raid5.c

来自「Linux Kernel 2.6.9 for OMAP1710」· C语言 代码 · 共 1,920 行 · 第 1/4 页

			conf->working_disks--;
			mddev->degraded++;
			conf->failed_disks++;
			rdev->in_sync = 0;
			/*
			 * if recovery was running, make sure it aborts.
			 */
			set_bit(MD_RECOVERY_ERR, &mddev->recovery);
		}
		rdev->faulty = 1;
		printk (KERN_ALERT
			"raid5: Disk failure on %s, disabling device."
			" Operation continuing on %d devices\n",
			bdevname(rdev->bdev,b), conf->working_disks);
	}
}	

/*
 * Input: a 'big' sector number,
 * Output: index of the data and parity disk, and the sector # in them.
 */
static sector_t raid5_compute_sector(sector_t r_sector, unsigned int raid_disks,
			unsigned int data_disks, unsigned int * dd_idx,
			unsigned int * pd_idx, raid5_conf_t *conf)
{
	long stripe;
	unsigned long chunk_number;
	unsigned int chunk_offset;
	sector_t new_sector;
	int sectors_per_chunk = conf->chunk_size >> 9;

	/* First compute the information on this sector */

	/*
	 * Compute the chunk number and the sector offset inside the chunk
	 */
	chunk_offset = sector_div(r_sector, sectors_per_chunk);
	chunk_number = r_sector;
	BUG_ON(r_sector != chunk_number);

	/*
	 * Compute the stripe number
	 */
	stripe = chunk_number / data_disks;

	/*
	 * Compute the data disk and parity disk indexes inside the stripe
	 */
	*dd_idx = chunk_number % data_disks;

	/*
	 * Select the parity disk based on the user selected algorithm.
	 */
	if (conf->level == 4)
		*pd_idx = data_disks;
	else switch (conf->algorithm) {
		case ALGORITHM_LEFT_ASYMMETRIC:
			*pd_idx = data_disks - stripe % raid_disks;
			if (*dd_idx >= *pd_idx)
				(*dd_idx)++;
			break;
		case ALGORITHM_RIGHT_ASYMMETRIC:
			*pd_idx = stripe % raid_disks;
			if (*dd_idx >= *pd_idx)
				(*dd_idx)++;
			break;
		case ALGORITHM_LEFT_SYMMETRIC:
			*pd_idx = data_disks - stripe % raid_disks;
			*dd_idx = (*pd_idx + 1 + *dd_idx) % raid_disks;
			break;
		case ALGORITHM_RIGHT_SYMMETRIC:
			*pd_idx = stripe % raid_disks;
			*dd_idx = (*pd_idx + 1 + *dd_idx) % raid_disks;
			break;
		default:
			printk("raid5: unsupported algorithm %d\n",
				conf->algorithm);
	}

	/*
	 * Finally, compute the new sector number
	 */
	new_sector = (sector_t)stripe * sectors_per_chunk + chunk_offset;
	return new_sector;
}


static sector_t compute_blocknr(struct stripe_head *sh, int i)
{
	raid5_conf_t *conf = sh->raid_conf;
	int raid_disks = conf->raid_disks, data_disks = raid_disks - 1;
	sector_t new_sector = sh->sector, check;
	int sectors_per_chunk = conf->chunk_size >> 9;
	sector_t stripe;
	int chunk_offset;
	int chunk_number, dummy1, dummy2, dd_idx = i;
	sector_t r_sector;

	chunk_offset = sector_div(new_sector, sectors_per_chunk);
	stripe = new_sector;
	BUG_ON(new_sector != stripe);

	
	switch (conf->algorithm) {
		case ALGORITHM_LEFT_ASYMMETRIC:
		case ALGORITHM_RIGHT_ASYMMETRIC:
			if (i > sh->pd_idx)
				i--;
			break;
		case ALGORITHM_LEFT_SYMMETRIC:
		case ALGORITHM_RIGHT_SYMMETRIC:
			if (i < sh->pd_idx)
				i += raid_disks;
			i -= (sh->pd_idx + 1);
			break;
		default:
			printk("raid5: unsupported algorithm %d\n",
				conf->algorithm);
	}

	chunk_number = stripe * data_disks + i;
	r_sector = (sector_t)chunk_number * sectors_per_chunk + chunk_offset;

	check = raid5_compute_sector (r_sector, raid_disks, data_disks, &dummy1, &dummy2, conf);
	if (check != sh->sector || dummy1 != dd_idx || dummy2 != sh->pd_idx) {
		printk("compute_blocknr: map not correct\n");
		return 0;
	}
	return r_sector;
}



