1 files changed, 137 insertions, 74 deletions

diff --git a/sha1_file.c b/sha1_file.c
index 1978d5f..0642664 100644
--- a/sha1_file.c
+++ b/sha1_file.c
@@ -13,6 +13,7 @@
 #include "commit.h"
 #include "tag.h"
 #include "tree.h"
+#include "refs.h"
 
 #ifndef O_NOATIME
 #if defined(__linux__) && (defined(__i386__) || defined(__PPC__))
@@ -437,7 +438,7 @@ static int check_packed_git_idx(const char *path,  struct packed_git *p)
 	void *idx_map;
 	struct pack_idx_header *hdr;
 	size_t idx_size;
-	uint32_t nr, i, *index;
+	uint32_t version, nr, i, *index;
 	int fd = open(path, O_RDONLY);
 	struct stat st;
 
@@ -455,21 +456,23 @@ static int check_packed_git_idx(const char *path,  struct packed_git *p)
 	idx_map = xmmap(NULL, idx_size, PROT_READ, MAP_PRIVATE, fd, 0);
 	close(fd);
 
-	/* a future index format would start with this, as older git
-	 * binaries would fail the non-monotonic index check below.
-	 * give a nicer warning to the user if we can.
-	 */
 	hdr = idx_map;
 	if (hdr->idx_signature == htonl(PACK_IDX_SIGNATURE)) {
-		munmap(idx_map, idx_size);
-		return error("index file %s is a newer version"
-			" and is not supported by this binary"
-			" (try upgrading GIT to a newer version)",
-			path);
-	}
+		version = ntohl(hdr->idx_version);
+		if (version < 2 || version > 2) {
+			munmap(idx_map, idx_size);
+			return error("index file %s is version %d"
+				     " and is not supported by this binary"
+				     " (try upgrading GIT to a newer version)",
+				     path, version);
+		}
+	} else
+		version = 1;
 
 	nr = 0;
 	index = idx_map;
+	if (version > 1)
+		index += 2;  /* skip index header */
 	for (i = 0; i < 256; i++) {
 		uint32_t n = ntohl(index[i]);
 		if (n < nr) {
@@ -479,21 +482,51 @@ static int check_packed_git_idx(const char *path,  struct packed_git *p)
 		nr = n;
 	}
 
-	/*
-	 * Total size:
-	 *  - 256 index entries 4 bytes each
-	 *  - 24-byte entries * nr (20-byte sha1 + 4-byte offset)
-	 *  - 20-byte SHA1 of the packfile
-	 *  - 20-byte SHA1 file checksum
-	 */
-	if (idx_size != 4*256 + nr * 24 + 20 + 20) {
-		munmap(idx_map, idx_size);
-		return error("wrong index file size in %s", path);
+	if (version == 1) {
+		/*
+		 * Total size:
+		 *  - 256 index entries 4 bytes each
+		 *  - 24-byte entries * nr (20-byte sha1 + 4-byte offset)
+		 *  - 20-byte SHA1 of the packfile
+		 *  - 20-byte SHA1 file checksum
+		 */
+		if (idx_size != 4*256 + nr * 24 + 20 + 20) {
+			munmap(idx_map, idx_size);
+			return error("wrong index file size in %s", path);
+		}
+	} else if (version == 2) {
+		/*
+		 * Minimum size:
+		 *  - 8 bytes of header
+		 *  - 256 index entries 4 bytes each
+		 *  - 20-byte sha1 entry * nr
+		 *  - 4-byte crc entry * nr
+		 *  - 4-byte offset entry * nr
+		 *  - 20-byte SHA1 of the packfile
+		 *  - 20-byte SHA1 file checksum
+		 * And after the 4-byte offset table might be a
+		 * variable sized table containing 8-byte entries
+		 * for offsets larger than 2^31.
+		 */
+		unsigned long min_size = 8 + 4*256 + nr*(20 + 4 + 4) + 20 + 20;
+		if (idx_size < min_size || idx_size > min_size + (nr - 1)*8) {
+			munmap(idx_map, idx_size);
+			return error("wrong index file size in %s", path);
+		}
+		if (idx_size != min_size) {
+			/* make sure we can deal with large pack offsets */
+			off_t x = 0x7fffffffUL, y = 0xffffffffUL;
+			if (x > (x + 1) || y > (y + 1)) {
+				munmap(idx_map, idx_size);
+				return error("pack too large for current definition of off_t in %s", path);
+			}
+		}
 	}
 
