/*
* This file contains the functions and defines necessary to modify and use
* the x86-64 page table tree.
- *
- * x86-64 has a 4 level table setup. Generic linux MM only supports
- * three levels. The fourth level is currently a single static page that
- * is shared by everybody and just contains a pointer to the current
- * three level page setup on the beginning and some kernel mappings at
- * the end. For more details see Documentation/x86_64/mm.txt
*/
#include <asm/processor.h>
#include <asm/fixmap.h>
#include <linux/threads.h>
#include <asm/pda.h>
-extern pgd_t level3_kernel_pgt[512];
-extern pgd_t level3_physmem_pgt[512];
-extern pgd_t level3_ident_pgt[512];
+extern pud_t level3_kernel_pgt[512];
+extern pud_t level3_physmem_pgt[512];
+extern pud_t level3_ident_pgt[512];
extern pmd_t level2_kernel_pgt[512];
-extern pml4_t init_level4_pgt[];
-extern pgd_t boot_vmalloc_pgt[];
+extern pgd_t init_level4_pgt[];
+extern pgd_t boot_level4_pgt[];
extern unsigned long __supported_pte_mask;
-#define swapper_pg_dir NULL
+#define swapper_pg_dir init_level4_pgt
extern void paging_init(void);
extern void clear_kernel_mapping(unsigned long addr, unsigned long size);
-extern unsigned long pgkern_mask;
-
/*
* ZERO_PAGE is a global shared page that is always zero: used
* for zero-mapped memory areas etc..
extern unsigned long empty_zero_page[PAGE_SIZE/sizeof(unsigned long)];
#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page))
-#define PML4_SHIFT 39
-#define PTRS_PER_PML4 512
-
/*
* PGDIR_SHIFT determines what a top-level page table entry can map
*/
-#define PGDIR_SHIFT 30
+#define PGDIR_SHIFT 39
#define PTRS_PER_PGD 512
+/*
+ * 3rd level page
+ */
+#define PUD_SHIFT 30
+#define PTRS_PER_PUD 512
+
/*
* PMD_SHIFT determines the size of the area a middle-level
* page table can map
printk("%s:%d: bad pte %p(%016lx).\n", __FILE__, __LINE__, &(e), pte_val(e))
#define pmd_ERROR(e) \
printk("%s:%d: bad pmd %p(%016lx).\n", __FILE__, __LINE__, &(e), pmd_val(e))
+#define pud_ERROR(e) \
+ printk("%s:%d: bad pud %p(%016lx).\n", __FILE__, __LINE__, &(e), pud_val(e))
#define pgd_ERROR(e) \
printk("%s:%d: bad pgd %p(%016lx).\n", __FILE__, __LINE__, &(e), pgd_val(e))
-
-#define pml4_none(x) (!pml4_val(x))
#define pgd_none(x) (!pgd_val(x))
-
-extern inline int pgd_present(pgd_t pgd) { return !pgd_none(pgd); }
+#define pud_none(x) (!pud_val(x))
static inline void set_pte(pte_t *dst, pte_t val)
{
pte_val(*dst) = pte_val(val);
}
+#define set_pte_at(mm,addr,ptep,pteval) set_pte(ptep,pteval)
static inline void set_pmd(pmd_t *dst, pmd_t val)
{
pmd_val(*dst) = pmd_val(val);
}
+static inline void set_pud(pud_t *dst, pud_t val)
+{
+ pud_val(*dst) = pud_val(val);
+}
+
+static inline void pud_clear (pud_t *pud)
+{
+ set_pud(pud, __pud(0));
+}
+
static inline void set_pgd(pgd_t *dst, pgd_t val)
{
pgd_val(*dst) = pgd_val(val);
}
-extern inline void pgd_clear (pgd_t * pgd)
+static inline void pgd_clear (pgd_t * pgd)
{
set_pgd(pgd, __pgd(0));
}
-static inline void set_pml4(pml4_t *dst, pml4_t val)
+#define ptep_get_and_clear(mm,addr,xp) __pte(xchg(&(xp)->pte, 0))
+
+struct mm_struct;
+
+static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm, unsigned long addr, pte_t *ptep, int full)
{
- pml4_val(*dst) = pml4_val(val);
+ pte_t pte;
+ if (full) {
+ pte = *ptep;
+ *ptep = __pte(0);
+ } else {
