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

Pull x86 mm changes from Ingo Molnar:
 "The main changes are: continued PAT work by Toshi Kani, plus a new
  boot time warning about insecure RWX kernel mappings, by Stephen
  Smalley.

  The new CONFIG_DEBUG_WX=y warning is marked default-y if
  CONFIG_DEBUG_RODATA=y is already eanbled, as a special exception, as
  these bugs are hard to notice and this check already found several
  live bugs"

* 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/mm: Warn on W^X mappings
  x86/mm: Fix no-change case in try_preserve_large_page()
  x86/mm: Fix __split_large_page() to handle large PAT bit
  x86/mm: Fix try_preserve_large_page() to handle large PAT bit
  x86/mm: Fix gup_huge_p?d() to handle large PAT bit
  x86/mm: Fix slow_virt_to_phys() to handle large PAT bit
  x86/mm: Fix page table dump to show PAT bit
  x86/asm: Add pud_pgprot() and pmd_pgprot()
  x86/asm: Fix pud/pmd interfaces to handle large PAT bit
  x86/asm: Add pud/pmd mask interfaces to handle large PAT bit
  x86/asm: Move PUD_PAGE macros to page_types.h
  x86/vdso32: Define PGTABLE_LEVELS to 32bit VDSO

Author: torvalds

arch/x86/Kconfig.debug

@@ -65,10 +65,14 @@ config EARLY_PRINTK_EFI
 	  This is useful for kernel debugging when your machine crashes very
 	  early before the console code is initialized.
 
+config X86_PTDUMP_CORE
+	def_bool n
+
 config X86_PTDUMP
 	bool "Export kernel pagetable layout to userspace via debugfs"
 	depends on DEBUG_KERNEL
 	select DEBUG_FS
+	select X86_PTDUMP_CORE
 	---help---
 	  Say Y here if you want to show the kernel pagetable layout in a
 	  debugfs file. This information is only useful for kernel developers
@@ -79,7 +83,8 @@ config X86_PTDUMP
 
 config EFI_PGT_DUMP
 	bool "Dump the EFI pagetable"
-	depends on EFI && X86_PTDUMP
+	depends on EFI
+	select X86_PTDUMP_CORE
 	---help---
 	  Enable this if you want to dump the EFI page table before
 	  enabling virtual mode. This can be used to debug miscellaneous
@@ -105,6 +110,35 @@ config DEBUG_RODATA_TEST
 	  feature as well as for the change_page_attr() infrastructure.
 	  If in doubt, say "N"
 
+config DEBUG_WX
+	bool "Warn on W+X mappings at boot"
+	depends on DEBUG_RODATA
+	default y
+	select X86_PTDUMP_CORE
+	---help---
+	  Generate a warning if any W+X mappings are found at boot.
+
+	  This is useful for discovering cases where the kernel is leaving
+	  W+X mappings after applying NX, as such mappings are a security risk.
+
+	  Look for a message in dmesg output like this:
+
+	    x86/mm: Checked W+X mappings: passed, no W+X pages found.
+
+	  or like this, if the check failed:
+
+	    x86/mm: Checked W+X mappings: FAILED, <N> W+X pages found.
+
+	  Note that even if the check fails, your kernel is possibly
+	  still fine, as W+X mappings are not a security hole in
+	  themselves, what they do is that they make the exploitation
+	  of other unfixed kernel bugs easier.
+
+	  There is no runtime or memory usage effect of this option
+	  once the kernel has booted up - it's a one time check.
+
+	  If in doubt, say "Y".
+
 config DEBUG_SET_MODULE_RONX
 	bool "Set loadable kernel module data as NX and text as RO"
 	depends on MODULES

arch/x86/entry/vdso/vdso32/vclock_gettime.c

@@ -14,11 +14,13 @@
  */
 #undef CONFIG_64BIT
 #undef CONFIG_X86_64
+#undef CONFIG_PGTABLE_LEVELS
 #undef CONFIG_ILLEGAL_POINTER_VALUE
 #undef CONFIG_SPARSEMEM_VMEMMAP
 #undef CONFIG_NR_CPUS
 
