reduce tlb/cache flush times of agpgart memory allocation

To reduce tlb/cache flush, makes agp memory allocation do one flush
after all pages in a region are changed to uc.

All agp drivers except agp-sgi uses agp_generic_alloc_page()
for .agp_alloc_page, so the patch should work for them. agp-sgi is only
for ia64, so not a problem too.

Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Cc: airlied@linux.ie
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Arjan van de Ven <arjan@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

drivers/char/agp/agp.h

@@ -30,6 +30,10 @@
 #define _AGP_BACKEND_PRIV_H 1
 
 #include <asm/agp.h>	/* for flush_agp_cache() */
+#ifndef map_page_into_agp_noflush
+#define map_page_into_agp_noflush(page) map_page_into_agp(page)
+#define map_page_into_agp_global_flush()
+#endif
 
 #define PFX "agpgart: "
 

drivers/char/agp/generic.c

@@ -274,6 +274,7 @@ struct agp_memory *agp_allocate_memory(struct agp_bridge_data *bridge,
 		new->memory[i] = virt_to_gart(addr);
 		new->page_count++;
 	}
+	map_page_into_agp_global_flush();
 	new->bridge = bridge;
 
 	return new;
@@ -1186,7 +1187,8 @@ void *agp_generic_alloc_page(struct agp_bridge_data *bridge)
 	if (page == NULL)
 		return NULL;
 
-	map_page_into_agp(page);
+	/* agp_allocate_memory will do flush */
+	map_page_into_agp_noflush(page);
 
 	get_page(page);
 	atomic_inc(&agp_bridge->current_memory_agp);

include/asm-x86/agp.h

@@ -15,6 +15,9 @@
 #define map_page_into_agp(page) set_pages_uc(page, 1)
 #define unmap_page_from_agp(page) set_pages_wb(page, 1)
 
+#define map_page_into_agp_noflush(page) set_pages_uc_noflush(page, 1)
+#define map_page_into_agp_global_flush() set_memory_flush_all()
+
 /*
  * Could use CLFLUSH here if the cpu supports it. But then it would
  * need to be called for each cacheline of the whole page so it may