dm-table.c

Linux Kernel 2.6.9 for OMAP1710

/*
 * Copyright (C) 2001 Sistina Software (UK) Limited.
 *
 * This file is released under the GPL.
 */

#include "dm.h"

#include <linux/module.h>
#include <linux/vmalloc.h>
#include <linux/blkdev.h>
#include <linux/namei.h>
#include <linux/ctype.h>
#include <linux/slab.h>
#include <linux/interrupt.h>
#include <asm/atomic.h>

#define MAX_DEPTH 16
#define NODE_SIZE L1_CACHE_BYTES
#define KEYS_PER_NODE (NODE_SIZE / sizeof(sector_t))
#define CHILDREN_PER_NODE (KEYS_PER_NODE + 1)

struct dm_table {
	atomic_t holders;

	/* btree table */
	unsigned int depth;
	unsigned int counts[MAX_DEPTH];	/* in nodes */
	sector_t *index[MAX_DEPTH];

	unsigned int num_targets;
	unsigned int num_allocated;
	sector_t *highs;
	struct dm_target *targets;

	/*
	 * Indicates the rw permissions for the new logical
	 * device.  This should be a combination of FMODE_READ
	 * and FMODE_WRITE.
	 */
	int mode;

	/* a list of devices used by this table */
	struct list_head devices;

	/*
	 * These are optimistic limits taken from all the
	 * targets, some targets will need smaller limits.
	 */
	struct io_restrictions limits;

	/* events get handed up using this callback */
	void (*event_fn)(void *);
	void *event_context;
};

/*
 * Similar to ceiling(log_size(n))
 */
static unsigned int int_log(unsigned long n, unsigned long base)
{
	int result = 0;

	while (n > 1) {
		n = dm_div_up(n, base);
		result++;
	}

	return result;
}

/*
 * Returns the minimum that is _not_ zero, unless both are zero.
 */
#define min_not_zero(l, r) (l == 0) ? r : ((r == 0) ? l : min(l, r))

/*
 * Combine two io_restrictions, always taking the lower value.
 */
static void combine_restrictions_low(struct io_restrictions *lhs,
				     struct io_restrictions *rhs)
{
	lhs->max_sectors =
		min_not_zero(lhs->max_sectors, rhs->max_sectors);

	lhs->max_phys_segments =
		min_not_zero(lhs->max_phys_segments, rhs->max_phys_segments);

	lhs->max_hw_segments =
		min_not_zero(lhs->max_hw_segments, rhs->max_hw_segments);

	lhs->hardsect_size = max(lhs->hardsect_size, rhs->hardsect_size);

	lhs->max_segment_size =
		min_not_zero(lhs->max_segment_size, rhs->max_segment_size);

	lhs->seg_boundary_mask =
		min_not_zero(lhs->seg_boundary_mask, rhs->seg_boundary_mask);
}

/*
 * Calculate the index of the child node of the n'th node k'th key.
 */
static inline unsigned int get_child(unsigned int n, unsigned int k)
{
	return (n * CHILDREN_PER_NODE) + k;
}

/*
 * Return the n'th node of level l from table t.
 */
static inline sector_t *get_node(struct dm_table *t,
				 unsigned int l, unsigned int n)
{
	return t->index[l] + (n * KEYS_PER_NODE);
}

/*
 * Return the highest key that you could lookup from the n'th
 * node on level l of the btree.
 */
static sector_t high(struct dm_table *t, unsigned int l, unsigned int n)
{
	for (; l < t->depth - 1; l++)
		n = get_child(n, CHILDREN_PER_NODE - 1);

	if (n >= t->counts[l])
		return (sector_t) - 1;

	return get_node(t, l, n)[KEYS_PER_NODE - 1];
}

/*
 * Fills in a level of the btree based on the highs of the level
 * below it.
 */
static int setup_btree_index(unsigned int l, struct dm_table *t)
{
	unsigned int n, k;
	sector_t *node;

	for (n = 0U; n < t->counts[l]; n++) {
		node = get_node(t, l, n);

		for (k = 0U; k < KEYS_PER_NODE; k++)
			node[k] = high(t, l + 1, get_child(n, k));
	}

	return 0;
}

void *dm_vcalloc(unsigned long nmemb, unsigned long elem_size)
{
	unsigned long size;
	void *addr;

