raid5.c

来自「linux 内核源代码」· C语言 代码 · 共 2,325 行 · 第 1/5 页

	case 5:
		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(KERN_ERR "raid5: unsupported algorithm %d\n",
			       conf->algorithm);
		}
		break;
	case 6:
		if (i == raid6_next_disk(sh->pd_idx, raid_disks))
			return 0; /* It is the Q disk */
		switch (conf->algorithm) {
		case ALGORITHM_LEFT_ASYMMETRIC:
		case ALGORITHM_RIGHT_ASYMMETRIC:
		  	if (sh->pd_idx == raid_disks-1)
				i--; 	/* Q D D D P */
			else if (i > sh->pd_idx)
				i -= 2; /* D D P Q D */
			break;
		case ALGORITHM_LEFT_SYMMETRIC:
		case ALGORITHM_RIGHT_SYMMETRIC:
			if (sh->pd_idx == raid_disks-1)
				i--; /* Q D D D P */
			else {
				/* D D P Q D */
				if (i < sh->pd_idx)
					i += raid_disks;
				i -= (sh->pd_idx + 2);
			}
			break;
		default:
			printk (KERN_CRIT "raid6: unsupported algorithm %d\n",
				conf->algorithm);
		}
		break;
	}

	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(KERN_ERR "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;
	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_blocks(count, STRIPE_SIZE, dest, ptr);\
				count = 0;				  \
			   }						  \
			} while(0)

static void compute_parity6(struct stripe_head *sh, int method)
{
	raid6_conf_t *conf = sh->raid_conf;
	int i, pd_idx = sh->pd_idx, qd_idx, d0_idx, disks = sh->disks, count;
	struct bio *chosen;
	/**** FIX THIS: This could be very bad if disks is close to 256 ****/
	void *ptrs[disks];

	qd_idx = raid6_next_disk(pd_idx, disks);
	d0_idx = raid6_next_disk(qd_idx, disks);

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

	switch(method) {
	case READ_MODIFY_WRITE:
		BUG();		/* READ_MODIFY_WRITE N/A for RAID-6 */
	case RECONSTRUCT_WRITE:
		for (i= disks; i-- ;)
			if ( i != pd_idx && i != qd_idx && sh->dev[i].towrite ) {
				chosen = sh->dev[i].towrite;
				sh->dev[i].towrite = NULL;

				if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
					wake_up(&conf->wait_for_overlap);

				BUG_ON(sh->dev[i].written);
				sh->dev[i].written = chosen;
			}
		break;
	case CHECK_PARITY:
		BUG();		/* Not implemented yet */
	}

	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:
//	case UPDATE_PARITY:
		/* Note that unlike RAID-5, the ordering of the disks matters greatly. */
		/* FIX: Is this ordering of drives even remotely optimal? */
		count = 0;
		i = d0_idx;
		do {
			ptrs[count++] = page_address(sh->dev[i].page);
			if (count <= disks-2 && !test_bit(R5_UPTODATE, &sh->dev[i].flags))
				printk("block %d/%d not uptodate on parity calc\n", i,count);
			i = raid6_next_disk(i, disks);
		} while ( i != d0_idx );
//		break;
//	}

	raid6_call.gen_syndrome(disks, STRIPE_SIZE, ptrs);

	switch(method) {
	case RECONSTRUCT_WRITE:
		set_bit(R5_UPTODATE, &sh->dev[pd_idx].flags);
		set_bit(R5_UPTODATE, &sh->dev[qd_idx].flags);
		set_bit(R5_LOCKED,   &sh->dev[pd_idx].flags);
		set_bit(R5_LOCKED,   &sh->dev[qd_idx].flags);
		break;
	case UPDATE_PARITY:
		set_bit(R5_UPTODATE, &sh->dev[pd_idx].flags);
		set_bit(R5_UPTODATE, &sh->dev[qd_idx].flags);
		break;
	}
}


