diff --git a/arch/sparc64/lib/copy_page.S b/arch/sparc64/lib/copy_page.S
new file mode 100644
index 0000000..23ebf2c
--- /dev/null
+++ b/arch/sparc64/lib/copy_page.S
@@ -0,0 +1,242 @@
+/* clear_page.S: UltraSparc optimized copy page.
+ *
+ * Copyright (C) 1996, 1998, 1999, 2000, 2004 David S. Miller (davem@redhat.com)
+ * Copyright (C) 1997 Jakub Jelinek (jakub@redhat.com)
+ */
+
+#include <asm/visasm.h>
+#include <asm/thread_info.h>
+#include <asm/page.h>
+#include <asm/pgtable.h>
+#include <asm/spitfire.h>
+#include <asm/head.h>
+
+	/* What we used to do was lock a TLB entry into a specific
+	 * TLB slot, clear the page with interrupts disabled, then
+	 * restore the original TLB entry.  This was great for
+	 * disturbing the TLB as little as possible, but it meant
+	 * we had to keep interrupts disabled for a long time.
+	 *
+	 * Now, we simply use the normal TLB loading mechanism,
+	 * and this makes the cpu choose a slot all by itself.
+	 * Then we do a normal TLB flush on exit.  We need only
+	 * disable preemption during the clear.
+	 */
+
+#define TTE_BITS_TOP	(_PAGE_VALID | _PAGE_SZBITS)
+#define TTE_BITS_BOTTOM	(_PAGE_CP | _PAGE_CV | _PAGE_P | _PAGE_L | _PAGE_W)
+#define	DCACHE_SIZE	(PAGE_SIZE * 2)
+
+#if (PAGE_SHIFT == 13) || (PAGE_SHIFT == 19)
+#define PAGE_SIZE_REM	0x80
+#elif (PAGE_SHIFT == 16) || (PAGE_SHIFT == 22)
+#define PAGE_SIZE_REM	0x100
+#else
+#error Wrong PAGE_SHIFT specified
+#endif
+
+#define TOUCH(reg0, reg1, reg2, reg3, reg4, reg5, reg6, reg7)	\
+	fmovd	%reg0, %f48; 	fmovd	%reg1, %f50;		\
+	fmovd	%reg2, %f52; 	fmovd	%reg3, %f54;		\
+	fmovd	%reg4, %f56; 	fmovd	%reg5, %f58;		\
+	fmovd	%reg6, %f60; 	fmovd	%reg7, %f62;
+
+	.text
+
+	.align		32
+	.globl		copy_user_page
+	.type		copy_user_page,#function
+copy_user_page:		/* %o0=dest, %o1=src, %o2=vaddr */
+	lduw		[%g6 + TI_PRE_COUNT], %o4
+	sethi		%uhi(PAGE_OFFSET), %g2
+	sethi		%hi(PAGE_SIZE), %o3
+
+	sllx		%g2, 32, %g2
+	sethi		%uhi(TTE_BITS_TOP), %g3
+
+	sllx		%g3, 32, %g3
+	sub		%o0, %g2, %g1		! dest paddr
+
+	sub		%o1, %g2, %g2		! src paddr
+	or		%g3, TTE_BITS_BOTTOM, %g3
+
+	and		%o2, %o3, %o0		! vaddr D-cache alias bit
+	or		%g1, %g3, %g1		! dest TTE data
+
+	or		%g2, %g3, %g2		! src TTE data
+	sethi		%hi(TLBTEMP_BASE), %o3
+
+	sethi		%hi(DCACHE_SIZE), %o1
+	add		%o0, %o3, %o0		! dest TTE vaddr
+
+	add		%o4, 1, %o2
+	add		%o0, %o1, %o1		! src TTE vaddr
+
+	/* Disable preemption.  */
+	mov		TLB_TAG_ACCESS, %g3
+	stw		%o2, [%g6 + TI_PRE_COUNT]
+
+	/* Load TLB entries.  */
+	rdpr		%pstate, %o2
+	wrpr		%o2, PSTATE_IE, %pstate
+	stxa		%o0, [%g3] ASI_DMMU
+	stxa		%g1, [%g0] ASI_DTLB_DATA_IN
+	membar		#Sync
+	stxa		%o1, [%g3] ASI_DMMU
+	stxa		%g2, [%g0] ASI_DTLB_DATA_IN
+	membar		#Sync
+	wrpr		%o2, 0x0, %pstate
+
+	BRANCH_IF_ANY_CHEETAH(g3,o2,1f)
+	ba,pt		%xcc, 9f
+	 nop
+
+1:
+	VISEntryHalf
+	membar		#StoreLoad | #StoreStore | #LoadStore
+	sethi		%hi((PAGE_SIZE/64)-2), %o2
+	mov		%o0, %g1
+	prefetch	[%o1 + 0x000], #one_read
+	or		%o2, %lo((PAGE_SIZE/64)-2), %o2
+	prefetch	[%o1 + 0x040], #one_read
+	prefetch	[%o1 + 0x080], #one_read
+	prefetch	[%o1 + 0x0c0], #one_read
+	ldd		[%o1 + 0x000], %f0
+	prefetch	[%o1 + 0x100], #one_read
