RDMA/mlx5: Enable vport loopback when user context or QP mandate

A user can create a QP which can accept loopback traffic, but that's not
enough. We need to enable loopback on the vport as well. Currently vport
loopback is enabled only when more than 1 users are using the IB device,
update the logic to consider whatever a QP which supports loopback was
created, if so enable vport loopback even if there is only a single user.
Signed-off-by: Mark Bloch <markb@mellanox.com>
Reviewed-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

drivers/infiniband/hw/mlx5/main.c

@@ -1571,28 +1571,44 @@ static void deallocate_uars(struct mlx5_ib_dev *dev,
 			mlx5_cmd_free_uar(dev->mdev, bfregi->sys_pages[i]);
 }
 
-static int mlx5_ib_enable_lb(struct mlx5_ib_dev *dev)
+int mlx5_ib_enable_lb(struct mlx5_ib_dev *dev, bool td, bool qp)
 {
 	int err = 0;
 
 	mutex_lock(&dev->lb.mutex);
+	if (td)
 		dev->lb.user_td++;
+	if (qp)
+		dev->lb.qps++;
 
-	if (dev->lb.user_td == 2)
+	if (dev->lb.user_td == 2 ||
+	    dev->lb.qps == 1) {
+		if (!dev->lb.enabled) {
 			err = mlx5_nic_vport_update_local_lb(dev->mdev, true);
+			dev->lb.enabled = true;
+		}
+	}
 
 	mutex_unlock(&dev->lb.mutex);
 
 	return err;
 }
 
-static void mlx5_ib_disable_lb(struct mlx5_ib_dev *dev)
+void mlx5_ib_disable_lb(struct mlx5_ib_dev *dev, bool td, bool qp)
 {
 	mutex_lock(&dev->lb.mutex);
+	if (td)
 		dev->lb.user_td--;
+	if (qp)
+		dev->lb.qps--;
 
-	if (dev->lb.user_td < 2)
+	if (dev->lb.user_td == 1 &&
+	    dev->lb.qps == 0) {
+		if (dev->lb.enabled) {
 			mlx5_nic_vport_update_local_lb(dev->mdev, false);
+			dev->lb.enabled = false;
+		}
+	}
 
 	mutex_unlock(&dev->lb.mutex);
 }
@@ -1613,7 +1629,7 @@ static int mlx5_ib_alloc_transport_domain(struct mlx5_ib_dev *dev, u32 *tdn)
 	     !MLX5_CAP_GEN(dev->mdev, disable_local_lb_mc)))
 		return err;
 
-	return mlx5_ib_enable_lb(dev);
+	return mlx5_ib_enable_lb(dev, true, false);
 }
 
 static void mlx5_ib_dealloc_transport_domain(struct mlx5_ib_dev *dev, u32 tdn)
@@ -1628,7 +1644,7 @@ static void mlx5_ib_dealloc_transport_domain(struct mlx5_ib_dev *dev, u32 tdn)
 	     !MLX5_CAP_GEN(dev->mdev, disable_local_lb_mc)))
 		return;
 
-	mlx5_ib_disable_lb(dev);
+	mlx5_ib_disable_lb(dev, true, false);
 }
 
 static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,

drivers/infiniband/hw/mlx5/mlx5_ib.h

@@ -862,6 +862,8 @@ struct mlx5_ib_lb_state {
 	/* protect the user_td */
 	struct mutex		mutex;
 	u32			user_td;
+	int			qps;
+	bool			enabled;
 };
 
 struct mlx5_ib_dev {
@@ -1020,6 +1022,8 @@ int mlx5_ib_query_srq(struct ib_srq *ibsrq, struct ib_srq_attr *srq_attr);
 int mlx5_ib_destroy_srq(struct ib_srq *srq);
 int mlx5_ib_post_srq_recv(struct ib_srq *ibsrq, const struct ib_recv_wr *wr,
 			  const struct ib_recv_wr **bad_wr);
+int mlx5_ib_enable_lb(struct mlx5_ib_dev *dev, bool td, bool qp);
+void mlx5_ib_disable_lb(struct mlx5_ib_dev *dev, bool td, bool qp);
 struct ib_qp *mlx5_ib_create_qp(struct ib_pd *pd,
 				struct ib_qp_init_attr *init_attr,
 				struct ib_udata *udata);

drivers/infiniband/hw/mlx5/qp.c

@@ -1256,6 +1256,16 @@ static bool tunnel_offload_supported(struct mlx5_core_dev *dev)
 		 MLX5_CAP_ETH(dev, tunnel_stateless_geneve_rx));
 }
 
+static void destroy_raw_packet_qp_tir(struct mlx5_ib_dev *dev,
+				      struct mlx5_ib_rq *rq,
+				      u32 qp_flags_en)
+{
+	if (qp_flags_en & (MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_UC |
+			   MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_MC))
+		mlx5_ib_disable_lb(dev, false, true);
+	mlx5_core_destroy_tir(dev->mdev, rq->tirn);
+}
+
 static int create_raw_packet_qp_tir(struct mlx5_ib_dev *dev,
 				    struct mlx5_ib_rq *rq, u32 tdn,
 				    u32 *qp_flags_en)
@@ -1293,17 +1303,17 @@ static int create_raw_packet_qp_tir(struct mlx5_ib_dev *dev,
 
 	err = mlx5_core_create_tir(dev->mdev, in, inlen, &rq->tirn);
 
+	if (!err && MLX5_GET(tirc, tirc, self_lb_block)) {
+		err = mlx5_ib_enable_lb(dev, false, true);
+
+		if (err)
+			destroy_raw_packet_qp_tir(dev, rq, 0);
+	}
 	kvfree(in);
 
 	return err;
 }
 
-static void destroy_raw_packet_qp_tir(struct mlx5_ib_dev *dev,
-				      struct mlx5_ib_rq *rq)
-{
-	mlx5_core_destroy_tir(dev->mdev, rq->tirn);
-}
-
 static int create_raw_packet_qp(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 				u32 *in, size_t inlen,
 				struct ib_pd *pd)
@@ -1372,7 +1382,7 @@ static void destroy_raw_packet_qp(struct mlx5_ib_dev *dev,
 	struct mlx5_ib_rq *rq = &raw_packet_qp->rq;
 
 	if (qp->rq.wqe_cnt) {
-		destroy_raw_packet_qp_tir(dev, rq);
+		destroy_raw_packet_qp_tir(dev, rq, qp->flags_en);
 		destroy_raw_packet_qp_rq(dev, rq);
 	}
 
@@ -1396,6 +1406,9 @@ static void raw_packet_qp_copy_info(struct mlx5_ib_qp *qp,
 
 static void destroy_rss_raw_qp_tir(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp)
 {
+	if (qp->flags_en & (MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_UC |
+			    MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_MC))
+		mlx5_ib_disable_lb(dev, false, true);
 	mlx5_core_destroy_tir(dev->mdev, qp->rss_qp.tirn);
 }
 
@@ -1606,6 +1619,13 @@ static int create_rss_raw_qp_tir(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 create_tir:
 	err = mlx5_core_create_tir(dev->mdev, in, inlen, &qp->rss_qp.tirn);
 
+	if (!err && MLX5_GET(tirc, tirc, self_lb_block)) {
+		err = mlx5_ib_enable_lb(dev, false, true);
+
+		if (err)
+			mlx5_core_destroy_tir(dev->mdev, qp->rss_qp.tirn);
+	}
+
 	if (err)
 		goto err;