#include <linux/list.h>
#include <linux/spinlock.h>
+struct mm_struct;
+struct vm_area_struct;
+
/*
* ZERO_PAGE is a global shared page that is always zero: used
* for zero-mapped memory areas etc..
void pgtable_cache_init(void);
void paging_init(void);
-#endif /* !__ASSEMBLY__ */
-
/*
* The Linux x86 paging architecture is 'compile-time dual-mode', it
* implements both the traditional 2-level x86 page tables and the
* newer 3-level PAE-mode page tables.
*/
-#ifndef __ASSEMBLY__
#ifdef CONFIG_X86_PAE
-# include <asm/pgtable-3level.h>
+# include <asm/pgtable-3level-defs.h>
+# define PMD_SIZE (1UL << PMD_SHIFT)
+# define PMD_MASK (~(PMD_SIZE-1))
#else
-# include <asm/pgtable-2level.h>
-#endif
+# include <asm/pgtable-2level-defs.h>
#endif
-#define PMD_SIZE (1UL << PMD_SHIFT)
-#define PMD_MASK (~(PMD_SIZE-1))
#define PGDIR_SIZE (1UL << PGDIR_SHIFT)
#define PGDIR_MASK (~(PGDIR_SIZE-1))
#define USER_PTRS_PER_PGD (TASK_SIZE/PGDIR_SIZE)
-#define FIRST_USER_PGD_NR 0
+#define FIRST_USER_ADDRESS 0
#define USER_PGD_PTRS (PAGE_OFFSET >> PGDIR_SHIFT)
#define KERNEL_PGD_PTRS (PTRS_PER_PGD-USER_PGD_PTRS)
#define BOOT_USER_PGD_PTRS (__PAGE_OFFSET >> TWOLEVEL_PGDIR_SHIFT)
#define BOOT_KERNEL_PGD_PTRS (1024-BOOT_USER_PGD_PTRS)
-
-#ifndef __ASSEMBLY__
/* Just any arbitrary offset to the start of the vmalloc VM area: the
* current 8MB value just means that there will be a 8MB "hole" after the
* physical memory until the kernel virtual memory starts. That means that
* area for the same reason. ;)
*/
#define VMALLOC_OFFSET (8*1024*1024)
-#define VMALLOC_START (((unsigned long) high_memory + 2*VMALLOC_OFFSET-1) & \
- ~(VMALLOC_OFFSET-1))
+#define VMALLOC_START (((unsigned long) high_memory + vmalloc_earlyreserve + \
+ 2*VMALLOC_OFFSET-1) & ~(VMALLOC_OFFSET-1))
#ifdef CONFIG_HIGHMEM
# define VMALLOC_END (PKMAP_BASE-2*PAGE_SIZE)
#else
#endif
/*
- * The 4MB page is guessing.. Detailed in the infamous "Chapter H"
- * of the Pentium details, but assuming intel did the straightforward
- * thing, this bit set in the page directory entry just means that
+ * _PAGE_PSE set in the page directory entry just means that
* the page directory entry points directly to a 4MB-aligned block of
* memory.
*/
#define _PAGE_BIT_UNUSED1 9 /* available for programmer */
#define _PAGE_BIT_UNUSED2 10
#define _PAGE_BIT_UNUSED3 11
+#define _PAGE_BIT_NX 63
#define _PAGE_PRESENT 0x001
#define _PAGE_RW 0x002
#define _PAGE_UNUSED2 0x400
#define _PAGE_UNUSED3 0x800
-#define _PAGE_FILE 0x040 /* set:pagecache unset:swap */
-#define _PAGE_PROTNONE 0x080 /* If not present */
+/* If _PAGE_PRESENT is clear, we use these: */
+#define _PAGE_FILE 0x040 /* nonlinear file mapping, saved PTE; unset:swap */
+#define _PAGE_PROTNONE 0x080 /* if the user mapped it with PROT_NONE;
+ pte_present gives true */
+#ifdef CONFIG_X86_PAE
+#define _PAGE_NX (1ULL<<_PAGE_BIT_NX)
+#else
+#define _PAGE_NX 0
+#endif
#define _PAGE_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED | _PAGE_DIRTY)
#define _KERNPG_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | _PAGE_DIRTY)
#define _PAGE_CHG_MASK (PTE_MASK | _PAGE_ACCESSED | _PAGE_DIRTY)
-#define PAGE_NONE __pgprot(_PAGE_PROTNONE | _PAGE_ACCESSED)
-#define PAGE_SHARED __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED)
-#define PAGE_COPY __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED)
-#define PAGE_READONLY __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED)
+#define PAGE_NONE \
+ __pgprot(_PAGE_PROTNONE | _PAGE_ACCESSED)
+#define PAGE_SHARED \
+ __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED)
+
+#define PAGE_SHARED_EXEC \
