memory.c

包括初始化、进程管理、进程通信、内存管理、设备管理、中断、文件系统、系统调用等精选源码分析。

/*
 *  linux/mm/memory.c
 *
 *  Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
 */

/*
 * demand-loading started 01.12.91 - seems it is high on the list of
 * things wanted, and it should be easy to implement. - Linus
 */

/*
 * Ok, demand-loading was easy, shared pages a little bit tricker. Shared
 * pages started 02.12.91, seems to work. - Linus.
 *
 * Tested sharing by executing about 30 /bin/sh: under the old kernel it
 * would have taken more than the 6M I have free, but it worked well as
 * far as I could see.
 *
 * Also corrected some "invalidate()"s - I wasn't doing enough of them.
 */

/*
 * Real VM (paging to/from disk) started 18.12.91. Much more work and
 * thought has to go into this. Oh, well..
 * 19.12.91  -  works, somewhat. Sometimes I get faults, don't know why.
 *		Found it. Everything seems to work now.
 * 20.12.91  -  Ok, making the swap-device changeable like the root.
 */

/*
 * 05.04.94  -  Multi-page memory management added for v1.1.
 * 		Idea by Alex Bligh ([e-mail])
 *
 * 16.07.99  -  Support of BIGMEM added by Gerhard Wichert, Siemens AG
 *		([e-mail])
 */

#include <linux/mm.h>
#include <linux/mman.h>
#include <linux/swap.h>
#include <linux/smp_lock.h>
#include <linux/swapctl.h>
#include <linux/iobuf.h>
#include <asm/uaccess.h>
#include <asm/pgalloc.h>
#include <linux/highmem.h>
#include <linux/pagemap.h>


unsigned long max_mapnr;
unsigned long num_physpages;
void * high_memory;
struct page *highmem_start_page;

/*
 * We special-case the C-O-W ZERO_PAGE, because it's such
 * a common occurrence (no need to read the page to know
 * that it's zero - better for the cache and memory subsystem).
 */
static inline void copy_cow_page(struct page * from, struct page * to, unsigned long address)
{
	if (from == ZERO_PAGE(address)) {
		clear_user_highpage(to, address);
		return;
	}
	copy_user_highpage(to, from, address);
}

mem_map_t * mem_map;

/*
 * Note: this doesn't free the actual pages themselves. That
 * has been handled earlier when unmapping all the memory regions.
 */
static inline void free_one_pmd(pmd_t * dir)
{
	pte_t * pte;

	if (pmd_none(*dir))
		return;
	if (pmd_bad(*dir)) {
		pmd_ERROR(*dir);
		pmd_clear(dir);
		return;
	}
	pte = pte_offset(dir, 0);
	pmd_clear(dir);
	pte_free(pte);
}

static inline void free_one_pgd(pgd_t * dir)
{
	int j;
	pmd_t * pmd;

	if (pgd_none(*dir))
		return;
	if (pgd_bad(*dir)) {
		pgd_ERROR(*dir);
		pgd_clear(dir);
		return;
	}
	pmd = pmd_offset(dir, 0);
	pgd_clear(dir);
	for (j = 0; j < PTRS_PER_PMD ; j++)
		free_one_pmd(pmd+j);
	pmd_free(pmd);
}

/* Low and high watermarks for page table cache.
   The system should try to have pgt_water[0] <= cache elements <= pgt_water[1]
 */
int pgt_cache_water[2] = { 25, 50 };

/* Returns the number of pages freed */
int check_pgt_cache(void)
{
	return do_check_pgt_cache(pgt_cache_water[0], pgt_cache_water[1]);
}


/*
 * This function clears all user-level page tables of a process - this
 * is needed by execve(), so that old pages aren't in the way.
 */
void clear_page_tables(struct mm_struct *mm, unsigned long first, int nr)
{
	pgd_t * page_dir = mm->pgd;

	page_dir += first;
	do {
		free_one_pgd(page_dir);
		page_dir++;
	} while (--nr);

