1 files changed, 43 insertions, 40 deletions

diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 76a75925b713..95dc354a86a0 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -24,6 +24,7 @@
 #include "raid10.h"
 #include "raid0.h"
 #include "md-bitmap.h"
+#include "md-cluster.h"
 
 /*
  * RAID10 provides a combination of RAID0 and RAID1 functionality.
@@ -398,6 +399,8 @@ static void raid10_end_read_request(struct bio *bio)
 		 * wait for the 'master' bio.
 		 */
 		set_bit(R10BIO_Uptodate, &r10_bio->state);
+	} else if (!raid1_should_handle_error(bio)) {
+		uptodate = 1;
 	} else {
 		/* If all other devices that store this block have
 		 * failed, we want to return the error upwards rather
@@ -455,9 +458,8 @@ static void raid10_end_write_request(struct bio *bio)
 	int slot, repl;
 	struct md_rdev *rdev = NULL;
 	struct bio *to_put = NULL;
-	bool discard_error;
-
-	discard_error = bio->bi_status && bio_op(bio) == REQ_OP_DISCARD;
+	bool ignore_error = !raid1_should_handle_error(bio) ||
+		(bio->bi_status && bio_op(bio) == REQ_OP_DISCARD);
 
 	dev = find_bio_disk(conf, r10_bio, bio, &slot, &repl);
 
@@ -471,7 +473,7 @@ static void raid10_end_write_request(struct bio *bio)
 	/*
 	 * this branch is our 'one mirror IO has finished' event handler:
 	 */
-	if (bio->bi_status && !discard_error) {
+	if (bio->bi_status && !ignore_error) {
 		if (repl)
 			/* Never record new bad blocks to replacement,
 			 * just fail it.
@@ -526,7 +528,7 @@ static void raid10_end_write_request(struct bio *bio)
 		/* Maybe we can clear some bad blocks. */
 		if (rdev_has_badblock(rdev, r10_bio->devs[slot].addr,
 				      r10_bio->sectors) &&
-		    !discard_error) {
+		    !ignore_error) {
 			bio_put(bio);
 			if (repl)
 				r10_bio->devs[slot].repl_bio = IO_MADE_GOOD;
@@ -1180,8 +1182,11 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio,
 		}
 	}
 
-	if (!regular_request_wait(mddev, conf, bio, r10_bio->sectors))
+	if (!regular_request_wait(mddev, conf, bio, r10_bio->sectors)) {
+		raid_end_bio_io(r10_bio);
 		return;
+	}
+
 	rdev = read_balance(conf, r10_bio, &max_sectors);
 	if (!rdev) {
 		if (err_rdev) {
@@ -1219,6 +1224,7 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio,
 		r10_bio->master_bio = bio;
 	}
 	read_bio = bio_alloc_clone(rdev->bdev, bio, gfp, &mddev->bio_set);
+	read_bio->bi_opf &= ~REQ_NOWAIT;
 
 	r10_bio->devs[slot].bio = read_bio;
 	r10_bio->devs[slot].rdev = rdev;
@@ -1254,6 +1260,7 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio,
 			     conf->mirrors[devnum].rdev;
 
 	mbio = bio_alloc_clone(rdev->bdev, bio, GFP_NOIO, &mddev->bio_set);
+	mbio->bi_opf &= ~REQ_NOWAIT;
 	if (replacement)
 		r10_bio->devs[n_copy].repl_bio = mbio;
 	else
@@ -1347,9 +1354,9 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio,
 	int error;
 
 	if ((mddev_is_clustered(mddev) &&
-	     md_cluster_ops->area_resyncing(mddev, WRITE,
-					    bio->bi_iter.bi_sector,
-					    bio_end_sector(bio)))) {
+	     mddev->cluster_ops->area_resyncing(mddev, WRITE,
+						bio->bi_iter.bi_sector,
+						bio_end_sector(bio)))) {
 		DEFINE_WAIT(w);
 		/* Bail out if REQ_NOWAIT is set for the bio */
 		if (bio->bi_opf & REQ_NOWAIT) {
@@ -1359,7 +1366,7 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio,
 		for (;;) {
 			prepare_to_wait(&conf->wait_barrier,
 					&w, TASK_IDLE);
-			if (!md_cluster_ops->area_resyncing(mddev, WRITE,
+			if (!mddev->cluster_ops->area_resyncing(mddev, WRITE,
 				 bio->bi_iter.bi_sector, bio_end_sector(bio)))
 				break;
 			schedule();
@@ -1368,8 +1375,11 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio,
 	}
 
