Merge branch 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 mm tree changes from Ingo Molnar:
 "The biggest change is full PAT support from Jürgen Gross:

     The x86 architecture offers via the PAT (Page Attribute Table) a
     way to specify different caching modes in page table entries.  The
     PAT MSR contains 8 entries each specifying one of 6 possible cache
     modes.  A pte references one of those entries via 3 bits:
     _PAGE_PAT, _PAGE_PWT and _PAGE_PCD.

     The Linux kernel currently supports only 4 different cache modes.
     The PAT MSR is set up in a way that the setting of _PAGE_PAT in a
     pte doesn't matter: the top 4 entries in the PAT MSR are the same
     as the 4 lower entries.

     This results in the kernel not supporting e.g. write-through mode.
     Especially this cache mode would speed up drivers of video cards
     which now have to use uncached accesses.

     OTOH some old processors (Pentium) don't support PAT correctly and
     the Xen hypervisor has been using a different PAT MSR configuration
     for some time now and can't change that as this setting is part of
     the ABI.

     This patch set abstracts the cache mode from the pte and introduces
     tables to translate between cache mode and pte bits (the default
     cache mode "write back" is hard-wired to PAT entry 0).  The tables
     are statically initialized with values being compatible to old
     processors and current usage.  As soon as the PAT MSR is changed
     (or - in case of Xen - is read at boot time) the tables are changed
     accordingly.  Requests of mappings with special cache modes are
     always possible now, in case they are not supported there will be a
     fallback to a compatible but slower mode.

     Summing it up, this patch set adds the following features:

      - capability to support WT and WP cache modes on processors with
        full PAT support

      - processors with no or uncorrect PAT support are still working as
        today, even if WT or WP cache mode are selected by drivers for
        some pages

      - reduction of Xen special handling regarding cache mode

  Another change is a boot speedup on ridiculously large RAM systems,
  plus other smaller fixes"

* 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (22 commits)
  x86: mm: Move PAT only functions to mm/pat.c
  xen: Support Xen pv-domains using PAT
  x86: Enable PAT to use cache mode translation tables
  x86: Respect PAT bit when copying pte values between large and normal pages
  x86: Support PAT bit in pagetable dump for lower levels
  x86: Clean up pgtable_types.h
  x86: Use new cache mode type in memtype related functions
  x86: Use new cache mode type in mm/ioremap.c
  x86: Use new cache mode type in setting page attributes
  x86: Remove looking for setting of _PAGE_PAT_LARGE in pageattr.c
  x86: Use new cache mode type in track_pfn_remap() and track_pfn_insert()
  x86: Use new cache mode type in mm/iomap_32.c
  x86: Use new cache mode type in asm/pgtable.h
  x86: Use new cache mode type in arch/x86/mm/init_64.c
  x86: Use new cache mode type in arch/x86/pci
  x86: Use new cache mode type in drivers/video/fbdev/vermilion
  x86: Use new cache mode type in drivers/video/fbdev/gbefb.c
  x86: Use new cache mode type in include/asm/fb.h
  x86: Make page cache mode a real type
  x86: mm: Use 2GB memory block size on large-memory x86-64 systems
  ...

arch/x86/include/asm/cacheflush.h

@@ -5,65 +5,6 @@
 #include <asm-generic/cacheflush.h>
 #include <asm/special_insns.h>
 
-#ifdef CONFIG_X86_PAT
-/*
- * X86 PAT uses page flags WC and Uncached together to keep track of
- * memory type of pages that have backing page struct. X86 PAT supports 3
- * different memory types, _PAGE_CACHE_WB, _PAGE_CACHE_WC and
- * _PAGE_CACHE_UC_MINUS and fourth state where page's memory type has not
- * been changed from its default (value of -1 used to denote this).
- * Note we do not support _PAGE_CACHE_UC here.
- */
-
-#define _PGMT_DEFAULT		0
-#define _PGMT_WC		(1UL << PG_arch_1)
-#define _PGMT_UC_MINUS		(1UL << PG_uncached)
-#define _PGMT_WB		(1UL << PG_uncached | 1UL << PG_arch_1)
-#define _PGMT_MASK		(1UL << PG_uncached | 1UL << PG_arch_1)
-#define _PGMT_CLEAR_MASK	(~_PGMT_MASK)
-
-static inline unsigned long get_page_memtype(struct page *pg)
-{
-	unsigned long pg_flags = pg->flags & _PGMT_MASK;
-
-	if (pg_flags == _PGMT_DEFAULT)
-		return -1;
-	else if (pg_flags == _PGMT_WC)
-		return _PAGE_CACHE_WC;
-	else if (pg_flags == _PGMT_UC_MINUS)
-		return _PAGE_CACHE_UC_MINUS;
-	else
-		return _PAGE_CACHE_WB;
-}
-
-static inline void set_page_memtype(struct page *pg, unsigned long memtype)
-{
-	unsigned long memtype_flags = _PGMT_DEFAULT;
-	unsigned long old_flags;
-	unsigned long new_flags;
-
-	switch (memtype) {
-	case _PAGE_CACHE_WC:
-		memtype_flags = _PGMT_WC;
-		break;
-	case _PAGE_CACHE_UC_MINUS:
-		memtype_flags = _PGMT_UC_MINUS;
-		break;
-	case _PAGE_CACHE_WB:
-		memtype_flags = _PGMT_WB;
-		break;
-	}
-
-	do {
-		old_flags = pg->flags;
-		new_flags = (old_flags & _PGMT_CLEAR_MASK) | memtype_flags;
-	} while (cmpxchg(&pg->flags, old_flags, new_flags) != old_flags);
-}
-#else
-static inline unsigned long get_page_memtype(struct page *pg) { return -1; }
-static inline void set_page_memtype(struct page *pg, unsigned long memtype) { }
-#endif
-
 /*
  * The set_memory_* API can be used to change various attributes of a virtual
  * address range. The attributes include:

arch/x86/include/asm/fb.h

@@ -8,8 +8,12 @@
 static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma,
 				unsigned long off)
 {
+	unsigned long prot;
+
+	prot = pgprot_val(vma->vm_page_prot) & ~_PAGE_CACHE_MASK;
 	if (boot_cpu_data.x86 > 3)
-		pgprot_val(vma->vm_page_prot) |= _PAGE_PCD;
+		pgprot_val(vma->vm_page_prot) =
+			prot | cachemode2protval(_PAGE_CACHE_MODE_UC_MINUS);
 }
 
 extern int fb_is_primary_device(struct fb_info *info);

arch/x86/include/asm/fixmap.h

@@ -136,9 +136,7 @@ enum fixed_addresses {
 extern void reserve_top_address(unsigned long reserve);
 
 #define FIXADDR_SIZE	(__end_of_permanent_fixed_addresses << PAGE_SHIFT)
-#define FIXADDR_BOOT_SIZE	(__end_of_fixed_addresses << PAGE_SHIFT)
 #define FIXADDR_START		(FIXADDR_TOP - FIXADDR_SIZE)
-#define FIXADDR_BOOT_START	(FIXADDR_TOP - FIXADDR_BOOT_SIZE)
 
 extern int fixmaps_set;
 

arch/x86/include/asm/highmem.h

@@ -38,17 +38,20 @@ extern unsigned long highstart_pfn, highend_pfn;
 /*
  * Ordering is:
  *
- * FIXADDR_TOP
- * 			fixed_addresses
- * FIXADDR_START
- * 			temp fixed addresses
- * FIXADDR_BOOT_START
- * 			Persistent kmap area
- * PKMAP_BASE
- * VMALLOC_END
- * 			Vmalloc area
+ * high memory on:			              high_memory off:
+ *    FIXADDR_TOP                                        FIXADDR_TOP
+ *        fixed addresses                                    fixed addresses
+ *    FIXADDR_START                                      FIXADDR_START
+ *        temp fixed addresses/persistent kmap area      VMALLOC_END
+ *    PKMAP_BASE                                             temp fixed addresses/vmalloc area
+ *    VMALLOC_END                                        VMALLOC_START
+ *        vmalloc area                                   high_memory
  *    VMALLOC_START
  *    high_memory
+ *
+ * The temp fixed area is only used during boot for early_ioremap(), and
+ * it is unused when the ioremap() is functional. vmalloc/pkmap area become
+ * available after early boot so the temp fixed area is available for re-use.
  */
 #define LAST_PKMAP_MASK (LAST_PKMAP-1)
 #define PKMAP_NR(virt)  ((virt-PKMAP_BASE) >> PAGE_SHIFT)

arch/x86/include/asm/io.h

@@ -318,7 +318,7 @@ extern void *xlate_dev_mem_ptr(phys_addr_t phys);
 extern void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr);
 
 extern int ioremap_change_attr(unsigned long vaddr, unsigned long size,
-				unsigned long prot_val);
+				enum page_cache_mode pcm);
 extern void __iomem *ioremap_wc(resource_size_t offset, unsigned long size);
 
 extern bool is_early_ioremap_ptep(pte_t *ptep);

arch/x86/include/asm/pat.h

@@ -11,16 +11,17 @@ static const int pat_enabled;
 #endif
 
 extern void pat_init(void);
+void pat_init_cache_modes(void);
 
 extern int reserve_memtype(u64 start, u64 end,
-		unsigned long req_type, unsigned long *ret_type);
+		enum page_cache_mode req_pcm, enum page_cache_mode *ret_pcm);
 extern int free_memtype(u64 start, u64 end);
 
 extern int kernel_map_sync_memtype(u64 base, unsigned long size,
-		unsigned long flag);
+		enum page_cache_mode pcm);
 
 int io_reserve_memtype(resource_size_t start, resource_size_t end,
-			unsigned long *type);
+			enum page_cache_mode *pcm);
 
 void io_free_memtype(resource_size_t start, resource_size_t end);
 

arch/x86/include/asm/pgtable.h

@@ -11,7 +11,8 @@
  */
 #define pgprot_noncached(prot)						\
 	((boot_cpu_data.x86 > 3)					\
-	 ? (__pgprot(pgprot_val(prot) | _PAGE_CACHE_UC_MINUS))	\
+	 ? (__pgprot(pgprot_val(prot) |					\
+		     cachemode2protval(_PAGE_CACHE_MODE_UC_MINUS)))	\
 	 : (prot))
 
