X-Git-Url: https://err.no/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=drivers%2Fmd%2Fraid5.c;h=0b66afef2d82009be4f54c34880df588a8a22b61;hb=b91cba52e9b7b3f1c0037908a192d93a869ca9e5;hp=810cf831edda3bc8bdfd703f3b134b5009f37d84;hpb=e89f89629b5de76e504d1be75c82c4a6b2419583;p=linux-2.6

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 810cf831ed..0b66afef2d 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -1516,130 +1516,6 @@ static void copy_data(int frombio, struct bio *bio,
 			   }						  \
 			} while(0)
 
-
-static void compute_block(struct stripe_head *sh, int dd_idx)
-{
-	int i, count, disks = sh->disks;
-	void *ptr[MAX_XOR_BLOCKS], *dest, *p;
-
-	pr_debug("compute_block, stripe %llu, idx %d\n",
-		(unsigned long long)sh->sector, dd_idx);
-
-	dest = page_address(sh->dev[dd_idx].page);
-	memset(dest, 0, STRIPE_SIZE);
-	count = 0;
-	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(KERN_ERR "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);
-	set_bit(R5_UPTODATE, &sh->dev[dd_idx].flags);
-}
-
-static void compute_parity5(struct stripe_head *sh, int method)
-{
-	raid5_conf_t *conf = sh->raid_conf;
-	int i, pd_idx = sh->pd_idx, disks = sh->disks, count;
-	void *ptr[MAX_XOR_BLOCKS], *dest;
-	struct bio *chosen;
-
-	pr_debug("compute_parity5, stripe %llu, method %d\n",
-		(unsigned long long)sh->sector, method);
-
-	count = 0;
-	dest = page_address(sh->dev[pd_idx].page);
-	switch(method) {
-	case READ_MODIFY_WRITE:
-		BUG_ON(!test_bit(R5_UPTODATE, &sh->dev[pd_idx].flags));
-		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 (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;
-				check_xor();
-			}
-		}
-		break;
-	case RECONSTRUCT_WRITE:
-		memset(dest, 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 (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:
-		break;
-	}
-	if (count) {
-		xor_blocks(count, STRIPE_SIZE, dest, ptr);
-		count = 0;
-	}
-	
-	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)
-		xor_blocks(count, STRIPE_SIZE, dest, 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);
-}
-
 static void compute_parity6(struct stripe_head *sh, int method)
 {
 	raid6_conf_t *conf = sh->raid_conf;
@@ -2049,9 +1925,12 @@ handle_requests_to_failed_array(raid5_conf_t *conf, struct stripe_head *sh,
 			bi = bi2;
 		}
 
-		/* fail any reads if this device is non-operational */
-		if (!test_bit(R5_Insync, &sh->dev[i].flags) ||
-		    test_bit(R5_ReadError, &sh->dev[i].flags)) {
+		/* fail any reads if this device is non-operational and
+		 * the data has not reached the cache yet.
+		 */
+		if (!test_bit(R5_Wantfill, &sh->dev[i].flags) &&
+		    (!test_bit(R5_Insync, &sh->dev[i].flags) ||
+		      test_bit(R5_ReadError, &sh->dev[i].flags))) {
 			bi = sh->dev[i].toread;
 			sh->dev[i].toread = NULL;
 			if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
@@ -2323,6 +2202,9 @@ static void handle_issuing_new_write_requests5(raid5_conf_t *conf,
 						"%d for r-m-w\n", i);
 					set_bit(R5_LOCKED, &dev->flags);
 					set_bit(R5_Wantread, &dev->flags);
+					if (!test_and_set_bit(
+						STRIPE_OP_IO, &sh->ops.pending))
+						sh->ops.count++;
 					s->locked++;
 				} else {
 					set_bit(STRIPE_DELAYED, &sh->state);
@@ -2346,6 +2228,9 @@ static void handle_issuing_new_write_requests5(raid5_conf_t *conf,
 						"%d for Reconstruct\n", i);
 					set_bit(R5_LOCKED, &dev->flags);
 					set_bit(R5_Wantread, &dev->flags);
+					if (!test_and_set_bit(
+						STRIPE_OP_IO, &sh->ops.pending))
+						sh->ops.count++;
 					s->locked++;
 				} else {
 					set_bit(STRIPE_DELAYED, &sh->state);
@@ -2542,6 +2427,9 @@ static void handle_parity_checks5(raid5_conf_t *conf, struct stripe_head *sh,
 
