IB/mlx5: Add RSS QP support

Add support for Raw Ethernet RX HASH QP. Currently, creation and
destruction of such a QP are supported. This QP is implemented as
a simple TIR object which points to the receive RQ indirection table.
The given hashing configuration is used to configure the TIR and by
that it chooses the right RQ from the RQ indirection table.

Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Matan Barak <matanb@mellanox.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Doug Ledford <dledford@redhat.com>

drivers/infiniband/hw/mlx5/mlx5_ib.h

@@ -295,6 +295,10 @@ struct mlx5_ib_qp_trans {
 	u8			resp_depth;
 };
 
+struct mlx5_ib_rss_qp {
+	u32	tirn;
+};
+
 struct mlx5_ib_rq {
 	struct mlx5_ib_qp_base base;
 	struct mlx5_ib_wq	*rq;
@@ -323,6 +327,7 @@ struct mlx5_ib_qp {
 	union {
 		struct mlx5_ib_qp_trans trans_qp;
 		struct mlx5_ib_raw_packet_qp raw_packet_qp;
+		struct mlx5_ib_rss_qp rss_qp;
 	};
 	struct mlx5_buf		buf;
 

drivers/infiniband/hw/mlx5/qp.c

@@ -1266,6 +1266,187 @@ static void raw_packet_qp_copy_info(struct mlx5_ib_qp *qp,
 	rq->doorbell = &qp->db;
 }
 
