swapfile.c

最新最稳定的Linux内存管理模块源代码

				prev_mm = mm;

				cond_resched();

				swcount = *swap_map;
				if (swcount <= 1)
					;
				else if (mm == &init_mm) {
					set_start_mm = 1;
					shmem = shmem_unuse(entry, page);
				} else
					retval = unuse_mm(mm, entry, page);
				if (set_start_mm && *swap_map < swcount) {
					mmput(new_start_mm);
					atomic_inc(&mm->mm_users);
					new_start_mm = mm;
					set_start_mm = 0;
				}
				spin_lock(&mmlist_lock);
			}
			spin_unlock(&mmlist_lock);
			mmput(prev_mm);
			mmput(start_mm);
			start_mm = new_start_mm;
		}
		if (shmem) {
			/* page has already been unlocked and released */
			if (shmem > 0)
				continue;
			retval = shmem;
			break;
		}
		if (retval) {
			unlock_page(page);
			page_cache_release(page);
			break;
		}

		/*
		 * How could swap count reach 0x7fff when the maximum
		 * pid is 0x7fff, and there's no way to repeat a swap
		 * page within an mm (except in shmem, where it's the
		 * shared object which takes the reference count)?
		 * We believe SWAP_MAP_MAX cannot occur in Linux 2.4.
		 *
		 * If that's wrong, then we should worry more about
		 * exit_mmap() and do_munmap() cases described above:
		 * we might be resetting SWAP_MAP_MAX too early here.
		 * We know "Undead"s can happen, they're okay, so don't
		 * report them; but do report if we reset SWAP_MAP_MAX.
		 */
		if (*swap_map == SWAP_MAP_MAX) {
			spin_lock(&swap_lock);
			*swap_map = 1;
			spin_unlock(&swap_lock);
			reset_overflow = 1;
		}

		/*
		 * If a reference remains (rare), we would like to leave
		 * the page in the swap cache; but try_to_unmap could
		 * then re-duplicate the entry once we drop page lock,
		 * so we might loop indefinitely; also, that page could
		 * not be swapped out to other storage meanwhile.  So:
		 * delete from cache even if there's another reference,
		 * after ensuring that the data has been saved to disk -
		 * since if the reference remains (rarer), it will be
		 * read from disk into another page.  Splitting into two
		 * pages would be incorrect if swap supported "shared
		 * private" pages, but they are handled by tmpfs files.
		 */
		if ((*swap_map > 1) && PageDirty(page) && PageSwapCache(page)) {
			struct writeback_control wbc = {
				.sync_mode = WB_SYNC_NONE,
			};

			swap_writepage(page, &wbc);
			lock_page(page);
			wait_on_page_writeback(page);
		}

		/*
		 * It is conceivable that a racing task removed this page from
		 * swap cache just before we acquired the page lock at the top,
		 * or while we dropped it in unuse_mm().  The page might even
		 * be back in swap cache on another swap area: that we must not
		 * delete, since it may not have been written out to swap yet.
		 */
		if (PageSwapCache(page) &&
		    likely(page_private(page) == entry.val))
			delete_from_swap_cache(page);

		/*
		 * So we could skip searching mms once swap count went
		 * to 1, we did not mark any present ptes as dirty: must
		 * mark page dirty so shrink_page_list will preserve it.
		 */
		SetPageDirty(page);
		unlock_page(page);
		page_cache_release(page);

		/*
		 * Make sure that we aren't completely killing
		 * interactive performance.
		 */
		cond_resched();
	}

	mmput(start_mm);
	if (reset_overflow) {
		printk(KERN_WARNING "swapoff: cleared swap entry overflow\n");
		swap_overflow = 0;
	}
	return retval;
}

