1 files changed, 142 insertions, 66 deletions

diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
index 6ba2c1dd1d87..c6d18cd8af44 100644
--- a/drivers/block/ublk_drv.c
+++ b/drivers/block/ublk_drv.c
@@ -60,7 +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                                \
@@ -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 */
@@ -664,30 +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)
@@ -1063,7 +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);
@@ -1091,7 +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);
@@ -1236,10 +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;
 	}
@@ -1254,6 +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))
@@ -1268,7 +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)) {
@@ -1322,7 +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;
 
@@ -1489,10 +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);
 	}
 }
 
@@ -1555,20 +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;
@@ -1597,7 +1625,7 @@ 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);
@@ -1617,6 +1645,37 @@ static void ublk_stop_dev(struct ublk_device *ub)
 	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)
 {
@@ -2130,14 +2189,6 @@ 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)
 {
@@ -2162,8 +2213,7 @@ 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);
 	ublk_put_device(ub);
 	ublks_added--;
@@ -2229,7 +2279,7 @@ static int ublk_ctrl_start_dev(struct ublk_device *ub, struct io_uring_cmd *cmd)
 		lim.features |= BLK_FEAT_ZONED;
 		lim.max_active_zones = p->max_active_zones;
 		lim.max_open_zones =  p->max_open_zones;
-		lim.max_zone_append_sectors = p->max_zone_append_sectors;
+		lim.max_hw_zone_append_sectors = p->max_zone_append_sectors;
 	}
 
 	if (ub->params.basic.attrs & UBLK_ATTR_VOLATILE_CACHE) {
@@ -2372,6 +2422,19 @@ 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
@@ -2424,8 +2487,7 @@ 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)
@@ -2560,9 +2622,7 @@ 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;
 }
 
@@ -2699,7 +2759,7 @@ 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;
@@ -2710,14 +2770,18 @@ 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;
 	}
@@ -2741,6 +2805,7 @@ 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);
@@ -2752,21 +2817,32 @@ 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);