ice: Support VF queue rate limit and quanta size configuration

Add support to configure VF queue rate limit and quanta size.

For quanta size configuration, the quanta profiles are divided evenly
by PF numbers. For each port, the first quanta profile is reserved for
default. When VF is asked to set queue quanta size, PF will search for
an available profile, change the fields and assigned this profile to the
queue.

Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Wenjun Wu <wenjun1.wu@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Link: https://patch.msgid.link/fddefc2c1ec3ab32b241ce444af401da19e834dd.1728460186.git.pabeni@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 335 insertions, 0 deletions

diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
index 59f62306b9cb..96543f69f5de 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
@@ -495,6 +495,9 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg)
 	if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_USO)
 		vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_USO;
 
+	if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_QOS)
+		vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_QOS;
+
 	vfres->num_vsis = 1;
 	/* Tx and Rx queue are equal for VF */
 	vfres->num_queue_pairs = vsi->num_txq;
@@ -1035,6 +1038,191 @@ error_param:
 }
 
 /**
+ * ice_vc_get_qos_caps - Get current QoS caps from PF
+ * @vf: pointer to the VF info
+ *
+ * Get VF's QoS capabilities, such as TC number, arbiter and
+ * bandwidth from PF.
+ *
+ * Return: 0 on success or negative error value.
+ */
+static int ice_vc_get_qos_caps(struct ice_vf *vf)
+{
+	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
+	struct virtchnl_qos_cap_list *cap_list = NULL;
+	u8 tc_prio[ICE_MAX_TRAFFIC_CLASS] = { 0 };
+	struct virtchnl_qos_cap_elem *cfg = NULL;
+	struct ice_vsi_ctx *vsi_ctx;
+	struct ice_pf *pf = vf->pf;
+	struct ice_port_info *pi;
+	struct ice_vsi *vsi;
+	u8 numtc, tc;
+	u16 len = 0;
+	int ret, i;
+
+	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto err;
+	}
+
+	vsi = ice_get_vf_vsi(vf);
+	if (!vsi) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto err;
+	}
+
+	pi = pf->hw.port_info;
+	numtc = vsi->tc_cfg.numtc;
+
+	vsi_ctx = ice_get_vsi_ctx(pi->hw, vf->lan_vsi_idx);
+	if (!vsi_ctx) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto err;
+	}
+
+	len = struct_size(cap_list, cap, numtc);
+	cap_list = kzalloc(len, GFP_KERNEL);
+	if (!cap_list) {
+		v_ret = VIRTCHNL_STATUS_ERR_NO_MEMORY;
+		len = 0;
+		goto err;
+	}
+
+	cap_list->vsi_id = vsi->vsi_num;
+	cap_list->num_elem = numtc;
+
+	/* Store the UP2TC configuration from DCB to a user priority bitmap
+	 * of each TC. Each element of prio_of_tc represents one TC. Each
+	 * bitmap indicates the user priorities belong to this TC.
+	 */
+	for (i = 0; i < ICE_MAX_USER_PRIORITY; i++) {
+		tc = pi->qos_cfg.local_dcbx_cfg.etscfg.prio_table[i];
+		tc_prio[tc] |= BIT(i);
+	}
+
+	for (i = 0; i < numtc; i++) {
+		cfg = &cap_list->cap[i];
+		cfg->tc_num = i;
+		cfg->tc_prio = tc_prio[i];
+		cfg->arbiter = pi->qos_cfg.local_dcbx_cfg.etscfg.tsatable[i];
+		cfg->weight = VIRTCHNL_STRICT_WEIGHT;
+		cfg->type = VIRTCHNL_BW_SHAPER;
+		cfg->shaper.committed = vsi_ctx->sched.bw_t_info[i].cir_bw.bw;
