nvme: add support for batched completion of polled IO

Take advantage of struct io_comp_batch, if passed in to the nvme poll
handler. If it's set, rather than complete each request individually
inline, store them in the io_comp_batch list. We only do so for requests
that will complete successfully, anything else will be completed inline as
before.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

3 files changed, 51 insertions, 12 deletions

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index ae15cb714596..3109bdf137e4 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -346,15 +346,19 @@ static inline enum nvme_disposition nvme_decide_disposition(struct request *req)
 	return RETRY;
 }
 
-static inline void nvme_end_req(struct request *req)
+static inline void nvme_end_req_zoned(struct request *req)
 {
-	blk_status_t status = nvme_error_status(nvme_req(req)->status);
-
 	if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) &&
 	    req_op(req) == REQ_OP_ZONE_APPEND)
 		req->__sector = nvme_lba_to_sect(req->q->queuedata,
 			le64_to_cpu(nvme_req(req)->result.u64));
+}
+
+static inline void nvme_end_req(struct request *req)
+{
+	blk_status_t status = nvme_error_status(nvme_req(req)->status);
 
+	nvme_end_req_zoned(req);
 	nvme_trace_bio_complete(req);
 	blk_mq_end_request(req, status);
 }
@@ -381,6 +385,13 @@ void nvme_complete_rq(struct request *req)
 }
 EXPORT_SYMBOL_GPL(nvme_complete_rq);
 
+void nvme_complete_batch_req(struct request *req)
+{
+	nvme_cleanup_cmd(req);
+	nvme_end_req_zoned(req);
+}
+EXPORT_SYMBOL_GPL(nvme_complete_batch_req);
+
 /*
  * Called to unwind from ->queue_rq on a failed command submission so that the
  * multipathing code gets called to potentially failover to another path.
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index ed79a6c7e804..ef2467b93adb 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -638,6 +638,20 @@ static inline bool nvme_is_aen_req(u16 qid, __u16 command_id)
 }
 
 void nvme_complete_rq(struct request *req);
+void nvme_complete_batch_req(struct request *req);
+
+static __always_inline void nvme_complete_batch(struct io_comp_batch *iob,
+						void (*fn)(struct request *rq))
+{
+	struct request *req;
+
+	rq_list_for_each(&iob->req_list, req) {
+		fn(req);
+		nvme_complete_batch_req(req);
+	}
+	blk_mq_end_request_batch(iob);
+}
+
 blk_status_t nvme_host_path_error(struct request *req);
 bool nvme_cancel_request(struct request *req, void *data, bool reserved);
 void nvme_cancel_tagset(struct nvme_ctrl *ctrl);
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index bb0482dfab3c..83d3503d5b88 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -959,7 +959,7 @@ out_free_cmd:
 	return ret;
 }
 
-static void nvme_pci_complete_rq(struct request *req)
+static __always_inline void nvme_pci_unmap_rq(struct request *req)
 {
 	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
 	struct nvme_dev *dev = iod->nvmeq->dev;
@@ -969,9 +969,19 @@ static void nvme_pci_complete_rq(struct request *req)
 			       rq_integrity_vec(req)->bv_len, rq_data_dir(req));
 	if (blk_rq_nr_phys_segments(req))
 		nvme_unmap_data(dev, req);
+}
+
+static void nvme_pci_complete_rq(struct request *req)
+{
+	nvme_pci_unmap_rq(req);
 	nvme_complete_rq(req);
 }
 
+static void nvme_pci_complete_batch(struct io_comp_batch *iob)
+{
+	nvme_complete_batch(iob, nvme_pci_unmap_rq);
+}
+
 /* We read the CQE phase first to check if the rest of the entry is valid */
 static inline bool nvme_cqe_pending(struct nvme_queue *nvmeq)
 {
@@ -996,7 +1006,8 @@ static inline struct blk_mq_tags *nvme_queue_tagset(struct nvme_queue *nvmeq)
 	return nvmeq->dev->tagset.tags[nvmeq->qid - 1];
 }
 
-static inline void nvme_handle_cqe(struct nvme_queue *nvmeq, u16 idx)
+static inline void nvme_handle_cqe(struct nvme_queue *nvmeq,
+				   struct io_comp_batch *iob, u16 idx)
 {
 	struct nvme_completion *cqe = &nvmeq->cqes[idx];
 	__u16 command_id = READ_ONCE(cqe->command_id);
@@ -1023,7 +1034,9 @@ static inline void nvme_handle_cqe(struct nvme_queue *nvmeq, u16 idx)
 	}
 
 	trace_nvme_sq(req, cqe->sq_head, nvmeq->sq_tail);
-	if (!nvme_try_complete_req(req, cqe->status, cqe->result))
+	if (!nvme_try_complete_req(req, cqe->status, cqe->result) &&
+	    !blk_mq_add_to_batch(req, iob, nvme_req(req)->status,
+					nvme_pci_complete_batch))
 		nvme_pci_complete_rq(req);
 }
 
@@ -1039,7 +1052,8 @@ static inline void nvme_update_cq_head(struct nvme_queue *nvmeq)
 	}
 }
 
-static inline int nvme_process_cq(struct nvme_queue *nvmeq)
+static inline int nvme_poll_cq(struct nvme_queue *nvmeq,
+			       struct io_comp_batch *iob)
 {
 	int found = 0;
 
@@ -1050,7 +1064,7 @@ static inline int nvme_process_cq(struct nvme_queue *nvmeq)
 		 * the cqe requires a full read memory barrier
 		 */
 		dma_rmb();
-		nvme_handle_cqe(nvmeq, nvmeq->cq_head);
+		nvme_handle_cqe(nvmeq, iob, nvmeq->cq_head);
 		nvme_update_cq_head(nvmeq);
 	}
 
@@ -1063,7 +1077,7 @@ static irqreturn_t nvme_irq(int irq, void *data)
 {
 	struct nvme_queue *nvmeq = data;
 
-	if (nvme_process_cq(nvmeq))
+	if (nvme_poll_cq(nvmeq, NULL))
 		return IRQ_HANDLED;
 	return IRQ_NONE;
 }
@@ -1088,7 +1102,7 @@ static void nvme_poll_irqdisable(struct nvme_queue *nvmeq)
 	WARN_ON_ONCE(test_bit(NVMEQ_POLLED, &nvmeq->flags));
 
 	disable_irq(pci_irq_vector(pdev, nvmeq->cq_vector));
-	nvme_process_cq(nvmeq);
+	nvme_poll_cq(nvmeq, NULL);
 	enable_irq(pci_irq_vector(pdev, nvmeq->cq_vector));
 }
 
@@ -1101,7 +1115,7 @@ static int nvme_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob)
 		return 0;
 
 	spin_lock(&nvmeq->cq_poll_lock);
-	found = nvme_process_cq(nvmeq);
+	found = nvme_poll_cq(nvmeq, iob);
 	spin_unlock(&nvmeq->cq_poll_lock);
 
 	return found;
@@ -1434,7 +1448,7 @@ static void nvme_reap_pending_cqes(struct nvme_dev *dev)
 
 	for (i = dev->ctrl.queue_count - 1; i > 0; i--) {
 		spin_lock(&dev->queues[i].cq_poll_lock);
-		nvme_process_cq(&dev->queues[i]);
+		nvme_poll_cq(&dev->queues[i], NULL);
 		spin_unlock(&dev->queues[i].cq_poll_lock);
 	}
 }