Merge tag 'md-6.18-20250909' of gitolite.kernel.org:pub/scm/linux/kernel/git/mdraid/linux into for-6.18/block

Pull MD changes from Yu Kuai:

"Redundant data is used to enhance data fault tolerance, and the storage
 method for redundant data vary depending on the RAID levels. And it's
 important to maintain the consistency of redundant data.

 Bitmap is used to record which data blocks have been synchronized and
 which ones need to be resynchronized or recovered. Each bit in the
 bitmap represents a segment of data in the array. When a bit is set,
 it indicates that the multiple redundant copies of that data segment
 may not be consistent. Data synchronization can be performed based on
 the bitmap after power failure or readding a disk. If there is no
 bitmap, a full disk synchronization is required.

 Due to known performance issues with md-bitmap and the unreasonable
 implementations:

 - self-managed IO submitting like filemap_write_page();
 - global spin_lock

 I have decided not to continue optimizing based on the current bitmap
 implementation, this new bitmap is invented without locking from IO fast
 path and can be used with fast disks.

 Key features for the new bitmap:
  - IO fastpath is lockless, if user issues lots of write IO to the same
    bitmap bit in a short time, only the first write has additional
    overhead to update bitmap bit, no additional overhead for the
    following writes;
  - support only resync or recover written data, means in the case
    creating new array or replacing with a new disk, there is no need to
    do a full disk resync/recovery;"

* tag 'md-6.18-20250909' of gitolite.kernel.org:pub/scm/linux/kernel/git/mdraid/linux: (24 commits)
  md/md-llbitmap: introduce new lockless bitmap
  md/md-bitmap: make method bitmap_ops->daemon_work optional
  md: add a new recovery_flag MD_RECOVERY_LAZY_RECOVER
  md/md-bitmap: add a new method blocks_synced() in bitmap_operations
  md/md-bitmap: add a new method skip_sync_blocks() in bitmap_operations
  md/md-bitmap: delay registration of bitmap_ops until creating bitmap
  md/md-bitmap: add a new sysfs api bitmap_type
  md: add a new mddev field 'bitmap_id'
  md/md-bitmap: support discard for bitmap ops
  md: factor out a helper raid_is_456()
  md: add a new parameter 'offset' to md_super_write()
  md/md-bitmap: introduce CONFIG_MD_BITMAP
  md: check before referencing mddev->bitmap_ops
  md/dm-raid: check before referencing mddev->bitmap_ops
  md/raid5: check before referencing mddev->bitmap_ops
  md/raid10: check before referencing mddev->bitmap_ops
  md/raid1: check before referencing mddev->bitmap_ops
  md/raid1: check bitmap before behind write
  md/md-bitmap: handle the case bitmap is not enabled before end_sync()
  md/md-bitmap: handle the case bitmap is not enabled before start_sync()
  ...

1 files changed, 25 insertions, 24 deletions

diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index c52ccd12d86b..312e8a0e93e7 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -3221,15 +3221,13 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 
 		if (mddev->curr_resync < max_sector) { /* aborted */
 			if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery))
-				mddev->bitmap_ops->end_sync(mddev,
-							    mddev->curr_resync,
-							    &sync_blocks);
+				md_bitmap_end_sync(mddev, mddev->curr_resync,
+						   &sync_blocks);
 			else for (i = 0; i < conf->geo.raid_disks; i++) {
 				sector_t sect =
 					raid10_find_virt(conf, mddev->curr_resync, i);
 
-				mddev->bitmap_ops->end_sync(mddev, sect,
-							    &sync_blocks);
+				md_bitmap_end_sync(mddev, sect, &sync_blocks);
 			}
 		} else {
 			/* completed sync */
@@ -3249,7 +3247,8 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 			}
 			conf->fullsync = 0;
 		}
-		mddev->bitmap_ops->close_sync(mddev);
+		if (md_bitmap_enabled(mddev, false))
+			mddev->bitmap_ops->close_sync(mddev);
 		close_sync(conf);
 		*skipped = 1;
 		return sectors_skipped;
@@ -3351,9 +3350,8 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 			 * we only need to recover the block if it is set in
 			 * the bitmap
 			 */
-			must_sync = mddev->bitmap_ops->start_sync(mddev, sect,
-								  &sync_blocks,
-								  true);
+			must_sync = md_bitmap_start_sync(mddev, sect,
+							 &sync_blocks, true);
 			if (sync_blocks < max_sync)
 				max_sync = sync_blocks;
 			if (!must_sync &&
@@ -3396,9 +3394,8 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 				}
 			}
 
