[PATCH iproute2-next 0/8] Statistics counter support

[PATCH iproute2-next 0/8] Statistics counter support

[Leon Romanovsky]

From: Leon Romanovsky <leonro@mellanox.com>

---------------------------------
Kernel patch is not accepted yet.
---------------------------------

Hi,

This is supplementary part of kernel series [1], that kernel series
provided an option to get various counters: global and per-objects.

Currently, all counters are printed in format similar to other
device/link properties, but maybe we should print them as table.

[leonro@server ~]$ rdma stat show
link mlx5_0/1 rx_write_requests 0 rx_read_requests 0 rx_atomic_requests
0 out_of_buffer 0 duplicate_request 0 rnr_nak_retry_err 0 packet_seq_err
0 implied_nak_seq_err 0 local_ack_timeout_err 0 resp_local_length_error
0 resp_cqe_error 0 req_cqe_error 0 req_remote_invalid_request 0
req_remote_access_errors 0 resp_remote_access_errors 0
resp_cqe_flush_error 0 req_cqe_flush_error 0 rp_cnp_ignored 0
rp_cnp_handled 0 np_ecn_marked_roce_packets 0 np_cnp_sent 0

Thanks

[1] https://www.spinics.net/lists/linux-rdma/msg77735.html

Thanks

Mark Zhang (8):
  rdma: Update uapi headers to add statistic counter support
  rdma: Add "stat qp show" support
  rdma: Add get per-port counter mode support
  rdma: Add rdma statistic counter per-port auto mode support
  rdma: Make get_port_from_argv() returns valid port in strict port mode
  rdma: Add stat manual mode support
  rdma: Add default counter show support
  rdma: Document counter statistic

 man/man8/rdma-dev.8                   |   1 +
 man/man8/rdma-link.8                  |   1 +
 man/man8/rdma-resource.8              |   1 +
 man/man8/rdma-statistic.8             | 170 ++++++
 man/man8/rdma.8                       |   5 +
 rdma/Makefile                         |   2 +-
 rdma/include/uapi/rdma/rdma_netlink.h |  82 ++-
 rdma/rdma.c                           |   3 +-
 rdma/rdma.h                           |   1 +
 rdma/stat.c                           | 802 ++++++++++++++++++++++++++
 rdma/utils.c                          |  17 +-
 11 files changed, 1069 insertions(+), 16 deletions(-)
 create mode 100644 man/man8/rdma-statistic.8
 create mode 100644 rdma/stat.c

[PATCH iproute2-next 1/8] rdma: Update uapi headers to add statistic counter support

[Leon Romanovsky]

From: Mark Zhang <markz@mellanox.com>

Update rdma_netlink.h for statistic counter support, which allows
a user to monitor specific QPs categories.

Signed-off-by: Mark Zhang <markz@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 rdma/include/uapi/rdma/rdma_netlink.h | 82 +++++++++++++++++++++++----
 1 file changed, 70 insertions(+), 12 deletions(-)

diff --git a/rdma/include/uapi/rdma/rdma_netlink.h b/rdma/include/uapi/rdma/rdma_netlink.h
index 23a90ad5..44d9f35b 100644
--- a/rdma/include/uapi/rdma/rdma_netlink.h
+++ b/rdma/include/uapi/rdma/rdma_netlink.h
@@ -49,17 +49,6 @@ enum {
 	RDMA_NL_IWPM_NUM_OPS
 };
 
-struct rdma_cm_id_stats {
-	__u32	qp_num;
-	__u32	bound_dev_if;
-	__u32	port_space;
-	__s32	pid;
-	__u8	cm_state;
-	__u8	node_type;
-	__u8	port_num;
-	__u8	qp_type;
-};
-
 enum {
 	IWPM_NLA_REG_PID_UNSPEC = 0,
 	IWPM_NLA_REG_PID_SEQ,
@@ -261,7 +250,10 @@ enum rdma_nldev_command {
 
 	RDMA_NLDEV_CMD_PORT_GET, /* can dump */
 
-	/* 6 - 8 are free to use */
+	RDMA_NLDEV_CMD_SYS_GET, /* can dump */
+	RDMA_NLDEV_CMD_SYS_SET,
+
+	/* 8 is free to use */
 
 	RDMA_NLDEV_CMD_RES_GET = 9, /* can dump */
 
@@ -275,6 +267,12 @@ enum rdma_nldev_command {
 
 	RDMA_NLDEV_CMD_RES_PD_GET, /* can dump */
 
+	RDMA_NLDEV_CMD_STAT_SET,
+
+	RDMA_NLDEV_CMD_STAT_GET, /* can dump */
+
+	RDMA_NLDEV_CMD_STAT_DEL,
+
 	RDMA_NLDEV_NUM_OPS
 };
 
@@ -472,9 +470,69 @@ enum rdma_nldev_attr {
 	 */
 	RDMA_NLDEV_ATTR_LINK_TYPE,		/* string */
 
+	/*
+	 * net namespace mode for rdma subsystem:
+	 * either shared or exclusive among multiple net namespaces.
+	 */
+	RDMA_NLDEV_SYS_ATTR_NETNS_MODE,		/* u8 */
+	/*
+	 * File descriptor handle of the net namespace object
+	 */
+	RDMA_NLDEV_NET_NS_FD,			/* u32 */
+
+	/*
+	 * Device protocol, e.g. ib, iw, usnic, roce and opa
+	 */
+	RDMA_NLDEV_ATTR_DEV_PROTOCOL,		/* string */
+	/*
+	 * Counter-specific attributes.
+	 */
+	RDMA_NLDEV_ATTR_STAT_MODE,		/* u32 */
+	RDMA_NLDEV_ATTR_STAT_RES,		/* u32 */
+	RDMA_NLDEV_ATTR_STAT_AUTO_MODE_MASK,	/* u32 */
+	RDMA_NLDEV_ATTR_STAT_COUNTER,		/* nested table */
+	RDMA_NLDEV_ATTR_STAT_COUNTER_ENTRY,	/* nested table */
+	RDMA_NLDEV_ATTR_STAT_COUNTER_ID,	/* u32 */
+	RDMA_NLDEV_ATTR_STAT_HWCOUNTERS,	/* nested table */
+	RDMA_NLDEV_ATTR_STAT_HWCOUNTER_ENTRY,	/* nested table */
+	RDMA_NLDEV_ATTR_STAT_HWCOUNTER_ENTRY_NAME,	/* string */
+	RDMA_NLDEV_ATTR_STAT_HWCOUNTER_ENTRY_VALUE,	/* u64 */
 	/*
 	 * Always the end
 	 */
 	RDMA_NLDEV_ATTR_MAX
 };
+
+/*
+ * Supported counter bind modes. All modes are mutual-exclusive.
+ */
+enum rdma_nl_counter_mode {
+	RDMA_COUNTER_MODE_NONE,
+
+	/*
+	 * A qp is bound with a counter automatically during initialization
+	 * based on the auto mode (e.g., qp type, ...)
+	 */
+	RDMA_COUNTER_MODE_AUTO,
+
+	/*
+	 * Which qp are bound with which counter is explicitly specified
+	 * by the user
+	 */
+	RDMA_COUNTER_MODE_MANUAL,
+
+	/*
+	 * Always the end
+	 */
+	RDMA_COUNTER_MODE_MAX,
+};
+
+/*
+ * Supported criteria in counter auto mode.
+ * Currently only "qp type" is supported
+ */
+enum rdma_nl_counter_mask {
+	RDMA_COUNTER_MASK_QP_TYPE = 1,
+};
+
 #endif /* _RDMA_NETLINK_H */
-- 
2.20.1

[PATCH iproute2-next 2/8] rdma: Add "stat qp show" support

[Leon Romanovsky]

From: Mark Zhang <markz@mellanox.com>

Show qp counters statistics in detail. Filters are also enabled.

