Merge tag 'for-6.8-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs fixes from David Sterba:

 - zoned mode fixes:
     - fix slowdown when writing large file sequentially by looking up
       block groups with enough space faster
     - locking fixes when activating a zone

 - new mount API fixes:
     - preserve mount options for a ro/rw mount of the same subvolume

 - scrub fixes:
     - fix use-after-free in case the chunk length is not aligned to
       64K, this does not happen normally but has been reported on
       images converted from ext4
     - similar alignment check was missing with raid-stripe-tree

 - subvolume deletion fixes:
     - prevent calling ioctl on already deleted subvolume
     - properly track flag tracking a deleted subvolume

 - in subpage mode, fix decompression of an inline extent (zlib, lzo,
   zstd)

 - fix crash when starting writeback on a folio, after integration with
   recent MM changes this needs to be started conditionally

 - reject unknown flags in defrag ioctl

 - error handling, API fixes, minor warning fixes

* tag 'for-6.8-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
  btrfs: scrub: limit RST scrub to chunk boundary
  btrfs: scrub: avoid use-after-free when chunk length is not 64K aligned
  btrfs: don't unconditionally call folio_start_writeback in subpage
  btrfs: use the original mount's mount options for the legacy reconfigure
  btrfs: don't warn if discard range is not aligned to sector
  btrfs: tree-checker: fix inline ref size in error messages
  btrfs: zstd: fix and simplify the inline extent decompression
  btrfs: lzo: fix and simplify the inline extent decompression
  btrfs: zlib: fix and simplify the inline extent decompression
  btrfs: defrag: reject unknown flags of btrfs_ioctl_defrag_range_args
  btrfs: avoid copying BTRFS_ROOT_SUBVOL_DEAD flag to snapshot of subvolume being deleted
  btrfs: don't abort filesystem when attempting to snapshot deleted subvolume
  btrfs: zoned: fix lock ordering in btrfs_zone_activate()
  btrfs: fix unbalanced unlock of mapping_tree_lock
  btrfs: ref-verify: free ref cache before clearing mount opt
  btrfs: fix kvcalloc() arguments order in btrfs_ioctl_send()
  btrfs: zoned: optimize hint byte for zoned allocator
  btrfs: zoned: factor out prepare_allocation_zoned()

Author: torvalds

fs/btrfs/compression.c

@@ -141,16 +141,16 @@ static int compression_decompress_bio(struct list_head *ws,
 }
 
 static int compression_decompress(int type, struct list_head *ws,
-               const u8 *data_in, struct page *dest_page,
-               unsigned long start_byte, size_t srclen, size_t destlen)
+		const u8 *data_in, struct page *dest_page,
+		unsigned long dest_pgoff, size_t srclen, size_t destlen)
 {
 	switch (type) {
 	case BTRFS_COMPRESS_ZLIB: return zlib_decompress(ws, data_in, dest_page,
-						start_byte, srclen, destlen);
+						dest_pgoff, srclen, destlen);
 	case BTRFS_COMPRESS_LZO:  return lzo_decompress(ws, data_in, dest_page,
-						start_byte, srclen, destlen);
+						dest_pgoff, srclen, destlen);
 	case BTRFS_COMPRESS_ZSTD: return zstd_decompress(ws, data_in, dest_page,
-						start_byte, srclen, destlen);
+						dest_pgoff, srclen, destlen);
 	case BTRFS_COMPRESS_NONE:
 	default:
 		/*
@@ -1037,14 +1037,23 @@ static int btrfs_decompress_bio(struct compressed_bio *cb)
  * start_byte tells us the offset into the compressed data we're interested in
  */
 int btrfs_decompress(int type, const u8 *data_in, struct page *dest_page,
-		     unsigned long start_byte, size_t srclen, size_t destlen)
+		     unsigned long dest_pgoff, size_t srclen, size_t destlen)
 {
+	struct btrfs_fs_info *fs_info = btrfs_sb(dest_page->mapping->host->i_sb);
 	struct list_head *workspace;
+	const u32 sectorsize = fs_info->sectorsize;
 	int ret;
 
