1 files changed, 161 insertions, 150 deletions

diff --git a/sha1_file.c b/sha1_file.c
index 63981fb3fd..d86a8db69a 100644
--- a/sha1_file.c
+++ b/sha1_file.c
@@ -35,60 +35,7 @@ static size_t sz_fmt(size_t s) { return s; }
 
 const unsigned char null_sha1[20];
 
-const signed char hexval_table[256] = {
-	 -1, -1, -1, -1, -1, -1, -1, -1,		/* 00-07 */
-	 -1, -1, -1, -1, -1, -1, -1, -1,		/* 08-0f */
-	 -1, -1, -1, -1, -1, -1, -1, -1,		/* 10-17 */
-	 -1, -1, -1, -1, -1, -1, -1, -1,		/* 18-1f */
-	 -1, -1, -1, -1, -1, -1, -1, -1,		/* 20-27 */
-	 -1, -1, -1, -1, -1, -1, -1, -1,		/* 28-2f */
-	  0,  1,  2,  3,  4,  5,  6,  7,		/* 30-37 */
-	  8,  9, -1, -1, -1, -1, -1, -1,		/* 38-3f */
-	 -1, 10, 11, 12, 13, 14, 15, -1,		/* 40-47 */
-	 -1, -1, -1, -1, -1, -1, -1, -1,		/* 48-4f */
-	 -1, -1, -1, -1, -1, -1, -1, -1,		/* 50-57 */
-	 -1, -1, -1, -1, -1, -1, -1, -1,		/* 58-5f */
-	 -1, 10, 11, 12, 13, 14, 15, -1,		/* 60-67 */
-	 -1, -1, -1, -1, -1, -1, -1, -1,		/* 68-67 */
-	 -1, -1, -1, -1, -1, -1, -1, -1,		/* 70-77 */
-	 -1, -1, -1, -1, -1, -1, -1, -1,		/* 78-7f */
-	 -1, -1, -1, -1, -1, -1, -1, -1,		/* 80-87 */
-	 -1, -1, -1, -1, -1, -1, -1, -1,		/* 88-8f */
-	 -1, -1, -1, -1, -1, -1, -1, -1,		/* 90-97 */
-	 -1, -1, -1, -1, -1, -1, -1, -1,		/* 98-9f */
-	 -1, -1, -1, -1, -1, -1, -1, -1,		/* a0-a7 */
-	 -1, -1, -1, -1, -1, -1, -1, -1,		/* a8-af */
-	 -1, -1, -1, -1, -1, -1, -1, -1,		/* b0-b7 */
-	 -1, -1, -1, -1, -1, -1, -1, -1,		/* b8-bf */
-	 -1, -1, -1, -1, -1, -1, -1, -1,		/* c0-c7 */
-	 -1, -1, -1, -1, -1, -1, -1, -1,		/* c8-cf */
-	 -1, -1, -1, -1, -1, -1, -1, -1,		/* d0-d7 */
-	 -1, -1, -1, -1, -1, -1, -1, -1,		/* d8-df */
-	 -1, -1, -1, -1, -1, -1, -1, -1,		/* e0-e7 */
-	 -1, -1, -1, -1, -1, -1, -1, -1,		/* e8-ef */
-	 -1, -1, -1, -1, -1, -1, -1, -1,		/* f0-f7 */
-	 -1, -1, -1, -1, -1, -1, -1, -1,		/* f8-ff */
-};
-
-int get_sha1_hex(const char *hex, unsigned char *sha1)
-{
-	int i;
-	for (i = 0; i < 20; i++) {
-		unsigned int val = (hexval(hex[0]) << 4) | hexval(hex[1]);
-		if (val & ~0xff)
-			return -1;
-		*sha1++ = val;
-		hex += 2;
-	}
-	return 0;
-}
-
-static inline int offset_1st_component(const char *path)
-{
-	if (has_dos_drive_prefix(path))
-		return 2 + (path[2] == '/');
-	return *path == '/';
-}
+static int git_open_noatime(const char *name, struct packed_git *p);
 
 int safe_create_leading_directories(char *path)
 {
@@ -133,24 +80,6 @@ int safe_create_leading_directories_const(const char *path)
 	return result;
 }
 
