swapfile.c

最新最稳定的Linux内存管理模块源代码

	loff_t l = *pos;

	mutex_lock(&swapon_mutex);

	if (!l)
		return SEQ_START_TOKEN;

	for (i = 0; i < nr_swapfiles; i++, ptr++) {
		if (!(ptr->flags & SWP_USED) || !ptr->swap_map)
			continue;
		if (!--l)
			return ptr;
	}

	return NULL;
}

static void *swap_next(struct seq_file *swap, void *v, loff_t *pos)
{
	struct swap_info_struct *ptr;
	struct swap_info_struct *endptr = swap_info + nr_swapfiles;

	if (v == SEQ_START_TOKEN)
		ptr = swap_info;
	else {
		ptr = v;
		ptr++;
	}

	for (; ptr < endptr; ptr++) {
		if (!(ptr->flags & SWP_USED) || !ptr->swap_map)
			continue;
		++*pos;
		return ptr;
	}

	return NULL;
}

static void swap_stop(struct seq_file *swap, void *v)
{
	mutex_unlock(&swapon_mutex);
}

static int swap_show(struct seq_file *swap, void *v)
{
	struct swap_info_struct *ptr = v;
	struct file *file;
	int len;

	if (ptr == SEQ_START_TOKEN) {
		seq_puts(swap,"Filename\t\t\t\tType\t\tSize\tUsed\tPriority\n");
		return 0;
	}

	file = ptr->swap_file;
	len = seq_path(swap, &file->f_path, " \t\n\\");
	seq_printf(swap, "%*s%s\t%u\t%u\t%d\n",
			len < 40 ? 40 - len : 1, " ",
			S_ISBLK(file->f_path.dentry->d_inode->i_mode) ?
				"partition" : "file\t",
			ptr->pages << (PAGE_SHIFT - 10),
			ptr->inuse_pages << (PAGE_SHIFT - 10),
			ptr->prio);
	return 0;
}

static const struct seq_operations swaps_op = {
	.start =	swap_start,
	.next =		swap_next,
	.stop =		swap_stop,
	.show =		swap_show
};

static int swaps_open(struct inode *inode, struct file *file)
{
	return seq_open(file, &swaps_op);
}

static const struct file_operations proc_swaps_operations = {
	.open		= swaps_open,
	.read		= seq_read,
	.llseek		= seq_lseek,
	.release	= seq_release,
};

static int __init procswaps_init(void)
{
	proc_create("swaps", 0, NULL, &proc_swaps_operations);
	return 0;
}
__initcall(procswaps_init);
#endif /* CONFIG_PROC_FS */

#ifdef MAX_SWAPFILES_CHECK
static int __init max_swapfiles_check(void)
{
	MAX_SWAPFILES_CHECK();
	return 0;
}
late_initcall(max_swapfiles_check);
#endif

/*
 * Written 01/25/92 by Simmule Turner, heavily changed by Linus.
 *
 * The swapon system call
 */
SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
{
	struct swap_info_struct * p;
	char *name = NULL;
	struct block_device *bdev = NULL;
	struct file *swap_file = NULL;
	struct address_space *mapping;
	unsigned int type;
	int i, prev;
	int error;
	union swap_header *swap_header = NULL;
	unsigned int nr_good_pages = 0;
	int nr_extents = 0;
	sector_t span;
	unsigned long maxpages = 1;
	unsigned long swapfilepages;
	unsigned short *swap_map = NULL;
	struct page *page = NULL;
	struct inode *inode = NULL;
	int did_down = 0;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;
	spin_lock(&swap_lock);
	p = swap_info;
	for (type = 0 ; type < nr_swapfiles ; type++,p++)
		if (!(p->flags & SWP_USED))
			break;
	error = -EPERM;
	if (type >= MAX_SWAPFILES) {
		spin_unlock(&swap_lock);
		goto out;
	}
	if (type >= nr_swapfiles)
		nr_swapfiles = type+1;
	memset(p, 0, sizeof(*p));
	INIT_LIST_HEAD(&p->extent_list);
	p->flags = SWP_USED;
	p->next = -1;
	spin_unlock(&swap_lock);
	name = getname(specialfile);
	error = PTR_ERR(name);
	if (IS_ERR(name)) {
		name = NULL;
		goto bad_swap_2;
	}
	swap_file = filp_open(name, O_RDWR|O_LARGEFILE, 0);
	error = PTR_ERR(swap_file);
	if (IS_ERR(swap_file)) {
		swap_file = NULL;
		goto bad_swap_2;
	}

