x86: fix performance drop for glx

fix the 3D performance drop reported at:

   http://bugzilla.kernel.org/show_bug.cgi?id=10328

fb drivers are using ioremap()/ioremap_nocache(), followed by mtrr_add with
WC attribute. Recent changes in page attribute code made both
ioremap()/ioremap_nocache() mappings as UC (instead of previous UC-). This
breaks the graphics performance, as the effective memory type is UC instead
of expected WC.

The correct way to fix this is to add ioremap_wc() (which uses UC- in the
absence of PAT kernel support and WC with PAT) and change all the
fb drivers to use this new ioremap_wc() API.

We can take this correct and longer route for post 2.6.25. For now,
revert back to the UC- behavior for ioremap/ioremap_nocache.
Signed-off-by: NSuresh Siddha <suresh.b.siddha@intel.com>
Signed-off-by: NVenkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Cc: Arjan van de Ven <arjan@linux.intel.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

arch/x86/mm/ioremap.c

@@ -137,7 +137,11 @@ static void __iomem *__ioremap(resource_size_t phys_addr, unsigned long size,
 	switch (mode) {
 	case IOR_MODE_UNCACHED:
 	default:
-		prot = PAGE_KERNEL_NOCACHE;
+		/*
+		 * FIXME: we will use UC MINUS for now, as video fb drivers
+		 * depend on it. Upcoming ioremap_wc() will fix this behavior.
+		 */
+		prot = PAGE_KERNEL_UC_MINUS;
 		break;
 	case IOR_MODE_CACHED:
 		prot = PAGE_KERNEL;

arch/x86/mm/pageattr.c

@@ -771,7 +771,7 @@ static inline int change_page_attr_clear(unsigned long addr, int numpages,
 int set_memory_uc(unsigned long addr, int numpages)
 {
 	return change_page_attr_set(addr, numpages,
-				    __pgprot(_PAGE_PCD | _PAGE_PWT));
+				    __pgprot(_PAGE_PCD));
 }
 EXPORT_SYMBOL(set_memory_uc);
 

include/asm-x86/pgtable.h

@@ -85,6 +85,7 @@ extern pteval_t __PAGE_KERNEL, __PAGE_KERNEL_EXEC;
 #define __PAGE_KERNEL_RX		(__PAGE_KERNEL_EXEC & ~_PAGE_RW)
 #define __PAGE_KERNEL_EXEC_NOCACHE	(__PAGE_KERNEL_EXEC | _PAGE_PCD | _PAGE_PWT)
 #define __PAGE_KERNEL_NOCACHE		(__PAGE_KERNEL | _PAGE_PCD | _PAGE_PWT)
+#define __PAGE_KERNEL_UC_MINUS		(__PAGE_KERNEL | _PAGE_PCD)
 #define __PAGE_KERNEL_VSYSCALL		(__PAGE_KERNEL_RX | _PAGE_USER)
 #define __PAGE_KERNEL_VSYSCALL_NOCACHE	(__PAGE_KERNEL_VSYSCALL | _PAGE_PCD | _PAGE_PWT)
 #define __PAGE_KERNEL_LARGE		(__PAGE_KERNEL | _PAGE_PSE)
@@ -101,6 +102,7 @@ extern pteval_t __PAGE_KERNEL, __PAGE_KERNEL_EXEC;
 #define PAGE_KERNEL_EXEC		MAKE_GLOBAL(__PAGE_KERNEL_EXEC)
 #define PAGE_KERNEL_RX			MAKE_GLOBAL(__PAGE_KERNEL_RX)
 #define PAGE_KERNEL_NOCACHE		MAKE_GLOBAL(__PAGE_KERNEL_NOCACHE)
+#define PAGE_KERNEL_UC_MINUS		MAKE_GLOBAL(__PAGE_KERNEL_UC_MINUS)
 #define PAGE_KERNEL_EXEC_NOCACHE	MAKE_GLOBAL(__PAGE_KERNEL_EXEC_NOCACHE)
 #define PAGE_KERNEL_LARGE		MAKE_GLOBAL(__PAGE_KERNEL_LARGE)
 #define PAGE_KERNEL_LARGE_EXEC		MAKE_GLOBAL(__PAGE_KERNEL_LARGE_EXEC)