[PATCH iproute2 1/5] rdma: Add basic infrastructure for RDMA tool

[Leon Romanovsky <leon-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>]

From: Leon Romanovsky <leonro-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>

RDMA devices are cross-functional devices from one side,
but very tailored for the specific markets from another.

Such diversity caused to spread of RDMA related configuration
across various tools, e.g. devlink, ip, ethtool, ib specific and
vendor specific solutions.

This patch adds ability to fill device and port information
by reading RDMA netlink.

Signed-off-by: Leon Romanovsky <leonro-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
---
 Makefile          |   2 +-
 man/man8/Makefile |   3 +-
 rdma/.gitignore   |   1 +
 rdma/Makefile     |  22 +++++
 rdma/rdma.c       | 110 ++++++++++++++++++++++
 rdma/rdma.h       |  76 +++++++++++++++
 rdma/utils.c      | 270 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
 7 files changed, 482 insertions(+), 2 deletions(-)
 create mode 100644 rdma/.gitignore
 create mode 100644 rdma/Makefile
 create mode 100644 rdma/rdma.c
 create mode 100644 rdma/rdma.h
 create mode 100644 rdma/utils.c

diff --git a/Makefile b/Makefile
index 18de7dcb..c255063b 100644
--- a/Makefile
+++ b/Makefile
@@ -52,7 +52,7 @@ WFLAGS += -Wmissing-declarations -Wold-style-definition -Wformat=2
 CFLAGS := $(WFLAGS) $(CCOPTS) -I../include $(DEFINES) $(CFLAGS)
 YACCFLAGS = -d -t -v

-SUBDIRS=lib ip tc bridge misc netem genl tipc devlink man
+SUBDIRS=lib ip tc bridge misc netem genl tipc devlink rdma man

 LIBNETLINK=../lib/libnetlink.a ../lib/libutil.a
 LDLIBS += $(LIBNETLINK)
diff --git a/man/man8/Makefile b/man/man8/Makefile
index f3318644..81979a07 100644
--- a/man/man8/Makefile
+++ b/man/man8/Makefile
@@ -19,7 +19,8 @@ MAN8PAGES = $(TARGETS) ip.8 arpd.8 lnstat.8 routel.8 rtacct.8 rtmon.8 rtpr.8 ss.
 	tc-simple.8 tc-skbedit.8 tc-vlan.8 tc-xt.8 tc-skbmod.8 tc-ife.8 \
 	tc-tunnel_key.8 tc-sample.8 \
 	devlink.8 devlink-dev.8 devlink-monitor.8 devlink-port.8 devlink-sb.8 \
-	ifstat.8
+	ifstat.8 \
+	rdma.8

 all: $(TARGETS)

