nvme: move common call to nvme_cleanup_cmd to core layer

nvme_cleanup_cmd should be called for each call to nvme_setup_cmd
(symmetrical functions). Move the call for nvme_cleanup_cmd to the common
core layer and call it during nvme_complete_rq for the good flow. For
error flow, each transport will call nvme_cleanup_cmd independently. Also
take care of a special case of path failure, where we call
nvme_complete_rq without doing nvme_setup_cmd.

Signed-off-by: Max Gurtovoy <maxg@mellanox.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 154fa4e..05f2dfa 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -1160,8 +1160,6 @@ static void nvme_rdma_unmap_data(struct nvme_rdma_queue *queue,
 	}
 
 	ib_dma_unmap_sg(ibdev, req->sg_table.sgl, req->nents, rq_dma_dir(rq));
-
-	nvme_cleanup_cmd(rq);
 	sg_free_table_chained(&req->sg_table, SG_CHUNK_SIZE);
 }
 
@@ -1760,7 +1758,6 @@ static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx,
 	if (unlikely(err < 0)) {
 		dev_err(queue->ctrl->ctrl.device,
 			     "Failed to map data (%d)\n", err);
-		nvme_cleanup_cmd(rq);
 		goto err;
 	}
 
@@ -1771,18 +1768,19 @@ static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx,
 
 	err = nvme_rdma_post_send(queue, sqe, req->sge, req->num_sge,
 			req->mr ? &req->reg_wr.wr : NULL);
-	if (unlikely(err)) {
-		nvme_rdma_unmap_data(queue, rq);
-		goto err;
-	}
+	if (unlikely(err))
+		goto err_unmap;
 
 	return BLK_STS_OK;
 
+err_unmap:
+	nvme_rdma_unmap_data(queue, rq);
 err:
 	if (err == -ENOMEM || err == -EAGAIN)
 		ret = BLK_STS_RESOURCE;
 	else
 		ret = BLK_STS_IOERR;
+	nvme_cleanup_cmd(rq);
 unmap_qe:
 	ib_dma_unmap_single(dev, req->sqe.dma, sizeof(struct nvme_command),
 			    DMA_TO_DEVICE);