Examples:
$ rdma stat qp show
link mlx5_2/1 cntn 5 pid 31609 comm client.1 rx_write_requests 0 rx_read_requests 0 rx_atomic_requests 0 out_of_buffer 0 out_of_sequence 0 duplicate_request 0 rnr_nak_retry_err 0 packet_seq_err 0 implied_nak_seq_err 0 local_ack_timeout_err 0 resp_local_length_error 0 resp_cqe_error 0 req_cqe_error 0 req_remote_invalid_request 0 req_remote_access_errors 0 resp_remote_access_errors 0 resp_cqe_flush_error 0 req_cqe_flush_error 0
    LQPN: <178>
$ rdma stat show link mlx5_2/1

Signed-off-by: Mark Zhang <markz@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 rdma/Makefile |   2 +-
 rdma/rdma.c   |   3 +-
 rdma/rdma.h   |   1 +
 rdma/stat.c   | 263 ++++++++++++++++++++++++++++++++++++++++++++++++++
 rdma/utils.c  |   7 ++
 5 files changed, 274 insertions(+), 2 deletions(-)
 create mode 100644 rdma/stat.c

diff --git a/rdma/Makefile b/rdma/Makefile
index 6a424234..e1af4414 100644
--- a/rdma/Makefile
+++ b/rdma/Makefile
@@ -7,7 +7,7 @@ ifeq ($(HAVE_MNL),y)
 CFLAGS += -I./include/uapi/
 
 RDMA_OBJ = rdma.o utils.o dev.o link.o res.o res-pd.o res-mr.o res-cq.o \
-	   res-cmid.o res-qp.o
+	   res-cmid.o res-qp.o stat.o
 
 TARGETS += rdma
 endif
diff --git a/rdma/rdma.c b/rdma/rdma.c
index 676e03c2..c8984764 100644
--- a/rdma/rdma.c
+++ b/rdma/rdma.c
@@ -11,7 +11,7 @@ static void help(char *name)
 {
 	pr_out("Usage: %s [ OPTIONS ] OBJECT { COMMAND | help }\n"
 	       "       %s [ -f[orce] ] -b[atch] filename\n"
-	       "where  OBJECT := { dev | link | resource | help }\n"
+	       "where  OBJECT := { dev | link | resource | statistic | help }\n"
 	       "       OPTIONS := { -V[ersion] | -d[etails] | -j[son] | -p[retty]}\n", name, name);
 }
 
@@ -29,6 +29,7 @@ static int rd_cmd(struct rd *rd, int argc, char **argv)
 		{ "dev",	cmd_dev },
 		{ "link",	cmd_link },
 		{ "resource",	cmd_res },
+		{ "statistic",	cmd_stat },
 		{ 0 }
 	};
 
diff --git a/rdma/rdma.h b/rdma/rdma.h
index 9ed9e045..b5ddcb07 100644
--- a/rdma/rdma.h
+++ b/rdma/rdma.h
@@ -93,6 +93,7 @@ char *rd_argv(struct rd *rd);
 int cmd_dev(struct rd *rd);
 int cmd_link(struct rd *rd);
 int cmd_res(struct rd *rd);
+int cmd_stat(struct rd *rd);
 int rd_exec_cmd(struct rd *rd, const struct rd_cmd *c, const char *str);
 int rd_exec_dev(struct rd *rd, int (*cb)(struct rd *rd));
 int rd_exec_require_dev(struct rd *rd, int (*cb)(struct rd *rd));
diff --git a/rdma/stat.c b/rdma/stat.c
new file mode 100644
index 00000000..0c3abc99
--- /dev/null
+++ b/rdma/stat.c
@@ -0,0 +1,263 @@
+/*
+ * stat.c	RDMA tool
+ *
+ *              This program is free software; you can redistribute it and/or
+ *              modify it under the terms of the GNU General Public License
+ *              as published by the Free Software Foundation; either version
+ *              2 of the License, or (at your option) any later version.
+ *
+ * Authors:     Mark Zhang <markz@mellanox.com>
+ */
+
+#include "rdma.h"
+#include "res.h"
+#include <inttypes.h>
+
+static int stat_help(struct rd *rd)
+{
+	pr_out("Usage: %s [ OPTIONS ] statistic { COMMAND | help }\n", rd->filename);
+	pr_out("       %s statistic OBJECT show\n", rd->filename);
+	pr_out("       %s statistic OBJECT show link [ DEV/PORT_INDEX ] [ FILTER-NAME FILTER-VALUE ]\n", rd->filename);
+	pr_out("Examples:\n");
+	pr_out("       %s statistic qp show\n", rd->filename);
+	pr_out("       %s statistic qp show link mlx5_2/1\n", rd->filename);
+
+	return 0;
+}
+
+static int res_show_hwcounters(struct rd *rd, struct nlattr *hwc_table)
+{
+	struct nlattr *nla_entry;
+	const char *nm;
+	uint64_t v;
+	int err;
+
+	mnl_attr_for_each_nested(nla_entry, hwc_table) {
+		struct nlattr *hw_line[RDMA_NLDEV_ATTR_MAX] = {};
+
+		err = mnl_attr_parse_nested(nla_entry, rd_attr_cb, hw_line);
+		if (err != MNL_CB_OK)
+			return -EINVAL;
+
+		if (!hw_line[RDMA_NLDEV_ATTR_STAT_HWCOUNTER_ENTRY_NAME] ||
+		    !hw_line[RDMA_NLDEV_ATTR_STAT_HWCOUNTER_ENTRY_VALUE]) {
+			return -EINVAL;
+		}
+
+		nm = mnl_attr_get_str(hw_line[RDMA_NLDEV_ATTR_STAT_HWCOUNTER_ENTRY_NAME]);
+		v = mnl_attr_get_u64(hw_line[RDMA_NLDEV_ATTR_STAT_HWCOUNTER_ENTRY_VALUE]);
+		res_print_uint(rd, nm, v, hw_line[RDMA_NLDEV_ATTR_STAT_HWCOUNTER_ENTRY_NAME]);
+	}
+
+	return MNL_CB_OK;
+}
+
+static int res_counter_line(struct rd *rd, const char *name, int index,
+		       struct nlattr **nla_line)
+{
+	uint32_t cntn, port = 0, pid = 0, qpn;
+	struct nlattr *hwc_table, *qp_table;
+	struct nlattr *nla_entry;
+	const char *comm = NULL;
+	int err;
+
+	if (nla_line[RDMA_NLDEV_ATTR_PORT_INDEX])
+		port = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_PORT_INDEX]);
+
+	hwc_table = nla_line[RDMA_NLDEV_ATTR_STAT_HWCOUNTERS];
+	qp_table = nla_line[RDMA_NLDEV_ATTR_RES_QP];
+	if (!hwc_table || !qp_table ||
+	    !nla_line[RDMA_NLDEV_ATTR_STAT_COUNTER_ID])
+		return MNL_CB_ERROR;
+
+	cntn = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_STAT_COUNTER_ID]);
+	if (rd_is_filtered_attr(rd, "cntn", cntn,
+				nla_line[RDMA_NLDEV_ATTR_STAT_COUNTER_ID]))
+		return MNL_CB_OK;
+
+	if (nla_line[RDMA_NLDEV_ATTR_RES_PID]) {
+		pid = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_PID]);
+		comm = get_task_name(pid);
+	}
+	if (rd_is_filtered_attr(rd, "pid", pid,
+				nla_line[RDMA_NLDEV_ATTR_RES_PID]))
+		return MNL_CB_OK;
+
+	if (nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])
+		comm = (char *)mnl_attr_get_str(
+			nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME]);
+
+	mnl_attr_for_each_nested(nla_entry, qp_table) {
+		struct nlattr *qp_line[RDMA_NLDEV_ATTR_MAX] = {};
+
+		err = mnl_attr_parse_nested(nla_entry, rd_attr_cb, qp_line);
+		if (err != MNL_CB_OK)
+			return -EINVAL;
+
+		if (!qp_line[RDMA_NLDEV_ATTR_RES_LQPN])
+			return -EINVAL;
+
+		qpn = mnl_attr_get_u32(qp_line[RDMA_NLDEV_ATTR_RES_LQPN]);
+		if (rd_is_filtered_attr(rd, "lqpn", qpn,
+					qp_line[RDMA_NLDEV_ATTR_RES_LQPN]))
+			return MNL_CB_OK;
+	}
+
+	if (rd->json_output) {
+		jsonw_string_field(rd->jw, "ifname", name);
+		if (port)
+			jsonw_uint_field(rd->jw, "port", port);
+		jsonw_uint_field(rd->jw, "cntn", cntn);
+	} else {
+		if (port)
+			pr_out("link %s/%u cntn %u ", name, port, cntn);
+		else
+			pr_out("dev %s cntn %u ", name, cntn);
+	}
+
+	res_print_uint(rd, "pid", pid, nla_line[RDMA_NLDEV_ATTR_RES_PID]);
+	print_comm(rd, comm, nla_line);
+
+	err = res_show_hwcounters(rd, hwc_table);
+	if (err != MNL_CB_OK)
+		return err;
+
+	mnl_attr_for_each_nested(nla_entry, qp_table) {
+		struct nlattr *qp_line[RDMA_NLDEV_ATTR_MAX] = {};
+		static bool isfirst = true;
+
+		if (isfirst && !rd->json_output)
+			pr_out("\n    LQPN: <");
+
+		err = mnl_attr_parse_nested(nla_entry, rd_attr_cb, qp_line);
+		if (err != MNL_CB_OK)
+			return -EINVAL;
+
+		if (!qp_line[RDMA_NLDEV_ATTR_RES_LQPN])
+			return -EINVAL;
+
+		qpn = mnl_attr_get_u32(qp_line[RDMA_NLDEV_ATTR_RES_LQPN]);
+		if (rd->json_output) {
+			jsonw_uint_field(rd->jw, "lqpn", qpn);
+		} else {
+			if (isfirst)
+				pr_out("%d", qpn);
+			else
+				pr_out(", %d", qpn);
+		}
+		isfirst = false;
+	}
+
+	if (!rd->json_output)
+		pr_out(">\n");
+	return MNL_CB_OK;
+}
+
+static int stat_qp_show_parse_cb(const struct nlmsghdr *nlh, void *data)
+{
+	struct nlattr *tb[RDMA_NLDEV_ATTR_MAX] = {};
+	struct nlattr *nla_table, *nla_entry;
+	struct rd *rd = data;
+	const char *name;
+	uint32_t idx;
+	int ret;
+
+	mnl_attr_parse(nlh, 0, rd_attr_cb, tb);
+	if (!tb[RDMA_NLDEV_ATTR_DEV_INDEX] || !tb[RDMA_NLDEV_ATTR_DEV_NAME] ||
+	    !tb[RDMA_NLDEV_ATTR_STAT_COUNTER])
+		return MNL_CB_ERROR;
+
+	name = mnl_attr_get_str(tb[RDMA_NLDEV_ATTR_DEV_NAME]);
+	idx = mnl_attr_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);
+	nla_table = tb[RDMA_NLDEV_ATTR_STAT_COUNTER];
+
+	mnl_attr_for_each_nested(nla_entry, nla_table) {
+		struct nlattr *nla_line[RDMA_NLDEV_ATTR_MAX] = {};
+		ret = mnl_attr_parse_nested(nla_entry, rd_attr_cb, nla_line);
+		if (ret != MNL_CB_OK)
+			break;
+
+		ret = res_counter_line(rd, name, idx, nla_line);
+		if (ret != MNL_CB_OK)
+			break;
+	}
+
+	return ret;
+}
+
+static const struct filters stat_valid_filters[MAX_NUMBER_OF_FILTERS] = {
+	{ .name = "cntn", .is_number = true },
+	{ .name = "lqpn", .is_number = true },
+	{ .name = "pid", .is_number = true },
+};
+
+static int stat_qp_show_one_link(struct rd *rd)
+{
+	int flags = NLM_F_REQUEST | NLM_F_ACK | NLM_F_DUMP;
+	uint32_t seq;
+	int ret;
+
+	if (!rd->port_idx)
+		return 0;
+
+	ret = rd_build_filter(rd, stat_valid_filters);
+	if (ret)
+		return ret;
+
+	rd_prepare_msg(rd, RDMA_NLDEV_CMD_STAT_GET, &seq, flags);
+	mnl_attr_put_u32(rd->nlh, RDMA_NLDEV_ATTR_DEV_INDEX, rd->dev_idx);
+	mnl_attr_put_u32(rd->nlh, RDMA_NLDEV_ATTR_PORT_INDEX, rd->port_idx);
+	ret = rd_send_msg(rd);
+	if (ret)
+		return ret;
+
+	if (rd->json_output)
+		jsonw_start_object(rd->jw);
+	ret = rd_recv_msg(rd, stat_qp_show_parse_cb, rd, seq);
+	if (rd->json_output)
+		jsonw_end_object(rd->jw);
+
+	return ret;
+}
+
+static int stat_qp_show_link(struct rd *rd)
+{
+	return rd_exec_link(rd, stat_qp_show_one_link, false);
+}
+
+static int stat_qp_show(struct rd *rd)
+{
+	const struct rd_cmd cmds[] = {
+		{ NULL,		stat_qp_show_link },
+		{ "link",	stat_qp_show_link },
+		{ "help",	stat_help },
+		{ 0 }
+	};
+
+	return rd_exec_cmd(rd, cmds, "parameter");
+}
+
+static int stat_qp(struct rd *rd)
+{
+	const struct rd_cmd cmds[] =  {
+		{ NULL,		stat_qp_show },
+		{ "show",	stat_qp_show },
+		{ "list",	stat_qp_show },
+		{ "help",	stat_help },
+		{ 0 }
+	};
+
+	return rd_exec_cmd(rd, cmds, "parameter");
+}
+
+int cmd_stat(struct rd *rd)
+{
+	const struct rd_cmd cmds[] =  {
+		{ NULL,		stat_help },
+		{ "help",	stat_help },
+		{ "qp",		stat_qp },
+		{ 0 }
+	};
+
+	return rd_exec_cmd(rd, cmds, "statistic command");
+}
diff --git a/rdma/utils.c b/rdma/utils.c
index 11ed8a73..ff781517 100644
--- a/rdma/utils.c
+++ b/rdma/utils.c
@@ -435,6 +435,13 @@ static const enum mnl_attr_data_type nldev_policy[RDMA_NLDEV_ATTR_MAX] = {
 	[RDMA_NLDEV_ATTR_DRIVER_U32] = MNL_TYPE_U32,
 	[RDMA_NLDEV_ATTR_DRIVER_S64] = MNL_TYPE_U64,
 	[RDMA_NLDEV_ATTR_DRIVER_U64] = MNL_TYPE_U64,
+	[RDMA_NLDEV_ATTR_STAT_COUNTER] = MNL_TYPE_NESTED,
+	[RDMA_NLDEV_ATTR_STAT_COUNTER_ENTRY] = MNL_TYPE_NESTED,
+	[RDMA_NLDEV_ATTR_STAT_COUNTER_ID] = MNL_TYPE_U32,
+	[RDMA_NLDEV_ATTR_STAT_HWCOUNTERS] = MNL_TYPE_NESTED,
+	[RDMA_NLDEV_ATTR_STAT_HWCOUNTER_ENTRY] = MNL_TYPE_NESTED,
+	[RDMA_NLDEV_ATTR_STAT_HWCOUNTER_ENTRY_NAME] = MNL_TYPE_NUL_STRING,
+	[RDMA_NLDEV_ATTR_STAT_HWCOUNTER_ENTRY_VALUE] = MNL_TYPE_U64,
 };
 
