fix aliasing-based undefined behavior in string functions

use the GNU C may_alias attribute if available, and fallback to naive
byte-by-byte loops if __GNUC__ is not defined.

this patch has been written to minimize changes so that history
remains reviewable; it does not attempt to bring the affected code
into a more consistent or elegant form.

8 files changed, 46 insertions, 19 deletions

diff --git a/src/string/memccpy.c b/src/string/memccpy.c
index 7c233d5e..f515581c 100644
--- a/src/string/memccpy.c
+++ b/src/string/memccpy.c
@@ -11,19 +11,22 @@ void *memccpy(void *restrict dest, const void *restrict src, int c, size_t n)
 {
 	unsigned char *d = dest;
 	const unsigned char *s = src;
-	size_t *wd, k;
-	const size_t *ws;
 
 	c = (unsigned char)c;
+#ifdef __GNUC__
+	typedef size_t __attribute__((__may_alias__)) word;
+	word *wd;
+	const word *ws;
 	if (((uintptr_t)s & ALIGN) == ((uintptr_t)d & ALIGN)) {
 		for (; ((uintptr_t)s & ALIGN) && n && (*d=*s)!=c; n--, s++, d++);
 		if ((uintptr_t)s & ALIGN) goto tail;
-		k = ONES * c;
+		size_t k = ONES * c;
 		wd=(void *)d; ws=(const void *)s;
 		for (; n>=sizeof(size_t) && !HASZERO(*ws^k);
 		       n-=sizeof(size_t), ws++, wd++) *wd = *ws;
 		d=(void *)wd; s=(const void *)ws;
 	}
+#endif
 	for (; n && (*d=*s)!=c; n--, s++, d++);
 tail:
 	if (*s==c) return d+1;
diff --git a/src/string/memchr.c b/src/string/memchr.c
index 4daff7bb..65f0d789 100644
--- a/src/string/memchr.c
+++ b/src/string/memchr.c
@@ -12,12 +12,16 @@ void *memchr(const void *src, int c, size_t n)
 {
 	const unsigned char *s = src;
 	c = (unsigned char)c;
+#ifdef __GNUC__
 	for (; ((uintptr_t)s & ALIGN) && n && *s != c; s++, n--);
 	if (n && *s != c) {
-		const size_t *w;
+		typedef size_t __attribute__((__may_alias__)) word;
+		const word *w;
 		size_t k = ONES * c;
 		for (w = (const void *)s; n>=SS && !HASZERO(*w^k); w++, n-=SS);
-		for (s = (const void *)w; n && *s != c; s++, n--);
+		s = (const void *)w;
 	}
+#endif
+	for (; n && *s != c; s++, n--);
 	return n ? (void *)s : 0;
 }
diff --git a/src/string/memmove.c b/src/string/memmove.c
index f225bb30..5dc9cdb9 100644
--- a/src/string/memmove.c
+++ b/src/string/memmove.c
@@ -1,8 +1,10 @@
 #include <string.h>
 #include <stdint.h>
 
-#define WT size_t
+#ifdef __GNUC__
+typedef __attribute__((__may_alias__)) size_t WT;
 #define WS (sizeof(WT))
+#endif
 
 void *memmove(void *dest, const void *src, size_t n)
 {
@@ -13,6 +15,7 @@ void *memmove(void *dest, const void *src, size_t n)
 	if ((uintptr_t)s-(uintptr_t)d-n <= -2*n) return memcpy(d, s, n);
 
 	if (d<s) {
+#ifdef __GNUC__
 		if ((uintptr_t)s % WS == (uintptr_t)d % WS) {
 			while ((uintptr_t)d % WS) {
 				if (!n--) return dest;
@@ -20,8 +23,10 @@ void *memmove(void *dest, const void *src, size_t n)
 			}
 			for (; n>=WS; n-=WS, d+=WS, s+=WS) *(WT *)d = *(WT *)s;
 		}
+#endif
 		for (; n; n--) *d++ = *s++;
 	} else {
+#ifdef __GNUC__
 		if ((uintptr_t)s % WS == (uintptr_t)d % WS) {
 			while ((uintptr_t)(d+n) % WS) {
 				if (!n--) return dest;
@@ -29,6 +34,7 @@ void *memmove(void *dest, const void *src, size_t n)
 			}
 			while (n>=WS) n-=WS, *(WT *)(d+n) = *(WT *)(s+n);
 		}
+#endif
 		while (n) n--, d[n] = s[n];
 	}
 
diff --git a/src/string/stpcpy.c b/src/string/stpcpy.c
index 54cf9ca5..4db46a9e 100644
--- a/src/string/stpcpy.c
+++ b/src/string/stpcpy.c
@@ -9,9 +9,10 @@
 