-char *sha1_to_hex(const unsigned char *sha1)
-{
-	static int bufno;
-	static char hexbuffer[4][50];
-	static const char hex[] = "0123456789abcdef";
-	char *buffer = hexbuffer[3 & ++bufno], *buf = buffer;
-	int i;
-
-	for (i = 0; i < 20; i++) {
-		unsigned int val = *sha1++;
-		*buf++ = hex[val >> 4];
-		*buf++ = hex[val & 0xf];
-	}
-	*buf = '\0';
-
-	return buffer;
-}
-
 static void fill_sha1_path(char *pathbuf, const unsigned char *sha1)
 {
 	int i;
@@ -175,20 +104,22 @@ static void fill_sha1_path(char *pathbuf, const unsigned char *sha1)
  */
 char *sha1_file_name(const unsigned char *sha1)
 {
-	static char *name, *base;
+	static char buf[PATH_MAX];
+	const char *objdir;
+	int len;
 
-	if (!base) {
-		const char *sha1_file_directory = get_object_directory();
-		int len = strlen(sha1_file_directory);
-		base = xmalloc(len + 60);
-		memcpy(base, sha1_file_directory, len);
-		memset(base+len, 0, 60);
-		base[len] = '/';
-		base[len+3] = '/';
-		name = base + len + 1;
-	}
-	fill_sha1_path(name, sha1);
-	return base;
+	objdir = get_object_directory();
+	len = strlen(objdir);
+
+	/* '/' + sha1(2) + '/' + sha1(38) + '\0' */
+	if (len + 43 > PATH_MAX)
+		die("insanely long object directory %s", objdir);
+	memcpy(buf, objdir, len);
+	buf[len] = '/';
+	buf[len+3] = '/';
+	buf[len+42] = '\0';
+	fill_sha1_path(buf + len + 1, sha1);
+	return buf;
 }
 
 static char *sha1_get_pack_name(const unsigned char *sha1,
@@ -369,7 +300,7 @@ static void read_info_alternates(const char * relative_base, int depth)
 	int fd;
 
 	sprintf(path, "%s/%s", relative_base, alt_file_name);
-	fd = open(path, O_RDONLY);
+	fd = git_open_noatime(path, NULL);
 	if (fd < 0)
 		return;
 	if (fstat(fd, &st) || (st.st_size == 0)) {
@@ -482,7 +413,7 @@ static int check_packed_git_idx(const char *path,  struct packed_git *p)
 	struct pack_idx_header *hdr;
 	size_t idx_size;
 	uint32_t version, nr, i, *index;
-	int fd = open(path, O_RDONLY);
+	int fd = git_open_noatime(path, p);
 	struct stat st;
 
 	if (fd < 0)
@@ -647,6 +578,21 @@ void release_pack_memory(size_t need, int fd)
 		; /* nothing */
 }
 
+void *xmmap(void *start, size_t length,
+	int prot, int flags, int fd, off_t offset)
+{
+	void *ret = mmap(start, length, prot, flags, fd, offset);
+	if (ret == MAP_FAILED) {
+		if (!length)
+			return NULL;
+		release_pack_memory(length, fd);
+		ret = mmap(start, length, prot, flags, fd, offset);
+		if (ret == MAP_FAILED)
+			die_errno("Out of memory? mmap failed");
+	}
+	return ret;
+}
+
 void close_pack_windows(struct packed_git *p)
 {
 	while (p->windows) {
@@ -672,6 +618,14 @@ void unuse_pack(struct pack_window **w_cursor)
 	}
 }
 
