md.c

来自「linux 内核源代码」· C语言 代码 · 共 2,595 行 · 第 1/5 页

			goto abort_free;
		}
	}
	INIT_LIST_HEAD(&rdev->same_set);

	return rdev;

abort_free:
	if (rdev->sb_page) {
		if (rdev->bdev)
			unlock_rdev(rdev);
		free_disk_sb(rdev);
	}
	kfree(rdev);
	return ERR_PTR(err);
}

/*
 * Check a full RAID array for plausibility
 */


static void analyze_sbs(mddev_t * mddev)
{
	int i;
	struct list_head *tmp;
	mdk_rdev_t *rdev, *freshest;
	char b[BDEVNAME_SIZE];

	freshest = NULL;
	ITERATE_RDEV(mddev,rdev,tmp)
		switch (super_types[mddev->major_version].
			load_super(rdev, freshest, mddev->minor_version)) {
		case 1:
			freshest = rdev;
			break;
		case 0:
			break;
		default:
			printk( KERN_ERR \
				"md: fatal superblock inconsistency in %s"
				" -- removing from array\n", 
				bdevname(rdev->bdev,b));
			kick_rdev_from_array(rdev);
		}


	super_types[mddev->major_version].
		validate_super(mddev, freshest);

	i = 0;
	ITERATE_RDEV(mddev,rdev,tmp) {
		if (rdev != freshest)
			if (super_types[mddev->major_version].
			    validate_super(mddev, rdev)) {
				printk(KERN_WARNING "md: kicking non-fresh %s"
					" from array!\n",
					bdevname(rdev->bdev,b));
				kick_rdev_from_array(rdev);
				continue;
			}
		if (mddev->level == LEVEL_MULTIPATH) {
			rdev->desc_nr = i++;
			rdev->raid_disk = rdev->desc_nr;
			set_bit(In_sync, &rdev->flags);
		} else if (rdev->raid_disk >= mddev->raid_disks) {
			rdev->raid_disk = -1;
			clear_bit(In_sync, &rdev->flags);
		}
	}



	if (mddev->recovery_cp != MaxSector &&
	    mddev->level >= 1)
		printk(KERN_ERR "md: %s: raid array is not clean"
		       " -- starting background reconstruction\n",
		       mdname(mddev));

}

static ssize_t
safe_delay_show(mddev_t *mddev, char *page)
{
	int msec = (mddev->safemode_delay*1000)/HZ;
	return sprintf(page, "%d.%03d\n", msec/1000, msec%1000);
}
static ssize_t
safe_delay_store(mddev_t *mddev, const char *cbuf, size_t len)
{
	int scale=1;
	int dot=0;
	int i;
	unsigned long msec;
	char buf[30];
	char *e;
	/* remove a period, and count digits after it */
	if (len >= sizeof(buf))
		return -EINVAL;
	strlcpy(buf, cbuf, len);
	buf[len] = 0;
	for (i=0; i<len; i++) {
		if (dot) {
			if (isdigit(buf[i])) {
				buf[i-1] = buf[i];
				scale *= 10;
			}
			buf[i] = 0;
		} else if (buf[i] == '.') {
			dot=1;
			buf[i] = 0;
		}
	}
	msec = simple_strtoul(buf, &e, 10);
	if (e == buf || (*e && *e != '\n'))
		return -EINVAL;
	msec = (msec * 1000) / scale;
	if (msec == 0)
		mddev->safemode_delay = 0;
	else {
		mddev->safemode_delay = (msec*HZ)/1000;
		if (mddev->safemode_delay == 0)
			mddev->safemode_delay = 1;
	}
	return len;
}
static struct md_sysfs_entry md_safe_delay =
__ATTR(safe_mode_delay, S_IRUGO|S_IWUSR,safe_delay_show, safe_delay_store);

