btrfs: zlib: fix and simplify the inline extent decompression

[BUG]

If we have a filesystem with 4k sectorsize, and an inlined compressed
extent created like this:

	item 4 key (257 INODE_ITEM 0) itemoff 15863 itemsize 160
		generation 8 transid 8 size 4096 nbytes 4096
		block group 0 mode 100600 links 1 uid 0 gid 0 rdev 0
		sequence 1 flags 0x0(none)
	item 5 key (257 INODE_REF 256) itemoff 15839 itemsize 24
		index 2 namelen 14 name: source_inlined
	item 6 key (257 EXTENT_DATA 0) itemoff 15770 itemsize 69
		generation 8 type 0 (inline)
		inline extent data size 48 ram_bytes 4096 compression 1 (zlib)

Which has an inline compressed extent at file offset 0, and its
decompressed size is 4K, allowing us to reflink that 4K range to another
location (which will not be compressed).

If we do such reflink on a subpage system, it would fail like this:

  # xfs_io -f -c "reflink $mnt/source_inlined 0 60k 4k" $mnt/dest
  XFS_IOC_CLONE_RANGE: Input/output error

[CAUSE]
In zlib_decompress(), we didn't treat @start_byte as just a page offset,
but also use it as an indicator on whether we should switch our output
buffer.

In reality, for subpage cases, although @start_byte can be non-zero,
we should never switch input/output buffer, since the whole input/output
buffer should never exceed one sector.

Note: The above assumption is only not true if we're going to support
multi-page sectorsize.

Thus the current code using @start_byte as a condition to switch
input/output buffer or finish the decompression is completely incorrect.

[FIX]
The fix involves several modifications:

- Rename @start_byte to @dest_pgoff to properly express its meaning

- Add an extra ASSERT() inside btrfs_decompress() to make sure the
  input/output size never exceeds one sector.

- Use Z_FINISH flag to make sure the decompression happens in one go

- Remove the loop needed to switch input/output buffers

- Use correct destination offset inside the destination page

- Consider early end as an error

After the fix, even on 64K page sized aarch64, above reflink now
works as expected:

  # xfs_io -f -c "reflink $mnt/source_inlined 0 60k 4k" $mnt/dest
  linked 4096/4096 bytes at offset 61440

And resulted a correct file layout:

	item 9 key (258 INODE_ITEM 0) itemoff 15542 itemsize 160
		generation 10 transid 10 size 65536 nbytes 4096
		block group 0 mode 100600 links 1 uid 0 gid 0 rdev 0
		sequence 1 flags 0x0(none)
	item 10 key (258 INODE_REF 256) itemoff 15528 itemsize 14
		index 3 namelen 4 name: dest
	item 11 key (258 XATTR_ITEM 3817753667) itemoff 15445 itemsize 83
		location key (0 UNKNOWN.0 0) type XATTR
		transid 10 data_len 37 name_len 16
		name: security.selinux
		data unconfined_u:object_r:unlabeled_t:s0
	item 12 key (258 EXTENT_DATA 61440) itemoff 15392 itemsize 53
		generation 10 type 1 (regular)
		extent data disk byte 13631488 nr 4096
		extent data offset 0 nr 4096 ram 4096
		extent compression 0 (none)

Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>

3 files changed, 36 insertions, 62 deletions

diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index 193168214eeb..68345f73d429 100644
--- a/fs/btrfs/compression.c
+++ b/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;
diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h
index 93cc92974dee..2b4dfb1b010c 100644
--- a/fs/btrfs/compression.h
+++ b/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);
diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c
index 36cf1f0e338e..8da66ea699e8 100644
--- a/fs/btrfs/zlib.c
+++ b/fs/btrfs/zlib.c
@@ -354,18 +354,13 @@ done:
 }
 
 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 workspace *workspace = list_entry(ws, struct workspace, list);
 	int ret = 0;
 	int wbits = MAX_WBITS;
-	unsigned long bytes_left;
-	unsigned long total_out = 0;
-	unsigned long pg_offset = 0;
-
-	destlen = min_t(unsigned long, destlen, PAGE_SIZE);
-	bytes_left = destlen;
+	unsigned long to_copy;
 
 	workspace->strm.next_in = data_in;
 	workspace->strm.avail_in = srclen;
@@ -390,60 +385,30 @@ int zlib_decompress(struct list_head *ws, const u8 *data_in,
 		return -EIO;
 	}
 
-	while (bytes_left > 0) {
-		unsigned long buf_start;
-		unsigned long buf_offset;
-		unsigned long bytes;
-
-		ret = zlib_inflate(&workspace->strm, Z_NO_FLUSH);
-		if (ret != Z_OK && ret != Z_STREAM_END)
-			break;
-
-		buf_start = total_out;
-		total_out = workspace->strm.total_out;
-
-		if (total_out == buf_start) {
-			ret = -EIO;
-			break;
-		}
-
-		if (total_out <= start_byte)
-			goto next;
-
-		if (total_out > start_byte && buf_start < start_byte)
-			buf_offset = start_byte - buf_start;
-		else
-			buf_offset = 0;
-
-		bytes = min(PAGE_SIZE - pg_offset,
-			    PAGE_SIZE - (buf_offset % PAGE_SIZE));
-		bytes = min(bytes, bytes_left);
+	/*
+	 * Everything (in/out buf) should be at most one sector, there should
+	 * be no need to switch any input/output buffer.
+	 */
+	ret = zlib_inflate(&workspace->strm, Z_FINISH);
+	to_copy = min(workspace->strm.total_out, destlen);
+	if (ret != Z_STREAM_END)
+		goto out;
 
-		memcpy_to_page(dest_page, pg_offset,
-			       workspace->buf + buf_offset, bytes);
+	memcpy_to_page(dest_page, dest_pgoff, workspace->buf, to_copy);
 
-		pg_offset += bytes;
-		bytes_left -= bytes;
-next:
-		workspace->strm.next_out = workspace->buf;
-		workspace->strm.avail_out = workspace->buf_size;
-	}
-
-	if (ret != Z_STREAM_END && bytes_left != 0)
+out:
+	if (unlikely(to_copy != destlen)) {
+		pr_warn_ratelimited("BTRFS: infalte failed, decompressed=%lu expected=%zu\n",
+					to_copy, destlen);
 		ret = -EIO;
-	else
+	} else {
 		ret = 0;
+	}
 
 	zlib_inflateEnd(&workspace->strm);
 
-	/*
-	 * this should only happen if zlib returned fewer bytes than we
-	 * expected.  btrfs_get_block is responsible for zeroing from the
-	 * end of the inline extent (destlen) to the end of the page
-	 */
-	if (pg_offset < destlen) {
-		memzero_page(dest_page, pg_offset, destlen - pg_offset);
-	}
+	if (unlikely(to_copy < destlen))
+		memzero_page(dest_page, dest_pgoff + to_copy, destlen - to_copy);
 	return ret;
 }