	/*
	 * Check that we're not going to overflow.
	 */
	if (nmemb > (ULONG_MAX / elem_size))
		return NULL;

	size = nmemb * elem_size;
	addr = vmalloc(size);
	if (addr)
		memset(addr, 0, size);

	return addr;
}

/*
 * highs, and targets are managed as dynamic arrays during a
 * table load.
 */
static int alloc_targets(struct dm_table *t, unsigned int num)
{
	sector_t *n_highs;
	struct dm_target *n_targets;
	int n = t->num_targets;

	/*
	 * Allocate both the target array and offset array at once.
	 */
	n_highs = (sector_t *) dm_vcalloc(num, sizeof(struct dm_target) +
					  sizeof(sector_t));
	if (!n_highs)
		return -ENOMEM;

	n_targets = (struct dm_target *) (n_highs + num);

	if (n) {
		memcpy(n_highs, t->highs, sizeof(*n_highs) * n);
		memcpy(n_targets, t->targets, sizeof(*n_targets) * n);
	}

	memset(n_highs + n, -1, sizeof(*n_highs) * (num - n));
	vfree(t->highs);

	t->num_allocated = num;
	t->highs = n_highs;
	t->targets = n_targets;

	return 0;
}

int dm_table_create(struct dm_table **result, int mode, unsigned num_targets)
{
	struct dm_table *t = kmalloc(sizeof(*t), GFP_KERNEL);

	if (!t)
		return -ENOMEM;

	memset(t, 0, sizeof(*t));
	INIT_LIST_HEAD(&t->devices);
	atomic_set(&t->holders, 1);

	if (!num_targets)
		num_targets = KEYS_PER_NODE;

	num_targets = dm_round_up(num_targets, KEYS_PER_NODE);

	if (alloc_targets(t, num_targets)) {
		kfree(t);
		t = NULL;
		return -ENOMEM;
	}

	t->mode = mode;
	*result = t;
	return 0;
}

static void free_devices(struct list_head *devices)
{
	struct list_head *tmp, *next;

	for (tmp = devices->next; tmp != devices; tmp = next) {
		struct dm_dev *dd = list_entry(tmp, struct dm_dev, list);
		next = tmp->next;
		kfree(dd);
	}
}

void table_destroy(struct dm_table *t)
{
	unsigned int i;

	/* free the indexes (see dm_table_complete) */
	if (t->depth >= 2)
		vfree(t->index[t->depth - 2]);

	/* free the targets */
	for (i = 0; i < t->num_targets; i++) {
		struct dm_target *tgt = t->targets + i;

		if (tgt->type->dtr)
			tgt->type->dtr(tgt);

		dm_put_target_type(tgt->type);
	}

	vfree(t->highs);

	/* free the device list */
	if (t->devices.next != &t->devices) {
		DMWARN("devices still present during destroy: "
		       "dm_table_remove_device calls missing");

		free_devices(&t->devices);
	}

	kfree(t);
}

void dm_table_get(struct dm_table *t)
{
	atomic_inc(&t->holders);
}

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

	if (atomic_dec_and_test(&t->holders))
		table_destroy(t);
}

/*
 * Checks to see if we need to extend highs or targets.
 */
static inline int check_space(struct dm_table *t)
{
	if (t->num_targets >= t->num_allocated)
		return alloc_targets(t, t->num_allocated * 2);

	return 0;
}

/*
 * Convert a device path to a dev_t.
 */
static int lookup_device(const char *path, dev_t *dev)
{
	int r;
	struct nameidata nd;
	struct inode *inode;