+static void destroy_rss_raw_qp_tir(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp)
+{
+	mlx5_core_destroy_tir(dev->mdev, qp->rss_qp.tirn);
+}
+
+static int create_rss_raw_qp_tir(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
+				 struct ib_pd *pd,
+				 struct ib_qp_init_attr *init_attr,
+				 struct ib_udata *udata)
+{
+	struct ib_uobject *uobj = pd->uobject;
+	struct ib_ucontext *ucontext = uobj->context;
+	struct mlx5_ib_ucontext *mucontext = to_mucontext(ucontext);
+	struct mlx5_ib_create_qp_resp resp = {};
+	int inlen;
+	int err;
+	u32 *in;
+	void *tirc;
+	void *hfso;
+	u32 selected_fields = 0;
+	size_t min_resp_len;
+	u32 tdn = mucontext->tdn;
+	struct mlx5_ib_create_qp_rss ucmd = {};
+	size_t required_cmd_sz;
+
+	if (init_attr->qp_type != IB_QPT_RAW_PACKET)
+		return -EOPNOTSUPP;
+
+	if (init_attr->create_flags || init_attr->send_cq)
+		return -EINVAL;
+
+	min_resp_len = offsetof(typeof(resp), uuar_index) + sizeof(resp.uuar_index);
+	if (udata->outlen < min_resp_len)
+		return -EINVAL;
+
+	required_cmd_sz = offsetof(typeof(ucmd), reserved1) + sizeof(ucmd.reserved1);
+	if (udata->inlen < required_cmd_sz) {
+		mlx5_ib_dbg(dev, "invalid inlen\n");
+		return -EINVAL;
+	}
+
+	if (udata->inlen > sizeof(ucmd) &&
+	    !ib_is_udata_cleared(udata, sizeof(ucmd),
+				 udata->inlen - sizeof(ucmd))) {
+		mlx5_ib_dbg(dev, "inlen is not supported\n");
+		return -EOPNOTSUPP;
+	}
+
+	if (ib_copy_from_udata(&ucmd, udata, min(sizeof(ucmd), udata->inlen))) {
+		mlx5_ib_dbg(dev, "copy failed\n");
+		return -EFAULT;
+	}
+
+	if (ucmd.comp_mask) {
+		mlx5_ib_dbg(dev, "invalid comp mask\n");
+		return -EOPNOTSUPP;
+	}
+
+	if (memchr_inv(ucmd.reserved, 0, sizeof(ucmd.reserved)) || ucmd.reserved1) {
+		mlx5_ib_dbg(dev, "invalid reserved\n");
+		return -EOPNOTSUPP;
+	}
+
+	err = ib_copy_to_udata(udata, &resp, min_resp_len);
+	if (err) {
+		mlx5_ib_dbg(dev, "copy failed\n");
+		return -EINVAL;
+	}
+
+	inlen = MLX5_ST_SZ_BYTES(create_tir_in);
+	in = mlx5_vzalloc(inlen);
+	if (!in)
+		return -ENOMEM;
+
+	tirc = MLX5_ADDR_OF(create_tir_in, in, ctx);
+	MLX5_SET(tirc, tirc, disp_type,
+		 MLX5_TIRC_DISP_TYPE_INDIRECT);
+	MLX5_SET(tirc, tirc, indirect_table,
+		 init_attr->rwq_ind_tbl->ind_tbl_num);
+	MLX5_SET(tirc, tirc, transport_domain, tdn);
+
+	hfso = MLX5_ADDR_OF(tirc, tirc, rx_hash_field_selector_outer);
+	switch (ucmd.rx_hash_function) {
+	case MLX5_RX_HASH_FUNC_TOEPLITZ:
+	{
+		void *rss_key = MLX5_ADDR_OF(tirc, tirc, rx_hash_toeplitz_key);
+		size_t len = MLX5_FLD_SZ_BYTES(tirc, rx_hash_toeplitz_key);
+
+		if (len != ucmd.rx_key_len) {
+			err = -EINVAL;
+			goto err;
+		}
+
+		MLX5_SET(tirc, tirc, rx_hash_fn, MLX5_RX_HASH_FN_TOEPLITZ);
+		MLX5_SET(tirc, tirc, rx_hash_symmetric, 1);
+		memcpy(rss_key, ucmd.rx_hash_key, len);
+		break;
+	}
+	default:
+		err = -EOPNOTSUPP;
+		goto err;
+	}
+
+	if (!ucmd.rx_hash_fields_mask) {
+		/* special case when this TIR serves as steering entry without hashing */
+		if (!init_attr->rwq_ind_tbl->log_ind_tbl_size)
+			goto create_tir;
+		err = -EINVAL;
+		goto err;
+	}
+
+	if (((ucmd.rx_hash_fields_mask & MLX5_RX_HASH_SRC_IPV4) ||
+	     (ucmd.rx_hash_fields_mask & MLX5_RX_HASH_DST_IPV4)) &&
+	     ((ucmd.rx_hash_fields_mask & MLX5_RX_HASH_SRC_IPV6) ||
+	     (ucmd.rx_hash_fields_mask & MLX5_RX_HASH_DST_IPV6))) {
+		err = -EINVAL;
+		goto err;
+	}
+
+	/* If none of IPV4 & IPV6 SRC/DST was set - this bit field is ignored */
+	if ((ucmd.rx_hash_fields_mask & MLX5_RX_HASH_SRC_IPV4) ||
+	    (ucmd.rx_hash_fields_mask & MLX5_RX_HASH_DST_IPV4))
+		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
+			 MLX5_L3_PROT_TYPE_IPV4);
+	else if ((ucmd.rx_hash_fields_mask & MLX5_RX_HASH_SRC_IPV6) ||
+		 (ucmd.rx_hash_fields_mask & MLX5_RX_HASH_DST_IPV6))
+		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
+			 MLX5_L3_PROT_TYPE_IPV6);
+
+	if (((ucmd.rx_hash_fields_mask & MLX5_RX_HASH_SRC_PORT_TCP) ||
+	     (ucmd.rx_hash_fields_mask & MLX5_RX_HASH_DST_PORT_TCP)) &&
+	     ((ucmd.rx_hash_fields_mask & MLX5_RX_HASH_SRC_PORT_UDP) ||
+	     (ucmd.rx_hash_fields_mask & MLX5_RX_HASH_DST_PORT_UDP))) {
+		err = -EINVAL;
+		goto err;
+	}
+
+	/* If none of TCP & UDP SRC/DST was set - this bit field is ignored */
+	if ((ucmd.rx_hash_fields_mask & MLX5_RX_HASH_SRC_PORT_TCP) ||
+	    (ucmd.rx_hash_fields_mask & MLX5_RX_HASH_DST_PORT_TCP))
+		MLX5_SET(rx_hash_field_select, hfso, l4_prot_type,
+			 MLX5_L4_PROT_TYPE_TCP);
+	else if ((ucmd.rx_hash_fields_mask & MLX5_RX_HASH_SRC_PORT_UDP) ||
+		 (ucmd.rx_hash_fields_mask & MLX5_RX_HASH_DST_PORT_UDP))
+		MLX5_SET(rx_hash_field_select, hfso, l4_prot_type,
+			 MLX5_L4_PROT_TYPE_UDP);
+
+	if ((ucmd.rx_hash_fields_mask & MLX5_RX_HASH_SRC_IPV4) ||
+	    (ucmd.rx_hash_fields_mask & MLX5_RX_HASH_SRC_IPV6))
+		selected_fields |= MLX5_HASH_FIELD_SEL_SRC_IP;
+
+	if ((ucmd.rx_hash_fields_mask & MLX5_RX_HASH_DST_IPV4) ||
+	    (ucmd.rx_hash_fields_mask & MLX5_RX_HASH_DST_IPV6))
+		selected_fields |= MLX5_HASH_FIELD_SEL_DST_IP;
+
+	if ((ucmd.rx_hash_fields_mask & MLX5_RX_HASH_SRC_PORT_TCP) ||
+	    (ucmd.rx_hash_fields_mask & MLX5_RX_HASH_SRC_PORT_UDP))
+		selected_fields |= MLX5_HASH_FIELD_SEL_L4_SPORT;
+
+	if ((ucmd.rx_hash_fields_mask & MLX5_RX_HASH_DST_PORT_TCP) ||
+	    (ucmd.rx_hash_fields_mask & MLX5_RX_HASH_DST_PORT_UDP))
+		selected_fields |= MLX5_HASH_FIELD_SEL_L4_DPORT;
+
+	MLX5_SET(rx_hash_field_select, hfso, selected_fields, selected_fields);
+
+create_tir:
+	err = mlx5_core_create_tir(dev->mdev, in, inlen, &qp->rss_qp.tirn);
+
+	if (err)
+		goto err;
+
+	kvfree(in);
+	/* qpn is reserved for that QP */
+	qp->trans_qp.base.mqp.qpn = 0;
+	return 0;
+
+err:
+	kvfree(in);
+	return err;
+}
+
 static int create_qp_common(struct mlx5_ib_dev *dev, struct ib_pd *pd,
 			    struct ib_qp_init_attr *init_attr,
 			    struct ib_udata *udata, struct mlx5_ib_qp *qp)
@@ -1292,6 +1473,14 @@ static int create_qp_common(struct mlx5_ib_dev *dev, struct ib_pd *pd,
 	spin_lock_init(&qp->sq.lock);
 	spin_lock_init(&qp->rq.lock);
 
