md.c

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

	switch(minor_version) {
	case 0:
		sb_offset = rdev->bdev->bd_inode->i_size >> 9;
		sb_offset -= 8*2;
		sb_offset &= ~(sector_t)(4*2-1);
		/* convert from sectors to K */
		sb_offset /= 2;
		break;
	case 1:
		sb_offset = 0;
		break;
	case 2:
		sb_offset = 4;
		break;
	default:
		return -EINVAL;
	}
	rdev->sb_offset = sb_offset;

	/* superblock is rarely larger than 1K, but it can be larger,
	 * and it is safe to read 4k, so we do that
	 */
	ret = read_disk_sb(rdev, 4096);
	if (ret) return ret;


	sb = (struct mdp_superblock_1*)page_address(rdev->sb_page);

	if (sb->magic != cpu_to_le32(MD_SB_MAGIC) ||
	    sb->major_version != cpu_to_le32(1) ||
	    le32_to_cpu(sb->max_dev) > (4096-256)/2 ||
	    le64_to_cpu(sb->super_offset) != (rdev->sb_offset<<1) ||
	    (le32_to_cpu(sb->feature_map) & ~MD_FEATURE_ALL) != 0)
		return -EINVAL;

	if (calc_sb_1_csum(sb) != sb->sb_csum) {
		printk("md: invalid superblock checksum on %s\n",
			bdevname(rdev->bdev,b));
		return -EINVAL;
	}
	if (le64_to_cpu(sb->data_size) < 10) {
		printk("md: data_size too small on %s\n",
		       bdevname(rdev->bdev,b));
		return -EINVAL;
	}
	if ((le32_to_cpu(sb->feature_map) & MD_FEATURE_BITMAP_OFFSET)) {
		if (sb->level != cpu_to_le32(1) &&
		    sb->level != cpu_to_le32(4) &&
		    sb->level != cpu_to_le32(5) &&
		    sb->level != cpu_to_le32(6) &&
		    sb->level != cpu_to_le32(10)) {
			printk(KERN_WARNING
			       "md: bitmaps not supported for this level.\n");
			return -EINVAL;
		}
	}

	rdev->preferred_minor = 0xffff;
	rdev->data_offset = le64_to_cpu(sb->data_offset);
	atomic_set(&rdev->corrected_errors, le32_to_cpu(sb->cnt_corrected_read));

	rdev->sb_size = le32_to_cpu(sb->max_dev) * 2 + 256;
	bmask = queue_hardsect_size(rdev->bdev->bd_disk->queue)-1;
	if (rdev->sb_size & bmask)
		rdev-> sb_size = (rdev->sb_size | bmask)+1;

	if (sb->level == cpu_to_le32(LEVEL_MULTIPATH))
		rdev->desc_nr = -1;
	else
		rdev->desc_nr = le32_to_cpu(sb->dev_number);

	if (refdev == 0)
		ret = 1;
	else {
		__u64 ev1, ev2;
		struct mdp_superblock_1 *refsb = 
			(struct mdp_superblock_1*)page_address(refdev->sb_page);

		if (memcmp(sb->set_uuid, refsb->set_uuid, 16) != 0 ||
		    sb->level != refsb->level ||
		    sb->layout != refsb->layout ||
		    sb->chunksize != refsb->chunksize) {
			printk(KERN_WARNING "md: %s has strangely different"
				" superblock to %s\n",
				bdevname(rdev->bdev,b),
				bdevname(refdev->bdev,b2));
			return -EINVAL;
		}
		ev1 = le64_to_cpu(sb->events);
		ev2 = le64_to_cpu(refsb->events);

		if (ev1 > ev2)
			ret = 1;
		else
			ret = 0;
	}
	if (minor_version) 
		rdev->size = ((rdev->bdev->bd_inode->i_size>>9) - le64_to_cpu(sb->data_offset)) / 2;
	else
		rdev->size = rdev->sb_offset;
	if (rdev->size < le64_to_cpu(sb->data_size)/2)
		return -EINVAL;
	rdev->size = le64_to_cpu(sb->data_size)/2;
	if (le32_to_cpu(sb->chunksize))
		rdev->size &= ~((sector_t)le32_to_cpu(sb->chunksize)/2 - 1);

