diff --git a/arch/x86/lib/clear_page_nocache_64.S b/arch/x86/lib/clear_page_nocache_64.S
index ee16d15..c092919 100644
--- a/arch/x86/lib/clear_page_nocache_64.S
+++ b/arch/x86/lib/clear_page_nocache_64.S
@@ -1,29 +1,92 @@
+/*
+ * Clear pages with cache bypass.
+ * 
+ * Copyright (C) 2011, 2012 Intel Corporation
+ * Author: Andi Kleen
+ *
+ * This software may be redistributed and/or modified under the terms of
+ * the GNU General Public License ("GPL") version 2 only as published by the
+ * Free Software Foundation.
+ */
+
 #include <linux/linkage.h>
+#include <asm/alternative-asm.h>
+#include <asm/cpufeature.h>
 #include <asm/dwarf2.h>
 
+#define SSE_UNROLL 128
+
 /*
  * Zero a page avoiding the caches
  * rdi	page
  */
 ENTRY(clear_page_nocache)
 	CFI_STARTPROC
-	xorl   %eax,%eax
-	movl   $4096/64,%ecx
+	push   %rdi
+	call   kernel_fpu_begin
+	pop    %rdi
+	sub    $16,%rsp
+	CFI_ADJUST_CFA_OFFSET 16
+	movdqu %xmm0,(%rsp)
+	xorpd  %xmm0,%xmm0
+	movl   $4096/SSE_UNROLL,%ecx
 	.p2align 4
 .Lloop:
 	decl	%ecx
-#define PUT(x) movnti %rax,x*8(%rdi)
-	movnti %rax,(%rdi)
-	PUT(1)
-	PUT(2)
-	PUT(3)
-	PUT(4)
-	PUT(5)
-	PUT(6)
-	PUT(7)
-	leaq	64(%rdi),%rdi
+	.set x,0
+	.rept SSE_UNROLL/16
+	movntdq %xmm0,x(%rdi)
+	.set x,x+16
+	.endr
+	leaq	SSE_UNROLL(%rdi),%rdi
 	jnz	.Lloop
-	nop
-	ret
+	movdqu (%rsp),%xmm0
+	addq   $16,%rsp
+	CFI_ADJUST_CFA_OFFSET -16
+	jmp   kernel_fpu_end
 	CFI_ENDPROC
 ENDPROC(clear_page_nocache)
+
+#ifdef CONFIG_AS_AVX
+
+	.section .altinstr_replacement,"ax"
+1:	.byte 0xeb					/* jmp <disp8> */
+	.byte (clear_page_nocache_avx - clear_page_nocache) - (2f - 1b)
+	/* offset */
+2:
+	.previous
+	.section .altinstructions,"a"
+	altinstruction_entry clear_page_nocache,1b,X86_FEATURE_AVX,\
+	                     16, 2b-1b
+	.previous
+
+#define AVX_UNROLL 256 /* TUNE ME */
+
+ENTRY(clear_page_nocache_avx)
+	CFI_STARTPROC
+	push   %rdi
+	call   kernel_fpu_begin
+	pop    %rdi
+	sub    $32,%rsp
+	CFI_ADJUST_CFA_OFFSET 32
+	vmovdqu %ymm0,(%rsp)
+	vxorpd  %ymm0,%ymm0,%ymm0
+	movl   $4096/AVX_UNROLL,%ecx
+	.p2align 4
+.Lloop_avx:
+	decl	%ecx
+	.set x,0
+	.rept AVX_UNROLL/32
+	vmovntdq %ymm0,x(%rdi)
+	.set x,x+32
+	.endr
+	leaq	AVX_UNROLL(%rdi),%rdi
+	jnz	.Lloop_avx
+	vmovdqu (%rsp),%ymm0
+	addq   $32,%rsp
+	CFI_ADJUST_CFA_OFFSET -32
+	jmp   kernel_fpu_end
+	CFI_ENDPROC
+ENDPROC(clear_page_nocache_avx)
+
+#endif