diff --git a/rdma/.gitignore b/rdma/.gitignore
new file mode 100644
index 00000000..51fb172b
--- /dev/null
+++ b/rdma/.gitignore
@@ -0,0 +1 @@
+rdma
diff --git a/rdma/Makefile b/rdma/Makefile
new file mode 100644
index 00000000..64da2142
--- /dev/null
+++ b/rdma/Makefile
@@ -0,0 +1,22 @@
+include ../Config
+
+ifeq ($(HAVE_MNL),y)
+
+RDMA_OBJ = rdma.o utils.o
+
+TARGETS=rdma
+CFLAGS += $(shell $(PKG_CONFIG) libmnl --cflags)
+LDLIBS += $(shell $(PKG_CONFIG) libmnl --libs)
+
+endif
+
+all:	$(TARGETS) $(LIBS)
+
+rdma:	$(RDMA_OBJ) $(LIBS)
+	$(QUIET_LINK)$(CC) $^ $(LDFLAGS) $(LDLIBS) -o $@
+
+install: all
+	install -m 0755 $(TARGETS) $(DESTDIR)$(SBINDIR)
+
+clean:
+	rm -f $(RDMA_OBJ) $(TARGETS)
diff --git a/rdma/rdma.c b/rdma/rdma.c
new file mode 100644
index 00000000..9c754da3
--- /dev/null
+++ b/rdma/rdma.c
@@ -0,0 +1,110 @@
+/*
+ * rdma.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:     Leon Romanovsky <leonro-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
+ */
+
+#include <limits.h>
+#include <rdma/rdma_netlink.h>
+
+#include "rdma.h"
+#include "SNAPSHOT.h"
+
+static void help(char *name)
+{
+	pr_out("Usage: %s [ OPTIONS ] OBJECT { COMMAND | help }\n"
+	       "where  OBJECT := { help }\n"
+	       "       OPTIONS := { -V[ersion] }\n", name);
+}
+
+static int cmd_help(struct rdma *rd)
+{
+	help(rd->filename);
+	return 0;
+}
+
+static int rd_cmd(struct rdma *rd)
+{
+	const struct rdma_cmd cmds[] = {
+		{ NULL,		cmd_help },
+		{ "help",	cmd_help },
+		{ 0 }
+	};
+
+	return rdma_exec_cmd(rd, cmds, "object");
+}
+
+static int rd_init(struct rdma *rd, int argc, char **argv, char *filename)
+{
+	uint32_t seq;
+	int ret;
+
+	rd->filename = filename;
+	rd->argc = argc;
+	rd->argv = argv;
+	INIT_LIST_HEAD(&rd->dev_map_list);
+	rd->buff = malloc(MNL_SOCKET_BUFFER_SIZE);
+	if (!rd->buff)
+		return -ENOMEM;
+
+	rdma_prepare_msg(rd, RDMA_NLDEV_CMD_GET, &seq, (NLM_F_REQUEST | NLM_F_ACK | NLM_F_DUMP));
+	if ((ret = rdma_send_msg(rd)))
+		return ret;
+
+	return rdma_recv_msg(rd, rd_dev_init_cb, rd, seq);
+}
+
+static void rd_free(struct rdma *rd)
+{
+	free(rd->buff);
+	rdma_free_devmap(rd);
+}
+int main(int argc, char **argv)
+{
+	char *filename;
+	static const struct option long_options[] = {
+		{ "version",		no_argument,		NULL, 'V' },
+		{ "help",		no_argument,		NULL, 'h' },
+		{ NULL, 0, NULL, 0 }
+	};
+	struct rdma rd;
+	int opt;
+	int err;
+
+	filename = basename(argv[0]);
+
+	while ((opt = getopt_long(argc, argv, "Vh",
+				  long_options, NULL)) >= 0) {
+
+		switch (opt) {
+		case 'V':
+			printf("%s utility, iproute2-ss%s\n", filename, SNAPSHOT);
+			return EXIT_SUCCESS;
+		case 'h':
+			help(filename);
+			return EXIT_SUCCESS;
+		default:
+			pr_err("Unknown option.\n");
+			help(filename);
+			return EXIT_FAILURE;
+		}
+	}
+
+	argc -= optind;
+	argv += optind;
+
+	err = rd_init(&rd, argc, argv, filename);
+	if (err)
+		goto out;
+
+	err = rd_cmd(&rd);
+out:
+	/* Always cleanup */
+	rd_free(&rd);
+	return (err) ? EXIT_FAILURE:EXIT_SUCCESS;
+}
diff --git a/rdma/rdma.h b/rdma/rdma.h
new file mode 100644
index 00000000..9841aebf
--- /dev/null
+++ b/rdma/rdma.h
@@ -0,0 +1,76 @@
+/*
+ * rdma.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:     Leon Romanovsky <leonro-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
+ */
+#ifndef _RDMA_TOOL_H_
+#define _RDMA_TOOL_H_
+
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+#include <getopt.h>
+#include <libmnl/libmnl.h>
+
+#include <rdma/rdma_netlink.h>
+#include "list.h"
