tc: flower: Fix buffer overflow on large labels

Buffer is 64bytes, but label printing can take 66bytes printing
in hex, and will overflow when setting the string delimiter ('\0').

Fix that by increasing the print buffer size.

Example of overflowing ct_label:
ct_label 11111111111111111111111111111111/11111111111111111111111111111111

Fixes: 2fffb1c030 ("tc: flower: Add matching on conntrack info")
Signed-off-by: Paul Blakey <paulb@nvidia.com>
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>

Makefile

@@ -1,6 +1,8 @@
 # SPDX-License-Identifier: GPL-2.0
 # Top level Makefile for iproute2
 
+-include config.mk
+
 ifeq ("$(origin V)", "command line")
 VERBOSE = $(V)
 endif
@@ -13,7 +15,6 @@ MAKEFLAGS += --no-print-directory
 endif
 
 PREFIX?=/usr
-LIBDIR?=$(PREFIX)/lib
 SBINDIR?=/sbin
 CONFDIR?=/etc/iproute2
 NETNS_RUN_DIR?=/var/run/netns
@@ -40,9 +41,18 @@ DEFINES+=-DCONFDIR=\"$(CONFDIR)\" \
          -DNETNS_RUN_DIR=\"$(NETNS_RUN_DIR)\" \
          -DNETNS_ETC_DIR=\"$(NETNS_ETC_DIR)\"
 
+#options for AX.25
+ADDLIB+=ax25_ntop.o
+
+#options for AX.25
+ADDLIB+=rose_ntop.o
+
 #options for mpls
 ADDLIB+=mpls_ntop.o mpls_pton.o
 
+#options for NETROM
+ADDLIB+=netrom_ntop.o
+
 CC := gcc
 HOSTCC ?= $(CC)
 DEFINES += -D_GNU_SOURCE
@@ -55,7 +65,7 @@ WFLAGS += -Wmissing-declarations -Wold-style-definition -Wformat=2
 CFLAGS := $(WFLAGS) $(CCOPTS) -I../include -I../include/uapi $(DEFINES) $(CFLAGS)
 YACCFLAGS = -d -t -v
 
-SUBDIRS=lib ip tc bridge misc netem genl tipc devlink rdma man
+SUBDIRS=lib ip tc bridge misc netem genl tipc devlink rdma dcb man vdpa
 
 LIBNETLINK=../lib/libutil.a ../lib/libnetlink.a
 LDLIBS += $(LIBNETLINK)
@@ -63,7 +73,9 @@ LDLIBS += $(LIBNETLINK)
 all: config.mk
 	@set -e; \
 	for i in $(SUBDIRS); \
-	do echo; echo $$i; $(MAKE) $(MFLAGS) -C $$i; done
+	do echo; echo $$i; $(MAKE) -C $$i; done
+
+.PHONY: clean clobber distclean check cscope version
 
 help:
 	@echo "Make Targets:"
@@ -73,13 +85,15 @@ help:
 	@echo " install             - install binaries on local machine"
 	@echo " check               - run tests"
 	@echo " cscope              - build cscope database"
-	@echo " snapshot            - generate version number header"
+	@echo " version             - update version"
 	@echo ""
 	@echo "Make Arguments:"
 	@echo " V=[0|1]             - set build verbosity level"
 
 config.mk:
-	sh configure $(KERNEL_INCLUDE)
+	@if [ ! -f config.mk -o configure -nt config.mk ]; then \
+		sh configure $(KERNEL_INCLUDE); \
+	fi
 
 install: all
 	install -m 0755 -d $(DESTDIR)$(SBINDIR)
@@ -93,17 +107,17 @@ install: all
 	install -m 0644 bash-completion/devlink $(DESTDIR)$(BASH_COMPDIR)
 	install -m 0644 include/bpf_elf.h $(DESTDIR)$(HDRDIR)
 
-snapshot:
+version:
-	echo "static const char SNAPSHOT[] = \""`date +%y%m%d`"\";" \
+	echo "static const char version[] = \""`git describe --tags --long`"\";" \
-		> include/SNAPSHOT.h
+		> include/version.h
 
 clean:
 	@for i in $(SUBDIRS) testsuite; \
-	do $(MAKE) $(MFLAGS) -C $$i clean; done
+	do $(MAKE) -C $$i clean; done
 
 clobber:
 	touch config.mk
-	$(MAKE) $(MFLAGS) clean
+	$(MAKE) clean
 	rm -f config.mk cscope.*
 
 distclean: clobber

README

@@ -28,17 +28,12 @@ The makefile will automatically build a config.mk file which
 contains definitions of libraries that may or may not be available
 on the system such as: ATM, ELF, MNL, and SELINUX.
 
-3. To make documentation, cd to doc/ directory , then
+3. include/uapi
-   look at start of Makefile and set correct values for
-   PAGESIZE=a4		, ie: a4 , letter ...	(string)
-   PAGESPERPAGE=2	, ie: 1 , 2 ...		(numeric)
-   and make there. It assumes, that latex, dvips and psnup
-   are in your path.
 
-4. This package includes matching sanitized kernel headers because
+This package includes matching sanitized kernel headers because
-   the build environment may not have up to date versions. See Makefile
+the build environment may not have up to date versions. See Makefile
-   if you have special requirements and need to point at different
+if you have special requirements and need to point at different
-   kernel include files.
+kernel include files.
 
 Stephen Hemminger
 stephen@networkplumber.org

bash-completion/devlink

@@ -319,6 +319,57 @@ _devlink_port_split()
     esac
 }
 
+# Completion for devlink port param set
+_devlink_port_param_set()
+{
+    case $cword in
+        7)
+            COMPREPLY=( $( compgen -W "value" -- "$cur" ) )
+            return
+            ;;
+        8)
+            # String argument
+            return
+            ;;
+        9)
+            COMPREPLY=( $( compgen -W "cmode" -- "$cur" ) )
+            return
+            ;;
+        10)
+            COMPREPLY=( $( compgen -W "runtime driverinit permanent" -- \
+                "$cur" ) )
+            return
+            ;;
+    esac
+}
+
+# Completion for devlink port param
+_devlink_port_param()
+{
+    case "$cword" in
+        3)
+            COMPREPLY=( $( compgen -W "show set" -- "$cur" ) )
+            return
+            ;;
+        4)
+            _devlink_direct_complete "port"
+            return
+            ;;
+        5)
+            COMPREPLY=( $( compgen -W "name" -- "$cur" ) )
+            return
+            ;;
+        6)
+            _devlink_direct_complete "param_name"
+            return
+            ;;
+    esac
+
+    if [[ "${words[3]}" == "set" ]]; then
+        _devlink_port_param_set
+    fi
+}
+
 # Completion for devlink port
 _devlink_port()
 {
@@ -331,6 +382,10 @@ _devlink_port()
             _devlink_port_split
             return
             ;;
+        param)
+            _devlink_port_param
+            return
+            ;;
         show|unsplit)
             if [[ $cword -eq 3 ]]; then
                 _devlink_direct_complete "port"
@@ -635,7 +690,7 @@ _devlink_health_reporter()
 _devlink_health()
 {
     case $command in
-        show|recover|diagnose|set)
+        show|recover|diagnose|set|test)
             _devlink_health_reporter 0
             if [[ $command == "set" ]]; then
                 case $cword in
@@ -678,7 +733,7 @@ _devlink_trap_set_action()
             COMPREPLY=( $( compgen -W "action" -- "$cur" ) )
             ;;
         $((7 + $i)))
-            COMPREPLY=( $( compgen -W "trap drop" -- "$cur" ) )
+            COMPREPLY=( $( compgen -W "trap drop mirror" -- "$cur" ) )
             ;;
     esac
 }
@@ -708,7 +763,7 @@ _devlink_trap_group_set()
 
     case $prev in
         action)
-            COMPREPLY=( $( compgen -W "trap drop" -- "$cur" ) )
+            COMPREPLY=( $( compgen -W "trap drop mirror" -- "$cur" ) )
             return
             ;;
         policer)

bridge/br_common.h

@@ -10,6 +10,11 @@ void print_vlan_info(struct rtattr *tb, int ifindex);
 int print_linkinfo(struct nlmsghdr *n, void *arg);
 int print_mdb_mon(struct nlmsghdr *n, void *arg);
 int print_fdb(struct nlmsghdr *n, void *arg);
+void print_stp_state(__u8 state);
+int parse_stp_state(const char *arg);
+int print_vlan_rtm(struct nlmsghdr *n, void *arg, bool monitor,
+		   bool global_only);
+void br_print_router_port_stats(struct rtattr *pattr);
 
 int do_fdb(int argc, char **argv);
 int do_mdb(int argc, char **argv);

bridge/bridge.c

@@ -12,7 +12,7 @@
 #include <string.h>
 #include <errno.h>
 
-#include "SNAPSHOT.h"
+#include "version.h"
 #include "utils.h"
 #include "br_common.h"
 #include "namespace.h"
@@ -37,10 +37,10 @@ static void usage(void)
 	fprintf(stderr,
 "Usage: bridge [ OPTIONS ] OBJECT { COMMAND | help }\n"
 "       bridge [ -force ] -batch filename\n"
-"where	OBJECT := { link | fdb | mdb | vlan | monitor }\n"
+"where  OBJECT := { link | fdb | mdb | vlan | monitor }\n"
-"	OPTIONS := { -V[ersion] | -s[tatistics] | -d[etails] |\n"
+"       OPTIONS := { -V[ersion] | -s[tatistics] | -d[etails] |\n"
-"		     -o[neline] | -t[imestamp] | -n[etns] name |\n"
+"                    -o[neline] | -t[imestamp] | -n[etns] name |\n"
-"		     -c[ompressvlans] -color -p[retty] -j[son] }\n");
+"                    -c[ompressvlans] -color -p[retty] -j[son] }\n");
 	exit(-1);
 }
 
@@ -77,20 +77,14 @@ static int do_cmd(const char *argv0, int argc, char **argv)
 	return -1;
 }
 
+static int br_batch_cmd(int argc, char *argv[], void *data)
+{
+	return do_cmd(argv[0], argc, argv);
+}
+
 static int batch(const char *name)
 {
-	char *line = NULL;
+	int ret;
-	size_t len = 0;
-	int ret = EXIT_SUCCESS;
-
-	if (name && strcmp(name, "-") != 0) {
-		if (freopen(name, "r", stdin) == NULL) {
-			fprintf(stderr,
-				"Cannot open file \"%s\" for reading: %s\n",
-				name, strerror(errno));
-			return EXIT_FAILURE;
-		}
-	}
 
 	if (rtnl_open(&rth, 0) < 0) {
 		fprintf(stderr, "Cannot open rtnetlink\n");
@@ -99,25 +93,7 @@ static int batch(const char *name)
 
 	rtnl_set_strict_dump(&rth);
 
-	cmdlineno = 0;
+	ret = do_batch(name, force, br_batch_cmd, NULL);
-	while (getcmdline(&line, &len, stdin) != -1) {
-		char *largv[100];
-		int largc;
-
-		largc = makeargs(line, largv, 100);
-		if (largc == 0)
-			continue;       /* blank line */
-
-		if (do_cmd(largv[0], largc, largv)) {
-			fprintf(stderr, "Command failed %s:%d\n",
-				name, cmdlineno);
-			ret = EXIT_FAILURE;
-			if (!force)
-				break;
-		}
-	}
-	if (line)
-		free(line);
 
 	rtnl_close(&rth);
 	return ret;
@@ -141,7 +117,7 @@ main(int argc, char **argv)
 		if (matches(opt, "-help") == 0) {
 			usage();
 		} else if (matches(opt, "-Version") == 0) {
-			printf("bridge utility, 0.0\n");
+			printf("bridge utility, %s\n", version);
 			exit(0);
 		} else if (matches(opt, "-stats") == 0 ||
 			   matches(opt, "-statistics") == 0) {
@@ -173,9 +149,9 @@ main(int argc, char **argv)
 			NEXT_ARG();
 			if (netns_switch(argv[1]))
 				exit(-1);
+		} else if (matches_color(opt, &color)) {
 		} else if (matches(opt, "-compressvlans") == 0) {
 			++compress_vlans;
-		} else if (matches_color(opt, &color)) {
 		} else if (matches(opt, "-force") == 0) {
 			++force;
 		} else if (matches(opt, "-json") == 0) {

bridge/fdb.c

@@ -30,19 +30,21 @@
 #include "rt_names.h"
 #include "utils.h"
 
-static unsigned int filter_index, filter_vlan, filter_state, filter_master;
+static unsigned int filter_index, filter_dynamic, filter_master,
+	filter_state, filter_vlan;
 
 static void usage(void)
 {
 	fprintf(stderr,
 		"Usage: bridge fdb { add | append | del | replace } ADDR dev DEV\n"
 		"              [ self ] [ master ] [ use ] [ router ] [ extern_learn ]\n"
-		"              [ sticky ] [ local | static | dynamic ] [ dst IPADDR ]\n"
+		"              [ sticky ] [ local | static | dynamic ] [ vlan VID ]\n"
-		"              [ vlan VID ] [ port PORT] [ vni VNI ] [ via DEV ]\n"
+		"              { [ dst IPADDR ] [ port PORT] [ vni VNI ] | [ nhid NHID ] }\n"
-		"              [ src_vni VNI ]\n"
+		"	       [ via DEV ] [ src_vni VNI ]\n"
-		"       bridge fdb [ show [ br BRDEV ] [ brport DEV ] [ vlan VID ] [ state STATE ] ]\n"
+		"       bridge fdb [ show [ br BRDEV ] [ brport DEV ] [ vlan VID ]\n"
-		"       bridge fdb get ADDR [ br BRDEV ] { brport |dev }  DEV [ vlan VID ]\n"
+		"              [ state STATE ] [ dynamic ] ]\n"
-		"              [ vni VNI ]\n");
+		"       bridge fdb get [ to ] LLADDR [ br BRDEV ] { brport | dev } DEV\n"
+		"              [ vlan VID ] [ vni VNI ] [ self ] [ master ] [ dynamic ]\n");
 	exit(-1);
 }
 
@@ -62,7 +64,10 @@ static const char *state_n2a(unsigned int s)
 	if (s & NUD_REACHABLE)
 		return "";
 
-	sprintf(buf, "state=%#x", s);
+	if (is_json_context())
+		sprintf(buf, "%#x", s);
+	else
+		sprintf(buf, "state=%#x", s);
 	return buf;
 }
 
@@ -167,6 +172,9 @@ int print_fdb(struct nlmsghdr *n, void *arg)
 	if (filter_vlan && filter_vlan != vid)
 		return 0;
 
+	if (filter_dynamic && (r->ndm_state & NUD_PERMANENT))
+		return 0;
+
 	open_json_object(NULL);
 	if (n->nlmsg_type == RTM_DELNEIGH)
 		print_bool(PRINT_ANY, "deleted", "Deleted ", true);
@@ -184,10 +192,13 @@ int print_fdb(struct nlmsghdr *n, void *arg)
 				   "mac", "%s ", lladdr);
 	}
 
-	if (!filter_index && r->ndm_ifindex)
+	if (!filter_index && r->ndm_ifindex) {
+		print_string(PRINT_FP, NULL, "dev ", NULL);
+
 		print_color_string(PRINT_ANY, COLOR_IFNAME,
-				   "ifname", "dev %s ",
+				   "ifname", "%s ",
 				   ll_index_to_name(r->ndm_ifindex));
+	}
 
 	if (tb[NDA_DST]) {
 		int family = AF_INET;
@@ -200,9 +211,11 @@ int print_fdb(struct nlmsghdr *n, void *arg)
 				  RTA_PAYLOAD(tb[NDA_DST]),
 				  RTA_DATA(tb[NDA_DST]));
 
+		print_string(PRINT_FP, NULL, "dst ", NULL);
+
 		print_color_string(PRINT_ANY,
 				   ifa_family_color(family),
-				    "dst", "dst %s ", dst);
+				   "dst", "%s ", dst);
 	}
 
 	if (vid)
@@ -237,6 +250,10 @@ int print_fdb(struct nlmsghdr *n, void *arg)
 					   ll_index_to_name(ifindex));
 	}
 
+	if (tb[NDA_NH_ID])
+		print_uint(PRINT_ANY, "nhid", "nhid %u ",
+			   rta_getattr_u32(tb[NDA_NH_ID]));
+
 	if (tb[NDA_LINK_NETNSID])
 		print_uint(PRINT_ANY,
 				 "linkNetNsId", "link-netnsid %d ",
@@ -322,6 +339,8 @@ static int fdb_show(int argc, char **argv)
 			if (state_a2n(&state, *argv))
 				invarg("invalid state", *argv);
 			filter_state |= state;
+		} else if (strcmp(*argv, "dynamic") == 0) {
+			filter_dynamic = 1;
 		} else {
 			if (matches(*argv, "help") == 0)
 				usage();
@@ -390,6 +409,7 @@ static int fdb_modify(int cmd, int flags, int argc, char **argv)
 	unsigned int via = 0;
 	char *endptr;
 	short vid = -1;
+	__u32 nhid = 0;
 
 	while (argc > 0) {
 		if (strcmp(*argv, "dev") == 0) {
@@ -401,6 +421,10 @@ static int fdb_modify(int cmd, int flags, int argc, char **argv)
 				duparg2("dst", *argv);
 			get_addr(&dst, *argv, preferred_family);
 			dst_ok = 1;
+		} else if (strcmp(*argv, "nhid") == 0) {
+			NEXT_ARG();
+			if (get_u32(&nhid, *argv, 0))
+				invarg("\"id\" value is invalid\n", *argv);
 		} else if (strcmp(*argv, "port") == 0) {
 
 			NEXT_ARG();
@@ -475,6 +499,11 @@ static int fdb_modify(int cmd, int flags, int argc, char **argv)
 		return -1;
 	}
 
+	if (nhid && (dst_ok || port || vni != ~0)) {
+		fprintf(stderr, "dst, port, vni are mutually exclusive with nhid\n");
+		return -1;
+	}
+
 	/* Assume self */
 	if (!(req.ndm.ndm_flags&(NTF_SELF|NTF_MASTER)))
 		req.ndm.ndm_flags |= NTF_SELF;
@@ -496,6 +525,8 @@ static int fdb_modify(int cmd, int flags, int argc, char **argv)
 
 	if (vid >= 0)
 		addattr16(&req.n, sizeof(req), NDA_VLAN, vid);
+	if (nhid > 0)
+		addattr32(&req.n, sizeof(req), NDA_NH_ID, nhid);
 
 	if (port) {
 		unsigned short dport;
@@ -566,6 +597,8 @@ static int fdb_get(int argc, char **argv)
 				duparg2("vlan", *argv);
 			NEXT_ARG();
 			vlan = atoi(*argv);
+		} else if (matches(*argv, "dynamic") == 0) {
+			filter_dynamic = 1;
 		} else {
 			if (strcmp(*argv, "to") == 0)
 				NEXT_ARG();
@@ -619,10 +652,16 @@ static int fdb_get(int argc, char **argv)
 	if (rtnl_talk(&rth, &req.n, &answer) < 0)
 		return -2;
 
+	/*
+	 * Initialize a json_writer and open an array object
+	 * if -json was specified.
+	 */
+	new_json_obj(json);
 	if (print_fdb(answer, stdout) < 0) {
 		fprintf(stderr, "An error :-)\n");
 		return -1;
 	}
+	delete_json_obj();
 
 	return 0;
 }

bridge/link.c

@@ -19,7 +19,7 @@
 
 static unsigned int filter_index;
 
-static const char *port_states[] = {
+static const char *stp_states[] = {
 	[BR_STATE_DISABLED] = "disabled",
 	[BR_STATE_LISTENING] = "listening",
 	[BR_STATE_LEARNING] = "learning",
@@ -68,22 +68,29 @@ static void print_link_flags(FILE *fp, unsigned int flags, unsigned int mdown)
 	close_json_array(PRINT_ANY, "> ");
 }
 
-static void print_portstate(__u8 state)
+void print_stp_state(__u8 state)
 {
 	if (state <= BR_STATE_BLOCKING)
 		print_string(PRINT_ANY, "state",
-			     "state %s ", port_states[state]);
+			     "state %s ", stp_states[state]);
 	else
 		print_uint(PRINT_ANY, "state",
 			     "state (%d) ", state);
 }
 
-static void print_onoff(FILE *fp, const char *flag, __u8 val)
+int parse_stp_state(const char *arg)
 {
-	if (is_json_context())
+	size_t nstates = ARRAY_SIZE(stp_states);
-		print_bool(PRINT_JSON, flag, NULL, val);
+	int state;
-	else
+
-		fprintf(fp, "%s %s ", flag, val ? "on" : "off");
+	for (state = 0; state < nstates; state++)
+		if (strcmp(stp_states[state], arg) == 0)
+			break;
+
+	if (state == nstates)
+		state = -1;
+
+	return state;
 }
 
 static void print_hwmode(__u16 mode)
@@ -104,7 +111,7 @@ static void print_protinfo(FILE *fp, struct rtattr *attr)
 		parse_rtattr_nested(prtb, IFLA_BRPORT_MAX, attr);
 
 		if (prtb[IFLA_BRPORT_STATE])
-			print_portstate(rta_getattr_u8(prtb[IFLA_BRPORT_STATE]));
+			print_stp_state(rta_getattr_u8(prtb[IFLA_BRPORT_STATE]));
 
 		if (prtb[IFLA_BRPORT_PRIORITY])
 			print_uint(PRINT_ANY, "priority",
@@ -123,38 +130,38 @@ static void print_protinfo(FILE *fp, struct rtattr *attr)
 			fprintf(fp, "%s    ", _SL_);
 
 		if (prtb[IFLA_BRPORT_MODE])
-			print_onoff(fp, "hairpin",
+			print_on_off(PRINT_ANY, "hairpin", "hairpin %s ",
-				    rta_getattr_u8(prtb[IFLA_BRPORT_MODE]));
+				     rta_getattr_u8(prtb[IFLA_BRPORT_MODE]));
 		if (prtb[IFLA_BRPORT_GUARD])
-			print_onoff(fp, "guard",
+			print_on_off(PRINT_ANY, "guard", "guard %s ",
-				    rta_getattr_u8(prtb[IFLA_BRPORT_GUARD]));
+				     rta_getattr_u8(prtb[IFLA_BRPORT_GUARD]));
 		if (prtb[IFLA_BRPORT_PROTECT])
-			print_onoff(fp, "root_block",
+			print_on_off(PRINT_ANY, "root_block", "root_block %s ",
-				    rta_getattr_u8(prtb[IFLA_BRPORT_PROTECT]));
+				     rta_getattr_u8(prtb[IFLA_BRPORT_PROTECT]));
 		if (prtb[IFLA_BRPORT_FAST_LEAVE])
-			print_onoff(fp, "fastleave",
+			print_on_off(PRINT_ANY, "fastleave", "fastleave %s ",
-				    rta_getattr_u8(prtb[IFLA_BRPORT_FAST_LEAVE]));
+				     rta_getattr_u8(prtb[IFLA_BRPORT_FAST_LEAVE]));
 		if (prtb[IFLA_BRPORT_LEARNING])
-			print_onoff(fp, "learning",
+			print_on_off(PRINT_ANY, "learning", "learning %s ",
-				    rta_getattr_u8(prtb[IFLA_BRPORT_LEARNING]));
+				     rta_getattr_u8(prtb[IFLA_BRPORT_LEARNING]));
 		if (prtb[IFLA_BRPORT_LEARNING_SYNC])
-			print_onoff(fp, "learning_sync",
+			print_on_off(PRINT_ANY, "learning_sync", "learning_sync %s ",
-				    rta_getattr_u8(prtb[IFLA_BRPORT_LEARNING_SYNC]));
+				     rta_getattr_u8(prtb[IFLA_BRPORT_LEARNING_SYNC]));
 		if (prtb[IFLA_BRPORT_UNICAST_FLOOD])
-			print_onoff(fp, "flood",
+			print_on_off(PRINT_ANY, "flood", "flood %s ",
-				    rta_getattr_u8(prtb[IFLA_BRPORT_UNICAST_FLOOD]));
+				     rta_getattr_u8(prtb[IFLA_BRPORT_UNICAST_FLOOD]));
 		if (prtb[IFLA_BRPORT_MCAST_FLOOD])
-			print_onoff(fp, "mcast_flood",
+			print_on_off(PRINT_ANY, "mcast_flood", "mcast_flood %s ",
-				    rta_getattr_u8(prtb[IFLA_BRPORT_MCAST_FLOOD]));
+				     rta_getattr_u8(prtb[IFLA_BRPORT_MCAST_FLOOD]));
 		if (prtb[IFLA_BRPORT_MCAST_TO_UCAST])
-			print_onoff(fp, "mcast_to_unicast",
+			print_on_off(PRINT_ANY, "mcast_to_unicast", "mcast_to_unicast %s ",
-				    rta_getattr_u8(prtb[IFLA_BRPORT_MCAST_TO_UCAST]));
+				     rta_getattr_u8(prtb[IFLA_BRPORT_MCAST_TO_UCAST]));
 		if (prtb[IFLA_BRPORT_NEIGH_SUPPRESS])
-			print_onoff(fp, "neigh_suppress",
+			print_on_off(PRINT_ANY, "neigh_suppress", "neigh_suppress %s ",
-				    rta_getattr_u8(prtb[IFLA_BRPORT_NEIGH_SUPPRESS]));
+				     rta_getattr_u8(prtb[IFLA_BRPORT_NEIGH_SUPPRESS]));
 		if (prtb[IFLA_BRPORT_VLAN_TUNNEL])
-			print_onoff(fp, "vlan_tunnel",
+			print_on_off(PRINT_ANY, "vlan_tunnel", "vlan_tunnel %s ",
-				    rta_getattr_u8(prtb[IFLA_BRPORT_VLAN_TUNNEL]));
+				     rta_getattr_u8(prtb[IFLA_BRPORT_VLAN_TUNNEL]));
 
 		if (prtb[IFLA_BRPORT_BACKUP_PORT]) {
 			int ifidx;
@@ -166,10 +173,10 @@ static void print_protinfo(FILE *fp, struct rtattr *attr)
 		}
 
 		if (prtb[IFLA_BRPORT_ISOLATED])
-			print_onoff(fp, "isolated",
+			print_on_off(PRINT_ANY, "isolated", "isolated %s ",
-				    rta_getattr_u8(prtb[IFLA_BRPORT_ISOLATED]));
+				     rta_getattr_u8(prtb[IFLA_BRPORT_ISOLATED]));
 	} else
-		print_portstate(rta_getattr_u8(attr));
+		print_stp_state(rta_getattr_u8(attr));
 }
 
 
@@ -275,22 +282,6 @@ static void usage(void)
 	exit(-1);
 }
 
-static bool on_off(char *arg, __s8 *attr, char *val)
-{
-	if (strcmp(val, "on") == 0)
-		*attr = 1;
-	else if (strcmp(val, "off") == 0)
-		*attr = 0;
-	else {
-		fprintf(stderr,
-			"Error: argument of \"%s\" must be \"on\" or \"off\"\n",
-			arg);
-		return false;
-	}
-
-	return true;
-}
-
 static int brlink_modify(int argc, char **argv)
 {
 	struct {
@@ -323,6 +314,7 @@ static int brlink_modify(int argc, char **argv)
 	__s16 mode = -1;
 	__u16 flags = 0;
 	struct rtattr *nest;
+	int ret;
 
 	while (argc > 0) {
 		if (strcmp(*argv, "dev") == 0) {
@@ -330,40 +322,49 @@ static int brlink_modify(int argc, char **argv)
 			d = *argv;
 		} else if (strcmp(*argv, "guard") == 0) {
 			NEXT_ARG();
-			if (!on_off("guard", &bpdu_guard, *argv))
+			bpdu_guard = parse_on_off("guard", *argv, &ret);
-				return -1;
+			if (ret)
+				return ret;
 		} else if (strcmp(*argv, "hairpin") == 0) {
 			NEXT_ARG();
-			if (!on_off("hairpin", &hairpin, *argv))
+			hairpin = parse_on_off("hairpin", *argv, &ret);
-				return -1;
+			if (ret)
+				return ret;
 		} else if (strcmp(*argv, "fastleave") == 0) {
 			NEXT_ARG();
-			if (!on_off("fastleave", &fast_leave, *argv))
+			fast_leave = parse_on_off("fastleave", *argv, &ret);
-				return -1;
+			if (ret)
+				return ret;
 		} else if (strcmp(*argv, "root_block") == 0) {
 			NEXT_ARG();
-			if (!on_off("root_block", &root_block, *argv))
+			root_block = parse_on_off("root_block", *argv, &ret);
-				return -1;
+			if (ret)
+				return ret;
 		} else if (strcmp(*argv, "learning") == 0) {
 			NEXT_ARG();
-			if (!on_off("learning", &learning, *argv))
+			learning = parse_on_off("learning", *argv, &ret);
-				return -1;
+			if (ret)
+				return ret;
 		} else if (strcmp(*argv, "learning_sync") == 0) {
 			NEXT_ARG();
-			if (!on_off("learning_sync", &learning_sync, *argv))
+			learning_sync = parse_on_off("learning_sync", *argv, &ret);
-				return -1;
+			if (ret)
+				return ret;
 		} else if (strcmp(*argv, "flood") == 0) {
 			NEXT_ARG();
-			if (!on_off("flood", &flood, *argv))
+			flood = parse_on_off("flood", *argv, &ret);
-				return -1;
+			if (ret)
+				return ret;
 		} else if (strcmp(*argv, "mcast_flood") == 0) {
 			NEXT_ARG();
-			if (!on_off("mcast_flood", &mcast_flood, *argv))
+			mcast_flood = parse_on_off("mcast_flood", *argv, &ret);
-				return -1;
+			if (ret)
+				return ret;
 		} else if (strcmp(*argv, "mcast_to_unicast") == 0) {
 			NEXT_ARG();
-			if (!on_off("mcast_to_unicast", &mcast_to_unicast, *argv))
+			mcast_to_unicast = parse_on_off("mcast_to_unicast", *argv, &ret);
-				return -1;
+			if (ret)
+				return ret;
 		} else if (strcmp(*argv, "cost") == 0) {
 			NEXT_ARG();
 			cost = atoi(*argv);
@@ -373,14 +374,11 @@ static int brlink_modify(int argc, char **argv)
 		} else if (strcmp(*argv, "state") == 0) {
 			NEXT_ARG();
 			char *endptr;
-			size_t nstates = ARRAY_SIZE(port_states);
 
 			state = strtol(*argv, &endptr, 10);
 			if (!(**argv != '\0' && *endptr == '\0')) {
-				for (state = 0; state < nstates; state++)
+				state = parse_stp_state(*argv);
-					if (strcasecmp(port_states[state], *argv) == 0)
+				if (state == -1) {
-						break;
-				if (state == nstates) {
 					fprintf(stderr,
 						"Error: invalid STP port state\n");
 					return -1;
@@ -404,18 +402,19 @@ static int brlink_modify(int argc, char **argv)
 			flags |= BRIDGE_FLAGS_MASTER;
 		} else if (strcmp(*argv, "neigh_suppress") == 0) {
 			NEXT_ARG();
-			if (!on_off("neigh_suppress", &neigh_suppress,
+			neigh_suppress = parse_on_off("neigh_suppress", *argv, &ret);
-				    *argv))
+			if (ret)
-				return -1;
+				return ret;
 		} else if (strcmp(*argv, "vlan_tunnel") == 0) {
 			NEXT_ARG();
-			if (!on_off("vlan_tunnel", &vlan_tunnel,
+			vlan_tunnel = parse_on_off("vlan_tunnel", *argv, &ret);
-				    *argv))
+			if (ret)
-				return -1;
+				return ret;
 		} else if (strcmp(*argv, "isolated") == 0) {
 			NEXT_ARG();
-			if (!on_off("isolated", &isolated, *argv))
+			isolated = parse_on_off("isolated", *argv, &ret);
-				return -1;
+			if (ret)
+				return ret;
 		} else if (strcmp(*argv, "backup_port") == 0) {
 			NEXT_ARG();
 			backup_port_idx = ll_name_to_index(*argv);

bridge/mdb.c

@@ -16,9 +16,9 @@
 #include <arpa/inet.h>
 
 #include "libnetlink.h"
+#include "utils.h"
 #include "br_common.h"
 #include "rt_names.h"
-#include "utils.h"
 #include "json_print.h"
 
 #ifndef MDBA_RTA
@@ -31,7 +31,7 @@ static unsigned int filter_index, filter_vlan;
 static void usage(void)
 {
 	fprintf(stderr,
-		"Usage: bridge mdb { add | del } dev DEV port PORT grp GROUP [permanent | temp] [vid VID]\n"
+		"Usage: bridge mdb { add | del } dev DEV port PORT grp GROUP [src SOURCE] [permanent | temp] [vid VID]\n"
 		"       bridge mdb {show} [ dev DEV ] [ vid VID ]\n");
 	exit(-1);
 }
@@ -41,20 +41,25 @@ static bool is_temp_mcast_rtr(__u8 type)
 	return type == MDB_RTR_TYPE_TEMP_QUERY || type == MDB_RTR_TYPE_TEMP;
 }
 
-static const char *format_timer(__u32 ticks)
+static const char *format_timer(__u32 ticks, int align)
 {
 	struct timeval tv;
 	static char tbuf[32];
 
 	__jiffies_to_tv(&tv, ticks);
-	snprintf(tbuf, sizeof(tbuf), "%4lu.%.2lu",
+	if (align)
-		 (unsigned long)tv.tv_sec,
+		snprintf(tbuf, sizeof(tbuf), "%4lu.%.2lu",
-		 (unsigned long)tv.tv_usec / 10000);
+			 (unsigned long)tv.tv_sec,
+			 (unsigned long)tv.tv_usec / 10000);
+	else
+		snprintf(tbuf, sizeof(tbuf), "%lu.%.2lu",
+			 (unsigned long)tv.tv_sec,
+			 (unsigned long)tv.tv_usec / 10000);
 
 	return tbuf;
 }
 
-static void __print_router_port_stats(FILE *f, struct rtattr *pattr)
+void br_print_router_port_stats(struct rtattr *pattr)
 {
 	struct rtattr *tb[MDBA_ROUTER_PATTR_MAX + 1];
 
@@ -65,7 +70,7 @@ static void __print_router_port_stats(FILE *f, struct rtattr *pattr)
 		__u32 timer = rta_getattr_u32(tb[MDBA_ROUTER_PATTR_TIMER]);
 
 		print_string(PRINT_ANY, "timer", " %s",
-			     format_timer(timer));
+			     format_timer(timer, 1));
 	}
 
 	if (tb[MDBA_ROUTER_PATTR_TYPE]) {
@@ -96,13 +101,13 @@ static void br_print_router_ports(FILE *f, struct rtattr *attr,
 			print_string(PRINT_JSON, "port", NULL, port_ifname);
 
 			if (show_stats)
-				__print_router_port_stats(f, i);
+				br_print_router_port_stats(i);
 			close_json_object();
 		} else if (show_stats) {
 			fprintf(f, "router ports on %s: %s",
 				brifname, port_ifname);
 
-			__print_router_port_stats(f, i);
+			br_print_router_port_stats(i);
 			fprintf(f, "\n");
 		} else {
 			fprintf(f, "%s ", port_ifname);
@@ -115,20 +120,53 @@ static void br_print_router_ports(FILE *f, struct rtattr *attr,
 	close_json_array(PRINT_JSON, NULL);
 }
 
+static void print_src_entry(struct rtattr *src_attr, int af, const char *sep)
+{
+	struct rtattr *stb[MDBA_MDB_SRCATTR_MAX + 1];
+	SPRINT_BUF(abuf);
+	const char *addr;
+	__u32 timer_val;
+
+	parse_rtattr_nested(stb, MDBA_MDB_SRCATTR_MAX, src_attr);
+	if (!stb[MDBA_MDB_SRCATTR_ADDRESS] || !stb[MDBA_MDB_SRCATTR_TIMER])
+		return;
+
+	addr = inet_ntop(af, RTA_DATA(stb[MDBA_MDB_SRCATTR_ADDRESS]), abuf,
+			 sizeof(abuf));
+	if (!addr)
+		return;
+	timer_val = rta_getattr_u32(stb[MDBA_MDB_SRCATTR_TIMER]);
+
+	open_json_object(NULL);
+	print_string(PRINT_FP, NULL, "%s", sep);
+	print_color_string(PRINT_ANY, ifa_family_color(af),
+			   "address", "%s", addr);
+	print_string(PRINT_ANY, "timer", "/%s", format_timer(timer_val, 0));
+	close_json_object();
+}
+
 static void print_mdb_entry(FILE *f, int ifindex, const struct br_mdb_entry *e,
 			    struct nlmsghdr *n, struct rtattr **tb)
 {
+	const void *grp, *src;
+	const char *addr;
 	SPRINT_BUF(abuf);
 	const char *dev;
-	const void *src;
 	int af;
 
 	if (filter_vlan && e->vid != filter_vlan)
 		return;
 
-	af = e->addr.proto == htons(ETH_P_IP) ? AF_INET : AF_INET6;
+	if (!e->addr.proto) {
-	src = af == AF_INET ? (const void *)&e->addr.u.ip4 :
+		af = AF_PACKET;
-			      (const void *)&e->addr.u.ip6;
+		grp = &e->addr.u.mac_addr;
+	} else if (e->addr.proto == htons(ETH_P_IP)) {
+		af = AF_INET;
+		grp = &e->addr.u.ip4;
+	} else {
+		af = AF_INET6;
+		grp = &e->addr.u.ip6;
+	}
 	dev = ll_index_to_name(ifindex);
 
 	open_json_object(NULL);
@@ -138,16 +176,64 @@ static void print_mdb_entry(FILE *f, int ifindex, const struct br_mdb_entry *e,
 	print_string(PRINT_ANY, "port", " port %s",
 		     ll_index_to_name(e->ifindex));
 
-	print_color_string(PRINT_ANY, ifa_family_color(af),
+	/* The ETH_ALEN argument is ignored for all cases but AF_PACKET */
-			    "grp", " grp %s",
+	addr = rt_addr_n2a_r(af, ETH_ALEN, grp, abuf, sizeof(abuf));
-			    inet_ntop(af, src, abuf, sizeof(abuf)));
+	if (!addr)
+		return;
 
+	print_color_string(PRINT_ANY, ifa_family_color(af),
+			    "grp", " grp %s", addr);
+
+	if (tb && tb[MDBA_MDB_EATTR_SOURCE]) {
+		src = (const void *)RTA_DATA(tb[MDBA_MDB_EATTR_SOURCE]);
+		print_color_string(PRINT_ANY, ifa_family_color(af),
+				   "src", " src %s",
+				   inet_ntop(af, src, abuf, sizeof(abuf)));
+	}
 	print_string(PRINT_ANY, "state", " %s",
 			   (e->state & MDB_PERMANENT) ? "permanent" : "temp");
+	if (show_details && tb) {
+		if (tb[MDBA_MDB_EATTR_GROUP_MODE]) {
+			__u8 mode = rta_getattr_u8(tb[MDBA_MDB_EATTR_GROUP_MODE]);
+
+			print_string(PRINT_ANY, "filter_mode", " filter_mode %s",
+				     mode == MCAST_INCLUDE ? "include" :
+							     "exclude");
+		}
+		if (tb[MDBA_MDB_EATTR_SRC_LIST]) {
+			struct rtattr *i, *attr = tb[MDBA_MDB_EATTR_SRC_LIST];
+			const char *sep = " ";
+			int rem;
+
+			open_json_array(PRINT_ANY, is_json_context() ?
+								"source_list" :
+								" source_list");
+			rem = RTA_PAYLOAD(attr);
+			for (i = RTA_DATA(attr); RTA_OK(i, rem);
+			     i = RTA_NEXT(i, rem)) {
+				print_src_entry(i, af, sep);
+				sep = ",";
+			}
+			close_json_array(PRINT_JSON, NULL);
+		}
+		if (tb[MDBA_MDB_EATTR_RTPROT]) {
+			__u8 rtprot = rta_getattr_u8(tb[MDBA_MDB_EATTR_RTPROT]);
+			SPRINT_BUF(rtb);
+
+			print_string(PRINT_ANY, "protocol", " proto %s ",
+				     rtnl_rtprot_n2a(rtprot, rtb, sizeof(rtb)));
+		}
+	}
 
 	open_json_array(PRINT_JSON, "flags");
 	if (e->flags & MDB_FLAGS_OFFLOAD)
 		print_string(PRINT_ANY, NULL, " %s", "offload");
+	if (e->flags & MDB_FLAGS_FAST_LEAVE)
+		print_string(PRINT_ANY, NULL, " %s", "fast_leave");
+	if (e->flags & MDB_FLAGS_STAR_EXCL)
+		print_string(PRINT_ANY, NULL, " %s", "added_by_star_ex");
+	if (e->flags & MDB_FLAGS_BLOCKED)
+		print_string(PRINT_ANY, NULL, " %s", "blocked");
 	close_json_array(PRINT_JSON, NULL);
 
 	if (e->vid)
@@ -157,7 +243,7 @@ static void print_mdb_entry(FILE *f, int ifindex, const struct br_mdb_entry *e,
 		__u32 timer = rta_getattr_u32(tb[MDBA_MDB_EATTR_TIMER]);
 
 		print_string(PRINT_ANY, "timer", " %s",
-			     format_timer(timer));
+			     format_timer(timer, 1));
 	}
 
 	print_nl();
@@ -175,8 +261,9 @@ static void br_print_mdb_entry(FILE *f, int ifindex, struct rtattr *attr,
 	rem = RTA_PAYLOAD(attr);
 	for (i = RTA_DATA(attr); RTA_OK(i, rem); i = RTA_NEXT(i, rem)) {
 		e = RTA_DATA(i);
-		parse_rtattr(etb, MDBA_MDB_EATTR_MAX, MDB_RTA(RTA_DATA(i)),
+		parse_rtattr_flags(etb, MDBA_MDB_EATTR_MAX, MDB_RTA(RTA_DATA(i)),
-			     RTA_PAYLOAD(i) - RTA_ALIGN(sizeof(*e)));
+				   RTA_PAYLOAD(i) - RTA_ALIGN(sizeof(*e)),
+				   NLA_F_NESTED);
 		print_mdb_entry(f, ifindex, e, n, etb);
 	}
 }
@@ -366,6 +453,25 @@ static int mdb_show(int argc, char **argv)
 	return 0;
 }
 
+static int mdb_parse_grp(const char *grp, struct br_mdb_entry *e)
+{
+	if (inet_pton(AF_INET, grp, &e->addr.u.ip4)) {
+		e->addr.proto = htons(ETH_P_IP);
+		return 0;
+	}
+	if (inet_pton(AF_INET6, grp, &e->addr.u.ip6)) {
+		e->addr.proto = htons(ETH_P_IPV6);
+		return 0;
+	}
+	if (ll_addr_a2n((char *)e->addr.u.mac_addr, sizeof(e->addr.u.mac_addr),
+			grp) == ETH_ALEN) {
+		e->addr.proto = 0;
+		return 0;
+	}
+
+	return -1;
+}
+
 static int mdb_modify(int cmd, int flags, int argc, char **argv)
 {
 	struct {
@@ -378,8 +484,8 @@ static int mdb_modify(int cmd, int flags, int argc, char **argv)
 		.n.nlmsg_type = cmd,
 		.bpm.family = PF_BRIDGE,
 	};
+	char *d = NULL, *p = NULL, *grp = NULL, *src = NULL;
 	struct br_mdb_entry entry = {};
-	char *d = NULL, *p = NULL, *grp = NULL;
 	short vid = 0;
 
 	while (argc > 0) {
@@ -400,6 +506,9 @@ static int mdb_modify(int cmd, int flags, int argc, char **argv)
 		} else if (strcmp(*argv, "vid") == 0) {
 			NEXT_ARG();
 			vid = atoi(*argv);
+		} else if (strcmp(*argv, "src") == 0) {
+			NEXT_ARG();
+			src = *argv;
 		} else {
 			if (matches(*argv, "help") == 0)
 				usage();
@@ -420,17 +529,31 @@ static int mdb_modify(int cmd, int flags, int argc, char **argv)
 	if (!entry.ifindex)
 		return nodev(p);
 
-	if (!inet_pton(AF_INET, grp, &entry.addr.u.ip4)) {
+	if (mdb_parse_grp(grp, &entry)) {
-		if (!inet_pton(AF_INET6, grp, &entry.addr.u.ip6)) {
+		fprintf(stderr, "Invalid address \"%s\"\n", grp);
-			fprintf(stderr, "Invalid address \"%s\"\n", grp);
+		return -1;
-			return -1;
+	}
-		} else
-			entry.addr.proto = htons(ETH_P_IPV6);
-	} else
-		entry.addr.proto = htons(ETH_P_IP);
 
 	entry.vid = vid;
 	addattr_l(&req.n, sizeof(req), MDBA_SET_ENTRY, &entry, sizeof(entry));
+	if (src) {
+		struct rtattr *nest = addattr_nest(&req.n, sizeof(req),
+						   MDBA_SET_ENTRY_ATTRS);
+		struct in6_addr src_ip6;
+		__be32 src_ip4;
+
+		nest->rta_type |= NLA_F_NESTED;
+		if (!inet_pton(AF_INET, src, &src_ip4)) {
+			if (!inet_pton(AF_INET6, src, &src_ip6)) {
+				fprintf(stderr, "Invalid source address \"%s\"\n", src);
+				return -1;
+			}
+			addattr_l(&req.n, sizeof(req), MDBE_ATTR_SOURCE, &src_ip6, sizeof(src_ip6));
+		} else {
+			addattr32(&req.n, sizeof(req), MDBE_ATTR_SOURCE, src_ip4);
+		}
+		addattr_nest_end(&req.n, nest);
+	}
 
 	if (rtnl_talk(&rth, &req.n, NULL) < 0)
 		return -1;

bridge/monitor.c

@@ -31,7 +31,7 @@ static int prefix_banner;
 
 static void usage(void)
 {
-	fprintf(stderr, "Usage: bridge monitor [file | link | fdb | mdb | all]\n");
+	fprintf(stderr, "Usage: bridge monitor [file | link | fdb | mdb | vlan | all]\n");
 	exit(-1);
 }
 
@@ -67,6 +67,12 @@ static int accept_msg(struct rtnl_ctrl_data *ctrl,
 		print_nlmsg_timestamp(fp, n);
 		return 0;
 
+	case RTM_NEWVLAN:
+	case RTM_DELVLAN:
+		if (prefix_banner)
+			fprintf(fp, "[VLAN]");
+		return print_vlan_rtm(n, arg, true, false);
+
 	default:
 		return 0;
 	}
@@ -79,6 +85,7 @@ int do_monitor(int argc, char **argv)
 	int llink = 0;
 	int lneigh = 0;
 	int lmdb = 0;
+	int lvlan = 0;
 
 	rtnl_close(&rth);
 
@@ -95,8 +102,12 @@ int do_monitor(int argc, char **argv)
 		} else if (matches(*argv, "mdb") == 0) {
 			lmdb = 1;
 			groups = 0;
+		} else if (matches(*argv, "vlan") == 0) {
+			lvlan = 1;
+			groups = 0;
 		} else if (strcmp(*argv, "all") == 0) {
 			groups = ~RTMGRP_TC;
+			lvlan = 1;
 			prefix_banner = 1;
 		} else if (matches(*argv, "help") == 0) {
 			usage();
@@ -134,6 +145,12 @@ int do_monitor(int argc, char **argv)
 
 	if (rtnl_open(&rth, groups) < 0)
 		exit(1);
+
+	if (lvlan && rtnl_add_nl_group(&rth, RTNLGRP_BRVLAN) < 0) {
+		fprintf(stderr, "Failed to add bridge vlan group to list\n");
+		exit(1);
+	}
+
 	ll_init_map(&rth);
 
 	if (rtnl_listen(&rth, accept_msg, stdout) < 0)

bridge/vlan.c

@@ -9,6 +9,7 @@
 #include <linux/if_bridge.h>
 #include <linux/if_ether.h>
 #include <string.h>
+#include <errno.h>
 
 #include "json_print.h"
 #include "libnetlink.h"
@@ -16,6 +17,7 @@
 #include "utils.h"
 
 static unsigned int filter_index, filter_vlan;
+static int vlan_rtm_cur_ifidx = -1;
 
 enum vlan_show_subject {
 	VLAN_SHOW_VLAN,
@@ -33,8 +35,24 @@ static void usage(void)
 		"Usage: bridge vlan { add | del } vid VLAN_ID dev DEV [ tunnel_info id TUNNEL_ID ]\n"
 		"                                                     [ pvid ] [ untagged ]\n"
 		"                                                     [ self ] [ master ]\n"
+		"       bridge vlan { set } vid VLAN_ID dev DEV [ state STP_STATE ]\n"
+		"                                               [ mcast_router MULTICAST_ROUTER ]\n"
 		"       bridge vlan { show } [ dev DEV ] [ vid VLAN_ID ]\n"
-		"       bridge vlan { tunnelshow } [ dev DEV ] [ vid VLAN_ID ]\n");
+		"       bridge vlan { tunnelshow } [ dev DEV ] [ vid VLAN_ID ]\n"
+		"       bridge vlan global { set } vid VLAN_ID dev DEV\n"
+		"                      [ mcast_snooping MULTICAST_SNOOPING ]\n"
+		"                      [ mcast_querier MULTICAST_QUERIER ]\n"
+		"                      [ mcast_igmp_version IGMP_VERSION ]\n"
+		"                      [ mcast_mld_version MLD_VERSION ]\n"
+		"                      [ mcast_last_member_count LAST_MEMBER_COUNT ]\n"
+		"                      [ mcast_last_member_interval LAST_MEMBER_INTERVAL ]\n"
+		"                      [ mcast_startup_query_count STARTUP_QUERY_COUNT ]\n"
+		"                      [ mcast_startup_query_interval STARTUP_QUERY_INTERVAL ]\n"
+		"                      [ mcast_membership_interval MEMBERSHIP_INTERVAL ]\n"
+		"                      [ mcast_querier_interval QUERIER_INTERVAL ]\n"
+		"                      [ mcast_query_interval QUERY_INTERVAL ]\n"
+		"                      [ mcast_query_response_interval QUERY_RESPONSE_INTERVAL ]\n"
+		"       bridge vlan global { show } [ dev DEV ] [ vid VLAN_ID ]\n");
 	exit(-1);
 }
 
@@ -241,6 +259,277 @@ static int vlan_modify(int cmd, int argc, char **argv)
 	return 0;
 }
 
