X-Git-Url: https://git.karo-electronics.de/?a=blobdiff_plain;f=drivers%2Fmd%2Fraid5.c;h=9768a7d67148225ccafad99f473c1d4bc107729a;hb=bc2607f393bd4fb844c1886a02af929ca0372056;hp=719445004dd992b95792127aa42f1c3e1680abfd;hpb=34b343cff4354ab9864be83be88405fd53d928a0;p=karo-tx-linux.git

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 719445004dd9..9768a7d67148 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -1658,8 +1658,10 @@ static void raid5_end_write_request(struct bio *bi, int error)
 		return;
 	}
 
-	if (!uptodate)
-		md_error(conf->mddev, conf->disks[i].rdev);
+	if (!uptodate) {
+		set_bit(WriteErrorSeen, &conf->disks[i].rdev->flags);
+		set_bit(R5_WriteError, &sh->dev[i].flags);
+	}
 
 	rdev_dec_pending(conf->disks[i].rdev, conf->mddev);
 	
@@ -1706,6 +1708,7 @@ static void error(mddev_t *mddev, mdk_rdev_t *rdev)
 		 */
 		set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 	}
+	set_bit(Blocked, &rdev->flags);
 	set_bit(Faulty, &rdev->flags);
 	set_bit(MD_CHANGE_DEVS, &mddev->flags);
 	printk(KERN_ALERT
@@ -2231,9 +2234,18 @@ handle_failed_stripe(raid5_conf_t *conf, struct stripe_head *sh,
 			rcu_read_lock();
 			rdev = rcu_dereference(conf->disks[i].rdev);
 			if (rdev && test_bit(In_sync, &rdev->flags))
-				/* multiple read failures in one stripe */
-				md_error(conf->mddev, rdev);
+				atomic_inc(&rdev->nr_pending);
+			else
+				rdev = NULL;
 			rcu_read_unlock();
+			if (rdev) {
+				if (!rdev_set_badblocks(
+					    rdev,
+					    sh->sector,
+					    STRIPE_SECTORS, 0))
+					md_error(conf->mddev, rdev);
+				rdev_dec_pending(rdev, conf->mddev);
+			}
 		}
 		spin_lock_irq(&conf->device_lock);
 		/* fail all writes first */
@@ -2312,6 +2324,41 @@ handle_failed_stripe(raid5_conf_t *conf, struct stripe_head *sh,
 			md_wakeup_thread(conf->mddev->thread);
 }
 
+static void
+handle_failed_sync(raid5_conf_t *conf, struct stripe_head *sh,
+		   struct stripe_head_state *s)
+{
+	int abort = 0;
+	int i;
+
+	md_done_sync(conf->mddev, STRIPE_SECTORS, 0);
+	clear_bit(STRIPE_SYNCING, &sh->state);
+	s->syncing = 0;
+	/* There is nothing more to do for sync/check/repair.
+	 * For recover we need to record a bad block on all
+	 * non-sync devices, or abort the recovery
+	 */
+	if (!test_bit(MD_RECOVERY_RECOVER, &conf->mddev->recovery))
+		return;
+	/* During recovery devices cannot be removed, so locking and
+	 * refcounting of rdevs is not needed
+	 */
+	for (i = 0; i < conf->raid_disks; i++) {
+		mdk_rdev_t *rdev = conf->disks[i].rdev;
+		if (!rdev
+		    || test_bit(Faulty, &rdev->flags)
+		    || test_bit(In_sync, &rdev->flags))
+			continue;
+		if (!rdev_set_badblocks(rdev, sh->sector,
+					STRIPE_SECTORS, 0))
+			abort = 1;
+	}
+	if (abort) {
+		conf->recovery_disabled = conf->mddev->recovery_disabled;
+		set_bit(MD_RECOVERY_INTR, &conf->mddev->recovery);
+	}
+}
+
 /* fetch_block - checks the given member device to see if its data needs
  * to be read or computed to satisfy a request.
  *
@@ -2922,6 +2969,9 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s)
 	spin_lock_irq(&conf->device_lock);
 	for (i=disks; i--; ) {
 		mdk_rdev_t *rdev;
+		sector_t first_bad;
+		int bad_sectors;
+		int is_bad = 0;
 
 		dev = &sh->dev[i];
 
@@ -2958,21 +3008,46 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s)
 		if (dev->written)
 			s->written++;
 		rdev = rcu_dereference(conf->disks[i].rdev);
-		if (s->blocked_rdev == NULL &&
-		    rdev && unlikely(test_bit(Blocked, &rdev->flags))) {
-			s->blocked_rdev = rdev;
-			atomic_inc(&rdev->nr_pending);
+		if (rdev) {
+			is_bad = is_badblock(rdev, sh->sector, STRIPE_SECTORS,
+					     &first_bad, &bad_sectors);
+			if (s->blocked_rdev == NULL
+			    && (test_bit(Blocked, &rdev->flags)
+				|| is_bad < 0)) {
+				if (is_bad < 0)
+					set_bit(BlockedBadBlocks,
+						&rdev->flags);
+				s->blocked_rdev = rdev;
+				atomic_inc(&rdev->nr_pending);
+			}
 		}
 		clear_bit(R5_Insync, &dev->flags);
 		if (!rdev)
 			/* Not in-sync */;
-		else if (test_bit(In_sync, &rdev->flags))
+		else if (is_bad) {
+			/* also not in-sync */
+			if (!test_bit(WriteErrorSeen, &rdev->flags)) {
+				/* treat as in-sync, but with a read error
+				 * which we can now try to correct
+				 */
+				set_bit(R5_Insync, &dev->flags);
+				set_bit(R5_ReadError, &dev->flags);
+			}
+		} else if (test_bit(In_sync, &rdev->flags))
 			set_bit(R5_Insync, &dev->flags);
 		else {
 			/* in sync if before recovery_offset */
 			if (sh->sector + STRIPE_SECTORS <= rdev->recovery_offset)
 				set_bit(R5_Insync, &dev->flags);
 		}
+		if (test_bit(R5_WriteError, &dev->flags)) {
+			clear_bit(R5_Insync, &dev->flags);
+			if (!test_bit(Faulty, &rdev->flags)) {
+				s->handle_bad_blocks = 1;
+				atomic_inc(&rdev->nr_pending);
+			} else
+				clear_bit(R5_WriteError, &dev->flags);
+		}
 		if (!test_bit(R5_Insync, &dev->flags)) {
 			/* The ReadError flag will just be confusing now */
 			clear_bit(R5_ReadError, &dev->flags);
@@ -3021,6 +3096,11 @@ static void handle_stripe(struct stripe_head *sh)
 
