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
  ...

25 files changed, 474 insertions, 343 deletions

diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h
index 9863ee3747da..47c8e32f621a 100644
--- a/arch/x86/include/asm/cacheflush.h
+++ b/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:
diff --git a/arch/x86/include/asm/fb.h b/arch/x86/include/asm/fb.h
index 2519d0679d99..c3dd5e71f439 100644
--- a/arch/x86/include/asm/fb.h
+++ b/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);
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index ffb1733ac91f..bf728e49c53c 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/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;
 
diff --git a/arch/x86/include/asm/highmem.h b/arch/x86/include/asm/highmem.h
index 302a323b3f67..04e9d023168f 100644
--- a/arch/x86/include/asm/highmem.h
+++ b/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
- * VMALLOC_START
- * high_memory
+ * 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)
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index 0cdbe6e81b45..34a5b93704d3 100644
--- a/arch/x86/include/asm/io.h
+++ b/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);
diff --git a/arch/x86/include/asm/pat.h b/arch/x86/include/asm/pat.h
index e2c1668dde7a..91bc4ba95f91 100644
--- a/arch/x86/include/asm/pat.h
+++ b/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);
 
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index aa97a070f09f..c112ea63f40d 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -9,9 +9,10 @@
 /*
  * Macro to mark a page protection value as UC-
  */
-#define pgprot_noncached(prot)					\
-	((boot_cpu_data.x86 > 3)				\
-	 ? (__pgprot(pgprot_val(prot) | _PAGE_CACHE_UC_MINUS))	\
+#define pgprot_noncached(prot)						\
+	((boot_cpu_data.x86 > 3)					\
+	 ? (__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;
 	}
 
diff --git a/arch/x86/include/asm/pgtable_32_types.h b/arch/x86/include/asm/pgtable_32_types.h
index ed5903be26fe..9fb2f2bc8245 100644
--- a/arch/x86/include/asm/pgtable_32_types.h
+++ b/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
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 07789647bf33..af447f95e3be 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/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;
 
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index 1a8053d1012e..f0cedf3395af 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -129,7 +129,7 @@ static void printk_prot(struct seq_file *m, pgprot_t prot, int level, bool dmsg)
 
 	if (!pgprot_val(prot)) {
 		/* Not present */
-		pt_dump_cont_printf(m, dmsg, "                          ");
+		pt_dump_cont_printf(m, dmsg, "                              ");
 	} else {
 		if (pr & _PAGE_USER)
 			pt_dump_cont_printf(m, dmsg, "USR ");
@@ -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)
-				pt_dump_cont_printf(m, dmsg, "PSE ");
-			else
-				pt_dump_cont_printf(m, dmsg, "    ");
-		} else {
-			if (pr & _PAGE_PAT)
-				pt_dump_cont_printf(m, dmsg, "pat ");
-			else
-				pt_dump_cont_printf(m, dmsg, "    ");
-		}
+		/* 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, "    ");
+		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
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 66dba36f2343..82b41d56bb98 100644
--- a/arch/x86/mm/init.c
+++ b/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;
+}
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 4e5dfec750fc..78e53c80fc12 100644
--- a/arch/x86/mm/init_64.c
+++ b/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))
diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c
index 7b179b499fa3..9ca35fc60cfe 100644
--- a/arch/x86/mm/iomap_32.c
+++ b/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);
 }
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index b12f43c192cf..fdf617c00e2f 100644
--- a/arch/x86/mm/ioremap.c
+++ b/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)),