Merge tag 'block-5.17-2022-02-11' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:

 - NVMe pull request
      - nvme-tcp: fix bogus request completion when failing to send AER
        (Sagi Grimberg)
      - add the missing nvme_complete_req tracepoint for batched
        completion (Bean Huo)

 - Revert of the loop async autoclear issue that has continued to plague
   us this release. A few patchsets exists to improve this, but they are
   too invasive to be considered at this point (Tetsuo)

* tag 'block-5.17-2022-02-11' of git://git.kernel.dk/linux-block:
  loop: revert "make autoclear operation asynchronous"
  nvme-tcp: fix bogus request completion when failing to send AER
  nvme: add nvme_complete_req tracepoint for batched completion

Author: torvalds

drivers/block/loop.c

@@ -1082,7 +1082,7 @@ static int loop_configure(struct loop_device *lo, fmode_t mode,
 	return error;
 }
 
-static void __loop_clr_fd(struct loop_device *lo)
+static void __loop_clr_fd(struct loop_device *lo, bool release)
 {
 	struct file *filp;
 	gfp_t gfp = lo->old_gfp_mask;
@@ -1144,59 +1144,53 @@ static void __loop_clr_fd(struct loop_device *lo)
 	/* 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);
 
 	disk_force_media_change(lo->lo_disk, DISK_EVENT_MEDIA_CHANGE);
 
 	if (lo->lo_flags & LO_FLAGS_PARTSCAN) {
 		int err;
 
-		mutex_lock(&lo->lo_disk->open_mutex);
+		/*
+		 * 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);
 		err = bdev_disk_changed(lo->lo_disk, false);
-		mutex_unlock(&lo->lo_disk->open_mutex);
+		if (!release)
+			mutex_unlock(&lo->lo_disk->open_mutex);
 		if (err)
 			pr_warn("%s: partition scan of loop%d failed (rc=%d)\n",
 				__func__, lo->lo_number, err);
 		/* Device is gone, no point in returning error */
 	}
 
+	/*
+	 * 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_rundown state protects us from all the other places trying to
+	 * change the 'lo' device.
+	 */
 	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);
-}
-
-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);
+	/*
+	 * 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.
+	 */
+	fput(filp);
 }
 
 static int loop_clr_fd(struct loop_device *lo)
@@ -1228,8 +1222,7 @@ static int loop_clr_fd(struct loop_device *lo)
 	lo->lo_state = Lo_rundown;
 	mutex_unlock(&lo->lo_mutex);
 
-	__loop_clr_fd(lo);
-	loop_rundown_completed(lo);
+	__loop_clr_fd(lo, false);
 	return 0;
 }
 
@@ -1754,7 +1747,7 @@ static void lo_release(struct gendisk *disk, fmode_t mode)
 		 * In autoclear mode, stop the loop thread
 		 * and remove configuration after last close.
 		 */
-		loop_schedule_rundown(lo);
+		__loop_clr_fd(lo, true);
 		return;
 	} else if (lo->lo_state == Lo_bound) {
 		/*

drivers/block/loop.h

@@ -56,7 +56,6 @@ struct loop_device {
 	struct gendisk		*lo_disk;
 	struct mutex		lo_mutex;
 	bool			idr_visible;
-	struct work_struct      rundown_work;
 };
 
 struct loop_cmd {

drivers/nvme/host/core.c

@@ -368,6 +368,7 @@ EXPORT_SYMBOL_GPL(nvme_complete_rq);
 
 void nvme_complete_batch_req(struct request *req)
 {
+	trace_nvme_complete_rq(req);
 	nvme_cleanup_cmd(req);
 	nvme_end_req_zoned(req);
 }

drivers/nvme/host/tcp.c

@@ -913,7 +913,15 @@ static inline void nvme_tcp_done_send_req(struct nvme_tcp_queue *queue)
 
 static void nvme_tcp_fail_request(struct nvme_tcp_request *req)
 {
-	nvme_tcp_end_request(blk_mq_rq_from_pdu(req), NVME_SC_HOST_PATH_ERROR);
+	if (nvme_tcp_async_req(req)) {
+		union nvme_result res = {};
+
+		nvme_complete_async_event(&req->queue->ctrl->ctrl,
+				cpu_to_le16(NVME_SC_HOST_PATH_ERROR), &res);
+	} else {
+		nvme_tcp_end_request(blk_mq_rq_from_pdu(req),
+				NVME_SC_HOST_PATH_ERROR);
+	}
 }
 
 static int nvme_tcp_try_send_data(struct nvme_tcp_request *req)