diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 15c5df9..8922909 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -655,8 +655,10 @@ static void init_amd(struct cpuinfo_x86 *c)
 	 */
 	clear_cpu_cap(c, 0*32+31);
 
-	if (c->x86 >= 0x10)
+	if (c->x86 >= 0x10) {
 		set_cpu_cap(c, X86_FEATURE_REP_GOOD);
+		set_cpu_cap(c, X86_FEATURE_ERMS);
+	}
 
 	/* get apicid instead of initial apic id from cpuid */
 	c->apicid = hard_smp_processor_id();
diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c
index c905e89..a20ba66 100644
--- a/arch/x86/lib/usercopy_64.c
+++ b/arch/x86/lib/usercopy_64.c
@@ -14,35 +14,13 @@
 
 unsigned long __clear_user(void __user *addr, unsigned long size)
 {
-	long __d0;
 	might_fault();
 	/* no memory constraint because it doesn't change any memory gcc knows
 	   about */
 	stac();
-	asm volatile(
-		"	testq  %[size8],%[size8]\n"
-		"	jz     4f\n"
-		"0:	movq %[zero],(%[dst])\n"
-		"	addq   %[eight],%[dst]\n"
-		"	decl %%ecx ; jnz   0b\n"
-		"4:	movq  %[size1],%%rcx\n"
-		"	testl %%ecx,%%ecx\n"
-		"	jz     2f\n"
-		"1:	movb   %b[zero],(%[dst])\n"
-		"	incq   %[dst]\n"
-		"	decl %%ecx ; jnz  1b\n"
-		"2:\n"
-		".section .fixup,\"ax\"\n"
-		"3:	lea 0(%[size1],%[size8],8),%[size8]\n"
-		"	jmp 2b\n"
-		".previous\n"
-		_ASM_EXTABLE(0b,3b)
-		_ASM_EXTABLE(1b,2b)
-		: [size8] "=&c"(size), [dst] "=&D" (__d0)
-		: [size1] "r"(size & 7), "[size8]" (size / 8), "[dst]"(addr),
-		  [zero] "r" (0UL), [eight] "r" (8UL));
+	asm volatile("xor %%al, %%al; cld; rep stosb" : : "c" (size), "D" (addr) : "%al", "cc", "memory");
 	clac();
-	return size;
+	return 0;
 }
 EXPORT_SYMBOL(__clear_user);