RDMA/mlx5: Add optional counters for RDMA_TX/RX_packets/bytes

Add the following optional counters:
rdma_tx_packets,rdma_rx_bytes,rdma_rx_packets,rdma_tx_bytes.

Which counts all RDMA packets/bytes sent and received per link.

Note that since each direction packet and byte counter are shared,
the counter is only reset when both counters of that direction
are removed. But from user-perspective each can be enabled/disabled separately.

The counters can be enabled using:
sudo rdma stat set link rocep8s0f0/1 optional-counters rdma_tx_packets
And can be seen using:
rdma stat -j show link rocep8s0f0/1

Signed-off-by: Patrisious Haddad <[e-mail]>
Reviewed-by: Mark Bloch <[e-mail]>
Link: https://patch.msgid.link/[e-mail]
Signed-off-by: Leon Romanovsky <[e-mail]>

drivers/infiniband/hw/mlx5/counters.c

···
 	INIT_OP_COUNTER(cc_tx_cnp_pkts, CC_TX_CNP_PKTS),
 };
 
+static const struct mlx5_ib_counter packets_op_cnts[] = {
+	INIT_OP_COUNTER(rdma_tx_packets, RDMA_TX_PACKETS),
+	INIT_OP_COUNTER(rdma_tx_bytes, RDMA_TX_BYTES),
+	INIT_OP_COUNTER(rdma_rx_packets, RDMA_RX_PACKETS),
+	INIT_OP_COUNTER(rdma_rx_bytes, RDMA_RX_BYTES),
+};
+
 static int mlx5_ib_read_counters(struct ib_counters *counters,
 				 struct ib_counters_read_attr *read_attr,
 				 struct uverbs_attr_bundle *attrs)
···
 	return num_counters;
 }
 
+static bool is_rdma_bytes_counter(u32 type)
+{
+	if (type == MLX5_IB_OPCOUNTER_RDMA_TX_BYTES ||
+	    type == MLX5_IB_OPCOUNTER_RDMA_RX_BYTES)
+		return true;
+
+	return false;
+}
+
 static int do_get_op_stat(struct ib_device *ibdev,
 			  struct rdma_hw_stats *stats,
 			  u32 port_num, int index)
···
 	struct mlx5_ib_dev *dev = to_mdev(ibdev);
 	const struct mlx5_ib_counters *cnts;
 	const struct mlx5_ib_op_fc *opfcs;
-	u64 packets = 0, bytes;
+	u64 packets, bytes;
 	u32 type;
 	int ret;
 
···
 	if (ret)
 		return ret;
 
+	if (is_rdma_bytes_counter(type))
+		stats->value[index] = bytes;
+	else
+		stats->value[index] = packets;
 out:
-	stats->value[index] = packets;
 	return index;
 }
 
···
 			descs[j].priv = &rdmatx_cnp_op_cnts[i].type;
 		}
 	}
+
+	for (i = 0; i < ARRAY_SIZE(packets_op_cnts); i++, j++) {
+		descs[j].name = packets_op_cnts[i].name;
+		descs[j].flags |= IB_STAT_FLAG_OPTIONAL;
+		descs[j].priv = &packets_op_cnts[i].type;
+	}
 }
 
 
···
 
 	num_op_counters = ARRAY_SIZE(basic_op_cnts);
 
+	num_op_counters += ARRAY_SIZE(packets_op_cnts);
+
 	if (MLX5_CAP_FLOWTABLE(dev->mdev,
 			       ft_field_support_2_nic_receive_rdma.bth_opcode))
 		num_op_counters += ARRAY_SIZE(rdmarx_cnp_op_cnts);
···
 	return -ENOMEM;
 }
 