+static int vlan_option_set(int argc, char **argv)
+{
+	struct {
+		struct nlmsghdr	n;
+		struct br_vlan_msg	bvm;
+		char			buf[1024];
+	} req = {
+		.n.nlmsg_len = NLMSG_LENGTH(sizeof(struct br_vlan_msg)),
+		.n.nlmsg_flags = NLM_F_REQUEST,
+		.n.nlmsg_type = RTM_NEWVLAN,
+		.bvm.family = PF_BRIDGE,
+	};
+	struct bridge_vlan_info vinfo = {};
+	struct rtattr *afspec;
+	char *d = NULL;
+	short vid = -1;
+
+	afspec = addattr_nest(&req.n, sizeof(req), BRIDGE_VLANDB_ENTRY);
+	afspec->rta_type |= NLA_F_NESTED;
+	while (argc > 0) {
+		if (strcmp(*argv, "dev") == 0) {
+			NEXT_ARG();
+			d = *argv;
+			req.bvm.ifindex = ll_name_to_index(d);
+			if (req.bvm.ifindex == 0) {
+				fprintf(stderr,
+					"Cannot find network device \"%s\"\n",
+					d);
+				return -1;
+			}
+		} else if (strcmp(*argv, "vid") == 0) {
+			short vid_end = -1;
+			char *p;
+
+			NEXT_ARG();
+			p = strchr(*argv, '-');
+			if (p) {
+				*p = '\0';
+				p++;
+				vid = atoi(*argv);
+				vid_end = atoi(p);
+				if (vid >= vid_end || vid_end >= 4096) {
+					fprintf(stderr, "Invalid VLAN range \"%hu-%hu\"\n",
+						vid, vid_end);
+					return -1;
+				}
+			} else {
+				vid = atoi(*argv);
+			}
+			if (vid >= 4096) {
+				fprintf(stderr, "Invalid VLAN ID \"%hu\"\n",
+					vid);
+				return -1;
+			}
+
+			vinfo.flags = BRIDGE_VLAN_INFO_ONLY_OPTS;
+			vinfo.vid = vid;
+			addattr_l(&req.n, sizeof(req), BRIDGE_VLANDB_ENTRY_INFO,
+				  &vinfo, sizeof(vinfo));
+			if (vid_end != -1)
+				addattr16(&req.n, sizeof(req),
+					  BRIDGE_VLANDB_ENTRY_RANGE, vid_end);
+		} else if (strcmp(*argv, "state") == 0) {
+			char *endptr;
+			int state;
+
+			NEXT_ARG();
+			state = strtol(*argv, &endptr, 10);
+			if (!(**argv != '\0' && *endptr == '\0'))
+				state = parse_stp_state(*argv);
+			if (state == -1) {
+				fprintf(stderr, "Error: invalid STP state\n");
+				return -1;
+			}
+			addattr8(&req.n, sizeof(req), BRIDGE_VLANDB_ENTRY_STATE,
+				 state);
+		} else if (strcmp(*argv, "mcast_router") == 0) {
+			__u8 mcast_router;
+
+			NEXT_ARG();
+			if (get_u8(&mcast_router, *argv, 0))
+				invarg("invalid mcast_router", *argv);
+			addattr8(&req.n, sizeof(req),
+				 BRIDGE_VLANDB_ENTRY_MCAST_ROUTER,
+				 mcast_router);
+		} else {
+			if (matches(*argv, "help") == 0)
+				NEXT_ARG();
+		}
+		argc--; argv++;
+	}
+	addattr_nest_end(&req.n, afspec);
+
+	if (d == NULL || vid == -1) {
+		fprintf(stderr, "Device and VLAN ID are required arguments.\n");
+		return -1;
+	}
+
+	if (rtnl_talk(&rth, &req.n, NULL) < 0)
+		return -1;
+
+	return 0;
+}
+
+static int vlan_global_option_set(int argc, char **argv)
+{
+	struct {
+		struct nlmsghdr	n;
+		struct br_vlan_msg	bvm;
+		char			buf[1024];
+	} req = {
+		.n.nlmsg_len = NLMSG_LENGTH(sizeof(struct br_vlan_msg)),
+		.n.nlmsg_flags = NLM_F_REQUEST,
+		.n.nlmsg_type = RTM_NEWVLAN,
+		.bvm.family = PF_BRIDGE,
+	};
+	struct rtattr *afspec;
+	short vid_end = -1;
+	char *d = NULL;
+	short vid = -1;
+	__u64 val64;
+	__u32 val32;
+	__u8 val8;
+
+	afspec = addattr_nest(&req.n, sizeof(req),
+			      BRIDGE_VLANDB_GLOBAL_OPTIONS);
+	afspec->rta_type |= NLA_F_NESTED;
+	while (argc > 0) {
+		if (strcmp(*argv, "dev") == 0) {
+			NEXT_ARG();
+			d = *argv;
+			req.bvm.ifindex = ll_name_to_index(d);
+			if (req.bvm.ifindex == 0) {
+				fprintf(stderr, "Cannot find network device \"%s\"\n",
+					d);
+				return -1;
+			}
+		} else if (strcmp(*argv, "vid") == 0) {
+			char *p;
+
+			NEXT_ARG();
+			p = strchr(*argv, '-');
+			if (p) {
+				*p = '\0';
+				p++;
+				vid = atoi(*argv);
+				vid_end = atoi(p);
+				if (vid >= vid_end || vid_end >= 4096) {
+					fprintf(stderr, "Invalid VLAN range \"%hu-%hu\"\n",
+						vid, vid_end);
+					return -1;
+				}
+			} else {
+				vid = atoi(*argv);
+			}
+			if (vid >= 4096) {
+				fprintf(stderr, "Invalid VLAN ID \"%hu\"\n",
+					vid);
+				return -1;
+			}
+			addattr16(&req.n, sizeof(req), BRIDGE_VLANDB_GOPTS_ID,
+				  vid);
+			if (vid_end != -1)
+				addattr16(&req.n, sizeof(req),
+					  BRIDGE_VLANDB_GOPTS_RANGE, vid_end);
+		} else if (strcmp(*argv, "mcast_snooping") == 0) {
+			NEXT_ARG();
+			if (get_u8(&val8, *argv, 0))
+				invarg("invalid mcast_snooping", *argv);
+			addattr8(&req.n, 1024,
+				 BRIDGE_VLANDB_GOPTS_MCAST_SNOOPING, val8);
+		} else if (strcmp(*argv, "mcast_querier") == 0) {
+			NEXT_ARG();
+			if (get_u8(&val8, *argv, 0))
+				invarg("invalid mcast_querier", *argv);
+			addattr8(&req.n, 1024,
+				 BRIDGE_VLANDB_GOPTS_MCAST_QUERIER, val8);
+		} else if (strcmp(*argv, "mcast_igmp_version") == 0) {
+			NEXT_ARG();
+			if (get_u8(&val8, *argv, 0))
+				invarg("invalid mcast_igmp_version", *argv);
+			addattr8(&req.n, 1024,
+				 BRIDGE_VLANDB_GOPTS_MCAST_IGMP_VERSION, val8);
+		} else if (strcmp(*argv, "mcast_mld_version") == 0) {
+			NEXT_ARG();
+			if (get_u8(&val8, *argv, 0))
+				invarg("invalid mcast_mld_version", *argv);
+			addattr8(&req.n, 1024,
+				 BRIDGE_VLANDB_GOPTS_MCAST_MLD_VERSION, val8);
+		} else if (strcmp(*argv, "mcast_last_member_count") == 0) {
+			NEXT_ARG();
+			if (get_u32(&val32, *argv, 0))
+				invarg("invalid mcast_last_member_count", *argv);
+			addattr32(&req.n, 1024,
+				  BRIDGE_VLANDB_GOPTS_MCAST_LAST_MEMBER_CNT,
+				  val32);
+		} else if (strcmp(*argv, "mcast_startup_query_count") == 0) {
+			NEXT_ARG();
+			if (get_u32(&val32, *argv, 0))
+				invarg("invalid mcast_startup_query_count",
+				       *argv);
+			addattr32(&req.n, 1024,
+				  BRIDGE_VLANDB_GOPTS_MCAST_STARTUP_QUERY_CNT,
+				  val32);
+		} else if (strcmp(*argv, "mcast_last_member_interval") == 0) {
+			NEXT_ARG();
+			if (get_u64(&val64, *argv, 0))
+				invarg("invalid mcast_last_member_interval",
+				       *argv);
+			addattr64(&req.n, 1024,
+				  BRIDGE_VLANDB_GOPTS_MCAST_LAST_MEMBER_INTVL,
+				  val64);
+		} else if (strcmp(*argv, "mcast_membership_interval") == 0) {
+			NEXT_ARG();
+			if (get_u64(&val64, *argv, 0))
+				invarg("invalid mcast_membership_interval",
+				       *argv);
+			addattr64(&req.n, 1024,
+				  BRIDGE_VLANDB_GOPTS_MCAST_MEMBERSHIP_INTVL,
+				  val64);
+		} else if (strcmp(*argv, "mcast_querier_interval") == 0) {
+			NEXT_ARG();
+			if (get_u64(&val64, *argv, 0))
+				invarg("invalid mcast_querier_interval",
+				       *argv);
+			addattr64(&req.n, 1024,
+				  BRIDGE_VLANDB_GOPTS_MCAST_QUERIER_INTVL,
+				  val64);
+		} else if (strcmp(*argv, "mcast_query_interval") == 0) {
+			NEXT_ARG();
+			if (get_u64(&val64, *argv, 0))
+				invarg("invalid mcast_query_interval",
+				       *argv);
+			addattr64(&req.n, 1024,
+				  BRIDGE_VLANDB_GOPTS_MCAST_QUERY_INTVL,
+				  val64);
+		} else if (strcmp(*argv, "mcast_query_response_interval") == 0) {
+			NEXT_ARG();
+			if (get_u64(&val64, *argv, 0))
+				invarg("invalid mcast_query_response_interval",
+				       *argv);
+			addattr64(&req.n, 1024,
+				  BRIDGE_VLANDB_GOPTS_MCAST_QUERY_RESPONSE_INTVL,
+				  val64);
+		} else if (strcmp(*argv, "mcast_startup_query_interval") == 0) {
+			NEXT_ARG();
+			if (get_u64(&val64, *argv, 0))
+				invarg("invalid mcast_startup_query_interval",
+				       *argv);
+			addattr64(&req.n, 1024,
+				  BRIDGE_VLANDB_GOPTS_MCAST_STARTUP_QUERY_INTVL,
+				  val64);
+		} else {
+			if (strcmp(*argv, "help") == 0)
+				NEXT_ARG();
+		}
+		argc--; argv++;
+	}
+	addattr_nest_end(&req.n, afspec);
+
+	if (d == NULL || vid == -1) {
+		fprintf(stderr, "Device and VLAN ID are required arguments.\n");
+		return -1;
+	}
+
+	if (rtnl_talk(&rth, &req.n, NULL) < 0)
+		return -1;
+
+	return 0;
+}
+
 /* In order to use this function for both filtering and non-filtering cases
  * we need to make it a tristate:
  * return -1 - if filtering we've gone over so don't continue
@@ -422,14 +711,8 @@ static void print_vlan_flags(__u16 flags)
 	close_json_array(PRINT_JSON, NULL);
 }
 
-static void print_one_vlan_stats(const struct bridge_vlan_xstats *vstats)
+static void __print_one_vlan_stats(const struct bridge_vlan_xstats *vstats)
 {
-	open_json_object(NULL);
-
-	print_hu(PRINT_ANY, "vid", "%hu", vstats->vid);
-	print_vlan_flags(vstats->flags);
-	print_nl();
-
 	print_string(PRINT_FP, NULL, "%-" __stringify(IFNAMSIZ) "s    ", "");
 	print_lluint(PRINT_ANY, "rx_bytes", "RX: %llu bytes",
 		     vstats->rx_bytes);
@@ -441,6 +724,16 @@ static void print_one_vlan_stats(const struct bridge_vlan_xstats *vstats)
 		     vstats->tx_bytes);
 	print_lluint(PRINT_ANY, "tx_packets", " %llu packets\n",
 		     vstats->tx_packets);
+}
+
+static void print_one_vlan_stats(const struct bridge_vlan_xstats *vstats)
+{
+	open_json_object(NULL);
+
+	print_hu(PRINT_ANY, "vid", "%hu", vstats->vid);
+	print_vlan_flags(vstats->flags);
+	print_nl();
+	__print_one_vlan_stats(vstats);
 
 	close_json_object();
 }
@@ -521,6 +814,288 @@ static int print_vlan_stats(struct nlmsghdr *n, void *arg)
 	return 0;
 }
 
+static void print_vlan_router_ports(struct rtattr *rattr)
+{
+	int rem = RTA_PAYLOAD(rattr);
+	struct rtattr *i;
+
+	print_string(PRINT_FP, NULL, "%-" __stringify(IFNAMSIZ) "s    ", "");
+	open_json_array(PRINT_ANY, is_json_context() ? "router_ports" :
+						       "router ports: ");
+	for (i = RTA_DATA(rattr); RTA_OK(i, rem); i = RTA_NEXT(i, rem)) {
+		uint32_t *port_ifindex = RTA_DATA(i);
+		const char *port_ifname = ll_index_to_name(*port_ifindex);
+
+		open_json_object(NULL);
+		if (show_stats && i != RTA_DATA(rattr)) {
+			print_nl();
+			/* start: IFNAMSIZ + 4 + strlen("router ports: ") */
+			print_string(PRINT_FP, NULL,
+				     "%-" __stringify(IFNAMSIZ) "s    "
+				     "              ",
+				     "");
+		}
+		print_string(PRINT_ANY, "port", "%s ", port_ifname);
+		if (show_stats)
+			br_print_router_port_stats(i);
+		close_json_object();
+	}
+	close_json_array(PRINT_JSON, NULL);
+	print_nl();
+}
+
+static void print_vlan_global_opts(struct rtattr *a, int ifindex)
+{
+	struct rtattr *vtb[BRIDGE_VLANDB_GOPTS_MAX + 1], *vattr;
+	__u16 vid, vrange = 0;
+
+	if ((a->rta_type & NLA_TYPE_MASK) != BRIDGE_VLANDB_GLOBAL_OPTIONS)
+		return;
+
+	parse_rtattr_flags(vtb, BRIDGE_VLANDB_GOPTS_MAX, RTA_DATA(a),
+			   RTA_PAYLOAD(a), NLA_F_NESTED);
+	vid = rta_getattr_u16(vtb[BRIDGE_VLANDB_GOPTS_ID]);
+	if (vtb[BRIDGE_VLANDB_GOPTS_RANGE])
+		vrange = rta_getattr_u16(vtb[BRIDGE_VLANDB_GOPTS_RANGE]);
+	else
+		vrange = vid;
+
+	if (filter_vlan && (filter_vlan < vid || filter_vlan > vrange))
+		return;
+
+	if (vlan_rtm_cur_ifidx != ifindex) {
+		open_vlan_port(ifindex, VLAN_SHOW_VLAN);
+		open_json_object(NULL);
+		vlan_rtm_cur_ifidx = ifindex;
+	} else {
+		open_json_object(NULL);
+		print_string(PRINT_FP, NULL, "%-" __stringify(IFNAMSIZ) "s  ", "");
+	}
+	print_range("vlan", vid, vrange);
+	print_nl();
+	print_string(PRINT_FP, NULL, "%-" __stringify(IFNAMSIZ) "s    ", "");
+	if (vtb[BRIDGE_VLANDB_GOPTS_MCAST_SNOOPING]) {
+		vattr = vtb[BRIDGE_VLANDB_GOPTS_MCAST_SNOOPING];
+		print_uint(PRINT_ANY, "mcast_snooping", "mcast_snooping %u ",
+			   rta_getattr_u8(vattr));
+	}
+	if (vtb[BRIDGE_VLANDB_GOPTS_MCAST_QUERIER]) {
+		vattr = vtb[BRIDGE_VLANDB_GOPTS_MCAST_QUERIER];
+		print_uint(PRINT_ANY, "mcast_querier", "mcast_querier %u ",
+			   rta_getattr_u8(vattr));
+	}
+	if (vtb[BRIDGE_VLANDB_GOPTS_MCAST_IGMP_VERSION]) {
+		vattr = vtb[BRIDGE_VLANDB_GOPTS_MCAST_IGMP_VERSION];
+		print_uint(PRINT_ANY, "mcast_igmp_version",
+			   "mcast_igmp_version %u ", rta_getattr_u8(vattr));
+	}
+	if (vtb[BRIDGE_VLANDB_GOPTS_MCAST_MLD_VERSION]) {
+		vattr = vtb[BRIDGE_VLANDB_GOPTS_MCAST_MLD_VERSION];
+		print_uint(PRINT_ANY, "mcast_mld_version",
+			   "mcast_mld_version %u ", rta_getattr_u8(vattr));
+	}
+	if (vtb[BRIDGE_VLANDB_GOPTS_MCAST_MLD_VERSION]) {
+		vattr = vtb[BRIDGE_VLANDB_GOPTS_MCAST_LAST_MEMBER_CNT];
+		print_uint(PRINT_ANY, "mcast_last_member_count",
+			   "mcast_last_member_count %u ",
+			   rta_getattr_u32(vattr));
+	}
+	if (vtb[BRIDGE_VLANDB_GOPTS_MCAST_LAST_MEMBER_INTVL]) {
+		vattr = vtb[BRIDGE_VLANDB_GOPTS_MCAST_LAST_MEMBER_INTVL];
+		print_lluint(PRINT_ANY, "mcast_last_member_interval",
+			     "mcast_last_member_interval %llu ",
+			     rta_getattr_u64(vattr));
+	}
+	if (vtb[BRIDGE_VLANDB_GOPTS_MCAST_STARTUP_QUERY_CNT]) {
+		vattr = vtb[BRIDGE_VLANDB_GOPTS_MCAST_STARTUP_QUERY_CNT];
+		print_uint(PRINT_ANY, "mcast_startup_query_count",
+			   "mcast_startup_query_count %u ",
+			   rta_getattr_u32(vattr));
+	}
+	if (vtb[BRIDGE_VLANDB_GOPTS_MCAST_STARTUP_QUERY_INTVL]) {
+		vattr = vtb[BRIDGE_VLANDB_GOPTS_MCAST_STARTUP_QUERY_INTVL];
+		print_lluint(PRINT_ANY, "mcast_startup_query_interval",
+			     "mcast_startup_query_interval %llu ",
+			     rta_getattr_u64(vattr));
+	}
+	if (vtb[BRIDGE_VLANDB_GOPTS_MCAST_MEMBERSHIP_INTVL]) {
+		vattr = vtb[BRIDGE_VLANDB_GOPTS_MCAST_MEMBERSHIP_INTVL];
+		print_lluint(PRINT_ANY, "mcast_membership_interval",
+			     "mcast_membership_interval %llu ",
+			     rta_getattr_u64(vattr));
+	}
+	if (vtb[BRIDGE_VLANDB_GOPTS_MCAST_QUERIER_INTVL]) {
+		vattr = vtb[BRIDGE_VLANDB_GOPTS_MCAST_QUERIER_INTVL];
+		print_lluint(PRINT_ANY, "mcast_querier_interval",
+			     "mcast_querier_interval %llu ",
+			     rta_getattr_u64(vattr));
+	}
+	if (vtb[BRIDGE_VLANDB_GOPTS_MCAST_QUERY_INTVL]) {
+		vattr = vtb[BRIDGE_VLANDB_GOPTS_MCAST_QUERY_INTVL];
+		print_lluint(PRINT_ANY, "mcast_query_interval",
+			     "mcast_query_interval %llu ",
+			     rta_getattr_u64(vattr));
+	}
+	if (vtb[BRIDGE_VLANDB_GOPTS_MCAST_QUERY_RESPONSE_INTVL]) {
+		vattr = vtb[BRIDGE_VLANDB_GOPTS_MCAST_QUERY_RESPONSE_INTVL];
+		print_lluint(PRINT_ANY, "mcast_query_response_interval",
+			     "mcast_query_response_interval %llu ",
+			     rta_getattr_u64(vattr));
+	}
+	print_nl();
+	if (vtb[BRIDGE_VLANDB_GOPTS_MCAST_ROUTER_PORTS]) {
+		vattr = RTA_DATA(vtb[BRIDGE_VLANDB_GOPTS_MCAST_ROUTER_PORTS]);
+		print_vlan_router_ports(vattr);
+	}
+	close_json_object();
+}
+
+static void print_vlan_opts(struct rtattr *a, int ifindex)
+{
+	struct rtattr *vtb[BRIDGE_VLANDB_ENTRY_MAX + 1], *vattr;
+	struct bridge_vlan_xstats vstats;
+	struct bridge_vlan_info *vinfo;
+	__u16 vrange = 0;
+	__u8 state = 0;
+
+	if ((a->rta_type & NLA_TYPE_MASK) != BRIDGE_VLANDB_ENTRY)
+		return;
+
+	parse_rtattr_flags(vtb, BRIDGE_VLANDB_ENTRY_MAX, RTA_DATA(a),
+			   RTA_PAYLOAD(a), NLA_F_NESTED);
+	vinfo = RTA_DATA(vtb[BRIDGE_VLANDB_ENTRY_INFO]);
+
+	memset(&vstats, 0, sizeof(vstats));
+	if (vtb[BRIDGE_VLANDB_ENTRY_RANGE])
+		vrange = rta_getattr_u16(vtb[BRIDGE_VLANDB_ENTRY_RANGE]);
+	else
+		vrange = vinfo->vid;
+
+	if (filter_vlan && (filter_vlan < vinfo->vid || filter_vlan > vrange))
+		return;
+
+	if (vtb[BRIDGE_VLANDB_ENTRY_STATE])
+		state = rta_getattr_u8(vtb[BRIDGE_VLANDB_ENTRY_STATE]);
+
+	if (vtb[BRIDGE_VLANDB_ENTRY_STATS]) {
+		struct rtattr *stb[BRIDGE_VLANDB_STATS_MAX+1];
+		struct rtattr *attr;
+
+		attr = vtb[BRIDGE_VLANDB_ENTRY_STATS];
+		parse_rtattr(stb, BRIDGE_VLANDB_STATS_MAX, RTA_DATA(attr),
+			     RTA_PAYLOAD(attr));
+
+		if (stb[BRIDGE_VLANDB_STATS_RX_BYTES]) {
+			attr = stb[BRIDGE_VLANDB_STATS_RX_BYTES];
+			vstats.rx_bytes = rta_getattr_u64(attr);
+		}
+		if (stb[BRIDGE_VLANDB_STATS_RX_PACKETS]) {
+			attr = stb[BRIDGE_VLANDB_STATS_RX_PACKETS];
+			vstats.rx_packets = rta_getattr_u64(attr);
+		}
+		if (stb[BRIDGE_VLANDB_STATS_TX_PACKETS]) {
+			attr = stb[BRIDGE_VLANDB_STATS_TX_PACKETS];
+			vstats.tx_packets = rta_getattr_u64(attr);
+		}
+		if (stb[BRIDGE_VLANDB_STATS_TX_BYTES]) {
+			attr = stb[BRIDGE_VLANDB_STATS_TX_BYTES];
+			vstats.tx_bytes = rta_getattr_u64(attr);
+		}
+	}
+
+	if (vlan_rtm_cur_ifidx != ifindex) {
+		open_vlan_port(ifindex, VLAN_SHOW_VLAN);
+		open_json_object(NULL);
+		vlan_rtm_cur_ifidx = ifindex;
+	} else {
+		open_json_object(NULL);
+		print_string(PRINT_FP, NULL, "%-" __stringify(IFNAMSIZ) "s  ", "");
+	}
+	print_range("vlan", vinfo->vid, vrange);
+	print_vlan_flags(vinfo->flags);
+	print_nl();
+	print_string(PRINT_FP, NULL, "%-" __stringify(IFNAMSIZ) "s    ", "");
+	print_stp_state(state);
+	if (vtb[BRIDGE_VLANDB_ENTRY_MCAST_ROUTER]) {
+		vattr = vtb[BRIDGE_VLANDB_ENTRY_MCAST_ROUTER];
+		print_uint(PRINT_ANY, "mcast_router", "mcast_router %u ",
+			   rta_getattr_u8(vattr));
+	}
+	print_nl();
+	if (show_stats)
+		__print_one_vlan_stats(&vstats);
+	close_json_object();
+}
+
+int print_vlan_rtm(struct nlmsghdr *n, void *arg, bool monitor, bool global_only)
+{
+	struct br_vlan_msg *bvm = NLMSG_DATA(n);
+	int len = n->nlmsg_len;
+	struct rtattr *a;
+	int rem;
+
+	if (n->nlmsg_type != RTM_NEWVLAN && n->nlmsg_type != RTM_DELVLAN &&
+	    n->nlmsg_type != RTM_GETVLAN) {
+		fprintf(stderr, "Unknown vlan rtm message: %08x %08x %08x\n",
+			n->nlmsg_len, n->nlmsg_type, n->nlmsg_flags);
+		return 0;
+	}
+
+	len -= NLMSG_LENGTH(sizeof(*bvm));
+	if (len < 0) {
+		fprintf(stderr, "BUG: wrong nlmsg len %d\n", len);
+		return -1;
+	}
+
+	if (bvm->family != AF_BRIDGE)
+		return 0;
+
+	if (filter_index && filter_index != bvm->ifindex)
+		return 0;
+
+	if (n->nlmsg_type == RTM_DELVLAN)
+		print_bool(PRINT_ANY, "deleted", "Deleted ", true);
+
+	if (monitor)
+		vlan_rtm_cur_ifidx = -1;
+
+	if (vlan_rtm_cur_ifidx != -1 && vlan_rtm_cur_ifidx != bvm->ifindex) {
+		close_vlan_port();
+		vlan_rtm_cur_ifidx = -1;
+	}
+
+	rem = len;
+	for (a = BRVLAN_RTA(bvm); RTA_OK(a, rem); a = RTA_NEXT(a, rem)) {
+		unsigned short rta_type = a->rta_type & NLA_TYPE_MASK;
+
+		/* skip unknown attributes */
+		if (rta_type > BRIDGE_VLANDB_MAX ||
+		    (global_only && rta_type != BRIDGE_VLANDB_GLOBAL_OPTIONS))
+			continue;
+
+		switch (rta_type) {
+		case BRIDGE_VLANDB_ENTRY:
+			print_vlan_opts(a, bvm->ifindex);
+			break;
+		case BRIDGE_VLANDB_GLOBAL_OPTIONS:
+			print_vlan_global_opts(a, bvm->ifindex);
+			break;
+		}
+	}
+
+	return 0;
+}
+
+static int print_vlan_rtm_filter(struct nlmsghdr *n, void *arg)
+{
+	return print_vlan_rtm(n, arg, false, false);
+}
+
+static int print_vlan_rtm_global_filter(struct nlmsghdr *n, void *arg)
+{
+	return print_vlan_rtm(n, arg, false, true);
+}
+
 static int vlan_show(int argc, char **argv, int subject)
 {
 	char *filter_dev = NULL;
@@ -549,6 +1124,34 @@ static int vlan_show(int argc, char **argv, int subject)
 
 	new_json_obj(json);
 
+	/* if show_details is true then use the new bridge vlan dump format */
+	if (show_details && subject == VLAN_SHOW_VLAN) {
+		__u32 dump_flags = show_stats ? BRIDGE_VLANDB_DUMPF_STATS : 0;
+
+		if (rtnl_brvlandump_req(&rth, PF_BRIDGE, dump_flags) < 0) {
+			perror("Cannot send dump request");
+			exit(1);
+		}
+
+		if (!is_json_context()) {
+			printf("%-" __stringify(IFNAMSIZ) "s  %-"
+			       __stringify(VLAN_ID_LEN) "s", "port",
+			       "vlan-id");
+			printf("\n");
+		}
+
+		ret = rtnl_dump_filter(&rth, print_vlan_rtm_filter, &subject);
+		if (ret < 0) {
+			fprintf(stderr, "Dump terminated\n");
+			exit(1);
+		}
+
+		if (vlan_rtm_cur_ifidx != -1)
+			close_vlan_port();
+
+		goto out;
+	}
+
 	if (!show_stats) {
 		if (rtnl_linkdump_req_filter(&rth, PF_BRIDGE,
 					     (compress_vlans ?
@@ -602,6 +1205,62 @@ static int vlan_show(int argc, char **argv, int subject)
 		}
 	}
 
+out:
+	delete_json_obj();
+	fflush(stdout);
+	return 0;
+}
+
+static int vlan_global_show(int argc, char **argv)
+{
+	__u32 dump_flags = BRIDGE_VLANDB_DUMPF_GLOBAL;
+	int ret = 0, subject = VLAN_SHOW_VLAN;
+	char *filter_dev = NULL;
+
+	while (argc > 0) {
+		if (strcmp(*argv, "dev") == 0) {
+			NEXT_ARG();
+			if (filter_dev)
+				duparg("dev", *argv);
+			filter_dev = *argv;
+		} else if (strcmp(*argv, "vid") == 0) {
+			NEXT_ARG();
+			if (filter_vlan)
+				duparg("vid", *argv);
+			filter_vlan = atoi(*argv);
+		}
+		argc--; argv++;
+	}
+
+	if (filter_dev) {
+		filter_index = ll_name_to_index(filter_dev);
+		if (!filter_index)
+			return nodev(filter_dev);
+	}
+
+	new_json_obj(json);
+
+	if (rtnl_brvlandump_req(&rth, PF_BRIDGE, dump_flags) < 0) {
+		perror("Cannot send dump request");
+		exit(1);
+	}
+
+	if (!is_json_context()) {
+		printf("%-" __stringify(IFNAMSIZ) "s  %-"
+		       __stringify(VLAN_ID_LEN) "s", "port",
+		       "vlan-id");
+		printf("\n");
+	}
+
+	ret = rtnl_dump_filter(&rth, print_vlan_rtm_global_filter, &subject);
+	if (ret < 0) {
+		fprintf(stderr, "Dump terminated\n");
+		exit(1);
+	}
+
+	if (vlan_rtm_cur_ifidx != -1)
+		close_vlan_port();
+
 	delete_json_obj();
 	fflush(stdout);
 	return 0;
@@ -651,6 +1310,24 @@ void print_vlan_info(struct rtattr *tb, int ifindex)
 		close_vlan_port();
 }
 
+static int vlan_global(int argc, char **argv)
+{
+	if (argc > 0) {
+		if (strcmp(*argv, "show") == 0 ||
+		    strcmp(*argv, "lst") == 0 ||
+		    strcmp(*argv, "list") == 0)
+			return vlan_global_show(argc-1, argv+1);
+		else if (strcmp(*argv, "set") == 0)
+			return vlan_global_option_set(argc-1, argv+1);
+		else
+			usage();
+	} else {
+		return vlan_global_show(0, NULL);
+	}
+
+	return 0;
+}
+
 int do_vlan(int argc, char **argv)
 {
 	ll_init_map(&rth);
@@ -667,6 +1344,10 @@ int do_vlan(int argc, char **argv)
 		if (matches(*argv, "tunnelshow") == 0) {
 			return vlan_show(argc-1, argv+1, VLAN_SHOW_TUNNELINFO);
 		}
+		if (matches(*argv, "set") == 0)
+			return vlan_option_set(argc-1, argv+1);
+		if (strcmp(*argv, "global") == 0)
+			return vlan_global(argc-1, argv+1);
 		if (matches(*argv, "help") == 0)
 			usage();
 	} else {

configure

@@ -1,8 +1,10 @@
 #!/bin/sh
 # SPDX-License-Identifier: GPL-2.0
 # This is not an autoconf generated configure
-#
+
-INCLUDE=${1:-"$PWD/include"}
+INCLUDE="$PWD/include"
+PREFIX="/usr"
+LIBDIR="\${prefix}/lib"
 
 # Output file which is input to Makefile
 CONFIG=config.mk
@@ -148,6 +150,15 @@ EOF
 	rm -f $TMPDIR/ipttest.c $TMPDIR/ipttest
 }
 
+check_lib_dir()
+{
+	LIBDIR=$(echo $LIBDIR | sed "s|\${prefix}|$PREFIX|")
+
+	echo -n "lib directory: "
+	echo "$LIBDIR"
+	echo "LIBDIR:=$LIBDIR" >> $CONFIG
+}
+
 check_ipt()
 {
 	if ! grep TC_CONFIG_XT $CONFIG > /dev/null; then
@@ -197,6 +208,31 @@ EOF
     rm -f $TMPDIR/setnstest.c $TMPDIR/setnstest
 }
 
+check_name_to_handle_at()
+{
+    cat >$TMPDIR/name_to_handle_at_test.c <<EOF
+#define _GNU_SOURCE
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+int main(int argc, char **argv)
+{
+	struct file_handle *fhp;
+	int mount_id, flags, dirfd;
+	char *pathname;
+	name_to_handle_at(dirfd, pathname, fhp, &mount_id, flags);
+	return 0;
+}
+EOF
+    if $CC -I$INCLUDE -o $TMPDIR/name_to_handle_at_test $TMPDIR/name_to_handle_at_test.c >/dev/null 2>&1; then
+        echo "yes"
+        echo "CFLAGS += -DHAVE_HANDLE_AT" >>$CONFIG
+    else
+        echo "no"
+    fi
+    rm -f $TMPDIR/name_to_handle_at_test.c $TMPDIR/name_to_handle_at_test
+}
+
 check_ipset()
 {
     cat >$TMPDIR/ipsettest.c <<EOF
@@ -208,7 +244,7 @@ typedef unsigned short ip_set_id_t;
 #include <linux/netfilter/xt_set.h>
 
 struct xt_set_info info;
-#if IPSET_PROTOCOL == 6
+#if IPSET_PROTOCOL == 6 || IPSET_PROTOCOL == 7
 int main(void)
 {
 	return IPSET_MAXNAMELEN;
@@ -240,6 +276,111 @@ check_elf()
     fi
 }
 
+have_libbpf_basic()
+{
+    cat >$TMPDIR/libbpf_test.c <<EOF
+#include <bpf/libbpf.h>
+int main(int argc, char **argv) {
+    bpf_program__set_autoload(NULL, false);
+    bpf_map__ifindex(NULL);
+    bpf_map__set_pin_path(NULL, NULL);
+    bpf_object__open_file(NULL, NULL);
+    return 0;
+}
+EOF
+
+    $CC -o $TMPDIR/libbpf_test $TMPDIR/libbpf_test.c $LIBBPF_CFLAGS $LIBBPF_LDLIBS >/dev/null 2>&1
+    local ret=$?
+
+    rm -f $TMPDIR/libbpf_test.c $TMPDIR/libbpf_test
+    return $ret
+}
+
+have_libbpf_sec_name()
+{
+    cat >$TMPDIR/libbpf_sec_test.c <<EOF
+#include <bpf/libbpf.h>
+int main(int argc, char **argv) {
+    void *ptr;
+    bpf_program__section_name(NULL);
+    return 0;
+}
+EOF
+
+    $CC -o $TMPDIR/libbpf_sec_test $TMPDIR/libbpf_sec_test.c $LIBBPF_CFLAGS $LIBBPF_LDLIBS >/dev/null 2>&1
+    local ret=$?
+
+    rm -f $TMPDIR/libbpf_sec_test.c $TMPDIR/libbpf_sec_test
+    return $ret
+}
+
+check_force_libbpf_on()
+{
+    # if set LIBBPF_FORCE=on but no libbpf support, just exist the config
+    # process to make sure we don't build without libbpf.
+    if [ "$LIBBPF_FORCE" = on ]; then
+        echo "	LIBBPF_FORCE=on set, but couldn't find a usable libbpf"
+        exit 1
+    fi
+}
+
+check_libbpf()
+{
+    # if set LIBBPF_FORCE=off, disable libbpf entirely
+    if [ "$LIBBPF_FORCE" = off ]; then
+        echo "no"
+        return
+    fi
+
+    if ! ${PKG_CONFIG} libbpf --exists && [ -z "$LIBBPF_DIR" ] ; then
+        echo "no"
+        check_force_libbpf_on
+        return
+    fi
+
+    if [ $(uname -m) = x86_64 ]; then
+        local LIBBPF_LIBDIR="${LIBBPF_DIR}/usr/lib64"
+    else
+        local LIBBPF_LIBDIR="${LIBBPF_DIR}/usr/lib"
+    fi
+
+    if [ -n "$LIBBPF_DIR" ]; then
+        LIBBPF_CFLAGS="-I${LIBBPF_DIR}/usr/include"
+        LIBBPF_LDLIBS="${LIBBPF_LIBDIR}/libbpf.a -lz -lelf"
+        LIBBPF_VERSION=$(PKG_CONFIG_LIBDIR=${LIBBPF_LIBDIR}/pkgconfig ${PKG_CONFIG} libbpf --modversion)
+    else
+        LIBBPF_CFLAGS=$(${PKG_CONFIG} libbpf --cflags)
+        LIBBPF_LDLIBS=$(${PKG_CONFIG} libbpf --libs)
+        LIBBPF_VERSION=$(${PKG_CONFIG} libbpf --modversion)
+    fi
+
+    if ! have_libbpf_basic; then
+        echo "no"
+        echo "	libbpf version $LIBBPF_VERSION is too low, please update it to at least 0.1.0"
+        check_force_libbpf_on
+        return
+    else
+        echo "HAVE_LIBBPF:=y" >> $CONFIG
+        echo 'CFLAGS += -DHAVE_LIBBPF ' $LIBBPF_CFLAGS >> $CONFIG
+        echo "CFLAGS += -DLIBBPF_VERSION=\\\"$LIBBPF_VERSION\\\"" >> $CONFIG
+        echo 'LDLIBS += ' $LIBBPF_LDLIBS >> $CONFIG
+
+        if [ -z "$LIBBPF_DIR" ]; then
+            echo "CFLAGS += -DLIBBPF_DYNAMIC" >> $CONFIG
+        fi
+    fi
+
+    # bpf_program__title() is deprecated since libbpf 0.2.0, use
+    # bpf_program__section_name() instead if we support
+    if have_libbpf_sec_name; then
+        echo "HAVE_LIBBPF_SECTION_NAME:=y" >> $CONFIG
+        echo 'CFLAGS += -DHAVE_LIBBPF_SECTION_NAME ' >> $CONFIG
+    fi
+
+    echo "yes"
+    echo "	libbpf version $LIBBPF_VERSION"
+}
+
 check_selinux()
 # SELinux is a compile time option in the ss utility
 {
@@ -351,6 +492,76 @@ endif
 EOF
 }
 
+usage()
+{
+	cat <<EOF
+Usage: $0 [OPTIONS]
+	--include_dir <dir>		Path to iproute2 include dir
+	--libdir <dir>			Path to iproute2 lib dir
+	--libbpf_dir <dir>		Path to libbpf DESTDIR
+	--libbpf_force <on|off>		Enable/disable libbpf by force. Available options:
+					  on: require link against libbpf, quit config if no libbpf support
+					  off: disable libbpf probing
+	--prefix <dir>			Path prefix of the lib files to install
+	-h | --help			Show this usage info
+EOF
+	exit $1
+}
+
+# Compat with the old INCLUDE path setting method.
+if [ $# -eq 1 ] && [ "$(echo $1 | cut -c 1)" != '-' ]; then
+	INCLUDE="$1"
+else
+	while [ "$#" -gt 0 ]; do
+		case "$1" in
+			--include_dir)
+				shift
+				INCLUDE="$1" ;;
+			--include_dir=*)
+				INCLUDE="${1#*=}" ;;
+			--libdir)
+				shift
+				LIBDIR="$1" ;;
+			--libdir=*)
+				LIBDIR="${1#*=}" ;;
+			--libbpf_dir)
+				shift
+				LIBBPF_DIR="$1" ;;
+			--libbpf_dir=*)
+				LIBBPF_DIR="${1#*=}" ;;
+			--libbpf_force)
+				shift
+				LIBBPF_FORCE="$1" ;;
+			--libbpf_force=*)
+				LIBBPF_FORCE="${1#*=}" ;;
+			--prefix)
+				shift
+				PREFIX="$1" ;;
+			--prefix=*)
+				PREFIX="${1#*=}" ;;
+			-h | --help)
+				usage 0 ;;
+			--*)
+				;;
+			*)
+				usage 1 ;;
+		esac
+		[ "$#" -gt 0 ] && shift
+	done
+fi
+
+[ -d "$INCLUDE" ] || usage 1
+if [ "${LIBBPF_DIR-unused}" != "unused" ]; then
+	[ -d "$LIBBPF_DIR" ] || usage 1
+fi
+if [ "${LIBBPF_FORCE-unused}" != "unused" ]; then
+	if [ "$LIBBPF_FORCE" != 'on' ] && [ "$LIBBPF_FORCE" != 'off' ]; then
+		usage 1
+	fi
+fi
+[ -z "$PREFIX" ] && usage 1
+[ -z "$LIBDIR" ] && usage 1
+
 echo "# Generated config based on" $INCLUDE >$CONFIG
 quiet_config >> $CONFIG
 
@@ -374,6 +585,7 @@ if ! grep -q TC_CONFIG_NO_XT $CONFIG; then
 fi
 
 echo
+check_lib_dir
 if ! grep -q TC_CONFIG_NO_XT $CONFIG; then
 	echo -n "iptables modules directory: "
 	check_ipt_lib_dir
@@ -382,9 +594,15 @@ fi
 echo -n "libc has setns: "
 check_setns
 
+echo -n "libc has name_to_handle_at: "
+check_name_to_handle_at
+
 echo -n "SELinux support: "
 check_selinux
 
+echo -n "libbpf support: "
+check_libbpf
+
 echo -n "ELF support: "
 check_elf
 

dcb/.gitignore

@@ -0,0 +1 @@
+dcb

dcb/Makefile

@@ -0,0 +1,31 @@
+# SPDX-License-Identifier: GPL-2.0
+include ../config.mk
+
+TARGETS :=
+
+ifeq ($(HAVE_MNL),y)
+
+DCBOBJ = dcb.o \
+         dcb_app.o \
+         dcb_buffer.o \
+         dcb_dcbx.o \
+         dcb_ets.o \
+         dcb_maxrate.o \
+         dcb_pfc.o
+TARGETS += dcb
+LDLIBS += -lm
+
+endif
+
+all: $(TARGETS) $(LIBS)
+
+dcb: $(DCBOBJ) $(LIBNETLINK)
+	$(QUIET_LINK)$(CC) $^ $(LDFLAGS) $(LDLIBS) -o $@
+
+install: all
+	for i in $(TARGETS); \
+	do install -m 0755 $$i $(DESTDIR)$(SBINDIR); \
+	done
+
+clean:
+	rm -f $(DCBOBJ) $(TARGETS)

dcb/dcb.c

@@ -0,0 +1,611 @@
+// SPDX-License-Identifier: GPL-2.0+
+
+#include <inttypes.h>
+#include <stdio.h>
+#include <linux/dcbnl.h>
+#include <libmnl/libmnl.h>
+#include <getopt.h>
+
+#include "dcb.h"
+#include "mnl_utils.h"
+#include "namespace.h"
+#include "utils.h"
+#include "version.h"
+
+static int dcb_init(struct dcb *dcb)
+{
+	dcb->buf = malloc(MNL_SOCKET_BUFFER_SIZE);
+	if (dcb->buf == NULL) {
+		perror("Netlink buffer allocation");
+		return -1;
+	}
+
+	dcb->nl = mnlu_socket_open(NETLINK_ROUTE);
+	if (dcb->nl == NULL) {
+		perror("Open netlink socket");
+		goto err_socket_open;
+	}
+
+	new_json_obj_plain(dcb->json_output);
+	return 0;
+
+err_socket_open:
+	free(dcb->buf);
+	return -1;
+}
+
+static void dcb_fini(struct dcb *dcb)
+{
+	delete_json_obj_plain();
+	mnl_socket_close(dcb->nl);
+	free(dcb->buf);
+}
+
+static struct dcb *dcb_alloc(void)
+{
+	struct dcb *dcb;
+
+	dcb = calloc(1, sizeof(*dcb));
+	if (!dcb)
+		return NULL;
+	return dcb;
+}
+
+static void dcb_free(struct dcb *dcb)
+{
+	free(dcb);
+}
+
+struct dcb_get_attribute {
+	struct dcb *dcb;
+	int attr;
+	void *payload;
+	__u16 payload_len;
+};
+
+static int dcb_get_attribute_attr_ieee_cb(const struct nlattr *attr, void *data)
+{
+	struct dcb_get_attribute *ga = data;
+
+	if (mnl_attr_get_type(attr) != ga->attr)
+		return MNL_CB_OK;
+
+	ga->payload = mnl_attr_get_payload(attr);
+	ga->payload_len = mnl_attr_get_payload_len(attr);
+	return MNL_CB_STOP;
+}
+
+static int dcb_get_attribute_attr_cb(const struct nlattr *attr, void *data)
+{
+	if (mnl_attr_get_type(attr) != DCB_ATTR_IEEE)
+		return MNL_CB_OK;
+
+	return mnl_attr_parse_nested(attr, dcb_get_attribute_attr_ieee_cb, data);
+}
+
+static int dcb_get_attribute_cb(const struct nlmsghdr *nlh, void *data)
+{
+	return mnl_attr_parse(nlh, sizeof(struct dcbmsg), dcb_get_attribute_attr_cb, data);
+}
+
+static int dcb_get_attribute_bare_cb(const struct nlmsghdr *nlh, void *data)
+{
+	/* Bare attributes (e.g. DCB_ATTR_DCBX) are not wrapped inside an IEEE
+	 * container, so this does not have to go through unpacking in
+	 * dcb_get_attribute_attr_cb().
+	 */
+	return mnl_attr_parse(nlh, sizeof(struct dcbmsg),
+			      dcb_get_attribute_attr_ieee_cb, data);
+}
+
+struct dcb_set_attribute_response {
+	int response_attr;
+};
+
+static int dcb_set_attribute_attr_cb(const struct nlattr *attr, void *data)
+{
+	struct dcb_set_attribute_response *resp = data;
+	uint16_t len;
+	uint8_t err;
+
+	if (mnl_attr_get_type(attr) != resp->response_attr)
+		return MNL_CB_OK;
+
+	len = mnl_attr_get_payload_len(attr);
+	if (len != 1) {
+		fprintf(stderr, "Response attribute expected to have size 1, not %d\n", len);
+		return MNL_CB_ERROR;
+	}
+
+	err = mnl_attr_get_u8(attr);
+	if (err) {
+		fprintf(stderr, "Error when attempting to set attribute: %s\n",
+			strerror(err));
+		return MNL_CB_ERROR;
+	}
+
+	return MNL_CB_STOP;
+}
+
+static int dcb_set_attribute_cb(const struct nlmsghdr *nlh, void *data)
+{
+	return mnl_attr_parse(nlh, sizeof(struct dcbmsg), dcb_set_attribute_attr_cb, data);
+}
+
+static int dcb_talk(struct dcb *dcb, struct nlmsghdr *nlh, mnl_cb_t cb, void *data)
+{
+	int ret;
+
+	ret = mnl_socket_sendto(dcb->nl, nlh, nlh->nlmsg_len);
+	if (ret < 0) {
+		perror("mnl_socket_sendto");
+		return -1;
+	}
+
+	return mnlu_socket_recv_run(dcb->nl, nlh->nlmsg_seq, dcb->buf, MNL_SOCKET_BUFFER_SIZE,
+				    cb, data);
+}
+
+static struct nlmsghdr *dcb_prepare(struct dcb *dcb, const char *dev,
+				    uint32_t nlmsg_type, uint8_t dcb_cmd)
+{
+	struct dcbmsg dcbm = {
+		.cmd = dcb_cmd,
+	};
+	struct nlmsghdr *nlh;
+
+	nlh = mnlu_msg_prepare(dcb->buf, nlmsg_type, NLM_F_REQUEST, &dcbm, sizeof(dcbm));
+	mnl_attr_put_strz(nlh, DCB_ATTR_IFNAME, dev);
+	return nlh;
+}
+
+static int __dcb_get_attribute(struct dcb *dcb, int command,
+			       const char *dev, int attr,
+			       void **payload_p, __u16 *payload_len_p,
+			       int (*get_attribute_cb)(const struct nlmsghdr *nlh,
+						       void *data))
+{
+	struct dcb_get_attribute ga;
+	struct nlmsghdr *nlh;
+	int ret;
+
+	nlh = dcb_prepare(dcb, dev, RTM_GETDCB, command);
+
+	ga = (struct dcb_get_attribute) {
+		.dcb = dcb,
+		.attr = attr,
+		.payload = NULL,
+	};
+	ret = dcb_talk(dcb, nlh, get_attribute_cb, &ga);
+	if (ret) {
+		perror("Attribute read");
+		return ret;
+	}
+	if (ga.payload == NULL) {
+		perror("Attribute not found");
+		return -ENOENT;
+	}
+
+	*payload_p = ga.payload;
+	*payload_len_p = ga.payload_len;
+	return 0;
+}
+
+int dcb_get_attribute_va(struct dcb *dcb, const char *dev, int attr,
+			 void **payload_p, __u16 *payload_len_p)
+{
+	return __dcb_get_attribute(dcb, DCB_CMD_IEEE_GET, dev, attr,
+				   payload_p, payload_len_p,
+				   dcb_get_attribute_cb);
+}
+
+int dcb_get_attribute_bare(struct dcb *dcb, int cmd, const char *dev, int attr,
+			   void **payload_p, __u16 *payload_len_p)
+{
+	return __dcb_get_attribute(dcb, cmd, dev, attr,
+				   payload_p, payload_len_p,
+				   dcb_get_attribute_bare_cb);
+}
+
+int dcb_get_attribute(struct dcb *dcb, const char *dev, int attr, void *data, size_t data_len)
+{
+	__u16 payload_len;
+	void *payload;
+	int ret;
+
+	ret = dcb_get_attribute_va(dcb, dev, attr, &payload, &payload_len);
+	if (ret)
+		return ret;
+
+	if (payload_len != data_len) {
+		fprintf(stderr, "Wrong len %d, expected %zd\n", payload_len, data_len);
+		return -EINVAL;
+	}
+
+	memcpy(data, payload, data_len);
+	return 0;
+}
+
+static int __dcb_set_attribute(struct dcb *dcb, int command, const char *dev,
+			       int (*cb)(struct dcb *, struct nlmsghdr *, void *),
+			       void *data, int response_attr)
+{
+	struct dcb_set_attribute_response resp = {
+		.response_attr = response_attr,
+	};
+	struct nlmsghdr *nlh;
+	int ret;
+
+	nlh = dcb_prepare(dcb, dev, RTM_SETDCB, command);
+
+	ret = cb(dcb, nlh, data);
+	if (ret)
+		return ret;
+
+	ret = dcb_talk(dcb, nlh, dcb_set_attribute_cb, &resp);
+	if (ret) {
+		perror("Attribute write");
+		return ret;
+	}
+	return 0;
+}
+
+struct dcb_set_attribute_ieee_cb {
+	int (*cb)(struct dcb *dcb, struct nlmsghdr *nlh, void *data);
+	void *data;
+};
+
+static int dcb_set_attribute_ieee_cb(struct dcb *dcb, struct nlmsghdr *nlh, void *data)
+{
+	struct dcb_set_attribute_ieee_cb *ieee_data = data;
+	struct nlattr *nest;
+	int ret;
+
+	nest = mnl_attr_nest_start(nlh, DCB_ATTR_IEEE);
+	ret = ieee_data->cb(dcb, nlh, ieee_data->data);
+	if (ret)
+		return ret;
+	mnl_attr_nest_end(nlh, nest);
+
+	return 0;
+}
+
+int dcb_set_attribute_va(struct dcb *dcb, int command, const char *dev,
+			 int (*cb)(struct dcb *dcb, struct nlmsghdr *nlh, void *data),
+			 void *data)
+{
+	struct dcb_set_attribute_ieee_cb ieee_data = {
+		.cb = cb,
+		.data = data,
+	};
+
+	return __dcb_set_attribute(dcb, command, dev,
+				   &dcb_set_attribute_ieee_cb, &ieee_data,
+				   DCB_ATTR_IEEE);
+}
+
+struct dcb_set_attribute {
+	int attr;
+	const void *data;
+	size_t data_len;
+};
+
+static int dcb_set_attribute_put(struct dcb *dcb, struct nlmsghdr *nlh, void *data)
+{
+	struct dcb_set_attribute *dsa = data;
+
+	mnl_attr_put(nlh, dsa->attr, dsa->data_len, dsa->data);
+	return 0;
+}
+
+int dcb_set_attribute(struct dcb *dcb, const char *dev, int attr, const void *data, size_t data_len)
+{
+	struct dcb_set_attribute dsa = {
+		.attr = attr,
+		.data = data,
+		.data_len = data_len,
+	};
+
+	return dcb_set_attribute_va(dcb, DCB_CMD_IEEE_SET, dev,
+				    &dcb_set_attribute_put, &dsa);
+}
+
+int dcb_set_attribute_bare(struct dcb *dcb, int command, const char *dev,
+			   int attr, const void *data, size_t data_len,
+			   int response_attr)
+{
+	struct dcb_set_attribute dsa = {
+		.attr = attr,
+		.data = data,
+		.data_len = data_len,
+	};
+
+	return __dcb_set_attribute(dcb, command, dev,
+				   &dcb_set_attribute_put, &dsa, response_attr);
+}
+
+void dcb_print_array_u8(const __u8 *array, size_t size)
+{
+	SPRINT_BUF(b);
+	size_t i;
+
+	for (i = 0; i < size; i++) {
+		snprintf(b, sizeof(b), "%zd:%%d ", i);
+		print_uint(PRINT_ANY, NULL, b, array[i]);
+	}
+}
+
+void dcb_print_array_u64(const __u64 *array, size_t size)
+{
+	SPRINT_BUF(b);
+	size_t i;
+
+	for (i = 0; i < size; i++) {
+		snprintf(b, sizeof(b), "%zd:%%" PRIu64 " ", i);
+		print_u64(PRINT_ANY, NULL, b, array[i]);
+	}
+}
+
+void dcb_print_array_on_off(const __u8 *array, size_t size)
+{
+	SPRINT_BUF(b);
+	size_t i;
+
+	for (i = 0; i < size; i++) {
+		snprintf(b, sizeof(b), "%zd:%%s ", i);
+		print_on_off(PRINT_ANY, NULL, b, array[i]);
+	}
+}
+
+void dcb_print_array_kw(const __u8 *array, size_t array_size,
+			const char *const kw[], size_t kw_size)
+{
+	SPRINT_BUF(b);
+	size_t i;
+
+	for (i = 0; i < array_size; i++) {
+		__u8 emt = array[i];
+
+		snprintf(b, sizeof(b), "%zd:%%s ", i);
+		if (emt < kw_size && kw[emt])
+			print_string(PRINT_ANY, NULL, b, kw[emt]);
+		else
+			print_string(PRINT_ANY, NULL, b, "???");
+	}
+}
+
+void dcb_print_named_array(const char *json_name, const char *fp_name,
+			   const __u8 *array, size_t size,
+			   void (*print_array)(const __u8 *, size_t))
+{
+	open_json_array(PRINT_JSON, json_name);
+	print_string(PRINT_FP, NULL, "%s ", fp_name);
+	print_array(array, size);
+	close_json_array(PRINT_JSON, json_name);
+}
+
+int dcb_parse_mapping(const char *what_key, __u32 key, __u32 max_key,
+		      const char *what_value, __u64 value, __u64 max_value,
+		      void (*set_array)(__u32 index, __u64 value, void *data),
+		      void *set_array_data)
+{
+	bool is_all = key == (__u32) -1;
+
+	if (!is_all && key > max_key) {
+		fprintf(stderr, "In %s:%s mapping, %s is expected to be 0..%d\n",
+			what_key, what_value, what_key, max_key);
+		return -EINVAL;
+	}
+
+	if (value > max_value) {
+		fprintf(stderr, "In %s:%s mapping, %s is expected to be 0..%llu\n",
+			what_key, what_value, what_value, max_value);
+		return -EINVAL;
+	}
+
+	if (is_all) {
+		for (key = 0; key <= max_key; key++)
+			set_array(key, value, set_array_data);
+	} else {
+		set_array(key, value, set_array_data);
+	}
+
+	return 0;
+}
+
+void dcb_set_u8(__u32 key, __u64 value, void *data)
+{
+	__u8 *array = data;
+
+	array[key] = value;
+}
+
+void dcb_set_u32(__u32 key, __u64 value, void *data)
+{
+	__u32 *array = data;
+
+	array[key] = value;
+}
+
+void dcb_set_u64(__u32 key, __u64 value, void *data)
+{
+	__u64 *array = data;
+
+	array[key] = value;
+}
+
+int dcb_cmd_parse_dev(struct dcb *dcb, int argc, char **argv,
+		      int (*and_then)(struct dcb *dcb, const char *dev,
+				      int argc, char **argv),
+		      void (*help)(void))
+{
+	const char *dev;
+
+	if (!argc || matches(*argv, "help") == 0) {
+		help();
+		return 0;
+	} else if (matches(*argv, "dev") == 0) {
+		NEXT_ARG();
+		dev = *argv;
+		if (check_ifname(dev)) {
+			invarg("not a valid ifname", *argv);
+			return -EINVAL;
+		}
+		NEXT_ARG_FWD();
+		return and_then(dcb, dev, argc, argv);
+	} else {
+		fprintf(stderr, "Expected `dev DEV', not `%s'", *argv);
+		help();
+		return -EINVAL;
+	}
+}
+
+static void dcb_help(void)
+{
+	fprintf(stderr,
+		"Usage: dcb [ OPTIONS ] OBJECT { COMMAND | help }\n"
+		"       dcb [ -f | --force ] { -b | --batch } filename [ -n | --netns ] netnsname\n"
+		"where  OBJECT := { app | buffer | dcbx | ets | maxrate | pfc }\n"
+		"       OPTIONS := [ -V | --Version | -i | --iec | -j | --json\n"
+		"                  | -N | --Numeric | -p | --pretty\n"
+		"                  | -s | --statistics | -v | --verbose]\n");
+}
+
+static int dcb_cmd(struct dcb *dcb, int argc, char **argv)
+{
+	if (!argc || matches(*argv, "help") == 0) {
+		dcb_help();
+		return 0;
+	} else if (matches(*argv, "app") == 0) {
+		return dcb_cmd_app(dcb, argc - 1, argv + 1);
+	} else if (matches(*argv, "buffer") == 0) {
+		return dcb_cmd_buffer(dcb, argc - 1, argv + 1);
+	} else if (matches(*argv, "dcbx") == 0) {
+		return dcb_cmd_dcbx(dcb, argc - 1, argv + 1);
+	} else if (matches(*argv, "ets") == 0) {
+		return dcb_cmd_ets(dcb, argc - 1, argv + 1);
+	} else if (matches(*argv, "maxrate") == 0) {
+		return dcb_cmd_maxrate(dcb, argc - 1, argv + 1);
+	} else if (matches(*argv, "pfc") == 0) {
+		return dcb_cmd_pfc(dcb, argc - 1, argv + 1);
+	}
+
+	fprintf(stderr, "Object \"%s\" is unknown\n", *argv);
+	return -ENOENT;
+}
+
+static int dcb_batch_cmd(int argc, char *argv[], void *data)
+{
+	struct dcb *dcb = data;
+
+	return dcb_cmd(dcb, argc, argv);
+}
+
+static int dcb_batch(struct dcb *dcb, const char *name, bool force)
+{
+	return do_batch(name, force, dcb_batch_cmd, dcb);
+}
+
+int main(int argc, char **argv)
+{
+	static const struct option long_options[] = {
+		{ "Version",		no_argument,		NULL, 'V' },
+		{ "force",		no_argument,		NULL, 'f' },
+		{ "batch",		required_argument,	NULL, 'b' },
+		{ "iec",		no_argument,		NULL, 'i' },
+		{ "json",		no_argument,		NULL, 'j' },
+		{ "Numeric",		no_argument,		NULL, 'N' },
+		{ "pretty",		no_argument,		NULL, 'p' },
+		{ "statistics",		no_argument,		NULL, 's' },
+		{ "netns",		required_argument,	NULL, 'n' },
+		{ "help",		no_argument,		NULL, 'h' },
+		{ NULL, 0, NULL, 0 }
+	};
+	const char *batch_file = NULL;
+	bool force = false;
+	struct dcb *dcb;
+	int opt;
+	int err;
+	int ret;
+
+	dcb = dcb_alloc();
+	if (!dcb) {
+		fprintf(stderr, "Failed to allocate memory for dcb\n");
+		return EXIT_FAILURE;
+	}
+
+	while ((opt = getopt_long(argc, argv, "b:fhijn:psvNV",
+				  long_options, NULL)) >= 0) {
+
+		switch (opt) {
+		case 'V':
+			printf("dcb utility, iproute2-%s\n", version);
+			ret = EXIT_SUCCESS;
+			goto dcb_free;
+		case 'f':
+			force = true;
+			break;
+		case 'b':
+			batch_file = optarg;
+			break;
+		case 'j':
+			dcb->json_output = true;
+			break;
+		case 'N':
+			dcb->numeric = true;
+			break;
+		case 'p':
+			pretty = true;
+			break;
+		case 's':
+			dcb->stats = true;
+			break;
+		case 'n':
+			if (netns_switch(optarg)) {
+				ret = EXIT_FAILURE;
+				goto dcb_free;
+			}
+			break;
+		case 'i':
+			dcb->use_iec = true;
+			break;
+		case 'h':
+			dcb_help();
+			ret = EXIT_SUCCESS;
+			goto dcb_free;
+		default:
+			fprintf(stderr, "Unknown option.\n");
+			dcb_help();
+			ret = EXIT_FAILURE;
+			goto dcb_free;
+		}
+	}
+
+	argc -= optind;
+	argv += optind;
+
+	err = dcb_init(dcb);
+	if (err) {
+		ret = EXIT_FAILURE;
+		goto dcb_free;
+	}
+
+	if (batch_file)
+		err = dcb_batch(dcb, batch_file, force);
+	else
+		err = dcb_cmd(dcb, argc, argv);
+
+	if (err) {
+		ret = EXIT_FAILURE;
+		goto dcb_fini;
+	}
+
+	ret = EXIT_SUCCESS;
+
+dcb_fini:
+	dcb_fini(dcb);
+dcb_free:
+	dcb_free(dcb);
+
+	return ret;
+}

