RDMA/hns: Support userspace configuring congestion control algorithm with QP granularity

Currently, congestion control algorithm is statically configured in
FW, and all QPs use the same algorithm(except UD which has a fixed
configuration of DCQCN). This is not flexible enough.

Support userspace configuring congestion control algorithm with QP
granularity while creating QPs. If the algorithm is not specified in
userspace, use the default one.

Signed-off-by: Junxian Huang <huangjunxian6@hisilicon.com>
Link: https://lore.kernel.org/r/20240301104845.1141083-1-huangjunxian6@hisilicon.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>

5 files changed, 69 insertions, 12 deletions

diff --git a/drivers/infiniband/hw/hns/hns_roce_device.h b/drivers/infiniband/hw/hns/hns_roce_device.h
index 1d062c522d69..bc015901a7d3 100644
--- a/drivers/infiniband/hw/hns/hns_roce_device.h
+++ b/drivers/infiniband/hw/hns/hns_roce_device.h
@@ -845,7 +845,8 @@ struct hns_roce_caps {
 	u16		default_aeq_period;
 	u16		default_aeq_arm_st;
 	u16		default_ceq_arm_st;
-	enum hns_roce_cong_type cong_type;
+	u8		cong_cap;
+	enum hns_roce_cong_type default_cong_type;
 };
 
 enum hns_roce_device_state {
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
index 42e28586cefa..38e426f4afb5 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
@@ -2209,11 +2209,12 @@ static int hns_roce_query_caps(struct hns_roce_dev *hr_dev)
 	caps->max_wqes = 1 << le16_to_cpu(resp_c->sq_depth);
 
 	caps->num_srqs = 1 << hr_reg_read(resp_d, PF_CAPS_D_NUM_SRQS);
-	caps->cong_type = hr_reg_read(resp_d, PF_CAPS_D_CONG_TYPE);
+	caps->cong_cap = hr_reg_read(resp_d, PF_CAPS_D_CONG_CAP);
 	caps->max_srq_wrs = 1 << le16_to_cpu(resp_d->srq_depth);
 	caps->ceqe_depth = 1 << hr_reg_read(resp_d, PF_CAPS_D_CEQ_DEPTH);
 	caps->num_comp_vectors = hr_reg_read(resp_d, PF_CAPS_D_NUM_CEQS);
 	caps->aeqe_depth = 1 << hr_reg_read(resp_d, PF_CAPS_D_AEQ_DEPTH);
+	caps->default_cong_type = hr_reg_read(resp_d, PF_CAPS_D_DEFAULT_ALG);
 	caps->reserved_pds = hr_reg_read(resp_d, PF_CAPS_D_RSV_PDS);
 	caps->num_uars = 1 << hr_reg_read(resp_d, PF_CAPS_D_NUM_UARS);
 	caps->reserved_qps = hr_reg_read(resp_d, PF_CAPS_D_RSV_QPS);
@@ -4737,14 +4738,8 @@ enum {
 static int check_cong_type(struct ib_qp *ibqp,
 			   struct hns_roce_congestion_algorithm *cong_alg)
 {
-	struct hns_roce_dev *hr_dev = to_hr_dev(ibqp->device);
 	struct hns_roce_qp *hr_qp = to_hr_qp(ibqp);
 
-	if (ibqp->qp_type == IB_QPT_UD || ibqp->qp_type == IB_QPT_GSI)
-		hr_qp->cong_type = CONG_TYPE_DCQCN;
-	else
-		hr_qp->cong_type = hr_dev->caps.cong_type;
-
 	/* different congestion types match different configurations */
 	switch (hr_qp->cong_type) {
 	case CONG_TYPE_DCQCN:
@@ -4772,9 +4767,6 @@ static int check_cong_type(struct ib_qp *ibqp,
 		cong_alg->wnd_mode_sel = WND_LIMIT;
 		break;
 	default:
-		ibdev_warn(&hr_dev->ib_dev,
-			   "invalid type(%u) for congestion selection.\n",
-			   hr_qp->cong_type);
 		hr_qp->cong_type = CONG_TYPE_DCQCN;
 		cong_alg->alg_sel = CONG_DCQCN;
 		cong_alg->alg_sub_sel = UNSUPPORT_CONG_LEVEL;
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
index cd97cbee682a..359a74672ba1 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
@@ -1214,12 +1214,13 @@ struct hns_roce_query_pf_caps_d {
 #define PF_CAPS_D_RQWQE_HOP_NUM PF_CAPS_D_FIELD_LOC(21, 20)
 #define PF_CAPS_D_EX_SGE_HOP_NUM PF_CAPS_D_FIELD_LOC(23, 22)
 #define PF_CAPS_D_SQWQE_HOP_NUM PF_CAPS_D_FIELD_LOC(25, 24)
-#define PF_CAPS_D_CONG_TYPE PF_CAPS_D_FIELD_LOC(29, 26)
+#define PF_CAPS_D_CONG_CAP PF_CAPS_D_FIELD_LOC(29, 26)
 #define PF_CAPS_D_CEQ_DEPTH PF_CAPS_D_FIELD_LOC(85, 64)
 #define PF_CAPS_D_NUM_CEQS PF_CAPS_D_FIELD_LOC(95, 86)
 #define PF_CAPS_D_AEQ_DEPTH PF_CAPS_D_FIELD_LOC(117, 96)
 #define PF_CAPS_D_AEQ_ARM_ST PF_CAPS_D_FIELD_LOC(119, 118)
 #define PF_CAPS_D_CEQ_ARM_ST PF_CAPS_D_FIELD_LOC(121, 120)
+#define PF_CAPS_D_DEFAULT_ALG PF_CAPS_D_FIELD_LOC(127, 122)
 #define PF_CAPS_D_RSV_PDS PF_CAPS_D_FIELD_LOC(147, 128)
 #define PF_CAPS_D_NUM_UARS PF_CAPS_D_FIELD_LOC(155, 148)
 #define PF_CAPS_D_RSV_QPS PF_CAPS_D_FIELD_LOC(179, 160)
diff --git a/drivers/infiniband/hw/hns/hns_roce_main.c b/drivers/infiniband/hw/hns/hns_roce_main.c
index b55fe6911f9f..1dc60c2b2b7a 100644
--- a/drivers/infiniband/hw/hns/hns_roce_main.c
+++ b/drivers/infiniband/hw/hns/hns_roce_main.c
@@ -394,6 +394,9 @@ static int hns_roce_alloc_ucontext(struct ib_ucontext *uctx,
 			resp.config |= HNS_ROCE_RSP_CQE_INLINE_FLAGS;
 	}
 
