swapfile.c

嵌入式系统设计与实例开发实验教材二源码 多线程应用程序设计 串行端口程序设计 AD接口实验 CAN总线通信实验 GPS通信实验 Linux内核移植与编译实验 IC卡读写实验 SD驱动使

/*
 *  linux/mm/swapfile.c
 *
 *  Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
 *  Swap reorganised 29.12.95, Stephen Tweedie
 */

#include <linux/slab.h>
#include <linux/smp_lock.h>
#include <linux/kernel_stat.h>
#include <linux/swap.h>
#include <linux/swapctl.h>
#include <linux/blkdev.h> /* for blk_size */
#include <linux/vmalloc.h>
#include <linux/pagemap.h>
#include <linux/shm.h>
#include <linux/compiler.h>

#include <asm/pgtable.h>

spinlock_t swaplock = SPIN_LOCK_UNLOCKED;
unsigned int nr_swapfiles;
int total_swap_pages;
static int swap_overflow;

static const char Bad_file[] = "Bad swap file entry ";
static const char Unused_file[] = "Unused swap file entry ";
static const char Bad_offset[] = "Bad swap offset entry ";
static const char Unused_offset[] = "Unused swap offset entry ";

struct swap_list_t swap_list = {-1, -1};

struct swap_info_struct swap_info[MAX_SWAPFILES];

#define SWAPFILE_CLUSTER 256

static inline int scan_swap_map(struct swap_info_struct *si)
{
	unsigned long offset;
	/* 
	 * We try to cluster swap pages by allocating them
	 * sequentially in swap.  Once we've allocated
	 * SWAPFILE_CLUSTER pages this way, however, we resort to
	 * first-free allocation, starting a new cluster.  This
	 * prevents us from scattering swap pages all over the entire
	 * swap partition, so that we reduce overall disk seek times
	 * between swap pages.  -- sct */
	if (si->cluster_nr) {
		while (si->cluster_next <= si->highest_bit) {
			offset = si->cluster_next++;
			if (si->swap_map[offset])
				continue;
			si->cluster_nr--;
			goto got_page;
		}
	}
	si->cluster_nr = SWAPFILE_CLUSTER;

	/* try to find an empty (even not aligned) cluster. */
	offset = si->lowest_bit;
 check_next_cluster:
	if (offset+SWAPFILE_CLUSTER-1 <= si->highest_bit)
	{
		int nr;
		for (nr = offset; nr < offset+SWAPFILE_CLUSTER; nr++)
			if (si->swap_map[nr])
			{
				offset = nr+1;
				goto check_next_cluster;
			}
		/* We found a completly empty cluster, so start
		 * using it.
		 */
		goto got_page;
	}
	/* No luck, so now go finegrined as usual. -Andrea */
	for (offset = si->lowest_bit; offset <= si->highest_bit ; offset++) {
		if (si->swap_map[offset])
			continue;
		si->lowest_bit = offset+1;
	got_page:
		if (offset == si->lowest_bit)
			si->lowest_bit++;
		if (offset == si->highest_bit)
			si->highest_bit--;
		if (si->lowest_bit > si->highest_bit) {
			si->lowest_bit = si->max;
			si->highest_bit = 0;
		}
		si->swap_map[offset] = 1;
		nr_swap_pages--;
		si->cluster_next = offset+1;
		return offset;
	}
	si->lowest_bit = si->max;
	si->highest_bit = 0;
	return 0;
}

swp_entry_t get_swap_page(void)
{
	struct swap_info_struct * p;
	unsigned long offset;
	swp_entry_t entry;
	int type, wrapped = 0;

	entry.val = 0;	/* Out of memory */
	swap_list_lock();
	type = swap_list.next;
	if (type < 0)
		goto out;
	if (nr_swap_pages <= 0)
		goto out;

	while (1) {
		p = &swap_info[type];
		if ((p->flags & SWP_WRITEOK) == SWP_WRITEOK) {
			swap_device_lock(p);
			offset = scan_swap_map(p);
			swap_device_unlock(p);
			if (offset) {
				entry = SWP_ENTRY(type,offset);
				type = swap_info[type].next;
				if (type < 0 ||
					p->prio != swap_info[type].prio) {
						swap_list.next = swap_list.head;
				} else {
					swap_list.next = type;
				}
				goto out;
			}
		}
		type = p->next;
		if (!wrapped) {
			if (type < 0 || p->prio != swap_info[type].prio) {
				type = swap_list.head;
				wrapped = 1;
			}
		} else
			if (type < 0)
				goto out;	/* out of swap space */
	}
out:
	swap_list_unlock();
	return entry;
}

