1 files changed, 292 insertions, 165 deletions

diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
index 1dfb2e77898b..ca9a67b5b537 100644
--- a/drivers/block/ublk_drv.c
+++ b/drivers/block/ublk_drv.c
@@ -48,6 +48,9 @@
 
 #define UBLK_MINORS		(1U << MINORBITS)
 
+/* private ioctl command mirror */
+#define UBLK_CMD_DEL_DEV_ASYNC	_IOC_NR(UBLK_U_CMD_DEL_DEV_ASYNC)
+
 /* All UBLK_F_* have to be included into UBLK_F_ALL */
 #define UBLK_F_ALL (UBLK_F_SUPPORT_ZERO_COPY \
 		| UBLK_F_URING_CMD_COMP_IN_TASK \
@@ -57,7 +60,12 @@
 		| UBLK_F_UNPRIVILEGED_DEV \
 		| UBLK_F_CMD_IOCTL_ENCODE \
 		| UBLK_F_USER_COPY \
-		| UBLK_F_ZONED)
+		| UBLK_F_ZONED \
+		| UBLK_F_USER_RECOVERY_FAIL_IO)
+
+#define UBLK_F_ALL_RECOVERY_FLAGS (UBLK_F_USER_RECOVERY \
+		| UBLK_F_USER_RECOVERY_REISSUE \
+		| UBLK_F_USER_RECOVERY_FAIL_IO)
 
 /* All UBLK_PARAM_TYPE_* should be included here */
 #define UBLK_PARAM_TYPE_ALL                                \
@@ -68,9 +76,6 @@ struct ublk_rq_data {
 	struct llist_node node;
 
 	struct kref ref;
-	__u64 sector;
-	__u32 operation;
-	__u32 nr_zones;
 };
 
 struct ublk_uring_cmd_pdu {
@@ -143,6 +148,7 @@ struct ublk_queue {
 	bool force_abort;
 	bool timeout;
 	bool canceling;
+	bool fail_io; /* copy of dev->state == UBLK_S_DEV_FAIL_IO */
 	unsigned short nr_io_ready;	/* how many ios setup */
 	spinlock_t		cancel_lock;
 	struct ublk_device *dev;
@@ -179,8 +185,7 @@ struct ublk_device {
 	unsigned int		nr_queues_ready;
 	unsigned int		nr_privileged_daemon;
 
-	struct work_struct	quiesce_work;
-	struct work_struct	stop_work;
+	struct work_struct	nosrv_work;
 };
 
 /* header of ublk_params */
@@ -211,6 +216,33 @@ static inline bool ublk_queue_is_zoned(struct ublk_queue *ubq)
 
 #ifdef CONFIG_BLK_DEV_ZONED
 
+struct ublk_zoned_report_desc {
+	__u64 sector;
+	__u32 operation;
+	__u32 nr_zones;
+};
+
+static DEFINE_XARRAY(ublk_zoned_report_descs);
+
+static int ublk_zoned_insert_report_desc(const struct request *req,
+		struct ublk_zoned_report_desc *desc)
+{
+	return xa_insert(&ublk_zoned_report_descs, (unsigned long)req,
+			    desc, GFP_KERNEL);
+}
+
+static struct ublk_zoned_report_desc *ublk_zoned_erase_report_desc(
+		const struct request *req)
+{
+	return xa_erase(&ublk_zoned_report_descs, (unsigned long)req);
+}
+
+static struct ublk_zoned_report_desc *ublk_zoned_get_report_desc(
+		const struct request *req)
+{
+	return xa_load(&ublk_zoned_report_descs, (unsigned long)req);
+}
+
 static int ublk_get_nr_zones(const struct ublk_device *ub)
 {
 	const struct ublk_param_basic *p = &ub->params.basic;
@@ -221,7 +253,7 @@ static int ublk_get_nr_zones(const struct ublk_device *ub)
 
 static int ublk_revalidate_disk_zones(struct ublk_device *ub)
 {
-	return blk_revalidate_disk_zones(ub->ub_disk, NULL);
+	return blk_revalidate_disk_zones(ub->ub_disk);
 }
 
 static int ublk_dev_param_zoned_validate(const struct ublk_device *ub)
@@ -246,21 +278,9 @@ static int ublk_dev_param_zoned_validate(const struct ublk_device *ub)
 	return 0;
 }
 
-static int ublk_dev_param_zoned_apply(struct ublk_device *ub)
+static void ublk_dev_param_zoned_apply(struct ublk_device *ub)
 {
-	const struct ublk_param_zoned *p = &ub->params.zoned;
-
-	disk_set_zoned(ub->ub_disk);
-	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, ub->ub_disk->queue);
-	blk_queue_required_elevator_features(ub->ub_disk->queue,
-					     ELEVATOR_F_ZBD_SEQ_WRITE);
-	disk_set_max_active_zones(ub->ub_disk, p->max_active_zones);
-	disk_set_max_open_zones(ub->ub_disk, p->max_open_zones);
-	blk_queue_max_zone_append_sectors(ub->ub_disk->queue, p->max_zone_append_sectors);
-
 	ub->ub_disk->nr_zones = ublk_get_nr_zones(ub);
-
-	return 0;
 }
 
