Merge tag 'block-6.3-2023-03-03' of git://git.kernel.dk/linux

Pull block fixes from Jens Axboe:

 - NVMe pull request via Christoph:
      - Don't access released socket during error recovery (Akinobu
        Mita)
      - Bring back auto-removal of deleted namespaces during sequential
        scan (Christoph Hellwig)
      - Fix an error code in nvme_auth_process_dhchap_challenge (Dan
        Carpenter)
      - Show well known discovery name (Daniel Wagner)
      - Add a missing endianess conversion in effects masking (Keith
        Busch)

 - Fix for a regression introduced in blk-rq-qos during init in this
   merge window (Breno)

 - Reorder a few fields in struct blk_mq_tag_set, eliminating a few
   holes and shrinking it (Christophe)

 - Remove redundant bdev_get_queue() NULL checks (Juhyung)

 - Add sed-opal single user mode support flag (Luca)

 - Remove SQE128 check in ublk as it isn't needed, saving some memory
   (Ming)

 - Op specific segment checking for cloned requests (Uday)

 - Exclusive open partition scan fixes (Yu)

 - Loop offset/size checking before assigning them in the device (Zhong)

 - Bio polling fixes (me)

* tag 'block-6.3-2023-03-03' of git://git.kernel.dk/linux:
  blk-mq: enforce op-specific segment limits in blk_insert_cloned_request
  nvme-fabrics: show well known discovery name
  nvme-tcp: don't access released socket during error recovery
  nvme-auth: fix an error code in nvme_auth_process_dhchap_challenge()
  nvme: bring back auto-removal of deleted namespaces during sequential scan
  blk-iocost: Pass gendisk to ioc_refresh_params
  nvme: fix sparse warning on effects masking
  block: be a bit more careful in checking for NULL bdev while polling
  block: clear bio->bi_bdev when putting a bio back in the cache
  loop: loop_set_status_from_info() check before assignment
  ublk: remove check IO_URING_F_SQE128 in ublk_ch_uring_cmd
  block: remove more NULL checks after bdev_get_queue()
  blk-mq: Reorder fields in 'struct blk_mq_tag_set'
  block: fix scan partition for exclusively open device again
  block: Revert "block: Do not reread partition table on exclusively open device"
  sed-opal: add support flag for SUM in status ioctl

1 files changed, 28 insertions, 9 deletions

diff --git a/block/genhd.c b/block/genhd.c
index d09d775c222a..3ee5577e1586 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -356,9 +356,10 @@ void disk_uevent(struct gendisk *disk, enum kobject_action action)
 }
 EXPORT_SYMBOL_GPL(disk_uevent);
 
-int disk_scan_partitions(struct gendisk *disk, fmode_t mode, void *owner)
+int disk_scan_partitions(struct gendisk *disk, fmode_t mode)
 {
 	struct block_device *bdev;
+	int ret = 0;
 
 	if (disk->flags & (GENHD_FL_NO_PART | GENHD_FL_HIDDEN))
 		return -EINVAL;
@@ -366,16 +367,29 @@ int disk_scan_partitions(struct gendisk *disk, fmode_t mode, void *owner)
 		return -EINVAL;
 	if (disk->open_partitions)
 		return -EBUSY;
-	/* Someone else has bdev exclusively open? */
-	if (disk->part0->bd_holder && disk->part0->bd_holder != owner)
-		return -EBUSY;
 
 	set_bit(GD_NEED_PART_SCAN, &disk->state);
-	bdev = blkdev_get_by_dev(disk_devt(disk), mode, NULL);
+	/*
+	 * If the device is opened exclusively by current thread already, it's
+	 * safe to scan partitons, otherwise, use bd_prepare_to_claim() to
+	 * synchronize with other exclusive openers and other partition
+	 * scanners.
+	 */
+	if (!(mode & FMODE_EXCL)) {
+		ret = bd_prepare_to_claim(disk->part0, disk_scan_partitions);
+		if (ret)
+			return ret;
+	}
+
+	bdev = blkdev_get_by_dev(disk_devt(disk), mode & ~FMODE_EXCL, NULL);
 	if (IS_ERR(bdev))
-		return PTR_ERR(bdev);
-	blkdev_put(bdev, mode);
-	return 0;
+		ret =  PTR_ERR(bdev);
+	else
+		blkdev_put(bdev, mode);
+
+	if (!(mode & FMODE_EXCL))
+		bd_abort_claiming(disk->part0, disk_scan_partitions);
+	return ret;
 }
 
 /**
@@ -497,9 +511,14 @@ int __must_check device_add_disk(struct device *parent, struct gendisk *disk,
 		if (ret)
 			goto out_unregister_bdi;
 
+		/* Make sure the first partition scan will be proceed */
+		if (get_capacity(disk) && !(disk->flags & GENHD_FL_NO_PART) &&
+		    !test_bit(GD_SUPPRESS_PART_SCAN, &disk->state))
+			set_bit(GD_NEED_PART_SCAN, &disk->state);
+
 		bdev_add(disk->part0, ddev->devt);
 		if (get_capacity(disk))
-			disk_scan_partitions(disk, FMODE_READ, NULL);
+			disk_scan_partitions(disk, FMODE_READ);
 
 		/*
 		 * Announce the disk and partitions after all partitions are