+/*
+ * Checks if the given flow counter type should be sharing the same flow counter
+ * with another type and if it should, checks if that other type flow counter
+ * was already created, if both conditions are met return true and the counter
+ * else return false.
+ */
+static bool mlx5r_is_opfc_shared_and_in_use(struct mlx5_ib_op_fc *opfcs,
+					    u32 type,
+					    struct mlx5_ib_op_fc **opfc)
+{
+	u32 shared_fc_type;
+
+	switch (type) {
+	case MLX5_IB_OPCOUNTER_RDMA_TX_PACKETS:
+		shared_fc_type = MLX5_IB_OPCOUNTER_RDMA_TX_BYTES;
+		break;
+	case MLX5_IB_OPCOUNTER_RDMA_TX_BYTES:
+		shared_fc_type = MLX5_IB_OPCOUNTER_RDMA_TX_PACKETS;
+		break;
+	case MLX5_IB_OPCOUNTER_RDMA_RX_PACKETS:
+		shared_fc_type = MLX5_IB_OPCOUNTER_RDMA_RX_BYTES;
+		break;
+	case MLX5_IB_OPCOUNTER_RDMA_RX_BYTES:
+		shared_fc_type = MLX5_IB_OPCOUNTER_RDMA_RX_PACKETS;
+		break;
+	default:
+		return false;
+	}
+
+	*opfc = &opfcs[shared_fc_type];
+	if (!(*opfc)->fc)
+		return false;
+
+	return true;
+}
+
 static void mlx5_ib_dealloc_counters(struct mlx5_ib_dev *dev)
 {
 	u32 in[MLX5_ST_SZ_DW(dealloc_q_counter_in)] = {};
 	int num_cnt_ports = dev->num_ports;
+	struct mlx5_ib_op_fc *in_use_opfc;
 	int i, j;
 
 	if (is_mdev_switchdev_mode(dev->mdev))
···
 			if (!dev->port[i].cnts.opfcs[j].fc)
 				continue;
 
+			if (mlx5r_is_opfc_shared_and_in_use(
+				    dev->port[i].cnts.opfcs, j, &in_use_opfc))
+				goto skip;
+
 			if (IS_ENABLED(CONFIG_INFINIBAND_USER_ACCESS))
 				mlx5_ib_fs_remove_op_fc(dev,
 					&dev->port[i].cnts.opfcs[j], j);
 			mlx5_fc_destroy(dev->mdev,
 					dev->port[i].cnts.opfcs[j].fc);
+skip:
 			dev->port[i].cnts.opfcs[j].fc = NULL;
 		}
 	}
···
 			       unsigned int index, bool enable)
 {
 	struct mlx5_ib_dev *dev = to_mdev(device);
+	struct mlx5_ib_op_fc *opfc, *in_use_opfc;
 	struct mlx5_ib_counters *cnts;
-	struct mlx5_ib_op_fc *opfc;
 	u32 num_hw_counters, type;
 	int ret;
 
···
 		if (opfc->fc)
 			return -EEXIST;
 
+		if (mlx5r_is_opfc_shared_and_in_use(cnts->opfcs, type,
+						    &in_use_opfc)) {
+			opfc->fc = in_use_opfc->fc;
+			opfc->rule[0] = in_use_opfc->rule[0];
+			return 0;
+		}
+
 		opfc->fc = mlx5_fc_create(dev->mdev, false);
 		if (IS_ERR(opfc->fc))
 			return PTR_ERR(opfc->fc);
···
 	if (!opfc->fc)
 		return -EINVAL;
 
+	if (mlx5r_is_opfc_shared_and_in_use(cnts->opfcs, type, &in_use_opfc))
+		goto out;
+
 	mlx5_ib_fs_remove_op_fc(dev, opfc, type);
 	mlx5_fc_destroy(dev->mdev, opfc->fc);
+out:
 	opfc->fc = NULL;
 	return 0;
 }

drivers/infiniband/hw/mlx5/fs.c

···
 enum {
 	RDMA_RX_ECN_OPCOUNTER_PRIO,
 	RDMA_RX_CNP_OPCOUNTER_PRIO,
+	RDMA_RX_PKTS_BYTES_OPCOUNTER_PRIO,
 };
 
 enum {
 	RDMA_TX_CNP_OPCOUNTER_PRIO,
+	RDMA_TX_PKTS_BYTES_OPCOUNTER_PRIO,
 };
 
 static int set_vhca_port_spec(struct mlx5_ib_dev *dev, u32 port_num,
···
 	return 0;
 }
 
