[PATCH for-next V2 00/15][PULL request] Mellanox mlx5 core driver updates 2016-10-25

@@ -1422,6 +1422,7 @@ static const struct pci_device_id mlx5_core_pci_table[] = {
 	{ PCI_VDEVICE(MELLANOX, 0x1017) },			/* ConnectX-5, PCIe 3.0 */
 	{ PCI_VDEVICE(MELLANOX, 0x1018), MLX5_PCI_DEV_IS_VF},	/* ConnectX-5 VF */
 	{ PCI_VDEVICE(MELLANOX, 0x1019) },			/* ConnectX-5, PCIe 4.0 */
+	{ PCI_VDEVICE(MELLANOX, 0x101a), MLX5_PCI_DEV_IS_VF},	/* ConnectX-5, PCIe 4.0 VF */
 	{ 0, }
 };
 

@@ -2844,7 +2844,7 @@ struct mlx5_ifc_xrqc_bits {
 
 	struct mlx5_ifc_tag_matching_topology_context_bits tag_matching_topology_context;
 
-	u8         reserved_at_180[0x200];
+	u8         reserved_at_180[0x880];
 
 	struct mlx5_ifc_wq_bits wq;
 };

@@ -2945,6 +2945,20 @@ static int mlx5e_set_vf_trust(struct net_device *dev, int vf, bool setting)
 
 	return mlx5_eswitch_set_vport_trust(mdev->priv.eswitch, vf + 1, setting);
 }
+
+static int mlx5e_set_vf_rate(struct net_device *dev, int vf, int min_tx_rate,
+			     int max_tx_rate)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+	struct mlx5_core_dev *mdev = priv->mdev;
+
+	if (min_tx_rate)
+		return -EOPNOTSUPP;
+
+	return mlx5_eswitch_set_vport_rate(mdev->priv.eswitch, vf + 1,
+					   max_tx_rate);
+}
+
 static int mlx5_vport_link2ifla(u8 esw_link)
 {
 	switch (esw_link) {

@@ -3252,6 +3266,7 @@ static const struct net_device_ops mlx5e_netdev_ops_sriov = {
 	.ndo_set_vf_vlan         = mlx5e_set_vf_vlan,
 	.ndo_set_vf_spoofchk     = mlx5e_set_vf_spoofchk,
 	.ndo_set_vf_trust        = mlx5e_set_vf_trust,
+	.ndo_set_vf_rate         = mlx5e_set_vf_rate,
 	.ndo_get_vf_config       = mlx5e_get_vf_config,
 	.ndo_set_vf_link_state   = mlx5e_set_vf_link_state,
 	.ndo_get_vf_stats        = mlx5e_get_vf_stats,

@@ -1451,6 +1451,47 @@ static void esw_vport_disable_qos(struct mlx5_eswitch *esw, int vport_num)
 	vport->qos.enabled = false;
 }
 
+static int esw_vport_qos_config(struct mlx5_eswitch *esw, int vport_num,
+				u32 max_rate)
+{
+	u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {0};
+	struct mlx5_vport *vport = &esw->vports[vport_num];
+	struct mlx5_core_dev *dev = esw->dev;
+	void *vport_elem;
+	u32 bitmask = 0;
+	int err = 0;
+
+	if (!MLX5_CAP_GEN(dev, qos) || !MLX5_CAP_QOS(dev, esw_scheduling))
+		return -EOPNOTSUPP;
+
+	if (!vport->qos.enabled)
+		return -EIO;
+
+	MLX5_SET(scheduling_context, &sched_ctx, element_type,
+		 SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT);
+	vport_elem = MLX5_ADDR_OF(scheduling_context, &sched_ctx,
+				  element_attributes);
+	MLX5_SET(vport_element, vport_elem, vport_number, vport_num);
+	MLX5_SET(scheduling_context, &sched_ctx, parent_element_id,
+		 esw->qos.root_tsar_id);
+	MLX5_SET(scheduling_context, &sched_ctx, max_average_bw,
+		 max_rate);
+	bitmask |= MODIFY_SCHEDULING_ELEMENT_IN_MODIFY_BITMASK_MAX_AVERAGE_BW;
+
+	err = mlx5_modify_scheduling_element_cmd(dev,
+						 SCHEDULING_HIERARCHY_E_SWITCH,
+						 &sched_ctx,
+						 vport->qos.esw_tsar_ix,
+						 bitmask);
+	if (err) {
+		esw_warn(esw->dev, "E-Switch modify TSAR vport element failed (vport=%d,err=%d)\n",
+			 vport_num, err);
+		return err;
+	}
+
+	return 0;
+}
+
 static void node_guid_gen_from_mac(u64 *node_guid, u8 mac[ETH_ALEN])
 {
 	((u8 *)node_guid)[7] = mac[0];

