init.c

Linux内核源代码 为压缩文件 是<<Linux内核>>一书中的源代码

/*
 *  linux/arch/i386/mm/init.c
 *
 *  Copyright (C) 1995  Linus Torvalds
 *
 *  Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
 */

#include <linux/config.h>
#include <linux/signal.h>
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/string.h>
#include <linux/types.h>
#include <linux/ptrace.h>
#include <linux/mman.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/smp.h>
#include <linux/init.h>
#ifdef CONFIG_BLK_DEV_INITRD
#include <linux/blk.h>
#endif
#include <linux/highmem.h>
#include <linux/pagemap.h>
#include <linux/bootmem.h>

#include <asm/processor.h>
#include <asm/system.h>
#include <asm/uaccess.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
#include <asm/dma.h>
#include <asm/fixmap.h>
#include <asm/e820.h>
#include <asm/apic.h>

unsigned long highstart_pfn, highend_pfn;
static unsigned long totalram_pages;
static unsigned long totalhigh_pages;

/*
 * BAD_PAGE is the page that is used for page faults when linux
 * is out-of-memory. Older versions of linux just did a
 * do_exit(), but using this instead means there is less risk
 * for a process dying in kernel mode, possibly leaving an inode
 * unused etc..
 *
 * BAD_PAGETABLE is the accompanying page-table: it is initialized
 * to point to BAD_PAGE entries.
 *
 * ZERO_PAGE is a special page that is used for zero-initialized
 * data and COW.
 */

/*
 * These are allocated in head.S so that we get proper page alignment.
 * If you change the size of these then change head.S as well.
 */
extern char empty_bad_page[PAGE_SIZE];
#if CONFIG_X86_PAE
extern pmd_t empty_bad_pmd_table[PTRS_PER_PMD];
#endif
extern pte_t empty_bad_pte_table[PTRS_PER_PTE];

/*
 * We init them before every return and make them writable-shared.
 * This guarantees we get out of the kernel in some more or less sane
 * way.
 */
#if CONFIG_X86_PAE
static pmd_t * get_bad_pmd_table(void)
{
	pmd_t v;
	int i;

	set_pmd(&v, __pmd(_PAGE_TABLE + __pa(empty_bad_pte_table)));

	for (i = 0; i < PAGE_SIZE/sizeof(pmd_t); i++)
		empty_bad_pmd_table[i] = v;

	return empty_bad_pmd_table;
}
#endif

static pte_t * get_bad_pte_table(void)
{
	pte_t v;
	int i;

	v = pte_mkdirty(mk_pte_phys(__pa(empty_bad_page), PAGE_SHARED));

	for (i = 0; i < PAGE_SIZE/sizeof(pte_t); i++)
		empty_bad_pte_table[i] = v;

	return empty_bad_pte_table;
}



void __handle_bad_pmd(pmd_t *pmd)
{
	pmd_ERROR(*pmd);
	set_pmd(pmd, __pmd(_PAGE_TABLE + __pa(get_bad_pte_table())));
}

void __handle_bad_pmd_kernel(pmd_t *pmd)
{
	pmd_ERROR(*pmd);
	set_pmd(pmd, __pmd(_KERNPG_TABLE + __pa(get_bad_pte_table())));
}

pte_t *get_pte_kernel_slow(pmd_t *pmd, unsigned long offset)
{
	pte_t *pte;

	pte = (pte_t *) __get_free_page(GFP_KERNEL);
	if (pmd_none(*pmd)) {
		if (pte) {
			clear_page(pte);
			set_pmd(pmd, __pmd(_KERNPG_TABLE + __pa(pte)));
			return pte + offset;
		}
		set_pmd(pmd, __pmd(_KERNPG_TABLE + __pa(get_bad_pte_table())));
		return NULL;
	}
	free_page((unsigned long)pte);
	if (pmd_bad(*pmd)) {
		__handle_bad_pmd_kernel(pmd);
		return NULL;
	}
	return (pte_t *) pmd_page(*pmd) + offset;
}

pte_t *get_pte_slow(pmd_t *pmd, unsigned long offset)
{
	unsigned long pte;

	pte = (unsigned long) __get_free_page(GFP_KERNEL);
	if (pmd_none(*pmd)) {
		if (pte) {
			clear_page((void *)pte);
			set_pmd(pmd, __pmd(_PAGE_TABLE + __pa(pte)));
			return (pte_t *)pte + offset;
		}
		set_pmd(pmd, __pmd(_PAGE_TABLE + __pa(get_bad_pte_table())));
		return NULL;
	}
	free_page(pte);
	if (pmd_bad(*pmd)) {
		__handle_bad_pmd(pmd);
		return NULL;
	}
	return (pte_t *) pmd_page(*pmd) + offset;
}

int do_check_pgt_cache(int low, int high)
{
	int freed = 0;
	if(pgtable_cache_size > high) {
		do {
			if(pgd_quicklist)
				free_pgd_slow(get_pgd_fast()), freed++;
			if(pmd_quicklist)
				free_pmd_slow(get_pmd_fast()), freed++;
			if(pte_quicklist)
				free_pte_slow(get_pte_fast()), freed++;
		} while(pgtable_cache_size > low);
	}
	return freed;
}

/*
 * NOTE: pagetable_init alloc all the fixmap pagetables contiguous on the
 * physical space so we can cache the place of the first one and move
 * around without checking the pgd every time.
 */

#if CONFIG_HIGHMEM
pte_t *kmap_pte;
pgprot_t kmap_prot;

