Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6

1 files changed, 61 insertions, 33 deletions

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 087eee0cb809..3b27df52456b 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -94,6 +94,8 @@
 #define __inline__
 #endif
 
+#define printk_rl(args...) ((void) (printk_ratelimit() && printk(args)))
+
 #if !RAID6_USE_EMPTY_ZERO_PAGE
 /* In .bss so it's zeroed */
 const char raid6_empty_zero_page[PAGE_SIZE] __attribute__((aligned(256)));
@@ -1143,10 +1145,12 @@ static void raid5_end_read_request(struct bio * bi, int error)
 		set_bit(R5_UPTODATE, &sh->dev[i].flags);
 		if (test_bit(R5_ReadError, &sh->dev[i].flags)) {
 			rdev = conf->disks[i].rdev;
-			printk(KERN_INFO "raid5:%s: read error corrected (%lu sectors at %llu on %s)\n",
-			       mdname(conf->mddev), STRIPE_SECTORS,
-			       (unsigned long long)(sh->sector + rdev->data_offset),
-			       bdevname(rdev->bdev, b));
+			printk_rl(KERN_INFO "raid5:%s: read error corrected"
+				  " (%lu sectors at %llu on %s)\n",
+				  mdname(conf->mddev), STRIPE_SECTORS,
+				  (unsigned long long)(sh->sector
+						       + rdev->data_offset),
+				  bdevname(rdev->bdev, b));
 			clear_bit(R5_ReadError, &sh->dev[i].flags);
 			clear_bit(R5_ReWrite, &sh->dev[i].flags);
 		}
@@ -1160,16 +1164,22 @@ static void raid5_end_read_request(struct bio * bi, int error)
 		clear_bit(R5_UPTODATE, &sh->dev[i].flags);
 		atomic_inc(&rdev->read_errors);
 		if (conf->mddev->degraded)
-			printk(KERN_WARNING "raid5:%s: read error not correctable (sector %llu on %s).\n",
-			       mdname(conf->mddev),
-			       (unsigned long long)(sh->sector + rdev->data_offset),
-			       bdn);
+			printk_rl(KERN_WARNING
+				  "raid5:%s: read error not correctable "
+				  "(sector %llu on %s).\n",
+				  mdname(conf->mddev),
+				  (unsigned long long)(sh->sector
+						       + rdev->data_offset),
+				  bdn);
 		else if (test_bit(R5_ReWrite, &sh->dev[i].flags))
 			/* Oh, no!!! */
-			printk(KERN_WARNING "raid5:%s: read error NOT corrected!! (sector %llu on %s).\n",
-			       mdname(conf->mddev),
-			       (unsigned long long)(sh->sector + rdev->data_offset),
-			       bdn);
+			printk_rl(KERN_WARNING
+				  "raid5:%s: read error NOT corrected!! "
+				  "(sector %llu on %s).\n",
+				  mdname(conf->mddev),
+				  (unsigned long long)(sh->sector
+						       + rdev->data_offset),
+				  bdn);
 		else if (atomic_read(&rdev->read_errors)
 			 > conf->max_nr_stripes)
 			printk(KERN_WARNING
@@ -1258,7 +1268,7 @@ static void error(mddev_t *mddev, mdk_rdev_t *rdev)
 			/*
 			 * if recovery was running, make sure it aborts.
 			 */
-			set_bit(MD_RECOVERY_ERR, &mddev->recovery);
+			set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 		}
 		set_bit(Faulty, &rdev->flags);
 		printk (KERN_ALERT
@@ -1992,6 +2002,7 @@ static int __handle_issuing_new_read_requests5(struct stripe_head *sh,
 		 * have quiesced.
 		 */
 		if ((s->uptodate == disks - 1) &&
+		    (s->failed && disk_idx == s->failed_num) &&
 		    !test_bit(STRIPE_OP_CHECK, &sh->ops.pending)) {
 			set_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending);
 			set_bit(R5_Wantcompute, &dev->flags);
@@ -2006,12 +2017,7 @@ static int __handle_issuing_new_read_requests5(struct stripe_head *sh,
 			 */
 			s->uptodate++;
 			return 0; /* uptodate + compute == disks */
-		} else if ((s->uptodate < disks - 1) &&
-			test_bit(R5_Insync, &dev->flags)) {
-			/* Note: we hold off compute operations while checks are
-			 * in flight, but we still prefer 'compute' over 'read'
-			 * hence we only read if (uptodate < * disks-1)
-			 */
+		} else if (test_bit(R5_Insync, &dev->flags)) {
 			set_bit(R5_LOCKED, &dev->flags);
 			set_bit(R5_Wantread, &dev->flags);
 			if (!test_and_set_bit(STRIPE_OP_IO, &sh->ops.pending))
@@ -2077,7 +2083,9 @@ static void handle_issuing_new_read_requests6(struct stripe_head *sh,
 			/* we would like to get this block, possibly
 			 * by computing it, but we might not be able to
 			 */
-			if (s->uptodate == disks-1) {
+			if ((s->uptodate == disks - 1) &&
+			    (s->failed && (i == r6s->failed_num[0] ||
+					   i == r6s->failed_num[1]))) {
 				pr_debug("Computing stripe %llu block %d\n",
 				       (unsigned long long)sh->sector, i);
 				compute_block_1(sh, i, 0);
@@ -2369,8 +2377,8 @@ 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 +2408,6 @@ 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 +2422,17 @@ 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
@@ -2634,6 +2643,7 @@ static void handle_stripe5(struct stripe_head *sh)
 	struct r5dev *dev;
 	unsigned long pending = 0;
 	mdk_rdev_t *blocked_rdev = NULL;
+	int prexor;
 