/*
 * After a successful try_to_unuse, if no swap is now in use, we know
 * we can empty the mmlist.  swap_lock must be held on entry and exit.
 * Note that mmlist_lock nests inside swap_lock, and an mm must be
 * added to the mmlist just after page_duplicate - before would be racy.
 */
static void drain_mmlist(void)
{
	struct list_head *p, *next;
	unsigned int i;

	for (i = 0; i < nr_swapfiles; i++)
		if (swap_info[i].inuse_pages)
			return;
	spin_lock(&mmlist_lock);
	list_for_each_safe(p, next, &init_mm.mmlist)
		list_del_init(p);
	spin_unlock(&mmlist_lock);
}

/*
 * Use this swapdev's extent info to locate the (PAGE_SIZE) block which
 * corresponds to page offset `offset'.
 */
sector_t map_swap_page(struct swap_info_struct *sis, pgoff_t offset)
{
	struct swap_extent *se = sis->curr_swap_extent;
	struct swap_extent *start_se = se;

	for ( ; ; ) {
		struct list_head *lh;

		if (se->start_page <= offset &&
				offset < (se->start_page + se->nr_pages)) {
			return se->start_block + (offset - se->start_page);
		}
		lh = se->list.next;
		if (lh == &sis->extent_list)
			lh = lh->next;
		se = list_entry(lh, struct swap_extent, list);
		sis->curr_swap_extent = se;
		BUG_ON(se == start_se);		/* It *must* be present */
	}
}

#ifdef CONFIG_HIBERNATION
/*
 * Get the (PAGE_SIZE) block corresponding to given offset on the swapdev
 * corresponding to given index in swap_info (swap type).
 */
sector_t swapdev_block(int swap_type, pgoff_t offset)
{
	struct swap_info_struct *sis;

	if (swap_type >= nr_swapfiles)
		return 0;

	sis = swap_info + swap_type;
	return (sis->flags & SWP_WRITEOK) ? map_swap_page(sis, offset) : 0;
}
#endif /* CONFIG_HIBERNATION */

/*
 * Free all of a swapdev's extent information
 */
static void destroy_swap_extents(struct swap_info_struct *sis)
{
	while (!list_empty(&sis->extent_list)) {
		struct swap_extent *se;

		se = list_entry(sis->extent_list.next,
				struct swap_extent, list);
		list_del(&se->list);
		kfree(se);
	}
}

/*
 * Add a block range (and the corresponding page range) into this swapdev's
 * extent list.  The extent list is kept sorted in page order.
 *
 * This function rather assumes that it is called in ascending page order.
 */
static int
add_swap_extent(struct swap_info_struct *sis, unsigned long start_page,
		unsigned long nr_pages, sector_t start_block)
{
	struct swap_extent *se;
	struct swap_extent *new_se;
	struct list_head *lh;

	lh = sis->extent_list.prev;	/* The highest page extent */
	if (lh != &sis->extent_list) {
		se = list_entry(lh, struct swap_extent, list);
		BUG_ON(se->start_page + se->nr_pages != start_page);
		if (se->start_block + se->nr_pages == start_block) {
			/* Merge it */
			se->nr_pages += nr_pages;
			return 0;
		}
	}

	/*
	 * No merge.  Insert a new extent, preserving ordering.
	 */
	new_se = kmalloc(sizeof(*se), GFP_KERNEL);
	if (new_se == NULL)
		return -ENOMEM;
	new_se->start_page = start_page;
	new_se->nr_pages = nr_pages;
	new_se->start_block = start_block;