	/* keep the page table cache within bounds */
	check_pgt_cache();
}

#define PTE_TABLE_MASK	((PTRS_PER_PTE-1) * sizeof(pte_t))
#define PMD_TABLE_MASK	((PTRS_PER_PMD-1) * sizeof(pmd_t))

/*
 * copy one vm_area from one task to the other. Assumes the page tables
 * already present in the new task to be cleared in the whole range
 * covered by this vma.
 *
 * 08Jan98 Merged into one routine from several inline routines to reduce
 *         variable count and make things faster. -jj
 */
int copy_page_range(struct mm_struct *dst, struct mm_struct *src,
			struct vm_area_struct *vma)
{
	pgd_t * src_pgd, * dst_pgd;
	unsigned long address = vma->vm_start;
	unsigned long end = vma->vm_end;
	unsigned long cow = (vma->vm_flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;

	src_pgd = pgd_offset(src, address)-1;
	dst_pgd = pgd_offset(dst, address)-1;
	
	for (;;) {
		pmd_t * src_pmd, * dst_pmd;

		src_pgd++; dst_pgd++;
		
		/* copy_pmd_range */
		
		if (pgd_none(*src_pgd))
			goto skip_copy_pmd_range;
		if (pgd_bad(*src_pgd)) {
			pgd_ERROR(*src_pgd);
			pgd_clear(src_pgd);
skip_copy_pmd_range:	address = (address + PGDIR_SIZE) & PGDIR_MASK;
			if (!address || (address >= end))
				goto out;
			continue;
		}
		if (pgd_none(*dst_pgd)) {
			if (!pmd_alloc(dst_pgd, 0))
				goto nomem;
		}
		
		src_pmd = pmd_offset(src_pgd, address);
		dst_pmd = pmd_offset(dst_pgd, address);

		do {
			pte_t * src_pte, * dst_pte;
		
			/* copy_pte_range */
		
			if (pmd_none(*src_pmd))
				goto skip_copy_pte_range;
			if (pmd_bad(*src_pmd)) {
				pmd_ERROR(*src_pmd);
				pmd_clear(src_pmd);
skip_copy_pte_range:		address = (address + PMD_SIZE) & PMD_MASK;
				if (address >= end)
					goto out;
				goto cont_copy_pmd_range;
			}
			if (pmd_none(*dst_pmd)) {
				if (!pte_alloc(dst_pmd, 0))
					goto nomem;
			}
			
			src_pte = pte_offset(src_pmd, address);
			dst_pte = pte_offset(dst_pmd, address);
			
			do {
				pte_t pte = *src_pte;
				struct page *ptepage;
				
				/* copy_one_pte */

				if (pte_none(pte))
					goto cont_copy_pte_range_noset;
				if (!pte_present(pte)) {
					swap_duplicate(pte_to_swp_entry(pte));
					goto cont_copy_pte_range;
				}
				ptepage = pte_page(pte);
				if ((!VALID_PAGE(ptepage)) || 
				    PageReserved(ptepage))
					goto cont_copy_pte_range;

				/* If it's a COW mapping, write protect it both in the parent and the child */
				if (cow) {
					ptep_set_wrprotect(src_pte);
					pte = *src_pte;
				}

				/* If it's a shared mapping, mark it clean in the child */
				if (vma->vm_flags & VM_SHARED)
					pte = pte_mkclean(pte);
				pte = pte_mkold(pte);
				get_page(ptepage);

cont_copy_pte_range:		set_pte(dst_pte, pte);
cont_copy_pte_range_noset:	address += PAGE_SIZE;
				if (address >= end)
					goto out;
				src_pte++;
				dst_pte++;
			} while ((unsigned long)src_pte & PTE_TABLE_MASK);
		
cont_copy_pmd_range:	src_pmd++;
			dst_pmd++;
		} while ((unsigned long)src_pmd & PMD_TABLE_MASK);
	}
out:
	return 0;