 #ifndef __ASSEMBLY__
@@ -404,8 +405,8 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
 #define canon_pgprot(p) __pgprot(massage_pgprot(p))
 
 static inline int is_new_memtype_allowed(u64 paddr, unsigned long size,
-					 unsigned long flags,
-					 unsigned long new_flags)
+					 enum page_cache_mode pcm,
+					 enum page_cache_mode new_pcm)
 {
 	/*
 	 * PAT type is always WB for untracked ranges, so no need to check.
@@ -419,10 +420,10 @@ static inline int is_new_memtype_allowed(u64 paddr, unsigned long size,
 	 * - request is uncached, return cannot be write-back
 	 * - request is write-combine, return cannot be write-back
 	 */
-	if ((flags == _PAGE_CACHE_UC_MINUS &&
-	     new_flags == _PAGE_CACHE_WB) ||
-	    (flags == _PAGE_CACHE_WC &&
-	     new_flags == _PAGE_CACHE_WB)) {
+	if ((pcm == _PAGE_CACHE_MODE_UC_MINUS &&
+	     new_pcm == _PAGE_CACHE_MODE_WB) ||
+	    (pcm == _PAGE_CACHE_MODE_WC &&
+	     new_pcm == _PAGE_CACHE_MODE_WB)) {
 		return 0;
 	}
 

arch/x86/include/asm/pgtable_32_types.h

@@ -37,7 +37,7 @@ extern bool __vmalloc_start_set; /* set once high_memory is set */
 #define LAST_PKMAP 1024
 #endif
 
-#define PKMAP_BASE ((FIXADDR_BOOT_START - PAGE_SIZE * (LAST_PKMAP + 1))	\
+#define PKMAP_BASE ((FIXADDR_START - PAGE_SIZE * (LAST_PKMAP + 1))	\
 		    & PMD_MASK)
 
 #ifdef CONFIG_HIGHMEM

arch/x86/include/asm/pgtable_types.h

@@ -128,11 +128,28 @@
 			 _PAGE_SOFT_DIRTY | _PAGE_NUMA)
 #define _HPAGE_CHG_MASK (_PAGE_CHG_MASK | _PAGE_PSE | _PAGE_NUMA)
 
-#define _PAGE_CACHE_MASK	(_PAGE_PCD | _PAGE_PWT)
-#define _PAGE_CACHE_WB		(0)
-#define _PAGE_CACHE_WC		(_PAGE_PWT)
-#define _PAGE_CACHE_UC_MINUS	(_PAGE_PCD)
-#define _PAGE_CACHE_UC		(_PAGE_PCD | _PAGE_PWT)
+/*
+ * The cache modes defined here are used to translate between pure SW usage
+ * and the HW defined cache mode bits and/or PAT entries.
+ *
+ * The resulting bits for PWT, PCD and PAT should be chosen in a way
+ * to have the WB mode at index 0 (all bits clear). This is the default
+ * right now and likely would break too much if changed.
+ */
+#ifndef __ASSEMBLY__
+enum page_cache_mode {
+	_PAGE_CACHE_MODE_WB = 0,
+	_PAGE_CACHE_MODE_WC = 1,
+	_PAGE_CACHE_MODE_UC_MINUS = 2,
+	_PAGE_CACHE_MODE_UC = 3,
+	_PAGE_CACHE_MODE_WT = 4,
+	_PAGE_CACHE_MODE_WP = 5,
+	_PAGE_CACHE_MODE_NUM = 8
+};
+#endif
+
+#define _PAGE_CACHE_MASK	(_PAGE_PAT | _PAGE_PCD | _PAGE_PWT)
+#define _PAGE_NOCACHE		(cachemode2protval(_PAGE_CACHE_MODE_UC))
 
 #define PAGE_NONE	__pgprot(_PAGE_PROTNONE | _PAGE_ACCESSED)
 #define PAGE_SHARED	__pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | \
@@ -156,41 +173,27 @@
 
 #define __PAGE_KERNEL_RO		(__PAGE_KERNEL & ~_PAGE_RW)
 #define __PAGE_KERNEL_RX		(__PAGE_KERNEL_EXEC & ~_PAGE_RW)
-#define __PAGE_KERNEL_EXEC_NOCACHE	(__PAGE_KERNEL_EXEC | _PAGE_PCD | _PAGE_PWT)
-#define __PAGE_KERNEL_WC		(__PAGE_KERNEL | _PAGE_CACHE_WC)
-#define __PAGE_KERNEL_NOCACHE		(__PAGE_KERNEL | _PAGE_PCD | _PAGE_PWT)
-#define __PAGE_KERNEL_UC_MINUS		(__PAGE_KERNEL | _PAGE_PCD)
+#define __PAGE_KERNEL_NOCACHE		(__PAGE_KERNEL | _PAGE_NOCACHE)
 #define __PAGE_KERNEL_VSYSCALL		(__PAGE_KERNEL_RX | _PAGE_USER)
 #define __PAGE_KERNEL_VVAR		(__PAGE_KERNEL_RO | _PAGE_USER)
-#define __PAGE_KERNEL_VVAR_NOCACHE	(__PAGE_KERNEL_VVAR | _PAGE_PCD | _PAGE_PWT)
 #define __PAGE_KERNEL_LARGE		(__PAGE_KERNEL | _PAGE_PSE)
-#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)
 #define __PAGE_KERNEL_IO_NOCACHE	(__PAGE_KERNEL_NOCACHE)
-#define __PAGE_KERNEL_IO_UC_MINUS	(__PAGE_KERNEL_UC_MINUS)
-#define __PAGE_KERNEL_IO_WC		(__PAGE_KERNEL_WC)
 
 #define PAGE_KERNEL			__pgprot(__PAGE_KERNEL)
 #define PAGE_KERNEL_RO			__pgprot(__PAGE_KERNEL_RO)
 #define PAGE_KERNEL_EXEC		__pgprot(__PAGE_KERNEL_EXEC)
 #define PAGE_KERNEL_RX			__pgprot(__PAGE_KERNEL_RX)
-#define PAGE_KERNEL_WC			__pgprot(__PAGE_KERNEL_WC)
 #define PAGE_KERNEL_NOCACHE		__pgprot(__PAGE_KERNEL_NOCACHE)
-#define PAGE_KERNEL_UC_MINUS		__pgprot(__PAGE_KERNEL_UC_MINUS)
-#define PAGE_KERNEL_EXEC_NOCACHE	__pgprot(__PAGE_KERNEL_EXEC_NOCACHE)
 #define PAGE_KERNEL_LARGE		__pgprot(__PAGE_KERNEL_LARGE)
-#define PAGE_KERNEL_LARGE_NOCACHE	__pgprot(__PAGE_KERNEL_LARGE_NOCACHE)
 #define PAGE_KERNEL_LARGE_EXEC		__pgprot(__PAGE_KERNEL_LARGE_EXEC)
 #define PAGE_KERNEL_VSYSCALL		__pgprot(__PAGE_KERNEL_VSYSCALL)
 #define PAGE_KERNEL_VVAR		__pgprot(__PAGE_KERNEL_VVAR)
-#define PAGE_KERNEL_VVAR_NOCACHE	__pgprot(__PAGE_KERNEL_VVAR_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
@@ -341,6 +344,59 @@ static inline pmdval_t pmdnuma_flags(pmd_t pmd)
 #define pgprot_val(x)	((x).pgprot)
 #define __pgprot(x)	((pgprot_t) { (x) } )
 
+extern uint16_t __cachemode2pte_tbl[_PAGE_CACHE_MODE_NUM];
+extern uint8_t __pte2cachemode_tbl[8];
+
+#define __pte2cm_idx(cb)				\
+	((((cb) >> (_PAGE_BIT_PAT - 2)) & 4) |		\
+	 (((cb) >> (_PAGE_BIT_PCD - 1)) & 2) |		\
+	 (((cb) >> _PAGE_BIT_PWT) & 1))
+#define __cm_idx2pte(i)					\
+	((((i) & 4) << (_PAGE_BIT_PAT - 2)) |		\
+	 (((i) & 2) << (_PAGE_BIT_PCD - 1)) |		\
+	 (((i) & 1) << _PAGE_BIT_PWT))
+
+static inline unsigned long cachemode2protval(enum page_cache_mode pcm)
+{
+	if (likely(pcm == 0))
+		return 0;
+	return __cachemode2pte_tbl[pcm];
+}
+static inline pgprot_t cachemode2pgprot(enum page_cache_mode pcm)
+{
+	return __pgprot(cachemode2protval(pcm));
+}
+static inline enum page_cache_mode pgprot2cachemode(pgprot_t pgprot)
+{
+	unsigned long masked;
+
+	masked = pgprot_val(pgprot) & _PAGE_CACHE_MASK;
+	if (likely(masked == 0))
+		return 0;
+	return __pte2cachemode_tbl[__pte2cm_idx(masked)];
+}
+static inline pgprot_t pgprot_4k_2_large(pgprot_t pgprot)
+{
+	pgprot_t new;
+	unsigned long val;
+
+	val = pgprot_val(pgprot);
+	pgprot_val(new) = (val & ~(_PAGE_PAT | _PAGE_PAT_LARGE)) |
+		((val & _PAGE_PAT) << (_PAGE_BIT_PAT_LARGE - _PAGE_BIT_PAT));
+	return new;
+}
+static inline pgprot_t pgprot_large_2_4k(pgprot_t pgprot)
+{
+	pgprot_t new;
+	unsigned long val;
+
+	val = pgprot_val(pgprot);
+	pgprot_val(new) = (val & ~(_PAGE_PAT | _PAGE_PAT_LARGE)) |
+			  ((val & _PAGE_PAT_LARGE) >>
+			   (_PAGE_BIT_PAT_LARGE - _PAGE_BIT_PAT));
+	return new;
+}
+
 
 typedef struct page *pgtable_t;
 

arch/x86/mm/dump_pagetables.c

@@ -148,18 +148,16 @@ static void printk_prot(struct seq_file *m, pgprot_t prot, int level, bool dmsg)
 		else
 			pt_dump_cont_printf(m, dmsg, "    ");
 