@@ -1888,6 +1929,7 @@ int mlx5_eswitch_get_vport_config(struct mlx5_eswitch *esw,
 	ivi->qos = evport->info.qos;
 	ivi->spoofchk = evport->info.spoofchk;
 	ivi->trusted = evport->info.trusted;
+	ivi->max_tx_rate = evport->info.max_rate;
 	mutex_unlock(&esw->state_lock);
 
 	return 0;

@@ -1981,6 +2023,27 @@ int mlx5_eswitch_set_vport_trust(struct mlx5_eswitch *esw,
 	return 0;
 }
 
+int mlx5_eswitch_set_vport_rate(struct mlx5_eswitch *esw,
+				int vport, u32 max_rate)
+{
+	struct mlx5_vport *evport;
+	int err = 0;
+
+	if (!ESW_ALLOWED(esw))
+		return -EPERM;
+	if (!LEGAL_VPORT(esw, vport))
+		return -EINVAL;
+
+	mutex_lock(&esw->state_lock);
+	evport = &esw->vports[vport];
+	err = esw_vport_qos_config(esw, vport, max_rate);
+	if (!err)
+		evport->info.max_rate = max_rate;
+
+	mutex_unlock(&esw->state_lock);
+	return err;
+}
+
 int mlx5_eswitch_get_vport_stats(struct mlx5_eswitch *esw,
 				 int vport,
 				 struct ifla_vf_stats *vf_stats)

@@ -246,6 +246,8 @@ int mlx5_eswitch_set_vport_spoofchk(struct mlx5_eswitch *esw,
 				    int vport, bool spoofchk);
 int mlx5_eswitch_set_vport_trust(struct mlx5_eswitch *esw,
 				 int vport_num, bool setting);
+int mlx5_eswitch_set_vport_rate(struct mlx5_eswitch *esw,
+				int vport, u32 max_rate);
 int mlx5_eswitch_get_vport_config(struct mlx5_eswitch *esw,
 				  int vport, struct ifla_vf_info *ivi);
 int mlx5_eswitch_get_vport_stats(struct mlx5_eswitch *esw,

@@ -374,6 +374,7 @@ static void del_rule(struct fs_node *node)
 	struct mlx5_core_dev *dev = get_dev(node);
 	int match_len = MLX5_ST_SZ_BYTES(fte_match_param);
 	int err;
+	bool update_fte = false;
 
 	match_value = mlx5_vzalloc(match_len);
 	if (!match_value) {

@@ -392,13 +393,23 @@ static void del_rule(struct fs_node *node)
 		list_del(&rule->next_ft);
 		mutex_unlock(&rule->dest_attr.ft->lock);
 	}
+
+	if (rule->dest_attr.type == MLX5_FLOW_DESTINATION_TYPE_COUNTER  &&
+	    --fte->dests_size) {
+		modify_mask = BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_ACTION);
+		fte->action &= ~MLX5_FLOW_CONTEXT_ACTION_COUNT;
+		update_fte = true;
+		goto out;
+	}
+
 	if ((fte->action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) &&
 	    --fte->dests_size) {
 		modify_mask = BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_DESTINATION_LIST),
-		err = mlx5_cmd_update_fte(dev, ft,
-					  fg->id,
-					  modify_mask,
-					  fte);
+		update_fte = true;
+	}
+out:
+	if (update_fte && fte->dests_size) {
+		err = mlx5_cmd_update_fte(dev, ft, fg->id, modify_mask, fte);
 		if (err)
 			mlx5_core_warn(dev,
 				       "%s can't del rule fg id=%d fte_index=%d\n",

@@ -1287,8 +1298,9 @@ static bool counter_is_valid(struct mlx5_fc *counter, u32 action)
 	if (!counter)
 		return false;
 
-	/* Hardware support counter for a drop action only */
-	return action == (MLX5_FLOW_CONTEXT_ACTION_DROP | MLX5_FLOW_CONTEXT_ACTION_COUNT);
+	return (action & (MLX5_FLOW_CONTEXT_ACTION_DROP |
+			  MLX5_FLOW_CONTEXT_ACTION_FWD_DEST)) &&
+		(action & MLX5_FLOW_CONTEXT_ACTION_COUNT);
 }
 
 static bool dest_is_valid(struct mlx5_flow_destination *dest,

@@ -1351,6 +1351,106 @@ static int esw_vport_egress_config(struct mlx5_eswitch *esw,
 	return err;
 }
 
