RDMA/hns: Support DSCP

Add support for DSCP configuration. For DSCP, get dscp-prio mapping
via hns3 nic driver api .get_dscp_prio() and fill the SL (in WQE for
UD or in QPC for RC) with the priority value. The prio-tc mapping is
configured to HW by hns3 nic driver. HW will select a corresponding
TC according to SL and the prio-tc mapping.

Signed-off-by: Junxian Huang <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]
Signed-off-by: Leon Romanovsky <[e-mail]>

drivers/infiniband/hw/hns/hns_roce_ah.c

···
 	struct hns_roce_dev *hr_dev = to_hr_dev(ibah->device);
 	struct hns_roce_ib_create_ah_resp resp = {};
 	struct hns_roce_ah *ah = to_hr_ah(ibah);
-	int ret = 0;
-	u32 max_sl;
+	u8 tclass = get_tclass(grh);
+	u8 priority = 0;
+	u8 tc_mode = 0;
+	int ret;
 
 	if (hr_dev->pci_dev->revision == PCI_REVISION_ID_HIP08 && udata)
 		return -EOPNOTSUPP;
···
 	ah->av.hop_limit = grh->hop_limit;
 	ah->av.flowlabel = grh->flow_label;
 	ah->av.udp_sport = get_ah_udp_sport(ah_attr);
-	ah->av.tclass = get_tclass(grh);
+	ah->av.tclass = tclass;
 
-	ah->av.sl = rdma_ah_get_sl(ah_attr);
-	max_sl = min_t(u32, MAX_SERVICE_LEVEL, hr_dev->caps.sl_num - 1);
-	if (unlikely(ah->av.sl > max_sl)) {
-		ibdev_err_ratelimited(&hr_dev->ib_dev,
-				      "failed to set sl, sl (%u) shouldn't be larger than %u.\n",
-				      ah->av.sl, max_sl);
+	ret = hr_dev->hw->get_dscp(hr_dev, tclass, &tc_mode, &priority);
+	if (ret == -EOPNOTSUPP)
+		ret = 0;
+
+	if (ret && grh->sgid_attr->gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP)
+		return ret;
+
+	if (tc_mode == HNAE3_TC_MAP_MODE_DSCP &&
+	    grh->sgid_attr->gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP)
+		ah->av.sl = priority;
+	else
+		ah->av.sl = rdma_ah_get_sl(ah_attr);
+
+	if (!check_sl_valid(hr_dev, ah->av.sl))
 		return -EINVAL;
-	}
 
 	memcpy(ah->av.dgid, grh->dgid.raw, HNS_ROCE_GID_SIZE);
 	memcpy(ah->av.mac, ah_attr->roce.dmac, ETH_ALEN);
···
 	}
 
 	if (udata) {
+		resp.priority = ah->av.sl;
+		resp.tc_mode = tc_mode;
 		memcpy(resp.dmac, ah_attr->roce.dmac, ETH_ALEN);
 		ret = ib_copy_to_udata(udata, &resp,
 				       min(udata->outlen, sizeof(resp)));

drivers/infiniband/hw/hns/hns_roce_device.h

···
 	struct hns_user_mmap_entry *dwqe_mmap_entry;
 	u32			config;
 	enum hns_roce_cong_type	cong_type;
+	u8			tc_mode;
+	u8			priority;
 };
 
 struct hns_roce_ib_iboe {
···
 	int (*query_sccc)(struct hns_roce_dev *hr_dev, u32 qpn, void *buffer);
 	int (*query_hw_counter)(struct hns_roce_dev *hr_dev,
 				u64 *stats, u32 port, int *hw_counters);
+	int (*get_dscp)(struct hns_roce_dev *hr_dev, u8 dscp,
+			u8 *tc_mode, u8 *priority);
 	const struct ib_device_ops *hns_roce_dev_ops;
 	const struct ib_device_ops *hns_roce_dev_srq_ops;
 };
···
 hns_roce_user_mmap_entry_insert(struct ib_ucontext *ucontext, u64 address,
 				size_t length,
 				enum hns_roce_mmap_type mmap_type);
+bool check_sl_valid(struct hns_roce_dev *hr_dev, u8 sl);
+
 #endif /* _HNS_ROCE_DEVICE_H */