 int rd_attr_check(const struct nlattr *attr, int *typep)
-- 
2.20.1

[PATCH iproute2-next 3/8] rdma: Add get per-port counter mode support

[Leon Romanovsky]

From: Mark Zhang <markz@mellanox.com>

Add an interface to show which mode is in active. Examples:

$ rdma statistic qp mode
0/1: mlx5_0/1: qp auto off
1/1: mlx5_1/1: qp auto off
2/1: mlx5_2/1: qp auto type on
3/1: mlx5_3/1: qp auto off

$ rdma statistic qp mode link mlx5_0
0/1: mlx5_0/1: qp auto off

Signed-off-by: Mark Zhang <markz@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 rdma/stat.c  | 140 +++++++++++++++++++++++++++++++++++++++++++++++++++
 rdma/utils.c |   2 +
 2 files changed, 142 insertions(+)

diff --git a/rdma/stat.c b/rdma/stat.c
index 0c3abc99..f11252f7 100644
--- a/rdma/stat.c
+++ b/rdma/stat.c
@@ -18,13 +18,152 @@ static int stat_help(struct rd *rd)
 	pr_out("Usage: %s [ OPTIONS ] statistic { COMMAND | help }\n", rd->filename);
 	pr_out("       %s statistic OBJECT show\n", rd->filename);
 	pr_out("       %s statistic OBJECT show link [ DEV/PORT_INDEX ] [ FILTER-NAME FILTER-VALUE ]\n", rd->filename);
+	pr_out("       %s statistic OBJECT mode\n", rd->filename);
+	pr_out("where  OBJECT: = { qp }\n");
 	pr_out("Examples:\n");
 	pr_out("       %s statistic qp show\n", rd->filename);
 	pr_out("       %s statistic qp show link mlx5_2/1\n", rd->filename);
+	pr_out("       %s statistic qp mode\n", rd->filename);
+	pr_out("       %s statistic qp mode link mlx5_0\n", rd->filename);
 