+	/*
+	 * The full destination page range should not exceed the page size.
+	 * And the @destlen should not exceed sectorsize, as this is only called for
+	 * inline file extents, which should not exceed sectorsize.
+	 */
+	ASSERT(dest_pgoff + destlen <= PAGE_SIZE && destlen <= sectorsize);
+
 	workspace = get_workspace(type, 0);
 	ret = compression_decompress(type, workspace, data_in, dest_page,
-				     start_byte, srclen, destlen);
+				     dest_pgoff, srclen, destlen);
 	put_workspace(type, workspace);
 
 	return ret;

fs/btrfs/compression.h

@@ -148,7 +148,7 @@ int zlib_compress_pages(struct list_head *ws, struct address_space *mapping,
 		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,
-		struct page *dest_page, unsigned long start_byte, size_t srclen,
+		struct page *dest_page, unsigned long dest_pgoff, size_t srclen,
 		size_t destlen);
 struct list_head *zlib_alloc_workspace(unsigned int level);
 void zlib_free_workspace(struct list_head *ws);
@@ -159,7 +159,7 @@ int lzo_compress_pages(struct list_head *ws, struct address_space *mapping,
 		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,
-		struct page *dest_page, unsigned long start_byte, size_t srclen,
+		struct page *dest_page, unsigned long dest_pgoff, size_t srclen,
 		size_t destlen);
 struct list_head *lzo_alloc_workspace(unsigned int level);
 void lzo_free_workspace(struct list_head *ws);
@@ -169,7 +169,7 @@ int zstd_compress_pages(struct list_head *ws, struct address_space *mapping,
 		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,
-		struct page *dest_page, unsigned long start_byte, size_t srclen,
+		struct page *dest_page, unsigned long dest_pgoff, size_t srclen,
 		size_t destlen);
 void zstd_init_workspace_manager(void);
 void zstd_cleanup_workspace_manager(void);

fs/btrfs/extent-tree.c

@@ -1260,7 +1260,8 @@ static int btrfs_issue_discard(struct block_device *bdev, u64 start, u64 len,
 	u64 bytes_left, end;
 	u64 aligned_start = ALIGN(start, 1 << SECTOR_SHIFT);
 
-	if (WARN_ON(start != aligned_start)) {
+	/* Adjust the range to be aligned to 512B sectors if necessary. */
+	if (start != aligned_start) {
 		len -= aligned_start - start;
 		len = round_down(len, 1 << SECTOR_SHIFT);
 		start = aligned_start;
@@ -4298,6 +4299,42 @@ static int prepare_allocation_clustered(struct btrfs_fs_info *fs_info,
 	return 0;
 }
 
+static int prepare_allocation_zoned(struct btrfs_fs_info *fs_info,
+				    struct find_free_extent_ctl *ffe_ctl)
+{
+	if (ffe_ctl->for_treelog) {
+		spin_lock(&fs_info->treelog_bg_lock);
+		if (fs_info->treelog_bg)
+			ffe_ctl->hint_byte = fs_info->treelog_bg;
+		spin_unlock(&fs_info->treelog_bg_lock);
+	} else if (ffe_ctl->for_data_reloc) {
+		spin_lock(&fs_info->relocation_bg_lock);
+		if (fs_info->data_reloc_bg)
+			ffe_ctl->hint_byte = fs_info->data_reloc_bg;
+		spin_unlock(&fs_info->relocation_bg_lock);
+	} else if (ffe_ctl->flags & BTRFS_BLOCK_GROUP_DATA) {
+		struct btrfs_block_group *block_group;
+
+		spin_lock(&fs_info->zone_active_bgs_lock);
+		list_for_each_entry(block_group, &fs_info->zone_active_bgs, active_bg_list) {
+			/*
+			 * No lock is OK here because avail is monotinically
+			 * decreasing, and this is just a hint.
+			 */
+			u64 avail = block_group->zone_capacity - block_group->alloc_offset;
+
+			if (block_group_bits(block_group, ffe_ctl->flags) &&
+			    avail >= ffe_ctl->num_bytes) {
+				ffe_ctl->hint_byte = block_group->start;
+				break;
+			}
+		}
+		spin_unlock(&fs_info->zone_active_bgs_lock);
+	}
+
+	return 0;
+}
+
 static int prepare_allocation(struct btrfs_fs_info *fs_info,
 			      struct find_free_extent_ctl *ffe_ctl,
 			      struct btrfs_space_info *space_info,
@@ -4308,19 +4345,7 @@ static int prepare_allocation(struct btrfs_fs_info *fs_info,
 		return prepare_allocation_clustered(fs_info, ffe_ctl,
 						    space_info, ins);
 	case BTRFS_EXTENT_ALLOC_ZONED:
-		if (ffe_ctl->for_treelog) {
-			spin_lock(&fs_info->treelog_bg_lock);
-			if (fs_info->treelog_bg)
-				ffe_ctl->hint_byte = fs_info->treelog_bg;
-			spin_unlock(&fs_info->treelog_bg_lock);
-		}
-		if (ffe_ctl->for_data_reloc) {
-			spin_lock(&fs_info->relocation_bg_lock);
-			if (fs_info->data_reloc_bg)
-				ffe_ctl->hint_byte = fs_info->data_reloc_bg;
-			spin_unlock(&fs_info->relocation_bg_lock);
-		}
-		return 0;
+		return prepare_allocation_zoned(fs_info, ffe_ctl);
 	default:
 		BUG();
 	}