 /* Based on virtblk_alloc_report_buffer */
@@ -317,7 +337,7 @@ static int ublk_report_zones(struct gendisk *disk, sector_t sector,
 		unsigned int zones_in_request =
 			min_t(unsigned int, remaining_zones, max_zones_per_request);
 		struct request *req;
-		struct ublk_rq_data *pdu;
+		struct ublk_zoned_report_desc desc;
 		blk_status_t status;
 
 		memset(buffer, 0, buffer_length);
@@ -328,20 +348,23 @@ static int ublk_report_zones(struct gendisk *disk, sector_t sector,
 			goto out;
 		}
 
-		pdu = blk_mq_rq_to_pdu(req);
-		pdu->operation = UBLK_IO_OP_REPORT_ZONES;
-		pdu->sector = sector;
-		pdu->nr_zones = zones_in_request;
+		desc.operation = UBLK_IO_OP_REPORT_ZONES;
+		desc.sector = sector;
+		desc.nr_zones = zones_in_request;
+		ret = ublk_zoned_insert_report_desc(req, &desc);
+		if (ret)
+			goto free_req;
 
 		ret = blk_rq_map_kern(disk->queue, req, buffer, buffer_length,
 					GFP_KERNEL);
-		if (ret) {
-			blk_mq_free_request(req);
-			goto out;
-		}
+		if (ret)
+			goto erase_desc;
 
 		status = blk_execute_rq(req, 0);
 		ret = blk_status_to_errno(status);
+erase_desc:
+		ublk_zoned_erase_report_desc(req);
+free_req:
 		blk_mq_free_request(req);
 		if (ret)
 			goto out;
@@ -375,7 +398,7 @@ static blk_status_t ublk_setup_iod_zoned(struct ublk_queue *ubq,
 {
 	struct ublksrv_io_desc *iod = ublk_get_iod(ubq, req->tag);
 	struct ublk_io *io = &ubq->ios[req->tag];
-	struct ublk_rq_data *pdu = blk_mq_rq_to_pdu(req);
+	struct ublk_zoned_report_desc *desc;
 	u32 ublk_op;
 
 	switch (req_op(req)) {
@@ -398,12 +421,15 @@ static blk_status_t ublk_setup_iod_zoned(struct ublk_queue *ubq,
 		ublk_op = UBLK_IO_OP_ZONE_RESET_ALL;
 		break;
 	case REQ_OP_DRV_IN:
-		ublk_op = pdu->operation;
+		desc = ublk_zoned_get_report_desc(req);
+		if (!desc)
+			return BLK_STS_IOERR;
+		ublk_op = desc->operation;
 		switch (ublk_op) {
 		case UBLK_IO_OP_REPORT_ZONES:
 			iod->op_flags = ublk_op | ublk_req_build_flags(req);
-			iod->nr_zones = pdu->nr_zones;
-			iod->start_sector = pdu->sector;
+			iod->nr_zones = desc->nr_zones;
+			iod->start_sector = desc->sector;
 			return BLK_STS_OK;
 		default:
 			return BLK_STS_IOERR;
@@ -432,9 +458,8 @@ static int ublk_dev_param_zoned_validate(const struct ublk_device *ub)
 	return -EOPNOTSUPP;
 }
 
-static int ublk_dev_param_zoned_apply(struct ublk_device *ub)
+static void ublk_dev_param_zoned_apply(struct ublk_device *ub)
 {
-	return -EOPNOTSUPP;
 }
 
 static int ublk_revalidate_disk_zones(struct ublk_device *ub)
@@ -495,44 +520,14 @@ static inline unsigned ublk_pos_to_tag(loff_t pos)
 
 static void ublk_dev_param_basic_apply(struct ublk_device *ub)
 {
-	struct request_queue *q = ub->ub_disk->queue;
 	const struct ublk_param_basic *p = &ub->params.basic;
 
-	blk_queue_logical_block_size(q, 1 << p->logical_bs_shift);
-	blk_queue_physical_block_size(q, 1 << p->physical_bs_shift);
-	blk_queue_io_min(q, 1 << p->io_min_shift);
-	blk_queue_io_opt(q, 1 << p->io_opt_shift);
-
-	blk_queue_write_cache(q, p->attrs & UBLK_ATTR_VOLATILE_CACHE,
-			p->attrs & UBLK_ATTR_FUA);
-	if (p->attrs & UBLK_ATTR_ROTATIONAL)
-		blk_queue_flag_clear(QUEUE_FLAG_NONROT, q);
-	else
-		blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
-
-	blk_queue_max_hw_sectors(q, p->max_sectors);
-	blk_queue_chunk_sectors(q, p->chunk_sectors);
-	blk_queue_virt_boundary(q, p->virt_boundary_mask);
-
 	if (p->attrs & UBLK_ATTR_READ_ONLY)
 		set_disk_ro(ub->ub_disk, true);
 
 	set_capacity(ub->ub_disk, p->dev_sectors);
 }
 
-static void ublk_dev_param_discard_apply(struct ublk_device *ub)
-{
-	struct request_queue *q = ub->ub_disk->queue;
-	const struct ublk_param_discard *p = &ub->params.discard;
-
-	q->limits.discard_alignment = p->discard_alignment;
-	q->limits.discard_granularity = p->discard_granularity;
-	blk_queue_max_discard_sectors(q, p->max_discard_sectors);
-	blk_queue_max_write_zeroes_sectors(q,
-			p->max_write_zeroes_sectors);
-	blk_queue_max_discard_segments(q, p->max_discard_segments);
-}
-
 static int ublk_validate_params(const struct ublk_device *ub)
 {
 	/* basic param is the only one which must be set */
@@ -576,20 +571,12 @@ static int ublk_validate_params(const struct ublk_device *ub)
 	return 0;
 }
 
