Merge tag 'for-5.17/drivers-2022-01-11' of git://git.kernel.dk/linux-block

Pull block driver updates from Jens Axboe:

 - mtip32xx pci cleanups (Bjorn)

 - mtip32xx conversion to generic power management (Vaibhav)

 - rsxx pci powermanagement cleanups (Bjorn)

 - Remove the rsxx driver. This hardware never saw much adoption, and
   it's been end of lifed for a while. (Christoph)

 - MD pull request from Song:
      - REQ_NOWAIT support (Vishal Verma)
      - raid6 benchmark optimization (Dirk Müller)
      - Fix for acct bioset (Xiao Ni)
      - Clean up max_queued_requests (Mariusz Tkaczyk)
      - PREEMPT_RT optimization (Davidlohr Bueso)
      - Use default_groups in kobj_type (Greg Kroah-Hartman)

 - Use attribute groups in pktcdvd and rnbd (Greg)

 - NVMe pull request from Christoph:
      - increment request genctr on completion (Keith Busch, Geliang
        Tang)
      - add a 'iopolicy' module parameter (Hannes Reinecke)
      - print out valid arguments when reading from /dev/nvme-fabrics
        (Hannes Reinecke)

 - Use struct_group() in drbd (Kees)

 - null_blk fixes (Ming)

 - Get rid of congestion logic in pktcdvd (Neil)

 - Floppy ejection hang fix (Tasos)

 - Floppy max user request size fix (Xiongwei)

 - Loop locking fix (Tetsuo)

* tag 'for-5.17/drivers-2022-01-11' of git://git.kernel.dk/linux-block: (32 commits)
  md: use default_groups in kobj_type
  md: Move alloc/free acct bioset in to personality
  lib/raid6: Use strict priority ranking for pq gen() benchmarking
  lib/raid6: skip benchmark of non-chosen xor_syndrome functions
  md: fix spelling of "its"
  md: raid456 add nowait support
  md: raid10 add nowait support
  md: raid1 add nowait support
  md: add support for REQ_NOWAIT
  md: drop queue limitation for RAID1 and RAID10
  md/raid5: play nice with PREEMPT_RT
  block/rnbd-clt-sysfs: use default_groups in kobj_type
  pktcdvd: convert to use attribute groups
  block: null_blk: only set set->nr_maps as 3 if active poll_queues is > 0
  nvme: add 'iopolicy' module parameter
  nvme: drop unused variable ctrl in nvme_setup_cmd
  nvme: increment request genctr on completion
  nvme-fabrics: print out valid arguments when reading from /dev/nvme-fabrics
  block: remove the rsxx driver
  rsxx: Drop PCI legacy power management
  ...

1 files changed, 52 insertions, 56 deletions

diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index e98ddf08d77de0..b1b05c45c07c42 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -1082,13 +1082,10 @@ out_putf:
 	return error;
 }
 
-static int __loop_clr_fd(struct loop_device *lo, bool release)
+static void __loop_clr_fd(struct loop_device *lo)
 {
-	struct file *filp = NULL;
+	struct file *filp;
 	gfp_t gfp = lo->old_gfp_mask;
-	int err = 0;
-	bool partscan = false;
-	int lo_number;
 	struct loop_worker *pos, *worker;
 
 	/*
@@ -1103,17 +1100,14 @@ static int __loop_clr_fd(struct loop_device *lo, bool release)
 	 * became visible.
 	 */
 
+	/*
+	 * Since this function is called upon "ioctl(LOOP_CLR_FD)" xor "close()
+	 * after ioctl(LOOP_CLR_FD)", it is a sign of something going wrong if
+	 * lo->lo_state has changed while waiting for lo->lo_mutex.
+	 */
 	mutex_lock(&lo->lo_mutex);
-	if (WARN_ON_ONCE(lo->lo_state != Lo_rundown)) {
-		err = -ENXIO;
-		goto out_unlock;
-	}
-
-	filp = lo->lo_backing_file;
-	if (filp == NULL) {
-		err = -EINVAL;
-		goto out_unlock;
-	}
+	BUG_ON(lo->lo_state != Lo_rundown);
+	mutex_unlock(&lo->lo_mutex);
 
 	if (test_bit(QUEUE_FLAG_WC, &lo->lo_queue->queue_flags))
 		blk_queue_write_cache(lo->lo_queue, false, false);
@@ -1134,6 +1128,7 @@ static int __loop_clr_fd(struct loop_device *lo, bool release)
 	del_timer_sync(&lo->timer);
 
 	spin_lock_irq(&lo->lo_lock);
+	filp = lo->lo_backing_file;
 	lo->lo_backing_file = NULL;
 	spin_unlock_irq(&lo->lo_lock);
 
