[PATCH v2 0/3] Add commit-graph fuzzer and fix buffer overflow
To
git@vger.kernel.org
gitster@pobox.com
stolee@gmail.com
avarab@gmail.com
From
Josh Steadmon
See Also
Prev
Date
2018-12-06 20:20:52 UTC
Add a new fuzz test for the commit graph and fix a buffer read-overflow
that it discovered. Additionally, fix the Makefile instructions for
building fuzzers.

Changes since V1:
  * Moved the parse_commit_graph() declaration to the header file, since
    we don't mind if others use it.
  * Moved some unnecessary comments into commit messages.
  * Fixed some style issues.
  * Added a test case for detecting commit graphs with missing chunk
    lookup entries.
  * Ævar's comments on the Makefile made me realize the fuzzer build
    instructions were using the wrong variable. Added a new commit to
    fix this.

Josh Steadmon (3):
  commit-graph, fuzz: Add fuzzer for commit-graph
  commit-graph: fix buffer read-overflow
  Makefile: correct example fuzz build

 .gitignore              |  1 +
 Makefile                |  3 +-
 commit-graph.c          | 67 +++++++++++++++++++++++++++++------------
 commit-graph.h          |  3 ++
 fuzz-commit-graph.c     | 16 ++++++++++
 t/t5318-commit-graph.sh | 28 +++++++++++++++++
 6 files changed, 98 insertions(+), 20 deletions(-)
 create mode 100644 fuzz-commit-graph.c

Range-diff against v1:
1:  53e62baaa8 ! 1:  0b57ecbe1b commit-graph, fuzz: Add fuzzer for commit-graph
    @@ -4,7 +4,9 @@
     
         Breaks load_commit_graph_one() into a new function,
         parse_commit_graph(). The latter function operates on arbitrary buffers,
    -    which makes it suitable as a fuzzing target.
    +    which makes it suitable as a fuzzing target. Since parse_commit_graph()
    +    is only called by load_commit_graph_one() (and the fuzzer described
    +    below), we omit error messages that would be duplicated by the caller.
     
         Adds fuzz-commit-graph.c, which provides a fuzzing entry point
         compatible with libFuzzer (and possibly other fuzzing engines).
    @@ -35,17 +37,6 @@
      diff --git a/commit-graph.c b/commit-graph.c
      --- a/commit-graph.c
      +++ b/commit-graph.c
    -@@
    - #define GRAPH_MIN_SIZE (GRAPH_HEADER_SIZE + 4 * GRAPH_CHUNKLOOKUP_WIDTH \
    - 			+ GRAPH_FANOUT_SIZE + GRAPH_OID_LEN)
    - 
    -+struct commit_graph *parse_commit_graph(void *graph_map, int fd,
    -+					size_t graph_size);
    -+
    -+
    - char *get_commit_graph_filename(const char *obj_dir)
    - {
    - 	return xstrfmt("%s/info/commit-graph", obj_dir);
     @@
      struct commit_graph *load_commit_graph_one(const char *graph_file)
      {
    @@ -70,7 +61,7 @@
      	graph_map = xmmap(NULL, graph_size, PROT_READ, MAP_PRIVATE, fd, 0);
     +	ret = parse_commit_graph(graph_map, fd, graph_size);
     +
    -+	if (ret == NULL) {
    ++	if (!ret) {
     +		munmap(graph_map, graph_size);
     +		close(fd);
     +		exit(1);
    @@ -79,10 +70,6 @@
     +	return ret;
     +}
     +
    -+/*
    -+ * This function is intended to be used only from load_commit_graph_one() or in
    -+ * fuzz tests.
    -+ */
     +struct commit_graph *parse_commit_graph(void *graph_map, int fd,
     +					size_t graph_size)
     +{
    @@ -94,11 +81,9 @@
     +	uint32_t graph_signature;
     +	unsigned char graph_version, hash_version;
     +
    -+	/*
    -+	 * This should already be checked in load_commit_graph_one, but we still
    -+	 * need a check here for when we're calling parse_commit_graph directly
    -+	 * from fuzz tests. We can omit the error message in that case.
    -+	 */
    ++	if (!graph_map)
    ++		return NULL;
    ++
     +	if (graph_size < GRAPH_MIN_SIZE)
     +		return NULL;
     +
    @@ -162,12 +147,25 @@
      
      static void prepare_commit_graph_one(struct repository *r, const char *obj_dir)
     