-		/* Bit 9 has a different meaning on level 3 vs 4 */
-		if (level <= 3) {
-			if (pr & _PAGE_PSE)
+		/* Bit 7 has a different meaning on level 3 vs 4 */
+		if (level <= 3 && pr & _PAGE_PSE)
 			pt_dump_cont_printf(m, dmsg, "PSE ");
 		else
 			pt_dump_cont_printf(m, dmsg, "    ");
-		} else {
-			if (pr & _PAGE_PAT)
+		if ((level == 4 && pr & _PAGE_PAT) ||
+		    ((level == 3 || level == 2) && pr & _PAGE_PAT_LARGE))
 			pt_dump_cont_printf(m, dmsg, "pat ");
 		else
 			pt_dump_cont_printf(m, dmsg, "    ");
-		}
 		if (pr & _PAGE_GLOBAL)
 			pt_dump_cont_printf(m, dmsg, "GLB ");
 		else

arch/x86/mm/init.c

@@ -27,6 +27,35 @@
 
 #include "mm_internal.h"
 
+/*
+ * Tables translating between page_cache_type_t and pte encoding.
+ * Minimal supported modes are defined statically, modified if more supported
+ * cache modes are available.
+ * Index into __cachemode2pte_tbl is the cachemode.
+ * Index into __pte2cachemode_tbl are the caching attribute bits of the pte
+ * (_PAGE_PWT, _PAGE_PCD, _PAGE_PAT) at index bit positions 0, 1, 2.
+ */
+uint16_t __cachemode2pte_tbl[_PAGE_CACHE_MODE_NUM] = {
+	[_PAGE_CACHE_MODE_WB]		= 0,
+	[_PAGE_CACHE_MODE_WC]		= _PAGE_PWT,
+	[_PAGE_CACHE_MODE_UC_MINUS]	= _PAGE_PCD,
+	[_PAGE_CACHE_MODE_UC]		= _PAGE_PCD | _PAGE_PWT,
+	[_PAGE_CACHE_MODE_WT]		= _PAGE_PCD,
+	[_PAGE_CACHE_MODE_WP]		= _PAGE_PCD,
+};
+EXPORT_SYMBOL_GPL(__cachemode2pte_tbl);
+uint8_t __pte2cachemode_tbl[8] = {
+	[__pte2cm_idx(0)] = _PAGE_CACHE_MODE_WB,
+	[__pte2cm_idx(_PAGE_PWT)] = _PAGE_CACHE_MODE_WC,
+	[__pte2cm_idx(_PAGE_PCD)] = _PAGE_CACHE_MODE_UC_MINUS,
+	[__pte2cm_idx(_PAGE_PWT | _PAGE_PCD)] = _PAGE_CACHE_MODE_UC,
+	[__pte2cm_idx(_PAGE_PAT)] = _PAGE_CACHE_MODE_WB,
+	[__pte2cm_idx(_PAGE_PWT | _PAGE_PAT)] = _PAGE_CACHE_MODE_WC,
+	[__pte2cm_idx(_PAGE_PCD | _PAGE_PAT)] = _PAGE_CACHE_MODE_UC_MINUS,
+	[__pte2cm_idx(_PAGE_PWT | _PAGE_PCD | _PAGE_PAT)] = _PAGE_CACHE_MODE_UC,
+};
+EXPORT_SYMBOL_GPL(__pte2cachemode_tbl);
+
 static unsigned long __initdata pgt_buf_start;
 static unsigned long __initdata pgt_buf_end;
 static unsigned long __initdata pgt_buf_top;
@@ -687,3 +716,11 @@ void __init zone_sizes_init(void)
 	free_area_init_nodes(max_zone_pfns);
 }
 
+void update_cache_mode_entry(unsigned entry, enum page_cache_mode cache)
+{
+	/* entry 0 MUST be WB (hardwired to speed up translations) */
+	BUG_ON(!entry && cache != _PAGE_CACHE_MODE_WB);
+
+	__cachemode2pte_tbl[cache] = __cm_idx2pte(entry);
+	__pte2cachemode_tbl[entry] = cache;
+}

arch/x86/mm/init_64.c

@@ -52,7 +52,6 @@
 #include <asm/numa.h>
 #include <asm/cacheflush.h>
 #include <asm/init.h>
-#include <asm/uv/uv.h>
 #include <asm/setup.h>
 
 #include "mm_internal.h"
@@ -338,12 +337,15 @@ pte_t * __init populate_extra_pte(unsigned long vaddr)
  * Create large page table mappings for a range of physical addresses.
  */
 static void __init __init_extra_mapping(unsigned long phys, unsigned long size,
-						pgprot_t prot)
+					enum page_cache_mode cache)
 {
 	pgd_t *pgd;
 	pud_t *pud;
 	pmd_t *pmd;
+	pgprot_t prot;
 
+	pgprot_val(prot) = pgprot_val(PAGE_KERNEL_LARGE) |
+		pgprot_val(pgprot_4k_2_large(cachemode2pgprot(cache)));
 	BUG_ON((phys & ~PMD_MASK) || (size & ~PMD_MASK));
 	for (; size; phys += PMD_SIZE, size -= PMD_SIZE) {
 		pgd = pgd_offset_k((unsigned long)__va(phys));
@@ -366,12 +368,12 @@ static void __init __init_extra_mapping(unsigned long phys, unsigned long size,
 
 void __init init_extra_mapping_wb(unsigned long phys, unsigned long size)
 {
-	__init_extra_mapping(phys, size, PAGE_KERNEL_LARGE);
+	__init_extra_mapping(phys, size, _PAGE_CACHE_MODE_WB);
 }
 
 void __init init_extra_mapping_uc(unsigned long phys, unsigned long size)
 {
-	__init_extra_mapping(phys, size, PAGE_KERNEL_LARGE_NOCACHE);
+	__init_extra_mapping(phys, size, _PAGE_CACHE_MODE_UC);
 }
 
 /*
@@ -1256,12 +1258,10 @@ static unsigned long probe_memory_block_size(void)
 	/* start from 2g */
 	unsigned long bz = 1UL<<31;
 
-#ifdef CONFIG_X86_UV
-	if (is_uv_system()) {
-		printk(KERN_INFO "UV: memory block size 2GB\n");
+	if (totalram_pages >= (64ULL << (30 - PAGE_SHIFT))) {
+		pr_info("Using 2GB memory block size for large-memory system\n");
 		return 2UL * 1024 * 1024 * 1024;
 	}
-#endif
 
 	/* less than 64g installed */
 	if ((max_pfn << PAGE_SHIFT) < (16UL << 32))

arch/x86/mm/iomap_32.c

@@ -33,17 +33,17 @@ static int is_io_mapping_possible(resource_size_t base, unsigned long size)
 
 int iomap_create_wc(resource_size_t base, unsigned long size, pgprot_t *prot)
 {
-	unsigned long flag = _PAGE_CACHE_WC;
+	enum page_cache_mode pcm = _PAGE_CACHE_MODE_WC;
 	int ret;
 
 	if (!is_io_mapping_possible(base, size))
 		return -EINVAL;
 
-	ret = io_reserve_memtype(base, base + size, &flag);
+	ret = io_reserve_memtype(base, base + size, &pcm);
 	if (ret)
 		return ret;
 
-	*prot = __pgprot(__PAGE_KERNEL | flag);
+	*prot = __pgprot(__PAGE_KERNEL | cachemode2protval(pcm));
 	return 0;
 }
 EXPORT_SYMBOL_GPL(iomap_create_wc);
@@ -82,8 +82,10 @@ iomap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot)
 	 * MTRR is UC or WC.  UC_MINUS gets the real intention, of the
 	 * user, which is "WC if the MTRR is WC, UC if you can't do that."
 	 */
-	if (!pat_enabled && pgprot_val(prot) == pgprot_val(PAGE_KERNEL_WC))
-		prot = PAGE_KERNEL_UC_MINUS;
+	if (!pat_enabled && pgprot_val(prot) ==
+	    (__PAGE_KERNEL | cachemode2protval(_PAGE_CACHE_MODE_WC)))
+		prot = __pgprot(__PAGE_KERNEL |
+				cachemode2protval(_PAGE_CACHE_MODE_UC_MINUS));
 
 	return (void __force __iomem *) kmap_atomic_prot_pfn(pfn, prot);
 }

arch/x86/mm/ioremap.c

@@ -29,20 +29,20 @@
  * conflicts.
  */
 int ioremap_change_attr(unsigned long vaddr, unsigned long size,
-			       unsigned long prot_val)
+			enum page_cache_mode pcm)
 {
 	unsigned long nrpages = size >> PAGE_SHIFT;
 	int err;
 