+void close_pack_index(struct packed_git *p)
+{
+	if (p->index_data) {
+		munmap((void *)p->index_data, p->index_size);
+		p->index_data = NULL;
+	}
+}
+
 /*
  * This is used by git-repack in case a newly created pack happens to
  * contain the same set of objects as an existing one.  In that case
@@ -693,8 +647,7 @@ void free_pack_by_name(const char *pack_name)
 			close_pack_windows(p);
 			if (p->pack_fd != -1)
 				close(p->pack_fd);
-			if (p->index_data)
-				munmap((void *)p->index_data, p->index_size);
+			close_pack_index(p);
 			free(p->bad_object_sha1);
 			*pp = p->next;
 			free(p);
@@ -719,9 +672,7 @@ static int open_packed_git_1(struct packed_git *p)
 	if (!p->index_data && open_pack_index(p))
 		return error("packfile %s index unavailable", p->pack_name);
 
-	p->pack_fd = open(p->pack_name, O_RDONLY);
-	while (p->pack_fd < 0 && errno == EMFILE && unuse_one_window(p, -1))
-		p->pack_fd = open(p->pack_name, O_RDONLY);
+	p->pack_fd = git_open_noatime(p->pack_name, p);
 	if (p->pack_fd < 0 || fstat(p->pack_fd, &st))
 		return -1;
 
@@ -867,11 +818,22 @@ static struct packed_git *alloc_packed_git(int extra)
 	return p;
 }
 
+static void try_to_free_pack_memory(size_t size)
+{
+	release_pack_memory(size, -1);
+}
+
 struct packed_git *add_packed_git(const char *path, int path_len, int local)
 {
+	static int have_set_try_to_free_routine;
 	struct stat st;
 	struct packed_git *p = alloc_packed_git(path_len + 2);
 
+	if (!have_set_try_to_free_routine) {
+		have_set_try_to_free_routine = 1;
+		set_try_to_free_routine(try_to_free_pack_memory);
+	}
+
 	/*
 	 * Make sure a corresponding .pack file exists and that
 	 * the index looks sane.
@@ -904,9 +866,8 @@ struct packed_git *add_packed_git(const char *path, int path_len, int local)
 	return p;
 }
 
-struct packed_git *parse_pack_index(unsigned char *sha1)
+struct packed_git *parse_pack_index(unsigned char *sha1, const char *idx_path)
 {
-	const char *idx_path = sha1_pack_index_name(sha1);
 	const char *path = sha1_pack_name(sha1);
 	struct packed_git *p = alloc_packed_git(strlen(path) + 1);
 
@@ -939,7 +900,7 @@ static void prepare_packed_git_one(char *objdir, int local)
 	sprintf(path, "%s/pack", objdir);
 	len = strlen(path);
 	dir = opendir(path);
-	while (!dir && errno == EMFILE && unuse_one_window(packed_git, -1))
+	while (!dir && errno == EMFILE && unuse_one_window(NULL, -1))
 		dir = opendir(path);
 	if (!dir) {
 		if (errno != ENOENT)
@@ -1068,7 +1029,7 @@ static void mark_bad_packed_object(struct packed_git *p,
 	p->num_bad_objects++;
 }
 
-static int has_packed_and_bad(const unsigned char *sha1)
+static const struct packed_git *has_packed_and_bad(const unsigned char *sha1)
 {
 	struct packed_git *p;
 	unsigned i;
@@ -1076,8 +1037,8 @@ static int has_packed_and_bad(const unsigned char *sha1)
 	for (p = packed_git; p; p = p->next)
 		for (i = 0; i < p->num_bad_objects; i++)
 			if (!hashcmp(sha1, p->bad_object_sha1 + 20 * i))
-				return 1;
-	return 0;
+				return p;
+	return NULL;
 }
 
 int check_sha1_signature(const unsigned char *sha1, void *map, unsigned long size, const char *type)
@@ -1087,18 +1048,31 @@ int check_sha1_signature(const unsigned char *sha1, void *map, unsigned long siz
 	return hashcmp(sha1, real_sha1) ? -1 : 0;
 }
 
-static int git_open_noatime(const char *name)
+static int git_open_noatime(const char *name, struct packed_git *p)
 {
 	static int sha1_file_open_flag = O_NOATIME;
-	int fd = open(name, O_RDONLY | sha1_file_open_flag);
 