 		set_bit(R5_LOCKED, &dev->flags);
 		set_bit(R5_Wantwrite, &dev->flags);
+		if (!test_and_set_bit(STRIPE_OP_IO, &sh->ops.pending))
+			sh->ops.count++;
+
 		clear_bit(STRIPE_DEGRADED, &sh->state);
 		s->locked++;
 		set_bit(STRIPE_INSYNC, &sh->state);
@@ -2650,6 +2538,7 @@ static void handle_stripe_expansion(raid5_conf_t *conf, struct stripe_head *sh,
 	/* We have read all the blocks in this stripe and now we need to
 	 * copy some of them into a target stripe for expand.
 	 */
+	struct dma_async_tx_descriptor *tx = NULL;
 	clear_bit(STRIPE_EXPAND_SOURCE, &sh->state);
 	for (i = 0; i < sh->disks; i++)
 		if (i != sh->pd_idx && (r6s && i != r6s->qd_idx)) {
@@ -2675,9 +2564,12 @@ static void handle_stripe_expansion(raid5_conf_t *conf, struct stripe_head *sh,
 				release_stripe(sh2);
 				continue;
 			}
-			memcpy(page_address(sh2->dev[dd_idx].page),
-			       page_address(sh->dev[i].page),
-			       STRIPE_SIZE);
+
+			/* place all the copies on one channel */
+			tx = async_memcpy(sh2->dev[dd_idx].page,
+				sh->dev[i].page, 0, 0, STRIPE_SIZE,
+				ASYNC_TX_DEP_ACK, tx, NULL, NULL);
+
 			set_bit(R5_Expanded, &sh2->dev[dd_idx].flags);
 			set_bit(R5_UPTODATE, &sh2->dev[dd_idx].flags);
 			for (j = 0; j < conf->raid_disks; j++)
@@ -2690,6 +2582,12 @@ static void handle_stripe_expansion(raid5_conf_t *conf, struct stripe_head *sh,
 				set_bit(STRIPE_HANDLE, &sh2->state);
 			}
 			release_stripe(sh2);
+
+			/* done submitting copies, wait for them to complete */
+			if (i + 1 >= sh->disks) {
+				async_tx_ack(tx);
+				dma_wait_for_async_tx(tx);
+			}
 		}
 }
 
@@ -2740,37 +2638,27 @@ static void handle_stripe5(struct stripe_head *sh)
 		struct r5dev *dev = &sh->dev[i];
 		clear_bit(R5_Insync, &dev->flags);
 
-		pr_debug("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;
-			pr_debug("Return read for disc %d\n", i);
-			spin_lock_irq(&conf->device_lock);
-			rbi = dev->toread;
-			dev->toread = NULL;
-			if (test_and_clear_bit(R5_Overlap, &dev->flags))
-				wake_up(&conf->wait_for_overlap);
-			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;
-			}
-		}
+		pr_debug("check %d: state 0x%lx toread %p read %p write %p "
+			"written %p\n",	i, dev->flags, dev->toread, dev->read,
+			dev->towrite, dev->written);
+
+		/* maybe we can request a biofill operation
+		 *
+		 * new wantfill requests are only permitted while
+		 * STRIPE_OP_BIOFILL is clear
+		 */
+		if (test_bit(R5_UPTODATE, &dev->flags) && dev->toread &&
+			!test_bit(STRIPE_OP_BIOFILL, &sh->ops.pending))
+			set_bit(R5_Wantfill, &dev->flags);
 
 		/* now count some things */
 		if (test_bit(R5_LOCKED, &dev->flags)) s.locked++;
 		if (test_bit(R5_UPTODATE, &dev->flags)) s.uptodate++;
 		if (test_bit(R5_Wantcompute, &dev->flags)) s.compute++;
 
-		if (dev->toread)
+		if (test_bit(R5_Wantfill, &dev->flags))
+			s.to_fill++;
+		else if (dev->toread)
 			s.to_read++;
 		if (dev->towrite) {
 			s.to_write++;
@@ -2793,6 +2681,10 @@ static void handle_stripe5(struct stripe_head *sh)
 			set_bit(R5_Insync, &dev->flags);
 	}
 	rcu_read_unlock();
+
+	if (s.to_fill && !test_and_set_bit(STRIPE_OP_BIOFILL, &sh->ops.pending))
+		sh->ops.count++;
+
 	pr_debug("locked=%d uptodate=%d to_read=%d"
 		" to_write=%d failed=%d failed_num=%d\n",
 		s.locked, s.uptodate, s.to_read, s.to_write,
@@ -2923,29 +2815,49 @@ static void handle_stripe5(struct stripe_head *sh)
 		dev = &sh->dev[s.failed_num];
 		if (!test_bit(R5_ReWrite, &dev->flags)) {
 			set_bit(R5_Wantwrite, &dev->flags);
+			if (!test_and_set_bit(STRIPE_OP_IO, &sh->ops.pending))
+				sh->ops.count++;
 			set_bit(R5_ReWrite, &dev->flags);
 			set_bit(R5_LOCKED, &dev->flags);
 			s.locked++;
 		} else {
 			/* let's read it back */
 			set_bit(R5_Wantread, &dev->flags);
+			if (!test_and_set_bit(STRIPE_OP_IO, &sh->ops.pending))
+				sh->ops.count++;
 			set_bit(R5_LOCKED, &dev->flags);
 			s.locked++;
 		}
 	}
 
