dm-table.c

linux 内核源代码

	atomic_inc(&dd->count);

	if (!check_device_area(dd, start, len)) {
		DMWARN("device %s too small for target", path);
		dm_put_device(ti, dd);
		return -EINVAL;
	}

	*result = dd;

	return 0;
}

void dm_set_device_limits(struct dm_target *ti, struct block_device *bdev)
{
	struct request_queue *q = bdev_get_queue(bdev);
	struct io_restrictions *rs = &ti->limits;

	/*
	 * Combine the device limits low.
	 *
	 * FIXME: if we move an io_restriction struct
	 *        into q this would just be a call to
	 *        combine_restrictions_low()
	 */
	rs->max_sectors =
		min_not_zero(rs->max_sectors, q->max_sectors);

	/* FIXME: Device-Mapper on top of RAID-0 breaks because DM
	 *        currently doesn't honor MD's merge_bvec_fn routine.
	 *        In this case, we'll force DM to use PAGE_SIZE or
	 *        smaller I/O, just to be safe. A better fix is in the
	 *        works, but add this for the time being so it will at
	 *        least operate correctly.
	 */
	if (q->merge_bvec_fn)
		rs->max_sectors =
			min_not_zero(rs->max_sectors,
				     (unsigned int) (PAGE_SIZE >> 9));

	rs->max_phys_segments =
		min_not_zero(rs->max_phys_segments,
			     q->max_phys_segments);

	rs->max_hw_segments =
		min_not_zero(rs->max_hw_segments, q->max_hw_segments);

	rs->hardsect_size = max(rs->hardsect_size, q->hardsect_size);

	rs->max_segment_size =
		min_not_zero(rs->max_segment_size, q->max_segment_size);

	rs->max_hw_sectors =
		min_not_zero(rs->max_hw_sectors, q->max_hw_sectors);

	rs->seg_boundary_mask =
		min_not_zero(rs->seg_boundary_mask,
			     q->seg_boundary_mask);

	rs->bounce_pfn = min_not_zero(rs->bounce_pfn, q->bounce_pfn);

	rs->no_cluster |= !test_bit(QUEUE_FLAG_CLUSTER, &q->queue_flags);
}
EXPORT_SYMBOL_GPL(dm_set_device_limits);

int dm_get_device(struct dm_target *ti, const char *path, sector_t start,
		  sector_t len, int mode, struct dm_dev **result)
{
	int r = __table_get_device(ti->table, ti, path,
				   start, len, mode, result);

	if (!r)
		dm_set_device_limits(ti, (*result)->bdev);

	return r;
}

/*
 * Decrement a devices use count and remove it if necessary.
 */
void dm_put_device(struct dm_target *ti, struct dm_dev *dd)
{
	if (atomic_dec_and_test(&dd->count)) {
		close_dev(dd, ti->table->md);
		list_del(&dd->list);
		kfree(dd);
	}
}

/*
 * Checks to see if the target joins onto the end of the table.
 */
static int adjoin(struct dm_table *table, struct dm_target *ti)
{
	struct dm_target *prev;

	if (!table->num_targets)
		return !ti->begin;

	prev = &table->targets[table->num_targets - 1];
	return (ti->begin == (prev->begin + prev->len));
}

/*
 * Used to dynamically allocate the arg array.
 */
static char **realloc_argv(unsigned *array_size, char **old_argv)
{
	char **argv;
	unsigned new_size;

	new_size = *array_size ? *array_size * 2 : 64;
	argv = kmalloc(new_size * sizeof(*argv), GFP_KERNEL);
	if (argv) {
		memcpy(argv, old_argv, *array_size * sizeof(*argv));
		*array_size = new_size;
	}

	kfree(old_argv);
	return argv;
}

/*
 * Destructively splits up the argument list to pass to ctr.
 */
int dm_split_args(int *argc, char ***argvp, char *input)
{
	char *start, *end = input, *out, **argv = NULL;
	unsigned array_size = 0;

	*argc = 0;

	if (!input) {
		*argvp = NULL;
		return 0;
	}

	argv = realloc_argv(&array_size, argv);
	if (!argv)
		return -ENOMEM;

	while (1) {
		start = end;

		/* Skip whitespace */
		while (*start && isspace(*start))
			start++;

		if (!*start)
			break;	/* success, we hit the end */

		/* 'out' is used to remove any back-quotes */
		end = out = start;
		while (*end) {
			/* Everything apart from '\0' can be quoted */
			if (*end == '\\' && *(end + 1)) {
				*out++ = *(end + 1);
				end += 2;
				continue;
			}

			if (isspace(*end))
				break;	/* end of token */

			*out++ = *end++;
		}

		/* have we already filled the array ? */
		if ((*argc + 1) > array_size) {
			argv = realloc_argv(&array_size, argv);
			if (!argv)
				return -ENOMEM;
		}