+ __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED)
+#define PAGE_COPY_NOEXEC \
+ __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED | _PAGE_NX)
+#define PAGE_COPY_EXEC \
+ __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED)
+#define PAGE_COPY \
+ PAGE_COPY_NOEXEC
+#define PAGE_READONLY \
+ __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED | _PAGE_NX)
+#define PAGE_READONLY_EXEC \
+ __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED)
#define _PAGE_KERNEL \
+ (_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_NX)
+#define _PAGE_KERNEL_EXEC \
(_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED)
-extern unsigned long __PAGE_KERNEL;
-#define __PAGE_KERNEL_RO (__PAGE_KERNEL & ~_PAGE_RW)
-#define __PAGE_KERNEL_NOCACHE (__PAGE_KERNEL | _PAGE_PCD)
-#define __PAGE_KERNEL_LARGE (__PAGE_KERNEL | _PAGE_PSE)
+extern unsigned long long __PAGE_KERNEL, __PAGE_KERNEL_EXEC;
+#define __PAGE_KERNEL_RO (__PAGE_KERNEL & ~_PAGE_RW)
+#define __PAGE_KERNEL_NOCACHE (__PAGE_KERNEL | _PAGE_PCD)
+#define __PAGE_KERNEL_LARGE (__PAGE_KERNEL | _PAGE_PSE)
+#define __PAGE_KERNEL_LARGE_EXEC (__PAGE_KERNEL_EXEC | _PAGE_PSE)
#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_NOCACHE __pgprot(__PAGE_KERNEL_NOCACHE)
#define PAGE_KERNEL_LARGE __pgprot(__PAGE_KERNEL_LARGE)
+#define PAGE_KERNEL_LARGE_EXEC __pgprot(__PAGE_KERNEL_LARGE_EXEC)
/*
* The i386 can't do page protection for execute, and considers that
#define __P001 PAGE_READONLY
#define __P010 PAGE_COPY
#define __P011 PAGE_COPY
-#define __P100 PAGE_READONLY
-#define __P101 PAGE_READONLY
-#define __P110 PAGE_COPY
-#define __P111 PAGE_COPY
+#define __P100 PAGE_READONLY_EXEC
+#define __P101 PAGE_READONLY_EXEC
+#define __P110 PAGE_COPY_EXEC
+#define __P111 PAGE_COPY_EXEC
#define __S000 PAGE_NONE
#define __S001 PAGE_READONLY
#define __S010 PAGE_SHARED
#define __S011 PAGE_SHARED
-#define __S100 PAGE_READONLY
-#define __S101 PAGE_READONLY
-#define __S110 PAGE_SHARED
-#define __S111 PAGE_SHARED
+#define __S100 PAGE_READONLY_EXEC
+#define __S101 PAGE_READONLY_EXEC
+#define __S110 PAGE_SHARED_EXEC
+#define __S111 PAGE_SHARED_EXEC
/*
* Define this if things work differently on an i386 and an i486:
* it will (on an i486) warn about kernel memory accesses that are
- * done without a 'verify_area(VERIFY_WRITE,..)'
+ * done without a 'access_ok(VERIFY_WRITE,..)'
*/
-#undef TEST_VERIFY_AREA
+#undef TEST_ACCESS_OK
/* The boot page tables (all created as a single array) */
extern unsigned long pg0[];
#define pte_present(x) ((x).pte_low & (_PAGE_PRESENT | _PAGE_PROTNONE))
-#define pte_clear(xp) do { set_pte(xp, __pte(0)); } while (0)
-#define pmd_none(x) (!pmd_val(x))
+/* To avoid harmful races, pmd_none(x) should check only the lower when PAE */
+#define pmd_none(x) (!(unsigned long)pmd_val(x))
#define pmd_present(x) (pmd_val(x) & _PAGE_PRESENT)
-#define pmd_clear(xp) do { set_pmd(xp, __pmd(0)); } while (0)
#define pmd_bad(x) ((pmd_val(x) & (~PAGE_MASK & ~_PAGE_USER)) != _KERNPG_TABLE)
*/
static inline int pte_user(pte_t pte) { return (pte).pte_low & _PAGE_USER; }
static inline int pte_read(pte_t pte) { return (pte).pte_low & _PAGE_USER; }
-static inline int pte_exec(pte_t pte) { return (pte).pte_low & _PAGE_USER; }
static inline int pte_dirty(pte_t pte) { return (pte).pte_low & _PAGE_DIRTY; }
static inline int pte_young(pte_t pte) { return (pte).pte_low & _PAGE_ACCESSED; }
static inline int pte_write(pte_t pte) { return (pte).pte_low & _PAGE_RW; }
+static inline int pte_huge(pte_t pte) { return (pte).pte_low & _PAGE_PSE; }
/*
* The following only works if pte_present() is not true.