	list_add_tail(&new_se->list, &sis->extent_list);
	return 1;
}

/*
 * A `swap extent' is a simple thing which maps a contiguous range of pages
 * onto a contiguous range of disk blocks.  An ordered list of swap extents
 * is built at swapon time and is then used at swap_writepage/swap_readpage
 * time for locating where on disk a page belongs.
 *
 * If the swapfile is an S_ISBLK block device, a single extent is installed.
 * This is done so that the main operating code can treat S_ISBLK and S_ISREG
 * swap files identically.
 *
 * Whether the swapdev is an S_ISREG file or an S_ISBLK blockdev, the swap
 * extent list operates in PAGE_SIZE disk blocks.  Both S_ISREG and S_ISBLK
 * swapfiles are handled *identically* after swapon time.
 *
 * For S_ISREG swapfiles, setup_swap_extents() will walk all the file's blocks
 * and will parse them into an ordered extent list, in PAGE_SIZE chunks.  If
 * some stray blocks are found which do not fall within the PAGE_SIZE alignment
 * requirements, they are simply tossed out - we will never use those blocks
 * for swapping.
 *
 * For S_ISREG swapfiles we set S_SWAPFILE across the life of the swapon.  This
 * prevents root from shooting her foot off by ftruncating an in-use swapfile,
 * which will scribble on the fs.
 *
 * The amount of disk space which a single swap extent represents varies.
 * Typically it is in the 1-4 megabyte range.  So we can have hundreds of
 * extents in the list.  To avoid much list walking, we cache the previous
 * search location in `curr_swap_extent', and start new searches from there.
 * This is extremely effective.  The average number of iterations in
 * map_swap_page() has been measured at about 0.3 per page.  - akpm.
 */
static int setup_swap_extents(struct swap_info_struct *sis, sector_t *span)
{
	struct inode *inode;
	unsigned blocks_per_page;
	unsigned long page_no;
	unsigned blkbits;
	sector_t probe_block;
	sector_t last_block;
	sector_t lowest_block = -1;
	sector_t highest_block = 0;
	int nr_extents = 0;
	int ret;

	inode = sis->swap_file->f_mapping->host;
	if (S_ISBLK(inode->i_mode)) {
		ret = add_swap_extent(sis, 0, sis->max, 0);
		*span = sis->pages;
		goto done;
	}

	blkbits = inode->i_blkbits;
	blocks_per_page = PAGE_SIZE >> blkbits;

	/*
	 * Map all the blocks into the extent list.  This code doesn't try
	 * to be very smart.
	 */
	probe_block = 0;
	page_no = 0;
	last_block = i_size_read(inode) >> blkbits;
	while ((probe_block + blocks_per_page) <= last_block &&
			page_no < sis->max) {
		unsigned block_in_page;
		sector_t first_block;

		first_block = bmap(inode, probe_block);
		if (first_block == 0)
			goto bad_bmap;

		/*
		 * It must be PAGE_SIZE aligned on-disk
		 */
		if (first_block & (blocks_per_page - 1)) {
			probe_block++;
			goto reprobe;
		}

		for (block_in_page = 1; block_in_page < blocks_per_page;
					block_in_page++) {
			sector_t block;

			block = bmap(inode, probe_block + block_in_page);
			if (block == 0)
				goto bad_bmap;
			if (block != first_block + block_in_page) {
				/* Discontiguity */
				probe_block++;
				goto reprobe;
			}
		}

		first_block >>= (PAGE_SHIFT - blkbits);
		if (page_no) {	/* exclude the header page */
			if (first_block < lowest_block)
				lowest_block = first_block;
			if (first_block > highest_block)
				highest_block = first_block;
		}

		/*
		 * We found a PAGE_SIZE-length, PAGE_SIZE-aligned run of blocks
		 */
		ret = add_swap_extent(sis, page_no, 1, first_block);
		if (ret < 0)
			goto out;
		nr_extents += ret;
		page_no++;
		probe_block += blocks_per_page;
reprobe:
		continue;
	}
	ret = nr_extents;
	*span = 1 + highest_block - lowest_block;
	if (page_no == 0)
		page_no = 1;	/* force Empty message */
	sis->max = page_no;
	sis->pages = page_no - 1;
	sis->highest_bit = page_no - 1;
done:
	sis->curr_swap_extent = list_entry(sis->extent_list.prev,
					struct swap_extent, list);
	goto out;
bad_bmap:
	printk(KERN_ERR "swapon: swapfile has holes\n");
	ret = -EINVAL;
out:
	return ret;
}

SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
{
	struct swap_info_struct * p = NULL;
	unsigned short *swap_map;
	struct file *swap_file, *victim;
	struct address_space *mapping;
	struct inode *inode;
	char * pathname;
	int i, type, prev;
	int err;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

	pathname = getname(specialfile);
	err = PTR_ERR(pathname);
	if (IS_ERR(pathname))
		goto out;

	victim = filp_open(pathname, O_RDWR|O_LARGEFILE, 0);
	putname(pathname);
	err = PTR_ERR(victim);
	if (IS_ERR(victim))
		goto out;

	mapping = victim->f_mapping;
	prev = -1;
	spin_lock(&swap_lock);
	for (type = swap_list.head; type >= 0; type = swap_info[type].next) {
		p = swap_info + type;
		if (p->flags & SWP_WRITEOK) {
			if (p->swap_file->f_mapping == mapping)
				break;
		}
		prev = type;
	}
	if (type < 0) {
		err = -EINVAL;
		spin_unlock(&swap_lock);
		goto out_dput;
	}
	if (!security_vm_enough_memory(p->pages))
		vm_unacct_memory(p->pages);
	else {
		err = -ENOMEM;
		spin_unlock(&swap_lock);
		goto out_dput;
	}
	if (prev < 0) {
		swap_list.head = p->next;
	} else {
		swap_info[prev].next = p->next;
	}
	if (type == swap_list.next) {
		/* just pick something that's safe... */
		swap_list.next = swap_list.head;
	}
	if (p->prio < 0) {
		for (i = p->next; i >= 0; i = swap_info[i].next)
			swap_info[i].prio = p->prio--;
		least_priority++;
	}
	nr_swap_pages -= p->pages;
	total_swap_pages -= p->pages;
	p->flags &= ~SWP_WRITEOK;
	spin_unlock(&swap_lock);

	current->flags |= PF_SWAPOFF;
	err = try_to_unuse(type);
	current->flags &= ~PF_SWAPOFF;

	if (err) {
		/* re-insert swap space back into swap_list */
		spin_lock(&swap_lock);
		if (p->prio < 0)
			p->prio = --least_priority;
		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;
		nr_swap_pages += p->pages;
		total_swap_pages += p->pages;
		p->flags |= SWP_WRITEOK;
		spin_unlock(&swap_lock);
		goto out_dput;
	}

	/* wait for any unplug function to finish */
	down_write(&swap_unplug_sem);
	up_write(&swap_unplug_sem);

	destroy_swap_extents(p);
	mutex_lock(&swapon_mutex);
	spin_lock(&swap_lock);
	drain_mmlist();

	/* wait for anyone still in scan_swap_map */
	p->highest_bit = 0;		/* cuts scans short */
	while (p->flags >= SWP_SCANNING) {
		spin_unlock(&swap_lock);
		schedule_timeout_uninterruptible(1);
		spin_lock(&swap_lock);
	}

	swap_file = p->swap_file;
	p->swap_file = NULL;
	p->max = 0;
	swap_map = p->swap_map;
	p->swap_map = NULL;
	p->flags = 0;
	spin_unlock(&swap_lock);
	mutex_unlock(&swapon_mutex);
	vfree(swap_map);
	/* Destroy swap account informatin */
	swap_cgroup_swapoff(type);

	inode = mapping->host;
	if (S_ISBLK(inode->i_mode)) {
		struct block_device *bdev = I_BDEV(inode);
		set_blocksize(bdev, p->old_block_size);
		bd_release(bdev);
	} else {
		mutex_lock(&inode->i_mutex);
		inode->i_flags &= ~S_SWAPFILE;
		mutex_unlock(&inode->i_mutex);
	}
	filp_close(swap_file, NULL);
	err = 0;

out_dput:
	filp_close(victim, NULL);
out:
	return err;
}

#ifdef CONFIG_PROC_FS
/* iterator */
static void *swap_start(struct seq_file *swap, loff_t *pos)
{
	struct swap_info_struct *ptr = swap_info;
	int i;