Allow __builtin_memset instead of bzero for small buffers of known size

In particular this eliminates function calls and related register save/restore
when only few writes would suffice.

Example speed up can be seen in a fstat microbenchmark on AMD Ryzen cpus, where
the throughput went up by ~4.5%.

Thanks to cem@ for benchmarking and reviewing the patch.

MFC after:	1 week

sys/sys/systm.h

@@ -258,6 +258,12 @@ 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);
 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));			\
+})
 void	explicit_bzero(void * _Nonnull, size_t);
 
 void	*memcpy(void * _Nonnull to, const void * _Nonnull from, size_t len);