	if (le64_to_cpu(sb->size) > rdev->size*2)
		return -EINVAL;
	return ret;
}

static int super_1_validate(mddev_t *mddev, mdk_rdev_t *rdev)
{
	struct mdp_superblock_1 *sb = (struct mdp_superblock_1*)page_address(rdev->sb_page);
	__u64 ev1 = le64_to_cpu(sb->events);

	rdev->raid_disk = -1;
	rdev->flags = 0;
	if (mddev->raid_disks == 0) {
		mddev->major_version = 1;
		mddev->patch_version = 0;
		mddev->persistent = 1;
		mddev->chunk_size = le32_to_cpu(sb->chunksize) << 9;
		mddev->ctime = le64_to_cpu(sb->ctime) & ((1ULL << 32)-1);
		mddev->utime = le64_to_cpu(sb->utime) & ((1ULL << 32)-1);
		mddev->level = le32_to_cpu(sb->level);
		mddev->clevel[0] = 0;
		mddev->layout = le32_to_cpu(sb->layout);
		mddev->raid_disks = le32_to_cpu(sb->raid_disks);
		mddev->size = le64_to_cpu(sb->size)/2;
		mddev->events = ev1;
		mddev->bitmap_offset = 0;
		mddev->default_bitmap_offset = 1024 >> 9;
		
		mddev->recovery_cp = le64_to_cpu(sb->resync_offset);
		memcpy(mddev->uuid, sb->set_uuid, 16);

		mddev->max_disks =  (4096-256)/2;

		if ((le32_to_cpu(sb->feature_map) & MD_FEATURE_BITMAP_OFFSET) &&
		    mddev->bitmap_file == NULL )
			mddev->bitmap_offset = (__s32)le32_to_cpu(sb->bitmap_offset);

		if ((le32_to_cpu(sb->feature_map) & MD_FEATURE_RESHAPE_ACTIVE)) {
			mddev->reshape_position = le64_to_cpu(sb->reshape_position);
			mddev->delta_disks = le32_to_cpu(sb->delta_disks);
			mddev->new_level = le32_to_cpu(sb->new_level);
			mddev->new_layout = le32_to_cpu(sb->new_layout);
			mddev->new_chunk = le32_to_cpu(sb->new_chunk)<<9;
		} else {
			mddev->reshape_position = MaxSector;
			mddev->delta_disks = 0;
			mddev->new_level = mddev->level;
			mddev->new_layout = mddev->layout;
			mddev->new_chunk = mddev->chunk_size;
		}

	} else if (mddev->pers == NULL) {
		/* Insist of good event counter while assembling */
		++ev1;
		if (ev1 < mddev->events)
			return -EINVAL;
	} else if (mddev->bitmap) {
		/* If adding to array with a bitmap, then we can accept an
		 * older device, but not too old.
		 */
		if (ev1 < mddev->bitmap->events_cleared)
			return 0;
	} else {
		if (ev1 < mddev->events)
			/* just a hot-add of a new device, leave raid_disk at -1 */
			return 0;
	}
	if (mddev->level != LEVEL_MULTIPATH) {
		int role;
		role = le16_to_cpu(sb->dev_roles[rdev->desc_nr]);
		switch(role) {
		case 0xffff: /* spare */
			break;
		case 0xfffe: /* faulty */
			set_bit(Faulty, &rdev->flags);
			break;
		default:
			if ((le32_to_cpu(sb->feature_map) &
			     MD_FEATURE_RECOVERY_OFFSET))
				rdev->recovery_offset = le64_to_cpu(sb->recovery_offset);
			else
				set_bit(In_sync, &rdev->flags);
			rdev->raid_disk = role;
			break;
		}
		if (sb->devflags & WriteMostly1)
			set_bit(WriteMostly, &rdev->flags);
	} else /* MULTIPATH are always insync */
		set_bit(In_sync, &rdev->flags);