	p->swap_file = swap_file;
	mapping = swap_file->f_mapping;
	inode = mapping->host;

	error = -EBUSY;
	for (i = 0; i < nr_swapfiles; i++) {
		struct swap_info_struct *q = &swap_info[i];

		if (i == type || !q->swap_file)
			continue;
		if (mapping == q->swap_file->f_mapping)
			goto bad_swap;
	}

	error = -EINVAL;
	if (S_ISBLK(inode->i_mode)) {
		bdev = I_BDEV(inode);
		error = bd_claim(bdev, sys_swapon);
		if (error < 0) {
			bdev = NULL;
			error = -EINVAL;
			goto bad_swap;
		}
		p->old_block_size = block_size(bdev);
		error = set_blocksize(bdev, PAGE_SIZE);
		if (error < 0)
			goto bad_swap;
		p->bdev = bdev;
	} else if (S_ISREG(inode->i_mode)) {
		p->bdev = inode->i_sb->s_bdev;
		mutex_lock(&inode->i_mutex);
		did_down = 1;
		if (IS_SWAPFILE(inode)) {
			error = -EBUSY;
			goto bad_swap;
		}
	} else {
		goto bad_swap;
	}

	swapfilepages = i_size_read(inode) >> PAGE_SHIFT;

	/*
	 * Read the swap header.
	 */
	if (!mapping->a_ops->readpage) {
		error = -EINVAL;
		goto bad_swap;
	}
	page = read_mapping_page(mapping, 0, swap_file);
	if (IS_ERR(page)) {
		error = PTR_ERR(page);
		goto bad_swap;
	}
	swap_header = kmap(page);

	if (memcmp("SWAPSPACE2", swap_header->magic.magic, 10)) {
		printk(KERN_ERR "Unable to find swap-space signature\n");
		error = -EINVAL;
		goto bad_swap;
	}

	/* swap partition endianess hack... */
	if (swab32(swap_header->info.version) == 1) {
		swab32s(&swap_header->info.version);
		swab32s(&swap_header->info.last_page);
		swab32s(&swap_header->info.nr_badpages);
		for (i = 0; i < swap_header->info.nr_badpages; i++)
			swab32s(&swap_header->info.badpages[i]);
	}
	/* Check the swap header's sub-version */
	if (swap_header->info.version != 1) {
		printk(KERN_WARNING
		       "Unable to handle swap header version %d\n",
		       swap_header->info.version);
		error = -EINVAL;
		goto bad_swap;
	}

	p->lowest_bit  = 1;
	p->cluster_next = 1;

	/*
	 * Find out how many pages are allowed for a single swap
	 * device. There are two limiting factors: 1) the number of
	 * bits for the swap offset in the swp_entry_t type and
	 * 2) the number of bits in the a swap pte as defined by
	 * the different architectures. In order to find the
	 * largest possible bit mask a swap entry with swap type 0
	 * and swap offset ~0UL is created, encoded to a swap pte,
	 * decoded to a swp_entry_t again and finally the swap
	 * offset is extracted. This will mask all the bits from
	 * the initial ~0UL mask that can't be encoded in either
	 * the swp_entry_t or the architecture definition of a
	 * swap pte.
	 */
	maxpages = swp_offset(pte_to_swp_entry(
			swp_entry_to_pte(swp_entry(0, ~0UL)))) - 1;
	if (maxpages > swap_header->info.last_page)
		maxpages = swap_header->info.last_page;
	p->highest_bit = maxpages - 1;

	error = -EINVAL;
	if (!maxpages)
		goto bad_swap;
	if (swapfilepages && maxpages > swapfilepages) {
		printk(KERN_WARNING
		       "Swap area shorter than signature indicates\n");
		goto bad_swap;
	}
	if (swap_header->info.nr_badpages && S_ISREG(inode->i_mode))
		goto bad_swap;
	if (swap_header->info.nr_badpages > MAX_SWAP_BADPAGES)
		goto bad_swap;