+ pte = ptep_get_and_clear(mm, addr, ptep);
+ }
+ return pte;
}
-#define pgd_page(pgd) \
-((unsigned long) __va(pgd_val(pgd) & PHYSICAL_PAGE_MASK))
-
-#define ptep_get_and_clear(xp) __pte(xchg(&(xp)->pte, 0))
#define pte_same(a, b) ((a).pte == (b).pte)
-#define PML4_SIZE (1UL << PML4_SHIFT)
-#define PML4_MASK (~(PML4_SIZE-1))
+#define pte_pgprot(a) (__pgprot((a).pte & ~PHYSICAL_PAGE_MASK))
+
#define PMD_SIZE (1UL << PMD_SHIFT)
#define PMD_MASK (~(PMD_SIZE-1))
+#define PUD_SIZE (1UL << PUD_SHIFT)
+#define PUD_MASK (~(PUD_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 USER_PGD_PTRS (PAGE_OFFSET >> PGDIR_SHIFT)
-#define KERNEL_PGD_PTRS (PTRS_PER_PGD-USER_PGD_PTRS)
-
-#define TWOLEVEL_PGDIR_SHIFT 20
-#define BOOT_USER_L4_PTRS 1
-#define BOOT_KERNEL_L4_PTRS 511 /* But we will do it in 4rd level */
-
-
+#define USER_PTRS_PER_PGD ((TASK_SIZE-1)/PGDIR_SIZE+1)
+#define FIRST_USER_ADDRESS 0
#ifndef __ASSEMBLY__
-#define VMALLOC_START 0xffffff0000000000UL
-#define VMALLOC_END 0xffffff7fffffffffUL
-#define MODULES_VADDR 0xffffffffa0000000UL
-#define MODULES_END 0xffffffffafffffffUL
+#define MAXMEM 0x3fffffffffffUL
+#define VMALLOC_START 0xffffc20000000000UL
+#define VMALLOC_END 0xffffe1ffffffffffUL
+#define MODULES_VADDR 0xffffffff88000000UL
+#define MODULES_END 0xfffffffffff00000UL
#define MODULES_LEN (MODULES_END - MODULES_VADDR)
-#define IOMAP_START 0xfffffe8000000000UL
-
#define _PAGE_BIT_PRESENT 0
#define _PAGE_BIT_RW 1
#define _PAGE_BIT_USER 2
#define _PAGE_ACCESSED 0x020
#define _PAGE_DIRTY 0x040
#define _PAGE_PSE 0x080 /* 2MB page */
-#define _PAGE_FILE 0x040 /* set:pagecache, unset:swap */
+#define _PAGE_FILE 0x040 /* nonlinear file mapping, saved PTE; unset:swap */
#define _PAGE_GLOBAL 0x100 /* Global TLB entry */
#define _PAGE_PROTNONE 0x080 /* If not present */
(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED | _PAGE_PCD)
#define __PAGE_KERNEL_LARGE \
(__PAGE_KERNEL | _PAGE_PSE)
+#define __PAGE_KERNEL_LARGE_EXEC \
+ (__PAGE_KERNEL_EXEC | _PAGE_PSE)
#define MAKE_GLOBAL(x) __pgprot((x) | _PAGE_GLOBAL)
#define PAGE_KERNEL_EXEC MAKE_GLOBAL(__PAGE_KERNEL_EXEC)
#define PAGE_KERNEL_RO MAKE_GLOBAL(__PAGE_KERNEL_RO)
#define PAGE_KERNEL_NOCACHE MAKE_GLOBAL(__PAGE_KERNEL_NOCACHE)
+#define PAGE_KERNEL_VSYSCALL32 __pgprot(__PAGE_KERNEL_VSYSCALL)
#define PAGE_KERNEL_VSYSCALL MAKE_GLOBAL(__PAGE_KERNEL_VSYSCALL)
#define PAGE_KERNEL_LARGE MAKE_GLOBAL(__PAGE_KERNEL_LARGE)
#define PAGE_KERNEL_VSYSCALL_NOCACHE MAKE_GLOBAL(__PAGE_KERNEL_VSYSCALL_NOCACHE)
#define __S110 PAGE_SHARED_EXEC
#define __S111 PAGE_SHARED_EXEC
-static inline unsigned long pgd_bad(pgd_t pgd)
-{
- unsigned long val = pgd_val(pgd);
- val &= ~PTE_MASK;
- val &= ~(_PAGE_USER | _PAGE_DIRTY);
- return val & ~(_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED);
-}
+static inline unsigned long pgd_bad(pgd_t pgd)
+{
+ return pgd_val(pgd) & ~(PTE_MASK | _KERNPG_TABLE | _PAGE_USER);
+}
+
+static inline unsigned long pud_bad(pud_t pud)
+{
+ return pud_val(pud) & ~(PTE_MASK | _KERNPG_TABLE | _PAGE_USER);
+}
+
+static inline unsigned long pmd_bad(pmd_t pmd)
+{
+ return pmd_val(pmd) & ~(PTE_MASK | _KERNPG_TABLE | _PAGE_USER);
+}
#define pte_none(x) (!pte_val(x))
#define pte_present(x) (pte_val(x) & (_PAGE_PRESENT | _PAGE_PROTNONE))
-#define pte_clear(xp) do { set_pte(xp, __pte(0)); } while (0)