-	switch (prot_val) {
-	case _PAGE_CACHE_UC:
+	switch (pcm) {
+	case _PAGE_CACHE_MODE_UC:
 	default:
 		err = _set_memory_uc(vaddr, nrpages);
 		break;
-	case _PAGE_CACHE_WC:
+	case _PAGE_CACHE_MODE_WC:
 		err = _set_memory_wc(vaddr, nrpages);
 		break;
-	case _PAGE_CACHE_WB:
+	case _PAGE_CACHE_MODE_WB:
 		err = _set_memory_wb(vaddr, nrpages);
 		break;
 	}
@@ -75,14 +75,14 @@ static int __ioremap_check_ram(unsigned long start_pfn, unsigned long nr_pages,
  * caller shouldn't need to know that small detail.
  */
 static void __iomem *__ioremap_caller(resource_size_t phys_addr,
-		unsigned long size, unsigned long prot_val, void *caller)
+		unsigned long size, enum page_cache_mode pcm, void *caller)
 {
 	unsigned long offset, vaddr;
 	resource_size_t pfn, last_pfn, last_addr;
 	const resource_size_t unaligned_phys_addr = phys_addr;
 	const unsigned long unaligned_size = size;
 	struct vm_struct *area;
-	unsigned long new_prot_val;
+	enum page_cache_mode new_pcm;
 	pgprot_t prot;
 	int retval;
 	void __iomem *ret_addr;
@@ -134,38 +134,40 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr,
 	size = PAGE_ALIGN(last_addr+1) - phys_addr;
 
 	retval = reserve_memtype(phys_addr, (u64)phys_addr + size,
-						prot_val, &new_prot_val);
+						pcm, &new_pcm);
 	if (retval) {
 		printk(KERN_ERR "ioremap reserve_memtype failed %d\n", retval);
 		return NULL;
 	}
 
-	if (prot_val != new_prot_val) {
-		if (!is_new_memtype_allowed(phys_addr, size,
-					    prot_val, new_prot_val)) {
+	if (pcm != new_pcm) {
+		if (!is_new_memtype_allowed(phys_addr, size, pcm, new_pcm)) {
 			printk(KERN_ERR
-		"ioremap error for 0x%llx-0x%llx, requested 0x%lx, got 0x%lx\n",
+		"ioremap error for 0x%llx-0x%llx, requested 0x%x, got 0x%x\n",
 				(unsigned long long)phys_addr,
 				(unsigned long long)(phys_addr + size),
-				prot_val, new_prot_val);
+				pcm, new_pcm);
 			goto err_free_memtype;
 		}
-		prot_val = new_prot_val;
+		pcm = new_pcm;
 	}
 
-	switch (prot_val) {
-	case _PAGE_CACHE_UC:
+	prot = PAGE_KERNEL_IO;
+	switch (pcm) {
+	case _PAGE_CACHE_MODE_UC:
 	default:
-		prot = PAGE_KERNEL_IO_NOCACHE;
+		prot = __pgprot(pgprot_val(prot) |
+				cachemode2protval(_PAGE_CACHE_MODE_UC));
 		break;
-	case _PAGE_CACHE_UC_MINUS:
-		prot = PAGE_KERNEL_IO_UC_MINUS;
+	case _PAGE_CACHE_MODE_UC_MINUS:
+		prot = __pgprot(pgprot_val(prot) |
+				cachemode2protval(_PAGE_CACHE_MODE_UC_MINUS));
 		break;
-	case _PAGE_CACHE_WC:
-		prot = PAGE_KERNEL_IO_WC;
+	case _PAGE_CACHE_MODE_WC:
+		prot = __pgprot(pgprot_val(prot) |
+				cachemode2protval(_PAGE_CACHE_MODE_WC));
 		break;
-	case _PAGE_CACHE_WB:
-		prot = PAGE_KERNEL_IO;
+	case _PAGE_CACHE_MODE_WB:
 		break;
 	}
 
@@ -178,7 +180,7 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr,
 	area->phys_addr = phys_addr;
 	vaddr = (unsigned long) area->addr;
 
-	if (kernel_map_sync_memtype(phys_addr, size, prot_val))
+	if (kernel_map_sync_memtype(phys_addr, size, pcm))
 		goto err_free_area;
 
 	if (ioremap_page_range(vaddr, vaddr + size, phys_addr, prot))
@@ -227,14 +229,14 @@ void __iomem *ioremap_nocache(resource_size_t phys_addr, unsigned long size)
 {
 	/*
 	 * Ideally, this should be:
-	 *	pat_enabled ? _PAGE_CACHE_UC : _PAGE_CACHE_UC_MINUS;
+	 *	pat_enabled ? _PAGE_CACHE_MODE_UC : _PAGE_CACHE_MODE_UC_MINUS;
 	 *
 	 * Till we fix all X drivers to use ioremap_wc(), we will use
 	 * UC MINUS.
 	 */
-	unsigned long val = _PAGE_CACHE_UC_MINUS;
+	enum page_cache_mode pcm = _PAGE_CACHE_MODE_UC_MINUS;
 
-	return __ioremap_caller(phys_addr, size, val,
+	return __ioremap_caller(phys_addr, size, pcm,
 				__builtin_return_address(0));
 }
 EXPORT_SYMBOL(ioremap_nocache);
@@ -252,7 +254,7 @@ EXPORT_SYMBOL(ioremap_nocache);
 void __iomem *ioremap_wc(resource_size_t phys_addr, unsigned long size)
 {
 	if (pat_enabled)
-		return __ioremap_caller(phys_addr, size, _PAGE_CACHE_WC,
+		return __ioremap_caller(phys_addr, size, _PAGE_CACHE_MODE_WC,
 					__builtin_return_address(0));
 	else
 		return ioremap_nocache(phys_addr, size);
@@ -261,7 +263,7 @@ EXPORT_SYMBOL(ioremap_wc);
 
 void __iomem *ioremap_cache(resource_size_t phys_addr, unsigned long size)
 {
-	return __ioremap_caller(phys_addr, size, _PAGE_CACHE_WB,
+	return __ioremap_caller(phys_addr, size, _PAGE_CACHE_MODE_WB,
 				__builtin_return_address(0));
 }
 EXPORT_SYMBOL(ioremap_cache);
@@ -269,7 +271,8 @@ EXPORT_SYMBOL(ioremap_cache);
 void __iomem *ioremap_prot(resource_size_t phys_addr, unsigned long size,
 				unsigned long prot_val)
 {
-	return __ioremap_caller(phys_addr, size, (prot_val & _PAGE_CACHE_MASK),
+	return __ioremap_caller(phys_addr, size,
+				pgprot2cachemode(__pgprot(prot_val)),
 				__builtin_return_address(0));
 }
 EXPORT_SYMBOL(ioremap_prot);

arch/x86/mm/mm_internal.h

@@ -16,4 +16,6 @@ void zone_sizes_init(void);
 
 extern int after_bootmem;
 
+void update_cache_mode_entry(unsigned entry, enum page_cache_mode cache);
+
 #endif	/* __X86_MM_INTERNAL_H */

arch/x86/mm/pageattr.c

@@ -485,13 +485,22 @@ try_preserve_large_page(pte_t *kpte, unsigned long address,
 
 	/*
 	 * We are safe now. Check whether the new pgprot is the same:
+	 * Convert protection attributes to 4k-format, as cpa->mask* are set
+	 * up accordingly.
 	 */
 	old_pte = *kpte;
-	old_prot = req_prot = pte_pgprot(old_pte);
+	old_prot = req_prot = pgprot_large_2_4k(pte_pgprot(old_pte));
 
 	pgprot_val(req_prot) &= ~pgprot_val(cpa->mask_clr);
 	pgprot_val(req_prot) |= pgprot_val(cpa->mask_set);
 
+	/*
+	 * req_prot is in format of 4k pages. It must be converted to large
+	 * page format: the caching mode includes the PAT bit located at
+	 * different bit positions in the two formats.
+	 */
+	req_prot = pgprot_4k_2_large(req_prot);
+
 	/*
 	 * Set the PSE and GLOBAL flags only if the PRESENT flag is
 	 * set otherwise pmd_present/pmd_huge will return true even on
@@ -585,13 +594,10 @@ __split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address,
 
 	paravirt_alloc_pte(&init_mm, page_to_pfn(base));
 	ref_prot = pte_pgprot(pte_clrhuge(*kpte));
-	/*
-	 * If we ever want to utilize the PAT bit, we need to
-	 * update this function to make sure it's converted from
-	 * bit 12 to bit 7 when we cross from the 2MB level to
-	 * the 4K level:
-	 */
-	WARN_ON_ONCE(pgprot_val(ref_prot) & _PAGE_PAT_LARGE);
+
+	/* promote PAT bit to correct position */
+	if (level == PG_LEVEL_2M)
+		ref_prot = pgprot_large_2_4k(ref_prot);
 
 #ifdef CONFIG_X86_64
 	if (level == PG_LEVEL_1G) {
@@ -879,6 +885,7 @@ static int populate_pmd(struct cpa_data *cpa,
 {
 	unsigned int cur_pages = 0;
 	pmd_t *pmd;
+	pgprot_t pmd_pgprot;
 
 	/*
 	 * Not on a 2M boundary?
@@ -910,6 +917,8 @@ static int populate_pmd(struct cpa_data *cpa,
 	if (num_pages == cur_pages)
 		return cur_pages;
 
+	pmd_pgprot = pgprot_4k_2_large(pgprot);
+
 	while (end - start >= PMD_SIZE) {
 
 		/*
@@ -921,7 +930,8 @@ static int populate_pmd(struct cpa_data *cpa,
 
 		pmd = pmd_offset(pud, start);
 
-		set_pmd(pmd, __pmd(cpa->pfn | _PAGE_PSE | massage_pgprot(pgprot)));
+		set_pmd(pmd, __pmd(cpa->pfn | _PAGE_PSE |
+				   massage_pgprot(pmd_pgprot)));
 
 		start	  += PMD_SIZE;
 		cpa->pfn  += PMD_SIZE;
@@ -949,6 +959,7 @@ static int populate_pud(struct cpa_data *cpa, unsigned long start, pgd_t *pgd,
 	pud_t *pud;
 	unsigned long end;
 	int cur_pages = 0;
+	pgprot_t pud_pgprot;
 
 	end = start + (cpa->numpages << PAGE_SHIFT);
 
@@ -986,12 +997,14 @@ static int populate_pud(struct cpa_data *cpa, unsigned long start, pgd_t *pgd,
 		return cur_pages;
 
 	pud = pud_offset(pgd, start);
+	pud_pgprot = pgprot_4k_2_large(pgprot);
 