-	/* Might the failure be due to O_NOATIME? */
-	if (fd < 0 && errno != ENOENT && sha1_file_open_flag) {
-		fd = open(name, O_RDONLY);
+	for (;;) {
+		int fd = open(name, O_RDONLY | sha1_file_open_flag);
 		if (fd >= 0)
+			return fd;
+
+		/* Might the failure be insufficient file descriptors? */
+		if (errno == EMFILE) {
+			if (unuse_one_window(p, -1))
+				continue;
+			else
+				return -1;
+		}
+
+		/* Might the failure be due to O_NOATIME? */
+		if (errno != ENOENT && sha1_file_open_flag) {
 			sha1_file_open_flag = 0;
+			continue;
+		}
+
+		return -1;
 	}
-	return fd;
 }
 
 static int open_sha1_file(const unsigned char *sha1)
@@ -1107,7 +1081,7 @@ static int open_sha1_file(const unsigned char *sha1)
 	char *name = sha1_file_name(sha1);
 	struct alternate_object_database *alt;
 
-	fd = git_open_noatime(name);
+	fd = git_open_noatime(name, NULL);
 	if (fd >= 0)
 		return fd;
 
@@ -1116,7 +1090,7 @@ static int open_sha1_file(const unsigned char *sha1)
 	for (alt = alt_odb_list; alt; alt = alt->next) {
 		name = alt->name;
 		fill_sha1_path(name, sha1);
-		fd = git_open_noatime(alt->base);
+		fd = git_open_noatime(alt->base, NULL);
 		if (fd >= 0)
 			return fd;
 	}
@@ -1232,7 +1206,7 @@ static int unpack_sha1_header(z_stream *stream, unsigned char *map, unsigned lon
 static void *unpack_sha1_rest(z_stream *stream, void *buffer, unsigned long size, const unsigned char *sha1)
 {
 	int bytes = strlen(buffer) + 1;
-	unsigned char *buf = xmalloc(1+size);
+	unsigned char *buf = xmallocz(size);
 	unsigned long n;
 	int status = Z_OK;
 
@@ -1260,7 +1234,6 @@ static void *unpack_sha1_rest(z_stream *stream, void *buffer, unsigned long size
 		while (status == Z_OK)
 			status = git_inflate(stream, Z_FINISH);
 	}
-	buf[size] = 0;
 	if (status == Z_STREAM_END && !stream->avail_in) {
 		git_inflate_end(stream);
 		return buf;
@@ -1583,8 +1556,7 @@ static void *unpack_compressed_entry(struct packed_git *p,
 	z_stream stream;
 	unsigned char *buffer, *in;
 
-	buffer = xmalloc(size + 1);
-	buffer[size] = 0;
+	buffer = xmallocz(size);
 	memset(&stream, 0, sizeof(stream));
 	stream.next_out = buffer;
 	stream.avail_out = size + 1;
@@ -2146,27 +2118,48 @@ static void *read_object(const unsigned char *sha1, enum object_type *type,
 	return read_packed_sha1(sha1, type, size);
 }
 
+/*
+ * This function dies on corrupt objects; the callers who want to
+ * deal with them should arrange to call read_object() and give error
+ * messages themselves.
+ */
 void *read_sha1_file_repl(const unsigned char *sha1,
 			  enum object_type *type,
 			  unsigned long *size,
 			  const unsigned char **replacement)
 {
 	const unsigned char *repl = lookup_replace_object(sha1);
-	void *data = read_object(repl, type, size);
+	void *data;
+	char *path;
+	const struct packed_git *p;
+
+	errno = 0;
+	data = read_object(repl, type, size);
+	if (data) {
+		if (replacement)
+			*replacement = repl;
+		return data;
+	}
+
+	if (errno && errno != ENOENT)
+		die_errno("failed to read object %s", sha1_to_hex(sha1));
 
 	/* die if we replaced an object with one that does not exist */
-	if (!data && repl != sha1)
+	if (repl != sha1)
 		die("replacement %s not found for %s",
 		    sha1_to_hex(repl), sha1_to_hex(sha1));
 
