Message-Id: <20170817065614.1393-3-leonro@mellanox.com>
Date:   Thu, 17 Aug 2017 09:56:08 +0300
From:   Leon Romanovsky <leonro@...lanox.com>
To:     Doug Ledford <dledford@...hat.com>,
        Stephen Hemminger <stephen@...workplumber.org>
Cc:     linux-rdma@...r.kernel.org, Leon Romanovsky <leonro@...lanox.com>,
        Dennis Dalessandro <dennis.dalessandro@...el.com>,
        Jason Gunthorpe <jgunthorpe@...idianresearch.com>,
        Jiri Pirko <jiri@...lanox.com>,
        Ariel Almog <ariela@...lanox.com>,
        David Laight <David.Laight@...LAB.COM>,
        Linux Netdev <netdev@...r.kernel.org>
Subject: [PATCH REPOST v5 iproute2 2/8] rdma: Add basic infrastructure for RDMA tool

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@...lanox.com>
---
 Makefile        |   2 +-
 rdma/.gitignore |   1 +
 rdma/Makefile   |  22 ++++++
 rdma/rdma.c     | 116 ++++++++++++++++++++++++++++++
 rdma/rdma.h     |  73 +++++++++++++++++++
 rdma/utils.c    | 217 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 6 files changed, 430 insertions(+), 1 deletion(-)
 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 1f88f7f5..dbb4a4af 100644
--- a/Makefile
+++ b/Makefile
@@ -49,7 +49,7 @@ 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 += $(LIBNETLINK)
diff --git a/rdma/.gitignore b/rdma/.gitignore
new file mode 100644
index 00000000..51fb172b
--- /dev/null
+++ b/rdma/.gitignore
@@ -0,0 +1 @@
+rdma
diff --git a/rdma/Makefile b/rdma/Makefile
new file mode 100644
index 00000000..64da2142
--- /dev/null
+++ b/rdma/Makefile
@@ -0,0 +1,22 @@
+include ../Config
+
+ifeq ($(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..d850e396
--- /dev/null
+++ b/rdma/rdma.c
@@ -0,0 +1,116 @@
+/*
+ * 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@...lanox.com>
+ */
+
+#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] | -d[etails]}\n", name);
+}
+
+static int cmd_help(struct rd *rd)
+{
+	help(rd->filename);
+	return 0;
+}
+
+static int rd_cmd(struct rd *rd)
+{
+	const struct rd_cmd cmds[] = {
+		{ NULL,		cmd_help },
+		{ "help",	cmd_help },
+		{ 0 }
+	};
+
+	return rd_exec_cmd(rd, cmds, "object");
+}
+
+static int rd_init(struct rd *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;
+
+	rd_prepare_msg(rd, RDMA_NLDEV_CMD_GET,
+		       &seq, (NLM_F_REQUEST | NLM_F_ACK | NLM_F_DUMP));
+	ret = rd_send_msg(rd);
+	if (ret)
+		return ret;
+
+	return rd_recv_msg(rd, rd_dev_init_cb, rd, seq);
+}
+
+static void rd_free(struct rd *rd)
+{
+	free(rd->buff);
+	rd_free_devmap(rd);
+}
+
+int main(int argc, char **argv)
+{
+	static const struct option long_options[] = {
+		{ "version",		no_argument,		NULL, 'V' },
+		{ "help",		no_argument,		NULL, 'h' },
+		{ "details",		no_argument,		NULL, 'd' },
+		{ NULL, 0, NULL, 0 }
+	};
+	bool show_details = false;
+	char *filename;
+	struct rd rd;
+	int opt;
+	int err;
+
+	filename = basename(argv[0]);
+
+	while ((opt = getopt_long(argc, argv, "Vhd",
+				  long_options, NULL)) >= 0) {
+		switch (opt) {
+		case 'V':
+			printf("%s utility, iproute2-ss%s\n",
+			       filename, SNAPSHOT);
+			return EXIT_SUCCESS;
+		case 'd':
+			show_details = true;
+			break;
+		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;
+
+	rd.show_details = show_details;