+/* Vport QoS management */
+static int esw_create_tsar(struct mlx5_eswitch *esw)
+{
+	u32 tsar_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {0};
+	struct mlx5_core_dev *dev = esw->dev;
+	int err;
+
+	if (!MLX5_CAP_GEN(dev, qos) || !MLX5_CAP_QOS(dev, esw_scheduling))
+		return 0;
+
+	if (esw->qos.enabled)
+		return -EEXIST;
+
+	err = mlx5_create_scheduling_element_cmd(dev,
+						 SCHEDULING_HIERARCHY_E_SWITCH,
+						 &tsar_ctx,
+						 &esw->qos.root_tsar_id);
+	if (err) {
+		esw_warn(esw->dev, "E-Switch create TSAR failed (%d)\n", err);
+		return err;
+	}
+
+	esw->qos.enabled = true;
+	return 0;
+}
+
+static void esw_destroy_tsar(struct mlx5_eswitch *esw)
+{
+	int err;
+
+	if (!esw->qos.enabled)
+		return;
+
+	err = mlx5_destroy_scheduling_element_cmd(esw->dev,
+						  SCHEDULING_HIERARCHY_E_SWITCH,
+						  esw->qos.root_tsar_id);
+	if (err)
+		esw_warn(esw->dev, "E-Switch destroy TSAR failed (%d)\n", err);
+
+	esw->qos.enabled = false;
+}
+
+static int esw_vport_enable_qos(struct mlx5_eswitch *esw, int vport_num,
+				u32 initial_max_rate)
+{
+	u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {0};
+	struct mlx5_vport *vport = &esw->vports[vport_num];
+	struct mlx5_core_dev *dev = esw->dev;
+	void *vport_elem;
+	int err = 0;
+
+	if (!esw->qos.enabled || !MLX5_CAP_GEN(dev, qos) ||
+	    !MLX5_CAP_QOS(dev, esw_scheduling))
+		return 0;
+
+	if (vport->qos.enabled)
+		return -EEXIST;
+
+	MLX5_SET(scheduling_context, &sched_ctx, element_type,
+		 SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT);
+	vport_elem = MLX5_ADDR_OF(scheduling_context, &sched_ctx,
+				  element_attributes);
+	MLX5_SET(vport_element, vport_elem, vport_number, vport_num);
+	MLX5_SET(scheduling_context, &sched_ctx, parent_element_id,
+		 esw->qos.root_tsar_id);
+	MLX5_SET(scheduling_context, &sched_ctx, max_average_bw,
+		 initial_max_rate);
+
+	err = mlx5_create_scheduling_element_cmd(dev,
+						 SCHEDULING_HIERARCHY_E_SWITCH,
+						 &sched_ctx,
+						 &vport->qos.esw_tsar_ix);
+	if (err) {
+		esw_warn(esw->dev, "E-Switch create TSAR vport element failed (vport=%d,err=%d)\n",
+			 vport_num, err);
+		return err;
+	}
+
+	vport->qos.enabled = true;
+	return 0;
+}
+
+static void esw_vport_disable_qos(struct mlx5_eswitch *esw, int vport_num)
+{
+	struct mlx5_vport *vport = &esw->vports[vport_num];
+	int err = 0;
+
+	if (!vport->qos.enabled)
+		return;
+
+	err = mlx5_destroy_scheduling_element_cmd(esw->dev,
+						  SCHEDULING_HIERARCHY_E_SWITCH,
+						  vport->qos.esw_tsar_ix);
+	if (err)
+		esw_warn(esw->dev, "E-Switch destroy TSAR vport element failed (vport=%d,err=%d)\n",
+			 vport_num, err);
+
+	vport->qos.enabled = false;
+}
+
 static void node_guid_gen_from_mac(u64 *node_guid, u8 mac[ETH_ALEN])
 {
 	((u8 *)node_guid)[7] = mac[0];

@@ -1386,6 +1486,7 @@ static void esw_apply_vport_conf(struct mlx5_eswitch *esw,
 		esw_vport_egress_config(esw, vport);
 	}
 }
+
 static void esw_enable_vport(struct mlx5_eswitch *esw, int vport_num,
 			     int enable_events)
 {