 	/*
 	 * Map everything starting from the Gb boundary, possibly with 1G pages
 	 */
 	while (end - start >= PUD_SIZE) {
-		set_pud(pud, __pud(cpa->pfn | _PAGE_PSE | massage_pgprot(pgprot)));
+		set_pud(pud, __pud(cpa->pfn | _PAGE_PSE |
+				   massage_pgprot(pud_pgprot)));
 
 		start	  += PUD_SIZE;
 		cpa->pfn  += PUD_SIZE;
@@ -1304,12 +1317,6 @@ static int __change_page_attr_set_clr(struct cpa_data *cpa, int checkalias)
 	return 0;
 }
 
-static inline int cache_attr(pgprot_t attr)
-{
-	return pgprot_val(attr) &
-		(_PAGE_PAT | _PAGE_PAT_LARGE | _PAGE_PWT | _PAGE_PCD);
-}
-
 static int change_page_attr_set_clr(unsigned long *addr, int numpages,
 				    pgprot_t mask_set, pgprot_t mask_clr,
 				    int force_split, int in_flag,
@@ -1390,7 +1397,7 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages,
 	 * No need to flush, when we did not set any of the caching
 	 * attributes:
 	 */
-	cache = cache_attr(mask_set);
+	cache = !!pgprot2cachemode(mask_set);
 
 	/*
 	 * On success we use CLFLUSH, when the CPU supports it to
@@ -1445,7 +1452,8 @@ 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_MINUS), 0);
+				    cachemode2pgprot(_PAGE_CACHE_MODE_UC_MINUS),
+				    0);
 }
 
 int set_memory_uc(unsigned long addr, int numpages)
@@ -1456,7 +1464,7 @@ int set_memory_uc(unsigned long addr, int numpages)
 	 * for now UC MINUS. see comments in ioremap_nocache()
 	 */
 	ret = reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE,
-			    _PAGE_CACHE_UC_MINUS, NULL);
+			      _PAGE_CACHE_MODE_UC_MINUS, NULL);
 	if (ret)
 		goto out_err;
 
@@ -1474,7 +1482,7 @@ int set_memory_uc(unsigned long addr, int numpages)
 EXPORT_SYMBOL(set_memory_uc);
 
 static int _set_memory_array(unsigned long *addr, int addrinarray,
-		unsigned long new_type)
+		enum page_cache_mode new_type)
 {
 	int i, j;
 	int ret;
@@ -1490,11 +1498,13 @@ static int _set_memory_array(unsigned long *addr, int addrinarray,
 	}
 
 	ret = change_page_attr_set(addr, addrinarray,
-				    __pgprot(_PAGE_CACHE_UC_MINUS), 1);
+				   cachemode2pgprot(_PAGE_CACHE_MODE_UC_MINUS),
+				   1);
 
-	if (!ret && new_type == _PAGE_CACHE_WC)
+	if (!ret && new_type == _PAGE_CACHE_MODE_WC)
 		ret = change_page_attr_set_clr(addr, addrinarray,
-					       __pgprot(_PAGE_CACHE_WC),
+					       cachemode2pgprot(
+						_PAGE_CACHE_MODE_WC),
 					       __pgprot(_PAGE_CACHE_MASK),
 					       0, CPA_ARRAY, NULL);
 	if (ret)
@@ -1511,13 +1521,13 @@ static int _set_memory_array(unsigned long *addr, int addrinarray,
 
 int set_memory_array_uc(unsigned long *addr, int addrinarray)
 {
-	return _set_memory_array(addr, addrinarray, _PAGE_CACHE_UC_MINUS);
+	return _set_memory_array(addr, addrinarray, _PAGE_CACHE_MODE_UC_MINUS);
 }
 EXPORT_SYMBOL(set_memory_array_uc);
 
 int set_memory_array_wc(unsigned long *addr, int addrinarray)
 {
-	return _set_memory_array(addr, addrinarray, _PAGE_CACHE_WC);
+	return _set_memory_array(addr, addrinarray, _PAGE_CACHE_MODE_WC);
 }
 EXPORT_SYMBOL(set_memory_array_wc);
 
@@ -1527,10 +1537,12 @@ int _set_memory_wc(unsigned long addr, int numpages)
 	unsigned long addr_copy = addr;
 
 	ret = change_page_attr_set(&addr, numpages,
-				    __pgprot(_PAGE_CACHE_UC_MINUS), 0);
+				   cachemode2pgprot(_PAGE_CACHE_MODE_UC_MINUS),
+				   0);
 	if (!ret) {
 		ret = change_page_attr_set_clr(&addr_copy, numpages,
-					       __pgprot(_PAGE_CACHE_WC),
+					       cachemode2pgprot(
+						_PAGE_CACHE_MODE_WC),
 					       __pgprot(_PAGE_CACHE_MASK),
 					       0, 0, NULL);
 	}
@@ -1545,7 +1557,7 @@ int set_memory_wc(unsigned long addr, int numpages)
 		return set_memory_uc(addr, numpages);
 
 	ret = reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE,
-		_PAGE_CACHE_WC, NULL);
+		_PAGE_CACHE_MODE_WC, NULL);
 	if (ret)
 		goto out_err;
 
@@ -1564,6 +1576,7 @@ EXPORT_SYMBOL(set_memory_wc);
 
 int _set_memory_wb(unsigned long addr, int numpages)
 {
+	/* WB cache mode is hard wired to all cache attribute bits being 0 */
 	return change_page_attr_clear(&addr, numpages,
 				      __pgprot(_PAGE_CACHE_MASK), 0);
 }
@@ -1586,6 +1599,7 @@ int set_memory_array_wb(unsigned long *addr, int addrinarray)
 	int i;
 	int ret;
 
+	/* WB cache mode is hard wired to all cache attribute bits being 0 */
 	ret = change_page_attr_clear(addr, addrinarray,
 				      __pgprot(_PAGE_CACHE_MASK), 1);
 	if (ret)
@@ -1648,7 +1662,7 @@ int set_pages_uc(struct page *page, int numpages)
 EXPORT_SYMBOL(set_pages_uc);
 
 static int _set_pages_array(struct page **pages, int addrinarray,
-		unsigned long new_type)
+		enum page_cache_mode new_type)
 {
 	unsigned long start;
 	unsigned long end;
@@ -1666,10 +1680,11 @@ static int _set_pages_array(struct page **pages, int addrinarray,
 	}
 
 	ret = cpa_set_pages_array(pages, addrinarray,
-			__pgprot(_PAGE_CACHE_UC_MINUS));
-	if (!ret && new_type == _PAGE_CACHE_WC)
+			cachemode2pgprot(_PAGE_CACHE_MODE_UC_MINUS));
+	if (!ret && new_type == _PAGE_CACHE_MODE_WC)
 		ret = change_page_attr_set_clr(NULL, addrinarray,
-					       __pgprot(_PAGE_CACHE_WC),
+					       cachemode2pgprot(
+						_PAGE_CACHE_MODE_WC),
 					       __pgprot(_PAGE_CACHE_MASK),
 					       0, CPA_PAGES_ARRAY, pages);
 	if (ret)
@@ -1689,13 +1704,13 @@ static int _set_pages_array(struct page **pages, int addrinarray,
 
 int set_pages_array_uc(struct page **pages, int addrinarray)
 {
-	return _set_pages_array(pages, addrinarray, _PAGE_CACHE_UC_MINUS);
+	return _set_pages_array(pages, addrinarray, _PAGE_CACHE_MODE_UC_MINUS);
 }
 EXPORT_SYMBOL(set_pages_array_uc);
 
 int set_pages_array_wc(struct page **pages, int addrinarray)
 {
-	return _set_pages_array(pages, addrinarray, _PAGE_CACHE_WC);
+	return _set_pages_array(pages, addrinarray, _PAGE_CACHE_MODE_WC);
 }
 EXPORT_SYMBOL(set_pages_array_wc);
 
@@ -1714,6 +1729,7 @@ int set_pages_array_wb(struct page **pages, int addrinarray)
 	unsigned long end;
 	int i;
 
+	/* WB cache mode is hard wired to all cache attribute bits being 0 */
 	retval = cpa_clear_pages_array(pages, addrinarray,
 			__pgprot(_PAGE_CACHE_MASK));
 	if (retval)

arch/x86/mm/pat.c

@@ -31,6 +31,7 @@
 #include <asm/io.h>
 
 #include "pat_internal.h"
+#include "mm_internal.h"
 
 #ifdef CONFIG_X86_PAT
 int __read_mostly pat_enabled = 1;
@@ -66,6 +67,75 @@ __setup("debugpat", pat_debug_setup);
 
 static u64 __read_mostly boot_pat_state;
 