	/* OK, set up the swap map and apply the bad block list */
	swap_map = vmalloc(maxpages * sizeof(short));
	if (!swap_map) {
		error = -ENOMEM;
		goto bad_swap;
	}

	memset(swap_map, 0, maxpages * sizeof(short));
	for (i = 0; i < swap_header->info.nr_badpages; i++) {
		int page_nr = swap_header->info.badpages[i];
		if (page_nr <= 0 || page_nr >= swap_header->info.last_page) {
			error = -EINVAL;
			goto bad_swap;
		}
		swap_map[page_nr] = SWAP_MAP_BAD;
	}

	error = swap_cgroup_swapon(type, maxpages);
	if (error)
		goto bad_swap;

	nr_good_pages = swap_header->info.last_page -
			swap_header->info.nr_badpages -
			1 /* header page */;

	if (nr_good_pages) {
		swap_map[0] = SWAP_MAP_BAD;
		p->max = maxpages;
		p->pages = nr_good_pages;
		nr_extents = setup_swap_extents(p, &span);
		if (nr_extents < 0) {
			error = nr_extents;
			goto bad_swap;
		}
		nr_good_pages = p->pages;
	}
	if (!nr_good_pages) {
		printk(KERN_WARNING "Empty swap-file\n");
		error = -EINVAL;
		goto bad_swap;
	}

	if (blk_queue_nonrot(bdev_get_queue(p->bdev))) {
		p->flags |= SWP_SOLIDSTATE;
		p->cluster_next = 1 + (random32() % p->highest_bit);
	}
	if (discard_swap(p) == 0)
		p->flags |= SWP_DISCARDABLE;

	mutex_lock(&swapon_mutex);
	spin_lock(&swap_lock);
	if (swap_flags & SWAP_FLAG_PREFER)
		p->prio =
		  (swap_flags & SWAP_FLAG_PRIO_MASK) >> SWAP_FLAG_PRIO_SHIFT;
	else
		p->prio = --least_priority;
	p->swap_map = swap_map;
	p->flags |= SWP_WRITEOK;
	nr_swap_pages += nr_good_pages;
	total_swap_pages += nr_good_pages;

	printk(KERN_INFO "Adding %uk swap on %s.  "
			"Priority:%d extents:%d across:%lluk %s%s\n",
		nr_good_pages<<(PAGE_SHIFT-10), name, p->prio,
		nr_extents, (unsigned long long)span<<(PAGE_SHIFT-10),
		(p->flags & SWP_SOLIDSTATE) ? "SS" : "",
		(p->flags & SWP_DISCARDABLE) ? "D" : "");

	/* insert swap space into swap_list: */
	prev = -1;
	for (i = swap_list.head; i >= 0; i = swap_info[i].next) {
		if (p->prio >= swap_info[i].prio) {
			break;
		}
		prev = i;
	}
	p->next = i;
	if (prev < 0) {
		swap_list.head = swap_list.next = p - swap_info;
	} else {
		swap_info[prev].next = p - swap_info;
	}
	spin_unlock(&swap_lock);
	mutex_unlock(&swapon_mutex);
	error = 0;
	goto out;
bad_swap:
	if (bdev) {
		set_blocksize(bdev, p->old_block_size);
		bd_release(bdev);
	}
	destroy_swap_extents(p);
	swap_cgroup_swapoff(type);
bad_swap_2:
	spin_lock(&swap_lock);
	p->swap_file = NULL;
	p->flags = 0;
	spin_unlock(&swap_lock);
	vfree(swap_map);
	if (swap_file)
		filp_close(swap_file, NULL);
out:
	if (page && !IS_ERR(page)) {
		kunmap(page);
		page_cache_release(page);
	}
	if (name)
		putname(name);
	if (did_down) {
		if (!error)
			inode->i_flags |= S_SWAPFILE;
		mutex_unlock(&inode->i_mutex);
	}
	return error;
}