 	return 0;
 }
 
+struct counter_param {
+	char *name;
+	uint32_t attr;
+};
+
+static struct counter_param auto_params[] = {
+	{ "type", RDMA_COUNTER_MASK_QP_TYPE, },
+	{ NULL },
+};
+
+static int prepare_auto_mode_str(struct nlattr **tb, uint32_t mask,
+				 char *output, int len)
+{
+	char s[] = "qp auto";
+	int i, outlen = strlen(s);
+
+	memset(output, 0, len);
+	snprintf(output, len, "%s", s);
+
+	if (mask) {
+		for (i = 0; auto_params[i].name != NULL; i++) {
+			if (mask & auto_params[i].attr) {
+				outlen += strlen(auto_params[i].name) + 1;
+				if (outlen >= len)
+					return -EINVAL;
+				strcat(output, " ");
+				strcat(output, auto_params[i].name);
+			}
+		}
+
+		if (outlen + strlen(" on") >= len)
+			return -EINVAL;
+		strcat(output, " on");
+	} else {
+		if (outlen + strlen(" off") >= len)
+			return -EINVAL;
+		strcat(output, " off");
+	}
+
+	return 0;
+}
+
+static int qp_link_get_mode_parse_cb(const struct nlmsghdr *nlh, void *data)
+{
+	struct nlattr *tb[RDMA_NLDEV_ATTR_MAX] = {};
+	uint32_t mode = 0, mask = 0;
+	char output[128] = {0};
+	struct rd *rd = data;
+	uint32_t idx, port;
+	const char *name;
+
+	mnl_attr_parse(nlh, 0, rd_attr_cb, tb);
+	if (!tb[RDMA_NLDEV_ATTR_DEV_INDEX] || !tb[RDMA_NLDEV_ATTR_DEV_NAME])
+		return MNL_CB_ERROR;
+
+	if (!tb[RDMA_NLDEV_ATTR_PORT_INDEX]) {
+		pr_err("This tool doesn't support switches yet\n");
+		return MNL_CB_ERROR;
+	}
+
+	idx = mnl_attr_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);
+	port = mnl_attr_get_u32(tb[RDMA_NLDEV_ATTR_PORT_INDEX]);
+	name = mnl_attr_get_str(tb[RDMA_NLDEV_ATTR_DEV_NAME]);
+	if (tb[RDMA_NLDEV_ATTR_STAT_MODE])
+		mode = mnl_attr_get_u32(tb[RDMA_NLDEV_ATTR_STAT_MODE]);
+
+	if (mode == RDMA_COUNTER_MODE_AUTO) {
+		if (!tb[RDMA_NLDEV_ATTR_STAT_AUTO_MODE_MASK])
+			return MNL_CB_ERROR;
+		mask = mnl_attr_get_u32(tb[RDMA_NLDEV_ATTR_STAT_AUTO_MODE_MASK]);
+		prepare_auto_mode_str(tb, mask, output, sizeof(output));
+	} else {
+		snprintf(output, sizeof(output), "qp auto off");
+	}
+
+	if (rd->json_output) {
+		jsonw_uint_field(rd->jw, "ifindex", idx);
+		jsonw_uint_field(rd->jw, "port", port);
+		jsonw_string_field(rd->jw, "mode", output);
+	} else {
+		pr_out("%u/%u: %s/%u: %s\n", idx, port, name, port, output);
+	}
+
+	return MNL_CB_OK;
+}
+
+static int stat_one_qp_link_get_mode(struct rd *rd)
+{
+	uint32_t seq;
+	int ret;
+
+	if (!rd->port_idx)
+		return 0;
+
+	rd_prepare_msg(rd, RDMA_NLDEV_CMD_STAT_GET,
+		       &seq, (NLM_F_REQUEST | NLM_F_ACK));
+
+	mnl_attr_put_u32(rd->nlh, RDMA_NLDEV_ATTR_DEV_INDEX, rd->dev_idx);
+	mnl_attr_put_u32(rd->nlh, RDMA_NLDEV_ATTR_PORT_INDEX, rd->port_idx);
+	/* Make RDMA_NLDEV_ATTR_STAT_MODE valid so that kernel knows
+	 * return only mode instead of all counters
+	 */
+	mnl_attr_put_u32(rd->nlh, RDMA_NLDEV_ATTR_STAT_MODE,
+			 RDMA_COUNTER_MODE_MANUAL);
+	mnl_attr_put_u32(rd->nlh, RDMA_NLDEV_ATTR_STAT_RES, RDMA_NLDEV_ATTR_RES_QP);
+	ret = rd_send_msg(rd);
+	if (ret)
+		return ret;
+
+	if (rd->json_output)
+		jsonw_start_object(rd->jw);
+	ret = rd_recv_msg(rd, qp_link_get_mode_parse_cb, rd, seq);
+	if (rd->json_output)
+		jsonw_end_object(rd->jw);
+
+	return ret;
+}
+
+static int stat_qp_link_get_mode(struct rd* rd)
+{
+	return rd_exec_link(rd, stat_one_qp_link_get_mode, false);
+}
+
+static int stat_qp_get_mode(struct rd *rd)
+{
+	const struct rd_cmd cmds[] = {
+		{ NULL,		stat_qp_link_get_mode },
+		{ "link",	stat_qp_link_get_mode },
+		{ "help",	stat_help },
+		{ 0 }
+	};
+
+	return rd_exec_cmd(rd, cmds, "parameter");
+}
+
 static int res_show_hwcounters(struct rd *rd, struct nlattr *hwc_table)
 {
 	struct nlattr *nla_entry;
@@ -243,6 +382,7 @@ static int stat_qp(struct rd *rd)
 		{ NULL,		stat_qp_show },
 		{ "show",	stat_qp_show },
 		{ "list",	stat_qp_show },
+		{ "mode",	stat_qp_get_mode },
 		{ "help",	stat_help },
 		{ 0 }
 	};
diff --git a/rdma/utils.c b/rdma/utils.c
index ff781517..5ad6c961 100644
--- a/rdma/utils.c
+++ b/rdma/utils.c
@@ -442,6 +442,8 @@ static const enum mnl_attr_data_type nldev_policy[RDMA_NLDEV_ATTR_MAX] = {
 	[RDMA_NLDEV_ATTR_STAT_HWCOUNTER_ENTRY] = MNL_TYPE_NESTED,
 	[RDMA_NLDEV_ATTR_STAT_HWCOUNTER_ENTRY_NAME] = MNL_TYPE_NUL_STRING,
 	[RDMA_NLDEV_ATTR_STAT_HWCOUNTER_ENTRY_VALUE] = MNL_TYPE_U64,
+	[RDMA_NLDEV_ATTR_STAT_MODE] = MNL_TYPE_U32,
+	[RDMA_NLDEV_ATTR_STAT_RES] = MNL_TYPE_U32,
 };
 
 int rd_attr_check(const struct nlattr *attr, int *typep)
-- 
2.20.1

[PATCH iproute2-next 4/8] rdma: Add rdma statistic counter per-port auto mode support

[Leon Romanovsky]

From: Mark Zhang <markz@mellanox.com>

With per-QP statistic counter support, a user is allowed to monitor
specific QPs categories, which are bound to/unbound from counters
dynamically allocated/deallocated.

In per-port "auto" mode, QPs are bound to counters automatically
according to common criteria. For example a per "type"(qp type)
scheme, where in each process all QPs have same qp type are bind
automatically to a single counter.
Currently only "type" (qp type) is supported. Examples:

$ rdma statistic qp set link mlx5_2/1 auto type on
$ rdma statistic qp set link mlx5_2/1 auto off

Signed-off-by: Mark Zhang <markz@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 rdma/stat.c  | 103 +++++++++++++++++++++++++++++++++++++++++++++++++++
 rdma/utils.c |   1 +
 2 files changed, 104 insertions(+)

diff --git a/rdma/stat.c b/rdma/stat.c
index f11252f7..aec0e837 100644
--- a/rdma/stat.c
+++ b/rdma/stat.c
@@ -19,12 +19,17 @@ static int stat_help(struct rd *rd)
 	pr_out("       %s statistic OBJECT show\n", rd->filename);
 	pr_out("       %s statistic OBJECT show link [ DEV/PORT_INDEX ] [ FILTER-NAME FILTER-VALUE ]\n", rd->filename);
 	pr_out("       %s statistic OBJECT mode\n", rd->filename);
+	pr_out("       %s statistic OBJECT set COUNTER_SCOPE [DEV/PORT_INDEX] auto {CRITERIA | off}\n", rd->filename);
 	pr_out("where  OBJECT: = { qp }\n");
+	pr_out("       CRITERIA : = { type }\n");
+	pr_out("       COUNTER_SCOPE: = { link | dev }\n");
 	pr_out("Examples:\n");
 	pr_out("       %s statistic qp show\n", rd->filename);
 	pr_out("       %s statistic qp show link mlx5_2/1\n", rd->filename);
 	pr_out("       %s statistic qp mode\n", rd->filename);
 	pr_out("       %s statistic qp mode link mlx5_0\n", rd->filename);
+	pr_out("       %s statistic qp set link mlx5_2/1 auto type on\n", rd->filename);
+	pr_out("       %s statistic qp set link mlx5_2/1 auto off\n", rd->filename);
 
 	return 0;
 }
@@ -376,6 +381,103 @@ static int stat_qp_show(struct rd *rd)
 	return rd_exec_cmd(rd, cmds, "parameter");
 }
 