		/* we know this is whitespace */
		if (*end)
			end++;

		/* terminate the string and put it in the array */
		*out = '\0';
		argv[*argc] = start;
		(*argc)++;
	}

	*argvp = argv;
	return 0;
}

static void check_for_valid_limits(struct io_restrictions *rs)
{
	if (!rs->max_sectors)
		rs->max_sectors = SAFE_MAX_SECTORS;
	if (!rs->max_hw_sectors)
		rs->max_hw_sectors = SAFE_MAX_SECTORS;
	if (!rs->max_phys_segments)
		rs->max_phys_segments = MAX_PHYS_SEGMENTS;
	if (!rs->max_hw_segments)
		rs->max_hw_segments = MAX_HW_SEGMENTS;
	if (!rs->hardsect_size)
		rs->hardsect_size = 1 << SECTOR_SHIFT;
	if (!rs->max_segment_size)
		rs->max_segment_size = MAX_SEGMENT_SIZE;
	if (!rs->seg_boundary_mask)
		rs->seg_boundary_mask = -1;
	if (!rs->bounce_pfn)
		rs->bounce_pfn = -1;
}

int dm_table_add_target(struct dm_table *t, const char *type,
			sector_t start, sector_t len, char *params)
{
	int r = -EINVAL, argc;
	char **argv;
	struct dm_target *tgt;

	if ((r = check_space(t)))
		return r;

	tgt = t->targets + t->num_targets;
	memset(tgt, 0, sizeof(*tgt));

	if (!len) {
		DMERR("%s: zero-length target", dm_device_name(t->md));
		return -EINVAL;
	}

	tgt->type = dm_get_target_type(type);
	if (!tgt->type) {
		DMERR("%s: %s: unknown target type", dm_device_name(t->md),
		      type);
		return -EINVAL;
	}

	tgt->table = t;
	tgt->begin = start;
	tgt->len = len;
	tgt->error = "Unknown error";

	/*
	 * Does this target adjoin the previous one ?
	 */
	if (!adjoin(t, tgt)) {
		tgt->error = "Gap in table";
		r = -EINVAL;
		goto bad;
	}

	r = dm_split_args(&argc, &argv, params);
	if (r) {
		tgt->error = "couldn't split parameters (insufficient memory)";
		goto bad;
	}

	r = tgt->type->ctr(tgt, argc, argv);
	kfree(argv);
	if (r)
		goto bad;

	t->highs[t->num_targets++] = tgt->begin + tgt->len - 1;

	/* FIXME: the plan is to combine high here and then have
	 * the merge fn apply the target level restrictions. */
	combine_restrictions_low(&t->limits, &tgt->limits);
	return 0;

 bad:
	DMERR("%s: %s: %s", dm_device_name(t->md), type, tgt->error);
	dm_put_target_type(tgt->type);
	return r;
}

static int setup_indexes(struct dm_table *t)
{
	int i;
	unsigned int total = 0;
	sector_t *indexes;

	/* allocate the space for *all* the indexes */
	for (i = t->depth - 2; i >= 0; i--) {
		t->counts[i] = dm_div_up(t->counts[i + 1], CHILDREN_PER_NODE);
		total += t->counts[i];
	}

	indexes = (sector_t *) dm_vcalloc(total, (unsigned long) NODE_SIZE);
	if (!indexes)
		return -ENOMEM;

	/* set up internal nodes, bottom-up */
	for (i = t->depth - 2, total = 0; i >= 0; i--) {
		t->index[i] = indexes;
		indexes += (KEYS_PER_NODE * t->counts[i]);
		setup_btree_index(i, t);
	}

	return 0;
}

/*
 * Builds the btree to index the map.
 */
int dm_table_complete(struct dm_table *t)
{
	int r = 0;
	unsigned int leaf_nodes;

	check_for_valid_limits(&t->limits);

	/* how many indexes will the btree have ? */
	leaf_nodes = dm_div_up(t->num_targets, KEYS_PER_NODE);
	t->depth = 1 + int_log(leaf_nodes, CHILDREN_PER_NODE);

	/* leaf layer has already been set up */
	t->counts[t->depth - 1] = leaf_nodes;
	t->index[t->depth - 1] = t->highs;

	if (t->depth >= 2)
		r = setup_indexes(t);

	return r;
}

static DEFINE_MUTEX(_event_lock);
void dm_table_event_callback(struct dm_table *t,
			     void (*fn)(void *), void *context)
{
	mutex_lock(&_event_lock);
	t->event_fn = fn;
	t->event_context = context;
	mutex_unlock(&_event_lock);
}

void dm_table_event(struct dm_table *t)
{
	/*
	 * You can no longer call dm_table_event() from interrupt
	 * context, use a bottom half instead.
	 */
	BUG_ON(in_interrupt());

