Merge branch 'rdma-net-namespace' into next

Parav Pandit  says:

====================

RDMA subsystem can be running in either of the modes.
(a) Sharing RDMA devices among multiple net namespaces or
(b) Exclusive mode where RDMA device is bound to single net namespace

This patch series adds
(1) query command to query rdma subsystem sharing mode
(2) set command to change rdma subsystem sharing mode
(3) assign rdma device to a net namespace

rdma tool examples:
(a) Query current rdma subsys net namespace sharing mode
$ rdma sys show
netns shared

(b) Change rdma subsys mode to exclusive mode
$ rdma sys set netns exclusive

$ rdma sys show
netns exclusive

(c) Assign rdma device to a specific newly created net namespace
$ ip netns add foo
$ rdma dev set mlx5_1 netns foo

====================

Signed-off-by: David Ahern <dsahern@gmail.com>

man/man8/rdma-dev.8

@@ -28,13 +28,19 @@ rdma-dev \- RDMA device configuration
 .BR name
 .BR NEWNAME
 
+.ti -8
+.B rdma dev set
+.RI "[ " DEV " ]"
+.BR netns
+.BR NSNAME
+
 .ti -8
 .B rdma dev help
 
 .SH "DESCRIPTION"
-.SS rdma dev set - rename rdma device
+.SS rdma dev set - rename RDMA device or set network namespace
 
-.SS rdma dev show - display rdma device attributes
+.SS rdma dev show - display RDMA device attributes
 
 .PP
 .I "DEV"
@@ -58,11 +64,19 @@ rdma dev set mlx5_3 name rdma_0
 Renames the mlx5_3 device to rdma_0.
 .RE
 .PP
+rdma dev set mlx5_3 netns foo
+.RS 4
+Changes the network namespace of RDMA device to foo where foo is
+previously created using iproute2 ip command.
+.RE
+.PP
 
 .SH SEE ALSO
+.BR ip (8),
 .BR rdma (8),
 .BR rdma-link (8),
 .BR rdma-resource (8),
+.BR rdma-system (8),
 .br
 
 .SH AUTHOR

man/man8/rdma-system.8

@@ -0,0 +1,82 @@
+.TH RDMA\-SYSTEM 8 "06 Jul 2017" "iproute2" "Linux"
+.SH NAME
+rdma-system \- RDMA subsystem configuration
+.SH SYNOPSIS
+.sp
+.ad l
+.in +8
+.ti -8
+.B rdma
+.RI "[ " OPTIONS " ]"
+.B sys
+.RI  " { " COMMAND " | "
+.BR help " }"
+.sp
+
+.ti -8
+.IR OPTIONS " := { "
+\fB\-V\fR[\fIersion\fR] |
+\fB\-d\fR[\fIetails\fR] }
+
+.ti -8
+.B rdma system show
+
+.ti -8
+.B rdma system set
+.BR netns
+.BR NEWMODE
+
+.ti -8
+.B rdma system help
+
+.SH "DESCRIPTION"
+.SS rdma system set - set RDMA subsystem network namespace mode
+
+.SS rdma system show - display RDMA subsystem network namespace mode
+
+.PP
+.I "NEWMODE"
+- specifies the RDMA subsystem mode. Either exclusive or shared.
+When user wants to assign dedicated RDMA device to a particular
+network namespace, exclusive mode should be set before creating
+any network namespace. If there are active network namespaces and if
+one or more RDMA devices exist, changing mode from shared to
+exclusive returns error code EBUSY.
+
+When RDMA subsystem is in shared mode, RDMA device is accessible in
+all network namespace. When RDMA device isolation among multiple
+network namespaces is not needed, shared mode can be used.
+
+It is preferred to not change the subsystem mode when there is active
+RDMA traffic running, even though it is supported.
+
+.SH "EXAMPLES"
+.PP
+rdma system show
+.RS 4
+Shows the state of RDMA subsystem network namespace mode on the system.
+.RE
+.PP
+rdma system set netns exclusive
+.RS 4
+Sets the RDMA subsystem in network namespace exclusive mode. In this mode RDMA devices
+are visible only in single network namespace.
+.RE
+.PP
+rdma system set netns shared
+.RS 4
+Sets the RDMA subsystem in network namespace shared mode. In this mode RDMA devices
+are shared among network namespaces.
+.RE
+.PP
+
+.SH SEE ALSO
+.BR rdma (8),
+.BR rdma-link (8),
+.BR rdma-resource (8),
+.BR network_namespaces (7),
+.BR namespaces (7),
+.br
+
+.SH AUTHOR
+Parav Pandit <parav@mellanox.com>

