swapfile.c

linux下内存管理源代码。。。精、简、强!

	if (!page)
		return -ENOMEM;

	len += sprintf(buf, "Filename\t\t\tType\t\tSize\tUsed\tPriority\n");
	for (i = 0 ; i < nr_swapfiles ; i++, ptr++) {
		if (ptr->flags & SWP_USED) {
			char * path = d_path(ptr->swap_file, ptr->swap_vfsmnt,
						page, PAGE_SIZE);

			len += sprintf(buf + len, "%-31s ", path);

			if (!ptr->swap_device)
				len += sprintf(buf + len, "file\t\t");
			else
				len += sprintf(buf + len, "partition\t");

			usedswap = 0;
			for (j = 0; j < ptr->max; ++j)
				switch (ptr->swap_map[j]) {
					case SWAP_MAP_BAD:
					case 0:
						continue;
					default:
						usedswap++;
				}
			len += sprintf(buf + len, "%d\t%d\t%d\n", ptr->pages << (PAGE_SHIFT - 10), 
				usedswap << (PAGE_SHIFT - 10), ptr->prio);
		}
	}
	free_page((unsigned long) page);
	return len;
}

int is_swap_partition(kdev_t dev) {
	struct swap_info_struct *ptr = swap_info;
	int i;

	for (i = 0 ; i < nr_swapfiles ; i++, ptr++) {
		if (ptr->flags & SWP_USED)
			if (ptr->swap_device == dev)
				return 1;
	}
	return 0;
}

/*
 * Written 01/25/92 by Simmule Turner, heavily changed by Linus.
 *
 * The swapon system call
 */
asmlinkage long sys_swapon(const char * specialfile, int swap_flags)
{
	struct swap_info_struct * p;
	struct nameidata nd;
	struct inode * swap_inode;
	unsigned int type;
	int i, j, prev;
	int error;
	static int least_priority = 0;
	union swap_header *swap_header = 0;
	int swap_header_version;
	int nr_good_pages = 0;
	unsigned long maxpages;
	int swapfilesize;
	struct block_device *bdev = NULL;
	
	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;
	lock_kernel();
	p = swap_info;
	for (type = 0 ; type < nr_swapfiles ; type++,p++)
		if (!(p->flags & SWP_USED))
			break;
	error = -EPERM;
	if (type >= MAX_SWAPFILES)
		goto out;
	if (type >= nr_swapfiles)
		nr_swapfiles = type+1;
	p->flags = SWP_USED;
	p->swap_file = NULL;
	p->swap_vfsmnt = NULL;
	p->swap_device = 0;
	p->swap_map = NULL;
	p->lowest_bit = 0;
	p->highest_bit = 0;
	p->cluster_nr = 0;
	p->sdev_lock = SPIN_LOCK_UNLOCKED;
	p->max = 1;
	p->next = -1;
	if (swap_flags & SWAP_FLAG_PREFER) {
		p->prio =
		  (swap_flags & SWAP_FLAG_PRIO_MASK)>>SWAP_FLAG_PRIO_SHIFT;
	} else {
		p->prio = --least_priority;
	}
	error = user_path_walk(specialfile, &nd);
	if (error)
		goto bad_swap_2;

	p->swap_file = nd.dentry;
	p->swap_vfsmnt = nd.mnt;
	swap_inode = nd.dentry->d_inode;
	error = -EINVAL;

	if (S_ISBLK(swap_inode->i_mode)) {
		kdev_t dev = swap_inode->i_rdev;
		struct block_device_operations *bdops;

		p->swap_device = dev;
		set_blocksize(dev, PAGE_SIZE);
		
		bdev = swap_inode->i_bdev;
		bdops = devfs_get_ops(devfs_get_handle_from_inode(swap_inode));
		if (bdops) bdev->bd_op = bdops;

		error = blkdev_get(bdev, FMODE_READ|FMODE_WRITE, 0, BDEV_SWAP);
		if (error)
			goto bad_swap_2;
		set_blocksize(dev, PAGE_SIZE);
		error = -ENODEV;
		if (!dev || (blk_size[MAJOR(dev)] &&
		     !blk_size[MAJOR(dev)][MINOR(dev)]))
			goto bad_swap;
		error = -EBUSY;
		for (i = 0 ; i < nr_swapfiles ; i++) {
			if (i == type)
				continue;
			if (dev == swap_info[i].swap_device)
				goto bad_swap;
		}
		swapfilesize = 0;
		if (blk_size[MAJOR(dev)])
			swapfilesize = blk_size[MAJOR(dev)][MINOR(dev)]
				>> (PAGE_SHIFT - 10);
	} else if (S_ISREG(swap_inode->i_mode)) {
		error = -EBUSY;
		for (i = 0 ; i < nr_swapfiles ; i++) {
			if (i == type || !swap_info[i].swap_file)
				continue;
			if (swap_inode == swap_info[i].swap_file->d_inode)
				goto bad_swap;
		}
		swapfilesize = swap_inode->i_size >> PAGE_SHIFT;
	} else
		goto bad_swap;

