X-Git-Url: https://err.no/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=drivers%2Fmd%2Fraid5.c;h=93fde48c0f42e52cbedad8be994d00362e6198b6;hb=754cdd4aba225b74dcc35cc384aeb0c42b505e8b;hp=968dacaced6de669181bba2d1e1902fbea3ffa8f;hpb=cfd299dffe6f47c04c47b95893708cdc65876fbd;p=linux-2.6

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 968dacaced..93fde48c0f 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -2369,8 +2369,8 @@ static void handle_parity_checks5(raid5_conf_t *conf, struct stripe_head *sh,
 
 	/* complete a check operation */
 	if (test_and_clear_bit(STRIPE_OP_CHECK, &sh->ops.complete)) {
-	    clear_bit(STRIPE_OP_CHECK, &sh->ops.ack);
-	    clear_bit(STRIPE_OP_CHECK, &sh->ops.pending);
+		clear_bit(STRIPE_OP_CHECK, &sh->ops.ack);
+		clear_bit(STRIPE_OP_CHECK, &sh->ops.pending);
 		if (s->failed == 0) {
 			if (sh->ops.zero_sum_result == 0)
 				/* parity is correct (on disc,
@@ -2400,16 +2400,6 @@ static void handle_parity_checks5(raid5_conf_t *conf, struct stripe_head *sh,
 			canceled_check = 1; /* STRIPE_INSYNC is not set */
 	}
 
-	/* check if we can clear a parity disk reconstruct */
-	if (test_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.complete) &&
-		test_bit(STRIPE_OP_MOD_REPAIR_PD, &sh->ops.pending)) {
-
-		clear_bit(STRIPE_OP_MOD_REPAIR_PD, &sh->ops.pending);
-		clear_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.complete);
-		clear_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.ack);
-		clear_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending);
-	}
-
 	/* start a new check operation if there are no failures, the stripe is
 	 * not insync, and a repair is not in flight
 	 */
@@ -2424,6 +2414,17 @@ static void handle_parity_checks5(raid5_conf_t *conf, struct stripe_head *sh,
 		}
 	}
 
+	/* check if we can clear a parity disk reconstruct */
+	if (test_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.complete) &&
+	    test_bit(STRIPE_OP_MOD_REPAIR_PD, &sh->ops.pending)) {
+
+		clear_bit(STRIPE_OP_MOD_REPAIR_PD, &sh->ops.pending);
+		clear_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.complete);
+		clear_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.ack);
+		clear_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending);
+	}
+
+
 	/* Wait for check parity and compute block operations to complete
 	 * before write-back.  If a failure occurred while the check operation
 	 * was in flight we need to cycle this stripe through handle_stripe
@@ -2607,6 +2608,7 @@ static void handle_stripe_expansion(raid5_conf_t *conf, struct stripe_head *sh,
 	}
 }
 
+
 /*
  * handle_stripe - do things to a stripe.
  *
@@ -2632,6 +2634,7 @@ static void handle_stripe5(struct stripe_head *sh)
 	struct stripe_head_state s;
 	struct r5dev *dev;
 	unsigned long pending = 0;
+	mdk_rdev_t *blocked_rdev = NULL;
 
 	memset(&s, 0, sizeof(s));
 	pr_debug("handling stripe %llu, state=%#lx cnt=%d, pd_idx=%d "
@@ -2691,6 +2694,11 @@ static void handle_stripe5(struct stripe_head *sh)
 		if (dev->written)
 			s.written++;
 		rdev = rcu_dereference(conf->disks[i].rdev);
+		if (rdev && unlikely(test_bit(Blocked, &rdev->flags))) {
+			blocked_rdev = rdev;
+			atomic_inc(&rdev->nr_pending);
+			break;
+		}
 		if (!rdev || !test_bit(In_sync, &rdev->flags)) {
 			/* The ReadError flag will just be confusing now */
 			clear_bit(R5_ReadError, &dev->flags);
@@ -2705,6 +2713,11 @@ static void handle_stripe5(struct stripe_head *sh)
 	}
 	rcu_read_unlock();
 
+	if (unlikely(blocked_rdev)) {
+		set_bit(STRIPE_HANDLE, &sh->state);
+		goto unlock;
+	}
+
 	if (s.to_fill && !test_and_set_bit(STRIPE_OP_BIOFILL, &sh->ops.pending))
 		sh->ops.count++;
 
@@ -2894,8 +2907,13 @@ static void handle_stripe5(struct stripe_head *sh)
 	if (sh->ops.count)
 		pending = get_stripe_work(sh);
 
+ unlock:
 	spin_unlock(&sh->lock);
 
+	/* wait for this device to become unblocked */
+	if (unlikely(blocked_rdev))
+		md_wait_for_blocked_rdev(blocked_rdev, conf->mddev);
+
 	if (pending)
 		raid5_run_ops(sh, pending);
 
@@ -2912,6 +2930,7 @@ static void handle_stripe6(struct stripe_head *sh, struct page *tmp_page)
 	struct stripe_head_state s;
 	struct r6_state r6s;
 	struct r5dev *dev, *pdev, *qdev;
+	mdk_rdev_t *blocked_rdev = NULL;
 
 	r6s.qd_idx = raid6_next_disk(pd_idx, disks);
 	pr_debug("handling stripe %llu, state=%#lx cnt=%d, "
@@ -2975,6 +2994,11 @@ static void handle_stripe6(struct stripe_head *sh, struct page *tmp_page)
 		if (dev->written)
 			s.written++;
 		rdev = rcu_dereference(conf->disks[i].rdev);
+		if (rdev && unlikely(test_bit(Blocked, &rdev->flags))) {
+			blocked_rdev = rdev;
+			atomic_inc(&rdev->nr_pending);
+			break;
+		}
 		if (!rdev || !test_bit(In_sync, &rdev->flags)) {
 			/* The ReadError flag will just be confusing now */
 			clear_bit(R5_ReadError, &dev->flags);
@@ -2989,6 +3013,11 @@ static void handle_stripe6(struct stripe_head *sh, struct page *tmp_page)
 			set_bit(R5_Insync, &dev->flags);
 	}
 	rcu_read_unlock();
+
+	if (unlikely(blocked_rdev)) {
+		set_bit(STRIPE_HANDLE, &sh->state);
+		goto unlock;
+	}
 	pr_debug("locked=%d uptodate=%d to_read=%d"
 	       " to_write=%d failed=%d failed_num=%d,%d\n",
 	       s.locked, s.uptodate, s.to_read, s.to_write, s.failed,
@@ -3094,8 +3123,13 @@ static void handle_stripe6(struct stripe_head *sh, struct page *tmp_page)
 	    !test_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending))
 		handle_stripe_expansion(conf, sh, &r6s);
 
+ unlock:
 	spin_unlock(&sh->lock);
 
+	/* wait for this device to become unblocked */
+	if (unlikely(blocked_rdev))
+		md_wait_for_blocked_rdev(blocked_rdev, conf->mddev);
+
 	return_io(return_bi);
 
 	for (i=disks; i-- ;) {
@@ -4223,6 +4257,7 @@ static int run(mddev_t *mddev)
 			goto abort;
 	}
 	spin_lock_init(&conf->device_lock);
+	mddev->queue->queue_lock = &conf->device_lock;
 	init_waitqueue_head(&conf->wait_for_stripe);
 	init_waitqueue_head(&conf->wait_for_overlap);
 	INIT_LIST_HEAD(&conf->handle_list);