-	p->index_version = 1;
+	p->index_version = version;
 	p->index_data = idx_map;
 	p->index_size = idx_size;
+	p->num_objects = nr;
 	return 0;
 }
 
@@ -605,11 +638,11 @@ static int open_packed_git_1(struct packed_git *p)
 			p->pack_name, ntohl(hdr.hdr_version));
 
 	/* Verify the pack matches its index. */
-	if (num_packed_objects(p) != ntohl(hdr.hdr_entries))
+	if (p->num_objects != ntohl(hdr.hdr_entries))
 		return error("packfile %s claims to have %u objects"
-			" while index size indicates %u objects",
-			p->pack_name, ntohl(hdr.hdr_entries),
-			num_packed_objects(p));
+			     " while index indicates %u objects",
+			     p->pack_name, ntohl(hdr.hdr_entries),
+			     p->num_objects);
 	if (lseek(p->pack_fd, p->pack_size - sizeof(sha1), SEEK_SET) == -1)
 		return error("end of packfile %s is unavailable", p->pack_name);
 	if (read_in_full(p->pack_fd, sha1, sizeof(sha1)) != sizeof(sha1))
@@ -1128,6 +1161,43 @@ static void *unpack_sha1_file(void *map, unsigned long mapsize, enum object_type
 	return unpack_sha1_rest(&stream, hdr, *size, sha1);
 }
 
+unsigned long get_size_from_delta(struct packed_git *p,
+				  struct pack_window **w_curs,
+			          off_t curpos)
+{
+	const unsigned char *data;
+	unsigned char delta_head[20], *in;
+	z_stream stream;
+	int st;
+
+	memset(&stream, 0, sizeof(stream));
+	stream.next_out = delta_head;
+	stream.avail_out = sizeof(delta_head);
+
+	inflateInit(&stream);
+	do {
+		in = use_pack(p, w_curs, curpos, &stream.avail_in);
+		stream.next_in = in;
+		st = inflate(&stream, Z_FINISH);
+		curpos += stream.next_in - in;
+	} while ((st == Z_OK || st == Z_BUF_ERROR) &&
+		 stream.total_out < sizeof(delta_head));
+	inflateEnd(&stream);
+	if ((st != Z_STREAM_END) && stream.total_out != sizeof(delta_head))
+		die("delta data unpack-initial failed");
+
+	/* Examine the initial part of the delta to figure out
+	 * the result size.
+	 */
+	data = delta_head;
+
+	/* ignore base size */
+	get_delta_hdr_size(&data, delta_head+sizeof(delta_head));
+
+	/* Read the result size */
+	return get_delta_hdr_size(&data, delta_head+sizeof(delta_head));
+}
+
 static off_t get_delta_base(struct packed_git *p,
 				    struct pack_window **w_curs,
 				    off_t *curpos,
@@ -1149,7 +1219,7 @@ static off_t get_delta_base(struct packed_git *p,
 		base_offset = c & 127;
 		while (c & 128) {
 			base_offset += 1;
-			if (!base_offset || base_offset & ~(~0UL >> 7))
+			if (!base_offset || MSB(base_offset, 7))
 				die("offset value overflow for delta base object");
 			c = base_info[used++];
 			base_offset = (base_offset << 7) + (c & 127);
@@ -1191,40 +1261,8 @@ static int packed_delta_info(struct packed_git *p,
 	 * based on a base with a wrong size.  This saves tons of
 	 * inflate() calls.
 	 */
-	if (sizep) {
-		const unsigned char *data;
-		unsigned char delta_head[20], *in;
-		z_stream stream;
-		int st;
-
-		memset(&stream, 0, sizeof(stream));
-		stream.next_out = delta_head;
-		stream.avail_out = sizeof(delta_head);
-
-		inflateInit(&stream);
-		do {
-			in = use_pack(p, w_curs, curpos, &stream.avail_in);
-			stream.next_in = in;
-			st = inflate(&stream, Z_FINISH);
-			curpos += stream.next_in - in;
-		} while ((st == Z_OK || st == Z_BUF_ERROR)
-			&& stream.total_out < sizeof(delta_head));
-		inflateEnd(&stream);
-		if ((st != Z_STREAM_END) &&
-		    stream.total_out != sizeof(delta_head))
-			die("delta data unpack-initial failed");
-
-		/* Examine the initial part of the delta to figure out
-		 * the result size.
-		 */
-		data = delta_head;
-
-		/* ignore base size */
-		get_delta_hdr_size(&data, delta_head+sizeof(delta_head));
-
-		/* Read the result size */
-		*sizep = get_delta_hdr_size(&data, delta_head+sizeof(delta_head));
-	}
+	if (sizep)
+		*sizep = get_size_from_delta(p, w_curs, curpos);
 