#define kmap_get_fixmap_pte(vaddr)					\
	pte_offset(pmd_offset(pgd_offset_k(vaddr), (vaddr)), (vaddr))

void __init kmap_init(void)
{
	unsigned long kmap_vstart;

	/* cache the first kmap pte */
	kmap_vstart = __fix_to_virt(FIX_KMAP_BEGIN);
	kmap_pte = kmap_get_fixmap_pte(kmap_vstart);

	kmap_prot = PAGE_KERNEL;
}
#endif /* CONFIG_HIGHMEM */

void show_mem(void)
{
	int i, total = 0, reserved = 0;
	int shared = 0, cached = 0;
	int highmem = 0;

	printk("Mem-info:\n");
	show_free_areas();
	printk("Free swap:       %6dkB\n",nr_swap_pages<<(PAGE_SHIFT-10));
	i = max_mapnr;
	while (i-- > 0) {
		total++;
		if (PageHighMem(mem_map+i))
			highmem++;
		if (PageReserved(mem_map+i))
			reserved++;
		else if (PageSwapCache(mem_map+i))
			cached++;
		else if (page_count(mem_map+i))
			shared += page_count(mem_map+i) - 1;
	}
	printk("%d pages of RAM\n", total);
	printk("%d pages of HIGHMEM\n",highmem);
	printk("%d reserved pages\n",reserved);
	printk("%d pages shared\n",shared);
	printk("%d pages swap cached\n",cached);
	printk("%ld pages in page table cache\n",pgtable_cache_size);
	show_buffers();
}

/* References to section boundaries */

extern char _text, _etext, _edata, __bss_start, _end;
extern char __init_begin, __init_end;

static inline void set_pte_phys (unsigned long vaddr,
			unsigned long phys, pgprot_t flags)
{
	pgprot_t prot;
	pgd_t *pgd;
	pmd_t *pmd;
	pte_t *pte;

	pgd = swapper_pg_dir + __pgd_offset(vaddr);
	if (pgd_none(*pgd)) {
		printk("PAE BUG #00!\n");
		return;
	}
	pmd = pmd_offset(pgd, vaddr);
	if (pmd_none(*pmd)) {
		printk("PAE BUG #01!\n");
		return;
	}
	pte = pte_offset(pmd, vaddr);
	if (pte_val(*pte))
		pte_ERROR(*pte);
	pgprot_val(prot) = pgprot_val(PAGE_KERNEL) | pgprot_val(flags);
	set_pte(pte, mk_pte_phys(phys, prot));

	/*
	 * It's enough to flush this one mapping.
	 * (PGE mappings get flushed as well)
	 */
	__flush_tlb_one(vaddr);
}

void __set_fixmap (enum fixed_addresses idx, unsigned long phys, pgprot_t flags)
{
	unsigned long address = __fix_to_virt(idx);

	if (idx >= __end_of_fixed_addresses) {
		printk("Invalid __set_fixmap\n");
		return;
	}
	set_pte_phys(address, phys, flags);
}

static void __init fixrange_init (unsigned long start, unsigned long end, pgd_t *pgd_base)
{
	pgd_t *pgd;
	pmd_t *pmd;
	pte_t *pte;
	int i, j;
	unsigned long vaddr;

	vaddr = start;
	i = __pgd_offset(vaddr);
	j = __pmd_offset(vaddr);
	pgd = pgd_base + i;

	for ( ; (i < PTRS_PER_PGD) && (vaddr != end); pgd++, i++) {
#if CONFIG_X86_PAE
		if (pgd_none(*pgd)) {
			pmd = (pmd_t *) alloc_bootmem_low_pages(PAGE_SIZE);
			set_pgd(pgd, __pgd(__pa(pmd) + 0x1));
			if (pmd != pmd_offset(pgd, 0))
				printk("PAE BUG #02!\n");
		}
		pmd = pmd_offset(pgd, vaddr);
#else
		pmd = (pmd_t *)pgd;
#endif
		for (; (j < PTRS_PER_PMD) && (vaddr != end); pmd++, j++) {
			if (pmd_none(*pmd)) {
				pte = (pte_t *) alloc_bootmem_low_pages(PAGE_SIZE);
				set_pmd(pmd, __pmd(_KERNPG_TABLE + __pa(pte)));
				if (pte != pte_offset(pmd, 0))
					BUG();
			}
			vaddr += PMD_SIZE;
		}
		j = 0;
	}
}

static void __init pagetable_init (void)
{
	unsigned long vaddr, end;
	pgd_t *pgd, *pgd_base;
	int i, j, k;
	pmd_t *pmd;
	pte_t *pte;

	/*
	 * This can be zero as well - no problem, in that case we exit
	 * the loops anyway due to the PTRS_PER_* conditions.
	 */
	end = (unsigned long)__va(max_low_pfn*PAGE_SIZE);

	pgd_base = swapper_pg_dir;
#if CONFIG_X86_PAE
	for (i = 0; i < PTRS_PER_PGD; i++) {
		pgd = pgd_base + i;
		__pgd_clear(pgd);
	}
#endif
	i = __pgd_offset(PAGE_OFFSET);
	pgd = pgd_base + i;

	for (; i < PTRS_PER_PGD; pgd++, i++) {
		vaddr = i*PGDIR_SIZE;
		if (end && (vaddr >= end))
			break;
#if CONFIG_X86_PAE
		pmd = (pmd_t *) alloc_bootmem_low_pages(PAGE_SIZE);
		set_pgd(pgd, __pgd(__pa(pmd) + 0x1));
#else
		pmd = (pmd_t *)pgd;
#endif
		if (pmd != pmd_offset(pgd, 0))