+	if (hr_dev->pci_dev->revision >= PCI_REVISION_ID_HIP09)
+		resp.congest_type = hr_dev->caps.cong_cap;
+
 	ret = hns_roce_uar_alloc(hr_dev, &context->uar);
 	if (ret)
 		goto error_out;
diff --git a/drivers/infiniband/hw/hns/hns_roce_qp.c b/drivers/infiniband/hw/hns/hns_roce_qp.c
index 31b147210688..f35a66325d9a 100644
--- a/drivers/infiniband/hw/hns/hns_roce_qp.c
+++ b/drivers/infiniband/hw/hns/hns_roce_qp.c
@@ -1004,6 +1004,60 @@ static void free_kernel_wrid(struct hns_roce_qp *hr_qp)
 	kfree(hr_qp->sq.wrid);
 }
 
+static void default_congest_type(struct hns_roce_dev *hr_dev,
+				 struct hns_roce_qp *hr_qp)
+{
+	if (hr_qp->ibqp.qp_type == IB_QPT_UD ||
+	    hr_qp->ibqp.qp_type == IB_QPT_GSI)
+		hr_qp->cong_type = CONG_TYPE_DCQCN;
+	else
+		hr_qp->cong_type = hr_dev->caps.default_cong_type;
+}
+
+static int set_congest_type(struct hns_roce_qp *hr_qp,
+			    struct hns_roce_ib_create_qp *ucmd)
+{
+	struct hns_roce_dev *hr_dev = to_hr_dev(hr_qp->ibqp.device);
+
+	switch (ucmd->cong_type_flags) {
+	case HNS_ROCE_CREATE_QP_FLAGS_DCQCN:
+		hr_qp->cong_type = CONG_TYPE_DCQCN;
+		break;
+	case HNS_ROCE_CREATE_QP_FLAGS_LDCP:
+		hr_qp->cong_type = CONG_TYPE_LDCP;
+		break;
+	case HNS_ROCE_CREATE_QP_FLAGS_HC3:
+		hr_qp->cong_type = CONG_TYPE_HC3;
+		break;
+	case HNS_ROCE_CREATE_QP_FLAGS_DIP:
+		hr_qp->cong_type = CONG_TYPE_DIP;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (!test_bit(hr_qp->cong_type, (unsigned long *)&hr_dev->caps.cong_cap))
+		return -EOPNOTSUPP;
+
+	if (hr_qp->ibqp.qp_type == IB_QPT_UD &&
+	    hr_qp->cong_type != CONG_TYPE_DCQCN)
+		return -EOPNOTSUPP;
+
+	return 0;
+}
+
+static int set_congest_param(struct hns_roce_dev *hr_dev,
+			     struct hns_roce_qp *hr_qp,
+			     struct hns_roce_ib_create_qp *ucmd)
+{
+	if (ucmd->comp_mask & HNS_ROCE_CREATE_QP_MASK_CONGEST_TYPE)
+		return set_congest_type(hr_qp, ucmd);
+
+	default_congest_type(hr_dev, hr_qp);
+
+	return 0;
+}
+
 static int set_qp_param(struct hns_roce_dev *hr_dev, struct hns_roce_qp *hr_qp,
 			struct ib_qp_init_attr *init_attr,
 			struct ib_udata *udata,
@@ -1043,6 +1097,10 @@ static int set_qp_param(struct hns_roce_dev *hr_dev, struct hns_roce_qp *hr_qp,
 			ibdev_err(ibdev,
 				  "failed to set user SQ size, ret = %d.\n",
 				  ret);
+
+		ret = set_congest_param(hr_dev, hr_qp, ucmd);
+		if (ret)
+			return ret;
 	} else {
 		if (hr_dev->pci_dev->revision >= PCI_REVISION_ID_HIP09)
 			hr_qp->config = HNS_ROCE_EXSGE_FLAGS;
@@ -1051,6 +1109,8 @@ static int set_qp_param(struct hns_roce_dev *hr_dev, struct hns_roce_qp *hr_qp,
 			ibdev_err(ibdev,
 				  "failed to set kernel SQ size, ret = %d.\n",
 				  ret);
+
+		default_congest_type(hr_dev, hr_qp);
 	}
 
 	return ret;