zlib: zlib can only process 4GB at a time

The size of objects we read from the repository and data we try to put
into the repository are represented in "unsigned long", so that on larger
architectures we can handle objects that weigh more than 4GB.

But the interface defined in zlib.h to communicate with inflate/deflate
limits avail_in (how many bytes of input are we calling zlib with) and
avail_out (how many bytes of output from zlib are we ready to accept)
fields effectively to 4GB by defining their type to be uInt.

In many places in our code, we allocate a large buffer (e.g. mmap'ing a
large loose object file) and tell zlib its size by assigning the size to
avail_in field of the stream, but that will truncate the high octets of
the real size. The worst part of this story is that we often pass around
z_stream (the state object used by zlib) to keep track of the number of
used bytes in input/output buffer by inspecting these two fields, which
practically limits our callchain to the same 4GB limit.

Wrap z_stream in another structure git_zstream that can express avail_in
and avail_out in unsigned long. For now, just die() when the caller gives
a size that cannot be given to a single zlib call. In later patches in the
series, we would make git_inflate() and git_deflate() internally loop to
give callers an illusion that our "improved" version of zlib interface can
operate on a buffer larger than 4GB in one go.

Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 9 insertions, 9 deletions

diff --git a/sha1_file.c b/sha1_file.c
index 0eefb6194e..94d431907c 100644
--- a/sha1_file.c
+++ b/sha1_file.c
@@ -833,7 +833,7 @@ static int in_window(struct pack_window *win, off_t offset)
 unsigned char *use_pack(struct packed_git *p,
 		struct pack_window **w_cursor,
 		off_t offset,
-		unsigned int *left)
+		unsigned long *left)
 {
 	struct pack_window *win = *w_cursor;
 
@@ -1244,7 +1244,7 @@ unsigned long unpack_object_header_buffer(const unsigned char *buf,
 	return used;
 }
 
-static int unpack_sha1_header(z_stream *stream, unsigned char *map, unsigned long mapsize, void *buffer, unsigned long bufsiz)
+static int unpack_sha1_header(git_zstream *stream, unsigned char *map, unsigned long mapsize, void *buffer, unsigned long bufsiz)
 {
 	unsigned long size, used;
 	static const char valid_loose_object_type[8] = {
@@ -1291,7 +1291,7 @@ static int unpack_sha1_header(z_stream *stream, unsigned char *map, unsigned lon
 	return 0;
 }
 
-static void *unpack_sha1_rest(z_stream *stream, void *buffer, unsigned long size, const unsigned char *sha1)
+static void *unpack_sha1_rest(git_zstream *stream, void *buffer, unsigned long size, const unsigned char *sha1)
 {
 	int bytes = strlen(buffer) + 1;
 	unsigned char *buf = xmallocz(size);
@@ -1390,7 +1390,7 @@ static int parse_sha1_header(const char *hdr, unsigned long *sizep)
 static void *unpack_sha1_file(void *map, unsigned long mapsize, enum object_type *type, unsigned long *size, const unsigned char *sha1)
 {
 	int ret;
-	z_stream stream;
+	git_zstream stream;
 	char hdr[8192];
 
 	ret = unpack_sha1_header(&stream, map, mapsize, hdr, sizeof(hdr));
@@ -1406,7 +1406,7 @@ unsigned long get_size_from_delta(struct packed_git *p,
 {
 	const unsigned char *data;
 	unsigned char delta_head[20], *in;
-	z_stream stream;
+	git_zstream stream;
 	int st;
 
 	memset(&stream, 0, sizeof(stream));
@@ -1528,7 +1528,7 @@ static int unpack_object_header(struct packed_git *p,
 				unsigned long *sizep)
 {
 	unsigned char *base;
-	unsigned int left;
+	unsigned long left;
 	unsigned long used;
 	enum object_type type;
 
@@ -1641,7 +1641,7 @@ static void *unpack_compressed_entry(struct packed_git *p,
 				    unsigned long size)
 {
 	int st;
-	z_stream stream;
+	git_zstream stream;
 	unsigned char *buffer, *in;
 
 	buffer = xmallocz(size);
@@ -2074,7 +2074,7 @@ static int sha1_loose_object_info(const unsigned char *sha1, unsigned long *size
 	int status;
 	unsigned long mapsize, size;
 	void *map;
-	z_stream stream;
+	git_zstream stream;
 	char hdr[32];
 
 	map = map_sha1_file(sha1, &mapsize);
@@ -2425,7 +2425,7 @@ static int write_loose_object(const unsigned char *sha1, char *hdr, int hdrlen,
 {
 	int fd, ret;
 	unsigned char compressed[4096];
-	z_stream stream;
+	git_zstream stream;
 	git_SHA_CTX c;
 	unsigned char parano_sha1[20];
 	char *filename;