sh: Optimized copy_{to,from}_user_page() for SH-4.

This moves copy_{to,from}_user_page() out-of-line on SH-4 and
converts for the kmap_coherent() API. Based on the MIPS
implementation.

Signed-off-by: Paul Mundt <lethal@linux-sh.org>
diff --git a/arch/sh/mm/pg-sh4.c b/arch/sh/mm/pg-sh4.c
index ede6dd1..8c7a9ca 100644
--- a/arch/sh/mm/pg-sh4.c
+++ b/arch/sh/mm/pg-sh4.c
@@ -52,33 +52,39 @@
 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,
diff --git a/include/asm-sh/cacheflush.h b/include/asm-sh/cacheflush.h
index aa558da..b912461 100644
--- a/include/asm-sh/cacheflush.h
+++ b/include/asm-sh/cacheflush.h
@@ -43,21 +43,31 @@
 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