md.c

来自「Linux Kernel 2.6.9 for OMAP1710」· C语言 代码 · 共 2,796 行 · 第 1/5 页

	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);
	kfree(rdev);
}

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: ");
	print_desc(&sb->this_disk);

}

static void print_rdev(mdk_rdev_t *rdev)
{
	char b[BDEVNAME_SIZE];
	printk(KERN_INFO "md: rdev %s, SZ:%08llu F:%d S:%d DN:%u\n",
		bdevname(rdev->bdev,b), (unsigned long long)rdev->size,
	       	rdev->faulty, rdev->in_sync, rdev->desc_nr);
	if (rdev->sb_loaded) {
		printk(KERN_INFO "md: rdev superblock:\n");
		print_sb((mdp_super_t*)page_address(rdev->sb_page));
	} else
		printk(KERN_INFO "md: no rdev superblock!\n");
}

void md_print_devices(void)
{
	struct list_head *tmp, *tmp2;
	mdk_rdev_t *rdev;
	mddev_t *mddev;
	char b[BDEVNAME_SIZE];

	printk("\n");
	printk("md:	**********************************\n");
	printk("md:	* <COMPLETE RAID STATE PRINTOUT> *\n");
	printk("md:	**********************************\n");
	ITERATE_MDDEV(mddev,tmp) {
		printk("%s: ", mdname(mddev));

		ITERATE_RDEV(mddev,rdev,tmp2)
			printk("<%s>", bdevname(rdev->bdev,b));
		printk("\n");

		ITERATE_RDEV(mddev,rdev,tmp2)
			print_rdev(rdev);
	}
	printk("md:	**********************************\n");
	printk("\n");
}


static int write_disk_sb(mdk_rdev_t * rdev)
{
	char b[BDEVNAME_SIZE];
	if (!rdev->sb_loaded) {
		MD_BUG();
		return 1;
	}
	if (rdev->faulty) {
		MD_BUG();
		return 1;
	}

	dprintk(KERN_INFO "(write) %s's sb offset: %llu\n",
		bdevname(rdev->bdev,b),
	       (unsigned long long)rdev->sb_offset);
  
	if (sync_page_io(rdev->bdev, rdev->sb_offset<<1, MD_SB_BYTES, rdev->sb_page, WRITE))
		return 0;

	printk("md: write_disk_sb failed for device %s\n", 
		bdevname(rdev->bdev,b));
	return 1;
}

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

	ITERATE_RDEV(mddev,rdev,tmp) {
		super_types[mddev->major_version].
			sync_super(mddev, rdev);
		rdev->sb_loaded = 1;
	}
}

static void md_update_sb(mddev_t * mddev)
{
	int err, count = 100;
	struct list_head *tmp;
	mdk_rdev_t *rdev;

	mddev->sb_dirty = 0;
repeat:
	mddev->utime = get_seconds();
	mddev->events ++;

	if (!mddev->events) {
		/*
		 * oops, this 64-bit counter should never wrap.
		 * Either we are in around ~1 trillion A.C., assuming
		 * 1 reboot per second, or we have a bug:
		 */
		MD_BUG();
		mddev->events --;
	}
	sync_sbs(mddev);

	/*
	 * do not write anything to disk if using
	 * nonpersistent superblocks
	 */
	if (!mddev->persistent)
		return;

	dprintk(KERN_INFO 
		"md: updating %s RAID superblock on device (in sync %d)\n",
		mdname(mddev),mddev->in_sync);

	err = 0;
	ITERATE_RDEV(mddev,rdev,tmp) {
		char b[BDEVNAME_SIZE];
		dprintk(KERN_INFO "md: ");
		if (rdev->faulty)
			dprintk("(skipping faulty ");

		dprintk("%s ", bdevname(rdev->bdev,b));
		if (!rdev->faulty) {
			err += write_disk_sb(rdev);
		} else
			dprintk(")\n");
		if (!err && mddev->level == LEVEL_MULTIPATH)
			/* only need to write one superblock... */
			break;
	}
	if (err) {
		if (--count) {
			printk(KERN_ERR "md: errors occurred during superblock"
				" update, repeating\n");
			goto repeat;
		}
		printk(KERN_ERR \
			"md: excessive errors occurred during superblock update, exiting\n");
	}
}

