Cast 64 bit off_t to 32 bit size_t

Some systems have sizeof(off_t) == 8 while sizeof(size_t) == 4.
This implies that we are able to access and work on files whose
maximum length is around 2^63-1 bytes, but we can only malloc or
mmap somewhat less than 2^32-1 bytes of memory.

On such a system an implicit conversion of off_t to size_t can cause
the size_t to wrap, resulting in unexpected and exciting behavior.
Right now we are working around all gcc warnings generated by the
-Wshorten-64-to-32 option by passing the off_t through xsize_t().

In the future we should make xsize_t on such problematic platforms
detect the wrapping and die if such a file is accessed.

Signed-off-by: Shawn O. Pearce <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: spearce

builtin-apply.c

@@ -1981,7 +1981,7 @@ static int apply_data(struct patch *patch, struct stat *st, struct cache_entry *
 		}
 	}
 	else if (patch->old_name) {
-		size = st->st_size;
+		size = xsize_t(st->st_size);
 		alloc = size + 8192;
 		buf = xmalloc(alloc);
 		if (read_old_data(st, patch->old_name, &buf, &alloc, &size))

builtin-blame.c

@@ -1963,7 +1963,7 @@ static struct commit *fake_working_tree_commit(const char *path, const char *con
 				die("Cannot lstat %s", path);
 			read_from = path;
 		}
-		fin_size = st.st_size;
+		fin_size = xsize_t(st.st_size);
 		buf = xmalloc(fin_size+1);
 		mode = canon_mode(st.st_mode);
 		switch (st.st_mode & S_IFMT) {

builtin-count-objects.c

@@ -44,7 +44,7 @@ static void count_objects(DIR *d, char *path, int len, int verbose,
 			if (lstat(path, &st) || !S_ISREG(st.st_mode))
 				bad = 1;
 			else
-				(*loose_size) += st.st_blocks;
+				(*loose_size) += xsize_t(st.st_blocks);
 		}
 		if (bad) {
 			if (verbose) {

builtin-grep.c

@@ -122,6 +122,8 @@ static int grep_file(struct grep_opt *opt, const char *filename)
 	struct stat st;
 	int i;
 	char *data;
+	size_t sz;
+
 	if (lstat(filename, &st) < 0) {
 	err_ret:
 		if (errno != ENOENT)
@@ -132,11 +134,12 @@ static int grep_file(struct grep_opt *opt, const char *filename)
 		return 0; /* empty file -- no grep hit */
 	if (!S_ISREG(st.st_mode))
 		return 0;
+	sz = xsize_t(st.st_size);
 	i = open(filename, O_RDONLY);
 	if (i < 0)
 		goto err_ret;
-	data = xmalloc(st.st_size + 1);
-	if (st.st_size != read_in_full(i, data, st.st_size)) {
+	data = xmalloc(sz + 1);
+	if (st.st_size != read_in_full(i, data, sz)) {
 		error("'%s': short read %s", filename, strerror(errno));
 		close(i);
 		free(data);
@@ -145,7 +148,7 @@ static int grep_file(struct grep_opt *opt, const char *filename)
 	close(i);
 	if (opt->relative && opt->prefix_length)
 		filename += opt->prefix_length;
-	i = grep_buffer(opt, filename, data, st.st_size);
+	i = grep_buffer(opt, filename, data, sz);
 	free(data);
 	return i;
 }

combine-diff.c

@@ -684,7 +684,7 @@ static void show_patch_diff(struct combine_diff_path *elem, int num_parent,
 			goto deleted_file;
 
 		if (S_ISLNK(st.st_mode)) {
-			size_t len = st.st_size;
+			size_t len = xsize_t(st.st_size);
 			result_size = len;
 			result = xmalloc(len + 1);
 			if (result_size != readlink(elem->path, result, len)) {
@@ -697,7 +697,7 @@ static void show_patch_diff(struct combine_diff_path *elem, int num_parent,
 		}
 		else if (0 <= (fd = open(elem->path, O_RDONLY)) &&
 			 !fstat(fd, &st)) {
-			size_t len = st.st_size;
+			size_t len = xsize_t(st.st_size);
 			size_t sz = 0;
 			int is_file, i;
 

config.c

@@ -431,7 +431,7 @@ static struct {
 	int do_not_match;
 	regex_t* value_regex;
 	int multi_replace;
-	off_t offset[MAX_MATCHES];
+	size_t offset[MAX_MATCHES];
 	enum { START, SECTION_SEEN, SECTION_END_SEEN, KEY_SEEN } state;
 	int seen;
 } store;
@@ -579,11 +579,11 @@ static int store_write_pair(int fd, const char* key, const char* value)
 	return 1;
 }
 
-static int find_beginning_of_line(const char* contents, int size,
-	int offset_, int* found_bracket)
+static ssize_t find_beginning_of_line(const char* contents, size_t size,
+	size_t offset_, int* found_bracket)
 {
-	int equal_offset = size, bracket_offset = size;
-	int offset;
+	size_t equal_offset = size, bracket_offset = size;
+	ssize_t offset;
 
 	for (offset = offset_-2; offset > 0 
 			&& contents[offset] != '\n'; offset--)
@@ -727,7 +727,8 @@ int git_config_set_multivar(const char* key, const char* value,
 	} else {
 		struct stat st;
 		char* contents;
-		int i, copy_begin, copy_end, new_line = 0;
+		size_t contents_sz, copy_begin, copy_end;
+		int i, new_line = 0;
 
 		if (value_regex == NULL)
 			store.value_regex = NULL;
@@ -784,7 +785,8 @@ int git_config_set_multivar(const char* key, const char* value,
 		}
 
 		fstat(in_fd, &st);
-		contents = xmmap(NULL, st.st_size, PROT_READ,
+		contents_sz = xsize_t(st.st_size);
+		contents = xmmap(NULL, contents_sz, PROT_READ,
 			MAP_PRIVATE, in_fd, 0);
 		close(in_fd);
 