+static int qp_set_link_auto_parse_cb(const struct nlmsghdr *nlh, void *data)
+{
+	return MNL_CB_OK;
+}
+
+static int stat_qp_set_link_auto_sendmsg(struct rd *rd, uint32_t mask)
+{
+	uint32_t seq;
+	int ret;
+
+	rd_prepare_msg(rd, RDMA_NLDEV_CMD_STAT_SET,
+		       &seq, (NLM_F_REQUEST | NLM_F_ACK));
+
+	mnl_attr_put_u32(rd->nlh, RDMA_NLDEV_ATTR_DEV_INDEX, rd->dev_idx);
+	mnl_attr_put_u32(rd->nlh, RDMA_NLDEV_ATTR_PORT_INDEX, rd->port_idx);
+	mnl_attr_put_u32(rd->nlh, RDMA_NLDEV_ATTR_STAT_RES, RDMA_NLDEV_ATTR_RES_QP);
+	mnl_attr_put_u32(rd->nlh, RDMA_NLDEV_ATTR_STAT_MODE,
+			 RDMA_COUNTER_MODE_AUTO);
+	mnl_attr_put_u32(rd->nlh, RDMA_NLDEV_ATTR_STAT_AUTO_MODE_MASK, mask);
+
+	ret = rd_send_msg(rd);
+	if (ret)
+		return ret;
+
+	if (rd->json_output)
+		jsonw_start_object(rd->jw);
+	ret = rd_recv_msg(rd, qp_set_link_auto_parse_cb, rd, seq);
+	if (rd->json_output)
+		jsonw_end_object(rd->jw);
+
+	return ret;
+}
+
+static int stat_one_qp_set_link_auto_off(struct rd *rd)
+{
+	return stat_qp_set_link_auto_sendmsg(rd, 0);
+}
+
+static int stat_one_qp_set_auto_type_on(struct rd *rd)
+{
+	return stat_qp_set_link_auto_sendmsg(rd, RDMA_COUNTER_MASK_QP_TYPE);
+}
+
+static int stat_one_qp_set_link_auto_type(struct rd *rd)
+{
+	const struct rd_cmd cmds[] = {
+		{ NULL,		stat_help },
+		{ "on",		stat_one_qp_set_auto_type_on },
+		{ 0 }
+	};
+
+	return rd_exec_cmd(rd, cmds, "parameter");
+}
+
+static int stat_one_qp_set_link_auto(struct rd *rd)
+{
+	const struct rd_cmd cmds[] = {
+		{ NULL,		stat_one_qp_link_get_mode },
+		{ "off",	stat_one_qp_set_link_auto_off },
+		{ "type", 	stat_one_qp_set_link_auto_type },
+		{ 0 }
+	};
+
+	return rd_exec_cmd(rd, cmds, "parameter");
+}
+
+static int stat_one_qp_set_link(struct rd *rd)
+{
+	const struct rd_cmd cmds[] = {
+		{ NULL,		stat_one_qp_link_get_mode },
+		{ "auto",	stat_one_qp_set_link_auto },
+		{ 0 }
+	};
+
+	if (!rd->port_idx)
+		return 0;
+
+	return rd_exec_cmd(rd, cmds, "parameter");
+}
+
+static int stat_qp_set_link(struct rd *rd)
+{
+	return rd_exec_link(rd, stat_one_qp_set_link, false);
+}
+
+static int stat_qp_set(struct rd *rd)
+{
+	const struct rd_cmd cmds[] = {
+		{ NULL,		stat_help },
+		{ "link",	stat_qp_set_link },
+		{ "help",	stat_help },
+		{ 0 }
+	};
+
+	return rd_exec_cmd(rd, cmds, "parameter");
+}
+
 static int stat_qp(struct rd *rd)
 {
 	const struct rd_cmd cmds[] =  {
@@ -383,6 +485,7 @@ static int stat_qp(struct rd *rd)
 		{ "show",	stat_qp_show },
 		{ "list",	stat_qp_show },
 		{ "mode",	stat_qp_get_mode },
+		{ "set",	stat_qp_set },
 		{ "help",	stat_help },
 		{ 0 }
 	};
diff --git a/rdma/utils.c b/rdma/utils.c
index 5ad6c961..1fda2879 100644
--- a/rdma/utils.c
+++ b/rdma/utils.c
@@ -444,6 +444,7 @@ static const enum mnl_attr_data_type nldev_policy[RDMA_NLDEV_ATTR_MAX] = {
 	[RDMA_NLDEV_ATTR_STAT_HWCOUNTER_ENTRY_VALUE] = MNL_TYPE_U64,
 	[RDMA_NLDEV_ATTR_STAT_MODE] = MNL_TYPE_U32,
 	[RDMA_NLDEV_ATTR_STAT_RES] = MNL_TYPE_U32,
+	[RDMA_NLDEV_ATTR_STAT_AUTO_MODE_MASK] = MNL_TYPE_U32,
 };
 
 int rd_attr_check(const struct nlattr *attr, int *typep)
-- 
2.20.1

[PATCH iproute2-next 5/8] rdma: Make get_port_from_argv() returns valid port in strict port mode

[Leon Romanovsky]

From: Mark Zhang <markz@mellanox.com>

When strict_port is set, make get_port_from_argv() returns failure if
no valid port is specified.

Signed-off-by: Mark Zhang <markz@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 rdma/utils.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/rdma/utils.c b/rdma/utils.c
index 1fda2879..8dc06fc6 100644
--- a/rdma/utils.c
+++ b/rdma/utils.c
@@ -56,7 +56,7 @@ bool rd_no_arg(struct rd *rd)
  * mlx5_1/1    | 1          | false
  * mlx5_1/-    | 0          | false
  *
- * In strict mode, /- will return error.
+ * In strict port mode, a non-0 port must be provided
  */
 static int get_port_from_argv(struct rd *rd, uint32_t *port,
 			      bool *is_dump_all, bool strict_port)
@@ -64,7 +64,7 @@ static int get_port_from_argv(struct rd *rd, uint32_t *port,
 	char *slash;
 
 	*port = 0;
-	*is_dump_all = true;
+	*is_dump_all = strict_port ? false : true;
 
 	slash = strchr(rd_argv(rd), '/');
 	/* if no port found, return 0 */
@@ -83,6 +83,9 @@ static int get_port_from_argv(struct rd *rd, uint32_t *port,
 		if (!*port && strlen(slash))
 			return -EINVAL;
 	}
+	if (strict_port && (*port == 0))
+		return -EINVAL;
+
 	return 0;
 }
 
-- 
2.20.1

[PATCH iproute2-next 6/8] rdma: Add stat manual mode support

[Leon Romanovsky]

From: Mark Zhang <markz@mellanox.com>

In manual mode a QP can be manually bound to a counter. If counter
is not specified that kernel will allocate one. And in unbind if
lqpn is not specified then all QPs on this counter will be unbound.
The manual and auto mode are mutual-exclusive.