+#define pte_clear(mm,addr,xp) do { set_pte_at(mm, addr, xp, __pte(0)); } while (0)
#define pages_to_mb(x) ((x) >> (20-PAGE_SHIFT)) /* FIXME: is this
right? */
#define pte_page(x) pfn_to_page(pte_pfn(x))
-#define pte_pfn(x) ((pte_val(x) >> PAGE_SHIFT) & __PHYSICAL_MASK)
+#define pte_pfn(x) ((pte_val(x) & __PHYSICAL_MASK) >> PAGE_SHIFT)
static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot)
{
* The following only work if pte_present() is true.
* Undefined behaviour if not..
*/
+#define __LARGE_PTE (_PAGE_PSE|_PAGE_PRESENT)
static inline int pte_user(pte_t pte) { return pte_val(pte) & _PAGE_USER; }
-extern inline int pte_read(pte_t pte) { return pte_val(pte) & _PAGE_USER; }
-extern inline int pte_exec(pte_t pte) { return pte_val(pte) & _PAGE_USER; }
-extern inline int pte_dirty(pte_t pte) { return pte_val(pte) & _PAGE_DIRTY; }
-extern inline int pte_young(pte_t pte) { return pte_val(pte) & _PAGE_ACCESSED; }
-extern inline int pte_write(pte_t pte) { return pte_val(pte) & _PAGE_RW; }
+static inline int pte_read(pte_t pte) { return pte_val(pte) & _PAGE_USER; }
+static inline int pte_exec(pte_t pte) { return !(pte_val(pte) & _PAGE_NX); }
+static inline int pte_dirty(pte_t pte) { return pte_val(pte) & _PAGE_DIRTY; }
+static inline int pte_young(pte_t pte) { return pte_val(pte) & _PAGE_ACCESSED; }
+static inline int pte_write(pte_t pte) { return pte_val(pte) & _PAGE_RW; }
static inline int pte_file(pte_t pte) { return pte_val(pte) & _PAGE_FILE; }
-
-extern inline pte_t pte_rdprotect(pte_t pte) { set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_USER)); return pte; }
-extern inline pte_t pte_exprotect(pte_t pte) { set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_USER)); return pte; }
-extern inline pte_t pte_mkclean(pte_t pte) { set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_DIRTY)); return pte; }
-extern inline pte_t pte_mkold(pte_t pte) { set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_ACCESSED)); return pte; }
-extern inline pte_t pte_wrprotect(pte_t pte) { set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_RW)); return pte; }
-extern inline pte_t pte_mkread(pte_t pte) { set_pte(&pte, __pte(pte_val(pte) | _PAGE_USER)); return pte; }
-extern inline pte_t pte_mkexec(pte_t pte) { set_pte(&pte, __pte(pte_val(pte) | _PAGE_USER)); return pte; }
-extern inline pte_t pte_mkdirty(pte_t pte) { set_pte(&pte, __pte(pte_val(pte) | _PAGE_DIRTY)); return pte; }
-extern inline pte_t pte_mkyoung(pte_t pte) { set_pte(&pte, __pte(pte_val(pte) | _PAGE_ACCESSED)); return pte; }
-extern inline pte_t pte_mkwrite(pte_t pte) { set_pte(&pte, __pte(pte_val(pte) | _PAGE_RW)); return pte; }
-
-static inline int ptep_test_and_clear_dirty(pte_t *ptep)
+static inline int pte_huge(pte_t pte) { return pte_val(pte) & _PAGE_PSE; }
+
+static inline pte_t pte_rdprotect(pte_t pte) { set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_USER)); return pte; }
+static inline pte_t pte_exprotect(pte_t pte) { set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_USER)); return pte; }
+static inline pte_t pte_mkclean(pte_t pte) { set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_DIRTY)); return pte; }
+static inline pte_t pte_mkold(pte_t pte) { set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_ACCESSED)); return pte; }
