diff options
author | Miod Vallat <miod@online.fr> | 2021-01-08 18:59:00 +0000 |
---|---|---|
committer | Kyle Evans <kevans@FreeBSD.org> | 2021-01-24 03:04:58 +0000 |
commit | 912086c27f9ab75253af8ae7914ae6001035a1b2 (patch) | |
tree | d6f5aab940afb7c441aa39860f00019508367fe1 | |
parent | 9ffee7b1eaeb4b48acd89d7be95fe627e9626724 (diff) | |
download | src-912086c27f9ab75253af8ae7914ae6001035a1b2.tar.gz src-912086c27f9ab75253af8ae7914ae6001035a1b2.zip |
libc: regex: rework unsafe pointer arithmetic
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.
PR: 252403
(cherry picked from commit d36b5dbe28d8ebab219fa29db533734d47f0c4a3)
-rw-r--r-- | lib/libc/regex/regcomp.c | 26 |
1 files changed, 14 insertions, 12 deletions
diff --git a/lib/libc/regex/regcomp.c b/lib/libc/regex/regcomp.c index 00ab6a77141b..fc66ea32046a 100644 --- a/lib/libc/regex/regcomp.c +++ b/lib/libc/regex/regcomp.c @@ -177,10 +177,10 @@ 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 SEESPEC(a) (p->bre ? SEETWO('\\', a) : SEE(a)) #define EAT(c) ((SEE(c)) ? (NEXT(), 1) : 0) #define EATTWO(a, b) ((SEETWO(a, b)) ? (NEXT2(), 1) : 0) @@ -997,15 +997,17 @@ p_bracket(struct parse *p) wint_t ch; /* 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) |