-static int ublk_apply_params(struct ublk_device *ub)
+static void ublk_apply_params(struct ublk_device *ub)
 {
-	if (!(ub->params.types & UBLK_PARAM_TYPE_BASIC))
-		return -EINVAL;
-
 	ublk_dev_param_basic_apply(ub);
 
-	if (ub->params.types & UBLK_PARAM_TYPE_DISCARD)
-		ublk_dev_param_discard_apply(ub);
-
 	if (ub->params.types & UBLK_PARAM_TYPE_ZONED)
-		return ublk_dev_param_zoned_apply(ub);
-
-	return 0;
+		ublk_dev_param_zoned_apply(ub);
 }
 
 static inline bool ublk_support_user_copy(const struct ublk_queue *ubq)
@@ -645,14 +632,16 @@ static inline bool ublk_need_get_data(const struct ublk_queue *ubq)
 	return ubq->flags & UBLK_F_NEED_GET_DATA;
 }
 
-static struct ublk_device *ublk_get_device(struct ublk_device *ub)
+/* Called in slow path only, keep it noinline for trace purpose */
+static noinline struct ublk_device *ublk_get_device(struct ublk_device *ub)
 {
 	if (kobject_get_unless_zero(&ub->cdev_dev.kobj))
 		return ub;
 	return NULL;
 }
 
-static void ublk_put_device(struct ublk_device *ub)
+/* Called in slow path only, keep it noinline for trace purpose */
+static noinline void ublk_put_device(struct ublk_device *ub)
 {
 	put_device(&ub->cdev_dev);
 }
@@ -680,30 +669,69 @@ static inline char *ublk_queue_cmd_buf(struct ublk_device *ub, int q_id)
 	return ublk_get_queue(ub, q_id)->io_cmd_buf;
 }
 
+static inline int __ublk_queue_cmd_buf_size(int depth)
+{
+	return round_up(depth * sizeof(struct ublksrv_io_desc), PAGE_SIZE);
+}
+
 static inline int ublk_queue_cmd_buf_size(struct ublk_device *ub, int q_id)
 {
 	struct ublk_queue *ubq = ublk_get_queue(ub, q_id);
 
-	return round_up(ubq->q_depth * sizeof(struct ublksrv_io_desc),
-			PAGE_SIZE);
+	return __ublk_queue_cmd_buf_size(ubq->q_depth);
+}
+
+static int ublk_max_cmd_buf_size(void)
+{
+	return __ublk_queue_cmd_buf_size(UBLK_MAX_QUEUE_DEPTH);
+}
+
+/*
+ * Should I/O outstanding to the ublk server when it exits be reissued?
+ * If not, outstanding I/O will get errors.
+ */
+static inline bool ublk_nosrv_should_reissue_outstanding(struct ublk_device *ub)
+{
+	return (ub->dev_info.flags & UBLK_F_USER_RECOVERY) &&
+	       (ub->dev_info.flags & UBLK_F_USER_RECOVERY_REISSUE);
+}
+
+/*
+ * Should I/O issued while there is no ublk server queue? If not, I/O
+ * issued while there is no ublk server will get errors.
+ */
+static inline bool ublk_nosrv_dev_should_queue_io(struct ublk_device *ub)
+{
+	return (ub->dev_info.flags & UBLK_F_USER_RECOVERY) &&
+	       !(ub->dev_info.flags & UBLK_F_USER_RECOVERY_FAIL_IO);
 }
 
-static inline bool ublk_queue_can_use_recovery_reissue(
-		struct ublk_queue *ubq)
+/*
+ * Same as ublk_nosrv_dev_should_queue_io, but uses a queue-local copy
+ * of the device flags for smaller cache footprint - better for fast
+ * paths.
+ */
+static inline bool ublk_nosrv_should_queue_io(struct ublk_queue *ubq)
 {
 	return (ubq->flags & UBLK_F_USER_RECOVERY) &&
-			(ubq->flags & UBLK_F_USER_RECOVERY_REISSUE);
+	       !(ubq->flags & UBLK_F_USER_RECOVERY_FAIL_IO);
 }
 
-static inline bool ublk_queue_can_use_recovery(
-		struct ublk_queue *ubq)
+/*
+ * Should ublk devices be stopped (i.e. no recovery possible) when the
+ * ublk server exits? If not, devices can be used again by a future
+ * incarnation of a ublk server via the start_recovery/end_recovery
+ * commands.
+ */
+static inline bool ublk_nosrv_should_stop_dev(struct ublk_device *ub)
 {
-	return ubq->flags & UBLK_F_USER_RECOVERY;
+	return !(ub->dev_info.flags & UBLK_F_USER_RECOVERY);
 }
 