static ssize_t
level_show(mddev_t *mddev, char *page)
{
	struct mdk_personality *p = mddev->pers;
	if (p)
		return sprintf(page, "%s\n", p->name);
	else if (mddev->clevel[0])
		return sprintf(page, "%s\n", mddev->clevel);
	else if (mddev->level != LEVEL_NONE)
		return sprintf(page, "%d\n", mddev->level);
	else
		return 0;
}

static ssize_t
level_store(mddev_t *mddev, const char *buf, size_t len)
{
	int rv = len;
	if (mddev->pers)
		return -EBUSY;
	if (len == 0)
		return 0;
	if (len >= sizeof(mddev->clevel))
		return -ENOSPC;
	strncpy(mddev->clevel, buf, len);
	if (mddev->clevel[len-1] == '\n')
		len--;
	mddev->clevel[len] = 0;
	mddev->level = LEVEL_NONE;
	return rv;
}

static struct md_sysfs_entry md_level =
__ATTR(level, S_IRUGO|S_IWUSR, level_show, level_store);


static ssize_t
layout_show(mddev_t *mddev, char *page)
{
	/* just a number, not meaningful for all levels */
	if (mddev->reshape_position != MaxSector &&
	    mddev->layout != mddev->new_layout)
		return sprintf(page, "%d (%d)\n",
			       mddev->new_layout, mddev->layout);
	return sprintf(page, "%d\n", mddev->layout);
}

static ssize_t
layout_store(mddev_t *mddev, const char *buf, size_t len)
{
	char *e;
	unsigned long n = simple_strtoul(buf, &e, 10);

	if (!*buf || (*e && *e != '\n'))
		return -EINVAL;

	if (mddev->pers)
		return -EBUSY;
	if (mddev->reshape_position != MaxSector)
		mddev->new_layout = n;
	else
		mddev->layout = n;
	return len;
}
static struct md_sysfs_entry md_layout =
__ATTR(layout, S_IRUGO|S_IWUSR, layout_show, layout_store);


static ssize_t
raid_disks_show(mddev_t *mddev, char *page)
{
	if (mddev->raid_disks == 0)
		return 0;
	if (mddev->reshape_position != MaxSector &&
	    mddev->delta_disks != 0)
		return sprintf(page, "%d (%d)\n", mddev->raid_disks,
			       mddev->raid_disks - mddev->delta_disks);
	return sprintf(page, "%d\n", mddev->raid_disks);
}

static int update_raid_disks(mddev_t *mddev, int raid_disks);

static ssize_t
raid_disks_store(mddev_t *mddev, const char *buf, size_t len)
{
	char *e;
	int rv = 0;
	unsigned long n = simple_strtoul(buf, &e, 10);

	if (!*buf || (*e && *e != '\n'))
		return -EINVAL;

	if (mddev->pers)
		rv = update_raid_disks(mddev, n);
	else if (mddev->reshape_position != MaxSector) {
		int olddisks = mddev->raid_disks - mddev->delta_disks;
		mddev->delta_disks = n - olddisks;
		mddev->raid_disks = n;
	} else
		mddev->raid_disks = n;
	return rv ? rv : len;
}
static struct md_sysfs_entry md_raid_disks =
__ATTR(raid_disks, S_IRUGO|S_IWUSR, raid_disks_show, raid_disks_store);

static ssize_t
chunk_size_show(mddev_t *mddev, char *page)
{
	if (mddev->reshape_position != MaxSector &&
	    mddev->chunk_size != mddev->new_chunk)
		return sprintf(page, "%d (%d)\n", mddev->new_chunk,
			       mddev->chunk_size);
	return sprintf(page, "%d\n", mddev->chunk_size);
}

static ssize_t
chunk_size_store(mddev_t *mddev, const char *buf, size_t len)
{
	/* can only set chunk_size if array is not yet active */
	char *e;
	unsigned long n = simple_strtoul(buf, &e, 10);

	if (!*buf || (*e && *e != '\n'))
		return -EINVAL;

