[PATCH v2] cleanup: fix possible overflow errors in binary search

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



A common mistake when writing binary search is to allow possible
integer overflow by using the simple average:

	mid = (min + max) / 2;

Instead, use the overflow-safe version:

	mid = min + (max - min) / 2;

This translation is safe since the operation occurs inside a loop
conditioned on "min < max". The included changes were found using
the following git grep:

	git grep '/ *2;' '*.c'

Making this cleanup will prevent future review friction when a new
binary search is contructed based on existing code.

Signed-off-by: Derrick Stolee <dstolee@xxxxxxxxxxxxx>
---
 builtin/index-pack.c          | 4 ++--
 builtin/pack-objects.c        | 2 +-
 builtin/unpack-objects.c      | 2 +-
 cache-tree.c                  | 2 +-
 compat/regex/regex_internal.c | 4 ++--
 compat/regex/regexec.c        | 2 +-
 packfile.c                    | 2 +-
 sha1-lookup.c                 | 4 ++--
 sha1_name.c                   | 2 +-
 string-list.c                 | 2 +-
 utf8.c                        | 2 +-
 xdiff/xpatience.c             | 2 +-
 12 files changed, 15 insertions(+), 15 deletions(-)

diff --git a/builtin/index-pack.c b/builtin/index-pack.c
index f2be145e1..8ec459f52 100644
--- a/builtin/index-pack.c
+++ b/builtin/index-pack.c
@@ -633,7 +633,7 @@ static int find_ofs_delta(const off_t offset, enum object_type type)
 	int first = 0, last = nr_ofs_deltas;
 
 	while (first < last) {
-		int next = (first + last) / 2;
+		int next = first + (last - first) / 2;
 		struct ofs_delta_entry *delta = &ofs_deltas[next];
 		int cmp;
 
@@ -687,7 +687,7 @@ static int find_ref_delta(const unsigned char *sha1, enum object_type type)
 	int first = 0, last = nr_ref_deltas;
 
 	while (first < last) {
-		int next = (first + last) / 2;
+		int next = first + (last - first) / 2;
 		struct ref_delta_entry *delta = &ref_deltas[next];
 		int cmp;
 
diff --git a/builtin/pack-objects.c b/builtin/pack-objects.c
index 5ee2c48ff..6e77dfd44 100644
--- a/builtin/pack-objects.c
+++ b/builtin/pack-objects.c
@@ -1277,7 +1277,7 @@ static int done_pbase_path_pos(unsigned hash)
 	int lo = 0;
 	int hi = done_pbase_paths_num;
 	while (lo < hi) {
-		int mi = (hi + lo) / 2;
+		int mi = lo + (hi - lo) / 2;
 		if (done_pbase_paths[mi] == hash)
 			return mi;
 		if (done_pbase_paths[mi] < hash)
diff --git a/builtin/unpack-objects.c b/builtin/unpack-objects.c
index 689a29fac..62ea264c4 100644
--- a/builtin/unpack-objects.c
+++ b/builtin/unpack-objects.c
@@ -394,7 +394,7 @@ static void unpack_delta_entry(enum object_type type, unsigned long delta_size,
 		lo = 0;
 		hi = nr;
 		while (lo < hi) {
-			mid = (lo + hi)/2;
+			mid = lo + (hi - lo) / 2;
 			if (base_offset < obj_list[mid].offset) {
 				hi = mid;
 			} else if (base_offset > obj_list[mid].offset) {
diff --git a/cache-tree.c b/cache-tree.c
index 71d092ed5..d3f740127 100644
--- a/cache-tree.c
+++ b/cache-tree.c
@@ -49,7 +49,7 @@ static int subtree_pos(struct cache_tree *it, const char *path, int pathlen)
 	lo = 0;
 	hi = it->subtree_nr;
 	while (lo < hi) {
-		int mi = (lo + hi) / 2;
+		int mi = lo + (hi - lo) / 2;
 		struct cache_tree_sub *mdl = down[mi];
 		int cmp = subtree_name_cmp(path, pathlen,
 					   mdl->name, mdl->namelen);
diff --git a/compat/regex/regex_internal.c b/compat/regex/regex_internal.c
index d4121f2f4..98342b831 100644
--- a/compat/regex/regex_internal.c
+++ b/compat/regex/regex_internal.c
@@ -613,7 +613,7 @@ re_string_reconstruct (re_string_t *pstr, int idx, int eflags)
 	      int low = 0, high = pstr->valid_len, mid;
 	      do
 		{
-		  mid = (high + low) / 2;
+		  mid = low + (high - low) / 2;
 		  if (pstr->offsets[mid] > offset)
 		    high = mid;
 		  else if (pstr->offsets[mid] < offset)
@@ -1394,7 +1394,7 @@ re_node_set_contains (const re_node_set *set, int elem)
   right = set->nelem - 1;
   while (idx < right)
     {
-      mid = (idx + right) / 2;
+      mid = idx + (right - idx) / 2;
       if (set->elems[mid] < elem)
 	idx = mid + 1;
       else
diff --git a/compat/regex/regexec.c b/compat/regex/regexec.c
index 0a745d9c3..6f2b48a78 100644
--- a/compat/regex/regexec.c
+++ b/compat/regex/regexec.c
@@ -4284,7 +4284,7 @@ search_cur_bkref_entry (const re_match_context_t *mctx, int str_idx)
   last = right = mctx->nbkref_ents;
   for (left = 0; left < right;)
     {
-      mid = (left + right) / 2;
+      mid = left + (right - left) / 2;
       if (mctx->bkref_ents[mid].str_idx < str_idx)
 	left = mid + 1;
       else
diff --git a/packfile.c b/packfile.c
index eab754248..4a5fe7ab1 100644
--- a/packfile.c
+++ b/packfile.c
@@ -1743,7 +1743,7 @@ off_t find_pack_entry_one(const unsigned char *sha1,
 		       sha1[0], sha1[1], sha1[2], lo, hi, p->num_objects);
 