 #define CONFIG_X86_32 1
+#define CONFIG_PGTABLE_LEVELS 2
 #define CONFIG_PAGE_OFFSET 0
 #define CONFIG_ILLEGAL_POINTER_VALUE 0
 #define CONFIG_NR_CPUS 1

arch/x86/include/asm/page_64_types.h

@@ -26,9 +26,6 @@
 #define MCE_STACK 4
 #define N_EXCEPTION_STACKS 4  /* hw limit: 7 */
 
-#define PUD_PAGE_SIZE		(_AC(1, UL) << PUD_SHIFT)
-#define PUD_PAGE_MASK		(~(PUD_PAGE_SIZE-1))
-
 /*
  * Set __PAGE_OFFSET to the most negative possible address +
  * PGDIR_SIZE*16 (pgd slot 272).  The gap is to allow a space for a

arch/x86/include/asm/page_types.h

@@ -20,6 +20,9 @@
 #define PMD_PAGE_SIZE		(_AC(1, UL) << PMD_SHIFT)
 #define PMD_PAGE_MASK		(~(PMD_PAGE_SIZE-1))
 
+#define PUD_PAGE_SIZE		(_AC(1, UL) << PUD_SHIFT)
+#define PUD_PAGE_MASK		(~(PUD_PAGE_SIZE-1))
+
 #define HPAGE_SHIFT		PMD_SHIFT
 #define HPAGE_SIZE		(_AC(1,UL) << HPAGE_SHIFT)
 #define HPAGE_MASK		(~(HPAGE_SIZE - 1))

arch/x86/include/asm/pgtable.h

@@ -19,6 +19,13 @@
 #include <asm/x86_init.h>
 
 void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd);
+void ptdump_walk_pgd_level_checkwx(void);
+
+#ifdef CONFIG_DEBUG_WX
+#define debug_checkwx() ptdump_walk_pgd_level_checkwx()
+#else
+#define debug_checkwx() do { } while (0)
+#endif
 
 /*
  * ZERO_PAGE is a global shared page that is always zero: used
@@ -142,12 +149,12 @@ static inline unsigned long pte_pfn(pte_t pte)
 
 static inline unsigned long pmd_pfn(pmd_t pmd)
 {
-	return (pmd_val(pmd) & PTE_PFN_MASK) >> PAGE_SHIFT;
+	return (pmd_val(pmd) & pmd_pfn_mask(pmd)) >> PAGE_SHIFT;
 }
 
 static inline unsigned long pud_pfn(pud_t pud)
 {
-	return (pud_val(pud) & PTE_PFN_MASK) >> PAGE_SHIFT;
+	return (pud_val(pud) & pud_pfn_mask(pud)) >> PAGE_SHIFT;
 }
 
 #define pte_page(pte)	pfn_to_page(pte_pfn(pte))
@@ -379,7 +386,9 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
 	return __pgprot(preservebits | addbits);
 }
 
-#define pte_pgprot(x) __pgprot(pte_flags(x) & PTE_FLAGS_MASK)
+#define pte_pgprot(x) __pgprot(pte_flags(x))
+#define pmd_pgprot(x) __pgprot(pmd_flags(x))
+#define pud_pgprot(x) __pgprot(pud_flags(x))
 
 #define canon_pgprot(p) __pgprot(massage_pgprot(p))
 
@@ -502,14 +511,15 @@ static inline int pmd_none(pmd_t pmd)
 
 static inline unsigned long pmd_page_vaddr(pmd_t pmd)
 {
-	return (unsigned long)__va(pmd_val(pmd) & PTE_PFN_MASK);
+	return (unsigned long)__va(pmd_val(pmd) & pmd_pfn_mask(pmd));
 }
 
 /*
  * Currently stuck as a macro due to indirect forward reference to
  * linux/mmzone.h's __section_mem_map_addr() definition:
  */
-#define pmd_page(pmd)	pfn_to_page((pmd_val(pmd) & PTE_PFN_MASK) >> PAGE_SHIFT)
+#define pmd_page(pmd)		\
+	pfn_to_page((pmd_val(pmd) & pmd_pfn_mask(pmd)) >> PAGE_SHIFT)
 