void si_swapinfo(struct sysinfo *val)
{
	unsigned int i;
	unsigned long nr_to_be_unused = 0;

	spin_lock(&swap_lock);
	for (i = 0; i < nr_swapfiles; i++) {
		if (!(swap_info[i].flags & SWP_USED) ||
		     (swap_info[i].flags & SWP_WRITEOK))
			continue;
		nr_to_be_unused += swap_info[i].inuse_pages;
	}
	val->freeswap = nr_swap_pages + nr_to_be_unused;
	val->totalswap = total_swap_pages + nr_to_be_unused;
	spin_unlock(&swap_lock);
}

/*
 * Verify that a swap entry is valid and increment its swap map count.
 *
 * Note: if swap_map[] reaches SWAP_MAP_MAX the entries are treated as
 * "permanent", but will be reclaimed by the next swapoff.
 */
int swap_duplicate(swp_entry_t entry)
{
	struct swap_info_struct * p;
	unsigned long offset, type;
	int result = 0;

	if (is_migration_entry(entry))
		return 1;

	type = swp_type(entry);
	if (type >= nr_swapfiles)
		goto bad_file;
	p = type + swap_info;
	offset = swp_offset(entry);

	spin_lock(&swap_lock);
	if (offset < p->max && p->swap_map[offset]) {
		if (p->swap_map[offset] < SWAP_MAP_MAX - 1) {
			p->swap_map[offset]++;
			result = 1;
		} else if (p->swap_map[offset] <= SWAP_MAP_MAX) {
			if (swap_overflow++ < 5)
				printk(KERN_WARNING "swap_dup: swap entry overflow\n");
			p->swap_map[offset] = SWAP_MAP_MAX;
			result = 1;
		}
	}
	spin_unlock(&swap_lock);
out:
	return result;

bad_file:
	printk(KERN_ERR "swap_dup: %s%08lx\n", Bad_file, entry.val);
	goto out;
}

struct swap_info_struct *
get_swap_info_struct(unsigned type)
{
	return &swap_info[type];
}

/*
 * swap_lock prevents swap_map being freed. Don't grab an extra
 * reference on the swaphandle, it doesn't matter if it becomes unused.
 */
int valid_swaphandles(swp_entry_t entry, unsigned long *offset)
{
	struct swap_info_struct *si;
	int our_page_cluster = page_cluster;
	pgoff_t target, toff;
	pgoff_t base, end;
	int nr_pages = 0;

	if (!our_page_cluster)	/* no readahead */
		return 0;

	si = &swap_info[swp_type(entry)];
	target = swp_offset(entry);
	base = (target >> our_page_cluster) << our_page_cluster;
	end = base + (1 << our_page_cluster);
	if (!base)		/* first page is swap header */
		base++;

	spin_lock(&swap_lock);
	if (end > si->max)	/* don't go beyond end of map */
		end = si->max;

	/* Count contiguous allocated slots above our target */
	for (toff = target; ++toff < end; nr_pages++) {
		/* Don't read in free or bad pages */
		if (!si->swap_map[toff])
			break;
		if (si->swap_map[toff] == SWAP_MAP_BAD)
			break;
	}
	/* Count contiguous allocated slots below our target */
	for (toff = target; --toff >= base; nr_pages++) {
		/* Don't read in free or bad pages */
		if (!si->swap_map[toff])
			break;
		if (si->swap_map[toff] == SWAP_MAP_BAD)
			break;
	}
	spin_unlock(&swap_lock);

	/*
	 * Indicate starting offset, and return number of pages to get:
	 * if only 1, say 0, since there's then no readahead to be done.
	 */
	*offset = ++toff;
	return nr_pages? ++nr_pages: 0;
}