Merge commit 'v4.9-rc5' into next

9 files changed, 58 insertions, 63 deletions

diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 8abde6b..6d53810 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -266,7 +266,7 @@ static struct raid_type {
 	{"raid10_offset", "raid10 offset (striped mirrors)",	    0, 2, 10, ALGORITHM_RAID10_OFFSET},
 	{"raid10_near",	  "raid10 near (striped mirrors)",	    0, 2, 10, ALGORITHM_RAID10_NEAR},
 	{"raid10",	  "raid10 (striped mirrors)",		    0, 2, 10, ALGORITHM_RAID10_DEFAULT},
-	{"raid4",	  "raid4 (dedicated last parity disk)",	    1, 2, 4,  ALGORITHM_PARITY_N}, /* raid4 layout = raid5_n */
+	{"raid4",	  "raid4 (dedicated first parity disk)",    1, 2, 5,  ALGORITHM_PARITY_0}, /* raid4 layout = raid5_0 */
 	{"raid5_n",	  "raid5 (dedicated last parity disk)",	    1, 2, 5,  ALGORITHM_PARITY_N},
 	{"raid5_ls",	  "raid5 (left symmetric)",		    1, 2, 5,  ALGORITHM_LEFT_SYMMETRIC},
 	{"raid5_rs",	  "raid5 (right symmetric)",		    1, 2, 5,  ALGORITHM_RIGHT_SYMMETRIC},
@@ -2087,11 +2087,11 @@ static int super_init_validation(struct raid_set *rs, struct md_rdev *rdev)
 		/*
 		 * No takeover/reshaping, because we don't have the extended v1.9.0 metadata
 		 */
-		if (le32_to_cpu(sb->level) != mddev->level) {
+		if (le32_to_cpu(sb->level) != mddev->new_level) {
 			DMERR("Reshaping/takeover raid sets not yet supported. (raid level/stripes/size change)");
 			return -EINVAL;
 		}
-		if (le32_to_cpu(sb->layout) != mddev->layout) {
+		if (le32_to_cpu(sb->layout) != mddev->new_layout) {
 			DMERR("Reshaping raid sets not yet supported. (raid layout change)");
 			DMERR("	 0x%X vs 0x%X", le32_to_cpu(sb->layout), mddev->layout);
 			DMERR("	 Old layout: %s w/ %d copies",
@@ -2102,7 +2102,7 @@ static int super_init_validation(struct raid_set *rs, struct md_rdev *rdev)
 			      raid10_md_layout_to_copies(mddev->layout));
 			return -EINVAL;
 		}
-		if (le32_to_cpu(sb->stripe_sectors) != mddev->chunk_sectors) {
+		if (le32_to_cpu(sb->stripe_sectors) != mddev->new_chunk_sectors) {
 			DMERR("Reshaping raid sets not yet supported. (stripe sectors change)");
 			return -EINVAL;
 		}
@@ -2115,6 +2115,8 @@ static int super_init_validation(struct raid_set *rs, struct md_rdev *rdev)
 			return -EINVAL;
 		}
 
+		DMINFO("Discovered old metadata format; upgrading to extended metadata format");
+
 		/* Table line is checked vs. authoritative superblock */
 		rs_set_new(rs);
 	}
@@ -2258,7 +2260,8 @@ static int super_validate(struct raid_set *rs, struct md_rdev *rdev)
 	if (!mddev->events && super_init_validation(rs, rdev))
 		return -EINVAL;
 
-	if (le32_to_cpu(sb->compat_features) != FEATURE_FLAG_SUPPORTS_V190) {
+	if (le32_to_cpu(sb->compat_features) &&
+	    le32_to_cpu(sb->compat_features) != FEATURE_FLAG_SUPPORTS_V190) {
 		rs->ti->error = "Unable to assemble array: Unknown flag(s) in compatible feature flags";
 		return -EINVAL;
 	}
@@ -3646,7 +3649,7 @@ static void raid_resume(struct dm_target *ti)
 
 static struct target_type raid_target = {
 	.name = "raid",
-	.version = {1, 9, 0},
+	.version = {1, 9, 1},
 	.module = THIS_MODULE,
 	.ctr = raid_ctr,
 	.dtr = raid_dtr,
diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c
index bdf1606..9a8b710 100644
--- a/drivers/md/dm-raid1.c
+++ b/drivers/md/dm-raid1.c
@@ -145,7 +145,6 @@ static void dispatch_bios(void *context, struct bio_list *bio_list)
 
 struct dm_raid1_bio_record {
 	struct mirror *m;
-	/* if details->bi_bdev == NULL, details were not saved */
 	struct dm_bio_details details;
 	region_t write_region;
 };
@@ -1200,8 +1199,6 @@ static int mirror_map(struct dm_target *ti, struct bio *bio)
 	struct dm_raid1_bio_record *bio_record =
 	  dm_per_bio_data(bio, sizeof(struct dm_raid1_bio_record));
 