+		cfg->shaper.peak = vsi_ctx->sched.bw_t_info[i].eir_bw.bw;
+	}
+
+err:
+	ret = ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_GET_QOS_CAPS, v_ret,
+				    (u8 *)cap_list, len);
+	kfree(cap_list);
+	return ret;
+}
+
+/**
+ * ice_vf_cfg_qs_bw - Configure per queue bandwidth
+ * @vf: pointer to the VF info
+ * @num_queues: number of queues to be configured
+ *
+ * Configure per queue bandwidth.
+ *
+ * Return: 0 on success or negative error value.
+ */
+static int ice_vf_cfg_qs_bw(struct ice_vf *vf, u16 num_queues)
+{
+	struct ice_hw *hw = &vf->pf->hw;
+	struct ice_vsi *vsi;
+	int ret;
+	u16 i;
+
+	vsi = ice_get_vf_vsi(vf);
+	if (!vsi)
+		return -EINVAL;
+
+	for (i = 0; i < num_queues; i++) {
+		u32 p_rate, min_rate;
+		u8 tc;
+
+		p_rate = vf->qs_bw[i].peak;
+		min_rate = vf->qs_bw[i].committed;
+		tc = vf->qs_bw[i].tc;
+		if (p_rate)
+			ret = ice_cfg_q_bw_lmt(hw->port_info, vsi->idx, tc,
+					       vf->qs_bw[i].queue_id,
+					       ICE_MAX_BW, p_rate);
+		else
+			ret = ice_cfg_q_bw_dflt_lmt(hw->port_info, vsi->idx, tc,
+						    vf->qs_bw[i].queue_id,
+						    ICE_MAX_BW);
+		if (ret)
+			return ret;
+
+		if (min_rate)
+			ret = ice_cfg_q_bw_lmt(hw->port_info, vsi->idx, tc,
+					       vf->qs_bw[i].queue_id,
+					       ICE_MIN_BW, min_rate);
+		else
+			ret = ice_cfg_q_bw_dflt_lmt(hw->port_info, vsi->idx, tc,
+						    vf->qs_bw[i].queue_id,
+						    ICE_MIN_BW);
+
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+/**
+ * ice_vf_cfg_q_quanta_profile - Configure quanta profile
+ * @vf: pointer to the VF info
+ * @quanta_prof_idx: pointer to the quanta profile index
+ * @quanta_size: quanta size to be set
+ *
+ * This function chooses available quanta profile and configures the register.
+ * The quanta profile is evenly divided by the number of device ports, and then
+ * available to the specific PF and VFs. The first profile for each PF is a
+ * reserved default profile. Only quanta size of the rest unused profile can be
+ * modified.
+ *
+ * Return: 0 on success or negative error value.
+ */
+static int ice_vf_cfg_q_quanta_profile(struct ice_vf *vf, u16 quanta_size,
+				       u16 *quanta_prof_idx)
+{
+	const u16 n_desc = calc_quanta_desc(quanta_size);
+	struct ice_hw *hw = &vf->pf->hw;
+	const u16 n_cmd = 2 * n_desc;
+	struct ice_pf *pf = vf->pf;
+	u16 per_pf, begin_id;
+	u8 n_used;
+	u32 reg;
+
+	begin_id = (GLCOMM_QUANTA_PROF_MAX_INDEX + 1) / hw->dev_caps.num_funcs *
+		   hw->logical_pf_id;
+
+	if (quanta_size == ICE_DFLT_QUANTA) {
+		*quanta_prof_idx = begin_id;
+	} else {
+		per_pf = (GLCOMM_QUANTA_PROF_MAX_INDEX + 1) /
+			 hw->dev_caps.num_funcs;
+		n_used = pf->num_quanta_prof_used;
+		if (n_used < per_pf) {
+			*quanta_prof_idx = begin_id + 1 + n_used;
+			pf->num_quanta_prof_used++;
+		} else {
+			return -EINVAL;
+		}
+	}
+
+	reg = FIELD_PREP(GLCOMM_QUANTA_PROF_QUANTA_SIZE_M, quanta_size) |
+	      FIELD_PREP(GLCOMM_QUANTA_PROF_MAX_CMD_M, n_cmd) |
+	      FIELD_PREP(GLCOMM_QUANTA_PROF_MAX_DESC_M, n_desc);
+	wr32(hw, GLCOMM_QUANTA_PROF(*quanta_prof_idx), reg);
+
+	return 0;
+}
+
+/**
  * ice_vc_cfg_promiscuous_mode_msg
  * @vf: pointer to the VF info
  * @msg: pointer to the msg buffer
@@ -1636,6 +1824,141 @@ error_param:
 }
 