 	while (lo < hi) {
-		unsigned mi = (lo + hi) / 2;
+		unsigned mi = lo + (hi - lo) / 2;
 		int cmp = hashcmp(index + mi * stride, sha1);
 
 		if (debug_lookup)
diff --git a/sha1-lookup.c b/sha1-lookup.c
index 2552b7902..4cf3ebd92 100644
--- a/sha1-lookup.c
+++ b/sha1-lookup.c
@@ -10,7 +10,7 @@ static uint32_t take2(const unsigned char *sha1)
  * Conventional binary search loop looks like this:
  *
  *      do {
- *              int mi = (lo + hi) / 2;
+ *              int mi = lo + (hi - lo) / 2;
  *              int cmp = "entry pointed at by mi" minus "target";
  *              if (!cmp)
  *                      return (mi is the wanted one)
@@ -95,7 +95,7 @@ int sha1_pos(const unsigned char *sha1, void *table, size_t nr,
 			hi = mi;
 		else
 			lo = mi + 1;
-		mi = (hi + lo) / 2;
+		mi = lo + (hi - lo) / 2;
 	} while (lo < hi);
 	return -lo-1;
 }
diff --git a/sha1_name.c b/sha1_name.c
index 134ac9742..c7c5ab376 100644
--- a/sha1_name.c
+++ b/sha1_name.c
@@ -157,7 +157,7 @@ static void unique_in_pack(struct packed_git *p,
 	num = p->num_objects;
 	last = num;
 	while (first < last) {
-		uint32_t mid = (first + last) / 2;
+		uint32_t mid = first + (last - first) / 2;
 		const unsigned char *current;
 		int cmp;
 
diff --git a/string-list.c b/string-list.c
index 806b4c872..a0cf0cfe8 100644
--- a/string-list.c
+++ b/string-list.c
@@ -16,7 +16,7 @@ static int get_entry_index(const struct string_list *list, const char *string,
 	compare_strings_fn cmp = list->cmp ? list->cmp : strcmp;
 
 	while (left + 1 < right) {
-		int middle = (left + right) / 2;
+		int middle = left + (right - left) / 2;
 		int compare = cmp(string, list->items[middle].string);
 		if (compare < 0)
 			right = middle;
diff --git a/utf8.c b/utf8.c
index 47a42047c..2c27ce013 100644
--- a/utf8.c
+++ b/utf8.c
@@ -32,7 +32,7 @@ static int bisearch(ucs_char_t ucs, const struct interval *table, int max)
 	if (ucs < table[0].first || ucs > table[max].last)
 		return 0;
 	while (max >= min) {
-		mid = (min + max) / 2;
+		mid = min + (max - min) / 2;
 		if (ucs > table[mid].last)
 			min = mid + 1;
 		else if (ucs < table[mid].first)
diff --git a/xdiff/xpatience.c b/xdiff/xpatience.c
index a613efc70..9f91702de 100644
--- a/xdiff/xpatience.c
+++ b/xdiff/xpatience.c
@@ -166,7 +166,7 @@ static int binary_search(struct entry **sequence, int longest,
 	int left = -1, right = longest;
 
 	while (left + 1 < right) {
-		int middle = (left + right) / 2;
+		int middle = left + (right - left) / 2;
 		/* by construction, no two entries can be equal */
 		if (sequence[middle]->line2 > entry->line2)
 			right = middle;
-- 
2.14.1.538.g56ec8fc98.dirty




[Index of Archives]     [Linux Kernel Development]     [Gcc Help]     [IETF Annouce]     [DCCP]     [Netdev]     [Networking]     [Security]     [V4L]     [Bugtraq]     [Yosemite]     [MIPS Linux]     [ARM Linux]     [Linux Security]     [Linux RAID]     [Linux SCSI]     [Fedora Users]

  Powered by Linux