	swap_header = (void *) __get_free_page(GFP_USER);
	if (!swap_header) {
		printk("Unable to start swapping: out of memory :-)\n");
		error = -ENOMEM;
		goto bad_swap;
	}

	lock_page(virt_to_page(swap_header));
	rw_swap_page_nolock(READ, SWP_ENTRY(type,0), (char *) swap_header, 1);

	if (!memcmp("SWAP-SPACE",swap_header->magic.magic,10))
		swap_header_version = 1;
	else if (!memcmp("SWAPSPACE2",swap_header->magic.magic,10))
		swap_header_version = 2;
	else {
		printk("Unable to find swap-space signature\n");
		error = -EINVAL;
		goto bad_swap;
	}
	
	switch (swap_header_version) {
	case 1:
		memset(((char *) swap_header)+PAGE_SIZE-10,0,10);
		j = 0;
		p->lowest_bit = 0;
		p->highest_bit = 0;
		for (i = 1 ; i < 8*PAGE_SIZE ; i++) {
			if (test_bit(i,(char *) swap_header)) {
				if (!p->lowest_bit)
					p->lowest_bit = i;
				p->highest_bit = i;
				p->max = i+1;
				j++;
			}
		}
		nr_good_pages = j;
		p->swap_map = vmalloc(p->max * sizeof(short));
		if (!p->swap_map) {
			error = -ENOMEM;		
			goto bad_swap;
		}
		for (i = 1 ; i < p->max ; i++) {
			if (test_bit(i,(char *) swap_header))
				p->swap_map[i] = 0;
			else
				p->swap_map[i] = SWAP_MAP_BAD;
		}
		break;

	case 2:
		/* Check the swap header's sub-version and the size of
                   the swap file and bad block lists */
		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->highest_bit = swap_header->info.last_page - 1;
		p->max	       = swap_header->info.last_page;

		maxpages = SWP_OFFSET(SWP_ENTRY(0,~0UL));
		if (p->max >= maxpages)
			p->max = maxpages-1;

		error = -EINVAL;
		if (swap_header->info.nr_badpages > MAX_SWAP_BADPAGES)
			goto bad_swap;
		
		/* OK, set up the swap map and apply the bad block list */
		if (!(p->swap_map = vmalloc (p->max * sizeof(short)))) {
			error = -ENOMEM;
			goto bad_swap;
		}

		error = 0;
		memset(p->swap_map, 0, p->max * sizeof(short));
		for (i=0; i<swap_header->info.nr_badpages; i++) {
			int page = swap_header->info.badpages[i];
			if (page <= 0 || page >= swap_header->info.last_page)
				error = -EINVAL;
			else
				p->swap_map[page] = SWAP_MAP_BAD;
		}
		nr_good_pages = swap_header->info.last_page -
				swap_header->info.nr_badpages -
				1 /* header page */;
		if (error) 
			goto bad_swap;
	}
	
	if (swapfilesize && p->max > swapfilesize) {
		printk(KERN_WARNING
		       "Swap area shorter than signature indicates\n");
		error = -EINVAL;
		goto bad_swap;
	}
	if (!nr_good_pages) {
		printk(KERN_WARNING "Empty swap-file\n");
		error = -EINVAL;
		goto bad_swap;
	}
	p->swap_map[0] = SWAP_MAP_BAD;
	p->flags = SWP_WRITEOK;
	p->pages = nr_good_pages;
	swap_list_lock();
	nr_swap_pages += nr_good_pages;
	printk(KERN_INFO "Adding Swap: %dk swap-space (priority %d)\n",
	       nr_good_pages<<(PAGE_SHIFT-10), p->prio);

	/* 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;
	}
	swap_list_unlock();
	error = 0;
	goto out;
bad_swap:
	if (bdev)
		blkdev_put(bdev, BDEV_SWAP);
bad_swap_2:
	if (p->swap_map)
		vfree(p->swap_map);
	nd.mnt = p->swap_vfsmnt;
	nd.dentry = p->swap_file;
	p->swap_device = 0;
	p->swap_file = NULL;
	p->swap_vfsmnt = NULL;
	p->swap_map = NULL;
	p->flags = 0;
	if (!(swap_flags & SWAP_FLAG_PREFER))
		++least_priority;
	path_release(&nd);
out:
	if (swap_header)
		free_page((long) swap_header);
	unlock_kernel();
	return error;
}