dcb/dcb.h

@@ -0,0 +1,81 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __DCB_H__
+#define __DCB_H__ 1
+
+#include <libmnl/libmnl.h>
+#include <stdbool.h>
+#include <stddef.h>
+
+/* dcb.c */
+
+struct dcb {
+	char *buf;
+	struct mnl_socket *nl;
+	bool json_output;
+	bool stats;
+	bool use_iec;
+	bool numeric;
+};
+
+int dcb_parse_mapping(const char *what_key, __u32 key, __u32 max_key,
+		      const char *what_value, __u64 value, __u64 max_value,
+		      void (*set_array)(__u32 index, __u64 value, void *data),
+		      void *set_array_data);
+int dcb_cmd_parse_dev(struct dcb *dcb, int argc, char **argv,
+		      int (*and_then)(struct dcb *dcb, const char *dev,
+				      int argc, char **argv),
+		      void (*help)(void));
+
+void dcb_set_u8(__u32 key, __u64 value, void *data);
+void dcb_set_u32(__u32 key, __u64 value, void *data);
+void dcb_set_u64(__u32 key, __u64 value, void *data);
+
+int dcb_get_attribute(struct dcb *dcb, const char *dev, int attr,
+		      void *data, size_t data_len);
+int dcb_set_attribute(struct dcb *dcb, const char *dev, int attr,
+		      const void *data, size_t data_len);
+int dcb_get_attribute_va(struct dcb *dcb, const char *dev, int attr,
+			 void **payload_p, __u16 *payload_len_p);
+int dcb_set_attribute_va(struct dcb *dcb, int command, const char *dev,
+			 int (*cb)(struct dcb *dcb, struct nlmsghdr *nlh, void *data),
+			 void *data);
+int dcb_get_attribute_bare(struct dcb *dcb, int cmd, const char *dev, int attr,
+			   void **payload_p, __u16 *payload_len_p);
+int dcb_set_attribute_bare(struct dcb *dcb, int command, const char *dev,
+			   int attr, const void *data, size_t data_len,
+			   int response_attr);
+
+void dcb_print_named_array(const char *json_name, const char *fp_name,
+			   const __u8 *array, size_t size,
+			   void (*print_array)(const __u8 *, size_t));
+void dcb_print_array_u8(const __u8 *array, size_t size);
+void dcb_print_array_u64(const __u64 *array, size_t size);
+void dcb_print_array_on_off(const __u8 *array, size_t size);
+void dcb_print_array_kw(const __u8 *array, size_t array_size,
+			const char *const kw[], size_t kw_size);
+
+/* dcb_app.c */
+
+int dcb_cmd_app(struct dcb *dcb, int argc, char **argv);
+
+/* dcb_buffer.c */
+
+int dcb_cmd_buffer(struct dcb *dcb, int argc, char **argv);
+
+/* dcb_dcbx.c */
+
+int dcb_cmd_dcbx(struct dcb *dcb, int argc, char **argv);
+
+/* dcb_ets.c */
+
+int dcb_cmd_ets(struct dcb *dcb, int argc, char **argv);
+
+/* dcb_maxrate.c */
+
+int dcb_cmd_maxrate(struct dcb *dcb, int argc, char **argv);
+
+/* dcb_pfc.c */
+
+int dcb_cmd_pfc(struct dcb *dcb, int argc, char **argv);
+
+#endif /* __DCB_H__ */

dcb/dcb_app.c

@@ -0,0 +1,795 @@
+// SPDX-License-Identifier: GPL-2.0+
+
+#include <errno.h>
+#include <inttypes.h>
+#include <stdio.h>
+#include <libmnl/libmnl.h>
+#include <linux/dcbnl.h>
+
+#include "dcb.h"
+#include "utils.h"
+#include "rt_names.h"
+
+static void dcb_app_help_add(void)
+{
+	fprintf(stderr,
+		"Usage: dcb app { add | del | replace } dev STRING\n"
+		"           [ default-prio PRIO ]\n"
+		"           [ ethtype-prio ET:PRIO ]\n"
+		"           [ stream-port-prio PORT:PRIO ]\n"
+		"           [ dgram-port-prio PORT:PRIO ]\n"
+		"           [ port-prio PORT:PRIO ]\n"
+		"           [ dscp-prio INTEGER:PRIO ]\n"
+		"\n"
+		" where PRIO := { 0 .. 7 }\n"
+		"       ET := { 0x600 .. 0xffff }\n"
+		"       PORT := { 1 .. 65535 }\n"
+		"       DSCP := { 0 .. 63 }\n"
+		"\n"
+	);
+}
+
+static void dcb_app_help_show_flush(void)
+{
+	fprintf(stderr,
+		"Usage: dcb app { show | flush } dev STRING\n"
+		"           [ default-prio ]\n"
+		"           [ ethtype-prio ]\n"
+		"           [ stream-port-prio ]\n"
+		"           [ dgram-port-prio ]\n"
+		"           [ port-prio ]\n"
+		"           [ dscp-prio ]\n"
+		"\n"
+	);
+}
+
+static void dcb_app_help(void)
+{
+	fprintf(stderr,
+		"Usage: dcb app help\n"
+		"\n"
+	);
+	dcb_app_help_show_flush();
+	dcb_app_help_add();
+}
+
+struct dcb_app_table {
+	struct dcb_app *apps;
+	size_t n_apps;
+};
+
+static void dcb_app_table_fini(struct dcb_app_table *tab)
+{
+	free(tab->apps);
+}
+
+static int dcb_app_table_push(struct dcb_app_table *tab, struct dcb_app *app)
+{
+	struct dcb_app *apps = realloc(tab->apps, (tab->n_apps + 1) * sizeof(*tab->apps));
+
+	if (apps == NULL) {
+		perror("Cannot allocate APP table");
+		return -ENOMEM;
+	}
+
+	tab->apps = apps;
+	tab->apps[tab->n_apps++] = *app;
+	return 0;
+}
+
+static void dcb_app_table_remove_existing(struct dcb_app_table *a,
+					  const struct dcb_app_table *b)
+{
+	size_t ia, ja;
+	size_t ib;
+
+	for (ia = 0, ja = 0; ia < a->n_apps; ia++) {
+		struct dcb_app *aa = &a->apps[ia];
+		bool found = false;
+
+		for (ib = 0; ib < b->n_apps; ib++) {
+			const struct dcb_app *ab = &b->apps[ib];
+
+			if (aa->selector == ab->selector &&
+			    aa->protocol == ab->protocol &&
+			    aa->priority == ab->priority) {
+				found = true;
+				break;
+			}
+		}
+
+		if (!found)
+			a->apps[ja++] = *aa;
+	}
+
+	a->n_apps = ja;
+}
+
+static void dcb_app_table_remove_replaced(struct dcb_app_table *a,
+					  const struct dcb_app_table *b)
+{
+	size_t ia, ja;
+	size_t ib;
+
+	for (ia = 0, ja = 0; ia < a->n_apps; ia++) {
+		struct dcb_app *aa = &a->apps[ia];
+		bool present = false;
+		bool found = false;
+
+		for (ib = 0; ib < b->n_apps; ib++) {
+			const struct dcb_app *ab = &b->apps[ib];
+
+			if (aa->selector == ab->selector &&
+			    aa->protocol == ab->protocol)
+				present = true;
+			else
+				continue;
+
+			if (aa->priority == ab->priority) {
+				found = true;
+				break;
+			}
+		}
+
+		/* Entries that remain in A will be removed, so keep in the
+		 * table only APP entries whose sel/pid is mentioned in B,
+		 * but that do not have the full sel/pid/prio match.
+		 */
+		if (present && !found)
+			a->apps[ja++] = *aa;
+	}
+
+	a->n_apps = ja;
+}
+
+static int dcb_app_table_copy(struct dcb_app_table *a,
+			      const struct dcb_app_table *b)
+{
+	size_t i;
+	int ret;
+
+	for (i = 0; i < b->n_apps; i++) {
+		ret = dcb_app_table_push(a, &b->apps[i]);
+		if (ret != 0)
+			return ret;
+	}
+	return 0;
+}
+
+static int dcb_app_cmp(const struct dcb_app *a, const struct dcb_app *b)
+{
+	if (a->protocol < b->protocol)
+		return -1;
+	if (a->protocol > b->protocol)
+		return 1;
+	return a->priority - b->priority;
+}
+
+static int dcb_app_cmp_cb(const void *a, const void *b)
+{
+	return dcb_app_cmp(a, b);
+}
+
+static void dcb_app_table_sort(struct dcb_app_table *tab)
+{
+	qsort(tab->apps, tab->n_apps, sizeof(*tab->apps), dcb_app_cmp_cb);
+}
+
+struct dcb_app_parse_mapping {
+	__u8 selector;
+	struct dcb_app_table *tab;
+	int err;
+};
+
+static void dcb_app_parse_mapping_cb(__u32 key, __u64 value, void *data)
+{
+	struct dcb_app_parse_mapping *pm = data;
+	struct dcb_app app = {
+		.selector = pm->selector,
+		.priority = value,
+		.protocol = key,
+	};
+
+	if (pm->err)
+		return;
+
+	pm->err = dcb_app_table_push(pm->tab, &app);
+}
+
+static int dcb_app_parse_mapping_ethtype_prio(__u32 key, char *value, void *data)
+{
+	__u8 prio;
+
+	if (key < 0x600) {
+		fprintf(stderr, "Protocol IDs < 0x600 are reserved for EtherType\n");
+		return -EINVAL;
+	}
+
+	if (get_u8(&prio, value, 0))
+		return -EINVAL;
+
+	return dcb_parse_mapping("ETHTYPE", key, 0xffff,
+				 "PRIO", prio, IEEE_8021QAZ_MAX_TCS - 1,
+				 dcb_app_parse_mapping_cb, data);
+}
+
+static int dcb_app_parse_dscp(__u32 *key, const char *arg)
+{
+	if (parse_mapping_num_all(key, arg) == 0)
+		return 0;
+
+	if (rtnl_dsfield_a2n(key, arg) != 0)
+		return -1;
+
+	if (*key & 0x03) {
+		fprintf(stderr, "The values `%s' uses non-DSCP bits.\n", arg);
+		return -1;
+	}
+
+	/* Unshift the value to convert it from dsfield to DSCP. */
+	*key >>= 2;
+	return 0;
+}
+
+static int dcb_app_parse_mapping_dscp_prio(__u32 key, char *value, void *data)
+{
+	__u8 prio;
+
+	if (get_u8(&prio, value, 0))
+		return -EINVAL;
+
+	return dcb_parse_mapping("DSCP", key, 63,
+				 "PRIO", prio, IEEE_8021QAZ_MAX_TCS - 1,
+				 dcb_app_parse_mapping_cb, data);
+}
+
+static int dcb_app_parse_mapping_port_prio(__u32 key, char *value, void *data)
+{
+	__u8 prio;
+
+	if (key == 0) {
+		fprintf(stderr, "Port ID of 0 is invalid\n");
+		return -EINVAL;
+	}
+
+	if (get_u8(&prio, value, 0))
+		return -EINVAL;
+
+	return dcb_parse_mapping("PORT", key, 0xffff,
+				 "PRIO", prio, IEEE_8021QAZ_MAX_TCS - 1,
+				 dcb_app_parse_mapping_cb, data);
+}
+
+static int dcb_app_parse_default_prio(int *argcp, char ***argvp, struct dcb_app_table *tab)
+{
+	int argc = *argcp;
+	char **argv = *argvp;
+	int ret = 0;
+
+	while (argc > 0) {
+		struct dcb_app app;
+		__u8 prio;
+
+		if (get_u8(&prio, *argv, 0)) {
+			ret = 1;
+			break;
+		}
+
+		app = (struct dcb_app){
+			.selector = IEEE_8021QAZ_APP_SEL_ETHERTYPE,
+			.protocol = 0,
+			.priority = prio,
+		};
+		ret = dcb_app_table_push(tab, &app);
+		if (ret != 0)
+			break;
+
+		argc--, argv++;
+	}
+
+	*argcp = argc;
+	*argvp = argv;
+	return ret;
+}
+
+static bool dcb_app_is_ethtype(const struct dcb_app *app)
+{
+	return app->selector == IEEE_8021QAZ_APP_SEL_ETHERTYPE &&
+	       app->protocol != 0;
+}
+
+static bool dcb_app_is_default(const struct dcb_app *app)
+{
+	return app->selector == IEEE_8021QAZ_APP_SEL_ETHERTYPE &&
+	       app->protocol == 0;
+}
+
+static bool dcb_app_is_dscp(const struct dcb_app *app)
+{
+	return app->selector == IEEE_8021QAZ_APP_SEL_DSCP;
+}
+
+static bool dcb_app_is_stream_port(const struct dcb_app *app)
+{
+	return app->selector == IEEE_8021QAZ_APP_SEL_STREAM;
+}
+
+static bool dcb_app_is_dgram_port(const struct dcb_app *app)
+{
+	return app->selector == IEEE_8021QAZ_APP_SEL_DGRAM;
+}
+
+static bool dcb_app_is_port(const struct dcb_app *app)
+{
+	return app->selector == IEEE_8021QAZ_APP_SEL_ANY;
+}
+
+static int dcb_app_print_key_dec(__u16 protocol)
+{
+	return print_uint(PRINT_ANY, NULL, "%d:", protocol);
+}
+
+static int dcb_app_print_key_hex(__u16 protocol)
+{
+	return print_uint(PRINT_ANY, NULL, "%x:", protocol);
+}
+
+static int dcb_app_print_key_dscp(__u16 protocol)
+{
+	const char *name = rtnl_dsfield_get_name(protocol << 2);
+
+
+	if (!is_json_context() && name != NULL)
+		return print_string(PRINT_FP, NULL, "%s:", name);
+	return print_uint(PRINT_ANY, NULL, "%d:", protocol);
+}
+
+static void dcb_app_print_filtered(const struct dcb_app_table *tab,
+				   bool (*filter)(const struct dcb_app *),
+				   int (*print_key)(__u16 protocol),
+				   const char *json_name,
+				   const char *fp_name)
+{
+	bool first = true;
+	size_t i;
+
+	for (i = 0; i < tab->n_apps; i++) {
+		struct dcb_app *app = &tab->apps[i];
+
+		if (!filter(app))
+			continue;
+		if (first) {
+			open_json_array(PRINT_JSON, json_name);
+			print_string(PRINT_FP, NULL, "%s ", fp_name);
+			first = false;
+		}
+
+		open_json_array(PRINT_JSON, NULL);
+		print_key(app->protocol);
+		print_uint(PRINT_ANY, NULL, "%d ", app->priority);
+		close_json_array(PRINT_JSON, NULL);
+	}
+
+	if (!first) {
+		close_json_array(PRINT_JSON, json_name);
+		print_nl();
+	}
+}
+
+static void dcb_app_print_ethtype_prio(const struct dcb_app_table *tab)
+{
+	dcb_app_print_filtered(tab, dcb_app_is_ethtype,  dcb_app_print_key_hex,
+			       "ethtype_prio", "ethtype-prio");
+}
+
+static void dcb_app_print_dscp_prio(const struct dcb *dcb,
+				    const struct dcb_app_table *tab)
+{
+	dcb_app_print_filtered(tab, dcb_app_is_dscp,
+			       dcb->numeric ? dcb_app_print_key_dec
+					    : dcb_app_print_key_dscp,
+			       "dscp_prio", "dscp-prio");
+}
+
+static void dcb_app_print_stream_port_prio(const struct dcb_app_table *tab)
+{
+	dcb_app_print_filtered(tab, dcb_app_is_stream_port, dcb_app_print_key_dec,
+			       "stream_port_prio", "stream-port-prio");
+}
+
+static void dcb_app_print_dgram_port_prio(const struct dcb_app_table *tab)
+{
+	dcb_app_print_filtered(tab, dcb_app_is_dgram_port, dcb_app_print_key_dec,
+			       "dgram_port_prio", "dgram-port-prio");
+}
+
+static void dcb_app_print_port_prio(const struct dcb_app_table *tab)
+{
+	dcb_app_print_filtered(tab, dcb_app_is_port, dcb_app_print_key_dec,
+			       "port_prio", "port-prio");
+}
+
+static void dcb_app_print_default_prio(const struct dcb_app_table *tab)
+{
+	bool first = true;
+	size_t i;
+
+	for (i = 0; i < tab->n_apps; i++) {
+		if (!dcb_app_is_default(&tab->apps[i]))
+			continue;
+		if (first) {
+			open_json_array(PRINT_JSON, "default_prio");
+			print_string(PRINT_FP, NULL, "default-prio ", NULL);
+			first = false;
+		}
+		print_uint(PRINT_ANY, NULL, "%d ", tab->apps[i].priority);
+	}
+
+	if (!first) {
+		close_json_array(PRINT_JSON, "default_prio");
+		print_nl();
+	}
+}
+
+static void dcb_app_print(const struct dcb *dcb, const struct dcb_app_table *tab)
+{
+	dcb_app_print_ethtype_prio(tab);
+	dcb_app_print_default_prio(tab);
+	dcb_app_print_dscp_prio(dcb, tab);
+	dcb_app_print_stream_port_prio(tab);
+	dcb_app_print_dgram_port_prio(tab);
+	dcb_app_print_port_prio(tab);
+}
+
+static int dcb_app_get_table_attr_cb(const struct nlattr *attr, void *data)
+{
+	struct dcb_app_table *tab = data;
+	struct dcb_app *app;
+	int ret;
+
+	if (mnl_attr_get_type(attr) != DCB_ATTR_IEEE_APP) {
+		fprintf(stderr, "Unknown attribute in DCB_ATTR_IEEE_APP_TABLE: %d\n",
+			mnl_attr_get_type(attr));
+		return MNL_CB_OK;
+	}
+	if (mnl_attr_get_payload_len(attr) < sizeof(struct dcb_app)) {
+		fprintf(stderr, "DCB_ATTR_IEEE_APP payload expected to have size %zd, not %d\n",
+			sizeof(struct dcb_app), mnl_attr_get_payload_len(attr));
+		return MNL_CB_OK;
+	}
+
+	app = mnl_attr_get_payload(attr);
+	ret = dcb_app_table_push(tab, app);
+	if (ret != 0)
+		return MNL_CB_ERROR;
+
+	return MNL_CB_OK;
+}
+
+static int dcb_app_get(struct dcb *dcb, const char *dev, struct dcb_app_table *tab)
+{
+	uint16_t payload_len;
+	void *payload;
+	int ret;
+
+	ret = dcb_get_attribute_va(dcb, dev, DCB_ATTR_IEEE_APP_TABLE, &payload, &payload_len);
+	if (ret != 0)
+		return ret;
+
+	ret = mnl_attr_parse_payload(payload, payload_len, dcb_app_get_table_attr_cb, tab);
+	if (ret != MNL_CB_OK)
+		return -EINVAL;
+
+	return 0;
+}
+
+struct dcb_app_add_del {
+	const struct dcb_app_table *tab;
+	bool (*filter)(const struct dcb_app *app);
+};
+
+static int dcb_app_add_del_cb(struct dcb *dcb, struct nlmsghdr *nlh, void *data)
+{
+	struct dcb_app_add_del *add_del = data;
+	struct nlattr *nest;
+	size_t i;
+
+	nest = mnl_attr_nest_start(nlh, DCB_ATTR_IEEE_APP_TABLE);
+
+	for (i = 0; i < add_del->tab->n_apps; i++) {
+		const struct dcb_app *app = &add_del->tab->apps[i];
+
+		if (add_del->filter == NULL || add_del->filter(app))
+			mnl_attr_put(nlh, DCB_ATTR_IEEE_APP, sizeof(*app), app);
+	}
+
+	mnl_attr_nest_end(nlh, nest);
+	return 0;
+}
+
+static int dcb_app_add_del(struct dcb *dcb, const char *dev, int command,
+			   const struct dcb_app_table *tab,
+			   bool (*filter)(const struct dcb_app *))
+{
+	struct dcb_app_add_del add_del = {
+		.tab = tab,
+		.filter = filter,
+	};
+
+	if (tab->n_apps == 0)
+		return 0;
+
+	return dcb_set_attribute_va(dcb, command, dev, dcb_app_add_del_cb, &add_del);
+}
+
+static int dcb_cmd_app_parse_add_del(struct dcb *dcb, const char *dev,
+				     int argc, char **argv, struct dcb_app_table *tab)
+{
+	struct dcb_app_parse_mapping pm = {
+		.tab = tab,
+	};
+	int ret;
+
+	if (!argc) {
+		dcb_app_help_add();
+		return 0;
+	}
+
+	do {
+		if (matches(*argv, "help") == 0) {
+			dcb_app_help_add();
+			return 0;
+		} else if (matches(*argv, "ethtype-prio") == 0) {
+			NEXT_ARG();
+			pm.selector = IEEE_8021QAZ_APP_SEL_ETHERTYPE;
+			ret = parse_mapping(&argc, &argv, false,
+					    &dcb_app_parse_mapping_ethtype_prio,
+					    &pm);
+		} else if (matches(*argv, "default-prio") == 0) {
+			NEXT_ARG();
+			ret = dcb_app_parse_default_prio(&argc, &argv, pm.tab);
+			if (ret != 0) {
+				fprintf(stderr, "Invalid default priority %s\n", *argv);
+				return ret;
+			}
+		} else if (matches(*argv, "dscp-prio") == 0) {
+			NEXT_ARG();
+			pm.selector = IEEE_8021QAZ_APP_SEL_DSCP;
+			ret = parse_mapping_gen(&argc, &argv,
+						&dcb_app_parse_dscp,
+						&dcb_app_parse_mapping_dscp_prio,
+						&pm);
+		} else if (matches(*argv, "stream-port-prio") == 0) {
+			NEXT_ARG();
+			pm.selector = IEEE_8021QAZ_APP_SEL_STREAM;
+			ret = parse_mapping(&argc, &argv, false,
+					    &dcb_app_parse_mapping_port_prio,
+					    &pm);
+		} else if (matches(*argv, "dgram-port-prio") == 0) {
+			NEXT_ARG();
+			pm.selector = IEEE_8021QAZ_APP_SEL_DGRAM;
+			ret = parse_mapping(&argc, &argv, false,
+					    &dcb_app_parse_mapping_port_prio,
+					    &pm);
+		} else if (matches(*argv, "port-prio") == 0) {
+			NEXT_ARG();
+			pm.selector = IEEE_8021QAZ_APP_SEL_ANY;
+			ret = parse_mapping(&argc, &argv, false,
+					    &dcb_app_parse_mapping_port_prio,
+					    &pm);
+		} else {
+			fprintf(stderr, "What is \"%s\"?\n", *argv);
+			dcb_app_help_add();
+			return -EINVAL;
+		}
+
+		if (ret != 0) {
+			fprintf(stderr, "Invalid mapping %s\n", *argv);
+			return ret;
+		}
+		if (pm.err)
+			return pm.err;
+	} while (argc > 0);
+
+	return 0;
+}
+
+static int dcb_cmd_app_add(struct dcb *dcb, const char *dev, int argc, char **argv)
+{
+	struct dcb_app_table tab = {};
+	int ret;
+
+	ret = dcb_cmd_app_parse_add_del(dcb, dev, argc, argv, &tab);
+	if (ret != 0)
+		return ret;
+
+	ret = dcb_app_add_del(dcb, dev, DCB_CMD_IEEE_SET, &tab, NULL);
+	dcb_app_table_fini(&tab);
+	return ret;
+}
+
+static int dcb_cmd_app_del(struct dcb *dcb, const char *dev, int argc, char **argv)
+{
+	struct dcb_app_table tab = {};
+	int ret;
+
+	ret = dcb_cmd_app_parse_add_del(dcb, dev, argc, argv, &tab);
+	if (ret != 0)
+		return ret;
+
+	ret = dcb_app_add_del(dcb, dev, DCB_CMD_IEEE_DEL, &tab, NULL);
+	dcb_app_table_fini(&tab);
+	return ret;
+}
+
+static int dcb_cmd_app_show(struct dcb *dcb, const char *dev, int argc, char **argv)
+{
+	struct dcb_app_table tab = {};
+	int ret;
+
+	ret = dcb_app_get(dcb, dev, &tab);
+	if (ret != 0)
+		return ret;
+
+	dcb_app_table_sort(&tab);
+
+	open_json_object(NULL);
+
+	if (!argc) {
+		dcb_app_print(dcb, &tab);
+		goto out;
+	}
+
+	do {
+		if (matches(*argv, "help") == 0) {
+			dcb_app_help_show_flush();
+			goto out;
+		} else if (matches(*argv, "ethtype-prio") == 0) {
+			dcb_app_print_ethtype_prio(&tab);
+		} else if (matches(*argv, "dscp-prio") == 0) {
+			dcb_app_print_dscp_prio(dcb, &tab);
+		} else if (matches(*argv, "stream-port-prio") == 0) {
+			dcb_app_print_stream_port_prio(&tab);
+		} else if (matches(*argv, "dgram-port-prio") == 0) {
+			dcb_app_print_dgram_port_prio(&tab);
+		} else if (matches(*argv, "port-prio") == 0) {
+			dcb_app_print_port_prio(&tab);
+		} else {
+			fprintf(stderr, "What is \"%s\"?\n", *argv);
+			dcb_app_help_show_flush();
+			ret = -EINVAL;
+			goto out;
+		}
+
+		NEXT_ARG_FWD();
+	} while (argc > 0);
+
+out:
+	close_json_object();
+	dcb_app_table_fini(&tab);
+	return ret;
+}
+
+static int dcb_cmd_app_flush(struct dcb *dcb, const char *dev, int argc, char **argv)
+{
+	struct dcb_app_table tab = {};
+	int ret;
+
+	ret = dcb_app_get(dcb, dev, &tab);
+	if (ret != 0)
+		return ret;
+
+	if (!argc) {
+		ret = dcb_app_add_del(dcb, dev, DCB_CMD_IEEE_DEL, &tab, NULL);
+		goto out;
+	}
+
+	do {
+		if (matches(*argv, "help") == 0) {
+			dcb_app_help_show_flush();
+			goto out;
+		} else if (matches(*argv, "ethtype-prio") == 0) {
+			ret = dcb_app_add_del(dcb, dev, DCB_CMD_IEEE_DEL, &tab,
+					      &dcb_app_is_ethtype);
+			if (ret != 0)
+				goto out;
+		} else if (matches(*argv, "default-prio") == 0) {
+			ret = dcb_app_add_del(dcb, dev, DCB_CMD_IEEE_DEL, &tab,
+					      &dcb_app_is_default);
+			if (ret != 0)
+				goto out;
+		} else if (matches(*argv, "dscp-prio") == 0) {
+			ret = dcb_app_add_del(dcb, dev, DCB_CMD_IEEE_DEL, &tab,
+					      &dcb_app_is_dscp);
+			if (ret != 0)
+				goto out;
+		} else {
+			fprintf(stderr, "What is \"%s\"?\n", *argv);
+			dcb_app_help_show_flush();
+			ret = -EINVAL;
+			goto out;
+		}
+
+		NEXT_ARG_FWD();
+	} while (argc > 0);
+
+out:
+	dcb_app_table_fini(&tab);
+	return ret;
+}
+
+static int dcb_cmd_app_replace(struct dcb *dcb, const char *dev, int argc, char **argv)
+{
+	struct dcb_app_table orig = {};
+	struct dcb_app_table tab = {};
+	struct dcb_app_table new = {};
+	int ret;
+
+	ret = dcb_app_get(dcb, dev, &orig);
+	if (ret != 0)
+		return ret;
+
+	ret = dcb_cmd_app_parse_add_del(dcb, dev, argc, argv, &tab);
+	if (ret != 0)
+		goto out;
+
+	/* Attempts to add an existing entry would be rejected, so drop
+	 * these entries from tab.
+	 */
+	ret = dcb_app_table_copy(&new, &tab);
+	if (ret != 0)
+		goto out;
+	dcb_app_table_remove_existing(&new, &orig);
+
+	ret = dcb_app_add_del(dcb, dev, DCB_CMD_IEEE_SET, &new, NULL);
+	if (ret != 0) {
+		fprintf(stderr, "Could not add new APP entries\n");
+		goto out;
+	}
+
+	/* Remove the obsolete entries. */
+	dcb_app_table_remove_replaced(&orig, &tab);
+	ret = dcb_app_add_del(dcb, dev, DCB_CMD_IEEE_DEL, &orig, NULL);
+	if (ret != 0) {
+		fprintf(stderr, "Could not remove replaced APP entries\n");
+		goto out;
+	}
+
+out:
+	dcb_app_table_fini(&new);
+	dcb_app_table_fini(&tab);
+	dcb_app_table_fini(&orig);
+	return 0;
+}
+
+int dcb_cmd_app(struct dcb *dcb, int argc, char **argv)
+{
+	if (!argc || matches(*argv, "help") == 0) {
+		dcb_app_help();
+		return 0;
+	} else if (matches(*argv, "show") == 0) {
+		NEXT_ARG_FWD();
+		return dcb_cmd_parse_dev(dcb, argc, argv,
+					 dcb_cmd_app_show, dcb_app_help_show_flush);
+	} else if (matches(*argv, "flush") == 0) {
+		NEXT_ARG_FWD();
+		return dcb_cmd_parse_dev(dcb, argc, argv,
+					 dcb_cmd_app_flush, dcb_app_help_show_flush);
+	} else if (matches(*argv, "add") == 0) {
+		NEXT_ARG_FWD();
+		return dcb_cmd_parse_dev(dcb, argc, argv,
+					 dcb_cmd_app_add, dcb_app_help_add);
+	} else if (matches(*argv, "del") == 0) {
+		NEXT_ARG_FWD();
+		return dcb_cmd_parse_dev(dcb, argc, argv,
+					 dcb_cmd_app_del, dcb_app_help_add);
+	} else if (matches(*argv, "replace") == 0) {
+		NEXT_ARG_FWD();
+		return dcb_cmd_parse_dev(dcb, argc, argv,
+					 dcb_cmd_app_replace, dcb_app_help_add);
+	} else {
+		fprintf(stderr, "What is \"%s\"?\n", *argv);
+		dcb_app_help();
+		return -EINVAL;
+	}
+}

dcb/dcb_buffer.c

@@ -0,0 +1,235 @@
+// SPDX-License-Identifier: GPL-2.0+
+
+#include <errno.h>
+#include <inttypes.h>
+#include <stdio.h>
+#include <linux/dcbnl.h>
+
+#include "dcb.h"
+#include "utils.h"
+
+static void dcb_buffer_help_set(void)
+{
+	fprintf(stderr,
+		"Usage: dcb buffer set dev STRING\n"
+		"           [ prio-buffer PRIO-MAP ]\n"
+		"           [ buffer-size SIZE-MAP ]\n"
+		"\n"
+		" where PRIO-MAP := [ PRIO-MAP ] PRIO-MAPPING\n"
+		"       PRIO-MAPPING := { all | PRIO }:BUFFER\n"
+		"       SIZE-MAP := [ SIZE-MAP ] SIZE-MAPPING\n"
+		"       SIZE-MAPPING := { all | BUFFER }:INTEGER\n"
+		"       PRIO := { 0 .. 7 }\n"
+		"       BUFFER := { 0 .. 7 }\n"
+		"\n"
+	);
+}
+
+static void dcb_buffer_help_show(void)
+{
+	fprintf(stderr,
+		"Usage: dcb buffer show dev STRING\n"
+		"           [ prio-buffer ] [ buffer-size ] [ total-size ]\n"
+		"\n"
+	);
+}
+
+static void dcb_buffer_help(void)
+{
+	fprintf(stderr,
+		"Usage: dcb buffer help\n"
+		"\n"
+	);
+	dcb_buffer_help_show();
+	dcb_buffer_help_set();
+}
+
+static int dcb_buffer_parse_mapping_prio_buffer(__u32 key, char *value, void *data)
+{
+	struct dcbnl_buffer *buffer = data;
+	__u8 buf;
+
+	if (get_u8(&buf, value, 0))
+		return -EINVAL;
+
+	return dcb_parse_mapping("PRIO", key, IEEE_8021Q_MAX_PRIORITIES - 1,
+				 "BUFFER", buf, DCBX_MAX_BUFFERS - 1,
+				 dcb_set_u8, buffer->prio2buffer);
+}
+
+static int dcb_buffer_parse_mapping_buffer_size(__u32 key, char *value, void *data)
+{
+	struct dcbnl_buffer *buffer = data;
+	unsigned int size;
+
+	if (get_size(&size, value)) {
+		fprintf(stderr, "%d:%s: Illegal value for buffer size\n", key, value);
+		return -EINVAL;
+	}
+
+	return dcb_parse_mapping("BUFFER", key, DCBX_MAX_BUFFERS - 1,
+				 "INTEGER", size, -1,
+				 dcb_set_u32, buffer->buffer_size);
+}
+
+static void dcb_buffer_print_total_size(const struct dcbnl_buffer *buffer)
+{
+	print_size(PRINT_ANY, "total_size", "total-size %s ", buffer->total_size);
+}
+
+static void dcb_buffer_print_prio_buffer(const struct dcbnl_buffer *buffer)
+{
+	dcb_print_named_array("prio_buffer", "prio-buffer",
+			      buffer->prio2buffer, ARRAY_SIZE(buffer->prio2buffer),
+			      dcb_print_array_u8);
+}
+
+static void dcb_buffer_print_buffer_size(const struct dcbnl_buffer *buffer)
+{
+	size_t size = ARRAY_SIZE(buffer->buffer_size);
+	SPRINT_BUF(b);
+	size_t i;
+
+	open_json_array(PRINT_JSON, "buffer_size");
+	print_string(PRINT_FP, NULL, "buffer-size ", NULL);
+
+	for (i = 0; i < size; i++) {
+		snprintf(b, sizeof(b), "%zd:%%s ", i);
+		print_size(PRINT_ANY, NULL, b, buffer->buffer_size[i]);
+	}
+
+	close_json_array(PRINT_JSON, "buffer_size");
+}
+
+static void dcb_buffer_print(const struct dcbnl_buffer *buffer)
+{
+	dcb_buffer_print_prio_buffer(buffer);
+	print_nl();
+
+	dcb_buffer_print_buffer_size(buffer);
+	print_nl();
+
+	dcb_buffer_print_total_size(buffer);
+	print_nl();
+}
+
+static int dcb_buffer_get(struct dcb *dcb, const char *dev, struct dcbnl_buffer *buffer)
+{
+	return dcb_get_attribute(dcb, dev, DCB_ATTR_DCB_BUFFER, buffer, sizeof(*buffer));
+}
+
+static int dcb_buffer_set(struct dcb *dcb, const char *dev, const struct dcbnl_buffer *buffer)
+{
+	return dcb_set_attribute(dcb, dev, DCB_ATTR_DCB_BUFFER, buffer, sizeof(*buffer));
+}
+
+static int dcb_cmd_buffer_set(struct dcb *dcb, const char *dev, int argc, char **argv)
+{
+	struct dcbnl_buffer buffer;
+	int ret;
+
+	if (!argc) {
+		dcb_buffer_help_set();
+		return 0;
+	}
+
+	ret = dcb_buffer_get(dcb, dev, &buffer);
+	if (ret)
+		return ret;
+
+	do {
+		if (matches(*argv, "help") == 0) {
+			dcb_buffer_help_set();
+			return 0;
+		} else if (matches(*argv, "prio-buffer") == 0) {
+			NEXT_ARG();
+			ret = parse_mapping(&argc, &argv, true,
+					    &dcb_buffer_parse_mapping_prio_buffer, &buffer);
+			if (ret) {
+				fprintf(stderr, "Invalid priority mapping %s\n", *argv);
+				return ret;
+			}
+			continue;
+		} else if (matches(*argv, "buffer-size") == 0) {
+			NEXT_ARG();
+			ret = parse_mapping(&argc, &argv, true,
+					    &dcb_buffer_parse_mapping_buffer_size, &buffer);
+			if (ret) {
+				fprintf(stderr, "Invalid buffer size mapping %s\n", *argv);
+				return ret;
+			}
+			continue;
+		} else {
+			fprintf(stderr, "What is \"%s\"?\n", *argv);
+			dcb_buffer_help_set();
+			return -EINVAL;
+		}
+
+		NEXT_ARG_FWD();
+	} while (argc > 0);
+
+	return dcb_buffer_set(dcb, dev, &buffer);
+}
+
+static int dcb_cmd_buffer_show(struct dcb *dcb, const char *dev, int argc, char **argv)
+{
+	struct dcbnl_buffer buffer;
+	int ret;
+
+	ret = dcb_buffer_get(dcb, dev, &buffer);
+	if (ret)
+		return ret;
+
+	open_json_object(NULL);
+
+	if (!argc) {
+		dcb_buffer_print(&buffer);
+		goto out;
+	}
+
+	do {
+		if (matches(*argv, "help") == 0) {
+			dcb_buffer_help_show();
+			return 0;
+		} else if (matches(*argv, "prio-buffer") == 0) {
+			dcb_buffer_print_prio_buffer(&buffer);
+			print_nl();
+		} else if (matches(*argv, "buffer-size") == 0) {
+			dcb_buffer_print_buffer_size(&buffer);
+			print_nl();
+		} else if (matches(*argv, "total-size") == 0) {
+			dcb_buffer_print_total_size(&buffer);
+			print_nl();
+		} else {
+			fprintf(stderr, "What is \"%s\"?\n", *argv);
+			dcb_buffer_help_show();
+			return -EINVAL;
+		}
+
+		NEXT_ARG_FWD();
+	} while (argc > 0);
+
+out:
+	close_json_object();
+	return 0;
+}
+
+int dcb_cmd_buffer(struct dcb *dcb, int argc, char **argv)
+{
+	if (!argc || matches(*argv, "help") == 0) {
+		dcb_buffer_help();
+		return 0;
+	} else if (matches(*argv, "show") == 0) {
+		NEXT_ARG_FWD();
+		return dcb_cmd_parse_dev(dcb, argc, argv,
+					 dcb_cmd_buffer_show, dcb_buffer_help_show);
+	} else if (matches(*argv, "set") == 0) {
+		NEXT_ARG_FWD();
+		return dcb_cmd_parse_dev(dcb, argc, argv,
+					 dcb_cmd_buffer_set, dcb_buffer_help_set);
+	} else {
+		fprintf(stderr, "What is \"%s\"?\n", *argv);
+		dcb_buffer_help();
+		return -EINVAL;
+	}
+}

dcb/dcb_dcbx.c

@@ -0,0 +1,192 @@
+// SPDX-License-Identifier: GPL-2.0+
+
+#include <errno.h>
+#include <inttypes.h>
+#include <stdio.h>
+#include <linux/dcbnl.h>
+
+#include "dcb.h"
+#include "utils.h"
+
+static void dcb_dcbx_help_set(void)
+{
+	fprintf(stderr,
+		"Usage: dcb dcbx set dev STRING\n"
+		"           [ host | lld-managed ]\n"
+		"           [ cee | ieee ] [ static ]\n"
+		"\n"
+	);
+}
+
+static void dcb_dcbx_help_show(void)
+{
+	fprintf(stderr,
+		"Usage: dcb dcbx show dev STRING\n"
+		"\n"
+	);
+}
+
+static void dcb_dcbx_help(void)
+{
+	fprintf(stderr,
+		"Usage: dcb dcbx help\n"
+		"\n"
+	);
+	dcb_dcbx_help_show();
+	dcb_dcbx_help_set();
+}
+
+struct dcb_dcbx_flag {
+	__u8 value;
+	const char *key_fp;
+	const char *key_json;
+};
+
+static struct dcb_dcbx_flag dcb_dcbx_flags[] = {
+	{DCB_CAP_DCBX_HOST, "host"},
+	{DCB_CAP_DCBX_LLD_MANAGED, "lld-managed", "lld_managed"},
+	{DCB_CAP_DCBX_VER_CEE, "cee"},
+	{DCB_CAP_DCBX_VER_IEEE, "ieee"},
+	{DCB_CAP_DCBX_STATIC, "static"},
+};
+
+static void dcb_dcbx_print(__u8 dcbx)
+{
+	int bit;
+	int i;
+
+	while ((bit = ffs(dcbx))) {
+		bool found = false;
+
+		bit--;
+		for (i = 0; i < ARRAY_SIZE(dcb_dcbx_flags); i++) {
+			struct dcb_dcbx_flag *flag = &dcb_dcbx_flags[i];
+
+			if (flag->value == 1 << bit) {
+				print_bool(PRINT_JSON, flag->key_json ?: flag->key_fp,
+					   NULL, true);
+				print_string(PRINT_FP, NULL, "%s ", flag->key_fp);
+				found = true;
+				break;
+			}
+		}
+
+		if (!found)
+			fprintf(stderr, "Unknown DCBX bit %#x.\n", 1 << bit);
+
+		dcbx &= ~(1 << bit);
+	}
+
+	print_nl();
+}
+
+static int dcb_dcbx_get(struct dcb *dcb, const char *dev, __u8 *dcbx)
+{
+	__u16 payload_len;
+	void *payload;
+	int err;
+
+	err = dcb_get_attribute_bare(dcb, DCB_CMD_IEEE_GET, dev, DCB_ATTR_DCBX,
+				     &payload, &payload_len);
+	if (err != 0)
+		return err;
+
+	if (payload_len != 1) {
+		fprintf(stderr, "DCB_ATTR_DCBX payload has size %d, expected 1.\n",
+			payload_len);
+		return -EINVAL;
+	}
+	*dcbx = *(__u8 *) payload;
+	return 0;
+}
+
+static int dcb_dcbx_set(struct dcb *dcb, const char *dev, __u8 dcbx)
+{
+	return dcb_set_attribute_bare(dcb, DCB_CMD_SDCBX, dev, DCB_ATTR_DCBX,
+				      &dcbx, 1, DCB_ATTR_DCBX);
+}
+
+static int dcb_cmd_dcbx_set(struct dcb *dcb, const char *dev, int argc, char **argv)
+{
+	__u8 dcbx = 0;
+	__u8 i;
+
+	if (!argc) {
+		dcb_dcbx_help_set();
+		return 0;
+	}
+
+	do {
+		if (matches(*argv, "help") == 0) {
+			dcb_dcbx_help_set();
+			return 0;
+		}
+
+		for (i = 0; i < ARRAY_SIZE(dcb_dcbx_flags); i++) {
+			struct dcb_dcbx_flag *flag = &dcb_dcbx_flags[i];
+
+			if (matches(*argv, flag->key_fp) == 0) {
+				dcbx |= flag->value;
+				NEXT_ARG_FWD();
+				goto next;
+			}
+		}
+
+		fprintf(stderr, "What is \"%s\"?\n", *argv);
+		dcb_dcbx_help_set();
+		return -EINVAL;
+
+next:
+		;
+	} while (argc > 0);
+
+	return dcb_dcbx_set(dcb, dev, dcbx);
+}
+
+static int dcb_cmd_dcbx_show(struct dcb *dcb, const char *dev, int argc, char **argv)
+{
+	__u8 dcbx;
+	int ret;
+
+	ret = dcb_dcbx_get(dcb, dev, &dcbx);
+	if (ret != 0)
+		return ret;
+
+	while (argc > 0) {
+		if (matches(*argv, "help") == 0) {
+			dcb_dcbx_help_show();
+			return 0;
+		} else {
+			fprintf(stderr, "What is \"%s\"?\n", *argv);
+			dcb_dcbx_help_show();
+			return -EINVAL;
+		}
+
+		NEXT_ARG_FWD();
+	}
+
+	open_json_object(NULL);
+	dcb_dcbx_print(dcbx);
+	close_json_object();
+	return 0;
+}
+
+int dcb_cmd_dcbx(struct dcb *dcb, int argc, char **argv)
+{
+	if (!argc || matches(*argv, "help") == 0) {
+		dcb_dcbx_help();
+		return 0;
+	} else if (matches(*argv, "show") == 0) {
+		NEXT_ARG_FWD();
+		return dcb_cmd_parse_dev(dcb, argc, argv,
+					 dcb_cmd_dcbx_show, dcb_dcbx_help_show);
+	} else if (matches(*argv, "set") == 0) {
+		NEXT_ARG_FWD();
+		return dcb_cmd_parse_dev(dcb, argc, argv,
+					 dcb_cmd_dcbx_set, dcb_dcbx_help_set);
+	} else {
+		fprintf(stderr, "What is \"%s\"?\n", *argv);
+		dcb_dcbx_help();
+		return -EINVAL;
+	}
+}