-	bio_record->details.bi_bdev = NULL;
-
 	if (rw == WRITE) {
 		/* Save region for mirror_end_io() handler */
 		bio_record->write_region = dm_rh_bio_to_region(ms->rh, bio);
@@ -1260,22 +1257,12 @@ static int mirror_end_io(struct dm_target *ti, struct bio *bio, int error)
 	}
 
 	if (error == -EOPNOTSUPP)
-		goto out;
+		return error;
 
 	if ((error == -EWOULDBLOCK) && (bio->bi_opf & REQ_RAHEAD))
-		goto out;
+		return error;
 
 	if (unlikely(error)) {
-		if (!bio_record->details.bi_bdev) {
-			/*
-			 * There wasn't enough memory to record necessary
-			 * information for a retry or there was no other
-			 * mirror in-sync.
-			 */
-			DMERR_LIMIT("Mirror read failed.");
-			return -EIO;
-		}
-
 		m = bio_record->m;
 
 		DMERR("Mirror read failed from %s. Trying alternative device.",
@@ -1291,7 +1278,7 @@ static int mirror_end_io(struct dm_target *ti, struct bio *bio, int error)
 			bd = &bio_record->details;
 
 			dm_bio_restore(bd, bio);
-			bio_record->details.bi_bdev = NULL;
+			bio->bi_error = 0;
 
 			queue_bio(ms, bio, rw);
 			return DM_ENDIO_INCOMPLETE;
@@ -1299,9 +1286,6 @@ static int mirror_end_io(struct dm_target *ti, struct bio *bio, int error)
 		DMERR("All replicated volumes dead, failing I/O");
 	}
 
-out:
-	bio_record->details.bi_bdev = NULL;
-
 	return error;
 }
 
diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c
index dc75bea..1d0d2ad 100644
--- a/drivers/md/dm-rq.c
+++ b/drivers/md/dm-rq.c
@@ -856,8 +856,11 @@ int dm_old_init_request_queue(struct mapped_device *md)
 	kthread_init_worker(&md->kworker);
 	md->kworker_task = kthread_run(kthread_worker_fn, &md->kworker,
 				       "kdmwork-%s", dm_device_name(md));
-	if (IS_ERR(md->kworker_task))
-		return PTR_ERR(md->kworker_task);
+	if (IS_ERR(md->kworker_task)) {
+		int error = PTR_ERR(md->kworker_task);
+		md->kworker_task = NULL;
+		return error;
+	}
 
 	elv_register_queue(md->queue);
 
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 3e407a9..c4b53b3 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -695,37 +695,32 @@ int dm_table_add_target(struct dm_table *t, const char *type,
 
 	tgt->type = dm_get_target_type(type);
 	if (!tgt->type) {
-		DMERR("%s: %s: unknown target type", dm_device_name(t->md),
-		      type);
+		DMERR("%s: %s: unknown target type", dm_device_name(t->md), type);
 		return -EINVAL;
 	}
 
 	if (dm_target_needs_singleton(tgt->type)) {
 		if (t->num_targets) {
-			DMERR("%s: target type %s must appear alone in table",
-			      dm_device_name(t->md), type);
-			return -EINVAL;
+			tgt->error = "singleton target type must appear alone in table";
+			goto bad;
 		}
 		t->singleton = true;
 	}
 
 	if (dm_target_always_writeable(tgt->type) && !(t->mode & FMODE_WRITE)) {
-		DMERR("%s: target type %s may not be included in read-only tables",
-		      dm_device_name(t->md), type);
-		return -EINVAL;
+		tgt->error = "target type may not be included in a read-only table";
+		goto bad;
 	}
 
 	if (t->immutable_target_type) {
 		if (t->immutable_target_type != tgt->type) {
-			DMERR("%s: immutable target type %s cannot be mixed with other target types",
-			      dm_device_name(t->md), t->immutable_target_type->name);
-			return -EINVAL;
+			tgt->error = "immutable target type cannot be mixed with other target types";
+			goto bad;
 		}
 	} else if (dm_target_is_immutable(tgt->type)) {
 		if (t->num_targets) {
-			DMERR("%s: immutable target type %s cannot be mixed with other target types",
-			      dm_device_name(t->md), tgt->type->name);
-			return -EINVAL;
+			tgt->error = "immutable target type cannot be mixed with other target types";
+			goto bad;
 		}
 		t->immutable_target_type = tgt->type;
 	}
@@ -740,7 +735,6 @@ int dm_table_add_target(struct dm_table *t, const char *type,
 	 */
 	if (!adjoin(t, tgt)) {
 		tgt->error = "Gap in table";
-		r = -EINVAL;
 		goto bad;
 	}
 