-static inline bool ublk_can_use_recovery(struct ublk_device *ub)
+static inline bool ublk_dev_in_recoverable_state(struct ublk_device *ub)
 {
-	return ub->dev_info.flags & UBLK_F_USER_RECOVERY;
+	return ub->dev_info.state == UBLK_S_DEV_QUIESCED ||
+	       ub->dev_info.state == UBLK_S_DEV_FAIL_IO;
 }
 
 static void ublk_free_disk(struct gendisk *disk)
@@ -711,7 +739,7 @@ static void ublk_free_disk(struct gendisk *disk)
 	struct ublk_device *ub = disk->private_data;
 
 	clear_bit(UB_STATE_USED, &ub->state);
-	put_device(&ub->cdev_dev);
+	ublk_put_device(ub);
 }
 
 static void ublk_store_owner_uid_gid(unsigned int *owner_uid,
@@ -1079,7 +1107,7 @@ static void __ublk_fail_req(struct ublk_queue *ubq, struct ublk_io *io,
 {
 	WARN_ON_ONCE(io->flags & UBLK_IO_FLAG_ACTIVE);
 
-	if (ublk_queue_can_use_recovery_reissue(ubq))
+	if (ublk_nosrv_should_reissue_outstanding(ubq->dev))
 		blk_mq_requeue_request(req, false);
 	else
 		ublk_put_req_ref(ubq, req);
@@ -1107,7 +1135,7 @@ static inline void __ublk_abort_rq(struct ublk_queue *ubq,
 		struct request *rq)
 {
 	/* We cannot process this rq so just requeue it. */
-	if (ublk_queue_can_use_recovery(ubq))
+	if (ublk_nosrv_dev_should_queue_io(ubq->dev))
 		blk_mq_requeue_request(rq, false);
 	else
 		blk_mq_end_request(rq, BLK_STS_IOERR);
@@ -1252,10 +1280,7 @@ static enum blk_eh_timer_return ublk_timeout(struct request *rq)
 		struct ublk_device *ub = ubq->dev;
 
 		if (ublk_abort_requests(ub, ubq)) {
-			if (ublk_can_use_recovery(ub))
-				schedule_work(&ub->quiesce_work);
-			else
-				schedule_work(&ub->stop_work);
+			schedule_work(&ub->nosrv_work);
 		}
 		return BLK_EH_DONE;
 	}
@@ -1270,6 +1295,10 @@ static blk_status_t ublk_queue_rq(struct blk_mq_hw_ctx *hctx,
 	struct request *rq = bd->rq;
 	blk_status_t res;
 
+	if (unlikely(ubq->fail_io)) {
+		return BLK_STS_TARGET;
+	}
+
 	/* fill iod to slot in io cmd buffer */
 	res = ublk_setup_iod(ubq, rq);
 	if (unlikely(res != BLK_STS_OK))
@@ -1284,7 +1313,7 @@ static blk_status_t ublk_queue_rq(struct blk_mq_hw_ctx *hctx,
 	 * Note: force_abort is guaranteed to be seen because it is set
 	 * before request queue is unqiuesced.
 	 */
-	if (ublk_queue_can_use_recovery(ubq) && unlikely(ubq->force_abort))
+	if (ublk_nosrv_should_queue_io(ubq) && unlikely(ubq->force_abort))
 		return BLK_STS_IOERR;
 
 	if (unlikely(ubq->canceling)) {
@@ -1338,7 +1367,7 @@ static int ublk_ch_mmap(struct file *filp, struct vm_area_struct *vma)
 {
 	struct ublk_device *ub = filp->private_data;
 	size_t sz = vma->vm_end - vma->vm_start;
-	unsigned max_sz = UBLK_MAX_QUEUE_DEPTH * sizeof(struct ublksrv_io_desc);
+	unsigned max_sz = ublk_max_cmd_buf_size();
 	unsigned long pfn, end, phys_off = vma->vm_pgoff << PAGE_SHIFT;
 	int q_id, ret = 0;
 
@@ -1505,10 +1534,7 @@ static void ublk_uring_cmd_cancel_fn(struct io_uring_cmd *cmd,
 	ublk_cancel_cmd(ubq, io, issue_flags);
 
 	if (need_schedule) {
-		if (ublk_can_use_recovery(ub))
-			schedule_work(&ub->quiesce_work);
-		else
-			schedule_work(&ub->stop_work);
+		schedule_work(&ub->nosrv_work);
 	}
 }
 
@@ -1571,20 +1597,6 @@ static void __ublk_quiesce_dev(struct ublk_device *ub)
 	ub->dev_info.state = UBLK_S_DEV_QUIESCED;
 }
 