/*
 * Import a device. If 'super_format' >= 0, then sanity check the superblock
 *
 * mark the device faulty if:
 *
 *   - the device is nonexistent (zero size)
 *   - the device has no valid superblock
 *
 * a faulty rdev _never_ has rdev->sb set.
 */
static mdk_rdev_t *md_import_device(dev_t newdev, int super_format, int super_minor)
{
	char b[BDEVNAME_SIZE];
	int err;
	mdk_rdev_t *rdev;
	sector_t size;

	rdev = (mdk_rdev_t *) kmalloc(sizeof(*rdev), GFP_KERNEL);
	if (!rdev) {
		printk(KERN_ERR "md: could not alloc mem for new device!\n");
		return ERR_PTR(-ENOMEM);
	}
	memset(rdev, 0, sizeof(*rdev));

	if ((err = alloc_disk_sb(rdev)))
		goto abort_free;

	err = lock_rdev(rdev, newdev);
	if (err)
		goto abort_free;

	rdev->desc_nr = -1;
	rdev->faulty = 0;
	rdev->in_sync = 0;
	rdev->data_offset = 0;
	atomic_set(&rdev->nr_pending, 0);

	size = rdev->bdev->bd_inode->i_size >> BLOCK_SIZE_BITS;
	if (!size) {
		printk(KERN_WARNING 
			"md: %s has zero or unknown size, marking faulty!\n",
			bdevname(rdev->bdev,b));
		err = -EINVAL;
		goto abort_free;
	}

	if (super_format >= 0) {
		err = super_types[super_format].
			load_super(rdev, NULL, super_minor);
		if (err == -EINVAL) {
			printk(KERN_WARNING 
				"md: %s has invalid sb, not importing!\n",
				bdevname(rdev->bdev,b));
			goto abort_free;
		}
		if (err < 0) {
			printk(KERN_WARNING 
				"md: could not read %s's sb, not importing!\n",
				bdevname(rdev->bdev,b));
			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 int 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;
			rdev->in_sync = 1;
		}
	}


	/*
	 * Check if we can support this RAID array
	 */
	if (mddev->major_version != MD_MAJOR_VERSION ||
			mddev->minor_version > MD_MINOR_VERSION) {
		printk(KERN_ALERT 
			"md: %s: unsupported raid array version %d.%d.%d\n",
			mdname(mddev), mddev->major_version,
			mddev->minor_version, mddev->patch_version);
		goto abort;
	}

	if ((mddev->recovery_cp != MaxSector) &&
	    ((mddev->level == 1) ||
	     ((mddev->level >= 4) && (mddev->level <= 6))))
		printk(KERN_ERR "md: %s: raid array is not clean"
		       " -- starting background reconstruction\n",
		       mdname(mddev));

	return 0;
abort:
	return 1;
}

int mdp_major = 0;

static struct kobject *md_probe(dev_t dev, int *part, void *data)
{
	static DECLARE_MUTEX(disks_sem);
	mddev_t *mddev = mddev_find(dev);
	struct gendisk *disk;
	int partitioned = (MAJOR(dev) != MD_MAJOR);
	int shift = partitioned ? MdpMinorShift : 0;
	int unit = MINOR(dev) >> shift;

	if (!mddev)
		return NULL;