/*
 * Copy data between a page in the stripe cache, and one or more bion
 * The page could align with the middle of the bio, or there could be 
 * several bion, each with several bio_vecs, which cover part of the page
 * Multiple bion are linked together on bi_next.  There may be extras
 * at the end of this list.  We ignore them.
 */
static void copy_data(int frombio, struct bio *bio,
		     struct page *page,
		     sector_t sector)
{
	char *pa = page_address(page);
	struct bio_vec *bvl;
	int i;

	for (;bio && bio->bi_sector < sector+STRIPE_SECTORS;
	      bio = r5_next_bio(bio, sector) ) {
		int page_offset;
		if (bio->bi_sector >= sector)
			page_offset = (signed)(bio->bi_sector - sector) * 512;
		else 
			page_offset = (signed)(sector - bio->bi_sector) * -512;
		bio_for_each_segment(bvl, bio, i) {
			int len = bio_iovec_idx(bio,i)->bv_len;
			int clen;
			int b_offset = 0;			

			if (page_offset < 0) {
				b_offset = -page_offset;
				page_offset += b_offset;
				len -= b_offset;
			}

			if (len > 0 && page_offset + len > STRIPE_SIZE)
				clen = STRIPE_SIZE - page_offset;	
			else clen = len;
			
			if (clen > 0) {
				char *ba = __bio_kmap_atomic(bio, i, KM_USER0);
				if (frombio)
					memcpy(pa+page_offset, ba+b_offset, clen);
				else
					memcpy(ba+b_offset, pa+page_offset, clen);
				__bio_kunmap_atomic(ba, KM_USER0);
			}	
			if (clen < len) /* hit end of page */
				break;
			page_offset +=  len;
		}
	}
}

#define check_xor() 	do { 						\
			   if (count == MAX_XOR_BLOCKS) {		\
				xor_block(count, STRIPE_SIZE, ptr);	\
				count = 1;				\
			   }						\
			} while(0)


static void compute_block(struct stripe_head *sh, int dd_idx)
{
	raid5_conf_t *conf = sh->raid_conf;
	int i, count, disks = conf->raid_disks;
	void *ptr[MAX_XOR_BLOCKS], *p;

	PRINTK("compute_block, stripe %llu, idx %d\n", 
		(unsigned long long)sh->sector, dd_idx);

	ptr[0] = page_address(sh->dev[dd_idx].page);
	memset(ptr[0], 0, STRIPE_SIZE);
	count = 1;
	for (i = disks ; i--; ) {
		if (i == dd_idx)
			continue;
		p = page_address(sh->dev[i].page);
		if (test_bit(R5_UPTODATE, &sh->dev[i].flags))
			ptr[count++] = p;
		else
			printk("compute_block() %d, stripe %llu, %d"
				" not present\n", dd_idx,
				(unsigned long long)sh->sector, i);

		check_xor();
	}
	if (count != 1)
		xor_block(count, STRIPE_SIZE, ptr);
	set_bit(R5_UPTODATE, &sh->dev[dd_idx].flags);
}

static void compute_parity(struct stripe_head *sh, int method)
{
	raid5_conf_t *conf = sh->raid_conf;
	int i, pd_idx = sh->pd_idx, disks = conf->raid_disks, count;
	void *ptr[MAX_XOR_BLOCKS];
	struct bio *chosen;

	PRINTK("compute_parity, stripe %llu, method %d\n",
		(unsigned long long)sh->sector, method);

