block and nvme passthrough error handling

index beae70a0e5e5..38f88552aa31 100644
@@ -63,6 +63,19 @@ void blk_execute_rq_nowait(struct gendisk *bd_disk, struct request *rq,
 }
 EXPORT_SYMBOL_GPL(blk_execute_rq_nowait);
 
+static bool blk_rq_is_poll(struct request *rq)
+{
+	return rq->mq_hctx && rq->mq_hctx->type == HCTX_TYPE_POLL;
+}
+
+static void blk_rq_poll_completion(struct request *rq, struct completion *wait)
+{
+	do {
+		blk_poll(rq->q, request_to_qc_t(rq->mq_hctx, rq), true);
+		cond_resched();
+	} while (!completion_done(wait));
+}
+
 /**
  * blk_execute_rq - insert a request into queue for execution
  * @bd_disk:	matching gendisk

@@ -83,7 +96,10 @@ void blk_execute_rq(struct gendisk *bd_disk, struct request *rq, int at_head)
 
 	/* Prevent hang_check timer from firing at us during very long I/O */
 	hang_check = sysctl_hung_task_timeout_secs;
-	if (hang_check)
+
+	if (blk_rq_is_poll(rq))
+		blk_rq_poll_completion(rq, &wait);
+	else if (hang_check)
 		while (!wait_for_completion_io_timeout(&wait, hang_check * (HZ/2)));
 	else
 		wait_for_completion_io(&wait);

index 762125f2905f..1a73eed61eee 100644
@@ -1012,31 +1012,6 @@ blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req)
 }
 EXPORT_SYMBOL_GPL(nvme_setup_cmd);
 
-static void nvme_end_sync_rq(struct request *rq, blk_status_t error)
-{
-	struct completion *waiting = rq->end_io_data;
-
-	rq->end_io_data = NULL;
-	complete(waiting);
-}
-
-static void nvme_execute_rq_polled(struct request_queue *q,
-		struct gendisk *bd_disk, struct request *rq, int at_head)
-{
-	DECLARE_COMPLETION_ONSTACK(wait);
-
-	WARN_ON_ONCE(!test_bit(QUEUE_FLAG_POLL, &q->queue_flags));
-
-	rq->cmd_flags |= REQ_HIPRI;
-	rq->end_io_data = &wait;
-	blk_execute_rq_nowait(bd_disk, rq, at_head, nvme_end_sync_rq);
-
-	while (!completion_done(&wait)) {
-		blk_poll(q, request_to_qc_t(rq->mq_hctx, rq), true);
-		cond_resched();
-	}
-}
-
 /*
  * Returns 0 on success.  If the result is negative, it's a Linux error code;
  * if the result is positive, it's an NVM Express status code

@@ -1044,7 +1019,7 @@ static void nvme_execute_rq_polled(struct request_queue *q,
 int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
 		union nvme_result *result, void *buffer, unsigned bufflen,
 		unsigned timeout, int qid, int at_head,
-		blk_mq_req_flags_t flags, bool poll)
+		blk_mq_req_flags_t flags)
 {
 	struct request *req;
 	int ret;

@@ -1065,10 +1040,7 @@ int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
 			goto out;
 	}
 
-	if (poll)
-		nvme_execute_rq_polled(req->q, NULL, req, at_head);
-	else
-		blk_execute_rq(NULL, req, at_head);
+	blk_execute_rq(NULL, req, at_head);
 	if (result)
 		*result = nvme_req(req)->result;
 	if (nvme_req(req)->flags & NVME_REQ_CANCELLED)

@@ -1085,7 +1057,7 @@ int nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
 		void *buffer, unsigned bufflen)
 {
 	return __nvme_submit_sync_cmd(q, cmd, NULL, buffer, bufflen, 0,
-			NVME_QID_ANY, 0, 0, false);
+			NVME_QID_ANY, 0, 0);
 }
 EXPORT_SYMBOL_GPL(nvme_submit_sync_cmd);
 