+#ifdef CONFIG_X86_PAT
+/*
+ * X86 PAT uses page flags WC and Uncached together to keep track of
+ * memory type of pages that have backing page struct. X86 PAT supports 3
+ * different memory types, _PAGE_CACHE_MODE_WB, _PAGE_CACHE_MODE_WC and
+ * _PAGE_CACHE_MODE_UC_MINUS and fourth state where page's memory type has not
+ * been changed from its default (value of -1 used to denote this).
+ * Note we do not support _PAGE_CACHE_MODE_UC here.
+ */
+
+#define _PGMT_DEFAULT		0
+#define _PGMT_WC		(1UL << PG_arch_1)
+#define _PGMT_UC_MINUS		(1UL << PG_uncached)
+#define _PGMT_WB		(1UL << PG_uncached | 1UL << PG_arch_1)
+#define _PGMT_MASK		(1UL << PG_uncached | 1UL << PG_arch_1)
+#define _PGMT_CLEAR_MASK	(~_PGMT_MASK)
+
+static inline enum page_cache_mode get_page_memtype(struct page *pg)
+{
+	unsigned long pg_flags = pg->flags & _PGMT_MASK;
+
+	if (pg_flags == _PGMT_DEFAULT)
+		return -1;
+	else if (pg_flags == _PGMT_WC)
+		return _PAGE_CACHE_MODE_WC;
+	else if (pg_flags == _PGMT_UC_MINUS)
+		return _PAGE_CACHE_MODE_UC_MINUS;
+	else
+		return _PAGE_CACHE_MODE_WB;
+}
+
+static inline void set_page_memtype(struct page *pg,
+				    enum page_cache_mode memtype)
+{
+	unsigned long memtype_flags;
+	unsigned long old_flags;
+	unsigned long new_flags;
+
+	switch (memtype) {
+	case _PAGE_CACHE_MODE_WC:
+		memtype_flags = _PGMT_WC;
+		break;
+	case _PAGE_CACHE_MODE_UC_MINUS:
+		memtype_flags = _PGMT_UC_MINUS;
+		break;
+	case _PAGE_CACHE_MODE_WB:
+		memtype_flags = _PGMT_WB;
+		break;
+	default:
+		memtype_flags = _PGMT_DEFAULT;
+		break;
+	}
+
+	do {
+		old_flags = pg->flags;
+		new_flags = (old_flags & _PGMT_CLEAR_MASK) | memtype_flags;
+	} while (cmpxchg(&pg->flags, old_flags, new_flags) != old_flags);
+}
+#else
+static inline enum page_cache_mode get_page_memtype(struct page *pg)
+{
+	return -1;
+}
+static inline void set_page_memtype(struct page *pg,
+				    enum page_cache_mode memtype)
+{
+}
+#endif
+
 enum {
 	PAT_UC = 0,		/* uncached */
 	PAT_WC = 1,		/* Write combining */
@@ -75,6 +145,52 @@ enum {
 	PAT_UC_MINUS = 7,	/* UC, but can be overriden by MTRR */
 };
 
+#define CM(c) (_PAGE_CACHE_MODE_ ## c)
+
+static enum page_cache_mode pat_get_cache_mode(unsigned pat_val, char *msg)
+{
+	enum page_cache_mode cache;
+	char *cache_mode;
+
+	switch (pat_val) {
+	case PAT_UC:       cache = CM(UC);       cache_mode = "UC  "; break;
+	case PAT_WC:       cache = CM(WC);       cache_mode = "WC  "; break;
+	case PAT_WT:       cache = CM(WT);       cache_mode = "WT  "; break;
+	case PAT_WP:       cache = CM(WP);       cache_mode = "WP  "; break;
+	case PAT_WB:       cache = CM(WB);       cache_mode = "WB  "; break;
+	case PAT_UC_MINUS: cache = CM(UC_MINUS); cache_mode = "UC- "; break;
+	default:           cache = CM(WB);       cache_mode = "WB  "; break;
+	}
+
+	memcpy(msg, cache_mode, 4);
+
+	return cache;
+}
+
+#undef CM
+
+/*
+ * Update the cache mode to pgprot translation tables according to PAT
+ * configuration.
+ * Using lower indices is preferred, so we start with highest index.
+ */
+void pat_init_cache_modes(void)
+{
+	int i;
+	enum page_cache_mode cache;
+	char pat_msg[33];
+	u64 pat;
+
+	rdmsrl(MSR_IA32_CR_PAT, pat);
+	pat_msg[32] = 0;
+	for (i = 7; i >= 0; i--) {
+		cache = pat_get_cache_mode((pat >> (i * 8)) & 7,
+					   pat_msg + 4 * i);
+		update_cache_mode_entry(i, cache);
+	}
+	pr_info("PAT configuration [0-7]: %s\n", pat_msg);
+}
+
 #define PAT(x, y)	((u64)PAT_ ## y << ((x)*8))
 
 void pat_init(void)
@@ -124,8 +240,7 @@ void pat_init(void)
 	wrmsrl(MSR_IA32_CR_PAT, pat);
 
 	if (boot_cpu)
-		printk(KERN_INFO "x86 PAT enabled: cpu %d, old 0x%Lx, new 0x%Lx\n",
-		       smp_processor_id(), boot_pat_state, pat);
+		pat_init_cache_modes();
 }
 
 #undef PAT
@@ -139,20 +254,21 @@ static DEFINE_SPINLOCK(memtype_lock);	/* protects memtype accesses */
  * The intersection is based on "Effective Memory Type" tables in IA-32
  * SDM vol 3a
  */
-static unsigned long pat_x_mtrr_type(u64 start, u64 end, unsigned long req_type)
+static unsigned long pat_x_mtrr_type(u64 start, u64 end,
+				     enum page_cache_mode req_type)
 {
 	/*
 	 * Look for MTRR hint to get the effective type in case where PAT
 	 * request is for WB.
 	 */
-	if (req_type == _PAGE_CACHE_WB) {
+	if (req_type == _PAGE_CACHE_MODE_WB) {
 		u8 mtrr_type;
 
 		mtrr_type = mtrr_type_lookup(start, end);
 		if (mtrr_type != MTRR_TYPE_WRBACK)
-			return _PAGE_CACHE_UC_MINUS;
+			return _PAGE_CACHE_MODE_UC_MINUS;
 
-		return _PAGE_CACHE_WB;
+		return _PAGE_CACHE_MODE_WB;
 	}
 
 	return req_type;
@@ -207,25 +323,26 @@ static int pat_pagerange_is_ram(resource_size_t start, resource_size_t end)
  * - Find the memtype of all the pages in the range, look for any conflicts
  * - In case of no conflicts, set the new memtype for pages in the range
  */
-static int reserve_ram_pages_type(u64 start, u64 end, unsigned long req_type,
-				  unsigned long *new_type)
+static int reserve_ram_pages_type(u64 start, u64 end,
+				  enum page_cache_mode req_type,
+				  enum page_cache_mode *new_type)
 {
 	struct page *page;
 	u64 pfn;
 
-	if (req_type == _PAGE_CACHE_UC) {
+	if (req_type == _PAGE_CACHE_MODE_UC) {
 		/* We do not support strong UC */
 		WARN_ON_ONCE(1);
-		req_type = _PAGE_CACHE_UC_MINUS;
+		req_type = _PAGE_CACHE_MODE_UC_MINUS;
 	}
 
 	for (pfn = (start >> PAGE_SHIFT); pfn < (end >> PAGE_SHIFT); ++pfn) {
-		unsigned long type;
+		enum page_cache_mode type;
 
 		page = pfn_to_page(pfn);
 		type = get_page_memtype(page);
 		if (type != -1) {
-			printk(KERN_INFO "reserve_ram_pages_type failed [mem %#010Lx-%#010Lx], track 0x%lx, req 0x%lx\n",
+			pr_info("reserve_ram_pages_type failed [mem %#010Lx-%#010Lx], track 0x%x, req 0x%x\n",
 				start, end - 1, type, req_type);
 			if (new_type)
 				*new_type = type;
@@ -258,21 +375,21 @@ static int free_ram_pages_type(u64 start, u64 end)
 
 /*
  * req_type typically has one of the:
- * - _PAGE_CACHE_WB
- * - _PAGE_CACHE_WC
- * - _PAGE_CACHE_UC_MINUS
- * - _PAGE_CACHE_UC
+ * - _PAGE_CACHE_MODE_WB
+ * - _PAGE_CACHE_MODE_WC
+ * - _PAGE_CACHE_MODE_UC_MINUS
+ * - _PAGE_CACHE_MODE_UC
  *
  * If new_type is NULL, function will return an error if it cannot reserve the
  * region with req_type. If new_type is non-NULL, function will return
  * available type in new_type in case of no error. In case of any error
  * it will return a negative return value.
  */
-int reserve_memtype(u64 start, u64 end, unsigned long req_type,
-		    unsigned long *new_type)
+int reserve_memtype(u64 start, u64 end, enum page_cache_mode req_type,
+		    enum page_cache_mode *new_type)
 {
 	struct memtype *new;
-	unsigned long actual_type;
+	enum page_cache_mode actual_type;
 	int is_range_ram;
 	int err = 0;
 
@@ -281,10 +398,10 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 	if (!pat_enabled) {
 		/* This is identical to page table setting without PAT */
 		if (new_type) {
-			if (req_type == _PAGE_CACHE_WC)
-				*new_type = _PAGE_CACHE_UC_MINUS;
+			if (req_type == _PAGE_CACHE_MODE_WC)
+				*new_type = _PAGE_CACHE_MODE_UC_MINUS;
 			else
-				*new_type = req_type & _PAGE_CACHE_MASK;
+				*new_type = req_type;
 		}
 		return 0;
 	}
@@ -292,7 +409,7 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 	/* Low ISA region is always mapped WB in page table. No need to track */
 	if (x86_platform.is_untracked_pat_range(start, end)) {
 		if (new_type)
-			*new_type = _PAGE_CACHE_WB;
+			*new_type = _PAGE_CACHE_MODE_WB;
 		return 0;
 	}
 