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

	for (i = 0; i < nr_swapfiles; i++) {
		unsigned int j;
		if ((swap_info[i].flags & SWP_WRITEOK) != SWP_WRITEOK)
			continue;
		for (j = 0; j < swap_info[i].max; ++j) {
			switch (swap_info[i].swap_map[j]) {
				case SWAP_MAP_BAD:
					continue;
				case 0:
					freeswap++;
				default:
					totalswap++;
			}
		}
	}
	val->freeswap = freeswap;
	val->totalswap = totalswap;
	return;
}

/*
 * Verify that a swap entry is valid and increment its swap map count.
 * Kernel_lock is held, which guarantees existance of swap device.
 *
 * 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;

	/* Swap entry 0 is illegal */
	if (!entry.val)
		goto out;
	type = SWP_TYPE(entry);
	if (type >= nr_swapfiles)
		goto bad_file;
	p = type + swap_info;
	offset = SWP_OFFSET(entry);
	if (offset >= p->max)
		goto bad_offset;
	if (!p->swap_map[offset])
		goto bad_unused;
	/*
	 * Entry is valid, so increment the map count.
	 */
	swap_device_lock(p);
	if (p->swap_map[offset] < SWAP_MAP_MAX)
		p->swap_map[offset]++;
	else {
		static int overflow = 0;
		if (overflow++ < 5)
			printk("VM: swap entry overflow\n");
		p->swap_map[offset] = SWAP_MAP_MAX;
	}
	swap_device_unlock(p);
	result = 1;
out:
	return result;

bad_file:
	printk("Bad swap file entry %08lx\n", entry.val);
	goto out;
bad_offset:
	printk("Bad swap offset entry %08lx\n", entry.val);
	goto out;
bad_unused:
	printk("Unused swap offset entry in swap_dup %08lx\n", entry.val);
	goto out;
}

/*
 * Page lock needs to be held in all cases to prevent races with
 * swap file deletion.
 */
int swap_count(struct page *page)
{
	struct swap_info_struct * p;
	unsigned long offset, type;
	swp_entry_t entry;
	int retval = 0;

	entry.val = page->index;
	if (!entry.val)
		goto bad_entry;
	type = SWP_TYPE(entry);
	if (type >= nr_swapfiles)
		goto bad_file;
	p = type + swap_info;
	offset = SWP_OFFSET(entry);
	if (offset >= p->max)
		goto bad_offset;
	if (!p->swap_map[offset])
		goto bad_unused;
	retval = p->swap_map[offset];
out:
	return retval;

bad_entry:
	printk(KERN_ERR "swap_count: null entry!\n");
	goto out;
bad_file:
	printk("Bad swap file entry %08lx\n", entry.val);
	goto out;
bad_offset:
	printk("Bad swap offset entry %08lx\n", entry.val);
	goto out;
bad_unused:
	printk("Unused swap offset entry in swap_count %08lx\n", entry.val);
	goto out;
}

/*
 * Kernel_lock protects against swap device deletion.
 */
void get_swaphandle_info(swp_entry_t entry, unsigned long *offset, 
			kdev_t *dev, struct inode **swapf)
{
	unsigned long type;
	struct swap_info_struct *p;

	type = SWP_TYPE(entry);
	if (type >= nr_swapfiles) {
		printk("Internal error: bad swap-device\n");
		return;
	}

	p = &swap_info[type];
	*offset = SWP_OFFSET(entry);
	if (*offset >= p->max) {
		printk("rw_swap_page: weirdness\n");
		return;
	}
	if (p->swap_map && !p->swap_map[*offset]) {
		printk("VM: Bad swap entry %08lx\n", entry.val);
		return;
	}
	if (!(p->flags & SWP_USED)) {
		printk(KERN_ERR "rw_swap_page: "
			"Trying to swap to unused swap-device\n");
		return;
	}

	if (p->swap_device) {
		*dev = p->swap_device;
	} else if (p->swap_file) {
		*swapf = p->swap_file->d_inode;
	} else {
		printk(KERN_ERR "rw_swap_page: no swap file or device\n");
	}
	return;
}

/*
 * Kernel_lock protects against swap device deletion. Grab an extra
 * reference on the swaphandle so that it dos not become unused.
 */
int valid_swaphandles(swp_entry_t entry, unsigned long *offset)
{
	int ret = 0, i = 1 << page_cluster;
	unsigned long toff;
	struct swap_info_struct *swapdev = SWP_TYPE(entry) + swap_info;

	*offset = SWP_OFFSET(entry);
	toff = *offset = (*offset >> page_cluster) << page_cluster;

	swap_device_lock(swapdev);
	do {
		/* Don't read-ahead past the end of the swap area */
		if (toff >= swapdev->max)
			break;
		/* Don't read in bad or busy pages */
		if (!swapdev->swap_map[toff])
			break;
		if (swapdev->swap_map[toff] == SWAP_MAP_BAD)
			break;
		swapdev->swap_map[toff]++;
		toff++;
		ret++;
	} while (--i);
	swap_device_unlock(swapdev);
	return ret;
}