static inline pte_t pte_mkdirty(pte_t pte) { (pte).pte_low |= _PAGE_DIRTY; return pte; }
static inline pte_t pte_mkyoung(pte_t pte) { (pte).pte_low |= _PAGE_ACCESSED; return pte; }
static inline pte_t pte_mkwrite(pte_t pte) { (pte).pte_low |= _PAGE_RW; return pte; }
+static inline pte_t pte_mkhuge(pte_t pte) { (pte).pte_low |= _PAGE_PSE; return pte; }
+
+#ifdef CONFIG_X86_PAE
+# include <asm/pgtable-3level.h>
+#else
+# include <asm/pgtable-2level.h>
+#endif
-static inline int ptep_test_and_clear_dirty(pte_t *ptep) { return test_and_clear_bit(_PAGE_BIT_DIRTY, &ptep->pte_low); }
-static inline int ptep_test_and_clear_young(pte_t *ptep) { return test_and_clear_bit(_PAGE_BIT_ACCESSED, &ptep->pte_low); }
-static inline void ptep_set_wrprotect(pte_t *ptep) { clear_bit(_PAGE_BIT_RW, &ptep->pte_low); }
-static inline void ptep_mkdirty(pte_t *ptep) { set_bit(_PAGE_BIT_DIRTY, &ptep->pte_low); }
+static inline int ptep_test_and_clear_dirty(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep)
+{
+ if (!pte_dirty(*ptep))
+ return 0;
+ return test_and_clear_bit(_PAGE_BIT_DIRTY, &ptep->pte_low);
+}
+
+static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep)
+{
+ if (!pte_young(*ptep))
+ return 0;
+ return test_and_clear_bit(_PAGE_BIT_ACCESSED, &ptep->pte_low);
+}
+
+static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm, unsigned long addr, pte_t *ptep, int full)
+{
+ pte_t pte;
+ if (full) {
+ pte = *ptep;
+ pte_clear(mm, addr, ptep);
+ } else {
+ pte = ptep_get_and_clear(mm, addr, ptep);
+ }
+ return pte;
+}
+
+static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
+{
+ clear_bit(_PAGE_BIT_RW, &ptep->pte_low);
+}
+
+/*
+ * clone_pgd_range(pgd_t *dst, pgd_t *src, int count);
+ *
+ * dst - pointer to pgd range anwhere on a pgd page
+ * src - ""
+ * count - the number of pgds to copy.
+ *
+ * dst and src can be on the same page, but the range must not overlap,
+ * and must not cross a page boundary.
+ */
+static inline void clone_pgd_range(pgd_t *dst, pgd_t *src, int count)
+{
+ memcpy(dst, src, count * sizeof(pgd_t));
+}
/*
* Macro to mark a page protection value as "uncacheable". On processors which do not support
*/
#define mk_pte(page, pgprot) pfn_pte(page_to_pfn(page), (pgprot))
-#define mk_pte_huge(entry) ((entry).pte_low |= _PAGE_PRESENT | _PAGE_PSE)
static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
{
pte.pte_low &= _PAGE_CHG_MASK;
pte.pte_low |= pgprot_val(newprot);
+#ifdef CONFIG_X86_PAE
+ /*
+ * Chop off the NX bit (if present), and add the NX portion of
+ * the newprot (if present):
+ */
+ pte.pte_high &= ~(1 << (_PAGE_BIT_NX - 32));
+ pte.pte_high |= (pgprot_val(newprot) >> 32) & \
+ (__supported_pte_mask >> 32);
+#endif
return pte;
}
-#define page_pte(page) page_pte_prot(page, __pgprot(0))
-
-#define pmd_page_kernel(pmd) \
-((unsigned long) __va(pmd_val(pmd) & PAGE_MASK))
-
-#ifndef CONFIG_DISCONTIGMEM
-#define pmd_page(pmd) (pfn_to_page(pmd_val(pmd) >> PAGE_SHIFT))
-#endif /* !CONFIG_DISCONTIGMEM */
-
#define pmd_large(pmd) \
- ((pmd_val(pmd) & (_PAGE_PSE|_PAGE_PRESENT)) == (_PAGE_PSE|_PAGE_PRESENT))
+((pmd_val(pmd) & (_PAGE_PSE|_PAGE_PRESENT)) == (_PAGE_PSE|_PAGE_PRESENT))
/*
* the pgd page can be thought of an array like this: pgd_t[PTRS_PER_PGD]
* control the given virtual address
*/
#define pgd_index(address) (((address) >> PGDIR_SHIFT) & (PTRS_PER_PGD-1))
+#define pgd_index_k(addr) pgd_index(addr)
/*
* pgd_offset() returns a (pgd_t *)
#define pte_offset_kernel(dir, address) \
((pte_t *) pmd_page_kernel(*(dir)) + pte_index(address))
+#define pmd_page(pmd) (pfn_to_page(pmd_val(pmd) >> PAGE_SHIFT))
+
+#define pmd_page_kernel(pmd) \
+ ((unsigned long) __va(pmd_val(pmd) & PAGE_MASK))
+
+/*
+ * Helper function that returns the kernel pagetable entry controlling
+ * the virtual address 'address'. NULL means no pagetable entry present.
