Import 1.3.16

[davej-history.git] / include / asm-i386 / pgtable.h

#ifndef _I386_PGTABLE_H
#define _I386_PGTABLE_H

/*
 * Define CONFIG_PENTIUM_MM if you want the 4MB page table optimizations.
 * This works only on a intel Pentium.
 */
#define CONFIG_PENTIUM_MM 1

/*
 * 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.
 */

/* PMD_SHIFT determines the size of the area a second-level page table can map */
#define PMD_SHIFT 22
#define PMD_SIZE (1UL << PMD_SHIFT)
#define PMD_MASK (~(PMD_SIZE-1))

/* PGDIR_SHIFT determines what a third-level page table entry can map */
#define PGDIR_SHIFT 22
#define PGDIR_SIZE (1UL << PGDIR_SHIFT)
#define PGDIR_MASK (~(PGDIR_SIZE-1))

/*
 * entries per page directory level: the i386 is two-level, so
 * we don't really have any PMD directory physically.
 */
#define PTRS_PER_PTE 1024
#define PTRS_PER_PMD 1
#define PTRS_PER_PGD 1024

/* 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 ((high_memory + VMALLOC_OFFSET) & ~(VMALLOC_OFFSET-1))
#define VMALLOC_VMADDR(x) (TASK_SIZE + (unsigned long)(x))

/*
 * The 4MB page is guessing.. Detailed in the infamous "Chapter H"
 * of the Pentium details, but assuming intel did the straigtforward
 * thing, this bit set in the page directory entry just means that
 * the page directory entry points directly to a 4MB-aligned block of
 * memory. 
 */
#define _PAGE_PRESENT 0x001
#define _PAGE_RW 0x002
#define _PAGE_USER 0x004
#define _PAGE_PCD 0x010
#define _PAGE_ACCESSED 0x020
#define _PAGE_DIRTY 0x040
#define _PAGE_4M 0x080/* 4 MB page, Pentium+.. */
#define _PAGE_COW 0x200/* implemented in software (one of the AVL bits) */

#define _PAGE_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED | _PAGE_DIRTY)
#define _PAGE_CHG_MASK (PAGE_MASK | _PAGE_ACCESSED | _PAGE_DIRTY)

#define PAGE_NONE __pgprot(_PAGE_PRESENT | _PAGE_ACCESSED)
#define PAGE_SHARED __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED)
#define PAGE_COPY __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED | _PAGE_COW)
#define PAGE_READONLY __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED)
#define PAGE_KERNEL __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED)

/*
 * 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
#define __P101 PAGE_READONLY
#define __P110 PAGE_COPY
#define __P111 PAGE_COPY

#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 this if things work differently on a i386 and a i486:
 * it will (on a i486) warn about kernel memory accesses that are
 * done without a 'verify_area(VERIFY_WRITE,..)'
 */
#undef CONFIG_TEST_VERIFY_AREA

/* page table for 0-4MB for everybody */
externunsigned long pg0[1024];
/* zero page used for unitialized stuff */
externunsigned long empty_zero_page[1024];

/*
 * BAD_PAGETABLE is used when we need a bogus page-table, while
 * BAD_PAGE is used for a bogus page.
 *
 * ZERO_PAGE is a global shared page that is always zero: used
 * for zero-mapped memory areas etc..
 */
extern pte_t __bad_page(void);
extern pte_t *__bad_pagetable(void);

#define BAD_PAGETABLE __bad_pagetable()
#define BAD_PAGE __bad_page()
#define ZERO_PAGE ((unsigned long) empty_zero_page)

/* number of bits that fit into a memory pointer */
#define BITS_PER_PTR (8*sizeof(unsigned long))

/* to align the pointer to a pointer address */
#define PTR_MASK (~(sizeof(void*)-1))

/* sizeof(void*)==1<<SIZEOF_PTR_LOG2 */
/* 64-bit machines, beware! SRB. */
#define SIZEOF_PTR_LOG2 2

/* to find an entry in a page-table */
#define PAGE_PTR(address) \
((unsigned long)(address)>>(PAGE_SHIFT-SIZEOF_PTR_LOG2)&PTR_MASK&~PAGE_MASK)

