Use __builtin for various mem* and b* (e.g. bzero) routines.

Some of the routines were using artificially limited builtin already,
drop the explicit limit.

The use of builtins allows quite often allows the compiler to elide the call
or most zeroing to begin with. For instance, if the target object is 32 bytes
in size and gets zeroed + has 16 bytes initialized, the compiler can just
add code to zero out the rest.

Note not all the primites have asm variants and some of the existing ones
are not optimized. Maintaines are strongly encourage to take a look
(regardless of this change).

sys/dev/cx/machdep.h

@@ -73,7 +73,6 @@
 #   include <machine/cpufunc.h>
 #   include <sys/libkern.h>
 #   include <sys/systm.h>
-#   define memset(a,b,c)	bzero (a,c)
 #   define port_t int
 
 #ifndef _SYS_CDEFS_H_

sys/libkern/bcmp.c

@@ -44,7 +44,7 @@ typedef const unsigned long	*culp;
  * bcmp -- vax cmpc3 instruction
  */
 int
-bcmp(const void *b1, const void *b2, size_t length)
+(bcmp)(const void *b1, const void *b2, size_t length)
 {
 #if BYTE_ORDER == LITTLE_ENDIAN
 	/*

sys/libkern/memcmp.c

@@ -41,7 +41,7 @@ __FBSDID("$FreeBSD$");
  * Compare memory regions.
  */
 int
-memcmp(const void *s1, const void *s2, size_t n)
+(memcmp)(const void *s1, const void *s2, size_t n)
 {
 	if (n != 0) {
 		const unsigned char *p1 = s1, *p2 = s2;

sys/libkern/memset.c

@@ -33,7 +33,7 @@ __FBSDID("$FreeBSD$");
 #include <sys/libkern.h>
 
 void *
-memset(void *b, int c, size_t len)
+(memset)(void *b, int c, size_t len)
 {
 	char *bb;
 

sys/sys/libkern.h

@@ -128,7 +128,6 @@ struct malloc_type;
 uint32_t arc4random(void);
 void	 arc4random_buf(void *, size_t);
 void	 arc4rand(void *, u_int, int);
-int	 bcmp(const void *, const void *, size_t);
 int	 timingsafe_bcmp(const void *, const void *, size_t);
 void	*bsearch(const void *, const void *, size_t,
 	    size_t, int (*)(const void *, const void *));
@@ -160,7 +159,6 @@ int	 fnmatch(const char *, const char *, int);
 int	 locc(int, char *, u_int);
 void	*memchr(const void *s, int c, size_t n);
 void	*memcchr(const void *s, int c, size_t n);
-int	 memcmp(const void *b1, const void *b2, size_t len);
 void	*memmem(const void *l, size_t l_len, const void *s, size_t s_len);
 void	 qsort(void *base, size_t nmemb, size_t size,
 	    int (*compar)(const void *, const void *));

sys/sys/systm.h

@@ -259,25 +259,21 @@ void	hexdump(const void *ptr, int length, const char *hdr, int flags);
 
 #define ovbcopy(f, t, l) bcopy((f), (t), (l))
 void	bcopy(const void * _Nonnull from, void * _Nonnull to, size_t len);
-#define bcopy(from, to, len) ({				\
-	if (__builtin_constant_p(len) && (len) <= 64)	\
-		__builtin_memmove((to), (from), (len));	\
-	else						\
-		bcopy((from), (to), (len));		\
-})
+#define bcopy(from, to, len) __builtin_memmove((to), (from), (len))
 void	bzero(void * _Nonnull buf, size_t len);
-#define bzero(buf, len) ({				\
-	if (__builtin_constant_p(len) && (len) <= 64)	\
-		__builtin_memset((buf), 0, (len));	\
-	else						\
-		bzero((buf), (len));			\
-})
+#define bzero(buf, len) __builtin_memset((buf), 0, (len))
 void	explicit_bzero(void * _Nonnull, size_t);
+int	bcmp(const void *b1, const void *b2, size_t len);
+#define bcmp(b1, b2, len) __builtin_memcmp((b1), (b2), (len))
 
 void	*memset(void * _Nonnull buf, int c, size_t len);
+#define memset(buf, c, len) __builtin_memset((buf), (c), (len))
 void	*memcpy(void * _Nonnull to, const void * _Nonnull from, size_t len);
-#define memcpy(to, from, len) __builtin_memcpy(to, from, len)
+#define memcpy(to, from, len) __builtin_memcpy((to), (from), (len))
 void	*memmove(void * _Nonnull dest, const void * _Nonnull src, size_t n);
+#define memmove(dest, src, n) __builtin_memmove((dest), (src), (n))
+int	memcmp(const void *b1, const void *b2, size_t len);
+#define memcmp(b1, b2, len) __builtin_memcmp((b1), (b2), (len))
 
 int	copystr(const void * _Nonnull __restrict kfaddr,
 	    void * _Nonnull __restrict kdaddr, size_t len,

sys/sys/zutil.h

@@ -32,8 +32,6 @@
 #include <sys/param.h>
 #include <sys/kernel.h>
 #  define HAVE_MEMCPY
-#  define memset(d, v, n)	bzero((d), (n))
-#  define memcmp		bcmp
 
 #else
 #if defined(__KERNEL__)