diff --git a/arch/sh/mm/clear_page.S b/arch/sh/mm/clear_page.S
index 8a706131e521..7a7c81ee3f01 100644
--- a/arch/sh/mm/clear_page.S
+++ b/arch/sh/mm/clear_page.S
@@ -150,48 +150,3 @@ ENTRY(__clear_user)
 	.long	8b, .Lbad_clear_user
 	.long	9b, .Lbad_clear_user
 .previous
-
-#if defined(CONFIG_CPU_SH4)
-/*
- * __clear_user_page
- * @to: P3 address (with same color)
- * @orig_to: P1 address
- *
- * void __clear_user_page(void *to, void *orig_to)
- */
-
-/*
- * r0 --- scratch 
- * r4 --- to
- * r5 --- orig_to
- * r6 --- to + PAGE_SIZE
- */
-ENTRY(__clear_user_page)
-	mov.l	.Lpsz,r0
-	mov	r4,r6
-	add	r0,r6
-	mov	#0,r0
-	!
-1:	ocbi	@r5
-	add	#32,r5
-	movca.l	r0,@r4
-	mov	r4,r1
-	add	#32,r4
-	mov.l	r0,@-r4
-	mov.l	r0,@-r4
-	mov.l	r0,@-r4
-	mov.l	r0,@-r4
-	mov.l	r0,@-r4
-	mov.l	r0,@-r4
-	mov.l	r0,@-r4
-	add	#28,r4
-	cmp/eq	r6,r4
-	bf/s	1b
-	 ocbwb	@r1
-	!
-	rts
-	 nop
-.Lpsz:	.long	PAGE_SIZE
-
-#endif
-
diff --git a/arch/sh/mm/copy_page.S b/arch/sh/mm/copy_page.S
index 3d8409daa4be..40685018b952 100644
--- a/arch/sh/mm/copy_page.S
+++ b/arch/sh/mm/copy_page.S
@@ -68,67 +68,6 @@ ENTRY(copy_page_slow)
 	rts
 	 nop
 
-#if defined(CONFIG_CPU_SH4)
-/*
- * __copy_user_page
- * @to: P1 address (with same color)
- * @from: P1 address
- * @orig_to: P1 address
- *
- * void __copy_user_page(void *to, void *from, void *orig_to)
- */
-
-/*
- * r0, r1, r2, r3, r4, r5, r6, r7 --- scratch 
- * r8 --- from + PAGE_SIZE
- * r9 --- orig_to
- * r10 --- to
- * r11 --- from
- */
-ENTRY(__copy_user_page)
-	mov.l	r8,@-r15
-	mov.l	r9,@-r15
-	mov.l	r10,@-r15
-	mov.l	r11,@-r15
-	mov	r4,r10
-	mov	r5,r11
-	mov	r6,r9
-	mov	r5,r8
-	mov.l	.Lpsz,r0
-	add	r0,r8
-	!
-1:	ocbi	@r9
-	add	#32,r9
-	mov.l	@r11+,r0
-	mov.l	@r11+,r1
-	mov.l	@r11+,r2
-	mov.l	@r11+,r3
-	mov.l	@r11+,r4
-	mov.l	@r11+,r5
-	mov.l	@r11+,r6
-	mov.l	@r11+,r7
-	movca.l	r0,@r10
-	mov	r10,r0
-	add	#32,r10
-	mov.l	r7,@-r10
-	mov.l	r6,@-r10
-	mov.l	r5,@-r10
-	mov.l	r4,@-r10
-	mov.l	r3,@-r10
-	mov.l	r2,@-r10
-	mov.l	r1,@-r10
-	ocbwb	@r0
-	cmp/eq	r11,r8
-	bf/s	1b
-	 add	#28,r10
-	!
-	mov.l	@r15+,r11
-	mov.l	@r15+,r10
-	mov.l	@r15+,r9
-	mov.l	@r15+,r8
-	rts
-	 nop
-#endif
 	.align 2
 .Lpsz:	.long	PAGE_SIZE
 /*
diff --git a/arch/sh/mm/pg-sh4.c b/arch/sh/mm/pg-sh4.c
index 25f5c6f6821d..8c7a9ca79879 100644
--- a/arch/sh/mm/pg-sh4.c
+++ b/arch/sh/mm/pg-sh4.c
@@ -9,6 +9,8 @@
 #include <linux/mm.h>
 #include <linux/mutex.h>
 #include <linux/fs.h>
+#include <linux/highmem.h>
+#include <linux/module.h>
 #include <asm/mmu_context.h>
 #include <asm/cacheflush.h>
 
@@ -50,35 +52,62 @@ static inline void kunmap_coherent(struct page *page)
 void clear_user_page(void *to, unsigned long address, struct page *page)
 {
 	__set_bit(PG_mapped, &page->flags);
-	if (((address ^ (unsigned long)to) & CACHE_ALIAS) == 0)
-		clear_page(to);
-	else {
-		void *vto = kmap_coherent(page, address);
-		__clear_user_page(vto, to);
-		kunmap_coherent(vto);
-	}
+
+	clear_page(to);
+	if ((((address & PAGE_MASK) ^ (unsigned long)to) & CACHE_ALIAS))
+		__flush_wback_region(to, PAGE_SIZE);
 }
 
