--- /dev/null
+#ifndef _I386_PGTABLE_H
+#define _I386_PGTABLE_H
+
+#include <linux/config.h>
+#include <asm/hypervisor.h>
+
+/*
+ * The Linux memory management assumes a three-level page table setup. On
+ * the i386, we use that, but "fold" the mid level into the top-level page
+ * table, so that we physically have the same two-level page table as the
+ * i386 mmu expects.
+ *
+ * This file contains the functions and defines necessary to modify and use
+ * the i386 page table tree.
+ */
+#ifndef __ASSEMBLY__
+#include <asm/processor.h>
+#include <asm/fixmap.h>
+#include <linux/threads.h>
+
+#ifndef _I386_BITOPS_H
+#include <asm/bitops.h>
+#endif
+
+#include <linux/slab.h>
+#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..
+ */
+#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page))
+extern unsigned long empty_zero_page[1024];
+extern pgd_t *swapper_pg_dir;
+extern kmem_cache_t *pgd_cache;
+extern kmem_cache_t *pmd_cache;
+extern spinlock_t pgd_lock;
+extern struct page *pgd_list;
+
+void pmd_ctor(void *, kmem_cache_t *, unsigned long);
+void pgd_ctor(void *, kmem_cache_t *, unsigned long);
+void pgd_dtor(void *, kmem_cache_t *, unsigned long);
+void pgtable_cache_init(void);
+void paging_init(void);
+
+/*
+ * 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.
+ */
+#ifdef CONFIG_X86_PAE
+# include <asm/pgtable-3level-defs.h>
+# define PMD_SIZE (1UL << PMD_SHIFT)
+# define PMD_MASK (~(PMD_SIZE-1))
+#else
+# include <asm/pgtable-2level-defs.h>
+#endif
+
+#define PGDIR_SIZE (1UL << PGDIR_SHIFT)
+#define PGDIR_MASK (~(PGDIR_SIZE-1))
+
+#define USER_PTRS_PER_PGD (TASK_SIZE/PGDIR_SIZE)
+#define FIRST_USER_ADDRESS 0
+
+#define USER_PGD_PTRS (PAGE_OFFSET >> PGDIR_SHIFT)
+#define KERNEL_PGD_PTRS (PTRS_PER_PGD-USER_PGD_PTRS)
+
+#define TWOLEVEL_PGDIR_SHIFT 22
+#define BOOT_USER_PGD_PTRS (__PAGE_OFFSET >> TWOLEVEL_PGDIR_SHIFT)
+#define BOOT_KERNEL_PGD_PTRS (1024-BOOT_USER_PGD_PTRS)
+
+/* 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
+ * any out-of-bounds memory accesses will hopefully be caught.
+ * The vmalloc() routines leaves a hole of 4kB between each vmalloced
+ * area for the same reason. ;)
+ */
+#define VMALLOC_OFFSET (8*1024*1024)
+#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
+# define VMALLOC_END (FIXADDR_START-2*PAGE_SIZE)
+#endif
+
+/*
+ * _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_PRESENT 0
+#define _PAGE_BIT_RW 1
+#define _PAGE_BIT_USER 2
+#define _PAGE_BIT_PWT 3
+#define _PAGE_BIT_PCD 4
+#define _PAGE_BIT_ACCESSED 5
+#define _PAGE_BIT_DIRTY 6
+#define _PAGE_BIT_PSE 7 /* 4 MB (or 2MB) page, Pentium+, if present.. */
+#define _PAGE_BIT_GLOBAL 8 /* Global TLB entry PPro+ */
+#define _PAGE_BIT_UNUSED1 9 /* available for programmer */
+#define _PAGE_BIT_UNUSED2 10
+#define _PAGE_BIT_UNUSED3 11
+#define _PAGE_BIT_NX 63
+
+#define _PAGE_PRESENT 0x001
+#define _PAGE_RW 0x002
+#define _PAGE_USER 0x004
+#define _PAGE_PWT 0x008
+#define _PAGE_PCD 0x010
+#define _PAGE_ACCESSED 0x020
+#define _PAGE_DIRTY 0x040
+#define _PAGE_PSE 0x080 /* 4 MB (or 2MB) page, Pentium+, if present.. */
+#define _PAGE_GLOBAL 0x100 /* Global TLB entry PPro+ */
+#define _PAGE_UNUSED1 0x200 /* available for programmer */
+#define _PAGE_UNUSED2 0x400
+#define _PAGE_UNUSED3 0x800
+
+/* 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_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 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
+ * the same are read. Also, write permissions imply read permissions.