fs/btrfs/inode.c

@@ -4458,6 +4458,8 @@ int btrfs_delete_subvolume(struct btrfs_inode *dir, struct dentry *dentry)
 	u64 root_flags;
 	int ret;
 
+	down_write(&fs_info->subvol_sem);
+
 	/*
 	 * Don't allow to delete a subvolume with send in progress. This is
 	 * inside the inode lock so the error handling that has to drop the bit
@@ -4469,25 +4471,25 @@ int btrfs_delete_subvolume(struct btrfs_inode *dir, struct dentry *dentry)
 		btrfs_warn(fs_info,
 			   "attempt to delete subvolume %llu during send",
 			   dest->root_key.objectid);
-		return -EPERM;
+		ret = -EPERM;
+		goto out_up_write;
 	}
 	if (atomic_read(&dest->nr_swapfiles)) {
 		spin_unlock(&dest->root_item_lock);
 		btrfs_warn(fs_info,
 			   "attempt to delete subvolume %llu with active swapfile",
 			   root->root_key.objectid);
-		return -EPERM;
+		ret = -EPERM;
+		goto out_up_write;
 	}
 	root_flags = btrfs_root_flags(&dest->root_item);
 	btrfs_set_root_flags(&dest->root_item,
 			     root_flags | BTRFS_ROOT_SUBVOL_DEAD);
 	spin_unlock(&dest->root_item_lock);
 
-	down_write(&fs_info->subvol_sem);
-
 	ret = may_destroy_subvol(dest);
 	if (ret)
-		goto out_up_write;
+		goto out_undead;
 
 	btrfs_init_block_rsv(&block_rsv, BTRFS_BLOCK_RSV_TEMP);
 	/*
@@ -4497,7 +4499,7 @@ int btrfs_delete_subvolume(struct btrfs_inode *dir, struct dentry *dentry)
 	 */
 	ret = btrfs_subvolume_reserve_metadata(root, &block_rsv, 5, true);
 	if (ret)
-		goto out_up_write;
+		goto out_undead;
 
 	trans = btrfs_start_transaction(root, 0);
 	if (IS_ERR(trans)) {
@@ -4563,15 +4565,17 @@ int btrfs_delete_subvolume(struct btrfs_inode *dir, struct dentry *dentry)
 	inode->i_flags |= S_DEAD;
 out_release:
 	btrfs_subvolume_release_metadata(root, &block_rsv);
-out_up_write:
-	up_write(&fs_info->subvol_sem);
+out_undead:
 	if (ret) {
 		spin_lock(&dest->root_item_lock);
 		root_flags = btrfs_root_flags(&dest->root_item);
 		btrfs_set_root_flags(&dest->root_item,
 				root_flags & ~BTRFS_ROOT_SUBVOL_DEAD);
 		spin_unlock(&dest->root_item_lock);
-	} else {
+	}
+out_up_write:
+	up_write(&fs_info->subvol_sem);
+	if (!ret) {
 		d_invalidate(dentry);
 		btrfs_prune_dentries(dest);
 		ASSERT(dest->send_in_progress == 0);

fs/btrfs/ioctl.c

@@ -790,6 +790,9 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
 		return -EOPNOTSUPP;
 	}
 