 	memset(&s, 0, sizeof(s));
 	pr_debug("handling stripe %llu, state=%#lx cnt=%d, pd_idx=%d "
@@ -2763,9 +2773,11 @@ static void handle_stripe5(struct stripe_head *sh)
 	/* leave prexor set until postxor is done, allows us to distinguish
 	 * a rmw from a rcw during biodrain
 	 */
+	prexor = 0;
 	if (test_bit(STRIPE_OP_PREXOR, &sh->ops.complete) &&
 		test_bit(STRIPE_OP_POSTXOR, &sh->ops.complete)) {
 
+		prexor = 1;
 		clear_bit(STRIPE_OP_PREXOR, &sh->ops.complete);
 		clear_bit(STRIPE_OP_PREXOR, &sh->ops.ack);
 		clear_bit(STRIPE_OP_PREXOR, &sh->ops.pending);
@@ -2799,6 +2811,8 @@ static void handle_stripe5(struct stripe_head *sh)
 				if (!test_and_set_bit(
 				    STRIPE_OP_IO, &sh->ops.pending))
 					sh->ops.count++;
+				if (prexor)
+					continue;
 				if (!test_bit(R5_Insync, &dev->flags) ||
 				    (i == sh->pd_idx && s.failed == 0))
 					set_bit(STRIPE_INSYNC, &sh->state);
@@ -2879,6 +2893,8 @@ static void handle_stripe5(struct stripe_head *sh)
 
 		for (i = conf->raid_disks; i--; ) {
 			set_bit(R5_Wantwrite, &sh->dev[i].flags);
+			set_bit(R5_LOCKED, &dev->flags);
+			s.locked++;
 			if (!test_and_set_bit(STRIPE_OP_IO, &sh->ops.pending))
 				sh->ops.count++;
 		}
@@ -2892,6 +2908,7 @@ static void handle_stripe5(struct stripe_head *sh)
 			conf->raid_disks);
 		s.locked += handle_write_operations5(sh, 1, 1);
 	} else if (s.expanded &&
+		   s.locked == 0 &&
 		!test_bit(STRIPE_OP_POSTXOR, &sh->ops.pending)) {
 		clear_bit(STRIPE_EXPAND_READY, &sh->state);
 		atomic_dec(&conf->reshape_stripes);
@@ -4256,6 +4273,7 @@ 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);
@@ -4285,7 +4303,9 @@ static int run(mddev_t *mddev)
 				" disk %d\n", bdevname(rdev->bdev,b),
 				raid_disk);
 			working_disks++;
-		}
+		} else
+			/* Cannot rely on bitmap to complete recovery */
+			conf->fullsync = 1;
 	}
 
 	/*
@@ -4562,6 +4582,14 @@ static int raid5_remove_disk(mddev_t *mddev, int number)
 			err = -EBUSY;
 			goto abort;
 		}
+		/* Only remove non-faulty devices if recovery
+		 * isn't possible.
+		 */
+		if (!test_bit(Faulty, &rdev->flags) &&
+		    mddev->degraded <= conf->max_degraded) {
+			err = -EBUSY;
+			goto abort;
+		}
 		p->rdev = NULL;
 		synchronize_rcu();
 		if (atomic_read(&rdev->nr_pending)) {