static struct swap_info_struct * swap_info_get(swp_entry_t entry)
{
	struct swap_info_struct * p;
	unsigned long offset, type;

	if (!entry.val)
		goto out;
	type = SWP_TYPE(entry);
	if (type >= nr_swapfiles)
		goto bad_nofile;
	p = & swap_info[type];
	if (!(p->flags & SWP_USED))
		goto bad_device;
	offset = SWP_OFFSET(entry);
	if (offset >= p->max)
		goto bad_offset;
	if (!p->swap_map[offset])
		goto bad_free;
	swap_list_lock();
	if (p->prio > swap_info[swap_list.next].prio)
		swap_list.next = type;
	swap_device_lock(p);
	return p;

bad_free:
	printk(KERN_ERR "swap_free: %s%08lx\n", Unused_offset, entry.val);
	goto out;
bad_offset:
	printk(KERN_ERR "swap_free: %s%08lx\n", Bad_offset, entry.val);
	goto out;
bad_device:
	printk(KERN_ERR "swap_free: %s%08lx\n", Unused_file, entry.val);
	goto out;
bad_nofile:
	printk(KERN_ERR "swap_free: %s%08lx\n", Bad_file, entry.val);
out:
	return NULL;
}	

static void swap_info_put(struct swap_info_struct * p)
{
	swap_device_unlock(p);
	swap_list_unlock();
}

static int swap_entry_free(struct swap_info_struct *p, unsigned long offset)
{
	int count = p->swap_map[offset];

	if (count < SWAP_MAP_MAX) {
		count--;
		p->swap_map[offset] = count;
		if (!count) {
			if (offset < p->lowest_bit)
				p->lowest_bit = offset;
			if (offset > p->highest_bit)
				p->highest_bit = offset;
			nr_swap_pages++;
		}
	}
	return count;
}

/*
 * Caller has made sure that the swapdevice corresponding to entry
 * is still around or has not been recycled.
 */
void swap_free(swp_entry_t entry)
{
	struct swap_info_struct * p;

	p = swap_info_get(entry);
	if (p) {
		swap_entry_free(p, SWP_OFFSET(entry));
		swap_info_put(p);
	}
}

/*
 * Check if we're the only user of a swap page,
 * when the page is locked.
 */
static int exclusive_swap_page(struct page *page)
{
	int retval = 0;
	struct swap_info_struct * p;
	swp_entry_t entry;

	entry.val = page->index;
	p = swap_info_get(entry);
	if (p) {
		/* Is the only swap cache user the cache itself? */
		if (p->swap_map[SWP_OFFSET(entry)] == 1) {
			/* Recheck the page count with the pagecache lock held.. */
			spin_lock(&pagecache_lock);
			if (page_count(page) - !!page->buffers == 2)
				retval = 1;
			spin_unlock(&pagecache_lock);
		}
		swap_info_put(p);
	}
	return retval;
}

/*
 * We can use this swap cache entry directly
 * if there are no other references to it.
 *
 * Here "exclusive_swap_page()" does the real
 * work, but we opportunistically check whether
 * we need to get all the locks first..
 */
int can_share_swap_page(struct page *page)
{
	int retval = 0;

	if (!PageLocked(page))
		BUG();
	switch (page_count(page)) {
	case 3:
		if (!page->buffers)
			break;
		/* Fallthrough */
	case 2:
		if (!PageSwapCache(page))
			break;
		retval = exclusive_swap_page(page);
		break;
	case 1:
		if (PageReserved(page))
			break;
		retval = 1;
	}
	return retval;
}

/*
 * Work out if there are any other processes sharing this
 * swap cache page. Free it if you can. Return success.
 */
int remove_exclusive_swap_page(struct page *page)
{
	int retval;
	struct swap_info_struct * p;
	swp_entry_t entry;

	if (!PageLocked(page))
		BUG();
	if (!PageSwapCache(page))
		return 0;
	if (page_count(page) - !!page->buffers != 2)	/* 2: us + cache */
		return 0;

	entry.val = page->index;
	p = swap_info_get(entry);
	if (!p)
		return 0;

