[PATCH] cleanup: fix possible overflow errors in binary search, part 2

From: René Scharfe <l.s.r@web.de>
Date: Jun 13, 2019, 17:51 UTC
Message-ID: <f0059613-d3e4-a1e2-2c01-727579e069d2@web.de>

Calculating the sum of two array indexes to find the midpoint between them can overflow, i.e. code like this is unsafe for big arrays:

	mid = (first + last) >> 1;

Make sure the intermediate value stays within the boundaries instead, like this:

	mid = first + ((last - first) >> 1);

The loop condition of the binary search makes sure that 'last' is always greater than 'first', so this is safe as long as 'first' is not negative. And that can be verified easily using the pre-context of each change, except for name-hash.c, so add an assertion to that effect there.

The unsafe calculations were found with:

	git grep '(.*+.*) *>> *1'

This is a continuation of 19716b21a4 (cleanup: fix possible overflow errors in binary search, 2017-10-08).

Signed-off-by: Rene Scharfe <l.s.r@web.de>
---
 builtin/ls-files.c  | 2 +-
 diffcore-rename.c   | 4 ++--
 dir.c               | 2 +-
 name-hash.c         | 3 ++-
 read-cache.c        | 2 +-
 sh-i18n--envsubst.c | 2 +-
 6 files changed, 8 insertions(+), 7 deletions(-)

diff --git a/builtin/ls-files.c b/builtin/ls-files.c
index 7f83c9a6f2..670e8fb93c 100644
--- a/builtin/ls-files.c
+++ b/builtin/ls-files.c
@@ -373,7 +373,7 @@ static void prune_index(struct index_state *istate,
 	first = pos;
 	last = istate->cache_nr;
 	while (last > first) {
-		int next = (last + first) >> 1;
+		int next = first + ((last - first) >> 1);
 		const struct cache_entry *ce = istate->cache[next];
 		if (!strncmp(ce->name, prefix, prefixlen)) {
 			first = next+1;
diff --git a/diffcore-rename.c b/diffcore-rename.c
index 07bd34b631..6af92d5eba 100644
--- a/diffcore-rename.c
+++ b/diffcore-rename.c
@@ -23,7 +23,7 @@ static int find_rename_dst(struct diff_filespec *two)
 	first = 0;
 	last = rename_dst_nr;
 	while (last > first) {
-		int next = (last + first) >> 1;
+		int next = first + ((last - first) >> 1);
 		struct diff_rename_dst *dst = &(rename_dst[next]);
 		int cmp = strcmp(two->path, dst->two->path);
 		if (!cmp)
@@ -83,7 +83,7 @@ static struct diff_rename_src *register_rename_src(struct diff_filepair *p)
 	first = 0;
 	last = rename_src_nr;
 	while (last > first) {
-		int next = (last + first) >> 1;
+		int next = first + ((last - first) >> 1);
 		struct diff_rename_src *src = &(rename_src[next]);
 		int cmp = strcmp(one->path, src->p->one->path);
 		if (!cmp)
diff --git a/dir.c b/dir.c
index ba4a51c296..d021c908e5 100644
--- a/dir.c
+++ b/dir.c
@@ -701,7 +701,7 @@ static struct untracked_cache_dir *lookup_untracked(struct untracked_cache *uc,
 	first = 0;
 	last = dir->dirs_nr;
 	while (last > first) {
-		int cmp, next = (last + first) >> 1;
+		int cmp, next = first + ((last - first) >> 1);
 		d = dir->dirs[next];
 		cmp = strncmp(name, d->name, len);
 		if (!cmp && strlen(d->name) > len)
diff --git a/name-hash.c b/name-hash.c
index b4861bc7b0..695908609f 100644
--- a/name-hash.c
+++ b/name-hash.c
@@ -345,8 +345,9 @@ static int handle_range_dir(
 	else {
 		int begin = k_start;
 		int end = k_end;
+		assert(begin >= 0);
 		while (begin < end) {
-			int mid = (begin + end) >> 1;
+			int mid = begin + ((end - begin) >> 1);
 			int cmp = strncmp(istate->cache[mid]->name, prefix->buf, prefix->len);
 			if (cmp == 0) /* mid has same prefix; look in second part */
 				begin = mid + 1;
diff --git a/read-cache.c b/read-cache.c
index 22e7b9944e..4f81fca320 100644
--- a/read-cache.c
+++ b/read-cache.c
@@ -549,7 +549,7 @@ static int index_name_stage_pos(const struct index_state *istate, const char *na
 	first = 0;
 	last = istate->cache_nr;
 	while (last > first) {
-		int next = (last + first) >> 1;
+		int next = first + ((last - first) >> 1);
 		struct cache_entry *ce = istate->cache[next];
 		int cmp = cache_name_stage_compare(name, namelen, stage, ce->name, ce_namelen(ce), ce_stage(ce));
 		if (!cmp)
diff --git a/sh-i18n--envsubst.c b/sh-i18n--envsubst.c
index cecfdd36c7..e7430b9aa8 100644
--- a/sh-i18n--envsubst.c
+++ b/sh-i18n--envsubst.c
@@ -249,7 +249,7 @@ sorted_string_list_member (const string_list_ty *slp, const char *s)
 	{
 	  /* Here we know that if s is in the list, it is at an index j
 	     with j1 <= j < j2.  */
-	  size_t j = (j1 + j2) >> 1;
+	  size_t j = j1 + ((j2 - j1) >> 1);
 	  int result = strcmp (slp->item[j], s);

 	  if (result > 0)
--
2.22.0