dcb/dcb_ets.c

@@ -0,0 +1,435 @@
+// SPDX-License-Identifier: GPL-2.0+
+
+#include <errno.h>
+#include <stdio.h>
+#include <linux/dcbnl.h>
+
+#include "dcb.h"
+#include "utils.h"
+
+static void dcb_ets_help_set(void)
+{
+	fprintf(stderr,
+		"Usage: dcb ets set dev STRING\n"
+		"           [ willing { on | off } ]\n"
+		"           [ { tc-tsa | reco-tc-tsa } TSA-MAP ]\n"
+		"           [ { pg-bw | tc-bw | reco-tc-bw } BW-MAP ]\n"
+		"           [ { prio-tc | reco-prio-tc } PRIO-MAP ]\n"
+		"\n"
+		" where TSA-MAP := [ TSA-MAP ] TSA-MAPPING\n"
+		"       TSA-MAPPING := { all | TC }:{ strict | cbs | ets | vendor }\n"
+		"       BW-MAP := [ BW-MAP ] BW-MAPPING\n"
+		"       BW-MAPPING := { all | TC }:INTEGER\n"
+		"       PRIO-MAP := [ PRIO-MAP ] PRIO-MAPPING\n"
+		"       PRIO-MAPPING := { all | PRIO }:TC\n"
+		"       TC := { 0 .. 7 }\n"
+		"       PRIO := { 0 .. 7 }\n"
+		"\n"
+	);
+}
+
+static void dcb_ets_help_show(void)
+{
+	fprintf(stderr,
+		"Usage: dcb ets show dev STRING\n"
+		"           [ willing ] [ ets-cap ] [ cbs ] [ tc-tsa ]\n"
+		"           [ reco-tc-tsa ] [ pg-bw ] [ tc-bw ] [ reco-tc-bw ]\n"
+		"           [ prio-tc ] [ reco-prio-tc ]\n"
+		"\n"
+	);
+}
+
+static void dcb_ets_help(void)
+{
+	fprintf(stderr,
+		"Usage: dcb ets help\n"
+		"\n"
+	);
+	dcb_ets_help_show();
+	dcb_ets_help_set();
+}
+
+static const char *const tsa_names[] = {
+	[IEEE_8021QAZ_TSA_STRICT] = "strict",
+	[IEEE_8021QAZ_TSA_CB_SHAPER] = "cbs",
+	[IEEE_8021QAZ_TSA_ETS] = "ets",
+	[IEEE_8021QAZ_TSA_VENDOR] = "vendor",
+};
+
+static int dcb_ets_parse_mapping_tc_tsa(__u32 key, char *value, void *data)
+{
+	__u8 tsa;
+	int ret;
+
+	tsa = parse_one_of("TSA", value, tsa_names, ARRAY_SIZE(tsa_names), &ret);
+	if (ret)
+		return ret;
+
+	return dcb_parse_mapping("TC", key, IEEE_8021QAZ_MAX_TCS - 1,
+				 "TSA", tsa, -1U,
+				 dcb_set_u8, data);
+}
+
+static int dcb_ets_parse_mapping_tc_bw(__u32 key, char *value, void *data)
+{
+	__u8 bw;
+
+	if (get_u8(&bw, value, 0))
+		return -EINVAL;
+
+	return dcb_parse_mapping("TC", key, IEEE_8021QAZ_MAX_TCS - 1,
+				 "BW", bw, 100,
+				 dcb_set_u8, data);
+}
+
+static int dcb_ets_parse_mapping_prio_tc(unsigned int key, char *value, void *data)
+{
+	__u8 tc;
+
+	if (get_u8(&tc, value, 0))
+		return -EINVAL;
+
+	return dcb_parse_mapping("PRIO", key, IEEE_8021QAZ_MAX_TCS - 1,
+				 "TC", tc, IEEE_8021QAZ_MAX_TCS - 1,
+				 dcb_set_u8, data);
+}
+
+static void dcb_print_array_tsa(const __u8 *array, size_t size)
+{
+	dcb_print_array_kw(array, size, tsa_names, ARRAY_SIZE(tsa_names));
+}
+
+static void dcb_ets_print_willing(const struct ieee_ets *ets)
+{
+	print_on_off(PRINT_ANY, "willing", "willing %s ", ets->willing);
+}
+
+static void dcb_ets_print_ets_cap(const struct ieee_ets *ets)
+{
+	print_uint(PRINT_ANY, "ets_cap", "ets-cap %d ", ets->ets_cap);
+}
+
+static void dcb_ets_print_cbs(const struct ieee_ets *ets)
+{
+	print_on_off(PRINT_ANY, "cbs", "cbs %s ", ets->cbs);
+}
+
+static void dcb_ets_print_tc_bw(const struct ieee_ets *ets)
+{
+	dcb_print_named_array("tc_bw", "tc-bw",
+			      ets->tc_tx_bw, ARRAY_SIZE(ets->tc_tx_bw),
+			      dcb_print_array_u8);
+}
+
+static void dcb_ets_print_pg_bw(const struct ieee_ets *ets)
+{
+	dcb_print_named_array("pg_bw", "pg-bw",
+			      ets->tc_rx_bw, ARRAY_SIZE(ets->tc_rx_bw),
+			      dcb_print_array_u8);
+}
+
+static void dcb_ets_print_tc_tsa(const struct ieee_ets *ets)
+{
+	dcb_print_named_array("tc_tsa", "tc-tsa",
+			      ets->tc_tsa, ARRAY_SIZE(ets->tc_tsa),
+			      dcb_print_array_tsa);
+}
+
+static void dcb_ets_print_prio_tc(const struct ieee_ets *ets)
+{
+	dcb_print_named_array("prio_tc", "prio-tc",
+			      ets->prio_tc, ARRAY_SIZE(ets->prio_tc),
+			      dcb_print_array_u8);
+}
+
+static void dcb_ets_print_reco_tc_bw(const struct ieee_ets *ets)
+{
+	dcb_print_named_array("reco_tc_bw", "reco-tc-bw",
+			      ets->tc_reco_bw, ARRAY_SIZE(ets->tc_reco_bw),
+			      dcb_print_array_u8);
+}
+
+static void dcb_ets_print_reco_tc_tsa(const struct ieee_ets *ets)
+{
+	dcb_print_named_array("reco_tc_tsa", "reco-tc-tsa",
+			      ets->tc_reco_tsa, ARRAY_SIZE(ets->tc_reco_tsa),
+			      dcb_print_array_tsa);
+}
+
+static void dcb_ets_print_reco_prio_tc(const struct ieee_ets *ets)
+{
+	dcb_print_named_array("reco_prio_tc", "reco-prio-tc",
+			      ets->reco_prio_tc, ARRAY_SIZE(ets->reco_prio_tc),
+			      dcb_print_array_u8);
+}
+
+static void dcb_ets_print(const struct ieee_ets *ets)
+{
+	dcb_ets_print_willing(ets);
+	dcb_ets_print_ets_cap(ets);
+	dcb_ets_print_cbs(ets);
+	print_nl();
+
+	dcb_ets_print_tc_bw(ets);
+	print_nl();
+
+	dcb_ets_print_pg_bw(ets);
+	print_nl();
+
+	dcb_ets_print_tc_tsa(ets);
+	print_nl();
+
+	dcb_ets_print_prio_tc(ets);
+	print_nl();
+
+	dcb_ets_print_reco_tc_bw(ets);
+	print_nl();
+
+	dcb_ets_print_reco_tc_tsa(ets);
+	print_nl();
+
+	dcb_ets_print_reco_prio_tc(ets);
+	print_nl();
+}
+
+static int dcb_ets_get(struct dcb *dcb, const char *dev, struct ieee_ets *ets)
+{
+	return dcb_get_attribute(dcb, dev, DCB_ATTR_IEEE_ETS, ets, sizeof(*ets));
+}
+
+static int dcb_ets_validate_bw(const __u8 bw[], const __u8 tsa[], const char *what)
+{
+	bool has_ets = false;
+	unsigned int total = 0;
+	unsigned int tc;
+
+	for (tc = 0; tc < IEEE_8021QAZ_MAX_TCS; tc++) {
+		if (tsa[tc] == IEEE_8021QAZ_TSA_ETS) {
+			has_ets = true;
+			break;
+		}
+	}
+
+	/* TC bandwidth is only intended for ETS, but 802.1Q-2018 only requires
+	 * that the sum be 100, and individual entries 0..100. It explicitly
+	 * notes that non-ETS TCs can have non-0 TC bandwidth during
+	 * reconfiguration.
+	 */
+	for (tc = 0; tc < IEEE_8021QAZ_MAX_TCS; tc++) {
+		if (bw[tc] > 100) {
+			fprintf(stderr, "%d%% for TC %d of %s is not a valid bandwidth percentage, expected 0..100%%\n",
+				bw[tc], tc, what);
+			return -EINVAL;
+		}
+		total += bw[tc];
+	}
+
+	/* This is what 802.1Q-2018 requires. */
+	if (total == 100)
+		return 0;
+
+	/* But this requirement does not make sense for all-strict
+	 * configurations. Anything else than 0 does not make sense: either BW
+	 * has not been reconfigured for the all-strict allocation yet, at which
+	 * point we expect sum of 100. Or it has already been reconfigured, at
+	 * which point accept 0.
+	 */
+	if (!has_ets && total == 0)
+		return 0;
+
+	fprintf(stderr, "Bandwidth percentages in %s sum to %d%%, expected %d%%\n",
+		what, total, has_ets ? 100 : 0);
+	return -EINVAL;
+}
+
+static int dcb_ets_set(struct dcb *dcb, const char *dev, const struct ieee_ets *ets)
+{
+	/* Do not validate pg-bw, which is not standard and has unclear
+	 * meaning.
+	 */
+	if (dcb_ets_validate_bw(ets->tc_tx_bw, ets->tc_tsa, "tc-bw") ||
+	    dcb_ets_validate_bw(ets->tc_reco_bw, ets->tc_reco_tsa, "reco-tc-bw"))
+		return -EINVAL;
+
+	return dcb_set_attribute(dcb, dev, DCB_ATTR_IEEE_ETS, ets, sizeof(*ets));
+}
+
+static int dcb_cmd_ets_set(struct dcb *dcb, const char *dev, int argc, char **argv)
+{
+	struct ieee_ets ets;
+	int ret;
+
+	if (!argc) {
+		dcb_ets_help_set();
+		return 1;
+	}
+
+	ret = dcb_ets_get(dcb, dev, &ets);
+	if (ret)
+		return ret;
+
+	do {
+		if (matches(*argv, "help") == 0) {
+			dcb_ets_help_set();
+			return 0;
+		} else if (matches(*argv, "willing") == 0) {
+			NEXT_ARG();
+			ets.willing = parse_on_off("willing", *argv, &ret);
+			if (ret)
+				return ret;
+		} else if (matches(*argv, "tc-tsa") == 0) {
+			NEXT_ARG();
+			ret = parse_mapping(&argc, &argv, true, &dcb_ets_parse_mapping_tc_tsa,
+					    ets.tc_tsa);
+			if (ret) {
+				fprintf(stderr, "Invalid tc-tsa mapping %s\n", *argv);
+				return ret;
+			}
+			continue;
+		} else if (matches(*argv, "reco-tc-tsa") == 0) {
+			NEXT_ARG();
+			ret = parse_mapping(&argc, &argv, true, &dcb_ets_parse_mapping_tc_tsa,
+					    ets.tc_reco_tsa);
+			if (ret) {
+				fprintf(stderr, "Invalid reco-tc-tsa mapping %s\n", *argv);
+				return ret;
+			}
+			continue;
+		} else if (matches(*argv, "tc-bw") == 0) {
+			NEXT_ARG();
+			ret = parse_mapping(&argc, &argv, true, &dcb_ets_parse_mapping_tc_bw,
+					    ets.tc_tx_bw);
+			if (ret) {
+				fprintf(stderr, "Invalid tc-bw mapping %s\n", *argv);
+				return ret;
+			}
+			continue;
+		} else if (matches(*argv, "pg-bw") == 0) {
+			NEXT_ARG();
+			ret = parse_mapping(&argc, &argv, true, &dcb_ets_parse_mapping_tc_bw,
+					    ets.tc_rx_bw);
+			if (ret) {
+				fprintf(stderr, "Invalid pg-bw mapping %s\n", *argv);
+				return ret;
+			}
+			continue;
+		} else if (matches(*argv, "reco-tc-bw") == 0) {
+			NEXT_ARG();
+			ret = parse_mapping(&argc, &argv, true, &dcb_ets_parse_mapping_tc_bw,
+					    ets.tc_reco_bw);
+			if (ret) {
+				fprintf(stderr, "Invalid reco-tc-bw mapping %s\n", *argv);
+				return ret;
+			}
+			continue;
+		} else if (matches(*argv, "prio-tc") == 0) {
+			NEXT_ARG();
+			ret = parse_mapping(&argc, &argv, true, &dcb_ets_parse_mapping_prio_tc,
+					    ets.prio_tc);
+			if (ret) {
+				fprintf(stderr, "Invalid prio-tc mapping %s\n", *argv);
+				return ret;
+			}
+			continue;
+		} else if (matches(*argv, "reco-prio-tc") == 0) {
+			NEXT_ARG();
+			ret = parse_mapping(&argc, &argv, true, &dcb_ets_parse_mapping_prio_tc,
+					    ets.reco_prio_tc);
+			if (ret) {
+				fprintf(stderr, "Invalid reco-prio-tc mapping %s\n", *argv);
+				return ret;
+			}
+			continue;
+		} else {
+			fprintf(stderr, "What is \"%s\"?\n", *argv);
+			dcb_ets_help_set();
+			return -EINVAL;
+		}
+
+		NEXT_ARG_FWD();
+	} while (argc > 0);
+
+	return dcb_ets_set(dcb, dev, &ets);
+}
+
+static int dcb_cmd_ets_show(struct dcb *dcb, const char *dev, int argc, char **argv)
+{
+	struct ieee_ets ets;
+	int ret;
+
+	ret = dcb_ets_get(dcb, dev, &ets);
+	if (ret)
+		return ret;
+
+	open_json_object(NULL);
+
+	if (!argc) {
+		dcb_ets_print(&ets);
+		goto out;
+	}
+
+	do {
+		if (matches(*argv, "help") == 0) {
+			dcb_ets_help_show();
+			return 0;
+		} else if (matches(*argv, "willing") == 0) {
+			dcb_ets_print_willing(&ets);
+			print_nl();
+		} else if (matches(*argv, "ets-cap") == 0) {
+			dcb_ets_print_ets_cap(&ets);
+			print_nl();
+		} else if (matches(*argv, "cbs") == 0) {
+			dcb_ets_print_cbs(&ets);
+			print_nl();
+		} else if (matches(*argv, "tc-tsa") == 0) {
+			dcb_ets_print_tc_tsa(&ets);
+			print_nl();
+		} else if (matches(*argv, "reco-tc-tsa") == 0) {
+			dcb_ets_print_reco_tc_tsa(&ets);
+			print_nl();
+		} else if (matches(*argv, "tc-bw") == 0) {
+			dcb_ets_print_tc_bw(&ets);
+			print_nl();
+		} else if (matches(*argv, "pg-bw") == 0) {
+			dcb_ets_print_pg_bw(&ets);
+			print_nl();
+		} else if (matches(*argv, "reco-tc-bw") == 0) {
+			dcb_ets_print_reco_tc_bw(&ets);
+			print_nl();
+		} else if (matches(*argv, "prio-tc") == 0) {
+			dcb_ets_print_prio_tc(&ets);
+			print_nl();
+		} else if (matches(*argv, "reco-prio-tc") == 0) {
+			dcb_ets_print_reco_prio_tc(&ets);
+			print_nl();
+		} else {
+			fprintf(stderr, "What is \"%s\"?\n", *argv);
+			dcb_ets_help_show();
+			return -EINVAL;
+		}
+
+		NEXT_ARG_FWD();
+	} while (argc > 0);
+
+out:
+	close_json_object();
+	return 0;
+}
+
+int dcb_cmd_ets(struct dcb *dcb, int argc, char **argv)
+{
+	if (!argc || matches(*argv, "help") == 0) {
+		dcb_ets_help();
+		return 0;
+	} else if (matches(*argv, "show") == 0) {
+		NEXT_ARG_FWD();
+		return dcb_cmd_parse_dev(dcb, argc, argv, dcb_cmd_ets_show, dcb_ets_help_show);
+	} else if (matches(*argv, "set") == 0) {
+		NEXT_ARG_FWD();
+		return dcb_cmd_parse_dev(dcb, argc, argv, dcb_cmd_ets_set, dcb_ets_help_set);
+	} else {
+		fprintf(stderr, "What is \"%s\"?\n", *argv);
+		dcb_ets_help();
+		return -EINVAL;
+	}
+}

dcb/dcb_maxrate.c

@@ -0,0 +1,182 @@
+// SPDX-License-Identifier: GPL-2.0+
+
+#include <errno.h>
+#include <inttypes.h>
+#include <stdio.h>
+#include <linux/dcbnl.h>
+
+#include "dcb.h"
+#include "utils.h"
+
+static void dcb_maxrate_help_set(void)
+{
+	fprintf(stderr,
+		"Usage: dcb maxrate set dev STRING\n"
+		"           [ tc-maxrate RATE-MAP ]\n"
+		"\n"
+		" where RATE-MAP := [ RATE-MAP ] RATE-MAPPING\n"
+		"       RATE-MAPPING := { all | TC }:RATE\n"
+		"       TC := { 0 .. 7 }\n"
+		"\n"
+	);
+}
+
+static void dcb_maxrate_help_show(void)
+{
+	fprintf(stderr,
+		"Usage: dcb [ -i ] maxrate show dev STRING\n"
+		"           [ tc-maxrate ]\n"
+		"\n"
+	);
+}
+
+static void dcb_maxrate_help(void)
+{
+	fprintf(stderr,
+		"Usage: dcb maxrate help\n"
+		"\n"
+	);
+	dcb_maxrate_help_show();
+	dcb_maxrate_help_set();
+}
+
+static int dcb_maxrate_parse_mapping_tc_maxrate(__u32 key, char *value, void *data)
+{
+	__u64 rate;
+
+	if (get_rate64(&rate, value))
+		return -EINVAL;
+
+	return dcb_parse_mapping("TC", key, IEEE_8021QAZ_MAX_TCS - 1,
+				 "RATE", rate, -1,
+				 dcb_set_u64, data);
+}
+
+static void dcb_maxrate_print_tc_maxrate(struct dcb *dcb, const struct ieee_maxrate *maxrate)
+{
+	size_t size = ARRAY_SIZE(maxrate->tc_maxrate);
+	SPRINT_BUF(b);
+	size_t i;
+
+	open_json_array(PRINT_JSON, "tc_maxrate");
+	print_string(PRINT_FP, NULL, "tc-maxrate ", NULL);
+
+	for (i = 0; i < size; i++) {
+		snprintf(b, sizeof(b), "%zd:%%s ", i);
+		print_rate(dcb->use_iec, PRINT_ANY, NULL, b, maxrate->tc_maxrate[i]);
+	}
+
+	close_json_array(PRINT_JSON, "tc_maxrate");
+}
+
+static void dcb_maxrate_print(struct dcb *dcb, const struct ieee_maxrate *maxrate)
+{
+	dcb_maxrate_print_tc_maxrate(dcb, maxrate);
+	print_nl();
+}
+
+static int dcb_maxrate_get(struct dcb *dcb, const char *dev, struct ieee_maxrate *maxrate)
+{
+	return dcb_get_attribute(dcb, dev, DCB_ATTR_IEEE_MAXRATE, maxrate, sizeof(*maxrate));
+}
+
+static int dcb_maxrate_set(struct dcb *dcb, const char *dev, const struct ieee_maxrate *maxrate)
+{
+	return dcb_set_attribute(dcb, dev, DCB_ATTR_IEEE_MAXRATE, maxrate, sizeof(*maxrate));
+}
+
+static int dcb_cmd_maxrate_set(struct dcb *dcb, const char *dev, int argc, char **argv)
+{
+	struct ieee_maxrate maxrate;
+	int ret;
+
+	if (!argc) {
+		dcb_maxrate_help_set();
+		return 0;
+	}
+
+	ret = dcb_maxrate_get(dcb, dev, &maxrate);
+	if (ret)
+		return ret;
+
+	do {
+		if (matches(*argv, "help") == 0) {
+			dcb_maxrate_help_set();
+			return 0;
+		} else if (matches(*argv, "tc-maxrate") == 0) {
+			NEXT_ARG();
+			ret = parse_mapping(&argc, &argv, true,
+					    &dcb_maxrate_parse_mapping_tc_maxrate, &maxrate);
+			if (ret) {
+				fprintf(stderr, "Invalid mapping %s\n", *argv);
+				return ret;
+			}
+			continue;
+		} else {
+			fprintf(stderr, "What is \"%s\"?\n", *argv);
+			dcb_maxrate_help_set();
+			return -EINVAL;
+		}
+
+		NEXT_ARG_FWD();
+	} while (argc > 0);
+
+	return dcb_maxrate_set(dcb, dev, &maxrate);
+}
+
+static int dcb_cmd_maxrate_show(struct dcb *dcb, const char *dev, int argc, char **argv)
+{
+	struct ieee_maxrate maxrate;
+	int ret;
+
+	ret = dcb_maxrate_get(dcb, dev, &maxrate);
+	if (ret)
+		return ret;
+
+	open_json_object(NULL);
+
+	if (!argc) {
+		dcb_maxrate_print(dcb, &maxrate);
+		goto out;
+	}
+
+	do {
+		if (matches(*argv, "help") == 0) {
+			dcb_maxrate_help_show();
+			return 0;
+		} else if (matches(*argv, "tc-maxrate") == 0) {
+			dcb_maxrate_print_tc_maxrate(dcb, &maxrate);
+			print_nl();
+		} else {
+			fprintf(stderr, "What is \"%s\"?\n", *argv);
+			dcb_maxrate_help_show();
+			return -EINVAL;
+		}
+
+		NEXT_ARG_FWD();
+	} while (argc > 0);
+
+out:
+	close_json_object();
+	return 0;
+}
+
+int dcb_cmd_maxrate(struct dcb *dcb, int argc, char **argv)
+{
+	if (!argc || matches(*argv, "help") == 0) {
+		dcb_maxrate_help();
+		return 0;
+	} else if (matches(*argv, "show") == 0) {
+		NEXT_ARG_FWD();
+		return dcb_cmd_parse_dev(dcb, argc, argv,
+					 dcb_cmd_maxrate_show, dcb_maxrate_help_show);
+	} else if (matches(*argv, "set") == 0) {
+		NEXT_ARG_FWD();
+		return dcb_cmd_parse_dev(dcb, argc, argv,
+					 dcb_cmd_maxrate_set, dcb_maxrate_help_set);
+	} else {
+		fprintf(stderr, "What is \"%s\"?\n", *argv);
+		dcb_maxrate_help();
+		return -EINVAL;
+	}
+}

dcb/dcb_pfc.c

@@ -0,0 +1,286 @@
+// SPDX-License-Identifier: GPL-2.0+
+
+#include <errno.h>
+#include <stdio.h>
+#include <linux/dcbnl.h>
+
+#include "dcb.h"
+#include "utils.h"
+
+static void dcb_pfc_help_set(void)
+{
+	fprintf(stderr,
+		"Usage: dcb pfc set dev STRING\n"
+		"           [ prio-pfc PFC-MAP ]\n"
+		"           [ macsec-bypass { on | off } ]\n"
+		"           [ delay INTEGER ]\n"
+		"\n"
+		" where PFC-MAP := [ PFC-MAP ] PFC-MAPPING\n"
+		"       PFC-MAPPING := { all | TC }:PFC\n"
+		"       TC := { 0 .. 7 }\n"
+		"       PFC := { on | off }\n"
+		"\n"
+	);
+}
+
+static void dcb_pfc_help_show(void)
+{
+	fprintf(stderr,
+		"Usage: dcb [ -s ] pfc show dev STRING\n"
+		"           [ pfc-cap ] [ prio-pfc ] [ macsec-bypass ]\n"
+		"           [ delay ] [ requests ] [ indications ]\n"
+		"\n"
+	);
+}
+
+static void dcb_pfc_help(void)
+{
+	fprintf(stderr,
+		"Usage: dcb pfc help\n"
+		"\n"
+	);
+	dcb_pfc_help_show();
+	dcb_pfc_help_set();
+}
+
+static void dcb_pfc_to_array(__u8 array[IEEE_8021QAZ_MAX_TCS], __u8 pfc_en)
+{
+	int i;
+
+	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++)
+		array[i] = !!(pfc_en & (1 << i));
+}
+
+static void dcb_pfc_from_array(__u8 array[IEEE_8021QAZ_MAX_TCS], __u8 *pfc_en_p)
+{
+	__u8 pfc_en = 0;
+	int i;
+
+	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
+		if (array[i])
+			pfc_en |= 1 << i;
+	}
+
+	*pfc_en_p = pfc_en;
+}
+
+static int dcb_pfc_parse_mapping_prio_pfc(__u32 key, char *value, void *data)
+{
+	struct ieee_pfc *pfc = data;
+	__u8 pfc_en[IEEE_8021QAZ_MAX_TCS];
+	bool enabled;
+	int ret;
+
+	dcb_pfc_to_array(pfc_en, pfc->pfc_en);
+
+	enabled = parse_on_off("PFC", value, &ret);
+	if (ret)
+		return ret;
+
+	ret = dcb_parse_mapping("PRIO", key, IEEE_8021QAZ_MAX_TCS - 1,
+				"PFC", enabled, -1,
+				dcb_set_u8, pfc_en);
+	if (ret)
+		return ret;
+
+	dcb_pfc_from_array(pfc_en, &pfc->pfc_en);
+	return 0;
+}
+
+static void dcb_pfc_print_pfc_cap(const struct ieee_pfc *pfc)
+{
+	print_uint(PRINT_ANY, "pfc_cap", "pfc-cap %d ", pfc->pfc_cap);
+}
+
+static void dcb_pfc_print_macsec_bypass(const struct ieee_pfc *pfc)
+{
+	print_on_off(PRINT_ANY, "macsec_bypass", "macsec-bypass %s ", pfc->mbc);
+}
+
+static void dcb_pfc_print_delay(const struct ieee_pfc *pfc)
+{
+	print_uint(PRINT_ANY, "delay", "delay %d ", pfc->delay);
+}
+
+static void dcb_pfc_print_prio_pfc(const struct ieee_pfc *pfc)
+{
+	__u8 pfc_en[IEEE_8021QAZ_MAX_TCS];
+
+	dcb_pfc_to_array(pfc_en, pfc->pfc_en);
+	dcb_print_named_array("prio_pfc", "prio-pfc",
+			      pfc_en, ARRAY_SIZE(pfc_en), &dcb_print_array_on_off);
+}
+
+static void dcb_pfc_print_requests(const struct ieee_pfc *pfc)
+{
+	open_json_array(PRINT_JSON, "requests");
+	print_string(PRINT_FP, NULL, "requests ", NULL);
+	dcb_print_array_u64(pfc->requests, ARRAY_SIZE(pfc->requests));
+	close_json_array(PRINT_JSON, "requests");
+}
+
+static void dcb_pfc_print_indications(const struct ieee_pfc *pfc)
+{
+	open_json_array(PRINT_JSON, "indications");
+	print_string(PRINT_FP, NULL, "indications ", NULL);
+	dcb_print_array_u64(pfc->indications, ARRAY_SIZE(pfc->indications));
+	close_json_array(PRINT_JSON, "indications");
+}
+
+static void dcb_pfc_print(const struct dcb *dcb, const struct ieee_pfc *pfc)
+{
+	dcb_pfc_print_pfc_cap(pfc);
+	dcb_pfc_print_macsec_bypass(pfc);
+	dcb_pfc_print_delay(pfc);
+	print_nl();
+
+	dcb_pfc_print_prio_pfc(pfc);
+	print_nl();
+
+	if (dcb->stats) {
+		dcb_pfc_print_requests(pfc);
+		print_nl();
+
+		dcb_pfc_print_indications(pfc);
+		print_nl();
+	}
+}
+
+static int dcb_pfc_get(struct dcb *dcb, const char *dev, struct ieee_pfc *pfc)
+{
+	return dcb_get_attribute(dcb, dev, DCB_ATTR_IEEE_PFC, pfc, sizeof(*pfc));
+}
+
+static int dcb_pfc_set(struct dcb *dcb, const char *dev, const struct ieee_pfc *pfc)
+{
+	return dcb_set_attribute(dcb, dev, DCB_ATTR_IEEE_PFC, pfc, sizeof(*pfc));
+}
+
+static int dcb_cmd_pfc_set(struct dcb *dcb, const char *dev, int argc, char **argv)
+{
+	struct ieee_pfc pfc;
+	int ret;
+
+	if (!argc) {
+		dcb_pfc_help_set();
+		return 0;
+	}
+
+	ret = dcb_pfc_get(dcb, dev, &pfc);
+	if (ret)
+		return ret;
+
+	do {
+		if (matches(*argv, "help") == 0) {
+			dcb_pfc_help_set();
+			return 0;
+		} else if (matches(*argv, "prio-pfc") == 0) {
+			NEXT_ARG();
+			ret = parse_mapping(&argc, &argv, true,
+					    &dcb_pfc_parse_mapping_prio_pfc, &pfc);
+			if (ret) {
+				fprintf(stderr, "Invalid pfc mapping %s\n", *argv);
+				return ret;
+			}
+			continue;
+		} else if (matches(*argv, "macsec-bypass") == 0) {
+			NEXT_ARG();
+			pfc.mbc = parse_on_off("macsec-bypass", *argv, &ret);
+			if (ret)
+				return ret;
+		} else if (matches(*argv, "delay") == 0) {
+			NEXT_ARG();
+			/* Do not support the size notations for delay.
+			 * Delay is specified in "bit times", not bits, so
+			 * it is not applicable. At the same time it would
+			 * be confusing that 10Kbit does not mean 10240,
+			 * but 1280.
+			 */
+			if (get_u16(&pfc.delay, *argv, 0)) {
+				fprintf(stderr, "Invalid delay `%s', expected an integer 0..65535\n",
+					*argv);
+				return -EINVAL;
+			}
+		} else {
+			fprintf(stderr, "What is \"%s\"?\n", *argv);
+			dcb_pfc_help_set();
+			return -EINVAL;
+		}
+
+		NEXT_ARG_FWD();
+	} while (argc > 0);
+
+	return dcb_pfc_set(dcb, dev, &pfc);
+}
+
+static int dcb_cmd_pfc_show(struct dcb *dcb, const char *dev, int argc, char **argv)
+{
+	struct ieee_pfc pfc;
+	int ret;
+
+	ret = dcb_pfc_get(dcb, dev, &pfc);
+	if (ret)
+		return ret;
+
+	open_json_object(NULL);
+
+	if (!argc) {
+		dcb_pfc_print(dcb, &pfc);
+		goto out;
+	}
+
+	do {
+		if (matches(*argv, "help") == 0) {
+			dcb_pfc_help_show();
+			return 0;
+		} else if (matches(*argv, "prio-pfc") == 0) {
+			dcb_pfc_print_prio_pfc(&pfc);
+			print_nl();
+		} else if (matches(*argv, "pfc-cap") == 0) {
+			dcb_pfc_print_pfc_cap(&pfc);
+			print_nl();
+		} else if (matches(*argv, "macsec-bypass") == 0) {
+			dcb_pfc_print_macsec_bypass(&pfc);
+			print_nl();
+		} else if (matches(*argv, "delay") == 0) {
+			dcb_pfc_print_delay(&pfc);
+			print_nl();
+		} else if (matches(*argv, "requests") == 0) {
+			dcb_pfc_print_requests(&pfc);
+			print_nl();
+		} else if (matches(*argv, "indications") == 0) {
+			dcb_pfc_print_indications(&pfc);
+			print_nl();
+		} else {
+			fprintf(stderr, "What is \"%s\"?\n", *argv);
+			dcb_pfc_help_show();
+			return -EINVAL;
+		}
+
+		NEXT_ARG_FWD();
+	} while (argc > 0);
+
+out:
+	close_json_object();
+	return 0;
+}
+
+int dcb_cmd_pfc(struct dcb *dcb, int argc, char **argv)
+{
+	if (!argc || matches(*argv, "help") == 0) {
+		dcb_pfc_help();
+		return 0;
+	} else if (matches(*argv, "show") == 0) {
+		NEXT_ARG_FWD();
+		return dcb_cmd_parse_dev(dcb, argc, argv,
+					 dcb_cmd_pfc_show, dcb_pfc_help_show);
+	} else if (matches(*argv, "set") == 0) {
+		NEXT_ARG_FWD();
+		return dcb_cmd_parse_dev(dcb, argc, argv,
+					 dcb_cmd_pfc_set, dcb_pfc_help_set);
+	} else {
+		fprintf(stderr, "What is \"%s\"?\n", *argv);
+		dcb_pfc_help();
+		return -EINVAL;
+	}
+}

devlink/Makefile

@@ -7,12 +7,13 @@ ifeq ($(HAVE_MNL),y)
 
 DEVLINKOBJ = devlink.o mnlg.o
 TARGETS += devlink
+LDLIBS += -lm
 
 endif
 
 all: $(TARGETS) $(LIBS)
 
-devlink: $(DEVLINKOBJ)
+devlink: $(DEVLINKOBJ) $(LIBNETLINK)
 	$(QUIET_LINK)$(CC) $^ $(LDFLAGS) $(LDLIBS) -o $@
 
 install: all

devlink/mnlg.c

@@ -14,11 +14,11 @@
 #include <string.h>
 #include <errno.h>
 #include <unistd.h>
-#include <time.h>
 #include <libmnl/libmnl.h>
 #include <linux/genetlink.h>
 
 #include "libnetlink.h"
+#include "mnl_utils.h"
 #include "utils.h"
 #include "mnlg.h"
 
@@ -28,97 +28,13 @@ struct mnlg_socket {
 	uint32_t id;
 	uint8_t version;
 	unsigned int seq;
-	unsigned int portid;
 };
 
-static struct nlmsghdr *__mnlg_msg_prepare(struct mnlg_socket *nlg, uint8_t cmd,
+int mnlg_socket_send(struct mnlu_gen_socket *nlg, const struct nlmsghdr *nlh)
-					   uint16_t flags, uint32_t id,
-					   uint8_t version)
-{
-	struct nlmsghdr *nlh;
-	struct genlmsghdr *genl;
-
-	nlh = mnl_nlmsg_put_header(nlg->buf);
-	nlh->nlmsg_type	= id;
-	nlh->nlmsg_flags = flags;
-	nlg->seq = time(NULL);
-	nlh->nlmsg_seq = nlg->seq;
-
-	genl = mnl_nlmsg_put_extra_header(nlh, sizeof(struct genlmsghdr));
-	genl->cmd = cmd;
-	genl->version = version;
-
-	return nlh;
-}
-
-struct nlmsghdr *mnlg_msg_prepare(struct mnlg_socket *nlg, uint8_t cmd,
-				  uint16_t flags)
-{
-	return __mnlg_msg_prepare(nlg, cmd, flags, nlg->id, nlg->version);
-}
-
-int mnlg_socket_send(struct mnlg_socket *nlg, const struct nlmsghdr *nlh)
 {
 	return mnl_socket_sendto(nlg->nl, nlh, nlh->nlmsg_len);
 }
 
-static int mnlg_cb_noop(const struct nlmsghdr *nlh, void *data)
-{
-	return MNL_CB_OK;
-}
-
-static int mnlg_cb_error(const struct nlmsghdr *nlh, void *data)
-{
-	const struct nlmsgerr *err = mnl_nlmsg_get_payload(nlh);
-
-	/* Netlink subsystems returns the errno value with different signess */
-	if (err->error < 0)
-		errno = -err->error;
-	else
-		errno = err->error;
-
-	if (nl_dump_ext_ack(nlh, NULL))
-		return MNL_CB_ERROR;
-
-	return err->error == 0 ? MNL_CB_STOP : MNL_CB_ERROR;
-}
-
-static int mnlg_cb_stop(const struct nlmsghdr *nlh, void *data)
-{
-	int len = *(int *)NLMSG_DATA(nlh);
-
-	if (len < 0) {
-		errno = -len;
-		nl_dump_ext_ack_done(nlh, len);
-		return MNL_CB_ERROR;
-	}
-	return MNL_CB_STOP;
-}
-
-static mnl_cb_t mnlg_cb_array[NLMSG_MIN_TYPE] = {
-	[NLMSG_NOOP]	= mnlg_cb_noop,
-	[NLMSG_ERROR]	= mnlg_cb_error,
-	[NLMSG_DONE]	= mnlg_cb_stop,
-	[NLMSG_OVERRUN]	= mnlg_cb_noop,
-};
-
-int mnlg_socket_recv_run(struct mnlg_socket *nlg, mnl_cb_t data_cb, void *data)
-{
-	int err;
-
-	do {
-		err = mnl_socket_recvfrom(nlg->nl, nlg->buf,
-					  MNL_SOCKET_BUFFER_SIZE);
-		if (err <= 0)
-			break;
-		err = mnl_cb_run2(nlg->buf, err, nlg->seq, nlg->portid,
-				  data_cb, data, mnlg_cb_array,
-				  ARRAY_SIZE(mnlg_cb_array));
-	} while (err > 0);
-
-	return err;
-}
-
 struct group_info {
 	bool found;
 	uint32_t id;
@@ -198,15 +114,17 @@ static int get_group_id_cb(const struct nlmsghdr *nlh, void *data)
 	return MNL_CB_OK;
 }
 
-int mnlg_socket_group_add(struct mnlg_socket *nlg, const char *group_name)
+int mnlg_socket_group_add(struct mnlu_gen_socket *nlg, const char *group_name)
 {
 	struct nlmsghdr *nlh;
 	struct group_info group_info;
 	int err;
 
-	nlh = __mnlg_msg_prepare(nlg, CTRL_CMD_GETFAMILY,
+	nlh = _mnlu_gen_socket_cmd_prepare(nlg, CTRL_CMD_GETFAMILY,
-				 NLM_F_REQUEST | NLM_F_ACK, GENL_ID_CTRL, 1);
+					   NLM_F_REQUEST | NLM_F_ACK,
-	mnl_attr_put_u16(nlh, CTRL_ATTR_FAMILY_ID, nlg->id);
+					   GENL_ID_CTRL, 1);
+
+	mnl_attr_put_u16(nlh, CTRL_ATTR_FAMILY_ID, nlg->family);
 
 	err = mnlg_socket_send(nlg, nlh);
 	if (err < 0)
@@ -214,7 +132,7 @@ int mnlg_socket_group_add(struct mnlg_socket *nlg, const char *group_name)
 
 	group_info.found = false;
 	group_info.name = group_name;
-	err = mnlg_socket_recv_run(nlg, get_group_id_cb, &group_info);
+	err = mnlu_gen_socket_recv_run(nlg, get_group_id_cb, &group_info);
 	if (err < 0)
 		return err;
 
@@ -231,97 +149,7 @@ int mnlg_socket_group_add(struct mnlg_socket *nlg, const char *group_name)
 	return 0;
 }
 
-static int get_family_id_attr_cb(const struct nlattr *attr, void *data)
+int mnlg_socket_get_fd(struct mnlu_gen_socket *nlg)
-{
-	const struct nlattr **tb = data;
-	int type = mnl_attr_get_type(attr);
-
-	if (mnl_attr_type_valid(attr, CTRL_ATTR_MAX) < 0)
-		return MNL_CB_ERROR;
-
-	if (type == CTRL_ATTR_FAMILY_ID &&
-	    mnl_attr_validate(attr, MNL_TYPE_U16) < 0)
-		return MNL_CB_ERROR;
-	tb[type] = attr;
-	return MNL_CB_OK;
-}
-
-static int get_family_id_cb(const struct nlmsghdr *nlh, void *data)
-{
-	uint32_t *p_id = data;
-	struct nlattr *tb[CTRL_ATTR_MAX + 1] = {};
-	struct genlmsghdr *genl = mnl_nlmsg_get_payload(nlh);
-
-	mnl_attr_parse(nlh, sizeof(*genl), get_family_id_attr_cb, tb);
-	if (!tb[CTRL_ATTR_FAMILY_ID])
-		return MNL_CB_ERROR;
-	*p_id = mnl_attr_get_u16(tb[CTRL_ATTR_FAMILY_ID]);
-	return MNL_CB_OK;
-}
-
-struct mnlg_socket *mnlg_socket_open(const char *family_name, uint8_t version)
-{
-	struct mnlg_socket *nlg;
-	struct nlmsghdr *nlh;
-	int one = 1;
-	int err;
-
-	nlg = malloc(sizeof(*nlg));
-	if (!nlg)
-		return NULL;
-
-	nlg->buf = malloc(MNL_SOCKET_BUFFER_SIZE);
-	if (!nlg->buf)
-		goto err_buf_alloc;
-
-	nlg->nl = mnl_socket_open(NETLINK_GENERIC);
-	if (!nlg->nl)
-		goto err_mnl_socket_open;
-
-	/* Older kernels may no support capped/extended ACK reporting */
-	mnl_socket_setsockopt(nlg->nl, NETLINK_CAP_ACK, &one, sizeof(one));
-	mnl_socket_setsockopt(nlg->nl, NETLINK_EXT_ACK, &one, sizeof(one));
-
-	err = mnl_socket_bind(nlg->nl, 0, MNL_SOCKET_AUTOPID);
-	if (err < 0)
-		goto err_mnl_socket_bind;
-
-	nlg->portid = mnl_socket_get_portid(nlg->nl);
-
-	nlh = __mnlg_msg_prepare(nlg, CTRL_CMD_GETFAMILY,
-				 NLM_F_REQUEST | NLM_F_ACK, GENL_ID_CTRL, 1);
-	mnl_attr_put_strz(nlh, CTRL_ATTR_FAMILY_NAME, family_name);
-
-	err = mnlg_socket_send(nlg, nlh);
-	if (err < 0)
-		goto err_mnlg_socket_send;
-
-	err = mnlg_socket_recv_run(nlg, get_family_id_cb, &nlg->id);
-	if (err < 0)
-		goto err_mnlg_socket_recv_run;
-
-	nlg->version = version;
-	return nlg;
-
-err_mnlg_socket_recv_run:
-err_mnlg_socket_send:
-err_mnl_socket_bind:
-	mnl_socket_close(nlg->nl);
-err_mnl_socket_open:
-	free(nlg->buf);
-err_buf_alloc:
-	free(nlg);
-	return NULL;
-}
-
-void mnlg_socket_close(struct mnlg_socket *nlg)
-{
-	mnl_socket_close(nlg->nl);
-	free(nlg->buf);
-	free(nlg);
-}
-
-int mnlg_socket_get_fd(struct mnlg_socket *nlg)
 {
 	return mnl_socket_get_fd(nlg->nl);
 }

devlink/mnlg.h

@@ -14,15 +14,10 @@
 
 #include <libmnl/libmnl.h>
 
-struct mnlg_socket;
+struct mnlu_gen_socket;
 
-struct nlmsghdr *mnlg_msg_prepare(struct mnlg_socket *nlg, uint8_t cmd,
+int mnlg_socket_send(struct mnlu_gen_socket *nlg, const struct nlmsghdr *nlh);
-				  uint16_t flags);
+int mnlg_socket_group_add(struct mnlu_gen_socket *nlg, const char *group_name);
-int mnlg_socket_send(struct mnlg_socket *nlg, const struct nlmsghdr *nlh);
+int mnlg_socket_get_fd(struct mnlu_gen_socket *nlg);
-int mnlg_socket_recv_run(struct mnlg_socket *nlg, mnl_cb_t data_cb, void *data);
-int mnlg_socket_group_add(struct mnlg_socket *nlg, const char *group_name);
-struct mnlg_socket *mnlg_socket_open(const char *family_name, uint8_t version);
-void mnlg_socket_close(struct mnlg_socket *nlg);
-int mnlg_socket_get_fd(struct mnlg_socket *nlg);
 
 #endif /* _MNLG_H_ */

doc/actions/gact-usage

@@ -10,7 +10,7 @@ Where:
 
 ACTION semantics
 - pass and ok are equivalent to accept
-- continue allows to restart classification lookup
+- continue allows one to restart classification lookup
 - drop drops packets
 - reclassify implies continue classification where we left off
 

etc/iproute2/rt_protos

@@ -14,8 +14,10 @@
 13	dnrouted
 14	xorp
 15	ntk
-16      dhcp
+16	dhcp
+18	keepalived
 42	babel
+99	openr
 186	bgp
 187	isis
 188	ospf

examples/bpf/README

@@ -1,8 +1,18 @@
 eBPF toy code examples (running in kernel) to familiarize yourself
 with syntax and features:
 
- - bpf_shared.c		-> Ingress/egress map sharing example
+- BTF defined map examples
- - bpf_tailcall.c	-> Using tail call chains
- - bpf_cyclic.c		-> Simple cycle as tail calls
  - bpf_graft.c		-> Demo on altering runtime behaviour
- - bpf_map_in_map.c     -> Using map in map example
+ - bpf_shared.c 	-> Ingress/egress map sharing example
+ - bpf_map_in_map.c	-> Using map in map example
+
+- legacy struct bpf_elf_map defined map examples
+ - legacy/bpf_shared.c		-> Ingress/egress map sharing example
+ - legacy/bpf_tailcall.c	-> Using tail call chains
+ - legacy/bpf_cyclic.c		-> Simple cycle as tail calls
+ - legacy/bpf_graft.c		-> Demo on altering runtime behaviour
+ - legacy/bpf_map_in_map.c	-> Using map in map example
+
+Note: Users should use new BTF way to defined the maps, the examples
+in legacy folder which is using struct bpf_elf_map defined maps is not
+recommanded.

examples/bpf/bpf_graft.c

@@ -33,13 +33,13 @@
  *   [...]
  */
 
-struct bpf_elf_map __section_maps jmp_tc = {
+struct {
-	.type		= BPF_MAP_TYPE_PROG_ARRAY,
+	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
-	.size_key	= sizeof(uint32_t),
+	__uint(key_size, sizeof(uint32_t));
-	.size_value	= sizeof(uint32_t),
+	__uint(value_size, sizeof(uint32_t));
-	.pinning	= PIN_GLOBAL_NS,
+	__uint(max_entries, 1);
-	.max_elem	= 1,
+	__uint(pinning, LIBBPF_PIN_BY_NAME);
-};
+} jmp_tc __section(".maps");
 
 __section("aaa")
 int cls_aaa(struct __sk_buff *skb)

examples/bpf/bpf_map_in_map.c

@@ -1,24 +1,23 @@
 #include "../../include/bpf_api.h"
 
-#define MAP_INNER_ID	42
+struct inner_map {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(key_size, sizeof(uint32_t));
+	__uint(value_size, sizeof(uint32_t));
+	__uint(max_entries, 1);
+} map_inner __section(".maps");
 
-struct bpf_elf_map __section_maps map_inner = {
+struct {
-	.type		= BPF_MAP_TYPE_ARRAY,
+	__uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS);
-	.size_key	= sizeof(uint32_t),
+	__uint(key_size, sizeof(uint32_t));
-	.size_value	= sizeof(uint32_t),
+	__uint(value_size, sizeof(uint32_t));
-	.id		= MAP_INNER_ID,
+	__uint(max_entries, 1);
-	.inner_idx	= 0,
+	__uint(pinning, LIBBPF_PIN_BY_NAME);
-	.pinning	= PIN_GLOBAL_NS,
+	__array(values, struct inner_map);
-	.max_elem	= 1,
+} map_outer __section(".maps") = {
-};
+	.values = {
-
+		[0] = &map_inner,
-struct bpf_elf_map __section_maps map_outer = {
+	},
-	.type		= BPF_MAP_TYPE_ARRAY_OF_MAPS,
-	.size_key	= sizeof(uint32_t),
-	.size_value	= sizeof(uint32_t),
-	.inner_id	= MAP_INNER_ID,
-	.pinning	= PIN_GLOBAL_NS,
-	.max_elem	= 1,
 };
 
 __section("egress")

examples/bpf/bpf_shared.c

@@ -18,13 +18,13 @@
  * instance is being created.
  */
 
-struct bpf_elf_map __section_maps map_sh = {
+struct {
-	.type		= BPF_MAP_TYPE_ARRAY,
+	__uint(type, BPF_MAP_TYPE_ARRAY);
-	.size_key	= sizeof(uint32_t),
+	__uint(key_size, sizeof(uint32_t));
-	.size_value	= sizeof(uint32_t),
+	__uint(value_size, sizeof(uint32_t));
-	.pinning	= PIN_OBJECT_NS, /* or PIN_GLOBAL_NS, or PIN_NONE */
+	__uint(max_entries, 1);
-	.max_elem	= 1,
+	__uint(pinning, LIBBPF_PIN_BY_NAME);	/* or LIBBPF_PIN_NONE */
-};
+} map_sh __section(".maps");
 
 __section("egress")
 int emain(struct __sk_buff *skb)

examples/bpf/legacy/bpf_cyclic.c

@@ -1,4 +1,4 @@
-#include "../../include/bpf_api.h"
+#include "../../../include/bpf_api.h"
 
 /* Cyclic dependency example to test the kernel's runtime upper
  * bound on loops. Also demonstrates on how to use direct-actions,

examples/bpf/legacy/bpf_graft.c

@@ -0,0 +1,66 @@
+#include "../../../include/bpf_api.h"
+
+/* This example demonstrates how classifier run-time behaviour
+ * can be altered with tail calls. We start out with an empty
+ * jmp_tc array, then add section aaa to the array slot 0, and
+ * later on atomically replace it with section bbb. Note that
+ * as shown in other examples, the tc loader can prepopulate
+ * tail called sections, here we start out with an empty one
+ * on purpose to show it can also be done this way.
+ *
+ * tc filter add dev foo parent ffff: bpf obj graft.o
+ * tc exec bpf dbg
+ *   [...]
+ *   Socket Thread-20229 [001] ..s. 138993.003923: : fallthrough
+ *   <idle>-0            [001] ..s. 138993.202265: : fallthrough
+ *   Socket Thread-20229 [001] ..s. 138994.004149: : fallthrough
+ *   [...]
+ *
+ * tc exec bpf graft m:globals/jmp_tc key 0 obj graft.o sec aaa
+ * tc exec bpf dbg
+ *   [...]
+ *   Socket Thread-19818 [002] ..s. 139012.053587: : aaa
+ *   <idle>-0            [002] ..s. 139012.172359: : aaa
+ *   Socket Thread-19818 [001] ..s. 139012.173556: : aaa
+ *   [...]
+ *
+ * tc exec bpf graft m:globals/jmp_tc key 0 obj graft.o sec bbb
+ * tc exec bpf dbg
+ *   [...]
+ *   Socket Thread-19818 [002] ..s. 139022.102967: : bbb
+ *   <idle>-0            [002] ..s. 139022.155640: : bbb
+ *   Socket Thread-19818 [001] ..s. 139022.156730: : bbb
+ *   [...]
+ */
+
+struct bpf_elf_map __section_maps jmp_tc = {
+	.type		= BPF_MAP_TYPE_PROG_ARRAY,
+	.size_key	= sizeof(uint32_t),
+	.size_value	= sizeof(uint32_t),
+	.pinning	= PIN_GLOBAL_NS,
+	.max_elem	= 1,
+};
+
+__section("aaa")
+int cls_aaa(struct __sk_buff *skb)
+{
+	printt("aaa\n");
+	return TC_H_MAKE(1, 42);
+}
+
+__section("bbb")
+int cls_bbb(struct __sk_buff *skb)
+{
+	printt("bbb\n");
+	return TC_H_MAKE(1, 43);
+}
+
+__section_cls_entry
+int cls_entry(struct __sk_buff *skb)
+{
+	tail_call(skb, &jmp_tc, 0);
+	printt("fallthrough\n");
+	return BPF_H_DEFAULT;
+}
+
+BPF_LICENSE("GPL");

examples/bpf/legacy/bpf_map_in_map.c

@@ -0,0 +1,56 @@
+#include "../../../include/bpf_api.h"
+
+#define MAP_INNER_ID	42
+
+struct bpf_elf_map __section_maps map_inner = {
+	.type		= BPF_MAP_TYPE_ARRAY,
+	.size_key	= sizeof(uint32_t),
+	.size_value	= sizeof(uint32_t),
+	.id		= MAP_INNER_ID,
+	.inner_idx	= 0,
+	.pinning	= PIN_GLOBAL_NS,
+	.max_elem	= 1,
+};
+
+struct bpf_elf_map __section_maps map_outer = {
+	.type		= BPF_MAP_TYPE_ARRAY_OF_MAPS,
+	.size_key	= sizeof(uint32_t),
+	.size_value	= sizeof(uint32_t),
+	.inner_id	= MAP_INNER_ID,
+	.pinning	= PIN_GLOBAL_NS,
+	.max_elem	= 1,
+};
+
+__section("egress")
+int emain(struct __sk_buff *skb)
+{
+	struct bpf_elf_map *map_inner;
+	int key = 0, *val;
+
+	map_inner = map_lookup_elem(&map_outer, &key);
+	if (map_inner) {
+		val = map_lookup_elem(map_inner, &key);
+		if (val)
+			lock_xadd(val, 1);
+	}
+
+	return BPF_H_DEFAULT;
+}
+
+__section("ingress")
+int imain(struct __sk_buff *skb)
+{
+	struct bpf_elf_map *map_inner;
+	int key = 0, *val;
+
+	map_inner = map_lookup_elem(&map_outer, &key);
+	if (map_inner) {
+		val = map_lookup_elem(map_inner, &key);
+		if (val)
+			printt("map val: %d\n", *val);
+	}
+
+	return BPF_H_DEFAULT;
+}
+
+BPF_LICENSE("GPL");

examples/bpf/legacy/bpf_shared.c

@@ -0,0 +1,53 @@
+#include "../../../include/bpf_api.h"
+
+/* Minimal, stand-alone toy map pinning example:
+ *
+ * clang -target bpf -O2 [...] -o bpf_shared.o -c bpf_shared.c
+ * tc filter add dev foo parent 1: bpf obj bpf_shared.o sec egress
+ * tc filter add dev foo parent ffff: bpf obj bpf_shared.o sec ingress
+ *
+ * Both classifier will share the very same map instance in this example,
+ * so map content can be accessed from ingress *and* egress side!
+ *
+ * This example has a pinning of PIN_OBJECT_NS, so it's private and
+ * thus shared among various program sections within the object.
+ *
+ * A setting of PIN_GLOBAL_NS would place it into a global namespace,
+ * so that it can be shared among different object files. A setting
+ * of PIN_NONE (= 0) means no sharing, so each tc invocation a new map
+ * instance is being created.
+ */
+
+struct bpf_elf_map __section_maps map_sh = {
+	.type		= BPF_MAP_TYPE_ARRAY,
+	.size_key	= sizeof(uint32_t),
+	.size_value	= sizeof(uint32_t),
+	.pinning	= PIN_OBJECT_NS, /* or PIN_GLOBAL_NS, or PIN_NONE */
+	.max_elem	= 1,
+};
+
+__section("egress")
+int emain(struct __sk_buff *skb)
+{
+	int key = 0, *val;
+
+	val = map_lookup_elem(&map_sh, &key);
+	if (val)
+		lock_xadd(val, 1);
+
+	return BPF_H_DEFAULT;
+}
+
+__section("ingress")
+int imain(struct __sk_buff *skb)
+{
+	int key = 0, *val;
+
+	val = map_lookup_elem(&map_sh, &key);
+	if (val)
+		printt("map val: %d\n", *val);
+
+	return BPF_H_DEFAULT;
+}
+
+BPF_LICENSE("GPL");

examples/bpf/legacy/bpf_tailcall.c

@@ -1,5 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-#include "../../include/bpf_api.h"
+#include "../../../include/bpf_api.h"
 