    + diff --git a/commit-graph.h b/commit-graph.h
    + --- a/commit-graph.h
    + +++ b/commit-graph.h
    +@@
    + 
    + struct commit_graph *load_commit_graph_one(const char *graph_file);
    + 
    ++struct commit_graph *parse_commit_graph(void *graph_map, int fd,
    ++					size_t graph_size);
    ++
    + /*
    +  * Return 1 if and only if the repository has a commit-graph
    +  * file and generation numbers are computed in that file.
    +
      diff --git a/fuzz-commit-graph.c b/fuzz-commit-graph.c
      new file mode 100644
      --- /dev/null
      +++ b/fuzz-commit-graph.c
     @@
    -+#include "object-store.h"
     +#include "commit-graph.h"
     +
     +struct commit_graph *parse_commit_graph(void *graph_map, int fd,
    @@ -179,9 +177,8 @@
     +{
     +	struct commit_graph *g;
     +
    -+	g = parse_commit_graph((void *) data, -1, size);
    -+	if (g)
    -+		free(g);
    ++	g = parse_commit_graph((void *)data, -1, size);
    ++	free(g);
     +
     +	return 0;
     +}
2:  ad2e761f44 ! 2:  af45c2337f commit-graph: fix buffer read-overflow
    @@ -22,7 +22,8 @@
     +		uint64_t chunk_offset;
      		int chunk_repeated = 0;
      
    -+		if (chunk_lookup + GRAPH_CHUNKLOOKUP_WIDTH > data + graph_size) {
    ++		if (chunk_lookup + GRAPH_CHUNKLOOKUP_WIDTH >
    ++		    data + graph_size) {
     +			error(_("chunk lookup table entry missing; graph file may be incomplete"));
     +			free(graph);
     +			return NULL;
    @@ -34,3 +35,49 @@
      		chunk_lookup += GRAPH_CHUNKLOOKUP_WIDTH;
      
      		if (chunk_offset > graph_size - GIT_MAX_RAWSZ) {
    +
    + diff --git a/t/t5318-commit-graph.sh b/t/t5318-commit-graph.sh
    + --- a/t/t5318-commit-graph.sh
    + +++ b/t/t5318-commit-graph.sh
    +@@
    + 	test_i18ngrep "$grepstr" err
    + }
    + 
    ++
    ++# usage: corrupt_and_zero_graph_then_verify <corrupt_position> <data> <zero_position> <string>
    ++# Manipulates the commit-graph file at <corrupt_position> by inserting the data,
    ++# then zeros the file starting at <zero_position>. Finally, runs
    ++# 'git commit-graph verify' and places the output in the file 'err'. Tests 'err'
    ++# for the given string.
    ++corrupt_and_zero_graph_then_verify() {
    ++	corrupt_pos=$1
    ++	data="${2:-\0}"
    ++	zero_pos=$3
    ++	grepstr=$4
    ++	orig_size=$(stat --format=%s $objdir/info/commit-graph)
    ++	cd "$TRASH_DIRECTORY/full" &&
    ++	test_when_finished mv commit-graph-backup $objdir/info/commit-graph &&
    ++	cp $objdir/info/commit-graph commit-graph-backup &&
    ++	printf "$data" | dd of="$objdir/info/commit-graph" bs=1 seek="$corrupt_pos" conv=notrunc &&
    ++	truncate --size=$zero_pos $objdir/info/commit-graph &&
    ++	truncate --size=$orig_size $objdir/info/commit-graph &&
    ++	test_must_fail git commit-graph verify 2>test_err &&
    ++	grep -v "^+" test_err >err &&
    ++	test_i18ngrep "$grepstr" err
    ++}
    ++
    + test_expect_success 'detect bad signature' '
    + 	corrupt_graph_and_verify 0 "\0" \
    + 		"graph signature"
    +@@
    + 		"incorrect checksum"
    + '
    + 
    ++test_expect_success 'detect truncated graph' '
    ++	corrupt_and_zero_graph_then_verify $GRAPH_BYTE_CHUNK_COUNT "\xff" \
    ++		$GRAPH_CHUNK_LOOKUP_OFFSET "chunk lookup table entry missing"
    ++'
    ++
    + test_expect_success 'git fsck (checks commit-graph)' '
    + 	cd "$TRASH_DIRECTORY/full" &&
    + 	git fsck &&
-:  ---------- > 3:  7519fc76df Makefile: correct example fuzz build
-- 
2.20.0.rc2.10.g7519fc76df