/* to set the page-dir */
#define SET_PAGE_DIR(tsk,pgdir) \
do { \
 (tsk)->tss.cr3 = (unsigned long) (pgdir); \
 if ((tsk) == current) \
 __asm__ __volatile__("movl %0,%%cr3": :"a" ((tsk)->tss.cr3)); \
} while (0)

extern inlineintpte_none(pte_t pte) {return!pte_val(pte); }
extern inlineintpte_present(pte_t pte) {returnpte_val(pte) & _PAGE_PRESENT; }
extern inlineintpte_inuse(pte_t *ptep) {return mem_map[MAP_NR(ptep)] !=1; }
extern inlinevoidpte_clear(pte_t *ptep) {pte_val(*ptep) =0; }
extern inlinevoidpte_reuse(pte_t * ptep)
{
if(!(mem_map[MAP_NR(ptep)] & MAP_PAGE_RESERVED))
 mem_map[MAP_NR(ptep)]++;
}

extern inlineintpmd_none(pmd_t pmd) {return!pmd_val(pmd); }
extern inlineintpmd_bad(pmd_t pmd) {return(pmd_val(pmd) & ~PAGE_MASK) != _PAGE_TABLE ||pmd_val(pmd) > high_memory; }
extern inlineintpmd_present(pmd_t pmd) {returnpmd_val(pmd) & _PAGE_PRESENT; }
#ifdef CONFIG_PENTIUM_MM
extern inlineintpmd_inuse(pmd_t *pmdp) {return(pmd_val(*pmdp) & _PAGE_4M) !=0; }
#else
extern inlineintpmd_inuse(pmd_t *pmdp) {return0; }
#endif
extern inlinevoidpmd_clear(pmd_t * pmdp) {pmd_val(*pmdp) =0; }
extern inlinevoidpmd_reuse(pmd_t * pmdp) { }

/*
 * The "pgd_xxx()" functions here are trivial for a folded two-level
 * setup: the pgd is never bad, and a pmd always exists (as it's folded
 * into the pgd entry)
 */
extern inlineintpgd_none(pgd_t pgd) {return0; }
extern inlineintpgd_bad(pgd_t pgd) {return0; }
extern inlineintpgd_present(pgd_t pgd) {return1; }
extern inlineintpgd_inuse(pgd_t * pgdp) {return mem_map[MAP_NR(pgdp)] !=1; }
extern inlinevoidpgd_clear(pgd_t * pgdp) { }
extern inlinevoidpgd_reuse(pgd_t * pgdp)
{
if(!(mem_map[MAP_NR(pgdp)] & MAP_PAGE_RESERVED))
 mem_map[MAP_NR(pgdp)]++;
}

/*
 * The following only work if pte_present() is true.
 * Undefined behaviour if not..
 */
extern inlineintpte_read(pte_t pte) {returnpte_val(pte) & _PAGE_USER; }
extern inlineintpte_write(pte_t pte) {returnpte_val(pte) & _PAGE_RW; }
extern inlineintpte_exec(pte_t pte) {returnpte_val(pte) & _PAGE_USER; }
extern inlineintpte_dirty(pte_t pte) {returnpte_val(pte) & _PAGE_DIRTY; }
extern inlineintpte_young(pte_t pte) {returnpte_val(pte) & _PAGE_ACCESSED; }
extern inlineintpte_cow(pte_t pte) {returnpte_val(pte) & _PAGE_COW; }

extern inline pte_t pte_wrprotect(pte_t pte) {pte_val(pte) &= ~_PAGE_RW;return pte; }
extern inline pte_t pte_rdprotect(pte_t pte) {pte_val(pte) &= ~_PAGE_USER;return pte; }
extern inline pte_t pte_exprotect(pte_t pte) {pte_val(pte) &= ~_PAGE_USER;return pte; }
extern inline pte_t pte_mkclean(pte_t pte) {pte_val(pte) &= ~_PAGE_DIRTY;return pte; }
extern inline pte_t pte_mkold(pte_t pte) {pte_val(pte) &= ~_PAGE_ACCESSED;return pte; }
extern inline pte_t pte_uncow(pte_t pte) {pte_val(pte) &= ~_PAGE_COW;return pte; }
extern inline pte_t pte_mkwrite(pte_t pte) {pte_val(pte) |= _PAGE_RW;return pte; }
extern inline pte_t pte_mkread(pte_t pte) {pte_val(pte) |= _PAGE_USER;return pte; }
extern inline pte_t pte_mkexec(pte_t pte) {pte_val(pte) |= _PAGE_USER;return pte; }
extern inline pte_t pte_mkdirty(pte_t pte) {pte_val(pte) |= _PAGE_DIRTY;return pte; }
extern inline pte_t pte_mkyoung(pte_t pte) {pte_val(pte) |= _PAGE_ACCESSED;return pte; }
extern inline pte_t pte_mkcow(pte_t pte) {pte_val(pte) |= _PAGE_COW;return pte; }

/*
 * Conversion functions: convert a page and protection to a page entry,
 * and a page entry and page directory to the page they refer to.
 */
extern inline pte_t mk_pte(unsigned long page, pgprot_t pgprot)
{ pte_t pte;pte_val(pte) = page |pgprot_val(pgprot);return pte; }

extern inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
{pte_val(pte) = (pte_val(pte) & _PAGE_CHG_MASK) |pgprot_val(newprot);return pte; }

extern inlineunsigned longpte_page(pte_t pte)
{returnpte_val(pte) & PAGE_MASK; }

extern inlineunsigned longpmd_page(pmd_t pmd)
{returnpmd_val(pmd) & PAGE_MASK; }

/* to find an entry in a page-table-directory */
extern inline pgd_t *pgd_offset(struct task_struct * tsk,unsigned long address)
{
return(pgd_t *) tsk->tss.cr3 + (address >> PGDIR_SHIFT);
}