-	/* legacy behavior is to die on corrupted objects */
-	if (!data && (has_loose_object(repl) || has_packed_and_bad(repl)))
-		die("object %s is corrupted", sha1_to_hex(repl));
+	if (has_loose_object(repl)) {
+		path = sha1_file_name(sha1);
+		die("loose object %s (stored in %s) is corrupt",
+		    sha1_to_hex(repl), path);
+	}
 
-	if (replacement)
-		*replacement = repl;
+	if ((p = has_packed_and_bad(repl)) != NULL)
+		die("packed object %s (stored in %s) is corrupt",
+		    sha1_to_hex(repl), p->pack_name);
 
-	return data;
+	return NULL;
 }
 
 void *read_object_with_reference(const unsigned char *sha1,
@@ -2274,7 +2267,7 @@ int move_temp_to_file(const char *tmpfile, const char *filename)
 	}
 
 out:
-	if (set_shared_perm(filename, (S_IFREG|0444)))
+	if (adjust_shared_perm(filename))
 		return error("unable to set permission to '%s'", filename);
 	return 0;
 }
@@ -2330,7 +2323,7 @@ static int create_tmpfile(char *buffer, size_t bufsiz, const char *filename)
 	}
 	memcpy(buffer, filename, dirlen);
 	strcpy(buffer + dirlen, "tmp_obj_XXXXXX");
-	fd = mkstemp(buffer);
+	fd = git_mkstemp_mode(buffer, 0444);
 	if (fd < 0 && dirlen && errno == ENOENT) {
 		/* Make sure the directory exists */
 		memcpy(buffer, filename, dirlen);
@@ -2340,24 +2333,25 @@ static int create_tmpfile(char *buffer, size_t bufsiz, const char *filename)
 
 		/* Try again */
 		strcpy(buffer + dirlen - 1, "/tmp_obj_XXXXXX");
-		fd = mkstemp(buffer);
+		fd = git_mkstemp_mode(buffer, 0444);
 	}
 	return fd;
 }
 
 static int write_loose_object(const unsigned char *sha1, char *hdr, int hdrlen,
-			      void *buf, unsigned long len, time_t mtime)
+			      const void *buf, unsigned long len, time_t mtime)
 {
 	int fd, ret;
-	size_t size;
-	unsigned char *compressed;
+	unsigned char compressed[4096];
 	z_stream stream;
+	git_SHA_CTX c;
+	unsigned char parano_sha1[20];
 	char *filename;
 	static char tmpfile[PATH_MAX];
 
 	filename = sha1_file_name(sha1);
 	fd = create_tmpfile(tmpfile, sizeof(tmpfile), filename);
-	while (fd < 0 && errno == EMFILE && unuse_one_window(packed_git, -1))
+	while (fd < 0 && errno == EMFILE && unuse_one_window(NULL, -1))
 		fd = create_tmpfile(tmpfile, sizeof(tmpfile), filename);
 	if (fd < 0) {
 		if (errno == EACCES)
@@ -2369,36 +2363,40 @@ static int write_loose_object(const unsigned char *sha1, char *hdr, int hdrlen,
 	/* Set it up */
 	memset(&stream, 0, sizeof(stream));
 	deflateInit(&stream, zlib_compression_level);
-	size = 8 + deflateBound(&stream, len+hdrlen);
-	compressed = xmalloc(size);
-
-	/* Compress it */
 	stream.next_out = compressed;
-	stream.avail_out = size;
+	stream.avail_out = sizeof(compressed);
+	git_SHA1_Init(&c);
 
 	/* First header.. */
 	stream.next_in = (unsigned char *)hdr;
 	stream.avail_in = hdrlen;
 	while (deflate(&stream, 0) == Z_OK)
 		/* nothing */;
+	git_SHA1_Update(&c, hdr, hdrlen);
 