	return 0;
}

static void super_1_sync(mddev_t *mddev, mdk_rdev_t *rdev)
{
	struct mdp_superblock_1 *sb;
	struct list_head *tmp;
	mdk_rdev_t *rdev2;
	int max_dev, i;
	/* make rdev->sb match mddev and rdev data. */

	sb = (struct mdp_superblock_1*)page_address(rdev->sb_page);

	sb->feature_map = 0;
	sb->pad0 = 0;
	sb->recovery_offset = cpu_to_le64(0);
	memset(sb->pad1, 0, sizeof(sb->pad1));
	memset(sb->pad2, 0, sizeof(sb->pad2));
	memset(sb->pad3, 0, sizeof(sb->pad3));

	sb->utime = cpu_to_le64((__u64)mddev->utime);
	sb->events = cpu_to_le64(mddev->events);
	if (mddev->in_sync)
		sb->resync_offset = cpu_to_le64(mddev->recovery_cp);
	else
		sb->resync_offset = cpu_to_le64(0);

	sb->cnt_corrected_read = cpu_to_le32(atomic_read(&rdev->corrected_errors));

	sb->raid_disks = cpu_to_le32(mddev->raid_disks);
	sb->size = cpu_to_le64(mddev->size<<1);

	if (mddev->bitmap && mddev->bitmap_file == NULL) {
		sb->bitmap_offset = cpu_to_le32((__u32)mddev->bitmap_offset);
		sb->feature_map = cpu_to_le32(MD_FEATURE_BITMAP_OFFSET);
	}

	if (rdev->raid_disk >= 0 &&
	    !test_bit(In_sync, &rdev->flags) &&
	    rdev->recovery_offset > 0) {
		sb->feature_map |= cpu_to_le32(MD_FEATURE_RECOVERY_OFFSET);
		sb->recovery_offset = cpu_to_le64(rdev->recovery_offset);
	}

	if (mddev->reshape_position != MaxSector) {
		sb->feature_map |= cpu_to_le32(MD_FEATURE_RESHAPE_ACTIVE);
		sb->reshape_position = cpu_to_le64(mddev->reshape_position);
		sb->new_layout = cpu_to_le32(mddev->new_layout);
		sb->delta_disks = cpu_to_le32(mddev->delta_disks);
		sb->new_level = cpu_to_le32(mddev->new_level);
		sb->new_chunk = cpu_to_le32(mddev->new_chunk>>9);
	}

	max_dev = 0;
	ITERATE_RDEV(mddev,rdev2,tmp)
		if (rdev2->desc_nr+1 > max_dev)
			max_dev = rdev2->desc_nr+1;

	if (max_dev > le32_to_cpu(sb->max_dev))
		sb->max_dev = cpu_to_le32(max_dev);
	for (i=0; i<max_dev;i++)
		sb->dev_roles[i] = cpu_to_le16(0xfffe);
	
	ITERATE_RDEV(mddev,rdev2,tmp) {
		i = rdev2->desc_nr;
		if (test_bit(Faulty, &rdev2->flags))
			sb->dev_roles[i] = cpu_to_le16(0xfffe);
		else if (test_bit(In_sync, &rdev2->flags))
			sb->dev_roles[i] = cpu_to_le16(rdev2->raid_disk);
		else if (rdev2->raid_disk >= 0 && rdev2->recovery_offset > 0)
			sb->dev_roles[i] = cpu_to_le16(rdev2->raid_disk);
		else
			sb->dev_roles[i] = cpu_to_le16(0xffff);
	}

	sb->sb_csum = calc_sb_1_csum(sb);
}


static struct super_type super_types[] = {
	[0] = {
		.name	= "0.90.0",
		.owner	= THIS_MODULE,
		.load_super	= super_90_load,
		.validate_super	= super_90_validate,
		.sync_super	= super_90_sync,
	},
	[1] = {
		.name	= "md-1",
		.owner	= THIS_MODULE,
		.load_super	= super_1_load,
		.validate_super	= super_1_validate,
		.sync_super	= super_1_sync,
	},
};

static int match_mddev_units(mddev_t *mddev1, mddev_t *mddev2)
{
	struct list_head *tmp, *tmp2;
	mdk_rdev_t *rdev, *rdev2;