+	ldd		[%o1 + 0x008], %f2
+	prefetch	[%o1 + 0x140], #one_read
+	ldd		[%o1 + 0x010], %f4
+	prefetch	[%o1 + 0x180], #one_read
+	fmovd		%f0, %f16
+	ldd		[%o1 + 0x018], %f6
+	fmovd		%f2, %f18
+	ldd		[%o1 + 0x020], %f8
+	fmovd		%f4, %f20
+	ldd		[%o1 + 0x028], %f10
+	fmovd		%f6, %f22
+	ldd		[%o1 + 0x030], %f12
+	fmovd		%f8, %f24
+	ldd		[%o1 + 0x038], %f14
+	fmovd		%f10, %f26
+	ldd		[%o1 + 0x040], %f0
+1:	ldd		[%o1 + 0x048], %f2
+	fmovd		%f12, %f28
+	ldd		[%o1 + 0x050], %f4
+	fmovd		%f14, %f30
+	stda		%f16, [%o0] ASI_BLK_P
+	ldd		[%o1 + 0x058], %f6
+	fmovd		%f0, %f16
+	ldd		[%o1 + 0x060], %f8
+	fmovd		%f2, %f18
+	ldd		[%o1 + 0x068], %f10
+	fmovd		%f4, %f20
+	ldd		[%o1 + 0x070], %f12
+	fmovd		%f6, %f22
+	ldd		[%o1 + 0x078], %f14
+	fmovd		%f8, %f24
+	ldd		[%o1 + 0x080], %f0
+	prefetch	[%o1 + 0x180], #one_read
+	fmovd		%f10, %f26
+	subcc		%o2, 1, %o2
+	add		%o0, 0x40, %o0
+	bne,pt		%xcc, 1b
+	 add		%o1, 0x40, %o1
+
+	ldd		[%o1 + 0x048], %f2
+	fmovd		%f12, %f28
+	ldd		[%o1 + 0x050], %f4
+	fmovd		%f14, %f30
+	stda		%f16, [%o0] ASI_BLK_P
+	ldd		[%o1 + 0x058], %f6
+	fmovd		%f0, %f16
+	ldd		[%o1 + 0x060], %f8
+	fmovd		%f2, %f18
+	ldd		[%o1 + 0x068], %f10
+	fmovd		%f4, %f20
+	ldd		[%o1 + 0x070], %f12
+	fmovd		%f6, %f22
+	add		%o0, 0x40, %o0
+	ldd		[%o1 + 0x078], %f14
+	fmovd		%f8, %f24
+	fmovd		%f10, %f26
+	fmovd		%f12, %f28
+	fmovd		%f14, %f30
+	stda		%f16, [%o0] ASI_BLK_P
+	membar		#Sync
+	VISExitHalf
+	ba,pt		%xcc, 5f
+	 nop
+
+9:
+	VISEntry
+	ldub		[%g6 + TI_FAULT_CODE], %g3
+	mov		%o0, %g1
+	cmp		%g3, 0
+	rd		%asi, %g3
+	be,a,pt		%icc, 1f
+	 wr		%g0, ASI_BLK_P, %asi
+	wr		%g0, ASI_BLK_COMMIT_P, %asi
+1:	ldda		[%o1] ASI_BLK_P, %f0
+	add		%o1, 0x40, %o1
+	ldda		[%o1] ASI_BLK_P, %f16
+	add		%o1, 0x40, %o1
+	sethi		%hi(PAGE_SIZE), %o2
+1:	TOUCH(f0, f2, f4, f6, f8, f10, f12, f14)
+	ldda		[%o1] ASI_BLK_P, %f32
+	stda		%f48, [%o0] %asi
+	add		%o1, 0x40, %o1
+	sub		%o2, 0x40, %o2
+	add		%o0, 0x40, %o0
+	TOUCH(f16, f18, f20, f22, f24, f26, f28, f30)
+	ldda		[%o1] ASI_BLK_P, %f0
+	stda		%f48, [%o0] %asi
+	add		%o1, 0x40, %o1
+	sub		%o2, 0x40, %o2
+	add		%o0, 0x40, %o0
+	TOUCH(f32, f34, f36, f38, f40, f42, f44, f46)
+	ldda		[%o1] ASI_BLK_P, %f16
+	stda		%f48, [%o0] %asi
+	sub		%o2, 0x40, %o2
+	add		%o1, 0x40, %o1
+	cmp		%o2, PAGE_SIZE_REM
+	bne,pt		%xcc, 1b
+	 add		%o0, 0x40, %o0
+#if (PAGE_SHIFT == 16) || (PAGE_SHIFT == 22)
+	TOUCH(f0, f2, f4, f6, f8, f10, f12, f14)
+	ldda		[%o1] ASI_BLK_P, %f32
+	stda		%f48, [%o0] %asi
+	add		%o1, 0x40, %o1
+	sub		%o2, 0x40, %o2
+	add		%o0, 0x40, %o0
+	TOUCH(f16, f18, f20, f22, f24, f26, f28, f30)
+	ldda		[%o1] ASI_BLK_P, %f0
+	stda		%f48, [%o0] %asi
+	add		%o1, 0x40, %o1
+	sub		%o2, 0x40, %o2
+	add		%o0, 0x40, %o0
+	membar		#Sync
+	stda		%f32, [%o0] %asi
+	add		%o0, 0x40, %o0
+	stda		%f0, [%o0] %asi
+#else
+	membar		#Sync
+	stda		%f0, [%o0] %asi
+	add		%o0, 0x40, %o0
+	stda		%f16, [%o0] %asi
+#endif
+	membar		#Sync
+	wr		%g3, 0x0, %asi
+	VISExit
+
+5:
+	stxa		%g0, [%g1] ASI_DMMU_DEMAP
+	membar		#Sync
+
+	sethi		%hi(DCACHE_SIZE), %g2
+	stxa		%g0, [%g1 + %g2] ASI_DMMU_DEMAP
+	membar		#Sync
+
+	retl
+	 stw		%o4, [%g6 + TI_PRE_COUNT]
+
+	.size		copy_user_page, .-copy_user_page