 	sectors = r10_bio->sectors;
-	if (!regular_request_wait(mddev, conf, bio, sectors))
+	if (!regular_request_wait(mddev, conf, bio, sectors)) {
+		raid_end_bio_io(r10_bio);
 		return;
+	}
+
 	if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) &&
 	    (mddev->reshape_backwards
 	     ? (bio->bi_iter.bi_sector < conf->reshape_safe &&
@@ -2425,7 +2435,6 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio)
 
 		atomic_inc(&conf->mirrors[d].rdev->nr_pending);
 		atomic_inc(&r10_bio->remaining);
-		md_sync_acct(conf->mirrors[d].rdev->bdev, bio_sectors(tbio));
 
 		if (test_bit(FailFast, &conf->mirrors[d].rdev->flags))
 			tbio->bi_opf |= MD_FAILFAST;
@@ -2437,18 +2446,13 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio)
 	 * that are active
 	 */
 	for (i = 0; i < conf->copies; i++) {
-		int d;
-
 		tbio = r10_bio->devs[i].repl_bio;
 		if (!tbio || !tbio->bi_end_io)
 			continue;
 		if (r10_bio->devs[i].bio->bi_end_io != end_sync_write
 		    && r10_bio->devs[i].bio != fbio)
 			bio_copy_data(tbio, fbio);
-		d = r10_bio->devs[i].devnum;
 		atomic_inc(&r10_bio->remaining);
-		md_sync_acct(conf->mirrors[d].replacement->bdev,
-			     bio_sectors(tbio));
 		submit_bio_noacct(tbio);
 	}
 
@@ -2582,13 +2586,10 @@ static void recovery_request_write(struct mddev *mddev, struct r10bio *r10_bio)
 	d = r10_bio->devs[1].devnum;
 	if (wbio->bi_end_io) {
 		atomic_inc(&conf->mirrors[d].rdev->nr_pending);
-		md_sync_acct(conf->mirrors[d].rdev->bdev, bio_sectors(wbio));
 		submit_bio_noacct(wbio);
 	}
 	if (wbio2) {
 		atomic_inc(&conf->mirrors[d].replacement->nr_pending);
-		md_sync_acct(conf->mirrors[d].replacement->bdev,
-			     bio_sectors(wbio2));
 		submit_bio_noacct(wbio2);
 	}
 }
@@ -2778,7 +2779,7 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10
 	}
 }
 
-static int narrow_write_error(struct r10bio *r10_bio, int i)
+static bool narrow_write_error(struct r10bio *r10_bio, int i)
 {
 	struct bio *bio = r10_bio->master_bio;
 	struct mddev *mddev = r10_bio->mddev;
@@ -2799,10 +2800,10 @@ static int narrow_write_error(struct r10bio *r10_bio, int i)
 	sector_t sector;
 	int sectors;
 	int sect_to_write = r10_bio->sectors;
-	int ok = 1;
+	bool ok = true;
 
 	if (rdev->badblocks.shift < 0)
-		return 0;
+		return false;
 
 	block_sectors = roundup(1 << rdev->badblocks.shift,
 				bdev_logical_block_size(rdev->bdev) >> 9);
@@ -3708,7 +3709,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 			conf->cluster_sync_low = mddev->curr_resync_completed;
 			raid10_set_cluster_sync_high(conf);
 			/* Send resync message */
-			md_cluster_ops->resync_info_update(mddev,
+			mddev->cluster_ops->resync_info_update(mddev,
 						conf->cluster_sync_low,
 						conf->cluster_sync_high);
 		}
@@ -3741,7 +3742,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 		}
 		if (broadcast_msg) {
 			raid10_set_cluster_sync_high(conf);
-			md_cluster_ops->resync_info_update(mddev,
+			mddev->cluster_ops->resync_info_update(mddev,
 						conf->cluster_sync_low,
 						conf->cluster_sync_high);
 		}
@@ -3756,7 +3757,6 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 		r10_bio->sectors = nr_sectors;
 
