fuzz: add fuzz testing for packfile indices.

Breaks the majority of check_packed_git_idx() into a separate function,
load_idx(). The latter function operates on arbitrary buffers, which
makes it suitable as a fuzzing test target.

Signed-off-by: Josh Steadmon <steadmon@google.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

5 files changed, 53 insertions, 19 deletions

diff --git a/.gitignore b/.gitignore
index 87a28b3..64b3377 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1,5 +1,6 @@
 /fuzz_corpora
 /fuzz-pack-headers
+/fuzz-pack-idx
 /GIT-BUILD-OPTIONS
 /GIT-CFLAGS
 /GIT-LDFLAGS
diff --git a/Makefile b/Makefile
index 7f5a19b..1b3d893 100644
--- a/Makefile
+++ b/Makefile
@@ -685,6 +685,7 @@ SCRIPTS = $(SCRIPT_SH_INS) \
 ETAGS_TARGET = TAGS
 
 FUZZ_OBJS += fuzz-pack-headers.o
+FUZZ_OBJS += fuzz-pack-idx.o
 
 # Always build fuzz objects even if not testing, to prevent bit-rot.
 all:: $(FUZZ_OBJS)
diff --git a/fuzz-pack-idx.c b/fuzz-pack-idx.c
new file mode 100644
index 0000000..0c3d777
--- /dev/null
+++ b/fuzz-pack-idx.c
@@ -0,0 +1,13 @@
+#include "object-store.h"
+#include "packfile.h"
+
+int LLVMFuzzerTestOneInput(const uint8_t *data, size_t size);
+
+int LLVMFuzzerTestOneInput(const uint8_t *data, size_t size)
+{
+	struct packed_git p;
+
+	load_idx("fuzz-input", GIT_SHA1_RAWSZ, (void *)data, size, &p);
+
+	return 0;
+}
diff --git a/packfile.c b/packfile.c
index 841b361..86074a7 100644
--- a/packfile.c
+++ b/packfile.c
@@ -80,10 +80,8 @@ void pack_report(void)
 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 version, nr, i, *index;
-	int fd = git_open(path);
+	int fd = git_open(path), ret;
 	struct stat st;
 	const unsigned int hashsz = the_hash_algo->rawsz;
 
@@ -101,16 +99,32 @@ 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);
 
-	hdr = idx_map;
+	ret = load_idx(path, hashsz, idx_map, idx_size, p);
+
+	if (ret)
+		munmap(idx_map, idx_size);
+
+	return ret;
+}
+
+int load_idx(const char *path, const unsigned int hashsz, void *idx_map,
+	     size_t idx_size, struct packed_git *p)
+{
+	struct pack_idx_header *hdr = idx_map;
+	uint32_t version, nr, i, *index;
+
+	if (idx_size < 4 * 256 + hashsz + hashsz)
+		return error("index file %s is too small", path);
+	if (idx_map == NULL)
+		return error("empty data");
+
 	if (hdr->idx_signature == htonl(PACK_IDX_SIGNATURE)) {
 		version = ntohl(hdr->idx_version);
-		if (version < 2 || version > 2) {
-			munmap(idx_map, idx_size);
+		if (version < 2 || version > 2)
 			return error("index file %s is version %"PRIu32
 				     " and is not supported by this binary"
 				     " (try upgrading GIT to a newer version)",
 				     path, version);
-		}
 	} else
 		version = 1;
 
@@ -120,10 +134,8 @@ static int check_packed_git_idx(const char *path, struct packed_git *p)
 		index += 2;  /* skip index header */
 	for (i = 0; i < 256; i++) {
 		uint32_t n = ntohl(index[i]);
-		if (n < nr) {
-			munmap(idx_map, idx_size);
+		if (n < nr)
 			return error("non-monotonic index %s", path);
-		}
 		nr = n;
 	}
 
@@ -135,10 +147,8 @@ static int check_packed_git_idx(const char *path, struct packed_git *p)
 		 *  - hash of the packfile
 		 *  - file checksum
 		 */
-		if (idx_size != 4*256 + nr * (hashsz + 4) + hashsz + hashsz) {
-			munmap(idx_map, idx_size);
+		if (idx_size != 4 * 256 + nr * (hashsz + 4) + hashsz + hashsz)
 			return error("wrong index v1 file size in %s", path);
-		}
 	} else if (version == 2) {
 		/*
 		 * Minimum size:
@@ -157,20 +167,16 @@ static int check_packed_git_idx(const char *path, struct packed_git *p)
 		unsigned long max_size = min_size;
 		if (nr)
 			max_size += (nr - 1)*8;
-		if (idx_size < min_size || idx_size > max_size) {
-			munmap(idx_map, idx_size);
+		if (idx_size < min_size || idx_size > max_size)
 			return error("wrong index v2 file size in %s", path);
-		}
 		if (idx_size != min_size &&
 		    /*
 		     * make sure we can deal with large pack offsets.
 		     * 31-bit signed offset won't be enough, neither
 		     * 32-bit unsigned one will be.
 		     */
-		    (sizeof(off_t) <= 4)) {
-			munmap(idx_map, idx_size);
+		    (sizeof(off_t) <= 4))
 			return error("pack too large for current definition of off_t in %s", path);
-		}
 	}
 
 	p->index_version = version;
diff --git a/packfile.h b/packfile.h
index 4426257..6c40376 100644
--- a/packfile.h
+++ b/packfile.h
@@ -164,4 +164,17 @@ extern int has_pack_index(const unsigned char *sha1);
  */
 extern int is_promisor_object(const struct object_id *oid);
 
+/*
+ * Expose a function for fuzz testing.
+ *
+ * load_idx() parses a block of memory as a packfile index and puts the results
+ * into a struct packed_git.
+ *
+ * This function should not be used directly. It is exposed here only so that we
+ * have a convenient entry-point for fuzz testing. For real uses, you should
+ * probably use open_pack_index() or parse_pack_index() instead.
+ */
+extern int load_idx(const char *path, const unsigned int hashsz, void *idx_map,
+		    size_t idx_size, struct packed_git *p);
+
 #endif