nvme-pci: optimize mapping single segment requests using SGLs

fix #29327388

commit 297910571f08f1d7e398793df6e606ebb375a3f1 upstream

If the controller supports SGLs we can take another short cut for single
segment request, given that we can always map those without another
indirection structure, and thus don't need to create a scatterlist
structure.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NKeith Busch <keith.busch@intel.com>
Reviewed-by: NSagi Grimberg <sagi@grimberg.me>
Reviewed-by: NChaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Signed-off-by: NBaolin Wang <baolin.wang@linux.alibaba.com>
Reviewed-by: NJoseph Qi <joseph.qi@linux.alibaba.com>

drivers/nvme/host/pci.c

@@ -824,6 +824,23 @@ static blk_status_t nvme_setup_prp_simple(struct nvme_dev *dev,
 	return 0;
 }
 
+static blk_status_t nvme_setup_sgl_simple(struct nvme_dev *dev,
+		struct request *req, struct nvme_rw_command *cmnd,
+		struct bio_vec *bv)
+{
+	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
+
+	iod->first_dma = dma_map_bvec(dev->dev, bv, rq_dma_dir(req), 0);
+	if (dma_mapping_error(dev->dev, iod->first_dma))
+		return BLK_STS_RESOURCE;
+	iod->dma_len = bv->bv_len;
+
+	cmnd->dptr.sgl.addr = cpu_to_le64(iod->first_dma);
+	cmnd->dptr.sgl.length = cpu_to_le32(iod->dma_len);
+	cmnd->dptr.sgl.type = NVME_SGL_FMT_DATA_DESC << 4;
+	return 0;
+}
+
 static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req,
 		struct nvme_command *cmnd)
 {
@@ -840,6 +857,11 @@ static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req,
 		if (bv.bv_offset + bv.bv_len <= dev->ctrl.page_size * 2)
 			return nvme_setup_prp_simple(dev, req,
 						     &cmnd->rw, &bv);
+
+		if (iod->nvmeq->qid &&
+		    dev->ctrl.sgls & ((1 << 0) | (1 << 1)))
+			return nvme_setup_sgl_simple(dev, req,
+						     &cmnd->rw, &bv);
 	}
 
 	iod->dma_len = 0;