-static void ublk_quiesce_work_fn(struct work_struct *work)
-{
-	struct ublk_device *ub =
-		container_of(work, struct ublk_device, quiesce_work);
-
-	mutex_lock(&ub->mutex);
-	if (ub->dev_info.state != UBLK_S_DEV_LIVE)
-		goto unlock;
-	__ublk_quiesce_dev(ub);
- unlock:
-	mutex_unlock(&ub->mutex);
-	ublk_cancel_dev(ub);
-}
-
 static void ublk_unquiesce_dev(struct ublk_device *ub)
 {
 	int i;
@@ -1606,6 +1618,21 @@ static void ublk_unquiesce_dev(struct ublk_device *ub)
 	blk_mq_kick_requeue_list(ub->ub_disk->queue);
 }
 
+static struct gendisk *ublk_detach_disk(struct ublk_device *ub)
+{
+	struct gendisk *disk;
+
+	/* Sync with ublk_abort_queue() by holding the lock */
+	spin_lock(&ub->lock);
+	disk = ub->ub_disk;
+	ub->dev_info.state = UBLK_S_DEV_DEAD;
+	ub->dev_info.ublksrv_pid = -1;
+	ub->ub_disk = NULL;
+	spin_unlock(&ub->lock);
+
+	return disk;
+}
+
 static void ublk_stop_dev(struct ublk_device *ub)
 {
 	struct gendisk *disk;
@@ -1613,26 +1640,50 @@ static void ublk_stop_dev(struct ublk_device *ub)
 	mutex_lock(&ub->mutex);
 	if (ub->dev_info.state == UBLK_S_DEV_DEAD)
 		goto unlock;
-	if (ublk_can_use_recovery(ub)) {
+	if (ublk_nosrv_dev_should_queue_io(ub)) {
 		if (ub->dev_info.state == UBLK_S_DEV_LIVE)
 			__ublk_quiesce_dev(ub);
 		ublk_unquiesce_dev(ub);
 	}
 	del_gendisk(ub->ub_disk);
-
-	/* Sync with ublk_abort_queue() by holding the lock */
-	spin_lock(&ub->lock);
-	disk = ub->ub_disk;
-	ub->dev_info.state = UBLK_S_DEV_DEAD;
-	ub->dev_info.ublksrv_pid = -1;
-	ub->ub_disk = NULL;
-	spin_unlock(&ub->lock);
+	disk = ublk_detach_disk(ub);
 	put_disk(disk);
  unlock:
 	mutex_unlock(&ub->mutex);
 	ublk_cancel_dev(ub);
 }
 
+static void ublk_nosrv_work(struct work_struct *work)
+{
+	struct ublk_device *ub =
+		container_of(work, struct ublk_device, nosrv_work);
+	int i;
+
+	if (ublk_nosrv_should_stop_dev(ub)) {
+		ublk_stop_dev(ub);
+		return;
+	}
+
+	mutex_lock(&ub->mutex);
+	if (ub->dev_info.state != UBLK_S_DEV_LIVE)
+		goto unlock;
+
+	if (ublk_nosrv_dev_should_queue_io(ub)) {
+		__ublk_quiesce_dev(ub);
+	} else {
+		blk_mq_quiesce_queue(ub->ub_disk->queue);
+		ub->dev_info.state = UBLK_S_DEV_FAIL_IO;
+		for (i = 0; i < ub->dev_info.nr_hw_queues; i++) {
+			ublk_get_queue(ub, i)->fail_io = true;
+		}
+		blk_mq_unquiesce_queue(ub->ub_disk->queue);
+	}
+
+ unlock:
+	mutex_unlock(&ub->mutex);
+	ublk_cancel_dev(ub);
+}
+
 /* device can only be started after all IOs are ready */
 static void ublk_mark_io_ready(struct ublk_device *ub, struct ublk_queue *ubq)
 {
@@ -1999,7 +2050,6 @@ static const struct file_operations ublk_ch_fops = {
 	.owner = THIS_MODULE,
 	.open = ublk_ch_open,
 	.release = ublk_ch_release,
-	.llseek = no_llseek,
 	.read_iter = ublk_ch_read_iter,
 	.write_iter = ublk_ch_write_iter,
 	.uring_cmd = ublk_ch_uring_cmd,
@@ -2147,14 +2197,6 @@ static int ublk_add_chdev(struct ublk_device *ub)
 	return ret;
 }
 
-static void ublk_stop_work_fn(struct work_struct *work)
-{
-	struct ublk_device *ub =
-		container_of(work, struct ublk_device, stop_work);
-
-	ublk_stop_dev(ub);
-}
-
 /* align max io buffer size with PAGE_SIZE */
 static void ublk_align_max_io_size(struct ublk_device *ub)
 {
@@ -2171,7 +2213,6 @@ static int ublk_add_tag_set(struct ublk_device *ub)
 	ub->tag_set.queue_depth = ub->dev_info.queue_depth;
 	ub->tag_set.numa_node = NUMA_NO_NODE;
 	ub->tag_set.cmd_size = sizeof(struct ublk_rq_data);
-	ub->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
 	ub->tag_set.driver_data = ub;
 	return blk_mq_alloc_tag_set(&ub->tag_set);
 }
@@ -2179,10 +2220,9 @@ static int ublk_add_tag_set(struct ublk_device *ub)
 static void ublk_remove(struct ublk_device *ub)
 {
 	ublk_stop_dev(ub);
-	cancel_work_sync(&ub->stop_work);
-	cancel_work_sync(&ub->quiesce_work);
+	cancel_work_sync(&ub->nosrv_work);
 	cdev_device_del(&ub->cdev, &ub->cdev_dev);
-	put_device(&ub->cdev_dev);
+	ublk_put_device(ub);
 	ublks_added--;
 }
 
