Merge branch 'md-fixes' of https://git.kernel.org/pub/scm/linux/kernel/git/song/md into block-5.10

Pull MD fixes from Song:

"This is to fix raid10 data corruption [1] in 5.10-rc7."

* 'md-fixes' of https://git.kernel.org/pub/scm/linux/kernel/git/song/md:
  Revert "md: add md_submit_discard_bio() for submitting discard bio"
  Revert "md/raid10: extend r10bio devs to raid disks"
  Revert "md/raid10: pull codes that wait for blocked dev into one function"
  Revert "md/raid10: improve raid10 discard request"
  Revert "md/raid10: improve discard request for far layout"
  Revert "dm raid: remove unnecessary discard limits for raid10"

drivers/md/dm-raid.c

@@ -3728,6 +3728,17 @@ static void raid_io_hints(struct dm_target *ti, struct queue_limits *limits)
 
 	blk_limits_io_min(limits, chunk_size_bytes);
 	blk_limits_io_opt(limits, chunk_size_bytes * mddev_data_stripes(rs));
+
+	/*
+	 * RAID10 personality requires bio splitting,
+	 * RAID0/1/4/5/6 don't and process large discard bios properly.
+	 */
+	if (rs_is_raid10(rs)) {
+		limits->discard_granularity = max(chunk_size_bytes,
+						  limits->discard_granularity);
+		limits->max_discard_sectors = min_not_zero(rs->md.chunk_sectors,
+							   limits->max_discard_sectors);
+	}
 }
 
 static void raid_postsuspend(struct dm_target *ti)

drivers/md/md.c

@@ -8582,26 +8582,6 @@ void md_write_end(struct mddev *mddev)
 
 EXPORT_SYMBOL(md_write_end);
 
-/* This is used by raid0 and raid10 */
-void md_submit_discard_bio(struct mddev *mddev, struct md_rdev *rdev,
-			struct bio *bio, sector_t start, sector_t size)
-{
-	struct bio *discard_bio = NULL;
-
-	if (__blkdev_issue_discard(rdev->bdev, start, size,
-		GFP_NOIO, 0, &discard_bio) || !discard_bio)
-		return;
-
-	bio_chain(discard_bio, bio);
-	bio_clone_blkg_association(discard_bio, bio);
-	if (mddev->gendisk)
-		trace_block_bio_remap(bdev_get_queue(rdev->bdev),
-			discard_bio, disk_devt(mddev->gendisk),
-			bio->bi_iter.bi_sector);
-	submit_bio_noacct(discard_bio);
-}
-EXPORT_SYMBOL(md_submit_discard_bio);
-
 /* md_allow_write(mddev)
  * Calling this ensures that the array is marked 'active' so that writes
  * may proceed without blocking.  It is important to call this before

drivers/md/md.h

@@ -713,8 +713,6 @@ extern void md_write_end(struct mddev *mddev);
 extern void md_done_sync(struct mddev *mddev, int blocks, int ok);
 extern void md_error(struct mddev *mddev, struct md_rdev *rdev);
 extern void md_finish_reshape(struct mddev *mddev);
-extern void md_submit_discard_bio(struct mddev *mddev, struct md_rdev *rdev,
-			struct bio *bio, sector_t start, sector_t size);
 
 extern bool __must_check md_flush_request(struct mddev *mddev, struct bio *bio);
 extern void md_super_write(struct mddev *mddev, struct md_rdev *rdev,

drivers/md/raid0.c

@@ -477,6 +477,7 @@ static void raid0_handle_discard(struct mddev *mddev, struct bio *bio)
 
 	for (disk = 0; disk < zone->nb_dev; disk++) {
 		sector_t dev_start, dev_end;
+		struct bio *discard_bio = NULL;
 		struct md_rdev *rdev;
 
 		if (disk < start_disk_index)
@@ -499,9 +500,18 @@ static void raid0_handle_discard(struct mddev *mddev, struct bio *bio)
 
 		rdev = conf->devlist[(zone - conf->strip_zone) *
 			conf->strip_zone[0].nb_dev + disk];
-		md_submit_discard_bio(mddev, rdev, bio,
+		if (__blkdev_issue_discard(rdev->bdev,
 			dev_start + zone->dev_start + rdev->data_offset,
-			dev_end - dev_start);
+			dev_end - dev_start, GFP_NOIO, 0, &discard_bio) ||
+		    !discard_bio)
+			continue;
+		bio_chain(discard_bio, bio);
+		bio_clone_blkg_association(discard_bio, bio);
+		if (mddev->gendisk)
+			trace_block_bio_remap(bdev_get_queue(rdev->bdev),
+				discard_bio, disk_devt(mddev->gendisk),
+				bio->bi_iter.bi_sector);
+		submit_bio_noacct(discard_bio);
 	}
 	bio_endio(bio);
 }

drivers/md/raid10.h

@@ -179,6 +179,5 @@ enum r10bio_state {
 	R10BIO_Previous,
 /* failfast devices did receive failfast requests. */
 	R10BIO_FailFast,
-	R10BIO_Discard,
 };
 #endif