Examples:
$ rdma statistic qp bind link mlx5_2/1 lqpn 178
$ rdma statistic qp bind link mlx5_2/1 lqpn 178 cntn 4
$ rdma statistic qp unbind link mlx5_2/1 cntn 4
$ rdma statistic qp unbind link mlx5_2/1 cntn 4 lqpn 178

Signed-off-by: Mark Zhang <markz@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 rdma/stat.c | 218 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 218 insertions(+)

diff --git a/rdma/stat.c b/rdma/stat.c
index aec0e837..c5395692 100644
--- a/rdma/stat.c
+++ b/rdma/stat.c
@@ -20,6 +20,8 @@ static int stat_help(struct rd *rd)
 	pr_out("       %s statistic OBJECT show link [ DEV/PORT_INDEX ] [ FILTER-NAME FILTER-VALUE ]\n", rd->filename);
 	pr_out("       %s statistic OBJECT mode\n", rd->filename);
 	pr_out("       %s statistic OBJECT set COUNTER_SCOPE [DEV/PORT_INDEX] auto {CRITERIA | off}\n", rd->filename);
+	pr_out("       %s statistic OBJECT bind COUNTER_SCOPE [DEV/PORT_INDEX] [OBJECT-ID] [COUNTER-ID]\n", rd->filename);
+	pr_out("       %s statistic OBJECT unbind COUNTER_SCOPE [DEV/PORT_INDEX] [COUNTER-ID]\n", rd->filename);
 	pr_out("where  OBJECT: = { qp }\n");
 	pr_out("       CRITERIA : = { type }\n");
 	pr_out("       COUNTER_SCOPE: = { link | dev }\n");
@@ -30,6 +32,10 @@ static int stat_help(struct rd *rd)
 	pr_out("       %s statistic qp mode link mlx5_0\n", rd->filename);
 	pr_out("       %s statistic qp set link mlx5_2/1 auto type on\n", rd->filename);
 	pr_out("       %s statistic qp set link mlx5_2/1 auto off\n", rd->filename);
+	pr_out("       %s statistic qp bind link mlx5_2/1 lqpn 178\n", rd->filename);
+	pr_out("       %s statistic qp bind link mlx5_2/1 lqpn 178 cntn 4\n", rd->filename);
+	pr_out("       %s statistic qp unbind link mlx5_2/1 cntn 4\n", rd->filename);
+	pr_out("       %s statistic qp unbind link mlx5_2/1 cntn 4 lqpn 178\n", rd->filename);
 
 	return 0;
 }
@@ -478,6 +484,216 @@ static int stat_qp_set(struct rd *rd)
 	return rd_exec_cmd(rd, cmds, "parameter");
 }
 
+static int qp_bind_unbind_parse_cb(const struct nlmsghdr *nlh, void *data)
+{
+	struct nlattr *tb[RDMA_NLDEV_ATTR_MAX] = {};
+
+	mnl_attr_parse(nlh, 0, rd_attr_cb, tb);
+	if (!tb[RDMA_NLDEV_ATTR_DEV_INDEX] || !tb[RDMA_NLDEV_ATTR_DEV_NAME] ||
+	    !tb[RDMA_NLDEV_ATTR_RES_LQPN] || !tb[RDMA_NLDEV_ATTR_STAT_COUNTER_ID])
+		return MNL_CB_ERROR;
+
+	return MNL_CB_OK;
+}
+
+static int stat_get_arg(struct rd *rd, const char *arg)
+{
+	int value = 0;
+	char *endp;
+
+	if (strcmpx(rd_argv(rd), arg) != 0)
+		return -EINVAL;
+
+	rd_arg_inc(rd);
+	value = strtol(rd_argv(rd), &endp, 10);
+	rd_arg_inc(rd);
+
+	return value;
+}
+
+static int stat_one_qp_bind(struct rd *rd)
+{
+	int lqpn = 0, cntn = 0, ret;
+	uint32_t seq;
+
+	if (rd_no_arg(rd)) {
+		stat_help(rd);
+		return -EINVAL;
+	}
+
+	ret = rd_build_filter(rd, stat_valid_filters);
+	if (ret)
+		return ret;
+
+	lqpn = stat_get_arg(rd, "lqpn");
+
+	rd_prepare_msg(rd, RDMA_NLDEV_CMD_STAT_SET,
+		       &seq, (NLM_F_REQUEST | NLM_F_ACK));
+
+	mnl_attr_put_u32(rd->nlh, RDMA_NLDEV_ATTR_STAT_MODE,
+			 RDMA_COUNTER_MODE_MANUAL);
+
+	mnl_attr_put_u32(rd->nlh, RDMA_NLDEV_ATTR_STAT_RES, RDMA_NLDEV_ATTR_RES_QP);
+	mnl_attr_put_u32(rd->nlh, RDMA_NLDEV_ATTR_DEV_INDEX, rd->dev_idx);
+	mnl_attr_put_u32(rd->nlh, RDMA_NLDEV_ATTR_PORT_INDEX, rd->port_idx);
+	mnl_attr_put_u32(rd->nlh, RDMA_NLDEV_ATTR_RES_LQPN, lqpn);
+
+	if (rd_argc(rd)) {
+		cntn = stat_get_arg(rd, "cntn");
+		mnl_attr_put_u32(rd->nlh, RDMA_NLDEV_ATTR_STAT_COUNTER_ID,
+				 cntn);
+	}
+
+	ret = rd_send_msg(rd);
+	if (ret)
+		return ret;
+
+	if (rd->json_output)
+		jsonw_start_object(rd->jw);
+	ret = rd_recv_msg(rd, qp_bind_unbind_parse_cb, rd, seq);
+	if (rd->json_output)
+		jsonw_end_object(rd->jw);
+
+	return ret;
+}
+
+static int do_stat_qp_unbind_lqpn(struct rd *rd, uint32_t cntn, uint32_t lqpn)
+{
+	uint32_t seq;
+	int ret;
+
+	rd_prepare_msg(rd, RDMA_NLDEV_CMD_STAT_DEL,
+		       &seq, (NLM_F_REQUEST | NLM_F_ACK));
+
+	mnl_attr_put_u32(rd->nlh, RDMA_NLDEV_ATTR_STAT_MODE,
+			 RDMA_COUNTER_MODE_MANUAL);
+	mnl_attr_put_u32(rd->nlh, RDMA_NLDEV_ATTR_STAT_RES, RDMA_NLDEV_ATTR_RES_QP);
+	mnl_attr_put_u32(rd->nlh, RDMA_NLDEV_ATTR_DEV_INDEX, rd->dev_idx);
+	mnl_attr_put_u32(rd->nlh, RDMA_NLDEV_ATTR_PORT_INDEX, rd->port_idx);
+	mnl_attr_put_u32(rd->nlh, RDMA_NLDEV_ATTR_STAT_COUNTER_ID, cntn);
+	mnl_attr_put_u32(rd->nlh, RDMA_NLDEV_ATTR_RES_LQPN, lqpn);
+
+	ret = rd_send_msg(rd);
+	if (ret)
+		return ret;
+
+	return rd_recv_msg(rd, qp_bind_unbind_parse_cb, rd, seq);
+}
+
+static int stat_get_counter_parse_cb(const struct nlmsghdr *nlh, void *data)
+{
+	struct nlattr *tb[RDMA_NLDEV_ATTR_MAX] = {};
+	struct nlattr *nla_table, *nla_entry;
+	struct rd *rd = data;
+	uint32_t lqpn, cntn;
+	int err;
+
+	mnl_attr_parse(nlh, 0, rd_attr_cb, tb);
+
+	if (!tb[RDMA_NLDEV_ATTR_STAT_COUNTER_ID])
+		return MNL_CB_ERROR;
+	cntn = mnl_attr_get_u32(tb[RDMA_NLDEV_ATTR_STAT_COUNTER_ID]);
+
+	nla_table = tb[RDMA_NLDEV_ATTR_RES_QP];
+	if (!nla_table)
+		return MNL_CB_ERROR;
+
+	mnl_attr_for_each_nested(nla_entry, nla_table) {
+		struct nlattr *nla_line[RDMA_NLDEV_ATTR_MAX] = {};
+
+		err = mnl_attr_parse_nested(nla_entry, rd_attr_cb, nla_line);
+		if (err != MNL_CB_OK)
+			return -EINVAL;
+
+		if (!nla_line[RDMA_NLDEV_ATTR_RES_LQPN])
+			return -EINVAL;
+
+		lqpn = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_LQPN]);
+		err = do_stat_qp_unbind_lqpn(rd, cntn, lqpn);
+		if (err)
+			return MNL_CB_ERROR;
+	}
+
+	return MNL_CB_OK;
+}
+
+static int stat_one_qp_unbind(struct rd *rd)
+{
+	int flags = NLM_F_REQUEST | NLM_F_ACK, ret;
+	char buf[MNL_SOCKET_BUFFER_SIZE];
+	int lqpn = 0, cntn = 0;
+	unsigned int portid;
+	uint32_t seq;
+
+	ret = rd_build_filter(rd, stat_valid_filters);
+	if (ret)
+		return ret;
+
+	cntn = stat_get_arg(rd, "cntn");
+	if (rd_argc(rd)) {
+		lqpn = stat_get_arg(rd, "lqpn");
+		return do_stat_qp_unbind_lqpn(rd, cntn, lqpn);
+	}
+
+	rd_prepare_msg(rd, RDMA_NLDEV_CMD_STAT_GET, &seq, flags);
+	mnl_attr_put_u32(rd->nlh, RDMA_NLDEV_ATTR_DEV_INDEX, rd->dev_idx);
+	mnl_attr_put_u32(rd->nlh, RDMA_NLDEV_ATTR_PORT_INDEX, rd->port_idx);
+	mnl_attr_put_u32(rd->nlh, RDMA_NLDEV_ATTR_STAT_COUNTER_ID, cntn);
+	ret = rd_send_msg(rd);
+	if (ret)
+		return ret;
+
+
+	/* Can't use rd_recv_msg() since the callback also calls it (recursively),
+	 * then rd_recv_msg() always return -1 here
+	 */
+	portid = mnl_socket_get_portid(rd->nl);
+	ret = mnl_socket_recvfrom(rd->nl, buf, sizeof(buf));
+	if (ret <= 0)
+		return ret;
+
+	ret = mnl_cb_run(buf, ret, seq, portid, stat_get_counter_parse_cb, rd);
+	mnl_socket_close(rd->nl);
+	if (ret != MNL_CB_OK)
+		return ret;
+
+	return 0;
+}
+
+static int stat_qp_bind_link(struct rd *rd)
+{
+	return rd_exec_link(rd, stat_one_qp_bind, true);
+}
+
+static int stat_qp_bind(struct rd *rd)
+{
+	const struct rd_cmd cmds[] = {
+		{ NULL,		stat_help },
+		{ "link",	stat_qp_bind_link },
+		{ "help",	stat_help },
+		{ 0 },
+	};
+
+	return rd_exec_cmd(rd, cmds, "parameter");
+}
+
+static int stat_qp_unbind_link(struct rd *rd)
+{
+	return rd_exec_link(rd, stat_one_qp_unbind, true);
+}
+
+static int stat_qp_unbind(struct rd *rd)
+{
+	const struct rd_cmd cmds[] = {
+		{ NULL,		stat_help },
+		{ "link",	stat_qp_unbind_link },
+		{ "help",	stat_help },
+		{ 0 },
+	};
+
+	return rd_exec_cmd(rd, cmds, "parameter");
+}
+
 static int stat_qp(struct rd *rd)
 {
 	const struct rd_cmd cmds[] =  {
@@ -486,6 +702,8 @@ static int stat_qp(struct rd *rd)
 		{ "list",	stat_qp_show },
 		{ "mode",	stat_qp_get_mode },
 		{ "set",	stat_qp_set },
+		{ "bind",	stat_qp_bind },
+		{ "unbind",	stat_qp_unbind },
 		{ "help",	stat_help },
 		{ 0 }
 	};
-- 
2.20.1