 #define ENTRY_INIT	3
 #define ENTRY_0		0

genl/ctrl.c

@@ -28,13 +28,15 @@
 static int usage(void)
 {
 	fprintf(stderr,"Usage: ctrl <CMD>\n" \
-		       "CMD   := get <PARMS> | list | monitor\n" \
+		       "CMD   := get <PARMS> | list | monitor | policy <PARMS>\n" \
 		       "PARMS := name <name> | id <id>\n" \
 		       "Examples:\n" \
 		       "\tctrl ls\n" \
 		       "\tctrl monitor\n" \
 		       "\tctrl get name foobar\n" \
-		       "\tctrl get id 0xF\n");
+		       "\tctrl get id 0xF\n"
+		       "\tctrl policy name foobar\n"
+		       "\tctrl policy id 0xF\n");
 	return -1;
 }
 
@@ -123,7 +125,8 @@ static int print_ctrl(struct rtnl_ctrl_data *ctrl,
 	    ghdr->cmd != CTRL_CMD_DELFAMILY &&
 	    ghdr->cmd != CTRL_CMD_NEWFAMILY &&
 	    ghdr->cmd != CTRL_CMD_NEWMCAST_GRP &&
-	    ghdr->cmd != CTRL_CMD_DELMCAST_GRP) {
+	    ghdr->cmd != CTRL_CMD_DELMCAST_GRP &&
+	    ghdr->cmd != CTRL_CMD_GETPOLICY) {
 		fprintf(stderr, "Unknown controller command %d\n", ghdr->cmd);
 		return 0;
 	}
@@ -136,7 +139,7 @@ static int print_ctrl(struct rtnl_ctrl_data *ctrl,
 	}
 
 	attrs = (struct rtattr *) ((char *) ghdr + GENL_HDRLEN);
-	parse_rtattr(tb, CTRL_ATTR_MAX, attrs, len);
+	parse_rtattr_flags(tb, CTRL_ATTR_MAX, attrs, len, NLA_F_NESTED);
 
 	if (tb[CTRL_ATTR_FAMILY_NAME]) {
 		char *name = RTA_DATA(tb[CTRL_ATTR_FAMILY_NAME]);
@@ -159,6 +162,36 @@ static int print_ctrl(struct rtnl_ctrl_data *ctrl,
 		__u32 *ma = RTA_DATA(tb[CTRL_ATTR_MAXATTR]);
 		fprintf(fp, " max attribs: %d ",*ma);
 	}
+	if (tb[CTRL_ATTR_OP_POLICY]) {
+		const struct rtattr *pos;
+
+		rtattr_for_each_nested(pos, tb[CTRL_ATTR_OP_POLICY]) {
+			struct rtattr *ptb[CTRL_ATTR_POLICY_DUMP_MAX + 1];
+			struct rtattr *pattrs = RTA_DATA(pos);
+			int plen = RTA_PAYLOAD(pos);
+
+			parse_rtattr_flags(ptb, CTRL_ATTR_POLICY_DUMP_MAX,
+					   pattrs, plen, NLA_F_NESTED);
+
+			fprintf(fp, " op %d policies:",
+				pos->rta_type & ~NLA_F_NESTED);
+
+			if (ptb[CTRL_ATTR_POLICY_DO]) {
+				__u32 *v = RTA_DATA(ptb[CTRL_ATTR_POLICY_DO]);
+
+				fprintf(fp, " do=%d", *v);
+			}
+
+			if (ptb[CTRL_ATTR_POLICY_DUMP]) {
+				__u32 *v = RTA_DATA(ptb[CTRL_ATTR_POLICY_DUMP]);
+
+				fprintf(fp, " dump=%d", *v);
+			}
+		}
+	}
+	if (tb[CTRL_ATTR_POLICY])
+		nl_print_policy(tb[CTRL_ATTR_POLICY], fp);
+
 	/* end of family definitions .. */
 	fprintf(fp,"\n");
 	if (tb[CTRL_ATTR_OPS]) {
@@ -235,7 +268,9 @@ static int ctrl_list(int cmd, int argc, char **argv)
 		exit(1);
 	}
 
-	if (cmd == CTRL_CMD_GETFAMILY) {
+	if (cmd == CTRL_CMD_GETFAMILY || cmd == CTRL_CMD_GETPOLICY) {
+		req.g.cmd = cmd;
+
 		if (argc != 2) {
 			fprintf(stderr, "Wrong number of params\n");
 			return -1;
@@ -260,7 +295,9 @@ static int ctrl_list(int cmd, int argc, char **argv)
 			fprintf(stderr, "Wrong params\n");
 			goto ctrl_done;
 		}
+	}
 
+	if (cmd == CTRL_CMD_GETFAMILY) {
 		if (rtnl_talk(&rth, nlh, &answer) < 0) {
 			fprintf(stderr, "Error talking to the kernel\n");
 			goto ctrl_done;
@@ -273,7 +310,7 @@ static int ctrl_list(int cmd, int argc, char **argv)
 
 	}
 
-	if (cmd == CTRL_CMD_UNSPEC) {
+	if (cmd == CTRL_CMD_UNSPEC || cmd == CTRL_CMD_GETPOLICY) {
 		nlh->nlmsg_flags = NLM_F_ROOT|NLM_F_MATCH|NLM_F_REQUEST;
 		nlh->nlmsg_seq = rth.dump = ++rth.seq;
 
@@ -324,6 +361,8 @@ static int parse_ctrl(struct genl_util *a, int argc, char **argv)
 	    matches(*argv, "show") == 0 ||
 	    matches(*argv, "lst") == 0)
 		return ctrl_list(CTRL_CMD_UNSPEC, argc-1, argv+1);
+	if (matches(*argv, "policy") == 0)
+		return ctrl_list(CTRL_CMD_GETPOLICY, argc-1, argv+1);
 	if (matches(*argv, "help") == 0)
 		return usage();
 

genl/genl.c

@@ -22,7 +22,7 @@
 #include <errno.h>
 #include <linux/netlink.h>
 #include <linux/rtnetlink.h> /* until we put our own header */
-#include "SNAPSHOT.h"
+#include "version.h"
 #include "utils.h"
 #include "genl_utils.h"
 
@@ -118,7 +118,7 @@ int main(int argc, char **argv)
 		} else if (matches(argv[1], "-raw") == 0) {
 			++show_raw;
 		} else if (matches(argv[1], "-Version") == 0) {
-			printf("genl utility, iproute2-ss%s\n", SNAPSHOT);
+			printf("genl utility, iproute2-%s\n", version);
 			exit(0);
 		} else if (matches(argv[1], "-help") == 0) {
 			usage();

genl/genl_utils.h

@@ -2,11 +2,10 @@
 #ifndef _TC_UTIL_H_
 #define _TC_UTIL_H_ 1
 
+#include <linux/genetlink.h>
 #include "utils.h"
-#include "linux/genetlink.h"
 
-struct genl_util
+struct genl_util {
-{
 	struct  genl_util *next;
 	char	name[16];
 	int	(*parse_genlopt)(struct genl_util *fu, int argc, char **argv);

include/SNAPSHOT.h

@@ -1 +0,0 @@
-static const char SNAPSHOT[] = "200602";

include/bpf_api.h

@@ -19,6 +19,19 @@
 
 #include "bpf_elf.h"
 
+/** libbpf pin type. */
+enum libbpf_pin_type {
+	LIBBPF_PIN_NONE,
+	/* PIN_BY_NAME: pin maps by name (in /sys/fs/bpf by default) */
+	LIBBPF_PIN_BY_NAME,
+};
+
+/** Type helper macros. */
+
+#define __uint(name, val) int (*name)[val]
+#define __type(name, val) typeof(val) *name
+#define __array(name, val) typeof(val) *name[]
+
 /** Misc macros. */
 
 #ifndef __stringify

include/bpf_util.h

@@ -274,12 +274,16 @@ int bpf_trace_pipe(void);
 
 void bpf_print_ops(struct rtattr *bpf_ops, __u16 len);
 
-int bpf_prog_load(enum bpf_prog_type type, const struct bpf_insn *insns,
+int bpf_prog_load_dev(enum bpf_prog_type type, const struct bpf_insn *insns,
-		  size_t size_insns, const char *license, char *log,
+		      size_t size_insns, const char *license, __u32 ifindex,
-		  size_t size_log);
+		      char *log, size_t size_log);
+int bpf_program_load(enum bpf_prog_type type, const struct bpf_insn *insns,
+		     size_t size_insns, const char *license, char *log,
+		     size_t size_log);
 
 int bpf_prog_attach_fd(int prog_fd, int target_fd, enum bpf_attach_type type);
 int bpf_prog_detach_fd(int target_fd, enum bpf_attach_type type);
+int bpf_program_attach(int prog_fd, int target_fd, enum bpf_attach_type type);
 
 int bpf_dump_prog_info(FILE *f, uint32_t id);
 
@@ -287,6 +291,16 @@ int bpf_dump_prog_info(FILE *f, uint32_t id);
 int bpf_send_map_fds(const char *path, const char *obj);
 int bpf_recv_map_fds(const char *path, int *fds, struct bpf_map_aux *aux,
 		     unsigned int entries);
+#ifdef HAVE_LIBBPF
+int iproute2_bpf_elf_ctx_init(struct bpf_cfg_in *cfg);
+int iproute2_bpf_fetch_ancillary(void);
+int iproute2_get_root_path(char *root_path, size_t len);
+bool iproute2_is_pin_map(const char *libbpf_map_name, char *pathname);
+bool iproute2_is_map_in_map(const char *libbpf_map_name, struct bpf_elf_map *imap,
+			    struct bpf_elf_map *omap, char *omap_name);
+int iproute2_find_map_name_by_id(unsigned int map_id, char *name);
+int iproute2_load_libbpf(struct bpf_cfg_in *cfg);
+#endif /* HAVE_LIBBPF */
 #else
 static inline int bpf_send_map_fds(const char *path, const char *obj)
 {
@@ -299,5 +313,15 @@ static inline int bpf_recv_map_fds(const char *path, int *fds,
 {
 	return -1;
 }
+#ifdef HAVE_LIBBPF
+static inline int iproute2_load_libbpf(struct bpf_cfg_in *cfg)
+{
+	fprintf(stderr, "No ELF library support compiled in.\n");
+	return -1;
+}
+#endif /* HAVE_LIBBPF */
 #endif /* HAVE_ELF */
+
+const char *get_libbpf_version(void);
+
 #endif /* __BPF_UTIL__ */

include/cg_map.h

@@ -0,0 +1,6 @@
+#ifndef __CG_MAP_H__
+#define __CG_MAP_H__
+
+const char *cg_id_to_path(__u64 id);
+
+#endif /* __CG_MAP_H__ */

include/json_print.h

@@ -15,6 +15,9 @@
 #include "json_writer.h"
 #include "color.h"
 
+#define _IS_JSON_CONTEXT(type) (is_json_context() && (type & PRINT_JSON || type & PRINT_ANY))
+#define _IS_FP_CONTEXT(type)   (!is_json_context() && (type & PRINT_FP || type & PRINT_ANY))
+
 json_writer_t *get_json_writer(void);
 
 /*
@@ -65,9 +68,11 @@ void print_nl(void);
 _PRINT_FUNC(int, int)
 _PRINT_FUNC(s64, int64_t)
 _PRINT_FUNC(bool, bool)
+_PRINT_FUNC(on_off, bool)
 _PRINT_FUNC(null, const char*)
 _PRINT_FUNC(string, const char*)
 _PRINT_FUNC(uint, unsigned int)
+_PRINT_FUNC(size, __u32)
 _PRINT_FUNC(u64, uint64_t)
 _PRINT_FUNC(hhu, unsigned char)
 _PRINT_FUNC(hu, unsigned short)
@@ -76,6 +81,7 @@ _PRINT_FUNC(0xhex, unsigned long long)
 _PRINT_FUNC(luint, unsigned long)
 _PRINT_FUNC(lluint, unsigned long long)
 _PRINT_FUNC(float, double)
+_PRINT_FUNC(tv, const struct timeval *)
 #undef _PRINT_FUNC
 
 #define _PRINT_NAME_VALUE_FUNC(type_name, type, format_char)		  \
@@ -85,4 +91,17 @@ _PRINT_NAME_VALUE_FUNC(uint, unsigned int, u);
 _PRINT_NAME_VALUE_FUNC(string, const char*, s);
 #undef _PRINT_NAME_VALUE_FUNC
 
+int print_color_rate(bool use_iec, enum output_type t, enum color_attr color,
+		     const char *key, const char *fmt, unsigned long long rate);
+
+static inline int print_rate(bool use_iec, enum output_type t,
+			     const char *key, const char *fmt,
+			     unsigned long long rate)
+{
+	return print_color_rate(use_iec, t, COLOR_NONE, key, fmt, rate);
+}
+
+/* A backdoor to the size formatter. Please use print_size() instead. */
+char *sprint_size(__u32 sz, char *buf);
+
 #endif /* _JSON_PRINT_H_ */

include/libgenl.h

@@ -21,6 +21,7 @@ struct {								\
 	},								\
 }
 
+int genl_add_mcast_grp(struct rtnl_handle *grth, __u16 genl_family, const char *group);
 int genl_resolve_family(struct rtnl_handle *grth, const char *family);
 int genl_init_handle(struct rtnl_handle *grth, const char *family,
 		     int *genl_family);

include/libnetlink.h

@@ -69,6 +69,8 @@ int rtnl_neightbldump_req(struct rtnl_handle *rth, int family)
 	__attribute__((warn_unused_result));
 int rtnl_mdbdump_req(struct rtnl_handle *rth, int family)
 	__attribute__((warn_unused_result));
+int rtnl_brvlandump_req(struct rtnl_handle *rth, int family, __u32 dump_flags)
+	__attribute__((warn_unused_result));
 int rtnl_netconfdump_req(struct rtnl_handle *rth, int family)
 	__attribute__((warn_unused_result));
 
@@ -97,6 +99,9 @@ int rtnl_dump_request_n(struct rtnl_handle *rth, struct nlmsghdr *n)
 int rtnl_nexthopdump_req(struct rtnl_handle *rth, int family,
 			 req_filter_fn_t filter_fn)
 	__attribute__((warn_unused_result));
+int rtnl_nexthop_bucket_dump_req(struct rtnl_handle *rth, int family,
+				 req_filter_fn_t filter_fn)
+	__attribute__((warn_unused_result));
 
 struct rtnl_ctrl_data {
 	int	nsid;
@@ -104,6 +109,27 @@ struct rtnl_ctrl_data {
 
 typedef int (*rtnl_filter_t)(struct nlmsghdr *n, void *);
 
+/**
+ * rtnl error handler called from
+ *      rtnl_dump_done()
+ *      rtnl_dump_error()
+ *
+ * Return value is a bitmask of the following values:
+ * RTNL_LET_NLERR
+ *      error handled as usual
+ * RTNL_SUPPRESS_NLMSG_DONE_NLERR
+ *      error in nlmsg_type == NLMSG_DONE will be suppressed
+ * RTNL_SUPPRESS_NLMSG_ERROR_NLERR
+ *      error in nlmsg_type == NLMSG_ERROR will be suppressed
+ *      and nlmsg will be skipped
+ * RTNL_SUPPRESS_NLERR - suppress error in both previous cases
+ */
+#define RTNL_LET_NLERR				0x01
+#define RTNL_SUPPRESS_NLMSG_DONE_NLERR		0x02
+#define RTNL_SUPPRESS_NLMSG_ERROR_NLERR		0x04
+#define RTNL_SUPPRESS_NLERR			0x06
+typedef int (*rtnl_err_hndlr_t)(struct nlmsghdr *n, void *);
+
 typedef int (*rtnl_listen_filter_t)(struct rtnl_ctrl_data *,
 				    struct nlmsghdr *n, void *);
 
@@ -113,6 +139,8 @@ typedef int (*nl_ext_ack_fn_t)(const char *errmsg, uint32_t off,
 struct rtnl_dump_filter_arg {
 	rtnl_filter_t filter;
 	void *arg1;
+	rtnl_err_hndlr_t errhndlr;
+	void *arg2;
 	__u16 nc_flags;
 };
 
@@ -121,6 +149,15 @@ int rtnl_dump_filter_nc(struct rtnl_handle *rth,
 			void *arg, __u16 nc_flags);
 #define rtnl_dump_filter(rth, filter, arg) \
 	rtnl_dump_filter_nc(rth, filter, arg, 0)
+int rtnl_dump_filter_errhndlr_nc(struct rtnl_handle *rth,
+				 rtnl_filter_t filter,
+				 void *arg1,
+				 rtnl_err_hndlr_t errhndlr,
+				 void *arg2,
+				 __u16 nc_flags);
+#define rtnl_dump_filter_errhndlr(rth, filter, farg, errhndlr, earg) \
+	rtnl_dump_filter_errhndlr_nc(rth, filter, farg, errhndlr, earg, 0)
+
 int rtnl_talk(struct rtnl_handle *rtnl, struct nlmsghdr *n,
 	      struct nlmsghdr **answer)
 	__attribute__((warn_unused_result));
@@ -280,8 +317,20 @@ int rtnl_from_file(FILE *, rtnl_listen_filter_t handler,
 	((struct rtattr *)(((char *)(r)) + NLMSG_ALIGN(sizeof(struct if_stats_msg))))
 #endif
 
+#ifndef BRVLAN_RTA
+#define BRVLAN_RTA(r) \
+	((struct rtattr *)(((char *)(r)) + NLMSG_ALIGN(sizeof(struct br_vlan_msg))))
+#endif
+
 /* User defined nlmsg_type which is used mostly for logging netlink
  * messages from dump file */
 #define NLMSG_TSTAMP	15
 
+#define rtattr_for_each_nested(attr, nest) \
+	for ((attr) = (void *)RTA_DATA(nest); \
+	     RTA_OK(attr, RTA_PAYLOAD(nest) - ((char *)(attr) - (char *)RTA_DATA((nest)))); \
+	     (attr) = RTA_TAIL((attr)))
+
+void nl_print_policy(const struct rtattr *attr, FILE *fp);
+
 #endif /* __LIBNETLINK_H__ */

include/mnl_utils.h

@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __MNL_UTILS_H__
+#define __MNL_UTILS_H__ 1
+
+struct mnlu_gen_socket {
+	struct mnl_socket *nl;
+	char *buf;
+	uint32_t family;
+	unsigned int seq;
+	uint8_t version;
+};
+
+int mnlu_gen_socket_open(struct mnlu_gen_socket *nlg, const char *family_name,
+			 uint8_t version);
+void mnlu_gen_socket_close(struct mnlu_gen_socket *nlg);
+struct nlmsghdr *
+_mnlu_gen_socket_cmd_prepare(struct mnlu_gen_socket *nlg,
+			     uint8_t cmd, uint16_t flags,
+			     uint32_t id, uint8_t version);
+struct nlmsghdr *mnlu_gen_socket_cmd_prepare(struct mnlu_gen_socket *nlg,
+					     uint8_t cmd, uint16_t flags);
+int mnlu_gen_socket_sndrcv(struct mnlu_gen_socket *nlg, const struct nlmsghdr *nlh,
+			   mnl_cb_t data_cb, void *data);
+
+struct mnl_socket *mnlu_socket_open(int bus);
+struct nlmsghdr *mnlu_msg_prepare(void *buf, uint32_t nlmsg_type, uint16_t flags,
+				  void *extra_header, size_t extra_header_size);
+int mnlu_socket_recv_run(struct mnl_socket *nl, unsigned int seq, void *buf, size_t buf_size,
+			 mnl_cb_t cb, void *data);
+int mnlu_gen_socket_recv_run(struct mnlu_gen_socket *nlg, mnl_cb_t cb,
+			     void *data);
+
+#endif /* __MNL_UTILS_H__ */

include/rt_names.h

@@ -9,6 +9,7 @@ const char *rtnl_rtscope_n2a(int id, char *buf, int len);
 const char *rtnl_rttable_n2a(__u32 id, char *buf, int len);
 const char *rtnl_rtrealm_n2a(int id, char *buf, int len);
 const char *rtnl_dsfield_n2a(int id, char *buf, int len);
+const char *rtnl_dsfield_get_name(int id);
 const char *rtnl_group_n2a(int id, char *buf, int len);
 
 int rtnl_rtprot_a2n(__u32 *id, const char *arg);
@@ -33,6 +34,9 @@ int ll_proto_a2n(unsigned short *id, const char *buf);
 const char *nl_proto_n2a(int id, char *buf, int len);
 int nl_proto_a2n(__u32 *id, const char *arg);
 
+int protodown_reason_a2n(__u32 *id, const char *arg);
+int protodown_reason_n2a(int id, char *buf, int len);
+
 extern int numeric;
 
 #endif

include/uapi/linux/amt.h

@@ -0,0 +1,62 @@
+/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */
+/*
+ * Copyright (c) 2021 Taehee Yoo <ap420073@gmail.com>
+ */
+#ifndef _AMT_H_
+#define _AMT_H_
+
+enum ifla_amt_mode {
+	/* AMT interface works as Gateway mode.
+	 * The Gateway mode encapsulates IGMP/MLD traffic and decapsulates
+	 * multicast traffic.
+	 */
+	AMT_MODE_GATEWAY = 0,
+	/* AMT interface works as Relay mode.
+	 * The Relay mode encapsulates multicast traffic and decapsulates
+	 * IGMP/MLD traffic.
+	 */
+	AMT_MODE_RELAY,
+	__AMT_MODE_MAX,
+};
+
+#define AMT_MODE_MAX (__AMT_MODE_MAX - 1)
+
+enum {
+	IFLA_AMT_UNSPEC,
+	/* This attribute specify mode etier Gateway or Relay. */
+	IFLA_AMT_MODE,
+	/* This attribute specify Relay port.
+	 * AMT interface is created as Gateway mode, this attribute is used
+	 * to specify relay(remote) port.
+	 * AMT interface is created as Relay mode, this attribute is used
+	 * as local port.
+	 */
+	IFLA_AMT_RELAY_PORT,
+	/* This attribute specify Gateway port.
+	 * AMT interface is created as Gateway mode, this attribute is used
+	 * as local port.
+	 * AMT interface is created as Relay mode, this attribute is not used.
+	 */
+	IFLA_AMT_GATEWAY_PORT,
+	/* This attribute specify physical device */
+	IFLA_AMT_LINK,
+	/* This attribute specify local ip address */
+	IFLA_AMT_LOCAL_IP,
+	/* This attribute specify Relay ip address.
+	 * So, this is not used by Relay.
+	 */
+	IFLA_AMT_REMOTE_IP,
+	/* This attribute specify Discovery ip address.
+	 * When Gateway get started, it send discovery message to find the
+	 * Relay's ip address.
+	 * So, this is not used by Relay.
+	 */
+	IFLA_AMT_DISCOVERY_IP,
+	/* This attribute specify number of maximum tunnel. */
+	IFLA_AMT_MAX_TUNNELS,
+	__IFLA_AMT_MAX,
+};
+
+#define IFLA_AMT_MAX (__IFLA_AMT_MAX - 1)
+
+#endif /* _AMT_H_ */

include/uapi/linux/atmioc.h

@@ -5,7 +5,7 @@
 
 
 /*
- * See http://icawww1.epfl.ch/linux-atm/magic.html for the complete list of
+ * See https://icawww1.epfl.ch/linux-atm/magic.html for the complete list of
  * "magic" ioctl numbers.
  */
 

include/uapi/linux/btf.h

@@ -43,7 +43,7 @@ struct btf_type {
 	 * "size" tells the size of the type it is describing.
 	 *
 	 * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT,
-	 * FUNC, FUNC_PROTO and VAR.
+	 * FUNC, FUNC_PROTO, VAR and DECL_TAG.
 	 * "type" is a type_id referring to another type.
 	 */
 	union {
@@ -52,28 +52,33 @@ struct btf_type {
 	};
 };
 
-#define BTF_INFO_KIND(info)	(((info) >> 24) & 0x0f)
+#define BTF_INFO_KIND(info)	(((info) >> 24) & 0x1f)
 #define BTF_INFO_VLEN(info)	((info) & 0xffff)
 #define BTF_INFO_KFLAG(info)	((info) >> 31)
 
-#define BTF_KIND_UNKN		0	/* Unknown	*/
+enum {
-#define BTF_KIND_INT		1	/* Integer	*/
+	BTF_KIND_UNKN		= 0,	/* Unknown	*/
-#define BTF_KIND_PTR		2	/* Pointer	*/
+	BTF_KIND_INT		= 1,	/* Integer	*/
-#define BTF_KIND_ARRAY		3	/* Array	*/
+	BTF_KIND_PTR		= 2,	/* Pointer	*/
-#define BTF_KIND_STRUCT		4	/* Struct	*/
+	BTF_KIND_ARRAY		= 3,	/* Array	*/
-#define BTF_KIND_UNION		5	/* Union	*/
+	BTF_KIND_STRUCT		= 4,	/* Struct	*/
-#define BTF_KIND_ENUM		6	/* Enumeration	*/
+	BTF_KIND_UNION		= 5,	/* Union	*/
-#define BTF_KIND_FWD		7	/* Forward	*/
+	BTF_KIND_ENUM		= 6,	/* Enumeration	*/
-#define BTF_KIND_TYPEDEF	8	/* Typedef	*/
+	BTF_KIND_FWD		= 7,	/* Forward	*/
-#define BTF_KIND_VOLATILE	9	/* Volatile	*/
+	BTF_KIND_TYPEDEF	= 8,	/* Typedef	*/
-#define BTF_KIND_CONST		10	/* Const	*/
+	BTF_KIND_VOLATILE	= 9,	/* Volatile	*/
-#define BTF_KIND_RESTRICT	11	/* Restrict	*/
+	BTF_KIND_CONST		= 10,	/* Const	*/
-#define BTF_KIND_FUNC		12	/* Function	*/
+	BTF_KIND_RESTRICT	= 11,	/* Restrict	*/
-#define BTF_KIND_FUNC_PROTO	13	/* Function Proto	*/
+	BTF_KIND_FUNC		= 12,	/* Function	*/
-#define BTF_KIND_VAR		14	/* Variable	*/
+	BTF_KIND_FUNC_PROTO	= 13,	/* Function Proto	*/
-#define BTF_KIND_DATASEC	15	/* Section	*/
+	BTF_KIND_VAR		= 14,	/* Variable	*/
-#define BTF_KIND_MAX		BTF_KIND_DATASEC
+	BTF_KIND_DATASEC	= 15,	/* Section	*/
-#define NR_BTF_KINDS		(BTF_KIND_MAX + 1)
+	BTF_KIND_FLOAT		= 16,	/* Floating point	*/
+	BTF_KIND_DECL_TAG	= 17,	/* Decl Tag */
+
+	NR_BTF_KINDS,
+	BTF_KIND_MAX		= NR_BTF_KINDS - 1,
+};
 
 /* For some specific BTF_KIND, "struct btf_type" is immediately
  * followed by extra data.
@@ -169,4 +174,15 @@ struct btf_var_secinfo {
 	__u32	size;
 };
 
+/* BTF_KIND_DECL_TAG is followed by a single "struct btf_decl_tag" to describe
+ * additional information related to the tag applied location.
+ * If component_idx == -1, the tag is applied to a struct, union,
+ * variable or function. Otherwise, it is applied to a struct/union
+ * member or a func argument, and component_idx indicates which member
+ * or argument (0 ... vlen-1).
+ */
+struct btf_decl_tag {
+       __s32   component_idx;
+};
+
 #endif /* __LINUX_BTF_H__ */

include/uapi/linux/can.h

@@ -84,6 +84,7 @@ typedef __u32 can_err_mask_t;
 
 /* CAN payload length and DLC definitions according to ISO 11898-1 */
 #define CAN_MAX_DLC 8
+#define CAN_MAX_RAW_DLC 15
 #define CAN_MAX_DLEN 8
 
 /* CAN FD payload length and DLC definitions according to ISO 11898-7 */
@@ -91,30 +92,39 @@ typedef __u32 can_err_mask_t;
 #define CANFD_MAX_DLEN 64
 
 /**
- * struct can_frame - basic CAN frame structure
+ * struct can_frame - Classical CAN frame structure (aka CAN 2.0B)
- * @can_id:  CAN ID of the frame and CAN_*_FLAG flags, see canid_t definition
+ * @can_id:   CAN ID of the frame and CAN_*_FLAG flags, see canid_t definition
- * @can_dlc: frame payload length in byte (0 .. 8) aka data length code
+ * @len:      CAN frame payload length in byte (0 .. 8)
- *           N.B. the DLC field from ISO 11898-1 Chapter 8.4.2.3 has a 1:1
+ * @can_dlc:  deprecated name for CAN frame payload length in byte (0 .. 8)
- *           mapping of the 'data length code' to the real payload length
+ * @__pad:    padding
- * @__pad:   padding
+ * @__res0:   reserved / padding
- * @__res0:  reserved / padding
+ * @len8_dlc: optional DLC value (9 .. 15) at 8 byte payload length
- * @__res1:  reserved / padding
+ *            len8_dlc contains values from 9 .. 15 when the payload length is
- * @data:    CAN frame payload (up to 8 byte)
+ *            8 bytes but the DLC value (see ISO 11898-1) is greater then 8.
+ *            CAN_CTRLMODE_CC_LEN8_DLC flag has to be enabled in CAN driver.
+ * @data:     CAN frame payload (up to 8 byte)
  */
 struct can_frame {
 	canid_t can_id;  /* 32 bit CAN_ID + EFF/RTR/ERR flags */
-	__u8    can_dlc; /* frame payload length in byte (0 .. CAN_MAX_DLEN) */
+	union {
-	__u8    __pad;   /* padding */
+		/* CAN frame payload length in byte (0 .. CAN_MAX_DLEN)
-	__u8    __res0;  /* reserved / padding */
+		 * was previously named can_dlc so we need to carry that
-	__u8    __res1;  /* reserved / padding */
+		 * name for legacy support
-	__u8    data[CAN_MAX_DLEN] __attribute__((aligned(8)));
+		 */
+		__u8 len;
+		__u8 can_dlc; /* deprecated */
+	} __attribute__((packed)); /* disable padding added in some ABIs */
+	__u8 __pad; /* padding */
+	__u8 __res0; /* reserved / padding */
+	__u8 len8_dlc; /* optional DLC for 8 byte payload length (9 .. 15) */
+	__u8 data[CAN_MAX_DLEN] __attribute__((aligned(8)));
 };
 
 /*
  * defined bits for canfd_frame.flags
  *
- * The use of struct canfd_frame implies the Extended Data Length (EDL) bit to
+ * The use of struct canfd_frame implies the FD Frame (FDF) bit to
- * be set in the CAN frame bitstream on the wire. The EDL bit switch turns
+ * be set in the CAN frame bitstream on the wire. The FDF bit switch turns
  * the CAN controllers bitstream processor into the CAN FD mode which creates
  * two new options within the CAN FD frame specification:
  *
@@ -125,9 +135,18 @@ struct can_frame {
  * controller only the CANFD_BRS bit is relevant for real CAN controllers when
  * building a CAN FD frame for transmission. Setting the CANFD_ESI bit can make
  * sense for virtual CAN interfaces to test applications with echoed frames.
+ *
+ * The struct can_frame and struct canfd_frame intentionally share the same
+ * layout to be able to write CAN frame content into a CAN FD frame structure.
+ * When this is done the former differentiation via CAN_MTU / CANFD_MTU gets
+ * lost. CANFD_FDF allows programmers to mark CAN FD frames in the case of
+ * using struct canfd_frame for mixed CAN / CAN FD content (dual use).
+ * N.B. the Kernel APIs do NOT provide mixed CAN / CAN FD content inside of
+ * struct canfd_frame therefore the CANFD_FDF flag is disregarded by Linux.
  */
 #define CANFD_BRS 0x01 /* bit rate switch (second bitrate for payload data) */
 #define CANFD_ESI 0x02 /* error state indicator of the transmitting node */
+#define CANFD_FDF 0x04 /* mark CAN FD for dual use of struct canfd_frame */
 
 /**
  * struct canfd_frame - CAN flexible data rate frame structure

include/uapi/linux/can/netlink.h

@@ -100,6 +100,9 @@ struct can_ctrlmode {
 #define CAN_CTRLMODE_FD			0x20	/* CAN FD mode */
 #define CAN_CTRLMODE_PRESUME_ACK	0x40	/* Ignore missing CAN ACKs */
 #define CAN_CTRLMODE_FD_NON_ISO		0x80	/* CAN FD in non-ISO mode */
+#define CAN_CTRLMODE_CC_LEN8_DLC	0x100	/* Classic CAN DLC option */
+#define CAN_CTRLMODE_TDC_AUTO		0x200	/* CAN transiver automatically calculates TDCV */
+#define CAN_CTRLMODE_TDC_MANUAL		0x400	/* TDCV is manually set up by user */
 
 /*
  * CAN device statistics
@@ -133,10 +136,35 @@ enum {
 	IFLA_CAN_BITRATE_CONST,
 	IFLA_CAN_DATA_BITRATE_CONST,
 	IFLA_CAN_BITRATE_MAX,
-	__IFLA_CAN_MAX
+	IFLA_CAN_TDC,
+
+	/* add new constants above here */
+	__IFLA_CAN_MAX,
+	IFLA_CAN_MAX = __IFLA_CAN_MAX - 1
 };
 
-#define IFLA_CAN_MAX	(__IFLA_CAN_MAX - 1)
+/*
+ * CAN FD Transmitter Delay Compensation (TDC)
+ *
+ * Please refer to struct can_tdc_const and can_tdc in
+ * include/linux/can/bittiming.h for further details.
+ */
+enum {
+	IFLA_CAN_TDC_UNSPEC,
+	IFLA_CAN_TDC_TDCV_MIN,	/* u32 */
+	IFLA_CAN_TDC_TDCV_MAX,	/* u32 */
+	IFLA_CAN_TDC_TDCO_MIN,	/* u32 */
+	IFLA_CAN_TDC_TDCO_MAX,	/* u32 */
+	IFLA_CAN_TDC_TDCF_MIN,	/* u32 */
+	IFLA_CAN_TDC_TDCF_MAX,	/* u32 */
+	IFLA_CAN_TDC_TDCV,	/* u32 */
+	IFLA_CAN_TDC_TDCO,	/* u32 */
+	IFLA_CAN_TDC_TDCF,	/* u32 */
+
+	/* add new constants above here */
+	__IFLA_CAN_TDC,
+	IFLA_CAN_TDC_MAX = __IFLA_CAN_TDC - 1
+};
 
 /* u16 termination range: 1..65535 Ohms */
 #define CAN_TERMINATION_DISABLED 0

include/uapi/linux/const.h

@@ -28,4 +28,9 @@
 #define _BITUL(x)	(_UL(1) << (x))
 #define _BITULL(x)	(_ULL(1) << (x))
 
+#define __ALIGN_KERNEL(x, a)		__ALIGN_KERNEL_MASK(x, (typeof(x))(a) - 1)
+#define __ALIGN_KERNEL_MASK(x, mask)	(((x) + (mask)) & ~(mask))
+
+#define __KERNEL_DIV_ROUND_UP(n, d) (((n) + (d) - 1) / (d))
+
 #endif /* _LINUX_CONST_H */