@@ -1449,7 +1421,7 @@ static int nvme_features(struct nvme_ctrl *dev, u8 op, unsigned int fid,
 	c.features.dword11 = cpu_to_le32(dword11);
 
 	ret = __nvme_submit_sync_cmd(dev->admin_q, &c, &res,
-			buffer, buflen, 0, NVME_QID_ANY, 0, 0, false);
+			buffer, buflen, 0, NVME_QID_ANY, 0, 0);
 	if (ret >= 0 && result)
 		*result = le32_to_cpu(res.u32);
 	return ret;

@@ -2048,7 +2020,7 @@ int nvme_sec_submit(void *data, u16 spsp, u8 secp, void *buffer, size_t len,
 	cmd.common.cdw11 = cpu_to_le32(len);
 
 	return __nvme_submit_sync_cmd(ctrl->admin_q, &cmd, NULL, buffer, len, 0,
-			NVME_QID_ANY, 1, 0, false);
+			NVME_QID_ANY, 1, 0);
 }
 EXPORT_SYMBOL_GPL(nvme_sec_submit);
 #endif /* CONFIG_BLK_SED_OPAL */

index a2bb7fc63a73..133ef9a62f53 100644
@@ -151,7 +151,7 @@ int nvmf_reg_read32(struct nvme_ctrl *ctrl, u32 off, u32 *val)
 	cmd.prop_get.offset = cpu_to_le32(off);
 
 	ret = __nvme_submit_sync_cmd(ctrl->fabrics_q, &cmd, &res, NULL, 0, 0,
-			NVME_QID_ANY, 0, 0, false);
+			NVME_QID_ANY, 0, 0);
 
 	if (ret >= 0)
 		*val = le64_to_cpu(res.u64);

@@ -198,7 +198,7 @@ int nvmf_reg_read64(struct nvme_ctrl *ctrl, u32 off, u64 *val)
 	cmd.prop_get.offset = cpu_to_le32(off);
 
 	ret = __nvme_submit_sync_cmd(ctrl->fabrics_q, &cmd, &res, NULL, 0, 0,
-			NVME_QID_ANY, 0, 0, false);
+			NVME_QID_ANY, 0, 0);
 
 	if (ret >= 0)
 		*val = le64_to_cpu(res.u64);

@@ -244,7 +244,7 @@ int nvmf_reg_write32(struct nvme_ctrl *ctrl, u32 off, u32 val)
 	cmd.prop_set.value = cpu_to_le64(val);
 
 	ret = __nvme_submit_sync_cmd(ctrl->fabrics_q, &cmd, NULL, NULL, 0, 0,
-			NVME_QID_ANY, 0, 0, false);
+			NVME_QID_ANY, 0, 0);
 	if (unlikely(ret))
 		dev_err(ctrl->device,
 			"Property Set error: %d, offset %#x\n",

@@ -396,7 +396,7 @@ int nvmf_connect_admin_queue(struct nvme_ctrl *ctrl)
 
 	ret = __nvme_submit_sync_cmd(ctrl->fabrics_q, &cmd, &res,
 			data, sizeof(*data), 0, NVME_QID_ANY, 1,
-			BLK_MQ_REQ_RESERVED | BLK_MQ_REQ_NOWAIT, false);
+			BLK_MQ_REQ_RESERVED | BLK_MQ_REQ_NOWAIT);
 	if (ret) {
 		nvmf_log_connect_error(ctrl, ret, le32_to_cpu(res.u32),
 				       &cmd, data);

@@ -420,7 +420,6 @@ EXPORT_SYMBOL_GPL(nvmf_connect_admin_queue);
  * @qid:	NVMe I/O queue number for the new I/O connection between
  *		host and target (note qid == 0 is illegal as this is
  *		the Admin queue, per NVMe standard).
- * @poll:	Whether or not to poll for the completion of the connect cmd.
  *
  * This function issues a fabrics-protocol connection
  * of a NVMe I/O queue (via NVMe Fabrics "Connect" command)