@@ -2205,12 +2245,58 @@ static struct ublk_device *ublk_get_device_from_id(int idx)
 static int ublk_ctrl_start_dev(struct ublk_device *ub, struct io_uring_cmd *cmd)
 {
 	const struct ublksrv_ctrl_cmd *header = io_uring_sqe_cmd(cmd->sqe);
+	const struct ublk_param_basic *p = &ub->params.basic;
 	int ublksrv_pid = (int)header->data[0];
+	struct queue_limits lim = {
+		.logical_block_size	= 1 << p->logical_bs_shift,
+		.physical_block_size	= 1 << p->physical_bs_shift,
+		.io_min			= 1 << p->io_min_shift,
+		.io_opt			= 1 << p->io_opt_shift,
+		.max_hw_sectors		= p->max_sectors,
+		.chunk_sectors		= p->chunk_sectors,
+		.virt_boundary_mask	= p->virt_boundary_mask,
+		.max_segments		= USHRT_MAX,
+		.max_segment_size	= UINT_MAX,
+		.dma_alignment		= 3,
+	};
 	struct gendisk *disk;
 	int ret = -EINVAL;
 
 	if (ublksrv_pid <= 0)
 		return -EINVAL;
+	if (!(ub->params.types & UBLK_PARAM_TYPE_BASIC))
+		return -EINVAL;
+
+	if (ub->params.types & UBLK_PARAM_TYPE_DISCARD) {
+		const struct ublk_param_discard *pd = &ub->params.discard;
+
+		lim.discard_alignment = pd->discard_alignment;
+		lim.discard_granularity = pd->discard_granularity;
+		lim.max_hw_discard_sectors = pd->max_discard_sectors;
+		lim.max_write_zeroes_sectors = pd->max_write_zeroes_sectors;
+		lim.max_discard_segments = pd->max_discard_segments;
+	}
+
+	if (ub->params.types & UBLK_PARAM_TYPE_ZONED) {
+		const struct ublk_param_zoned *p = &ub->params.zoned;
+
+		if (!IS_ENABLED(CONFIG_BLK_DEV_ZONED))
+			return -EOPNOTSUPP;
+
+		lim.features |= BLK_FEAT_ZONED;
+		lim.max_active_zones = p->max_active_zones;
+		lim.max_open_zones =  p->max_open_zones;
+		lim.max_hw_zone_append_sectors = p->max_zone_append_sectors;
+	}
+
+	if (ub->params.basic.attrs & UBLK_ATTR_VOLATILE_CACHE) {
+		lim.features |= BLK_FEAT_WRITE_CACHE;
+		if (ub->params.basic.attrs & UBLK_ATTR_FUA)
+			lim.features |= BLK_FEAT_FUA;
+	}
+
+	if (ub->params.basic.attrs & UBLK_ATTR_ROTATIONAL)
+		lim.features |= BLK_FEAT_ROTATIONAL;
 
 	if (wait_for_completion_interruptible(&ub->completion) != 0)
 		return -EINTR;
@@ -2222,7 +2308,7 @@ static int ublk_ctrl_start_dev(struct ublk_device *ub, struct io_uring_cmd *cmd)
 		goto out_unlock;
 	}
 
-	disk = blk_mq_alloc_disk(&ub->tag_set, NULL);
+	disk = blk_mq_alloc_disk(&ub->tag_set, &lim, NULL);
 	if (IS_ERR(disk)) {
 		ret = PTR_ERR(disk);
 		goto out_unlock;
@@ -2234,15 +2320,13 @@ static int ublk_ctrl_start_dev(struct ublk_device *ub, struct io_uring_cmd *cmd)
 	ub->dev_info.ublksrv_pid = ublksrv_pid;
 	ub->ub_disk = disk;
 
-	ret = ublk_apply_params(ub);
-	if (ret)
-		goto out_put_disk;
+	ublk_apply_params(ub);
 
 	/* don't probe partitions if any one ubq daemon is un-trusted */
 	if (ub->nr_privileged_daemon != ub->nr_queues_ready)
 		set_bit(GD_SUPPRESS_PART_SCAN, &disk->state);
 
-	get_device(&ub->cdev_dev);
+	ublk_get_device(ub);
 	ub->dev_info.state = UBLK_S_DEV_LIVE;
 
 	if (ublk_dev_is_zoned(ub)) {
@@ -2259,10 +2343,9 @@ static int ublk_ctrl_start_dev(struct ublk_device *ub, struct io_uring_cmd *cmd)
 
 out_put_cdev:
 	if (ret) {
-		ub->dev_info.state = UBLK_S_DEV_DEAD;
+		ublk_detach_disk(ub);
 		ublk_put_device(ub);
 	}
-out_put_disk:
 	if (ret)
 		put_disk(disk);
 out_unlock:
@@ -2346,6 +2429,19 @@ static int ublk_ctrl_add_dev(struct io_uring_cmd *cmd)
 	else if (!(info.flags & UBLK_F_UNPRIVILEGED_DEV))
 		return -EPERM;
 