include/uapi/linux/dcbnl.h

@@ -0,0 +1,769 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Copyright (c) 2008-2011, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
+ * Place - Suite 330, Boston, MA 02111-1307 USA.
+ *
+ * Author: Lucy Liu <lucy.liu@intel.com>
+ */
+
+#ifndef __LINUX_DCBNL_H__
+#define __LINUX_DCBNL_H__
+
+#include <linux/types.h>
+
+/* IEEE 802.1Qaz std supported values */
+#define IEEE_8021QAZ_MAX_TCS	8
+
+#define IEEE_8021QAZ_TSA_STRICT		0
+#define IEEE_8021QAZ_TSA_CB_SHAPER	1
+#define IEEE_8021QAZ_TSA_ETS		2
+#define IEEE_8021QAZ_TSA_VENDOR		255
+
+/* This structure contains the IEEE 802.1Qaz ETS managed object
+ *
+ * @willing: willing bit in ETS configuration TLV
+ * @ets_cap: indicates supported capacity of ets feature
+ * @cbs: credit based shaper ets algorithm supported
+ * @tc_tx_bw: tc tx bandwidth indexed by traffic class
+ * @tc_rx_bw: tc rx bandwidth indexed by traffic class
+ * @tc_tsa: TSA Assignment table, indexed by traffic class
+ * @prio_tc: priority assignment table mapping 8021Qp to traffic class
+ * @tc_reco_bw: recommended tc bandwidth indexed by traffic class for TLV
+ * @tc_reco_tsa: recommended tc bandwidth indexed by traffic class for TLV
+ * @reco_prio_tc: recommended tc tx bandwidth indexed by traffic class for TLV
+ *
+ * Recommended values are used to set fields in the ETS recommendation TLV
+ * with hardware offloaded LLDP.
+ *
+ * ----
+ *  TSA Assignment 8 bit identifiers
+ *	0	strict priority
+ *	1	credit-based shaper
+ *	2	enhanced transmission selection
+ *	3-254	reserved
+ *	255	vendor specific
+ */
+struct ieee_ets {
+	__u8	willing;
+	__u8	ets_cap;
+	__u8	cbs;
+	__u8	tc_tx_bw[IEEE_8021QAZ_MAX_TCS];
+	__u8	tc_rx_bw[IEEE_8021QAZ_MAX_TCS];
+	__u8	tc_tsa[IEEE_8021QAZ_MAX_TCS];
+	__u8	prio_tc[IEEE_8021QAZ_MAX_TCS];
+	__u8	tc_reco_bw[IEEE_8021QAZ_MAX_TCS];
+	__u8	tc_reco_tsa[IEEE_8021QAZ_MAX_TCS];
+	__u8	reco_prio_tc[IEEE_8021QAZ_MAX_TCS];
+};
+
+/* This structure contains rate limit extension to the IEEE 802.1Qaz ETS
+ * managed object.
+ * Values are 64 bits long and specified in Kbps to enable usage over both
+ * slow and very fast networks.
+ *
+ * @tc_maxrate: maximal tc tx bandwidth indexed by traffic class
+ */
+struct ieee_maxrate {
+	__u64	tc_maxrate[IEEE_8021QAZ_MAX_TCS];
+};
+
+enum dcbnl_cndd_states {
+	DCB_CNDD_RESET = 0,
+	DCB_CNDD_EDGE,
+	DCB_CNDD_INTERIOR,
+	DCB_CNDD_INTERIOR_READY,
+};
+
+/* This structure contains the IEEE 802.1Qau QCN managed object.
+ *
+ *@rpg_enable: enable QCN RP
+ *@rppp_max_rps: maximum number of RPs allowed for this CNPV on this port
+ *@rpg_time_reset: time between rate increases if no CNMs received.
+ *		   given in u-seconds
+ *@rpg_byte_reset: transmitted data between rate increases if no CNMs received.
+ *		   given in Bytes
+ *@rpg_threshold: The number of times rpByteStage or rpTimeStage can count
+ *		   before RP rate control state machine advances states
+ *@rpg_max_rate: the maxinun rate, in Mbits per second,
+ *		 at which an RP can transmit
+ *@rpg_ai_rate: The rate, in Mbits per second,
+ *		used to increase rpTargetRate in the RPR_ACTIVE_INCREASE
+ *@rpg_hai_rate: The rate, in Mbits per second,
+ *		 used to increase rpTargetRate in the RPR_HYPER_INCREASE state
+ *@rpg_gd: Upon CNM receive, flow rate is limited to (Fb/Gd)*CurrentRate.
+ *	   rpgGd is given as log2(Gd), where Gd may only be powers of 2
+ *@rpg_min_dec_fac: The minimum factor by which the current transmit rate
+ *		    can be changed by reception of a CNM.
+ *		    value is given as percentage (1-100)
+ *@rpg_min_rate: The minimum value, in bits per second, for rate to limit
+ *@cndd_state_machine: The state of the congestion notification domain
+ *		       defense state machine, as defined by IEEE 802.3Qau
+ *		       section 32.1.1. In the interior ready state,
+ *		       the QCN capable hardware may add CN-TAG TLV to the
+ *		       outgoing traffic, to specifically identify outgoing
+ *		       flows.
+ */
+
+struct ieee_qcn {
+	__u8 rpg_enable[IEEE_8021QAZ_MAX_TCS];
+	__u32 rppp_max_rps[IEEE_8021QAZ_MAX_TCS];
+	__u32 rpg_time_reset[IEEE_8021QAZ_MAX_TCS];
+	__u32 rpg_byte_reset[IEEE_8021QAZ_MAX_TCS];
+	__u32 rpg_threshold[IEEE_8021QAZ_MAX_TCS];
+	__u32 rpg_max_rate[IEEE_8021QAZ_MAX_TCS];
+	__u32 rpg_ai_rate[IEEE_8021QAZ_MAX_TCS];
+	__u32 rpg_hai_rate[IEEE_8021QAZ_MAX_TCS];
+	__u32 rpg_gd[IEEE_8021QAZ_MAX_TCS];
+	__u32 rpg_min_dec_fac[IEEE_8021QAZ_MAX_TCS];
+	__u32 rpg_min_rate[IEEE_8021QAZ_MAX_TCS];
+	__u32 cndd_state_machine[IEEE_8021QAZ_MAX_TCS];
+};
+
+/* This structure contains the IEEE 802.1Qau QCN statistics.
+ *
+ *@rppp_rp_centiseconds: the number of RP-centiseconds accumulated
+ *			 by RPs at this priority level on this Port
+ *@rppp_created_rps: number of active RPs(flows) that react to CNMs
+ */
+
+struct ieee_qcn_stats {
+	__u64 rppp_rp_centiseconds[IEEE_8021QAZ_MAX_TCS];
+	__u32 rppp_created_rps[IEEE_8021QAZ_MAX_TCS];
+};
+
+/* This structure contains the IEEE 802.1Qaz PFC managed object
+ *
+ * @pfc_cap: Indicates the number of traffic classes on the local device
+ *	     that may simultaneously have PFC enabled.
+ * @pfc_en: bitmap indicating pfc enabled traffic classes
+ * @mbc: enable macsec bypass capability
+ * @delay: the allowance made for a round-trip propagation delay of the
+ *	   link in bits.
+ * @requests: count of the sent pfc frames
+ * @indications: count of the received pfc frames
+ */
+struct ieee_pfc {
+	__u8	pfc_cap;
+	__u8	pfc_en;
+	__u8	mbc;
+	__u16	delay;
+	__u64	requests[IEEE_8021QAZ_MAX_TCS];
+	__u64	indications[IEEE_8021QAZ_MAX_TCS];
+};
+
+#define IEEE_8021Q_MAX_PRIORITIES 8
+#define DCBX_MAX_BUFFERS  8
+struct dcbnl_buffer {
+	/* priority to buffer mapping */
+	__u8    prio2buffer[IEEE_8021Q_MAX_PRIORITIES];
+	/* buffer size in Bytes */
+	__u32   buffer_size[DCBX_MAX_BUFFERS];
+	__u32   total_size;
+};
+
+/* CEE DCBX std supported values */
+#define CEE_DCBX_MAX_PGS	8
+#define CEE_DCBX_MAX_PRIO	8
+
+/**
+ * struct cee_pg - CEE Priority-Group managed object
+ *
+ * @willing: willing bit in the PG tlv
+ * @error: error bit in the PG tlv
+ * @pg_en: enable bit of the PG feature
+ * @tcs_supported: number of traffic classes supported
+ * @pg_bw: bandwidth percentage for each priority group
+ * @prio_pg: priority to PG mapping indexed by priority
+ */
+struct cee_pg {
+	__u8    willing;
+	__u8    error;
+	__u8    pg_en;
+	__u8    tcs_supported;
+	__u8    pg_bw[CEE_DCBX_MAX_PGS];
+	__u8    prio_pg[CEE_DCBX_MAX_PGS];
+};
+
+/**
+ * struct cee_pfc - CEE PFC managed object
+ *
+ * @willing: willing bit in the PFC tlv
+ * @error: error bit in the PFC tlv
+ * @pfc_en: bitmap indicating pfc enabled traffic classes
+ * @tcs_supported: number of traffic classes supported
+ */
+struct cee_pfc {
+	__u8    willing;
+	__u8    error;
+	__u8    pfc_en;
+	__u8    tcs_supported;
+};
+
+/* IEEE 802.1Qaz std supported values */
+#define IEEE_8021QAZ_APP_SEL_ETHERTYPE	1
+#define IEEE_8021QAZ_APP_SEL_STREAM	2
+#define IEEE_8021QAZ_APP_SEL_DGRAM	3
+#define IEEE_8021QAZ_APP_SEL_ANY	4
+#define IEEE_8021QAZ_APP_SEL_DSCP       5
+
+/* This structure contains the IEEE 802.1Qaz APP managed object. This
+ * object is also used for the CEE std as well.
+ *
+ * @selector: protocol identifier type
+ * @protocol: protocol of type indicated
+ * @priority: 3-bit unsigned integer indicating priority for IEEE
+ *            8-bit 802.1p user priority bitmap for CEE
+ *
+ * ----
+ *  Selector field values for IEEE 802.1Qaz
+ *	0	Reserved
+ *	1	Ethertype
+ *	2	Well known port number over TCP or SCTP
+ *	3	Well known port number over UDP or DCCP
+ *	4	Well known port number over TCP, SCTP, UDP, or DCCP
+ *	5	Differentiated Services Code Point (DSCP) value
+ *	6-7	Reserved
+ *
+ *  Selector field values for CEE
+ *	0	Ethertype
+ *	1	Well known port number over TCP or UDP
+ *	2-3	Reserved
+ */
+struct dcb_app {
+	__u8	selector;
+	__u8	priority;
+	__u16	protocol;
+};
+
+/**
+ * struct dcb_peer_app_info - APP feature information sent by the peer
+ *
+ * @willing: willing bit in the peer APP tlv
+ * @error: error bit in the peer APP tlv
+ *
+ * In addition to this information the full peer APP tlv also contains
+ * a table of 'app_count' APP objects defined above.
+ */
+struct dcb_peer_app_info {
+	__u8	willing;
+	__u8	error;
+};
+
+struct dcbmsg {
+	__u8               dcb_family;
+	__u8               cmd;
+	__u16              dcb_pad;
+};
+
+/**
+ * enum dcbnl_commands - supported DCB commands
+ *
+ * @DCB_CMD_UNDEFINED: unspecified command to catch errors
+ * @DCB_CMD_GSTATE: request the state of DCB in the device
+ * @DCB_CMD_SSTATE: set the state of DCB in the device
+ * @DCB_CMD_PGTX_GCFG: request the priority group configuration for Tx
+ * @DCB_CMD_PGTX_SCFG: set the priority group configuration for Tx
+ * @DCB_CMD_PGRX_GCFG: request the priority group configuration for Rx
+ * @DCB_CMD_PGRX_SCFG: set the priority group configuration for Rx
+ * @DCB_CMD_PFC_GCFG: request the priority flow control configuration
+ * @DCB_CMD_PFC_SCFG: set the priority flow control configuration
+ * @DCB_CMD_SET_ALL: apply all changes to the underlying device
+ * @DCB_CMD_GPERM_HWADDR: get the permanent MAC address of the underlying
+ *                        device.  Only useful when using bonding.
+ * @DCB_CMD_GCAP: request the DCB capabilities of the device
+ * @DCB_CMD_GNUMTCS: get the number of traffic classes currently supported
+ * @DCB_CMD_SNUMTCS: set the number of traffic classes
+ * @DCB_CMD_GBCN: set backward congestion notification configuration
+ * @DCB_CMD_SBCN: get backward congestion notification configuration.
+ * @DCB_CMD_GAPP: get application protocol configuration
+ * @DCB_CMD_SAPP: set application protocol configuration
+ * @DCB_CMD_IEEE_SET: set IEEE 802.1Qaz configuration
+ * @DCB_CMD_IEEE_GET: get IEEE 802.1Qaz configuration
+ * @DCB_CMD_GDCBX: get DCBX engine configuration
+ * @DCB_CMD_SDCBX: set DCBX engine configuration
+ * @DCB_CMD_GFEATCFG: get DCBX features flags
+ * @DCB_CMD_SFEATCFG: set DCBX features negotiation flags
+ * @DCB_CMD_CEE_GET: get CEE aggregated configuration
+ * @DCB_CMD_IEEE_DEL: delete IEEE 802.1Qaz configuration
+ */
+enum dcbnl_commands {
+	DCB_CMD_UNDEFINED,
+
+	DCB_CMD_GSTATE,
+	DCB_CMD_SSTATE,
+
+	DCB_CMD_PGTX_GCFG,
+	DCB_CMD_PGTX_SCFG,
+	DCB_CMD_PGRX_GCFG,
+	DCB_CMD_PGRX_SCFG,
+
+	DCB_CMD_PFC_GCFG,
+	DCB_CMD_PFC_SCFG,
+
+	DCB_CMD_SET_ALL,
+
+	DCB_CMD_GPERM_HWADDR,
+
+	DCB_CMD_GCAP,
+
+	DCB_CMD_GNUMTCS,
+	DCB_CMD_SNUMTCS,
+
+	DCB_CMD_PFC_GSTATE,
+	DCB_CMD_PFC_SSTATE,
+
+	DCB_CMD_BCN_GCFG,
+	DCB_CMD_BCN_SCFG,
+
+	DCB_CMD_GAPP,
+	DCB_CMD_SAPP,
+
+	DCB_CMD_IEEE_SET,
+	DCB_CMD_IEEE_GET,
+
+	DCB_CMD_GDCBX,
+	DCB_CMD_SDCBX,
+
+	DCB_CMD_GFEATCFG,
+	DCB_CMD_SFEATCFG,
+
+	DCB_CMD_CEE_GET,
+	DCB_CMD_IEEE_DEL,
+
+	__DCB_CMD_ENUM_MAX,
+	DCB_CMD_MAX = __DCB_CMD_ENUM_MAX - 1,
+};
+
+/**
+ * enum dcbnl_attrs - DCB top-level netlink attributes
+ *
+ * @DCB_ATTR_UNDEFINED: unspecified attribute to catch errors
+ * @DCB_ATTR_IFNAME: interface name of the underlying device (NLA_STRING)
+ * @DCB_ATTR_STATE: enable state of DCB in the device (NLA_U8)
+ * @DCB_ATTR_PFC_STATE: enable state of PFC in the device (NLA_U8)
+ * @DCB_ATTR_PFC_CFG: priority flow control configuration (NLA_NESTED)
+ * @DCB_ATTR_NUM_TC: number of traffic classes supported in the device (NLA_U8)
+ * @DCB_ATTR_PG_CFG: priority group configuration (NLA_NESTED)
+ * @DCB_ATTR_SET_ALL: bool to commit changes to hardware or not (NLA_U8)
+ * @DCB_ATTR_PERM_HWADDR: MAC address of the physical device (NLA_NESTED)
+ * @DCB_ATTR_CAP: DCB capabilities of the device (NLA_NESTED)
+ * @DCB_ATTR_NUMTCS: number of traffic classes supported (NLA_NESTED)
+ * @DCB_ATTR_BCN: backward congestion notification configuration (NLA_NESTED)
+ * @DCB_ATTR_IEEE: IEEE 802.1Qaz supported attributes (NLA_NESTED)
+ * @DCB_ATTR_DCBX: DCBX engine configuration in the device (NLA_U8)
+ * @DCB_ATTR_FEATCFG: DCBX features flags (NLA_NESTED)
+ * @DCB_ATTR_CEE: CEE std supported attributes (NLA_NESTED)
+ */
+enum dcbnl_attrs {
+	DCB_ATTR_UNDEFINED,
+
+	DCB_ATTR_IFNAME,
+	DCB_ATTR_STATE,
+	DCB_ATTR_PFC_STATE,
+	DCB_ATTR_PFC_CFG,
+	DCB_ATTR_NUM_TC,
+	DCB_ATTR_PG_CFG,
+	DCB_ATTR_SET_ALL,
+	DCB_ATTR_PERM_HWADDR,
+	DCB_ATTR_CAP,
+	DCB_ATTR_NUMTCS,
+	DCB_ATTR_BCN,
+	DCB_ATTR_APP,
+
+	/* IEEE std attributes */
+	DCB_ATTR_IEEE,
+
+	DCB_ATTR_DCBX,
+	DCB_ATTR_FEATCFG,
+
+	/* CEE nested attributes */
+	DCB_ATTR_CEE,
+
+	__DCB_ATTR_ENUM_MAX,
+	DCB_ATTR_MAX = __DCB_ATTR_ENUM_MAX - 1,
+};
+
+/**
+ * enum ieee_attrs - IEEE 802.1Qaz get/set attributes
+ *
+ * @DCB_ATTR_IEEE_UNSPEC: unspecified
+ * @DCB_ATTR_IEEE_ETS: negotiated ETS configuration
+ * @DCB_ATTR_IEEE_PFC: negotiated PFC configuration
+ * @DCB_ATTR_IEEE_APP_TABLE: negotiated APP configuration
+ * @DCB_ATTR_IEEE_PEER_ETS: peer ETS configuration - get only
+ * @DCB_ATTR_IEEE_PEER_PFC: peer PFC configuration - get only
+ * @DCB_ATTR_IEEE_PEER_APP: peer APP tlv - get only
+ */
+enum ieee_attrs {
+	DCB_ATTR_IEEE_UNSPEC,
+	DCB_ATTR_IEEE_ETS,
+	DCB_ATTR_IEEE_PFC,
+	DCB_ATTR_IEEE_APP_TABLE,
+	DCB_ATTR_IEEE_PEER_ETS,
+	DCB_ATTR_IEEE_PEER_PFC,
+	DCB_ATTR_IEEE_PEER_APP,
+	DCB_ATTR_IEEE_MAXRATE,
+	DCB_ATTR_IEEE_QCN,
+	DCB_ATTR_IEEE_QCN_STATS,
+	DCB_ATTR_DCB_BUFFER,
+	__DCB_ATTR_IEEE_MAX
+};
+#define DCB_ATTR_IEEE_MAX (__DCB_ATTR_IEEE_MAX - 1)
+
+enum ieee_attrs_app {
+	DCB_ATTR_IEEE_APP_UNSPEC,
+	DCB_ATTR_IEEE_APP,
+	__DCB_ATTR_IEEE_APP_MAX
+};
+#define DCB_ATTR_IEEE_APP_MAX (__DCB_ATTR_IEEE_APP_MAX - 1)
+
+/**
+ * enum cee_attrs - CEE DCBX get attributes.
+ *
+ * @DCB_ATTR_CEE_UNSPEC: unspecified
+ * @DCB_ATTR_CEE_PEER_PG: peer PG configuration - get only
+ * @DCB_ATTR_CEE_PEER_PFC: peer PFC configuration - get only
+ * @DCB_ATTR_CEE_PEER_APP_TABLE: peer APP tlv - get only
+ * @DCB_ATTR_CEE_TX_PG: TX PG configuration (DCB_CMD_PGTX_GCFG)
+ * @DCB_ATTR_CEE_RX_PG: RX PG configuration (DCB_CMD_PGRX_GCFG)
+ * @DCB_ATTR_CEE_PFC: PFC configuration (DCB_CMD_PFC_GCFG)
+ * @DCB_ATTR_CEE_APP_TABLE: APP configuration (multi DCB_CMD_GAPP)
+ * @DCB_ATTR_CEE_FEAT: DCBX features flags (DCB_CMD_GFEATCFG)
+ *
+ * An aggregated collection of the cee std negotiated parameters.
+ */
+enum cee_attrs {
+	DCB_ATTR_CEE_UNSPEC,
+	DCB_ATTR_CEE_PEER_PG,
+	DCB_ATTR_CEE_PEER_PFC,
+	DCB_ATTR_CEE_PEER_APP_TABLE,
+	DCB_ATTR_CEE_TX_PG,
+	DCB_ATTR_CEE_RX_PG,
+	DCB_ATTR_CEE_PFC,
+	DCB_ATTR_CEE_APP_TABLE,
+	DCB_ATTR_CEE_FEAT,
+	__DCB_ATTR_CEE_MAX
+};
+#define DCB_ATTR_CEE_MAX (__DCB_ATTR_CEE_MAX - 1)
+
+enum peer_app_attr {
+	DCB_ATTR_CEE_PEER_APP_UNSPEC,
+	DCB_ATTR_CEE_PEER_APP_INFO,
+	DCB_ATTR_CEE_PEER_APP,
+	__DCB_ATTR_CEE_PEER_APP_MAX
+};
+#define DCB_ATTR_CEE_PEER_APP_MAX (__DCB_ATTR_CEE_PEER_APP_MAX - 1)
+
+enum cee_attrs_app {
+	DCB_ATTR_CEE_APP_UNSPEC,
+	DCB_ATTR_CEE_APP,
+	__DCB_ATTR_CEE_APP_MAX
+};
+#define DCB_ATTR_CEE_APP_MAX (__DCB_ATTR_CEE_APP_MAX - 1)
+
+/**
+ * enum dcbnl_pfc_attrs - DCB Priority Flow Control user priority nested attrs
+ *
+ * @DCB_PFC_UP_ATTR_UNDEFINED: unspecified attribute to catch errors
+ * @DCB_PFC_UP_ATTR_0: Priority Flow Control value for User Priority 0 (NLA_U8)
+ * @DCB_PFC_UP_ATTR_1: Priority Flow Control value for User Priority 1 (NLA_U8)
+ * @DCB_PFC_UP_ATTR_2: Priority Flow Control value for User Priority 2 (NLA_U8)
+ * @DCB_PFC_UP_ATTR_3: Priority Flow Control value for User Priority 3 (NLA_U8)
+ * @DCB_PFC_UP_ATTR_4: Priority Flow Control value for User Priority 4 (NLA_U8)
+ * @DCB_PFC_UP_ATTR_5: Priority Flow Control value for User Priority 5 (NLA_U8)
+ * @DCB_PFC_UP_ATTR_6: Priority Flow Control value for User Priority 6 (NLA_U8)
+ * @DCB_PFC_UP_ATTR_7: Priority Flow Control value for User Priority 7 (NLA_U8)
+ * @DCB_PFC_UP_ATTR_MAX: highest attribute number currently defined
+ * @DCB_PFC_UP_ATTR_ALL: apply to all priority flow control attrs (NLA_FLAG)
+ *
+ */
+enum dcbnl_pfc_up_attrs {
+	DCB_PFC_UP_ATTR_UNDEFINED,
+
+	DCB_PFC_UP_ATTR_0,
+	DCB_PFC_UP_ATTR_1,
+	DCB_PFC_UP_ATTR_2,
+	DCB_PFC_UP_ATTR_3,
+	DCB_PFC_UP_ATTR_4,
+	DCB_PFC_UP_ATTR_5,
+	DCB_PFC_UP_ATTR_6,
+	DCB_PFC_UP_ATTR_7,
+	DCB_PFC_UP_ATTR_ALL,
+
+	__DCB_PFC_UP_ATTR_ENUM_MAX,
+	DCB_PFC_UP_ATTR_MAX = __DCB_PFC_UP_ATTR_ENUM_MAX - 1,
+};
+
+/**
+ * enum dcbnl_pg_attrs - DCB Priority Group attributes
+ *
+ * @DCB_PG_ATTR_UNDEFINED: unspecified attribute to catch errors
+ * @DCB_PG_ATTR_TC_0: Priority Group Traffic Class 0 configuration (NLA_NESTED)
+ * @DCB_PG_ATTR_TC_1: Priority Group Traffic Class 1 configuration (NLA_NESTED)
+ * @DCB_PG_ATTR_TC_2: Priority Group Traffic Class 2 configuration (NLA_NESTED)
+ * @DCB_PG_ATTR_TC_3: Priority Group Traffic Class 3 configuration (NLA_NESTED)
+ * @DCB_PG_ATTR_TC_4: Priority Group Traffic Class 4 configuration (NLA_NESTED)
+ * @DCB_PG_ATTR_TC_5: Priority Group Traffic Class 5 configuration (NLA_NESTED)
+ * @DCB_PG_ATTR_TC_6: Priority Group Traffic Class 6 configuration (NLA_NESTED)
+ * @DCB_PG_ATTR_TC_7: Priority Group Traffic Class 7 configuration (NLA_NESTED)
+ * @DCB_PG_ATTR_TC_MAX: highest attribute number currently defined
+ * @DCB_PG_ATTR_TC_ALL: apply to all traffic classes (NLA_NESTED)
+ * @DCB_PG_ATTR_BW_ID_0: Percent of link bandwidth for Priority Group 0 (NLA_U8)
+ * @DCB_PG_ATTR_BW_ID_1: Percent of link bandwidth for Priority Group 1 (NLA_U8)
+ * @DCB_PG_ATTR_BW_ID_2: Percent of link bandwidth for Priority Group 2 (NLA_U8)
+ * @DCB_PG_ATTR_BW_ID_3: Percent of link bandwidth for Priority Group 3 (NLA_U8)
+ * @DCB_PG_ATTR_BW_ID_4: Percent of link bandwidth for Priority Group 4 (NLA_U8)
+ * @DCB_PG_ATTR_BW_ID_5: Percent of link bandwidth for Priority Group 5 (NLA_U8)
+ * @DCB_PG_ATTR_BW_ID_6: Percent of link bandwidth for Priority Group 6 (NLA_U8)
+ * @DCB_PG_ATTR_BW_ID_7: Percent of link bandwidth for Priority Group 7 (NLA_U8)
+ * @DCB_PG_ATTR_BW_ID_MAX: highest attribute number currently defined
+ * @DCB_PG_ATTR_BW_ID_ALL: apply to all priority groups (NLA_FLAG)
+ *
+ */
+enum dcbnl_pg_attrs {
+	DCB_PG_ATTR_UNDEFINED,
+
+	DCB_PG_ATTR_TC_0,
+	DCB_PG_ATTR_TC_1,
+	DCB_PG_ATTR_TC_2,
+	DCB_PG_ATTR_TC_3,
+	DCB_PG_ATTR_TC_4,
+	DCB_PG_ATTR_TC_5,
+	DCB_PG_ATTR_TC_6,
+	DCB_PG_ATTR_TC_7,
+	DCB_PG_ATTR_TC_MAX,
+	DCB_PG_ATTR_TC_ALL,
+
+	DCB_PG_ATTR_BW_ID_0,
+	DCB_PG_ATTR_BW_ID_1,
+	DCB_PG_ATTR_BW_ID_2,
+	DCB_PG_ATTR_BW_ID_3,
+	DCB_PG_ATTR_BW_ID_4,
+	DCB_PG_ATTR_BW_ID_5,
+	DCB_PG_ATTR_BW_ID_6,
+	DCB_PG_ATTR_BW_ID_7,
+	DCB_PG_ATTR_BW_ID_MAX,
+	DCB_PG_ATTR_BW_ID_ALL,
+
+	__DCB_PG_ATTR_ENUM_MAX,
+	DCB_PG_ATTR_MAX = __DCB_PG_ATTR_ENUM_MAX - 1,
+};
+
+/**
+ * enum dcbnl_tc_attrs - DCB Traffic Class attributes
+ *
+ * @DCB_TC_ATTR_PARAM_UNDEFINED: unspecified attribute to catch errors
+ * @DCB_TC_ATTR_PARAM_PGID: (NLA_U8) Priority group the traffic class belongs to
+ *                          Valid values are:  0-7
+ * @DCB_TC_ATTR_PARAM_UP_MAPPING: (NLA_U8) Traffic class to user priority map
+ *                                Some devices may not support changing the
+ *                                user priority map of a TC.
+ * @DCB_TC_ATTR_PARAM_STRICT_PRIO: (NLA_U8) Strict priority setting
+ *                                 0 - none
+ *                                 1 - group strict
+ *                                 2 - link strict
+ * @DCB_TC_ATTR_PARAM_BW_PCT: optional - (NLA_U8) If supported by the device and
+ *                            not configured to use link strict priority,
+ *                            this is the percentage of bandwidth of the
+ *                            priority group this traffic class belongs to
+ * @DCB_TC_ATTR_PARAM_ALL: (NLA_FLAG) all traffic class parameters
+ *
+ */
+enum dcbnl_tc_attrs {
+	DCB_TC_ATTR_PARAM_UNDEFINED,
+
+	DCB_TC_ATTR_PARAM_PGID,
+	DCB_TC_ATTR_PARAM_UP_MAPPING,
+	DCB_TC_ATTR_PARAM_STRICT_PRIO,
+	DCB_TC_ATTR_PARAM_BW_PCT,
+	DCB_TC_ATTR_PARAM_ALL,
+
+	__DCB_TC_ATTR_PARAM_ENUM_MAX,
+	DCB_TC_ATTR_PARAM_MAX = __DCB_TC_ATTR_PARAM_ENUM_MAX - 1,
+};
+
+/**
+ * enum dcbnl_cap_attrs - DCB Capability attributes
+ *
+ * @DCB_CAP_ATTR_UNDEFINED: unspecified attribute to catch errors
+ * @DCB_CAP_ATTR_ALL: (NLA_FLAG) all capability parameters
+ * @DCB_CAP_ATTR_PG: (NLA_U8) device supports Priority Groups
+ * @DCB_CAP_ATTR_PFC: (NLA_U8) device supports Priority Flow Control
+ * @DCB_CAP_ATTR_UP2TC: (NLA_U8) device supports user priority to
+ *                               traffic class mapping
+ * @DCB_CAP_ATTR_PG_TCS: (NLA_U8) bitmap where each bit represents a
+ *                                number of traffic classes the device
+ *                                can be configured to use for Priority Groups
+ * @DCB_CAP_ATTR_PFC_TCS: (NLA_U8) bitmap where each bit represents a
+ *                                 number of traffic classes the device can be
+ *                                 configured to use for Priority Flow Control
+ * @DCB_CAP_ATTR_GSP: (NLA_U8) device supports group strict priority
+ * @DCB_CAP_ATTR_BCN: (NLA_U8) device supports Backwards Congestion
+ *                             Notification
+ * @DCB_CAP_ATTR_DCBX: (NLA_U8) device supports DCBX engine
+ *
+ */
+enum dcbnl_cap_attrs {
+	DCB_CAP_ATTR_UNDEFINED,
+	DCB_CAP_ATTR_ALL,
+	DCB_CAP_ATTR_PG,
+	DCB_CAP_ATTR_PFC,
+	DCB_CAP_ATTR_UP2TC,
+	DCB_CAP_ATTR_PG_TCS,
+	DCB_CAP_ATTR_PFC_TCS,
+	DCB_CAP_ATTR_GSP,
+	DCB_CAP_ATTR_BCN,
+	DCB_CAP_ATTR_DCBX,
+
+	__DCB_CAP_ATTR_ENUM_MAX,
+	DCB_CAP_ATTR_MAX = __DCB_CAP_ATTR_ENUM_MAX - 1,
+};
+
+/**
+ * DCBX capability flags
+ *
+ * @DCB_CAP_DCBX_HOST: DCBX negotiation is performed by the host LLDP agent.
+ *                     'set' routines are used to configure the device with
+ *                     the negotiated parameters
+ *
+ * @DCB_CAP_DCBX_LLD_MANAGED: DCBX negotiation is not performed in the host but
+ *                            by another entity
+ *                            'get' routines are used to retrieve the
+ *                            negotiated parameters
+ *                            'set' routines can be used to set the initial
+ *                            negotiation configuration
+ *
+ * @DCB_CAP_DCBX_VER_CEE: for a non-host DCBX engine, indicates the engine
+ *                        supports the CEE protocol flavor
+ *
+ * @DCB_CAP_DCBX_VER_IEEE: for a non-host DCBX engine, indicates the engine
+ *                         supports the IEEE protocol flavor
+ *
+ * @DCB_CAP_DCBX_STATIC: for a non-host DCBX engine, indicates the engine
+ *                       supports static configuration (i.e no actual
+ *                       negotiation is performed negotiated parameters equal
+ *                       the initial configuration)
+ *
+ */
+#define DCB_CAP_DCBX_HOST		0x01
+#define DCB_CAP_DCBX_LLD_MANAGED	0x02
+#define DCB_CAP_DCBX_VER_CEE		0x04
+#define DCB_CAP_DCBX_VER_IEEE		0x08
+#define DCB_CAP_DCBX_STATIC		0x10
+
+/**
+ * enum dcbnl_numtcs_attrs - number of traffic classes
+ *
+ * @DCB_NUMTCS_ATTR_UNDEFINED: unspecified attribute to catch errors
+ * @DCB_NUMTCS_ATTR_ALL: (NLA_FLAG) all traffic class attributes
+ * @DCB_NUMTCS_ATTR_PG: (NLA_U8) number of traffic classes used for
+ *                               priority groups
+ * @DCB_NUMTCS_ATTR_PFC: (NLA_U8) number of traffic classes which can
+ *                                support priority flow control
+ */
+enum dcbnl_numtcs_attrs {
+	DCB_NUMTCS_ATTR_UNDEFINED,
+	DCB_NUMTCS_ATTR_ALL,
+	DCB_NUMTCS_ATTR_PG,
+	DCB_NUMTCS_ATTR_PFC,
+
+	__DCB_NUMTCS_ATTR_ENUM_MAX,
+	DCB_NUMTCS_ATTR_MAX = __DCB_NUMTCS_ATTR_ENUM_MAX - 1,
+};
+
+enum dcbnl_bcn_attrs{
+	DCB_BCN_ATTR_UNDEFINED = 0,
+
+	DCB_BCN_ATTR_RP_0,
+	DCB_BCN_ATTR_RP_1,
+	DCB_BCN_ATTR_RP_2,
+	DCB_BCN_ATTR_RP_3,
+	DCB_BCN_ATTR_RP_4,
+	DCB_BCN_ATTR_RP_5,
+	DCB_BCN_ATTR_RP_6,
+	DCB_BCN_ATTR_RP_7,
+	DCB_BCN_ATTR_RP_ALL,
+
+	DCB_BCN_ATTR_BCNA_0,
+	DCB_BCN_ATTR_BCNA_1,
+	DCB_BCN_ATTR_ALPHA,
+	DCB_BCN_ATTR_BETA,
+	DCB_BCN_ATTR_GD,
+	DCB_BCN_ATTR_GI,
+	DCB_BCN_ATTR_TMAX,
+	DCB_BCN_ATTR_TD,
+	DCB_BCN_ATTR_RMIN,
+	DCB_BCN_ATTR_W,
+	DCB_BCN_ATTR_RD,
+	DCB_BCN_ATTR_RU,
+	DCB_BCN_ATTR_WRTT,
+	DCB_BCN_ATTR_RI,
+	DCB_BCN_ATTR_C,
+	DCB_BCN_ATTR_ALL,
+
+	__DCB_BCN_ATTR_ENUM_MAX,
+	DCB_BCN_ATTR_MAX = __DCB_BCN_ATTR_ENUM_MAX - 1,
+};
+
+/**
+ * enum dcb_general_attr_values - general DCB attribute values
+ *
+ * @DCB_ATTR_UNDEFINED: value used to indicate an attribute is not supported
+ *
+ */
+enum dcb_general_attr_values {
+	DCB_ATTR_VALUE_UNDEFINED = 0xff
+};
+
+#define DCB_APP_IDTYPE_ETHTYPE	0x00
+#define DCB_APP_IDTYPE_PORTNUM	0x01
+enum dcbnl_app_attrs {
+	DCB_APP_ATTR_UNDEFINED,
+
+	DCB_APP_ATTR_IDTYPE,
+	DCB_APP_ATTR_ID,
+	DCB_APP_ATTR_PRIORITY,
+
+	__DCB_APP_ATTR_ENUM_MAX,
+	DCB_APP_ATTR_MAX = __DCB_APP_ATTR_ENUM_MAX - 1,
+};
+
+/**
+ * enum dcbnl_featcfg_attrs - features conifiguration flags
+ *
+ * @DCB_FEATCFG_ATTR_UNDEFINED: unspecified attribute to catch errors
+ * @DCB_FEATCFG_ATTR_ALL: (NLA_FLAG) all features configuration attributes
+ * @DCB_FEATCFG_ATTR_PG: (NLA_U8) configuration flags for priority groups
+ * @DCB_FEATCFG_ATTR_PFC: (NLA_U8) configuration flags for priority
+ *                                 flow control
+ * @DCB_FEATCFG_ATTR_APP: (NLA_U8) configuration flags for application TLV
+ *
+ */
+#define DCB_FEATCFG_ERROR	0x01	/* error in feature resolution */
+#define DCB_FEATCFG_ENABLE	0x02	/* enable feature */
+#define DCB_FEATCFG_WILLING	0x04	/* feature is willing */
+#define DCB_FEATCFG_ADVERTISE	0x08	/* advertise feature */
+enum dcbnl_featcfg_attrs {
+	DCB_FEATCFG_ATTR_UNDEFINED,
+	DCB_FEATCFG_ATTR_ALL,
+	DCB_FEATCFG_ATTR_PG,
+	DCB_FEATCFG_ATTR_PFC,
+	DCB_FEATCFG_ATTR_APP,
+
+	__DCB_FEATCFG_ATTR_ENUM_MAX,
+	DCB_FEATCFG_ATTR_MAX = __DCB_FEATCFG_ATTR_ENUM_MAX - 1,
+};
+
+#endif /* __LINUX_DCBNL_H__ */

include/uapi/linux/devlink.h

@@ -13,6 +13,8 @@
 #ifndef _LINUX_DEVLINK_H_
 #define _LINUX_DEVLINK_H_
 
+#include <linux/const.h>
+
 #define DEVLINK_GENL_NAME "devlink"
 #define DEVLINK_GENL_VERSION 0x1
 #define DEVLINK_GENL_MCGRP_CONFIG_NAME "config"
@@ -122,6 +124,13 @@ enum devlink_command {
 	DEVLINK_CMD_TRAP_POLICER_NEW,
 	DEVLINK_CMD_TRAP_POLICER_DEL,
 
+	DEVLINK_CMD_HEALTH_REPORTER_TEST,
+
+	DEVLINK_CMD_RATE_GET,		/* can dump */
+	DEVLINK_CMD_RATE_SET,
+	DEVLINK_CMD_RATE_NEW,
+	DEVLINK_CMD_RATE_DEL,
+
 	/* add new commands above here */
 	__DEVLINK_CMD_MAX,
 	DEVLINK_CMD_MAX = __DEVLINK_CMD_MAX - 1
@@ -193,6 +202,18 @@ enum devlink_port_flavour {
 				      * port that faces the PCI VF.
 				      */
 	DEVLINK_PORT_FLAVOUR_VIRTUAL, /* Any virtual port facing the user. */
+	DEVLINK_PORT_FLAVOUR_UNUSED, /* Port which exists in the switch, but
+				      * is not used in any way.
+				      */
+	DEVLINK_PORT_FLAVOUR_PCI_SF, /* Represents eswitch port
+				      * for the PCI SF. It is an internal
+				      * port that faces the PCI SF.
+				      */
+};
+
+enum devlink_rate_type {
+	DEVLINK_RATE_TYPE_LEAF,
+	DEVLINK_RATE_TYPE_NODE,
 };
 
 enum devlink_param_cmode {
@@ -228,15 +249,40 @@ enum {
 	DEVLINK_ATTR_STATS_MAX = __DEVLINK_ATTR_STATS_MAX - 1
 };
 
+/* Specify what sections of a flash component can be overwritten when
+ * performing an update. Overwriting of firmware binary sections is always
+ * implicitly assumed to be allowed.
+ *
+ * Each section must be documented in
+ * Documentation/networking/devlink/devlink-flash.rst
+ *
+ */
+enum {
+	DEVLINK_FLASH_OVERWRITE_SETTINGS_BIT,
+	DEVLINK_FLASH_OVERWRITE_IDENTIFIERS_BIT,
+
+	__DEVLINK_FLASH_OVERWRITE_MAX_BIT,
+	DEVLINK_FLASH_OVERWRITE_MAX_BIT = __DEVLINK_FLASH_OVERWRITE_MAX_BIT - 1
+};
+
+#define DEVLINK_FLASH_OVERWRITE_SETTINGS _BITUL(DEVLINK_FLASH_OVERWRITE_SETTINGS_BIT)
+#define DEVLINK_FLASH_OVERWRITE_IDENTIFIERS _BITUL(DEVLINK_FLASH_OVERWRITE_IDENTIFIERS_BIT)
+
+#define DEVLINK_SUPPORTED_FLASH_OVERWRITE_SECTIONS \
+	(_BITUL(__DEVLINK_FLASH_OVERWRITE_MAX_BIT) - 1)
+
 /**
  * enum devlink_trap_action - Packet trap action.
  * @DEVLINK_TRAP_ACTION_DROP: Packet is dropped by the device and a copy is not
  *                            sent to the CPU.
  * @DEVLINK_TRAP_ACTION_TRAP: The sole copy of the packet is sent to the CPU.
+ * @DEVLINK_TRAP_ACTION_MIRROR: Packet is forwarded by the device and a copy is
+ *                              sent to the CPU.
  */
 enum devlink_trap_action {
 	DEVLINK_TRAP_ACTION_DROP,
 	DEVLINK_TRAP_ACTION_TRAP,
+	DEVLINK_TRAP_ACTION_MIRROR,
 };
 
 /**
@@ -250,10 +296,16 @@ enum devlink_trap_action {
  *                               control plane for resolution. Trapped packets
  *                               are processed by devlink and injected to
  *                               the kernel's Rx path.
+ * @DEVLINK_TRAP_TYPE_CONTROL: Packet was trapped because it is required for
+ *                             the correct functioning of the control plane.
+ *                             For example, an ARP request packet. Trapped
+ *                             packets are injected to the kernel's Rx path,
+ *                             but not reported to drop monitor.
  */
 enum devlink_trap_type {
 	DEVLINK_TRAP_TYPE_DROP,
 	DEVLINK_TRAP_TYPE_EXCEPTION,
+	DEVLINK_TRAP_TYPE_CONTROL,
 };
 
 enum {
@@ -263,6 +315,29 @@ enum {
 	DEVLINK_ATTR_TRAP_METADATA_TYPE_FA_COOKIE,
 };
 
+enum devlink_reload_action {
+	DEVLINK_RELOAD_ACTION_UNSPEC,
+	DEVLINK_RELOAD_ACTION_DRIVER_REINIT,	/* Driver entities re-instantiation */
+	DEVLINK_RELOAD_ACTION_FW_ACTIVATE,	/* FW activate */
+
+	/* Add new reload actions above */
+	__DEVLINK_RELOAD_ACTION_MAX,
+	DEVLINK_RELOAD_ACTION_MAX = __DEVLINK_RELOAD_ACTION_MAX - 1
+};
+
+enum devlink_reload_limit {
+	DEVLINK_RELOAD_LIMIT_UNSPEC,	/* unspecified, no constraints */
+	DEVLINK_RELOAD_LIMIT_NO_RESET,	/* No reset allowed, no down time allowed,
+					 * no link flap and no configuration is lost.
+					 */
+
+	/* Add new reload limit above */
+	__DEVLINK_RELOAD_LIMIT_MAX,
+	DEVLINK_RELOAD_LIMIT_MAX = __DEVLINK_RELOAD_LIMIT_MAX - 1
+};
+
+#define DEVLINK_RELOAD_LIMITS_VALID_MASK (_BITUL(__DEVLINK_RELOAD_LIMIT_MAX) - 1)
+
 enum devlink_attr {
 	/* don't change the order or add anything between, this is ABI! */
 	DEVLINK_ATTR_UNSPEC,
@@ -442,6 +517,42 @@ enum devlink_attr {
 	DEVLINK_ATTR_TRAP_POLICER_RATE,			/* u64 */
 	DEVLINK_ATTR_TRAP_POLICER_BURST,		/* u64 */
 
+	DEVLINK_ATTR_PORT_FUNCTION,			/* nested */
+
+	DEVLINK_ATTR_INFO_BOARD_SERIAL_NUMBER,	/* string */
+
+	DEVLINK_ATTR_PORT_LANES,			/* u32 */
+	DEVLINK_ATTR_PORT_SPLITTABLE,			/* u8 */
+
+	DEVLINK_ATTR_PORT_EXTERNAL,		/* u8 */
+	DEVLINK_ATTR_PORT_CONTROLLER_NUMBER,	/* u32 */
+
+	DEVLINK_ATTR_FLASH_UPDATE_STATUS_TIMEOUT,	/* u64 */
+	DEVLINK_ATTR_FLASH_UPDATE_OVERWRITE_MASK,	/* bitfield32 */
+
+	DEVLINK_ATTR_RELOAD_ACTION,		/* u8 */
+	DEVLINK_ATTR_RELOAD_ACTIONS_PERFORMED,	/* bitfield32 */
+	DEVLINK_ATTR_RELOAD_LIMITS,		/* bitfield32 */
+
+	DEVLINK_ATTR_DEV_STATS,			/* nested */
+	DEVLINK_ATTR_RELOAD_STATS,		/* nested */
+	DEVLINK_ATTR_RELOAD_STATS_ENTRY,	/* nested */
+	DEVLINK_ATTR_RELOAD_STATS_LIMIT,	/* u8 */
+	DEVLINK_ATTR_RELOAD_STATS_VALUE,	/* u32 */
+	DEVLINK_ATTR_REMOTE_RELOAD_STATS,	/* nested */
+	DEVLINK_ATTR_RELOAD_ACTION_INFO,        /* nested */
+	DEVLINK_ATTR_RELOAD_ACTION_STATS,       /* nested */
+
+	DEVLINK_ATTR_PORT_PCI_SF_NUMBER,	/* u32 */
+
+	DEVLINK_ATTR_RATE_TYPE,			/* u16 */
+	DEVLINK_ATTR_RATE_TX_SHARE,		/* u64 */
+	DEVLINK_ATTR_RATE_TX_MAX,		/* u64 */
+	DEVLINK_ATTR_RATE_NODE_NAME,		/* string */
+	DEVLINK_ATTR_RATE_PARENT_NODE_NAME,	/* string */
+
+	DEVLINK_ATTR_REGION_MAX_SNAPSHOTS,	/* u32 */
+
 	/* add new attributes above here, update the policy in devlink.c */
 
 	__DEVLINK_ATTR_MAX,
@@ -488,4 +599,32 @@ enum devlink_resource_unit {
 	DEVLINK_RESOURCE_UNIT_ENTRY,
 };
 
+enum devlink_port_function_attr {
+	DEVLINK_PORT_FUNCTION_ATTR_UNSPEC,
+	DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR,	/* binary */
+	DEVLINK_PORT_FN_ATTR_STATE,	/* u8 */
+	DEVLINK_PORT_FN_ATTR_OPSTATE,	/* u8 */
+
+	__DEVLINK_PORT_FUNCTION_ATTR_MAX,
+	DEVLINK_PORT_FUNCTION_ATTR_MAX = __DEVLINK_PORT_FUNCTION_ATTR_MAX - 1
+};
+
+enum devlink_port_fn_state {
+	DEVLINK_PORT_FN_STATE_INACTIVE,
+	DEVLINK_PORT_FN_STATE_ACTIVE,
+};
+
+/**
+ * enum devlink_port_fn_opstate - indicates operational state of the function
+ * @DEVLINK_PORT_FN_OPSTATE_ATTACHED: Driver is attached to the function.
+ * For graceful tear down of the function, after inactivation of the
+ * function, user should wait for operational state to turn DETACHED.
+ * @DEVLINK_PORT_FN_OPSTATE_DETACHED: Driver is detached from the function.
+ * It is safe to delete the port.
+ */
+enum devlink_port_fn_opstate {
+	DEVLINK_PORT_FN_OPSTATE_DETACHED,
+	DEVLINK_PORT_FN_OPSTATE_ATTACHED,
+};
+
 #endif /* _LINUX_DEVLINK_H_ */

include/uapi/linux/genetlink.h

@@ -48,6 +48,7 @@ enum {
 	CTRL_CMD_NEWMCAST_GRP,
 	CTRL_CMD_DELMCAST_GRP,
 	CTRL_CMD_GETMCAST_GRP, /* unused */
+	CTRL_CMD_GETPOLICY,
 	__CTRL_CMD_MAX,
 };
 
@@ -62,6 +63,9 @@ enum {
 	CTRL_ATTR_MAXATTR,
 	CTRL_ATTR_OPS,
 	CTRL_ATTR_MCAST_GROUPS,
+	CTRL_ATTR_POLICY,
+	CTRL_ATTR_OP_POLICY,
+	CTRL_ATTR_OP,
 	__CTRL_ATTR_MAX,
 };
 
@@ -83,6 +87,15 @@ enum {
 	__CTRL_ATTR_MCAST_GRP_MAX,
 };
 
+enum {
+	CTRL_ATTR_POLICY_UNSPEC,
+	CTRL_ATTR_POLICY_DO,
+	CTRL_ATTR_POLICY_DUMP,
+
+	__CTRL_ATTR_POLICY_DUMP_MAX,
+	CTRL_ATTR_POLICY_DUMP_MAX = __CTRL_ATTR_POLICY_DUMP_MAX - 1
+};
+
 #define CTRL_ATTR_MCAST_GRP_MAX (__CTRL_ATTR_MCAST_GRP_MAX - 1)
 
 

include/uapi/linux/icmpv6.h

@@ -68,6 +68,7 @@ struct icmp6hdr {
 #define icmp6_mtu		icmp6_dataun.un_data32[0]
 #define icmp6_unused		icmp6_dataun.un_data32[0]
 #define icmp6_maxdelay		icmp6_dataun.un_data16[0]
+#define icmp6_datagram_len	icmp6_dataun.un_data8[0]
 #define icmp6_router		icmp6_dataun.u_nd_advt.router
 #define icmp6_solicited		icmp6_dataun.u_nd_advt.solicited
 #define icmp6_override		icmp6_dataun.u_nd_advt.override
@@ -137,7 +138,11 @@ struct icmp6hdr {
 #define ICMPV6_HDR_FIELD		0
 #define ICMPV6_UNK_NEXTHDR		1
 #define ICMPV6_UNK_OPTION		2
+#define ICMPV6_HDR_INCOMP		3
 
+/* Codes for EXT_ECHO (PROBE) */
+#define ICMPV6_EXT_ECHO_REQUEST		160
+#define ICMPV6_EXT_ECHO_REPLY		161
 /*
  *	constants for (set|get)sockopt
  */

include/uapi/linux/if.h

@@ -176,6 +176,7 @@ enum {
 enum {
 	IF_LINK_MODE_DEFAULT,
 	IF_LINK_MODE_DORMANT,	/* limit upward transition to dormant */
+	IF_LINK_MODE_TESTING,	/* limit upward transition to testing */
 };
 
 /*

include/uapi/linux/if_alg.h

@@ -24,6 +24,22 @@ struct sockaddr_alg {
 	__u8	salg_name[64];
 };
 
+/*
+ * Linux v4.12 and later removed the 64-byte limit on salg_name[]; it's now an
+ * arbitrary-length field.  We had to keep the original struct above for source
+ * compatibility with existing userspace programs, though.  Use the new struct
+ * below if support for very long algorithm names is needed.  To do this,
+ * allocate 'sizeof(struct sockaddr_alg_new) + strlen(algname) + 1' bytes, and
+ * copy algname (including the null terminator) into salg_name.
+ */
+struct sockaddr_alg_new {
+	__u16	salg_family;
+	__u8	salg_type[14];
+	__u32	salg_feat;
+	__u32	salg_mask;
+	__u8	salg_name[];
+};
+
 struct af_alg_iv {
 	__u32	ivlen;
 	__u8	iv[0];
@@ -35,6 +51,7 @@ struct af_alg_iv {
 #define ALG_SET_OP			3
 #define ALG_SET_AEAD_ASSOCLEN		4
 #define ALG_SET_AEAD_AUTHSIZE		5
+#define ALG_SET_DRBG_ENTROPY		6
 
 /* Operations */
 #define ALG_OP_DECRYPT			0

include/uapi/linux/if_arp.h

@@ -54,6 +54,7 @@
 #define ARPHRD_X25	271		/* CCITT X.25			*/
 #define ARPHRD_HWX25	272		/* Boards with X.25 in firmware	*/
 #define ARPHRD_CAN	280		/* Controller Area Network      */
+#define ARPHRD_MCTP	290
 #define ARPHRD_PPP	512
 #define ARPHRD_CISCO	513		/* Cisco HDLC	 		*/
 #define ARPHRD_HDLC	ARPHRD_CISCO

include/uapi/linux/if_bonding.h

@@ -94,6 +94,7 @@
 #define BOND_XMIT_POLICY_LAYER23	2 /* layer 2+3 (IP ^ MAC) */
 #define BOND_XMIT_POLICY_ENCAP23	3 /* encapsulated layer 2+3 */
 #define BOND_XMIT_POLICY_ENCAP34	4 /* encapsulated layer 3+4 */
+#define BOND_XMIT_POLICY_VLAN_SRCMAC	5 /* vlan + source MAC */
 
 /* 802.3ad port state definitions (43.4.2.2 in the 802.3ad standard) */
 #define LACP_STATE_LACP_ACTIVITY   0x1
@@ -152,14 +153,3 @@ enum {
 #define BOND_3AD_STAT_MAX (__BOND_3AD_STAT_MAX - 1)
 
 #endif /* _LINUX_IF_BONDING_H */
-
-/*
- * Local variables:
- *  version-control: t
- *  kept-new-versions: 5
- *  c-indent-level: 8
- *  c-basic-offset: 8
- *  tab-width: 8
- * End:
- */
-

include/uapi/linux/if_bridge.h

@@ -120,6 +120,8 @@ enum {
 	IFLA_BRIDGE_MODE,
 	IFLA_BRIDGE_VLAN_INFO,
 	IFLA_BRIDGE_VLAN_TUNNEL_INFO,
+	IFLA_BRIDGE_MRP,
+	IFLA_BRIDGE_CFM,
 	__IFLA_BRIDGE_MAX,
 };
 #define IFLA_BRIDGE_MAX (__IFLA_BRIDGE_MAX - 1)
@@ -157,6 +159,300 @@ struct bridge_vlan_xstats {
 	__u32 pad2;
 };
 
+enum {
+	IFLA_BRIDGE_MRP_UNSPEC,
+	IFLA_BRIDGE_MRP_INSTANCE,
+	IFLA_BRIDGE_MRP_PORT_STATE,
+	IFLA_BRIDGE_MRP_PORT_ROLE,
+	IFLA_BRIDGE_MRP_RING_STATE,
+	IFLA_BRIDGE_MRP_RING_ROLE,
+	IFLA_BRIDGE_MRP_START_TEST,
+	IFLA_BRIDGE_MRP_INFO,
+	IFLA_BRIDGE_MRP_IN_ROLE,
+	IFLA_BRIDGE_MRP_IN_STATE,
+	IFLA_BRIDGE_MRP_START_IN_TEST,
+	__IFLA_BRIDGE_MRP_MAX,
+};
+
+#define IFLA_BRIDGE_MRP_MAX (__IFLA_BRIDGE_MRP_MAX - 1)
+
+enum {
+	IFLA_BRIDGE_MRP_INSTANCE_UNSPEC,
+	IFLA_BRIDGE_MRP_INSTANCE_RING_ID,
+	IFLA_BRIDGE_MRP_INSTANCE_P_IFINDEX,
+	IFLA_BRIDGE_MRP_INSTANCE_S_IFINDEX,
+	IFLA_BRIDGE_MRP_INSTANCE_PRIO,
+	__IFLA_BRIDGE_MRP_INSTANCE_MAX,
+};
+
+#define IFLA_BRIDGE_MRP_INSTANCE_MAX (__IFLA_BRIDGE_MRP_INSTANCE_MAX - 1)
+
+enum {
+	IFLA_BRIDGE_MRP_PORT_STATE_UNSPEC,
+	IFLA_BRIDGE_MRP_PORT_STATE_STATE,
+	__IFLA_BRIDGE_MRP_PORT_STATE_MAX,
+};
+
+#define IFLA_BRIDGE_MRP_PORT_STATE_MAX (__IFLA_BRIDGE_MRP_PORT_STATE_MAX - 1)
+
+enum {
+	IFLA_BRIDGE_MRP_PORT_ROLE_UNSPEC,
+	IFLA_BRIDGE_MRP_PORT_ROLE_ROLE,
+	__IFLA_BRIDGE_MRP_PORT_ROLE_MAX,
+};
+
+#define IFLA_BRIDGE_MRP_PORT_ROLE_MAX (__IFLA_BRIDGE_MRP_PORT_ROLE_MAX - 1)
+
+enum {
+	IFLA_BRIDGE_MRP_RING_STATE_UNSPEC,
+	IFLA_BRIDGE_MRP_RING_STATE_RING_ID,
+	IFLA_BRIDGE_MRP_RING_STATE_STATE,
+	__IFLA_BRIDGE_MRP_RING_STATE_MAX,
+};
+
+#define IFLA_BRIDGE_MRP_RING_STATE_MAX (__IFLA_BRIDGE_MRP_RING_STATE_MAX - 1)
+
+enum {
+	IFLA_BRIDGE_MRP_RING_ROLE_UNSPEC,
+	IFLA_BRIDGE_MRP_RING_ROLE_RING_ID,
+	IFLA_BRIDGE_MRP_RING_ROLE_ROLE,
+	__IFLA_BRIDGE_MRP_RING_ROLE_MAX,
+};
+
+#define IFLA_BRIDGE_MRP_RING_ROLE_MAX (__IFLA_BRIDGE_MRP_RING_ROLE_MAX - 1)
+
+enum {
+	IFLA_BRIDGE_MRP_START_TEST_UNSPEC,
+	IFLA_BRIDGE_MRP_START_TEST_RING_ID,
+	IFLA_BRIDGE_MRP_START_TEST_INTERVAL,
+	IFLA_BRIDGE_MRP_START_TEST_MAX_MISS,
+	IFLA_BRIDGE_MRP_START_TEST_PERIOD,
+	IFLA_BRIDGE_MRP_START_TEST_MONITOR,
+	__IFLA_BRIDGE_MRP_START_TEST_MAX,
+};
+
+#define IFLA_BRIDGE_MRP_START_TEST_MAX (__IFLA_BRIDGE_MRP_START_TEST_MAX - 1)
+
+enum {
+	IFLA_BRIDGE_MRP_INFO_UNSPEC,
+	IFLA_BRIDGE_MRP_INFO_RING_ID,
+	IFLA_BRIDGE_MRP_INFO_P_IFINDEX,
+	IFLA_BRIDGE_MRP_INFO_S_IFINDEX,
+	IFLA_BRIDGE_MRP_INFO_PRIO,
+	IFLA_BRIDGE_MRP_INFO_RING_STATE,
+	IFLA_BRIDGE_MRP_INFO_RING_ROLE,
+	IFLA_BRIDGE_MRP_INFO_TEST_INTERVAL,
+	IFLA_BRIDGE_MRP_INFO_TEST_MAX_MISS,
+	IFLA_BRIDGE_MRP_INFO_TEST_MONITOR,
+	IFLA_BRIDGE_MRP_INFO_I_IFINDEX,
+	IFLA_BRIDGE_MRP_INFO_IN_STATE,
+	IFLA_BRIDGE_MRP_INFO_IN_ROLE,
+	IFLA_BRIDGE_MRP_INFO_IN_TEST_INTERVAL,
+	IFLA_BRIDGE_MRP_INFO_IN_TEST_MAX_MISS,
+	__IFLA_BRIDGE_MRP_INFO_MAX,
+};
+
+#define IFLA_BRIDGE_MRP_INFO_MAX (__IFLA_BRIDGE_MRP_INFO_MAX - 1)
+
+enum {
+	IFLA_BRIDGE_MRP_IN_STATE_UNSPEC,
+	IFLA_BRIDGE_MRP_IN_STATE_IN_ID,
+	IFLA_BRIDGE_MRP_IN_STATE_STATE,
+	__IFLA_BRIDGE_MRP_IN_STATE_MAX,
+};
+
+#define IFLA_BRIDGE_MRP_IN_STATE_MAX (__IFLA_BRIDGE_MRP_IN_STATE_MAX - 1)
+
+enum {
+	IFLA_BRIDGE_MRP_IN_ROLE_UNSPEC,
+	IFLA_BRIDGE_MRP_IN_ROLE_RING_ID,
+	IFLA_BRIDGE_MRP_IN_ROLE_IN_ID,
+	IFLA_BRIDGE_MRP_IN_ROLE_ROLE,
+	IFLA_BRIDGE_MRP_IN_ROLE_I_IFINDEX,
+	__IFLA_BRIDGE_MRP_IN_ROLE_MAX,
+};
+
+#define IFLA_BRIDGE_MRP_IN_ROLE_MAX (__IFLA_BRIDGE_MRP_IN_ROLE_MAX - 1)
+
+enum {
+	IFLA_BRIDGE_MRP_START_IN_TEST_UNSPEC,
+	IFLA_BRIDGE_MRP_START_IN_TEST_IN_ID,
+	IFLA_BRIDGE_MRP_START_IN_TEST_INTERVAL,
+	IFLA_BRIDGE_MRP_START_IN_TEST_MAX_MISS,
+	IFLA_BRIDGE_MRP_START_IN_TEST_PERIOD,
+	__IFLA_BRIDGE_MRP_START_IN_TEST_MAX,
+};
+
+#define IFLA_BRIDGE_MRP_START_IN_TEST_MAX (__IFLA_BRIDGE_MRP_START_IN_TEST_MAX - 1)
+
+struct br_mrp_instance {
+	__u32 ring_id;
+	__u32 p_ifindex;
+	__u32 s_ifindex;
+	__u16 prio;
+};
+
+struct br_mrp_ring_state {
+	__u32 ring_id;
+	__u32 ring_state;
+};
+
+struct br_mrp_ring_role {
+	__u32 ring_id;
+	__u32 ring_role;
+};
+
+struct br_mrp_start_test {
+	__u32 ring_id;
+	__u32 interval;
+	__u32 max_miss;
+	__u32 period;
+	__u32 monitor;
+};
+
+struct br_mrp_in_state {
+	__u32 in_state;
+	__u16 in_id;
+};
+
+struct br_mrp_in_role {
+	__u32 ring_id;
+	__u32 in_role;
+	__u32 i_ifindex;
+	__u16 in_id;
+};
+
+struct br_mrp_start_in_test {
+	__u32 interval;
+	__u32 max_miss;
+	__u32 period;
+	__u16 in_id;
+};
+
+enum {
+	IFLA_BRIDGE_CFM_UNSPEC,
+	IFLA_BRIDGE_CFM_MEP_CREATE,
+	IFLA_BRIDGE_CFM_MEP_DELETE,
+	IFLA_BRIDGE_CFM_MEP_CONFIG,
+	IFLA_BRIDGE_CFM_CC_CONFIG,
+	IFLA_BRIDGE_CFM_CC_PEER_MEP_ADD,
+	IFLA_BRIDGE_CFM_CC_PEER_MEP_REMOVE,
+	IFLA_BRIDGE_CFM_CC_RDI,
+	IFLA_BRIDGE_CFM_CC_CCM_TX,
+	IFLA_BRIDGE_CFM_MEP_CREATE_INFO,
+	IFLA_BRIDGE_CFM_MEP_CONFIG_INFO,
+	IFLA_BRIDGE_CFM_CC_CONFIG_INFO,
+	IFLA_BRIDGE_CFM_CC_RDI_INFO,
+	IFLA_BRIDGE_CFM_CC_CCM_TX_INFO,
+	IFLA_BRIDGE_CFM_CC_PEER_MEP_INFO,
+	IFLA_BRIDGE_CFM_MEP_STATUS_INFO,
+	IFLA_BRIDGE_CFM_CC_PEER_STATUS_INFO,
+	__IFLA_BRIDGE_CFM_MAX,
+};
+
+#define IFLA_BRIDGE_CFM_MAX (__IFLA_BRIDGE_CFM_MAX - 1)
+
+enum {
+	IFLA_BRIDGE_CFM_MEP_CREATE_UNSPEC,
+	IFLA_BRIDGE_CFM_MEP_CREATE_INSTANCE,
+	IFLA_BRIDGE_CFM_MEP_CREATE_DOMAIN,
+	IFLA_BRIDGE_CFM_MEP_CREATE_DIRECTION,
+	IFLA_BRIDGE_CFM_MEP_CREATE_IFINDEX,
+	__IFLA_BRIDGE_CFM_MEP_CREATE_MAX,
+};
+
+#define IFLA_BRIDGE_CFM_MEP_CREATE_MAX (__IFLA_BRIDGE_CFM_MEP_CREATE_MAX - 1)
+
+enum {
+	IFLA_BRIDGE_CFM_MEP_DELETE_UNSPEC,
+	IFLA_BRIDGE_CFM_MEP_DELETE_INSTANCE,
+	__IFLA_BRIDGE_CFM_MEP_DELETE_MAX,
+};
+
+#define IFLA_BRIDGE_CFM_MEP_DELETE_MAX (__IFLA_BRIDGE_CFM_MEP_DELETE_MAX - 1)
+
+enum {
+	IFLA_BRIDGE_CFM_MEP_CONFIG_UNSPEC,
+	IFLA_BRIDGE_CFM_MEP_CONFIG_INSTANCE,
+	IFLA_BRIDGE_CFM_MEP_CONFIG_UNICAST_MAC,
+	IFLA_BRIDGE_CFM_MEP_CONFIG_MDLEVEL,
+	IFLA_BRIDGE_CFM_MEP_CONFIG_MEPID,
+	__IFLA_BRIDGE_CFM_MEP_CONFIG_MAX,
+};
+
+#define IFLA_BRIDGE_CFM_MEP_CONFIG_MAX (__IFLA_BRIDGE_CFM_MEP_CONFIG_MAX - 1)
+
+enum {
+	IFLA_BRIDGE_CFM_CC_CONFIG_UNSPEC,
+	IFLA_BRIDGE_CFM_CC_CONFIG_INSTANCE,
+	IFLA_BRIDGE_CFM_CC_CONFIG_ENABLE,
+	IFLA_BRIDGE_CFM_CC_CONFIG_EXP_INTERVAL,
+	IFLA_BRIDGE_CFM_CC_CONFIG_EXP_MAID,
+	__IFLA_BRIDGE_CFM_CC_CONFIG_MAX,
+};
+
+#define IFLA_BRIDGE_CFM_CC_CONFIG_MAX (__IFLA_BRIDGE_CFM_CC_CONFIG_MAX - 1)
+
+enum {
+	IFLA_BRIDGE_CFM_CC_PEER_MEP_UNSPEC,
+	IFLA_BRIDGE_CFM_CC_PEER_MEP_INSTANCE,
+	IFLA_BRIDGE_CFM_CC_PEER_MEPID,
+	__IFLA_BRIDGE_CFM_CC_PEER_MEP_MAX,
+};
+
+#define IFLA_BRIDGE_CFM_CC_PEER_MEP_MAX (__IFLA_BRIDGE_CFM_CC_PEER_MEP_MAX - 1)
+
+enum {
+	IFLA_BRIDGE_CFM_CC_RDI_UNSPEC,
+	IFLA_BRIDGE_CFM_CC_RDI_INSTANCE,
+	IFLA_BRIDGE_CFM_CC_RDI_RDI,
+	__IFLA_BRIDGE_CFM_CC_RDI_MAX,
+};
+
+#define IFLA_BRIDGE_CFM_CC_RDI_MAX (__IFLA_BRIDGE_CFM_CC_RDI_MAX - 1)
+
+enum {
+	IFLA_BRIDGE_CFM_CC_CCM_TX_UNSPEC,
+	IFLA_BRIDGE_CFM_CC_CCM_TX_INSTANCE,
+	IFLA_BRIDGE_CFM_CC_CCM_TX_DMAC,
+	IFLA_BRIDGE_CFM_CC_CCM_TX_SEQ_NO_UPDATE,
+	IFLA_BRIDGE_CFM_CC_CCM_TX_PERIOD,
+	IFLA_BRIDGE_CFM_CC_CCM_TX_IF_TLV,
+	IFLA_BRIDGE_CFM_CC_CCM_TX_IF_TLV_VALUE,
+	IFLA_BRIDGE_CFM_CC_CCM_TX_PORT_TLV,
+	IFLA_BRIDGE_CFM_CC_CCM_TX_PORT_TLV_VALUE,
+	__IFLA_BRIDGE_CFM_CC_CCM_TX_MAX,
+};
+
+#define IFLA_BRIDGE_CFM_CC_CCM_TX_MAX (__IFLA_BRIDGE_CFM_CC_CCM_TX_MAX - 1)
+
+enum {
+	IFLA_BRIDGE_CFM_MEP_STATUS_UNSPEC,
+	IFLA_BRIDGE_CFM_MEP_STATUS_INSTANCE,
+	IFLA_BRIDGE_CFM_MEP_STATUS_OPCODE_UNEXP_SEEN,
+	IFLA_BRIDGE_CFM_MEP_STATUS_VERSION_UNEXP_SEEN,
+	IFLA_BRIDGE_CFM_MEP_STATUS_RX_LEVEL_LOW_SEEN,
+	__IFLA_BRIDGE_CFM_MEP_STATUS_MAX,
+};
+
+#define IFLA_BRIDGE_CFM_MEP_STATUS_MAX (__IFLA_BRIDGE_CFM_MEP_STATUS_MAX - 1)
+
+enum {
+	IFLA_BRIDGE_CFM_CC_PEER_STATUS_UNSPEC,
+	IFLA_BRIDGE_CFM_CC_PEER_STATUS_INSTANCE,
+	IFLA_BRIDGE_CFM_CC_PEER_STATUS_PEER_MEPID,
+	IFLA_BRIDGE_CFM_CC_PEER_STATUS_CCM_DEFECT,
+	IFLA_BRIDGE_CFM_CC_PEER_STATUS_RDI,
+	IFLA_BRIDGE_CFM_CC_PEER_STATUS_PORT_TLV_VALUE,
+	IFLA_BRIDGE_CFM_CC_PEER_STATUS_IF_TLV_VALUE,
+	IFLA_BRIDGE_CFM_CC_PEER_STATUS_SEEN,
+	IFLA_BRIDGE_CFM_CC_PEER_STATUS_TLV_SEEN,
+	IFLA_BRIDGE_CFM_CC_PEER_STATUS_SEQ_UNEXP_SEEN,
+	__IFLA_BRIDGE_CFM_CC_PEER_STATUS_MAX,
+};
+
+#define IFLA_BRIDGE_CFM_CC_PEER_STATUS_MAX (__IFLA_BRIDGE_CFM_CC_PEER_STATUS_MAX - 1)
+
 struct bridge_stp_xstats {
 	__u64 transition_blk;
 	__u64 transition_fwd;
@@ -183,16 +479,22 @@ enum {
 
