x86 PAT: fix performance drop for glx, use UC minus for ioremap(), ioremap_nocache() and pci_mmap_page_range()

Use UC_MINUS for ioremap(), ioremap_nocache() instead of strong UC.
Once all the X drivers move to ioremap_wc(), we can go back to strong
UC semantics for ioremap() and ioremap_nocache().

To avoid attribute aliasing issues, pci_mmap_page_range() will also
use UC_MINUS for default non write-combining mapping request.

Next steps:
	a) change all the video drivers using ioremap() or ioremap_nocache()
	   and adding WC MTTR using mttr_add() to ioremap_wc()

	b) for strict usage, we can go back to strong uc semantics
	   for ioremap() and ioremap_nocache() after some grace period for
	   completing step-a.

	c) user level X server needs to use the appropriate method for setting
	   up WC mapping (like using resourceX_wc sysfs file instead of
	   adding MTRR for WC and using /dev/mem or resourceX under /sys)

Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

arch/x86/mm/ioremap.c

@@ -176,11 +176,11 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr,
 		/*
 		 * Do not fallback to certain memory types with certain
 		 * requested type:
-		 * - request is uncached, return cannot be write-back
+		 * - request is uc-, return cannot be write-back
-		 * - request is uncached, return cannot be write-combine
+		 * - request is uc-, return cannot be write-combine
 		 * - request is write-combine, return cannot be write-back
 		 */
-		if ((prot_val == _PAGE_CACHE_UC &&
+		if ((prot_val == _PAGE_CACHE_UC_MINUS &&
 		     (new_prot_val == _PAGE_CACHE_WB ||
 		      new_prot_val == _PAGE_CACHE_WC)) ||
 		    (prot_val == _PAGE_CACHE_WC &&
@@ -201,6 +201,9 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr,
 	default:
 		prot = PAGE_KERNEL_NOCACHE;
 		break;
+	case _PAGE_CACHE_UC_MINUS:
+		prot = PAGE_KERNEL_UC_MINUS;
+		break;
 	case _PAGE_CACHE_WC:
 		prot = PAGE_KERNEL_WC;
 		break;
@@ -255,7 +258,16 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr,
  */
 void __iomem *ioremap_nocache(resource_size_t phys_addr, unsigned long size)
 {
-	return __ioremap_caller(phys_addr, size, _PAGE_CACHE_UC,
+	/*
+	 * Ideally, this should be:
+	 *	pat_wc_enabled ? _PAGE_CACHE_UC : _PAGE_CACHE_UC_MINUS;
+	 *
+	 * Till we fix all X drivers to use ioremap_wc(), we will use
+	 * UC MINUS.
+	 */
+	unsigned long val = _PAGE_CACHE_UC_MINUS;
+
+	return __ioremap_caller(phys_addr, size, val,
 				__builtin_return_address(0));
 }
 EXPORT_SYMBOL(ioremap_nocache);

arch/x86/mm/pageattr.c

@@ -777,14 +777,20 @@ static inline int change_page_attr_clear(unsigned long addr, int numpages,
 
 int _set_memory_uc(unsigned long addr, int numpages)
 {
+	/*
+	 * for now UC MINUS. see comments in ioremap_nocache()
+	 */
 	return change_page_attr_set(addr, numpages,
-				    __pgprot(_PAGE_CACHE_UC));
+				    __pgprot(_PAGE_CACHE_UC_MINUS));
 }
 
 int set_memory_uc(unsigned long addr, int numpages)
 {
+	/*
+	 * for now UC MINUS. see comments in ioremap_nocache()
+	 */
 	if (reserve_memtype(addr, addr + numpages * PAGE_SIZE,
-	                    _PAGE_CACHE_UC, NULL))
+			    _PAGE_CACHE_UC_MINUS, NULL))
 		return -EINVAL;
 
 	return _set_memory_uc(addr, numpages);

arch/x86/pci/i386.c

@@ -301,6 +301,13 @@ int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
 	prot = pgprot_val(vma->vm_page_prot);
 	if (pat_wc_enabled && write_combine)
 		prot |= _PAGE_CACHE_WC;
+	else if (pat_wc_enabled)
+		/*
+		 * ioremap() and ioremap_nocache() defaults to UC MINUS for now.
+		 * To avoid attribute conflicts, request UC MINUS here
+		 * aswell.
+		 */
+		prot |= _PAGE_CACHE_UC_MINUS;
 	else if (boot_cpu_data.x86 > 3)
 		prot |= _PAGE_CACHE_UC;
 
@@ -319,9 +326,8 @@ int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
 		 * - request is uncached, return cannot be write-combine
 		 * - request is write-combine, return cannot be write-back
 		 */
-		if ((flags == _PAGE_CACHE_UC &&
+		if ((flags == _PAGE_CACHE_UC_MINUS &&
-		     (new_flags == _PAGE_CACHE_WB ||
+		     (new_flags == _PAGE_CACHE_WB)) ||
-		      new_flags == _PAGE_CACHE_WC)) ||
 		    (flags == _PAGE_CACHE_WC &&
 		     new_flags == _PAGE_CACHE_WB)) {
 			free_memtype(addr, addr+len);