+
+#define pr_err(args...) fprintf(stderr, ##args)
+#define pr_out(args...) fprintf(stdout, ##args)
+
+struct port_map {
+	struct list_head list;
+	uint32_t idx;
+};
+
+struct dev_map {
+	struct list_head list;
+	char *dev_name;
+	uint32_t num_ports;
+	struct list_head port_map_list;
+	uint32_t idx;
+};
+
+struct rdma {
+	int argc;
+	char **argv;
+	char *filename;
+	struct list_head dev_map_list;
+	struct mnl_socket *nl;
+	struct nlmsghdr *nlh;
+	char *buff;
+};
+
+struct rdma_cmd {
+	const char *cmd;
+	int (*func)(struct rdma *rd);
+};
+
+/*
+ * Parser interface
+ */
+bool rd_no_arg(struct rdma *rd);
+bool rd_argv_match(struct rdma *rd, const char *pattern);
+void rd_arg_inc(struct rdma *rd);
+
+int rdma_exec_cmd(struct rdma *rd, const struct rdma_cmd *c, const char *str);
+
+/*
+ * Device manipulation
+ */
+void rdma_free_devmap(struct rdma *rd);
+
+/*
+ * Netlink
+ */
+int rdma_send_msg(struct rdma *rd);
+int rdma_recv_msg(struct rdma *rd, mnl_cb_t callback, void *data, uint32_t seq);
+int rdma_prepare_msg(struct rdma *rd, uint32_t cmd, uint32_t *seq, uint16_t flags);
+int rd_dev_init_cb(const struct nlmsghdr *nlh, void *data);
+int rd_attr_cb(const struct nlattr *attr, void *data);
+#endif /* _RDMA_TOOL_H_ */
diff --git a/rdma/utils.c b/rdma/utils.c
new file mode 100644
index 00000000..96278a4c
--- /dev/null
+++ b/rdma/utils.c
@@ -0,0 +1,270 @@
+/*
+ * utils.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:     Leon Romanovsky <leonro-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
+ */
+
+#include <sys/types.h>
+#include <dirent.h>
+#include <time.h>
+
+#include "rdma.h"
+#include <rdma/rdma_netlink.h>
+
+/*
+ * This macro will be moved to generic layer,
+ * after code will be accepted.
+ * it is placed here to avoid rebases with upstream code.
+ */
+#define MAX(a, b)	((a) > (b) ? (a) : (b))
+
+static int rd_argc(struct rdma *rd)
+{
+	return rd->argc;
+}
+
+static char *rd_argv(struct rdma *rd)
+{
+	if (!rd_argc(rd))
+		return NULL;
+	return *rd->argv;
+}
+
+static int strcmpx(const char *str1, const char *str2)
+{
+	if (strlen(str1) > strlen(str2))
+			return -1;
+	return strncmp(str1, str2, strlen(str1));
+}
+
+bool rd_argv_match(struct rdma *rd, const char *pattern)
+{
+	if (!rd_argc(rd))
+		return false;
+	return strcmpx(rd_argv(rd), pattern) == 0;
+}
+
+void rd_arg_inc(struct rdma *rd)
+{
+	if (!rd_argc(rd))
+		return;
+	rd->argc--;
+	rd->argv++;
+}
+
+bool rd_no_arg(struct rdma *rd)
+{
+	return rd_argc(rd) == 0;
+}
+
+static struct dev_map *dev_map_alloc(const char *dev_name)
+{
+	struct dev_map *dev_map;
+
+	dev_map = calloc(1, sizeof(*dev_map));
+	if (!dev_map)
+		return NULL;
+	dev_map->dev_name = strdup(dev_name);
+	INIT_LIST_HEAD(&dev_map->port_map_list);
+
+	return dev_map;
+}
+
+static void port_map_free(struct port_map *port_map)
+{
+	if(!port_map)
+		return;
+	free(port_map);
+}
+
+static void dev_map_free(struct dev_map *dev_map)
+{
+	struct port_map *port_map, *tmp;
+
+	if(!dev_map)
+		return;
+
+	list_for_each_entry_safe(port_map, tmp,
+				 &dev_map->port_map_list, list) {
+		list_del(&port_map->list);
+		port_map_free(port_map);
+	}
+
+	free(dev_map->dev_name);
+	free(dev_map);
+}
+
+static void dev_map_cleanup(struct rdma *rd)
+{
+	struct dev_map *dev_map, *tmp;
+
+	list_for_each_entry_safe(dev_map, tmp,
+				 &rd->dev_map_list, list) {
+		list_del(&dev_map->list);
+		dev_map_free(dev_map);
+	}
+}
+
+static int port_map_alloc(struct dev_map *dev_map, uint32_t num_ports)
+{