 /* flags used in BRIDGE_VLANDB_DUMP_FLAGS attribute to affect dumps */
 #define BRIDGE_VLANDB_DUMPF_STATS	(1 << 0) /* Include stats in the dump */
+#define BRIDGE_VLANDB_DUMPF_GLOBAL	(1 << 1) /* Dump global vlan options only */
 
 /* Bridge vlan RTM attributes
  * [BRIDGE_VLANDB_ENTRY] = {
  *     [BRIDGE_VLANDB_ENTRY_INFO]
  *     ...
  * }
+ * [BRIDGE_VLANDB_GLOBAL_OPTIONS] = {
+ *     [BRIDGE_VLANDB_GOPTS_ID]
+ *     ...
+ * }
  */
 enum {
 	BRIDGE_VLANDB_UNSPEC,
 	BRIDGE_VLANDB_ENTRY,
+	BRIDGE_VLANDB_GLOBAL_OPTIONS,
 	__BRIDGE_VLANDB_MAX,
 };
 #define BRIDGE_VLANDB_MAX (__BRIDGE_VLANDB_MAX - 1)
@@ -204,6 +506,7 @@ enum {
 	BRIDGE_VLANDB_ENTRY_STATE,
 	BRIDGE_VLANDB_ENTRY_TUNNEL_INFO,
 	BRIDGE_VLANDB_ENTRY_STATS,
+	BRIDGE_VLANDB_ENTRY_MCAST_ROUTER,
 	__BRIDGE_VLANDB_ENTRY_MAX,
 };
 #define BRIDGE_VLANDB_ENTRY_MAX (__BRIDGE_VLANDB_ENTRY_MAX - 1)
@@ -242,6 +545,29 @@ enum {
 };
 #define BRIDGE_VLANDB_STATS_MAX (__BRIDGE_VLANDB_STATS_MAX - 1)
 
+enum {
+	BRIDGE_VLANDB_GOPTS_UNSPEC,
+	BRIDGE_VLANDB_GOPTS_ID,
+	BRIDGE_VLANDB_GOPTS_RANGE,
+	BRIDGE_VLANDB_GOPTS_MCAST_SNOOPING,
+	BRIDGE_VLANDB_GOPTS_MCAST_IGMP_VERSION,
+	BRIDGE_VLANDB_GOPTS_MCAST_MLD_VERSION,
+	BRIDGE_VLANDB_GOPTS_MCAST_LAST_MEMBER_CNT,
+	BRIDGE_VLANDB_GOPTS_MCAST_STARTUP_QUERY_CNT,
+	BRIDGE_VLANDB_GOPTS_MCAST_LAST_MEMBER_INTVL,
+	BRIDGE_VLANDB_GOPTS_PAD,
+	BRIDGE_VLANDB_GOPTS_MCAST_MEMBERSHIP_INTVL,
+	BRIDGE_VLANDB_GOPTS_MCAST_QUERIER_INTVL,
+	BRIDGE_VLANDB_GOPTS_MCAST_QUERY_INTVL,
+	BRIDGE_VLANDB_GOPTS_MCAST_QUERY_RESPONSE_INTVL,
+	BRIDGE_VLANDB_GOPTS_MCAST_STARTUP_QUERY_INTVL,
+	BRIDGE_VLANDB_GOPTS_MCAST_QUERIER,
+	BRIDGE_VLANDB_GOPTS_MCAST_ROUTER_PORTS,
+	BRIDGE_VLANDB_GOPTS_MCAST_QUERIER_STATE,
+	__BRIDGE_VLANDB_GOPTS_MAX
+};
+#define BRIDGE_VLANDB_GOPTS_MAX (__BRIDGE_VLANDB_GOPTS_MAX - 1)
+
 /* Bridge multicast database attributes
  * [MDBA_MDB] = {
  *     [MDBA_MDB_ENTRY] = {
@@ -284,10 +610,33 @@ enum {
 enum {
 	MDBA_MDB_EATTR_UNSPEC,
 	MDBA_MDB_EATTR_TIMER,
+	MDBA_MDB_EATTR_SRC_LIST,
+	MDBA_MDB_EATTR_GROUP_MODE,
+	MDBA_MDB_EATTR_SOURCE,
+	MDBA_MDB_EATTR_RTPROT,
 	__MDBA_MDB_EATTR_MAX
 };
 #define MDBA_MDB_EATTR_MAX (__MDBA_MDB_EATTR_MAX - 1)
 
+/* per mdb entry source */
+enum {
+	MDBA_MDB_SRCLIST_UNSPEC,
+	MDBA_MDB_SRCLIST_ENTRY,
+	__MDBA_MDB_SRCLIST_MAX
+};
+#define MDBA_MDB_SRCLIST_MAX (__MDBA_MDB_SRCLIST_MAX - 1)
+
+/* per mdb entry per source attributes
+ * these are embedded in MDBA_MDB_SRCLIST_ENTRY
+ */
+enum {
+	MDBA_MDB_SRCATTR_UNSPEC,
+	MDBA_MDB_SRCATTR_ADDRESS,
+	MDBA_MDB_SRCATTR_TIMER,
+	__MDBA_MDB_SRCATTR_MAX
+};
+#define MDBA_MDB_SRCATTR_MAX (__MDBA_MDB_SRCATTR_MAX - 1)
+
 /* multicast router types */
 enum {
 	MDB_RTR_TYPE_DISABLED,
@@ -308,6 +657,9 @@ enum {
 	MDBA_ROUTER_PATTR_UNSPEC,
 	MDBA_ROUTER_PATTR_TIMER,
 	MDBA_ROUTER_PATTR_TYPE,
+	MDBA_ROUTER_PATTR_INET_TIMER,
+	MDBA_ROUTER_PATTR_INET6_TIMER,
+	MDBA_ROUTER_PATTR_VID,
 	__MDBA_ROUTER_PATTR_MAX
 };
 #define MDBA_ROUTER_PATTR_MAX (__MDBA_ROUTER_PATTR_MAX - 1)
@@ -324,12 +676,15 @@ struct br_mdb_entry {
 	__u8 state;
 #define MDB_FLAGS_OFFLOAD	(1 << 0)
 #define MDB_FLAGS_FAST_LEAVE	(1 << 1)
+#define MDB_FLAGS_STAR_EXCL	(1 << 2)
+#define MDB_FLAGS_BLOCKED	(1 << 3)
 	__u8 flags;
 	__u16 vid;
 	struct {
 		union {
 			__be32	ip4;
 			struct in6_addr ip6;
+			unsigned char mac_addr[ETH_ALEN];
 		} u;
 		__be16		proto;
 	} addr;
@@ -338,10 +693,23 @@ struct br_mdb_entry {
 enum {
 	MDBA_SET_ENTRY_UNSPEC,
 	MDBA_SET_ENTRY,
+	MDBA_SET_ENTRY_ATTRS,
 	__MDBA_SET_ENTRY_MAX,
 };
 #define MDBA_SET_ENTRY_MAX (__MDBA_SET_ENTRY_MAX - 1)
 
+/* [MDBA_SET_ENTRY_ATTRS] = {
+ *    [MDBE_ATTR_xxx]
+ *    ...
+ * }
+ */
+enum {
+	MDBE_ATTR_UNSPEC,
+	MDBE_ATTR_SOURCE,
+	__MDBE_ATTR_MAX,
+};
+#define MDBE_ATTR_MAX (__MDBE_ATTR_MAX - 1)
+
 /* Embedded inside LINK_XSTATS_TYPE_BRIDGE */
 enum {
 	BRIDGE_XSTATS_UNSPEC,
@@ -383,12 +751,14 @@ struct br_mcast_stats {
 
 /* bridge boolean options
  * BR_BOOLOPT_NO_LL_LEARN - disable learning from link-local packets
+ * BR_BOOLOPT_MCAST_VLAN_SNOOPING - control vlan multicast snooping
  *
  * IMPORTANT: if adding a new option do not forget to handle
  *            it in br_boolopt_toggle/get and bridge sysfs
  */
 enum br_boolopt_id {
 	BR_BOOLOPT_NO_LL_LEARN,
+	BR_BOOLOPT_MCAST_VLAN_SNOOPING,
 	BR_BOOLOPT_MAX
 };
 
@@ -401,4 +771,17 @@ struct br_boolopt_multi {
 	__u32 optval;
 	__u32 optmask;
 };
+
+enum {
+	BRIDGE_QUERIER_UNSPEC,
+	BRIDGE_QUERIER_IP_ADDRESS,
+	BRIDGE_QUERIER_IP_PORT,
+	BRIDGE_QUERIER_IP_OTHER_TIMER,
+	BRIDGE_QUERIER_PAD,
+	BRIDGE_QUERIER_IPV6_ADDRESS,
+	BRIDGE_QUERIER_IPV6_PORT,
+	BRIDGE_QUERIER_IPV6_OTHER_TIMER,
+	__BRIDGE_QUERIER_MAX
+};
+#define BRIDGE_QUERIER_MAX (__BRIDGE_QUERIER_MAX - 1)
 #endif /* _LINUX_IF_BRIDGE_H */

include/uapi/linux/if_ether.h

@@ -86,18 +86,21 @@
 					 * over Ethernet
 					 */
 #define ETH_P_PAE	0x888E		/* Port Access Entity (IEEE 802.1X) */
+#define ETH_P_REALTEK	0x8899          /* Multiple proprietary protocols */
 #define ETH_P_AOE	0x88A2		/* ATA over Ethernet		*/
 #define ETH_P_8021AD	0x88A8          /* 802.1ad Service VLAN		*/
 #define ETH_P_802_EX1	0x88B5		/* 802.1 Local Experimental 1.  */
 #define ETH_P_PREAUTH	0x88C7		/* 802.11 Preauthentication */
 #define ETH_P_TIPC	0x88CA		/* TIPC 			*/
 #define ETH_P_LLDP	0x88CC		/* Link Layer Discovery Protocol */
+#define ETH_P_MRP	0x88E3		/* Media Redundancy Protocol	*/
 #define ETH_P_MACSEC	0x88E5		/* 802.1ae MACsec */
 #define ETH_P_8021AH	0x88E7          /* 802.1ah Backbone Service Tag */
 #define ETH_P_MVRP	0x88F5          /* 802.1Q MVRP                  */
 #define ETH_P_1588	0x88F7		/* IEEE 1588 Timesync */
 #define ETH_P_NCSI	0x88F8		/* NCSI protocol		*/
 #define ETH_P_PRP	0x88FB		/* IEC 62439-3 PRP/HSRv0	*/
+#define ETH_P_CFM	0x8902		/* Connectivity Fault Management */
 #define ETH_P_FCOE	0x8906		/* Fibre Channel over Ethernet  */
 #define ETH_P_IBOE	0x8915		/* Infiniband over Ethernet	*/
 #define ETH_P_TDLS	0x890D          /* TDLS */
@@ -114,7 +117,7 @@
 #define ETH_P_IFE	0xED3E		/* ForCES inter-FE LFB type */
 #define ETH_P_AF_IUCV   0xFBFB		/* IBM af_iucv [ NOT AN OFFICIALLY REGISTERED ID ] */
 
-#define ETH_P_802_3_MIN	0x0600		/* If the value in the ethernet type is less than this value
+#define ETH_P_802_3_MIN	0x0600		/* If the value in the ethernet type is more than this value
 					 * then the frame is Ethernet II. Else it is 802.3 */
 
 /*
@@ -149,6 +152,9 @@
 #define ETH_P_MAP	0x00F9		/* Qualcomm multiplexing and
 					 * aggregation protocol
 					 */
+#define ETH_P_MCTP	0x00FA		/* Management component transport
+					 * protocol packets
+					 */
 
 /*
  *	This is an Ethernet frame header.

include/uapi/linux/if_link.h

@@ -7,24 +7,23 @@
 
 /* This struct should be in sync with struct rtnl_link_stats64 */
 struct rtnl_link_stats {
-	__u32	rx_packets;		/* total packets received	*/
+	__u32	rx_packets;
-	__u32	tx_packets;		/* total packets transmitted	*/
+	__u32	tx_packets;
-	__u32	rx_bytes;		/* total bytes received 	*/
+	__u32	rx_bytes;
-	__u32	tx_bytes;		/* total bytes transmitted	*/
+	__u32	tx_bytes;
-	__u32	rx_errors;		/* bad packets received		*/
+	__u32	rx_errors;
-	__u32	tx_errors;		/* packet transmit problems	*/
+	__u32	tx_errors;
-	__u32	rx_dropped;		/* no space in linux buffers	*/
+	__u32	rx_dropped;
-	__u32	tx_dropped;		/* no space available in linux	*/
+	__u32	tx_dropped;
-	__u32	multicast;		/* multicast packets received	*/
+	__u32	multicast;
 	__u32	collisions;
-
 	/* detailed rx_errors: */
 	__u32	rx_length_errors;
-	__u32	rx_over_errors;		/* receiver ring buff overflow	*/
+	__u32	rx_over_errors;
-	__u32	rx_crc_errors;		/* recved pkt with crc error	*/
+	__u32	rx_crc_errors;
-	__u32	rx_frame_errors;	/* recv'd frame alignment error */
+	__u32	rx_frame_errors;
-	__u32	rx_fifo_errors;		/* recv'r fifo overrun		*/
+	__u32	rx_fifo_errors;
-	__u32	rx_missed_errors;	/* receiver missed packet	*/
+	__u32	rx_missed_errors;
 
 	/* detailed tx_errors */
 	__u32	tx_aborted_errors;
@@ -37,29 +36,201 @@ struct rtnl_link_stats {
 	__u32	rx_compressed;
 	__u32	tx_compressed;
 
-	__u32	rx_nohandler;		/* dropped, no handler found	*/
+	__u32	rx_nohandler;
 };
 
-/* The main device statistics structure */
+/**
+ * struct rtnl_link_stats64 - The main device statistics structure.
+ *
+ * @rx_packets: Number of good packets received by the interface.
+ *   For hardware interfaces counts all good packets received from the device
+ *   by the host, including packets which host had to drop at various stages
+ *   of processing (even in the driver).
+ *
+ * @tx_packets: Number of packets successfully transmitted.
+ *   For hardware interfaces counts packets which host was able to successfully
+ *   hand over to the device, which does not necessarily mean that packets
+ *   had been successfully transmitted out of the device, only that device
+ *   acknowledged it copied them out of host memory.
+ *
+ * @rx_bytes: Number of good received bytes, corresponding to @rx_packets.
+ *
+ *   For IEEE 802.3 devices should count the length of Ethernet Frames
+ *   excluding the FCS.
+ *
+ * @tx_bytes: Number of good transmitted bytes, corresponding to @tx_packets.
+ *
+ *   For IEEE 802.3 devices should count the length of Ethernet Frames
+ *   excluding the FCS.
+ *
+ * @rx_errors: Total number of bad packets received on this network device.
+ *   This counter must include events counted by @rx_length_errors,
+ *   @rx_crc_errors, @rx_frame_errors and other errors not otherwise
+ *   counted.
+ *
+ * @tx_errors: Total number of transmit problems.
+ *   This counter must include events counter by @tx_aborted_errors,
+ *   @tx_carrier_errors, @tx_fifo_errors, @tx_heartbeat_errors,
+ *   @tx_window_errors and other errors not otherwise counted.
+ *
+ * @rx_dropped: Number of packets received but not processed,
+ *   e.g. due to lack of resources or unsupported protocol.
+ *   For hardware interfaces this counter may include packets discarded
+ *   due to L2 address filtering but should not include packets dropped
+ *   by the device due to buffer exhaustion which are counted separately in
+ *   @rx_missed_errors (since procfs folds those two counters together).
+ *
+ * @tx_dropped: Number of packets dropped on their way to transmission,
+ *   e.g. due to lack of resources.
+ *
+ * @multicast: Multicast packets received.
+ *   For hardware interfaces this statistic is commonly calculated
+ *   at the device level (unlike @rx_packets) and therefore may include
+ *   packets which did not reach the host.
+ *
+ *   For IEEE 802.3 devices this counter may be equivalent to:
+ *
+ *    - 30.3.1.1.21 aMulticastFramesReceivedOK
+ *
+ * @collisions: Number of collisions during packet transmissions.
+ *
+ * @rx_length_errors: Number of packets dropped due to invalid length.
+ *   Part of aggregate "frame" errors in `/proc/net/dev`.
+ *
+ *   For IEEE 802.3 devices this counter should be equivalent to a sum
+ *   of the following attributes:
+ *
+ *    - 30.3.1.1.23 aInRangeLengthErrors
+ *    - 30.3.1.1.24 aOutOfRangeLengthField
+ *    - 30.3.1.1.25 aFrameTooLongErrors
+ *
+ * @rx_over_errors: Receiver FIFO overflow event counter.
+ *
+ *   Historically the count of overflow events. Such events may be
+ *   reported in the receive descriptors or via interrupts, and may
+ *   not correspond one-to-one with dropped packets.
+ *
+ *   The recommended interpretation for high speed interfaces is -
+ *   number of packets dropped because they did not fit into buffers
+ *   provided by the host, e.g. packets larger than MTU or next buffer
+ *   in the ring was not available for a scatter transfer.
+ *
+ *   Part of aggregate "frame" errors in `/proc/net/dev`.
+ *
+ *   This statistics was historically used interchangeably with
+ *   @rx_fifo_errors.
+ *
+ *   This statistic corresponds to hardware events and is not commonly used
+ *   on software devices.
+ *
+ * @rx_crc_errors: Number of packets received with a CRC error.
+ *   Part of aggregate "frame" errors in `/proc/net/dev`.
+ *
+ *   For IEEE 802.3 devices this counter must be equivalent to:
+ *
+ *    - 30.3.1.1.6 aFrameCheckSequenceErrors
+ *
+ * @rx_frame_errors: Receiver frame alignment errors.
+ *   Part of aggregate "frame" errors in `/proc/net/dev`.
+ *
+ *   For IEEE 802.3 devices this counter should be equivalent to:
+ *
+ *    - 30.3.1.1.7 aAlignmentErrors
+ *
+ * @rx_fifo_errors: Receiver FIFO error counter.
+ *
+ *   Historically the count of overflow events. Those events may be
+ *   reported in the receive descriptors or via interrupts, and may
+ *   not correspond one-to-one with dropped packets.
+ *
+ *   This statistics was used interchangeably with @rx_over_errors.
+ *   Not recommended for use in drivers for high speed interfaces.
+ *
+ *   This statistic is used on software devices, e.g. to count software
+ *   packet queue overflow (can) or sequencing errors (GRE).
+ *
+ * @rx_missed_errors: Count of packets missed by the host.
+ *   Folded into the "drop" counter in `/proc/net/dev`.
+ *
+ *   Counts number of packets dropped by the device due to lack
+ *   of buffer space. This usually indicates that the host interface
+ *   is slower than the network interface, or host is not keeping up
+ *   with the receive packet rate.
+ *
+ *   This statistic corresponds to hardware events and is not used
+ *   on software devices.
+ *
+ * @tx_aborted_errors:
+ *   Part of aggregate "carrier" errors in `/proc/net/dev`.
+ *   For IEEE 802.3 devices capable of half-duplex operation this counter
+ *   must be equivalent to:
+ *
+ *    - 30.3.1.1.11 aFramesAbortedDueToXSColls
+ *
+ *   High speed interfaces may use this counter as a general device
+ *   discard counter.
+ *
+ * @tx_carrier_errors: Number of frame transmission errors due to loss
+ *   of carrier during transmission.
+ *   Part of aggregate "carrier" errors in `/proc/net/dev`.
+ *
+ *   For IEEE 802.3 devices this counter must be equivalent to:
+ *
+ *    - 30.3.1.1.13 aCarrierSenseErrors
+ *
+ * @tx_fifo_errors: Number of frame transmission errors due to device
+ *   FIFO underrun / underflow. This condition occurs when the device
+ *   begins transmission of a frame but is unable to deliver the
+ *   entire frame to the transmitter in time for transmission.
+ *   Part of aggregate "carrier" errors in `/proc/net/dev`.
+ *
+ * @tx_heartbeat_errors: Number of Heartbeat / SQE Test errors for
+ *   old half-duplex Ethernet.
+ *   Part of aggregate "carrier" errors in `/proc/net/dev`.
+ *
+ *   For IEEE 802.3 devices possibly equivalent to:
+ *
+ *    - 30.3.2.1.4 aSQETestErrors
+ *
+ * @tx_window_errors: Number of frame transmission errors due
+ *   to late collisions (for Ethernet - after the first 64B of transmission).
+ *   Part of aggregate "carrier" errors in `/proc/net/dev`.
+ *
+ *   For IEEE 802.3 devices this counter must be equivalent to:
+ *
+ *    - 30.3.1.1.10 aLateCollisions
+ *
+ * @rx_compressed: Number of correctly received compressed packets.
+ *   This counters is only meaningful for interfaces which support
+ *   packet compression (e.g. CSLIP, PPP).
+ *
+ * @tx_compressed: Number of transmitted compressed packets.
+ *   This counters is only meaningful for interfaces which support
+ *   packet compression (e.g. CSLIP, PPP).
+ *
+ * @rx_nohandler: Number of packets received on the interface
+ *   but dropped by the networking stack because the device is
+ *   not designated to receive packets (e.g. backup link in a bond).
+ */
 struct rtnl_link_stats64 {
-	__u64	rx_packets;		/* total packets received	*/
+	__u64	rx_packets;
-	__u64	tx_packets;		/* total packets transmitted	*/
+	__u64	tx_packets;
-	__u64	rx_bytes;		/* total bytes received 	*/
+	__u64	rx_bytes;
-	__u64	tx_bytes;		/* total bytes transmitted	*/
+	__u64	tx_bytes;
-	__u64	rx_errors;		/* bad packets received		*/
+	__u64	rx_errors;
-	__u64	tx_errors;		/* packet transmit problems	*/
+	__u64	tx_errors;
-	__u64	rx_dropped;		/* no space in linux buffers	*/
+	__u64	rx_dropped;
-	__u64	tx_dropped;		/* no space available in linux	*/
+	__u64	tx_dropped;
-	__u64	multicast;		/* multicast packets received	*/
+	__u64	multicast;
 	__u64	collisions;
 
 	/* detailed rx_errors: */
 	__u64	rx_length_errors;
-	__u64	rx_over_errors;		/* receiver ring buff overflow	*/
+	__u64	rx_over_errors;
-	__u64	rx_crc_errors;		/* recved pkt with crc error	*/
+	__u64	rx_crc_errors;
-	__u64	rx_frame_errors;	/* recv'd frame alignment error */
+	__u64	rx_frame_errors;
-	__u64	rx_fifo_errors;		/* recv'r fifo overrun		*/
+	__u64	rx_fifo_errors;
-	__u64	rx_missed_errors;	/* receiver missed packet	*/
+	__u64	rx_missed_errors;
 
 	/* detailed tx_errors */
 	__u64	tx_aborted_errors;
@@ -71,8 +242,7 @@ struct rtnl_link_stats64 {
 	/* for cslip etc */
 	__u64	rx_compressed;
 	__u64	tx_compressed;
-
+	__u64	rx_nohandler;
-	__u64	rx_nohandler;		/* dropped, no handler found	*/
 };
 
 /* The struct should be in sync with struct ifmap */
@@ -170,12 +340,29 @@ enum {
 	IFLA_PROP_LIST,
 	IFLA_ALT_IFNAME, /* Alternative ifname */
 	IFLA_PERM_ADDRESS,
+	IFLA_PROTO_DOWN_REASON,
+
+	/* device (sysfs) name as parent, used instead
+	 * of IFLA_LINK where there's no parent netdev
+	 */
+	IFLA_PARENT_DEV_NAME,
+	IFLA_PARENT_DEV_BUS_NAME,
+
 	__IFLA_MAX
 };
 
 
 #define IFLA_MAX (__IFLA_MAX - 1)
 
+enum {
+	IFLA_PROTO_DOWN_REASON_UNSPEC,
+	IFLA_PROTO_DOWN_REASON_MASK,	/* u32, mask for reason bits */
+	IFLA_PROTO_DOWN_REASON_VALUE,   /* u32, reason bit value */
+
+	__IFLA_PROTO_DOWN_REASON_CNT,
+	IFLA_PROTO_DOWN_REASON_MAX = __IFLA_PROTO_DOWN_REASON_CNT - 1
+};
+
 /* backwards compatibility for userspace */
 #define IFLA_RTA(r)  ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct ifinfomsg))))
 #define IFLA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct ifinfomsg))
@@ -228,6 +415,7 @@ enum {
 	IFLA_INET6_ICMP6STATS,	/* statistics (icmpv6)		*/
 	IFLA_INET6_TOKEN,	/* device token			*/
 	IFLA_INET6_ADDR_GEN_MODE, /* implicit address generator mode */
+	IFLA_INET6_RA_MTU,	/* mtu carried in the RA message */
 	__IFLA_INET6_MAX
 };
 
@@ -290,6 +478,7 @@ enum {
 	IFLA_BR_MCAST_MLD_VERSION,
 	IFLA_BR_VLAN_STATS_PER_PORT,
 	IFLA_BR_MULTI_BOOLOPT,
+	IFLA_BR_MCAST_QUERIER_STATE,
 	__IFLA_BR_MAX,
 };
 
@@ -341,6 +530,10 @@ enum {
 	IFLA_BRPORT_NEIGH_SUPPRESS,
 	IFLA_BRPORT_ISOLATED,
 	IFLA_BRPORT_BACKUP_PORT,
+	IFLA_BRPORT_MRP_RING_OPEN,
+	IFLA_BRPORT_MRP_IN_OPEN,
+	IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT,
+	IFLA_BRPORT_MCAST_EHT_HOSTS_CNT,
 	__IFLA_BRPORT_MAX
 };
 #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1)
@@ -405,6 +598,8 @@ enum {
 	IFLA_MACVLAN_MACADDR,
 	IFLA_MACVLAN_MACADDR_DATA,
 	IFLA_MACVLAN_MACADDR_COUNT,
+	IFLA_MACVLAN_BC_QUEUE_LEN,
+	IFLA_MACVLAN_BC_QUEUE_LEN_USED,
 	__IFLA_MACVLAN_MAX,
 };
 
@@ -426,6 +621,7 @@ enum macvlan_macaddr_mode {
 };
 
 #define MACVLAN_FLAG_NOPROMISC	1
+#define MACVLAN_FLAG_NODST	2 /* skip dst macvlan if matching src macvlan */
 
 /* VRF section */
 enum {
@@ -659,6 +855,7 @@ enum {
 	IFLA_BOND_AD_ACTOR_SYSTEM,
 	IFLA_BOND_TLB_DYNAMIC_LB,
 	IFLA_BOND_PEER_NOTIF_DELAY,
+	IFLA_BOND_AD_LACP_ACTIVE,
 	__IFLA_BOND_MAX,
 };
 
@@ -903,7 +1100,14 @@ enum {
 #define IFLA_IPOIB_MAX (__IFLA_IPOIB_MAX - 1)
 
 
-/* HSR section */
+/* HSR/PRP section, both uses same interface */
+
+/* Different redundancy protocols for hsr device */
+enum {
+	HSR_PROTOCOL_HSR,
+	HSR_PROTOCOL_PRP,
+	HSR_PROTOCOL_MAX,
+};
 
 enum {
 	IFLA_HSR_UNSPEC,
@@ -913,6 +1117,9 @@ enum {
 	IFLA_HSR_SUPERVISION_ADDR,	/* Supervision frame multicast addr */
 	IFLA_HSR_SEQ_NR,
 	IFLA_HSR_VERSION,		/* HSR version */
+	IFLA_HSR_PROTOCOL,		/* Indicate different protocol than
+					 * HSR. For example PRP.
+					 */
 	__IFLA_HSR_MAX,
 };
 
@@ -1037,6 +1244,8 @@ enum {
 #define RMNET_FLAGS_INGRESS_MAP_COMMANDS          (1U << 1)
 #define RMNET_FLAGS_INGRESS_MAP_CKSUMV4           (1U << 2)
 #define RMNET_FLAGS_EGRESS_MAP_CKSUMV4            (1U << 3)
+#define RMNET_FLAGS_INGRESS_MAP_CKSUMV5           (1U << 4)
+#define RMNET_FLAGS_EGRESS_MAP_CKSUMV5            (1U << 5)
 
 enum {
 	IFLA_RMNET_UNSPEC,
@@ -1052,4 +1261,14 @@ struct ifla_rmnet_flags {
 	__u32	mask;
 };
 
+/* MCTP section */
+
+enum {
+	IFLA_MCTP_UNSPEC,
+	IFLA_MCTP_NET,
+	__IFLA_MCTP_MAX,
+};
+
+#define IFLA_MCTP_MAX (__IFLA_MCTP_MAX - 1)
+
 #endif /* _LINUX_IF_LINK_H */

include/uapi/linux/if_packet.h

@@ -2,6 +2,7 @@
 #ifndef __LINUX_IF_PACKET_H
 #define __LINUX_IF_PACKET_H
 
+#include <asm/byteorder.h>
 #include <linux/types.h>
 
 struct sockaddr_pkt {
@@ -296,6 +297,17 @@ struct packet_mreq {
 	unsigned char	mr_address[8];
 };
 
+struct fanout_args {
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+	__u16		id;
+	__u16		type_flags;
+#else
+	__u16		type_flags;
+	__u16		id;
+#endif
+	__u32		max_num_members;
+};
+
 #define PACKET_MR_MULTICAST	0
 #define PACKET_MR_PROMISC	1
 #define PACKET_MR_ALLMULTI	2

include/uapi/linux/in.h

@@ -123,6 +123,7 @@ struct in_addr {
 #define IP_CHECKSUM	23
 #define IP_BIND_ADDRESS_NO_PORT	24
 #define IP_RECVFRAGSIZE	25
+#define IP_RECVERR_RFC4884	26
 
 /* IP_MTU_DISCOVER values */
 #define IP_PMTUDISC_DONT		0	/* Never send DF frames */
@@ -134,7 +135,7 @@ struct in_addr {
  * this socket to prevent accepting spoofed ones.
  */
 #define IP_PMTUDISC_INTERFACE		4
-/* weaker version of IP_PMTUDISC_INTERFACE, which allos packets to get
+/* weaker version of IP_PMTUDISC_INTERFACE, which allows packets to get
  * fragmented if they exeed the interface mtu
  */
 #define IP_PMTUDISC_OMIT		5
@@ -187,11 +188,22 @@ struct ip_mreq_source {
 };
 
 struct ip_msfilter {
-	__be32		imsf_multiaddr;
+	union {
-	__be32		imsf_interface;
+		struct {
-	__u32		imsf_fmode;
+			__be32		imsf_multiaddr_aux;
-	__u32		imsf_numsrc;
+			__be32		imsf_interface_aux;
-	__be32		imsf_slist[1];
+			__u32		imsf_fmode_aux;
+			__u32		imsf_numsrc_aux;
+			__be32		imsf_slist[1];
+		};
+		struct {
+			__be32		imsf_multiaddr;
+			__be32		imsf_interface;
+			__u32		imsf_fmode;
+			__u32		imsf_numsrc;
+			__be32		imsf_slist_flex[];
+		};
+	};
 };
 
 #define IP_MSFILTER_SIZE(numsrc) \
@@ -210,11 +222,22 @@ struct group_source_req {
 };
 
 struct group_filter {
-	__u32				 gf_interface;	/* interface index */
+	union {
-	struct __kernel_sockaddr_storage gf_group;	/* multicast address */
+		struct {
-	__u32				 gf_fmode;	/* filter mode */
+			__u32				 gf_interface_aux; /* interface index */
-	__u32				 gf_numsrc;	/* number of sources */
+			struct __kernel_sockaddr_storage gf_group_aux;	   /* multicast address */
-	struct __kernel_sockaddr_storage gf_slist[1];	/* interface index */
+			__u32				 gf_fmode_aux;	   /* filter mode */
+			__u32				 gf_numsrc_aux;	   /* number of sources */
+			struct __kernel_sockaddr_storage gf_slist[1];	   /* interface index */
+		};
+		struct {
+			__u32				 gf_interface;	  /* interface index */
+			struct __kernel_sockaddr_storage gf_group;	  /* multicast address */
+			__u32				 gf_fmode;	  /* filter mode */
+			__u32				 gf_numsrc;	  /* number of sources */
+			struct __kernel_sockaddr_storage gf_slist_flex[]; /* interface index */
+		};
+	};
 };
 
 #define GROUP_FILTER_SIZE(numsrc) \
@@ -288,6 +311,9 @@ struct sockaddr_in {
 /* Address indicating an error return. */
 #define	INADDR_NONE		((unsigned long int) 0xffffffff)
 
+/* Dummy address for src of ICMP replies if no real address is set (RFC7600). */
+#define	INADDR_DUMMY		((unsigned long int) 0xc0000008)
+
 /* Network number for local host loopback. */
 #define	IN_LOOPBACKNET		127
 

include/uapi/linux/in6.h

@@ -145,6 +145,7 @@ struct in6_flowlabel_req {
 #define IPV6_TLV_PADN		1
 #define IPV6_TLV_ROUTERALERT	5
 #define IPV6_TLV_CALIPSO	7	/* RFC 5570 */
+#define IPV6_TLV_IOAM		49	/* TEMPORARY IANA allocation for IOAM */
 #define IPV6_TLV_JUMBO		194
 #define IPV6_TLV_HAO		201	/* home address option */
 
@@ -179,6 +180,7 @@ struct in6_flowlabel_req {
 #define IPV6_LEAVE_ANYCAST	28
 #define IPV6_MULTICAST_ALL	29
 #define IPV6_ROUTER_ALERT_ISOLATE	30
+#define IPV6_RECVERR_RFC4884	31
 
 /* IPV6_MTU_DISCOVER values */
 #define IPV6_PMTUDISC_DONT		0

include/uapi/linux/inet_diag.h

@@ -65,6 +65,7 @@ enum {
 	INET_DIAG_REQ_NONE,
 	INET_DIAG_REQ_BYTECODE,
 	INET_DIAG_REQ_SK_BPF_STORAGES,
+	INET_DIAG_REQ_PROTOCOL,
 	__INET_DIAG_REQ_MAX,
 };
 
@@ -96,6 +97,7 @@ enum {
 	INET_DIAG_BC_MARK_COND,
 	INET_DIAG_BC_S_EQ,
 	INET_DIAG_BC_D_EQ,
+	INET_DIAG_BC_CGROUP_COND,   /* u64 cgroup v2 ID */
 };
 
 struct inet_diag_hostcond {
@@ -157,6 +159,8 @@ enum {
 	INET_DIAG_MD5SIG,
 	INET_DIAG_ULP_INFO,
 	INET_DIAG_SK_BPF_STORAGES,
+	INET_DIAG_CGROUP_ID,
+	INET_DIAG_SOCKOPT,
 	__INET_DIAG_MAX,
 };
 
@@ -180,6 +184,23 @@ struct inet_diag_meminfo {
 	__u32	idiag_tmem;
 };
 
+/* INET_DIAG_SOCKOPT */
+
+struct inet_diag_sockopt {
+	__u8	recverr:1,
+		is_icsk:1,
+		freebind:1,
+		hdrincl:1,
+		mc_loop:1,
+		transparent:1,
+		mc_all:1,
+		nodefrag:1;
+	__u8	bind_address_no_port:1,
+		recverr_rfc4884:1,
+		defer_connect:1,
+		unused:5;
+};
+
 /* INET_DIAG_VEGASINFO */
 
 struct tcpvegas_info {

include/uapi/linux/ioam6.h

@@ -0,0 +1,133 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ *  IPv6 IOAM implementation
+ *
+ *  Author:
+ *  Justin Iurman <justin.iurman@uliege.be>
+ */
+
+#ifndef _LINUX_IOAM6_H
+#define _LINUX_IOAM6_H
+
+#include <asm/byteorder.h>
+#include <linux/types.h>
+
+#define IOAM6_U16_UNAVAILABLE U16_MAX
+#define IOAM6_U32_UNAVAILABLE U32_MAX
+#define IOAM6_U64_UNAVAILABLE U64_MAX
+
+#define IOAM6_DEFAULT_ID (IOAM6_U32_UNAVAILABLE >> 8)
+#define IOAM6_DEFAULT_ID_WIDE (IOAM6_U64_UNAVAILABLE >> 8)
+#define IOAM6_DEFAULT_IF_ID IOAM6_U16_UNAVAILABLE
+#define IOAM6_DEFAULT_IF_ID_WIDE IOAM6_U32_UNAVAILABLE
+
+/*
+ * IPv6 IOAM Option Header
+ */
+struct ioam6_hdr {
+	__u8 opt_type;
+	__u8 opt_len;
+	__u8 :8;				/* reserved */
+#define IOAM6_TYPE_PREALLOC 0
+	__u8 type;
+} __attribute__((packed));
+
+/*
+ * IOAM Trace Header
+ */
+struct ioam6_trace_hdr {
+	__be16	namespace_id;
+
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+
+	__u8	:1,				/* unused */
+		:1,				/* unused */
+		overflow:1,
+		nodelen:5;
+
+	__u8	remlen:7,
+		:1;				/* unused */
+
+	union {
+		__be32 type_be32;
+
+		struct {
+			__u32	bit7:1,
+				bit6:1,
+				bit5:1,
+				bit4:1,
+				bit3:1,
+				bit2:1,
+				bit1:1,
+				bit0:1,
+				bit15:1,	/* unused */
+				bit14:1,	/* unused */
+				bit13:1,	/* unused */
+				bit12:1,	/* unused */
+				bit11:1,
+				bit10:1,
+				bit9:1,
+				bit8:1,
+				bit23:1,	/* reserved */
+				bit22:1,
+				bit21:1,	/* unused */
+				bit20:1,	/* unused */
+				bit19:1,	/* unused */
+				bit18:1,	/* unused */
+				bit17:1,	/* unused */
+				bit16:1,	/* unused */
+				:8;		/* reserved */
+		} type;
+	};
+
+#elif defined(__BIG_ENDIAN_BITFIELD)
+
+	__u8	nodelen:5,
+		overflow:1,
+		:1,				/* unused */
+		:1;				/* unused */
+
+	__u8	:1,				/* unused */
+		remlen:7;
+
+	union {
+		__be32 type_be32;
+
+		struct {
+			__u32	bit0:1,
+				bit1:1,
+				bit2:1,
+				bit3:1,
+				bit4:1,
+				bit5:1,
+				bit6:1,
+				bit7:1,
+				bit8:1,
+				bit9:1,
+				bit10:1,
+				bit11:1,
+				bit12:1,	/* unused */
+				bit13:1,	/* unused */
+				bit14:1,	/* unused */
+				bit15:1,	/* unused */
+				bit16:1,	/* unused */
+				bit17:1,	/* unused */
+				bit18:1,	/* unused */
+				bit19:1,	/* unused */
+				bit20:1,	/* unused */
+				bit21:1,	/* unused */
+				bit22:1,
+				bit23:1,	/* reserved */
+				:8;		/* reserved */
+		} type;
+	};
+
+#else
+#error "Please fix <asm/byteorder.h>"
+#endif
+
+#define IOAM6_TRACE_DATA_SIZE_MAX 244
+	__u8	data[0];
+} __attribute__((packed));
+
+#endif /* _LINUX_IOAM6_H */

include/uapi/linux/ioam6_genl.h

@@ -0,0 +1,52 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ *  IPv6 IOAM Generic Netlink API
+ *
+ *  Author:
+ *  Justin Iurman <justin.iurman@uliege.be>
+ */
+
+#ifndef _LINUX_IOAM6_GENL_H
+#define _LINUX_IOAM6_GENL_H
+
+#define IOAM6_GENL_NAME "IOAM6"
+#define IOAM6_GENL_VERSION 0x1
+
+enum {
+	IOAM6_ATTR_UNSPEC,
+
+	IOAM6_ATTR_NS_ID,	/* u16 */
+	IOAM6_ATTR_NS_DATA,	/* u32 */
+	IOAM6_ATTR_NS_DATA_WIDE,/* u64 */
+
+#define IOAM6_MAX_SCHEMA_DATA_LEN (255 * 4)
+	IOAM6_ATTR_SC_ID,	/* u32 */
+	IOAM6_ATTR_SC_DATA,	/* Binary */
+	IOAM6_ATTR_SC_NONE,	/* Flag */
+
+	IOAM6_ATTR_PAD,
+
+	__IOAM6_ATTR_MAX,
+};
+
+#define IOAM6_ATTR_MAX (__IOAM6_ATTR_MAX - 1)
+
+enum {
+	IOAM6_CMD_UNSPEC,
+
+	IOAM6_CMD_ADD_NAMESPACE,
+	IOAM6_CMD_DEL_NAMESPACE,
+	IOAM6_CMD_DUMP_NAMESPACES,
+
+	IOAM6_CMD_ADD_SCHEMA,
+	IOAM6_CMD_DEL_SCHEMA,
+	IOAM6_CMD_DUMP_SCHEMAS,
+
+	IOAM6_CMD_NS_SET_SCHEMA,
+
+	__IOAM6_CMD_MAX,
+};
+
+#define IOAM6_CMD_MAX (__IOAM6_CMD_MAX - 1)
+
+#endif /* _LINUX_IOAM6_GENL_H */

include/uapi/linux/ioam6_iptunnel.h

@@ -0,0 +1,49 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ *  IPv6 IOAM Lightweight Tunnel API
+ *
+ *  Author:
+ *  Justin Iurman <justin.iurman@uliege.be>
+ */
+
+#ifndef _LINUX_IOAM6_IPTUNNEL_H
+#define _LINUX_IOAM6_IPTUNNEL_H
+
+/* Encap modes:
+ *  - inline: direct insertion
+ *  - encap: ip6ip6 encapsulation
+ *  - auto: __inline__ for local packets, encap for in-transit packets
+ */
+enum {
+	__IOAM6_IPTUNNEL_MODE_MIN,
+
+	IOAM6_IPTUNNEL_MODE_INLINE,
+	IOAM6_IPTUNNEL_MODE_ENCAP,
+	IOAM6_IPTUNNEL_MODE_AUTO,
+
+	__IOAM6_IPTUNNEL_MODE_MAX,
+};
+
+#define IOAM6_IPTUNNEL_MODE_MIN (__IOAM6_IPTUNNEL_MODE_MIN + 1)
+#define IOAM6_IPTUNNEL_MODE_MAX (__IOAM6_IPTUNNEL_MODE_MAX - 1)
+
+enum {
+	IOAM6_IPTUNNEL_UNSPEC,
+
+	/* Encap mode */
+	IOAM6_IPTUNNEL_MODE,		/* u8 */
+
+	/* Tunnel dst address.
+	 * For encap,auto modes.
+	 */
+	IOAM6_IPTUNNEL_DST,		/* struct in6_addr */
+
+	/* IOAM Trace Header */
+	IOAM6_IPTUNNEL_TRACE,		/* struct ioam6_trace_hdr */
+
+	__IOAM6_IPTUNNEL_MAX,
+};
+
+#define IOAM6_IPTUNNEL_MAX (__IOAM6_IPTUNNEL_MAX - 1)
+
+#endif /* _LINUX_IOAM6_IPTUNNEL_H */

include/uapi/linux/ip.h

@@ -169,6 +169,7 @@ enum
 	IPV4_DEVCONF_DROP_UNICAST_IN_L2_MULTICAST,
 	IPV4_DEVCONF_DROP_GRATUITOUS_ARP,
 	IPV4_DEVCONF_BC_FORWARDING,
+	IPV4_DEVCONF_ARP_EVICT_NOCARRIER,
 	__IPV4_DEVCONF_MAX
 };
 

include/uapi/linux/kernel.h

@@ -3,13 +3,6 @@
 #define _LINUX_KERNEL_H
 
 #include <linux/sysinfo.h>
-
+#include <linux/const.h>
-/*
- * 'kernel.h' contains some often-used function prototypes etc
- */
-#define __ALIGN_KERNEL(x, a)		__ALIGN_KERNEL_MASK(x, (typeof(x))(a) - 1)
-#define __ALIGN_KERNEL_MASK(x, mask)	(((x) + (mask)) & ~(mask))
-
-#define __KERNEL_DIV_ROUND_UP(n, d) (((n) + (d) - 1) / (d))
 
 #endif /* _LINUX_KERNEL_H */

include/uapi/linux/l2tp.h

@@ -108,7 +108,7 @@ enum {
 	L2TP_ATTR_VLAN_ID,		/* u16 (not used) */
 	L2TP_ATTR_COOKIE,		/* 0, 4 or 8 bytes */
 	L2TP_ATTR_PEER_COOKIE,		/* 0, 4 or 8 bytes */
-	L2TP_ATTR_DEBUG,		/* u32, enum l2tp_debug_flags */
+	L2TP_ATTR_DEBUG,		/* u32, enum l2tp_debug_flags (not used) */
 	L2TP_ATTR_RECV_SEQ,		/* u8 */
 	L2TP_ATTR_SEND_SEQ,		/* u8 */
 	L2TP_ATTR_LNS_MODE,		/* u8 */
@@ -144,6 +144,8 @@ enum {
 	L2TP_ATTR_RX_OOS_PACKETS,	/* u64 */
 	L2TP_ATTR_RX_ERRORS,		/* u64 */
 	L2TP_ATTR_STATS_PAD,
+	L2TP_ATTR_RX_COOKIE_DISCARDS,	/* u64 */
+	L2TP_ATTR_RX_INVALID,		/* u64 */
 	__L2TP_ATTR_STATS_MAX,
 };
 
@@ -177,7 +179,9 @@ enum l2tp_seqmode {
 };
 
 /**
- * enum l2tp_debug_flags - debug message categories for L2TP tunnels/sessions
+ * enum l2tp_debug_flags - debug message categories for L2TP tunnels/sessions.
+ *
+ * Unused.
  *
  * @L2TP_MSG_DEBUG: verbose debug (if compiled in)
  * @L2TP_MSG_CONTROL: userspace - kernel interface

include/uapi/linux/lwtunnel.h

@@ -14,6 +14,7 @@ enum lwtunnel_encap_types {
 	LWTUNNEL_ENCAP_BPF,
 	LWTUNNEL_ENCAP_SEG6_LOCAL,
 	LWTUNNEL_ENCAP_RPL,
+	LWTUNNEL_ENCAP_IOAM6,
 	__LWTUNNEL_ENCAP_MAX,
 };
 

include/uapi/linux/magic.h

@@ -94,7 +94,9 @@
 #define BALLOON_KVM_MAGIC	0x13661366
 #define ZSMALLOC_MAGIC		0x58295829
 #define DMA_BUF_MAGIC		0x444d4142	/* "DMAB" */
+#define DEVMEM_MAGIC		0x454d444d	/* "DMEM" */
 #define Z3FOLD_MAGIC		0x33
 #define PPC_CMM_MAGIC		0xc7571590
+#define SECRETMEM_MAGIC		0x5345434d	/* "SECM" */
 