	if (mddev->pers)
		return -EBUSY;
	else if (mddev->reshape_position != MaxSector)
		mddev->new_chunk = n;
	else
		mddev->chunk_size = n;
	return len;
}
static struct md_sysfs_entry md_chunk_size =
__ATTR(chunk_size, S_IRUGO|S_IWUSR, chunk_size_show, chunk_size_store);

static ssize_t
resync_start_show(mddev_t *mddev, char *page)
{
	return sprintf(page, "%llu\n", (unsigned long long)mddev->recovery_cp);
}

static ssize_t
resync_start_store(mddev_t *mddev, const char *buf, size_t len)
{
	/* can only set chunk_size if array is not yet active */
	char *e;
	unsigned long long n = simple_strtoull(buf, &e, 10);

	if (mddev->pers)
		return -EBUSY;
	if (!*buf || (*e && *e != '\n'))
		return -EINVAL;

	mddev->recovery_cp = n;
	return len;
}
static struct md_sysfs_entry md_resync_start =
__ATTR(resync_start, S_IRUGO|S_IWUSR, resync_start_show, resync_start_store);

/*
 * The array state can be:
 *
 * clear
 *     No devices, no size, no level
 *     Equivalent to STOP_ARRAY ioctl
 * inactive
 *     May have some settings, but array is not active
 *        all IO results in error
 *     When written, doesn't tear down array, but just stops it
 * suspended (not supported yet)
 *     All IO requests will block. The array can be reconfigured.
 *     Writing this, if accepted, will block until array is quiessent
 * readonly
 *     no resync can happen.  no superblocks get written.
 *     write requests fail
 * read-auto
 *     like readonly, but behaves like 'clean' on a write request.
 *
 * clean - no pending writes, but otherwise active.
 *     When written to inactive array, starts without resync
 *     If a write request arrives then
 *       if metadata is known, mark 'dirty' and switch to 'active'.
 *       if not known, block and switch to write-pending
 *     If written to an active array that has pending writes, then fails.
 * active
 *     fully active: IO and resync can be happening.
 *     When written to inactive array, starts with resync
 *
 * write-pending
 *     clean, but writes are blocked waiting for 'active' to be written.
 *
 * active-idle
 *     like active, but no writes have been seen for a while (100msec).
 *
 */
enum array_state { clear, inactive, suspended, readonly, read_auto, clean, active,
		   write_pending, active_idle, bad_word};
static char *array_states[] = {
	"clear", "inactive", "suspended", "readonly", "read-auto", "clean", "active",
	"write-pending", "active-idle", NULL };

static int match_word(const char *word, char **list)
{
	int n;
	for (n=0; list[n]; n++)
		if (cmd_match(word, list[n]))
			break;
	return n;
}

static ssize_t
array_state_show(mddev_t *mddev, char *page)
{
	enum array_state st = inactive;

	if (mddev->pers)
		switch(mddev->ro) {
		case 1:
			st = readonly;
			break;
		case 2:
			st = read_auto;
			break;
		case 0:
			if (mddev->in_sync)
				st = clean;
			else if (mddev->safemode)
				st = active_idle;
			else
				st = active;
		}
	else {
		if (list_empty(&mddev->disks) &&
		    mddev->raid_disks == 0 &&
		    mddev->size == 0)
			st = clear;
		else
			st = inactive;
	}
	return sprintf(page, "%s\n", array_states[st]);
}

static int do_md_stop(mddev_t * mddev, int ro);
static int do_md_run(mddev_t * mddev);
static int restart_array(mddev_t *mddev);