+	if (init_attr->rwq_ind_tbl) {
+		if (!udata)
+			return -ENOSYS;
+
+		err = create_rss_raw_qp_tir(dev, qp, pd, init_attr, udata);
+		return err;
+	}
+
 	if (init_attr->create_flags & IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK) {
 		if (!MLX5_CAP_GEN(mdev, block_lb_mc)) {
 			mlx5_ib_dbg(dev, "block multicast loopback isn't supported\n");
@@ -1644,6 +1833,11 @@ static void destroy_qp_common(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp)
 	struct mlx5_modify_qp_mbox_in *in;
 	int err;
 
+	if (qp->ibqp.rwq_ind_tbl) {
+		destroy_rss_raw_qp_tir(dev, qp);
+		return;
+	}
+
 	base = qp->ibqp.qp_type == IB_QPT_RAW_PACKET ?
 	       &qp->raw_packet_qp.rq.base :
 	       &qp->trans_qp.base;
@@ -2504,6 +2698,9 @@ int mlx5_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 	int port;
 	enum rdma_link_layer ll = IB_LINK_LAYER_UNSPECIFIED;
 
+	if (ibqp->rwq_ind_tbl)
+		return -ENOSYS;
+
 	if (unlikely(ibqp->qp_type == IB_QPT_GSI))
 		return mlx5_ib_gsi_modify_qp(ibqp, attr, attr_mask);
 
@@ -4119,6 +4316,9 @@ int mlx5_ib_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr,
 	int err = 0;
 	u8 raw_packet_qp_state;
 
+	if (ibqp->rwq_ind_tbl)
+		return -ENOSYS;
+
 	if (unlikely(ibqp->qp_type == IB_QPT_GSI))
 		return mlx5_ib_gsi_query_qp(ibqp, qp_attr, qp_attr_mask,
 					    qp_init_attr);

drivers/infiniband/hw/mlx5/user.h

@@ -152,6 +152,40 @@ struct mlx5_ib_create_qp {
 	__u64	sq_buf_addr;
 };
 
+/* RX Hash function flags */
+enum mlx5_rx_hash_function_flags {
+	MLX5_RX_HASH_FUNC_TOEPLITZ	= 1 << 0,
+};
+
+/*
+ * RX Hash flags, these flags allows to set which incoming packet's field should
+ * participates in RX Hash. Each flag represent certain packet's field,
+ * when the flag is set the field that is represented by the flag will
+ * participate in RX Hash calculation.
+ * Note: *IPV4 and *IPV6 flags can't be enabled together on the same QP
+ * and *TCP and *UDP flags can't be enabled together on the same QP.
+*/
+enum mlx5_rx_hash_fields {
+	MLX5_RX_HASH_SRC_IPV4	= 1 << 0,
+	MLX5_RX_HASH_DST_IPV4	= 1 << 1,
+	MLX5_RX_HASH_SRC_IPV6	= 1 << 2,
+	MLX5_RX_HASH_DST_IPV6	= 1 << 3,
+	MLX5_RX_HASH_SRC_PORT_TCP	= 1 << 4,
+	MLX5_RX_HASH_DST_PORT_TCP	= 1 << 5,
+	MLX5_RX_HASH_SRC_PORT_UDP	= 1 << 6,
+	MLX5_RX_HASH_DST_PORT_UDP	= 1 << 7
+};
+
+struct mlx5_ib_create_qp_rss {
+	__u64 rx_hash_fields_mask; /* enum mlx5_rx_hash_fields */
+	__u8 rx_hash_function; /* enum mlx5_rx_hash_function_flags */
+	__u8 rx_key_len; /* valid only for Toeplitz */
+	__u8 reserved[6];
+	__u8 rx_hash_key[128]; /* valid only for Toeplitz */
+	__u32   comp_mask;
+	__u32   reserved1;
+};
+
 struct mlx5_ib_create_qp_resp {
 	__u32	uuar_index;
 };