man/man8/rdma.8

@@ -19,7 +19,7 @@ rdma \- RDMA tool
 
 .ti -8
 .IR OBJECT " := { "
-.BR dev " | " link " }"
+.BR dev " | " link " | " system " }"
 .sp
 
 .ti -8
@@ -70,6 +70,10 @@ Generate JSON output.
 .B link
 - RDMA port related.
 
+.TP
+.B sys
+- RDMA subsystem 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-system (8),
 .br
 
 .SH REPORTING BUGS

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 sys.o
 
 TARGETS += rdma
 endif

rdma/dev.c

@@ -4,12 +4,14 @@
  * Authors:     Leon Romanovsky <leonro@mellanox.com>
  */
 
+#include <fcntl.h>
 #include "rdma.h"
 
 static int dev_help(struct rd *rd)
 {
 	pr_out("Usage: %s dev show [DEV]\n", rd->filename);
 	pr_out("       %s dev set [DEV] name DEVNAME\n", rd->filename);
+	pr_out("       %s dev set [DEV] netns NSNAME\n", rd->filename);
 	return 0;
 }
 
@@ -272,11 +274,46 @@ static int dev_set_name(struct rd *rd)
 	return rd_sendrecv_msg(rd, seq);
 }
 
+static int dev_set_netns(struct rd *rd)
+{
+	char *netns_path;
+	uint32_t seq;
+	int netns;
+	int ret;
+
+	if (rd_no_arg(rd)) {
+		pr_err("Please provide device name.\n");
+		return -EINVAL;
+	}
+
+	if (asprintf(&netns_path, "%s/%s", NETNS_RUN_DIR, rd_argv(rd)) < 0)
+		return -ENOMEM;
+
+	netns = open(netns_path, O_RDONLY | O_CLOEXEC);
+	if (netns < 0) {
+		fprintf(stderr, "Cannot open network namespace \"%s\": %s\n",
+			rd_argv(rd), strerror(errno));
+		ret = -EINVAL;
+		goto done;
+	}
+
+	rd_prepare_msg(rd, RDMA_NLDEV_CMD_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_NET_NS_FD, netns);
+	ret = rd_sendrecv_msg(rd, seq);
+	close(netns);
+done:
+	free(netns_path);
+	return ret;
+}
+
 static int dev_one_set(struct rd *rd)
 {
 	const struct rd_cmd cmds[] = {
 		{ NULL,		dev_help},
 		{ "name",	dev_set_name},
+		{ "netns",	dev_set_netns},
 		{ 0 }
 	};
 

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 | system | 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 },
+		{ "system",	cmd_sys },
 		{ 0 }
 	};
 

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_sys(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));