nomem:
	return -ENOMEM;
}

/*
 * Return indicates whether a page was freed so caller can adjust rss
 */
static inline int free_pte(pte_t pte)
{
	if (pte_present(pte)) {
		struct page *page = pte_page(pte);
		if ((!VALID_PAGE(page)) || PageReserved(page))
			return 0;
		/* 
		 * free_page() used to be able to clear swap cache
		 * entries.  We may now have to do it manually.  
		 */
		if (pte_dirty(pte) && page->mapping)
			set_page_dirty(page);
		free_page_and_swap_cache(page);
		return 1;
	}
	swap_free(pte_to_swp_entry(pte));
	return 0;
}

static inline void forget_pte(pte_t page)
{
	if (!pte_none(page)) {
		printk("forget_pte: old mapping existed!\n");
		free_pte(page);
	}
}

static inline int zap_pte_range(struct mm_struct *mm, pmd_t * pmd, unsigned long address, unsigned long size)
{
	pte_t * pte;
	int freed;

	if (pmd_none(*pmd))
		return 0;
	if (pmd_bad(*pmd)) {
		pmd_ERROR(*pmd);
		pmd_clear(pmd);
		return 0;
	}
	pte = pte_offset(pmd, address);
	address &= ~PMD_MASK;
	if (address + size > PMD_SIZE)
		size = PMD_SIZE - address;
	size >>= PAGE_SHIFT;
	freed = 0;
	for (;;) {
		pte_t page;
		if (!size)
			break;
		page = ptep_get_and_clear(pte);
		pte++;
		size--;
		if (pte_none(page))
			continue;
		freed += free_pte(page);
	}
	return freed;
}

static inline int zap_pmd_range(struct mm_struct *mm, pgd_t * dir, unsigned long address, unsigned long size)
{
	pmd_t * pmd;
	unsigned long end;
	int freed;

	if (pgd_none(*dir))
		return 0;
	if (pgd_bad(*dir)) {
		pgd_ERROR(*dir);
		pgd_clear(dir);
		return 0;
	}
	pmd = pmd_offset(dir, address);
	address &= ~PGDIR_MASK;
	end = address + size;
	if (end > PGDIR_SIZE)
		end = PGDIR_SIZE;
	freed = 0;
	do {
		freed += zap_pte_range(mm, pmd, address, end - address);
		address = (address + PMD_SIZE) & PMD_MASK; 
		pmd++;
	} while (address < end);
	return freed;
}

/*
 * remove user pages in a given range.
 */
void zap_page_range(struct mm_struct *mm, unsigned long address, unsigned long size)
{
	pgd_t * dir;
	unsigned long end = address + size;
	int freed = 0;

	dir = pgd_offset(mm, address);

	/*
	 * This is a long-lived spinlock. That's fine.
	 * There's no contention, because the page table
	 * lock only protects against kswapd anyway, and
	 * even if kswapd happened to be looking at this
	 * process we _want_ it to get stuck.
	 */
	if (address >= end)
		BUG();
	spin_lock(&mm->page_table_lock);
	do {
		freed += zap_pmd_range(mm, dir, address, end - address);
		address = (address + PGDIR_SIZE) & PGDIR_MASK;
		dir++;
	} while (address && (address < end));
	spin_unlock(&mm->page_table_lock);
	/*
	 * Update rss for the mm_struct (not necessarily current->mm)
	 * Notice that rss is an unsigned long.
	 */
	if (mm->rss > freed)
		mm->rss -= freed;
	else
		mm->rss = 0;
}


/*
 * Do a quick page-table lookup for a single page. 
 */
static struct page * follow_page(unsigned long address) 
{
	pgd_t *pgd;
	pmd_t *pmd;

	pgd = pgd_offset(current->mm, address);
	pmd = pmd_offset(pgd, address);
	if (pmd) {
		pte_t * pte = pte_offset(pmd, address);
		if (pte && pte_present(*pte))
			return pte_page(*pte);
	}
	
	return NULL;
}

/* 
 * Given a physical address, is there a useful struct page pointing to
 * it?  This may become more complex in the future if we start dealing
 * with IO-aperture pages in kiobufs.
 */