-			must_sync = mddev->bitmap_ops->start_sync(mddev, sect,
-						&sync_blocks, still_degraded);
-
+			md_bitmap_start_sync(mddev, sect, &sync_blocks,
+					     still_degraded);
 			any_working = 0;
 			for (j=0; j<conf->copies;j++) {
 				int k;
@@ -3570,13 +3567,13 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 		 * safety reason, which ensures curr_resync_completed is
 		 * updated in bitmap_cond_end_sync.
 		 */
-		mddev->bitmap_ops->cond_end_sync(mddev, sector_nr,
+		if (md_bitmap_enabled(mddev, false))
+			mddev->bitmap_ops->cond_end_sync(mddev, sector_nr,
 					mddev_is_clustered(mddev) &&
 					(sector_nr + 2 * RESYNC_SECTORS > conf->cluster_sync_high));
 
-		if (!mddev->bitmap_ops->start_sync(mddev, sector_nr,
-						   &sync_blocks,
-						   mddev->degraded) &&
+		if (!md_bitmap_start_sync(mddev, sector_nr, &sync_blocks,
+					  mddev->degraded) &&
 		    !conf->fullsync && !test_bit(MD_RECOVERY_REQUESTED,
 						 &mddev->recovery)) {
 			/* We can skip this block */
@@ -4225,7 +4222,6 @@ static int raid10_resize(struct mddev *mddev, sector_t sectors)
 	 */
 	struct r10conf *conf = mddev->private;
 	sector_t oldsize, size;
-	int ret;
 
 	if (mddev->reshape_position != MaxSector)
 		return -EBUSY;
@@ -4239,9 +4235,12 @@ static int raid10_resize(struct mddev *mddev, sector_t sectors)
 	    mddev->array_sectors > size)
 		return -EINVAL;
 
-	ret = mddev->bitmap_ops->resize(mddev, size, 0, false);
-	if (ret)
-		return ret;
+	if (md_bitmap_enabled(mddev, false)) {
+		int ret = mddev->bitmap_ops->resize(mddev, size, 0);
+
+		if (ret)
+			return ret;
+	}
 
 	md_set_array_sectors(mddev, size);
 	if (sectors > mddev->dev_sectors &&
@@ -4507,8 +4506,9 @@ static int raid10_start_reshape(struct mddev *mddev)
 		oldsize = raid10_size(mddev, 0, 0);
 		newsize = raid10_size(mddev, 0, conf->geo.raid_disks);
 
-		if (!mddev_is_clustered(mddev)) {
-			ret = mddev->bitmap_ops->resize(mddev, newsize, 0, false);
+		if (!mddev_is_clustered(mddev) &&
+		    md_bitmap_enabled(mddev, false)) {
+			ret = mddev->bitmap_ops->resize(mddev, newsize, 0);
 			if (ret)
 				goto abort;
 			else
@@ -4530,13 +4530,14 @@ static int raid10_start_reshape(struct mddev *mddev)
 			    MD_FEATURE_RESHAPE_ACTIVE)) || (oldsize == newsize))
 			goto out;
 
-		ret = mddev->bitmap_ops->resize(mddev, newsize, 0, false);
+		/* cluster can't be setup without bitmap */
+		ret = mddev->bitmap_ops->resize(mddev, newsize, 0);
 		if (ret)
 			goto abort;
 
 		ret = mddev->cluster_ops->resize_bitmaps(mddev, newsize, oldsize);
 		if (ret) {
-			mddev->bitmap_ops->resize(mddev, oldsize, 0, false);
+			mddev->bitmap_ops->resize(mddev, oldsize, 0);
 			goto abort;
 		}
 	}