Netdev Archive on lore.kernel.org
 help / color / Atom feed
From: Leon Romanovsky <leon@kernel.org>
To: Doug Ledford <dledford@redhat.com>, Jason Gunthorpe <jgg@mellanox.com>
Cc: Leon Romanovsky <leonro@mellanox.com>,
	RDMA mailing list <linux-rdma@vger.kernel.org>,
	Majd Dibbiny <majd@mellanox.com>, Mark Zhang <markz@mellanox.com>,
	Saeed Mahameed <saeedm@mellanox.com>,
	linux-netdev <netdev@vger.kernel.org>
Subject: [PATCH rdma-next v4 17/17] RDMA/nldev: Allow get default counter statistics through RDMA netlink
Date: Tue, 18 Jun 2019 20:26:25 +0300
Message-ID: <20190618172625.13432-18-leon@kernel.org> (raw)
In-Reply-To: <20190618172625.13432-1-leon@kernel.org>

From: Mark Zhang <markz@mellanox.com>

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>
---
 drivers/infiniband/core/nldev.c | 98 ++++++++++++++++++++++++++++++++-
 drivers/infiniband/core/sysfs.c |  6 ++
 include/rdma/ib_verbs.h         |  1 +
 3 files changed, 104 insertions(+), 1 deletion(-)

diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c
index ccbc85d692e1..a6502b94239f 100644
--- a/drivers/infiniband/core/nldev.c
+++ b/drivers/infiniband/core/nldev.c
@@ -1705,6 +1705,99 @@ 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[])

@@ -1777,9 +1870,12 @@ 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);
diff --git a/drivers/infiniband/core/sysfs.c b/drivers/infiniband/core/sysfs.c
index c59b80e0a740..b477295a96c2 100644
--- a/drivers/infiniband/core/sysfs.c
+++ b/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);
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index ff1a312d3e79..d1401f2a25be 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -2237,6 +2237,7 @@ 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 */
--
2.20.1


      parent reply index

Thread overview: 23+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-06-18 17:26 [PATCH rdma-next v4 00/17] Statistics counter support Leon Romanovsky
2019-06-18 17:26 ` [PATCH mlx5-next v4 01/17] net/mlx5: Add rts2rts_qp_counters_set_id field in hca cap Leon Romanovsky
2019-06-18 18:47   ` Saeed Mahameed
2019-06-18 17:26 ` [PATCH rdma-next v4 02/17] RDMA/restrack: Introduce statistic counter Leon Romanovsky
2019-06-18 17:26 ` [PATCH rdma-next v4 03/17] RDMA/restrack: Add an API to attach a task to a resource Leon Romanovsky
2019-06-18 17:26 ` [PATCH rdma-next v4 04/17] RDMA/restrack: Make is_visible_in_pid_ns() as an API Leon Romanovsky
2019-06-18 17:26 ` [PATCH rdma-next v4 05/17] RDMA/counter: Add set/clear per-port auto mode support Leon Romanovsky
2019-06-18 17:26 ` [PATCH rdma-next v4 06/17] RDMA/counter: Add "auto" configuration " Leon Romanovsky
2019-06-30  0:32   ` Jason Gunthorpe
2019-06-30  0:40   ` Jason Gunthorpe
2019-07-01  8:42     ` Leon Romanovsky
2019-06-18 17:26 ` [PATCH mlx5-next v4 07/17] IB/mlx5: Support set qp counter Leon Romanovsky
2019-06-18 18:49   ` Saeed Mahameed
2019-06-18 17:26 ` [PATCH rdma-next v4 08/17] IB/mlx5: Add counter set id as a parameter for mlx5_ib_query_q_counters() Leon Romanovsky
2019-06-18 17:26 ` [PATCH rdma-next v4 09/17] IB/mlx5: Support statistic q counter configuration Leon Romanovsky
2019-06-18 17:26 ` [PATCH rdma-next v4 10/17] RDMA/nldev: Allow counter auto mode configration through RDMA netlink Leon Romanovsky
2019-06-18 17:26 ` [PATCH rdma-next v4 11/17] RDMA/netlink: Implement counter dumpit calback Leon Romanovsky
2019-06-18 17:26 ` [PATCH rdma-next v4 12/17] IB/mlx5: Add counter_alloc_stats() and counter_update_stats() support Leon Romanovsky
2019-06-18 17:26 ` [PATCH rdma-next v4 13/17] RDMA/core: Get sum value of all counters when perform a sysfs stat read Leon Romanovsky
2019-06-18 17:26 ` [PATCH rdma-next v4 14/17] RDMA/counter: Allow manual mode configuration support Leon Romanovsky
2019-06-18 17:26 ` [PATCH rdma-next v4 15/17] RDMA/nldev: Allow counter manual mode configration through RDMA netlink Leon Romanovsky
2019-06-18 17:26 ` [PATCH rdma-next v4 16/17] RDMA/nldev: Allow get counter mode " Leon Romanovsky
2019-06-18 17:26 ` Leon Romanovsky [this message]

Reply instructions:

You may reply publically to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20190618172625.13432-18-leon@kernel.org \
    --to=leon@kernel.org \
    --cc=dledford@redhat.com \
    --cc=jgg@mellanox.com \
    --cc=leonro@mellanox.com \
    --cc=linux-rdma@vger.kernel.org \
    --cc=majd@mellanox.com \
    --cc=markz@mellanox.com \
    --cc=netdev@vger.kernel.org \
    --cc=saeedm@mellanox.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

Netdev Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/netdev/0 netdev/git/0.git
	git clone --mirror https://lore.kernel.org/netdev/1 netdev/git/1.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 netdev netdev/ https://lore.kernel.org/netdev \
		netdev@vger.kernel.org netdev@archiver.kernel.org
	public-inbox-index netdev

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.netdev


AGPL code for this site: git clone https://public-inbox.org/ public-inbox