 	analyse_stripe(sh, &s);
 
+	if (s.handle_bad_blocks) {
+		set_bit(STRIPE_HANDLE, &sh->state);
+		goto finish;
+	}
+
 	if (unlikely(s.blocked_rdev)) {
 		if (s.syncing || s.expanding || s.expanded ||
 		    s.to_write || s.written) {
@@ -3046,11 +3126,8 @@ static void handle_stripe(struct stripe_head *sh)
 	 */
 	if (s.failed > conf->max_degraded && s.to_read+s.to_write+s.written)
 		handle_failed_stripe(conf, sh, &s, disks, &s.return_bi);
-	if (s.failed > conf->max_degraded && s.syncing) {
-		md_done_sync(conf->mddev, STRIPE_SECTORS, 0);
-		clear_bit(STRIPE_SYNCING, &sh->state);
-		s.syncing = 0;
-	}
+	if (s.failed > conf->max_degraded && s.syncing)
+		handle_failed_sync(conf, sh, &s);
 
 	/*
 	 * might be able to return some write requests if the parity blocks
@@ -3221,6 +3298,20 @@ finish:
 	if (unlikely(s.blocked_rdev))
 		md_wait_for_blocked_rdev(s.blocked_rdev, conf->mddev);
 
+	if (s.handle_bad_blocks)
+		for (i = disks; i--; ) {
+			mdk_rdev_t *rdev;
+			struct r5dev *dev = &sh->dev[i];
+			if (test_and_clear_bit(R5_WriteError, &dev->flags)) {
+				/* We own a safe reference to the rdev */
+				rdev = conf->disks[i].rdev;
+				if (!rdev_set_badblocks(rdev, sh->sector,
+							STRIPE_SECTORS, 0))
+					md_error(conf->mddev, rdev);
+				rdev_dec_pending(rdev, conf->mddev);
+			}
+		}
+
 	if (s.ops_request)
 		raid_run_ops(sh, s.ops_request);
 
@@ -3470,6 +3561,9 @@ static int chunk_aligned_read(mddev_t *mddev, struct bio * raid_bio)
 	rcu_read_lock();
 	rdev = rcu_dereference(conf->disks[dd_idx].rdev);
 	if (rdev && test_bit(In_sync, &rdev->flags)) {
+		sector_t first_bad;
+		int bad_sectors;
+
 		atomic_inc(&rdev->nr_pending);
 		rcu_read_unlock();
 		raid_bio->bi_next = (void*)rdev;
@@ -3477,8 +3571,10 @@ static int chunk_aligned_read(mddev_t *mddev, struct bio * raid_bio)
 		align_bi->bi_flags &= ~(1 << BIO_SEG_VALID);
 		align_bi->bi_sector += rdev->data_offset;
 
-		if (!bio_fits_rdev(align_bi)) {
-			/* too big in some way */
+		if (!bio_fits_rdev(align_bi) ||
+		    is_badblock(rdev, align_bi->bi_sector, align_bi->bi_size>>9,
+				&first_bad, &bad_sectors)) {
+			/* too big in some way, or has a known bad block */
 			bio_put(align_bi);
 			rdev_dec_pending(rdev, mddev);
 			return 0;
@@ -4143,6 +4239,9 @@ static void raid5d(mddev_t *mddev)
 		release_stripe(sh);
 		cond_resched();
 
+		if (mddev->flags & ~(1<<MD_CHANGE_PENDING))
+			md_check_recovery(mddev);
+
 		spin_lock_irq(&conf->device_lock);
 	}
 	pr_debug("%d stripes handled\n", handled);
@@ -4667,10 +4766,6 @@ static int run(mddev_t *mddev)
 	 * 0 for a fully functional array, 1 or 2 for a degraded array.
 	 */
 	list_for_each_entry(rdev, &mddev->disks, same_set) {
-		if (rdev->badblocks.count) {
-			printk(KERN_ERR "md/raid5: cannot handle bad blocks yet\n");
-			goto abort;
-		}
 		if (rdev->raid_disk < 0)
 			continue;
 		if (test_bit(In_sync, &rdev->flags)) {
@@ -4951,6 +5046,7 @@ static int raid5_remove_disk(mddev_t *mddev, int number)
 		 * isn't possible.
 		 */
 		if (!test_bit(Faulty, &rdev->flags) &&
+		    mddev->recovery_disabled != conf->recovery_disabled &&
 		    !has_failed(conf) &&
 		    number < conf->raid_disks) {
 			err = -EBUSY;
@@ -4979,8 +5075,8 @@ static int raid5_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
 	int first = 0;
 	int last = conf->raid_disks - 1;
 
-	if (rdev->badblocks.count)
-		return -EINVAL;
+	if (mddev->recovery_disabled == conf->recovery_disabled)
+		return -EBUSY;
 
 	if (has_failed(conf))
 		/* no point adding a device */