x86/compat: provide optimized memcpy_x86

Implementation for PIE's builtin_memcpy located at
criu/arch/x86/include/asm/string.h

travis-ci: success for Compel/compat cleanups
Signed-off-by: Dmitry Safonov <dsafonov@virtuozzo.com>
Acked-by: Cyrill Gorcunov <gorcunov@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@virtuozzo.com>
Signed-off-by: Andrei Vagin <avagin@virtuozzo.com>

criu/arch/x86/compat/memcpy-compat.c

+#include <stddef.h>
+
+/*
+ * This provides an optimized implementation of memcpy, and a simplified
+ * implementation of memset and memmove. These are used here because the
+ * standard kernel runtime versions are not yet available and we don't
+ * trust the gcc built-in implementations as they may do unexpected things
+ * (e.g. FPU ops) in the minimal decompression stub execution environment.
+ *
+ * From Linux kernel boot helpers: arch/x86/boot/compressed/string.c
+ */
+
+void *memcpy_x86(void *dest, const void *src, size_t n)
+{
+	int d0, d1, d2;
+	asm volatile(
+		"rep ; movsl\n\t"
+		"movl %4,%%ecx\n\t"
+		"rep ; movsb\n\t"
+		: "=&c" (d0), "=&D" (d1), "=&S" (d2)
+		: "0" (n >> 2), "g" (n & 3), "1" (dest), "2" (src)
+		: "memory");
+
+	return dest;
+}