/* Compute one missing block */
static void compute_block_1(struct stripe_head *sh, int dd_idx, int nozero)
{
	int i, count, disks = sh->disks;
	void *ptr[MAX_XOR_BLOCKS], *dest, *p;
	int pd_idx = sh->pd_idx;
	int qd_idx = raid6_next_disk(pd_idx, disks);

	pr_debug("compute_block_1, stripe %llu, idx %d\n",
		(unsigned long long)sh->sector, dd_idx);

	if ( dd_idx == qd_idx ) {
		/* We're actually computing the Q drive */
		compute_parity6(sh, UPDATE_PARITY);
	} else {
		dest = page_address(sh->dev[dd_idx].page);
		if (!nozero) memset(dest, 0, STRIPE_SIZE);
		count = 0;
		for (i = disks ; i--; ) {
			if (i == dd_idx || i == qd_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)
			xor_blocks(count, STRIPE_SIZE, dest, ptr);
		if (!nozero) set_bit(R5_UPTODATE, &sh->dev[dd_idx].flags);
		else clear_bit(R5_UPTODATE, &sh->dev[dd_idx].flags);
	}
}

/* Compute two missing blocks */
static void compute_block_2(struct stripe_head *sh, int dd_idx1, int dd_idx2)
{
	int i, count, disks = sh->disks;
	int pd_idx = sh->pd_idx;
	int qd_idx = raid6_next_disk(pd_idx, disks);
	int d0_idx = raid6_next_disk(qd_idx, disks);
	int faila, failb;

	/* faila and failb are disk numbers relative to d0_idx */
	/* pd_idx become disks-2 and qd_idx become disks-1 */
	faila = (dd_idx1 < d0_idx) ? dd_idx1+(disks-d0_idx) : dd_idx1-d0_idx;
	failb = (dd_idx2 < d0_idx) ? dd_idx2+(disks-d0_idx) : dd_idx2-d0_idx;

	BUG_ON(faila == failb);
	if ( failb < faila ) { int tmp = faila; faila = failb; failb = tmp; }

	pr_debug("compute_block_2, stripe %llu, idx %d,%d (%d,%d)\n",
	       (unsigned long long)sh->sector, dd_idx1, dd_idx2, faila, failb);

	if ( failb == disks-1 ) {
		/* Q disk is one of the missing disks */
		if ( faila == disks-2 ) {
			/* Missing P+Q, just recompute */
			compute_parity6(sh, UPDATE_PARITY);
			return;
		} else {
			/* We're missing D+Q; recompute D from P */
			compute_block_1(sh, (dd_idx1 == qd_idx) ? dd_idx2 : dd_idx1, 0);
			compute_parity6(sh, UPDATE_PARITY); /* Is this necessary? */
			return;
		}
	}

	/* We're missing D+P or D+D; build pointer table */
	{
		/**** FIX THIS: This could be very bad if disks is close to 256 ****/
		void *ptrs[disks];

		count = 0;
		i = d0_idx;
		do {
			ptrs[count++] = page_address(sh->dev[i].page);
			i = raid6_next_disk(i, disks);
			if (i != dd_idx1 && i != dd_idx2 &&
			    !test_bit(R5_UPTODATE, &sh->dev[i].flags))
				printk("compute_2 with missing block %d/%d\n", count, i);
		} while ( i != d0_idx );

		if ( failb == disks-2 ) {
			/* We're missing D+P. */
			raid6_datap_recov(disks, STRIPE_SIZE, faila, ptrs);
		} else {
			/* We're missing D+D. */
			raid6_2data_recov(disks, STRIPE_SIZE, faila, failb, ptrs);
		}

		/* Both the above update both missing blocks */
		set_bit(R5_UPTODATE, &sh->dev[dd_idx1].flags);
		set_bit(R5_UPTODATE, &sh->dev[dd_idx2].flags);
	}
}

static int
handle_write_operations5(struct stripe_head *sh, int rcw, int expand)
{
	int i, pd_idx = sh->pd_idx, disks = sh->disks;
	int locked = 0;

	if (rcw) {
		/* if we are not expanding this is a proper write request, and
		 * there will be bios with new data to be drained into the
		 * stripe cache
		 */
		if (!expand) {
			set_bit(STRIPE_OP_BIODRAIN, &sh->ops.pending);
			sh->ops.count++;
		}

		set_bit(STRIPE_OP_POSTXOR, &sh->ops.pending);
		sh->ops.count++;

		for (i = disks; i--; ) {
			struct r5dev *dev = &sh->dev[i];