+	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..c1ef1059
--- /dev/null
+++ b/rdma/rdma.h
@@ -0,0 +1,73 @@
+/*
+ * 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@...lanox.com>
+ */
+#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 <time.h>
+#include <rdma/ib_user_verbs.h>
+#include <rdma/rdma_netlink.h>
+
+#include "list.h"
+
+#define pr_err(args...) fprintf(stderr, ##args)
+#define pr_out(args...) fprintf(stdout, ##args)
+
+struct dev_map {
+	struct list_head list;
+	char *dev_name;
+	uint32_t num_ports;
+	uint32_t idx;
+};
+
+struct rd {
+	int argc;
+	char **argv;
+	char *filename;
+	bool show_details;
+	struct list_head dev_map_list;
+	struct mnl_socket *nl;
+	struct nlmsghdr *nlh;
+	char *buff;
+};
+
+struct rd_cmd {
+	const char *cmd;
+	int (*func)(struct rd *rd);
+};
+
+/*
+ * Parser interface
+ */
+bool rd_no_arg(struct rd *rd);
+void rd_arg_inc(struct rd *rd);
+
+int rd_exec_cmd(struct rd *rd, const struct rd_cmd *c, const char *str);
+
+/*
+ * Device manipulation
+ */
+void rd_free_devmap(struct rd *rd);
+
+/*
+ * Netlink
+ */
+int rd_send_msg(struct rd *rd);
+int rd_recv_msg(struct rd *rd, mnl_cb_t callback, void *data, uint32_t seq);
+void rd_prepare_msg(struct rd *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..9bd7418f
--- /dev/null
+++ b/rdma/utils.c
@@ -0,0 +1,217 @@
+/*
+ * 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@...lanox.com>
+ */
+
+#include "rdma.h"
+
+static int rd_argc(struct rd *rd)
+{
+	return rd->argc;
+}
+
+static char *rd_argv(struct rd *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));
+}
+
+static bool rd_argv_match(struct rd *rd, const char *pattern)
+{
+	if (!rd_argc(rd))
+		return false;
+	return strcmpx(rd_argv(rd), pattern) == 0;
+}
+
+void rd_arg_inc(struct rd *rd)
+{
+	if (!rd_argc(rd))
+		return;
+	rd->argc--;
+	rd->argv++;
+}
+
+bool rd_no_arg(struct rd *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);
+
+	return dev_map;
+}
+
+static void dev_map_free(struct dev_map *dev_map)
+{
+	if (!dev_map)
+		return;
+
+	free(dev_map->dev_name);
+	free(dev_map);
+}
+
+static void dev_map_cleanup(struct rd *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 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 rd *rd = data;
+	const char *dev_name;
+
+	mnl_attr_parse(nlh, 0, rd_attr_cb, tb);
+	if (!tb[RDMA_NLDEV_ATTR_DEV_NAME] || !tb[RDMA_NLDEV_ATTR_DEV_INDEX])
+		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]);
+
+	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->num_ports = mnl_attr_get_u32(tb[RDMA_NLDEV_ATTR_PORT_INDEX]);
+	dev_map->idx = mnl_attr_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);
+	return MNL_CB_OK;
+}
+
+void rd_free_devmap(struct rd *rd)
+{
+	if (!rd)
+		return;
+	dev_map_cleanup(rd);
+}
+
+int rd_exec_cmd(struct rd *rd, const struct rd_cmd *cmds, const char *str)
+{
+	const struct rd_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;
+}
+
+void rd_prepare_msg(struct rd *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;
+}
+
+int rd_send_msg(struct rd *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 rd_recv_msg(struct rd *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;
+}
--
2.14.1

Powered by blists - more mailing lists