+	struct port_map *port_map;
+	int idx = 1;
+
+	while (idx <= num_ports) {
+		port_map = calloc(1, sizeof(*port_map));
+		if (!port_map)
+			return -ENOMEM;
+
+		list_add_tail(&port_map->list, &dev_map->port_map_list);
+		port_map->idx = idx++;
+	}
+
+	return 0;
+}
+
+static const enum mnl_attr_data_type nldev_policy[RDMA_NLDEV_ATTR_MAX] = {
+	[RDMA_NLDEV_ATTR_DEV_NAME] = MNL_TYPE_NUL_STRING,
+	[RDMA_NLDEV_ATTR_PORT_INDEX] = MNL_TYPE_U32,
+};
+
+int rd_attr_cb(const struct nlattr *attr, void *data)
+{
+	const struct nlattr **tb = data;
+	int type;
+
+	if (mnl_attr_type_valid(attr, RDMA_NLDEV_ATTR_MAX) < 0)
+		return MNL_CB_ERROR;
+
+	type = mnl_attr_get_type(attr);
+
+	if (mnl_attr_validate(attr, nldev_policy[type]) < 0)
+		return MNL_CB_ERROR;
+
+	tb[type] = attr;
+	return MNL_CB_OK;
+}
+
+int rd_dev_init_cb(const struct nlmsghdr *nlh, void *data)
+{
+	struct nlattr *tb[RDMA_NLDEV_ATTR_MAX] = {};
+	struct dev_map *dev_map;
+	struct rdma *rd = data;
+	const char *dev_name;
+	uint32_t num_ports;
+	static int i = 1;
+
+	mnl_attr_parse(nlh, 0, rd_attr_cb, tb);
+	if (!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;
+	}
+
+	dev_name = mnl_attr_get_str(tb[RDMA_NLDEV_ATTR_DEV_NAME]);
+	num_ports = mnl_attr_get_u32(tb[RDMA_NLDEV_ATTR_PORT_INDEX]);
+
+	dev_map = dev_map_alloc(dev_name);
+	if (!dev_map)
+		/* The main function will cleanup the allocations */
+		return MNL_CB_ERROR;
+	list_add_tail(&dev_map->list, &rd->dev_map_list);
+	dev_map->idx = i++;
+
+	if (port_map_alloc(dev_map, num_ports))
+		return MNL_CB_ERROR;
+	dev_map->num_ports = num_ports;
+
+	return MNL_CB_OK;
+}
+
+void rdma_free_devmap(struct rdma *rd)
+{
+	if(!rd)
+		return;
+	dev_map_cleanup(rd);
+	return;
+}
+
+int rdma_exec_cmd(struct rdma *rd, const struct rdma_cmd *cmds, const char *str)
+{
+	const struct rdma_cmd *c;
+
+	/* First argument in objs table is default variant */
+	if (rd_no_arg(rd))
+		return cmds->func(rd);
+
+	for (c = cmds + 1; c->cmd; ++c) {
+		if (rd_argv_match(rd, c->cmd)) {
+			/* Move to next argument */
+			rd_arg_inc(rd);
+			return c->func(rd);
+		}
+	}
+
+	pr_err("Unknown %s '%s'.\n", str, rd_argv(rd));
+	return 0;
+}
+
+int rdma_prepare_msg(struct rdma *rd, uint32_t cmd, uint32_t *seq, uint16_t flags)
+{
+	*seq = time(NULL);
+
+	rd->nlh = mnl_nlmsg_put_header(rd->buff);
+	rd->nlh->nlmsg_type = RDMA_NL_GET_TYPE(RDMA_NL_NLDEV, cmd);
+	rd->nlh->nlmsg_seq = *seq;
+	rd->nlh->nlmsg_flags = flags;
+
+	return 0;
+}
+
+int rdma_send_msg(struct rdma *rd)
+{
+	int ret;
+
+	rd->nl = mnl_socket_open(NETLINK_RDMA);
+	if (!rd->nl) {
+		pr_err("Failed to open NETLINK_RDMA socket\n");
+		return -ENODEV;
+	}
+
+	ret = mnl_socket_bind(rd->nl, 0, MNL_SOCKET_AUTOPID);
+	if (ret < 0) {
+		pr_err("Failed to bind socket with err %d\n", ret);
+		goto err;
+	}
+
+	ret = mnl_socket_sendto(rd->nl, rd->nlh, rd->nlh->nlmsg_len);
+	if (ret < 0) {
+		pr_err("Failed to send to socket with err %d\n", ret);
+		goto err;
+	}
+	return 0;
+
+err:	mnl_socket_close(rd->nl);
+	return ret;
+}
+
+int rdma_recv_msg(struct rdma *rd, mnl_cb_t callback, void *data, unsigned int seq)
+{
+	int ret;
+	unsigned int portid;
+	char buf[MNL_SOCKET_BUFFER_SIZE];
+
+	portid = mnl_socket_get_portid(rd->nl);
+	do {
+		ret = mnl_socket_recvfrom(rd->nl, buf, sizeof(buf));
+		if (ret <= 0)
+			break;
+
+		ret = mnl_cb_run(buf, ret, seq, portid, callback, data);
+	} while (ret > 0);
+
+	mnl_socket_close(rd->nl);
+	return ret;
+}
--
2.13.1

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html