rdma/sys.c

@@ -0,0 +1,138 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/*
+ * sys.c	RDMA tool
+ */
+
+#include "rdma.h"
+
+static int sys_help(struct rd *rd)
+{
+	pr_out("Usage: %s system show [ netns ]\n", rd->filename);
+	pr_out("       %s system set netns { shared | exclusive }\n", rd->filename);
+	return 0;
+}
+
+static const char *netns_modes_str[] = {
+	"exclusive",
+	"shared",
+};
+
+static int sys_show_parse_cb(const struct nlmsghdr *nlh, void *data)
+{
+	struct nlattr *tb[RDMA_NLDEV_ATTR_MAX] = {};
+	struct rd *rd = data;
+
+	mnl_attr_parse(nlh, 0, rd_attr_cb, tb);
+
+	if (tb[RDMA_NLDEV_SYS_ATTR_NETNS_MODE]) {
+		const char *mode_str;
+		uint8_t netns_mode;
+
+		netns_mode =
+			mnl_attr_get_u8(tb[RDMA_NLDEV_SYS_ATTR_NETNS_MODE]);
+
+		if (netns_mode <= ARRAY_SIZE(netns_modes_str))
+			mode_str = netns_modes_str[netns_mode];
+		else
+			mode_str = "unknown";
+
+		if (rd->json_output)
+			jsonw_string_field(rd->jw, "netns", mode_str);
+		else
+			pr_out("netns %s\n", mode_str);
+	}
+	return MNL_CB_OK;
+}
+
+static int sys_show_no_args(struct rd *rd)
+{
+	uint32_t seq;
+	int ret;
+
+	rd_prepare_msg(rd, RDMA_NLDEV_CMD_SYS_GET,
+		       &seq, (NLM_F_REQUEST | NLM_F_ACK));
+	ret = rd_send_msg(rd);
+	if (ret)
+		return ret;
+
+	return rd_recv_msg(rd, sys_show_parse_cb, rd, seq);
+}
+
+static int sys_show(struct rd *rd)
+{
+	const struct rd_cmd cmds[] = {
+		{ NULL,		sys_show_no_args},
+		{ "netns",	sys_show_no_args},
+		{ 0 }
+	};
+
+	return rd_exec_cmd(rd, cmds, "parameter");
+}
+
+static int sys_set_netns_cmd(struct rd *rd, bool enable)
+{
+	uint32_t seq;
+
+	rd_prepare_msg(rd, RDMA_NLDEV_CMD_SYS_SET,
+		       &seq, (NLM_F_REQUEST | NLM_F_ACK));
+	mnl_attr_put_u8(rd->nlh, RDMA_NLDEV_SYS_ATTR_NETNS_MODE, enable);
+
+	return rd_sendrecv_msg(rd, seq);
+}
+
+static bool sys_valid_netns_cmd(const char *cmd)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(netns_modes_str); i++) {
+		if (!strcmp(cmd, netns_modes_str[i]))
+			return true;
+	}
+	return false;
+}
+
+static int sys_set_netns_args(struct rd *rd)
+{
+	bool cmd;
+
+	if (rd_no_arg(rd) || !sys_valid_netns_cmd(rd_argv(rd))) {
+		pr_err("valid options are: { shared | exclusive }\n");
+		return -EINVAL;
+	}
+
+	cmd = (strcmp(rd_argv(rd), "shared") == 0) ? true : false;
+
+	return sys_set_netns_cmd(rd, cmd);
+}
+
+static int sys_set_help(struct rd *rd)
+{
+	pr_out("Usage: %s system set [PARAM] value\n", rd->filename);
+	pr_out("            system set netns { shared | exclusive }\n");
+	return 0;
+}
+
+static int sys_set(struct rd *rd)
+{
+	const struct rd_cmd cmds[] = {
+		{ NULL,			sys_set_help },
+		{ "help",		sys_set_help },
+		{ "netns",		sys_set_netns_args},
+		{ 0 }
+	};
+
+	return rd_exec_cmd(rd, cmds, "parameter");
+}
+
+int cmd_sys(struct rd *rd)
+{
+	const struct rd_cmd cmds[] = {
+		{ NULL,		sys_show },
+		{ "show",	sys_show },
+		{ "set",	sys_set },
+		{ "help",	sys_help },
+		{ 0 }
+	};
+
+	return rd_exec_cmd(rd, cmds, "system command");
+}

rdma/utils.c

@@ -435,6 +435,7 @@ 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_SYS_ATTR_NETNS_MODE] = MNL_TYPE_U8,
 };
 
 int rd_attr_check(const struct nlattr *attr, int *typep)