Merge tag 'md-6.11-20240704' of git://git.kernel.org/pub/scm/linux/kernel/git/song/md into for-6.11/block

Merge MD fixes from Song:

"This PR contains various small fixes by Yu Kuai,
 Benjamin Marzinski, Christophe JAILLET, and Yang Li."

* tag 'md-6.11-20240704' of git://git.kernel.org/pub/scm/linux/kernel/git/song/md:
  md/raid5: recheck if reshape has finished with device_lock held
  md: Don't wait for MD_RECOVERY_NEEDED for HOT_REMOVE_DISK ioctl
  md-cluster: Constify struct md_cluster_operations
  md: Remove unneeded semicolon
  md/raid5: fix spares errors about rcu usage

Author: axboe

drivers/md/md-cluster.c

@@ -1570,7 +1570,7 @@ static int gather_bitmaps(struct md_rdev *rdev)
 	return err;
 }
 
-static struct md_cluster_operations cluster_ops = {
+static const struct md_cluster_operations cluster_ops = {
 	.join   = join,
 	.leave  = leave,
 	.slot_number = slot_number,

drivers/md/md.c

@@ -85,7 +85,7 @@ static DEFINE_SPINLOCK(pers_lock);
 
 static const struct kobj_type md_ktype;
 
-struct md_cluster_operations *md_cluster_ops;
+const struct md_cluster_operations *md_cluster_ops;
 EXPORT_SYMBOL(md_cluster_ops);
 static struct module *md_cluster_mod;
 
@@ -627,7 +627,7 @@ static void md_submit_flush_data(struct work_struct *ws)
 		 * always is 0, make_request() will not be called here.
 		 */
 		if (WARN_ON_ONCE(!mddev->pers->make_request(mddev, bio)))
-			bio_io_error(bio);;
+			bio_io_error(bio);
 	}
 
 	/* The pair is percpu_ref_get() from md_flush_request() */
@@ -7765,12 +7765,6 @@ static int md_ioctl(struct block_device *bdev, blk_mode_t mode,
 		return get_bitmap_file(mddev, argp);
 	}
 
-	if (cmd == HOT_REMOVE_DISK)
-		/* need to ensure recovery thread has run */
-		wait_event_interruptible_timeout(mddev->sb_wait,
-						 !test_bit(MD_RECOVERY_NEEDED,
-							   &mddev->recovery),
-						 msecs_to_jiffies(5000));
 	if (cmd == STOP_ARRAY || cmd == STOP_ARRAY_RO) {
 		/* Need to flush page cache, and ensure no-one else opens
 		 * and writes
@@ -8543,7 +8537,7 @@ int unregister_md_personality(struct md_personality *p)
 }
 EXPORT_SYMBOL(unregister_md_personality);
 
-int register_md_cluster_operations(struct md_cluster_operations *ops,
+int register_md_cluster_operations(const struct md_cluster_operations *ops,
 				   struct module *module)
 {
 	int ret = 0;

drivers/md/md.h

@@ -849,7 +849,7 @@ static inline void safe_put_page(struct page *p)
 
 extern int register_md_personality(struct md_personality *p);
 extern int unregister_md_personality(struct md_personality *p);
-extern int register_md_cluster_operations(struct md_cluster_operations *ops,
+extern int register_md_cluster_operations(const struct md_cluster_operations *ops,
 		struct module *module);
 extern int unregister_md_cluster_operations(void);
 extern int md_setup_cluster(struct mddev *mddev, int nodes);
@@ -932,7 +932,7 @@ static inline void rdev_dec_pending(struct md_rdev *rdev, struct mddev *mddev)
 	}
 }
 
-extern struct md_cluster_operations *md_cluster_ops;
+extern const struct md_cluster_operations *md_cluster_ops;
 static inline int mddev_is_clustered(struct mddev *mddev)
 {
 	return mddev->cluster_info && mddev->bitmap_info.nodes > 1;

drivers/md/raid5.c

@@ -155,7 +155,7 @@ static int raid6_idx_to_slot(int idx, struct stripe_head *sh,
 	return slot;
 }
 
-static void print_raid5_conf (struct r5conf *conf);
+static void print_raid5_conf(struct r5conf *conf);
 
 static int stripe_operations_active(struct stripe_head *sh)
 {
@@ -5899,6 +5899,39 @@ static int add_all_stripe_bios(struct r5conf *conf,
 	return ret;
 }
 