drivers/infiniband/hw/hns/hns_roce_hw_v2.c

···
 	hr_reg_write(ud_sq_wqe, UD_SEND_WQE_HOPLIMIT, ah->av.hop_limit);
 	hr_reg_write(ud_sq_wqe, UD_SEND_WQE_TCLASS, ah->av.tclass);
 	hr_reg_write(ud_sq_wqe, UD_SEND_WQE_FLOW_LABEL, ah->av.flowlabel);
-
-	if (WARN_ON(ah->av.sl > MAX_SERVICE_LEVEL))
-		return -EINVAL;
-
 	hr_reg_write(ud_sq_wqe, UD_SEND_WQE_SL, ah->av.sl);
 
 	ud_sq_wqe->sgid_index = ah->av.gid_index;
···
 	return 0;
 }
 
+static int hns_roce_hw_v2_get_dscp(struct hns_roce_dev *hr_dev, u8 dscp,
+				   u8 *tc_mode, u8 *priority)
+{
+	struct hns_roce_v2_priv *priv = hr_dev->priv;
+	struct hnae3_handle *handle = priv->handle;
+	const struct hnae3_ae_ops *ops = handle->ae_algo->ops;
+
+	if (!ops->get_dscp_prio)
+		return -EOPNOTSUPP;
+
+	return ops->get_dscp_prio(handle, dscp, tc_mode, priority);
+}
+
+bool check_sl_valid(struct hns_roce_dev *hr_dev, u8 sl)
+{
+	u32 max_sl;
+
+	max_sl = min_t(u32, MAX_SERVICE_LEVEL, hr_dev->caps.sl_num - 1);
+	if (unlikely(sl > max_sl)) {
+		ibdev_err_ratelimited(&hr_dev->ib_dev,
+				      "failed to set SL(%u). Shouldn't be larger than %u.\n",
+				      sl, max_sl);
+		return false;
+	}
+
+	return true;
+}
+
+static int hns_roce_set_sl(struct ib_qp *ibqp,
+			   const struct ib_qp_attr *attr,
+			   struct hns_roce_v2_qp_context *context,
+			   struct hns_roce_v2_qp_context *qpc_mask)
+{
+	const struct ib_global_route *grh = rdma_ah_read_grh(&attr->ah_attr);
+	struct hns_roce_dev *hr_dev = to_hr_dev(ibqp->device);
+	struct hns_roce_qp *hr_qp = to_hr_qp(ibqp);
+	struct ib_device *ibdev = &hr_dev->ib_dev;
+	int ret;
+
+	ret = hns_roce_hw_v2_get_dscp(hr_dev, get_tclass(&attr->ah_attr.grh),
+				      &hr_qp->tc_mode, &hr_qp->priority);
+	if (ret && ret != -EOPNOTSUPP &&
+	    grh->sgid_attr->gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP) {
+		ibdev_err_ratelimited(ibdev,
+				      "failed to get dscp, ret = %d.\n", ret);
+		return ret;
+	}
+
+	if (hr_qp->tc_mode == HNAE3_TC_MAP_MODE_DSCP &&
+	    grh->sgid_attr->gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP)
+		hr_qp->sl = hr_qp->priority;
+	else
+		hr_qp->sl = rdma_ah_get_sl(&attr->ah_attr);
+
+	if (!check_sl_valid(hr_dev, hr_qp->sl))
+		return -EINVAL;
+
+	hr_reg_write(context, QPC_SL, hr_qp->sl);
+	hr_reg_clear(qpc_mask, QPC_SL);
+
+	return 0;
+}
+
 static int hns_roce_v2_set_path(struct ib_qp *ibqp,
 				const struct ib_qp_attr *attr,
 				int attr_mask,
···
 	int is_roce_protocol;
 	u16 vlan_id = 0xffff;
 	bool is_udp = false;
-	u32 max_sl;
 	u8 ib_port;
 	u8 hr_port;
 	int ret;
-
-	max_sl = min_t(u32, MAX_SERVICE_LEVEL, hr_dev->caps.sl_num - 1);
-	if (unlikely(sl > max_sl)) {
-		ibdev_err_ratelimited(ibdev,
-				      "failed to fill QPC, sl (%u) shouldn't be larger than %u.\n",
-				      sl, max_sl);
-		return -EINVAL;
-	}
 
