Merge branch 'nd/hash-object-sanity'

* nd/hash-object-sanity:
  Make hash-object more robust against malformed objects

Conflicts:
	cache.h

5 files changed, 63 insertions, 10 deletions

diff --git a/builtin/hash-object.c b/builtin/hash-object.c
index 080af1a01b..c90acddcb2 100644
--- a/builtin/hash-object.c
+++ b/builtin/hash-object.c
@@ -15,7 +15,7 @@ static void hash_fd(int fd, const char *type, int write_object, const char *path
 	struct stat st;
 	unsigned char sha1[20];
 	if (fstat(fd, &st) < 0 ||
-	    index_fd(sha1, fd, &st, write_object, type_from_string(type), path))
+	    index_fd(sha1, fd, &st, write_object, type_from_string(type), path, 1))
 		die(write_object
 		    ? "Unable to add %s to database"
 		    : "Unable to hash %s", path);
diff --git a/cache.h b/cache.h
index 677994a23a..5cc2f896dc 100644
--- a/cache.h
+++ b/cache.h
@@ -516,7 +516,7 @@ struct pathspec {
 extern int init_pathspec(struct pathspec *, const char **);
 extern void free_pathspec(struct pathspec *);
 extern int ce_path_match(const struct cache_entry *ce, const struct pathspec *pathspec);
-extern int index_fd(unsigned char *sha1, int fd, struct stat *st, int write_object, enum object_type type, const char *path);
+extern int index_fd(unsigned char *sha1, int fd, struct stat *st, int write_object, enum object_type type, const char *path, int format_check);
 extern int index_path(unsigned char *sha1, const char *path, struct stat *st, int write_object);
 extern void fill_stat_cache_info(struct cache_entry *ce, struct stat *st);
 
diff --git a/read-cache.c b/read-cache.c
index b97b5668eb..98d526bd48 100644
--- a/read-cache.c
+++ b/read-cache.c
@@ -92,7 +92,7 @@ static int ce_compare_data(struct cache_entry *ce, struct stat *st)
 
 	if (fd >= 0) {
 		unsigned char sha1[20];
-		if (!index_fd(sha1, fd, st, 0, OBJ_BLOB, ce->name))
+		if (!index_fd(sha1, fd, st, 0, OBJ_BLOB, ce->name, 0))
 			match = hashcmp(sha1, ce->sha1);
 		/* index_fd() closed the file descriptor already */
 	}
diff --git a/sha1_file.c b/sha1_file.c
index 27730c334c..d949b35c33 100644
--- a/sha1_file.c
+++ b/sha1_file.c
@@ -13,6 +13,7 @@
 #include "commit.h"
 #include "tag.h"
 #include "tree.h"
+#include "tree-walk.h"
 #include "refs.h"
 #include "pack-revindex.h"
 #include "sha1-lookup.h"
@@ -2479,8 +2480,37 @@ int has_sha1_file(const unsigned char *sha1)
 	return has_loose_object(sha1);
 }
 
+static void check_tree(const void *buf, size_t size)
+{
+	struct tree_desc desc;
+	struct name_entry entry;
+
+	init_tree_desc(&desc, buf, size);
+	while (tree_entry(&desc, &entry))
+		/* do nothing
+		 * tree_entry() will die() on malformed entries */
+		;
+}
+
+static void check_commit(const void *buf, size_t size)
+{
+	struct commit c;
+	memset(&c, 0, sizeof(c));
+	if (parse_commit_buffer(&c, buf, size))
+		die("corrupt commit");
+}
+
+static void check_tag(const void *buf, size_t size)
+{
+	struct tag t;
+	memset(&t, 0, sizeof(t));
+	if (parse_tag_buffer(&t, buf, size))
+		die("corrupt tag");
+}
+
 static int index_mem(unsigned char *sha1, void *buf, size_t size,
-		     int write_object, enum object_type type, const char *path)
+		     int write_object, enum object_type type,
+		     const char *path, int format_check)
 {
 	int ret, re_allocated = 0;
 
@@ -2498,6 +2528,14 @@ static int index_mem(unsigned char *sha1, void *buf, size_t size,
 			re_allocated = 1;
 		}
 	}
+	if (format_check) {
+		if (type == OBJ_TREE)
+			check_tree(buf, size);
+		if (type == OBJ_COMMIT)
+			check_commit(buf, size);
+		if (type == OBJ_TAG)
+			check_tag(buf, size);
+	}
 
 	if (write_object)
 		ret = write_sha1_file(buf, size, typename(type), sha1);
@@ -2511,7 +2549,7 @@ static int index_mem(unsigned char *sha1, void *buf, size_t size,
 #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)
+	     enum object_type type, const char *path, int format_check)
 {
 	int ret;
 	size_t size = xsize_t(st->st_size);
@@ -2520,23 +2558,25 @@ int index_fd(unsigned char *sha1, int fd, struct stat *st, int write_object,
 		struct strbuf sbuf = STRBUF_INIT;
 		if (strbuf_read(&sbuf, fd, 4096) >= 0)
 			ret = index_mem(sha1, sbuf.buf, sbuf.len, write_object,
-					type, path);
+					type, path, format_check);
 		else
 			ret = -1;
 		strbuf_release(&sbuf);
 	} else if (!size) {
-		ret = index_mem(sha1, NULL, size, write_object, type, path);
+		ret = index_mem(sha1, NULL, size, write_object, type, path,
+				format_check);
 	} 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);
+					path, format_check);
 		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);
+		ret = index_mem(sha1, buf, size, write_object, type, path,
+				format_check);
 		munmap(buf, size);
 	}
 	close(fd);
@@ -2554,7 +2594,7 @@ int index_path(unsigned char *sha1, const char *path, struct stat *st, int write
 		if (fd < 0)
 			return error("open(\"%s\"): %s", path,
 				     strerror(errno));
-		if (index_fd(sha1, fd, st, write_object, OBJ_BLOB, path) < 0)
+		if (index_fd(sha1, fd, st, write_object, OBJ_BLOB, path, 0) < 0)
 			return error("%s: failed to insert into database",
 				     path);
 		break;
diff --git a/t/t1007-hash-object.sh b/t/t1007-hash-object.sh
index dd32432d62..6d52b824b1 100755
--- a/t/t1007-hash-object.sh
+++ b/t/t1007-hash-object.sh
@@ -188,4 +188,17 @@ for args in "-w --stdin-paths" "--stdin-paths -w"; do
 	pop_repo
 done
 
+test_expect_success 'corrupt tree' '
+	echo abc >malformed-tree
+	test_must_fail git hash-object -t tree malformed-tree
+'
+
+test_expect_success 'corrupt commit' '
+	test_must_fail git hash-object -t commit --stdin </dev/null
+'
+
+test_expect_success 'corrupt tag' '
+	test_must_fail git hash-object -t tag --stdin </dev/null
+'
+
 test_done