto out;
 		}

fs/btrfs/qgroup.c

@@ -1407,7 +1407,7 @@ int btrfs_quota_disable(struct btrfs_fs_info *fs_info)
 	fs_info->quota_root = NULL;
 	fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_ON;
 	fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_SIMPLE_MODE;
-	fs_info->qgroup_drop_subtree_thres = BTRFS_MAX_LEVEL;
+	fs_info->qgroup_drop_subtree_thres = BTRFS_QGROUP_DROP_SUBTREE_THRES_DEFAULT;
 	spin_unlock(&fs_info->qgroup_lock);
 
 	btrfs_free_qgroup_config(fs_info);

fs/btrfs/qgroup.h

@@ -121,6 +121,8 @@ struct btrfs_inode;
 #define BTRFS_QGROUP_RUNTIME_FLAG_CANCEL_RESCAN		(1ULL << 63)
 #define BTRFS_QGROUP_RUNTIME_FLAG_NO_ACCOUNTING		(1ULL << 62)
 
+#define BTRFS_QGROUP_DROP_SUBTREE_THRES_DEFAULT		(3)
+
 /*
  * Record a dirty extent, and info qgroup to update quota on it
  */

fs/btrfs/super.c

@@ -340,6 +340,15 @@ static int btrfs_parse_param(struct fs_context *fc, struct fs_parameter *param)
 		fallthrough;
 	case Opt_compress:
 	case Opt_compress_type:
+		/*
+		 * Provide the same semantics as older kernels that don't use fs
+		 * context, specifying the "compress" option clears
+		 * "force-compress" without the need to pass
+		 * "compress-force=[no|none]" before specifying "compress".
+		 */
+		if (opt != Opt_compress_force && opt != Opt_compress_force_type)
+			btrfs_clear_opt(ctx->mount_opt, FORCE_COMPRESS);
+
 		if (opt == Opt_compress || opt == Opt_compress_force) {
 			ctx->compress_type = BTRFS_COMPRESS_ZLIB;
 			ctx->compress_level = BTRFS_ZLIB_DEFAULT_LEVEL;
@@ -1498,8 +1507,7 @@ static int btrfs_reconfigure(struct fs_context *fc)
 	sync_filesystem(sb);
 	set_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state);
 
-	if (!mount_reconfigure &&
-	    !btrfs_check_options(fs_info, &ctx->mount_opt, fc->sb_flags))
+	if (!btrfs_check_options(fs_info, &ctx->mount_opt, fc->sb_flags))
 		return -EINVAL;
 
 	ret = btrfs_check_features(fs_info, !(fc->sb_flags & SB_RDONLY));