+static inline pte_t pte_wrprotect(pte_t pte) { set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_RW)); return pte; }
+static inline pte_t pte_mkread(pte_t pte) { set_pte(&pte, __pte(pte_val(pte) | _PAGE_USER)); return pte; }
+static inline pte_t pte_mkexec(pte_t pte) { set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_NX)); return pte; }
+static inline pte_t pte_mkdirty(pte_t pte) { set_pte(&pte, __pte(pte_val(pte) | _PAGE_DIRTY)); return pte; }
+static inline pte_t pte_mkyoung(pte_t pte) { set_pte(&pte, __pte(pte_val(pte) | _PAGE_ACCESSED)); return pte; }
+static inline pte_t pte_mkwrite(pte_t pte) { set_pte(&pte, __pte(pte_val(pte) | _PAGE_RW)); return pte; }
+static inline pte_t pte_mkhuge(pte_t pte) { set_pte(&pte, __pte(pte_val(pte) | _PAGE_PSE)); return pte; }
+static inline pte_t pte_clrhuge(pte_t pte) { set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_PSE)); return pte; }
+
+struct vm_area_struct;
+
+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);
+ return test_and_clear_bit(_PAGE_BIT_DIRTY, &ptep->pte);
}
-static inline int ptep_test_and_clear_young(pte_t *ptep)
+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);
+ return test_and_clear_bit(_PAGE_BIT_ACCESSED, &ptep->pte);
}
-static inline void ptep_set_wrprotect(pte_t *ptep) { clear_bit(_PAGE_BIT_RW, ptep); }
-static inline void ptep_mkdirty(pte_t *ptep) { set_bit(_PAGE_BIT_DIRTY, ptep); }
+static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
+{
+ clear_bit(_PAGE_BIT_RW, &ptep->pte);
+}
/*
* Macro to mark a page protection value as "uncacheable".
*/
#define pgprot_noncached(prot) (__pgprot(pgprot_val(prot) | _PAGE_PCD | _PAGE_PWT))
-#define __LARGE_PTE (_PAGE_PSE|_PAGE_PRESENT)
static inline int pmd_large(pmd_t pte) {
return (pmd_val(pte) & __LARGE_PTE) == __LARGE_PTE;
}
* and a page entry and page directory to the page they refer to.
*/
-#define page_pte(page) page_pte_prot(page, __pgprot(0))
-
/*
* Level 4 access.
- * Never use these in the common code.
*/
-#define pml4_page(pml4) ((unsigned long) __va(pml4_val(pml4) & PTE_MASK))
-#define pml4_index(address) ((address >> PML4_SHIFT) & (PTRS_PER_PML4-1))
-#define pml4_offset_k(address) (init_level4_pgt + pml4_index(address))
-#define pml4_present(pml4) (pml4_val(pml4) & _PAGE_PRESENT)
-#define mk_kernel_pml4(address) ((pml4_t){ (address) | _KERNPG_TABLE })
-#define level3_offset_k(dir, address) ((pgd_t *) pml4_page(*(dir)) + pgd_index(address))
-
-/* PGD - Level3 access */
+#define pgd_page_vaddr(pgd) ((unsigned long) __va((unsigned long)pgd_val(pgd) & PTE_MASK))
+#define pgd_page(pgd) (pfn_to_page(pgd_val(pgd) >> PAGE_SHIFT))
+#define pgd_index(address) (((address) >> PGDIR_SHIFT) & (PTRS_PER_PGD-1))
+#define pgd_offset(mm, addr) ((mm)->pgd + pgd_index(addr))
+#define pgd_offset_k(address) (init_level4_pgt + pgd_index(address))
+#define pgd_present(pgd) (pgd_val(pgd) & _PAGE_PRESENT)
+#define mk_kernel_pgd(address) ((pgd_t){ (address) | _KERNPG_TABLE })
+
+/* PUD - Level3 access */
/* to find an entry in a page-table-directory. */
-#define pgd_index(address) ((address >> PGDIR_SHIFT) & (PTRS_PER_PGD-1))
-static inline pgd_t *__pgd_offset_k(pgd_t *pgd, unsigned long address)
-{
- return pgd + pgd_index(address);
-}
-
-/* Find correct pgd via the hidden fourth level page level: */
-
-/* This accesses the reference page table of the boot cpu.