	down(&disks_sem);
	if (mddev->gendisk) {
		up(&disks_sem);
		mddev_put(mddev);
		return NULL;
	}
	disk = alloc_disk(1 << shift);
	if (!disk) {
		up(&disks_sem);
		mddev_put(mddev);
		return NULL;
	}
	disk->major = MAJOR(dev);
	disk->first_minor = unit << shift;
	if (partitioned)
		sprintf(disk->disk_name, "md_d%d", unit);
	else
		sprintf(disk->disk_name, "md%d", unit);
	disk->fops = &md_fops;
	disk->private_data = mddev;
	disk->queue = mddev->queue;
	add_disk(disk);
	mddev->gendisk = disk;
	up(&disks_sem);
	return NULL;
}

void md_wakeup_thread(mdk_thread_t *thread);

static void md_safemode_timeout(unsigned long data)
{
	mddev_t *mddev = (mddev_t *) data;

	mddev->safemode = 1;
	md_wakeup_thread(mddev->thread);
}


static int do_md_run(mddev_t * mddev)
{
	int pnum, err;
	int chunk_size;
	struct list_head *tmp;
	mdk_rdev_t *rdev;
	struct gendisk *disk;
	char b[BDEVNAME_SIZE];

	if (list_empty(&mddev->disks)) {
		MD_BUG();
		return -EINVAL;
	}

	if (mddev->pers)
		return -EBUSY;

	/*
	 * Analyze all RAID superblock(s)
	 */
	if (!mddev->raid_disks && analyze_sbs(mddev)) {
		MD_BUG();
		return -EINVAL;
	}

	chunk_size = mddev->chunk_size;
	pnum = level_to_pers(mddev->level);

	if ((pnum != MULTIPATH) && (pnum != RAID1)) {
		if (!chunk_size) {
			/*
			 * 'default chunksize' in the old md code used to
			 * be PAGE_SIZE, baaad.
			 * we abort here to be on the safe side. We don't
			 * want to continue the bad practice.
			 */
			printk(KERN_ERR 
				"no chunksize specified, see 'man raidtab'\n");
			return -EINVAL;
		}
		if (chunk_size > MAX_CHUNK_SIZE) {
			printk(KERN_ERR "too big chunk_size: %d > %d\n",
				chunk_size, MAX_CHUNK_SIZE);
			return -EINVAL;
		}
		/*
		 * chunk-size has to be a power of 2 and multiples of PAGE_SIZE
		 */
		if ( (1 << ffz(~chunk_size)) != chunk_size) {
			MD_BUG();
			return -EINVAL;
		}
		if (chunk_size < PAGE_SIZE) {
			printk(KERN_ERR "too small chunk_size: %d < %ld\n",
				chunk_size, PAGE_SIZE);
			return -EINVAL;
		}

		/* devices must have minimum size of one chunk */
		ITERATE_RDEV(mddev,rdev,tmp) {
			if (rdev->faulty)
				continue;
			if (rdev->size < chunk_size / 1024) {
				printk(KERN_WARNING
					"md: Dev %s smaller than chunk_size:"
					" %lluk < %dk\n",
					bdevname(rdev->bdev,b),
					(unsigned long long)rdev->size,
					chunk_size / 1024);
				return -EINVAL;
			}
		}
	}

	if (pnum >= MAX_PERSONALITY) {
		MD_BUG();
		return -EINVAL;
	}

#ifdef CONFIG_KMOD
	if (!pers[pnum])
	{
		request_module("md-personality-%d", pnum);
	}
#endif

	/*
	 * Drop all container device buffers, from now on
	 * the only valid external interface is through the md
	 * device.
	 * Also find largest hardsector size
	 */
	ITERATE_RDEV(mddev,rdev,tmp) {
		if (rdev->faulty)
			continue;
		sync_blockdev(rdev->bdev);
		invalidate_bdev(rdev->bdev, 0);
	}

	md_probe(mddev->unit, NULL, NULL);
	disk = mddev->gendisk;
	if (!disk)
		return -ENOMEM;

	spin_lock(&pers_lock);
	if (!pers[pnum] || !try_module_get(pers[pnum]->owner)) {
		spin_unlock(&pers_lock);
		printk(KERN_WARNING "md: personality %d is not loaded!\n",
		       pnum);
		return -EINVAL;
	}