 	return type;
 }
@@ -1526,37 +1564,60 @@ void *unpack_entry(struct packed_git *p, off_t obj_offset,
 	return data;
 }
 
-uint32_t num_packed_objects(const struct packed_git *p)
+const unsigned char *nth_packed_object_sha1(const struct packed_git *p,
+					    uint32_t n)
 {
-	/* See check_packed_git_idx() */
-	return (uint32_t)((p->index_size - 20 - 20 - 4*256) / 24);
+	const unsigned char *index = p->index_data;
+	if (n >= p->num_objects)
+		return NULL;
+	index += 4 * 256;
+	if (p->index_version == 1) {
+		return index + 24 * n + 4;
+	} else {
+		index += 8;
+		return index + 20 * n;
+	}
 }
 
-const unsigned char *nth_packed_object_sha1(const struct packed_git *p,
-					    uint32_t n)
+static off_t nth_packed_object_offset(const struct packed_git *p, uint32_t n)
 {
 	const unsigned char *index = p->index_data;
 	index += 4 * 256;
-	if (num_packed_objects(p) <= n)
-		return NULL;
-	return index + 24 * n + 4;
+	if (p->index_version == 1) {
+		return ntohl(*((uint32_t *)(index + 24 * n)));
+	} else {
+		uint32_t off;
+		index += 8 + p->num_objects * (20 + 4);
+		off = ntohl(*((uint32_t *)(index + 4 * n)));
+		if (!(off & 0x80000000))
+			return off;
+		index += p->num_objects * 4 + (off & 0x7fffffff) * 8;
+		return (((uint64_t)ntohl(*((uint32_t *)(index + 0)))) << 32) |
+				   ntohl(*((uint32_t *)(index + 4)));
+	}
 }
 
 off_t find_pack_entry_one(const unsigned char *sha1,
 				  struct packed_git *p)
 {
 	const uint32_t *level1_ofs = p->index_data;
-	int hi = ntohl(level1_ofs[*sha1]);
-	int lo = ((*sha1 == 0x0) ? 0 : ntohl(level1_ofs[*sha1 - 1]));
 	const unsigned char *index = p->index_data;
+	unsigned hi, lo;
 
+	if (p->index_version > 1) {
+		level1_ofs += 2;
+		index += 8;
+	}
 	index += 4 * 256;
+	hi = ntohl(level1_ofs[*sha1]);
+	lo = ((*sha1 == 0x0) ? 0 : ntohl(level1_ofs[*sha1 - 1]));
 
 	do {
-		int mi = (lo + hi) / 2;
-		int cmp = hashcmp(index + 24 * mi + 4, sha1);
+		unsigned mi = (lo + hi) / 2;
+		unsigned x = (p->index_version > 1) ? (mi * 20) : (mi * 24 + 4);
+		int cmp = hashcmp(index + x, sha1);
 		if (!cmp)
-			return ntohl(*((uint32_t *)((char *)index + (24 * mi))));
+			return nth_packed_object_offset(p, mi);
 		if (cmp > 0)
 			hi = mi;
 		else
@@ -2331,6 +2392,8 @@ int index_path(unsigned char *sha1, const char *path, struct stat *st, int write
 				     path);
 		free(target);
 		break;
+	case S_IFDIR:
+		return resolve_gitlink_ref(path, "HEAD", sha1);
 	default:
 		return error("%s: unsupported file type", path);
 	}