	if ((r = path_lookup(path, LOOKUP_FOLLOW, &nd)))
		return r;

	inode = nd.dentry->d_inode;
	if (!inode) {
		r = -ENOENT;
		goto out;
	}

	if (!S_ISBLK(inode->i_mode)) {
		r = -ENOTBLK;
		goto out;
	}

	*dev = inode->i_rdev;

 out:
	path_release(&nd);
	return r;
}

/*
 * See if we've already got a device in the list.
 */
static struct dm_dev *find_device(struct list_head *l, dev_t dev)
{
	struct dm_dev *dd;

	list_for_each_entry (dd, l, list)
		if (dd->bdev->bd_dev == dev)
			return dd;

	return NULL;
}

/*
 * Open a device so we can use it as a map destination.
 */
static int open_dev(struct dm_dev *d, dev_t dev)
{
	static char *_claim_ptr = "I belong to device-mapper";
	struct block_device *bdev;

	int r;

	if (d->bdev)
		BUG();

	bdev = open_by_devnum(dev, d->mode);
	if (IS_ERR(bdev))
		return PTR_ERR(bdev);
	r = bd_claim(bdev, _claim_ptr);
	if (r)
		blkdev_put(bdev);
	else
		d->bdev = bdev;
	return r;
}

/*
 * Close a device that we've been using.
 */
static void close_dev(struct dm_dev *d)
{
	if (!d->bdev)
		return;

	bd_release(d->bdev);
	blkdev_put(d->bdev);
	d->bdev = NULL;
}

/*
 * If possible (ie. blk_size[major] is set), this checks an area
 * of a destination device is valid.
 */
static int check_device_area(struct dm_dev *dd, sector_t start, sector_t len)
{
	sector_t dev_size;
	dev_size = dd->bdev->bd_inode->i_size >> SECTOR_SHIFT;
	return ((start < dev_size) && (len <= (dev_size - start)));
}

/*
 * This upgrades the mode on an already open dm_dev.  Being
 * careful to leave things as they were if we fail to reopen the
 * device.
 */
static int upgrade_mode(struct dm_dev *dd, int new_mode)
{
	int r;
	struct dm_dev dd_copy;
	dev_t dev = dd->bdev->bd_dev;

	dd_copy = *dd;

	dd->mode |= new_mode;
	dd->bdev = NULL;
	r = open_dev(dd, dev);
	if (!r)
		close_dev(&dd_copy);
	else
		*dd = dd_copy;

	return r;
}

/*
 * Add a device to the list, or just increment the usage count if
 * it's already present.
 */
static int __table_get_device(struct dm_table *t, struct dm_target *ti,
			      const char *path, sector_t start, sector_t len,
			      int mode, struct dm_dev **result)
{
	int r;
	dev_t dev;
	struct dm_dev *dd;
	unsigned int major, minor;

	if (!t)
		BUG();

	if (sscanf(path, "%u:%u", &major, &minor) == 2) {
		/* Extract the major/minor numbers */
		dev = MKDEV(major, minor);
		if (MAJOR(dev) != major || MINOR(dev) != minor)
			return -EOVERFLOW;
	} else {
		/* convert the path to a device */
		if ((r = lookup_device(path, &dev)))
			return r;
	}

	dd = find_device(&t->devices, dev);
	if (!dd) {
		dd = kmalloc(sizeof(*dd), GFP_KERNEL);
		if (!dd)
			return -ENOMEM;

		dd->mode = mode;
		dd->bdev = NULL;

		if ((r = open_dev(dd, dev))) {
			kfree(dd);
			return r;
		}

		atomic_set(&dd->count, 0);
		list_add(&dd->list, &t->devices);

	} else if (dd->mode != (mode | dd->mode)) {
		r = upgrade_mode(dd, mode);
		if (r)
			return r;
	}
	atomic_inc(&dd->count);

	if (!check_device_area(dd, start, len)) {