@@ -793,12 +795,12 @@ int git_config_set_multivar(const char* key, const char* value,
 
 		for (i = 0, copy_begin = 0; i < store.seen; i++) {
 			if (store.offset[i] == 0) {
-				store.offset[i] = copy_end = st.st_size;
+				store.offset[i] = copy_end = contents_sz;
 			} else if (store.state != KEY_SEEN) {
 				copy_end = store.offset[i];
 			} else
 				copy_end = find_beginning_of_line(
-					contents, st.st_size,
+					contents, contents_sz,
 					store.offset[i]-2, &new_line);
 
 			/* write the first part of the config */
@@ -825,13 +827,13 @@ int git_config_set_multivar(const char* key, const char* value,
 		}
 
 		/* write the rest of the config */
-		if (copy_begin < st.st_size)
+		if (copy_begin < contents_sz)
 			if (write_in_full(fd, contents + copy_begin,
-					  st.st_size - copy_begin) <
-			    st.st_size - copy_begin)
+					  contents_sz - copy_begin) <
+			    contents_sz - copy_begin)
 				goto write_err_out;
 
-		munmap(contents, st.st_size);
+		munmap(contents, contents_sz);
 		unlink(config_filename);
 	}
 

diff.c

@@ -1399,7 +1399,7 @@ int diff_populate_filespec(struct diff_filespec *s, int size_only)
 				return err;
 			}
 		}
-		s->size = st.st_size;
+		s->size = xsize_t(st.st_size);
 		if (!s->size)
 			goto empty;
 		if (size_only)
@@ -1515,12 +1515,13 @@ static void prepare_temp_file(const char *name,
 		if (S_ISLNK(st.st_mode)) {
 			int ret;
 			char buf[PATH_MAX + 1]; /* ought to be SYMLINK_MAX */
+			size_t sz = xsize_t(st.st_size);
 			if (sizeof(buf) <= st.st_size)
 				die("symlink too long: %s", name);
-			ret = readlink(name, buf, st.st_size);
+			ret = readlink(name, buf, sz);
 			if (ret < 0)
 				die("readlink(%s)", name);
-			prep_temp_blob(temp, buf, st.st_size,
+			prep_temp_blob(temp, buf, sz,
 				       (one->sha1_valid ?
 					one->sha1 : null_sha1),
 				       (one->sha1_valid ?
@@ -2138,7 +2139,7 @@ static int parse_num(const char **cp_p)
 	/* user says num divided by scale and we say internally that
 	 * is MAX_SCORE * num / scale.
 	 */
-	return (num >= scale) ? MAX_SCORE : (MAX_SCORE * num / scale);
+	return (int)((num >= scale) ? MAX_SCORE : (MAX_SCORE * num / scale));
 }
 
 int diff_scoreopt_parse(const char *opt)

diffcore-break.c

@@ -89,7 +89,7 @@ static int should_break(struct diff_filespec *src,
 	 * merge the surviving pair together if the score is
 	 * less than the minimum, after rename/copy runs.
 	 */
-	*merge_score_p = src_removed * MAX_SCORE / src->size;
+	*merge_score_p = (int)(src_removed * MAX_SCORE / src->size);
 
 	/* Extent of damage, which counts both inserts and
 	 * deletes.

diffcore-order.c

@@ -14,6 +14,7 @@ static void prepare_order(const char *orderfile)
 	void *map;
 	char *cp, *endp;
 	struct stat st;
+	size_t sz;
 
 	if (order)
 		return;
@@ -25,11 +26,12 @@ static void prepare_order(const char *orderfile)
 		close(fd);
 		return;
 	}
-	map = mmap(NULL, st.st_size, PROT_READ|PROT_WRITE, MAP_PRIVATE, fd, 0);
+	sz = xsize_t(st.st_size);
+	map = mmap(NULL, sz, PROT_READ|PROT_WRITE, MAP_PRIVATE, fd, 0);
 	close(fd);
 	if (map == MAP_FAILED)
 		return;
-	endp = (char *) map + st.st_size;
+	endp = (char *) map + sz;
 	for (pass = 0; pass < 2; pass++) {
 		cnt = 0;
 		cp = map;

diffcore-rename.c

@@ -172,7 +172,8 @@ static int estimate_similarity(struct diff_filespec *src,
 		return 0; /* error but caught downstream */
 
 
-	delta_limit = base_size * (MAX_SCORE-minimum_score) / MAX_SCORE;
+	delta_limit = (unsigned long)
+		(base_size * (MAX_SCORE-minimum_score) / MAX_SCORE);
 	if (diffcore_count_changes(src->data, src->size,
 				   dst->data, dst->size,
 				   &src->cnt_data, &dst->cnt_data,
@@ -186,7 +187,7 @@ static int estimate_similarity(struct diff_filespec *src,
 	if (!dst->size)
 		score = 0; /* should not happen */
 	else
-		score = src_copied * MAX_SCORE / max_size;
+		score = (int)(src_copied * MAX_SCORE / max_size);
 	return score;
 }
 
@@ -297,7 +298,7 @@ void diffcore_rename(struct diff_options *options)
 				struct diff_filespec *one = rename_src[j].one;
 				if (!is_exact_match(one, two, contents_too))
 					continue;
-				record_rename_pair(i, j, MAX_SCORE);
+				record_rename_pair(i, j, (int)MAX_SCORE);
 				rename_count++;
 				break; /* we are done with this entry */
 			}