+	if (btrfs_root_refs(&root->root_item) == 0)
+		return -ENOENT;
+
 	if (!test_bit(BTRFS_ROOT_SHAREABLE, &root->state))
 		return -EINVAL;
 
@@ -2608,6 +2611,10 @@ static int btrfs_ioctl_defrag(struct file *file, void __user *argp)
 				ret = -EFAULT;
 				goto out;
 			}
+			if (range.flags & ~BTRFS_DEFRAG_RANGE_FLAGS_SUPP) {
+				ret = -EOPNOTSUPP;
+				goto out;
+			}
 			/* compression requires us to start the IO */
 			if ((range.flags & BTRFS_DEFRAG_RANGE_COMPRESS)) {
 				range.flags |= BTRFS_DEFRAG_RANGE_START_IO;

fs/btrfs/lzo.c

@@ -425,16 +425,16 @@ int lzo_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
 }
 
 int lzo_decompress(struct list_head *ws, const u8 *data_in,
-		struct page *dest_page, unsigned long start_byte, size_t srclen,
+		struct page *dest_page, unsigned long dest_pgoff, size_t srclen,
 		size_t destlen)
 {
 	struct workspace *workspace = list_entry(ws, struct workspace, list);
+	struct btrfs_fs_info *fs_info = btrfs_sb(dest_page->mapping->host->i_sb);
+	const u32 sectorsize = fs_info->sectorsize;
 	size_t in_len;
 	size_t out_len;
 	size_t max_segment_len = WORKSPACE_BUF_LENGTH;
 	int ret = 0;
-	char *kaddr;
-	unsigned long bytes;
 
 	if (srclen < LZO_LEN || srclen > max_segment_len + LZO_LEN * 2)
 		return -EUCLEAN;
@@ -451,37 +451,21 @@ int lzo_decompress(struct list_head *ws, const u8 *data_in,
 	}
 	data_in += LZO_LEN;
 
-	out_len = PAGE_SIZE;
+	out_len = sectorsize;
 	ret = lzo1x_decompress_safe(data_in, in_len, workspace->buf, &out_len);
 	if (ret != LZO_E_OK) {
 		pr_warn("BTRFS: decompress failed!\n");
 		ret = -EIO;
 		goto out;
 	}
 
-	if (out_len < start_byte) {
+	ASSERT(out_len <= sectorsize);
+	memcpy_to_page(dest_page, dest_pgoff, workspace->buf, out_len);
+	/* Early end, considered as an error. */
+	if (unlikely(out_len < destlen)) {
 		ret = -EIO;
-		goto out;
+		memzero_page(dest_page, dest_pgoff + out_len, destlen - out_len);
 	}
-
-	/*
-	 * the caller is already checking against PAGE_SIZE, but lets
-	 * move this check closer to the memcpy/memset
-	 */
-	destlen = min_t(unsigned long, destlen, PAGE_SIZE);
-	bytes = min_t(unsigned long, destlen, out_len - start_byte);
-
-	kaddr = kmap_local_page(dest_page);
-	memcpy(kaddr, workspace->buf + start_byte, bytes);
-
-	/*
-	 * btrfs_getblock is doing a zero on the tail of the page too,
-	 * but this will cover anything missing from the decompressed
-	 * data.
-	 */
-	if (bytes < destlen)
-		memset(kaddr+bytes, 0, destlen-bytes);
-	kunmap_local(kaddr);
 out:
 	return ret;
 }

fs/btrfs/ref-verify.c

@@ -889,8 +889,10 @@ int btrfs_ref_tree_mod(struct btrfs_fs_info *fs_info,
 out_unlock:
 	spin_unlock(&fs_info->ref_verify_lock);
 out:
-	if (ret)
+	if (ret) {
+		btrfs_free_ref_cache(fs_info);
 		btrfs_clear_opt(fs_info->mount_opt, REF_VERIFY);
+	}
 	return ret;
 }
 
@@ -1021,8 +1023,8 @@ int btrfs_build_ref_tree(struct btrfs_fs_info *fs_info)
 		}
 	}
 	if (ret) {
-		btrfs_clear_opt(fs_info->mount_opt, REF_VERIFY);
 		btrfs_free_ref_cache(fs_info);
+		btrfs_clear_opt(fs_info->mount_opt, REF_VERIFY);
 	}
 	btrfs_free_path(path);
 	return ret;