x86: add _PAGE_IOMAP pte flag for IO mappings

Use one of the software-defined PTE bits to indicate that a mapping is
intended for an IO address.  On native hardware this is irrelevent,
since a physical address is a physical address.  But in a virtual
environment, physical addresses are also virtualized, so there needs
to be some way to distinguish between pseudo-physical addresses and
actual hardware addresses; _PAGE_IOMAP indicates this intent.

By default, __supported_pte_mask masks out _PAGE_IOMAP, so it doesn't
even appear in the final pagetable.
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

arch/x86/mm/init_32.c

@@ -558,7 +558,7 @@ void zap_low_mappings(void)
 
 int nx_enabled;
 
-pteval_t __supported_pte_mask __read_mostly = ~(_PAGE_NX | _PAGE_GLOBAL);
+pteval_t __supported_pte_mask __read_mostly = ~(_PAGE_NX | _PAGE_GLOBAL | _PAGE_IOMAP);
 EXPORT_SYMBOL_GPL(__supported_pte_mask);
 
 #ifdef CONFIG_X86_PAE

arch/x86/mm/init_64.c

@@ -89,7 +89,7 @@ early_param("gbpages", parse_direct_gbpages_on);
 
 int after_bootmem;
 
-unsigned long __supported_pte_mask __read_mostly = ~0UL;
+pteval_t __supported_pte_mask __read_mostly = ~_PAGE_IOMAP;
 EXPORT_SYMBOL_GPL(__supported_pte_mask);
 
 static int do_not_nx __cpuinitdata;

arch/x86/mm/ioremap.c

@@ -242,16 +242,16 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr,
 	switch (prot_val) {
 	case _PAGE_CACHE_UC:
 	default:
-		prot = PAGE_KERNEL_NOCACHE;
+		prot = PAGE_KERNEL_IO_NOCACHE;
 		break;
 	case _PAGE_CACHE_UC_MINUS:
-		prot = PAGE_KERNEL_UC_MINUS;
+		prot = PAGE_KERNEL_IO_UC_MINUS;
 		break;
 	case _PAGE_CACHE_WC:
-		prot = PAGE_KERNEL_WC;
+		prot = PAGE_KERNEL_IO_WC;
 		break;
 	case _PAGE_CACHE_WB:
-		prot = PAGE_KERNEL;
+		prot = PAGE_KERNEL_IO;
 		break;
 	}
 

include/asm-x86/pgtable.h

@@ -15,7 +15,7 @@
 #define _PAGE_BIT_PAT		7	/* on 4KB pages */
 #define _PAGE_BIT_GLOBAL	8	/* Global TLB entry PPro+ */
 #define _PAGE_BIT_UNUSED1	9	/* available for programmer */
-#define _PAGE_BIT_UNUSED2	10
+#define _PAGE_BIT_IOMAP		10	/* flag used to indicate IO mapping */
 #define _PAGE_BIT_UNUSED3	11
 #define _PAGE_BIT_PAT_LARGE	12	/* On 2MB or 1GB pages */
 #define _PAGE_BIT_SPECIAL	_PAGE_BIT_UNUSED1
@@ -32,7 +32,7 @@
 #define _PAGE_PSE	(_AT(pteval_t, 1) << _PAGE_BIT_PSE)
 #define _PAGE_GLOBAL	(_AT(pteval_t, 1) << _PAGE_BIT_GLOBAL)
 #define _PAGE_UNUSED1	(_AT(pteval_t, 1) << _PAGE_BIT_UNUSED1)
-#define _PAGE_UNUSED2	(_AT(pteval_t, 1) << _PAGE_BIT_UNUSED2)
+#define _PAGE_IOMAP	(_AT(pteval_t, 1) << _PAGE_BIT_IOMAP)
 #define _PAGE_UNUSED3	(_AT(pteval_t, 1) << _PAGE_BIT_UNUSED3)
 #define _PAGE_PAT	(_AT(pteval_t, 1) << _PAGE_BIT_PAT)
 #define _PAGE_PAT_LARGE (_AT(pteval_t, 1) << _PAGE_BIT_PAT_LARGE)
@@ -99,6 +99,11 @@
 #define __PAGE_KERNEL_LARGE_NOCACHE	(__PAGE_KERNEL | _PAGE_CACHE_UC | _PAGE_PSE)
 #define __PAGE_KERNEL_LARGE_EXEC	(__PAGE_KERNEL_EXEC | _PAGE_PSE)
 
+#define __PAGE_KERNEL_IO		(__PAGE_KERNEL | _PAGE_IOMAP)
+#define __PAGE_KERNEL_IO_NOCACHE	(__PAGE_KERNEL_NOCACHE | _PAGE_IOMAP)
+#define __PAGE_KERNEL_IO_UC_MINUS	(__PAGE_KERNEL_UC_MINUS | _PAGE_IOMAP)
+#define __PAGE_KERNEL_IO_WC		(__PAGE_KERNEL_WC | _PAGE_IOMAP)
+
 #define PAGE_KERNEL			__pgprot(__PAGE_KERNEL)
 #define PAGE_KERNEL_RO			__pgprot(__PAGE_KERNEL_RO)
 #define PAGE_KERNEL_EXEC		__pgprot(__PAGE_KERNEL_EXEC)
@@ -113,6 +118,11 @@
 #define PAGE_KERNEL_VSYSCALL		__pgprot(__PAGE_KERNEL_VSYSCALL)
 #define PAGE_KERNEL_VSYSCALL_NOCACHE	__pgprot(__PAGE_KERNEL_VSYSCALL_NOCACHE)
 
+#define PAGE_KERNEL_IO			__pgprot(__PAGE_KERNEL_IO)
+#define PAGE_KERNEL_IO_NOCACHE		__pgprot(__PAGE_KERNEL_IO_NOCACHE)
+#define PAGE_KERNEL_IO_UC_MINUS		__pgprot(__PAGE_KERNEL_IO_UC_MINUS)
+#define PAGE_KERNEL_IO_WC		__pgprot(__PAGE_KERNEL_IO_WC)
+
 /*         xwr */
 #define __P000	PAGE_NONE
 #define __P001	PAGE_READONLY