 /*
  * the pmd page can be thought of an array like this: pmd_t[PTRS_PER_PMD]
@@ -570,14 +580,15 @@ static inline int pud_present(pud_t pud)
 
 static inline unsigned long pud_page_vaddr(pud_t pud)
 {
-	return (unsigned long)__va((unsigned long)pud_val(pud) & PTE_PFN_MASK);
+	return (unsigned long)__va(pud_val(pud) & pud_pfn_mask(pud));
 }
 
 /*
  * Currently stuck as a macro due to indirect forward reference to
  * linux/mmzone.h's __section_mem_map_addr() definition:
  */
-#define pud_page(pud)		pfn_to_page(pud_val(pud) >> PAGE_SHIFT)
+#define pud_page(pud)		\
+	pfn_to_page((pud_val(pud) & pud_pfn_mask(pud)) >> PAGE_SHIFT)
 
 /* Find an entry in the second-level page table.. */
 static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address)

arch/x86/include/asm/pgtable_types.h

@@ -209,10 +209,10 @@ enum page_cache_mode {
 
 #include <linux/types.h>
 
-/* PTE_PFN_MASK extracts the PFN from a (pte|pmd|pud|pgd)val_t */
+/* Extracts the PFN from a (pte|pmd|pud|pgd)val_t of a 4KB page */
 #define PTE_PFN_MASK		((pteval_t)PHYSICAL_PAGE_MASK)
 
-/* PTE_FLAGS_MASK extracts the flags from a (pte|pmd|pud|pgd)val_t */
+/* Extracts the flags from a (pte|pmd|pud|pgd)val_t of a 4KB page */
 #define PTE_FLAGS_MASK		(~PTE_PFN_MASK)
 
 typedef struct pgprot { pgprotval_t pgprot; } pgprot_t;
@@ -276,14 +276,46 @@ static inline pmdval_t native_pmd_val(pmd_t pmd)
 }
 #endif
 
+static inline pudval_t pud_pfn_mask(pud_t pud)
+{
+	if (native_pud_val(pud) & _PAGE_PSE)
+		return PUD_PAGE_MASK & PHYSICAL_PAGE_MASK;
+	else
+		return PTE_PFN_MASK;
+}
+
+static inline pudval_t pud_flags_mask(pud_t pud)
+{
+	if (native_pud_val(pud) & _PAGE_PSE)
+		return ~(PUD_PAGE_MASK & (pudval_t)PHYSICAL_PAGE_MASK);
+	else
+		return ~PTE_PFN_MASK;
+}
+
 static inline pudval_t pud_flags(pud_t pud)
 {
-	return native_pud_val(pud) & PTE_FLAGS_MASK;
+	return native_pud_val(pud) & pud_flags_mask(pud);
+}
+
+static inline pmdval_t pmd_pfn_mask(pmd_t pmd)
+{
+	if (native_pmd_val(pmd) & _PAGE_PSE)
+		return PMD_PAGE_MASK & PHYSICAL_PAGE_MASK;
+	else
+		return PTE_PFN_MASK;
+}
+
+static inline pmdval_t pmd_flags_mask(pmd_t pmd)
+{
+	if (native_pmd_val(pmd) & _PAGE_PSE)
+		return ~(PMD_PAGE_MASK & (pmdval_t)PHYSICAL_PAGE_MASK);
+	else
+		return ~PTE_PFN_MASK;
 }
 
 static inline pmdval_t pmd_flags(pmd_t pmd)
 {
-	return native_pmd_val(pmd) & PTE_FLAGS_MASK;
+	return native_pmd_val(pmd) & pmd_flags_mask(pmd);
 }
 
 static inline pte_t native_make_pte(pteval_t val)

arch/x86/mm/Makefile

@@ -14,7 +14,7 @@ obj-$(CONFIG_SMP)		+= tlb.o
 obj-$(CONFIG_X86_32)		+= pgtable_32.o iomap_32.o
 
 obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
-obj-$(CONFIG_X86_PTDUMP)	+= dump_pagetables.o
+obj-$(CONFIG_X86_PTDUMP_CORE)	+= dump_pagetables.o
 
 obj-$(CONFIG_HIGHMEM)		+= highmem_32.o