+ * This is the closest we can get..
+ */
+#define __P000 PAGE_NONE
+#define __P001 PAGE_READONLY
+#define __P010 PAGE_COPY
+#define __P011 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_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 'access_ok(VERIFY_WRITE,..)'
+ */
+#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))
+
+/* To avoid harmful races, pmd_none(x) should check only the lower when PAE */
+#define pmd_none(x) (!(unsigned long)pmd_val(x))
+/* pmd_present doesn't just test the _PAGE_PRESENT bit since wr.p.t.
+ can temporarily clear it. */
+#define pmd_present(x) (pmd_val(x))
+#define pmd_bad(x) ((pmd_val(x) & (~PAGE_MASK & ~_PAGE_USER & ~_PAGE_PRESENT)) != (_KERNPG_TABLE & ~_PAGE_PRESENT))
+
+
+#define pages_to_mb(x) ((x) >> (20-PAGE_SHIFT))
+
+/*
+ * The following only work if pte_present() is true.
+ * Undefined behaviour if not..
+ */
+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_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 int pte_file(pte_t pte) { return (pte).pte_low & _PAGE_FILE; }
+
+static inline pte_t pte_rdprotect(pte_t pte) { (pte).pte_low &= ~_PAGE_USER; return pte; }
+static inline pte_t pte_exprotect(pte_t pte) { (pte).pte_low &= ~_PAGE_USER; return pte; }
+static inline pte_t pte_mkclean(pte_t pte) { (pte).pte_low &= ~_PAGE_DIRTY; return pte; }
+static inline pte_t pte_mkold(pte_t pte) { (pte).pte_low &= ~_PAGE_ACCESSED; return pte; }
+static inline pte_t pte_wrprotect(pte_t pte) { (pte).pte_low &= ~_PAGE_RW; return pte; }
+static inline pte_t pte_mkread(pte_t pte) { (pte).pte_low |= _PAGE_USER; return pte; }
+static inline pte_t pte_mkexec(pte_t pte) { (pte).pte_low |= _PAGE_USER; return pte; }
+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(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)
+{
+ if (pte_write(*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
+ * it, this is a no-op.
+ */
+#define pgprot_noncached(prot) ((boot_cpu_data.x86 > 3) \
+ ? (__pgprot(pgprot_val(prot) | _PAGE_PCD | _PAGE_PWT)) : (prot))
+
+/*
+ * Conversion functions: convert a page and protection to a page entry,
+ * and a page entry and page directory to the page they refer to.