	count = 1;
	ptr[0] = page_address(sh->dev[pd_idx].page);
	switch(method) {
	case READ_MODIFY_WRITE:
		if (!test_bit(R5_UPTODATE, &sh->dev[pd_idx].flags))
			BUG();
		for (i=disks ; i-- ;) {
			if (i==pd_idx)
				continue;
			if (sh->dev[i].towrite &&
			    test_bit(R5_UPTODATE, &sh->dev[i].flags)) {
				ptr[count++] = page_address(sh->dev[i].page);
				chosen = sh->dev[i].towrite;
				sh->dev[i].towrite = NULL;
				if (sh->dev[i].written) BUG();
				sh->dev[i].written = chosen;
				check_xor();
			}
		}
		break;
	case RECONSTRUCT_WRITE:
		memset(ptr[0], 0, STRIPE_SIZE);
		for (i= disks; i-- ;)
			if (i!=pd_idx && sh->dev[i].towrite) {
				chosen = sh->dev[i].towrite;
				sh->dev[i].towrite = NULL;
				if (sh->dev[i].written) BUG();
				sh->dev[i].written = chosen;
			}
		break;
	case CHECK_PARITY:
		break;
	}
	if (count>1) {
		xor_block(count, STRIPE_SIZE, ptr);
		count = 1;
	}
	
	for (i = disks; i--;)
		if (sh->dev[i].written) {
			sector_t sector = sh->dev[i].sector;
			struct bio *wbi = sh->dev[i].written;
			while (wbi && wbi->bi_sector < sector + STRIPE_SECTORS) {
				copy_data(1, wbi, sh->dev[i].page, sector);
				wbi = r5_next_bio(wbi, sector);
			}

			set_bit(R5_LOCKED, &sh->dev[i].flags);
			set_bit(R5_UPTODATE, &sh->dev[i].flags);
		}

	switch(method) {
	case RECONSTRUCT_WRITE:
	case CHECK_PARITY:
		for (i=disks; i--;)
			if (i != pd_idx) {
				ptr[count++] = page_address(sh->dev[i].page);
				check_xor();
			}
		break;
	case READ_MODIFY_WRITE:
		for (i = disks; i--;)
			if (sh->dev[i].written) {
				ptr[count++] = page_address(sh->dev[i].page);
				check_xor();
			}
	}
	if (count != 1)
		xor_block(count, STRIPE_SIZE, ptr);
	
	if (method != CHECK_PARITY) {
		set_bit(R5_UPTODATE, &sh->dev[pd_idx].flags);
		set_bit(R5_LOCKED,   &sh->dev[pd_idx].flags);
	} else
		clear_bit(R5_UPTODATE, &sh->dev[pd_idx].flags);
}

/*
 * Each stripe/dev can have one or more bion attached.
 * toread/towrite point to the first in a chain. 
 * The bi_next chain must be in order.
 */
static void add_stripe_bio (struct stripe_head *sh, struct bio *bi, int dd_idx, int forwrite)
{
	struct bio **bip;
	raid5_conf_t *conf = sh->raid_conf;

	PRINTK("adding bh b#%llu to stripe s#%llu\n",
		(unsigned long long)bi->bi_sector,
		(unsigned long long)sh->sector);


	spin_lock(&sh->lock);
	spin_lock_irq(&conf->device_lock);
	if (forwrite)
		bip = &sh->dev[dd_idx].towrite;
	else
		bip = &sh->dev[dd_idx].toread;
	while (*bip && (*bip)->bi_sector < bi->bi_sector) {
		BUG_ON((*bip)->bi_sector + ((*bip)->bi_size >> 9) > bi->bi_sector);
		bip = & (*bip)->bi_next;
	}
/* FIXME do I need to worry about overlapping bion */
	if (*bip && bi->bi_next && (*bip) != bi->bi_next)
		BUG();
	if (*bip)
		bi->bi_next = *bip;
	*bip = bi;
	bi->bi_phys_segments ++;
	spin_unlock_irq(&conf->device_lock);
	spin_unlock(&sh->lock);

	PRINTK("added bi b#%llu to stripe s#%llu, disk %d.\n",
		(unsigned long long)bi->bi_sector,
		(unsigned long long)sh->sector, dd_idx);

	if (forwrite) {
		/* check if page is coverred */
		sector_t sector = sh->dev[dd_idx].sector;
		for (bi=sh->dev[dd_idx].towrite;
		     sector < sh->dev[dd_idx].sector + STRIPE_SECTORS &&
			     bi && bi->bi_sector <= sector;
		     bi = r5_next_bio(bi, sh->dev[dd_idx].sector)) {
			if (bi->bi_sector + (bi->bi_size>>9) >= sector)
				sector = bi->bi_sector + (bi->bi_size>>9);
		}
		if (sector >= sh->dev[dd_idx].sector + STRIPE_SECTORS)
			set_bit(R5_OVERWRITE, &sh->dev[dd_idx].flags);
	}
}