[PATCH iproute2-next 7/8] rdma: Add default counter show support

[Leon Romanovsky]

From: Mark Zhang <markz@mellanox.com>

Show default counter statistics, which are same through the sysfs
interface: /sys/class/infiniband/<dev>/ports/<port>/hw_counters/

Example:
$ rdma stat show link mlx5_2/1
link mlx5_2/1 rx_write_requests 8 rx_read_requests 4 rx_atomic_requests 0 out_of_buffer 0 out_of_sequence 0 duplicate_request 0 rnr_nak_retry_err 0 packet_seq_err 0 implied_nak_seq_err 0 local_ack_timeout_err 0 resp_local_length_error 0 resp_cqe_error 0 req_cqe_error 0 req_remote_invalid_request 0 req_remote_access_errors 0 resp_remote_access_errors 0 resp_cqe_flush_error 0 req_cqe_flush_error 0 rp_cnp_ignored 0 rp_cnp_handled 0 np_ecn_marked_roce_packets 0 np_cnp_sent 0 rx_icrc_encapsulated 0

Signed-off-by: Mark Zhang <markz@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 rdma/stat.c | 80 ++++++++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 79 insertions(+), 1 deletion(-)

diff --git a/rdma/stat.c b/rdma/stat.c
index c5395692..cf2f0a02 100644
--- a/rdma/stat.c
+++ b/rdma/stat.c
@@ -22,6 +22,8 @@ static int stat_help(struct rd *rd)
 	pr_out("       %s statistic OBJECT set COUNTER_SCOPE [DEV/PORT_INDEX] auto {CRITERIA | off}\n", rd->filename);
 	pr_out("       %s statistic OBJECT bind COUNTER_SCOPE [DEV/PORT_INDEX] [OBJECT-ID] [COUNTER-ID]\n", rd->filename);
 	pr_out("       %s statistic OBJECT unbind COUNTER_SCOPE [DEV/PORT_INDEX] [COUNTER-ID]\n", rd->filename);
+	pr_out("       %s statistic show\n", rd->filename);
+	pr_out("       %s statistic show link [ DEV/PORT_INDEX ]\n", rd->filename);
 	pr_out("where  OBJECT: = { qp }\n");
 	pr_out("       CRITERIA : = { type }\n");
 	pr_out("       COUNTER_SCOPE: = { link | dev }\n");
@@ -36,6 +38,8 @@ static int stat_help(struct rd *rd)
 	pr_out("       %s statistic qp bind link mlx5_2/1 lqpn 178 cntn 4\n", rd->filename);
 	pr_out("       %s statistic qp unbind link mlx5_2/1 cntn 4\n", rd->filename);
 	pr_out("       %s statistic qp unbind link mlx5_2/1 cntn 4 lqpn 178\n", rd->filename);
+	pr_out("       %s statistic show\n", rd->filename);
+	pr_out("       %s statistic show link mlx5_2/1\n", rd->filename);
 
 	return 0;
 }
@@ -711,10 +715,84 @@ static int stat_qp(struct rd *rd)
 	return rd_exec_cmd(rd, cmds, "parameter");
 }
 
+static int stat_show_parse_cb(const struct nlmsghdr *nlh, void *data)
+{
+	struct nlattr *tb[RDMA_NLDEV_ATTR_MAX] = {};
+	struct rd *rd = data;
+	const char *name;
+	uint32_t port;
+	int ret;
+
+	mnl_attr_parse(nlh, 0, rd_attr_cb, tb);
+	if (!tb[RDMA_NLDEV_ATTR_DEV_INDEX] || !tb[RDMA_NLDEV_ATTR_DEV_NAME] ||
+	    !tb[RDMA_NLDEV_ATTR_PORT_INDEX] ||
+	    !tb[RDMA_NLDEV_ATTR_STAT_HWCOUNTERS])
+		return MNL_CB_ERROR;
+
+	name = mnl_attr_get_str(tb[RDMA_NLDEV_ATTR_DEV_NAME]);
+	port = mnl_attr_get_u32(tb[RDMA_NLDEV_ATTR_PORT_INDEX]);
+	if (rd->json_output) {
+		jsonw_string_field(rd->jw, "ifname", name);
+		jsonw_uint_field(rd->jw, "port", port);
+	} else {
+		pr_out("link %s/%u ", name, port);
+	}
+
+	ret = res_show_hwcounters(rd, tb[RDMA_NLDEV_ATTR_STAT_HWCOUNTERS]);
+
+	if (!rd->json_output)
+		pr_out("\n");
+	return ret;
+}
+
+static int stat_show_one_link(struct rd *rd)
+{
+	int flags = NLM_F_REQUEST | NLM_F_ACK;
+	uint32_t seq;
+	int ret;
+
+	if (!rd->port_idx)
+		return 0;
+
+	rd_prepare_msg(rd, RDMA_NLDEV_CMD_STAT_GET, &seq,  flags);
+	mnl_attr_put_u32(rd->nlh, RDMA_NLDEV_ATTR_DEV_INDEX, rd->dev_idx);
+	mnl_attr_put_u32(rd->nlh, RDMA_NLDEV_ATTR_PORT_INDEX, rd->port_idx);
+	ret = rd_send_msg(rd);
+	if (ret)
+		return ret;
+
+	if (rd->json_output)
+		jsonw_start_object(rd->jw);
+	ret = rd_recv_msg(rd, stat_show_parse_cb, rd, seq);
+	if (rd->json_output)
+		jsonw_end_object(rd->jw);
+
+	return ret;
+}
+
+static int stat_show_link(struct rd *rd)
+{
+	return rd_exec_link(rd, stat_show_one_link, false);
+}
+
+static int stat_show(struct rd *rd)
+{
+	const struct rd_cmd cmds[] = {
+		{ NULL,		stat_show_link },
+		{ "link",	stat_show_link },
+		{ "help",	stat_help },
+		{ 0 }
+	};
+
+	return rd_exec_cmd(rd, cmds, "parameter");
+}
+
 int cmd_stat(struct rd *rd)
 {
 	const struct rd_cmd cmds[] =  {
-		{ NULL,		stat_help },
+		{ NULL,		stat_show },
+		{ "show",	stat_show },
+		{ "list",	stat_show },
 		{ "help",	stat_help },
 		{ "qp",		stat_qp },
 		{ 0 }
-- 
2.20.1

[PATCH iproute2-next 8/8] rdma: Document counter statistic

[Leon Romanovsky]

From: Mark Zhang <markz@mellanox.com>

Add document of accessing the QP counter, including bind/unbind a QP
to a counter manually or automatically, and dump counter statistics.