+	/* forbid nonsense combinations of recovery flags */
+	switch (info.flags & UBLK_F_ALL_RECOVERY_FLAGS) {
+	case 0:
+	case UBLK_F_USER_RECOVERY:
+	case (UBLK_F_USER_RECOVERY | UBLK_F_USER_RECOVERY_REISSUE):
+	case (UBLK_F_USER_RECOVERY | UBLK_F_USER_RECOVERY_FAIL_IO):
+		break;
+	default:
+		pr_warn("%s: invalid recovery flags %llx\n", __func__,
+			info.flags & UBLK_F_ALL_RECOVERY_FLAGS);
+		return -EINVAL;
+	}
+
 	/*
 	 * unprivileged device can't be trusted, but RECOVERY and
 	 * RECOVERY_REISSUE still may hang error handling, so can't
@@ -2354,10 +2450,19 @@ static int ublk_ctrl_add_dev(struct io_uring_cmd *cmd)
 	 * TODO: provide forward progress for RECOVERY handler, so that
 	 * unprivileged device can benefit from it
 	 */
-	if (info.flags & UBLK_F_UNPRIVILEGED_DEV)
+	if (info.flags & UBLK_F_UNPRIVILEGED_DEV) {
 		info.flags &= ~(UBLK_F_USER_RECOVERY_REISSUE |
 				UBLK_F_USER_RECOVERY);
 
+		/*
+		 * For USER_COPY, we depends on userspace to fill request
+		 * buffer by pwrite() to ublk char device, which can't be
+		 * used for unprivileged device
+		 */
+		if (info.flags & UBLK_F_USER_COPY)
+			return -EINVAL;
+	}
+
 	/* the created device is always owned by current user */
 	ublk_store_owner_uid_gid(&info.owner_uid, &info.owner_gid);
 
@@ -2389,8 +2494,7 @@ static int ublk_ctrl_add_dev(struct io_uring_cmd *cmd)
 		goto out_unlock;
 	mutex_init(&ub->mutex);
 	spin_lock_init(&ub->lock);
-	INIT_WORK(&ub->quiesce_work, ublk_quiesce_work_fn);
-	INIT_WORK(&ub->stop_work, ublk_stop_work_fn);
+	INIT_WORK(&ub->nosrv_work, ublk_nosrv_work);
 
 	ret = ublk_alloc_dev_number(ub, header->dev_id);
 	if (ret < 0)
@@ -2474,7 +2578,7 @@ static inline bool ublk_idr_freed(int id)
 	return ptr == NULL;
 }
 
-static int ublk_ctrl_del_dev(struct ublk_device **p_ub)
+static int ublk_ctrl_del_dev(struct ublk_device **p_ub, bool wait)
 {
 	struct ublk_device *ub = *p_ub;
 	int idx = ub->ub_number;
@@ -2508,7 +2612,7 @@ static int ublk_ctrl_del_dev(struct ublk_device **p_ub)
 	 * - the device number is freed already, we will not find this
 	 *   device via ublk_get_device_from_id()
 	 */
-	if (wait_event_interruptible(ublk_idr_wq, ublk_idr_freed(idx)))
+	if (wait && wait_event_interruptible(ublk_idr_wq, ublk_idr_freed(idx)))
 		return -EINTR;
 	return 0;
 }
@@ -2525,9 +2629,7 @@ static inline void ublk_ctrl_cmd_dump(struct io_uring_cmd *cmd)
 static int ublk_ctrl_stop_dev(struct ublk_device *ub)
 {
 	ublk_stop_dev(ub);
-	cancel_work_sync(&ub->stop_work);
-	cancel_work_sync(&ub->quiesce_work);
-
+	cancel_work_sync(&ub->nosrv_work);
 	return 0;
 }
 
@@ -2613,9 +2715,12 @@ static int ublk_ctrl_set_params(struct ublk_device *ub,
 	if (ph.len > sizeof(struct ublk_params))
 		ph.len = sizeof(struct ublk_params);
 
-	/* parameters can only be changed when device isn't live */
 	mutex_lock(&ub->mutex);
-	if (ub->dev_info.state == UBLK_S_DEV_LIVE) {
+	if (test_bit(UB_STATE_USED, &ub->state)) {
+		/*
+		 * Parameters can only be changed when device hasn't
+		 * been started yet
+		 */
 		ret = -EACCES;
 	} else if (copy_from_user(&ub->params, argp, ph.len)) {
 		ret = -EFAULT;
@@ -2664,7 +2769,9 @@ static int ublk_ctrl_start_recovery(struct ublk_device *ub,
 	int i;
 
