Merge tag 'md-6.15-20250312' of https://git.kernel.org/pub/scm/linux/kernel/git/mdraid/linux into for-6.15/block

Merge MD changes from Yu:

"- fix recovery can preempt resync (Li Nan)
 - fix md-bitmap IO limit (Su Yue)
 - fix raid10 discard with REQ_NOWAIT (Xiao Ni)
 - fix raid1 memory leak (Zheng Qixing)
 - fix mddev uaf (Yu Kuai)
 - fix raid1,raid10 IO flags (Yu Kuai)
 - some refactor and cleanup (Yu Kuai)"

* tag 'md-6.15-20250312' of https://git.kernel.org/pub/scm/linux/kernel/git/mdraid/linux:
  md/raid10: wait barrier before returning discard request with REQ_NOWAIT
  md/md-bitmap: fix wrong bitmap_limit for clustermd when write sb
  md/raid1,raid10: don't ignore IO flags
  md/raid5: merge reshape_progress checking inside get_reshape_loc()
  md: fix mddev uaf while iterating all_mddevs list
  md: switch md-cluster to use md_submodle_head
  md: don't export md_cluster_ops
  md/md-cluster: cleanup md_cluster_ops reference
  md: switch personalities to use md_submodule_head
  md: introduce struct md_submodule_head and APIs
  md: only include md-cluster.h if necessary
  md: merge common code into find_pers()
  md/raid1: fix memory leak in raid1_run() if no active rdev
  md: ensure resync is prioritized over recovery

1 files changed, 24 insertions, 28 deletions

diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index a8664e29aada..d412aeeafc18 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.
@@ -1146,8 +1147,6 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio,
 {
 	struct r10conf *conf = mddev->private;
 	struct bio *read_bio;
-	const enum req_op op = bio_op(bio);
-	const blk_opf_t do_sync = bio->bi_opf & REQ_SYNC;
 	int max_sectors;
 	struct md_rdev *rdev;
 	char b[BDEVNAME_SIZE];
@@ -1228,7 +1227,6 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio,
 	read_bio->bi_iter.bi_sector = r10_bio->devs[slot].addr +
 		choose_data_offset(r10_bio, rdev);
 	read_bio->bi_end_io = raid10_end_read_request;
-	read_bio->bi_opf = op | do_sync;
 	if (test_bit(FailFast, &rdev->flags) &&
 	    test_bit(R10BIO_FailFast, &r10_bio->state))
 	        read_bio->bi_opf |= MD_FAILFAST;
@@ -1247,10 +1245,6 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio,
 				  struct bio *bio, bool replacement,
 				  int n_copy)
 {
-	const enum req_op op = bio_op(bio);
-	const blk_opf_t do_sync = bio->bi_opf & REQ_SYNC;
-	const blk_opf_t do_fua = bio->bi_opf & REQ_FUA;
-	const blk_opf_t do_atomic = bio->bi_opf & REQ_ATOMIC;
 	unsigned long flags;
 	struct r10conf *conf = mddev->private;
 	struct md_rdev *rdev;
@@ -1269,7 +1263,6 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio,
 	mbio->bi_iter.bi_sector	= (r10_bio->devs[n_copy].addr +
 				   choose_data_offset(r10_bio, rdev));
 	mbio->bi_end_io	= raid10_end_write_request;
-	mbio->bi_opf = op | do_sync | do_fua | do_atomic;
 	if (!replacement && test_bit(FailFast,
 				     &conf->mirrors[devnum].rdev->flags)
 			 && enough(conf, devnum))
@@ -1355,9 +1348,9 @@ 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) {
@@ -1367,7 +1360,7 @@ 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();
@@ -1631,11 +1624,10 @@ static int raid10_handle_discard(struct mddev *mddev, struct bio *bio)
 	if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery))
 		return -EAGAIN;
 
-	if (WARN_ON_ONCE(bio->bi_opf & REQ_NOWAIT)) {
+	if (!wait_barrier(conf, bio->bi_opf & REQ_NOWAIT)) {
 		bio_wouldblock_error(bio);
 		return 0;
 	}
-	wait_barrier(conf, false);
 
 	/*
 	 * Check reshape again to avoid reshape happens after checking
@@ -3716,7 +3708,7 @@ 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);
 		}
@@ -3749,7 +3741,7 @@ 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);
 		}
@@ -4543,7 +4535,7 @@ 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;
@@ -4834,7 +4826,7 @@ 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);
 	}
 
@@ -4979,7 +4971,7 @@ 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;
@@ -5125,9 +5117,13 @@ 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,
@@ -5147,18 +5143,18 @@ 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 */