 char *__stpcpy(char *restrict d, const char *restrict s)
 {
-	size_t *wd;
-	const size_t *ws;
-
+#ifdef __GNUC__
+	typedef size_t __attribute__((__may_alias__)) word;
+	word *wd;
+	const word *ws;
 	if ((uintptr_t)s % ALIGN == (uintptr_t)d % ALIGN) {
 		for (; (uintptr_t)s % ALIGN; s++, d++)
 			if (!(*d=*s)) return d;
@@ -19,6 +20,7 @@ char *__stpcpy(char *restrict d, const char *restrict s)
 		for (; !HASZERO(*ws); *wd++ = *ws++);
 		d=(void *)wd; s=(const void *)ws;
 	}
+#endif
 	for (; (*d=*s); s++, d++);
 
 	return d;
diff --git a/src/string/stpncpy.c b/src/string/stpncpy.c
index d6d92ffc..f57fa6b7 100644
--- a/src/string/stpncpy.c
+++ b/src/string/stpncpy.c
@@ -9,9 +9,10 @@
 
 char *__stpncpy(char *restrict d, const char *restrict s, size_t n)
 {
-	size_t *wd;
-	const size_t *ws;
-
+#ifdef __GNUC__
+	typedef size_t __attribute__((__may_alias__)) word;
+	word *wd;
+	const word *ws;
 	if (((uintptr_t)s & ALIGN) == ((uintptr_t)d & ALIGN)) {
 		for (; ((uintptr_t)s & ALIGN) && n && (*d=*s); n--, s++, d++);
 		if (!n || !*s) goto tail;
@@ -20,6 +21,7 @@ char *__stpncpy(char *restrict d, const char *restrict s, size_t n)
 		       n-=sizeof(size_t), ws++, wd++) *wd = *ws;
 		d=(void *)wd; s=(const void *)ws;
 	}
+#endif
 	for (; n && (*d=*s); n--, s++, d++);
 tail:
 	memset(d, 0, n);
diff --git a/src/string/strchrnul.c b/src/string/strchrnul.c
index f2b9ae11..39e2635b 100644
--- a/src/string/strchrnul.c
+++ b/src/string/strchrnul.c
@@ -9,16 +9,19 @@
 
 char *__strchrnul(const char *s, int c)
 {
-	size_t *w, k;
-
 	c = (unsigned char)c;
 	if (!c) return (char *)s + strlen(s);
 
+#ifdef __GNUC__
+	typedef size_t __attribute__((__may_alias__)) word;
+	const word *w;
 	for (; (uintptr_t)s % ALIGN; s++)
 		if (!*s || *(unsigned char *)s == c) return (char *)s;
-	k = ONES * c;
+	size_t k = ONES * c;
 	for (w = (void *)s; !HASZERO(*w) && !HASZERO(*w^k); w++);
-	for (s = (void *)w; *s && *(unsigned char *)s != c; s++);
+	s = (void *)w;
+#endif
+	for (; *s && *(unsigned char *)s != c; s++);
 	return (char *)s;
 }
 
diff --git a/src/string/strlcpy.c b/src/string/strlcpy.c
index dcb22f6e..ffa0b0b0 100644
--- a/src/string/strlcpy.c
+++ b/src/string/strlcpy.c
@@ -12,9 +12,11 @@ size_t strlcpy(char *d, const char *s, size_t n)
 {
 	char *d0 = d;
 	size_t *wd;
-	const size_t *ws;
 
 	if (!n--) goto finish;
+#ifdef __GNUC__
+	typedef size_t __attribute__((__may_alias__)) word;
+	const word *ws;
 	if (((uintptr_t)s & ALIGN) == ((uintptr_t)d & ALIGN)) {
 		for (; ((uintptr_t)s & ALIGN) && n && (*d=*s); n--, s++, d++);
 		if (n && *s) {
@@ -24,6 +26,7 @@ size_t strlcpy(char *d, const char *s, size_t n)
 			d=(void *)wd; s=(const void *)ws;
 		}
 	}
+#endif
 	for (; n && (*d=*s); n--, s++, d++);
 	*d = 0;
 finish:
diff --git a/src/string/strlen.c b/src/string/strlen.c
index 929ddcbc..309990f0 100644
--- a/src/string/strlen.c
+++ b/src/string/strlen.c
@@ -10,9 +10,13 @@
 size_t strlen(const char *s)
 {
 	const char *a = s;
-	const size_t *w;
+#ifdef __GNUC__
+	typedef size_t __attribute__((__may_alias__)) word;
+	const word *w;
 	for (; (uintptr_t)s % ALIGN; s++) if (!*s) return s-a;
 	for (w = (const void *)s; !HASZERO(*w); w++);
-	for (s = (const void *)w; *s; s++);
+	s = (const void *)w;
+#endif
+	for (; *s; s++);
 	return s-a;
 }