static ssize_t
array_state_store(mddev_t *mddev, const char *buf, size_t len)
{
	int err = -EINVAL;
	enum array_state st = match_word(buf, array_states);
	switch(st) {
	case bad_word:
		break;
	case clear:
		/* stopping an active array */
		if (mddev->pers) {
			if (atomic_read(&mddev->active) > 1)
				return -EBUSY;
			err = do_md_stop(mddev, 0);
		}
		break;
	case inactive:
		/* stopping an active array */
		if (mddev->pers) {
			if (atomic_read(&mddev->active) > 1)
				return -EBUSY;
			err = do_md_stop(mddev, 2);
		}
		break;
	case suspended:
		break; /* not supported yet */
	case readonly:
		if (mddev->pers)
			err = do_md_stop(mddev, 1);
		else {
			mddev->ro = 1;
			err = do_md_run(mddev);
		}
		break;
	case read_auto:
		/* stopping an active array */
		if (mddev->pers) {
			err = do_md_stop(mddev, 1);
			if (err == 0)
				mddev->ro = 2; /* FIXME mark devices writable */
		} else {
			mddev->ro = 2;
			err = do_md_run(mddev);
		}
		break;
	case clean:
		if (mddev->pers) {
			restart_array(mddev);
			spin_lock_irq(&mddev->write_lock);
			if (atomic_read(&mddev->writes_pending) == 0) {
				mddev->in_sync = 1;
				set_bit(MD_CHANGE_CLEAN, &mddev->flags);
			}
			spin_unlock_irq(&mddev->write_lock);
		} else {
			mddev->ro = 0;
			mddev->recovery_cp = MaxSector;
			err = do_md_run(mddev);
		}
		break;
	case active:
		if (mddev->pers) {
			restart_array(mddev);
			clear_bit(MD_CHANGE_CLEAN, &mddev->flags);
			wake_up(&mddev->sb_wait);
			err = 0;
		} else {
			mddev->ro = 0;
			err = do_md_run(mddev);
		}
		break;
	case write_pending:
	case active_idle:
		/* these cannot be set */
		break;
	}
	if (err)
		return err;
	else
		return len;
}
static struct md_sysfs_entry md_array_state =
__ATTR(array_state, S_IRUGO|S_IWUSR, array_state_show, array_state_store);

static ssize_t
null_show(mddev_t *mddev, char *page)
{
	return -EINVAL;
}

static ssize_t
new_dev_store(mddev_t *mddev, const char *buf, size_t len)
{
	/* buf must be %d:%d\n? giving major and minor numbers */
	/* The new device is added to the array.
	 * If the array has a persistent superblock, we read the
	 * superblock to initialise info and check validity.
	 * Otherwise, only checking done is that in bind_rdev_to_array,
	 * which mainly checks size.
	 */
	char *e;
	int major = simple_strtoul(buf, &e, 10);
	int minor;
	dev_t dev;
	mdk_rdev_t *rdev;
	int err;

	if (!*buf || *e != ':' || !e[1] || e[1] == '\n')
		return -EINVAL;
	minor = simple_strtoul(e+1, &e, 10);
	if (*e && *e != '\n')
		return -EINVAL;
	dev = MKDEV(major, minor);
	if (major != MAJOR(dev) ||
	    minor != MINOR(dev))
		return -EOVERFLOW;


	if (mddev->persistent) {
		rdev = md_import_device(dev, mddev->major_version,
					mddev->minor_version);
		if (!IS_ERR(rdev) && !list_empty(&mddev->disks)) {
			mdk_rdev_t *rdev0 = list_entry(mddev->disks.next,
						       mdk_rdev_t, same_set);
			err = super_types[mddev->major_version]
				.load_super(rdev, rdev0, mddev->minor_version);
			if (err < 0)
				goto out;
		}
	} else
		rdev = md_import_device(dev, -1, -1);

	if (IS_ERR(rdev))
		return PTR_ERR(rdev);
	err = bind_rdev_to_array(rdev, mddev);
 out:
	if (err)
		export_rdev(rdev);
	return err ? err : len;
}

static struct md_sysfs_entry md_new_device =
__ATTR(new_dev, S_IWUSR, null