 /**
+ * ice_vc_cfg_q_bw - Configure per queue bandwidth
+ * @vf: pointer to the VF info
+ * @msg: pointer to the msg buffer which holds the command descriptor
+ *
+ * Configure VF queues bandwidth.
+ *
+ * Return: 0 on success or negative error value.
+ */
+static int ice_vc_cfg_q_bw(struct ice_vf *vf, u8 *msg)
+{
+	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
+	struct virtchnl_queues_bw_cfg *qbw =
+		(struct virtchnl_queues_bw_cfg *)msg;
+	struct ice_vsi *vsi;
+	u16 i;
+
+	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states) ||
+	    !ice_vc_isvalid_vsi_id(vf, qbw->vsi_id)) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto err;
+	}
+
+	vsi = ice_get_vf_vsi(vf);
+	if (!vsi) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto err;
+	}
+
+	if (qbw->num_queues > ICE_MAX_RSS_QS_PER_VF ||
+	    qbw->num_queues > min_t(u16, vsi->alloc_txq, vsi->alloc_rxq)) {
+		dev_err(ice_pf_to_dev(vf->pf), "VF-%d trying to configure more than allocated number of queues: %d\n",
+			vf->vf_id, min_t(u16, vsi->alloc_txq, vsi->alloc_rxq));
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto err;
+	}
+
+	for (i = 0; i < qbw->num_queues; i++) {
+		if (qbw->cfg[i].shaper.peak != 0 && vf->max_tx_rate != 0 &&
+		    qbw->cfg[i].shaper.peak > vf->max_tx_rate)
+			dev_warn(ice_pf_to_dev(vf->pf), "The maximum queue %d rate limit configuration may not take effect because the maximum TX rate for VF-%d is %d\n",
+				 qbw->cfg[i].queue_id, vf->vf_id,
+				 vf->max_tx_rate);
+		if (qbw->cfg[i].shaper.committed != 0 && vf->min_tx_rate != 0 &&
+		    qbw->cfg[i].shaper.committed < vf->min_tx_rate)
+			dev_warn(ice_pf_to_dev(vf->pf), "The minimum queue %d rate limit configuration may not take effect because the minimum TX rate for VF-%d is %d\n",
+				 qbw->cfg[i].queue_id, vf->vf_id,
+				 vf->max_tx_rate);
+	}
+
+	for (i = 0; i < qbw->num_queues; i++) {
+		vf->qs_bw[i].queue_id = qbw->cfg[i].queue_id;
+		vf->qs_bw[i].peak = qbw->cfg[i].shaper.peak;
+		vf->qs_bw[i].committed = qbw->cfg[i].shaper.committed;
+		vf->qs_bw[i].tc = qbw->cfg[i].tc;
+	}
+
+	if (ice_vf_cfg_qs_bw(vf, qbw->num_queues))
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+
+err:
+	/* send the response to the VF */
+	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_QUEUE_BW,
+				    v_ret, NULL, 0);
+}
+
+/**
+ * ice_vc_cfg_q_quanta - Configure per queue quanta
+ * @vf: pointer to the VF info
+ * @msg: pointer to the msg buffer which holds the command descriptor
+ *
+ * Configure VF queues quanta.
+ *
+ * Return: 0 on success or negative error value.
+ */
+static int ice_vc_cfg_q_quanta(struct ice_vf *vf, u8 *msg)
+{
+	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
+	u16 quanta_prof_id, quanta_size, start_qid, end_qid, i;
+	struct virtchnl_quanta_cfg *qquanta =
+		(struct virtchnl_quanta_cfg *)msg;
+	struct ice_vsi *vsi;
+	int ret;
+
+	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto err;
+	}
+
+	vsi = ice_get_vf_vsi(vf);
+	if (!vsi) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto err;
+	}
+
+	end_qid = qquanta->queue_select.start_queue_id +
+		  qquanta->queue_select.num_queues;
+	if (end_qid > ICE_MAX_RSS_QS_PER_VF ||
+	    end_qid > min_t(u16, vsi->alloc_txq, vsi->alloc_rxq)) {
+		dev_err(ice_pf_to_dev(vf->pf), "VF-%d trying to configure more than allocated number of queues: %d\n",
+			vf->vf_id, min_t(u16, vsi->alloc_txq, vsi->alloc_rxq));
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto err;
+	}
+
+	quanta_size = qquanta->quanta_size;
+	if (quanta_size > ICE_MAX_QUANTA_SIZE ||
+	    quanta_size < ICE_MIN_QUANTA_SIZE) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto err;
+	}
+
+	if (quanta_size % 64) {
+		dev_err(ice_pf_to_dev(vf->pf), "quanta size should be the product of 64\n");
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto err;
+	}
+
+	ret = ice_vf_cfg_q_quanta_profile(vf, quanta_size,
+					  &quanta_prof_id);
+	if (ret) {
+		v_ret = VIRTCHNL_STATUS_ERR_NOT_SUPPORTED;
+		goto err;
+	}
+
+	start_qid = qquanta->queue_select.start_queue_id;
+	for (i = start_qid; i < end_qid; i++)
+		vsi->tx_rings[i]->quanta_prof_id = quanta_prof_id;
+
+err:
+	/* send the response to the VF */
+	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_QUANTA,
+				     v_ret, NULL, 0);
+}
+
+/**
  * ice_vc_cfg_qs_msg
  * @vf: pointer to the VF info
  * @msg: pointer to the msg buffer
@@ -3821,6 +4144,9 @@ static const struct ice_virtchnl_ops ice_virtchnl_dflt_ops = {
 	.dis_vlan_stripping_v2_msg = ice_vc_dis_vlan_stripping_v2_msg,
 	.ena_vlan_insertion_v2_msg = ice_vc_ena_vlan_insertion_v2_msg,
 	.dis_vlan_insertion_v2_msg = ice_vc_dis_vlan_insertion_v2_msg,
+	.get_qos_caps = ice_vc_get_qos_caps,
+	.cfg_q_bw = ice_vc_cfg_q_bw,
+	.cfg_q_quanta = ice_vc_cfg_q_quanta,
 };
 
 /**
@@ -4177,6 +4503,15 @@ error_handler:
 	case VIRTCHNL_OP_DISABLE_VLAN_INSERTION_V2:
 		err = ops->dis_vlan_insertion_v2_msg(vf, msg);
 		break;
+	case VIRTCHNL_OP_GET_QOS_CAPS:
+		err = ops->get_qos_caps(vf);
+		break;
+	case VIRTCHNL_OP_CONFIG_QUEUE_BW:
+		err = ops->cfg_q_bw(vf, msg);
+		break;
+	case VIRTCHNL_OP_CONFIG_QUANTA:
+		err = ops->cfg_q_quanta(vf, msg);
+		break;
 	case VIRTCHNL_OP_UNKNOWN:
 	default:
 		dev_err(dev, "Unsupported opcode %d from VF %d\n", v_opcode,