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 147af95..ef7bf1d 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1423,8 +1423,6 @@ static void cleanup_mapped_device(struct mapped_device *md)
 	if (md->bs)
 		bioset_free(md->bs);
 
-	cleanup_srcu_struct(&md->io_barrier);
-
 	if (md->disk) {
 		spin_lock(&_minor_lock);
 		md->disk->private_data = NULL;
@@ -1436,6 +1434,8 @@ static void cleanup_mapped_device(struct mapped_device *md)
 	if (md->queue)
 		blk_cleanup_queue(md->queue);
 
+	cleanup_srcu_struct(&md->io_barrier);
+
 	if (md->bdev) {
 		bdput(md->bdev);
 		md->bdev = NULL;
diff --git a/drivers/md/md.c b/drivers/md/md.c
index eac84d8..2089d46 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -3887,10 +3887,10 @@ array_state_show(struct mddev *mddev, char *page)
 			st = read_auto;
 			break;
 		case 0:
-			if (mddev->in_sync)
-				st = clean;
-			else if (test_bit(MD_CHANGE_PENDING, &mddev->flags))
+			if (test_bit(MD_CHANGE_PENDING, &mddev->flags))
 				st = write_pending;
+			else if (mddev->in_sync)
+				st = clean;
 			else if (mddev->safemode)
 				st = active_idle;
 			else
@@ -8144,14 +8144,14 @@ void md_do_sync(struct md_thread *thread)
 
 	if (!test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) &&
 	    !test_bit(MD_RECOVERY_INTR, &mddev->recovery) &&
-	    mddev->curr_resync > 2) {
+	    mddev->curr_resync > 3) {
 		mddev->curr_resync_completed = mddev->curr_resync;
 		sysfs_notify(&mddev->kobj, NULL, "sync_completed");
 	}
 	mddev->pers->sync_request(mddev, max_sectors, &skipped);
 
 	if (!test_bit(MD_RECOVERY_CHECK, &mddev->recovery) &&
-	    mddev->curr_resync > 2) {
+	    mddev->curr_resync > 3) {
 		if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) {
 			if (test_bit(MD_RECOVERY_INTR, &mddev->recovery)) {
 				if (mddev->curr_resync >= mddev->recovery_cp) {
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 1961d82..29e2df5 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -403,11 +403,14 @@ static void raid1_end_write_request(struct bio *bio)
 	struct bio *to_put = NULL;
 	int mirror = find_bio_disk(r1_bio, bio);
 	struct md_rdev *rdev = conf->mirrors[mirror].rdev;
+	bool discard_error;
+
+	discard_error = bio->bi_error && bio_op(bio) == REQ_OP_DISCARD;
 
 	/*
 	 * 'one mirror IO has finished' event handler:
 	 */
-	if (bio->bi_error) {
+	if (bio->bi_error && !discard_error) {
 		set_bit(WriteErrorSeen,	&rdev->flags);
 		if (!test_and_set_bit(WantReplacement, &rdev->flags))
 			set_bit(MD_RECOVERY_NEEDED, &
@@ -444,7 +447,7 @@ static void raid1_end_write_request(struct bio *bio)
 
 		/* Maybe we can clear some bad blocks. */
 		if (is_badblock(rdev, r1_bio->sector, r1_bio->sectors,
-				&first_bad, &bad_sectors)) {
+				&first_bad, &bad_sectors) && !discard_error) {
 			r1_bio->bios[mirror] = IO_MADE_GOOD;
 			set_bit(R1BIO_MadeGood, &r1_bio->state);
 		}
@@ -2294,17 +2297,23 @@ static void handle_read_error(struct r1conf *conf, struct r1bio *r1_bio)
 	 * This is all done synchronously while the array is
 	 * frozen
 	 */
+
+	bio = r1_bio->bios[r1_bio->read_disk];
+	bdevname(bio->bi_bdev, b);
+	bio_put(bio);
+	r1_bio->bios[r1_bio->read_disk] = NULL;
+
 	if (mddev->ro == 0) {
 		freeze_array(conf, 1);
 		fix_read_error(conf, r1_bio->read_disk,
 			       r1_bio->sector, r1_bio->sectors);
 		unfreeze_array(conf);
-	} else
-		md_error(mddev, conf->mirrors[r1_bio->read_disk].rdev);
+	} else {
+		r1_bio->bios[r1_bio->read_disk] = IO_BLOCKED;
+	}
+
 	rdev_dec_pending(conf->mirrors[r1_bio->read_disk].rdev, conf->mddev);
 
