pgtable.h

基于组件方式开发操作系统的OSKIT源代码

#ifndef _I386_PGTABLE_H
#define _I386_PGTABLE_H

#include <linux/config.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/tasks.h>

/* Caches aren't brain-dead on the intel. */
#define flush_cache_all()			do { } while (0)
#define flush_cache_mm(mm)			do { } while (0)
#define flush_cache_range(mm, start, end)	do { } while (0)
#define flush_cache_page(vma, vmaddr)		do { } while (0)
#define flush_page_to_ram(page)			do { } while (0)
#define flush_icache_range(start, end)		do { } while (0)

#ifndef OSKIT
/* We do not have to worry about context switch TLB flushes */
/*
 * TLB flushing:
 *
 *  - flush_tlb() flushes the current mm struct TLBs
 *  - flush_tlb_all() flushes all processes TLBs
 *  - flush_tlb_mm(mm) flushes the specified mm context TLB's
 *  - flush_tlb_page(vma, vmaddr) flushes one page
 *  - flush_tlb_range(mm, start, end) flushes a range of pages
 *
 * ..but the i386 has somewhat limited tlb flushing capabilities,
 * and page-granular flushes are available only on i486 and up.
 */

#define __flush_tlb() \
do { unsigned long tmpreg; __asm__ __volatile__("movl %%cr3,%0\n\tmovl %0,%%cr3":"=r" (tmpreg) : :"memory"); } while (0)

#ifndef CONFIG_X86_INVLPG
#define __flush_tlb_one(addr) flush_tlb()
#else
#define __flush_tlb_one(addr) \
__asm__ __volatile__("invlpg %0": :"m" (*(char *) addr))
#endif
 
#ifndef __SMP__

#define flush_tlb() __flush_tlb()
#define flush_tlb_all() __flush_tlb()
#define local_flush_tlb() __flush_tlb()

static inline void flush_tlb_mm(struct mm_struct *mm)
{
	if (mm == current->mm)
		__flush_tlb();
}

static inline void flush_tlb_page(struct vm_area_struct *vma,
	unsigned long addr)
{
	if (vma->vm_mm == current->mm)
		__flush_tlb_one(addr);
}

static inline void flush_tlb_range(struct mm_struct *mm,
	unsigned long start, unsigned long end)
{
	if (mm == current->mm)
		__flush_tlb();
}

#else

/*
 * We aren't very clever about this yet -  SMP could certainly
 * avoid some global flushes..
 */

#include <asm/smp.h>

#define local_flush_tlb() \
	__flush_tlb()


#define CLEVER_SMP_INVALIDATE
#ifdef CLEVER_SMP_INVALIDATE

/*
 *	Smarter SMP flushing macros. 
 *		c/o Linus Torvalds.
 *
 *	These mean you can really definitely utterly forget about
 *	writing to user space from interrupts. (Its not allowed anyway).
 */
 
static inline void flush_tlb_current_task(void)
{
	/* just one copy of this mm? */
	if (atomic_read(&current->mm->count) == 1)
		local_flush_tlb();	/* and that's us, so.. */
	else
		smp_flush_tlb();
}

#define flush_tlb() flush_tlb_current_task()

#define flush_tlb_all() smp_flush_tlb()

static inline void flush_tlb_mm(struct mm_struct * mm)
{
	if (mm == current->mm && atomic_read(&mm->count) == 1)
		local_flush_tlb();
	else
		smp_flush_tlb();
}

static inline void flush_tlb_page(struct vm_area_struct * vma,
	unsigned long va)
{
	if (vma->vm_mm == current->mm && atomic_read(&current->mm->count) == 1)
		__flush_tlb_one(va);
	else
		smp_flush_tlb();
}

static inline void flush_tlb_range(struct mm_struct * mm,
	unsigned long start, unsigned long end)
{
	flush_tlb_mm(mm);
}


#else

#define flush_tlb() \
	smp_flush_tlb()

#define flush_tlb_all() flush_tlb()

static inline void flush_tlb_mm(struct mm_struct *mm)
{
	flush_tlb();
}

static inline void flush_tlb_page(struct vm_area_struct *vma,
	unsigned long addr)
{
	flush_tlb();
}

static inline void flush_tlb_range(struct mm_struct *mm,
	unsigned long start, unsigned long end)
{
	flush_tlb();
}
#endif
#endif
#endif /* !OSKIT */
#endif /* !__ASSEMBLY__ */

/* Certain architectures need to do special things when PTEs
 * within a page table are directly modified.  Thus, the following
 * hook is made available.
 */
#define set_pte(pteptr, pteval) ((*(pteptr)) = (pteval))

/* 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
#define USER_PTRS_PER_PGD	(TASK_SIZE/PGDIR_SIZE)

/*
 * pgd entries used up by user/kernel:
 */

#define USER_PGD_PTRS (PAGE_OFFSET >> PGDIR_SHIFT)
#define KERNEL_PGD_PTRS (PTRS_PER_PGD-USER_PGD_PTRS)
#define __USER_PGD_PTRS ((__PAGE_OFFSET >> PGDIR_SHIFT) & 0x3ff)
#define __KERNEL_PGD_PTRS (PTRS_PER_PGD-__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
 * 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_OFFSET) & ~(VMALLOC_OFFSET-1))
#define VMALLOC_VMADDR(x) ((unsigned long)(x))
#define VMALLOC_END	(FIXADDR_START)

/*
 * 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
 * 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_PWT	0x008
#define _PAGE_PCD	0x010
#define _PAGE_ACCESSED	0x020
#define _PAGE_DIRTY	0x040
#define _PAGE_4M	0x080	/* 4 MB page, Pentium+, if present.. */
#define _PAGE_GLOBAL	0x100	/* Global TLB entry PPro+ */

#define _PAGE_PROTNONE	0x080	/* If not present */

#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	(PAGE_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_KERNEL	__pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED)
#define PAGE_KERNEL_RO	__pgprot(_PAGE_PRESENT | _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

#ifndef OSKIT
/*
 * 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,..)'
 */
#undef TEST_VERIFY_AREA

/* page table for 0-4MB for everybody */
extern unsigned long pg0[1024];
/* zero page used for uninitialized stuff */
extern unsigned 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(vaddr) ((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