 	/* Then the data itself.. */
-	stream.next_in = buf;
+	stream.next_in = (void *)buf;
 	stream.avail_in = len;
-	ret = deflate(&stream, Z_FINISH);
+	do {
+		unsigned char *in0 = stream.next_in;
+		ret = deflate(&stream, Z_FINISH);
+		git_SHA1_Update(&c, in0, stream.next_in - in0);
+		if (write_buffer(fd, compressed, stream.next_out - compressed) < 0)
+			die("unable to write sha1 file");
+		stream.next_out = compressed;
+		stream.avail_out = sizeof(compressed);
+	} while (ret == Z_OK);
+
 	if (ret != Z_STREAM_END)
 		die("unable to deflate new object %s (%d)", sha1_to_hex(sha1), ret);
-
 	ret = deflateEnd(&stream);
 	if (ret != Z_OK)
 		die("deflateEnd on object %s failed (%d)", sha1_to_hex(sha1), ret);
+	git_SHA1_Final(parano_sha1, &c);
+	if (hashcmp(sha1, parano_sha1) != 0)
+		die("confused by unstable object source data for %s", sha1_to_hex(sha1));
 
-	size = stream.total_out;
-
-	if (write_buffer(fd, compressed, size) < 0)
-		die("unable to write sha1 file");
 	close_sha1_file(fd);
-	free(compressed);
 
 	if (mtime) {
 		struct utimbuf utb;
@@ -2412,7 +2410,7 @@ static int write_loose_object(const unsigned char *sha1, char *hdr, int hdrlen,
 	return move_temp_to_file(tmpfile, filename);
 }
 
-int write_sha1_file(void *buf, unsigned long len, const char *type, unsigned char *returnsha1)
+int write_sha1_file(const void *buf, unsigned long len, const char *type, unsigned char *returnsha1)
 {
 	unsigned char sha1[20];
 	char hdr[32];
@@ -2458,14 +2456,6 @@ int has_pack_index(const unsigned char *sha1)
 	return 1;
 }
 
-int has_pack_file(const unsigned char *sha1)
-{
-	struct stat st;
-	if (stat(sha1_pack_name(sha1), &st))
-		return 0;
-	return 1;
-}
-
 int has_sha1_pack(const unsigned char *sha1)
 {
 	struct pack_entry e;
@@ -2510,6 +2500,8 @@ static int index_mem(unsigned char *sha1, void *buf, size_t size,
 	return ret;
 }
 
+#define SMALL_FILE_SIZE (32*1024)
+
 int index_fd(unsigned char *sha1, int fd, struct stat *st, int write_object,
 	     enum object_type type, const char *path)
 {
@@ -2524,12 +2516,21 @@ int index_fd(unsigned char *sha1, int fd, struct stat *st, int write_object,
 		else
 			ret = -1;
 		strbuf_release(&sbuf);
-	} else if (size) {
+	} else if (!size) {
+		ret = index_mem(sha1, NULL, size, write_object, type, path);
+	} else if (size <= SMALL_FILE_SIZE) {
+		char *buf = xmalloc(size);
+		if (size == read_in_full(fd, buf, size))
+			ret = index_mem(sha1, buf, size, write_object, type,
+					path);
+		else
+			ret = error("short read %s", strerror(errno));
+		free(buf);
+	} else {
 		void *buf = xmmap(NULL, size, PROT_READ, MAP_PRIVATE, fd, 0);
 		ret = index_mem(sha1, buf, size, write_object, type, path);
 		munmap(buf, size);
-	} else
-		ret = index_mem(sha1, NULL, size, write_object, type, path);
+	}
 	close(fd);
 	return ret;
 }
@@ -2584,3 +2585,13 @@ int read_pack_header(int fd, struct pack_header *header)
 		return PH_ERROR_PROTOCOL;
 	return 0;
 }
+
+void assert_sha1_type(const unsigned char *sha1, enum object_type expect)
+{
+	enum object_type type = sha1_object_info(sha1, NULL);
+	if (type < 0)
+		die("%s is not a valid object", sha1_to_hex(sha1));
+	if (type != expect)
+		die("%s is not a valid '%s' object", sha1_to_hex(sha1),
+		    typename(expect));
+}