@@ -302,7 +419,7 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 	 * tools and ACPI tools). Use WB request for WB memory and use
 	 * UC_MINUS otherwise.
 	 */
-	actual_type = pat_x_mtrr_type(start, end, req_type & _PAGE_CACHE_MASK);
+	actual_type = pat_x_mtrr_type(start, end, req_type);
 
 	if (new_type)
 		*new_type = actual_type;
@@ -394,12 +511,12 @@ int free_memtype(u64 start, u64 end)
  *
  * Only to be called when PAT is enabled
  *
- * Returns _PAGE_CACHE_WB, _PAGE_CACHE_WC, _PAGE_CACHE_UC_MINUS or
- * _PAGE_CACHE_UC
+ * Returns _PAGE_CACHE_MODE_WB, _PAGE_CACHE_MODE_WC, _PAGE_CACHE_MODE_UC_MINUS
+ * or _PAGE_CACHE_MODE_UC
  */
-static unsigned long lookup_memtype(u64 paddr)
+static enum page_cache_mode lookup_memtype(u64 paddr)
 {
-	int rettype = _PAGE_CACHE_WB;
+	enum page_cache_mode rettype = _PAGE_CACHE_MODE_WB;
 	struct memtype *entry;
 
 	if (x86_platform.is_untracked_pat_range(paddr, paddr + PAGE_SIZE))
@@ -414,7 +531,7 @@ static unsigned long lookup_memtype(u64 paddr)
 		 * default state and not reserved, and hence of type WB
 		 */
 		if (rettype == -1)
-			rettype = _PAGE_CACHE_WB;
+			rettype = _PAGE_CACHE_MODE_WB;
 
 		return rettype;
 	}
@@ -425,7 +542,7 @@ static unsigned long lookup_memtype(u64 paddr)
 	if (entry != NULL)
 		rettype = entry->type;
 	else
-		rettype = _PAGE_CACHE_UC_MINUS;
+		rettype = _PAGE_CACHE_MODE_UC_MINUS;
 
 	spin_unlock(&memtype_lock);
 	return rettype;
@@ -442,11 +559,11 @@ static unsigned long lookup_memtype(u64 paddr)
  * On failure, returns non-zero
  */
 int io_reserve_memtype(resource_size_t start, resource_size_t end,
-			unsigned long *type)
+			enum page_cache_mode *type)
 {
 	resource_size_t size = end - start;
-	unsigned long req_type = *type;
-	unsigned long new_type;
+	enum page_cache_mode req_type = *type;
+	enum page_cache_mode new_type;
 	int ret;
 
 	WARN_ON_ONCE(iomem_map_sanity_check(start, size));
@@ -520,13 +637,13 @@ static inline int range_is_allowed(unsigned long pfn, unsigned long size)
 int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
 				unsigned long size, pgprot_t *vma_prot)
 {
-	unsigned long flags = _PAGE_CACHE_WB;
+	enum page_cache_mode pcm = _PAGE_CACHE_MODE_WB;
 
 	if (!range_is_allowed(pfn, size))
 		return 0;
 
 	if (file->f_flags & O_DSYNC)
-		flags = _PAGE_CACHE_UC_MINUS;
+		pcm = _PAGE_CACHE_MODE_UC_MINUS;
 
 #ifdef CONFIG_X86_32
 	/*
@@ -543,12 +660,12 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
 	      boot_cpu_has(X86_FEATURE_CYRIX_ARR) ||
 	      boot_cpu_has(X86_FEATURE_CENTAUR_MCR)) &&
 	    (pfn << PAGE_SHIFT) >= __pa(high_memory)) {
-		flags = _PAGE_CACHE_UC;
+		pcm = _PAGE_CACHE_MODE_UC;
 	}
 #endif
 
 	*vma_prot = __pgprot((pgprot_val(*vma_prot) & ~_PAGE_CACHE_MASK) |
-			     flags);
+			     cachemode2protval(pcm));
 	return 1;
 }
 
@@ -556,7 +673,8 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
  * Change the memory type for the physial address range in kernel identity
  * mapping space if that range is a part of identity map.
  */
-int kernel_map_sync_memtype(u64 base, unsigned long size, unsigned long flags)
+int kernel_map_sync_memtype(u64 base, unsigned long size,
+			    enum page_cache_mode pcm)
 {
 	unsigned long id_sz;
 
@@ -574,11 +692,11 @@ int kernel_map_sync_memtype(u64 base, unsigned long size, unsigned long flags)
 				__pa(high_memory) - base :
 				size;
 
-	if (ioremap_change_attr((unsigned long)__va(base), id_sz, flags) < 0) {
+	if (ioremap_change_attr((unsigned long)__va(base), id_sz, pcm) < 0) {
 		printk(KERN_INFO "%s:%d ioremap_change_attr failed %s "
 			"for [mem %#010Lx-%#010Lx]\n",
 			current->comm, current->pid,
-			cattr_name(flags),
+			cattr_name(pcm),
 			base, (unsigned long long)(base + size-1));
 		return -EINVAL;
 	}
@@ -595,8 +713,8 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot,
 {
 	int is_ram = 0;
 	int ret;
-	unsigned long want_flags = (pgprot_val(*vma_prot) & _PAGE_CACHE_MASK);
-	unsigned long flags = want_flags;
+	enum page_cache_mode want_pcm = pgprot2cachemode(*vma_prot);
+	enum page_cache_mode pcm = want_pcm;
 
 	is_ram = pat_pagerange_is_ram(paddr, paddr + size);
 
@@ -609,36 +727,36 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot,
 		if (!pat_enabled)
 			return 0;
 
-		flags = lookup_memtype(paddr);
-		if (want_flags != flags) {
+		pcm = lookup_memtype(paddr);
+		if (want_pcm != pcm) {
 			printk(KERN_WARNING "%s:%d map pfn RAM range req %s for [mem %#010Lx-%#010Lx], got %s\n",
 				current->comm, current->pid,
-				cattr_name(want_flags),
+				cattr_name(want_pcm),
 				(unsigned long long)paddr,
 				(unsigned long long)(paddr + size - 1),
-				cattr_name(flags));
+				cattr_name(pcm));
 			*vma_prot = __pgprot((pgprot_val(*vma_prot) &
 					     (~_PAGE_CACHE_MASK)) |
-					     flags);
+					     cachemode2protval(pcm));
 		}
 		return 0;
 	}
 
-	ret = reserve_memtype(paddr, paddr + size, want_flags, &flags);
+	ret = reserve_memtype(paddr, paddr + size, want_pcm, &pcm);
 	if (ret)
 		return ret;
 
-	if (flags != want_flags) {
+	if (pcm != want_pcm) {
 		if (strict_prot ||
-		    !is_new_memtype_allowed(paddr, size, want_flags, flags)) {
+		    !is_new_memtype_allowed(paddr, size, want_pcm, pcm)) {
 			free_memtype(paddr, paddr + size);
 			printk(KERN_ERR "%s:%d map pfn expected mapping type %s"
 				" for [mem %#010Lx-%#010Lx], got %s\n",
 				current->comm, current->pid,
-				cattr_name(want_flags),
+				cattr_name(want_pcm),
 				(unsigned long long)paddr,
 				(unsigned long long)(paddr + size - 1),
-				cattr_name(flags));
+				cattr_name(pcm));
 			return -EINVAL;
 		}
 		/*
@@ -647,10 +765,10 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot,
 		 */
 		*vma_prot = __pgprot((pgprot_val(*vma_prot) &
 				      (~_PAGE_CACHE_MASK)) |
-				     flags);
+				     cachemode2protval(pcm));
 	}
 
-	if (kernel_map_sync_memtype(paddr, size, flags) < 0) {
+	if (kernel_map_sync_memtype(paddr, size, pcm) < 0) {
 		free_memtype(paddr, paddr + size);
 		return -EINVAL;
 	}
@@ -709,7 +827,7 @@ int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot,
 		    unsigned long pfn, unsigned long addr, unsigned long size)
 {
 	resource_size_t paddr = (resource_size_t)pfn << PAGE_SHIFT;
-	unsigned long flags;
+	enum page_cache_mode pcm;
 
 	/* reserve the whole chunk starting from paddr */
 	if (addr == vma->vm_start && size == (vma->vm_end - vma->vm_start)) {
@@ -728,18 +846,18 @@ int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot,
 	 * For anything smaller than the vma size we set prot based on the
 	 * lookup.
 	 */
-	flags = lookup_memtype(paddr);
+	pcm = lookup_memtype(paddr);
 
 	/* Check memtype for the remaining pages */
 	while (size > PAGE_SIZE) {
 		size -= PAGE_SIZE;
 		paddr += PAGE_SIZE;
-		if (flags != lookup_memtype(paddr))
+		if (pcm != lookup_memtype(paddr))
 			return -EINVAL;
 	}
 
 	*prot = __pgprot((pgprot_val(vma->vm_page_prot) & (~_PAGE_CACHE_MASK)) |
-			 flags);
+			 cachemode2protval(pcm));
 
 	return 0;
 }
@@ -747,15 +865,15 @@ int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot,
 int track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot,
 		     unsigned long pfn)
 {
-	unsigned long flags;
+	enum page_cache_mode pcm;
 
 	if (!pat_enabled)
 		return 0;
 
 	/* Set prot based on lookup */
-	flags = lookup_memtype((resource_size_t)pfn << PAGE_SHIFT);
+	pcm = lookup_memtype((resource_size_t)pfn << PAGE_SHIFT);
 	*prot = __pgprot((pgprot_val(vma->vm_page_prot) & (~_PAGE_CACHE_MASK)) |
-			 flags);
+			 cachemode2protval(pcm));
 
 	return 0;
 }
@@ -791,7 +909,8 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
 pgprot_t pgprot_writecombine(pgprot_t prot)
 {
 	if (pat_enabled)
-		return __pgprot(pgprot_val(prot) | _PAGE_CACHE_WC);
+		return __pgprot(pgprot_val(prot) |
+				cachemode2protval(_PAGE_CACHE_MODE_WC));
 	else
 		return pgprot_noncached(prot);
 }

arch/x86/mm/pat_internal.h

@@ -10,30 +10,32 @@ struct memtype {
 	u64			start;
 	u64			end;
 	u64			subtree_max_end;
-	unsigned long		type;
+	enum page_cache_mode	type;
 	struct rb_node		rb;
 };
 
-static inline char *cattr_name(unsigned long flags)
+static inline char *cattr_name(enum page_cache_mode pcm)
 {
-	switch (flags & _PAGE_CACHE_MASK) {
-	case _PAGE_CACHE_UC:		return "uncached";
-	case _PAGE_CACHE_UC_MINUS:	return "uncached-minus";
-	case _PAGE_CACHE_WB:		return "write-back";
-	case _PAGE_CACHE_WC:		return "write-combining";
+	switch (pcm) {
+	case _PAGE_CACHE_MODE_UC:		return "uncached";
+	case _PAGE_CACHE_MODE_UC_MINUS:		return "uncached-minus";
+	case _PAGE_CACHE_MODE_WB:		return "write-back";
+	case _PAGE_CACHE_MODE_WC:		return "write-combining";
+	case _PAGE_CACHE_MODE_WT:		return "write-through";
+	case _PAGE_CACHE_MODE_WP:		return "write-protected";
 	default:				return "broken";
 	}
 }
 