	mutex_lock(&_event_lock);
	if (t->event_fn)
		t->event_fn(t->event_context);
	mutex_unlock(&_event_lock);
}

sector_t dm_table_get_size(struct dm_table *t)
{
	return t->num_targets ? (t->highs[t->num_targets - 1] + 1) : 0;
}

struct dm_target *dm_table_get_target(struct dm_table *t, unsigned int index)
{
	if (index >= t->num_targets)
		return NULL;

	return t->targets + index;
}

/*
 * Search the btree for the correct target.
 *
 * Caller should check returned pointer with dm_target_is_valid()
 * to trap I/O beyond end of device.
 */
struct dm_target *dm_table_find_target(struct dm_table *t, sector_t sector)
{
	unsigned int l, n = 0, k = 0;
	sector_t *node;

	for (l = 0; l < t->depth; l++) {
		n = get_child(n, k);
		node = get_node(t, l, n);

		for (k = 0; k < KEYS_PER_NODE; k++)
			if (node[k] >= sector)
				break;
	}

	return &t->targets[(KEYS_PER_NODE * n) + k];
}

void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q)
{
	/*
	 * Make sure we obey the optimistic sub devices
	 * restrictions.
	 */
	blk_queue_max_sectors(q, t->limits.max_sectors);
	q->max_phys_segments = t->limits.max_phys_segments;
	q->max_hw_segments = t->limits.max_hw_segments;
	q->hardsect_size = t->limits.hardsect_size;
	q->max_segment_size = t->limits.max_segment_size;
	q->max_hw_sectors = t->limits.max_hw_sectors;
	q->seg_boundary_mask = t->limits.seg_boundary_mask;
	q->bounce_pfn = t->limits.bounce_pfn;
	if (t->limits.no_cluster)
		q->queue_flags &= ~(1 << QUEUE_FLAG_CLUSTER);
	else
		q->queue_flags |= (1 << QUEUE_FLAG_CLUSTER);

}

unsigned int dm_table_get_num_targets(struct dm_table *t)
{
	return t->num_targets;
}

struct list_head *dm_table_get_devices(struct dm_table *t)
{
	return &t->devices;
}

int dm_table_get_mode(struct dm_table *t)
{
	return t->mode;
}

static void suspend_targets(struct dm_table *t, unsigned postsuspend)
{
	int i = t->num_targets;
	struct dm_target *ti = t->targets;

	while (i--) {
		if (postsuspend) {
			if (ti->type->postsuspend)
				ti->type->postsuspend(ti);
		} else if (ti->type->presuspend)
			ti->type->presuspend(ti);

		ti++;
	}
}

void dm_table_presuspend_targets(struct dm_table *t)
{
	if (!t)
		return;

	return suspend_targets(t, 0);
}

void dm_table_postsuspend_targets(struct dm_table *t)
{
	if (!t)
		return;

	return suspend_targets(t, 1);
}

int dm_table_resume_targets(struct dm_table *t)
{
	int i, r = 0;

	for (i = 0; i < t->num_targets; i++) {
		struct dm_target *ti = t->targets + i;

		if (!ti->type->preresume)
			continue;

		r = ti->type->preresume(ti);
		if (r)
			return r;
	}

	for (i = 0; i < t->num_targets; i++) {
		struct dm_target *ti = t->targets + i;

		if (ti->type->resume)
			ti->type->resume(ti);
	}

	return 0;
}

int dm_table_any_congested(struct dm_table *t, int bdi_bits)
{
	struct list_head *d, *devices;
	int r = 0;

	devices = dm_table_get_devices(t);
	for (d = devices->next; d != devices; d = d->next) {
		struct dm_dev *dd = list_entry(d, struct dm_dev, list);
		struct request_queue *q = bdev_get_queue(dd->bdev);
		r |= bdi_congested(&q->backing_dev_info, bdi_bits);
	}

	return r;
}

void dm_table_unplug_all(struct dm_table *t)
{
	struct list_head *d, *devices = dm_table_get_devices(t);

	for (d = devices->next; d != devices; d = d->next) {
		struct dm_dev *dd = list_entry(d, struct dm_dev, list);
		struct request_queue *q = bdev_get_queue(dd->bdev);

		blk_unplug(q);
	}
}

struct mapped_device *dm_table_get_md(struct dm_table *t)
{
	dm_get(t->md);

	return t->md;
}

EXPORT_SYMBOL(dm_vcalloc);
EXPORT_SYMBOL(dm_get_device);
EXPORT_SYMBOL(dm_put_device);
EXPORT_SYMBOL(dm_table_event);
EXPORT_SYMBOL(dm_table_get_size);
EXPORT_SYMBOL(dm_table_get_mode);
EXPORT_SYMBOL(dm_table_get_md);
EXPORT_SYMBOL(dm_table_put);
EXPORT_SYMBOL(dm_table_get);
EXPORT_SYMBOL(dm_table_unplug_all);