 	mutex_lock(&ub->mutex);
-	if (!ublk_can_use_recovery(ub))
+	if (ublk_nosrv_should_stop_dev(ub))
+		goto out_unlock;
+	if (!ub->nr_queues_ready)
 		goto out_unlock;
 	/*
 	 * START_RECOVERY is only allowd after:
@@ -2673,14 +2780,18 @@ static int ublk_ctrl_start_recovery(struct ublk_device *ub,
 	 *     and related io_uring ctx is freed so file struct of /dev/ublkcX is
 	 *     released.
 	 *
+	 * and one of the following holds
+	 *
 	 * (2) UBLK_S_DEV_QUIESCED is set, which means the quiesce_work:
 	 *     (a)has quiesced request queue
 	 *     (b)has requeued every inflight rqs whose io_flags is ACTIVE
 	 *     (c)has requeued/aborted every inflight rqs whose io_flags is NOT ACTIVE
 	 *     (d)has completed/camceled all ioucmds owned by ther dying process
+	 *
+	 * (3) UBLK_S_DEV_FAIL_IO is set, which means the queue is not
+	 *     quiesced, but all I/O is being immediately errored
 	 */
-	if (test_bit(UB_STATE_OPEN, &ub->state) ||
-			ub->dev_info.state != UBLK_S_DEV_QUIESCED) {
+	if (test_bit(UB_STATE_OPEN, &ub->state) || !ublk_dev_in_recoverable_state(ub)) {
 		ret = -EBUSY;
 		goto out_unlock;
 	}
@@ -2704,6 +2815,7 @@ static int ublk_ctrl_end_recovery(struct ublk_device *ub,
 	const struct ublksrv_ctrl_cmd *header = io_uring_sqe_cmd(cmd->sqe);
 	int ublksrv_pid = (int)header->data[0];
 	int ret = -EINVAL;
+	int i;
 
 	pr_devel("%s: Waiting for new ubq_daemons(nr: %d) are ready, dev id %d...\n",
 			__func__, ub->dev_info.nr_hw_queues, header->dev_id);
@@ -2715,21 +2827,32 @@ static int ublk_ctrl_end_recovery(struct ublk_device *ub,
 			__func__, ub->dev_info.nr_hw_queues, header->dev_id);
 
 	mutex_lock(&ub->mutex);
-	if (!ublk_can_use_recovery(ub))
+	if (ublk_nosrv_should_stop_dev(ub))
 		goto out_unlock;
 
-	if (ub->dev_info.state != UBLK_S_DEV_QUIESCED) {
+	if (!ublk_dev_in_recoverable_state(ub)) {
 		ret = -EBUSY;
 		goto out_unlock;
 	}
 	ub->dev_info.ublksrv_pid = ublksrv_pid;
 	pr_devel("%s: new ublksrv_pid %d, dev id %d\n",
 			__func__, ublksrv_pid, header->dev_id);
-	blk_mq_unquiesce_queue(ub->ub_disk->queue);
-	pr_devel("%s: queue unquiesced, dev id %d.\n",
-			__func__, header->dev_id);
-	blk_mq_kick_requeue_list(ub->ub_disk->queue);
-	ub->dev_info.state = UBLK_S_DEV_LIVE;
+
+	if (ublk_nosrv_dev_should_queue_io(ub)) {
+		ub->dev_info.state = UBLK_S_DEV_LIVE;
+		blk_mq_unquiesce_queue(ub->ub_disk->queue);
+		pr_devel("%s: queue unquiesced, dev id %d.\n",
+				__func__, header->dev_id);
+		blk_mq_kick_requeue_list(ub->ub_disk->queue);
+	} else {
+		blk_mq_quiesce_queue(ub->ub_disk->queue);
+		ub->dev_info.state = UBLK_S_DEV_LIVE;
+		for (i = 0; i < ub->dev_info.nr_hw_queues; i++) {
+			ublk_get_queue(ub, i)->fail_io = false;
+		}
+		blk_mq_unquiesce_queue(ub->ub_disk->queue);
+	}
+
 	ret = 0;
  out_unlock:
 	mutex_unlock(&ub->mutex);
@@ -2907,7 +3030,10 @@ static int ublk_ctrl_uring_cmd(struct io_uring_cmd *cmd,
 		ret = ublk_ctrl_add_dev(cmd);
 		break;
 	case UBLK_CMD_DEL_DEV:
-		ret = ublk_ctrl_del_dev(&ub);
+		ret = ublk_ctrl_del_dev(&ub, true);
+		break;
+	case UBLK_CMD_DEL_DEV_ASYNC:
+		ret = ublk_ctrl_del_dev(&ub, false);
 		break;
 	case UBLK_CMD_GET_QUEUE_AFFINITY:
 		ret = ublk_ctrl_get_queue_affinity(ub, cmd);
@@ -2925,7 +3051,7 @@ static int ublk_ctrl_uring_cmd(struct io_uring_cmd *cmd,
 		ret = ublk_ctrl_end_recovery(ub, cmd);
 		break;
 	default:
-		ret = -ENOTSUPP;
+		ret = -EOPNOTSUPP;
 		break;
 	}
 
@@ -3019,4 +3145,5 @@ module_param_cb(ublks_max, &ublk_max_ublks_ops, &ublks_max, 0644);
 MODULE_PARM_DESC(ublks_max, "max number of ublk devices allowed to add(default: 64)");
 
 MODULE_AUTHOR("Ming Lei <ming.lei@redhat.com>");
+MODULE_DESCRIPTION("Userspace block device");
 MODULE_LICENSE("GPL");