@@ -432,7 +431,7 @@ EXPORT_SYMBOL_GPL(nvmf_connect_admin_queue);
  *	> 0: NVMe error status code
  *	< 0: Linux errno error code
  */
-int nvmf_connect_io_queue(struct nvme_ctrl *ctrl, u16 qid, bool poll)
+int nvmf_connect_io_queue(struct nvme_ctrl *ctrl, u16 qid)
 {
 	struct nvme_command cmd;
 	struct nvmf_connect_data *data;

@@ -459,7 +458,7 @@ int nvmf_connect_io_queue(struct nvme_ctrl *ctrl, u16 qid, bool poll)
 
 	ret = __nvme_submit_sync_cmd(ctrl->connect_q, &cmd, &res,
 			data, sizeof(*data), 0, qid, 1,
-			BLK_MQ_REQ_RESERVED | BLK_MQ_REQ_NOWAIT, poll);
+			BLK_MQ_REQ_RESERVED | BLK_MQ_REQ_NOWAIT);
 	if (ret) {
 		nvmf_log_connect_error(ctrl, ret, le32_to_cpu(res.u32),
 				       &cmd, data);

index d7f7974dc208..b698a3e5cb35 100644
@@ -178,7 +178,7 @@ int nvmf_reg_read32(struct nvme_ctrl *ctrl, u32 off, u32 *val);
 int nvmf_reg_read64(struct nvme_ctrl *ctrl, u32 off, u64 *val);
 int nvmf_reg_write32(struct nvme_ctrl *ctrl, u32 off, u32 val);
 int nvmf_connect_admin_queue(struct nvme_ctrl *ctrl);
-int nvmf_connect_io_queue(struct nvme_ctrl *ctrl, u16 qid, bool poll);
+int nvmf_connect_io_queue(struct nvme_ctrl *ctrl, u16 qid);
 int nvmf_register_transport(struct nvmf_transport_ops *ops);
 void nvmf_unregister_transport(struct nvmf_transport_ops *ops);
 void nvmf_free_options(struct nvmf_ctrl_options *opts);

index d9ab9e7871d0..e4495ee55552 100644
@@ -2346,7 +2346,7 @@ nvme_fc_connect_io_queues(struct nvme_fc_ctrl *ctrl, u16 qsize)
 					(qsize / 5));
 		if (ret)
 			break;
-		ret = nvmf_connect_io_queue(&ctrl->ctrl, i, false);
+		ret = nvmf_connect_io_queue(&ctrl->ctrl, i);
 		if (ret)
 			break;
 

index 0015860ec12b..84bff995a308 100644
@@ -658,7 +658,7 @@ int nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
 int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
 		union nvme_result *result, void *buffer, unsigned bufflen,
 		unsigned timeout, int qid, int at_head,
-		blk_mq_req_flags_t flags, bool poll);
+		blk_mq_req_flags_t flags);
 int nvme_set_features(struct nvme_ctrl *dev, unsigned int fid,
 		      unsigned int dword11, void *buffer, size_t buflen,
 		      u32 *result);

index 37943dc4c2c1..36c018762701 100644
@@ -680,11 +680,10 @@ static void nvme_rdma_stop_io_queues(struct nvme_rdma_ctrl *ctrl)
 static int nvme_rdma_start_queue(struct nvme_rdma_ctrl *ctrl, int idx)
 {
 	struct nvme_rdma_queue *queue = &ctrl->queues[idx];
-	bool poll = nvme_rdma_poll_queue(queue);
 	int ret;
 
 	if (idx)
-		ret = nvmf_connect_io_queue(&ctrl->ctrl, idx, poll);
+		ret = nvmf_connect_io_queue(&ctrl->ctrl, idx);
 	else
 		ret = nvmf_connect_admin_queue(&ctrl->ctrl);
 

index d07eb13d8713..f18e2beceed1 100644
@@ -1559,7 +1559,7 @@ static int nvme_tcp_start_queue(struct nvme_ctrl *nctrl, int idx)
 	int ret;
 
 	if (idx)
-		ret = nvmf_connect_io_queue(nctrl, idx, false);
+		ret = nvmf_connect_io_queue(nctrl, idx);
 	else
 		ret = nvmf_connect_admin_queue(nctrl);
 