	ITERATE_RDEV(mddev1,rdev,tmp)
		ITERATE_RDEV(mddev2, rdev2, tmp2)
			if (rdev->bdev->bd_contains ==
			    rdev2->bdev->bd_contains)
				return 1;

	return 0;
}

static LIST_HEAD(pending_raid_disks);

static int bind_rdev_to_array(mdk_rdev_t * rdev, mddev_t * mddev)
{
	char b[BDEVNAME_SIZE];
	struct kobject *ko;
	char *s;
	int err;

	if (rdev->mddev) {
		MD_BUG();
		return -EINVAL;
	}
	/* make sure rdev->size exceeds mddev->size */
	if (rdev->size && (mddev->size == 0 || rdev->size < mddev->size)) {
		if (mddev->pers) {
			/* Cannot change size, so fail
			 * If mddev->level <= 0, then we don't care
			 * about aligning sizes (e.g. linear)
			 */
			if (mddev->level > 0)
				return -ENOSPC;
		} else
			mddev->size = rdev->size;
	}

	/* Verify rdev->desc_nr is unique.
	 * If it is -1, assign a free number, else
	 * check number is not in use
	 */
	if (rdev->desc_nr < 0) {
		int choice = 0;
		if (mddev->pers) choice = mddev->raid_disks;
		while (find_rdev_nr(mddev, choice))
			choice++;
		rdev->desc_nr = choice;
	} else {
		if (find_rdev_nr(mddev, rdev->desc_nr))
			return -EBUSY;
	}
	bdevname(rdev->bdev,b);
	if (kobject_set_name(&rdev->kobj, "dev-%s", b) < 0)
		return -ENOMEM;
	while ( (s=strchr(rdev->kobj.k_name, '/')) != NULL)
		*s = '!';
			
	rdev->mddev = mddev;
	printk(KERN_INFO "md: bind<%s>\n", b);

	rdev->kobj.parent = &mddev->kobj;
	if ((err = kobject_add(&rdev->kobj)))
		goto fail;

	if (rdev->bdev->bd_part)
		ko = &rdev->bdev->bd_part->kobj;
	else
		ko = &rdev->bdev->bd_disk->kobj;
	if ((err = sysfs_create_link(&rdev->kobj, ko, "block"))) {
		kobject_del(&rdev->kobj);
		goto fail;
	}
	list_add(&rdev->same_set, &mddev->disks);
	bd_claim_by_disk(rdev->bdev, rdev, mddev->gendisk);
	return 0;

 fail:
	printk(KERN_WARNING "md: failed to register dev-%s for %s\n",
	       b, mdname(mddev));
	return err;
}

static void delayed_delete(struct work_struct *ws)
{
	mdk_rdev_t *rdev = container_of(ws, mdk_rdev_t, del_work);
	kobject_del(&rdev->kobj);
}

static void unbind_rdev_from_array(mdk_rdev_t * rdev)
{
	char b[BDEVNAME_SIZE];
	if (!rdev->mddev) {
		MD_BUG();
		return;
	}
	bd_release_from_disk(rdev->bdev, rdev->mddev->gendisk);
	list_del_init(&rdev->same_set);
	printk(KERN_INFO "md: unbind<%s>\n", bdevname(rdev->bdev,b));
	rdev->mddev = NULL;
	sysfs_remove_link(&rdev->kobj, "block");

	/* We need to delay this, otherwise we can deadlock when
	 * writing to 'remove' to "dev/state"
	 */
	INIT_WORK(&rdev->del_work, delayed_delete);
	schedule_work(&rdev->del_work);
}