+ * NOTE: the return type is pte_t but if the pmd is PSE then we return it
+ * as a pte too.
+ */
+extern pte_t *lookup_address(unsigned long address);
+
+/*
+ * Make a given kernel text page executable/non-executable.
+ * Returns the previous executability setting of that page (which
+ * is used to restore the previous state). Used by the SMP bootup code.
+ * NOTE: this is an __init function for security reasons.
+ */
+#ifdef CONFIG_X86_PAE
+ extern int set_kernel_exec(unsigned long vaddr, int enable);
+#else
+ static inline int set_kernel_exec(unsigned long vaddr, int enable) { return 0;}
+#endif
+
+extern void noexec_setup(const char *str);
+
#if defined(CONFIG_HIGHPTE)
#define pte_offset_map(dir, address) \
((pte_t *)kmap_atomic(pmd_page(*(dir)),KM_PTE0) + pte_index(address))
#define pte_unmap_nested(pte) do { } while (0)
#endif
-#if defined(CONFIG_HIGHPTE) && defined(CONFIG_HIGHMEM4G)
-typedef u32 pte_addr_t;
-#endif
-
-#if defined(CONFIG_HIGHPTE) && defined(CONFIG_HIGHMEM64G)
-typedef u64 pte_addr_t;
-#endif
-
-#if !defined(CONFIG_HIGHPTE)
-typedef pte_t *pte_addr_t;
-#endif
-
/*
* The i386 doesn't have any external MMU info: the kernel page
* tables contain all the necessary information.
+ *
+ * Also, we only update the dirty/accessed state if we set
+ * the dirty bit by hand in the kernel, since the hardware
+ * will do the accessed bit for us, and we don't want to
+ * race with other CPU's that might be updating the dirty
+ * bit at the same time.
*/
#define update_mmu_cache(vma,address,pte) do { } while (0)
-
-/* Encode and de-code a swap entry */
-#define __swp_type(x) (((x).val >> 1) & 0x1f)
-#define __swp_offset(x) ((x).val >> 8)
-#define __swp_entry(type, offset) ((swp_entry_t) { ((type) << 1) | ((offset) << 8) })
-#define __pte_to_swp_entry(pte) ((swp_entry_t) { (pte).pte_low })
-#define __swp_entry_to_pte(x) ((pte_t) { (x).val })
+#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
+#define ptep_set_access_flags(__vma, __address, __ptep, __entry, __dirty) \
+ do { \
+ if (__dirty) { \
+ (__ptep)->pte_low = (__entry).pte_low; \
+ flush_tlb_page(__vma, __address); \
+ } \
+ } while (0)
#endif /* !__ASSEMBLY__ */
-#ifndef CONFIG_DISCONTIGMEM
+#ifdef CONFIG_FLATMEM
#define kern_addr_valid(addr) (1)
-#endif /* !CONFIG_DISCONTIGMEM */
+#endif /* CONFIG_FLATMEM */
+
+#define io_remap_pfn_range(vma, vaddr, pfn, size, prot) \
+ remap_pfn_range(vma, vaddr, pfn, size, prot)
-#define io_remap_page_range remap_page_range
+#define MK_IOSPACE_PFN(space, pfn) (pfn)
+#define GET_IOSPACE(pfn) 0
+#define GET_PFN(pfn) (pfn)
#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_DIRTY
#define __HAVE_ARCH_PTEP_GET_AND_CLEAR
+#define __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL
#define __HAVE_ARCH_PTEP_SET_WRPROTECT
-#define __HAVE_ARCH_PTEP_MKDIRTY
#define __HAVE_ARCH_PTE_SAME
#include <asm-generic/pgtable.h>
git://git.onelab.eu / linux-2.6.git / blobdiff