			if (dev->towrite) {
				set_bit(R5_LOCKED, &dev->flags);
				if (!expand)
					clear_bit(R5_UPTODATE, &dev->flags);
				locked++;
			}
		}
	} else {
		BUG_ON(!(test_bit(R5_UPTODATE, &sh->dev[pd_idx].flags) ||
			test_bit(R5_Wantcompute, &sh->dev[pd_idx].flags)));

		set_bit(STRIPE_OP_PREXOR, &sh->ops.pending);
		set_bit(STRIPE_OP_BIODRAIN, &sh->ops.pending);
		set_bit(STRIPE_OP_POSTXOR, &sh->ops.pending);

		sh->ops.count += 3;

		for (i = disks; i--; ) {
			struct r5dev *dev = &sh->dev[i];
			if (i == pd_idx)
				continue;

			/* For a read-modify write there may be blocks that are
			 * locked for reading while others are ready to be
			 * written so we distinguish these blocks by the
			 * R5_Wantprexor bit
			 */
			if (dev->towrite &&
			    (test_bit(R5_UPTODATE, &dev->flags) ||
			    test_bit(R5_Wantcompute, &dev->flags))) {
				set_bit(R5_Wantprexor, &dev->flags);
				set_bit(R5_LOCKED, &dev->flags);
				clear_bit(R5_UPTODATE, &dev->flags);
				locked++;
			}
		}
	}

	/* keep the parity disk locked while asynchronous operations
	 * are in flight
	 */
	set_bit(R5_LOCKED, &sh->dev[pd_idx].flags);
	clear_bit(R5_UPTODATE, &sh->dev[pd_idx].flags);
	locked++;

	pr_debug("%s: stripe %llu locked: %d pending: %lx\n",
		__FUNCTION__, (unsigned long long)sh->sector,
		locked, sh->ops.pending);

	return locked;
}

/*
 * 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 int 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;
	int firstwrite=0;

	pr_debug("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;
		if (*bip == NULL && sh->dev[dd_idx].written == NULL)
			firstwrite = 1;
	} else
		bip = &sh->dev[dd_idx].toread;
	while (*bip && (*bip)->bi_sector < bi->bi_sector) {
		if ((*bip)->bi_sector + ((*bip)->bi_size >> 9) > bi->bi_sector)
			goto overlap;
		bip = & (*bip)->bi_next;
	}
	if (*bip && (*bip)->bi_sector < bi->bi_sector + ((bi->bi_size)>>9))
		goto overlap;

	BUG_ON(*bip && bi->bi_next && (*bip) != bi->bi_next);
	if (*bip)
		bi->bi_next = *bip;
	*bip = bi;
	bi->bi_phys_segments ++;
	spin_unlock_irq(&conf->device_lock);
	spin_unlock(&sh->lock);

	pr_debug("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 (conf->mddev->bitmap && firstwrite) {
		bitmap_startwrite(conf->mddev->bitmap, sh->sector,
				  STRIPE_SECTORS, 0);
		sh->bm_seq = conf->seq_flush+1;
		set_bit(STRIPE_BIT_DELAY, &sh->state);
	}

	if (forwrite) {
		/* check if page is covered */
		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);
	}
	return 1;

 overlap:
	set_bit(R5_Overlap, &sh->dev[dd_idx].flags);
	spin_unlock_irq(&conf->device_lock);
	spin_unlock(&sh->lock);
	return 0;
}

static void end_reshape(raid5_conf_t *conf);

static int page_is_zero(struct page *p)
{
	char *a = page_address(p);
	return ((*(u32*)a) == 0 &&
		memcmp(a, a+4, STRIPE_SIZE-4)==0);
}

static int stripe_to_pdidx(sector_t stripe, raid5_conf_t *conf, int disks)
{
	int sectors_per_chunk = conf->chunk_size >> 9;
	int pd_idx, dd_idx;
	int chunk_offset = sector_div(stripe, sectors_per_chunk);

	raid5_compute_sector(stripe * (disks - conf->max_degraded)
			     *sectors_per_chunk + chunk_offset,
			     disks, disks - conf->max_degraded,
			     &dd_idx, &pd_idx, conf);
	return pd_idx;