@@ -1149,60 +1144,59 @@ static int __loop_clr_fd(struct loop_device *lo, bool release)
 	/* let user-space know about this change */
 	kobject_uevent(&disk_to_dev(lo->lo_disk)->kobj, KOBJ_CHANGE);
 	mapping_set_gfp_mask(filp->f_mapping, gfp);
-	/* This is safe: open() is still holding a reference. */
-	module_put(THIS_MODULE);
 	blk_mq_unfreeze_queue(lo->lo_queue);
 
-	partscan = lo->lo_flags & LO_FLAGS_PARTSCAN;
-	lo_number = lo->lo_number;
 	disk_force_media_change(lo->lo_disk, DISK_EVENT_MEDIA_CHANGE);
-out_unlock:
-	mutex_unlock(&lo->lo_mutex);
-	if (partscan) {
-		/*
-		 * open_mutex has been held already in release path, so don't
-		 * acquire it if this function is called in such case.
-		 *
-		 * If the reread partition isn't from release path, lo_refcnt
-		 * must be at least one and it can only become zero when the
-		 * current holder is released.
-		 */
-		if (!release)
-			mutex_lock(&lo->lo_disk->open_mutex);
+
+	if (lo->lo_flags & LO_FLAGS_PARTSCAN) {
+		int err;
+
+		mutex_lock(&lo->lo_disk->open_mutex);
 		err = bdev_disk_changed(lo->lo_disk, false);
-		if (!release)
-			mutex_unlock(&lo->lo_disk->open_mutex);
+		mutex_unlock(&lo->lo_disk->open_mutex);
 		if (err)
 			pr_warn("%s: partition scan of loop%d failed (rc=%d)\n",
-				__func__, lo_number, err);
+				__func__, lo->lo_number, err);
 		/* Device is gone, no point in returning error */
-		err = 0;
 	}
 
-	/*
-	 * lo->lo_state is set to Lo_unbound here after above partscan has
-	 * finished.
-	 *
-	 * There cannot be anybody else entering __loop_clr_fd() as
-	 * lo->lo_backing_file is already cleared and Lo_rundown state
-	 * protects us from all the other places trying to change the 'lo'
-	 * device.
-	 */
-	mutex_lock(&lo->lo_mutex);
 	lo->lo_flags = 0;
 	if (!part_shift)
 		lo->lo_disk->flags |= GENHD_FL_NO_PART;
+
+	fput(filp);
+}
+
+static void loop_rundown_completed(struct loop_device *lo)
+{
+	mutex_lock(&lo->lo_mutex);
 	lo->lo_state = Lo_unbound;
 	mutex_unlock(&lo->lo_mutex);
+	module_put(THIS_MODULE);
+}
 
-	/*
-	 * Need not hold lo_mutex to fput backing file. Calling fput holding
-	 * lo_mutex triggers a circular lock dependency possibility warning as
-	 * fput can take open_mutex which is usually taken before lo_mutex.
-	 */
-	if (filp)
-		fput(filp);
-	return err;
+static void loop_rundown_workfn(struct work_struct *work)
+{
+	struct loop_device *lo = container_of(work, struct loop_device,
+					      rundown_work);
+	struct block_device *bdev = lo->lo_device;
+	struct gendisk *disk = lo->lo_disk;
+
+	__loop_clr_fd(lo);
+	kobject_put(&bdev->bd_device.kobj);
+	module_put(disk->fops->owner);
+	loop_rundown_completed(lo);
+}
+
+static void loop_schedule_rundown(struct loop_device *lo)
+{
+	struct block_device *bdev = lo->lo_device;
+	struct gendisk *disk = lo->lo_disk;
+
+	__module_get(disk->fops->owner);
+	kobject_get(&bdev->bd_device.kobj);
+	INIT_WORK(&lo->rundown_work, loop_rundown_workfn);
+	queue_work(system_long_wq, &lo->rundown_work);
 }
 
 static int loop_clr_fd(struct loop_device *lo)
@@ -1234,7 +1228,9 @@ static int loop_clr_fd(struct loop_device *lo)
 	lo->lo_state = Lo_rundown;
 	mutex_unlock(&lo->lo_mutex);
 
-	return __loop_clr_fd(lo, false);
+	__loop_clr_fd(lo);
+	loop_rundown_completed(lo);
+	return 0;
 }
 
 static int
@@ -1758,7 +1754,7 @@ static void lo_release(struct gendisk *disk, fmode_t mode)
 		 * In autoclear mode, stop the loop thread
 		 * and remove configuration after last close.
 		 */
-		__loop_clr_fd(lo, true);
+		loop_schedule_rundown(lo);
 		return;
 	} else if (lo->lo_state == Lo_bound) {
 		/*