-/*
- * copy_user_page
- * @to: P1 address
- * @from: P1 address
- * @address: U0 address to be mapped
- * @page: page (virt_to_page(to))
- */
-void copy_user_page(void *to, void *from, unsigned long address,
-		    struct page *page)
+void copy_to_user_page(struct vm_area_struct *vma, struct page *page,
+		       unsigned long vaddr, void *dst, const void *src,
+		       unsigned long len)
 {
+	void *vto;
+
 	__set_bit(PG_mapped, &page->flags);
-	if (((address ^ (unsigned long)to) & CACHE_ALIAS) == 0)
-		copy_page(to, from);
-	else {
-		void *vfrom = kmap_coherent(page, address);
-		__copy_user_page(vfrom, from, to);
-		kunmap_coherent(vfrom);
-	}
+
+	vto = kmap_coherent(page, vaddr) + (vaddr & ~PAGE_MASK);
+	memcpy(vto, src, len);
+	kunmap_coherent(vto);
+
+	if (vma->vm_flags & VM_EXEC)
+		flush_cache_page(vma, vaddr, page_to_pfn(page));
 }
 
+void copy_from_user_page(struct vm_area_struct *vma, struct page *page,
+			 unsigned long vaddr, void *dst, const void *src,
+			 unsigned long len)
+{
+	void *vfrom;
+
+	__set_bit(PG_mapped, &page->flags);
+
+	vfrom = kmap_coherent(page, vaddr) + (vaddr & ~PAGE_MASK);
+	memcpy(dst, vfrom, len);
+	kunmap_coherent(vfrom);
+}
+
+void copy_user_highpage(struct page *to, struct page *from,
+			unsigned long vaddr, struct vm_area_struct *vma)
+{
+	void *vfrom, *vto;
+
+	__set_bit(PG_mapped, &to->flags);
+
+	vto = kmap_atomic(to, KM_USER1);
+	vfrom = kmap_coherent(from, vaddr);
+	copy_page(vto, vfrom);
+	kunmap_coherent(vfrom);
+
+	if (((vaddr ^ (unsigned long)vto) & CACHE_ALIAS))
+		__flush_wback_region(vto, PAGE_SIZE);
+
+	kunmap_atomic(vto, KM_USER1);
+	/* Make sure this page is cleared on other CPU's too before using it */
+	smp_wmb();
+}
+EXPORT_SYMBOL(copy_user_highpage);
+
 /*
  * For SH-4, we have our own implementation for ptep_get_and_clear
  */
diff --git a/include/asm-sh/cacheflush.h b/include/asm-sh/cacheflush.h
index aa558da08471..b91246153b7e 100644
--- a/include/asm-sh/cacheflush.h
+++ b/include/asm-sh/cacheflush.h
@@ -43,21 +43,31 @@ extern void __flush_purge_region(void *start, int size);
 extern void __flush_invalidate_region(void *start, int size);
 #endif
 
-#define flush_cache_vmap(start, end)		flush_cache_all()
-#define flush_cache_vunmap(start, end)		flush_cache_all()
+#ifdef CONFIG_CPU_SH4
+extern void copy_to_user_page(struct vm_area_struct *vma,
+	struct page *page, unsigned long vaddr, void *dst, const void *src,
+	unsigned long len);
 
-#define copy_to_user_page(vma, page, vaddr, dst, src, len) \
+extern void copy_from_user_page(struct vm_area_struct *vma,
+	struct page *page, unsigned long vaddr, void *dst, const void *src,
+	unsigned long len);
+#else
+#define copy_to_user_page(vma, page, vaddr, dst, src, len)	\
 	do {							\
 		flush_cache_page(vma, vaddr, page_to_pfn(page));\
 		memcpy(dst, src, len);				\
 		flush_icache_user_range(vma, page, vaddr, len);	\
 	} while (0)
 
-#define copy_from_user_page(vma, page, vaddr, dst, src, len) \
+#define copy_from_user_page(vma, page, vaddr, dst, src, len)	\
 	do {							\
 		flush_cache_page(vma, vaddr, page_to_pfn(page));\
 		memcpy(dst, src, len);				\
 	} while (0)
+#endif
+
+#define flush_cache_vmap(start, end)		flush_cache_all()
+#define flush_cache_vunmap(start, end)		flush_cache_all()
 
 #define HAVE_ARCH_UNMAPPED_AREA
 
diff --git a/include/asm-sh/page.h b/include/asm-sh/page.h
index 3aa8b07da47d..d00a8fde7c7f 100644
--- a/include/asm-sh/page.h
+++ b/include/asm-sh/page.h
@@ -73,10 +73,13 @@ extern void copy_page_nommu(void *to, void *from);
 #if !defined(CONFIG_CACHE_OFF) && defined(CONFIG_MMU) && \
 	(defined(CONFIG_CPU_SH4) || defined(CONFIG_SH7705_CACHE_32KB))
 struct page;
-extern void clear_user_page(void *to, unsigned long address, struct page *pg);
-extern void copy_user_page(void *to, void *from, unsigned long address, struct page *pg);
-extern void __clear_user_page(void *to, void *orig_to);
-extern void __copy_user_page(void *to, void *from, void *orig_to);
+struct vm_area_struct;
+extern void clear_user_page(void *to, unsigned long address, struct page *page);
+#ifdef CONFIG_CPU_SH4
+extern void copy_user_highpage(struct page *to, struct page *from,
+			       unsigned long vaddr, struct vm_area_struct *vma);
+#define __HAVE_ARCH_COPY_USER_HIGHPAGE
+#endif
 #else
 #define clear_user_page(page, vaddr, pg)	clear_page(page)
 #define copy_user_page(to, from, vaddr, pg)	copy_page(to, from)