summaryrefslogtreecommitdiff
path: root/lib/libc/regex
diff options
context:
space:
mode:
authorTheo Buehler <tb@cvs.openbsd.org>2020-12-30 08:59:18 +0000
committerTheo Buehler <tb@cvs.openbsd.org>2020-12-30 08:59:18 +0000
commitb18aadc29809b27bbd884d2515a338d080ba8168 (patch)
tree26df4f1e85f7be54b3e07573b59df23279aeb9de /lib/libc/regex
parent0a06cb68fce6a8ef263ea09c1ef7c868f8bba311 (diff)
regcomp.c uses the "start + count < end" idiom to check that there are
"count" bytes available in an array of char "start" and "end" both point to. This is fine, unless "start + count" goes beyond the last element of the array. In this case, pedantic interpretation of the C standard makes the comparison of such a pointer against "end" undefined, and optimizers from hell will happily remove as much code as possible because of this. An example of this occurs in regcomp.c's bothcases(), which defines bracket[3], sets "next" to "bracket" and "end" to "bracket + 2". Then it invokes p_bracket(), which starts with "if (p->next + 5 < p->end)"... Because bothcases() and p_bracket() are static functions in regcomp.c, there is a real risk of miscompilation if aggressive inlining happens. The following diff rewrites the "start + count < end" constructs into "end - start > count". Assuming "end" and "start" are always pointing in the array (such as "bracket[3]" above), "end - start" is well-defined and can be compared without trouble. As a bonus, MORE2() implies MORE() therefore SEETWO() can be simplified a bit. from miod, ok millert
Diffstat (limited to 'lib/libc/regex')
-rw-r--r--lib/libc/regex/regcomp.c28
1 files changed, 15 insertions, 13 deletions
diff --git a/lib/libc/regex/regcomp.c b/lib/libc/regex/regcomp.c
index fb8b5687060..d7f06dd8bed 100644
--- a/lib/libc/regex/regcomp.c
+++ b/lib/libc/regex/regcomp.c
@@ -1,4 +1,4 @@
-/* $OpenBSD: regcomp.c,v 1.37 2020/12/30 08:54:42 tb Exp $ */
+/* $OpenBSD: regcomp.c,v 1.38 2020/12/30 08:59:17 tb Exp $ */
/*-
* Copyright (c) 1992, 1993, 1994 Henry Spencer.
* Copyright (c) 1992, 1993, 1994
@@ -110,10 +110,10 @@ static char nuls[10]; /* place to point scanner in event of error */
*/
#define PEEK() (*p->next)
#define PEEK2() (*(p->next+1))
-#define MORE() (p->next < p->end)
-#define MORE2() (p->next+1 < p->end)
+#define MORE() (p->end - p->next > 0)
+#define MORE2() (p->end - p->next > 1)
#define SEE(c) (MORE() && PEEK() == (c))
-#define SEETWO(a, b) (MORE() && MORE2() && PEEK() == (a) && PEEK2() == (b))
+#define SEETWO(a, b) (MORE2() && PEEK() == (a) && PEEK2() == (b))
#define EAT(c) ((SEE(c)) ? (NEXT(), 1) : 0)
#define EATTWO(a, b) ((SEETWO(a, b)) ? (NEXT2(), 1) : 0)
#define NEXT() (p->next++)
@@ -620,15 +620,17 @@ p_bracket(struct parse *p)
int invert = 0;
/* Dept of Truly Sickening Special-Case Kludges */
- if (p->next + 5 < p->end && strncmp(p->next, "[:<:]]", 6) == 0) {
- EMIT(OBOW, 0);
- NEXTn(6);
- return;
- }
- if (p->next + 5 < p->end && strncmp(p->next, "[:>:]]", 6) == 0) {
- EMIT(OEOW, 0);
- NEXTn(6);
- return;
+ if (p->end - p->next > 5) {
+ if (strncmp(p->next, "[:<:]]", 6) == 0) {
+ EMIT(OBOW, 0);
+ NEXTn(6);
+ return;
+ }
+ if (strncmp(p->next, "[:>:]]", 6) == 0) {
+ EMIT(OEOW, 0);
+ NEXTn(6);
+ return;
+ }
}
if ((cs = allocset(p)) == NULL) {