RDMA/nldev: Allow get default counter statistics through RDMA netlink

This patch adds the ability to return the hwstats of per-port default
counters (which can also be queried through sysfs nodes).
Signed-off-by: Mark Zhang <markz@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

drivers/infiniband/core/nldev.c

@@ -1799,6 +1799,99 @@ static int nldev_stat_del_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
 	return ret;
 }
 
+static int stat_get_doit_default_counter(struct sk_buff *skb,
+					 struct nlmsghdr *nlh,
+					 struct netlink_ext_ack *extack,
+					 struct nlattr *tb[])
+{
+	struct rdma_hw_stats *stats;
+	struct nlattr *table_attr;
+	struct ib_device *device;
+	int ret, num_cnts, i;
+	struct sk_buff *msg;
+	u32 index, port;
+	u64 v;
+
+	if (!tb[RDMA_NLDEV_ATTR_DEV_INDEX] || !tb[RDMA_NLDEV_ATTR_PORT_INDEX])
+		return -EINVAL;
+
+	index = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);
+	device = ib_device_get_by_index(sock_net(skb->sk), index);
+	if (!device)
+		return -EINVAL;
+
+	if (!device->ops.alloc_hw_stats || !device->ops.get_hw_stats) {
+		ret = -EINVAL;
+		goto err;
+	}
+
+	port = nla_get_u32(tb[RDMA_NLDEV_ATTR_PORT_INDEX]);
+	if (!rdma_is_port_valid(device, port)) {
+		ret = -EINVAL;
+		goto err;
+	}
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg) {
+		ret = -ENOMEM;
+		goto err;
+	}
+
+	nlh = nlmsg_put(msg, NETLINK_CB(skb).portid, nlh->nlmsg_seq,
+			RDMA_NL_GET_TYPE(RDMA_NL_NLDEV,
+					 RDMA_NLDEV_CMD_STAT_GET),
+			0, 0);
+
+	if (fill_nldev_handle(msg, device) ||
+	    nla_put_u32(msg, RDMA_NLDEV_ATTR_PORT_INDEX, port)) {
+		ret = -EMSGSIZE;
+		goto err_msg;
+	}
+
+	stats = device->port_data ? device->port_data[port].hw_stats : NULL;
+	if (stats == NULL) {
+		ret = -EINVAL;
+		goto err_msg;
+	}
+	mutex_lock(&stats->lock);
+
+	num_cnts = device->ops.get_hw_stats(device, stats, port, 0);
+	if (num_cnts < 0) {
+		ret = -EINVAL;
+		goto err_stats;
+	}
+
+	table_attr = nla_nest_start(msg, RDMA_NLDEV_ATTR_STAT_HWCOUNTERS);
+	if (!table_attr) {
+		ret = -EMSGSIZE;
+		goto err_stats;
+	}
+	for (i = 0; i < num_cnts; i++) {
+		v = stats->value[i] +
+			rdma_counter_get_hwstat_value(device, port, i);
+		if (fill_stat_hwcounter_entry(msg, stats->names[i], v)) {
+			ret = -EMSGSIZE;
+			goto err_table;
+		}
+	}
+	nla_nest_end(msg, table_attr);
+
+	mutex_unlock(&stats->lock);
+	nlmsg_end(msg, nlh);
+	ib_device_put(device);
+	return rdma_nl_unicast(msg, NETLINK_CB(skb).portid);
+
+err_table:
+	nla_nest_cancel(msg, table_attr);
+err_stats:
+	mutex_unlock(&stats->lock);
+err_msg:
+	nlmsg_free(msg);
+err:
+	ib_device_put(device);
+	return ret;
+}
+
 static int stat_get_doit_qp(struct sk_buff *skb, struct nlmsghdr *nlh,
 			    struct netlink_ext_ack *extack, struct nlattr *tb[])
 
@@ -1871,9 +1964,12 @@ static int nldev_stat_get_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
 
 	ret = nlmsg_parse(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1,
 			  nldev_policy, extack);
-	if (ret || !tb[RDMA_NLDEV_ATTR_STAT_RES])
+	if (ret)
 		return -EINVAL;
 
+	if (!tb[RDMA_NLDEV_ATTR_STAT_RES])
+		return stat_get_doit_default_counter(skb, nlh, extack, tb);
+
 	switch (nla_get_u32(tb[RDMA_NLDEV_ATTR_STAT_RES])) {
 	case RDMA_NLDEV_ATTR_RES_QP:
 		ret = stat_get_doit_qp(skb, nlh, extack, tb);

drivers/infiniband/core/sysfs.c

@@ -1003,6 +1003,8 @@ static void setup_hw_stats(struct ib_device *device, struct ib_port *port,
 			goto err;
 		port->hw_stats_ag = hsag;
 		port->hw_stats = stats;
+		if (device->port_data)
+			device->port_data[port_num].hw_stats = stats;
 	} else {
 		struct kobject *kobj = &device->dev.kobj;
 		ret = sysfs_create_group(kobj, hsag);
@@ -1293,6 +1295,8 @@ const struct attribute_group ib_dev_attr_group = {
 
 void ib_free_port_attrs(struct ib_core_device *coredev)
 {
+	struct ib_device *device = rdma_device_to_ibdev(&coredev->dev);
+	bool is_full_dev = &device->coredev == coredev;
 	struct kobject *p, *t;
 
 	list_for_each_entry_safe(p, t, &coredev->port_list, entry) {
@@ -1302,6 +1306,8 @@ void ib_free_port_attrs(struct ib_core_device *coredev)
 		if (port->hw_stats_ag)
 			free_hsag(&port->kobj, port->hw_stats_ag);
 		kfree(port->hw_stats);
+		if (device->port_data && is_full_dev)
+			device->port_data[port->port_num].hw_stats = NULL;
 
 		if (port->pma_table)
 			sysfs_remove_group(p, port->pma_table);

include/rdma/ib_verbs.h

@@ -2124,6 +2124,7 @@ struct ib_port_data {
 	struct net_device __rcu *netdev;
 	struct hlist_node ndev_hash_link;
 	struct rdma_port_counter port_counter;
+	struct rdma_hw_stats *hw_stats;
 };
 
 /* rdma netdev type - specifies protocol type */