/*
 * handle_stripe - do things to a stripe.
 *
 * We lock the stripe and then examine the state of various bits
 * to see what needs to be done.
 * Possible results:
 *    return some read request which now have data
 *    return some write requests which are safely on disc
 *    schedule a read on some buffers
 *    schedule a write of some buffers
 *    return confirmation of parity correctness
 *
 * Parity calculations are done inside the stripe lock
 * buffers are taken off read_list or write_list, and bh_cache buffers
 * get BH_Lock set before the stripe lock is released.
 *
 */
 
static void handle_stripe(struct stripe_head *sh)
{
	raid5_conf_t *conf = sh->raid_conf;
	int disks = conf->raid_disks;
	struct bio *return_bi= NULL;
	struct bio *bi;
	int i;
	int syncing;
	int locked=0, uptodate=0, to_read=0, to_write=0, failed=0, written=0;
	int non_overwrite = 0;
	int failed_num=0;
	struct r5dev *dev;

	PRINTK("handling stripe %llu, cnt=%d, pd_idx=%d\n",
		(unsigned long long)sh->sector, atomic_read(&sh->count),
		sh->pd_idx);

	spin_lock(&sh->lock);
	clear_bit(STRIPE_HANDLE, &sh->state);
	clear_bit(STRIPE_DELAYED, &sh->state);

	syncing = test_bit(STRIPE_SYNCING, &sh->state);
	/* Now to look around and see what can be done */

	for (i=disks; i--; ) {
		mdk_rdev_t *rdev;
		dev = &sh->dev[i];
		clear_bit(R5_Insync, &dev->flags);
		clear_bit(R5_Syncio, &dev->flags);

		PRINTK("check %d: state 0x%lx read %p write %p written %p\n",
			i, dev->flags, dev->toread, dev->towrite, dev->written);
		/* maybe we can reply to a read */
		if (test_bit(R5_UPTODATE, &dev->flags) && dev->toread) {
			struct bio *rbi, *rbi2;
			PRINTK("Return read for disc %d\n", i);
			spin_lock_irq(&conf->device_lock);
			rbi = dev->toread;
			dev->toread = NULL;
			spin_unlock_irq(&conf->device_lock);
			while (rbi && rbi->bi_sector < dev->sector + STRIPE_SECTORS) {
				copy_data(0, rbi, dev->page, dev->sector);
				rbi2 = r5_next_bio(rbi, dev->sector);
				spin_lock_irq(&conf->device_lock);
				if (--rbi->bi_phys_segments == 0) {
					rbi->bi_next = return_bi;
					return_bi = rbi;
				}
				spin_unlock_irq(&conf->device_lock);
				rbi = rbi2;
			}
		}

		/* now count some things */
		if (test_bit(R5_LOCKED, &dev->flags)) locked++;
		if (test_bit(R5_UPTODATE, &dev->flags)) uptodate++;

		
		if (dev->toread) to_read++;
		if (dev->towrite) {
			to_write++;
			if (!test_bit(R5_OVERWRITE, &dev->flags))
				non_overwrite++;
		}
		if (dev->written) written++;
		rdev = conf->disks[i].rdev; /* FIXME, should I be looking rdev */
		if (!rdev || !rdev->in_sync) {
			failed++;
			failed_num = i;
		} else
			set_bit(R5_Insync, &dev->flags);
	}
	PRINTK("locked=%d uptodate=%d to_read=%d"
		" to_write=%d failed=%d failed_num=%d\n",
		locked, uptodate, to_read, to_write, failed, failed_num);
	/* check if the array has lost two devices and, if so, some requests might
	 * need to be failed
	 */
	if (failed > 1 && to_read+to_write+written) {
		spin_lock_irq(&conf->device_lock);
		for (i=disks; i--; ) {
			/* fail all writes first */
			bi = sh->dev[i].towrite;
			sh->dev[i].towrite = NULL;
			if (bi) to_write--;

			while (bi && bi->bi_sector < sh->dev[i].sector + STRIPE_SECTORS){
				struct bio *nextbi = r5_next_bio(bi, sh->dev[i].sector);
				clear_bit(BIO_UPTODATE, &bi->bi_flags);
				if (--bi->bi_phys_segments == 0) {
					md_write_end(conf->mddev);
					bi->bi_next = return_bi;
					return_bi = bi;
				}
				bi = nextbi;
			}
			/* and fail all 'written' */