@@ -1399,6 +1500,10 @@ static void esw_enable_vport(struct mlx5_eswitch *esw, int vport_num,
 	/* Restore old vport configuration */
 	esw_apply_vport_conf(esw, vport);
 
+	/* Attach vport to the eswitch rate limiter */
+	if (esw_vport_enable_qos(esw, vport_num, vport->info.max_rate))
+		esw_warn(esw->dev, "Failed to attach vport %d to eswitch rate limiter", vport_num);
+
 	/* Sync with current vport context */
 	vport->enabled_events = enable_events;
 	vport->enabled = true;

@@ -1437,7 +1542,7 @@ static void esw_disable_vport(struct mlx5_eswitch *esw, int vport_num)
 	 */
 	esw_vport_change_handle_locked(vport);
 	vport->enabled_events = 0;
-
+	esw_vport_disable_qos(esw, vport_num);
 	if (vport_num && esw->mode == SRIOV_LEGACY) {
 		mlx5_modify_vport_admin_state(esw->dev,
 					      MLX5_QUERY_VPORT_STATE_IN_OP_MOD_ESW_VPORT,

@@ -1483,6 +1588,10 @@ int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode)
 	if (err)
 		goto abort;
 
+	err = esw_create_tsar(esw);
+	if (err)
+		esw_warn(esw->dev, "Failed to create eswitch TSAR");
+
 	enabled_events = (mode == SRIOV_LEGACY) ? SRIOV_VPORT_EVENTS : UC_ADDR_CHANGE;
 	for (i = 0; i <= nvfs; i++)
 		esw_enable_vport(esw, i, enabled_events);

@@ -1519,6 +1628,8 @@ void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw)
 	if (mc_promisc && mc_promisc->uplink_rule)
 		mlx5_del_flow_rule(mc_promisc->uplink_rule);
 
+	esw_destroy_tsar(esw);
+
 	if (esw->mode == SRIOV_LEGACY)
 		esw_destroy_legacy_fdb_table(esw);
 	else if (esw->mode == SRIOV_OFFLOADS)

@@ -115,6 +115,7 @@ struct mlx5_vport_info {
 	u8                      qos;
 	u64                     node_guid;
 	int                     link_state;
+	u32                     max_rate;
 	bool                    spoofchk;
 	bool                    trusted;
 };

@@ -133,6 +134,11 @@ struct mlx5_vport {
 
 	struct mlx5_vport_info  info;
 
+	struct {
+		bool            enabled;
+		u32             esw_tsar_ix;
+	} qos;
+
 	bool                    enabled;
 	u16                     enabled_events;
 };

@@ -209,6 +215,12 @@ struct mlx5_eswitch {
 	 */
 	struct mutex            state_lock;
 	struct esw_mc_addr      *mc_promisc;
+
+	struct {
+		bool            enabled;
+		u32             root_tsar_id;
+	} qos;
+
 	struct mlx5_esw_offload offloads;
 	int                     mode;
 };

@@ -55,7 +55,7 @@ struct mlx5_srq_attr {
 	u32 lwm;
 	u32 user_index;
 	u64 db_record;
-	u64 *pas;
+	__be64 *pas;
 };
 
 struct mlx5_core_dev;

@@ -1107,9 +1107,8 @@ static struct mlx5_flow_rule *add_rule_fg(struct mlx5_flow_group *fg,
 				return rule;
 			}
 			rule = add_rule_fte(fte, fg, dest);
-			unlock_ref_node(&fte->node);
 			if (IS_ERR(rule))
-				goto unlock_fg;
+				goto unlock_fte;
 			else
 				goto add_rule;
 		}

@@ -1127,6 +1126,7 @@ static struct mlx5_flow_rule *add_rule_fg(struct mlx5_flow_group *fg,
 		goto unlock_fg;
 	}
 	tree_init_node(&fte->node, 0, del_fte);
+	nested_lock_ref_node(&fte->node, FS_MUTEX_CHILD);
 	rule = add_rule_fte(fte, fg, dest);
 	if (IS_ERR(rule)) {
 		kfree(fte);

@@ -1139,6 +1139,8 @@ static struct mlx5_flow_rule *add_rule_fg(struct mlx5_flow_group *fg,
 	list_add(&fte->node.list, prev);
 add_rule:
 	tree_add_node(&rule->node, &fte->node);
+unlock_fte:
+	unlock_ref_node(&fte->node);
 unlock_fg:
 	unlock_ref_node(&fg->node);
 	return rule;