index 74b3b150e1a5..9718c06abe38 100644
@@ -335,7 +335,7 @@ static int nvme_loop_connect_io_queues(struct nvme_loop_ctrl *ctrl)
 	int i, ret;
 
 	for (i = 1; i < ctrl->ctrl.queue_count; i++) {
-		ret = nvmf_connect_io_queue(&ctrl->ctrl, i, false);
+		ret = nvmf_connect_io_queue(&ctrl->ctrl, i);
 		if (ret)
 			return ret;
 		set_bit(NVME_LOOP_Q_LIVE, &ctrl->queues[i].flags);

index 38f88552aa31..d6cd501c0d34 100644
@@ -21,7 +21,7 @@ static void blk_end_sync_rq(struct request *rq, blk_status_t error)
 {
 	struct completion *waiting = rq->end_io_data;
 
-	rq->end_io_data = NULL;
+	rq->end_io_data = (void *)(uintptr_t)error;
 
 	/*
 	 * complete last, if this is a stack request the process (and thus

@@ -85,8 +85,9 @@ static void blk_rq_poll_completion(struct request *rq, struct completion *wait)
  * Description:
  *    Insert a fully prepared request at the back of the I/O scheduler queue
  *    for execution and wait for completion.
+ * Return: The blk_status_t result provided to blk_mq_end_request().
  */
-void blk_execute_rq(struct gendisk *bd_disk, struct request *rq, int at_head)
+blk_status_t blk_execute_rq(struct gendisk *bd_disk, struct request *rq, int at_head)
 {
 	DECLARE_COMPLETION_ONSTACK(wait);
 	unsigned long hang_check;

@@ -103,5 +104,7 @@ void blk_execute_rq(struct gendisk *bd_disk, struct request *rq, int at_head)
 		while (!wait_for_completion_io_timeout(&wait, hang_check * (HZ/2)));
 	else
 		wait_for_completion_io(&wait);
+
+	return (blk_status_t)(uintptr_t)rq->end_io_data;
 }
 EXPORT_SYMBOL(blk_execute_rq);

index 2c28577b50f4..2d2b477241ba 100644
@@ -936,10 +936,12 @@ extern int blk_rq_map_kern(struct request_queue *, struct request *, void *, uns
 extern int blk_rq_map_user_iov(struct request_queue *, struct request *,
 			       struct rq_map_data *, const struct iov_iter *,
 			       gfp_t);
-extern void blk_execute_rq(struct gendisk *, struct request *, int);
 extern void blk_execute_rq_nowait(struct gendisk *,
 				  struct request *, int, rq_end_io_fn *);
 
+blk_status_t blk_execute_rq(struct gendisk *bd_disk, struct request *rq,
+			    int at_head);
+
 /* Helper to convert REQ_OP_XXX to its string format XXX */
 extern const char *blk_op_str(unsigned int op);
 

index 1a73eed61eee..99e10476f377 100644
@@ -589,6 +589,7 @@ EXPORT_SYMBOL_NS_GPL(nvme_put_ns, NVME_TARGET_PASSTHRU);
 
 static inline void nvme_clear_nvme_request(struct request *req)
 {
+	nvme_req(req)->status = 0;
 	nvme_req(req)->retries = 0;
 	nvme_req(req)->flags = 0;
 	req->rq_flags |= RQF_DONTPREP;

@@ -1012,6 +1013,21 @@ blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req)
 }
 EXPORT_SYMBOL_GPL(nvme_setup_cmd);
 
+/*
+ * Return values:
+ * 0:  success
+ * >0: nvme controller's cqe status response
+ * <0: kernel error in lieu of controller response
+ */
+static int nvme_passthrough_status(struct request *rq, blk_status_t status)
+{
+	if (nvme_req(rq)->flags & NVME_REQ_CANCELLED)
+		return -EINTR;
+	else if (nvme_req(rq)->status)
+		return nvme_req(rq)->status;
+	return blk_status_to_errno(status);
+}
+
 /*
  * Returns 0 on success.  If the result is negative, it's a Linux error code;
  * if the result is positive, it's an NVM Express status code