	/* Is the only swap cache user the cache itself? */
	retval = 0;
	if (p->swap_map[SWP_OFFSET(entry)] == 1) {
		/* Recheck the page count with the pagecache lock held.. */
		spin_lock(&pagecache_lock);
		if (page_count(page) - !!page->buffers == 2) {
			__delete_from_swap_cache(page);
			SetPageDirty(page);
			retval = 1;
		}
		spin_unlock(&pagecache_lock);
	}
	swap_info_put(p);

	if (retval) {
		block_flushpage(page, 0);
		swap_free(entry);
		page_cache_release(page);
	}

	return retval;
}

/*
 * Free the swap entry like above, but also try to
 * free the page cache entry if it is the last user.
 */
void free_swap_and_cache(swp_entry_t entry)
{
	struct swap_info_struct * p;
	struct page *page = NULL;

	p = swap_info_get(entry);
	if (p) {
		if (swap_entry_free(p, SWP_OFFSET(entry)) == 1)
			page = find_trylock_page(&swapper_space, entry.val);
		swap_info_put(p);
	}
	if (page) {
		page_cache_get(page);
		/* Only cache user (+us), or swap space full? Free it! */
		if (page_count(page) - !!page->buffers == 2 || vm_swap_full()) {
			delete_from_swap_cache(page);
			SetPageDirty(page);
		}
		UnlockPage(page);
		page_cache_release(page);
	}
}

/*
 * The swap entry has been read in advance, and we return 1 to indicate
 * that the page has been used or is no longer needed.
 *
 * Always set the resulting pte to be nowrite (the same as COW pages
 * after one process has exited).  We don't know just how many PTEs will
 * share this swap entry, so be cautious and let do_wp_page work out
 * what to do if a write is requested later.
 */
/* mmlist_lock and vma->vm_mm->page_table_lock are held */
static inline void unuse_pte(struct vm_area_struct * vma, unsigned long address,
	pte_t *dir, swp_entry_t entry, struct page* page)
{
	pte_t pte = *dir;

	if (likely(pte_to_swp_entry(pte).val != entry.val))
		return;
	if (unlikely(pte_none(pte) || pte_present(pte)))
		return;
	get_page(page);
	set_pte(dir, pte_mkold(mk_pte(page, vma->vm_page_prot)));
	swap_free(entry);
	++vma->vm_mm->rss;
}

/* mmlist_lock and vma->vm_mm->page_table_lock are held */
static inline void unuse_pmd(struct vm_area_struct * vma, pmd_t *dir,
	unsigned long address, unsigned long size, unsigned long offset,
	swp_entry_t entry, struct page* page)
{
	pte_t * pte;
	unsigned long end;

	if (pmd_none(*dir))
		return;
	if (pmd_bad(*dir)) {
		pmd_ERROR(*dir);
		pmd_clear(dir);
		return;
	}
	pte = pte_offset(dir, address);
	offset += address & PMD_MASK;
	address &= ~PMD_MASK;
	end = address + size;
	if (end > PMD_SIZE)
		end = PMD_SIZE;
	do {
		unuse_pte(vma, offset+address-vma->vm_start, pte, entry, page);
		address += PAGE_SIZE;
		pte++;
	} while (address && (address < end));
}

/* mmlist_lock and vma->vm_mm->page_table_lock are held */
static inline void unuse_pgd(struct vm_area_struct * vma, pgd_t *dir,
	unsigned long address, unsigned long size,
	swp_entry_t entry, struct page* page)
{
	pmd_t * pmd;
	unsigned long offset, end;

	if (pgd_none(*dir))
		return;
	if (pgd_bad(*dir)) {
		pgd_ERROR(*dir);
		pgd_clear(dir);
		return;
	}
	pmd = pmd_offset(dir, address);
	offset = address & PGDIR_MASK;
	address &= ~PGDIR_MASK;
	end = address + size;
	if (end > PGDIR_SIZE)
		end = PGDIR_SIZE;
	if (address >= end)
		BUG();
	do {