+/* Returns the prio we should use for the given optional counter type,
+ * whereas for bytes type we use the packet type, since they share the same
+ * resources.
+ */
+static struct mlx5_ib_flow_prio *get_opfc_prio(struct mlx5_ib_dev *dev,
+					       u32 type)
+{
+	u32 prio_type;
+
+	switch (type) {
+	case MLX5_IB_OPCOUNTER_RDMA_TX_BYTES:
+		prio_type = MLX5_IB_OPCOUNTER_RDMA_TX_PACKETS;
+		break;
+	case MLX5_IB_OPCOUNTER_RDMA_RX_BYTES:
+		prio_type = MLX5_IB_OPCOUNTER_RDMA_RX_PACKETS;
+		break;
+	default:
+		prio_type = type;
+	}
+
+	return &dev->flow_db->opfcs[prio_type];
+}
+
 int mlx5_ib_fs_add_op_fc(struct mlx5_ib_dev *dev, u32 port_num,
 			 struct mlx5_ib_op_fc *opfc,
 			 enum mlx5_ib_optional_counter_type type)
···
 		priority = RDMA_TX_CNP_OPCOUNTER_PRIO;
 		break;
 
+	case MLX5_IB_OPCOUNTER_RDMA_TX_PACKETS:
+	case MLX5_IB_OPCOUNTER_RDMA_TX_BYTES:
+		spec_num = 1;
+		fn_type = MLX5_FLOW_NAMESPACE_RDMA_TX_COUNTERS;
+		priority = RDMA_TX_PKTS_BYTES_OPCOUNTER_PRIO;
+		break;
+
+	case MLX5_IB_OPCOUNTER_RDMA_RX_PACKETS:
+	case MLX5_IB_OPCOUNTER_RDMA_RX_BYTES:
+		spec_num = 1;
+		fn_type = MLX5_FLOW_NAMESPACE_RDMA_RX_COUNTERS;
+		priority = RDMA_RX_PKTS_BYTES_OPCOUNTER_PRIO;
+		break;
+
 	default:
 		err = -EOPNOTSUPP;
 		goto free;
···
 		goto free;
 	}
 
-	prio = &dev->flow_db->opfcs[type];
+	prio = get_opfc_prio(dev, type);
 	if (!prio->flow_table) {
 		prio = _get_prio(dev, ns, prio, priority,
 				 dev->num_ports * MAX_OPFC_RULES, 1, 0, 0);
···
 			     struct mlx5_ib_op_fc *opfc,
 			     enum mlx5_ib_optional_counter_type type)
 {
+	struct mlx5_ib_flow_prio *prio;
 	int i;
+
+	prio = get_opfc_prio(dev, type);
 
 	for (i = 0; i < MAX_OPFC_RULES && opfc->rule[i]; i++) {
 		mlx5_del_flow_rules(opfc->rule[i]);
-		put_flow_table(dev, &dev->flow_db->opfcs[type], true);
+		put_flow_table(dev, prio, true);
 	}
 }
 

drivers/infiniband/hw/mlx5/mlx5_ib.h

···
 	MLX5_IB_OPCOUNTER_CC_RX_CE_PKTS,
 	MLX5_IB_OPCOUNTER_CC_RX_CNP_PKTS,
 	MLX5_IB_OPCOUNTER_CC_TX_CNP_PKTS,
+	MLX5_IB_OPCOUNTER_RDMA_TX_PACKETS,
+	MLX5_IB_OPCOUNTER_RDMA_TX_BYTES,
+	MLX5_IB_OPCOUNTER_RDMA_RX_PACKETS,
+	MLX5_IB_OPCOUNTER_RDMA_RX_BYTES,
 
 	MLX5_IB_OPCOUNTER_MAX,
 };

include/linux/mlx5/device.h

···
 	return MLX5_MIN_PKEY_TABLE_SIZE << pkey_sz;
 }
 
-#define MLX5_RDMA_RX_NUM_COUNTERS_PRIOS 2
-#define MLX5_RDMA_TX_NUM_COUNTERS_PRIOS 1
+#define MLX5_RDMA_RX_NUM_COUNTERS_PRIOS 3
+#define MLX5_RDMA_TX_NUM_COUNTERS_PRIOS 2
 #define MLX5_BY_PASS_NUM_REGULAR_PRIOS 16
 #define MLX5_BY_PASS_NUM_DONT_TRAP_PRIOS 16
 #define MLX5_BY_PASS_NUM_MULTICAST_PRIOS 1