 #ifdef CONFIG_X86_PAT
 extern int rbt_memtype_check_insert(struct memtype *new,
-					unsigned long *new_type);
+					enum page_cache_mode *new_type);
 extern struct memtype *rbt_memtype_erase(u64 start, u64 end);
 extern struct memtype *rbt_memtype_lookup(u64 addr);
 extern int rbt_memtype_copy_nth_element(struct memtype *out, loff_t pos);
 #else
 static inline int rbt_memtype_check_insert(struct memtype *new,
-					unsigned long *new_type)
+					enum page_cache_mode *new_type)
 { return 0; }
 static inline struct memtype *rbt_memtype_erase(u64 start, u64 end)
 { return NULL; }

arch/x86/mm/pat_rbtree.c

@@ -122,11 +122,12 @@ static struct memtype *memtype_rb_exact_match(struct rb_root *root,
 
 static int memtype_rb_check_conflict(struct rb_root *root,
 				u64 start, u64 end,
-				unsigned long reqtype, unsigned long *newtype)
+				enum page_cache_mode reqtype,
+				enum page_cache_mode *newtype)
 {
 	struct rb_node *node;
 	struct memtype *match;
-	int found_type = reqtype;
+	enum page_cache_mode found_type = reqtype;
 
 	match = memtype_rb_lowest_match(&memtype_rbroot, start, end);
 	if (match == NULL)
@@ -187,7 +188,8 @@ static void memtype_rb_insert(struct rb_root *root, struct memtype *newdata)
 	rb_insert_augmented(&newdata->rb, root, &memtype_rb_augment_cb);
 }
 
-int rbt_memtype_check_insert(struct memtype *new, unsigned long *ret_type)
+int rbt_memtype_check_insert(struct memtype *new,
+			     enum page_cache_mode *ret_type)
 {
 	int err = 0;
 

arch/x86/pci/i386.c

@@ -433,14 +433,14 @@ int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
 		return -EINVAL;
 
 	if (pat_enabled && write_combine)
-		prot |= _PAGE_CACHE_WC;
+		prot |= cachemode2protval(_PAGE_CACHE_MODE_WC);
 	else if (pat_enabled || boot_cpu_data.x86 > 3)
 		/*
 		 * ioremap() and ioremap_nocache() defaults to UC MINUS for now.
 		 * To avoid attribute conflicts, request UC MINUS here
 		 * as well.
 		 */
-		prot |= _PAGE_CACHE_UC_MINUS;
+		prot |= cachemode2protval(_PAGE_CACHE_MODE_UC_MINUS);
 
 	vma->vm_page_prot = __pgprot(prot);
 

arch/x86/xen/enlighten.c

@@ -1100,12 +1100,6 @@ static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high)
 		/* Fast syscall setup is all done in hypercalls, so
 		   these are all ignored.  Stub them out here to stop
 		   Xen console noise. */
-		break;
-
-	case MSR_IA32_CR_PAT:
-		if (smp_processor_id() == 0)
-			xen_set_pat(((u64)high << 32) | low);
-		break;
 
 	default:
 		ret = native_write_msr_safe(msr, low, high);
@@ -1561,10 +1555,6 @@ asmlinkage __visible void __init xen_start_kernel(void)
 
 	/* Prevent unwanted bits from being set in PTEs. */
 	__supported_pte_mask &= ~_PAGE_GLOBAL;
-#if 0
-	if (!xen_initial_domain())
-#endif
-		__supported_pte_mask &= ~(_PAGE_PWT | _PAGE_PCD);
 
 	/*
 	 * Prevent page tables from being allocated in highmem, even
@@ -1617,14 +1607,6 @@ asmlinkage __visible void __init xen_start_kernel(void)
 	 * be meaningless.  Prevent it from trying.
 	 */
 	acpi_numa = -1;
-#endif
-#ifdef CONFIG_X86_PAT
-	/*
-	 * For right now disable the PAT. We should remove this once
-	 * git commit 8eaffa67b43e99ae581622c5133e20b0f48bcef1
-	 * (xen/pat: Disable PAT support for now) is reverted.
-	 */
-	pat_enabled = 0;
 #endif
 	/* Don't do the full vcpu_info placement stuff until we have a
 	   possible map and a non-dummy shared_info. */
@@ -1636,6 +1618,13 @@ asmlinkage __visible void __init xen_start_kernel(void)
 	xen_raw_console_write("mapping kernel into physical memory\n");
 	xen_setup_kernel_pagetable((pgd_t *)xen_start_info->pt_base, xen_start_info->nr_pages);
 
+	/*
+	 * Modify the cache mode translation tables to match Xen's PAT
+	 * configuration.
+	 */
+
+	pat_init_cache_modes();
+
 	/* keep using Xen gdt for now; no urgent need to change it */
 
 #ifdef CONFIG_X86_32

arch/x86/xen/mmu.c

@@ -410,13 +410,7 @@ static pteval_t pte_pfn_to_mfn(pteval_t val)
 __visible pteval_t xen_pte_val(pte_t pte)
 {
 	pteval_t pteval = pte.pte;
-#if 0
-	/* If this is a WC pte, convert back from Xen WC to Linux WC */
-	if ((pteval & (_PAGE_PAT | _PAGE_PCD | _PAGE_PWT)) == _PAGE_PAT) {
-		WARN_ON(!pat_enabled);
-		pteval = (pteval & ~_PAGE_PAT) | _PAGE_PWT;
-	}
-#endif
+
 	return pte_mfn_to_pfn(pteval);
 }
 PV_CALLEE_SAVE_REGS_THUNK(xen_pte_val);
@@ -427,47 +421,8 @@ __visible pgdval_t xen_pgd_val(pgd_t pgd)
 }
 PV_CALLEE_SAVE_REGS_THUNK(xen_pgd_val);
 
-/*
- * Xen's PAT setup is part of its ABI, though I assume entries 6 & 7
- * are reserved for now, to correspond to the Intel-reserved PAT
- * types.
- *
- * We expect Linux's PAT set as follows:
- *
- * Idx  PTE flags        Linux    Xen    Default
- * 0                     WB       WB     WB
- * 1            PWT      WC       WT     WT
- * 2        PCD          UC-      UC-    UC-
- * 3        PCD PWT      UC       UC     UC
- * 4    PAT              WB       WC     WB
- * 5    PAT     PWT      WC       WP     WT
- * 6    PAT PCD          UC-      rsv    UC-
- * 7    PAT PCD PWT      UC       rsv    UC
- */
-
-void xen_set_pat(u64 pat)
-{
-	/* We expect Linux to use a PAT setting of
-	 * UC UC- WC WB (ignoring the PAT flag) */
-	WARN_ON(pat != 0x0007010600070106ull);
-}
-
 __visible pte_t xen_make_pte(pteval_t pte)
 {
-#if 0
-	/* If Linux is trying to set a WC pte, then map to the Xen WC.
-	 * If _PAGE_PAT is set, then it probably means it is really
-	 * _PAGE_PSE, so avoid fiddling with the PAT mapping and hope
-	 * things work out OK...
-	 *
-	 * (We should never see kernel mappings with _PAGE_PSE set,
-	 * but we could see hugetlbfs mappings, I think.).
-	 */
-	if (pat_enabled && !WARN_ON(pte & _PAGE_PAT)) {
-		if ((pte & (_PAGE_PCD | _PAGE_PWT)) == _PAGE_PWT)
-			pte = (pte & ~(_PAGE_PCD | _PAGE_PWT)) | _PAGE_PAT;
-	}
-#endif
 	pte = pte_pfn_to_mfn(pte);
 
 	return native_make_pte(pte);

arch/x86/xen/xen-ops.h

@@ -33,7 +33,6 @@ extern unsigned long xen_max_p2m_pfn;
 
 void xen_mm_pin_all(void);
 void xen_mm_unpin_all(void);
-void xen_set_pat(u64);
 
 char * __init xen_memory_setup(void);
 char * xen_auto_xlated_memory_setup(void);

drivers/video/fbdev/gbefb.c

@@ -54,7 +54,8 @@ struct gbefb_par {
 #endif
 #endif
 #ifdef CONFIG_X86
-#define pgprot_fb(_prot) ((_prot) | _PAGE_PCD)
+#define pgprot_fb(_prot) (((_prot) & ~_PAGE_CACHE_MASK) |	\
+			  cachemode2protval(_PAGE_CACHE_MODE_UC_MINUS))
 #endif
 
 /*

drivers/video/fbdev/vermilion/vermilion.c

@@ -1003,13 +1003,15 @@ static int vmlfb_mmap(struct fb_info *info, struct vm_area_struct *vma)
 	struct vml_info *vinfo = container_of(info, struct vml_info, info);
 	unsigned long offset = vma->vm_pgoff << PAGE_SHIFT;
 	int ret;
+	unsigned long prot;
 
 	ret = vmlfb_vram_offset(vinfo, offset);
 	if (ret)
 		return -EINVAL;
 
-	pgprot_val(vma->vm_page_prot) |= _PAGE_PCD;
-	pgprot_val(vma->vm_page_prot) &= ~_PAGE_PWT;
+	prot = pgprot_val(vma->vm_page_prot) & ~_PAGE_CACHE_MASK;
+	pgprot_val(vma->vm_page_prot) =
+		prot | cachemode2protval(_PAGE_CACHE_MODE_UC_MINUS);
 
 	return vm_iomap_memory(vma, vinfo->vram_start,
 			vinfo->vram_contig_size);