 	/*
 	 * If free_mr_en of qp is set, it means that this qp comes from
···
 	 * In the loopback scenario, only sl needs to be set.
 	 */
 	if (hr_qp->free_mr_en) {
+		if (!check_sl_valid(hr_dev, sl))
+			return -EINVAL;
 		hr_reg_write(context, QPC_SL, sl);
 		hr_reg_clear(qpc_mask, QPC_SL);
 		hr_qp->sl = sl;
···
 	memcpy(context->dgid, grh->dgid.raw, sizeof(grh->dgid.raw));
 	memset(qpc_mask->dgid, 0, sizeof(grh->dgid.raw));
 
-	hr_qp->sl = sl;
-	hr_reg_write(context, QPC_SL, hr_qp->sl);
-	hr_reg_clear(qpc_mask, QPC_SL);
-
-	return 0;
+	return  hns_roce_set_sl(ibqp, attr, context, qpc_mask);
 }
 
 static bool check_qp_state(enum ib_qp_state cur_state,
···
 	.query_srqc = hns_roce_v2_query_srqc,
 	.query_sccc = hns_roce_v2_query_sccc,
 	.query_hw_counter = hns_roce_hw_v2_query_counter,
+	.get_dscp = hns_roce_hw_v2_get_dscp,
 	.hns_roce_dev_ops = &hns_roce_v2_dev_ops,
 	.hns_roce_dev_srq_ops = &hns_roce_v2_dev_srq_ops,
 };

drivers/infiniband/hw/hns/hns_roce_qp.c

···
 		       int attr_mask, struct ib_udata *udata)
 {
 	struct hns_roce_dev *hr_dev = to_hr_dev(ibqp->device);
+	struct hns_roce_ib_modify_qp_resp resp = {};
 	struct hns_roce_qp *hr_qp = to_hr_qp(ibqp);
 	enum ib_qp_state cur_state, new_state;
 	int ret = -EINVAL;
···
 
 	ret = hr_dev->hw->modify_qp(ibqp, attr, attr_mask, cur_state,
 				    new_state, udata);
+	if (ret)
+		goto out;
+
+	if (udata && udata->outlen) {
+		resp.tc_mode = hr_qp->tc_mode;
+		resp.priority = hr_qp->sl;
+		ret = ib_copy_to_udata(udata, &resp,
+				       min(udata->outlen, sizeof(resp)));
+		if (ret)
+			ibdev_err_ratelimited(&hr_dev->ib_dev,
+					      "failed to copy modify qp resp.\n");
+	}
 
 out:
 	mutex_unlock(&hr_qp->mutex);

include/uapi/rdma/hns-abi.h

···
 	__aligned_u64 dwqe_mmap_key;
 };
 
+struct hns_roce_ib_modify_qp_resp {
+	__u8	tc_mode;
+	__u8	priority;
+	__u8	reserved[6];
+};
+
 enum {
 	HNS_ROCE_EXSGE_FLAGS = 1 << 0,
 	HNS_ROCE_RQ_INLINE_FLAGS = 1 << 1,
···
 
 struct hns_roce_ib_create_ah_resp {
 	__u8 dmac[6];
-	__u8 reserved[2];
+	__u8 priority;
+	__u8 tc_mode;
 };
 
 #endif /* HNS_ABI_USER_H */