@@ -1022,6 +1038,7 @@ int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
 		blk_mq_req_flags_t flags)
 {
 	struct request *req;
+	blk_status_t status;
 	int ret;
 
 	if (qid == NVME_QID_ANY)

@@ -1040,13 +1057,10 @@ int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
 			goto out;
 	}
 
-	blk_execute_rq(NULL, req, at_head);
-	if (result)
+	status = blk_execute_rq(NULL, req, at_head);
+	ret = nvme_passthrough_status(req, status);
+	if (result && ret >= 0)
 		*result = nvme_req(req)->result;
-	if (nvme_req(req)->flags & NVME_REQ_CANCELLED)
-		ret = -EINTR;
-	else
-		ret = nvme_req(req)->status;
  out:
 	blk_mq_free_request(req);
 	return ret;

@@ -1134,18 +1148,21 @@ static void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects)
 	}
 }
 
-void nvme_execute_passthru_rq(struct request *rq)
+int nvme_execute_passthru_rq(struct request *rq)
 {
 	struct nvme_command *cmd = nvme_req(rq)->cmd;
 	struct nvme_ctrl *ctrl = nvme_req(rq)->ctrl;
 	struct nvme_ns *ns = rq->q->queuedata;
 	struct gendisk *disk = ns ? ns->disk : NULL;
+	blk_status_t status;
 	u32 effects;
 
 	effects = nvme_passthru_start(ctrl, ns, cmd->common.opcode);
-	blk_execute_rq(disk, rq, 0);
+	status = blk_execute_rq(disk, rq, 0);
 	if (effects) /* nothing to be done for zero cmd effects */
 		nvme_passthru_end(ctrl, effects);
+
+	return nvme_passthrough_status(rq, status);
 }
 EXPORT_SYMBOL_NS_GPL(nvme_execute_passthru_rq, NVME_TARGET_PASSTHRU);
 

index 9557ead02de1..4e6bcc3c1c0d 100644
@@ -93,11 +93,7 @@ static int nvme_submit_user_cmd(struct request_queue *q,
 		}
 	}
 
-	nvme_execute_passthru_rq(req);
-	if (nvme_req(req)->flags & NVME_REQ_CANCELLED)
-		ret = -EINTR;
-	else
-		ret = nvme_req(req)->status;
+	ret = nvme_execute_passthru_rq(req);
 	if (result)
 		*result = le64_to_cpu(nvme_req(req)->result.u64);
 	if (meta && !ret && !write) {

index 84bff995a308..9ea827871d67 100644
@@ -877,7 +877,7 @@ static inline void nvme_hwmon_exit(struct nvme_ctrl *ctrl)
 
 u32 nvme_command_effects(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 			 u8 opcode);
-void nvme_execute_passthru_rq(struct request *rq);
+int nvme_execute_passthru_rq(struct request *rq);
 struct nvme_ctrl *nvme_ctrl_from_file(struct file *file);
 struct nvme_ns *nvme_find_get_ns(struct nvme_ctrl *ctrl, unsigned nsid);
 void nvme_put_ns(struct nvme_ns *ns);

index 39b1473f7204..ba28ce42cb55 100644
@@ -153,11 +153,10 @@ static void nvmet_passthru_execute_cmd_work(struct work_struct *w)
 {
 	struct nvmet_req *req = container_of(w, struct nvmet_req, p.work);
 	struct request *rq = req->p.rq;
-	u16 status;
+	int status;
 
-	nvme_execute_passthru_rq(rq);
+	status = nvme_execute_passthru_rq(rq);
 
-	status = nvme_req(rq)->status;
 	if (status == NVME_SC_SUCCESS &&
 	    req->cmd->common.opcode == nvme_admin_identify) {
 		switch (req->cmd->identify.cns) {

@@ -168,7 +167,8 @@ static void nvmet_passthru_execute_cmd_work(struct work_struct *w)
 			nvmet_passthru_override_id_ns(req);
 			break;
 		}
-	}
+	} else if (status < 0)
+		status = NVME_SC_INTERNAL;
 
 	req->cqe->result = nvme_req(rq)->result;
 	nvmet_req_complete(req, status);