+enum reshape_loc {
+	LOC_NO_RESHAPE,
+	LOC_AHEAD_OF_RESHAPE,
+	LOC_INSIDE_RESHAPE,
+	LOC_BEHIND_RESHAPE,
+};
+
+static enum reshape_loc get_reshape_loc(struct mddev *mddev,
+		struct r5conf *conf, sector_t logical_sector)
+{
+	sector_t reshape_progress, reshape_safe;
+	/*
+	 * Spinlock is needed as reshape_progress may be
+	 * 64bit on a 32bit platform, and so it might be
+	 * possible to see a half-updated value
+	 * Of course reshape_progress could change after
+	 * the lock is dropped, so once we get a reference
+	 * to the stripe that we think it is, we will have
+	 * to check again.
+	 */
+	spin_lock_irq(&conf->device_lock);
+	reshape_progress = conf->reshape_progress;
+	reshape_safe = conf->reshape_safe;
+	spin_unlock_irq(&conf->device_lock);
+	if (reshape_progress == MaxSector)
+		return LOC_NO_RESHAPE;
+	if (ahead_of_reshape(mddev, logical_sector, reshape_progress))
+		return LOC_AHEAD_OF_RESHAPE;
+	if (ahead_of_reshape(mddev, logical_sector, reshape_safe))
+		return LOC_INSIDE_RESHAPE;
+	return LOC_BEHIND_RESHAPE;
+}
+
 static enum stripe_result make_stripe_request(struct mddev *mddev,
 		struct r5conf *conf, struct stripe_request_ctx *ctx,
 		sector_t logical_sector, struct bio *bi)
@@ -5913,28 +5946,14 @@ static enum stripe_result make_stripe_request(struct mddev *mddev,
 	seq = read_seqcount_begin(&conf->gen_lock);
 
 	if (unlikely(conf->reshape_progress != MaxSector)) {
-		/*
-		 * Spinlock is needed as reshape_progress may be
-		 * 64bit on a 32bit platform, and so it might be
-		 * possible to see a half-updated value
-		 * Of course reshape_progress could change after
-		 * the lock is dropped, so once we get a reference
-		 * to the stripe that we think it is, we will have
-		 * to check again.
-		 */
-		spin_lock_irq(&conf->device_lock);
-		if (ahead_of_reshape(mddev, logical_sector,
-				     conf->reshape_progress)) {
-			previous = 1;
-		} else {
-			if (ahead_of_reshape(mddev, logical_sector,
-					     conf->reshape_safe)) {
-				spin_unlock_irq(&conf->device_lock);
-				ret = STRIPE_SCHEDULE_AND_RETRY;
-				goto out;
-			}
+		enum reshape_loc loc = get_reshape_loc(mddev, conf,
+						       logical_sector);
+		if (loc == LOC_INSIDE_RESHAPE) {
+			ret = STRIPE_SCHEDULE_AND_RETRY;
+			goto out;
 		}
-		spin_unlock_irq(&conf->device_lock);
+		if (loc == LOC_AHEAD_OF_RESHAPE)
+			previous = 1;
 	}
 
 	new_sector = raid5_compute_sector(conf, logical_sector, previous,
@@ -6112,8 +6131,7 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi)
 	/* Bail out if conflicts with reshape and REQ_NOWAIT is set */
 	if ((bi->bi_opf & REQ_NOWAIT) &&
 	    (conf->reshape_progress != MaxSector) &&
-	    !ahead_of_reshape(mddev, logical_sector, conf->reshape_progress) &&
-	    ahead_of_reshape(mddev, logical_sector, conf->reshape_safe)) {
+	    get_reshape_loc(mddev, conf, logical_sector) == LOC_INSIDE_RESHAPE) {
 		bio_wouldblock_error(bi);
 		if (rw == WRITE)
 			md_write_end(mddev);
@@ -7568,11 +7586,11 @@ static struct r5conf *setup_conf(struct mddev *mddev)
 		if (test_bit(Replacement, &rdev->flags)) {
 			if (disk->replacement)
 				goto abort;
-			RCU_INIT_POINTER(disk->replacement, rdev);
+			disk->replacement = rdev;
 		} else {
 			if (disk->rdev)
 				goto abort;
-			RCU_INIT_POINTER(disk->rdev, rdev);
+			disk->rdev = rdev;
 		}
 
 		if (test_bit(In_sync, &rdev->flags)) {
@@ -8054,7 +8072,7 @@ static void raid5_status(struct seq_file *seq, struct mddev *mddev)
 	seq_printf (seq, "]");
 }
 
-static void print_raid5_conf (struct r5conf *conf)
+static void print_raid5_conf(struct r5conf *conf)
 {
 	struct md_rdev *rdev;
 	int i;
@@ -8068,15 +8086,13 @@ static void print_raid5_conf (struct r5conf *conf)
 	       conf->raid_disks,
 	       conf->raid_disks - conf->mddev->degraded);
 
-	rcu_read_lock();
 	for (i = 0; i < conf->raid_disks; i++) {
-		rdev = rcu_dereference(conf->disks[i].rdev);
+		rdev = conf->disks[i].rdev;
 		if (rdev)
 			pr_debug(" disk %d, o:%d, dev:%pg\n",
 			       i, !test_bit(Faulty, &rdev->flags),
 			       rdev->bdev);
 	}
-	rcu_read_unlock();
 }
 
 static int raid5_spare_active(struct mddev *mddev)