[PATCH v3 6/9] index-helper: add --strict

["Nguyễn Thái Ngọc Duy" <pclouds@gmail.com>]

There's are "holes" in the index-helper approach because the shared
memory is not verified again by git. If $USER is compromised, shared
memory could be modified. But then they can already modify
$GIT_DIR/index. A more realistic risk is some bugs in index-helper
produce corrupt shared memory. --strict is added to avoid that

Strictly speaking there's still a very small gap where corrupt shared
memory could still be read by git: after we write the trailing SHA-1 in
the shared memory (thus signaling "this shm is ready") and before
verify_shm() detects an error.

Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
---
 Documentation/git-index-helper.txt |  9 ++++++++
 cache.h                            |  1 +
 index-helper.c                     | 47 ++++++++++++++++++++++++++++++++++++++
 read-cache.c                       |  9 +++++---
 4 files changed, 63 insertions(+), 3 deletions(-)

diff --git a/Documentation/git-index-helper.txt b/Documentation/git-index-helper.txt
index da41c4d..406856d 100644
--- a/Documentation/git-index-helper.txt
+++ b/Documentation/git-index-helper.txt
@@ -22,6 +22,15 @@ OPTIONS
 	Exit if the cached index is not accessed for `<n>`
 	minutes. Specify 0 to wait forever. Default is 10.
 
+--strict::
+--no-strict::
+	Strict mode makes index-helper verify the shared memory after
+	it's created. If the result does not match what's read from
+	$GIT_DIR/index, the shared memory is destroyed. This makes
+	index-helper take more than double the amount of time required
+	for reading an index, but because it will happen in the
+	background, it's not noticable. `--strict` is enabled by default.
+
 NOTES
 -----
 On UNIX-like systems, $GIT_DIR/index-helper.pid contains the process
diff --git a/cache.h b/cache.h
index 4266771..0f515e5 100644
--- a/cache.h
+++ b/cache.h
@@ -307,6 +307,7 @@ struct index_state {
 	struct cache_time timestamp;
 	unsigned name_hash_initialized : 1,
 		 keep_mmap : 1,
+		 always_verify_trailing_sha1 : 1,
 		 initialized : 1;
 	struct hashmap name_hash;
 	struct hashmap dir_hash;
diff --git a/index-helper.c b/index-helper.c
index 8fa0af9..c82d307 100644
--- a/index-helper.c
+++ b/index-helper.c
@@ -13,6 +13,7 @@ struct index_shm {
 
 static struct index_shm shm_index;
 static struct index_shm shm_base_index;
+static int to_verify = 1;
 
 static void free_index_shm(struct index_shm *is)
 {
@@ -68,6 +69,48 @@ static void share_index(struct index_state *istate, struct index_shm *is)
 	hashcpy((unsigned char *)new_mmap + istate->mmap_size - 20, is->sha1);
 }
 
+static int verify_shm(void)
+{
+	int i;
+	struct index_state istate;
+	memset(&istate, 0, sizeof(istate));
+	istate.always_verify_trailing_sha1 = 1;
+	i = read_index(&istate);
+	if (i != the_index.cache_nr)
+		goto done;
+	for (; i < the_index.cache_nr; i++) {
+		struct cache_entry *base, *ce;
+		/* namelen is checked separately */
+		const unsigned int ondisk_flags =
+			CE_STAGEMASK | CE_VALID | CE_EXTENDED_FLAGS;
+		unsigned int ce_flags, base_flags, ret;
+		base = the_index.cache[i];
+		ce = istate.cache[i];
+		if (ce->ce_namelen != base->ce_namelen ||
+		    strcmp(ce->name, base->name)) {
+			warning("mismatch at entry %d", i);
+			break;
+		}
+		ce_flags = ce->ce_flags;
+		base_flags = base->ce_flags;
+		/* only on-disk flags matter */
+		ce->ce_flags   &= ondisk_flags;
+		base->ce_flags &= ondisk_flags;
+		ret = memcmp(&ce->ce_stat_data, &base->ce_stat_data,
+			     offsetof(struct cache_entry, name) -
+			     offsetof(struct cache_entry, ce_stat_data));
+		ce->ce_flags = ce_flags;
+		base->ce_flags = base_flags;
+		if (ret) {
+			warning("mismatch at entry %d", i);
+			break;
+		}
+	}
+done:
+	discard_index(&istate);
+	return i == the_index.cache_nr;
+}
+
 static void refresh(int sig)
 {
 	the_index.keep_mmap = 1;
@@ -76,6 +119,8 @@ static void refresh(int sig)
 	if (the_index.split_index && the_index.split_index->base)
 		share_index(the_index.split_index->base, &shm_base_index);
 	share_index(&the_index, &shm_index);
+	if (to_verify && !verify_shm())
+		cleanup_shm();
 	discard_index(&the_index);
 }
 
@@ -123,6 +168,8 @@ int main(int argc, char **argv)
 	struct option options[] = {
 		OPT_INTEGER(0, "exit-after", &idle_in_minutes,
 			    N_("exit if not used after some minutes")),
+		OPT_BOOL(0, "strict", &to_verify,
+			 "verify shared memory after creating"),
 		OPT_END()
 	};
 
diff --git a/read-cache.c b/read-cache.c
index 4bd2abe..d6eb17f 100644
--- a/read-cache.c
+++ b/read-cache.c
@@ -1568,9 +1568,12 @@ int do_read_index(struct index_state *istate, const char *path, int must_exist)
 
 	istate->mmap = mmap;
 	istate->mmap_size = mmap_size;
-	if (try_shm(istate) &&
-	    verify_hdr(istate->mmap, istate->mmap_size) < 0)
-		goto unmap;
+	if (try_shm(istate)) {
+		if (verify_hdr(istate->mmap, istate->mmap_size) < 0)
+			goto unmap;
+	} else if (istate->always_verify_trailing_sha1 &&
+		   verify_hdr(istate->mmap, istate->mmap_size) < 0)
+			goto unmap;
 	hdr = mmap = istate->mmap;
 	mmap_size = istate->mmap_size;
 	if (!istate->keep_mmap)
-- 
2.1.0.rc0.66.gb9187ad