/* Find an entry in the second-level page table.. */
extern inline pmd_t *pmd_offset(pgd_t * dir,unsigned long address)
{
return(pmd_t *) dir;
}

/* Find an entry in the third-level page table.. */
extern inline pte_t *pte_offset(pmd_t * dir,unsigned long address)
{
return(pte_t *)pmd_page(*dir) + ((address >> PAGE_SHIFT) & (PTRS_PER_PTE -1));
}

/*
 * Allocate and free page tables. The xxx_kernel() versions are
 * used to allocate a kernel page table - this turns on ASN bits
 * if any, and marks the page tables reserved.
 */
extern inlinevoidpte_free_kernel(pte_t * pte)
{
 mem_map[MAP_NR(pte)] =1;
free_page((unsigned long) pte);
}

extern inline pte_t *pte_alloc_kernel(pmd_t * pmd,unsigned long address)
{
 address = (address >> PAGE_SHIFT) & (PTRS_PER_PTE -1);
if(pmd_none(*pmd)) {
 pte_t * page = (pte_t *)get_free_page(GFP_KERNEL);
if(pmd_none(*pmd)) {
if(page) {
pmd_val(*pmd) = _PAGE_TABLE | (unsigned long) page;
 mem_map[MAP_NR(page)] = MAP_PAGE_RESERVED;
return page + address;
}
pmd_val(*pmd) = _PAGE_TABLE | (unsigned long) BAD_PAGETABLE;
return NULL;
}
free_page((unsigned long) page);
}
if(pmd_bad(*pmd)) {
printk("Bad pmd in pte_alloc: %08lx\n",pmd_val(*pmd));
pmd_val(*pmd) = _PAGE_TABLE | (unsigned long) BAD_PAGETABLE;
return NULL;
}
return(pte_t *)pmd_page(*pmd) + address;
}

/*
 * allocating and freeing a pmd is trivial: the 1-entry pmd is
 * inside the pgd, so has no extra memory associated with it.
 */
extern inlinevoidpmd_free_kernel(pmd_t * pmd)
{
pmd_val(*pmd) =0;
}

extern inline pmd_t *pmd_alloc_kernel(pgd_t * pgd,unsigned long address)
{
return(pmd_t *) pgd;
}

extern inlinevoidpte_free(pte_t * pte)
{
free_page((unsigned long) pte);
}

extern inline pte_t *pte_alloc(pmd_t * pmd,unsigned long address)
{
 address = (address >> PAGE_SHIFT) & (PTRS_PER_PTE -1);
if(pmd_none(*pmd)) {
 pte_t * page = (pte_t *)get_free_page(GFP_KERNEL);
if(pmd_none(*pmd)) {
if(page) {
pmd_val(*pmd) = _PAGE_TABLE | (unsigned long) page;
return page + address;
}
pmd_val(*pmd) = _PAGE_TABLE | (unsigned long) BAD_PAGETABLE;
return NULL;
}
free_page((unsigned long) page);
}
if(pmd_bad(*pmd)) {
printk("Bad pmd in pte_alloc: %08lx\n",pmd_val(*pmd));
pmd_val(*pmd) = _PAGE_TABLE | (unsigned long) BAD_PAGETABLE;
return NULL;
}
return(pte_t *)pmd_page(*pmd) + address;
}

/*
 * allocating and freeing a pmd is trivial: the 1-entry pmd is
 * inside the pgd, so has no extra memory associated with it.
 */
extern inlinevoidpmd_free(pmd_t * pmd)
{
pmd_val(*pmd) =0;
}

extern inline pmd_t *pmd_alloc(pgd_t * pgd,unsigned long address)
{
return(pmd_t *) pgd;
}

extern inlinevoidpgd_free(pgd_t * pgd)
{
free_page((unsigned long) pgd);
}

extern inline pgd_t *pgd_alloc(void)
{
return(pgd_t *)get_free_page(GFP_KERNEL);
}

extern pgd_t swapper_pg_dir[1024];

/*
 * The i386 doesn't have any external MMU info: the kernel page
 * tables contain all the necessary information.
 */
extern inlinevoidupdate_mmu_cache(struct vm_area_struct * vma,
unsigned long address, pte_t pte)
{
}

#define SWP_TYPE(entry) (((entry) >> 1) & 0x7f)
#define SWP_OFFSET(entry) ((entry) >> 8)
#define SWP_ENTRY(type,offset) (((type) << 1) | ((offset) << 8))

#endif/* _I386_PAGE_H */