 #endif /* __LINUX_MAGIC_H__ */

include/uapi/linux/mptcp.h

@@ -0,0 +1,229 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+#ifndef _MPTCP_H
+#define _MPTCP_H
+
+#include <linux/const.h>
+#include <linux/types.h>
+#include <linux/in.h>		/* for sockaddr_in			*/
+#include <linux/in6.h>		/* for sockaddr_in6			*/
+#include <linux/socket.h>	/* for sockaddr_storage and sa_family	*/
+
+#include <sys/socket.h>		/* for struct sockaddr			*/
+
+#define MPTCP_SUBFLOW_FLAG_MCAP_REM		_BITUL(0)
+#define MPTCP_SUBFLOW_FLAG_MCAP_LOC		_BITUL(1)
+#define MPTCP_SUBFLOW_FLAG_JOIN_REM		_BITUL(2)
+#define MPTCP_SUBFLOW_FLAG_JOIN_LOC		_BITUL(3)
+#define MPTCP_SUBFLOW_FLAG_BKUP_REM		_BITUL(4)
+#define MPTCP_SUBFLOW_FLAG_BKUP_LOC		_BITUL(5)
+#define MPTCP_SUBFLOW_FLAG_FULLY_ESTABLISHED	_BITUL(6)
+#define MPTCP_SUBFLOW_FLAG_CONNECTED		_BITUL(7)
+#define MPTCP_SUBFLOW_FLAG_MAPVALID		_BITUL(8)
+
+enum {
+	MPTCP_SUBFLOW_ATTR_UNSPEC,
+	MPTCP_SUBFLOW_ATTR_TOKEN_REM,
+	MPTCP_SUBFLOW_ATTR_TOKEN_LOC,
+	MPTCP_SUBFLOW_ATTR_RELWRITE_SEQ,
+	MPTCP_SUBFLOW_ATTR_MAP_SEQ,
+	MPTCP_SUBFLOW_ATTR_MAP_SFSEQ,
+	MPTCP_SUBFLOW_ATTR_SSN_OFFSET,
+	MPTCP_SUBFLOW_ATTR_MAP_DATALEN,
+	MPTCP_SUBFLOW_ATTR_FLAGS,
+	MPTCP_SUBFLOW_ATTR_ID_REM,
+	MPTCP_SUBFLOW_ATTR_ID_LOC,
+	MPTCP_SUBFLOW_ATTR_PAD,
+	__MPTCP_SUBFLOW_ATTR_MAX
+};
+
+#define MPTCP_SUBFLOW_ATTR_MAX (__MPTCP_SUBFLOW_ATTR_MAX - 1)
+
+/* netlink interface */
+#define MPTCP_PM_NAME		"mptcp_pm"
+#define MPTCP_PM_CMD_GRP_NAME	"mptcp_pm_cmds"
+#define MPTCP_PM_EV_GRP_NAME	"mptcp_pm_events"
+#define MPTCP_PM_VER		0x1
+
+/*
+ * ATTR types defined for MPTCP
+ */
+enum {
+	MPTCP_PM_ATTR_UNSPEC,
+
+	MPTCP_PM_ATTR_ADDR,				/* nested address */
+	MPTCP_PM_ATTR_RCV_ADD_ADDRS,			/* u32 */
+	MPTCP_PM_ATTR_SUBFLOWS,				/* u32 */
+
+	__MPTCP_PM_ATTR_MAX
+};
+
+#define MPTCP_PM_ATTR_MAX (__MPTCP_PM_ATTR_MAX - 1)
+
+enum {
+	MPTCP_PM_ADDR_ATTR_UNSPEC,
+
+	MPTCP_PM_ADDR_ATTR_FAMILY,			/* u16 */
+	MPTCP_PM_ADDR_ATTR_ID,				/* u8 */
+	MPTCP_PM_ADDR_ATTR_ADDR4,			/* struct in_addr */
+	MPTCP_PM_ADDR_ATTR_ADDR6,			/* struct in6_addr */
+	MPTCP_PM_ADDR_ATTR_PORT,			/* u16 */
+	MPTCP_PM_ADDR_ATTR_FLAGS,			/* u32 */
+	MPTCP_PM_ADDR_ATTR_IF_IDX,			/* s32 */
+
+	__MPTCP_PM_ADDR_ATTR_MAX
+};
+
+#define MPTCP_PM_ADDR_ATTR_MAX (__MPTCP_PM_ADDR_ATTR_MAX - 1)
+
+#define MPTCP_PM_ADDR_FLAG_SIGNAL			(1 << 0)
+#define MPTCP_PM_ADDR_FLAG_SUBFLOW			(1 << 1)
+#define MPTCP_PM_ADDR_FLAG_BACKUP			(1 << 2)
+#define MPTCP_PM_ADDR_FLAG_FULLMESH			(1 << 3)
+
+enum {
+	MPTCP_PM_CMD_UNSPEC,
+
+	MPTCP_PM_CMD_ADD_ADDR,
+	MPTCP_PM_CMD_DEL_ADDR,
+	MPTCP_PM_CMD_GET_ADDR,
+	MPTCP_PM_CMD_FLUSH_ADDRS,
+	MPTCP_PM_CMD_SET_LIMITS,
+	MPTCP_PM_CMD_GET_LIMITS,
+	MPTCP_PM_CMD_SET_FLAGS,
+
+	__MPTCP_PM_CMD_AFTER_LAST
+};
+
+#define MPTCP_INFO_FLAG_FALLBACK		_BITUL(0)
+#define MPTCP_INFO_FLAG_REMOTE_KEY_RECEIVED	_BITUL(1)
+
+struct mptcp_info {
+	__u8	mptcpi_subflows;
+	__u8	mptcpi_add_addr_signal;
+	__u8	mptcpi_add_addr_accepted;
+	__u8	mptcpi_subflows_max;
+	__u8	mptcpi_add_addr_signal_max;
+	__u8	mptcpi_add_addr_accepted_max;
+	__u32	mptcpi_flags;
+	__u32	mptcpi_token;
+	__u64	mptcpi_write_seq;
+	__u64	mptcpi_snd_una;
+	__u64	mptcpi_rcv_nxt;
+	__u8	mptcpi_local_addr_used;
+	__u8	mptcpi_local_addr_max;
+	__u8	mptcpi_csum_enabled;
+};
+
+/*
+ * MPTCP_EVENT_CREATED: token, family, saddr4 | saddr6, daddr4 | daddr6,
+ *                      sport, dport
+ * A new MPTCP connection has been created. It is the good time to allocate
+ * memory and send ADD_ADDR if needed. Depending on the traffic-patterns
+ * it can take a long time until the MPTCP_EVENT_ESTABLISHED is sent.
+ *
+ * MPTCP_EVENT_ESTABLISHED: token, family, saddr4 | saddr6, daddr4 | daddr6,
+ *			    sport, dport
+ * A MPTCP connection is established (can start new subflows).
+ *
+ * MPTCP_EVENT_CLOSED: token
+ * A MPTCP connection has stopped.
+ *
+ * MPTCP_EVENT_ANNOUNCED: token, rem_id, family, daddr4 | daddr6 [, dport]
+ * A new address has been announced by the peer.
+ *
+ * MPTCP_EVENT_REMOVED: token, rem_id
+ * An address has been lost by the peer.
+ *
+ * MPTCP_EVENT_SUB_ESTABLISHED: token, family, saddr4 | saddr6,
+ *                              daddr4 | daddr6, sport, dport, backup,
+ *                              if_idx [, error]
+ * A new subflow has been established. 'error' should not be set.
+ *
+ * MPTCP_EVENT_SUB_CLOSED: token, family, saddr4 | saddr6, daddr4 | daddr6,
+ *                         sport, dport, backup, if_idx [, error]
+ * A subflow has been closed. An error (copy of sk_err) could be set if an
+ * error has been detected for this subflow.
+ *
+ * MPTCP_EVENT_SUB_PRIORITY: token, family, saddr4 | saddr6, daddr4 | daddr6,
+ *                           sport, dport, backup, if_idx [, error]
+ *       The priority of a subflow has changed. 'error' should not be set.
+ */
+enum mptcp_event_type {
+	MPTCP_EVENT_UNSPEC = 0,
+	MPTCP_EVENT_CREATED = 1,
+	MPTCP_EVENT_ESTABLISHED = 2,
+	MPTCP_EVENT_CLOSED = 3,
+
+	MPTCP_EVENT_ANNOUNCED = 6,
+	MPTCP_EVENT_REMOVED = 7,
+
+	MPTCP_EVENT_SUB_ESTABLISHED = 10,
+	MPTCP_EVENT_SUB_CLOSED = 11,
+
+	MPTCP_EVENT_SUB_PRIORITY = 13,
+};
+
+enum mptcp_event_attr {
+	MPTCP_ATTR_UNSPEC = 0,
+
+	MPTCP_ATTR_TOKEN,	/* u32 */
+	MPTCP_ATTR_FAMILY,	/* u16 */
+	MPTCP_ATTR_LOC_ID,	/* u8 */
+	MPTCP_ATTR_REM_ID,	/* u8 */
+	MPTCP_ATTR_SADDR4,	/* be32 */
+	MPTCP_ATTR_SADDR6,	/* struct in6_addr */
+	MPTCP_ATTR_DADDR4,	/* be32 */
+	MPTCP_ATTR_DADDR6,	/* struct in6_addr */
+	MPTCP_ATTR_SPORT,	/* be16 */
+	MPTCP_ATTR_DPORT,	/* be16 */
+	MPTCP_ATTR_BACKUP,	/* u8 */
+	MPTCP_ATTR_ERROR,	/* u8 */
+	MPTCP_ATTR_FLAGS,	/* u16 */
+	MPTCP_ATTR_TIMEOUT,	/* u32 */
+	MPTCP_ATTR_IF_IDX,	/* s32 */
+	MPTCP_ATTR_RESET_REASON,/* u32 */
+	MPTCP_ATTR_RESET_FLAGS, /* u32 */
+
+	__MPTCP_ATTR_AFTER_LAST
+};
+
+#define MPTCP_ATTR_MAX (__MPTCP_ATTR_AFTER_LAST - 1)
+
+/* MPTCP Reset reason codes, rfc8684 */
+#define MPTCP_RST_EUNSPEC	0
+#define MPTCP_RST_EMPTCP	1
+#define MPTCP_RST_ERESOURCE	2
+#define MPTCP_RST_EPROHIBIT	3
+#define MPTCP_RST_EWQ2BIG	4
+#define MPTCP_RST_EBADPERF	5
+#define MPTCP_RST_EMIDDLEBOX	6
+
+struct mptcp_subflow_data {
+	__u32		size_subflow_data;		/* size of this structure in userspace */
+	__u32		num_subflows;			/* must be 0, set by kernel */
+	__u32		size_kernel;			/* must be 0, set by kernel */
+	__u32		size_user;			/* size of one element in data[] */
+} __attribute__((aligned(8)));
+
+struct mptcp_subflow_addrs {
+	union {
+		__kernel_sa_family_t sa_family;
+		struct sockaddr sa_local;
+		struct sockaddr_in sin_local;
+		struct sockaddr_in6 sin6_local;
+		struct __kernel_sockaddr_storage ss_local;
+	};
+	union {
+		struct sockaddr sa_remote;
+		struct sockaddr_in sin_remote;
+		struct sockaddr_in6 sin6_remote;
+		struct __kernel_sockaddr_storage ss_remote;
+	};
+};
+
+/* MPTCP socket options */
+#define MPTCP_INFO		1
+#define MPTCP_TCPINFO		2
+#define MPTCP_SUBFLOW_ADDRS	3
+
+#endif /* _MPTCP_H */

include/uapi/linux/neighbour.h

@@ -29,6 +29,9 @@ enum {
 	NDA_LINK_NETNSID,
 	NDA_SRC_VNI,
 	NDA_PROTOCOL,  /* Originator of entry */
+	NDA_NH_ID,
+	NDA_FDB_EXT_ATTRS,
+	NDA_FLAGS_EXT,
 	__NDA_MAX
 };
 
@@ -38,14 +41,16 @@ enum {
  *	Neighbor Cache Entry Flags
  */
 
-#define NTF_USE		0x01
+#define NTF_USE		(1 << 0)
-#define NTF_SELF	0x02
+#define NTF_SELF	(1 << 1)
-#define NTF_MASTER	0x04
+#define NTF_MASTER	(1 << 2)
-#define NTF_PROXY	0x08	/* == ATF_PUBL */
+#define NTF_PROXY	(1 << 3)	/* == ATF_PUBL */
-#define NTF_EXT_LEARNED	0x10
+#define NTF_EXT_LEARNED	(1 << 4)
-#define NTF_OFFLOADED   0x20
+#define NTF_OFFLOADED   (1 << 5)
-#define NTF_STICKY	0x40
+#define NTF_STICKY	(1 << 6)
-#define NTF_ROUTER	0x80
+#define NTF_ROUTER	(1 << 7)
+/* Extended flags under NDA_FLAGS_EXT: */
+#define NTF_EXT_MANAGED	(1 << 0)
 
 /*
  *	Neighbor Cache Entry States.
@@ -63,9 +68,22 @@ enum {
 #define NUD_PERMANENT	0x80
 #define NUD_NONE	0x00
 
-/* NUD_NOARP & NUD_PERMANENT are pseudostates, they never change
+/* NUD_NOARP & NUD_PERMANENT are pseudostates, they never change and make no
-   and make no address resolution or NUD.
+ * address resolution or NUD.
-   NUD_PERMANENT also cannot be deleted by garbage collectors.
+ *
+ * NUD_PERMANENT also cannot be deleted by garbage collectors. This holds true
+ * for dynamic entries with NTF_EXT_LEARNED flag as well. However, upon carrier
+ * down event, NUD_PERMANENT entries are not flushed whereas NTF_EXT_LEARNED
+ * flagged entries explicitly are (which is also consistent with the routing
+ * subsystem).
+ *
+ * When NTF_EXT_LEARNED is set for a bridge fdb entry the different cache entry
+ * states don't make sense and thus are ignored. Such entries don't age and
+ * can roam.
+ *
+ * NTF_EXT_MANAGED flagged neigbor entries are managed by the kernel on behalf
+ * of a user space control plane, and automatically refreshed so that (if
+ * possible) they remain in NUD_REACHABLE state.
  */
 
 struct nda_cacheinfo {
@@ -171,4 +189,27 @@ enum {
 };
 #define NDTA_MAX (__NDTA_MAX - 1)
 
+ /* FDB activity notification bits used in NFEA_ACTIVITY_NOTIFY:
+  * - FDB_NOTIFY_BIT - notify on activity/expire for any entry
+  * - FDB_NOTIFY_INACTIVE_BIT - mark as inactive to avoid multiple notifications
+  */
+enum {
+	FDB_NOTIFY_BIT		= (1 << 0),
+	FDB_NOTIFY_INACTIVE_BIT	= (1 << 1)
+};
+
+/* embedded into NDA_FDB_EXT_ATTRS:
+ * [NDA_FDB_EXT_ATTRS] = {
+ *     [NFEA_ACTIVITY_NOTIFY]
+ *     ...
+ * }
+ */
+enum {
+	NFEA_UNSPEC,
+	NFEA_ACTIVITY_NOTIFY,
+	NFEA_DONT_REFRESH,
+	__NFEA_MAX
+};
+#define NFEA_MAX (__NFEA_MAX - 1)
+
 #endif

include/uapi/linux/netfilter.h

@@ -43,11 +43,13 @@ enum nf_inet_hooks {
 	NF_INET_FORWARD,
 	NF_INET_LOCAL_OUT,
 	NF_INET_POST_ROUTING,
-	NF_INET_NUMHOOKS
+	NF_INET_NUMHOOKS,
+	NF_INET_INGRESS = NF_INET_NUMHOOKS,
 };
 
 enum nf_dev_hooks {
 	NF_NETDEV_INGRESS,
+	NF_NETDEV_EGRESS,
 	NF_NETDEV_NUMHOOKS
 };
 

include/uapi/linux/netfilter/ipset/ip_set.h

@@ -92,11 +92,11 @@ enum {
 	/* Reserve empty slots */
 	IPSET_ATTR_CADT_MAX = 16,
 	/* Create-only specific attributes */
-	IPSET_ATTR_GC,
+	IPSET_ATTR_INITVAL,	/* was unused IPSET_ATTR_GC */
 	IPSET_ATTR_HASHSIZE,
 	IPSET_ATTR_MAXELEM,
 	IPSET_ATTR_NETMASK,
-	IPSET_ATTR_PROBES,
+	IPSET_ATTR_BUCKETSIZE,	/* was unused IPSET_ATTR_PROBES */
 	IPSET_ATTR_RESIZE,
 	IPSET_ATTR_SIZE,
 	/* Kernel-only */
@@ -214,6 +214,8 @@ enum ipset_cadt_flags {
 enum ipset_create_flags {
 	IPSET_CREATE_FLAG_BIT_FORCEADD = 0,
 	IPSET_CREATE_FLAG_FORCEADD = (1 << IPSET_CREATE_FLAG_BIT_FORCEADD),
+	IPSET_CREATE_FLAG_BIT_BUCKETSIZE = 1,
+	IPSET_CREATE_FLAG_BUCKETSIZE = (1 << IPSET_CREATE_FLAG_BIT_BUCKETSIZE),
 	IPSET_CREATE_FLAG_BIT_MAX = 7,
 };
 

include/uapi/linux/netfilter/x_tables.h

@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef _X_TABLES_H
 #define _X_TABLES_H
-#include <linux/kernel.h>
+#include <linux/const.h>
 #include <linux/types.h>
 
 #define XT_FUNCTION_MAXNAMELEN 30

include/uapi/linux/netlink.h

@@ -2,7 +2,7 @@
 #ifndef __LINUX_NETLINK_H
 #define __LINUX_NETLINK_H
 
-#include <linux/kernel.h>
+#include <linux/const.h>
 #include <linux/socket.h> /* for __kernel_sa_family_t */
 #include <linux/types.h>
 
@@ -91,9 +91,10 @@ struct nlmsghdr {
 #define NLMSG_HDRLEN	 ((int) NLMSG_ALIGN(sizeof(struct nlmsghdr)))
 #define NLMSG_LENGTH(len) ((len) + NLMSG_HDRLEN)
 #define NLMSG_SPACE(len) NLMSG_ALIGN(NLMSG_LENGTH(len))
-#define NLMSG_DATA(nlh)  ((void*)(((char*)nlh) + NLMSG_LENGTH(0)))
+#define NLMSG_DATA(nlh)  ((void *)(((char *)nlh) + NLMSG_HDRLEN))
 #define NLMSG_NEXT(nlh,len)	 ((len) -= NLMSG_ALIGN((nlh)->nlmsg_len), \
-				  (struct nlmsghdr*)(((char*)(nlh)) + NLMSG_ALIGN((nlh)->nlmsg_len)))
+				  (struct nlmsghdr *)(((char *)(nlh)) + \
+				  NLMSG_ALIGN((nlh)->nlmsg_len)))
 #define NLMSG_OK(nlh,len) ((len) >= (int)sizeof(struct nlmsghdr) && \
 			   (nlh)->nlmsg_len >= sizeof(struct nlmsghdr) && \
 			   (nlh)->nlmsg_len <= (len))
@@ -129,6 +130,7 @@ struct nlmsgerr {
  * @NLMSGERR_ATTR_COOKIE: arbitrary subsystem specific cookie to
  *	be used - in the success case - to identify a created
  *	object or operation or similar (binary)
+ * @NLMSGERR_ATTR_POLICY: policy for a rejected attribute
  * @__NLMSGERR_ATTR_MAX: number of attributes
  * @NLMSGERR_ATTR_MAX: highest attribute number
  */
@@ -137,6 +139,7 @@ enum nlmsgerr_attrs {
 	NLMSGERR_ATTR_MSG,
 	NLMSGERR_ATTR_OFFS,
 	NLMSGERR_ATTR_COOKIE,
+	NLMSGERR_ATTR_POLICY,
 
 	__NLMSGERR_ATTR_MAX,
 	NLMSGERR_ATTR_MAX = __NLMSGERR_ATTR_MAX - 1
@@ -245,4 +248,109 @@ struct nla_bitfield32 {
 	__u32 selector;
 };
 
+/*
+ * policy descriptions - it's specific to each family how this is used
+ * Normally, it should be retrieved via a dump inside another attribute
+ * specifying where it applies.
+ */
+
+/**
+ * enum netlink_attribute_type - type of an attribute
+ * @NL_ATTR_TYPE_INVALID: unused
+ * @NL_ATTR_TYPE_FLAG: flag attribute (present/not present)
+ * @NL_ATTR_TYPE_U8: 8-bit unsigned attribute
+ * @NL_ATTR_TYPE_U16: 16-bit unsigned attribute
+ * @NL_ATTR_TYPE_U32: 32-bit unsigned attribute
+ * @NL_ATTR_TYPE_U64: 64-bit unsigned attribute
+ * @NL_ATTR_TYPE_S8: 8-bit signed attribute
+ * @NL_ATTR_TYPE_S16: 16-bit signed attribute
+ * @NL_ATTR_TYPE_S32: 32-bit signed attribute
+ * @NL_ATTR_TYPE_S64: 64-bit signed attribute
+ * @NL_ATTR_TYPE_BINARY: binary data, min/max length may be specified
+ * @NL_ATTR_TYPE_STRING: string, min/max length may be specified
+ * @NL_ATTR_TYPE_NUL_STRING: NUL-terminated string,
+ *	min/max length may be specified
+ * @NL_ATTR_TYPE_NESTED: nested, i.e. the content of this attribute
+ *	consists of sub-attributes. The nested policy and maxtype
+ *	inside may be specified.
+ * @NL_ATTR_TYPE_NESTED_ARRAY: nested array, i.e. the content of this
+ *	attribute contains sub-attributes whose type is irrelevant
+ *	(just used to separate the array entries) and each such array
+ *	entry has attributes again, the policy for those inner ones
+ *	and the corresponding maxtype may be specified.
+ * @NL_ATTR_TYPE_BITFIELD32: &struct nla_bitfield32 attribute
+ */
+enum netlink_attribute_type {
+	NL_ATTR_TYPE_INVALID,
+
+	NL_ATTR_TYPE_FLAG,
+
+	NL_ATTR_TYPE_U8,
+	NL_ATTR_TYPE_U16,
+	NL_ATTR_TYPE_U32,
+	NL_ATTR_TYPE_U64,
+
+	NL_ATTR_TYPE_S8,
+	NL_ATTR_TYPE_S16,
+	NL_ATTR_TYPE_S32,
+	NL_ATTR_TYPE_S64,
+
+	NL_ATTR_TYPE_BINARY,
+	NL_ATTR_TYPE_STRING,
+	NL_ATTR_TYPE_NUL_STRING,
+
+	NL_ATTR_TYPE_NESTED,
+	NL_ATTR_TYPE_NESTED_ARRAY,
+
+	NL_ATTR_TYPE_BITFIELD32,
+};
+
+/**
+ * enum netlink_policy_type_attr - policy type attributes
+ * @NL_POLICY_TYPE_ATTR_UNSPEC: unused
+ * @NL_POLICY_TYPE_ATTR_TYPE: type of the attribute,
+ *	&enum netlink_attribute_type (U32)
+ * @NL_POLICY_TYPE_ATTR_MIN_VALUE_S: minimum value for signed
+ *	integers (S64)
+ * @NL_POLICY_TYPE_ATTR_MAX_VALUE_S: maximum value for signed
+ *	integers (S64)
+ * @NL_POLICY_TYPE_ATTR_MIN_VALUE_U: minimum value for unsigned
+ *	integers (U64)
+ * @NL_POLICY_TYPE_ATTR_MAX_VALUE_U: maximum value for unsigned
+ *	integers (U64)
+ * @NL_POLICY_TYPE_ATTR_MIN_LENGTH: minimum length for binary
+ *	attributes, no minimum if not given (U32)
+ * @NL_POLICY_TYPE_ATTR_MAX_LENGTH: maximum length for binary
+ *	attributes, no maximum if not given (U32)
+ * @NL_POLICY_TYPE_ATTR_POLICY_IDX: sub policy for nested and
+ *	nested array types (U32)
+ * @NL_POLICY_TYPE_ATTR_POLICY_MAXTYPE: maximum sub policy
+ *	attribute for nested and nested array types, this can
+ *	in theory be < the size of the policy pointed to by
+ *	the index, if limited inside the nesting (U32)
+ * @NL_POLICY_TYPE_ATTR_BITFIELD32_MASK: valid mask for the
+ *	bitfield32 type (U32)
+ * @NL_POLICY_TYPE_ATTR_MASK: mask of valid bits for unsigned integers (U64)
+ * @NL_POLICY_TYPE_ATTR_PAD: pad attribute for 64-bit alignment
+ */
+enum netlink_policy_type_attr {
+	NL_POLICY_TYPE_ATTR_UNSPEC,
+	NL_POLICY_TYPE_ATTR_TYPE,
+	NL_POLICY_TYPE_ATTR_MIN_VALUE_S,
+	NL_POLICY_TYPE_ATTR_MAX_VALUE_S,
+	NL_POLICY_TYPE_ATTR_MIN_VALUE_U,
+	NL_POLICY_TYPE_ATTR_MAX_VALUE_U,
+	NL_POLICY_TYPE_ATTR_MIN_LENGTH,
+	NL_POLICY_TYPE_ATTR_MAX_LENGTH,
+	NL_POLICY_TYPE_ATTR_POLICY_IDX,
+	NL_POLICY_TYPE_ATTR_POLICY_MAXTYPE,
+	NL_POLICY_TYPE_ATTR_BITFIELD32_MASK,
+	NL_POLICY_TYPE_ATTR_PAD,
+	NL_POLICY_TYPE_ATTR_MASK,
+
+	/* keep last */
+	__NL_POLICY_TYPE_ATTR_MAX,
+	NL_POLICY_TYPE_ATTR_MAX = __NL_POLICY_TYPE_ATTR_MAX - 1
+};
+
 #endif /* __LINUX_NETLINK_H */

include/uapi/linux/nexthop.h

@@ -21,7 +21,10 @@ struct nexthop_grp {
 };
 
 enum {
-	NEXTHOP_GRP_TYPE_MPATH,  /* default type if not specified */
+	NEXTHOP_GRP_TYPE_MPATH,  /* hash-threshold nexthop group
+				  * default type if not specified
+				  */
+	NEXTHOP_GRP_TYPE_RES,    /* resilient nexthop group */
 	__NEXTHOP_GRP_TYPE_MAX,
 };
 
@@ -49,8 +52,53 @@ enum {
 	NHA_GROUPS,	/* flag; only return nexthop groups in dump */
 	NHA_MASTER,	/* u32;  only return nexthops with given master dev */
 
+	NHA_FDB,	/* flag; nexthop belongs to a bridge fdb */
+	/* if NHA_FDB is added, OIF, BLACKHOLE, ENCAP cannot be set */
+
+	/* nested; resilient nexthop group attributes */
+	NHA_RES_GROUP,
+	/* nested; nexthop bucket attributes */
+	NHA_RES_BUCKET,
+
 	__NHA_MAX,
 };
 
 #define NHA_MAX	(__NHA_MAX - 1)
+
+enum {
+	NHA_RES_GROUP_UNSPEC,
+	/* Pad attribute for 64-bit alignment. */
+	NHA_RES_GROUP_PAD = NHA_RES_GROUP_UNSPEC,
+
+	/* u16; number of nexthop buckets in a resilient nexthop group */
+	NHA_RES_GROUP_BUCKETS,
+	/* clock_t as u32; nexthop bucket idle timer (per-group) */
+	NHA_RES_GROUP_IDLE_TIMER,
+	/* clock_t as u32; nexthop unbalanced timer */
+	NHA_RES_GROUP_UNBALANCED_TIMER,
+	/* clock_t as u64; nexthop unbalanced time */
+	NHA_RES_GROUP_UNBALANCED_TIME,
+
+	__NHA_RES_GROUP_MAX,
+};
+
+#define NHA_RES_GROUP_MAX	(__NHA_RES_GROUP_MAX - 1)
+
+enum {
+	NHA_RES_BUCKET_UNSPEC,
+	/* Pad attribute for 64-bit alignment. */
+	NHA_RES_BUCKET_PAD = NHA_RES_BUCKET_UNSPEC,
+
+	/* u16; nexthop bucket index */
+	NHA_RES_BUCKET_INDEX,
+	/* clock_t as u64; nexthop bucket idle time */
+	NHA_RES_BUCKET_IDLE_TIME,
+	/* u32; nexthop id assigned to the nexthop bucket */
+	NHA_RES_BUCKET_NH_ID,
+
+	__NHA_RES_BUCKET_MAX,
+};
+
+#define NHA_RES_BUCKET_MAX	(__NHA_RES_BUCKET_MAX - 1)
+
 #endif

include/uapi/linux/pkt_cls.h

@@ -22,6 +22,7 @@ enum {
 	__TCA_ACT_MAX
 };
 
+/* See other TCA_ACT_FLAGS_ * flags in include/net/act_api.h. */
 #define TCA_ACT_FLAGS_NO_PERCPU_STATS 1 /* Don't use percpu allocator for
 					 * actions stats.
 					 */
@@ -134,6 +135,7 @@ enum tca_id {
 	TCA_ID_CTINFO,
 	TCA_ID_MPLS,
 	TCA_ID_CT,
+	TCA_ID_GATE,
 	/* other actions go here */
 	__TCA_ID_MAX = 255
 };
@@ -189,6 +191,8 @@ enum {
 	TCA_POLICE_PAD,
 	TCA_POLICE_RATE64,
 	TCA_POLICE_PEAKRATE64,
+	TCA_POLICE_PKTRATE64,
+	TCA_POLICE_PKTBURST64,
 	__TCA_POLICE_MAX
 #define TCA_POLICE_RESULT TCA_POLICE_RESULT
 };
@@ -575,6 +579,11 @@ enum {
 	TCA_FLOWER_KEY_CT_LABELS,	/* u128 */
 	TCA_FLOWER_KEY_CT_LABELS_MASK,	/* u128 */
 
+	TCA_FLOWER_KEY_MPLS_OPTS,
+
+	TCA_FLOWER_KEY_HASH,		/* u32 */
+	TCA_FLOWER_KEY_HASH_MASK,	/* u32 */
+
 	__TCA_FLOWER_MAX,
 };
 
@@ -585,6 +594,9 @@ enum {
 	TCA_FLOWER_KEY_CT_FLAGS_ESTABLISHED = 1 << 1, /* Part of an existing connection. */
 	TCA_FLOWER_KEY_CT_FLAGS_RELATED = 1 << 2, /* Related to an established connection. */
 	TCA_FLOWER_KEY_CT_FLAGS_TRACKED = 1 << 3, /* Conntrack has occurred. */
+	TCA_FLOWER_KEY_CT_FLAGS_INVALID = 1 << 4, /* Conntrack is invalid. */
+	TCA_FLOWER_KEY_CT_FLAGS_REPLY = 1 << 5, /* Packet is in the reply direction. */
+	__TCA_FLOWER_KEY_CT_FLAGS_MAX,
 };
 
 enum {
@@ -639,6 +651,27 @@ enum {
 #define TCA_FLOWER_KEY_ENC_OPT_ERSPAN_MAX \
 		(__TCA_FLOWER_KEY_ENC_OPT_ERSPAN_MAX - 1)
 
+enum {
+	TCA_FLOWER_KEY_MPLS_OPTS_UNSPEC,
+	TCA_FLOWER_KEY_MPLS_OPTS_LSE,
+	__TCA_FLOWER_KEY_MPLS_OPTS_MAX,
+};
+
+#define TCA_FLOWER_KEY_MPLS_OPTS_MAX (__TCA_FLOWER_KEY_MPLS_OPTS_MAX - 1)
+
+enum {
+	TCA_FLOWER_KEY_MPLS_OPT_LSE_UNSPEC,
+	TCA_FLOWER_KEY_MPLS_OPT_LSE_DEPTH,
+	TCA_FLOWER_KEY_MPLS_OPT_LSE_TTL,
+	TCA_FLOWER_KEY_MPLS_OPT_LSE_BOS,
+	TCA_FLOWER_KEY_MPLS_OPT_LSE_TC,
+	TCA_FLOWER_KEY_MPLS_OPT_LSE_LABEL,
+	__TCA_FLOWER_KEY_MPLS_OPT_LSE_MAX,
+};
+
+#define TCA_FLOWER_KEY_MPLS_OPT_LSE_MAX \
+		(__TCA_FLOWER_KEY_MPLS_OPT_LSE_MAX - 1)
+
 enum {
 	TCA_FLOWER_KEY_FLAGS_IS_FRAGMENT = (1 << 0),
 	TCA_FLOWER_KEY_FLAGS_FRAG_IS_FIRST = (1 << 1),

include/uapi/linux/pkt_sched.h

@@ -257,6 +257,8 @@ enum {
 	TCA_RED_STAB,
 	TCA_RED_MAX_P,
 	TCA_RED_FLAGS,		/* bitfield32 */
+	TCA_RED_EARLY_DROP_BLOCK, /* u32 */
+	TCA_RED_MARK_BLOCK,	/* u32 */
 	__TCA_RED_MAX,
 };
 
@@ -432,6 +434,7 @@ enum {
 	TCA_HTB_RATE64,
 	TCA_HTB_CEIL64,
 	TCA_HTB_PAD,
+	TCA_HTB_OFFLOAD,
 	__TCA_HTB_MAX,
 };
 
@@ -824,6 +827,8 @@ struct tc_codel_xstats {
 
 /* FQ_CODEL */
 
+#define FQ_CODEL_QUANTUM_MAX (1 << 20)
+
 enum {
 	TCA_FQ_CODEL_UNSPEC,
 	TCA_FQ_CODEL_TARGET,
@@ -835,6 +840,8 @@ enum {
 	TCA_FQ_CODEL_CE_THRESHOLD,
 	TCA_FQ_CODEL_DROP_BATCH_SIZE,
 	TCA_FQ_CODEL_MEMORY_LIMIT,
+	TCA_FQ_CODEL_CE_THRESHOLD_SELECTOR,
+	TCA_FQ_CODEL_CE_THRESHOLD_MASK,
 	__TCA_FQ_CODEL_MAX
 };
 
@@ -913,6 +920,10 @@ enum {
 
 	TCA_FQ_TIMER_SLACK,	/* timer slack */
 
+	TCA_FQ_HORIZON,		/* time horizon in us */
+
+	TCA_FQ_HORIZON_DROP,	/* drop packets beyond horizon, or cap their EDT */
+
 	__TCA_FQ_MAX
 };
 
@@ -932,6 +943,8 @@ struct tc_fq_qd_stats {
 	__u32	throttled_flows;
 	__u32	unthrottle_latency_ns;
 	__u64	ce_mark;		/* packets above ce_threshold */
+	__u64	horizon_drops;
+	__u64	horizon_caps;
 };
 
 /* Heavy-Hitter Filter */

include/uapi/linux/rpl.h

@@ -0,0 +1,48 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ *  IPv6 RPL-SR implementation
+ *
+ *  Author:
+ *  (C) 2020 Alexander Aring <alex.aring@gmail.com>
+ */
+
+#ifndef _LINUX_RPL_H
+#define _LINUX_RPL_H
+
+#include <asm/byteorder.h>
+#include <linux/types.h>
+#include <linux/in6.h>
+
+/*
+ * RPL SR Header
+ */
+struct ipv6_rpl_sr_hdr {
+	__u8	nexthdr;
+	__u8	hdrlen;
+	__u8	type;
+	__u8	segments_left;
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+	__u32	cmpre:4,
+		cmpri:4,
+		reserved:4,
+		pad:4,
+		reserved1:16;
+#elif defined(__BIG_ENDIAN_BITFIELD)
+	__u32	cmpri:4,
+		cmpre:4,
+		pad:4,
+		reserved:20;
+#else
+#error  "Please fix <asm/byteorder.h>"
+#endif
+
+	union {
+		struct in6_addr addr[0];
+		__u8 data[0];
+	} segments;
+} __attribute__((packed));
+
+#define rpl_segaddr	segments.addr
+#define rpl_segdata	segments.data
+
+#endif

include/uapi/linux/rpl_iptunnel.h

@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ *  IPv6 RPL-SR implementation
+ *
+ *  Author:
+ *  (C) 2020 Alexander Aring <alex.aring@gmail.com>
+ */
+
+#ifndef _LINUX_RPL_IPTUNNEL_H
+#define _LINUX_RPL_IPTUNNEL_H
+
+enum {
+	RPL_IPTUNNEL_UNSPEC,
+	RPL_IPTUNNEL_SRH,
+	__RPL_IPTUNNEL_MAX,
+};
+#define RPL_IPTUNNEL_MAX (__RPL_IPTUNNEL_MAX - 1)
+
+#define RPL_IPTUNNEL_SRH_SIZE(srh) (((srh)->hdrlen + 1) << 3)
+
+#endif

include/uapi/linux/rtnetlink.h

@@ -178,6 +178,13 @@ enum {
 	RTM_GETVLAN,
 #define RTM_GETVLAN	RTM_GETVLAN
 
+	RTM_NEWNEXTHOPBUCKET = 116,
+#define RTM_NEWNEXTHOPBUCKET	RTM_NEWNEXTHOPBUCKET
+	RTM_DELNEXTHOPBUCKET,
+#define RTM_DELNEXTHOPBUCKET	RTM_DELNEXTHOPBUCKET
+	RTM_GETNEXTHOPBUCKET,
+#define RTM_GETNEXTHOPBUCKET	RTM_GETNEXTHOPBUCKET
+
 	__RTM_MAX,
 #define RTM_MAX		(((__RTM_MAX + 3) & ~3) - 1)
 };
@@ -257,12 +264,12 @@ enum {
 
 /* rtm_protocol */
 
-#define RTPROT_UNSPEC	0
+#define RTPROT_UNSPEC		0
-#define RTPROT_REDIRECT	1	/* Route installed by ICMP redirects;
+#define RTPROT_REDIRECT		1	/* Route installed by ICMP redirects;
-				   not used by current IPv4 */
+					   not used by current IPv4 */
-#define RTPROT_KERNEL	2	/* Route installed by kernel		*/
+#define RTPROT_KERNEL		2	/* Route installed by kernel		*/
-#define RTPROT_BOOT	3	/* Route installed during boot		*/
+#define RTPROT_BOOT		3	/* Route installed during boot		*/
-#define RTPROT_STATIC	4	/* Route installed by administrator	*/
+#define RTPROT_STATIC		4	/* Route installed by administrator	*/
 
 /* Values of protocol >= RTPROT_STATIC are not interpreted by kernel;
    they are just passed from user and back as is.
@@ -271,22 +278,24 @@ enum {
    avoid conflicts.
  */
 
-#define RTPROT_GATED	8	/* Apparently, GateD */
+#define RTPROT_GATED		8	/* Apparently, GateD */
-#define RTPROT_RA	9	/* RDISC/ND router advertisements */
+#define RTPROT_RA		9	/* RDISC/ND router advertisements */
-#define RTPROT_MRT	10	/* Merit MRT */
+#define RTPROT_MRT		10	/* Merit MRT */
-#define RTPROT_ZEBRA	11	/* Zebra */
+#define RTPROT_ZEBRA		11	/* Zebra */
-#define RTPROT_BIRD	12	/* BIRD */
+#define RTPROT_BIRD		12	/* BIRD */
-#define RTPROT_DNROUTED	13	/* DECnet routing daemon */
+#define RTPROT_DNROUTED		13	/* DECnet routing daemon */
-#define RTPROT_XORP	14	/* XORP */
+#define RTPROT_XORP		14	/* XORP */
-#define RTPROT_NTK	15	/* Netsukuku */
+#define RTPROT_NTK		15	/* Netsukuku */
-#define RTPROT_DHCP	16      /* DHCP client */
+#define RTPROT_DHCP		16	/* DHCP client */
-#define RTPROT_MROUTED	17      /* Multicast daemon */
+#define RTPROT_MROUTED		17	/* Multicast daemon */
-#define RTPROT_BABEL	42      /* Babel daemon */
+#define RTPROT_KEEPALIVED	18	/* Keepalived daemon */
-#define RTPROT_BGP	186     /* BGP Routes */
+#define RTPROT_BABEL		42	/* Babel daemon */
-#define RTPROT_ISIS	187     /* ISIS Routes */
+#define RTPROT_OPENR		99	/* Open Routing (Open/R) Routes */
-#define RTPROT_OSPF	188     /* OSPF Routes */
+#define RTPROT_BGP		186	/* BGP Routes */
-#define RTPROT_RIP	189     /* RIP Routes */
+#define RTPROT_ISIS		187	/* ISIS Routes */
-#define RTPROT_EIGRP	192     /* EIGRP Routes */
+#define RTPROT_OSPF		188	/* OSPF Routes */
+#define RTPROT_RIP		189	/* RIP Routes */
+#define RTPROT_EIGRP		192	/* EIGRP Routes */
 
 /* rtm_scope
 
@@ -318,6 +327,11 @@ enum rt_scope_t {
 #define RTM_F_FIB_MATCH	        0x2000	/* return full fib lookup match */
 #define RTM_F_OFFLOAD		0x4000	/* route is offloaded */
 #define RTM_F_TRAP		0x8000	/* route is trapping packets */
+#define RTM_F_OFFLOAD_FAILED	0x20000000 /* route offload failed, this value
+					    * is chosen to avoid conflicts with
+					    * other flags defined in
+					    * include/uapi/linux/ipv6_route.h
+					    */
 
 /* Reserved table identifiers */
 
@@ -395,11 +409,13 @@ struct rtnexthop {
 #define RTNH_F_DEAD		1	/* Nexthop is dead (used by multipath)	*/
 #define RTNH_F_PERVASIVE	2	/* Do recursive gateway lookup	*/
 #define RTNH_F_ONLINK		4	/* Gateway is forced on link	*/
-#define RTNH_F_OFFLOAD		8	/* offloaded route */
+#define RTNH_F_OFFLOAD		8	/* Nexthop is offloaded */
 #define RTNH_F_LINKDOWN		16	/* carrier-down on nexthop */
 #define RTNH_F_UNRESOLVED	32	/* The entry is unresolved (ipmr) */
+#define RTNH_F_TRAP		64	/* Nexthop is trapping packets */
 
-#define RTNH_COMPARE_MASK	(RTNH_F_DEAD | RTNH_F_LINKDOWN | RTNH_F_OFFLOAD)
+#define RTNH_COMPARE_MASK	(RTNH_F_DEAD | RTNH_F_LINKDOWN | \
+				 RTNH_F_OFFLOAD | RTNH_F_TRAP)
 
 /* Macros to handle hexthops */
 
@@ -609,11 +625,17 @@ enum {
 	TCA_HW_OFFLOAD,
 	TCA_INGRESS_BLOCK,
 	TCA_EGRESS_BLOCK,
+	TCA_DUMP_FLAGS,
 	__TCA_MAX
 };
 
 #define TCA_MAX (__TCA_MAX - 1)
 
+#define TCA_DUMP_FLAGS_TERSE (1 << 0) /* Means that in dump user gets only basic
+				       * data necessary to identify the objects
+				       * (handle, cookie, etc.) and stats.
+				       */
+
 #define TCA_RTA(r)  ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct tcmsg))))
 #define TCA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct tcmsg))
 
@@ -757,18 +779,27 @@ enum {
 #define TA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct tcamsg))
 /* tcamsg flags stored in attribute TCA_ROOT_FLAGS
  *
- * TCA_FLAG_LARGE_DUMP_ON user->kernel to request for larger than TCA_ACT_MAX_PRIO
+ * TCA_ACT_FLAG_LARGE_DUMP_ON user->kernel to request for larger than
- * actions in a dump. All dump responses will contain the number of actions
+ * TCA_ACT_MAX_PRIO actions in a dump. All dump responses will contain the
- * being dumped stored in for user app's consumption in TCA_ROOT_COUNT
+ * number of actions being dumped stored in for user app's consumption in
+ * TCA_ROOT_COUNT
+ *
+ * TCA_ACT_FLAG_TERSE_DUMP user->kernel to request terse (brief) dump that only
+ * includes essential action info (kind, index, etc.)
  *
  */
 #define TCA_FLAG_LARGE_DUMP_ON		(1 << 0)
+#define TCA_ACT_FLAG_LARGE_DUMP_ON	TCA_FLAG_LARGE_DUMP_ON
+#define TCA_ACT_FLAG_TERSE_DUMP		(1 << 1)
 
 /* New extended info filters for IFLA_EXT_MASK */
 #define RTEXT_FILTER_VF		(1 << 0)
 #define RTEXT_FILTER_BRVLAN	(1 << 1)
 #define RTEXT_FILTER_BRVLAN_COMPRESSED	(1 << 2)
 #define	RTEXT_FILTER_SKIP_STATS	(1 << 3)
+#define RTEXT_FILTER_MRP	(1 << 4)
+#define RTEXT_FILTER_CFM_CONFIG	(1 << 5)
+#define RTEXT_FILTER_CFM_STATUS	(1 << 6)
 
 /* End of information exported to user level */
 

include/uapi/linux/sctp.h

@@ -140,6 +140,8 @@ typedef __s32 sctp_assoc_t;
 #define SCTP_ECN_SUPPORTED	130
 #define SCTP_EXPOSE_POTENTIALLY_FAILED_STATE	131
 #define SCTP_EXPOSE_PF_STATE	SCTP_EXPOSE_POTENTIALLY_FAILED_STATE
+#define SCTP_REMOTE_UDP_ENCAPS_PORT	132
+#define SCTP_PLPMTUD_PROBE_INTERVAL	133
 
 /* PR-SCTP policies */
 #define SCTP_PR_SCTP_NONE	0x0000
@@ -1191,6 +1193,12 @@ struct sctp_event {
 	uint8_t se_on;
 };
 
+struct sctp_udpencaps {
+	sctp_assoc_t sue_assoc_id;
+	struct sockaddr_storage sue_address;
+	uint16_t sue_port;
+};
+
 /* SCTP Stream schedulers */
 enum sctp_sched_type {
 	SCTP_SS_FCFS,
@@ -1200,4 +1208,11 @@ enum sctp_sched_type {
 	SCTP_SS_MAX = SCTP_SS_RR
 };
 
+/* Probe Interval socket option */
+struct sctp_probeinterval {
+	sctp_assoc_t spi_assoc_id;
+	struct sockaddr_storage spi_address;
+	__u32 spi_interval;
+};
+
 #endif /* _SCTP_H */

include/uapi/linux/seg6_iptunnel.h

@@ -37,5 +37,4 @@ enum {
 	SEG6_IPTUN_MODE_L2ENCAP,
 };
 
-
 #endif

include/uapi/linux/seg6_local.h

@@ -26,6 +26,8 @@ enum {
 	SEG6_LOCAL_IIF,
 	SEG6_LOCAL_OIF,
 	SEG6_LOCAL_BPF,
+	SEG6_LOCAL_VRFTABLE,
+	SEG6_LOCAL_COUNTERS,
 	__SEG6_LOCAL_MAX,
 };
 #define SEG6_LOCAL_MAX (__SEG6_LOCAL_MAX - 1)
@@ -62,6 +64,8 @@ enum {
 	SEG6_LOCAL_ACTION_END_AM	= 14,
 	/* custom BPF action */
 	SEG6_LOCAL_ACTION_END_BPF	= 15,
+	/* decap and lookup of DA in v4 or v6 table */
+	SEG6_LOCAL_ACTION_END_DT46	= 16,
 
 	__SEG6_LOCAL_ACTION_MAX,
 };
@@ -77,4 +81,33 @@ enum {
 
 #define SEG6_LOCAL_BPF_PROG_MAX (__SEG6_LOCAL_BPF_PROG_MAX - 1)
 
+/* SRv6 Behavior counters are encoded as netlink attributes guaranteeing the
+ * correct alignment.
+ * Each counter is identified by a different attribute type (i.e.
+ * SEG6_LOCAL_CNT_PACKETS).
+ *
+ * - SEG6_LOCAL_CNT_PACKETS: identifies a counter that counts the number of
+ *   packets that have been CORRECTLY processed by an SRv6 Behavior instance
+ *   (i.e., packets that generate errors or are dropped are NOT counted).
+ *
+ * - SEG6_LOCAL_CNT_BYTES: identifies a counter that counts the total amount
+ *   of traffic in bytes of all packets that have been CORRECTLY processed by
+ *   an SRv6 Behavior instance (i.e., packets that generate errors or are
+ *   dropped are NOT counted).
+ *
+ * - SEG6_LOCAL_CNT_ERRORS: identifies a counter that counts the number of
+ *   packets that have NOT been properly processed by an SRv6 Behavior instance
+ *   (i.e., packets that generate errors or are dropped).
+ */
+enum {
+	SEG6_LOCAL_CNT_UNSPEC,
+	SEG6_LOCAL_CNT_PAD,		/* pad for 64 bits values */
+	SEG6_LOCAL_CNT_PACKETS,
+	SEG6_LOCAL_CNT_BYTES,
+	SEG6_LOCAL_CNT_ERRORS,
+	__SEG6_LOCAL_CNT_MAX,
+};
+
+#define SEG6_LOCAL_CNT_MAX (__SEG6_LOCAL_CNT_MAX - 1)
+
 #endif

include/uapi/linux/snmp.h

@@ -159,6 +159,7 @@ enum
 	UDP_MIB_SNDBUFERRORS,			/* SndbufErrors */
 	UDP_MIB_CSUMERRORS,			/* InCsumErrors */
 	UDP_MIB_IGNOREDMULTI,			/* IgnoredMulti */
+	UDP_MIB_MEMERRORS,			/* MemErrors */
 	__UDP_MIB_MAX
 };
 
@@ -287,6 +288,10 @@ enum
 	LINUX_MIB_TCPFASTOPENPASSIVEALTKEY,	/* TCPFastOpenPassiveAltKey */
 	LINUX_MIB_TCPTIMEOUTREHASH,		/* TCPTimeoutRehash */
 	LINUX_MIB_TCPDUPLICATEDATAREHASH,	/* TCPDuplicateDataRehash */
+	LINUX_MIB_TCPDSACKRECVSEGS,		/* TCPDSACKRecvSegs */
+	LINUX_MIB_TCPDSACKIGNOREDDUBIOUS,	/* TCPDSACKIgnoredDubious */
+	LINUX_MIB_TCPMIGRATEREQSUCCESS,		/* TCPMigrateReqSuccess */
+	LINUX_MIB_TCPMIGRATEREQFAILURE,		/* TCPMigrateReqFailure */
 	__LINUX_MIB_MAX
 };
 

include/uapi/linux/socket.h

@@ -26,4 +26,9 @@ struct __kernel_sockaddr_storage {
 	};
 };
 
+#define SOCK_SNDBUF_LOCK	1
+#define SOCK_RCVBUF_LOCK	2
+
+#define SOCK_BUF_LOCK_MASK (SOCK_SNDBUF_LOCK | SOCK_RCVBUF_LOCK)
+
 #endif /* _LINUX_SOCKET_H */

include/uapi/linux/stddef.h

@@ -4,3 +4,40 @@
 #ifndef __always_inline
 #define __always_inline __inline__
 #endif
+
+/**
+ * __struct_group() - Create a mirrored named and anonyomous struct
+ *
+ * @TAG: The tag name for the named sub-struct (usually empty)
+ * @NAME: The identifier name of the mirrored sub-struct
+ * @ATTRS: Any struct attributes (usually empty)
+ * @MEMBERS: The member declarations for the mirrored structs
+ *
+ * Used to create an anonymous union of two structs with identical layout
+ * and size: one anonymous and one named. The former's members can be used
+ * normally without sub-struct naming, and the latter can be used to
+ * reason about the start, end, and size of the group of struct members.
+ * The named struct can also be explicitly tagged for layer reuse, as well
+ * as both having struct attributes appended.
+ */
+#define __struct_group(TAG, NAME, ATTRS, MEMBERS...) \
+	union { \
+		struct { MEMBERS } ATTRS; \
+		struct TAG { MEMBERS } ATTRS NAME; \
+	}
+
+/**
+ * __DECLARE_FLEX_ARRAY() - Declare a flexible array usable in a union
+ *
+ * @TYPE: The type of each flexible array element
+ * @NAME: The name of the flexible array member
+ *
+ * In order to have a flexible array member in a union or alone in a
+ * struct, it needs to be wrapped in an anonymous struct with at least 1
+ * named member, but that member can be empty.
+ */
+#define __DECLARE_FLEX_ARRAY(TYPE, NAME)	\
+	struct { \
+		struct { } __empty_ ## NAME; \
+		TYPE NAME[]; \
+	}

include/uapi/linux/tc_act/tc_gate.h

@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/* Copyright 2020 NXP */
+
+#ifndef __LINUX_TC_GATE_H
+#define __LINUX_TC_GATE_H
+
+#include <linux/pkt_cls.h>
+
+struct tc_gate {
+	tc_gen;
+};
+
+enum {
+	TCA_GATE_ENTRY_UNSPEC,
+	TCA_GATE_ENTRY_INDEX,
+	TCA_GATE_ENTRY_GATE,
+	TCA_GATE_ENTRY_INTERVAL,
+	TCA_GATE_ENTRY_IPV,
+	TCA_GATE_ENTRY_MAX_OCTETS,
+	__TCA_GATE_ENTRY_MAX,
+};
+#define TCA_GATE_ENTRY_MAX (__TCA_GATE_ENTRY_MAX - 1)
+
+enum {
+	TCA_GATE_ONE_ENTRY_UNSPEC,
+	TCA_GATE_ONE_ENTRY,
+	__TCA_GATE_ONE_ENTRY_MAX,
+};
+#define TCA_GATE_ONE_ENTRY_MAX (__TCA_GATE_ONE_ENTRY_MAX - 1)
+
+enum {
+	TCA_GATE_UNSPEC,
+	TCA_GATE_TM,
+	TCA_GATE_PARMS,
+	TCA_GATE_PAD,
+	TCA_GATE_PRIORITY,
+	TCA_GATE_ENTRY_LIST,
+	TCA_GATE_BASE_TIME,
+	TCA_GATE_CYCLE_TIME,
+	TCA_GATE_CYCLE_TIME_EXT,
+	TCA_GATE_FLAGS,
+	TCA_GATE_CLOCKID,
+	__TCA_GATE_MAX,
+};
+#define TCA_GATE_MAX (__TCA_GATE_MAX - 1)
+
+#endif

include/uapi/linux/tc_act/tc_mpls.h

@@ -10,6 +10,7 @@
 #define TCA_MPLS_ACT_PUSH	2
 #define TCA_MPLS_ACT_MODIFY	3
 #define TCA_MPLS_ACT_DEC_TTL	4
+#define TCA_MPLS_ACT_MAC_PUSH	5
 
 struct tc_mpls {
 	tc_gen;		/* generic TC action fields. */

include/uapi/linux/tc_act/tc_skbmod.h

@@ -17,6 +17,7 @@
 #define SKBMOD_F_SMAC	0x2
 #define SKBMOD_F_ETYPE	0x4
 #define SKBMOD_F_SWAPMAC 0x8
+#define SKBMOD_F_ECN	0x10
 
 struct tc_skbmod {
 	tc_gen;

include/uapi/linux/tc_act/tc_vlan.h

@@ -16,6 +16,8 @@
 #define TCA_VLAN_ACT_POP	1
 #define TCA_VLAN_ACT_PUSH	2
 #define TCA_VLAN_ACT_MODIFY	3
+#define TCA_VLAN_ACT_POP_ETH	4
+#define TCA_VLAN_ACT_PUSH_ETH	5
 
 struct tc_vlan {
 	tc_gen;
@@ -30,6 +32,8 @@ enum {
 	TCA_VLAN_PUSH_VLAN_PROTOCOL,
 	TCA_VLAN_PAD,
 	TCA_VLAN_PUSH_VLAN_PRIORITY,
+	TCA_VLAN_PUSH_ETH_DST,
+	TCA_VLAN_PUSH_ETH_SRC,
 	__TCA_VLAN_MAX,
 };
 #define TCA_VLAN_MAX (__TCA_VLAN_MAX - 1)