git/list[1] front-page[2] threads[3] people[4] search[5] about
 

[PATCH 1/2] archive: use size_t for the size of archive entries

From
Elia Pinto <gitter.spiros@gmail.com>
Date
Nov 1, 2026, 09:19 UTC
Message-ID
<bfd638278f13b1ca127b723e6af738784fc6a429.1793524457.git.gitter.spiros@gmail.com>
In-Reply-To
<cover.1793524457.git.gitter.spiros@gmail.com>

The archive entry callback and format implementations use "unsigned long" for the entry size, while blobs above core.bigFileThreshold arrive as size_t.

On platforms where "long" is 32 bits but size_t is 64 bits, such as 64-bit Windows, streaming a file of 4GiB or more causes silent corruption: for tar, the truncated size goes into the ustar header while stream_blocked() writes the entire blob, corrupting the archive; for zip, write_zip_entry() overflows compressed_size, producing incorrect headers and a corrupted archive.

This was verified using a 16-bit simulation, where tar extracted truncated data and Python's zipfile rejected the output due to bad magic numbers or CRC-32 errors.

Use size_t in the callback, tar writer, and zip writer functions, allowing the existing zip64 helpers to handle large files correctly.

Triggering this requires processing a file of 4GiB or more on a platform where "long" is 32 bits but size_t is 64 bits, so no test is added.

Signed-off-by: Elia Pinto <gitter.spiros@gmail.com>
---
 archive-tar.c | 10 +++++-----
 archive-zip.c | 16 ++++++++--------
 archive.h     |  2 +-
 3 files changed, 14 insertions(+), 14 deletions(-)
diff --git a/archive-tar.c b/archive-tar.c
index a1c66024d4..31ab704886 100644
--- a/archive-tar.c
+++ b/archive-tar.c
@@ -66,7 +66,7 @@ static void write_if_needed(void)
  * queues up writes, so that all our write(2) calls write exactly one
  * full block; pads writes to RECORDSIZE
  */
-static void do_write_blocked(const void *data, unsigned long size)
+static void do_write_blocked(const void *data, size_t size)
 {
 	const char *buf = data;
 
@@ -102,7 +102,7 @@ static void finish_record(void)
 	write_if_needed();
 }
 
-static void write_blocked(const void *data, unsigned long size)
+static void write_blocked(const void *data, size_t size)
 {
 	do_write_blocked(data, size);
 	finish_record();
@@ -218,7 +218,7 @@ static size_t get_path_prefix(const char *path, size_t pathlen, size_t maxlen)
 
 static void prepare_header(struct archiver_args *args,
 			   struct ustar_header *header,
-			   unsigned int mode, unsigned long size)
+			   unsigned int mode, size_t size)
 {
 	xsnprintf(header->mode, sizeof(header->mode), "%07o", mode & 07777);
 	xsnprintf(header->size, sizeof(header->size), "%011"PRIoMAX , S_ISREG(mode) ? (uintmax_t)size : (uintmax_t)0);
@@ -256,11 +256,11 @@ static int write_tar_entry(struct archiver_args *args,
 			   const struct object_id *oid,
 			   const char *path, size_t pathlen,
 			   unsigned int mode,
-			   void *buffer, unsigned long size)
+			   void *buffer, size_t size)
 {
 	struct ustar_header header;
 	struct strbuf ext_header = STRBUF_INIT;
-	unsigned long size_in_header;
+	size_t size_in_header;
 	int err = 0;
 
 	memset(&header, 0, sizeof(header));
diff --git a/archive-zip.c b/archive-zip.c
index 785689584c..2ca6dd956d 100644
--- a/archive-zip.c
+++ b/archive-zip.c
@@ -191,9 +191,9 @@ static uint32_t clamp32(uintmax_t n)
 	return (n < max) ? n : max;
 }
 
-static void *zlib_deflate_raw(void *data, unsigned long size,
+static void *zlib_deflate_raw(void *data, size_t size,
 			      int compression_level,
-			      unsigned long *compressed_size)
+			      size_t *compressed_size)
 {
 	git_zstream stream;
 	size_t maxsize;
@@ -224,8 +224,8 @@ static void *zlib_deflate_raw(void *data, unsigned long size,
 	return buffer;
 }
 
-static void write_zip_data_desc(unsigned long size,
-				unsigned long compressed_size,
+static void write_zip_data_desc(size_t size,
+				size_t compressed_size,
 				unsigned long crc)
 {
 	if (size >= 0xffffffff || compressed_size >= 0xffffffff) {
@@ -248,8 +248,8 @@ static void write_zip_data_desc(unsigned long size,
 }
 
 static void set_zip_header_data_desc(struct zip_local_header *header,
-				     unsigned long size,
-				     unsigned long compressed_size,
+				     size_t size,
+				     size_t compressed_size,
 				     unsigned long crc)
 {
 	copy_le32(header->crc32, crc);
@@ -285,7 +285,7 @@ static int write_zip_entry(struct archiver_args *args,
 			   const struct object_id *oid,
 			   const char *path, size_t pathlen,
 			   unsigned int mode,
-			   void *buffer, unsigned long size)
+			   void *buffer, size_t size)
 {
 	struct zip_local_header header;
 	uintmax_t offset = zip_offset;
@@ -293,7 +293,7 @@ static int write_zip_entry(struct archiver_args *args,
 	size_t header_extra_size = zip_extra_mtime.len;
 	int need_zip64_extra = 0;
 	unsigned long attr2;
-	unsigned long compressed_size;
+	size_t compressed_size;
 	unsigned long crc;
 	enum zip_method method;
 	unsigned char *out;
diff --git a/archive.h b/archive.h
index bbe65ba0f9..e52328d639 100644
--- a/archive.h
+++ b/archive.h
@@ -56,7 +56,7 @@ typedef int (*write_archive_entry_fn_t)(struct archiver_args *args,
 					const struct object_id *oid,
 					const char *path, size_t pathlen,
 					unsigned int mode,
-					void *buffer, unsigned long size);
+					void *buffer, size_t size);
 
 int write_archive_entries(struct archiver_args *args, write_archive_entry_fn_t write_entry);
 
-- 
2.53.0
Previous: Elia PintoNext: Elia Pinto
Message 2 of 6 in “archive, apply: do not truncate files of 4GiB or more”
  1. 0/2 archive, apply: do not truncate files of 4GiB or moreElia Pinto, Nov 1, 2026
  2. 1/2 archive: use size_t for the size of archive entriesElia Pinto, Nov 1, 2026
  3. 2/2 apply: use size_t for the size of the result written outElia Pinto, Nov 1, 2026
  4. Elia PintoNov 19, 2026
  5. Patrick SteinhardtNov 19, 2026
  6. Elia PintoNov 19, 2026

Read the whole thread, see it on lore, or plain text.

$ cat FOOTERMessages come from the public archive at lore.kernel.org/git, fetched every hour. The front page is chosen and written each morning by an AI editor and can be wrong; the threads themselves are the record. About and API. For agents: an MCP server at https://gitlist.dev/mcp, and any thread, story or person page as Markdown by adding .md to its URL (or sending Accept: text/markdown). Details in /llms.txt.