+ */
+
+#define mk_pte(page, pgprot) pfn_pte(page_to_pfn(page), (pgprot))
+
+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 pmd_large(pmd) \
+((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]
+ *
+ * this macro returns the index of the entry in the pgd page which would
+ * 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 *)
+ * pgd_index() is used get the offset into the pgd page's array of pgd_t's;
+ */
+#define pgd_offset(mm, address) ((mm)->pgd+pgd_index(address))
+
+/*
+ * a shortcut which implies the use of the kernel's pgd, instead
+ * of a process's
+ */
+#define pgd_offset_k(address) pgd_offset(&init_mm, address)
+
+/*
+ * the pmd page can be thought of an array like this: pmd_t[PTRS_PER_PMD]
+ *
+ * this macro returns the index of the entry in the pmd page which would
+ * control the given virtual address
+ */
+#define pmd_index(address) \
+ (((address) >> PMD_SHIFT) & (PTRS_PER_PMD-1))
+
+/*
+ * the pte page can be thought of an array like this: pte_t[PTRS_PER_PTE]
+ *
+ * this macro returns the index of the entry in the pte page which would
+ * control the given virtual address
+ */
+#define pte_index(address) \
+ (((address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
+#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_pte(pmd_page(*(dir)),KM_PTE0) + \
+ pte_index(address))
+#define pte_offset_map_nested(dir, address) \
+ ((pte_t *)kmap_atomic_pte(pmd_page(*(dir)),KM_PTE1) + \
+ pte_index(address))
+#define pte_unmap(pte) kunmap_atomic(pte, KM_PTE0)
+#define pte_unmap_nested(pte) kunmap_atomic(pte, KM_PTE1)
+#else
+#define pte_offset_map(dir, address) \
+ ((pte_t *)page_address(pmd_page(*(dir))) + pte_index(address))
+#define pte_offset_map_nested(dir, address) pte_offset_map(dir, address)
+#define pte_unmap(pte) do { } while (0)
+#define pte_unmap_nested(pte) do { } while (0)
+#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)
+#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
+#define ptep_set_access_flags(__vma, __address, __ptep, __entry, __dirty) \
+ do { \
+ if (__dirty) { \
+ if ( likely((__vma)->vm_mm == current->mm) ) { \
+ BUG_ON(HYPERVISOR_update_va_mapping((__address), (__entry), UVMF_INVLPG|UVMF_MULTI|(unsigned long)((__vma)->vm_mm->cpu_vm_mask.bits))); \
+ } else { \
+ xen_l1_entry_update((__ptep), (__entry)); \
+ flush_tlb_page((__vma), (__address)); \
+ } \
+ } \
+ } while (0)
+
+#define __HAVE_ARCH_PTEP_ESTABLISH
+#define ptep_establish(__vma, __address, __ptep, __entry) \
+do { \
+ ptep_set_access_flags(__vma, __address, __ptep, __entry, 1); \
+} while (0)
+
+#include <xen/features.h>
+void make_lowmem_page_readonly(void *va, unsigned int feature);
+void make_lowmem_page_writable(void *va, unsigned int feature);
+void make_page_readonly(void *va, unsigned int feature);
+void make_page_writable(void *va, unsigned int feature);
+void make_pages_readonly(void *va, unsigned int nr, unsigned int feature);
+void make_pages_writable(void *va, unsigned int nr, unsigned int feature);
+
+#define virt_to_ptep(__va) \
+({ \
+ pgd_t *__pgd = pgd_offset_k((unsigned long)(__va)); \
+ pud_t *__pud = pud_offset(__pgd, (unsigned long)(__va)); \
+ pmd_t *__pmd = pmd_offset(__pud, (unsigned long)(__va)); \
+ pte_offset_kernel(__pmd, (unsigned long)(__va)); \
+})
+
+#define arbitrary_virt_to_machine(__va) \
+({ \
+ maddr_t m = (maddr_t)pte_mfn(*virt_to_ptep(__va)) << PAGE_SHIFT;\
+ m | ((unsigned long)(__va) & (PAGE_SIZE-1)); \
+})
+
+#endif /* !__ASSEMBLY__ */
+
+#ifdef CONFIG_FLATMEM
+#define kern_addr_valid(addr) (1)
+#endif /* CONFIG_FLATMEM */
+
+int direct_remap_pfn_range(struct vm_area_struct *vma,
+ unsigned long address,
+ unsigned long mfn,
+ unsigned long size,
+ pgprot_t prot,
+ domid_t domid);
+int direct_kernel_remap_pfn_range(unsigned long address,
+ unsigned long mfn,
+ unsigned long size,
+ pgprot_t prot,
+ domid_t domid);
+int create_lookup_pte_addr(struct mm_struct *mm,
+ unsigned long address,
+ uint64_t *ptep);
+int touch_pte_range(struct mm_struct *mm,
+ unsigned long address,
+ unsigned long size);
+
+#define io_remap_pfn_range(vma,from,pfn,size,prot) \
+direct_remap_pfn_range(vma,from,pfn,size,prot,DOMID_IO)
+
+#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_PTE_SAME
+#include <asm-generic/pgtable.h>
+
+#endif /* _I386_PGTABLE_H */
git://git.onelab.eu / linux-2.6.git / blobdiff