- Other CPUs get synced lazily via the page fault handler. */
-static inline pgd_t *pgd_offset_k(unsigned long address)
-{
- unsigned long addr;
-
- addr = pml4_val(init_level4_pgt[pml4_index(address)]);
- addr &= PHYSICAL_PAGE_MASK;
- return __pgd_offset_k((pgd_t *)__va(addr), address);
-}
-
-/* Access the pgd of the page table as seen by the current CPU. */
-static inline pgd_t *current_pgd_offset_k(unsigned long address)
-{
- unsigned long addr;
-
- addr = read_pda(level4_pgt)[pml4_index(address)];
- addr &= PHYSICAL_PAGE_MASK;
- return __pgd_offset_k((pgd_t *)__va(addr), address);
-}
-
-#define pgd_offset(mm, address) ((mm)->pgd+pgd_index(address))
+#define pud_page_vaddr(pud) ((unsigned long) __va(pud_val(pud) & PHYSICAL_PAGE_MASK))
+#define pud_page(pud) (pfn_to_page(pud_val(pud) >> PAGE_SHIFT))
+#define pud_index(address) (((address) >> PUD_SHIFT) & (PTRS_PER_PUD-1))
+#define pud_offset(pgd, address) ((pud_t *) pgd_page_vaddr(*(pgd)) + pud_index(address))
+#define pud_present(pud) (pud_val(pud) & _PAGE_PRESENT)
/* PMD - Level 2 access */
-#define pmd_page_kernel(pmd) ((unsigned long) __va(pmd_val(pmd) & PTE_MASK))
+#define pmd_page_vaddr(pmd) ((unsigned long) __va(pmd_val(pmd) & PTE_MASK))
#define pmd_page(pmd) (pfn_to_page(pmd_val(pmd) >> PAGE_SHIFT))
#define pmd_index(address) (((address) >> PMD_SHIFT) & (PTRS_PER_PMD-1))
-#define pmd_offset(dir, address) ((pmd_t *) pgd_page(*(dir)) + \
+#define pmd_offset(dir, address) ((pmd_t *) pud_page_vaddr(*(dir)) + \
pmd_index(address))
#define pmd_none(x) (!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) & (~PTE_MASK & ~_PAGE_USER)) != _KERNPG_TABLE )
#define pfn_pmd(nr,prot) (__pmd(((nr) << PAGE_SHIFT) | pgprot_val(prot)))
-#define pmd_pfn(x) ((pmd_val(x) >> PAGE_SHIFT) & __PHYSICAL_MASK)
+#define pmd_pfn(x) ((pmd_val(x) & __PHYSICAL_MASK) >> PAGE_SHIFT)
#define pte_to_pgoff(pte) ((pte_val(pte) & PHYSICAL_PAGE_MASK) >> PAGE_SHIFT)
#define pgoff_to_pte(off) ((pte_t) { ((off) << PAGE_SHIFT) | _PAGE_FILE })
{
pte_t pte;
pte_val(pte) = physpage | pgprot_val(pgprot);
+ pte_val(pte) &= __supported_pte_mask;
return pte;
}
/* Change flags of a PTE */
-extern inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
+static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
{
pte_val(pte) &= _PAGE_CHG_MASK;
pte_val(pte) |= pgprot_val(newprot);
}
#define pte_index(address) \
- ((address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
-#define pte_offset_kernel(dir, address) ((pte_t *) pmd_page_kernel(*(dir)) + \
+ (((address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
+#define pte_offset_kernel(dir, address) ((pte_t *) pmd_page_vaddr(*(dir)) + \
pte_index(address))
/* x86-64 always has all page tables mapped. */
#define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) })
#define __swp_entry_to_pte(x) ((pte_t) { (x).val })
+extern spinlock_t pgd_lock;
+extern struct page *pgd_list;
+void vmalloc_sync_all(void);
+
#endif /* !__ASSEMBLY__ */
extern int kern_addr_valid(unsigned long addr);
-#define io_remap_page_range remap_page_range
+#define io_remap_pfn_range(vma, vaddr, pfn, size, prot) \
+ remap_pfn_range(vma, vaddr, pfn, size, prot)
+
+#define MK_IOSPACE_PFN(space, pfn) (pfn)
+#define GET_IOSPACE(pfn) 0
+#define GET_PFN(pfn) (pfn)
#define HAVE_ARCH_UNMAPPED_AREA
#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