Signed-off-by: Mark Zhang <markz@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 man/man8/rdma-dev.8       |   1 +
 man/man8/rdma-link.8      |   1 +
 man/man8/rdma-resource.8  |   1 +
 man/man8/rdma-statistic.8 | 170 ++++++++++++++++++++++++++++++++++++++
 man/man8/rdma.8           |   5 ++
 5 files changed, 178 insertions(+)
 create mode 100644 man/man8/rdma-statistic.8

diff --git a/man/man8/rdma-dev.8 b/man/man8/rdma-dev.8
index 069f4717..f1b81033 100644
--- a/man/man8/rdma-dev.8
+++ b/man/man8/rdma-dev.8
@@ -63,6 +63,7 @@ Renames the mlx5_3 device to rdma_0.
 .BR rdma (8),
 .BR rdma-link (8),
 .BR rdma-resource (8),
+.BR rdma-statistic (8),
 .br
 
 .SH AUTHOR
diff --git a/man/man8/rdma-link.8 b/man/man8/rdma-link.8
index b3b40de7..32f80228 100644
--- a/man/man8/rdma-link.8
+++ b/man/man8/rdma-link.8
@@ -97,6 +97,7 @@ Removes RXE link rxe_eth0
 .BR rdma (8),
 .BR rdma-dev (8),
 .BR rdma-resource (8),
+.BR rdma-statistic (8),
 .br
 
 .SH AUTHOR
diff --git a/man/man8/rdma-resource.8 b/man/man8/rdma-resource.8
index 40b073db..05030d0a 100644
--- a/man/man8/rdma-resource.8
+++ b/man/man8/rdma-resource.8
@@ -103,6 +103,7 @@ Show CQs belonging to pid 30489
 .BR rdma (8),
 .BR rdma-dev (8),
 .BR rdma-link (8),
+.BR rdma-statistic (8),
 .br
 
 .SH AUTHOR
diff --git a/man/man8/rdma-statistic.8 b/man/man8/rdma-statistic.8
new file mode 100644
index 00000000..3a48ae8d
--- /dev/null
+++ b/man/man8/rdma-statistic.8
@@ -0,0 +1,170 @@
+.TH RDMA\-STATISTIC 8 "17 Mar 2019" "iproute2" "Linux"
+.SH NAME
+rdma-statistic \- RDMA statistic counter configuration
+.SH SYNOPSIS
+.sp
+.ad l
+.in +8
+.ti -8
+.B rdma
+.RI "[ " OPTIONS " ]"
+.B statistic
+.RI  " { " COMMAND " | "
+.BR help " }"
+.sp
+
+.ti -8
+.B rdma statistic
+.RI "[ " OBJECT " ]"
+.B show
+
+.ti -8
+.B rdma statistic
+.RI "[ " OBJECT " ]"
+.B show link
+.RI "[ " DEV/PORT_INDX " ]"
+
+.ti -8
+.B rdma statistic
+.IR OBJECT
+.B mode
+
+.ti -8
+.B rdma statistic
+.IR OBJECT
+.B set
+.IR COUNTER_SCOPE
+.RI "[ " DEV/PORT_INDEX "]"
+.B auto
+.RI "{ " CRITERIA " | "
+.BR off " }"
+
+.ti -8
+.B rdma statistic
+.IR OBJECT
+.B bind
+.IR COUNTER_SCOPE
+.RI "[ " DEV/PORT_INDEX "]"
+.RI "[ " OBJECT-ID " ]"
+.RI "[ " COUNTER-ID " ]"
+
+.ti -8
+.B rdma statistic
+.IR OBJECT
+.B unbind
+.IR COUNTER_SCOPE
+.RI "[ " DEV/PORT_INDEX "]"
+.RI "[ " COUNTER-ID " ]"
+.RI "[ " OBJECT-ID " ]"
+
+.ti -8
+.IR COUNTER_SCOPE " := "
+.RB "{ " link " | " dev " }"
+
+.ti -8
+.IR OBJECT " := "
+.RB "{ " qp " }"
+
+.ti -8
+.IR CRITERIA " := "
+.RB "{ " type " }"
+
+.SH "DESCRIPTION"
+.SS rdma statistic [object] show - Queries the specified RDMA device for RDMA and driver-specific statistics. Show the default counter if object is not specified
+
+.PP
+.I "DEV"
+- specifies counters on this RDMA device to show.
+
+.I "PORT_INDEX"
+- specifies counters on this RDMA port to show.
+
+.SS rdma statistic <object> set - configure counter statistic auto-mode for a specific device/port
+In auto mode all objects belong to one category are bind automatically to a single counter set.
+
+.SS rdma statistic <object> bind - manually bind an object (e.g., a qp) with a counter
+When bound the statistics of this object are available in this counter.
+
+.SS rdma statistic <object> unbind - manually unbind an object (e.g., a qp) from the counter previously bound
+When unbound the statistics of this object are no longer available in this counter; And if object id is not specified then all objects on this counter will be unbound.
+
+.I "LQPN"
+- specifies the qp number to be bound/unbind.
+
+.I "COUNTER-ID"
+- specifies the id of the counter to be bound.
+If this argument is omitted then a new counter will be allocated.
+
+.SH "EXAMPLES"
+.PP
+rdma statistic show
+.RS 4
+Shows the state of the default counter of all RDMA devices on the system.
+.RE
+.PP
+rdma statistic show link mlx5_2/1
+.RS 4
+Shows the state of the default counter of specified RDMA port
+.RE
+.PP
+rdma statistic qp show
+.RS 4
+Shows the state of all qp counters of all RDMA devices on the system.
+.RE
+.PP
+rdma statistic qp show link mlx5_2/1
+.RS 4
+Shows the state of all qp counters of specified RDMA port.
+.RE
+.PP
+rdma statistic qp show link mlx5_2 pid 30489
+.RS 4
+Shows the state of all qp counters of specified RDMA port and belonging to pid 30489
+.RE
+.PP
+rdma statistic qp mode
+.RS 4
+List current counter mode on all deivces
+.RE
+.PP
+rdma statistic qp mode link mlx5_2/1
+.RS 4
+List current counter mode of deivce mlx5_2 port 1
+.RE
+.PP
+rdma statistic qp set link mlx5_2/1 auto type on
+.RS 4
+On device mlx5_2 port 1, for each new QP bind it with a counter automatically. Per counter for QPs with same qp type in each process. Currently only "type" is supported.
+.RE
+.PP
+rdma statistic qp set link mlx5_2/1 auto off
+.RS 4
+Turn-off auto mode on device mlx5_2 port 1. The allocated counters can be manually accessed.
+.RE
+.PP
+rdma statistic qp bind link mlx5_2/1 lqpn 178
+.RS 4
+On device mlx5_2 port 1, allocate a counter and bind the specified qp on it
+.RE
+.PP
+rdma statistic qp unbind link mlx5_2/1 cntn 4 lqpn 178
+.RS 4
+On device mlx5_2 port 1, bind the specified qp on the specified counter
+.RE
+.PP
+rdma statistic qp unbind link mlx5_2/1 cntn 4
+.RS 4
+On device mlx5_2 port 1, unbind all QPs on the specified counter. After that this counter will be released automatically by the kernel.
+
+.RE
+.PP
+
+.SH SEE ALSO
+.BR rdma (8),
+.BR rdma-dev (8),
+.BR rdma-link (8),
+.BR rdma-resource (8),
+.br
+
+.SH AUTHOR
+Mark Zhang <markz@mellanox.com>
diff --git a/man/man8/rdma.8 b/man/man8/rdma.8
index b2b5aef8..63a2dd21 100644
--- a/man/man8/rdma.8
+++ b/man/man8/rdma.8
@@ -70,6 +70,10 @@ Generate JSON output.
 .B link
 - RDMA port related.
 
+.TP
+.B statistic
+- RDMA counter statistic related.
+
 .PP
 The names of all objects may be written in full or
 abbreviated form, for example
@@ -107,6 +111,7 @@ Exit status is 0 if command was successful or a positive integer upon failure.
 .BR rdma-dev (8),
 .BR rdma-link (8),
 .BR rdma-resource (8),
+.BR rdma-statistic (8),
 .br
 
 .SH REPORTING BUGS
-- 
2.20.1