-	if (s.expanded && test_bit(STRIPE_EXPANDING, &sh->state)) {
-		/* Need to write out all blocks after computing parity */
-		sh->disks = conf->raid_disks;
-		sh->pd_idx = stripe_to_pdidx(sh->sector, conf, conf->raid_disks);
-		compute_parity5(sh, RECONSTRUCT_WRITE);
+	/* Finish postxor operations initiated by the expansion
+	 * process
+	 */
+	if (test_bit(STRIPE_OP_POSTXOR, &sh->ops.complete) &&
+		!test_bit(STRIPE_OP_BIODRAIN, &sh->ops.pending)) {
+
+		clear_bit(STRIPE_EXPANDING, &sh->state);
+
+		clear_bit(STRIPE_OP_POSTXOR, &sh->ops.pending);
+		clear_bit(STRIPE_OP_POSTXOR, &sh->ops.ack);
+		clear_bit(STRIPE_OP_POSTXOR, &sh->ops.complete);
+
 		for (i = conf->raid_disks; i--; ) {
-			set_bit(R5_LOCKED, &sh->dev[i].flags);
-			s.locked++;
 			set_bit(R5_Wantwrite, &sh->dev[i].flags);
+			if (!test_and_set_bit(STRIPE_OP_IO, &sh->ops.pending))
+				sh->ops.count++;
 		}
-		clear_bit(STRIPE_EXPANDING, &sh->state);
-	} else if (s.expanded) {
+	}
+
+	if (s.expanded && test_bit(STRIPE_EXPANDING, &sh->state) &&
+		!test_bit(STRIPE_OP_POSTXOR, &sh->ops.pending)) {
+		/* Need to write out all blocks after computing parity */
+		sh->disks = conf->raid_disks;
+		sh->pd_idx = stripe_to_pdidx(sh->sector, conf,
+			conf->raid_disks);
+		s.locked += handle_write_operations5(sh, 0, 1);
+	} else if (s.expanded &&
+		!test_bit(STRIPE_OP_POSTXOR, &sh->ops.pending)) {
 		clear_bit(STRIPE_EXPAND_READY, &sh->state);
 		atomic_dec(&conf->reshape_stripes);
 		wake_up(&conf->wait_for_overlap);
@@ -2965,64 +2877,6 @@ static void handle_stripe5(struct stripe_head *sh)
 
 	return_io(return_bi);
 
-	for (i=disks; i-- ;) {
-		int rw;
-		struct bio *bi;
-		mdk_rdev_t *rdev;
-		if (test_and_clear_bit(R5_Wantwrite, &sh->dev[i].flags))
-			rw = WRITE;
-		else if (test_and_clear_bit(R5_Wantread, &sh->dev[i].flags))
-			rw = READ;
-		else
-			continue;
- 
-		bi = &sh->dev[i].req;
- 
-		bi->bi_rw = rw;
-		if (rw == WRITE)
-			bi->bi_end_io = raid5_end_write_request;
-		else
-			bi->bi_end_io = raid5_end_read_request;
- 
-		rcu_read_lock();
-		rdev = rcu_dereference(conf->disks[i].rdev);
-		if (rdev && test_bit(Faulty, &rdev->flags))
-			rdev = NULL;
-		if (rdev)
-			atomic_inc(&rdev->nr_pending);
-		rcu_read_unlock();
- 
-		if (rdev) {
-			if (s.syncing || s.expanding || s.expanded)
-				md_sync_acct(rdev->bdev, STRIPE_SECTORS);
-
-			bi->bi_bdev = rdev->bdev;
-			pr_debug("for %llu schedule op %ld on disc %d\n",
-				(unsigned long long)sh->sector, bi->bi_rw, i);
-			atomic_inc(&sh->count);
-			bi->bi_sector = sh->sector + rdev->data_offset;
-			bi->bi_flags = 1 << BIO_UPTODATE;
-			bi->bi_vcnt = 1;	
-			bi->bi_max_vecs = 1;
-			bi->bi_idx = 0;
-			bi->bi_io_vec = &sh->dev[i].vec;
-			bi->bi_io_vec[0].bv_len = STRIPE_SIZE;
-			bi->bi_io_vec[0].bv_offset = 0;
-			bi->bi_size = STRIPE_SIZE;
-			bi->bi_next = NULL;
-			if (rw == WRITE &&
-			    test_bit(R5_ReWrite, &sh->dev[i].flags))
-				atomic_add(STRIPE_SECTORS, &rdev->corrected_errors);
-			generic_make_request(bi);
-		} else {
-			if (rw == WRITE)
-				set_bit(STRIPE_DEGRADED, &sh->state);
-			pr_debug("skip op %ld on disc %d for sector %llu\n",
-				bi->bi_rw, i, (unsigned long long)sh->sector);
-			clear_bit(R5_LOCKED, &sh->dev[i].flags);
-			set_bit(STRIPE_HANDLE, &sh->state);
-		}
-	}
 }
 
 static void handle_stripe6(struct stripe_head *sh, struct page *tmp_page)