 		if (bio->bi_end_io == end_sync_read) {
-			md_sync_acct_bio(bio, nr_sectors);
 			bio->bi_status = 0;
 			submit_bio_noacct(bio);
 		}
@@ -4009,6 +4009,7 @@ static int raid10_set_queue_limits(struct mddev *mddev)
 	md_init_stacking_limits(&lim);
 	lim.max_write_zeroes_sectors = 0;
 	lim.io_min = mddev->chunk_sectors << 9;
+	lim.chunk_sectors = mddev->chunk_sectors;
 	lim.io_opt = lim.io_min * raid10_nr_stripes(conf);
 	lim.features |= BLK_FEAT_ATOMIC_WRITES;
 	err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY);
@@ -4533,7 +4534,7 @@ static int raid10_start_reshape(struct mddev *mddev)
 		if (ret)
 			goto abort;
 
-		ret = md_cluster_ops->resize_bitmaps(mddev, newsize, oldsize);
+		ret = mddev->cluster_ops->resize_bitmaps(mddev, newsize, oldsize);
 		if (ret) {
 			mddev->bitmap_ops->resize(mddev, oldsize, 0, false);
 			goto abort;
@@ -4824,7 +4825,7 @@ read_more:
 				conf->cluster_sync_low = sb_reshape_pos;
 		}
 
-		md_cluster_ops->resync_info_update(mddev, conf->cluster_sync_low,
+		mddev->cluster_ops->resync_info_update(mddev, conf->cluster_sync_low,
 							  conf->cluster_sync_high);
 	}
 
@@ -4879,7 +4880,6 @@ read_more:
 	r10_bio->sectors = nr_sectors;
 
 	/* Now submit the read */
-	md_sync_acct_bio(read_bio, r10_bio->sectors);
 	atomic_inc(&r10_bio->remaining);
 	read_bio->bi_next = NULL;
 	submit_bio_noacct(read_bio);
@@ -4939,7 +4939,6 @@ static void reshape_request_write(struct mddev *mddev, struct r10bio *r10_bio)
 			continue;
 
 		atomic_inc(&rdev->nr_pending);
-		md_sync_acct_bio(b, r10_bio->sectors);
 		atomic_inc(&r10_bio->remaining);
 		b->bi_next = NULL;
 		submit_bio_noacct(b);
@@ -4969,7 +4968,7 @@ static void raid10_update_reshape_pos(struct mddev *mddev)
 	struct r10conf *conf = mddev->private;
 	sector_t lo, hi;
 
-	md_cluster_ops->resync_info_get(mddev, &lo, &hi);
+	mddev->cluster_ops->resync_info_get(mddev, &lo, &hi);
 	if (((mddev->reshape_position <= hi) && (mddev->reshape_position >= lo))
 	    || mddev->reshape_position == MaxSector)
 		conf->reshape_progress = mddev->reshape_position;
@@ -5115,9 +5114,13 @@ static void raid10_finish_reshape(struct mddev *mddev)
 
 static struct md_personality raid10_personality =
 {
-	.name		= "raid10",
-	.level		= 10,
-	.owner		= THIS_MODULE,
+	.head = {
+		.type	= MD_PERSONALITY,
+		.id	= ID_RAID10,
+		.name	= "raid10",
+		.owner	= THIS_MODULE,
+	},
+
 	.make_request	= raid10_make_request,
 	.run		= raid10_run,
 	.free		= raid10_free,
@@ -5137,18 +5140,18 @@ static struct md_personality raid10_personality =
 	.update_reshape_pos = raid10_update_reshape_pos,
 };
 
-static int __init raid_init(void)
+static int __init raid10_init(void)
 {
-	return register_md_personality(&raid10_personality);
+	return register_md_submodule(&raid10_personality.head);
 }
 
-static void raid_exit(void)
+static void __exit raid10_exit(void)
 {
-	unregister_md_personality(&raid10_personality);
+	unregister_md_submodule(&raid10_personality.head);
 }
 
-module_init(raid_init);
-module_exit(raid_exit);
+module_init(raid10_init);
+module_exit(raid10_exit);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("RAID10 (striped mirror) personality for MD");
 MODULE_ALIAS("md-personality-9"); /* RAID10 */