/*
 * prevent the device from being mounted, repartitioned or
 * otherwise reused by a RAID array (or any other kernel
 * subsystem), by bd_claiming the device.
 */
static int lock_rdev(mdk_rdev_t *rdev, dev_t dev)
{
	int err = 0;
	struct block_device *bdev;
	char b[BDEVNAME_SIZE];

	bdev = open_by_devnum(dev, FMODE_READ|FMODE_WRITE);
	if (IS_ERR(bdev)) {
		printk(KERN_ERR "md: could not open %s.\n",
			__bdevname(dev, b));
		return PTR_ERR(bdev);
	}
	err = bd_claim(bdev, rdev);
	if (err) {
		printk(KERN_ERR "md: could not bd_claim %s.\n",
			bdevname(bdev, b));
		blkdev_put(bdev);
		return err;
	}
	rdev->bdev = bdev;
	return err;
}

static void unlock_rdev(mdk_rdev_t *rdev)
{
	struct block_device *bdev = rdev->bdev;
	rdev->bdev = NULL;
	if (!bdev)
		MD_BUG();
	bd_release(bdev);
	blkdev_put(bdev);
}

void md_autodetect_dev(dev_t dev);

static void export_rdev(mdk_rdev_t * rdev)
{
	char b[BDEVNAME_SIZE];
	printk(KERN_INFO "md: export_rdev(%s)\n",
		bdevname(rdev->bdev,b));
	if (rdev->mddev)
		MD_BUG();
	free_disk_sb(rdev);
	list_del_init(&rdev->same_set);
#ifndef MODULE
	md_autodetect_dev(rdev->bdev->bd_dev);
#endif
	unlock_rdev(rdev);
	kobject_put(&rdev->kobj);
}

static void kick_rdev_from_array(mdk_rdev_t * rdev)
{
	unbind_rdev_from_array(rdev);
	export_rdev(rdev);
}

static void export_array(mddev_t *mddev)
{
	struct list_head *tmp;
	mdk_rdev_t *rdev;

	ITERATE_RDEV(mddev,rdev,tmp) {
		if (!rdev->mddev) {
			MD_BUG();
			continue;
		}
		kick_rdev_from_array(rdev);
	}
	if (!list_empty(&mddev->disks))
		MD_BUG();
	mddev->raid_disks = 0;
	mddev->major_version = 0;
}

static void print_desc(mdp_disk_t *desc)
{
	printk(" DISK<N:%d,(%d,%d),R:%d,S:%d>\n", desc->number,
		desc->major,desc->minor,desc->raid_disk,desc->state);
}

static void print_sb(mdp_super_t *sb)
{
	int i;

	printk(KERN_INFO 
		"md:  SB: (V:%d.%d.%d) ID:<%08x.%08x.%08x.%08x> CT:%08x\n",
		sb->major_version, sb->minor_version, sb->patch_version,
		sb->set_uuid0, sb->set_uuid1, sb->set_uuid2, sb->set_uuid3,
		sb->ctime);
	printk(KERN_INFO "md:     L%d S%08d ND:%d RD:%d md%d LO:%d CS:%d\n",
		sb->level, sb->size, sb->nr_disks, sb->raid_disks,
		sb->md_minor, sb->layout, sb->chunk_size);
	printk(KERN_INFO "md:     UT:%08x ST:%d AD:%d WD:%d"
		" FD:%d SD:%d CSUM:%08x E:%08lx\n",
		sb->utime, sb->state, sb->active_disks, sb->working_disks,
		sb->failed_disks, sb->spare_disks,
		sb->sb_csum, (unsigned long)sb->events_lo);

	printk(KERN_INFO);
	for (i = 0; i < MD_SB_DISKS; i++) {
		mdp_disk_t *desc;

		desc = sb->disks + i;
		if (desc->number || desc->major || desc->minor ||
		    desc->raid_disk || (desc->state && (desc->state != 4))) {
			printk("     D %2d: ", i);
			print_desc(desc);
		}
	}
	printk(KERN_INFO "md:     THIS: ");