-	bio = r1_bio->bios[r1_bio->read_disk];
-	bdevname(bio->bi_bdev, b);
 read_more:
 	disk = read_balance(conf, r1_bio, &max_sectors);
 	if (disk == -1) {
@@ -2315,11 +2324,6 @@ read_more:
 	} else {
 		const unsigned long do_sync
 			= r1_bio->master_bio->bi_opf & REQ_SYNC;
-		if (bio) {
-			r1_bio->bios[r1_bio->read_disk] =
-				mddev->ro ? IO_BLOCKED : NULL;
-			bio_put(bio);
-		}
 		r1_bio->read_disk = disk;
 		bio = bio_clone_mddev(r1_bio->master_bio, GFP_NOIO, mddev);
 		bio_trim(bio, r1_bio->sector - bio->bi_iter.bi_sector,
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index be1a9fc..39fddda 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -447,6 +447,9 @@ static void raid10_end_write_request(struct bio *bio)
 	struct r10conf *conf = r10_bio->mddev->private;
 	int slot, repl;
 	struct md_rdev *rdev = NULL;
+	bool discard_error;
+
+	discard_error = bio->bi_error && bio_op(bio) == REQ_OP_DISCARD;
 
 	dev = find_bio_disk(conf, r10_bio, bio, &slot, &repl);
 
@@ -460,7 +463,7 @@ static void raid10_end_write_request(struct bio *bio)
 	/*
 	 * this branch is our 'one mirror IO has finished' event handler:
 	 */
-	if (bio->bi_error) {
+	if (bio->bi_error && !discard_error) {
 		if (repl)
 			/* Never record new bad blocks to replacement,
 			 * just fail it.
@@ -503,7 +506,7 @@ static void raid10_end_write_request(struct bio *bio)
 		if (is_badblock(rdev,
 				r10_bio->devs[slot].addr,
 				r10_bio->sectors,
-				&first_bad, &bad_sectors)) {
+				&first_bad, &bad_sectors) && !discard_error) {
 			bio_put(bio);
 			if (repl)
 				r10_bio->devs[slot].repl_bio = IO_MADE_GOOD;
diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c
index 1b1ab4a..a227a9f 100644
--- a/drivers/md/raid5-cache.c
+++ b/drivers/md/raid5-cache.c
@@ -1087,7 +1087,7 @@ static int r5l_recovery_log(struct r5l_log *log)
 	 * 1's seq + 10 and let superblock points to meta2. The same recovery will
 	 * not think meta 3 is a valid meta, because its seq doesn't match
 	 */
-	if (ctx.seq > log->last_cp_seq + 1) {
+	if (ctx.seq > log->last_cp_seq) {
 		int ret;
 
 		ret = r5l_log_write_empty_meta_block(log, ctx.pos, ctx.seq + 10);
@@ -1096,6 +1096,8 @@ static int r5l_recovery_log(struct r5l_log *log)
 		log->seq = ctx.seq + 11;
 		log->log_start = r5l_ring_add(log, ctx.pos, BLOCK_SECTORS);
 		r5l_write_super(log, ctx.pos);
+		log->last_checkpoint = ctx.pos;
+		log->next_checkpoint = ctx.pos;
 	} else {
 		log->log_start = ctx.pos;
 		log->seq = ctx.seq;
@@ -1154,6 +1156,7 @@ create:
 	if (create_super) {
 		log->last_cp_seq = prandom_u32();
 		cp = 0;
+		r5l_log_write_empty_meta_block(log, cp, log->last_cp_seq);
 		/*
 		 * Make sure super points to correct address. Log might have
 		 * data very soon. If super hasn't correct log tail address,
@@ -1168,6 +1171,7 @@ create:
 	if (log->max_free_space > RECLAIM_MAX_FREE_SPACE)
 		log->max_free_space = RECLAIM_MAX_FREE_SPACE;
 	log->last_checkpoint = cp;
+	log->next_checkpoint = cp;
 
 	__free_page(page);